From fe052a1810ec4687ee7d606290561af504047707 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 29 Jun 2015 13:08:19 +0300 Subject: target: Use struct t10_pi_tuple Its not a good idea to keep target specific definition of the same t10-pi tuple. (Fix v4.2-rc1 patch fuzz - nab) Signed-off-by: Sagi Grimberg Signed-off-by: Nicholas Bellinger --- include/target/target_core_base.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 17ae2d6a4891..a6816444d81b 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -426,12 +427,6 @@ enum target_core_dif_check { TARGET_DIF_CHECK_REFTAG = 0x1 << 2, }; -struct se_dif_v1_tuple { - __be16 guard_tag; - __be16 app_tag; - __be32 ref_tag; -}; - /* for sam_task_attr */ #define TCM_SIMPLE_TAG 0x20 #define TCM_HEAD_TAG 0x21 -- cgit v1.2.3 From e986a35aba67558381d5cec59a14c4d0b20f0d47 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Thu, 18 Jun 2015 11:43:38 +0200 Subject: tcm_loop: Send I_T_NEXUS_LOSS_OCCURRED UA If the virtual SAS link is set to 'offline' we should be queueing an I_T_NEXUS_LOSS_OCCURRED UA. Signed-off-by: Hannes Reinecke Signed-off-by: Nicholas Bellinger --- drivers/target/loopback/tcm_loop.c | 5 +++++ drivers/target/target_core_tpg.c | 17 +++++++++++++++++ include/target/target_core_fabric.h | 1 + 3 files changed, 23 insertions(+) (limited to 'include') diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index b179d934cee1..5bc85ffed720 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -1034,6 +1034,11 @@ static ssize_t tcm_loop_tpg_store_transport_status( } if (!strncmp(page, "offline", 7)) { tl_tpg->tl_transport_status = TCM_TRANSPORT_OFFLINE; + if (tl_tpg->tl_nexus) { + struct se_session *tl_sess = tl_tpg->tl_nexus->se_sess; + + core_allocate_nexus_loss_ua(tl_sess->se_node_acl); + } return count; } return -EINVAL; diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index babde4ad841f..2d0381dd105c 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -41,6 +41,7 @@ #include "target_core_internal.h" #include "target_core_alua.h" #include "target_core_pr.h" +#include "target_core_ua.h" extern struct se_device *g_lun0_dev; @@ -83,6 +84,22 @@ struct se_node_acl *core_tpg_get_initiator_node_acl( } EXPORT_SYMBOL(core_tpg_get_initiator_node_acl); +void core_allocate_nexus_loss_ua( + struct se_node_acl *nacl) +{ + struct se_dev_entry *deve; + + if (!nacl) + return; + + rcu_read_lock(); + hlist_for_each_entry_rcu(deve, &nacl->lun_entry_hlist, link) + core_scsi3_ua_allocate(deve, 0x29, + ASCQ_29H_NEXUS_LOSS_OCCURRED); + rcu_read_unlock(); +} +EXPORT_SYMBOL(core_allocate_nexus_loss_ua); + /* core_tpg_add_node_to_devs(): * * diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 18afef91b447..69355feabd1d 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -152,6 +152,7 @@ int transport_generic_handle_tmr(struct se_cmd *); void transport_generic_request_failure(struct se_cmd *, sense_reason_t); void __target_execute_cmd(struct se_cmd *); int transport_lookup_tmr_lun(struct se_cmd *, u64); +void core_allocate_nexus_loss_ua(struct se_node_acl *acl); struct se_node_acl *core_tpg_get_initiator_node_acl(struct se_portal_group *tpg, unsigned char *); -- cgit v1.2.3 From 7708c1656552ddd60b9b9df3a9ee156acd1801ba Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 8 Jul 2015 17:58:52 +0300 Subject: scsi: Move sense handling routines to scsi_common Sense data handling is also done in the target stack. Hence, move sense handling routines to scsi_common so the target will be able to use them as well. Signed-off-by: Sagi Grimberg Reviewed-by: Bart Van Assche Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Signed-off-by: Nicholas Bellinger --- drivers/scsi/scsi_common.c | 98 +++++++++++++++++++++++++++++++++++++++++++++ drivers/scsi/scsi_error.c | 99 +--------------------------------------------- include/scsi/scsi_common.h | 5 +++ include/scsi/scsi_eh.h | 7 +--- 4 files changed, 105 insertions(+), 104 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_common.c b/drivers/scsi/scsi_common.c index 2ff092252b76..41432c10dda2 100644 --- a/drivers/scsi/scsi_common.c +++ b/drivers/scsi/scsi_common.c @@ -5,6 +5,7 @@ #include #include #include +#include #include /* NB: These are exposed through /proc/scsi/scsi and form part of the ABI. @@ -176,3 +177,100 @@ bool scsi_normalize_sense(const u8 *sense_buffer, int sb_len, return true; } EXPORT_SYMBOL(scsi_normalize_sense); + +/** + * scsi_sense_desc_find - search for a given descriptor type in descriptor sense data format. + * @sense_buffer: byte array of descriptor format sense data + * @sb_len: number of valid bytes in sense_buffer + * @desc_type: value of descriptor type to find + * (e.g. 0 -> information) + * + * Notes: + * only valid when sense data is in descriptor format + * + * Return value: + * pointer to start of (first) descriptor if found else NULL + */ +const u8 * scsi_sense_desc_find(const u8 * sense_buffer, int sb_len, + int desc_type) +{ + int add_sen_len, add_len, desc_len, k; + const u8 * descp; + + if ((sb_len < 8) || (0 == (add_sen_len = sense_buffer[7]))) + return NULL; + if ((sense_buffer[0] < 0x72) || (sense_buffer[0] > 0x73)) + return NULL; + add_sen_len = (add_sen_len < (sb_len - 8)) ? + add_sen_len : (sb_len - 8); + descp = &sense_buffer[8]; + for (desc_len = 0, k = 0; k < add_sen_len; k += desc_len) { + descp += desc_len; + add_len = (k < (add_sen_len - 1)) ? descp[1]: -1; + desc_len = add_len + 2; + if (descp[0] == desc_type) + return descp; + if (add_len < 0) // short descriptor ?? + break; + } + return NULL; +} +EXPORT_SYMBOL(scsi_sense_desc_find); + +/** + * scsi_build_sense_buffer - build sense data in a buffer + * @desc: Sense format (non zero == descriptor format, + * 0 == fixed format) + * @buf: Where to build sense data + * @key: Sense key + * @asc: Additional sense code + * @ascq: Additional sense code qualifier + * + **/ +void scsi_build_sense_buffer(int desc, u8 *buf, u8 key, u8 asc, u8 ascq) +{ + if (desc) { + buf[0] = 0x72; /* descriptor, current */ + buf[1] = key; + buf[2] = asc; + buf[3] = ascq; + buf[7] = 0; + } else { + buf[0] = 0x70; /* fixed, current */ + buf[2] = key; + buf[7] = 0xa; + buf[12] = asc; + buf[13] = ascq; + } +} +EXPORT_SYMBOL(scsi_build_sense_buffer); + +/** + * scsi_set_sense_information - set the information field in a + * formatted sense data buffer + * @buf: Where to build sense data + * @info: 64-bit information value to be set + * + **/ +void scsi_set_sense_information(u8 *buf, u64 info) +{ + if ((buf[0] & 0x7f) == 0x72) { + u8 *ucp, len; + + len = buf[7]; + ucp = (char *)scsi_sense_desc_find(buf, len + 8, 0); + if (!ucp) { + buf[7] = len + 0xa; + ucp = buf + 8 + len; + } + ucp[0] = 0; + ucp[1] = 0xa; + ucp[2] = 0x80; /* Valid bit */ + ucp[3] = 0; + put_unaligned_be64(info, &ucp[4]); + } else if ((buf[0] & 0x7f) == 0x70) { + buf[0] |= 0x80; + put_unaligned_be64(info, &buf[3]); + } +} +EXPORT_SYMBOL(scsi_set_sense_information); diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 106884a5444e..6e6b2d26d3ce 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include @@ -34,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -2407,45 +2407,6 @@ bool scsi_command_normalize_sense(const struct scsi_cmnd *cmd, } EXPORT_SYMBOL(scsi_command_normalize_sense); -/** - * scsi_sense_desc_find - search for a given descriptor type in descriptor sense data format. - * @sense_buffer: byte array of descriptor format sense data - * @sb_len: number of valid bytes in sense_buffer - * @desc_type: value of descriptor type to find - * (e.g. 0 -> information) - * - * Notes: - * only valid when sense data is in descriptor format - * - * Return value: - * pointer to start of (first) descriptor if found else NULL - */ -const u8 * scsi_sense_desc_find(const u8 * sense_buffer, int sb_len, - int desc_type) -{ - int add_sen_len, add_len, desc_len, k; - const u8 * descp; - - if ((sb_len < 8) || (0 == (add_sen_len = sense_buffer[7]))) - return NULL; - if ((sense_buffer[0] < 0x72) || (sense_buffer[0] > 0x73)) - return NULL; - add_sen_len = (add_sen_len < (sb_len - 8)) ? - add_sen_len : (sb_len - 8); - descp = &sense_buffer[8]; - for (desc_len = 0, k = 0; k < add_sen_len; k += desc_len) { - descp += desc_len; - add_len = (k < (add_sen_len - 1)) ? descp[1]: -1; - desc_len = add_len + 2; - if (descp[0] == desc_type) - return descp; - if (add_len < 0) // short descriptor ?? - break; - } - return NULL; -} -EXPORT_SYMBOL(scsi_sense_desc_find); - /** * scsi_get_sense_info_fld - get information field from sense data (either fixed or descriptor format) * @sense_buffer: byte array of sense data @@ -2495,61 +2456,3 @@ int scsi_get_sense_info_fld(const u8 * sense_buffer, int sb_len, } } EXPORT_SYMBOL(scsi_get_sense_info_fld); - -/** - * scsi_build_sense_buffer - build sense data in a buffer - * @desc: Sense format (non zero == descriptor format, - * 0 == fixed format) - * @buf: Where to build sense data - * @key: Sense key - * @asc: Additional sense code - * @ascq: Additional sense code qualifier - * - **/ -void scsi_build_sense_buffer(int desc, u8 *buf, u8 key, u8 asc, u8 ascq) -{ - if (desc) { - buf[0] = 0x72; /* descriptor, current */ - buf[1] = key; - buf[2] = asc; - buf[3] = ascq; - buf[7] = 0; - } else { - buf[0] = 0x70; /* fixed, current */ - buf[2] = key; - buf[7] = 0xa; - buf[12] = asc; - buf[13] = ascq; - } -} -EXPORT_SYMBOL(scsi_build_sense_buffer); - -/** - * scsi_set_sense_information - set the information field in a - * formatted sense data buffer - * @buf: Where to build sense data - * @info: 64-bit information value to be set - * - **/ -void scsi_set_sense_information(u8 *buf, u64 info) -{ - if ((buf[0] & 0x7f) == 0x72) { - u8 *ucp, len; - - len = buf[7]; - ucp = (char *)scsi_sense_desc_find(buf, len + 8, 0); - if (!ucp) { - buf[7] = len + 0xa; - ucp = buf + 8 + len; - } - ucp[0] = 0; - ucp[1] = 0xa; - ucp[2] = 0x80; /* Valid bit */ - ucp[3] = 0; - put_unaligned_be64(info, &ucp[4]); - } else if ((buf[0] & 0x7f) == 0x70) { - buf[0] |= 0x80; - put_unaligned_be64(info, &buf[3]); - } -} -EXPORT_SYMBOL(scsi_set_sense_information); diff --git a/include/scsi/scsi_common.h b/include/scsi/scsi_common.h index 676b03b78e57..156d673db900 100644 --- a/include/scsi/scsi_common.h +++ b/include/scsi/scsi_common.h @@ -61,4 +61,9 @@ static inline bool scsi_sense_valid(const struct scsi_sense_hdr *sshdr) extern bool scsi_normalize_sense(const u8 *sense_buffer, int sb_len, struct scsi_sense_hdr *sshdr); +extern void scsi_build_sense_buffer(int desc, u8 *buf, u8 key, u8 asc, u8 ascq); +extern void scsi_set_sense_information(u8 *buf, u64 info); +extern const u8 * scsi_sense_desc_find(const u8 * sense_buffer, int sb_len, + int desc_type); + #endif /* _SCSI_COMMON_H_ */ diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h index 4942710ef720..dbb8c640e26f 100644 --- a/include/scsi/scsi_eh.h +++ b/include/scsi/scsi_eh.h @@ -4,6 +4,7 @@ #include #include +#include struct scsi_device; struct Scsi_Host; @@ -21,15 +22,9 @@ static inline bool scsi_sense_is_deferred(const struct scsi_sense_hdr *sshdr) return ((sshdr->response_code >= 0x70) && (sshdr->response_code & 1)); } -extern const u8 * scsi_sense_desc_find(const u8 * sense_buffer, int sb_len, - int desc_type); - extern int scsi_get_sense_info_fld(const u8 * sense_buffer, int sb_len, u64 * info_out); -extern void scsi_build_sense_buffer(int desc, u8 *buf, u8 key, u8 asc, u8 ascq); -extern void scsi_set_sense_information(u8 *buf, u64 info); - extern int scsi_ioctl_reset(struct scsi_device *, int __user *); struct scsi_eh_save { -- cgit v1.2.3 From f5a8b3a796db01b639435515b3adc003b9f27387 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 15 Jul 2015 10:55:37 +0300 Subject: scsi: Protect against buffer possible overflow in scsi_set_sense_information Make sure that the input sense buffer has sufficient length to fit the information descriptor (12 additional bytes). Modify scsi_set_sense_information to receive the sense buffer length and adjust its callers scsi target and libata. (Fix patch fuzz in scsi_set_sense_information - nab) Reported-by: Hannes Reinecke Signed-off-by: Sagi Grimberg Reviewed-by: Martin K. Petersen Cc: Tejun Heo Reviewed-by: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- drivers/ata/libata-scsi.c | 4 +++- drivers/scsi/scsi_common.c | 13 ++++++++++++- drivers/target/target_core_transport.c | 14 +++++++++++--- include/scsi/scsi_common.h | 2 +- 4 files changed, 27 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 3131adcc1f87..2fb7c79e727f 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -289,7 +289,9 @@ void ata_scsi_set_sense_information(struct scsi_cmnd *cmd, return; information = ata_tf_read_block(tf, NULL); - scsi_set_sense_information(cmd->sense_buffer, information); + scsi_set_sense_information(cmd->sense_buffer, + SCSI_SENSE_BUFFERSIZE, + information); } static ssize_t diff --git a/drivers/scsi/scsi_common.c b/drivers/scsi/scsi_common.c index ee6bdf43a8ea..c126966130ab 100644 --- a/drivers/scsi/scsi_common.c +++ b/drivers/scsi/scsi_common.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -249,10 +250,13 @@ EXPORT_SYMBOL(scsi_build_sense_buffer); * scsi_set_sense_information - set the information field in a * formatted sense data buffer * @buf: Where to build sense data + * @buf_len: buffer length * @info: 64-bit information value to be set * + * Return value: + * 0 on success or EINVAL for invalid sense buffer length **/ -void scsi_set_sense_information(u8 *buf, u64 info) +int scsi_set_sense_information(u8 *buf, int buf_len, u64 info) { if ((buf[0] & 0x7f) == 0x72) { u8 *ucp, len; @@ -263,6 +267,11 @@ void scsi_set_sense_information(u8 *buf, u64 info) buf[7] = len + 0xc; ucp = buf + 8 + len; } + + if (buf_len < len + 0xc) + /* Not enough room for info */ + return -EINVAL; + ucp[0] = 0; ucp[1] = 0xa; ucp[2] = 0x80; /* Valid bit */ @@ -272,5 +281,7 @@ void scsi_set_sense_information(u8 *buf, u64 info) buf[0] |= 0x80; put_unaligned_be64(info, &buf[3]); } + + return 0; } EXPORT_SYMBOL(scsi_set_sense_information); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 2bece607ca0f..7fb031bbcc8d 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -2729,7 +2729,7 @@ static const struct sense_info sense_info_table[] = { }, }; -static void translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason) +static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason) { const struct sense_info *si; u8 *buffer = cmd->sense_buffer; @@ -2756,7 +2756,11 @@ static void translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason) scsi_build_sense_buffer(0, buffer, si->key, asc, ascq); if (si->add_sector_info) - scsi_set_sense_information(buffer, cmd->bad_sector); + return scsi_set_sense_information(buffer, + cmd->scsi_sense_length, + cmd->bad_sector); + + return 0; } int @@ -2774,10 +2778,14 @@ transport_send_check_condition_and_sense(struct se_cmd *cmd, spin_unlock_irqrestore(&cmd->t_state_lock, flags); if (!from_transport) { + int rc; + cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE; - translate_sense_reason(cmd, reason); cmd->scsi_status = SAM_STAT_CHECK_CONDITION; cmd->scsi_sense_length = TRANSPORT_SENSE_BUFFER; + rc = translate_sense_reason(cmd, reason); + if (rc) + return rc; } trace_target_cmd_complete(cmd); diff --git a/include/scsi/scsi_common.h b/include/scsi/scsi_common.h index 156d673db900..11571b2a831e 100644 --- a/include/scsi/scsi_common.h +++ b/include/scsi/scsi_common.h @@ -62,7 +62,7 @@ extern bool scsi_normalize_sense(const u8 *sense_buffer, int sb_len, struct scsi_sense_hdr *sshdr); extern void scsi_build_sense_buffer(int desc, u8 *buf, u8 key, u8 asc, u8 ascq); -extern void scsi_set_sense_information(u8 *buf, u64 info); +int scsi_set_sense_information(u8 *buf, int buf_len, u64 info); extern const u8 * scsi_sense_desc_find(const u8 * sense_buffer, int sb_len, int desc_type); -- cgit v1.2.3 From 4e4937e8aefde8d49340e803ebbedcdf4b43e5f0 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 16 Jul 2015 10:28:05 +0300 Subject: target: Return descriptor format sense data in case the LU spans 64bit sectors In case a LU spans 64bit sectors, fixed size sense data information field is only 32 bits which means the sector information will be truncated. Thus, if the LU spans 64bit sectors, use descriptor format sense data to correctly report sector information. Reported-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Signed-off-by: Sagi Grimberg Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_hba.c | 5 +++++ drivers/target/target_core_spc.c | 12 +++++++++--- drivers/target/target_core_transport.c | 3 ++- include/target/target_core_backend.h | 2 ++ 4 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_hba.c b/drivers/target/target_core_hba.c index 62ea4e8e70a8..d746a3a4a623 100644 --- a/drivers/target/target_core_hba.c +++ b/drivers/target/target_core_hba.c @@ -176,3 +176,8 @@ core_delete_hba(struct se_hba *hba) kfree(hba); return 0; } + +bool target_sense_desc_format(struct se_device *dev) +{ + return dev->transport->get_blocks(dev) > U32_MAX; +} diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index c43dcbf2d48e..b949d335a6ba 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -761,7 +761,12 @@ static int spc_modesense_control(struct se_cmd *cmd, u8 pc, u8 *p) if (pc == 1) goto out; - p[2] = 2; + /* GLTSD: No implicit save of log parameters */ + p[2] = (1 << 1); + if (target_sense_desc_format(dev)) + /* D_SENSE: Descriptor format sense data for 64bit sectors */ + p[2] |= (1 << 2); + /* * From spc4r23, 7.4.7 Control mode page * @@ -1144,6 +1149,7 @@ static sense_reason_t spc_emulate_request_sense(struct se_cmd *cmd) unsigned char *rbuf; u8 ua_asc = 0, ua_ascq = 0; unsigned char buf[SE_SENSE_BUF]; + bool desc_format = target_sense_desc_format(cmd->se_dev); memset(buf, 0, SE_SENSE_BUF); @@ -1158,10 +1164,10 @@ static sense_reason_t spc_emulate_request_sense(struct se_cmd *cmd) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; if (!core_scsi3_ua_clear_for_request_sense(cmd, &ua_asc, &ua_ascq)) - scsi_build_sense_buffer(0, buf, UNIT_ATTENTION, + scsi_build_sense_buffer(desc_format, buf, UNIT_ATTENTION, ua_asc, ua_ascq); else - scsi_build_sense_buffer(0, buf, NO_SENSE, 0x0, 0x0); + scsi_build_sense_buffer(desc_format, buf, NO_SENSE, 0x0, 0x0); memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length)); transport_kunmap_data_sg(cmd); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 7fb031bbcc8d..98155db28365 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -2735,6 +2735,7 @@ static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason) u8 *buffer = cmd->sense_buffer; int r = (__force int)reason; u8 asc, ascq; + bool desc_format = target_sense_desc_format(cmd->se_dev); if (r < ARRAY_SIZE(sense_info_table) && sense_info_table[r].key) si = &sense_info_table[r]; @@ -2754,7 +2755,7 @@ static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason) ascq = si->ascq; } - scsi_build_sense_buffer(0, buffer, si->key, asc, ascq); + scsi_build_sense_buffer(desc_format, buffer, si->key, asc, ascq); if (si->add_sector_info) return scsi_set_sense_information(buffer, cmd->scsi_sense_length, diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 1e5c8f949bae..56cf8e485ef2 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -93,4 +93,6 @@ bool target_lun_is_rdonly(struct se_cmd *); sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd, sense_reason_t (*exec_cmd)(struct se_cmd *cmd)); +bool target_sense_desc_format(struct se_device *dev); + #endif /* TARGET_CORE_BACKEND_H */ -- cgit v1.2.3 From ae1ff3d623905947158fd3394854c23026337810 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Mon, 13 Jul 2015 14:31:28 +0300 Subject: iommu: iova: Move iova cache management to the iova library This is necessary to separate intel-iommu from the iova library. Signed-off-by: Sakari Ailus Signed-off-by: David Woodhouse --- drivers/iommu/intel-iommu.c | 6 ++-- drivers/iommu/iova.c | 83 ++++++++++++++++++++++++++------------------- include/linux/iova.h | 4 +-- 3 files changed, 54 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 92101597cede..2d5cf39e1053 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -3743,7 +3743,7 @@ static inline int iommu_devinfo_cache_init(void) static int __init iommu_init_mempool(void) { int ret; - ret = iommu_iova_cache_init(); + ret = iova_cache_get(); if (ret) return ret; @@ -3757,7 +3757,7 @@ static int __init iommu_init_mempool(void) kmem_cache_destroy(iommu_domain_cache); domain_error: - iommu_iova_cache_destroy(); + iova_cache_put(); return -ENOMEM; } @@ -3766,7 +3766,7 @@ static void __init iommu_exit_mempool(void) { kmem_cache_destroy(iommu_devinfo_cache); kmem_cache_destroy(iommu_domain_cache); - iommu_iova_cache_destroy(); + iova_cache_put(); } static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev) diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 29f2efcf668e..ed95f7a0fad3 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -20,40 +20,6 @@ #include #include -static struct kmem_cache *iommu_iova_cache; - -int iommu_iova_cache_init(void) -{ - int ret = 0; - - iommu_iova_cache = kmem_cache_create("iommu_iova", - sizeof(struct iova), - 0, - SLAB_HWCACHE_ALIGN, - NULL); - if (!iommu_iova_cache) { - pr_err("Couldn't create iova cache\n"); - ret = -ENOMEM; - } - - return ret; -} - -void iommu_iova_cache_destroy(void) -{ - kmem_cache_destroy(iommu_iova_cache); -} - -struct iova *alloc_iova_mem(void) -{ - return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC); -} - -void free_iova_mem(struct iova *iova) -{ - kmem_cache_free(iommu_iova_cache, iova); -} - void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn, unsigned long pfn_32bit) @@ -237,6 +203,55 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova) rb_insert_color(&iova->node, root); } +static struct kmem_cache *iova_cache; +static unsigned int iova_cache_users; +static DEFINE_MUTEX(iova_cache_mutex); + +struct iova *alloc_iova_mem(void) +{ + return kmem_cache_alloc(iova_cache, GFP_ATOMIC); +} +EXPORT_SYMBOL(alloc_iova_mem); + +void free_iova_mem(struct iova *iova) +{ + kmem_cache_free(iova_cache, iova); +} +EXPORT_SYMBOL(free_iova_mem); + +int iova_cache_get(void) +{ + mutex_lock(&iova_cache_mutex); + if (!iova_cache_users) { + iova_cache = kmem_cache_create( + "iommu_iova", sizeof(struct iova), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!iova_cache) { + mutex_unlock(&iova_cache_mutex); + printk(KERN_ERR "Couldn't create iova cache\n"); + return -ENOMEM; + } + } + + iova_cache_users++; + mutex_unlock(&iova_cache_mutex); + + return 0; +} + +void iova_cache_put(void) +{ + mutex_lock(&iova_cache_mutex); + if (WARN_ON(!iova_cache_users)) { + mutex_unlock(&iova_cache_mutex); + return; + } + iova_cache_users--; + if (!iova_cache_users) + kmem_cache_destroy(iova_cache); + mutex_unlock(&iova_cache_mutex); +} + /** * alloc_iova - allocates an iova * @iovad: - iova domain in question diff --git a/include/linux/iova.h b/include/linux/iova.h index 3920a19d8194..92f7177db2ce 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -68,8 +68,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova) return iova >> iova_shift(iovad); } -int iommu_iova_cache_init(void); -void iommu_iova_cache_destroy(void); +int iova_cache_get(void); +void iova_cache_put(void); struct iova *alloc_iova_mem(void); void free_iova_mem(struct iova *iova); -- cgit v1.2.3 From 53c46995b6ed7cb32a28bce1f4a25065baf65d8f Mon Sep 17 00:00:00 2001 From: Chris Zankel Date: Mon, 20 Jul 2015 16:29:49 -0700 Subject: target: remove unused lun_flags field from se_lun The lun_flags field is not used, so drop it. Signed-off-by: Chris Zankel Signed-off-by: Spencer Baugh Reviewed-by: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- include/target/target_core_base.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index a6816444d81b..d57a0cbf265b 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -680,7 +680,6 @@ struct se_lun { #define SE_LUN_LINK_MAGIC 0xffff7771 u32 lun_link_magic; u32 lun_access; - u32 lun_flags; u32 lun_index; /* RELATIVE TARGET PORT IDENTIFER */ -- cgit v1.2.3 From b6a54b8d895648d915c7e8308f3d3e6bf2505d69 Mon Sep 17 00:00:00 2001 From: Chris Zankel Date: Mon, 20 Jul 2015 16:29:50 -0700 Subject: target: remove initiatorname field in se_acl_lun From: Chris Zankel The initiatorname field in se_acl_lun is only a copy of the same field in se_node_acl, so remove it and use the version in se_node_acl where needed (it's actually only used for pr_debug) Signed-off-by: Chris Zankel Signed-off-by: Spencer Baugh Reviewed-by: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 8 +++----- drivers/target/target_core_fabric_configfs.c | 2 +- include/target/target_core_base.h | 1 - 3 files changed, 4 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index db7034292053..55f2cb2a9947 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -620,8 +620,6 @@ struct se_lun_acl *core_dev_init_initiator_node_lun_acl( lacl->mapped_lun = mapped_lun; lacl->se_lun_nacl = nacl; - snprintf(lacl->initiatorname, TRANSPORT_IQN_LEN, "%s", - nacl->initiatorname); return lacl; } @@ -656,7 +654,7 @@ int core_dev_add_initiator_node_lun_acl( " InitiatorNode: %s\n", tpg->se_tpg_tfo->get_fabric_name(), tpg->se_tpg_tfo->tpg_get_tag(tpg), lun->unpacked_lun, lacl->mapped_lun, (lun_access & TRANSPORT_LUNFLAGS_READ_WRITE) ? "RW" : "RO", - lacl->initiatorname); + nacl->initiatorname); /* * Check to see if there are any existing persistent reservation APTPL * pre-registrations that need to be enabled for this LUN ACL.. @@ -688,7 +686,7 @@ int core_dev_del_initiator_node_lun_acl( " InitiatorNode: %s Mapped LUN: %llu\n", tpg->se_tpg_tfo->get_fabric_name(), tpg->se_tpg_tfo->tpg_get_tag(tpg), lun->unpacked_lun, - lacl->initiatorname, lacl->mapped_lun); + nacl->initiatorname, lacl->mapped_lun); return 0; } @@ -701,7 +699,7 @@ void core_dev_free_initiator_node_lun_acl( " Mapped LUN: %llu\n", tpg->se_tpg_tfo->get_fabric_name(), tpg->se_tpg_tfo->tpg_get_tag(tpg), tpg->se_tpg_tfo->get_fabric_name(), - lacl->initiatorname, lacl->mapped_lun); + lacl->se_lun_nacl->initiatorname, lacl->mapped_lun); kfree(lacl); } diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 48a36989c1a6..be42429468e2 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -203,7 +203,7 @@ static ssize_t target_fabric_mappedlun_store_write_protect( pr_debug("%s_ConfigFS: Changed Initiator ACL: %s" " Mapped LUN: %llu Write Protect bit to %s\n", se_tpg->se_tpg_tfo->get_fabric_name(), - lacl->initiatorname, lacl->mapped_lun, (op) ? "ON" : "OFF"); + se_nacl->initiatorname, lacl->mapped_lun, (op) ? "ON" : "OFF"); return count; diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index d57a0cbf265b..95e65bd31e05 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -593,7 +593,6 @@ struct se_ml_stat_grps { }; struct se_lun_acl { - char initiatorname[TRANSPORT_IQN_LEN]; u64 mapped_lun; struct se_node_acl *se_lun_nacl; struct se_lun *se_lun; -- cgit v1.2.3 From 9c31820b6ab93ec298ad98abeee49759b5f5958c Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Tue, 21 Jul 2015 17:45:32 -0700 Subject: target: Remove cmd->se_ordered_id (unused except debug log lines) For every command, we set se_ordered_id by doing atomic_inc_return on dev->dev_ordered_id for the corresponding device. However, the only places this value gets used are in pr_debug() calls, which doesn't seem worth an extra atomic op per IO. Signed-off-by: Roland Dreier Reviewed-by: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 1 - drivers/target/target_core_transport.c | 39 ++++++++++++---------------------- include/target/target_core_base.h | 2 -- 3 files changed, 13 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 55f2cb2a9947..dcc424ac35d4 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -769,7 +769,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) spin_lock_init(&dev->se_tmr_lock); spin_lock_init(&dev->qf_cmd_lock); sema_init(&dev->caw_sem, 1); - atomic_set(&dev->dev_ordered_id, 0); INIT_LIST_HEAD(&dev->t10_wwn.t10_vpd_list); spin_lock_init(&dev->t10_wwn.t10_vpd_lock); INIT_LIST_HEAD(&dev->t10_pr.registration_list); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index bd68727a6806..3f0b50082de4 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1178,14 +1178,7 @@ transport_check_alloc_task_attr(struct se_cmd *cmd) " emulation is not supported\n"); return TCM_INVALID_CDB_FIELD; } - /* - * Used to determine when ORDERED commands should go from - * Dormant to Active status. - */ - cmd->se_ordered_id = atomic_inc_return(&dev->dev_ordered_id); - pr_debug("Allocated se_ordered_id: %u for Task Attr: 0x%02x on %s\n", - cmd->se_ordered_id, cmd->sam_task_attr, - dev->transport->name); + return 0; } @@ -1773,16 +1766,14 @@ static bool target_handle_task_attr(struct se_cmd *cmd) */ switch (cmd->sam_task_attr) { case TCM_HEAD_TAG: - pr_debug("Added HEAD_OF_QUEUE for CDB: 0x%02x, " - "se_ordered_id: %u\n", - cmd->t_task_cdb[0], cmd->se_ordered_id); + pr_debug("Added HEAD_OF_QUEUE for CDB: 0x%02x\n", + cmd->t_task_cdb[0]); return false; case TCM_ORDERED_TAG: atomic_inc_mb(&dev->dev_ordered_sync); - pr_debug("Added ORDERED for CDB: 0x%02x to ordered list, " - " se_ordered_id: %u\n", - cmd->t_task_cdb[0], cmd->se_ordered_id); + pr_debug("Added ORDERED for CDB: 0x%02x to ordered list\n", + cmd->t_task_cdb[0]); /* * Execute an ORDERED command if no other older commands @@ -1806,10 +1797,8 @@ static bool target_handle_task_attr(struct se_cmd *cmd) list_add_tail(&cmd->se_delayed_node, &dev->delayed_cmd_list); spin_unlock(&dev->delayed_cmd_lock); - pr_debug("Added CDB: 0x%02x Task Attr: 0x%02x to" - " delayed CMD list, se_ordered_id: %u\n", - cmd->t_task_cdb[0], cmd->sam_task_attr, - cmd->se_ordered_id); + pr_debug("Added CDB: 0x%02x Task Attr: 0x%02x to delayed CMD listn", + cmd->t_task_cdb[0], cmd->sam_task_attr); return true; } @@ -1894,20 +1883,18 @@ static void transport_complete_task_attr(struct se_cmd *cmd) if (cmd->sam_task_attr == TCM_SIMPLE_TAG) { atomic_dec_mb(&dev->simple_cmds); dev->dev_cur_ordered_id++; - pr_debug("Incremented dev->dev_cur_ordered_id: %u for" - " SIMPLE: %u\n", dev->dev_cur_ordered_id, - cmd->se_ordered_id); + pr_debug("Incremented dev->dev_cur_ordered_id: %u for SIMPLE\n", + dev->dev_cur_ordered_id); } else if (cmd->sam_task_attr == TCM_HEAD_TAG) { dev->dev_cur_ordered_id++; - pr_debug("Incremented dev_cur_ordered_id: %u for" - " HEAD_OF_QUEUE: %u\n", dev->dev_cur_ordered_id, - cmd->se_ordered_id); + pr_debug("Incremented dev_cur_ordered_id: %u for HEAD_OF_QUEUE\n", + dev->dev_cur_ordered_id); } else if (cmd->sam_task_attr == TCM_ORDERED_TAG) { atomic_dec_mb(&dev->dev_ordered_sync); dev->dev_cur_ordered_id++; - pr_debug("Incremented dev_cur_ordered_id: %u for ORDERED:" - " %u\n", dev->dev_cur_ordered_id, cmd->se_ordered_id); + pr_debug("Incremented dev_cur_ordered_id: %u for ORDERED\n", + dev->dev_cur_ordered_id); } target_restart_delayed_cmds(dev); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 95e65bd31e05..3afd8dba54e8 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -454,7 +454,6 @@ struct se_cmd { unsigned unknown_data_length:1; /* See se_cmd_flags_table */ u32 se_cmd_flags; - u32 se_ordered_id; /* Total size in bytes associated with command */ u32 data_length; u32 residual_count; @@ -744,7 +743,6 @@ struct se_device { atomic_long_t write_bytes; /* Active commands on this virtual SE device */ atomic_t simple_cmds; - atomic_t dev_ordered_id; atomic_t dev_ordered_sync; atomic_t dev_qf_count; u32 export_count; -- cgit v1.2.3 From 915270c3cacfc80cb3fe7fdd8130439039a85bbb Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Tue, 21 Jul 2015 17:45:33 -0700 Subject: target: Shrink struct se_cmd by rearranging fields On x86-64, these changes reduce the struct size from 528 bytes to 496 bytes. We save a cacheline and get under 512 bytes for better packing. Signed-off-by: Roland Dreier Acked-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- include/target/target_core_base.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 3afd8dba54e8..ac9bf1c0e42d 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -439,6 +439,9 @@ struct se_cmd { u8 scsi_asc; u8 scsi_ascq; u16 scsi_sense_length; + unsigned cmd_wait_set:1; + unsigned unknown_data_length:1; + bool state_active:1; u64 tag; /* SAM command identifier aka task tag */ /* Delay for ALUA Active/NonOptimized state access in milliseconds */ int alua_nonop_delay; @@ -450,8 +453,6 @@ struct se_cmd { unsigned int map_tag; /* Transport protocol dependent state, see transport_state_table */ enum transport_state_table t_state; - unsigned cmd_wait_set:1; - unsigned unknown_data_length:1; /* See se_cmd_flags_table */ u32 se_cmd_flags; /* Total size in bytes associated with command */ @@ -471,7 +472,6 @@ struct se_cmd { struct se_tmr_req *se_tmr_req; struct list_head se_cmd_list; struct completion cmd_wait_comp; - struct kref cmd_kref; const struct target_core_fabric_ops *se_tfo; sense_reason_t (*execute_cmd)(struct se_cmd *); sense_reason_t (*transport_complete_callback)(struct se_cmd *, bool); @@ -491,6 +491,7 @@ struct se_cmd { #define CMD_T_REQUEST_STOP (1 << 8) #define CMD_T_BUSY (1 << 9) spinlock_t t_state_lock; + struct kref cmd_kref; struct completion t_transport_stop_comp; struct work_struct work; @@ -503,8 +504,10 @@ struct se_cmd { struct scatterlist *t_bidi_data_sg; unsigned int t_bidi_data_nents; + /* Used for lun->lun_ref counting */ + int lun_ref_active; + struct list_head state_list; - bool state_active; /* old task stop completion, consider merging with some of the above */ struct completion task_stop_comp; @@ -512,20 +515,17 @@ struct se_cmd { /* backend private data */ void *priv; - /* Used for lun->lun_ref counting */ - int lun_ref_active; - /* DIF related members */ enum target_prot_op prot_op; enum target_prot_type prot_type; u8 prot_checks; + bool prot_pto; u32 prot_length; u32 reftag_seed; struct scatterlist *t_prot_sg; unsigned int t_prot_nents; sense_reason_t pi_err; sector_t bad_sector; - bool prot_pto; }; struct se_ua { -- cgit v1.2.3 From a6415cddc4e6e1675a5648e7785aef716980c90c Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Sat, 1 Aug 2015 00:10:12 -0700 Subject: iscsi-target: Add tpg_enabled_sendtargets for disabled discovery This patch adds a new tpg_enabled_sendtargets configfs attribute to allow in-band sendtargets discovery information to include target-portal-groups (TPGs) in !TPG_STATE_ACTIVE state. This functionality is useful for clustered iSCSI targets, where TPGTs handled on remote cluster nodes should be advertised in the SendTargets response. By default, this new attribute retains the default behaviour of existing code which to ignore portal-groups in !TPG_STATE_ACTIVE state. Signed-off-by: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target.c | 10 +++++----- drivers/target/iscsi/iscsi_target_configfs.c | 6 ++++++ drivers/target/iscsi/iscsi_target_tpg.c | 19 +++++++++++++++++++ drivers/target/iscsi/iscsi_target_tpg.h | 1 + include/target/iscsi/iscsi_target_core.h | 3 +++ 5 files changed, 34 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index a4cf58cb835d..986518c3ea12 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -3398,6 +3398,7 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd, int target_name_printed; unsigned char buf[ISCSI_IQN_LEN+12]; /* iqn + "TargetName=" + \0 */ unsigned char *text_in = cmd->text_in_ptr, *text_ptr = NULL; + bool active; buffer_len = min(conn->conn_ops->MaxRecvDataSegmentLength, SENDTARGETS_BUF_LIMIT); @@ -3451,13 +3452,12 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd, } spin_lock(&tpg->tpg_state_lock); - if ((tpg->tpg_state == TPG_STATE_FREE) || - (tpg->tpg_state == TPG_STATE_INACTIVE)) { - spin_unlock(&tpg->tpg_state_lock); - continue; - } + active = (tpg->tpg_state == TPG_STATE_ACTIVE); spin_unlock(&tpg->tpg_state_lock); + if (!active && tpg->tpg_attrib.tpg_enabled_sendtargets) + continue; + spin_lock(&tpg->tpg_np_lock); list_for_each_entry(tpg_np, &tpg->tpg_gnp_list, tpg_np_list) { diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index c1898c84b3d2..05f16640fb9b 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -1010,6 +1010,11 @@ TPG_ATTR(t10_pi, S_IRUGO | S_IWUSR); */ DEF_TPG_ATTRIB(fabric_prot_type); TPG_ATTR(fabric_prot_type, S_IRUGO | S_IWUSR); +/* + * Define iscsi_tpg_attrib_s_tpg_enabled_sendtargets + */ +DEF_TPG_ATTRIB(tpg_enabled_sendtargets); +TPG_ATTR(tpg_enabled_sendtargets, S_IRUGO | S_IWUSR); static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = { &iscsi_tpg_attrib_authentication.attr, @@ -1024,6 +1029,7 @@ static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = { &iscsi_tpg_attrib_default_erl.attr, &iscsi_tpg_attrib_t10_pi.attr, &iscsi_tpg_attrib_fabric_prot_type.attr, + &iscsi_tpg_attrib_tpg_enabled_sendtargets.attr, NULL, }; diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index 968068ffcb1c..8262a853e888 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -226,6 +226,7 @@ static void iscsit_set_default_tpg_attribs(struct iscsi_portal_group *tpg) a->default_erl = TA_DEFAULT_ERL; a->t10_pi = TA_DEFAULT_T10_PI; a->fabric_prot_type = TA_DEFAULT_FABRIC_PROT_TYPE; + a->tpg_enabled_sendtargets = TA_DEFAULT_TPG_ENABLED_SENDTARGETS; } int iscsit_tpg_add_portal_group(struct iscsi_tiqn *tiqn, struct iscsi_portal_group *tpg) @@ -892,3 +893,21 @@ int iscsit_ta_fabric_prot_type( return 0; } + +int iscsit_ta_tpg_enabled_sendtargets( + struct iscsi_portal_group *tpg, + u32 flag) +{ + struct iscsi_tpg_attrib *a = &tpg->tpg_attrib; + + if ((flag != 0) && (flag != 1)) { + pr_err("Illegal value %d\n", flag); + return -EINVAL; + } + + a->tpg_enabled_sendtargets = flag; + pr_debug("iSCSI_TPG[%hu] - TPG enabled bit required for SendTargets:" + " %s\n", tpg->tpgt, (a->tpg_enabled_sendtargets) ? "ON" : "OFF"); + + return 0; +} diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h index 95ff5bdecd71..a2790fd8f7da 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.h +++ b/drivers/target/iscsi/iscsi_target_tpg.h @@ -40,5 +40,6 @@ extern int iscsit_ta_demo_mode_discovery(struct iscsi_portal_group *, u32); extern int iscsit_ta_default_erl(struct iscsi_portal_group *, u32); extern int iscsit_ta_t10_pi(struct iscsi_portal_group *, u32); extern int iscsit_ta_fabric_prot_type(struct iscsi_portal_group *, u32); +extern int iscsit_ta_tpg_enabled_sendtargets(struct iscsi_portal_group *, u32); #endif /* ISCSI_TARGET_TPG_H */ diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 34117b8b72e4..ab465858f462 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -62,6 +62,8 @@ /* T10 protection information disabled by default */ #define TA_DEFAULT_T10_PI 0 #define TA_DEFAULT_FABRIC_PROT_TYPE 0 +/* TPG status needs to be enabled to return sendtargets discovery endpoint info */ +#define TA_DEFAULT_TPG_ENABLED_SENDTARGETS 1 #define ISCSI_IOV_DATA_BUFFER 5 @@ -763,6 +765,7 @@ struct iscsi_tpg_attrib { u32 default_erl; u8 t10_pi; u32 fabric_prot_type; + u32 tpg_enabled_sendtargets; struct iscsi_portal_group *tpg; }; -- cgit v1.2.3 From 109e2381749c1cfd94a0d22b2b54142539024973 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Thu, 23 Jul 2015 14:53:32 -0700 Subject: target: Drop iSCSI use of mutex around max_cmd_sn increment In a performance profile, taking a mutex in iscsit_increment_maxcmdsn() shows up very high. However taking a mutex around "sess->max_cmd_sn += 1" seems pretty silly: we're not serializing against other contexts in any useful way. I did a quick audit and there don't appear to be any other places that use max_cmd_sn within the mutex more than once, so this lock can't be providing any useful serialization. (Get correct values for logging - fix whitespace damage) Signed-off-by: Roland Dreier Signed-off-by: Spencer Baugh Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target.c | 18 +++++++++--------- drivers/target/iscsi/iscsi_target_configfs.c | 6 ++++-- drivers/target/iscsi/iscsi_target_device.c | 7 ++----- drivers/target/iscsi/iscsi_target_login.c | 2 +- drivers/target/iscsi/iscsi_target_nego.c | 9 +++------ drivers/target/iscsi/iscsi_target_tmr.c | 2 +- drivers/target/iscsi/iscsi_target_util.c | 7 ++++--- include/target/iscsi/iscsi_target_core.h | 2 +- 8 files changed, 25 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 986518c3ea12..e55f49c7c847 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -2555,7 +2555,7 @@ static int iscsit_send_conn_drop_async_message( cmd->stat_sn = conn->stat_sn++; hdr->statsn = cpu_to_be32(cmd->stat_sn); hdr->exp_cmdsn = cpu_to_be32(conn->sess->exp_cmd_sn); - hdr->max_cmdsn = cpu_to_be32(conn->sess->max_cmd_sn); + hdr->max_cmdsn = cpu_to_be32((u32) atomic_read(&conn->sess->max_cmd_sn)); hdr->async_event = ISCSI_ASYNC_MSG_DROPPING_CONNECTION; hdr->param1 = cpu_to_be16(cmd->logout_cid); hdr->param2 = cpu_to_be16(conn->sess->sess_ops->DefaultTime2Wait); @@ -2627,7 +2627,7 @@ iscsit_build_datain_pdu(struct iscsi_cmd *cmd, struct iscsi_conn *conn, hdr->statsn = cpu_to_be32(0xFFFFFFFF); hdr->exp_cmdsn = cpu_to_be32(conn->sess->exp_cmd_sn); - hdr->max_cmdsn = cpu_to_be32(conn->sess->max_cmd_sn); + hdr->max_cmdsn = cpu_to_be32((u32) atomic_read(&conn->sess->max_cmd_sn)); hdr->datasn = cpu_to_be32(datain->data_sn); hdr->offset = cpu_to_be32(datain->offset); @@ -2838,7 +2838,7 @@ iscsit_build_logout_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn, iscsit_increment_maxcmdsn(cmd, conn->sess); hdr->exp_cmdsn = cpu_to_be32(conn->sess->exp_cmd_sn); - hdr->max_cmdsn = cpu_to_be32(conn->sess->max_cmd_sn); + hdr->max_cmdsn = cpu_to_be32((u32) atomic_read(&conn->sess->max_cmd_sn)); pr_debug("Built Logout Response ITT: 0x%08x StatSN:" " 0x%08x Response: 0x%02x CID: %hu on CID: %hu\n", @@ -2901,7 +2901,7 @@ iscsit_build_nopin_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn, iscsit_increment_maxcmdsn(cmd, conn->sess); hdr->exp_cmdsn = cpu_to_be32(conn->sess->exp_cmd_sn); - hdr->max_cmdsn = cpu_to_be32(conn->sess->max_cmd_sn); + hdr->max_cmdsn = cpu_to_be32((u32) atomic_read(&conn->sess->max_cmd_sn)); pr_debug("Built NOPIN %s Response ITT: 0x%08x, TTT: 0x%08x," " StatSN: 0x%08x, Length %u\n", (nopout_response) ? @@ -3048,7 +3048,7 @@ static int iscsit_send_r2t( hdr->ttt = cpu_to_be32(r2t->targ_xfer_tag); hdr->statsn = cpu_to_be32(conn->stat_sn); hdr->exp_cmdsn = cpu_to_be32(conn->sess->exp_cmd_sn); - hdr->max_cmdsn = cpu_to_be32(conn->sess->max_cmd_sn); + hdr->max_cmdsn = cpu_to_be32((u32) atomic_read(&conn->sess->max_cmd_sn)); hdr->r2tsn = cpu_to_be32(r2t->r2t_sn); hdr->data_offset = cpu_to_be32(r2t->offset); hdr->data_length = cpu_to_be32(r2t->xfer_len); @@ -3201,7 +3201,7 @@ void iscsit_build_rsp_pdu(struct iscsi_cmd *cmd, struct iscsi_conn *conn, iscsit_increment_maxcmdsn(cmd, conn->sess); hdr->exp_cmdsn = cpu_to_be32(conn->sess->exp_cmd_sn); - hdr->max_cmdsn = cpu_to_be32(conn->sess->max_cmd_sn); + hdr->max_cmdsn = cpu_to_be32((u32) atomic_read(&conn->sess->max_cmd_sn)); pr_debug("Built SCSI Response, ITT: 0x%08x, StatSN: 0x%08x," " Response: 0x%02x, SAM Status: 0x%02x, CID: %hu\n", @@ -3320,7 +3320,7 @@ iscsit_build_task_mgt_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn, iscsit_increment_maxcmdsn(cmd, conn->sess); hdr->exp_cmdsn = cpu_to_be32(conn->sess->exp_cmd_sn); - hdr->max_cmdsn = cpu_to_be32(conn->sess->max_cmd_sn); + hdr->max_cmdsn = cpu_to_be32((u32) atomic_read(&conn->sess->max_cmd_sn)); pr_debug("Built Task Management Response ITT: 0x%08x," " StatSN: 0x%08x, Response: 0x%02x, CID: %hu\n", @@ -3575,7 +3575,7 @@ iscsit_build_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn, */ cmd->maxcmdsn_inc = 0; hdr->exp_cmdsn = cpu_to_be32(conn->sess->exp_cmd_sn); - hdr->max_cmdsn = cpu_to_be32(conn->sess->max_cmd_sn); + hdr->max_cmdsn = cpu_to_be32((u32) atomic_read(&conn->sess->max_cmd_sn)); pr_debug("Built Text Response: ITT: 0x%08x, TTT: 0x%08x, StatSN: 0x%08x," " Length: %u, CID: %hu F: %d C: %d\n", cmd->init_task_tag, @@ -3653,7 +3653,7 @@ iscsit_build_reject(struct iscsi_cmd *cmd, struct iscsi_conn *conn, cmd->stat_sn = conn->stat_sn++; hdr->statsn = cpu_to_be32(cmd->stat_sn); hdr->exp_cmdsn = cpu_to_be32(conn->sess->exp_cmd_sn); - hdr->max_cmdsn = cpu_to_be32(conn->sess->max_cmd_sn); + hdr->max_cmdsn = cpu_to_be32((u32) atomic_read(&conn->sess->max_cmd_sn)); } EXPORT_SYMBOL(iscsit_build_reject); diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 05f16640fb9b..48f708bc101d 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -656,6 +656,7 @@ static ssize_t lio_target_nacl_show_info( struct iscsi_conn *conn; struct se_session *se_sess; ssize_t rb = 0; + u32 max_cmd_sn; spin_lock_bh(&se_nacl->nacl_sess_lock); se_sess = se_nacl->nacl_sess; @@ -703,11 +704,12 @@ static ssize_t lio_target_nacl_show_info( " Values]-----------------------\n"); rb += sprintf(page+rb, " CmdSN/WR : CmdSN/WC : ExpCmdSN" " : MaxCmdSN : ITT : TTT\n"); + max_cmd_sn = (u32) atomic_read(&sess->max_cmd_sn); rb += sprintf(page+rb, " 0x%08x 0x%08x 0x%08x 0x%08x" " 0x%08x 0x%08x\n", sess->cmdsn_window, - (sess->max_cmd_sn - sess->exp_cmd_sn) + 1, - sess->exp_cmd_sn, sess->max_cmd_sn, + (max_cmd_sn - sess->exp_cmd_sn) + 1, + sess->exp_cmd_sn, max_cmd_sn, sess->init_task_tag, sess->targ_xfer_tag); rb += sprintf(page+rb, "----------------------[iSCSI" " Connections]-------------------------\n"); diff --git a/drivers/target/iscsi/iscsi_target_device.c b/drivers/target/iscsi/iscsi_target_device.c index 5fabcd3d623f..07d2ef67dba6 100644 --- a/drivers/target/iscsi/iscsi_target_device.c +++ b/drivers/target/iscsi/iscsi_target_device.c @@ -47,7 +47,7 @@ void iscsit_determine_maxcmdsn(struct iscsi_session *sess) * core_set_queue_depth_for_node(). */ sess->cmdsn_window = se_nacl->queue_depth; - sess->max_cmd_sn = (sess->max_cmd_sn + se_nacl->queue_depth) - 1; + atomic_set(&sess->max_cmd_sn, (u32) atomic_read(&sess->max_cmd_sn) + se_nacl->queue_depth - 1); } void iscsit_increment_maxcmdsn(struct iscsi_cmd *cmd, struct iscsi_session *sess) @@ -57,9 +57,6 @@ void iscsit_increment_maxcmdsn(struct iscsi_cmd *cmd, struct iscsi_session *sess cmd->maxcmdsn_inc = 1; - mutex_lock(&sess->cmdsn_mutex); - sess->max_cmd_sn += 1; - pr_debug("Updated MaxCmdSN to 0x%08x\n", sess->max_cmd_sn); - mutex_unlock(&sess->cmdsn_mutex); + pr_debug("Updated MaxCmdSN to 0x%08x\n", atomic_inc_return(&sess->max_cmd_sn)); } EXPORT_SYMBOL(iscsit_increment_maxcmdsn); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 3d0fe4ff5590..bd192f88e1e6 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -330,7 +330,7 @@ static int iscsi_login_zero_tsih_s1( * The FFP CmdSN window values will be allocated from the TPG's * Initiator Node's ACL once the login has been successfully completed. */ - sess->max_cmd_sn = be32_to_cpu(pdu->cmdsn); + atomic_set(&sess->max_cmd_sn, be32_to_cpu(pdu->cmdsn)); sess->sess_ops = kzalloc(sizeof(struct iscsi_sess_ops), GFP_KERNEL); if (!sess->sess_ops) { diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index 8c02fa34716f..74d041e815f4 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -340,7 +340,6 @@ static int iscsi_target_check_first_request( static int iscsi_target_do_tx_login_io(struct iscsi_conn *conn, struct iscsi_login *login) { u32 padding = 0; - struct iscsi_session *sess = conn->sess; struct iscsi_login_rsp *login_rsp; login_rsp = (struct iscsi_login_rsp *) login->rsp; @@ -352,7 +351,7 @@ static int iscsi_target_do_tx_login_io(struct iscsi_conn *conn, struct iscsi_log login_rsp->itt = login->init_task_tag; login_rsp->statsn = cpu_to_be32(conn->stat_sn++); login_rsp->exp_cmdsn = cpu_to_be32(conn->sess->exp_cmd_sn); - login_rsp->max_cmdsn = cpu_to_be32(conn->sess->max_cmd_sn); + login_rsp->max_cmdsn = cpu_to_be32((u32) atomic_read(&conn->sess->max_cmd_sn)); pr_debug("Sending Login Response, Flags: 0x%02x, ITT: 0x%08x," " ExpCmdSN; 0x%08x, MaxCmdSN: 0x%08x, StatSN: 0x%08x, Length:" @@ -367,10 +366,8 @@ static int iscsi_target_do_tx_login_io(struct iscsi_conn *conn, struct iscsi_log return -1; login->rsp_length = 0; - mutex_lock(&sess->cmdsn_mutex); - login_rsp->exp_cmdsn = cpu_to_be32(sess->exp_cmd_sn); - login_rsp->max_cmdsn = cpu_to_be32(sess->max_cmd_sn); - mutex_unlock(&sess->cmdsn_mutex); + login_rsp->exp_cmdsn = cpu_to_be32(login_rsp->exp_cmdsn); + login_rsp->max_cmdsn = cpu_to_be32(login_rsp->max_cmdsn); return 0; } diff --git a/drivers/target/iscsi/iscsi_target_tmr.c b/drivers/target/iscsi/iscsi_target_tmr.c index cf59c397007b..11320df939f7 100644 --- a/drivers/target/iscsi/iscsi_target_tmr.c +++ b/drivers/target/iscsi/iscsi_target_tmr.c @@ -50,7 +50,7 @@ u8 iscsit_tmr_abort_task( pr_err("Unable to locate RefTaskTag: 0x%08x on CID:" " %hu.\n", hdr->rtt, conn->cid); return (iscsi_sna_gte(be32_to_cpu(hdr->refcmdsn), conn->sess->exp_cmd_sn) && - iscsi_sna_lte(be32_to_cpu(hdr->refcmdsn), conn->sess->max_cmd_sn)) ? + iscsi_sna_lte(be32_to_cpu(hdr->refcmdsn), (u32) atomic_read(&conn->sess->max_cmd_sn))) ? ISCSI_TMF_RSP_COMPLETE : ISCSI_TMF_RSP_NO_TASK; } if (ref_cmd->cmd_sn != be32_to_cpu(hdr->refcmdsn)) { diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index a2bff0702eb2..7df4fac69f39 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -233,6 +233,7 @@ struct iscsi_r2t *iscsit_get_holder_for_r2tsn( static inline int iscsit_check_received_cmdsn(struct iscsi_session *sess, u32 cmdsn) { + u32 max_cmdsn; int ret; /* @@ -241,10 +242,10 @@ static inline int iscsit_check_received_cmdsn(struct iscsi_session *sess, u32 cm * or order CmdSNs due to multiple connection sessions and/or * CRC failures. */ - if (iscsi_sna_gt(cmdsn, sess->max_cmd_sn)) { + max_cmdsn = atomic_read(&sess->max_cmd_sn); + if (iscsi_sna_gt(cmdsn, max_cmdsn)) { pr_err("Received CmdSN: 0x%08x is greater than" - " MaxCmdSN: 0x%08x, ignoring.\n", cmdsn, - sess->max_cmd_sn); + " MaxCmdSN: 0x%08x, ignoring.\n", cmdsn, max_cmdsn); ret = CMDSN_MAXCMDSN_OVERRUN; } else if (cmdsn == sess->exp_cmd_sn) { diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index ab465858f462..d4616ef12e04 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -637,7 +637,7 @@ struct iscsi_session { /* session wide counter: expected command sequence number */ u32 exp_cmd_sn; /* session wide counter: maximum allowed command sequence number */ - u32 max_cmd_sn; + atomic_t max_cmd_sn; struct list_head sess_ooo_cmdsn_list; /* LIO specific session ID */ -- cgit v1.2.3 From 17e8351a77397e8a83727eb17e3a3e9b8ab5257a Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Fri, 24 Jul 2015 08:12:54 +0200 Subject: thermal: consistently use int for temperatures MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer Acked-by: Geert Uytterhoeven Reviewed-by: Jean Delvare Reviewed-by: Lukasz Majewski Reviewed-by: Darren Hart Reviewed-by: Heiko Stuebner Reviewed-by: Peter Feuerer Cc: Punit Agrawal Cc: Zhang Rui Cc: Eduardo Valentin Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare Cc: Peter Feuerer Cc: Heiko Stuebner Cc: Lukasz Majewski Cc: Stephen Warren Cc: Thierry Reding Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck Cc: Rafael J. Wysocki Cc: Maxime Ripard Cc: Darren Hart Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui --- drivers/acpi/thermal.c | 12 +++++----- drivers/hwmon/lm75.c | 2 +- drivers/hwmon/ntc_thermistor.c | 2 +- drivers/hwmon/tmp102.c | 2 +- drivers/input/touchscreen/sun4i-ts.c | 8 +++---- drivers/platform/x86/acerhdf.c | 9 ++++---- drivers/platform/x86/intel_mid_thermal.c | 9 ++++---- drivers/power/charger-manager.c | 2 +- drivers/power/power_supply_core.c | 2 +- drivers/thermal/armada_thermal.c | 2 +- drivers/thermal/db8500_thermal.c | 7 +++--- drivers/thermal/dove_thermal.c | 2 +- drivers/thermal/fair_share.c | 2 +- drivers/thermal/gov_bang_bang.c | 5 ++-- drivers/thermal/hisi_thermal.c | 4 ++-- drivers/thermal/imx_thermal.c | 27 +++++++++++----------- drivers/thermal/int340x_thermal/int3400_thermal.c | 2 +- .../thermal/int340x_thermal/int340x_thermal_zone.c | 10 ++++---- .../thermal/int340x_thermal/int340x_thermal_zone.h | 8 +++---- .../int340x_thermal/processor_thermal_device.c | 4 ++-- drivers/thermal/intel_quark_dts_thermal.c | 13 +++++------ drivers/thermal/intel_soc_dts_iosf.c | 8 +++---- drivers/thermal/kirkwood_thermal.c | 2 +- drivers/thermal/of-thermal.c | 14 +++++------ drivers/thermal/power_allocator.c | 16 ++++++------- drivers/thermal/qcom-spmi-temp-alarm.c | 2 +- drivers/thermal/rcar_thermal.c | 7 +++--- drivers/thermal/rockchip_thermal.c | 10 ++++---- drivers/thermal/samsung/exynos_tmu.c | 23 +++++++++--------- drivers/thermal/spear_thermal.c | 2 +- drivers/thermal/st/st_thermal.c | 5 ++-- drivers/thermal/step_wise.c | 4 ++-- drivers/thermal/tegra_soctherm.c | 4 ++-- drivers/thermal/thermal_core.c | 26 ++++++++++----------- drivers/thermal/thermal_hwmon.c | 10 ++++---- drivers/thermal/ti-soc-thermal/ti-thermal-common.c | 10 ++++---- drivers/thermal/x86_pkg_temp_thermal.c | 10 ++++---- include/linux/thermal.h | 26 +++++++++------------ include/trace/events/thermal_power_allocator.h | 6 ++--- 39 files changed, 152 insertions(+), 167 deletions(-) (limited to 'include') diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 6d4e44ea74ac..e66ad25d112f 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -529,8 +529,7 @@ static void acpi_thermal_check(void *data) /* sys I/F for generic thermal sysfs support */ -static int thermal_get_temp(struct thermal_zone_device *thermal, - unsigned long *temp) +static int thermal_get_temp(struct thermal_zone_device *thermal, int *temp) { struct acpi_thermal *tz = thermal->devdata; int result; @@ -637,7 +636,7 @@ static int thermal_get_trip_type(struct thermal_zone_device *thermal, } static int thermal_get_trip_temp(struct thermal_zone_device *thermal, - int trip, unsigned long *temp) + int trip, int *temp) { struct acpi_thermal *tz = thermal->devdata; int i; @@ -690,7 +689,8 @@ static int thermal_get_trip_temp(struct thermal_zone_device *thermal, } static int thermal_get_crit_temp(struct thermal_zone_device *thermal, - unsigned long *temperature) { + int *temperature) +{ struct acpi_thermal *tz = thermal->devdata; if (tz->trips.critical.flags.valid) { @@ -713,8 +713,8 @@ static int thermal_get_trend(struct thermal_zone_device *thermal, return -EINVAL; if (type == THERMAL_TRIP_ACTIVE) { - unsigned long trip_temp; - unsigned long temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET( + int trip_temp; + int temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET( tz->temperature, tz->kelvin_offset); if (thermal_get_trip_temp(thermal, trip, &trip_temp)) return -EINVAL; diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c index fe41d5ae7cb2..e4e57bbafb10 100644 --- a/drivers/hwmon/lm75.c +++ b/drivers/hwmon/lm75.c @@ -104,7 +104,7 @@ static inline long lm75_reg_to_mc(s16 temp, u8 resolution) /* sysfs attributes for hwmon */ -static int lm75_read_temp(void *dev, long *temp) +static int lm75_read_temp(void *dev, int *temp) { struct lm75_data *data = lm75_update_device(dev); diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c index dc0b76c5e302..feed30646d91 100644 --- a/drivers/hwmon/ntc_thermistor.c +++ b/drivers/hwmon/ntc_thermistor.c @@ -477,7 +477,7 @@ static int ntc_thermistor_get_ohm(struct ntc_data *data) return -EINVAL; } -static int ntc_read_temp(void *dev, long *temp) +static int ntc_read_temp(void *dev, int *temp) { struct ntc_data *data = dev_get_drvdata(dev); int ohm; diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c index 9da2735f1424..65482624ea2c 100644 --- a/drivers/hwmon/tmp102.c +++ b/drivers/hwmon/tmp102.c @@ -98,7 +98,7 @@ static struct tmp102 *tmp102_update_device(struct device *dev) return tmp102; } -static int tmp102_read_temp(void *dev, long *temp) +static int tmp102_read_temp(void *dev, int *temp) { struct tmp102 *tmp102 = tmp102_update_device(dev); diff --git a/drivers/input/touchscreen/sun4i-ts.c b/drivers/input/touchscreen/sun4i-ts.c index c0116994067d..485794376ee5 100644 --- a/drivers/input/touchscreen/sun4i-ts.c +++ b/drivers/input/touchscreen/sun4i-ts.c @@ -191,7 +191,7 @@ static void sun4i_ts_close(struct input_dev *dev) writel(TEMP_IRQ_EN(1), ts->base + TP_INT_FIFOC); } -static int sun4i_get_temp(const struct sun4i_ts_data *ts, long *temp) +static int sun4i_get_temp(const struct sun4i_ts_data *ts, int *temp) { /* No temp_data until the first irq */ if (ts->temp_data == -1) @@ -202,7 +202,7 @@ static int sun4i_get_temp(const struct sun4i_ts_data *ts, long *temp) return 0; } -static int sun4i_get_tz_temp(void *data, long *temp) +static int sun4i_get_tz_temp(void *data, int *temp) { return sun4i_get_temp(data, temp); } @@ -215,14 +215,14 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *devattr, char *buf) { struct sun4i_ts_data *ts = dev_get_drvdata(dev); - long temp; + int temp; int error; error = sun4i_get_temp(ts, &temp); if (error) return error; - return sprintf(buf, "%ld\n", temp); + return sprintf(buf, "%d\n", temp); } static ssize_t show_temp_label(struct device *dev, diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c index 1ef02daddb60..460fa6708bfc 100644 --- a/drivers/platform/x86/acerhdf.c +++ b/drivers/platform/x86/acerhdf.c @@ -346,8 +346,7 @@ static void acerhdf_check_param(struct thermal_zone_device *thermal) * as late as the polling interval is since we can't do that in the respective * accessors of the module parameters. */ -static int acerhdf_get_ec_temp(struct thermal_zone_device *thermal, - unsigned long *t) +static int acerhdf_get_ec_temp(struct thermal_zone_device *thermal, int *t) { int temp, err = 0; @@ -453,7 +452,7 @@ static int acerhdf_get_trip_type(struct thermal_zone_device *thermal, int trip, } static int acerhdf_get_trip_hyst(struct thermal_zone_device *thermal, int trip, - unsigned long *temp) + int *temp) { if (trip != 0) return -EINVAL; @@ -464,7 +463,7 @@ static int acerhdf_get_trip_hyst(struct thermal_zone_device *thermal, int trip, } static int acerhdf_get_trip_temp(struct thermal_zone_device *thermal, int trip, - unsigned long *temp) + int *temp) { if (trip == 0) *temp = fanon; @@ -477,7 +476,7 @@ static int acerhdf_get_trip_temp(struct thermal_zone_device *thermal, int trip, } static int acerhdf_get_crit_temp(struct thermal_zone_device *thermal, - unsigned long *temperature) + int *temperature) { *temperature = ACERHDF_TEMP_CRIT; return 0; diff --git a/drivers/platform/x86/intel_mid_thermal.c b/drivers/platform/x86/intel_mid_thermal.c index 0944e834af8d..9f713b832ba3 100644 --- a/drivers/platform/x86/intel_mid_thermal.c +++ b/drivers/platform/x86/intel_mid_thermal.c @@ -132,7 +132,7 @@ static int is_valid_adc(uint16_t adc_val, uint16_t min, uint16_t max) * to achieve very close approximate temp value with less than * 0.5C error */ -static int adc_to_temp(int direct, uint16_t adc_val, unsigned long *tp) +static int adc_to_temp(int direct, uint16_t adc_val, int *tp) { int temp; @@ -174,14 +174,13 @@ static int adc_to_temp(int direct, uint16_t adc_val, unsigned long *tp) * * Can sleep */ -static int mid_read_temp(struct thermal_zone_device *tzd, unsigned long *temp) +static int mid_read_temp(struct thermal_zone_device *tzd, int *temp) { struct thermal_device_info *td_info = tzd->devdata; uint16_t adc_val, addr; uint8_t data = 0; int ret; - unsigned long curr_temp; - + int curr_temp; addr = td_info->chnl_addr; @@ -453,7 +452,7 @@ static SIMPLE_DEV_PM_OPS(mid_thermal_pm, * * Can sleep */ -static int read_curr_temp(struct thermal_zone_device *tzd, unsigned long *temp) +static int read_curr_temp(struct thermal_zone_device *tzd, int *temp) { WARN_ON(tzd == NULL); return mid_read_temp(tzd, temp); diff --git a/drivers/power/charger-manager.c b/drivers/power/charger-manager.c index 1c202ccbd2a6..907293e6f2a4 100644 --- a/drivers/power/charger-manager.c +++ b/drivers/power/charger-manager.c @@ -619,7 +619,7 @@ static int cm_get_battery_temperature(struct charger_manager *cm, #ifdef CONFIG_THERMAL if (cm->tzd_batt) { - ret = thermal_zone_get_temp(cm->tzd_batt, (unsigned long *)temp); + ret = thermal_zone_get_temp(cm->tzd_batt, temp); if (!ret) /* Calibrate temperature unit */ *temp /= 100; diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c index 869284c2e1e8..456987c88baa 100644 --- a/drivers/power/power_supply_core.c +++ b/drivers/power/power_supply_core.c @@ -557,7 +557,7 @@ EXPORT_SYMBOL_GPL(power_supply_unreg_notifier); #ifdef CONFIG_THERMAL static int power_supply_read_temp(struct thermal_zone_device *tzd, - unsigned long *temp) + int *temp) { struct power_supply *psy; union power_supply_propval val; diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c index 01255fd65135..26b8d326546a 100644 --- a/drivers/thermal/armada_thermal.c +++ b/drivers/thermal/armada_thermal.c @@ -155,7 +155,7 @@ static bool armada_is_valid(struct armada_thermal_priv *priv) } static int armada_get_temp(struct thermal_zone_device *thermal, - unsigned long *temp) + int *temp) { struct armada_thermal_priv *priv = thermal->devdata; unsigned long reg; diff --git a/drivers/thermal/db8500_thermal.c b/drivers/thermal/db8500_thermal.c index 2fb273c4baa9..652acd8fbe48 100644 --- a/drivers/thermal/db8500_thermal.c +++ b/drivers/thermal/db8500_thermal.c @@ -107,8 +107,7 @@ static int db8500_cdev_unbind(struct thermal_zone_device *thermal, } /* Callback to get current temperature */ -static int db8500_sys_get_temp(struct thermal_zone_device *thermal, - unsigned long *temp) +static int db8500_sys_get_temp(struct thermal_zone_device *thermal, int *temp) { struct db8500_thermal_zone *pzone = thermal->devdata; @@ -180,7 +179,7 @@ static int db8500_sys_get_trip_type(struct thermal_zone_device *thermal, /* Callback to get trip point temperature */ static int db8500_sys_get_trip_temp(struct thermal_zone_device *thermal, - int trip, unsigned long *temp) + int trip, int *temp) { struct db8500_thermal_zone *pzone = thermal->devdata; struct db8500_thsens_platform_data *ptrips = pzone->trip_tab; @@ -195,7 +194,7 @@ static int db8500_sys_get_trip_temp(struct thermal_zone_device *thermal, /* Callback to get critical trip point temperature */ static int db8500_sys_get_crit_temp(struct thermal_zone_device *thermal, - unsigned long *temp) + int *temp) { struct db8500_thermal_zone *pzone = thermal->devdata; struct db8500_thsens_platform_data *ptrips = pzone->trip_tab; diff --git a/drivers/thermal/dove_thermal.c b/drivers/thermal/dove_thermal.c index 09f6e304c274..a0bc9de42553 100644 --- a/drivers/thermal/dove_thermal.c +++ b/drivers/thermal/dove_thermal.c @@ -93,7 +93,7 @@ static int dove_init_sensor(const struct dove_thermal_priv *priv) } static int dove_get_temp(struct thermal_zone_device *thermal, - unsigned long *temp) + int *temp) { unsigned long reg; struct dove_thermal_priv *priv = thermal->devdata; diff --git a/drivers/thermal/fair_share.c b/drivers/thermal/fair_share.c index c2c10bbe24d6..34fe36504a55 100644 --- a/drivers/thermal/fair_share.c +++ b/drivers/thermal/fair_share.c @@ -34,7 +34,7 @@ static int get_trip_level(struct thermal_zone_device *tz) { int count = 0; - unsigned long trip_temp; + int trip_temp; enum thermal_trip_type trip_type; if (tz->trips == 0 || !tz->ops->get_trip_temp) diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c index c5dd76b2ee74..70836c5b89bc 100644 --- a/drivers/thermal/gov_bang_bang.c +++ b/drivers/thermal/gov_bang_bang.c @@ -25,14 +25,13 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) { - long trip_temp; - unsigned long trip_hyst; + int trip_temp, trip_hyst; struct thermal_instance *instance; tz->ops->get_trip_temp(tz, trip, &trip_temp); tz->ops->get_trip_hyst(tz, trip, &trip_hyst); - dev_dbg(&tz->device, "Trip%d[temp=%ld]:temp=%d:hyst=%ld\n", + dev_dbg(&tz->device, "Trip%d[temp=%d]:temp=%d:hyst=%d\n", trip, trip_temp, tz->temperature, trip_hyst); diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index d5dd357ba57c..49aa068d1603 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -155,7 +155,7 @@ static void hisi_thermal_disable_sensor(struct hisi_thermal_data *data) mutex_unlock(&data->thermal_lock); } -static int hisi_thermal_get_temp(void *_sensor, long *temp) +static int hisi_thermal_get_temp(void *_sensor, int *temp) { struct hisi_thermal_sensor *sensor = _sensor; struct hisi_thermal_data *data = sensor->thermal; @@ -178,7 +178,7 @@ static int hisi_thermal_get_temp(void *_sensor, long *temp) data->irq_bind_sensor = sensor_id; mutex_unlock(&data->thermal_lock); - dev_dbg(&data->pdev->dev, "id=%d, irq=%d, temp=%ld, thres=%d\n", + dev_dbg(&data->pdev->dev, "id=%d, irq=%d, temp=%d, thres=%d\n", sensor->id, data->irq_enabled, *temp, sensor->thres_temp); /* * Bind irq to sensor for two cases: diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index fde4c2876d14..4bec1d3c3d27 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -98,10 +98,10 @@ struct imx_thermal_data { enum thermal_device_mode mode; struct regmap *tempmon; u32 c1, c2; /* See formula in imx_get_sensor_data() */ - unsigned long temp_passive; - unsigned long temp_critical; - unsigned long alarm_temp; - unsigned long last_temp; + int temp_passive; + int temp_critical; + int alarm_temp; + int last_temp; bool irq_enabled; int irq; struct clk *thermal_clk; @@ -109,7 +109,7 @@ struct imx_thermal_data { }; static void imx_set_panic_temp(struct imx_thermal_data *data, - signed long panic_temp) + int panic_temp) { struct regmap *map = data->tempmon; int critical_value; @@ -121,7 +121,7 @@ static void imx_set_panic_temp(struct imx_thermal_data *data, } static void imx_set_alarm_temp(struct imx_thermal_data *data, - signed long alarm_temp) + int alarm_temp) { struct regmap *map = data->tempmon; int alarm_value; @@ -133,7 +133,7 @@ static void imx_set_alarm_temp(struct imx_thermal_data *data, TEMPSENSE0_ALARM_VALUE_SHIFT); } -static int imx_get_temp(struct thermal_zone_device *tz, unsigned long *temp) +static int imx_get_temp(struct thermal_zone_device *tz, int *temp) { struct imx_thermal_data *data = tz->devdata; struct regmap *map = data->tempmon; @@ -189,13 +189,13 @@ static int imx_get_temp(struct thermal_zone_device *tz, unsigned long *temp) if (data->alarm_temp == data->temp_critical && *temp < data->temp_passive) { imx_set_alarm_temp(data, data->temp_passive); - dev_dbg(&tz->device, "thermal alarm off: T < %lu\n", + dev_dbg(&tz->device, "thermal alarm off: T < %d\n", data->alarm_temp / 1000); } } if (*temp != data->last_temp) { - dev_dbg(&tz->device, "millicelsius: %ld\n", *temp); + dev_dbg(&tz->device, "millicelsius: %d\n", *temp); data->last_temp = *temp; } @@ -262,8 +262,7 @@ static int imx_get_trip_type(struct thermal_zone_device *tz, int trip, return 0; } -static int imx_get_crit_temp(struct thermal_zone_device *tz, - unsigned long *temp) +static int imx_get_crit_temp(struct thermal_zone_device *tz, int *temp) { struct imx_thermal_data *data = tz->devdata; @@ -272,7 +271,7 @@ static int imx_get_crit_temp(struct thermal_zone_device *tz, } static int imx_get_trip_temp(struct thermal_zone_device *tz, int trip, - unsigned long *temp) + int *temp) { struct imx_thermal_data *data = tz->devdata; @@ -282,7 +281,7 @@ static int imx_get_trip_temp(struct thermal_zone_device *tz, int trip, } static int imx_set_trip_temp(struct thermal_zone_device *tz, int trip, - unsigned long temp) + int temp) { struct imx_thermal_data *data = tz->devdata; @@ -434,7 +433,7 @@ static irqreturn_t imx_thermal_alarm_irq_thread(int irq, void *dev) { struct imx_thermal_data *data = dev; - dev_dbg(&data->tz->device, "THERMAL ALARM: T > %lu\n", + dev_dbg(&data->tz->device, "THERMAL ALARM: T > %d\n", data->alarm_temp / 1000); thermal_zone_device_update(data->tz); diff --git a/drivers/thermal/int340x_thermal/int3400_thermal.c b/drivers/thermal/int340x_thermal/int3400_thermal.c index 031018e7a65b..5836e5554433 100644 --- a/drivers/thermal/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/int340x_thermal/int3400_thermal.c @@ -186,7 +186,7 @@ static int int3400_thermal_run_osc(acpi_handle handle, } static int int3400_thermal_get_temp(struct thermal_zone_device *thermal, - unsigned long *temp) + int *temp) { *temp = 20 * 1000; /* faked temp sensor with 20C */ return 0; diff --git a/drivers/thermal/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/int340x_thermal/int340x_thermal_zone.c index 1e25133d35e2..b9b2666aa94c 100644 --- a/drivers/thermal/int340x_thermal/int340x_thermal_zone.c +++ b/drivers/thermal/int340x_thermal/int340x_thermal_zone.c @@ -20,7 +20,7 @@ #include "int340x_thermal_zone.h" static int int340x_thermal_get_zone_temp(struct thermal_zone_device *zone, - unsigned long *temp) + int *temp) { struct int34x_thermal_zone *d = zone->devdata; unsigned long long tmp; @@ -49,7 +49,7 @@ static int int340x_thermal_get_zone_temp(struct thermal_zone_device *zone, } static int int340x_thermal_get_trip_temp(struct thermal_zone_device *zone, - int trip, unsigned long *temp) + int trip, int *temp) { struct int34x_thermal_zone *d = zone->devdata; int i; @@ -114,7 +114,7 @@ static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, } static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone, - int trip, unsigned long temp) + int trip, int temp) { struct int34x_thermal_zone *d = zone->devdata; acpi_status status; @@ -136,7 +136,7 @@ static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone, static int int340x_thermal_get_trip_hyst(struct thermal_zone_device *zone, - int trip, unsigned long *temp) + int trip, int *temp) { struct int34x_thermal_zone *d = zone->devdata; acpi_status status; @@ -163,7 +163,7 @@ static struct thermal_zone_device_ops int340x_thermal_zone_ops = { }; static int int340x_thermal_get_trip_config(acpi_handle handle, char *name, - unsigned long *temp) + int *temp) { unsigned long long r; acpi_status status; diff --git a/drivers/thermal/int340x_thermal/int340x_thermal_zone.h b/drivers/thermal/int340x_thermal/int340x_thermal_zone.h index 9f38ab72c4bf..aaadf724ff2e 100644 --- a/drivers/thermal/int340x_thermal/int340x_thermal_zone.h +++ b/drivers/thermal/int340x_thermal/int340x_thermal_zone.h @@ -21,7 +21,7 @@ #define INT340X_THERMAL_MAX_ACT_TRIP_COUNT 10 struct active_trip { - unsigned long temp; + int temp; int id; bool valid; }; @@ -31,11 +31,11 @@ struct int34x_thermal_zone { struct active_trip act_trips[INT340X_THERMAL_MAX_ACT_TRIP_COUNT]; unsigned long *aux_trips; int aux_trip_nr; - unsigned long psv_temp; + int psv_temp; int psv_trip_id; - unsigned long crt_temp; + int crt_temp; int crt_trip_id; - unsigned long hot_temp; + int hot_temp; int hot_trip_id; struct thermal_zone_device *zone; struct thermal_zone_device_ops *override_ops; diff --git a/drivers/thermal/int340x_thermal/processor_thermal_device.c b/drivers/thermal/int340x_thermal/processor_thermal_device.c index 3df3dc34b124..ccc0ad02d066 100644 --- a/drivers/thermal/int340x_thermal/processor_thermal_device.c +++ b/drivers/thermal/int340x_thermal/processor_thermal_device.c @@ -145,7 +145,7 @@ static int get_tjmax(void) return -EINVAL; } -static int read_temp_msr(unsigned long *temp) +static int read_temp_msr(int *temp) { int cpu; u32 eax, edx; @@ -177,7 +177,7 @@ err_ret: } static int proc_thermal_get_zone_temp(struct thermal_zone_device *zone, - unsigned long *temp) + int *temp) { int ret; diff --git a/drivers/thermal/intel_quark_dts_thermal.c b/drivers/thermal/intel_quark_dts_thermal.c index 4434ec812cb7..5ed90e6c8a64 100644 --- a/drivers/thermal/intel_quark_dts_thermal.c +++ b/drivers/thermal/intel_quark_dts_thermal.c @@ -186,7 +186,7 @@ static int soc_dts_disable(struct thermal_zone_device *tzd) return ret; } -static int _get_trip_temp(int trip, unsigned long *temp) +static int _get_trip_temp(int trip, int *temp) { int status; u32 out; @@ -212,19 +212,18 @@ static int _get_trip_temp(int trip, unsigned long *temp) } static inline int sys_get_trip_temp(struct thermal_zone_device *tzd, - int trip, unsigned long *temp) + int trip, int *temp) { return _get_trip_temp(trip, temp); } -static inline int sys_get_crit_temp(struct thermal_zone_device *tzd, - unsigned long *temp) +static inline int sys_get_crit_temp(struct thermal_zone_device *tzd, int *temp) { return _get_trip_temp(QRK_DTS_ID_TP_CRITICAL, temp); } static int update_trip_temp(struct soc_sensor_entry *aux_entry, - int trip, unsigned long temp) + int trip, int temp) { u32 out; u32 temp_out; @@ -272,7 +271,7 @@ failed: } static inline int sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, - unsigned long temp) + int temp) { return update_trip_temp(tzd->devdata, trip, temp); } @@ -289,7 +288,7 @@ static int sys_get_trip_type(struct thermal_zone_device *thermal, } static int sys_get_curr_temp(struct thermal_zone_device *tzd, - unsigned long *temp) + int *temp) { u32 out; int ret; diff --git a/drivers/thermal/intel_soc_dts_iosf.c b/drivers/thermal/intel_soc_dts_iosf.c index 42e4b6ac3875..5841d1d72996 100644 --- a/drivers/thermal/intel_soc_dts_iosf.c +++ b/drivers/thermal/intel_soc_dts_iosf.c @@ -80,7 +80,7 @@ err_ret: } static int sys_get_trip_temp(struct thermal_zone_device *tzd, int trip, - unsigned long *temp) + int *temp) { int status; u32 out; @@ -106,7 +106,7 @@ static int sys_get_trip_temp(struct thermal_zone_device *tzd, int trip, } static int update_trip_temp(struct intel_soc_dts_sensor_entry *dts, - int thres_index, unsigned long temp, + int thres_index, int temp, enum thermal_trip_type trip_type) { int status; @@ -196,7 +196,7 @@ err_restore_ptps: } static int sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, - unsigned long temp) + int temp) { struct intel_soc_dts_sensor_entry *dts = tzd->devdata; struct intel_soc_dts_sensors *sensors = dts->sensors; @@ -226,7 +226,7 @@ static int sys_get_trip_type(struct thermal_zone_device *tzd, } static int sys_get_curr_temp(struct thermal_zone_device *tzd, - unsigned long *temp) + int *temp) { int status; u32 out; diff --git a/drivers/thermal/kirkwood_thermal.c b/drivers/thermal/kirkwood_thermal.c index 11041fe63dc2..892236621767 100644 --- a/drivers/thermal/kirkwood_thermal.c +++ b/drivers/thermal/kirkwood_thermal.c @@ -33,7 +33,7 @@ struct kirkwood_thermal_priv { }; static int kirkwood_get_temp(struct thermal_zone_device *thermal, - unsigned long *temp) + int *temp) { unsigned long reg; struct kirkwood_thermal_priv *priv = thermal->devdata; diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c index b295b2b6c191..42b7d4253b94 100644 --- a/drivers/thermal/of-thermal.c +++ b/drivers/thermal/of-thermal.c @@ -91,7 +91,7 @@ struct __thermal_zone { /*** DT thermal zone device callbacks ***/ static int of_thermal_get_temp(struct thermal_zone_device *tz, - unsigned long *temp) + int *temp) { struct __thermal_zone *data = tz->devdata; @@ -177,7 +177,7 @@ EXPORT_SYMBOL_GPL(of_thermal_get_trip_points); * Return: zero on success, error code otherwise */ static int of_thermal_set_emul_temp(struct thermal_zone_device *tz, - unsigned long temp) + int temp) { struct __thermal_zone *data = tz->devdata; @@ -311,7 +311,7 @@ static int of_thermal_get_trip_type(struct thermal_zone_device *tz, int trip, } static int of_thermal_get_trip_temp(struct thermal_zone_device *tz, int trip, - unsigned long *temp) + int *temp) { struct __thermal_zone *data = tz->devdata; @@ -324,7 +324,7 @@ static int of_thermal_get_trip_temp(struct thermal_zone_device *tz, int trip, } static int of_thermal_set_trip_temp(struct thermal_zone_device *tz, int trip, - unsigned long temp) + int temp) { struct __thermal_zone *data = tz->devdata; @@ -338,7 +338,7 @@ static int of_thermal_set_trip_temp(struct thermal_zone_device *tz, int trip, } static int of_thermal_get_trip_hyst(struct thermal_zone_device *tz, int trip, - unsigned long *hyst) + int *hyst) { struct __thermal_zone *data = tz->devdata; @@ -351,7 +351,7 @@ static int of_thermal_get_trip_hyst(struct thermal_zone_device *tz, int trip, } static int of_thermal_set_trip_hyst(struct thermal_zone_device *tz, int trip, - unsigned long hyst) + int hyst) { struct __thermal_zone *data = tz->devdata; @@ -365,7 +365,7 @@ static int of_thermal_set_trip_hyst(struct thermal_zone_device *tz, int trip, } static int of_thermal_get_crit_temp(struct thermal_zone_device *tz, - unsigned long *temp) + int *temp) { struct __thermal_zone *data = tz->devdata; int i; diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c index 4672250b329f..045aea59ce9d 100644 --- a/drivers/thermal/power_allocator.c +++ b/drivers/thermal/power_allocator.c @@ -92,8 +92,8 @@ struct power_allocator_params { * Return: The power budget for the next period. */ static u32 pid_controller(struct thermal_zone_device *tz, - unsigned long current_temp, - unsigned long control_temp, + int current_temp, + int control_temp, u32 max_allocatable_power) { s64 p, i, d, power_range; @@ -102,7 +102,7 @@ static u32 pid_controller(struct thermal_zone_device *tz, max_power_frac = int_to_frac(max_allocatable_power); - err = ((s32)control_temp - (s32)current_temp); + err = control_temp - current_temp; err = int_to_frac(err); /* Calculate the proportional term */ @@ -223,8 +223,8 @@ static void divvy_up_power(u32 *req_power, u32 *max_power, int num_actors, } static int allocate_power(struct thermal_zone_device *tz, - unsigned long current_temp, - unsigned long control_temp) + int current_temp, + int control_temp) { struct thermal_instance *instance; struct power_allocator_params *params = tz->governor_data; @@ -326,7 +326,7 @@ static int allocate_power(struct thermal_zone_device *tz, granted_power, total_granted_power, num_actors, power_range, max_allocatable_power, current_temp, - (s32)control_temp - (s32)current_temp); + control_temp - current_temp); devm_kfree(&tz->device, req_power); unlock: @@ -411,7 +411,7 @@ static int power_allocator_bind(struct thermal_zone_device *tz) { int ret; struct power_allocator_params *params; - unsigned long switch_on_temp, control_temp; + int switch_on_temp, control_temp; u32 temperature_threshold; if (!tz->tzp || !tz->tzp->sustainable_power) { @@ -476,7 +476,7 @@ static void power_allocator_unbind(struct thermal_zone_device *tz) static int power_allocator_throttle(struct thermal_zone_device *tz, int trip) { int ret; - unsigned long switch_on_temp, control_temp, current_temp; + int switch_on_temp, control_temp, current_temp; struct power_allocator_params *params = tz->governor_data; /* diff --git a/drivers/thermal/qcom-spmi-temp-alarm.c b/drivers/thermal/qcom-spmi-temp-alarm.c index c8d27b8fb9ec..b677aada5b52 100644 --- a/drivers/thermal/qcom-spmi-temp-alarm.c +++ b/drivers/thermal/qcom-spmi-temp-alarm.c @@ -117,7 +117,7 @@ static int qpnp_tm_update_temp_no_adc(struct qpnp_tm_chip *chip) return 0; } -static int qpnp_tm_get_temp(void *data, long *temp) +static int qpnp_tm_get_temp(void *data, int *temp) { struct qpnp_tm_chip *chip = data; int ret, mili_celsius; diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c index fe4e767018c4..5d4ae7d705e0 100644 --- a/drivers/thermal/rcar_thermal.c +++ b/drivers/thermal/rcar_thermal.c @@ -200,8 +200,7 @@ err_out_unlock: return ret; } -static int rcar_thermal_get_temp(struct thermal_zone_device *zone, - unsigned long *temp) +static int rcar_thermal_get_temp(struct thermal_zone_device *zone, int *temp) { struct rcar_thermal_priv *priv = rcar_zone_to_priv(zone); @@ -235,7 +234,7 @@ static int rcar_thermal_get_trip_type(struct thermal_zone_device *zone, } static int rcar_thermal_get_trip_temp(struct thermal_zone_device *zone, - int trip, unsigned long *temp) + int trip, int *temp) { struct rcar_thermal_priv *priv = rcar_zone_to_priv(zone); struct device *dev = rcar_priv_to_dev(priv); @@ -299,7 +298,7 @@ static void _rcar_thermal_irq_ctrl(struct rcar_thermal_priv *priv, int enable) static void rcar_thermal_work(struct work_struct *work) { struct rcar_thermal_priv *priv; - unsigned long cctemp, nctemp; + int cctemp, nctemp; priv = container_of(work, struct rcar_thermal_priv, work.work); diff --git a/drivers/thermal/rockchip_thermal.c b/drivers/thermal/rockchip_thermal.c index cd8f5f93b42c..c89ffb26a354 100644 --- a/drivers/thermal/rockchip_thermal.c +++ b/drivers/thermal/rockchip_thermal.c @@ -64,7 +64,7 @@ struct rockchip_tsadc_chip { void (*control)(void __iomem *reg, bool on); /* Per-sensor methods */ - int (*get_temp)(int chn, void __iomem *reg, long *temp); + int (*get_temp)(int chn, void __iomem *reg, int *temp); void (*set_tshut_temp)(int chn, void __iomem *reg, long temp); void (*set_tshut_mode)(int chn, void __iomem *reg, enum tshut_mode m); }; @@ -191,7 +191,7 @@ static u32 rk_tsadcv2_temp_to_code(long temp) return 0; } -static long rk_tsadcv2_code_to_temp(u32 code) +static int rk_tsadcv2_code_to_temp(u32 code) { unsigned int low = 0; unsigned int high = ARRAY_SIZE(v2_code_table) - 1; @@ -277,7 +277,7 @@ static void rk_tsadcv2_control(void __iomem *regs, bool enable) writel_relaxed(val, regs + TSADCV2_AUTO_CON); } -static int rk_tsadcv2_get_temp(int chn, void __iomem *regs, long *temp) +static int rk_tsadcv2_get_temp(int chn, void __iomem *regs, int *temp) { u32 val; @@ -366,7 +366,7 @@ static irqreturn_t rockchip_thermal_alarm_irq_thread(int irq, void *dev) return IRQ_HANDLED; } -static int rockchip_thermal_get_temp(void *_sensor, long *out_temp) +static int rockchip_thermal_get_temp(void *_sensor, int *out_temp) { struct rockchip_thermal_sensor *sensor = _sensor; struct rockchip_thermal_data *thermal = sensor->thermal; @@ -374,7 +374,7 @@ static int rockchip_thermal_get_temp(void *_sensor, long *out_temp) int retval; retval = tsadc->get_temp(sensor->id, thermal->regs, out_temp); - dev_dbg(&thermal->pdev->dev, "sensor %d - temp: %ld, retval: %d\n", + dev_dbg(&thermal->pdev->dev, "sensor %d - temp: %d, retval: %d\n", sensor->id, *out_temp, retval); return retval; diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c index 531f4b179871..9ec29a33aeea 100644 --- a/drivers/thermal/samsung/exynos_tmu.c +++ b/drivers/thermal/samsung/exynos_tmu.c @@ -207,8 +207,7 @@ struct exynos_tmu_data { int (*tmu_initialize)(struct platform_device *pdev); void (*tmu_control)(struct platform_device *pdev, bool on); int (*tmu_read)(struct exynos_tmu_data *data); - void (*tmu_set_emulation)(struct exynos_tmu_data *data, - unsigned long temp); + void (*tmu_set_emulation)(struct exynos_tmu_data *data, int temp); void (*tmu_clear_irqs)(struct exynos_tmu_data *data); }; @@ -216,7 +215,7 @@ static void exynos_report_trigger(struct exynos_tmu_data *p) { char data[10], *envp[] = { data, NULL }; struct thermal_zone_device *tz = p->tzd; - unsigned long temp; + int temp; unsigned int i; if (!tz) { @@ -517,7 +516,7 @@ static int exynos5433_tmu_initialize(struct platform_device *pdev) struct thermal_zone_device *tz = data->tzd; unsigned int status, trim_info; unsigned int rising_threshold = 0, falling_threshold = 0; - unsigned long temp, temp_hist; + int temp, temp_hist; int ret = 0, threshold_code, i, sensor_id, cal_type; status = readb(data->base + EXYNOS_TMU_REG_STATUS); @@ -610,7 +609,7 @@ static int exynos5440_tmu_initialize(struct platform_device *pdev) struct exynos_tmu_data *data = platform_get_drvdata(pdev); unsigned int trim_info = 0, con, rising_threshold; int ret = 0, threshold_code; - unsigned long crit_temp = 0; + int crit_temp = 0; /* * For exynos5440 soc triminfo value is swapped between TMU0 and @@ -663,7 +662,7 @@ static int exynos7_tmu_initialize(struct platform_device *pdev) unsigned int status, trim_info; unsigned int rising_threshold = 0, falling_threshold = 0; int ret = 0, threshold_code, i; - unsigned long temp, temp_hist; + int temp, temp_hist; unsigned int reg_off, bit_off; status = readb(data->base + EXYNOS_TMU_REG_STATUS); @@ -876,7 +875,7 @@ static void exynos7_tmu_control(struct platform_device *pdev, bool on) writel(con, data->base + EXYNOS_TMU_REG_CONTROL); } -static int exynos_get_temp(void *p, long *temp) +static int exynos_get_temp(void *p, int *temp) { struct exynos_tmu_data *data = p; @@ -896,7 +895,7 @@ static int exynos_get_temp(void *p, long *temp) #ifdef CONFIG_THERMAL_EMULATION static u32 get_emul_con_reg(struct exynos_tmu_data *data, unsigned int val, - unsigned long temp) + int temp) { if (temp) { temp /= MCELSIUS; @@ -926,7 +925,7 @@ static u32 get_emul_con_reg(struct exynos_tmu_data *data, unsigned int val, } static void exynos4412_tmu_set_emulation(struct exynos_tmu_data *data, - unsigned long temp) + int temp) { unsigned int val; u32 emul_con; @@ -946,7 +945,7 @@ static void exynos4412_tmu_set_emulation(struct exynos_tmu_data *data, } static void exynos5440_tmu_set_emulation(struct exynos_tmu_data *data, - unsigned long temp) + int temp) { unsigned int val; @@ -955,7 +954,7 @@ static void exynos5440_tmu_set_emulation(struct exynos_tmu_data *data, writel(val, data->base + EXYNOS5440_TMU_S0_7_DEBUG); } -static int exynos_tmu_set_emulation(void *drv_data, unsigned long temp) +static int exynos_tmu_set_emulation(void *drv_data, int temp) { struct exynos_tmu_data *data = drv_data; int ret = -EINVAL; @@ -978,7 +977,7 @@ out: #else #define exynos4412_tmu_set_emulation NULL #define exynos5440_tmu_set_emulation NULL -static int exynos_tmu_set_emulation(void *drv_data, unsigned long temp) +static int exynos_tmu_set_emulation(void *drv_data, int temp) { return -EINVAL; } #endif /* CONFIG_THERMAL_EMULATION */ diff --git a/drivers/thermal/spear_thermal.c b/drivers/thermal/spear_thermal.c index bddb71744a6c..534dd9136662 100644 --- a/drivers/thermal/spear_thermal.c +++ b/drivers/thermal/spear_thermal.c @@ -38,7 +38,7 @@ struct spear_thermal_dev { }; static inline int thermal_get_temp(struct thermal_zone_device *thermal, - unsigned long *temp) + int *temp) { struct spear_thermal_dev *stdev = thermal->devdata; diff --git a/drivers/thermal/st/st_thermal.c b/drivers/thermal/st/st_thermal.c index 76c515dd802b..44cbba99716a 100644 --- a/drivers/thermal/st/st_thermal.c +++ b/drivers/thermal/st/st_thermal.c @@ -111,8 +111,7 @@ static int st_thermal_calibration(struct st_thermal_sensor *sensor) } /* Callback to get temperature from HW*/ -static int st_thermal_get_temp(struct thermal_zone_device *th, - unsigned long *temperature) +static int st_thermal_get_temp(struct thermal_zone_device *th, int *temperature) { struct st_thermal_sensor *sensor = th->devdata; struct device *dev = sensor->dev; @@ -159,7 +158,7 @@ static int st_thermal_get_trip_type(struct thermal_zone_device *th, } static int st_thermal_get_trip_temp(struct thermal_zone_device *th, - int trip, unsigned long *temp) + int trip, int *temp) { struct st_thermal_sensor *sensor = th->devdata; struct device *dev = sensor->dev; diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c index 5a0f12d08e8b..2f9f7086ac3d 100644 --- a/drivers/thermal/step_wise.c +++ b/drivers/thermal/step_wise.c @@ -113,7 +113,7 @@ static void update_passive_instance(struct thermal_zone_device *tz, static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) { - long trip_temp; + int trip_temp; enum thermal_trip_type trip_type; enum thermal_trend trend; struct thermal_instance *instance; @@ -135,7 +135,7 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) trace_thermal_zone_trip(tz, trip, trip_type); } - dev_dbg(&tz->device, "Trip%d[type=%d,temp=%ld]:trend=%d,throttle=%d\n", + dev_dbg(&tz->device, "Trip%d[type=%d,temp=%d]:trend=%d,throttle=%d\n", trip, trip_type, trip_temp, trend, throttle); mutex_lock(&tz->lock); diff --git a/drivers/thermal/tegra_soctherm.c b/drivers/thermal/tegra_soctherm.c index 9197fc05c5cc..74ea5765938b 100644 --- a/drivers/thermal/tegra_soctherm.c +++ b/drivers/thermal/tegra_soctherm.c @@ -293,7 +293,7 @@ static int enable_tsensor(struct tegra_soctherm *tegra, * H denotes an addition of 0.5 Celsius and N denotes negation * of the final value. */ -static long translate_temp(u16 val) +static int translate_temp(u16 val) { long t; @@ -306,7 +306,7 @@ static long translate_temp(u16 val) return t; } -static int tegra_thermctl_get_temp(void *data, long *out_temp) +static int tegra_thermctl_get_temp(void *data, int *out_temp) { struct tegra_thermctl_zone *zone = data; u32 val; diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index c4700950e42e..387c4287fc74 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -426,7 +426,7 @@ static void handle_non_critical_trips(struct thermal_zone_device *tz, static void handle_critical_trips(struct thermal_zone_device *tz, int trip, enum thermal_trip_type trip_type) { - long trip_temp; + int trip_temp; tz->ops->get_trip_temp(tz, trip, &trip_temp); @@ -474,12 +474,12 @@ static void handle_thermal_trip(struct thermal_zone_device *tz, int trip) * * Return: On success returns 0, an error code otherwise */ -int thermal_zone_get_temp(struct thermal_zone_device *tz, unsigned long *temp) +int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp) { int ret = -EINVAL; #ifdef CONFIG_THERMAL_EMULATION int count; - unsigned long crit_temp = -1UL; + int crit_temp = INT_MAX; enum thermal_trip_type type; #endif @@ -516,8 +516,7 @@ EXPORT_SYMBOL_GPL(thermal_zone_get_temp); static void update_temperature(struct thermal_zone_device *tz) { - long temp; - int ret; + int temp, ret; ret = thermal_zone_get_temp(tz, &temp); if (ret) { @@ -577,15 +576,14 @@ static ssize_t temp_show(struct device *dev, struct device_attribute *attr, char *buf) { struct thermal_zone_device *tz = to_thermal_zone(dev); - long temperature; - int ret; + int temperature, ret; ret = thermal_zone_get_temp(tz, &temperature); if (ret) return ret; - return sprintf(buf, "%ld\n", temperature); + return sprintf(buf, "%d\n", temperature); } static ssize_t @@ -689,7 +687,7 @@ trip_point_temp_show(struct device *dev, struct device_attribute *attr, { struct thermal_zone_device *tz = to_thermal_zone(dev); int trip, ret; - long temperature; + int temperature; if (!tz->ops->get_trip_temp) return -EPERM; @@ -702,7 +700,7 @@ trip_point_temp_show(struct device *dev, struct device_attribute *attr, if (ret) return ret; - return sprintf(buf, "%ld\n", temperature); + return sprintf(buf, "%d\n", temperature); } static ssize_t @@ -711,7 +709,7 @@ trip_point_hyst_store(struct device *dev, struct device_attribute *attr, { struct thermal_zone_device *tz = to_thermal_zone(dev); int trip, ret; - unsigned long temperature; + int temperature; if (!tz->ops->set_trip_hyst) return -EPERM; @@ -719,7 +717,7 @@ trip_point_hyst_store(struct device *dev, struct device_attribute *attr, if (!sscanf(attr->attr.name, "trip_point_%d_hyst", &trip)) return -EINVAL; - if (kstrtoul(buf, 10, &temperature)) + if (kstrtoint(buf, 10, &temperature)) return -EINVAL; /* @@ -738,7 +736,7 @@ trip_point_hyst_show(struct device *dev, struct device_attribute *attr, { struct thermal_zone_device *tz = to_thermal_zone(dev); int trip, ret; - unsigned long temperature; + int temperature; if (!tz->ops->get_trip_hyst) return -EPERM; @@ -748,7 +746,7 @@ trip_point_hyst_show(struct device *dev, struct device_attribute *attr, ret = tz->ops->get_trip_hyst(tz, trip, &temperature); - return ret ? ret : sprintf(buf, "%ld\n", temperature); + return ret ? ret : sprintf(buf, "%d\n", temperature); } static ssize_t diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c index 1967bee4f076..06fd2ed9ef9d 100644 --- a/drivers/thermal/thermal_hwmon.c +++ b/drivers/thermal/thermal_hwmon.c @@ -69,7 +69,7 @@ static DEVICE_ATTR(name, 0444, name_show, NULL); static ssize_t temp_input_show(struct device *dev, struct device_attribute *attr, char *buf) { - long temperature; + int temperature; int ret; struct thermal_hwmon_attr *hwmon_attr = container_of(attr, struct thermal_hwmon_attr, attr); @@ -83,7 +83,7 @@ temp_input_show(struct device *dev, struct device_attribute *attr, char *buf) if (ret) return ret; - return sprintf(buf, "%ld\n", temperature); + return sprintf(buf, "%d\n", temperature); } static ssize_t @@ -95,14 +95,14 @@ temp_crit_show(struct device *dev, struct device_attribute *attr, char *buf) = container_of(hwmon_attr, struct thermal_hwmon_temp, temp_crit); struct thermal_zone_device *tz = temp->tz; - long temperature; + int temperature; int ret; ret = tz->ops->get_trip_temp(tz, 0, &temperature); if (ret) return ret; - return sprintf(buf, "%ld\n", temperature); + return sprintf(buf, "%d\n", temperature); } @@ -142,7 +142,7 @@ thermal_hwmon_lookup_temp(const struct thermal_hwmon_device *hwmon, static bool thermal_zone_crit_temp_valid(struct thermal_zone_device *tz) { - unsigned long temp; + int temp; return tz->ops->get_crit_temp && !tz->ops->get_crit_temp(tz, &temp); } diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c index c7c5b3779dac..b213a1222295 100644 --- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c +++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c @@ -76,14 +76,14 @@ static inline int ti_thermal_hotspot_temperature(int t, int s, int c) /* thermal zone ops */ /* Get temperature callback function for thermal zone */ -static inline int __ti_thermal_get_temp(void *devdata, long *temp) +static inline int __ti_thermal_get_temp(void *devdata, int *temp) { struct thermal_zone_device *pcb_tz = NULL; struct ti_thermal_data *data = devdata; struct ti_bandgap *bgp; const struct ti_temp_sensor *s; int ret, tmp, slope, constant; - unsigned long pcb_temp; + int pcb_temp; if (!data) return 0; @@ -119,7 +119,7 @@ static inline int __ti_thermal_get_temp(void *devdata, long *temp) } static inline int ti_thermal_get_temp(struct thermal_zone_device *thermal, - unsigned long *temp) + int *temp) { struct ti_thermal_data *data = thermal->devdata; @@ -229,7 +229,7 @@ static int ti_thermal_get_trip_type(struct thermal_zone_device *thermal, /* Get trip temperature callback functions for thermal zone */ static int ti_thermal_get_trip_temp(struct thermal_zone_device *thermal, - int trip, unsigned long *temp) + int trip, int *temp) { if (!ti_thermal_is_valid_trip(trip)) return -EINVAL; @@ -280,7 +280,7 @@ static int ti_thermal_get_trend(struct thermal_zone_device *thermal, /* Get critical temperature callback functions for thermal zone */ static int ti_thermal_get_crit_temp(struct thermal_zone_device *thermal, - unsigned long *temp) + int *temp) { /* shutdown zone */ return ti_thermal_get_trip_temp(thermal, OMAP_TRIP_NUMBER - 1, temp); diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c index 50d1d2cb091a..7fc919f7da4d 100644 --- a/drivers/thermal/x86_pkg_temp_thermal.c +++ b/drivers/thermal/x86_pkg_temp_thermal.c @@ -164,7 +164,7 @@ err_ret: return err; } -static int sys_get_curr_temp(struct thermal_zone_device *tzd, unsigned long *temp) +static int sys_get_curr_temp(struct thermal_zone_device *tzd, int *temp) { u32 eax, edx; struct phy_dev_entry *phy_dev_entry; @@ -175,7 +175,7 @@ static int sys_get_curr_temp(struct thermal_zone_device *tzd, unsigned long *tem if (eax & 0x80000000) { *temp = phy_dev_entry->tj_max - ((eax >> 16) & 0x7f) * 1000; - pr_debug("sys_get_curr_temp %ld\n", *temp); + pr_debug("sys_get_curr_temp %d\n", *temp); return 0; } @@ -183,7 +183,7 @@ static int sys_get_curr_temp(struct thermal_zone_device *tzd, unsigned long *tem } static int sys_get_trip_temp(struct thermal_zone_device *tzd, - int trip, unsigned long *temp) + int trip, int *temp) { u32 eax, edx; struct phy_dev_entry *phy_dev_entry; @@ -214,13 +214,13 @@ static int sys_get_trip_temp(struct thermal_zone_device *tzd, *temp = phy_dev_entry->tj_max - thres_reg_value * 1000; else *temp = 0; - pr_debug("sys_get_trip_temp %ld\n", *temp); + pr_debug("sys_get_trip_temp %d\n", *temp); return 0; } static int sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, - unsigned long temp) + int temp) { u32 l, h; struct phy_dev_entry *phy_dev_entry; diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 037e9df2f610..17292fee8686 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -92,23 +92,19 @@ struct thermal_zone_device_ops { struct thermal_cooling_device *); int (*unbind) (struct thermal_zone_device *, struct thermal_cooling_device *); - int (*get_temp) (struct thermal_zone_device *, unsigned long *); + int (*get_temp) (struct thermal_zone_device *, int *); int (*get_mode) (struct thermal_zone_device *, enum thermal_device_mode *); int (*set_mode) (struct thermal_zone_device *, enum thermal_device_mode); int (*get_trip_type) (struct thermal_zone_device *, int, enum thermal_trip_type *); - int (*get_trip_temp) (struct thermal_zone_device *, int, - unsigned long *); - int (*set_trip_temp) (struct thermal_zone_device *, int, - unsigned long); - int (*get_trip_hyst) (struct thermal_zone_device *, int, - unsigned long *); - int (*set_trip_hyst) (struct thermal_zone_device *, int, - unsigned long); - int (*get_crit_temp) (struct thermal_zone_device *, unsigned long *); - int (*set_emul_temp) (struct thermal_zone_device *, unsigned long); + int (*get_trip_temp) (struct thermal_zone_device *, int, int *); + int (*set_trip_temp) (struct thermal_zone_device *, int, int); + int (*get_trip_hyst) (struct thermal_zone_device *, int, int *); + int (*set_trip_hyst) (struct thermal_zone_device *, int, int); + int (*get_crit_temp) (struct thermal_zone_device *, int *); + int (*set_emul_temp) (struct thermal_zone_device *, int); int (*get_trend) (struct thermal_zone_device *, int, enum thermal_trend *); int (*notify) (struct thermal_zone_device *, int, @@ -332,9 +328,9 @@ struct thermal_genl_event { * temperature. */ struct thermal_zone_of_device_ops { - int (*get_temp)(void *, long *); + int (*get_temp)(void *, int *); int (*get_trend)(void *, long *); - int (*set_emul_temp)(void *, unsigned long); + int (*set_emul_temp)(void *, int); }; /** @@ -406,7 +402,7 @@ thermal_of_cooling_device_register(struct device_node *np, char *, void *, const struct thermal_cooling_device_ops *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); -int thermal_zone_get_temp(struct thermal_zone_device *tz, unsigned long *temp); +int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); int get_tz_trend(struct thermal_zone_device *, int); struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, @@ -457,7 +453,7 @@ static inline struct thermal_zone_device *thermal_zone_get_zone_by_name( const char *name) { return ERR_PTR(-ENODEV); } static inline int thermal_zone_get_temp( - struct thermal_zone_device *tz, unsigned long *temp) + struct thermal_zone_device *tz, int *temp) { return -ENODEV; } static inline int get_tz_trend(struct thermal_zone_device *tz, int trip) { return -ENODEV; } diff --git a/include/trace/events/thermal_power_allocator.h b/include/trace/events/thermal_power_allocator.h index 12e1321c4e0c..5afae8fe3795 100644 --- a/include/trace/events/thermal_power_allocator.h +++ b/include/trace/events/thermal_power_allocator.h @@ -11,7 +11,7 @@ TRACE_EVENT(thermal_power_allocator, u32 total_req_power, u32 *granted_power, u32 total_granted_power, size_t num_actors, u32 power_range, u32 max_allocatable_power, - unsigned long current_temp, s32 delta_temp), + int current_temp, s32 delta_temp), TP_ARGS(tz, req_power, total_req_power, granted_power, total_granted_power, num_actors, power_range, max_allocatable_power, current_temp, delta_temp), @@ -24,7 +24,7 @@ TRACE_EVENT(thermal_power_allocator, __field(size_t, num_actors ) __field(u32, power_range ) __field(u32, max_allocatable_power ) - __field(unsigned long, current_temp ) + __field(int, current_temp ) __field(s32, delta_temp ) ), TP_fast_assign( @@ -42,7 +42,7 @@ TRACE_EVENT(thermal_power_allocator, __entry->delta_temp = delta_temp; ), - TP_printk("thermal_zone_id=%d req_power={%s} total_req_power=%u granted_power={%s} total_granted_power=%u power_range=%u max_allocatable_power=%u current_temperature=%lu delta_temperature=%d", + TP_printk("thermal_zone_id=%d req_power={%s} total_req_power=%u granted_power={%s} total_granted_power=%u power_range=%u max_allocatable_power=%u current_temperature=%d delta_temperature=%d", __entry->tz_id, __print_array(__get_dynamic_array(req_power), __entry->num_actors, 4), -- cgit v1.2.3 From 8025e5ddf9c1cac0e632dad49a63abf7848b78cb Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 13 Jul 2015 11:55:44 -0300 Subject: [media] mm: Provide new get_vaddr_frames() helper Provide new function get_vaddr_frames(). This function maps virtual addresses from given start and fills given array with page frame numbers of the corresponding pages. If given start belongs to a normal vma, the function grabs reference to each of the pages to pin them in memory. If start belongs to VM_IO | VM_PFNMAP vma, we don't touch page structures. Caller must make sure pfns aren't reused for anything else while he is using them. This function is created for various drivers to simplify handling of their buffers. Signed-off-by: Jan Kara Acked-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Andrew Morton Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/mm.h | 44 ++++++++++ mm/Kconfig | 3 + mm/Makefile | 1 + mm/frame_vector.c | 230 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 278 insertions(+) create mode 100644 mm/frame_vector.c (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2e872f92dbac..79ad29a8a60a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -20,6 +20,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -1198,6 +1199,49 @@ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, int write, int force, struct page **pages); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); + +/* Container for pinned pfns / pages */ +struct frame_vector { + unsigned int nr_allocated; /* Number of frames we have space for */ + unsigned int nr_frames; /* Number of frames stored in ptrs array */ + bool got_ref; /* Did we pin pages by getting page ref? */ + bool is_pfns; /* Does array contain pages or pfns? */ + void *ptrs[0]; /* Array of pinned pfns / pages. Use + * pfns_vector_pages() or pfns_vector_pfns() + * for access */ +}; + +struct frame_vector *frame_vector_create(unsigned int nr_frames); +void frame_vector_destroy(struct frame_vector *vec); +int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, + bool write, bool force, struct frame_vector *vec); +void put_vaddr_frames(struct frame_vector *vec); +int frame_vector_to_pages(struct frame_vector *vec); +void frame_vector_to_pfns(struct frame_vector *vec); + +static inline unsigned int frame_vector_count(struct frame_vector *vec) +{ + return vec->nr_frames; +} + +static inline struct page **frame_vector_pages(struct frame_vector *vec) +{ + if (vec->is_pfns) { + int err = frame_vector_to_pages(vec); + + if (err) + return ERR_PTR(err); + } + return (struct page **)(vec->ptrs); +} + +static inline unsigned long *frame_vector_pfns(struct frame_vector *vec) +{ + if (!vec->is_pfns) + frame_vector_to_pfns(vec); + return (unsigned long *)(vec->ptrs); +} + struct kvec; int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); diff --git a/mm/Kconfig b/mm/Kconfig index e79de2bd12cd..7f146dd32fc5 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -654,3 +654,6 @@ config DEFERRED_STRUCT_PAGE_INIT when kswapd starts. This has a potential performance impact on processes running early in the lifetime of the systemm until kswapd finishes the initialisation. + +config FRAME_VECTOR + bool diff --git a/mm/Makefile b/mm/Makefile index 98c4eaeabdcb..be5d5c866305 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -78,3 +78,4 @@ obj-$(CONFIG_CMA) += cma.o obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o +obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o diff --git a/mm/frame_vector.c b/mm/frame_vector.c new file mode 100644 index 000000000000..cdabcb93c6a6 --- /dev/null +++ b/mm/frame_vector.c @@ -0,0 +1,230 @@ +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * get_vaddr_frames() - map virtual addresses to pfns + * @start: starting user address + * @nr_frames: number of pages / pfns from start to map + * @write: whether pages will be written to by the caller + * @force: whether to force write access even if user mapping is + * readonly. See description of the same argument of + get_user_pages(). + * @vec: structure which receives pages / pfns of the addresses mapped. + * It should have space for at least nr_frames entries. + * + * This function maps virtual addresses from @start and fills @vec structure + * with page frame numbers or page pointers to corresponding pages (choice + * depends on the type of the vma underlying the virtual address). If @start + * belongs to a normal vma, the function grabs reference to each of the pages + * to pin them in memory. If @start belongs to VM_IO | VM_PFNMAP vma, we don't + * touch page structures and the caller must make sure pfns aren't reused for + * anything else while he is using them. + * + * The function returns number of pages mapped which may be less than + * @nr_frames. In particular we stop mapping if there are more vmas of + * different type underlying the specified range of virtual addresses. + * When the function isn't able to map a single page, it returns error. + * + * This function takes care of grabbing mmap_sem as necessary. + */ +int get_vaddr_frames(unsigned long start, unsigned int nr_frames, + bool write, bool force, struct frame_vector *vec) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + int ret = 0; + int err; + int locked; + + if (nr_frames == 0) + return 0; + + if (WARN_ON_ONCE(nr_frames > vec->nr_allocated)) + nr_frames = vec->nr_allocated; + + down_read(&mm->mmap_sem); + locked = 1; + vma = find_vma_intersection(mm, start, start + 1); + if (!vma) { + ret = -EFAULT; + goto out; + } + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) { + vec->got_ref = true; + vec->is_pfns = false; + ret = get_user_pages_locked(current, mm, start, nr_frames, + write, force, (struct page **)(vec->ptrs), &locked); + goto out; + } + + vec->got_ref = false; + vec->is_pfns = true; + do { + unsigned long *nums = frame_vector_pfns(vec); + + while (ret < nr_frames && start + PAGE_SIZE <= vma->vm_end) { + err = follow_pfn(vma, start, &nums[ret]); + if (err) { + if (ret == 0) + ret = err; + goto out; + } + start += PAGE_SIZE; + ret++; + } + /* + * We stop if we have enough pages or if VMA doesn't completely + * cover the tail page. + */ + if (ret >= nr_frames || start < vma->vm_end) + break; + vma = find_vma_intersection(mm, start, start + 1); + } while (vma && vma->vm_flags & (VM_IO | VM_PFNMAP)); +out: + if (locked) + up_read(&mm->mmap_sem); + if (!ret) + ret = -EFAULT; + if (ret > 0) + vec->nr_frames = ret; + return ret; +} +EXPORT_SYMBOL(get_vaddr_frames); + +/** + * put_vaddr_frames() - drop references to pages if get_vaddr_frames() acquired + * them + * @vec: frame vector to put + * + * Drop references to pages if get_vaddr_frames() acquired them. We also + * invalidate the frame vector so that it is prepared for the next call into + * get_vaddr_frames(). + */ +void put_vaddr_frames(struct frame_vector *vec) +{ + int i; + struct page **pages; + + if (!vec->got_ref) + goto out; + pages = frame_vector_pages(vec); + /* + * frame_vector_pages() might needed to do a conversion when + * get_vaddr_frames() got pages but vec was later converted to pfns. + * But it shouldn't really fail to convert pfns back... + */ + if (WARN_ON(IS_ERR(pages))) + goto out; + for (i = 0; i < vec->nr_frames; i++) + put_page(pages[i]); + vec->got_ref = false; +out: + vec->nr_frames = 0; +} +EXPORT_SYMBOL(put_vaddr_frames); + +/** + * frame_vector_to_pages - convert frame vector to contain page pointers + * @vec: frame vector to convert + * + * Convert @vec to contain array of page pointers. If the conversion is + * successful, return 0. Otherwise return an error. Note that we do not grab + * page references for the page structures. + */ +int frame_vector_to_pages(struct frame_vector *vec) +{ + int i; + unsigned long *nums; + struct page **pages; + + if (!vec->is_pfns) + return 0; + nums = frame_vector_pfns(vec); + for (i = 0; i < vec->nr_frames; i++) + if (!pfn_valid(nums[i])) + return -EINVAL; + pages = (struct page **)nums; + for (i = 0; i < vec->nr_frames; i++) + pages[i] = pfn_to_page(nums[i]); + vec->is_pfns = false; + return 0; +} +EXPORT_SYMBOL(frame_vector_to_pages); + +/** + * frame_vector_to_pfns - convert frame vector to contain pfns + * @vec: frame vector to convert + * + * Convert @vec to contain array of pfns. + */ +void frame_vector_to_pfns(struct frame_vector *vec) +{ + int i; + unsigned long *nums; + struct page **pages; + + if (vec->is_pfns) + return; + pages = (struct page **)(vec->ptrs); + nums = (unsigned long *)pages; + for (i = 0; i < vec->nr_frames; i++) + nums[i] = page_to_pfn(pages[i]); + vec->is_pfns = true; +} +EXPORT_SYMBOL(frame_vector_to_pfns); + +/** + * frame_vector_create() - allocate & initialize structure for pinned pfns + * @nr_frames: number of pfns slots we should reserve + * + * Allocate and initialize struct pinned_pfns to be able to hold @nr_pfns + * pfns. + */ +struct frame_vector *frame_vector_create(unsigned int nr_frames) +{ + struct frame_vector *vec; + int size = sizeof(struct frame_vector) + sizeof(void *) * nr_frames; + + if (WARN_ON_ONCE(nr_frames == 0)) + return NULL; + /* + * This is absurdly high. It's here just to avoid strange effects when + * arithmetics overflows. + */ + if (WARN_ON_ONCE(nr_frames > INT_MAX / sizeof(void *) / 2)) + return NULL; + /* + * Avoid higher order allocations, use vmalloc instead. It should + * be rare anyway. + */ + if (size <= PAGE_SIZE) + vec = kmalloc(size, GFP_KERNEL); + else + vec = vmalloc(size); + if (!vec) + return NULL; + vec->nr_allocated = nr_frames; + vec->nr_frames = 0; + return vec; +} +EXPORT_SYMBOL(frame_vector_create); + +/** + * frame_vector_destroy() - free memory allocated to carry frame vector + * @vec: Frame vector to free + * + * Free structure allocated by frame_vector_create() to carry frames. + */ +void frame_vector_destroy(struct frame_vector *vec) +{ + /* Make sure put_vaddr_frames() got called properly... */ + VM_BUG_ON(vec->nr_frames > 0); + kvfree(vec); +} +EXPORT_SYMBOL(frame_vector_destroy); -- cgit v1.2.3 From 21fb0cb7ec65a40b9f5f7cda59eba0eb2ae76473 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 13 Jul 2015 11:55:46 -0300 Subject: [media] vb2: Provide helpers for mapping virtual addresses Provide simple helper functions to map virtual address range into an array of pfns / pages. Tested-by: Marek Szyprowski Signed-off-by: Jan Kara Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/Kconfig | 1 + drivers/media/v4l2-core/videobuf2-memops.c | 58 ++++++++++++++++++++++++++++++ include/media/videobuf2-memops.h | 5 +++ 3 files changed, 64 insertions(+) (limited to 'include') diff --git a/drivers/media/v4l2-core/Kconfig b/drivers/media/v4l2-core/Kconfig index b4b022933e29..82876a67f144 100644 --- a/drivers/media/v4l2-core/Kconfig +++ b/drivers/media/v4l2-core/Kconfig @@ -84,6 +84,7 @@ config VIDEOBUF2_CORE config VIDEOBUF2_MEMOPS tristate + select FRAME_VECTOR config VIDEOBUF2_DMA_CONTIG tristate diff --git a/drivers/media/v4l2-core/videobuf2-memops.c b/drivers/media/v4l2-core/videobuf2-memops.c index 81c1ad8b2cf1..0ec186d41b9b 100644 --- a/drivers/media/v4l2-core/videobuf2-memops.c +++ b/drivers/media/v4l2-core/videobuf2-memops.c @@ -136,6 +136,64 @@ int vb2_get_contig_userptr(unsigned long vaddr, unsigned long size, } EXPORT_SYMBOL_GPL(vb2_get_contig_userptr); +/** + * vb2_create_framevec() - map virtual addresses to pfns + * @start: Virtual user address where we start mapping + * @length: Length of a range to map + * @write: Should we map for writing into the area + * + * This function allocates and fills in a vector with pfns corresponding to + * virtual address range passed in arguments. If pfns have corresponding pages, + * page references are also grabbed to pin pages in memory. The function + * returns pointer to the vector on success and error pointer in case of + * failure. Returned vector needs to be freed via vb2_destroy_pfnvec(). + */ +struct frame_vector *vb2_create_framevec(unsigned long start, + unsigned long length, + bool write) +{ + int ret; + unsigned long first, last; + unsigned long nr; + struct frame_vector *vec; + + first = start >> PAGE_SHIFT; + last = (start + length - 1) >> PAGE_SHIFT; + nr = last - first + 1; + vec = frame_vector_create(nr); + if (!vec) + return ERR_PTR(-ENOMEM); + ret = get_vaddr_frames(start, nr, write, 1, vec); + if (ret < 0) + goto out_destroy; + /* We accept only complete set of PFNs */ + if (ret != nr) { + ret = -EFAULT; + goto out_release; + } + return vec; +out_release: + put_vaddr_frames(vec); +out_destroy: + frame_vector_destroy(vec); + return ERR_PTR(ret); +} +EXPORT_SYMBOL(vb2_create_framevec); + +/** + * vb2_destroy_framevec() - release vector of mapped pfns + * @vec: vector of pfns / pages to release + * + * This releases references to all pages in the vector @vec (if corresponding + * pfns are backed by pages) and frees the passed vector. + */ +void vb2_destroy_framevec(struct frame_vector *vec) +{ + put_vaddr_frames(vec); + frame_vector_destroy(vec); +} +EXPORT_SYMBOL(vb2_destroy_framevec); + /** * vb2_common_vm_open() - increase refcount of the vma * @vma: virtual memory region for the mapping diff --git a/include/media/videobuf2-memops.h b/include/media/videobuf2-memops.h index f05444ca8c0c..2f0564ff5f31 100644 --- a/include/media/videobuf2-memops.h +++ b/include/media/videobuf2-memops.h @@ -15,6 +15,7 @@ #define _MEDIA_VIDEOBUF2_MEMOPS_H #include +#include /** * vb2_vmarea_handler - common vma refcount tracking handler @@ -36,5 +37,9 @@ int vb2_get_contig_userptr(unsigned long vaddr, unsigned long size, struct vm_area_struct *vb2_get_vma(struct vm_area_struct *vma); void vb2_put_vma(struct vm_area_struct *vma); +struct frame_vector *vb2_create_framevec(unsigned long start, + unsigned long length, + bool write); +void vb2_destroy_framevec(struct frame_vector *vec); #endif -- cgit v1.2.3 From 6690c8c78c745239bb1f22b23f3889a0a14c249b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 13 Jul 2015 11:55:50 -0300 Subject: [media] media: vb2: Remove unused functions Conversion to the use of pinned pfns made some functions unused. Remove them. Also there's no need to lock mmap_sem in __buf_prepare() anymore. Tested-by: Marek Szyprowski Signed-off-by: Jan Kara Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/videobuf2-memops.c | 114 ----------------------------- include/media/videobuf2-memops.h | 6 -- 2 files changed, 120 deletions(-) (limited to 'include') diff --git a/drivers/media/v4l2-core/videobuf2-memops.c b/drivers/media/v4l2-core/videobuf2-memops.c index 0ec186d41b9b..48c6a49c4928 100644 --- a/drivers/media/v4l2-core/videobuf2-memops.c +++ b/drivers/media/v4l2-core/videobuf2-memops.c @@ -22,120 +22,6 @@ #include #include -/** - * vb2_get_vma() - acquire and lock the virtual memory area - * @vma: given virtual memory area - * - * This function attempts to acquire an area mapped in the userspace for - * the duration of a hardware operation. The area is "locked" by performing - * the same set of operation that are done when process calls fork() and - * memory areas are duplicated. - * - * Returns a copy of a virtual memory region on success or NULL. - */ -struct vm_area_struct *vb2_get_vma(struct vm_area_struct *vma) -{ - struct vm_area_struct *vma_copy; - - vma_copy = kmalloc(sizeof(*vma_copy), GFP_KERNEL); - if (vma_copy == NULL) - return NULL; - - if (vma->vm_ops && vma->vm_ops->open) - vma->vm_ops->open(vma); - - if (vma->vm_file) - get_file(vma->vm_file); - - memcpy(vma_copy, vma, sizeof(*vma)); - - vma_copy->vm_mm = NULL; - vma_copy->vm_next = NULL; - vma_copy->vm_prev = NULL; - - return vma_copy; -} -EXPORT_SYMBOL_GPL(vb2_get_vma); - -/** - * vb2_put_userptr() - release a userspace virtual memory area - * @vma: virtual memory region associated with the area to be released - * - * This function releases the previously acquired memory area after a hardware - * operation. - */ -void vb2_put_vma(struct vm_area_struct *vma) -{ - if (!vma) - return; - - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); - - if (vma->vm_file) - fput(vma->vm_file); - - kfree(vma); -} -EXPORT_SYMBOL_GPL(vb2_put_vma); - -/** - * vb2_get_contig_userptr() - lock physically contiguous userspace mapped memory - * @vaddr: starting virtual address of the area to be verified - * @size: size of the area - * @res_paddr: will return physical address for the given vaddr - * @res_vma: will return locked copy of struct vm_area for the given area - * - * This function will go through memory area of size @size mapped at @vaddr and - * verify that the underlying physical pages are contiguous. If they are - * contiguous the virtual memory area is locked and a @res_vma is filled with - * the copy and @res_pa set to the physical address of the buffer. - * - * Returns 0 on success. - */ -int vb2_get_contig_userptr(unsigned long vaddr, unsigned long size, - struct vm_area_struct **res_vma, dma_addr_t *res_pa) -{ - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - unsigned long offset, start, end; - unsigned long this_pfn, prev_pfn; - dma_addr_t pa = 0; - - start = vaddr; - offset = start & ~PAGE_MASK; - end = start + size; - - vma = find_vma(mm, start); - - if (vma == NULL || vma->vm_end < end) - return -EFAULT; - - for (prev_pfn = 0; start < end; start += PAGE_SIZE) { - int ret = follow_pfn(vma, start, &this_pfn); - if (ret) - return ret; - - if (prev_pfn == 0) - pa = this_pfn << PAGE_SHIFT; - else if (this_pfn != prev_pfn + 1) - return -EFAULT; - - prev_pfn = this_pfn; - } - - /* - * Memory is contigous, lock vma and return to the caller - */ - *res_vma = vb2_get_vma(vma); - if (*res_vma == NULL) - return -ENOMEM; - - *res_pa = pa + offset; - return 0; -} -EXPORT_SYMBOL_GPL(vb2_get_contig_userptr); - /** * vb2_create_framevec() - map virtual addresses to pfns * @start: Virtual user address where we start mapping diff --git a/include/media/videobuf2-memops.h b/include/media/videobuf2-memops.h index 2f0564ff5f31..830b5239fd8b 100644 --- a/include/media/videobuf2-memops.h +++ b/include/media/videobuf2-memops.h @@ -31,12 +31,6 @@ struct vb2_vmarea_handler { extern const struct vm_operations_struct vb2_common_vm_ops; -int vb2_get_contig_userptr(unsigned long vaddr, unsigned long size, - struct vm_area_struct **res_vma, dma_addr_t *res_pa); - -struct vm_area_struct *vb2_get_vma(struct vm_area_struct *vma); -void vb2_put_vma(struct vm_area_struct *vma); - struct frame_vector *vb2_create_framevec(unsigned long start, unsigned long length, bool write); -- cgit v1.2.3 From 76c28f1fcfeb42b47f798fe498351ee1d60086ae Mon Sep 17 00:00:00 2001 From: Andy Grover Date: Mon, 24 Aug 2015 10:26:03 -0700 Subject: target/iscsi: Fix np_ip bracket issue by removing np_ip Revert commit 1997e6259, which causes double brackets on ipv6 inaddr_any addresses. Since we have np_sockaddr, if we need a textual representation we can use "%pISc". Change iscsit_add_network_portal() and iscsit_add_np() signatures to remove *ip_str parameter. Fix and extend some comments earlier in the function. Tested to work for :: and ::1 via iscsiadm, previously :: failed, see https://bugzilla.redhat.com/show_bug.cgi?id=1249107 . CC: stable@vger.kernel.org Signed-off-by: Andy Grover Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target.c | 33 ++++++++++++++-------------- drivers/target/iscsi/iscsi_target.h | 2 +- drivers/target/iscsi/iscsi_target_configfs.c | 14 ++++++------ drivers/target/iscsi/iscsi_target_login.c | 8 +++---- drivers/target/iscsi/iscsi_target_tpg.c | 15 ++++++------- drivers/target/iscsi/iscsi_target_tpg.h | 2 +- include/target/iscsi/iscsi_target_core.h | 1 - 7 files changed, 36 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index e55f49c7c847..d75eeb5ce13a 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -341,7 +341,6 @@ static struct iscsi_np *iscsit_get_np( struct iscsi_np *iscsit_add_np( struct __kernel_sockaddr_storage *sockaddr, - char *ip_str, int network_transport) { struct sockaddr_in *sock_in; @@ -370,11 +369,9 @@ struct iscsi_np *iscsit_add_np( np->np_flags |= NPF_IP_NETWORK; if (sockaddr->ss_family == AF_INET6) { sock_in6 = (struct sockaddr_in6 *)sockaddr; - snprintf(np->np_ip, IPV6_ADDRESS_SPACE, "%s", ip_str); np->np_port = ntohs(sock_in6->sin6_port); } else { sock_in = (struct sockaddr_in *)sockaddr; - sprintf(np->np_ip, "%s", ip_str); np->np_port = ntohs(sock_in->sin_port); } @@ -411,8 +408,8 @@ struct iscsi_np *iscsit_add_np( list_add_tail(&np->np_list, &g_np_list); mutex_unlock(&np_lock); - pr_debug("CORE[0] - Added Network Portal: %s:%hu on %s\n", - np->np_ip, np->np_port, np->np_transport->name); + pr_debug("CORE[0] - Added Network Portal: %pISc:%hu on %s\n", + &np->np_sockaddr, np->np_port, np->np_transport->name); return np; } @@ -481,8 +478,8 @@ int iscsit_del_np(struct iscsi_np *np) list_del(&np->np_list); mutex_unlock(&np_lock); - pr_debug("CORE[0] - Removed Network Portal: %s:%hu on %s\n", - np->np_ip, np->np_port, np->np_transport->name); + pr_debug("CORE[0] - Removed Network Portal: %pISc:%hu on %s\n", + &np->np_sockaddr, np->np_port, np->np_transport->name); iscsit_put_transport(np->np_transport); kfree(np); @@ -3463,7 +3460,6 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd, tpg_np_list) { struct iscsi_np *np = tpg_np->tpg_np; bool inaddr_any = iscsit_check_inaddr_any(np); - char *fmt_str; if (np->np_network_transport != network_transport) continue; @@ -3491,15 +3487,18 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd, } } - if (np->np_sockaddr.ss_family == AF_INET6) - fmt_str = "TargetAddress=[%s]:%hu,%hu"; - else - fmt_str = "TargetAddress=%s:%hu,%hu"; - - len = sprintf(buf, fmt_str, - inaddr_any ? conn->local_ip : np->np_ip, - np->np_port, - tpg->tpgt); + if (inaddr_any) { + len = sprintf(buf, "TargetAddress=" + "%s:%hu,%hu", + conn->local_ip, + np->np_port, + tpg->tpgt); + } else { + len = sprintf(buf, "TargetAddress=" + "%pISpc,%hu", + &np->np_sockaddr, + tpg->tpgt); + } len += 1; if ((len + payload_len) > buffer_len) { diff --git a/drivers/target/iscsi/iscsi_target.h b/drivers/target/iscsi/iscsi_target.h index 7d0f9c00d9c2..d294f030a097 100644 --- a/drivers/target/iscsi/iscsi_target.h +++ b/drivers/target/iscsi/iscsi_target.h @@ -13,7 +13,7 @@ extern int iscsit_deaccess_np(struct iscsi_np *, struct iscsi_portal_group *, extern bool iscsit_check_np_match(struct __kernel_sockaddr_storage *, struct iscsi_np *, int); extern struct iscsi_np *iscsit_add_np(struct __kernel_sockaddr_storage *, - char *, int); + int); extern int iscsit_reset_np_thread(struct iscsi_np *, struct iscsi_tpg_np *, struct iscsi_portal_group *, bool); extern int iscsit_del_np(struct iscsi_np *); diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 48f708bc101d..ad6a889dadc0 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -99,7 +99,7 @@ static ssize_t lio_target_np_store_sctp( * Use existing np->np_sockaddr for SCTP network portal reference */ tpg_np_sctp = iscsit_tpg_add_network_portal(tpg, &np->np_sockaddr, - np->np_ip, tpg_np, ISCSI_SCTP_TCP); + tpg_np, ISCSI_SCTP_TCP); if (!tpg_np_sctp || IS_ERR(tpg_np_sctp)) goto out; } else { @@ -177,7 +177,7 @@ static ssize_t lio_target_np_store_iser( } tpg_np_iser = iscsit_tpg_add_network_portal(tpg, &np->np_sockaddr, - np->np_ip, tpg_np, ISCSI_INFINIBAND); + tpg_np, ISCSI_INFINIBAND); if (IS_ERR(tpg_np_iser)) { rc = PTR_ERR(tpg_np_iser); goto out; @@ -248,8 +248,8 @@ static struct se_tpg_np *lio_target_call_addnptotpg( return ERR_PTR(-EINVAL); } str++; /* Skip over leading "[" */ - *str2 = '\0'; /* Terminate the IPv6 address */ - str2++; /* Skip over the "]" */ + *str2 = '\0'; /* Terminate the unbracketed IPv6 address */ + str2++; /* Skip over the \0 */ port_str = strstr(str2, ":"); if (!port_str) { pr_err("Unable to locate \":port\"" @@ -316,7 +316,7 @@ static struct se_tpg_np *lio_target_call_addnptotpg( * sys/kernel/config/iscsi/$IQN/$TPG/np/$IP:$PORT/ * */ - tpg_np = iscsit_tpg_add_network_portal(tpg, &sockaddr, str, NULL, + tpg_np = iscsit_tpg_add_network_portal(tpg, &sockaddr, NULL, ISCSI_TCP); if (IS_ERR(tpg_np)) { iscsit_put_tpg(tpg); @@ -344,8 +344,8 @@ static void lio_target_call_delnpfromtpg( se_tpg = &tpg->tpg_se_tpg; pr_debug("LIO_Target_ConfigFS: DEREGISTER -> %s TPGT: %hu" - " PORTAL: %s:%hu\n", config_item_name(&se_tpg->se_tpg_wwn->wwn_group.cg_item), - tpg->tpgt, tpg_np->tpg_np->np_ip, tpg_np->tpg_np->np_port); + " PORTAL: %pISc:%hu\n", config_item_name(&se_tpg->se_tpg_wwn->wwn_group.cg_item), + tpg->tpgt, &tpg_np->tpg_np->np_sockaddr, tpg_np->tpg_np->np_port); ret = iscsit_tpg_del_network_portal(tpg, tpg_np); if (ret < 0) diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index bd192f88e1e6..88e0b97e8ea6 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -823,8 +823,8 @@ static void iscsi_handle_login_thread_timeout(unsigned long data) struct iscsi_np *np = (struct iscsi_np *) data; spin_lock_bh(&np->np_thread_lock); - pr_err("iSCSI Login timeout on Network Portal %s:%hu\n", - np->np_ip, np->np_port); + pr_err("iSCSI Login timeout on Network Portal %pISc:%hu\n", + &np->np_sockaddr, np->np_port); if (np->np_login_timer_flags & ISCSI_TF_STOP) { spin_unlock_bh(&np->np_thread_lock); @@ -1302,8 +1302,8 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) spin_lock_bh(&np->np_thread_lock); if (np->np_thread_state != ISCSI_NP_THREAD_ACTIVE) { spin_unlock_bh(&np->np_thread_lock); - pr_err("iSCSI Network Portal on %s:%hu currently not" - " active.\n", np->np_ip, np->np_port); + pr_err("iSCSI Network Portal on %pISc:%hu currently not" + " active.\n", &np->np_sockaddr, np->np_port); iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, ISCSI_LOGIN_STATUS_SVC_UNAVAILABLE); goto new_sess_out; diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index 8262a853e888..31007cb4c877 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -461,7 +461,6 @@ static bool iscsit_tpg_check_network_portal( struct iscsi_tpg_np *iscsit_tpg_add_network_portal( struct iscsi_portal_group *tpg, struct __kernel_sockaddr_storage *sockaddr, - char *ip_str, struct iscsi_tpg_np *tpg_np_parent, int network_transport) { @@ -471,8 +470,8 @@ struct iscsi_tpg_np *iscsit_tpg_add_network_portal( if (!tpg_np_parent) { if (iscsit_tpg_check_network_portal(tpg->tpg_tiqn, sockaddr, network_transport)) { - pr_err("Network Portal: %s already exists on a" - " different TPG on %s\n", ip_str, + pr_err("Network Portal: %pISc already exists on a" + " different TPG on %s\n", sockaddr, tpg->tpg_tiqn->tiqn); return ERR_PTR(-EEXIST); } @@ -485,7 +484,7 @@ struct iscsi_tpg_np *iscsit_tpg_add_network_portal( return ERR_PTR(-ENOMEM); } - np = iscsit_add_np(sockaddr, ip_str, network_transport); + np = iscsit_add_np(sockaddr, network_transport); if (IS_ERR(np)) { kfree(tpg_np); return ERR_CAST(np); @@ -515,8 +514,8 @@ struct iscsi_tpg_np *iscsit_tpg_add_network_portal( spin_unlock(&tpg_np_parent->tpg_np_parent_lock); } - pr_debug("CORE[%s] - Added Network Portal: %s:%hu,%hu on %s\n", - tpg->tpg_tiqn->tiqn, np->np_ip, np->np_port, tpg->tpgt, + pr_debug("CORE[%s] - Added Network Portal: %pISc:%hu,%hu on %s\n", + tpg->tpg_tiqn->tiqn, &np->np_sockaddr, np->np_port, tpg->tpgt, np->np_transport->name); return tpg_np; @@ -529,8 +528,8 @@ static int iscsit_tpg_release_np( { iscsit_clear_tpg_np_login_thread(tpg_np, tpg, true); - pr_debug("CORE[%s] - Removed Network Portal: %s:%hu,%hu on %s\n", - tpg->tpg_tiqn->tiqn, np->np_ip, np->np_port, tpg->tpgt, + pr_debug("CORE[%s] - Removed Network Portal: %pISc:%hu,%hu on %s\n", + tpg->tpg_tiqn->tiqn, &np->np_sockaddr, np->np_port, tpg->tpgt, np->np_transport->name); tpg_np->tpg_np = NULL; diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h index a2790fd8f7da..1c0b1d6605cf 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.h +++ b/drivers/target/iscsi/iscsi_target_tpg.h @@ -22,7 +22,7 @@ extern struct iscsi_node_attrib *iscsit_tpg_get_node_attrib(struct iscsi_session extern void iscsit_tpg_del_external_nps(struct iscsi_tpg_np *); extern struct iscsi_tpg_np *iscsit_tpg_locate_child_np(struct iscsi_tpg_np *, int); extern struct iscsi_tpg_np *iscsit_tpg_add_network_portal(struct iscsi_portal_group *, - struct __kernel_sockaddr_storage *, char *, struct iscsi_tpg_np *, + struct __kernel_sockaddr_storage *, struct iscsi_tpg_np *, int); extern int iscsit_tpg_del_network_portal(struct iscsi_portal_group *, struct iscsi_tpg_np *); diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index d4616ef12e04..1051d0c40ddd 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -778,7 +778,6 @@ struct iscsi_np { enum iscsi_timer_flags_table np_login_timer_flags; u32 np_exports; enum np_flags_table np_flags; - unsigned char np_ip[IPV6_ADDRESS_SPACE]; u16 np_port; spinlock_t np_thread_lock; struct completion np_restart_comp; -- cgit v1.2.3 From 69d755747d31c07a416064f251c2f408938fb67a Mon Sep 17 00:00:00 2001 From: Andy Grover Date: Mon, 24 Aug 2015 10:26:04 -0700 Subject: target/iscsi: Keep local_ip as the actual sockaddr This is a more natural format that lets us format it with the appropriate printk specifier as needed. This also lets us handle v4-mapped ipv6 addresses a little more nicely, by storing the addr as an actual v4 sockaddr in conn->local_sockaddr. Finally, we no longer need to maintain variables for port, since this is contained in sockaddr. Remove iscsi_np.np_port and iscsi_conn.local_port. Signed-off-by: Andy Grover Signed-off-by: Nicholas Bellinger --- drivers/infiniband/ulp/isert/ib_isert.c | 8 ++--- drivers/target/iscsi/iscsi_target.c | 46 +++++++++++----------------- drivers/target/iscsi/iscsi_target_configfs.c | 4 +-- drivers/target/iscsi/iscsi_target_login.c | 43 +++++++++++++------------- drivers/target/iscsi/iscsi_target_tpg.c | 8 ++--- include/target/iscsi/iscsi_target_core.h | 4 +-- 6 files changed, 48 insertions(+), 65 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 771700963127..9e7094c244ea 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -3218,9 +3218,7 @@ isert_set_conn_info(struct iscsi_np *np, struct iscsi_conn *conn, conn->login_port = ntohs(sock_in6->sin6_port); sock_in6 = (struct sockaddr_in6 *)&cm_route->addr.src_addr; - snprintf(conn->local_ip, sizeof(conn->local_ip), "%pI6c", - &sock_in6->sin6_addr.in6_u); - conn->local_port = ntohs(sock_in6->sin6_port); + memcpy(&conn->local_sockaddr , &sock_in6, sizeof(sock_in6)); } else { sock_in = (struct sockaddr_in *)&cm_route->addr.dst_addr; sprintf(conn->login_ip, "%pI4", @@ -3228,9 +3226,7 @@ isert_set_conn_info(struct iscsi_np *np, struct iscsi_conn *conn, conn->login_port = ntohs(sock_in->sin_port); sock_in = (struct sockaddr_in *)&cm_route->addr.src_addr; - sprintf(conn->local_ip, "%pI4", - &sock_in->sin_addr.s_addr); - conn->local_port = ntohs(sock_in->sin_port); + memcpy(&conn->local_sockaddr , &sock_in, sizeof(sock_in)); } } diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index d75eeb5ce13a..f752235a1615 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -276,7 +276,7 @@ bool iscsit_check_np_match( struct sockaddr_in *sock_in, *sock_in_e; struct sockaddr_in6 *sock_in6, *sock_in6_e; bool ip_match = false; - u16 port; + u16 port, port_e; if (sockaddr->ss_family == AF_INET6) { sock_in6 = (struct sockaddr_in6 *)sockaddr; @@ -288,6 +288,7 @@ bool iscsit_check_np_match( ip_match = true; port = ntohs(sock_in6->sin6_port); + port_e = ntohs(sock_in6_e->sin6_port); } else { sock_in = (struct sockaddr_in *)sockaddr; sock_in_e = (struct sockaddr_in *)&np->np_sockaddr; @@ -296,9 +297,10 @@ bool iscsit_check_np_match( ip_match = true; port = ntohs(sock_in->sin_port); + port_e = ntohs(sock_in_e->sin_port); } - if (ip_match && (np->np_port == port) && + if (ip_match && (port_e == port) && (np->np_network_transport == network_transport)) return true; @@ -343,8 +345,6 @@ struct iscsi_np *iscsit_add_np( struct __kernel_sockaddr_storage *sockaddr, int network_transport) { - struct sockaddr_in *sock_in; - struct sockaddr_in6 *sock_in6; struct iscsi_np *np; int ret; @@ -367,14 +367,6 @@ struct iscsi_np *iscsit_add_np( } np->np_flags |= NPF_IP_NETWORK; - if (sockaddr->ss_family == AF_INET6) { - sock_in6 = (struct sockaddr_in6 *)sockaddr; - np->np_port = ntohs(sock_in6->sin6_port); - } else { - sock_in = (struct sockaddr_in *)sockaddr; - np->np_port = ntohs(sock_in->sin_port); - } - np->np_network_transport = network_transport; spin_lock_init(&np->np_thread_lock); init_completion(&np->np_restart_comp); @@ -408,8 +400,8 @@ struct iscsi_np *iscsit_add_np( list_add_tail(&np->np_list, &g_np_list); mutex_unlock(&np_lock); - pr_debug("CORE[0] - Added Network Portal: %pISc:%hu on %s\n", - &np->np_sockaddr, np->np_port, np->np_transport->name); + pr_debug("CORE[0] - Added Network Portal: %pISpc on %s\n", + &np->np_sockaddr, np->np_transport->name); return np; } @@ -478,8 +470,8 @@ int iscsit_del_np(struct iscsi_np *np) list_del(&np->np_list); mutex_unlock(&np_lock); - pr_debug("CORE[0] - Removed Network Portal: %pISc:%hu on %s\n", - &np->np_sockaddr, np->np_port, np->np_transport->name); + pr_debug("CORE[0] - Removed Network Portal: %pISpc on %s\n", + &np->np_sockaddr, np->np_transport->name); iscsit_put_transport(np->np_transport); kfree(np); @@ -3460,6 +3452,7 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd, tpg_np_list) { struct iscsi_np *np = tpg_np->tpg_np; bool inaddr_any = iscsit_check_inaddr_any(np); + struct __kernel_sockaddr_storage *sockaddr; if (np->np_network_transport != network_transport) continue; @@ -3487,18 +3480,15 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd, } } - if (inaddr_any) { - len = sprintf(buf, "TargetAddress=" - "%s:%hu,%hu", - conn->local_ip, - np->np_port, - tpg->tpgt); - } else { - len = sprintf(buf, "TargetAddress=" - "%pISpc,%hu", - &np->np_sockaddr, - tpg->tpgt); - } + if (inaddr_any) + sockaddr = &conn->local_sockaddr; + else + sockaddr = &np->np_sockaddr; + + len = sprintf(buf, "TargetAddress=" + "%pISpc,%hu", + sockaddr, + tpg->tpgt); len += 1; if ((len + payload_len) > buffer_len) { diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index ad6a889dadc0..8d69c4132221 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -344,8 +344,8 @@ static void lio_target_call_delnpfromtpg( se_tpg = &tpg->tpg_se_tpg; pr_debug("LIO_Target_ConfigFS: DEREGISTER -> %s TPGT: %hu" - " PORTAL: %pISc:%hu\n", config_item_name(&se_tpg->se_tpg_wwn->wwn_group.cg_item), - tpg->tpgt, &tpg_np->tpg_np->np_sockaddr, tpg_np->tpg_np->np_port); + " PORTAL: %pISpc\n", config_item_name(&se_tpg->se_tpg_wwn->wwn_group.cg_item), + tpg->tpgt, &tpg_np->tpg_np->np_sockaddr); ret = iscsit_tpg_del_network_portal(tpg, tpg_np); if (ret < 0) diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 88e0b97e8ea6..007299acefbd 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -729,8 +729,8 @@ int iscsi_post_login_handler( } pr_debug("iSCSI Login successful on CID: %hu from %s to" - " %s:%hu,%hu\n", conn->cid, conn->login_ip, - conn->local_ip, conn->local_port, tpg->tpgt); + " %pISpc,%hu\n", conn->cid, conn->login_ip, + &conn->local_sockaddr, tpg->tpgt); list_add_tail(&conn->conn_list, &sess->sess_conn_list); atomic_inc(&sess->nconn); @@ -774,8 +774,8 @@ int iscsi_post_login_handler( pr_debug("Moving to TARG_SESS_STATE_LOGGED_IN.\n"); sess->session_state = TARG_SESS_STATE_LOGGED_IN; - pr_debug("iSCSI Login successful on CID: %hu from %s to %s:%hu,%hu\n", - conn->cid, conn->login_ip, conn->local_ip, conn->local_port, + pr_debug("iSCSI Login successful on CID: %hu from %s to %pISpc,%hu\n", + conn->cid, conn->login_ip, &conn->local_sockaddr, tpg->tpgt); spin_lock_bh(&sess->conn_lock); @@ -823,8 +823,8 @@ static void iscsi_handle_login_thread_timeout(unsigned long data) struct iscsi_np *np = (struct iscsi_np *) data; spin_lock_bh(&np->np_thread_lock); - pr_err("iSCSI Login timeout on Network Portal %pISc:%hu\n", - &np->np_sockaddr, np->np_port); + pr_err("iSCSI Login timeout on Network Portal %pISpc\n", + &np->np_sockaddr); if (np->np_login_timer_flags & ISCSI_TF_STOP) { spin_unlock_bh(&np->np_thread_lock); @@ -1027,13 +1027,15 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) rc = conn->sock->ops->getname(conn->sock, (struct sockaddr *)&sock_in6, &err, 0); if (!rc) { - if (!ipv6_addr_v4mapped(&sock_in6.sin6_addr)) - snprintf(conn->local_ip, sizeof(conn->local_ip), "[%pI6c]", - &sock_in6.sin6_addr.in6_u); - else - snprintf(conn->local_ip, sizeof(conn->local_ip), "%pI4", - &sock_in6.sin6_addr.s6_addr32[3]); - conn->local_port = ntohs(sock_in6.sin6_port); + if (!ipv6_addr_v4mapped(&sock_in6.sin6_addr)) { + memcpy(&conn->local_sockaddr, &sock_in6, sizeof(sock_in6)); + } else { + /* Pretend to be an ipv4 socket */ + sock_in.sin_family = AF_INET; + sock_in.sin_port = sock_in6.sin6_port; + memcpy(&sock_in.sin_addr, &sock_in6.sin6_addr.s6_addr32[3], 4); + memcpy(&conn->local_sockaddr, &sock_in, sizeof(sock_in)); + } } } else { memset(&sock_in, 0, sizeof(struct sockaddr_in)); @@ -1048,11 +1050,8 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) rc = conn->sock->ops->getname(conn->sock, (struct sockaddr *)&sock_in, &err, 0); - if (!rc) { - sprintf(conn->local_ip, "%pI4", - &sock_in.sin_addr.s_addr); - conn->local_port = ntohs(sock_in.sin_port); - } + if (!rc) + memcpy(&conn->local_sockaddr, &sock_in, sizeof(sock_in)); } return 0; @@ -1302,8 +1301,8 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) spin_lock_bh(&np->np_thread_lock); if (np->np_thread_state != ISCSI_NP_THREAD_ACTIVE) { spin_unlock_bh(&np->np_thread_lock); - pr_err("iSCSI Network Portal on %pISc:%hu currently not" - " active.\n", &np->np_sockaddr, np->np_port); + pr_err("iSCSI Network Portal on %pISpc currently not" + " active.\n", &np->np_sockaddr); iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, ISCSI_LOGIN_STATUS_SVC_UNAVAILABLE); goto new_sess_out; @@ -1313,8 +1312,8 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) conn->network_transport = np->np_network_transport; pr_debug("Received iSCSI login request from %s on %s Network" - " Portal %s:%hu\n", conn->login_ip, np->np_transport->name, - conn->local_ip, conn->local_port); + " Portal %pISpc\n", conn->login_ip, np->np_transport->name, + &conn->local_sockaddr); pr_debug("Moving to TARG_CONN_STATE_IN_LOGIN.\n"); conn->conn_state = TARG_CONN_STATE_IN_LOGIN; diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index 31007cb4c877..d61ae5167c42 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -514,8 +514,8 @@ struct iscsi_tpg_np *iscsit_tpg_add_network_portal( spin_unlock(&tpg_np_parent->tpg_np_parent_lock); } - pr_debug("CORE[%s] - Added Network Portal: %pISc:%hu,%hu on %s\n", - tpg->tpg_tiqn->tiqn, &np->np_sockaddr, np->np_port, tpg->tpgt, + pr_debug("CORE[%s] - Added Network Portal: %pISpc,%hu on %s\n", + tpg->tpg_tiqn->tiqn, &np->np_sockaddr, tpg->tpgt, np->np_transport->name); return tpg_np; @@ -528,8 +528,8 @@ static int iscsit_tpg_release_np( { iscsit_clear_tpg_np_login_thread(tpg_np, tpg, true); - pr_debug("CORE[%s] - Removed Network Portal: %pISc:%hu,%hu on %s\n", - tpg->tpg_tiqn->tiqn, &np->np_sockaddr, np->np_port, tpg->tpgt, + pr_debug("CORE[%s] - Removed Network Portal: %pISpc,%hu on %s\n", + tpg->tpg_tiqn->tiqn, &np->np_sockaddr, tpg->tpgt, np->np_transport->name); tpg_np->tpg_np = NULL; diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 1051d0c40ddd..b9434117785f 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -519,7 +519,6 @@ struct iscsi_conn { u16 cid; /* Remote TCP Port */ u16 login_port; - u16 local_port; int net_size; int login_family; u32 auth_id; @@ -531,7 +530,7 @@ struct iscsi_conn { u32 stat_sn; #define IPV6_ADDRESS_SPACE 48 unsigned char login_ip[IPV6_ADDRESS_SPACE]; - unsigned char local_ip[IPV6_ADDRESS_SPACE]; + struct __kernel_sockaddr_storage local_sockaddr; int conn_usage_count; int conn_waiting_on_uc; atomic_t check_immediate_queue; @@ -778,7 +777,6 @@ struct iscsi_np { enum iscsi_timer_flags_table np_login_timer_flags; u32 np_exports; enum np_flags_table np_flags; - u16 np_port; spinlock_t np_thread_lock; struct completion np_restart_comp; struct socket *np_socket; -- cgit v1.2.3 From dc58f760e2e1f8f2265b581d35f211415c4fee0c Mon Sep 17 00:00:00 2001 From: Andy Grover Date: Mon, 24 Aug 2015 10:26:05 -0700 Subject: target/iscsi: Replace conn->login_ip with login_sockaddr Very similar to how it went with local_sockaddr. It was embedded in iscsi_login_stats so some changes there, and we needed to copy in a sockaddr_storage comparison function. Hopefully the kernel will get a standard one soon, our implementation makes the 3rd. isert_set_conn_info() became much smaller. IPV6_ADDRESS_SPACE define goes away, had to modify a call to in6_pton(), can just use -1 since we are sure string is null-terminated. Signed-off-by: Andy Grover Signed-off-by: Nicholas Bellinger --- drivers/infiniband/ulp/isert/ib_isert.c | 21 ++--------------- drivers/target/iscsi/iscsi_target_configfs.c | 4 ++-- drivers/target/iscsi/iscsi_target_login.c | 35 ++++++++++++++-------------- drivers/target/iscsi/iscsi_target_stat.c | 2 +- drivers/target/iscsi/iscsi_target_util.c | 32 ++++++++++++++++++++++--- include/target/iscsi/iscsi_target_core.h | 3 +-- include/target/iscsi/iscsi_target_stat.h | 2 +- 7 files changed, 53 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 9e7094c244ea..aa08606f75a2 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -3206,28 +3206,11 @@ isert_set_conn_info(struct iscsi_np *np, struct iscsi_conn *conn, { struct rdma_cm_id *cm_id = isert_conn->cm_id; struct rdma_route *cm_route = &cm_id->route; - struct sockaddr_in *sock_in; - struct sockaddr_in6 *sock_in6; conn->login_family = np->np_sockaddr.ss_family; - if (np->np_sockaddr.ss_family == AF_INET6) { - sock_in6 = (struct sockaddr_in6 *)&cm_route->addr.dst_addr; - snprintf(conn->login_ip, sizeof(conn->login_ip), "%pI6c", - &sock_in6->sin6_addr.in6_u); - conn->login_port = ntohs(sock_in6->sin6_port); - - sock_in6 = (struct sockaddr_in6 *)&cm_route->addr.src_addr; - memcpy(&conn->local_sockaddr , &sock_in6, sizeof(sock_in6)); - } else { - sock_in = (struct sockaddr_in *)&cm_route->addr.dst_addr; - sprintf(conn->login_ip, "%pI4", - &sock_in->sin_addr.s_addr); - conn->login_port = ntohs(sock_in->sin_port); - - sock_in = (struct sockaddr_in *)&cm_route->addr.src_addr; - memcpy(&conn->local_sockaddr , &sock_in, sizeof(sock_in)); - } + conn->login_sockaddr = cm_route->addr.dst_addr; + conn->local_sockaddr = cm_route->addr.src_addr; } static int diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 8d69c4132221..5afa6294eda2 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -267,7 +267,7 @@ static struct se_tpg_np *lio_target_call_addnptotpg( sock_in6 = (struct sockaddr_in6 *)&sockaddr; sock_in6->sin6_family = AF_INET6; sock_in6->sin6_port = htons((unsigned short)port); - ret = in6_pton(str, IPV6_ADDRESS_SPACE, + ret = in6_pton(str, -1, (void *)&sock_in6->sin6_addr.in6_u, -1, &end); if (ret <= 0) { pr_err("in6_pton returned: %d\n", ret); @@ -753,7 +753,7 @@ static ssize_t lio_target_nacl_show_info( break; } - rb += sprintf(page+rb, " Address %s %s", conn->login_ip, + rb += sprintf(page+rb, " Address %pISc %s", &conn->login_sockaddr, (conn->network_transport == ISCSI_TCP) ? "TCP" : "SCTP"); rb += sprintf(page+rb, " StatSN: 0x%08x\n", diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 007299acefbd..b7ef6fa82fbf 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -728,8 +728,8 @@ int iscsi_post_login_handler( stop_timer = 1; } - pr_debug("iSCSI Login successful on CID: %hu from %s to" - " %pISpc,%hu\n", conn->cid, conn->login_ip, + pr_debug("iSCSI Login successful on CID: %hu from %pISpc to" + " %pISpc,%hu\n", conn->cid, &conn->login_sockaddr, &conn->local_sockaddr, tpg->tpgt); list_add_tail(&conn->conn_list, &sess->sess_conn_list); @@ -774,8 +774,8 @@ int iscsi_post_login_handler( pr_debug("Moving to TARG_SESS_STATE_LOGGED_IN.\n"); sess->session_state = TARG_SESS_STATE_LOGGED_IN; - pr_debug("iSCSI Login successful on CID: %hu from %s to %pISpc,%hu\n", - conn->cid, conn->login_ip, &conn->local_sockaddr, + pr_debug("iSCSI Login successful on CID: %hu from %pISpc to %pISpc,%hu\n", + conn->cid, &conn->login_sockaddr, &conn->local_sockaddr, tpg->tpgt); spin_lock_bh(&sess->conn_lock); @@ -1015,13 +1015,15 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) rc = conn->sock->ops->getname(conn->sock, (struct sockaddr *)&sock_in6, &err, 1); if (!rc) { - if (!ipv6_addr_v4mapped(&sock_in6.sin6_addr)) - snprintf(conn->login_ip, sizeof(conn->login_ip), "[%pI6c]", - &sock_in6.sin6_addr.in6_u); - else - snprintf(conn->login_ip, sizeof(conn->login_ip), "%pI4", - &sock_in6.sin6_addr.s6_addr32[3]); - conn->login_port = ntohs(sock_in6.sin6_port); + if (!ipv6_addr_v4mapped(&sock_in6.sin6_addr)) { + memcpy(&conn->login_sockaddr, &sock_in6, sizeof(sock_in6)); + } else { + /* Pretend to be an ipv4 socket */ + sock_in.sin_family = AF_INET; + sock_in.sin_port = sock_in6.sin6_port; + memcpy(&sock_in.sin_addr, &sock_in6.sin6_addr.s6_addr32[3], 4); + memcpy(&conn->login_sockaddr, &sock_in, sizeof(sock_in)); + } } rc = conn->sock->ops->getname(conn->sock, @@ -1042,11 +1044,8 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) rc = conn->sock->ops->getname(conn->sock, (struct sockaddr *)&sock_in, &err, 1); - if (!rc) { - sprintf(conn->login_ip, "%pI4", - &sock_in.sin_addr.s_addr); - conn->login_port = ntohs(sock_in.sin_port); - } + if (!rc) + memcpy(&conn->login_sockaddr, &sock_in, sizeof(sock_in)); rc = conn->sock->ops->getname(conn->sock, (struct sockaddr *)&sock_in, &err, 0); @@ -1311,8 +1310,8 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) conn->network_transport = np->np_network_transport; - pr_debug("Received iSCSI login request from %s on %s Network" - " Portal %pISpc\n", conn->login_ip, np->np_transport->name, + pr_debug("Received iSCSI login request from %pISpc on %s Network" + " Portal %pISpc\n", &conn->login_sockaddr, np->np_transport->name, &conn->local_sockaddr); pr_debug("Moving to TARG_CONN_STATE_IN_LOGIN.\n"); diff --git a/drivers/target/iscsi/iscsi_target_stat.c b/drivers/target/iscsi/iscsi_target_stat.c index 5e1349a3b143..9dd94ff0b62c 100644 --- a/drivers/target/iscsi/iscsi_target_stat.c +++ b/drivers/target/iscsi/iscsi_target_stat.c @@ -430,7 +430,7 @@ static ssize_t iscsi_stat_tgt_attr_show_attr_fail_intr_addr( int ret; spin_lock(&lstat->lock); - ret = snprintf(page, PAGE_SIZE, "%s\n", lstat->last_intr_fail_ip_addr); + ret = snprintf(page, PAGE_SIZE, "%pISc\n", &lstat->last_intr_fail_sockaddr); spin_unlock(&lstat->lock); return ret; diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 7df4fac69f39..428b0d9e3dba 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -1372,6 +1372,33 @@ int tx_data( return iscsit_do_tx_data(conn, &c); } +static bool sockaddr_equal(struct sockaddr_storage *x, struct sockaddr_storage *y) +{ + switch (x->ss_family) { + case AF_INET: { + struct sockaddr_in *sinx = (struct sockaddr_in *)x; + struct sockaddr_in *siny = (struct sockaddr_in *)y; + if (sinx->sin_addr.s_addr != siny->sin_addr.s_addr) + return false; + if (sinx->sin_port != siny->sin_port) + return false; + break; + } + case AF_INET6: { + struct sockaddr_in6 *sinx = (struct sockaddr_in6 *)x; + struct sockaddr_in6 *siny = (struct sockaddr_in6 *)y; + if (!ipv6_addr_equal(&sinx->sin6_addr, &siny->sin6_addr)) + return false; + if (sinx->sin6_port != siny->sin6_port) + return false; + break; + } + default: + return false; + } + return true; +} + void iscsit_collect_login_stats( struct iscsi_conn *conn, u8 status_class, @@ -1388,7 +1415,7 @@ void iscsit_collect_login_stats( ls = &tiqn->login_stats; spin_lock(&ls->lock); - if (!strcmp(conn->login_ip, ls->last_intr_fail_ip_addr) && + if (sockaddr_equal(&conn->login_sockaddr, &ls->last_intr_fail_sockaddr) && ((get_jiffies_64() - ls->last_fail_time) < 10)) { /* We already have the failure info for this login */ spin_unlock(&ls->lock); @@ -1428,8 +1455,7 @@ void iscsit_collect_login_stats( ls->last_intr_fail_ip_family = conn->login_family; - snprintf(ls->last_intr_fail_ip_addr, IPV6_ADDRESS_SPACE, - "%s", conn->login_ip); + ls->last_intr_fail_sockaddr = conn->login_sockaddr; ls->last_fail_time = get_jiffies_64(); } diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index b9434117785f..f3eb99809557 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -528,8 +528,7 @@ struct iscsi_conn { u32 exp_statsn; /* Per connection status sequence number */ u32 stat_sn; -#define IPV6_ADDRESS_SPACE 48 - unsigned char login_ip[IPV6_ADDRESS_SPACE]; + struct __kernel_sockaddr_storage login_sockaddr; struct __kernel_sockaddr_storage local_sockaddr; int conn_usage_count; int conn_waiting_on_uc; diff --git a/include/target/iscsi/iscsi_target_stat.h b/include/target/iscsi/iscsi_target_stat.h index 3ff76b4faad3..f2a583cdf08b 100644 --- a/include/target/iscsi/iscsi_target_stat.h +++ b/include/target/iscsi/iscsi_target_stat.h @@ -50,7 +50,7 @@ struct iscsi_login_stats { u64 last_fail_time; /* time stamp (jiffies) */ u32 last_fail_type; int last_intr_fail_ip_family; - unsigned char last_intr_fail_ip_addr[IPV6_ADDRESS_SPACE]; + struct __kernel_sockaddr_storage last_intr_fail_sockaddr; char last_intr_fail_name[224]; } ____cacheline_aligned; -- cgit v1.2.3 From 13a3cf08fa1e4b3a252f24202d47a556242aea03 Mon Sep 17 00:00:00 2001 From: Andy Grover Date: Mon, 24 Aug 2015 10:26:06 -0700 Subject: target/iscsi: Replace __kernel_sockaddr_storage with sockaddr_storage It appears to be what the rest of the kernel does, so let's do it too. Signed-off-by: Andy Grover Signed-off-by: Nicholas Bellinger --- drivers/infiniband/ulp/isert/ib_isert.c | 4 ++-- drivers/target/iscsi/iscsi_target.c | 8 ++++---- drivers/target/iscsi/iscsi_target.h | 4 ++-- drivers/target/iscsi/iscsi_target_configfs.c | 4 ++-- drivers/target/iscsi/iscsi_target_login.c | 6 +++--- drivers/target/iscsi/iscsi_target_login.h | 4 ++-- drivers/target/iscsi/iscsi_target_tpg.c | 4 ++-- drivers/target/iscsi/iscsi_target_tpg.h | 2 +- include/target/iscsi/iscsi_target_core.h | 6 +++--- include/target/iscsi/iscsi_target_stat.h | 2 +- include/target/iscsi/iscsi_transport.h | 2 +- 11 files changed, 23 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index aa08606f75a2..20a0a4629456 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -3102,7 +3102,7 @@ out: static int isert_setup_np(struct iscsi_np *np, - struct __kernel_sockaddr_storage *ksockaddr) + struct sockaddr_storage *ksockaddr) { struct isert_np *isert_np; struct rdma_cm_id *isert_lid; @@ -3124,7 +3124,7 @@ isert_setup_np(struct iscsi_np *np, * in iscsi_target_configfs.c code.. */ memcpy(&np->np_sockaddr, ksockaddr, - sizeof(struct __kernel_sockaddr_storage)); + sizeof(struct sockaddr_storage)); isert_lid = isert_setup_id(isert_np); if (IS_ERR(isert_lid)) { diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index f752235a1615..a9257a083c39 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -269,7 +269,7 @@ int iscsit_deaccess_np(struct iscsi_np *np, struct iscsi_portal_group *tpg, } bool iscsit_check_np_match( - struct __kernel_sockaddr_storage *sockaddr, + struct sockaddr_storage *sockaddr, struct iscsi_np *np, int network_transport) { @@ -311,7 +311,7 @@ bool iscsit_check_np_match( * Called with mutex np_lock held */ static struct iscsi_np *iscsit_get_np( - struct __kernel_sockaddr_storage *sockaddr, + struct sockaddr_storage *sockaddr, int network_transport) { struct iscsi_np *np; @@ -342,7 +342,7 @@ static struct iscsi_np *iscsit_get_np( } struct iscsi_np *iscsit_add_np( - struct __kernel_sockaddr_storage *sockaddr, + struct sockaddr_storage *sockaddr, int network_transport) { struct iscsi_np *np; @@ -3452,7 +3452,7 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd, tpg_np_list) { struct iscsi_np *np = tpg_np->tpg_np; bool inaddr_any = iscsit_check_inaddr_any(np); - struct __kernel_sockaddr_storage *sockaddr; + struct sockaddr_storage *sockaddr; if (np->np_network_transport != network_transport) continue; diff --git a/drivers/target/iscsi/iscsi_target.h b/drivers/target/iscsi/iscsi_target.h index d294f030a097..4cf2c0f2ba2f 100644 --- a/drivers/target/iscsi/iscsi_target.h +++ b/drivers/target/iscsi/iscsi_target.h @@ -10,9 +10,9 @@ extern int iscsit_access_np(struct iscsi_np *, struct iscsi_portal_group *); extern void iscsit_login_kref_put(struct kref *); extern int iscsit_deaccess_np(struct iscsi_np *, struct iscsi_portal_group *, struct iscsi_tpg_np *); -extern bool iscsit_check_np_match(struct __kernel_sockaddr_storage *, +extern bool iscsit_check_np_match(struct sockaddr_storage *, struct iscsi_np *, int); -extern struct iscsi_np *iscsit_add_np(struct __kernel_sockaddr_storage *, +extern struct iscsi_np *iscsit_add_np(struct sockaddr_storage *, int); extern int iscsit_reset_np_thread(struct iscsi_np *, struct iscsi_tpg_np *, struct iscsi_portal_group *, bool); diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 5afa6294eda2..c7461d770d3a 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -220,7 +220,7 @@ static struct se_tpg_np *lio_target_call_addnptotpg( struct iscsi_portal_group *tpg; struct iscsi_tpg_np *tpg_np; char *str, *str2, *ip_str, *port_str; - struct __kernel_sockaddr_storage sockaddr; + struct sockaddr_storage sockaddr; struct sockaddr_in *sock_in; struct sockaddr_in6 *sock_in6; unsigned long port; @@ -235,7 +235,7 @@ static struct se_tpg_np *lio_target_call_addnptotpg( memset(buf, 0, MAX_PORTAL_LEN + 1); snprintf(buf, MAX_PORTAL_LEN + 1, "%s", name); - memset(&sockaddr, 0, sizeof(struct __kernel_sockaddr_storage)); + memset(&sockaddr, 0, sizeof(struct sockaddr_storage)); str = strstr(buf, "["); if (str) { diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index b7ef6fa82fbf..fc7b79672d05 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -877,7 +877,7 @@ static void iscsi_stop_login_thread_timer(struct iscsi_np *np) int iscsit_setup_np( struct iscsi_np *np, - struct __kernel_sockaddr_storage *sockaddr) + struct sockaddr_storage *sockaddr) { struct socket *sock = NULL; int backlog = ISCSIT_TCP_BACKLOG, ret, opt = 0, len; @@ -916,7 +916,7 @@ int iscsit_setup_np( * in iscsi_target_configfs.c code.. */ memcpy(&np->np_sockaddr, sockaddr, - sizeof(struct __kernel_sockaddr_storage)); + sizeof(struct sockaddr_storage)); if (sockaddr->ss_family == AF_INET6) len = sizeof(struct sockaddr_in6); @@ -975,7 +975,7 @@ fail: int iscsi_target_setup_login_socket( struct iscsi_np *np, - struct __kernel_sockaddr_storage *sockaddr) + struct sockaddr_storage *sockaddr) { struct iscsit_transport *t; int rc; diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h index 1c7358081533..35aeffee0686 100644 --- a/drivers/target/iscsi/iscsi_target_login.h +++ b/drivers/target/iscsi/iscsi_target_login.h @@ -5,9 +5,9 @@ extern int iscsi_login_setup_crypto(struct iscsi_conn *); extern int iscsi_check_for_session_reinstatement(struct iscsi_conn *); extern int iscsi_login_post_auth_non_zero_tsih(struct iscsi_conn *, u16, u32); extern int iscsit_setup_np(struct iscsi_np *, - struct __kernel_sockaddr_storage *); + struct sockaddr_storage *); extern int iscsi_target_setup_login_socket(struct iscsi_np *, - struct __kernel_sockaddr_storage *); + struct sockaddr_storage *); extern int iscsit_accept_np(struct iscsi_np *, struct iscsi_conn *); extern int iscsit_get_login_rx(struct iscsi_conn *, struct iscsi_login *); extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32); diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index d61ae5167c42..23c95cd14167 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -431,7 +431,7 @@ struct iscsi_tpg_np *iscsit_tpg_locate_child_np( static bool iscsit_tpg_check_network_portal( struct iscsi_tiqn *tiqn, - struct __kernel_sockaddr_storage *sockaddr, + struct sockaddr_storage *sockaddr, int network_transport) { struct iscsi_portal_group *tpg; @@ -460,7 +460,7 @@ static bool iscsit_tpg_check_network_portal( struct iscsi_tpg_np *iscsit_tpg_add_network_portal( struct iscsi_portal_group *tpg, - struct __kernel_sockaddr_storage *sockaddr, + struct sockaddr_storage *sockaddr, struct iscsi_tpg_np *tpg_np_parent, int network_transport) { diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h index 1c0b1d6605cf..9db32bd24cd4 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.h +++ b/drivers/target/iscsi/iscsi_target_tpg.h @@ -22,7 +22,7 @@ extern struct iscsi_node_attrib *iscsit_tpg_get_node_attrib(struct iscsi_session extern void iscsit_tpg_del_external_nps(struct iscsi_tpg_np *); extern struct iscsi_tpg_np *iscsit_tpg_locate_child_np(struct iscsi_tpg_np *, int); extern struct iscsi_tpg_np *iscsit_tpg_add_network_portal(struct iscsi_portal_group *, - struct __kernel_sockaddr_storage *, struct iscsi_tpg_np *, + struct sockaddr_storage *, struct iscsi_tpg_np *, int); extern int iscsit_tpg_del_network_portal(struct iscsi_portal_group *, struct iscsi_tpg_np *); diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index f3eb99809557..84abe73450c5 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -528,8 +528,8 @@ struct iscsi_conn { u32 exp_statsn; /* Per connection status sequence number */ u32 stat_sn; - struct __kernel_sockaddr_storage login_sockaddr; - struct __kernel_sockaddr_storage local_sockaddr; + struct sockaddr_storage login_sockaddr; + struct sockaddr_storage local_sockaddr; int conn_usage_count; int conn_waiting_on_uc; atomic_t check_immediate_queue; @@ -779,7 +779,7 @@ struct iscsi_np { spinlock_t np_thread_lock; struct completion np_restart_comp; struct socket *np_socket; - struct __kernel_sockaddr_storage np_sockaddr; + struct sockaddr_storage np_sockaddr; struct task_struct *np_thread; struct timer_list np_login_timer; void *np_context; diff --git a/include/target/iscsi/iscsi_target_stat.h b/include/target/iscsi/iscsi_target_stat.h index f2a583cdf08b..e615bb485d0b 100644 --- a/include/target/iscsi/iscsi_target_stat.h +++ b/include/target/iscsi/iscsi_target_stat.h @@ -50,7 +50,7 @@ struct iscsi_login_stats { u64 last_fail_time; /* time stamp (jiffies) */ u32 last_fail_type; int last_intr_fail_ip_family; - struct __kernel_sockaddr_storage last_intr_fail_sockaddr; + struct sockaddr_storage last_intr_fail_sockaddr; char last_intr_fail_name[224]; } ____cacheline_aligned; diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index e6bb166f12c2..90e37faa2ede 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -9,7 +9,7 @@ struct iscsit_transport { int priv_size; struct module *owner; struct list_head t_node; - int (*iscsit_setup_np)(struct iscsi_np *, struct __kernel_sockaddr_storage *); + int (*iscsit_setup_np)(struct iscsi_np *, struct sockaddr_storage *); int (*iscsit_accept_np)(struct iscsi_np *, struct iscsi_conn *); void (*iscsit_free_np)(struct iscsi_np *); void (*iscsit_wait_conn)(struct iscsi_conn *); -- cgit v1.2.3 From 1bab0de0274fbe8c8ac92179e6705584c55ed169 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 27 Aug 2015 14:16:54 +0200 Subject: dm-mpath, scsi_dh: don't let dm detach device handlers While allowing dm-mpath to attach device handlers is a functionality we need for backwards compatibility reason there is no reason to reference count them and detach them if dm-mpath stops using the device for some reason. If the device handler works for the given device it can just stay attached, and we can take the retain_hw_handler codepath. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Acked-by: Hannes Reinecke Signed-off-by: James Bottomley --- drivers/md/dm-mpath.c | 21 +++----- drivers/scsi/device_handler/scsi_dh.c | 96 ++++++++--------------------------- include/scsi/scsi_device.h | 1 - include/scsi/scsi_dh.h | 5 -- 4 files changed, 28 insertions(+), 95 deletions(-) (limited to 'include') diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index eff7bdd7731d..a9f58fdb5d69 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -159,12 +159,9 @@ static struct priority_group *alloc_priority_group(void) static void free_pgpaths(struct list_head *pgpaths, struct dm_target *ti) { struct pgpath *pgpath, *tmp; - struct multipath *m = ti->private; list_for_each_entry_safe(pgpath, tmp, pgpaths, list) { list_del(&pgpath->list); - if (m->hw_handler_name) - scsi_dh_detach(bdev_get_queue(pgpath->path.dev->bdev)); dm_put_device(ti, pgpath->path.dev); free_pgpath(pgpath); } @@ -580,6 +577,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps q = bdev_get_queue(p->path.dev->bdev); if (m->retain_attached_hw_handler) { +retain: attached_handler_name = scsi_dh_attached_handler_name(q, GFP_KERNEL); if (attached_handler_name) { /* @@ -599,20 +597,14 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps } if (m->hw_handler_name) { - /* - * Increments scsi_dh reference, even when using an - * already-attached handler. - */ r = scsi_dh_attach(q, m->hw_handler_name); if (r == -EBUSY) { - /* - * Already attached to different hw_handler: - * try to reattach with correct one. - */ - scsi_dh_detach(q); - r = scsi_dh_attach(q, m->hw_handler_name); - } + char b[BDEVNAME_SIZE]; + printk(KERN_INFO "dm-mpath: retaining handler on device %s\n", + bdevname(p->path.dev->bdev, b)); + goto retain; + } if (r < 0) { ti->error = "error attaching hardware handler"; dm_put_device(ti, p->path.dev); @@ -624,7 +616,6 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps if (r < 0) { ti->error = "unable to set hardware " "handler parameters"; - scsi_dh_detach(q); dm_put_device(ti, p->path.dev); goto bad; } diff --git a/drivers/scsi/device_handler/scsi_dh.c b/drivers/scsi/device_handler/scsi_dh.c index 1efebc9eedfb..869b5bd1ad25 100644 --- a/drivers/scsi/device_handler/scsi_dh.c +++ b/drivers/scsi/device_handler/scsi_dh.c @@ -100,14 +100,6 @@ static int scsi_dh_handler_attach(struct scsi_device *sdev, { struct scsi_dh_data *d; - if (sdev->scsi_dh_data) { - if (sdev->scsi_dh_data->scsi_dh != scsi_dh) - return -EBUSY; - - kref_get(&sdev->scsi_dh_data->kref); - return 0; - } - if (!try_module_get(scsi_dh->module)) return -EINVAL; @@ -120,7 +112,6 @@ static int scsi_dh_handler_attach(struct scsi_device *sdev, } d->scsi_dh = scsi_dh; - kref_init(&d->kref); d->sdev = sdev; spin_lock_irq(sdev->request_queue->queue_lock); @@ -129,12 +120,14 @@ static int scsi_dh_handler_attach(struct scsi_device *sdev, return 0; } -static void __detach_handler (struct kref *kref) +/* + * scsi_dh_handler_detach - Detach a device handler from a device + * @sdev - SCSI device the device handler should be detached from + */ +static void scsi_dh_handler_detach(struct scsi_device *sdev) { - struct scsi_dh_data *scsi_dh_data = - container_of(kref, struct scsi_dh_data, kref); + struct scsi_dh_data *scsi_dh_data = sdev->scsi_dh_data; struct scsi_device_handler *scsi_dh = scsi_dh_data->scsi_dh; - struct scsi_device *sdev = scsi_dh_data->sdev; scsi_dh->detach(sdev); @@ -146,30 +139,6 @@ static void __detach_handler (struct kref *kref) module_put(scsi_dh->module); } -/* - * scsi_dh_handler_detach - Detach a device handler from a device - * @sdev - SCSI device the device handler should be detached from - * @scsi_dh - Device handler to be detached - * - * Detach from a device handler. If a device handler is specified, - * only detach if the currently attached handler matches @scsi_dh. - */ -static void scsi_dh_handler_detach(struct scsi_device *sdev, - struct scsi_device_handler *scsi_dh) -{ - if (!sdev->scsi_dh_data) - return; - - if (scsi_dh && scsi_dh != sdev->scsi_dh_data->scsi_dh) - return; - - if (!scsi_dh) - scsi_dh = sdev->scsi_dh_data->scsi_dh; - - if (scsi_dh) - kref_put(&sdev->scsi_dh_data->kref, __detach_handler); -} - /* * Functions for sysfs attribute 'dh_state' */ @@ -198,7 +167,7 @@ store_dh_state(struct device *dev, struct device_attribute *attr, /* * Detach from a device handler */ - scsi_dh_handler_detach(sdev, scsi_dh); + scsi_dh_handler_detach(sdev); err = 0; } else if (!strncmp(buf, "activate", 8)) { /* @@ -290,7 +259,8 @@ static int scsi_dh_notifier(struct notifier_block *nb, err = scsi_dh_handler_attach(sdev, devinfo); } else if (action == BUS_NOTIFY_DEL_DEVICE) { device_remove_file(dev, &scsi_dh_state_attr); - scsi_dh_handler_detach(sdev, NULL); + if (sdev->scsi_dh_data) + scsi_dh_handler_detach(sdev); } return err; } @@ -335,7 +305,8 @@ static int scsi_dh_notifier_remove(struct device *dev, void *data) sdev = to_scsi_device(dev); - scsi_dh_handler_detach(sdev, scsi_dh); + if (sdev->scsi_dh_data && sdev->scsi_dh_data->scsi_dh == scsi_dh) + scsi_dh_handler_detach(sdev); put_device(dev); @@ -517,45 +488,22 @@ int scsi_dh_attach(struct request_queue *q, const char *name) err = -ENODEV; spin_unlock_irqrestore(q->queue_lock, flags); - if (!err) { - err = scsi_dh_handler_attach(sdev, scsi_dh); - put_device(&sdev->sdev_gendev); - } - return err; -} -EXPORT_SYMBOL_GPL(scsi_dh_attach); - -/* - * scsi_dh_detach - Detach device handler - * @q - Request queue that is associated with the scsi_device - * the handler should be detached from - * - * This function will detach the device handler only - * if the sdev is not part of the internal list, ie - * if it has been attached manually. - */ -void scsi_dh_detach(struct request_queue *q) -{ - unsigned long flags; - struct scsi_device *sdev; - struct scsi_device_handler *scsi_dh = NULL; - - spin_lock_irqsave(q->queue_lock, flags); - sdev = q->queuedata; - if (!sdev || !get_device(&sdev->sdev_gendev)) - sdev = NULL; - spin_unlock_irqrestore(q->queue_lock, flags); - - if (!sdev) - return; + if (err) + return err; if (sdev->scsi_dh_data) { - scsi_dh = sdev->scsi_dh_data->scsi_dh; - scsi_dh_handler_detach(sdev, scsi_dh); + if (sdev->scsi_dh_data->scsi_dh != scsi_dh) + err = -EBUSY; + goto out_put_device; } + + err = scsi_dh_handler_attach(sdev, scsi_dh); + +out_put_device: put_device(&sdev->sdev_gendev); + return err; } -EXPORT_SYMBOL_GPL(scsi_dh_detach); +EXPORT_SYMBOL_GPL(scsi_dh_attach); /* * scsi_dh_attached_handler_name - Get attached device handler's name diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 50c2a363bc8f..798d67994aeb 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -221,7 +221,6 @@ struct scsi_device_handler { struct scsi_dh_data { struct scsi_device_handler *scsi_dh; struct scsi_device *sdev; - struct kref kref; }; #define to_scsi_device(d) \ diff --git a/include/scsi/scsi_dh.h b/include/scsi/scsi_dh.h index 620c723ee8ed..99c9196fe606 100644 --- a/include/scsi/scsi_dh.h +++ b/include/scsi/scsi_dh.h @@ -59,7 +59,6 @@ enum { extern int scsi_dh_activate(struct request_queue *, activate_complete, void *); extern int scsi_dh_handler_exist(const char *); extern int scsi_dh_attach(struct request_queue *, const char *); -extern void scsi_dh_detach(struct request_queue *); extern const char *scsi_dh_attached_handler_name(struct request_queue *, gfp_t); extern int scsi_dh_set_params(struct request_queue *, const char *); #else @@ -77,10 +76,6 @@ static inline int scsi_dh_attach(struct request_queue *req, const char *name) { return SCSI_DH_NOSYS; } -static inline void scsi_dh_detach(struct request_queue *q) -{ - return; -} static inline const char *scsi_dh_attached_handler_name(struct request_queue *q, gfp_t gfp) { -- cgit v1.2.3 From 566079c849cfe538e908c44ac11a9c4638db8f91 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 27 Aug 2015 14:16:55 +0200 Subject: dm-mpath, scsi_dh: request scsi_dh modules in scsi_dh, not dm-mpath This way we can reused the same code any attachment method, not just those requested from dm-mpath. [jejb: fixup checkpatch error] Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Acked-by: Mike Snitzer Signed-off-by: James Bottomley --- drivers/md/dm-mpath.c | 6 ------ drivers/scsi/device_handler/scsi_dh.c | 36 ++++++++++++++++++----------------- include/scsi/scsi_dh.h | 5 ----- 3 files changed, 19 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index a9f58fdb5d69..5a67671a3973 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -725,12 +725,6 @@ static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m) return 0; m->hw_handler_name = kstrdup(dm_shift_arg(as), GFP_KERNEL); - if (!try_then_request_module(scsi_dh_handler_exist(m->hw_handler_name), - "scsi_dh_%s", m->hw_handler_name)) { - ti->error = "unknown hardware handler type"; - ret = -EINVAL; - goto fail; - } if (hw_argc > 1) { char *p; diff --git a/drivers/scsi/device_handler/scsi_dh.c b/drivers/scsi/device_handler/scsi_dh.c index 869b5bd1ad25..3dfef5b0d298 100644 --- a/drivers/scsi/device_handler/scsi_dh.c +++ b/drivers/scsi/device_handler/scsi_dh.c @@ -29,7 +29,7 @@ static DEFINE_SPINLOCK(list_lock); static LIST_HEAD(scsi_dh_list); -static struct scsi_device_handler *get_device_handler(const char *name) +static struct scsi_device_handler *__scsi_dh_lookup(const char *name) { struct scsi_device_handler *tmp, *found = NULL; @@ -44,6 +44,19 @@ static struct scsi_device_handler *get_device_handler(const char *name) return found; } +static struct scsi_device_handler *scsi_dh_lookup(const char *name) +{ + struct scsi_device_handler *dh; + + dh = __scsi_dh_lookup(name); + if (!dh) { + request_module(name); + dh = __scsi_dh_lookup(name); + } + + return dh; +} + /* * device_handler_match_function - Match a device handler to a device * @sdev - SCSI device to be tested @@ -158,7 +171,8 @@ store_dh_state(struct device *dev, struct device_attribute *attr, /* * Attach to a device handler */ - if (!(scsi_dh = get_device_handler(buf))) + scsi_dh = scsi_dh_lookup(buf); + if (!scsi_dh) return err; err = scsi_dh_handler_attach(sdev, scsi_dh); } else { @@ -322,8 +336,7 @@ static int scsi_dh_notifier_remove(struct device *dev, void *data) */ int scsi_register_device_handler(struct scsi_device_handler *scsi_dh) { - - if (get_device_handler(scsi_dh->name)) + if (__scsi_dh_lookup(scsi_dh->name)) return -EBUSY; if (!scsi_dh->attach || !scsi_dh->detach) @@ -350,7 +363,7 @@ EXPORT_SYMBOL_GPL(scsi_register_device_handler); int scsi_unregister_device_handler(struct scsi_device_handler *scsi_dh) { - if (!get_device_handler(scsi_dh->name)) + if (!__scsi_dh_lookup(scsi_dh->name)) return -ENODEV; bus_for_each_dev(&scsi_bus_type, NULL, scsi_dh, @@ -454,17 +467,6 @@ int scsi_dh_set_params(struct request_queue *q, const char *params) } EXPORT_SYMBOL_GPL(scsi_dh_set_params); -/* - * scsi_dh_handler_exist - Return TRUE(1) if a device handler exists for - * the given name. FALSE(0) otherwise. - * @name - name of the device handler. - */ -int scsi_dh_handler_exist(const char *name) -{ - return (get_device_handler(name) != NULL); -} -EXPORT_SYMBOL_GPL(scsi_dh_handler_exist); - /* * scsi_dh_attach - Attach device handler * @q - Request queue that is associated with the scsi_device @@ -478,7 +480,7 @@ int scsi_dh_attach(struct request_queue *q, const char *name) struct scsi_device_handler *scsi_dh; int err = 0; - scsi_dh = get_device_handler(name); + scsi_dh = scsi_dh_lookup(name); if (!scsi_dh) return -EINVAL; diff --git a/include/scsi/scsi_dh.h b/include/scsi/scsi_dh.h index 99c9196fe606..966b921135b5 100644 --- a/include/scsi/scsi_dh.h +++ b/include/scsi/scsi_dh.h @@ -57,7 +57,6 @@ enum { }; #if defined(CONFIG_SCSI_DH) || defined(CONFIG_SCSI_DH_MODULE) extern int scsi_dh_activate(struct request_queue *, activate_complete, void *); -extern int scsi_dh_handler_exist(const char *); extern int scsi_dh_attach(struct request_queue *, const char *); extern const char *scsi_dh_attached_handler_name(struct request_queue *, gfp_t); extern int scsi_dh_set_params(struct request_queue *, const char *); @@ -68,10 +67,6 @@ static inline int scsi_dh_activate(struct request_queue *req, fn(data, 0); return 0; } -static inline int scsi_dh_handler_exist(const char *name) -{ - return 0; -} static inline int scsi_dh_attach(struct request_queue *req, const char *name) { return SCSI_DH_NOSYS; -- cgit v1.2.3 From 086b91d052ebe4ead5d28021afe3bdfd70af15bf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 27 Aug 2015 14:16:57 +0200 Subject: scsi_dh: integrate into the core SCSI code Stop building scsi_dh as a separate module and integrate it fully into the core SCSI code with explicit callouts at bus scan time. For now the callouts are placed at the same point as the old bus notifiers were called, but in the future we will be able to look at ALUA INQUIRY data earlier on. Note that this also means that the device handler modules need to be loaded by the time we scan the bus. The next patches will add support for autoloading device handlers at bus scan time to make sure they are always loaded if they are enabled in the kernel config. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Acked-by: Mike Snitzer Signed-off-by: James Bottomley --- drivers/scsi/Makefile | 1 + drivers/scsi/device_handler/Kconfig | 2 +- drivers/scsi/device_handler/Makefile | 1 - drivers/scsi/scsi_dh.c | 183 +++-------------------------------- drivers/scsi/scsi_priv.h | 9 ++ drivers/scsi/scsi_sysfs.c | 10 ++ include/scsi/scsi_dh.h | 2 +- 7 files changed, 34 insertions(+), 174 deletions(-) (limited to 'include') diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index 471d08791766..1a8c9b53fafa 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -172,6 +172,7 @@ scsi_mod-$(CONFIG_SYSCTL) += scsi_sysctl.o scsi_mod-$(CONFIG_SCSI_PROC_FS) += scsi_proc.o scsi_mod-y += scsi_trace.o scsi_logging.o scsi_mod-$(CONFIG_PM) += scsi_pm.o +scsi_mod-$(CONFIG_SCSI_DH) += scsi_dh.o hv_storvsc-y := storvsc_drv.o diff --git a/drivers/scsi/device_handler/Kconfig b/drivers/scsi/device_handler/Kconfig index 69abd0ad48e2..e5647d59224f 100644 --- a/drivers/scsi/device_handler/Kconfig +++ b/drivers/scsi/device_handler/Kconfig @@ -3,7 +3,7 @@ # menuconfig SCSI_DH - tristate "SCSI Device Handlers" + bool "SCSI Device Handlers" depends on SCSI default n help diff --git a/drivers/scsi/device_handler/Makefile b/drivers/scsi/device_handler/Makefile index e1d2ea083e15..09866c50fbb4 100644 --- a/drivers/scsi/device_handler/Makefile +++ b/drivers/scsi/device_handler/Makefile @@ -1,7 +1,6 @@ # # SCSI Device Handler # -obj-$(CONFIG_SCSI_DH) += scsi_dh.o obj-$(CONFIG_SCSI_DH_RDAC) += scsi_dh_rdac.o obj-$(CONFIG_SCSI_DH_HP_SW) += scsi_dh_hp_sw.o obj-$(CONFIG_SCSI_DH_EMC) += scsi_dh_emc.o diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c index 3de9b6767be4..f0dfdccc060e 100644 --- a/drivers/scsi/scsi_dh.c +++ b/drivers/scsi/scsi_dh.c @@ -57,15 +57,8 @@ static struct scsi_device_handler *scsi_dh_lookup(const char *name) return dh; } -/* - * device_handler_match_function - Match a device handler to a device - * @sdev - SCSI device to be tested - * - * Tests @sdev against the match function of all registered device_handler. - * Returns the found device handler or NULL if not found. - */ static struct scsi_device_handler * -device_handler_match_function(struct scsi_device *sdev) +device_handler_match(struct scsi_device *sdev) { struct scsi_device_handler *tmp_dh, *found_dh = NULL; @@ -80,29 +73,6 @@ device_handler_match_function(struct scsi_device *sdev) return found_dh; } -/* - * device_handler_match - Attach a device handler to a device - * @scsi_dh - The device handler to match against or NULL - * @sdev - SCSI device to be tested against @scsi_dh - * - * Tests @sdev against the device handler @scsi_dh or against - * all registered device_handler if @scsi_dh == NULL. - * Returns the found device handler or NULL if not found. - */ -static struct scsi_device_handler * -device_handler_match(struct scsi_device_handler *scsi_dh, - struct scsi_device *sdev) -{ - struct scsi_device_handler *found_dh; - - found_dh = device_handler_match_function(sdev); - - if (scsi_dh && found_dh != scsi_dh) - found_dh = NULL; - - return found_dh; -} - /* * scsi_dh_handler_attach - Attach a device handler to a device * @sdev - SCSI device the device handler should attach to @@ -212,119 +182,26 @@ static struct device_attribute scsi_dh_state_attr = __ATTR(dh_state, S_IRUGO | S_IWUSR, show_dh_state, store_dh_state); -/* - * scsi_dh_sysfs_attr_add - Callback for scsi_init_dh - */ -static int scsi_dh_sysfs_attr_add(struct device *dev, void *data) +int scsi_dh_add_device(struct scsi_device *sdev) { - struct scsi_device *sdev; + struct scsi_device_handler *devinfo; int err; - if (!scsi_is_sdev_device(dev)) - return 0; - - sdev = to_scsi_device(dev); - - err = device_create_file(&sdev->sdev_gendev, - &scsi_dh_state_attr); - - return 0; -} - -/* - * scsi_dh_sysfs_attr_remove - Callback for scsi_exit_dh - */ -static int scsi_dh_sysfs_attr_remove(struct device *dev, void *data) -{ - struct scsi_device *sdev; - - if (!scsi_is_sdev_device(dev)) - return 0; - - sdev = to_scsi_device(dev); - - device_remove_file(&sdev->sdev_gendev, - &scsi_dh_state_attr); - - return 0; -} + err = device_create_file(&sdev->sdev_gendev, &scsi_dh_state_attr); + if (err) + return err; -/* - * scsi_dh_notifier - notifier chain callback - */ -static int scsi_dh_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - struct scsi_device *sdev; - int err = 0; - struct scsi_device_handler *devinfo = NULL; - - if (!scsi_is_sdev_device(dev)) - return 0; - - sdev = to_scsi_device(dev); - - if (action == BUS_NOTIFY_ADD_DEVICE) { - err = device_create_file(dev, &scsi_dh_state_attr); - /* don't care about err */ - devinfo = device_handler_match(NULL, sdev); - if (devinfo) - err = scsi_dh_handler_attach(sdev, devinfo); - } else if (action == BUS_NOTIFY_DEL_DEVICE) { - device_remove_file(dev, &scsi_dh_state_attr); - if (sdev->scsi_dh_data) - scsi_dh_handler_detach(sdev); - } + devinfo = device_handler_match(sdev); + if (devinfo) + err = scsi_dh_handler_attach(sdev, devinfo); return err; } -/* - * scsi_dh_notifier_add - Callback for scsi_register_device_handler - */ -static int scsi_dh_notifier_add(struct device *dev, void *data) +void scsi_dh_remove_device(struct scsi_device *sdev) { - struct scsi_device_handler *scsi_dh = data; - struct scsi_device *sdev; - - if (!scsi_is_sdev_device(dev)) - return 0; - - if (!get_device(dev)) - return 0; - - sdev = to_scsi_device(dev); - - if (device_handler_match(scsi_dh, sdev)) - scsi_dh_handler_attach(sdev, scsi_dh); - - put_device(dev); - - return 0; -} - -/* - * scsi_dh_notifier_remove - Callback for scsi_unregister_device_handler - */ -static int scsi_dh_notifier_remove(struct device *dev, void *data) -{ - struct scsi_device_handler *scsi_dh = data; - struct scsi_device *sdev; - - if (!scsi_is_sdev_device(dev)) - return 0; - - if (!get_device(dev)) - return 0; - - sdev = to_scsi_device(dev); - - if (sdev->scsi_dh_data && sdev->scsi_dh_data->scsi_dh == scsi_dh) + if (sdev->scsi_dh_data) scsi_dh_handler_detach(sdev); - - put_device(dev); - - return 0; + device_remove_file(&sdev->sdev_gendev, &scsi_dh_state_attr); } /* @@ -346,7 +223,6 @@ int scsi_register_device_handler(struct scsi_device_handler *scsi_dh) list_add(&scsi_dh->list, &scsi_dh_list); spin_unlock(&list_lock); - bus_for_each_dev(&scsi_bus_type, NULL, scsi_dh, scsi_dh_notifier_add); printk(KERN_INFO "%s: device handler registered\n", scsi_dh->name); return SCSI_DH_OK; @@ -362,13 +238,9 @@ EXPORT_SYMBOL_GPL(scsi_register_device_handler); */ int scsi_unregister_device_handler(struct scsi_device_handler *scsi_dh) { - if (!__scsi_dh_lookup(scsi_dh->name)) return -ENODEV; - bus_for_each_dev(&scsi_bus_type, NULL, scsi_dh, - scsi_dh_notifier_remove); - spin_lock(&list_lock); list_del(&scsi_dh->list); spin_unlock(&list_lock); @@ -538,34 +410,3 @@ const char *scsi_dh_attached_handler_name(struct request_queue *q, gfp_t gfp) return handler_name; } EXPORT_SYMBOL_GPL(scsi_dh_attached_handler_name); - -static struct notifier_block scsi_dh_nb = { - .notifier_call = scsi_dh_notifier -}; - -static int __init scsi_dh_init(void) -{ - int r; - - r = bus_register_notifier(&scsi_bus_type, &scsi_dh_nb); - - if (!r) - bus_for_each_dev(&scsi_bus_type, NULL, NULL, - scsi_dh_sysfs_attr_add); - - return r; -} - -static void __exit scsi_dh_exit(void) -{ - bus_for_each_dev(&scsi_bus_type, NULL, NULL, - scsi_dh_sysfs_attr_remove); - bus_unregister_notifier(&scsi_bus_type, &scsi_dh_nb); -} - -module_init(scsi_dh_init); -module_exit(scsi_dh_exit); - -MODULE_DESCRIPTION("SCSI device handler"); -MODULE_AUTHOR("Chandra Seetharaman "); -MODULE_LICENSE("GPL"); diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index e3902fc66278..644bb7339b55 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -170,6 +170,15 @@ static inline void scsi_autopm_put_host(struct Scsi_Host *h) {} extern struct async_domain scsi_sd_pm_domain; extern struct async_domain scsi_sd_probe_domain; +/* scsi_dh.c */ +#ifdef CONFIG_SCSI_DH +int scsi_dh_add_device(struct scsi_device *sdev); +void scsi_dh_remove_device(struct scsi_device *sdev); +#else +static inline int scsi_dh_add_device(struct scsi_device *sdev) { return 0; } +static inline void scsi_dh_remove_device(struct scsi_device *sdev) { } +#endif + /* * internal scsi timeout functions: for use by mid-layer and transport * classes. diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 9ad41168d26d..b333389f248f 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1030,11 +1030,20 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev) "failed to add device: %d\n", error); return error; } + + error = scsi_dh_add_device(sdev); + if (error) { + sdev_printk(KERN_INFO, sdev, + "failed to add device handler: %d\n", error); + return error; + } + device_enable_async_suspend(&sdev->sdev_dev); error = device_add(&sdev->sdev_dev); if (error) { sdev_printk(KERN_INFO, sdev, "failed to add class device: %d\n", error); + scsi_dh_remove_device(sdev); device_del(&sdev->sdev_gendev); return error; } @@ -1074,6 +1083,7 @@ void __scsi_remove_device(struct scsi_device *sdev) bsg_unregister_queue(sdev->request_queue); device_unregister(&sdev->sdev_dev); transport_remove_device(dev); + scsi_dh_remove_device(sdev); device_del(dev); } else put_device(&sdev->sdev_dev); diff --git a/include/scsi/scsi_dh.h b/include/scsi/scsi_dh.h index 966b921135b5..3a37b4c45997 100644 --- a/include/scsi/scsi_dh.h +++ b/include/scsi/scsi_dh.h @@ -55,7 +55,7 @@ enum { SCSI_DH_NOSYS, SCSI_DH_DRIVER_MAX, }; -#if defined(CONFIG_SCSI_DH) || defined(CONFIG_SCSI_DH_MODULE) +#ifdef CONFIG_SCSI_DH extern int scsi_dh_activate(struct request_queue *, activate_complete, void *); extern int scsi_dh_attach(struct request_queue *, const char *); extern const char *scsi_dh_attached_handler_name(struct request_queue *, gfp_t); -- cgit v1.2.3 From d95dbff2a41e934cd8789734b34dc591e78ba11c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 27 Aug 2015 14:16:58 +0200 Subject: scsi_dh: move device matching to the core code Add a single list of devices that need non-ALUA device handlers to the core scsi_dh code so that we can autoload the modules for them at probe time. While this is a little ugly in terms of architecture it actually significantly simplifies the code in addition to the new autoloading functionality. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Acked-by: Mike Snitzer Signed-off-by: James Bottomley --- drivers/scsi/device_handler/scsi_dh_alua.c | 6 --- drivers/scsi/device_handler/scsi_dh_emc.c | 29 ---------- drivers/scsi/device_handler/scsi_dh_hp_sw.c | 30 ----------- drivers/scsi/device_handler/scsi_dh_rdac.c | 50 ----------------- drivers/scsi/scsi_dh.c | 84 ++++++++++++++++++++++------- include/scsi/scsi_device.h | 1 - 6 files changed, 66 insertions(+), 134 deletions(-) (limited to 'include') diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 854b568b9931..ace2457747a7 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -819,11 +819,6 @@ static int alua_prep_fn(struct scsi_device *sdev, struct request *req) } -static bool alua_match(struct scsi_device *sdev) -{ - return (scsi_device_tpgs(sdev) != 0); -} - /* * alua_bus_attach - Attach device handler * @sdev: device to be attached to @@ -877,7 +872,6 @@ static struct scsi_device_handler alua_dh = { .check_sense = alua_check_sense, .activate = alua_activate, .set_params = alua_set_params, - .match = alua_match, }; static int __init alua_init(void) diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c index 6ed1caadbc6a..fd31e67e9f50 100644 --- a/drivers/scsi/device_handler/scsi_dh_emc.c +++ b/drivers/scsi/device_handler/scsi_dh_emc.c @@ -622,34 +622,6 @@ done: return result; } -static const struct { - char *vendor; - char *model; -} clariion_dev_list[] = { - {"DGC", "RAID"}, - {"DGC", "DISK"}, - {"DGC", "VRAID"}, - {NULL, NULL}, -}; - -static bool clariion_match(struct scsi_device *sdev) -{ - int i; - - if (scsi_device_tpgs(sdev)) - return false; - - for (i = 0; clariion_dev_list[i].vendor; i++) { - if (!strncmp(sdev->vendor, clariion_dev_list[i].vendor, - strlen(clariion_dev_list[i].vendor)) && - !strncmp(sdev->model, clariion_dev_list[i].model, - strlen(clariion_dev_list[i].model))) { - return true; - } - } - return false; -} - static struct scsi_dh_data *clariion_bus_attach(struct scsi_device *sdev) { struct clariion_dh_data *h; @@ -698,7 +670,6 @@ static struct scsi_device_handler clariion_dh = { .activate = clariion_activate, .prep_fn = clariion_prep_fn, .set_params = clariion_set_params, - .match = clariion_match, }; static int __init clariion_init(void) diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c index 485d99544a15..1bf10d37289a 100644 --- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c +++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c @@ -311,35 +311,6 @@ static int hp_sw_activate(struct scsi_device *sdev, return 0; } -static const struct { - char *vendor; - char *model; -} hp_sw_dh_data_list[] = { - {"COMPAQ", "MSA1000 VOLUME"}, - {"COMPAQ", "HSV110"}, - {"HP", "HSV100"}, - {"DEC", "HSG80"}, - {NULL, NULL}, -}; - -static bool hp_sw_match(struct scsi_device *sdev) -{ - int i; - - if (scsi_device_tpgs(sdev)) - return false; - - for (i = 0; hp_sw_dh_data_list[i].vendor; i++) { - if (!strncmp(sdev->vendor, hp_sw_dh_data_list[i].vendor, - strlen(hp_sw_dh_data_list[i].vendor)) && - !strncmp(sdev->model, hp_sw_dh_data_list[i].model, - strlen(hp_sw_dh_data_list[i].model))) { - return true; - } - } - return false; -} - static struct scsi_dh_data *hp_sw_bus_attach(struct scsi_device *sdev) { struct hp_sw_dh_data *h; @@ -379,7 +350,6 @@ static struct scsi_device_handler hp_sw_dh = { .detach = hp_sw_bus_detach, .activate = hp_sw_activate, .prep_fn = hp_sw_prep_fn, - .match = hp_sw_match, }; static int __init hp_sw_init(void) diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c index b46ace3d4bf0..d89616fe3ffa 100644 --- a/drivers/scsi/device_handler/scsi_dh_rdac.c +++ b/drivers/scsi/device_handler/scsi_dh_rdac.c @@ -778,55 +778,6 @@ static int rdac_check_sense(struct scsi_device *sdev, return SCSI_RETURN_NOT_HANDLED; } -static const struct { - char *vendor; - char *model; -} rdac_dev_list[] = { - {"IBM", "1722"}, - {"IBM", "1724"}, - {"IBM", "1726"}, - {"IBM", "1742"}, - {"IBM", "1745"}, - {"IBM", "1746"}, - {"IBM", "1813"}, - {"IBM", "1814"}, - {"IBM", "1815"}, - {"IBM", "1818"}, - {"IBM", "3526"}, - {"SGI", "TP9"}, - {"SGI", "IS"}, - {"STK", "OPENstorage D280"}, - {"STK", "FLEXLINE 380"}, - {"SUN", "CSM"}, - {"SUN", "LCSM100"}, - {"SUN", "STK6580_6780"}, - {"SUN", "SUN_6180"}, - {"SUN", "ArrayStorage"}, - {"DELL", "MD3"}, - {"NETAPP", "INF-01-00"}, - {"LSI", "INF-01-00"}, - {"ENGENIO", "INF-01-00"}, - {NULL, NULL}, -}; - -static bool rdac_match(struct scsi_device *sdev) -{ - int i; - - if (scsi_device_tpgs(sdev)) - return false; - - for (i = 0; rdac_dev_list[i].vendor; i++) { - if (!strncmp(sdev->vendor, rdac_dev_list[i].vendor, - strlen(rdac_dev_list[i].vendor)) && - !strncmp(sdev->model, rdac_dev_list[i].model, - strlen(rdac_dev_list[i].model))) { - return true; - } - } - return false; -} - static struct scsi_dh_data *rdac_bus_attach(struct scsi_device *sdev) { struct rdac_dh_data *h; @@ -895,7 +846,6 @@ static struct scsi_device_handler rdac_dh = { .attach = rdac_bus_attach, .detach = rdac_bus_detach, .activate = rdac_activate, - .match = rdac_match, }; static int __init rdac_init(void) diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c index f0dfdccc060e..9c153309c96b 100644 --- a/drivers/scsi/scsi_dh.c +++ b/drivers/scsi/scsi_dh.c @@ -29,6 +29,67 @@ static DEFINE_SPINLOCK(list_lock); static LIST_HEAD(scsi_dh_list); +struct scsi_dh_blist { + const char *vendor; + const char *model; + const char *driver; +}; + +static const struct scsi_dh_blist scsi_dh_blist[] = { + {"DGC", "RAID", "clariion" }, + {"DGC", "DISK", "clariion" }, + {"DGC", "VRAID", "clariion" }, + + {"COMPAQ", "MSA1000 VOLUME", "hp_sw" }, + {"COMPAQ", "HSV110", "hp_sw" }, + {"HP", "HSV100", "hp_sw"}, + {"DEC", "HSG80", "hp_sw"}, + + {"IBM", "1722", "rdac", }, + {"IBM", "1724", "rdac", }, + {"IBM", "1726", "rdac", }, + {"IBM", "1742", "rdac", }, + {"IBM", "1745", "rdac", }, + {"IBM", "1746", "rdac", }, + {"IBM", "1813", "rdac", }, + {"IBM", "1814", "rdac", }, + {"IBM", "1815", "rdac", }, + {"IBM", "1818", "rdac", }, + {"IBM", "3526", "rdac", }, + {"SGI", "TP9", "rdac", }, + {"SGI", "IS", "rdac", }, + {"STK", "OPENstorage D280", "rdac", }, + {"STK", "FLEXLINE 380", "rdac", }, + {"SUN", "CSM", "rdac", }, + {"SUN", "LCSM100", "rdac", }, + {"SUN", "STK6580_6780", "rdac", }, + {"SUN", "SUN_6180", "rdac", }, + {"SUN", "ArrayStorage", "rdac", }, + {"DELL", "MD3", "rdac", }, + {"NETAPP", "INF-01-00", "rdac", }, + {"LSI", "INF-01-00", "rdac", }, + {"ENGENIO", "INF-01-00", "rdac", }, + {NULL, NULL, NULL }, +}; + +static const char * +scsi_dh_find_driver(struct scsi_device *sdev) +{ + const struct scsi_dh_blist *b; + + if (scsi_device_tpgs(sdev)) + return "alua"; + + for (b = scsi_dh_blist; b->vendor; b++) { + if (!strncmp(sdev->vendor, b->vendor, strlen(b->vendor)) && + !strncmp(sdev->model, b->model, strlen(b->model))) { + return b->driver; + } + } + return NULL; +} + + static struct scsi_device_handler *__scsi_dh_lookup(const char *name) { struct scsi_device_handler *tmp, *found = NULL; @@ -57,22 +118,6 @@ static struct scsi_device_handler *scsi_dh_lookup(const char *name) return dh; } -static struct scsi_device_handler * -device_handler_match(struct scsi_device *sdev) -{ - struct scsi_device_handler *tmp_dh, *found_dh = NULL; - - spin_lock(&list_lock); - list_for_each_entry(tmp_dh, &scsi_dh_list, list) { - if (tmp_dh->match && tmp_dh->match(sdev)) { - found_dh = tmp_dh; - break; - } - } - spin_unlock(&list_lock); - return found_dh; -} - /* * scsi_dh_handler_attach - Attach a device handler to a device * @sdev - SCSI device the device handler should attach to @@ -184,14 +229,17 @@ static struct device_attribute scsi_dh_state_attr = int scsi_dh_add_device(struct scsi_device *sdev) { - struct scsi_device_handler *devinfo; + struct scsi_device_handler *devinfo = NULL; + const char *drv; int err; err = device_create_file(&sdev->sdev_gendev, &scsi_dh_state_attr); if (err) return err; - devinfo = device_handler_match(sdev); + drv = scsi_dh_find_driver(sdev); + if (drv) + devinfo = scsi_dh_lookup(drv); if (devinfo) err = scsi_dh_handler_attach(sdev, devinfo); return err; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 798d67994aeb..4d501b7baa9b 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -215,7 +215,6 @@ struct scsi_device_handler { int (*activate)(struct scsi_device *, activate_complete, void *); int (*prep_fn)(struct scsi_device *, struct request *); int (*set_params)(struct scsi_device *, const char *); - bool (*match)(struct scsi_device *); }; struct scsi_dh_data { -- cgit v1.2.3 From ee14c674e8fc57251223054fb52dc0ecfe711028 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 27 Aug 2015 14:16:59 +0200 Subject: scsi_dh: kill struct scsi_dh_data Add a ->handler and a ->handler_data field to struct scsi_device and kill this indirection. Also move struct scsi_device_handler to scsi_dh.h so that changes to it don't require rebuilding every SCSI LLDD. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: James Bottomley --- drivers/scsi/device_handler/scsi_dh_alua.c | 25 ++++------ drivers/scsi/device_handler/scsi_dh_emc.c | 29 +++++------ drivers/scsi/device_handler/scsi_dh_hp_sw.c | 25 ++++------ drivers/scsi/device_handler/scsi_dh_rdac.c | 30 +++++------- drivers/scsi/scsi_dh.c | 75 +++++++++++------------------ drivers/scsi/scsi_error.c | 6 +-- drivers/scsi/scsi_lib.c | 6 +-- include/scsi/scsi_device.h | 25 ++-------- include/scsi/scsi_dh.h | 17 +++++++ 9 files changed, 98 insertions(+), 140 deletions(-) (limited to 'include') diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index ace2457747a7..cc2773b5de68 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -62,7 +62,6 @@ #define ALUA_OPTIMIZE_STPG 1 struct alua_dh_data { - struct scsi_dh_data dh_data; int group_id; int rel_port; int tpgs; @@ -86,11 +85,6 @@ struct alua_dh_data { static char print_alua_state(int); static int alua_check_sense(struct scsi_device *, struct scsi_sense_hdr *); -static inline struct alua_dh_data *get_alua_data(struct scsi_device *sdev) -{ - return container_of(sdev->scsi_dh_data, struct alua_dh_data, dh_data); -} - static int realloc_buffer(struct alua_dh_data *h, unsigned len) { if (h->buff && h->buff != h->inq) @@ -708,7 +702,7 @@ out: */ static int alua_set_params(struct scsi_device *sdev, const char *params) { - struct alua_dh_data *h = get_alua_data(sdev); + struct alua_dh_data *h = sdev->handler_data; unsigned int optimize = 0, argc; const char *p = params; int result = SCSI_DH_OK; @@ -746,7 +740,7 @@ MODULE_PARM_DESC(optimize_stpg, "Allow use of a non-optimized path, rather than static int alua_activate(struct scsi_device *sdev, activate_complete fn, void *data) { - struct alua_dh_data *h = get_alua_data(sdev); + struct alua_dh_data *h = sdev->handler_data; int err = SCSI_DH_OK; int stpg = 0; @@ -804,7 +798,7 @@ out: */ static int alua_prep_fn(struct scsi_device *sdev, struct request *req) { - struct alua_dh_data *h = get_alua_data(sdev); + struct alua_dh_data *h = sdev->handler_data; int ret = BLKPREP_OK; if (h->state == TPGS_STATE_TRANSITIONING) @@ -823,14 +817,14 @@ static int alua_prep_fn(struct scsi_device *sdev, struct request *req) * alua_bus_attach - Attach device handler * @sdev: device to be attached to */ -static struct scsi_dh_data *alua_bus_attach(struct scsi_device *sdev) +static int alua_bus_attach(struct scsi_device *sdev) { struct alua_dh_data *h; int err; h = kzalloc(sizeof(*h) , GFP_KERNEL); if (!h) - return ERR_PTR(-ENOMEM); + return -ENOMEM; h->tpgs = TPGS_MODE_UNINITIALIZED; h->state = TPGS_STATE_OPTIMIZED; h->group_id = -1; @@ -843,11 +837,11 @@ static struct scsi_dh_data *alua_bus_attach(struct scsi_device *sdev) if (err != SCSI_DH_OK && err != SCSI_DH_DEV_OFFLINED) goto failed; - sdev_printk(KERN_NOTICE, sdev, "%s: Attached\n", ALUA_DH_NAME); - return &h->dh_data; + sdev->handler_data = h; + return 0; failed: kfree(h); - return ERR_PTR(-EINVAL); + return -EINVAL; } /* @@ -856,10 +850,11 @@ failed: */ static void alua_bus_detach(struct scsi_device *sdev) { - struct alua_dh_data *h = get_alua_data(sdev); + struct alua_dh_data *h = sdev->handler_data; if (h->buff && h->inq != h->buff) kfree(h->buff); + sdev->handler_data = NULL; kfree(h); } diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c index fd31e67e9f50..e6fb97cb12f4 100644 --- a/drivers/scsi/device_handler/scsi_dh_emc.c +++ b/drivers/scsi/device_handler/scsi_dh_emc.c @@ -72,7 +72,6 @@ static const char * lun_state[] = }; struct clariion_dh_data { - struct scsi_dh_data dh_data; /* * Flags: * CLARIION_SHORT_TRESPASS @@ -114,13 +113,6 @@ struct clariion_dh_data { int current_sp; }; -static inline struct clariion_dh_data - *get_clariion_data(struct scsi_device *sdev) -{ - return container_of(sdev->scsi_dh_data, struct clariion_dh_data, - dh_data); -} - /* * Parse MODE_SELECT cmd reply. */ @@ -450,7 +442,7 @@ static int clariion_check_sense(struct scsi_device *sdev, static int clariion_prep_fn(struct scsi_device *sdev, struct request *req) { - struct clariion_dh_data *h = get_clariion_data(sdev); + struct clariion_dh_data *h = sdev->handler_data; int ret = BLKPREP_OK; if (h->lun_state != CLARIION_LUN_OWNED) { @@ -533,7 +525,7 @@ retry: static int clariion_activate(struct scsi_device *sdev, activate_complete fn, void *data) { - struct clariion_dh_data *csdev = get_clariion_data(sdev); + struct clariion_dh_data *csdev = sdev->handler_data; int result; result = clariion_send_inquiry(sdev, csdev); @@ -574,7 +566,7 @@ done: */ static int clariion_set_params(struct scsi_device *sdev, const char *params) { - struct clariion_dh_data *csdev = get_clariion_data(sdev); + struct clariion_dh_data *csdev = sdev->handler_data; unsigned int hr = 0, st = 0, argc; const char *p = params; int result = SCSI_DH_OK; @@ -622,14 +614,14 @@ done: return result; } -static struct scsi_dh_data *clariion_bus_attach(struct scsi_device *sdev) +static int clariion_bus_attach(struct scsi_device *sdev) { struct clariion_dh_data *h; int err; h = kzalloc(sizeof(*h) , GFP_KERNEL); if (!h) - return ERR_PTR(-ENOMEM); + return -ENOMEM; h->lun_state = CLARIION_LUN_UNINITIALIZED; h->default_sp = CLARIION_UNBOUND_LU; h->current_sp = CLARIION_UNBOUND_LU; @@ -647,18 +639,19 @@ static struct scsi_dh_data *clariion_bus_attach(struct scsi_device *sdev) CLARIION_NAME, h->current_sp + 'A', h->port, lun_state[h->lun_state], h->default_sp + 'A'); - return &h->dh_data; + + sdev->handler_data = h; + return 0; failed: kfree(h); - return ERR_PTR(-EINVAL); + return -EINVAL; } static void clariion_bus_detach(struct scsi_device *sdev) { - struct clariion_dh_data *h = get_clariion_data(sdev); - - kfree(h); + kfree(sdev->handler_data); + sdev->handler_data = NULL; } static struct scsi_device_handler clariion_dh = { diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c index 1bf10d37289a..9406d5f4a3d3 100644 --- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c +++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c @@ -38,7 +38,6 @@ #define HP_SW_PATH_PASSIVE 1 struct hp_sw_dh_data { - struct scsi_dh_data dh_data; unsigned char sense[SCSI_SENSE_BUFFERSIZE]; int path_state; int retries; @@ -50,11 +49,6 @@ struct hp_sw_dh_data { static int hp_sw_start_stop(struct hp_sw_dh_data *); -static inline struct hp_sw_dh_data *get_hp_sw_data(struct scsi_device *sdev) -{ - return container_of(sdev->scsi_dh_data, struct hp_sw_dh_data, dh_data); -} - /* * tur_done - Handle TEST UNIT READY return status * @sdev: sdev the command has been sent to @@ -267,7 +261,7 @@ static int hp_sw_start_stop(struct hp_sw_dh_data *h) static int hp_sw_prep_fn(struct scsi_device *sdev, struct request *req) { - struct hp_sw_dh_data *h = get_hp_sw_data(sdev); + struct hp_sw_dh_data *h = sdev->handler_data; int ret = BLKPREP_OK; if (h->path_state != HP_SW_PATH_ACTIVE) { @@ -292,7 +286,7 @@ static int hp_sw_activate(struct scsi_device *sdev, activate_complete fn, void *data) { int ret = SCSI_DH_OK; - struct hp_sw_dh_data *h = get_hp_sw_data(sdev); + struct hp_sw_dh_data *h = sdev->handler_data; ret = hp_sw_tur(sdev, h); @@ -311,14 +305,14 @@ static int hp_sw_activate(struct scsi_device *sdev, return 0; } -static struct scsi_dh_data *hp_sw_bus_attach(struct scsi_device *sdev) +static int hp_sw_bus_attach(struct scsi_device *sdev) { struct hp_sw_dh_data *h; int ret; h = kzalloc(sizeof(*h), GFP_KERNEL); if (!h) - return ERR_PTR(-ENOMEM); + return -ENOMEM; h->path_state = HP_SW_PATH_UNINITIALIZED; h->retries = HP_SW_RETRIES; h->sdev = sdev; @@ -330,17 +324,18 @@ static struct scsi_dh_data *hp_sw_bus_attach(struct scsi_device *sdev) sdev_printk(KERN_INFO, sdev, "%s: attached to %s path\n", HP_SW_NAME, h->path_state == HP_SW_PATH_ACTIVE? "active":"passive"); - return &h->dh_data; + + sdev->handler_data = h; + return 0; failed: kfree(h); - return ERR_PTR(-EINVAL); + return -EINVAL; } static void hp_sw_bus_detach( struct scsi_device *sdev ) { - struct hp_sw_dh_data *h = get_hp_sw_data(sdev); - - kfree(h); + kfree(sdev->handler_data); + sdev->handler_data = NULL; } static struct scsi_device_handler hp_sw_dh = { diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c index d89616fe3ffa..361358134315 100644 --- a/drivers/scsi/device_handler/scsi_dh_rdac.c +++ b/drivers/scsi/device_handler/scsi_dh_rdac.c @@ -181,7 +181,6 @@ struct c2_inquiry { }; struct rdac_dh_data { - struct scsi_dh_data dh_data; struct rdac_controller *ctlr; #define UNINITIALIZED_LUN (1 << 8) unsigned lun; @@ -260,11 +259,6 @@ do { \ sdev_printk(KERN_INFO, sdev, RDAC_NAME ": " f "\n", ## arg); \ } while (0); -static inline struct rdac_dh_data *get_rdac_data(struct scsi_device *sdev) -{ - return container_of(sdev->scsi_dh_data, struct rdac_dh_data, dh_data); -} - static struct request *get_rdac_req(struct scsi_device *sdev, void *buffer, unsigned buflen, int rw) { @@ -544,7 +538,7 @@ static int mode_select_handle_sense(struct scsi_device *sdev, { struct scsi_sense_hdr sense_hdr; int err = SCSI_DH_IO, ret; - struct rdac_dh_data *h = get_rdac_data(sdev); + struct rdac_dh_data *h = sdev->handler_data; ret = scsi_normalize_sense(sensebuf, SCSI_SENSE_BUFFERSIZE, &sense_hdr); if (!ret) @@ -589,7 +583,7 @@ static void send_mode_select(struct work_struct *work) container_of(work, struct rdac_controller, ms_work); struct request *rq; struct scsi_device *sdev = ctlr->ms_sdev; - struct rdac_dh_data *h = get_rdac_data(sdev); + struct rdac_dh_data *h = sdev->handler_data; struct request_queue *q = sdev->request_queue; int err, retry_cnt = RDAC_RETRY_COUNT; struct rdac_queue_data *tmp, *qdata; @@ -648,7 +642,7 @@ static int queue_mode_select(struct scsi_device *sdev, if (!qdata) return SCSI_DH_RETRY; - qdata->h = get_rdac_data(sdev); + qdata->h = sdev->handler_data; qdata->callback_fn = fn; qdata->callback_data = data; @@ -667,7 +661,7 @@ static int queue_mode_select(struct scsi_device *sdev, static int rdac_activate(struct scsi_device *sdev, activate_complete fn, void *data) { - struct rdac_dh_data *h = get_rdac_data(sdev); + struct rdac_dh_data *h = sdev->handler_data; int err = SCSI_DH_OK; int act = 0; @@ -702,7 +696,7 @@ done: static int rdac_prep_fn(struct scsi_device *sdev, struct request *req) { - struct rdac_dh_data *h = get_rdac_data(sdev); + struct rdac_dh_data *h = sdev->handler_data; int ret = BLKPREP_OK; if (h->state != RDAC_STATE_ACTIVE) { @@ -716,7 +710,7 @@ static int rdac_prep_fn(struct scsi_device *sdev, struct request *req) static int rdac_check_sense(struct scsi_device *sdev, struct scsi_sense_hdr *sense_hdr) { - struct rdac_dh_data *h = get_rdac_data(sdev); + struct rdac_dh_data *h = sdev->handler_data; RDAC_LOG(RDAC_LOG_SENSE, sdev, "array %s, ctlr %d, " "I/O returned with sense %02x/%02x/%02x", @@ -778,7 +772,7 @@ static int rdac_check_sense(struct scsi_device *sdev, return SCSI_RETURN_NOT_HANDLED; } -static struct scsi_dh_data *rdac_bus_attach(struct scsi_device *sdev) +static int rdac_bus_attach(struct scsi_device *sdev) { struct rdac_dh_data *h; int err; @@ -787,7 +781,7 @@ static struct scsi_dh_data *rdac_bus_attach(struct scsi_device *sdev) h = kzalloc(sizeof(*h) , GFP_KERNEL); if (!h) - return ERR_PTR(-ENOMEM); + return -ENOMEM; h->lun = UNINITIALIZED_LUN; h->state = RDAC_STATE_ACTIVE; @@ -812,7 +806,8 @@ static struct scsi_dh_data *rdac_bus_attach(struct scsi_device *sdev) RDAC_NAME, h->lun, mode[(int)h->mode], lun_state[(int)h->lun_state]); - return &h->dh_data; + sdev->handler_data = h; + return 0; clean_ctlr: spin_lock(&list_lock); @@ -821,12 +816,12 @@ clean_ctlr: failed: kfree(h); - return ERR_PTR(-EINVAL); + return -EINVAL; } static void rdac_bus_detach( struct scsi_device *sdev ) { - struct rdac_dh_data *h = get_rdac_data(sdev); + struct rdac_dh_data *h = sdev->handler_data; if (h->ctlr && h->ctlr->ms_queued) flush_workqueue(kmpath_rdacd); @@ -835,6 +830,7 @@ static void rdac_bus_detach( struct scsi_device *sdev ) if (h->ctlr) kref_put(&h->ctlr->kref, release_controller); spin_unlock(&list_lock); + sdev->handler_data = NULL; kfree(h); } diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c index 9c153309c96b..33c1148ff3b5 100644 --- a/drivers/scsi/scsi_dh.c +++ b/drivers/scsi/scsi_dh.c @@ -126,26 +126,20 @@ static struct scsi_device_handler *scsi_dh_lookup(const char *name) static int scsi_dh_handler_attach(struct scsi_device *sdev, struct scsi_device_handler *scsi_dh) { - struct scsi_dh_data *d; + int error; if (!try_module_get(scsi_dh->module)) return -EINVAL; - d = scsi_dh->attach(sdev); - if (IS_ERR(d)) { - sdev_printk(KERN_ERR, sdev, "%s: Attach failed (%ld)\n", - scsi_dh->name, PTR_ERR(d)); + error = scsi_dh->attach(sdev); + if (error) { + sdev_printk(KERN_ERR, sdev, "%s: Attach failed (%d)\n", + scsi_dh->name, error); module_put(scsi_dh->module); - return PTR_ERR(d); - } - - d->scsi_dh = scsi_dh; - d->sdev = sdev; + } else + sdev->handler = scsi_dh; - spin_lock_irq(sdev->request_queue->queue_lock); - sdev->scsi_dh_data = d; - spin_unlock_irq(sdev->request_queue->queue_lock); - return 0; + return error; } /* @@ -154,17 +148,9 @@ static int scsi_dh_handler_attach(struct scsi_device *sdev, */ static void scsi_dh_handler_detach(struct scsi_device *sdev) { - struct scsi_dh_data *scsi_dh_data = sdev->scsi_dh_data; - struct scsi_device_handler *scsi_dh = scsi_dh_data->scsi_dh; - - scsi_dh->detach(sdev); - - spin_lock_irq(sdev->request_queue->queue_lock); - sdev->scsi_dh_data = NULL; - spin_unlock_irq(sdev->request_queue->queue_lock); - - sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", scsi_dh->name); - module_put(scsi_dh->module); + sdev->handler->detach(sdev); + sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", sdev->handler->name); + module_put(sdev->handler->module); } /* @@ -182,7 +168,7 @@ store_dh_state(struct device *dev, struct device_attribute *attr, sdev->sdev_state == SDEV_DEL) return -ENODEV; - if (!sdev->scsi_dh_data) { + if (!sdev->handler) { /* * Attach to a device handler */ @@ -191,7 +177,6 @@ store_dh_state(struct device *dev, struct device_attribute *attr, return err; err = scsi_dh_handler_attach(sdev, scsi_dh); } else { - scsi_dh = sdev->scsi_dh_data->scsi_dh; if (!strncmp(buf, "detach", 6)) { /* * Detach from a device handler @@ -202,8 +187,8 @@ store_dh_state(struct device *dev, struct device_attribute *attr, /* * Activate a device handler */ - if (scsi_dh->activate) - err = scsi_dh->activate(sdev, NULL, NULL); + if (sdev->handler->activate) + err = sdev->handler->activate(sdev, NULL, NULL); else err = 0; } @@ -217,10 +202,10 @@ show_dh_state(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_device *sdev = to_scsi_device(dev); - if (!sdev->scsi_dh_data) + if (!sdev->handler) return snprintf(buf, 20, "detached\n"); - return snprintf(buf, 20, "%s\n", sdev->scsi_dh_data->scsi_dh->name); + return snprintf(buf, 20, "%s\n", sdev->handler->name); } static struct device_attribute scsi_dh_state_attr = @@ -247,7 +232,7 @@ int scsi_dh_add_device(struct scsi_device *sdev) void scsi_dh_remove_device(struct scsi_device *sdev) { - if (sdev->scsi_dh_data) + if (sdev->handler) scsi_dh_handler_detach(sdev); device_remove_file(&sdev->sdev_gendev, &scsi_dh_state_attr); } @@ -316,7 +301,6 @@ int scsi_dh_activate(struct request_queue *q, activate_complete fn, void *data) int err = 0; unsigned long flags; struct scsi_device *sdev; - struct scsi_device_handler *scsi_dh = NULL; struct device *dev = NULL; spin_lock_irqsave(q->queue_lock, flags); @@ -329,10 +313,8 @@ int scsi_dh_activate(struct request_queue *q, activate_complete fn, void *data) return err; } - if (sdev->scsi_dh_data) - scsi_dh = sdev->scsi_dh_data->scsi_dh; dev = get_device(&sdev->sdev_gendev); - if (!scsi_dh || !dev || + if (!sdev->handler || !dev || sdev->sdev_state == SDEV_CANCEL || sdev->sdev_state == SDEV_DEL) err = SCSI_DH_NOSYS; @@ -346,8 +328,8 @@ int scsi_dh_activate(struct request_queue *q, activate_complete fn, void *data) goto out; } - if (scsi_dh->activate) - err = scsi_dh->activate(sdev, fn, data); + if (sdev->handler->activate) + err = sdev->handler->activate(sdev, fn, data); out: put_device(dev); return err; @@ -369,19 +351,18 @@ int scsi_dh_set_params(struct request_queue *q, const char *params) int err = -SCSI_DH_NOSYS; unsigned long flags; struct scsi_device *sdev; - struct scsi_device_handler *scsi_dh = NULL; spin_lock_irqsave(q->queue_lock, flags); sdev = q->queuedata; - if (sdev && sdev->scsi_dh_data) - scsi_dh = sdev->scsi_dh_data->scsi_dh; - if (scsi_dh && scsi_dh->set_params && get_device(&sdev->sdev_gendev)) + if (sdev->handler && + sdev->handler->set_params && + get_device(&sdev->sdev_gendev)) err = 0; spin_unlock_irqrestore(q->queue_lock, flags); if (err) return err; - err = scsi_dh->set_params(sdev, params); + err = sdev->handler->set_params(sdev, params); put_device(&sdev->sdev_gendev); return err; } @@ -413,8 +394,8 @@ int scsi_dh_attach(struct request_queue *q, const char *name) if (err) return err; - if (sdev->scsi_dh_data) { - if (sdev->scsi_dh_data->scsi_dh != scsi_dh) + if (sdev->handler) { + if (sdev->handler != scsi_dh) err = -EBUSY; goto out_put_device; } @@ -451,8 +432,8 @@ const char *scsi_dh_attached_handler_name(struct request_queue *q, gfp_t gfp) if (!sdev) return NULL; - if (sdev->scsi_dh_data) - handler_name = kstrdup(sdev->scsi_dh_data->scsi_dh->name, gfp); + if (sdev->handler) + handler_name = kstrdup(sdev->handler->name, gfp); put_device(&sdev->sdev_gendev); return handler_name; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 3aacd96d63f3..410911c31c67 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include "scsi_priv.h" @@ -464,11 +465,10 @@ static int scsi_check_sense(struct scsi_cmnd *scmd) if (scsi_sense_is_deferred(&sshdr)) return NEEDS_RETRY; - if (sdev->scsi_dh_data && sdev->scsi_dh_data->scsi_dh && - sdev->scsi_dh_data->scsi_dh->check_sense) { + if (sdev->handler && sdev->handler->check_sense) { int rc; - rc = sdev->scsi_dh_data->scsi_dh->check_sense(sdev, &sshdr); + rc = sdev->handler->check_sense(sdev, &sshdr); if (rc != SCSI_RETURN_NOT_HANDLED) return rc; /* handler does not care. Drop down to default handling */ diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 882864f5cbae..cbfc5990052b 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -31,6 +31,7 @@ #include #include #include +#include #include @@ -1248,9 +1249,8 @@ static int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req) { struct scsi_cmnd *cmd = req->special; - if (unlikely(sdev->scsi_dh_data && sdev->scsi_dh_data->scsi_dh - && sdev->scsi_dh_data->scsi_dh->prep_fn)) { - int ret = sdev->scsi_dh_data->scsi_dh->prep_fn(sdev, req); + if (unlikely(sdev->handler && sdev->handler->prep_fn)) { + int ret = sdev->handler->prep_fn(sdev, req); if (ret != BLKPREP_OK) return ret; } diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 4d501b7baa9b..fe89d7cd67b9 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -196,32 +196,13 @@ struct scsi_device { struct execute_work ew; /* used to get process context on put */ struct work_struct requeue_work; - struct scsi_dh_data *scsi_dh_data; + struct scsi_device_handler *handler; + void *handler_data; + enum scsi_device_state sdev_state; unsigned long sdev_data[0]; } __attribute__((aligned(sizeof(unsigned long)))); -typedef void (*activate_complete)(void *, int); -struct scsi_device_handler { - /* Used by the infrastructure */ - struct list_head list; /* list of scsi_device_handlers */ - - /* Filled by the hardware handler */ - struct module *module; - const char *name; - int (*check_sense)(struct scsi_device *, struct scsi_sense_hdr *); - struct scsi_dh_data *(*attach)(struct scsi_device *); - void (*detach)(struct scsi_device *); - int (*activate)(struct scsi_device *, activate_complete, void *); - int (*prep_fn)(struct scsi_device *, struct request *); - int (*set_params)(struct scsi_device *, const char *); -}; - -struct scsi_dh_data { - struct scsi_device_handler *scsi_dh; - struct scsi_device *sdev; -}; - #define to_scsi_device(d) \ container_of(d, struct scsi_device, sdev_gendev) #define class_to_sdev(d) \ diff --git a/include/scsi/scsi_dh.h b/include/scsi/scsi_dh.h index 3a37b4c45997..85d731746834 100644 --- a/include/scsi/scsi_dh.h +++ b/include/scsi/scsi_dh.h @@ -55,6 +55,23 @@ enum { SCSI_DH_NOSYS, SCSI_DH_DRIVER_MAX, }; + +typedef void (*activate_complete)(void *, int); +struct scsi_device_handler { + /* Used by the infrastructure */ + struct list_head list; /* list of scsi_device_handlers */ + + /* Filled by the hardware handler */ + struct module *module; + const char *name; + int (*check_sense)(struct scsi_device *, struct scsi_sense_hdr *); + int (*attach)(struct scsi_device *); + void (*detach)(struct scsi_device *); + int (*activate)(struct scsi_device *, activate_complete, void *); + int (*prep_fn)(struct scsi_device *, struct request *); + int (*set_params)(struct scsi_device *, const char *); +}; + #ifdef CONFIG_SCSI_DH extern int scsi_dh_activate(struct request_queue *, activate_complete, void *); extern int scsi_dh_attach(struct request_queue *, const char *); -- cgit v1.2.3 From b0e010c527de742cb18e8d50a06dfd1a995b5382 Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Wed, 26 Aug 2015 09:40:28 -0700 Subject: ipvs: replace ip_vs_fill_ip4hdr with ip_vs_fill_iph_skb_off This removes some duplicated code and makes the ICMPv6 path look more like the ICMP path. Signed-off-by: Alex Gartrell Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 49 +++++++++++++++++------------ net/netfilter/ipvs/ip_vs_core.c | 70 +++++++++++++++-------------------------- net/netfilter/ipvs/ip_vs_xmit.c | 15 ++++----- 3 files changed, 63 insertions(+), 71 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 9b9ca87a4210..0c8309f34982 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -104,6 +104,7 @@ static inline struct net *seq_file_single_net(struct seq_file *seq) extern int ip_vs_conn_tab_size; struct ip_vs_iphdr { + __u32 off; /* Where IP or IPv4 header starts */ __u32 len; /* IPv4 simply where L4 starts * IPv6 where L4 Transport Header starts */ __u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/ @@ -120,48 +121,56 @@ static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset, return skb_header_pointer(skb, offset, len, buffer); } -static inline void -ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr) -{ - const struct iphdr *iph = nh; - - iphdr->len = iph->ihl * 4; - iphdr->fragoffs = 0; - iphdr->protocol = iph->protocol; - iphdr->saddr.ip = iph->saddr; - iphdr->daddr.ip = iph->daddr; -} - /* This function handles filling *ip_vs_iphdr, both for IPv4 and IPv6. * IPv6 requires some extra work, as finding proper header position, * depend on the IPv6 extension headers. */ -static inline void -ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr) +static inline int +ip_vs_fill_iph_skb_off(int af, const struct sk_buff *skb, int offset, + struct ip_vs_iphdr *iphdr) { + iphdr->off = offset; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - const struct ipv6hdr *iph = - (struct ipv6hdr *)skb_network_header(skb); + struct ipv6hdr _iph; + const struct ipv6hdr *iph = skb_header_pointer( + skb, offset, sizeof(_iph), &_iph); + if (!iph) + return 0; + iphdr->saddr.in6 = iph->saddr; iphdr->daddr.in6 = iph->daddr; /* ipv6_find_hdr() updates len, flags */ - iphdr->len = 0; + iphdr->len = offset; iphdr->flags = 0; iphdr->protocol = ipv6_find_hdr(skb, &iphdr->len, -1, &iphdr->fragoffs, &iphdr->flags); + if (iphdr->protocol < 0) + return 0; } else #endif { - const struct iphdr *iph = - (struct iphdr *)skb_network_header(skb); - iphdr->len = iph->ihl * 4; + struct iphdr _iph; + const struct iphdr *iph = skb_header_pointer( + skb, offset, sizeof(_iph), &_iph); + if (!iph) + return 0; + + iphdr->len = offset + iph->ihl * 4; iphdr->fragoffs = 0; iphdr->protocol = iph->protocol; iphdr->saddr.ip = iph->saddr; iphdr->daddr.ip = iph->daddr; } + + return 1; +} + +static inline int +ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr) +{ + return ip_vs_fill_iph_skb_off(af, skb, skb_network_offset(skb), iphdr); } static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst, diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 38fbc194b9cb..b831fe84bff7 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -436,7 +436,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, * with persistence the connection is created on SYN+ACK. */ if (pptr[0] == FTPDATA) { - IP_VS_DBG_PKT(12, svc->af, pp, skb, 0, + IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling FTPDATA"); return NULL; } @@ -446,7 +446,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, */ if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) && (cp = pp->conn_in_get(svc->af, skb, iph, 1))) { - IP_VS_DBG_PKT(12, svc->af, pp, skb, 0, + IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling reply for existing connection"); __ip_vs_conn_put(cp); return NULL; @@ -934,8 +934,8 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); - ip_vs_fill_ip4hdr(cih, &ciph); - ciph.len += offset; + ip_vs_fill_iph_skb_off(AF_INET, skb, offset, &ciph); + /* The embedded headers contain source and dest in reverse order */ cp = pp->conn_out_get(AF_INET, skb, &ciph, 1); if (!cp) @@ -951,12 +951,11 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *ipvsh) { struct icmp6hdr _icmph, *ic; - struct ipv6hdr _ip6h, *ip6h; /* The ip header contained within ICMP */ struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; union nf_inet_addr snet; - unsigned int writable; + unsigned int offset; *related = 1; ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph, ipvsh); @@ -984,17 +983,9 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, ic->icmp6_type, ntohs(icmpv6_id(ic)), &ipvsh->saddr, &ipvsh->daddr); - /* Now find the contained IP header */ - ciph.len = ipvsh->len + sizeof(_icmph); - ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h); - if (ip6h == NULL) + if (!ip_vs_fill_iph_skb_off(AF_INET6, skb, ipvsh->len + sizeof(_icmph), + &ciph)) return NF_ACCEPT; /* The packet looks wrong, ignore */ - ciph.saddr.in6 = ip6h->saddr; /* conn_out_get() handles reverse order */ - ciph.daddr.in6 = ip6h->daddr; - /* skip possible IPv6 exthdrs of contained IPv6 packet */ - ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL); - if (ciph.protocol < 0) - return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */ pp = ip_vs_proto_get(ciph.protocol); if (!pp) @@ -1006,9 +997,9 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, return NF_ACCEPT; snet.in6 = ciph.saddr.in6; - writable = ciph.len; + offset = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, - pp, writable, sizeof(struct ipv6hdr), + pp, offset, sizeof(struct ipv6hdr), hooknum); } #endif @@ -1093,7 +1084,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, { struct ip_vs_protocol *pp = pd->pp; - IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet"); + IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet"); if (!skb_make_writable(skb, iph->len)) goto drop; @@ -1130,7 +1121,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, if (ip_vs_route_me_harder(af, skb, hooknum)) goto drop; - IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT"); + IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT"); ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); @@ -1221,7 +1212,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_defrag_user(hooknum))) return NF_STOLEN; - ip_vs_fill_ip4hdr(skb_network_header(skb), &iph); + ip_vs_fill_iph_skb(AF_INET, skb, &iph); } /* @@ -1272,7 +1263,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) } } } - IP_VS_DBG_PKT(12, af, pp, skb, 0, + IP_VS_DBG_PKT(12, af, pp, skb, iph.off, "ip_vs_out: packet continues traversal as normal"); return NF_ACCEPT; } @@ -1416,9 +1407,9 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) "Checking incoming ICMP for"); offset2 = offset; - ip_vs_fill_ip4hdr(cih, &ciph); - ciph.len += offset; + ip_vs_fill_iph_skb_off(AF_INET, skb, offset, &ciph); offset = ciph.len; + /* The embedded headers contain source and dest in reverse order. * For IPIP this is error for request, not for reply. */ @@ -1511,13 +1502,12 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *iph) { struct net *net = NULL; - struct ipv6hdr _ip6h, *ip6h; struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; - unsigned int offs_ciph, writable, verdict; + unsigned int offset, verdict; *related = 1; @@ -1546,18 +1536,9 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, ic->icmp6_type, ntohs(icmpv6_id(ic)), &iph->saddr, &iph->daddr); - /* Now find the contained IP header */ - ciph.len = iph->len + sizeof(_icmph); - offs_ciph = ciph.len; /* Save ip header offset */ - ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h); - if (ip6h == NULL) - return NF_ACCEPT; /* The packet looks wrong, ignore */ - ciph.saddr.in6 = ip6h->saddr; /* conn_in_get() handles reverse order */ - ciph.daddr.in6 = ip6h->daddr; - /* skip possible IPv6 exthdrs of contained IPv6 packet */ - ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL); - if (ciph.protocol < 0) - return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */ + offset = iph->len + sizeof(_icmph); + if (!ip_vs_fill_iph_skb_off(AF_INET6, skb, offset, &ciph)) + return NF_ACCEPT; net = skb_net(skb); pd = ip_vs_proto_data_get(net, ciph.protocol); @@ -1569,7 +1550,7 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, if (ciph.fragoffs) return NF_ACCEPT; - IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offs_ciph, + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, "Checking incoming ICMPv6 for"); /* The embedded headers contain source and dest in reverse order @@ -1591,12 +1572,12 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, ip_vs_in_stats(cp, skb); /* Need to mangle contained IPv6 header in ICMPv6 packet */ - writable = ciph.len; + offset = ciph.len; if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol || IPPROTO_SCTP == ciph.protocol) - writable += 2 * sizeof(__u16); /* Also mangle ports */ + offset += 2 * sizeof(__u16); /* Also mangle ports */ - verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, writable, hooknum, &ciph); + verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph); __ip_vs_conn_put(cp); @@ -1720,12 +1701,13 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) * is missing module nf_defrag_ipv6 */ IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n"); - IP_VS_DBG_PKT(7, af, pp, skb, 0, "unhandled fragment"); + IP_VS_DBG_PKT(7, af, pp, skb, iph.off, + "unhandled fragment"); } return NF_ACCEPT; } - IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); + IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet"); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 258a0b0e82a2..9a26f2ea86d9 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -723,7 +723,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { - IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0, + IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, ipvsh->off, "ip_vs_nat_xmit(): " "stopping DNAT to local address"); goto tx_error; @@ -733,8 +733,9 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* From world but DNAT to loopback address? */ if (local && ipv4_is_loopback(cp->daddr.ip) && was_input) { - IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): " - "stopping DNAT to loopback address"); + IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, ipvsh->off, + "ip_vs_nat_xmit(): stopping DNAT to loopback " + "address"); goto tx_error; } @@ -751,7 +752,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, ip_hdr(skb)->daddr = cp->daddr.ip; ip_send_check(ip_hdr(skb)); - IP_VS_DBG_PKT(10, AF_INET, pp, skb, 0, "After DNAT"); + IP_VS_DBG_PKT(10, AF_INET, pp, skb, ipvsh->off, "After DNAT"); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still @@ -812,7 +813,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { - IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0, + IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, ipvsh->off, "ip_vs_nat_xmit_v6(): " "stopping DNAT to local address"); goto tx_error; @@ -823,7 +824,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* From world but DNAT to loopback address? */ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) { - IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0, + IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, ipvsh->off, "ip_vs_nat_xmit_v6(): " "stopping DNAT to loopback address"); goto tx_error; @@ -841,7 +842,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; ipv6_hdr(skb)->daddr = cp->daddr.in6; - IP_VS_DBG_PKT(10, AF_INET6, pp, skb, 0, "After DNAT"); + IP_VS_DBG_PKT(10, AF_INET6, pp, skb, ipvsh->off, "After DNAT"); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still -- cgit v1.2.3 From 4fd9beef37f3a14aa34cb025479a0e431dc9e58b Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Wed, 26 Aug 2015 09:40:29 -0700 Subject: ipvs: Add hdr_flags to iphdr These flags contain information like whether or not the addresses are inverted or from icmp. The first will allow us to drop an inverse param all over the place, and the second will later be useful in scheduling icmp. Signed-off-by: Alex Gartrell Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 43 ++++++++++++++++++++++++++++++++++++--- net/netfilter/ipvs/ip_vs_core.c | 20 +++++++++--------- net/netfilter/ipvs/ip_vs_pe_sip.c | 2 +- net/netfilter/xt_ipvs.c | 2 +- 4 files changed, 52 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 0c8309f34982..ac336a79ad3d 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -29,6 +29,9 @@ #endif #include /* Netw namespace */ +#define IP_VS_HDR_INVERSE 1 +#define IP_VS_HDR_ICMP 2 + /* Generic access of ipvs struct */ static inline struct netns_ipvs *net_ipvs(struct net* net) { @@ -104,6 +107,7 @@ static inline struct net *seq_file_single_net(struct seq_file *seq) extern int ip_vs_conn_tab_size; struct ip_vs_iphdr { + int hdr_flags; /* ipvs flags */ __u32 off; /* Where IP or IPv4 header starts */ __u32 len; /* IPv4 simply where L4 starts * IPv6 where L4 Transport Header starts */ @@ -127,9 +131,11 @@ static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset, */ static inline int ip_vs_fill_iph_skb_off(int af, const struct sk_buff *skb, int offset, - struct ip_vs_iphdr *iphdr) + int hdr_flags, struct ip_vs_iphdr *iphdr) { + iphdr->hdr_flags = hdr_flags; iphdr->off = offset; + #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { struct ipv6hdr _iph; @@ -168,9 +174,40 @@ ip_vs_fill_iph_skb_off(int af, const struct sk_buff *skb, int offset, } static inline int -ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr) +ip_vs_fill_iph_skb_icmp(int af, const struct sk_buff *skb, int offset, + bool inverse, struct ip_vs_iphdr *iphdr) +{ + int hdr_flags = IP_VS_HDR_ICMP; + + if (inverse) + hdr_flags |= IP_VS_HDR_INVERSE; + + return ip_vs_fill_iph_skb_off(af, skb, offset, hdr_flags, iphdr); +} + +static inline int +ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, bool inverse, + struct ip_vs_iphdr *iphdr) +{ + int hdr_flags = 0; + + if (inverse) + hdr_flags |= IP_VS_HDR_INVERSE; + + return ip_vs_fill_iph_skb_off(af, skb, skb_network_offset(skb), + hdr_flags, iphdr); +} + +static inline bool +ip_vs_iph_inverse(const struct ip_vs_iphdr *iph) +{ + return !!(iph->hdr_flags & IP_VS_HDR_INVERSE); +} + +static inline bool +ip_vs_iph_icmp(const struct ip_vs_iphdr *iph) { - return ip_vs_fill_iph_skb_off(af, skb, skb_network_offset(skb), iphdr); + return !!(iph->hdr_flags & IP_VS_HDR_ICMP); } static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst, diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index b831fe84bff7..4f5d3d174517 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -934,7 +934,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); - ip_vs_fill_iph_skb_off(AF_INET, skb, offset, &ciph); + ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); /* The embedded headers contain source and dest in reverse order */ cp = pp->conn_out_get(AF_INET, skb, &ciph, 1); @@ -983,8 +983,8 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, ic->icmp6_type, ntohs(icmpv6_id(ic)), &ipvsh->saddr, &ipvsh->daddr); - if (!ip_vs_fill_iph_skb_off(AF_INET6, skb, ipvsh->len + sizeof(_icmph), - &ciph)) + if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, ipvsh->len + sizeof(_icmph), + true, &ciph)) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(ciph.protocol); @@ -1177,7 +1177,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) if (!net_ipvs(net)->enable) return NF_ACCEPT; - ip_vs_fill_iph_skb(af, skb, &iph); + ip_vs_fill_iph_skb(af, skb, false, &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { @@ -1212,7 +1212,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_defrag_user(hooknum))) return NF_STOLEN; - ip_vs_fill_iph_skb(AF_INET, skb, &iph); + ip_vs_fill_iph_skb(AF_INET, skb, false, &iph); } /* @@ -1407,7 +1407,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) "Checking incoming ICMP for"); offset2 = offset; - ip_vs_fill_iph_skb_off(AF_INET, skb, offset, &ciph); + ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !ipip, &ciph); offset = ciph.len; /* The embedded headers contain source and dest in reverse order. @@ -1537,7 +1537,7 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, &iph->saddr, &iph->daddr); offset = iph->len + sizeof(_icmph); - if (!ip_vs_fill_iph_skb_off(AF_INET6, skb, offset, &ciph)) + if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, offset, true, &ciph)) return NF_ACCEPT; net = skb_net(skb); @@ -1614,7 +1614,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) if (unlikely((skb->pkt_type != PACKET_HOST && hooknum != NF_INET_LOCAL_OUT) || !skb_dst(skb))) { - ip_vs_fill_iph_skb(af, skb, &iph); + ip_vs_fill_iph_skb(af, skb, false, &iph); IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s" " ignored in hook %u\n", skb->pkt_type, iph.protocol, @@ -1627,7 +1627,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; - ip_vs_fill_iph_skb(af, skb, &iph); + ip_vs_fill_iph_skb(af, skb, false, &iph); /* Bad... Do not break raw sockets */ if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT && @@ -1841,7 +1841,7 @@ ip_vs_forward_icmp_v6(const struct nf_hook_ops *ops, struct sk_buff *skb, struct netns_ipvs *ipvs; struct ip_vs_iphdr iphdr; - ip_vs_fill_iph_skb(AF_INET6, skb, &iphdr); + ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); if (iphdr.protocol != IPPROTO_ICMPV6) return NF_ACCEPT; diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index bed5f7042529..1b8d594e493a 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -70,7 +70,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) const char *dptr; int retc; - ip_vs_fill_iph_skb(p->af, skb, &iph); + ip_vs_fill_iph_skb(p->af, skb, false, &iph); /* Only useful with UDP */ if (iph.protocol != IPPROTO_UDP) diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c index 8d47c3780fda..370462572d84 100644 --- a/net/netfilter/xt_ipvs.c +++ b/net/netfilter/xt_ipvs.c @@ -67,7 +67,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par) goto out; } - ip_vs_fill_iph_skb(family, skb, &iph); + ip_vs_fill_iph_skb(family, skb, true, &iph); if (data->bitmask & XT_IPVS_PROTO) if ((iph.protocol == data->l4proto) ^ -- cgit v1.2.3 From 802c41adcf3be63f351c302c9665865d705cada9 Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Wed, 26 Aug 2015 09:40:32 -0700 Subject: ipvs: drop inverse argument to conn_{in,out}_get No longer necessary since the information is included in the ip_vs_iphdr itself. Signed-off-by: Alex Gartrell Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 12 ++++-------- net/netfilter/ipvs/ip_vs_conn.c | 12 ++++++------ net/netfilter/ipvs/ip_vs_core.c | 31 ++++++++++++++++++------------- net/netfilter/ipvs/ip_vs_proto_ah_esp.c | 17 ++++++++--------- net/netfilter/xt_ipvs.c | 2 +- 5 files changed, 37 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index ac336a79ad3d..ba90729d1111 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -495,14 +495,12 @@ struct ip_vs_protocol { struct ip_vs_conn * (*conn_in_get)(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse); + const struct ip_vs_iphdr *iph); struct ip_vs_conn * (*conn_out_get)(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse); + const struct ip_vs_iphdr *iph); int (*snat_handler)(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph); @@ -1232,14 +1230,12 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse); + const struct ip_vs_iphdr *iph); struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse); + const struct ip_vs_iphdr *iph); /* Get reference to gain full access to conn. * By default, RCU read-side critical sections have access only to diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index b0f7b626b56d..f71b3146a5a1 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -316,7 +316,7 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p) static int ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph, - int inverse, struct ip_vs_conn_param *p) + struct ip_vs_conn_param *p) { __be16 _ports[2], *pptr; struct net *net = skb_net(skb); @@ -325,7 +325,7 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb, if (pptr == NULL) return 1; - if (likely(!inverse)) + if (likely(!ip_vs_iph_inverse(iph))) ip_vs_conn_fill_param(net, af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1], p); else @@ -336,11 +336,11 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb, struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, int inverse) + const struct ip_vs_iphdr *iph) { struct ip_vs_conn_param p; - if (ip_vs_conn_fill_param_proto(af, skb, iph, inverse, &p)) + if (ip_vs_conn_fill_param_proto(af, skb, iph, &p)) return NULL; return ip_vs_conn_in_get(&p); @@ -440,11 +440,11 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, int inverse) + const struct ip_vs_iphdr *iph) { struct ip_vs_conn_param p; - if (ip_vs_conn_fill_param_proto(af, skb, iph, inverse, &p)) + if (ip_vs_conn_fill_param_proto(af, skb, iph, &p)) return NULL; return ip_vs_conn_out_get(&p); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 2c44e34314c2..ebfb371daa3b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -444,12 +444,18 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, /* * Do not schedule replies from local real server. */ - if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) && - (cp = pp->conn_in_get(svc->af, skb, iph, 1))) { - IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, - "Not scheduling reply for existing connection"); - __ip_vs_conn_put(cp); - return NULL; + if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK)) { + iph->hdr_flags ^= IP_VS_HDR_INVERSE; + cp = pp->conn_in_get(svc->af, skb, iph); + iph->hdr_flags ^= IP_VS_HDR_INVERSE; + + if (cp) { + IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, + "Not scheduling reply for existing" + " connection"); + __ip_vs_conn_put(cp); + return NULL; + } } /* @@ -946,7 +952,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(AF_INET, skb, &ciph, 1); + cp = pp->conn_out_get(AF_INET, skb, &ciph); if (!cp) return NF_ACCEPT; @@ -1001,7 +1007,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, return NF_ACCEPT; /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(AF_INET6, skb, &ciph, 1); + cp = pp->conn_out_get(AF_INET6, skb, &ciph); if (!cp) return NF_ACCEPT; @@ -1227,7 +1233,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(af, skb, &iph, 0); + cp = pp->conn_out_get(af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); @@ -1458,7 +1464,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) /* The embedded headers contain source and dest in reverse order. * For IPIP this is error for request, not for reply. */ - cp = pp->conn_in_get(AF_INET, skb, &ciph, ipip ? 0 : 1); + cp = pp->conn_in_get(AF_INET, skb, &ciph); if (!cp) return NF_ACCEPT; @@ -1601,8 +1607,7 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, /* The embedded headers contain source and dest in reverse order * if not from localhost */ - cp = pp->conn_in_get(AF_INET6, skb, &ciph, - (hooknum == NF_INET_LOCAL_OUT) ? 0 : 1); + cp = pp->conn_in_get(AF_INET6, skb, &ciph); if (!cp) return NF_ACCEPT; @@ -1712,7 +1717,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) /* * Check if the packet belongs to an existing connection entry */ - cp = pp->conn_in_get(af, skb, &iph, 0); + cp = pp->conn_in_get(af, skb, &iph); conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); if (conn_reuse_mode && !iph.fragoffs && diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index 5de3dd312c0f..be1791d1c03f 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -42,10 +42,10 @@ struct isakmp_hdr { static void ah_esp_conn_fill_param_proto(struct net *net, int af, - const struct ip_vs_iphdr *iph, int inverse, + const struct ip_vs_iphdr *iph, struct ip_vs_conn_param *p) { - if (likely(!inverse)) + if (likely(!ip_vs_iph_inverse(iph))) ip_vs_conn_fill_param(net, af, IPPROTO_UDP, &iph->saddr, htons(PORT_ISAKMP), &iph->daddr, htons(PORT_ISAKMP), p); @@ -57,14 +57,13 @@ ah_esp_conn_fill_param_proto(struct net *net, int af, static struct ip_vs_conn * ah_esp_conn_in_get(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse) + const struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; struct net *net = skb_net(skb); - ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p); + ah_esp_conn_fill_param_proto(net, af, iph, &p); cp = ip_vs_conn_in_get(&p); if (!cp) { /* @@ -73,7 +72,7 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, */ IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for outin packet " "%s%s %s->%s\n", - inverse ? "ICMP+" : "", + ip_vs_iph_icmp(iph) ? "ICMP+" : "", ip_vs_proto_get(iph->protocol)->name, IP_VS_DBG_ADDR(af, &iph->saddr), IP_VS_DBG_ADDR(af, &iph->daddr)); @@ -85,18 +84,18 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, static struct ip_vs_conn * ah_esp_conn_out_get(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, int inverse) + const struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; struct net *net = skb_net(skb); - ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p); + ah_esp_conn_fill_param_proto(net, af, iph, &p); cp = ip_vs_conn_out_get(&p); if (!cp) { IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet " "%s%s %s->%s\n", - inverse ? "ICMP+" : "", + ip_vs_iph_icmp(iph) ? "ICMP+" : "", ip_vs_proto_get(iph->protocol)->name, IP_VS_DBG_ADDR(af, &iph->saddr), IP_VS_DBG_ADDR(af, &iph->daddr)); diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c index 370462572d84..452ba2a3e7ae 100644 --- a/net/netfilter/xt_ipvs.c +++ b/net/netfilter/xt_ipvs.c @@ -85,7 +85,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par) /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(family, skb, &iph, 1 /* inverse */); + cp = pp->conn_out_get(family, skb, &iph); if (unlikely(cp == NULL)) { match = false; goto out; -- cgit v1.2.3 From 94485fedcb176a9105961e47bd9dda23801c1906 Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Wed, 26 Aug 2015 09:40:34 -0700 Subject: ipvs: add schedule_icmp sysctl This sysctl will be used to enable the scheduling of icmp packets. Signed-off-by: Alex Gartrell Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 11 +++++++++++ net/netfilter/ipvs/ip_vs_ctl.c | 8 +++++++- 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index ba90729d1111..47677f0493c7 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -997,6 +997,7 @@ struct netns_ipvs { int sysctl_pmtu_disc; int sysctl_backup_only; int sysctl_conn_reuse_mode; + int sysctl_schedule_icmp; /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1115,6 +1116,11 @@ static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs) return ipvs->sysctl_conn_reuse_mode; } +static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_schedule_icmp; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1187,6 +1193,11 @@ static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs) return 1; } +static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) +{ + return 0; +} + #endif /* IPVS core functions diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 1a23e91d50d8..31d80e203863 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1844,6 +1844,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "schedule_icmp", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -3895,7 +3901,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) tbl[idx++].data = &ipvs->sysctl_backup_only; ipvs->sysctl_conn_reuse_mode = 1; tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode; - + tbl[idx++].data = &ipvs->sysctl_schedule_icmp; ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); if (ipvs->sysctl_hdr == NULL) { -- cgit v1.2.3 From 9642d18eee2cd169b60c6ac0f20bda745b5a3d1e Mon Sep 17 00:00:00 2001 From: Vatika Harlalka Date: Tue, 1 Sep 2015 16:50:59 +0200 Subject: nohz: Affine unpinned timers to housekeepers The problem addressed in this patch is about affining unpinned timers. Adaptive or Full Dynticks CPUs are currently disturbed by unnecessary jitter due to firing of such timers on them. This patch will affine timers to online CPUs which are not full dynticks in NOHZ_FULL configured systems. It should not introduce overhead in nohz full off case due to static keys. Signed-off-by: Vatika Harlalka Signed-off-by: Frederic Weisbecker Reviewed-by: Preeti U Murthy Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1441119060-2230-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/tick.h | 9 +++++++++ kernel/sched/core.c | 7 +++++-- 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/tick.h b/include/linux/tick.h index 48d901f83f92..e312219ff823 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -147,11 +147,20 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) cpumask_or(mask, mask, tick_nohz_full_mask); } +static inline int housekeeping_any_cpu(void) +{ + return cpumask_any_and(housekeeping_mask, cpu_online_mask); +} + extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_cpu(int cpu); extern void tick_nohz_full_kick_all(void); extern void __tick_nohz_task_switch(void); #else +static inline int housekeeping_any_cpu(void) +{ + return smp_processor_id(); +} static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8b864ecee0e1..0902e4d72671 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -623,18 +623,21 @@ int get_nohz_timer_target(void) int i, cpu = smp_processor_id(); struct sched_domain *sd; - if (!idle_cpu(cpu)) + if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu)) return cpu; rcu_read_lock(); for_each_domain(cpu, sd) { for_each_cpu(i, sched_domain_span(sd)) { - if (!idle_cpu(i)) { + if (!idle_cpu(i) && is_housekeeping_cpu(cpu)) { cpu = i; goto unlock; } } } + + if (!is_housekeeping_cpu(cpu)) + cpu = housekeeping_any_cpu(); unlock: rcu_read_unlock(); return cpu; -- cgit v1.2.3 From 5e7c4274a70aa2d6f485996d0ca1dad52d0039ca Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 3 Sep 2015 19:28:20 +0300 Subject: block: Check for gaps on front and back merges We are checking for gaps to previous bio_vec, which can only detect back merges gaps. Moreover, at the point where we check for a gap, we don't know if we will attempt a back or a front merge. Thus, check for gap to prev in a back merge attempt and check for a gap to next in a front merge attempt. Signed-off-by: Jens Axboe [sagig: Minor rename change] Signed-off-by: Sagi Grimberg --- block/blk-merge.c | 19 ++++++------------- include/linux/blkdev.h | 20 ++++++++++++++++++++ 2 files changed, 26 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/block/blk-merge.c b/block/blk-merge.c index cce23ba1ae5f..d9eddbc189f5 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -438,6 +438,8 @@ no_merge: int ll_back_merge_fn(struct request_queue *q, struct request *req, struct bio *bio) { + if (req_gap_back_merge(req, bio)) + return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req)) { req->cmd_flags |= REQ_NOMERGE; @@ -456,6 +458,9 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req, int ll_front_merge_fn(struct request_queue *q, struct request *req, struct bio *bio) { + + if (req_gap_front_merge(req, bio)) + return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req)) { req->cmd_flags |= REQ_NOMERGE; @@ -482,14 +487,6 @@ static bool req_no_special_merge(struct request *req) return !q->mq_ops && req->special; } -static int req_gap_to_prev(struct request *req, struct bio *next) -{ - struct bio *prev = req->biotail; - - return bvec_gap_to_prev(req->q, &prev->bi_io_vec[prev->bi_vcnt - 1], - next->bi_io_vec[0].bv_offset); -} - static int ll_merge_requests_fn(struct request_queue *q, struct request *req, struct request *next) { @@ -504,7 +501,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req, if (req_no_special_merge(req) || req_no_special_merge(next)) return 0; - if (req_gap_to_prev(req, next->bio)) + if (req_gap_back_merge(req, next->bio)) return 0; /* @@ -712,10 +709,6 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) !blk_write_same_mergeable(rq->bio, bio)) return false; - /* Only check gaps if the bio carries data */ - if (bio_has_data(bio) && req_gap_to_prev(rq, bio)) - return false; - return true; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a622f270f09e..2ff94def041e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1368,6 +1368,26 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); } +static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, + struct bio *next) +{ + if (!bio_has_data(prev)) + return false; + + return bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], + next->bi_io_vec[0].bv_offset); +} + +static inline bool req_gap_back_merge(struct request *req, struct bio *bio) +{ + return bio_will_gap(req->q, req->biotail, bio); +} + +static inline bool req_gap_front_merge(struct request *req, struct bio *bio) +{ + return bio_will_gap(req->q, bio, req->bio); +} + struct work_struct; int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_delayed_work(struct delayed_work *dwork, unsigned long delay); -- cgit v1.2.3 From e74bfeedad08180b968d8613dcde141ffb0720c3 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Mon, 13 Jul 2015 08:07:17 -0400 Subject: NTB: Add flow control to the ntb_netdev Right now if we push the NTB really hard, we start dropping packets due to not able to process the packets fast enough. We need to st:qop the upper layer from flooding us when that happens. A timer is necessary in order to restart the queue once the resource has been processed on the receive side. Due to the way NTB is setup, the resources on the tx side are tied to the processing of the rx side and there's no async way to know when the rx side has released those resources. Signed-off-by: Dave Jiang Signed-off-by: Jon Mason --- drivers/net/ntb_netdev.c | 77 +++++++++++++++++++++++++++++++++++++++++++ drivers/ntb/ntb_transport.c | 18 +++++++++- include/linux/ntb_transport.h | 1 + 3 files changed, 95 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index d8757bf9ad75..a9acf7156855 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -61,11 +61,21 @@ MODULE_VERSION(NTB_NETDEV_VER); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Intel Corporation"); +/* Time in usecs for tx resource reaper */ +static unsigned int tx_time = 1; + +/* Number of descriptors to free before resuming tx */ +static unsigned int tx_start = 10; + +/* Number of descriptors still available before stop upper layer tx */ +static unsigned int tx_stop = 5; + struct ntb_netdev { struct list_head list; struct pci_dev *pdev; struct net_device *ndev; struct ntb_transport_qp *qp; + struct timer_list tx_timer; }; #define NTB_TX_TIMEOUT_MS 1000 @@ -136,11 +146,42 @@ enqueue_again: } } +static int __ntb_netdev_maybe_stop_tx(struct net_device *netdev, + struct ntb_transport_qp *qp, int size) +{ + struct ntb_netdev *dev = netdev_priv(netdev); + + netif_stop_queue(netdev); + /* Make sure to see the latest value of ntb_transport_tx_free_entry() + * since the queue was last started. + */ + smp_mb(); + + if (likely(ntb_transport_tx_free_entry(qp) < size)) { + mod_timer(&dev->tx_timer, jiffies + usecs_to_jiffies(tx_time)); + return -EBUSY; + } + + netif_start_queue(netdev); + return 0; +} + +static int ntb_netdev_maybe_stop_tx(struct net_device *ndev, + struct ntb_transport_qp *qp, int size) +{ + if (netif_queue_stopped(ndev) || + (ntb_transport_tx_free_entry(qp) >= size)) + return 0; + + return __ntb_netdev_maybe_stop_tx(ndev, qp, size); +} + static void ntb_netdev_tx_handler(struct ntb_transport_qp *qp, void *qp_data, void *data, int len) { struct net_device *ndev = qp_data; struct sk_buff *skb; + struct ntb_netdev *dev = netdev_priv(ndev); skb = data; if (!skb || !ndev) @@ -155,6 +196,15 @@ static void ntb_netdev_tx_handler(struct ntb_transport_qp *qp, void *qp_data, } dev_kfree_skb(skb); + + if (ntb_transport_tx_free_entry(dev->qp) >= tx_start) { + /* Make sure anybody stopping the queue after this sees the new + * value of ntb_transport_tx_free_entry() + */ + smp_mb(); + if (netif_queue_stopped(ndev)) + netif_wake_queue(ndev); + } } static netdev_tx_t ntb_netdev_start_xmit(struct sk_buff *skb, @@ -163,10 +213,15 @@ static netdev_tx_t ntb_netdev_start_xmit(struct sk_buff *skb, struct ntb_netdev *dev = netdev_priv(ndev); int rc; + ntb_netdev_maybe_stop_tx(ndev, dev->qp, tx_stop); + rc = ntb_transport_tx_enqueue(dev->qp, skb, skb->data, skb->len); if (rc) goto err; + /* check for next submit */ + ntb_netdev_maybe_stop_tx(ndev, dev->qp, tx_stop); + return NETDEV_TX_OK; err: @@ -175,6 +230,23 @@ err: return NETDEV_TX_BUSY; } +static void ntb_netdev_tx_timer(unsigned long data) +{ + struct net_device *ndev = (struct net_device *)data; + struct ntb_netdev *dev = netdev_priv(ndev); + + if (ntb_transport_tx_free_entry(dev->qp) < tx_stop) { + mod_timer(&dev->tx_timer, jiffies + msecs_to_jiffies(tx_time)); + } else { + /* Make sure anybody stopping the queue after this sees the new + * value of ntb_transport_tx_free_entry() + */ + smp_mb(); + if (netif_queue_stopped(ndev)) + netif_wake_queue(ndev); + } +} + static int ntb_netdev_open(struct net_device *ndev) { struct ntb_netdev *dev = netdev_priv(ndev); @@ -197,8 +269,11 @@ static int ntb_netdev_open(struct net_device *ndev) } } + setup_timer(&dev->tx_timer, ntb_netdev_tx_timer, (unsigned long)ndev); + netif_carrier_off(ndev); ntb_transport_link_up(dev->qp); + netif_start_queue(ndev); return 0; @@ -219,6 +294,8 @@ static int ntb_netdev_close(struct net_device *ndev) while ((skb = ntb_transport_rx_remove(dev->qp, &len))) dev_kfree_skb(skb); + del_timer_sync(&dev->tx_timer); + return 0; } diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 1c6386d5f79c..0d851d684523 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -494,6 +494,12 @@ static ssize_t debugfs_read(struct file *filp, char __user *ubuf, size_t count, "tx_index - \t%u\n", qp->tx_index); out_offset += snprintf(buf + out_offset, out_count - out_offset, "tx_max_entry - \t%u\n", qp->tx_max_entry); + out_offset += snprintf(buf + out_offset, out_count - out_offset, + "qp->remote_rx_info->entry - \t%u\n", + qp->remote_rx_info->entry); + out_offset += snprintf(buf + out_offset, out_count - out_offset, + "free tx - \t%u\n", + ntb_transport_tx_free_entry(qp)); out_offset += snprintf(buf + out_offset, out_count - out_offset, "\nQP Link %s\n", @@ -535,6 +541,7 @@ static struct ntb_queue_entry *ntb_list_rm(spinlock_t *lock, } entry = list_first_entry(list, struct ntb_queue_entry, entry); list_del(&entry->entry); + out: spin_unlock_irqrestore(lock, flags); @@ -1843,7 +1850,7 @@ int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data, entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q); if (!entry) { qp->tx_err_no_buf++; - return -ENOMEM; + return -EBUSY; } entry->cb_data = cb; @@ -1969,6 +1976,15 @@ unsigned int ntb_transport_max_size(struct ntb_transport_qp *qp) } EXPORT_SYMBOL_GPL(ntb_transport_max_size); +unsigned int ntb_transport_tx_free_entry(struct ntb_transport_qp *qp) +{ + unsigned int head = qp->tx_index; + unsigned int tail = qp->remote_rx_info->entry; + + return tail > head ? tail - head : qp->tx_max_entry + tail - head; +} +EXPORT_SYMBOL_GPL(ntb_transport_tx_free_entry); + static void ntb_transport_doorbell_callback(void *data, int vector) { struct ntb_transport_ctx *nt = data; diff --git a/include/linux/ntb_transport.h b/include/linux/ntb_transport.h index 2862861366a5..7243eb98a722 100644 --- a/include/linux/ntb_transport.h +++ b/include/linux/ntb_transport.h @@ -83,3 +83,4 @@ void *ntb_transport_rx_remove(struct ntb_transport_qp *qp, unsigned int *len); void ntb_transport_link_up(struct ntb_transport_qp *qp); void ntb_transport_link_down(struct ntb_transport_qp *qp); bool ntb_transport_link_query(struct ntb_transport_qp *qp); +unsigned int ntb_transport_tx_free_entry(struct ntb_transport_qp *qp); -- cgit v1.2.3 From a7c23237481782fbea3c2230e362b72863e144b0 Mon Sep 17 00:00:00 2001 From: Allen Hubbe Date: Wed, 15 Jul 2015 04:15:28 -0400 Subject: NTB: Fix documentation for ntb_link_is_up There was a copy and paste error in the documentation for ntb_link_is_up. The long description was mistakenly copied from ntb_link_set_trans. This adds the appropriate long description for ntb_link_is_up. Reported-by: Dave Jiang Signed-off-by: Allen Hubbe Signed-off-by: Jon Mason --- include/linux/ntb.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index b02f72bb8e32..e3d3299c6052 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -522,10 +522,9 @@ static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) * @speed: OUT - The link speed expressed as PCIe generation number. * @width: OUT - The link width expressed as the number of PCIe lanes. * - * Set the translation of a memory window. The peer may access local memory - * through the window starting at the address, up to the size. The address - * must be aligned to the alignment specified by ntb_mw_get_range(). The size - * must be aligned to the size alignment specified by ntb_mw_get_range(). + * Get the current state of the ntb link. It is recommended to query the link + * state once after every link event. It is safe to query the link state in + * the context of the link event callback. * * Return: One if the link is up, zero if the link is down, otherwise a * negative value indicating the error number. -- cgit v1.2.3 From 86663c91866ae85c219f1a80ef2c9460b7ca5cd8 Mon Sep 17 00:00:00 2001 From: Allen Hubbe Date: Wed, 15 Jul 2015 12:43:21 -0400 Subject: NTB: Fix documentation for ntb_peer_db_clear. The documentation should say "peer" not "local" when referring to the peer doorbell register. Reported-by: Dave Jiang Signed-off-by: Allen Hubbe Signed-off-by: Jon Mason --- include/linux/ntb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index e3d3299c6052..f798e2afba88 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -794,7 +794,7 @@ static inline int ntb_peer_db_set(struct ntb_dev *ntb, u64 db_bits) } /** - * ntb_peer_db_clear() - clear bits in the local doorbell register + * ntb_peer_db_clear() - clear bits in the peer doorbell register * @ntb: NTB device context. * @db_bits: Doorbell bits to clear. * -- cgit v1.2.3 From edcd591c77a48da753456f92daf8bb50fe9bac93 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Mon, 7 Sep 2015 13:18:03 -0600 Subject: locking/static_keys: Fix a silly typo Commit: 412758cb2670 ("jump label, locking/static_keys: Update docs") introduced a typo that might as well get fixed. Signed-off-by: Jonathan Corbet Cc: Andrew Morton Cc: Jason Baron Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20150907131803.54c027e1@lwn.net Signed-off-by: Ingo Molnar --- Documentation/static-keys.txt | 2 +- include/linux/jump_label.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/Documentation/static-keys.txt b/Documentation/static-keys.txt index f4cb0b2d5cd7..ec911583f6c5 100644 --- a/Documentation/static-keys.txt +++ b/Documentation/static-keys.txt @@ -16,7 +16,7 @@ The updated API replacements are: DEFINE_STATIC_KEY_TRUE(key); DEFINE_STATIC_KEY_FALSE(key); static_key_likely() -statick_key_unlikely() +static_key_unlikely() 0) Abstract diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 7f653e8f6690..0684bd3a48fc 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -22,7 +22,7 @@ * DEFINE_STATIC_KEY_TRUE(key); * DEFINE_STATIC_KEY_FALSE(key); * static_key_likely() - * statick_key_unlikely() + * static_key_unlikely() * * Jump labels provide an interface to generate dynamic branches using * self-modifying code. Assuming toolchain and architecture support, if we -- cgit v1.2.3 From 8b9558aab853e98ba6e3fee0dd8545544966958c Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 1 Sep 2015 17:19:38 +0800 Subject: libceph: use keepalive2 to verify the mon session is alive Signed-off-by: Yan, Zheng Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 2 ++ include/linux/ceph/messenger.h | 4 +++ include/linux/ceph/msgr.h | 4 ++- net/ceph/ceph_common.c | 1 + net/ceph/messenger.c | 59 ++++++++++++++++++++++++++++++++++++++---- net/ceph/mon_client.c | 37 ++++++++++++++++++++------ 6 files changed, 93 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 9ebee53d3bf5..397c5cd09794 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -46,6 +46,7 @@ struct ceph_options { unsigned long mount_timeout; /* jiffies */ unsigned long osd_idle_ttl; /* jiffies */ unsigned long osd_keepalive_timeout; /* jiffies */ + unsigned long monc_ping_timeout; /* jiffies */ /* * any type that can't be simply compared or doesn't need need @@ -66,6 +67,7 @@ struct ceph_options { #define CEPH_MOUNT_TIMEOUT_DEFAULT msecs_to_jiffies(60 * 1000) #define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) #define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) +#define CEPH_MONC_PING_TIMEOUT_DEFAULT msecs_to_jiffies(30 * 1000) #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 37753278987a..7e1252e97a30 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -248,6 +248,8 @@ struct ceph_connection { int in_base_pos; /* bytes read */ __le64 in_temp_ack; /* for reading an ack */ + struct timespec last_keepalive_ack; + struct delayed_work work; /* send|recv work */ unsigned long delay; /* current delay interval */ }; @@ -285,6 +287,8 @@ extern void ceph_msg_revoke(struct ceph_msg *msg); extern void ceph_msg_revoke_incoming(struct ceph_msg *msg); extern void ceph_con_keepalive(struct ceph_connection *con); +extern bool ceph_con_keepalive_expired(struct ceph_connection *con, + unsigned long interval); extern void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment); diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h index 1c1887206ffa..0fe2656ac415 100644 --- a/include/linux/ceph/msgr.h +++ b/include/linux/ceph/msgr.h @@ -84,10 +84,12 @@ struct ceph_entity_inst { #define CEPH_MSGR_TAG_MSG 7 /* message */ #define CEPH_MSGR_TAG_ACK 8 /* message ack */ #define CEPH_MSGR_TAG_KEEPALIVE 9 /* just a keepalive byte! */ -#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ +#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ #define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */ #define CEPH_MSGR_TAG_FEATURES 12 /* insufficient features */ #define CEPH_MSGR_TAG_SEQ 13 /* 64-bit int follows with seen seq number */ +#define CEPH_MSGR_TAG_KEEPALIVE2 14 /* keepalive2 byte + ceph_timespec */ +#define CEPH_MSGR_TAG_KEEPALIVE2_ACK 15 /* keepalive2 reply */ /* diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index f30329f72641..3f56eefc2a07 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -357,6 +357,7 @@ ceph_parse_options(char *options, const char *dev_name, opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; + opt->monc_ping_timeout = CEPH_MONC_PING_TIMEOUT_DEFAULT; /* get mon ip(s) */ /* ip1[:port1][,ip2[:port2]...] */ diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 101ab6285fba..36757d46ac40 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -163,6 +163,7 @@ static struct kmem_cache *ceph_msg_data_cache; static char tag_msg = CEPH_MSGR_TAG_MSG; static char tag_ack = CEPH_MSGR_TAG_ACK; static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE; +static char tag_keepalive2 = CEPH_MSGR_TAG_KEEPALIVE2; #ifdef CONFIG_LOCKDEP static struct lock_class_key socket_class; @@ -1351,7 +1352,15 @@ static void prepare_write_keepalive(struct ceph_connection *con) { dout("prepare_write_keepalive %p\n", con); con_out_kvec_reset(con); - con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive); + if (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2) { + struct timespec ts = CURRENT_TIME; + struct ceph_timespec ceph_ts; + ceph_encode_timespec(&ceph_ts, &ts); + con_out_kvec_add(con, sizeof(tag_keepalive2), &tag_keepalive2); + con_out_kvec_add(con, sizeof(ceph_ts), &ceph_ts); + } else { + con_out_kvec_add(con, sizeof(tag_keepalive), &tag_keepalive); + } con_flag_set(con, CON_FLAG_WRITE_PENDING); } @@ -1625,6 +1634,12 @@ static void prepare_read_tag(struct ceph_connection *con) con->in_tag = CEPH_MSGR_TAG_READY; } +static void prepare_read_keepalive_ack(struct ceph_connection *con) +{ + dout("prepare_read_keepalive_ack %p\n", con); + con->in_base_pos = 0; +} + /* * Prepare to read a message. */ @@ -2457,6 +2472,17 @@ static void process_message(struct ceph_connection *con) mutex_lock(&con->mutex); } +static int read_keepalive_ack(struct ceph_connection *con) +{ + struct ceph_timespec ceph_ts; + size_t size = sizeof(ceph_ts); + int ret = read_partial(con, size, size, &ceph_ts); + if (ret <= 0) + return ret; + ceph_decode_timespec(&con->last_keepalive_ack, &ceph_ts); + prepare_read_tag(con); + return 1; +} /* * Write something to the socket. Called in a worker thread when the @@ -2526,6 +2552,10 @@ more_kvec: do_next: if (con->state == CON_STATE_OPEN) { + if (con_flag_test_and_clear(con, CON_FLAG_KEEPALIVE_PENDING)) { + prepare_write_keepalive(con); + goto more; + } /* is anything else pending? */ if (!list_empty(&con->out_queue)) { prepare_write_message(con); @@ -2535,10 +2565,6 @@ do_next: prepare_write_ack(con); goto more; } - if (con_flag_test_and_clear(con, CON_FLAG_KEEPALIVE_PENDING)) { - prepare_write_keepalive(con); - goto more; - } } /* Nothing to do! */ @@ -2641,6 +2667,9 @@ more: case CEPH_MSGR_TAG_ACK: prepare_read_ack(con); break; + case CEPH_MSGR_TAG_KEEPALIVE2_ACK: + prepare_read_keepalive_ack(con); + break; case CEPH_MSGR_TAG_CLOSE: con_close_socket(con); con->state = CON_STATE_CLOSED; @@ -2684,6 +2713,12 @@ more: process_ack(con); goto more; } + if (con->in_tag == CEPH_MSGR_TAG_KEEPALIVE2_ACK) { + ret = read_keepalive_ack(con); + if (ret <= 0) + goto out; + goto more; + } out: dout("try_read done on %p ret %d\n", con, ret); @@ -3101,6 +3136,20 @@ void ceph_con_keepalive(struct ceph_connection *con) } EXPORT_SYMBOL(ceph_con_keepalive); +bool ceph_con_keepalive_expired(struct ceph_connection *con, + unsigned long interval) +{ + if (interval > 0 && + (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2)) { + struct timespec now = CURRENT_TIME; + struct timespec ts; + jiffies_to_timespec(interval, &ts); + ts = timespec_add(con->last_keepalive_ack, ts); + return timespec_compare(&now, &ts) >= 0; + } + return false; +} + static struct ceph_msg_data *ceph_msg_data_create(enum ceph_msg_data_type type) { struct ceph_msg_data *data; diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 9d6ff1215928..edda01626a45 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -149,6 +149,10 @@ static int __open_session(struct ceph_mon_client *monc) CEPH_ENTITY_TYPE_MON, monc->cur_mon, &monc->monmap->mon_inst[monc->cur_mon].addr); + /* send an initial keepalive to ensure our timestamp is + * valid by the time we are in an OPENED state */ + ceph_con_keepalive(&monc->con); + /* initiatiate authentication handshake */ ret = ceph_auth_build_hello(monc->auth, monc->m_auth->front.iov_base, @@ -170,14 +174,19 @@ static bool __sub_expired(struct ceph_mon_client *monc) */ static void __schedule_delayed(struct ceph_mon_client *monc) { - unsigned int delay; + struct ceph_options *opt = monc->client->options; + unsigned long delay; - if (monc->cur_mon < 0 || __sub_expired(monc)) + if (monc->cur_mon < 0 || __sub_expired(monc)) { delay = 10 * HZ; - else + } else { delay = 20 * HZ; - dout("__schedule_delayed after %u\n", delay); - schedule_delayed_work(&monc->delayed_work, delay); + if (opt->monc_ping_timeout > 0) + delay = min(delay, opt->monc_ping_timeout / 3); + } + dout("__schedule_delayed after %lu\n", delay); + schedule_delayed_work(&monc->delayed_work, + round_jiffies_relative(delay)); } /* @@ -743,11 +752,23 @@ static void delayed_work(struct work_struct *work) __close_session(monc); __open_session(monc); /* continue hunting */ } else { - ceph_con_keepalive(&monc->con); + struct ceph_options *opt = monc->client->options; + int is_auth = ceph_auth_is_authenticated(monc->auth); + if (ceph_con_keepalive_expired(&monc->con, + opt->monc_ping_timeout)) { + dout("monc keepalive timeout\n"); + is_auth = 0; + __close_session(monc); + monc->hunting = true; + __open_session(monc); + } - __validate_auth(monc); + if (!monc->hunting) { + ceph_con_keepalive(&monc->con); + __validate_auth(monc); + } - if (ceph_auth_is_authenticated(monc->auth)) + if (is_auth) __send_subscribe(monc); } __schedule_delayed(monc); -- cgit v1.2.3 From 4eafbd15b6c84cd3f6c76022c8a6c27f7cc076e1 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 8 Sep 2015 18:41:01 +0200 Subject: PM / OPP: add dev_pm_opp_get_suspend_opp() helper Add dev_pm_opp_get_suspend_opp() helper to obtain suspend opp. Acked-by: Viresh Kumar Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Rafael J. Wysocki --- drivers/base/power/opp.c | 30 ++++++++++++++++++++++++++++++ include/linux/pm_opp.h | 6 ++++++ 2 files changed, 36 insertions(+) (limited to 'include') diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c index bb703b5ebaff..3df62dbcec3a 100644 --- a/drivers/base/power/opp.c +++ b/drivers/base/power/opp.c @@ -340,6 +340,36 @@ unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) } EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency); +/** + * dev_pm_opp_get_suspend_opp() - Get suspend opp + * @dev: device for which we do this operation + * + * Return: This function returns pointer to the suspend opp if it is + * defined, otherwise it returns NULL. + * + * Locking: This function must be called under rcu_read_lock(). opp is a rcu + * protected pointer. The reason for the same is that the opp pointer which is + * returned will remain valid for use with opp_get_{voltage, freq} only while + * under the locked area. The pointer returned must be used prior to unlocking + * with rcu_read_unlock() to maintain the integrity of the pointer. + */ +struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) +{ + struct device_opp *dev_opp; + struct dev_pm_opp *opp; + + opp_rcu_lockdep_assert(); + + dev_opp = _find_device_opp(dev); + if (IS_ERR(dev_opp)) + opp = NULL; + else + opp = dev_opp->suspend_opp; + + return opp; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp); + /** * dev_pm_opp_get_opp_count() - Get number of opps available in the opp list * @dev: device for which we do this operation diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index cab7ba55bedb..e817722ee3f0 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -34,6 +34,7 @@ bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp); int dev_pm_opp_get_opp_count(struct device *dev); unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev); +struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, @@ -80,6 +81,11 @@ static inline unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) return 0; } +static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) +{ + return NULL; +} + static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available) { -- cgit v1.2.3 From 08e75e754a6d9838e490b74551d19fc04d0fd6f9 Mon Sep 17 00:00:00 2001 From: Javi Merino Date: Fri, 14 Aug 2015 18:56:56 +0100 Subject: PM / devfreq: cache the last call to get_dev_status() The return value of get_dev_status() can be reused. Cache it so that other parts of the kernel can reuse it instead of having to call the same function again. Cc: Kyungmin Park Signed-off-by: Javi Merino Signed-off-by: MyungJoo Ham --- drivers/devfreq/governor_simpleondemand.c | 33 +++++++++++++++++-------------- include/linux/devfreq.h | 15 ++++++++++++++ 2 files changed, 33 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/drivers/devfreq/governor_simpleondemand.c b/drivers/devfreq/governor_simpleondemand.c index 0720ba84ca92..ae72ba5e78df 100644 --- a/drivers/devfreq/governor_simpleondemand.c +++ b/drivers/devfreq/governor_simpleondemand.c @@ -21,17 +21,20 @@ static int devfreq_simple_ondemand_func(struct devfreq *df, unsigned long *freq) { - struct devfreq_dev_status stat; - int err = df->profile->get_dev_status(df->dev.parent, &stat); + int err; + struct devfreq_dev_status *stat; unsigned long long a, b; unsigned int dfso_upthreshold = DFSO_UPTHRESHOLD; unsigned int dfso_downdifferential = DFSO_DOWNDIFFERENCTIAL; struct devfreq_simple_ondemand_data *data = df->data; unsigned long max = (df->max_freq) ? df->max_freq : UINT_MAX; + err = devfreq_update_stats(df); if (err) return err; + stat = &df->last_status; + if (data) { if (data->upthreshold) dfso_upthreshold = data->upthreshold; @@ -43,41 +46,41 @@ static int devfreq_simple_ondemand_func(struct devfreq *df, return -EINVAL; /* Assume MAX if it is going to be divided by zero */ - if (stat.total_time == 0) { + if (stat->total_time == 0) { *freq = max; return 0; } /* Prevent overflow */ - if (stat.busy_time >= (1 << 24) || stat.total_time >= (1 << 24)) { - stat.busy_time >>= 7; - stat.total_time >>= 7; + if (stat->busy_time >= (1 << 24) || stat->total_time >= (1 << 24)) { + stat->busy_time >>= 7; + stat->total_time >>= 7; } /* Set MAX if it's busy enough */ - if (stat.busy_time * 100 > - stat.total_time * dfso_upthreshold) { + if (stat->busy_time * 100 > + stat->total_time * dfso_upthreshold) { *freq = max; return 0; } /* Set MAX if we do not know the initial frequency */ - if (stat.current_frequency == 0) { + if (stat->current_frequency == 0) { *freq = max; return 0; } /* Keep the current frequency */ - if (stat.busy_time * 100 > - stat.total_time * (dfso_upthreshold - dfso_downdifferential)) { - *freq = stat.current_frequency; + if (stat->busy_time * 100 > + stat->total_time * (dfso_upthreshold - dfso_downdifferential)) { + *freq = stat->current_frequency; return 0; } /* Set the desired frequency based on the load */ - a = stat.busy_time; - a *= stat.current_frequency; - b = div_u64(a, stat.total_time); + a = stat->busy_time; + a *= stat->current_frequency; + b = div_u64(a, stat->total_time); b *= 100; b = div_u64(b, (dfso_upthreshold - dfso_downdifferential / 2)); *freq = (unsigned long) b; diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index ce447f0f1bad..70a1c60ddda4 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -161,6 +161,7 @@ struct devfreq { struct delayed_work work; unsigned long previous_freq; + struct devfreq_dev_status last_status; void *data; /* private data for governors */ @@ -204,6 +205,15 @@ extern int devm_devfreq_register_opp_notifier(struct device *dev, extern void devm_devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq); +/** + * devfreq_update_stats() - update the last_status pointer in struct devfreq + * @df: the devfreq instance whose status needs updating + */ +static inline int devfreq_update_stats(struct devfreq *df) +{ + return df->profile->get_dev_status(df->dev.parent, &df->last_status); +} + #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) /** * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq @@ -289,6 +299,11 @@ static inline void devm_devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq) { } + +static inline int devfreq_update_stats(struct devfreq *df) +{ + return -EINVAL; +} #endif /* CONFIG_PM_DEVFREQ */ #endif /* __LINUX_DEVFREQ_H__ */ -- cgit v1.2.3 From d54cdf3fc91aae3780433471d15d73413a845bc0 Mon Sep 17 00:00:00 2001 From: MyungJoo Ham Date: Tue, 18 Aug 2015 13:45:49 +0900 Subject: PM / devfreq: comments for get_dev_status usage updated With the introduction of devfreq_update_stats(), governors are not recommended to use get_dev_status() directly. Signed-off-by: MyungJoo Ham --- include/linux/devfreq.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 70a1c60ddda4..68030e22af35 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -65,7 +65,10 @@ struct devfreq_dev_status { * The "flags" parameter's possible values are * explained above with "DEVFREQ_FLAG_*" macros. * @get_dev_status: The device should provide the current performance - * status to devfreq, which is used by governors. + * status to devfreq. Governors are recommended not to + * use this directly. Instead, governors are recommended + * to use devfreq_update_stats() along with + * devfreq.last_status. * @get_cur_freq: The device should provide the current frequency * at which it is operating. * @exit: An optional callback that is called when devfreq @@ -208,6 +211,10 @@ extern void devm_devfreq_unregister_opp_notifier(struct device *dev, /** * devfreq_update_stats() - update the last_status pointer in struct devfreq * @df: the devfreq instance whose status needs updating + * + * Governors are recommended to use this function along with last_status, + * which allows other entities to reuse the last_status without affecting + * the values fetched later by governors. */ static inline int devfreq_update_stats(struct devfreq *df) { -- cgit v1.2.3 From 43b3f02899f74ae9914a39547cc5492156f0027a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 4 Sep 2015 17:25:23 +0200 Subject: locking/qspinlock/x86: Fix performance regression under unaccelerated VMs Dave ran into horrible performance on a VM without PARAVIRT_SPINLOCKS set and Linus noted that the test-and-set implementation was retarded. One should spin on the variable with a load, not a RMW. While there, remove 'queued' from the name, as the lock isn't queued at all, but a simple test-and-set. Suggested-by: Linus Torvalds Reported-by: Dave Chinner Tested-by: Dave Chinner Signed-off-by: Peter Zijlstra (Intel) Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Cc: stable@vger.kernel.org # v4.2+ Link: http://lkml.kernel.org/r/20150904152523.GR18673@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- arch/x86/include/asm/qspinlock.h | 16 ++++++++++++---- include/asm-generic/qspinlock.h | 4 ++-- kernel/locking/qspinlock.c | 2 +- 3 files changed, 15 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index 9d51fae1cba3..8dde3bdc4a05 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -39,15 +39,23 @@ static inline void queued_spin_unlock(struct qspinlock *lock) } #endif -#define virt_queued_spin_lock virt_queued_spin_lock +#define virt_spin_lock virt_spin_lock -static inline bool virt_queued_spin_lock(struct qspinlock *lock) +static inline bool virt_spin_lock(struct qspinlock *lock) { if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) return false; - while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0) - cpu_relax(); + /* + * On hypervisors without PARAVIRT_SPINLOCKS support we fall + * back to a Test-and-Set spinlock, because fair locks have + * horrible lock 'holder' preemption issues. + */ + + do { + while (atomic_read(&lock->val) != 0) + cpu_relax(); + } while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0); return true; } diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h index 83bfb87f5bf1..e2aadbc7151f 100644 --- a/include/asm-generic/qspinlock.h +++ b/include/asm-generic/qspinlock.h @@ -111,8 +111,8 @@ static inline void queued_spin_unlock_wait(struct qspinlock *lock) cpu_relax(); } -#ifndef virt_queued_spin_lock -static __always_inline bool virt_queued_spin_lock(struct qspinlock *lock) +#ifndef virt_spin_lock +static __always_inline bool virt_spin_lock(struct qspinlock *lock) { return false; } diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 337c8818541d..87e9ce6a63c5 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -289,7 +289,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) if (pv_enabled()) goto queue; - if (virt_queued_spin_lock(lock)) + if (virt_spin_lock(lock)) return; /* -- cgit v1.2.3 From 8f9b565482c537821588444e09ff732c7d65ed6e Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Thu, 30 Jul 2015 18:28:13 -0700 Subject: target/qla2xxx: Honor max_data_sg_nents I/O transfer limit This patch adds an optional fabric driver provided SGL limit that target-core will honor as it's own internal I/O maximum transfer length limit, as exposed by EVPD=0xb0 block limits parameters. This is required for handling cases when host I/O transfer length exceeds the requested EVPD block limits maximum transfer length. The initial user of this logic is qla2xxx, so that we can avoid having to reject I/Os from some legacy FC hosts where EVPD=0xb0 parameters are not honored. When se_cmd payload length exceeds the provided limit in target_check_max_data_sg_nents() code, se_cmd->data_length + se_cmd->prot_length are reset with se_cmd->residual_count plus underflow bit for outgoing TFO response callbacks. It also checks for existing CDB level underflow + overflow and recalculates final residual_count as necessary. Note this patch currently assumes 1:1 mapping of PAGE_SIZE per struct scatterlist entry. Reported-by: Craig Watson Cc: Craig Watson Tested-by: Himanshu Madhani Cc: Roland Dreier Cc: Arun Easi Cc: Giridhar Malavali Cc: Andrew Vasquez Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Martin K. Petersen Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/tcm_qla2xxx.c | 5 ++++ drivers/target/target_core_spc.c | 13 +++++++-- drivers/target/target_core_transport.c | 51 +++++++++++++++++++++++++++++++++- include/target/target_core_fabric.h | 13 +++++++++ 4 files changed, 78 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index c621623abeed..edeb3aefa6fe 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -1808,6 +1808,11 @@ static const struct target_core_fabric_ops tcm_qla2xxx_ops = { .module = THIS_MODULE, .name = "qla2xxx", .node_acl_size = sizeof(struct tcm_qla2xxx_nacl), + /* + * XXX: Limit assumes single page per scatter-gather-list entry. + * Current maximum is ~4.9 MB per se_cmd->t_data_sg with PAGE_SIZE=4096 + */ + .max_data_sg_nents = 1200, .get_fabric_name = tcm_qla2xxx_get_fabric_name, .tpg_get_wwn = tcm_qla2xxx_get_fabric_wwn, .tpg_get_tag = tcm_qla2xxx_get_tag, diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index a07d455e0dd5..0e0456f6a282 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -477,8 +477,8 @@ static sense_reason_t spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf) { struct se_device *dev = cmd->se_dev; - int have_tp = 0; - int opt, min; + u32 mtl = 0; + int have_tp = 0, opt, min; /* * Following spc3r22 section 6.5.3 Block Limits VPD page, when @@ -509,8 +509,15 @@ spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf) /* * Set MAXIMUM TRANSFER LENGTH + * + * XXX: Currently assumes single PAGE_SIZE per scatterlist for fabrics + * enforcing maximum HW scatter-gather-list entry limit */ - put_unaligned_be32(dev->dev_attrib.hw_max_sectors, &buf[8]); + if (cmd->se_tfo->max_data_sg_nents) { + mtl = (cmd->se_tfo->max_data_sg_nents * PAGE_SIZE) / + dev->dev_attrib.block_size; + } + put_unaligned_be32(min_not_zero(mtl, dev->dev_attrib.hw_max_sectors), &buf[8]); /* * Set OPTIMAL TRANSFER LENGTH diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 3f0b50082de4..62bafaa670f4 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1075,6 +1075,55 @@ transport_set_vpd_ident(struct t10_vpd *vpd, unsigned char *page_83) } EXPORT_SYMBOL(transport_set_vpd_ident); +static sense_reason_t +target_check_max_data_sg_nents(struct se_cmd *cmd, struct se_device *dev, + unsigned int size) +{ + u32 mtl; + + if (!cmd->se_tfo->max_data_sg_nents) + return TCM_NO_SENSE; + /* + * Check if fabric enforced maximum SGL entries per I/O descriptor + * exceeds se_cmd->data_length. If true, set SCF_UNDERFLOW_BIT + + * residual_count and reduce original cmd->data_length to maximum + * length based on single PAGE_SIZE entry scatter-lists. + */ + mtl = (cmd->se_tfo->max_data_sg_nents * PAGE_SIZE); + if (cmd->data_length > mtl) { + /* + * If an existing CDB overflow is present, calculate new residual + * based on CDB size minus fabric maximum transfer length. + * + * If an existing CDB underflow is present, calculate new residual + * based on original cmd->data_length minus fabric maximum transfer + * length. + * + * Otherwise, set the underflow residual based on cmd->data_length + * minus fabric maximum transfer length. + */ + if (cmd->se_cmd_flags & SCF_OVERFLOW_BIT) { + cmd->residual_count = (size - mtl); + } else if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) { + u32 orig_dl = size + cmd->residual_count; + cmd->residual_count = (orig_dl - mtl); + } else { + cmd->se_cmd_flags |= SCF_UNDERFLOW_BIT; + cmd->residual_count = (cmd->data_length - mtl); + } + cmd->data_length = mtl; + /* + * Reset sbc_check_prot() calculated protection payload + * length based upon the new smaller MTL. + */ + if (cmd->prot_length) { + u32 sectors = (mtl / dev->dev_attrib.block_size); + cmd->prot_length = dev->prot_length * sectors; + } + } + return TCM_NO_SENSE; +} + sense_reason_t target_cmd_size_check(struct se_cmd *cmd, unsigned int size) { @@ -1120,7 +1169,7 @@ target_cmd_size_check(struct se_cmd *cmd, unsigned int size) } } - return 0; + return target_check_max_data_sg_nents(cmd, dev, size); } diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 69355feabd1d..7fb2557a760e 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -5,6 +5,19 @@ struct target_core_fabric_ops { struct module *module; const char *name; size_t node_acl_size; + /* + * Limits number of scatterlist entries per SCF_SCSI_DATA_CDB payload. + * Setting this value tells target-core to enforce this limit, and + * report as INQUIRY EVPD=b0 MAXIMUM TRANSFER LENGTH. + * + * target-core will currently reset se_cmd->data_length to this + * maximum size, and set UNDERFLOW residual count if length exceeds + * this limit. + * + * XXX: Not all initiator hosts honor this block-limit EVPD + * XXX: Currently assumes single PAGE_SIZE per scatterlist entry + */ + u32 max_data_sg_nents; char *(*get_fabric_name)(void); char *(*tpg_get_wwn)(struct se_portal_group *); u16 (*tpg_get_tag)(struct se_portal_group *); -- cgit v1.2.3 From ac64a2ce509104a746321a4f9646b6750cf281eb Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Fri, 4 Sep 2015 01:39:56 +0200 Subject: target: use stringify.h instead of own definition Signed-off-by: David Disseldorp Acked-by: Andy Grover Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 3 ++- include/uapi/linux/target_core_user.h | 4 ---- 2 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index d0bb652b65b5..937cebf76633 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -898,7 +899,7 @@ static int tcmu_configure_device(struct se_device *dev) WARN_ON(!PAGE_ALIGNED(udev->data_off)); WARN_ON(udev->data_size % PAGE_SIZE); - info->version = xstr(TCMU_MAILBOX_VERSION); + info->version = __stringify(TCMU_MAILBOX_VERSION); info->mem[0].name = "tcm-user command & data buffer"; info->mem[0].addr = (phys_addr_t) udev->mb_addr; diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h index b67f99d3c520..95c6521d8a95 100644 --- a/include/uapi/linux/target_core_user.h +++ b/include/uapi/linux/target_core_user.h @@ -42,10 +42,6 @@ #define TCMU_MAILBOX_VERSION 2 #define ALIGN_SIZE 64 /* Should be enough for most CPUs */ -/* See https://gcc.gnu.org/onlinedocs/cpp/Stringification.html */ -#define xstr(s) str(s) -#define str(s) #s - struct tcmu_mailbox { __u16 version; __u16 flags; -- cgit v1.2.3 From 7f39add3b08cbbdb99abe50e6d7c342e6800d684 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Fri, 11 Sep 2015 09:03:04 -0600 Subject: block: Refuse request/bio merges with gaps in the integrity payload If a driver sets the block queue virtual boundary mask, it means that it cannot handle gaps so we must not allow those in the integrity payload as well. Signed-off-by: Sagi Grimberg Fixed up by me to have duplicate integrity merge functions, depending on whether block integrity is enabled or not. Fixes a compilations issue with CONFIG_BLK_DEV_INTEGRITY unset. Signed-off-by: Jens Axboe --- block/blk-integrity.c | 3 +++ block/blk-merge.c | 6 ++++++ include/linux/blkdev.h | 30 ++++++++++++++++++++++++++++++ 3 files changed, 39 insertions(+) (limited to 'include') diff --git a/block/blk-integrity.c b/block/blk-integrity.c index f548b64be092..75f29cf70188 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -204,6 +204,9 @@ bool blk_integrity_merge_rq(struct request_queue *q, struct request *req, q->limits.max_integrity_segments) return false; + if (integrity_req_gap_back_merge(req, next->bio)) + return false; + return true; } EXPORT_SYMBOL(blk_integrity_merge_rq); diff --git a/block/blk-merge.c b/block/blk-merge.c index d9eddbc189f5..574ea7c0468f 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -440,6 +440,9 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req, { if (req_gap_back_merge(req, bio)) return 0; + if (blk_integrity_rq(req) && + integrity_req_gap_back_merge(req, bio)) + return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req)) { req->cmd_flags |= REQ_NOMERGE; @@ -461,6 +464,9 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req, if (req_gap_front_merge(req, bio)) return 0; + if (blk_integrity_rq(req) && + integrity_req_gap_front_merge(req, bio)) + return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req)) { req->cmd_flags |= REQ_NOMERGE; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2ff94def041e..1aac7316a4b5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1514,6 +1514,26 @@ queue_max_integrity_segments(struct request_queue *q) return q->limits.max_integrity_segments; } +static inline bool integrity_req_gap_back_merge(struct request *req, + struct bio *next) +{ + struct bio_integrity_payload *bip = bio_integrity(req->bio); + struct bio_integrity_payload *bip_next = bio_integrity(next); + + return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], + bip_next->bip_vec[0].bv_offset); +} + +static inline bool integrity_req_gap_front_merge(struct request *req, + struct bio *bio) +{ + struct bio_integrity_payload *bip = bio_integrity(bio); + struct bio_integrity_payload *bip_next = bio_integrity(req->bio); + + return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], + bip_next->bip_vec[0].bv_offset); +} + #else /* CONFIG_BLK_DEV_INTEGRITY */ struct bio; @@ -1580,6 +1600,16 @@ static inline bool blk_integrity_is_initialized(struct gendisk *g) { return 0; } +static inline bool integrity_req_gap_back_merge(struct request *req, + struct bio *next) +{ + return false; +} +static inline bool integrity_req_gap_front_merge(struct request *req, + struct bio *bio) +{ + return false; +} #endif /* CONFIG_BLK_DEV_INTEGRITY */ -- cgit v1.2.3 From 5b25b13ab08f616efd566347d809b4ece54570d1 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 11 Sep 2015 13:07:39 -0700 Subject: sys_membarrier(): system-wide memory barrier (generic, x86) Here is an implementation of a new system call, sys_membarrier(), which executes a memory barrier on all threads running on the system. It is implemented by calling synchronize_sched(). It can be used to distribute the cost of user-space memory barriers asymmetrically by transforming pairs of memory barriers into pairs consisting of sys_membarrier() and a compiler barrier. For synchronization primitives that distinguish between read-side and write-side (e.g. userspace RCU [1], rwlocks), the read-side can be accelerated significantly by moving the bulk of the memory barrier overhead to the write-side. The existing applications of which I am aware that would be improved by this system call are as follows: * Through Userspace RCU library (http://urcu.so) - DNS server (Knot DNS) https://www.knot-dns.cz/ - Network sniffer (http://netsniff-ng.org/) - Distributed object storage (https://sheepdog.github.io/sheepdog/) - User-space tracing (http://lttng.org) - Network storage system (https://www.gluster.org/) - Virtual routers (https://events.linuxfoundation.org/sites/events/files/slides/DPDK_RCU_0MQ.pdf) - Financial software (https://lkml.org/lkml/2015/3/23/189) Those projects use RCU in userspace to increase read-side speed and scalability compared to locking. Especially in the case of RCU used by libraries, sys_membarrier can speed up the read-side by moving the bulk of the memory barrier cost to synchronize_rcu(). * Direct users of sys_membarrier - core dotnet garbage collector (https://github.com/dotnet/coreclr/issues/198) Microsoft core dotnet GC developers are planning to use the mprotect() side-effect of issuing memory barriers through IPIs as a way to implement Windows FlushProcessWriteBuffers() on Linux. They are referring to sys_membarrier in their github thread, specifically stating that sys_membarrier() is what they are looking for. To explain the benefit of this scheme, let's introduce two example threads: Thread A (non-frequent, e.g. executing liburcu synchronize_rcu()) Thread B (frequent, e.g. executing liburcu rcu_read_lock()/rcu_read_unlock()) In a scheme where all smp_mb() in thread A are ordering memory accesses with respect to smp_mb() present in Thread B, we can change each smp_mb() within Thread A into calls to sys_membarrier() and each smp_mb() within Thread B into compiler barriers "barrier()". Before the change, we had, for each smp_mb() pairs: Thread A Thread B previous mem accesses previous mem accesses smp_mb() smp_mb() following mem accesses following mem accesses After the change, these pairs become: Thread A Thread B prev mem accesses prev mem accesses sys_membarrier() barrier() follow mem accesses follow mem accesses As we can see, there are two possible scenarios: either Thread B memory accesses do not happen concurrently with Thread A accesses (1), or they do (2). 1) Non-concurrent Thread A vs Thread B accesses: Thread A Thread B prev mem accesses sys_membarrier() follow mem accesses prev mem accesses barrier() follow mem accesses In this case, thread B accesses will be weakly ordered. This is OK, because at that point, thread A is not particularly interested in ordering them with respect to its own accesses. 2) Concurrent Thread A vs Thread B accesses Thread A Thread B prev mem accesses prev mem accesses sys_membarrier() barrier() follow mem accesses follow mem accesses In this case, thread B accesses, which are ensured to be in program order thanks to the compiler barrier, will be "upgraded" to full smp_mb() by synchronize_sched(). * Benchmarks On Intel Xeon E5405 (8 cores) (one thread is calling sys_membarrier, the other 7 threads are busy looping) 1000 non-expedited sys_membarrier calls in 33s =3D 33 milliseconds/call. * User-space user of this system call: Userspace RCU library Both the signal-based and the sys_membarrier userspace RCU schemes permit us to remove the memory barrier from the userspace RCU rcu_read_lock() and rcu_read_unlock() primitives, thus significantly accelerating them. These memory barriers are replaced by compiler barriers on the read-side, and all matching memory barriers on the write-side are turned into an invocation of a memory barrier on all active threads in the process. By letting the kernel perform this synchronization rather than dumbly sending a signal to every process threads (as we currently do), we diminish the number of unnecessary wake ups and only issue the memory barriers on active threads. Non-running threads do not need to execute such barrier anyway, because these are implied by the scheduler context switches. Results in liburcu: Operations in 10s, 6 readers, 2 writers: memory barriers in reader: 1701557485 reads, 2202847 writes signal-based scheme: 9830061167 reads, 6700 writes sys_membarrier: 9952759104 reads, 425 writes sys_membarrier (dyn. check): 7970328887 reads, 425 writes The dynamic sys_membarrier availability check adds some overhead to the read-side compared to the signal-based scheme, but besides that, sys_membarrier slightly outperforms the signal-based scheme. However, this non-expedited sys_membarrier implementation has a much slower grace period than signal and memory barrier schemes. Besides diminishing the number of wake-ups, one major advantage of the membarrier system call over the signal-based scheme is that it does not need to reserve a signal. This plays much more nicely with libraries, and with processes injected into for tracing purposes, for which we cannot expect that signals will be unused by the application. An expedited version of this system call can be added later on to speed up the grace period. Its implementation will likely depend on reading the cpu_curr()->mm without holding each CPU's rq lock. This patch adds the system call to x86 and to asm-generic. [1] http://urcu.so membarrier(2) man page: MEMBARRIER(2) Linux Programmer's Manual MEMBARRIER(2) NAME membarrier - issue memory barriers on a set of threads SYNOPSIS #include int membarrier(int cmd, int flags); DESCRIPTION The cmd argument is one of the following: MEMBARRIER_CMD_QUERY Query the set of supported commands. It returns a bitmask of supported commands. MEMBARRIER_CMD_SHARED Execute a memory barrier on all threads running on the system. Upon return from system call, the caller thread is ensured that all running threads have passed through a state where all memory accesses to user-space addresses match program order between entry to and return from the system call (non-running threads are de facto in such a state). This covers threads from all pro=E2=80=90 cesses running on the system. This command returns 0. The flags argument needs to be 0. For future extensions. All memory accesses performed in program order from each targeted thread is guaranteed to be ordered with respect to sys_membarrier(). If we use the semantic "barrier()" to represent a compiler barrier forcing memory accesses to be performed in program order across the barrier, and smp_mb() to represent explicit memory barriers forcing full memory ordering across the barrier, we have the following ordering table for each pair of barrier(), sys_membarrier() and smp_mb(): The pair ordering is detailed as (O: ordered, X: not ordered): barrier() smp_mb() sys_membarrier() barrier() X X O smp_mb() X O O sys_membarrier() O O O RETURN VALUE On success, these system calls return zero. On error, -1 is returned, and errno is set appropriately. For a given command, with flags argument set to 0, this system call is guaranteed to always return the same value until reboot. ERRORS ENOSYS System call is not implemented. EINVAL Invalid arguments. Linux 2015-04-15 MEMBARRIER(2) Signed-off-by: Mathieu Desnoyers Reviewed-by: Paul E. McKenney Reviewed-by: Josh Triplett Cc: KOSAKI Motohiro Cc: Steven Rostedt Cc: Nicholas Miell Cc: Ingo Molnar Cc: Alan Cox Cc: Lai Jiangshan Cc: Stephen Hemminger Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: David Howells Cc: Pranith Kumar Cc: Michael Kerrisk Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 8 +++++ arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + include/linux/syscalls.h | 2 ++ include/uapi/asm-generic/unistd.h | 4 ++- include/uapi/linux/Kbuild | 1 + include/uapi/linux/membarrier.h | 53 +++++++++++++++++++++++++++ init/Kconfig | 12 +++++++ kernel/Makefile | 1 + kernel/membarrier.c | 66 ++++++++++++++++++++++++++++++++++ kernel/sys_ni.c | 3 ++ 11 files changed, 151 insertions(+), 1 deletion(-) create mode 100644 include/uapi/linux/membarrier.h create mode 100644 kernel/membarrier.c (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 310da4295c70..e77bc84dc580 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6789,6 +6789,14 @@ W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlxsw/ +MEMBARRIER SUPPORT +M: Mathieu Desnoyers +M: "Paul E. McKenney" +L: linux-kernel@vger.kernel.org +S: Supported +F: kernel/membarrier.c +F: include/uapi/linux/membarrier.h + MEMORY MANAGEMENT L: linux-mm@kvack.org W: http://www.linux-mm.org diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 477bfa6db370..7663c455b9f6 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -381,3 +381,4 @@ 372 i386 recvmsg sys_recvmsg compat_sys_recvmsg 373 i386 shutdown sys_shutdown 374 i386 userfaultfd sys_userfaultfd +375 i386 membarrier sys_membarrier diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 81c490634db9..278842fdf1f6 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -330,6 +330,7 @@ 321 common bpf sys_bpf 322 64 execveat stub_execveat 323 common userfaultfd sys_userfaultfd +324 common membarrier sys_membarrier # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 08001317aee7..a460e2ef2843 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -885,4 +885,6 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp, int flags); +asmlinkage long sys_membarrier(int cmd, int flags); + #endif diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index e016bd9b1a04..8da542a2874d 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -709,9 +709,11 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create) __SYSCALL(__NR_bpf, sys_bpf) #define __NR_execveat 281 __SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat) +#define __NR_membarrier 282 +__SYSCALL(__NR_membarrier, sys_membarrier) #undef __NR_syscalls -#define __NR_syscalls 282 +#define __NR_syscalls 283 /* * All syscalls below here should go away really, diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 70ff1d9abf0d..f7b2db44eb4b 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -252,6 +252,7 @@ header-y += mdio.h header-y += media.h header-y += media-bus-format.h header-y += mei.h +header-y += membarrier.h header-y += memfd.h header-y += mempolicy.h header-y += meye.h diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h new file mode 100644 index 000000000000..e0b108bd2624 --- /dev/null +++ b/include/uapi/linux/membarrier.h @@ -0,0 +1,53 @@ +#ifndef _UAPI_LINUX_MEMBARRIER_H +#define _UAPI_LINUX_MEMBARRIER_H + +/* + * linux/membarrier.h + * + * membarrier system call API + * + * Copyright (c) 2010, 2015 Mathieu Desnoyers + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +/** + * enum membarrier_cmd - membarrier system call command + * @MEMBARRIER_CMD_QUERY: Query the set of supported commands. It returns + * a bitmask of valid commands. + * @MEMBARRIER_CMD_SHARED: Execute a memory barrier on all running threads. + * Upon return from system call, the caller thread + * is ensured that all running threads have passed + * through a state where all memory accesses to + * user-space addresses match program order between + * entry to and return from the system call + * (non-running threads are de facto in such a + * state). This covers threads from all processes + * running on the system. This command returns 0. + * + * Command to be passed to the membarrier system call. The commands need to + * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to + * the value 0. + */ +enum membarrier_cmd { + MEMBARRIER_CMD_QUERY = 0, + MEMBARRIER_CMD_SHARED = (1 << 0), +}; + +#endif /* _UAPI_LINUX_MEMBARRIER_H */ diff --git a/init/Kconfig b/init/Kconfig index 02da9f1fd9df..c24b6f767bf0 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1602,6 +1602,18 @@ config PCI_QUIRKS bugs/quirks. Disable this only if your target machine is unaffected by PCI quirks. +config MEMBARRIER + bool "Enable membarrier() system call" if EXPERT + default y + help + Enable the membarrier() system call that allows issuing memory + barriers across all running threads, which can be used to distribute + the cost of user-space memory barriers asymmetrically by transforming + pairs of memory barriers into pairs consisting of membarrier() and a + compiler barrier. + + If unsure, say Y. + config EMBEDDED bool "Embedded system" option allnoconfig_y diff --git a/kernel/Makefile b/kernel/Makefile index d4988410b410..53abf008ecb3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -100,6 +100,7 @@ obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o obj-$(CONFIG_TORTURE_TEST) += torture.o +obj-$(CONFIG_MEMBARRIER) += membarrier.o obj-$(CONFIG_HAS_IOMEM) += memremap.o diff --git a/kernel/membarrier.c b/kernel/membarrier.c new file mode 100644 index 000000000000..536c727a56e9 --- /dev/null +++ b/kernel/membarrier.c @@ -0,0 +1,66 @@ +/* + * Copyright (C) 2010, 2015 Mathieu Desnoyers + * + * membarrier system call + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include + +/* + * Bitmask made from a "or" of all commands within enum membarrier_cmd, + * except MEMBARRIER_CMD_QUERY. + */ +#define MEMBARRIER_CMD_BITMASK (MEMBARRIER_CMD_SHARED) + +/** + * sys_membarrier - issue memory barriers on a set of threads + * @cmd: Takes command values defined in enum membarrier_cmd. + * @flags: Currently needs to be 0. For future extensions. + * + * If this system call is not implemented, -ENOSYS is returned. If the + * command specified does not exist, or if the command argument is invalid, + * this system call returns -EINVAL. For a given command, with flags argument + * set to 0, this system call is guaranteed to always return the same value + * until reboot. + * + * All memory accesses performed in program order from each targeted thread + * is guaranteed to be ordered with respect to sys_membarrier(). If we use + * the semantic "barrier()" to represent a compiler barrier forcing memory + * accesses to be performed in program order across the barrier, and + * smp_mb() to represent explicit memory barriers forcing full memory + * ordering across the barrier, we have the following ordering table for + * each pair of barrier(), sys_membarrier() and smp_mb(): + * + * The pair ordering is detailed as (O: ordered, X: not ordered): + * + * barrier() smp_mb() sys_membarrier() + * barrier() X X O + * smp_mb() X O O + * sys_membarrier() O O O + */ +SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) +{ + if (unlikely(flags)) + return -EINVAL; + switch (cmd) { + case MEMBARRIER_CMD_QUERY: + return MEMBARRIER_CMD_BITMASK; + case MEMBARRIER_CMD_SHARED: + if (num_online_cpus() > 1) + synchronize_sched(); + return 0; + default: + return -EINVAL; + } +} diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 03c3875d9958..a02decf15583 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -245,3 +245,6 @@ cond_syscall(sys_bpf); /* execveat */ cond_syscall(sys_execveat); + +/* membarrier */ +cond_syscall(sys_membarrier); -- cgit v1.2.3 From 6798a8caaf64fa68b9ab2044e070fe4545034e03 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 11 Sep 2015 13:07:48 -0700 Subject: fs/seq_file: convert int seq_vprint/seq_printf/etc... returns to void The seq_ function return values were frequently misused. See: commit 1f33c41c03da ("seq_file: Rename seq_overflow() to seq_has_overflowed() and make public") All uses of these return values have been removed, so convert the return types to void. Miscellanea: o Move seq_put_decimal_ and seq_escape prototypes closer the other seq_vprintf prototypes o Reorder seq_putc and seq_puts to return early on overflow o Add argument names to seq_vprintf and seq_printf o Update the seq_escape kernel-doc o Convert a couple of leading spaces to tabs in seq_escape Signed-off-by: Joe Perches Cc: Al Viro Cc: Steven Rostedt Cc: Mark Brown Cc: Stephen Rothwell Cc: Joerg Roedel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/iommu/omap-iommu-debug.c | 3 +- fs/nsfs.c | 3 +- fs/seq_file.c | 70 ++++++++++++++++++---------------------- include/linux/seq_file.h | 19 +++++------ 4 files changed, 45 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c index 0717aa96ce39..9bc20e2119a3 100644 --- a/drivers/iommu/omap-iommu-debug.c +++ b/drivers/iommu/omap-iommu-debug.c @@ -135,8 +135,9 @@ __dump_tlb_entries(struct omap_iommu *obj, struct cr_regs *crs, int num) static ssize_t iotlb_dump_cr(struct omap_iommu *obj, struct cr_regs *cr, struct seq_file *s) { - return seq_printf(s, "%08x %08x %01x\n", cr->cam, cr->ram, + seq_printf(s, "%08x %08x %01x\n", cr->cam, cr->ram, (cr->cam & MMU_CAM_P) ? 1 : 0); + return 0; } static size_t omap_dump_tlb_entries(struct omap_iommu *obj, struct seq_file *s) diff --git a/fs/nsfs.c b/fs/nsfs.c index e4905fbf3396..8f20d6016e20 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -142,7 +142,8 @@ static int nsfs_show_path(struct seq_file *seq, struct dentry *dentry) struct inode *inode = d_inode(dentry); const struct proc_ns_operations *ns_ops = dentry->d_fsdata; - return seq_printf(seq, "%s:[%lu]", ns_ops->name, inode->i_ino); + seq_printf(seq, "%s:[%lu]", ns_ops->name, inode->i_ino); + return 0; } static const struct super_operations nsfs_ops = { diff --git a/fs/seq_file.c b/fs/seq_file.c index 263b125dbcf4..225586e141ca 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -372,16 +372,16 @@ EXPORT_SYMBOL(seq_release); * @esc: set of characters that need escaping * * Puts string into buffer, replacing each occurrence of character from - * @esc with usual octal escape. Returns 0 in case of success, -1 - in - * case of overflow. + * @esc with usual octal escape. + * Use seq_has_overflowed() to check for errors. */ -int seq_escape(struct seq_file *m, const char *s, const char *esc) +void seq_escape(struct seq_file *m, const char *s, const char *esc) { char *end = m->buf + m->size; - char *p; + char *p; char c; - for (p = m->buf + m->count; (c = *s) != '\0' && p < end; s++) { + for (p = m->buf + m->count; (c = *s) != '\0' && p < end; s++) { if (!strchr(esc, c)) { *p++ = c; continue; @@ -394,14 +394,13 @@ int seq_escape(struct seq_file *m, const char *s, const char *esc) continue; } seq_set_overflow(m); - return -1; - } + return; + } m->count = p - m->buf; - return 0; } EXPORT_SYMBOL(seq_escape); -int seq_vprintf(struct seq_file *m, const char *f, va_list args) +void seq_vprintf(struct seq_file *m, const char *f, va_list args) { int len; @@ -409,24 +408,20 @@ int seq_vprintf(struct seq_file *m, const char *f, va_list args) len = vsnprintf(m->buf + m->count, m->size - m->count, f, args); if (m->count + len < m->size) { m->count += len; - return 0; + return; } } seq_set_overflow(m); - return -1; } EXPORT_SYMBOL(seq_vprintf); -int seq_printf(struct seq_file *m, const char *f, ...) +void seq_printf(struct seq_file *m, const char *f, ...) { - int ret; va_list args; va_start(args, f); - ret = seq_vprintf(m, f, args); + seq_vprintf(m, f, args); va_end(args); - - return ret; } EXPORT_SYMBOL(seq_printf); @@ -664,26 +659,25 @@ int seq_open_private(struct file *filp, const struct seq_operations *ops, } EXPORT_SYMBOL(seq_open_private); -int seq_putc(struct seq_file *m, char c) +void seq_putc(struct seq_file *m, char c) { - if (m->count < m->size) { - m->buf[m->count++] = c; - return 0; - } - return -1; + if (m->count >= m->size) + return; + + m->buf[m->count++] = c; } EXPORT_SYMBOL(seq_putc); -int seq_puts(struct seq_file *m, const char *s) +void seq_puts(struct seq_file *m, const char *s) { int len = strlen(s); - if (m->count + len < m->size) { - memcpy(m->buf + m->count, s, len); - m->count += len; - return 0; + + if (m->count + len >= m->size) { + seq_set_overflow(m); + return; } - seq_set_overflow(m); - return -1; + memcpy(m->buf + m->count, s, len); + m->count += len; } EXPORT_SYMBOL(seq_puts); @@ -694,8 +688,8 @@ EXPORT_SYMBOL(seq_puts); * This routine is very quick when you show lots of numbers. * In usual cases, it will be better to use seq_printf(). It's easier to read. */ -int seq_put_decimal_ull(struct seq_file *m, char delimiter, - unsigned long long num) +void seq_put_decimal_ull(struct seq_file *m, char delimiter, + unsigned long long num) { int len; @@ -707,35 +701,33 @@ int seq_put_decimal_ull(struct seq_file *m, char delimiter, if (num < 10) { m->buf[m->count++] = num + '0'; - return 0; + return; } len = num_to_str(m->buf + m->count, m->size - m->count, num); if (!len) goto overflow; m->count += len; - return 0; + return; + overflow: seq_set_overflow(m); - return -1; } EXPORT_SYMBOL(seq_put_decimal_ull); -int seq_put_decimal_ll(struct seq_file *m, char delimiter, - long long num) +void seq_put_decimal_ll(struct seq_file *m, char delimiter, long long num) { if (num < 0) { if (m->count + 3 >= m->size) { seq_set_overflow(m); - return -1; + return; } if (delimiter) m->buf[m->count++] = delimiter; num = -num; delimiter = '-'; } - return seq_put_decimal_ull(m, delimiter, num); - + seq_put_decimal_ull(m, delimiter, num); } EXPORT_SYMBOL(seq_put_decimal_ll); diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index adeadbd6d7bf..dde00defbaa5 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -114,13 +114,18 @@ int seq_open(struct file *, const struct seq_operations *); ssize_t seq_read(struct file *, char __user *, size_t, loff_t *); loff_t seq_lseek(struct file *, loff_t, int); int seq_release(struct inode *, struct file *); -int seq_escape(struct seq_file *, const char *, const char *); -int seq_putc(struct seq_file *m, char c); -int seq_puts(struct seq_file *m, const char *s); int seq_write(struct seq_file *seq, const void *data, size_t len); -__printf(2, 3) int seq_printf(struct seq_file *, const char *, ...); -__printf(2, 0) int seq_vprintf(struct seq_file *, const char *, va_list args); +__printf(2, 0) +void seq_vprintf(struct seq_file *m, const char *fmt, va_list args); +__printf(2, 3) +void seq_printf(struct seq_file *m, const char *fmt, ...); +void seq_putc(struct seq_file *m, char c); +void seq_puts(struct seq_file *m, const char *s); +void seq_put_decimal_ull(struct seq_file *m, char delimiter, + unsigned long long num); +void seq_put_decimal_ll(struct seq_file *m, char delimiter, long long num); +void seq_escape(struct seq_file *m, const char *s, const char *esc); void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, @@ -138,10 +143,6 @@ int single_release(struct inode *, struct file *); void *__seq_open_private(struct file *, const struct seq_operations *, int); int seq_open_private(struct file *, const struct seq_operations *, int); int seq_release_private(struct inode *, struct file *); -int seq_put_decimal_ull(struct seq_file *m, char delimiter, - unsigned long long num); -int seq_put_decimal_ll(struct seq_file *m, char delimiter, - long long num); static inline struct user_namespace *seq_user_ns(struct seq_file *seq) { -- cgit v1.2.3 From 10fbd36e362a0f367e34a7cd876a81295d8fc5ca Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 27 May 2015 15:32:15 -0700 Subject: blk: rq_data_dir() should not return a boolean MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit rq_data_dir() returns either READ or WRITE (0 == READ, 1 == WRITE), not a boolean value. Now, admittedly the "!= 0" doesn't really change the value (0 stays as zero, 1 stays as one), but it's not only redundant, it confuses gcc, and causes gcc to warn about the construct switch (rq_data_dir(req)) { case READ: ... case WRITE: ... that we have in a few drivers. Now, the gcc warning is silly and stupid (it seems to warn not about the switch value having a different type from the case statements, but about _any_ boolean switch value), but in this case the code itself is silly and stupid too, so let's just change it, and get rid of warnings like this: drivers/block/hd.c: In function ‘hd_request’: drivers/block/hd.c:630:11: warning: switch condition has boolean value [-Wswitch-bool] switch (rq_data_dir(req)) { The odd '!= 0' came in when "cmd_flags" got turned into a "u64" in commit 5953316dbf90 ("block: make rq->cmd_flags be 64-bit") and is presumably because the old code (that just did a logical 'and' with 1) would then end up making the type of rq_data_dir() be u64 too. But if we want to retain the old regular integer type, let's just cast the result to 'int' rather than use that rather odd '!= 0'. Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 708923b9b623..38a5ff772a37 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -584,7 +584,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -#define rq_data_dir(rq) (((rq)->cmd_flags & 1) != 0) +#define rq_data_dir(rq) ((int)((rq)->cmd_flags & 1)) /* * Driver can handle struct request, if it either has an old style -- cgit v1.2.3 From cd33dc9ac2977ebe30cecbf39d2992190fbac5b4 Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Tue, 8 Sep 2015 14:51:12 +0100 Subject: thermal: Fix thermal_zone_of_sensor_register to match documentation thermal_zone_of_sensor_register is documented as returning a pointer to either a valid thermal_zone_device on success, or a corresponding ERR_PTR() value. In contrast, the function returns NULL when THERMAL_OF is configured off. Fix this. Signed-off-by: Punit Agrawal Acked-by: Guenter Roeck Cc: Eduardo Valentin Cc: Zhang Rui Signed-off-by: Eduardo Valentin --- include/linux/thermal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 17292fee8686..0c5518e13584 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -360,7 +360,7 @@ static inline struct thermal_zone_device * thermal_zone_of_sensor_register(struct device *dev, int id, void *data, const struct thermal_zone_of_device_ops *ops) { - return NULL; + return ERR_PTR(-ENODEV); } static inline -- cgit v1.2.3 From eef7635a22f6b144206b5ca2f1398f637acffc4d Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 11 Sep 2015 09:34:26 +0530 Subject: clockevents: Remove unused set_mode() callback All users are migrated to the per-state callbacks, get rid of the unused interface and the core support code. Signed-off-by: Viresh Kumar Signed-off-by: Thomas Gleixner Cc: linaro-kernel@lists.linaro.org Cc: John Stultz Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/fd60de14cf6d125489c031207567bb255ad946f6.1441943991.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar --- include/linux/clockchips.h | 29 +++++-------------------- kernel/time/clockevents.c | 42 +----------------------------------- kernel/time/tick-common.c | 1 - kernel/time/timer_list.c | 54 +++++++++++++++++++++------------------------- 4 files changed, 30 insertions(+), 96 deletions(-) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 31ce435981fe..bdcf358dfce2 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -18,15 +18,6 @@ struct clock_event_device; struct module; -/* Clock event mode commands for legacy ->set_mode(): OBSOLETE */ -enum clock_event_mode { - CLOCK_EVT_MODE_UNUSED, - CLOCK_EVT_MODE_SHUTDOWN, - CLOCK_EVT_MODE_PERIODIC, - CLOCK_EVT_MODE_ONESHOT, - CLOCK_EVT_MODE_RESUME, -}; - /* * Possible states of a clock event device. * @@ -86,16 +77,14 @@ enum clock_event_state { * @min_delta_ns: minimum delta value in ns * @mult: nanosecond to cycles multiplier * @shift: nanoseconds to cycles divisor (power of two) - * @mode: operating mode, relevant only to ->set_mode(), OBSOLETE * @state_use_accessors:current state of the device, assigned by the core code * @features: features * @retries: number of forced programming retries - * @set_mode: legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME. - * @set_state_periodic: switch state to periodic, if !set_mode - * @set_state_oneshot: switch state to oneshot, if !set_mode - * @set_state_oneshot_stopped: switch state to oneshot_stopped, if !set_mode - * @set_state_shutdown: switch state to shutdown, if !set_mode - * @tick_resume: resume clkevt device, if !set_mode + * @set_state_periodic: switch state to periodic + * @set_state_oneshot: switch state to oneshot + * @set_state_oneshot_stopped: switch state to oneshot_stopped + * @set_state_shutdown: switch state to shutdown + * @tick_resume: resume clkevt device * @broadcast: function to broadcast events * @min_delta_ticks: minimum delta value in ticks stored for reconfiguration * @max_delta_ticks: maximum delta value in ticks stored for reconfiguration @@ -116,18 +105,10 @@ struct clock_event_device { u64 min_delta_ns; u32 mult; u32 shift; - enum clock_event_mode mode; enum clock_event_state state_use_accessors; unsigned int features; unsigned long retries; - /* - * State transition callback(s): Only one of the two groups should be - * defined: - * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME. - * - set_state_{shutdown|periodic|oneshot|oneshot_stopped}(), tick_resume(). - */ - void (*set_mode)(enum clock_event_mode mode, struct clock_event_device *); int (*set_state_periodic)(struct clock_event_device *); int (*set_state_oneshot)(struct clock_event_device *); int (*set_state_oneshot_stopped)(struct clock_event_device *); diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 50eb107f1198..a9b76a40319e 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -97,20 +97,6 @@ EXPORT_SYMBOL_GPL(clockevent_delta2ns); static int __clockevents_switch_state(struct clock_event_device *dev, enum clock_event_state state) { - /* Transition with legacy set_mode() callback */ - if (dev->set_mode) { - /* Legacy callback doesn't support new modes */ - if (state > CLOCK_EVT_STATE_ONESHOT) - return -ENOSYS; - /* - * 'clock_event_state' and 'clock_event_mode' have 1-to-1 - * mapping until *_ONESHOT, and so a simple cast will work. - */ - dev->set_mode((enum clock_event_mode)state, dev); - dev->mode = (enum clock_event_mode)state; - return 0; - } - if (dev->features & CLOCK_EVT_FEAT_DUMMY) return 0; @@ -204,12 +190,8 @@ int clockevents_tick_resume(struct clock_event_device *dev) { int ret = 0; - if (dev->set_mode) { - dev->set_mode(CLOCK_EVT_MODE_RESUME, dev); - dev->mode = CLOCK_EVT_MODE_RESUME; - } else if (dev->tick_resume) { + if (dev->tick_resume) ret = dev->tick_resume(dev); - } return ret; } @@ -460,26 +442,6 @@ int clockevents_unbind_device(struct clock_event_device *ced, int cpu) } EXPORT_SYMBOL_GPL(clockevents_unbind_device); -/* Sanity check of state transition callbacks */ -static int clockevents_sanity_check(struct clock_event_device *dev) -{ - /* Legacy set_mode() callback */ - if (dev->set_mode) { - /* We shouldn't be supporting new modes now */ - WARN_ON(dev->set_state_periodic || dev->set_state_oneshot || - dev->set_state_shutdown || dev->tick_resume || - dev->set_state_oneshot_stopped); - - BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); - return 0; - } - - if (dev->features & CLOCK_EVT_FEAT_DUMMY) - return 0; - - return 0; -} - /** * clockevents_register_device - register a clock event device * @dev: device to register @@ -488,8 +450,6 @@ void clockevents_register_device(struct clock_event_device *dev) { unsigned long flags; - BUG_ON(clockevents_sanity_check(dev)); - /* Initialize state to DETACHED */ clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index d11c55b6ab7d..4fcd99e12aa0 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -398,7 +398,6 @@ void tick_shutdown(unsigned int cpu) * the set mode function! */ clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED); - dev->mode = CLOCK_EVT_MODE_UNUSED; clockevents_exchange_device(dev, NULL); dev->event_handler = clockevents_handle_noop; td->evtdev = NULL; diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 129c96033e46..f75e35b60149 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -225,7 +225,7 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) (unsigned long long) dev->min_delta_ns); SEQ_printf(m, " mult: %u\n", dev->mult); SEQ_printf(m, " shift: %u\n", dev->shift); - SEQ_printf(m, " mode: %d\n", dev->mode); + SEQ_printf(m, " mode: %d\n", clockevent_get_state(dev)); SEQ_printf(m, " next_event: %Ld nsecs\n", (unsigned long long) ktime_to_ns(dev->next_event)); @@ -233,40 +233,34 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) print_name_offset(m, dev->set_next_event); SEQ_printf(m, "\n"); - if (dev->set_mode) { - SEQ_printf(m, " set_mode: "); - print_name_offset(m, dev->set_mode); + if (dev->set_state_shutdown) { + SEQ_printf(m, " shutdown: "); + print_name_offset(m, dev->set_state_shutdown); SEQ_printf(m, "\n"); - } else { - if (dev->set_state_shutdown) { - SEQ_printf(m, " shutdown: "); - print_name_offset(m, dev->set_state_shutdown); - SEQ_printf(m, "\n"); - } + } - if (dev->set_state_periodic) { - SEQ_printf(m, " periodic: "); - print_name_offset(m, dev->set_state_periodic); - SEQ_printf(m, "\n"); - } + if (dev->set_state_periodic) { + SEQ_printf(m, " periodic: "); + print_name_offset(m, dev->set_state_periodic); + SEQ_printf(m, "\n"); + } - if (dev->set_state_oneshot) { - SEQ_printf(m, " oneshot: "); - print_name_offset(m, dev->set_state_oneshot); - SEQ_printf(m, "\n"); - } + if (dev->set_state_oneshot) { + SEQ_printf(m, " oneshot: "); + print_name_offset(m, dev->set_state_oneshot); + SEQ_printf(m, "\n"); + } - if (dev->set_state_oneshot_stopped) { - SEQ_printf(m, " oneshot stopped: "); - print_name_offset(m, dev->set_state_oneshot_stopped); - SEQ_printf(m, "\n"); - } + if (dev->set_state_oneshot_stopped) { + SEQ_printf(m, " oneshot stopped: "); + print_name_offset(m, dev->set_state_oneshot_stopped); + SEQ_printf(m, "\n"); + } - if (dev->tick_resume) { - SEQ_printf(m, " resume: "); - print_name_offset(m, dev->tick_resume); - SEQ_printf(m, "\n"); - } + if (dev->tick_resume) { + SEQ_printf(m, " resume: "); + print_name_offset(m, dev->tick_resume); + SEQ_printf(m, "\n"); } SEQ_printf(m, " event_handler: "); -- cgit v1.2.3 From c973c3bcec3752455c4d7545edd42935cd7942d9 Mon Sep 17 00:00:00 2001 From: Javi Merino Date: Mon, 14 Sep 2015 14:23:50 +0100 Subject: thermal: Add a function to get the minimum power The thermal core already has a function to get the maximum power of a cooling device: power_actor_get_max_power(). Add a function to get the minimum power of a cooling device. Cc: Zhang Rui Cc: Eduardo Valentin Reviewed-by: Daniel Kurtz Signed-off-by: Javi Merino Signed-off-by: Eduardo Valentin --- drivers/thermal/thermal_core.c | 28 ++++++++++++++++++++++++++++ include/linux/thermal.h | 6 ++++++ 2 files changed, 34 insertions(+) (limited to 'include') diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 5e5fc7015c7f..d9e525cc9c1c 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1012,6 +1012,34 @@ int power_actor_get_max_power(struct thermal_cooling_device *cdev, return cdev->ops->state2power(cdev, tz, 0, max_power); } +/** + * power_actor_get_min_power() - get the mainimum power that a cdev can consume + * @cdev: pointer to &thermal_cooling_device + * @tz: a valid thermal zone device pointer + * @min_power: pointer in which to store the minimum power + * + * Calculate the minimum power consumption in milliwatts that the + * cooling device can currently consume and store it in @min_power. + * + * Return: 0 on success, -EINVAL if @cdev doesn't support the + * power_actor API or -E* on other error. + */ +int power_actor_get_min_power(struct thermal_cooling_device *cdev, + struct thermal_zone_device *tz, u32 *min_power) +{ + unsigned long max_state; + int ret; + + if (!cdev_is_power_actor(cdev)) + return -EINVAL; + + ret = cdev->ops->get_max_state(cdev, &max_state); + if (ret) + return ret; + + return cdev->ops->state2power(cdev, tz, max_state, min_power); +} + /** * power_actor_set_power() - limit the maximum power that a cooling device can consume * @cdev: pointer to &thermal_cooling_device diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 0c5518e13584..157d366e761b 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -380,6 +380,8 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) int power_actor_get_max_power(struct thermal_cooling_device *, struct thermal_zone_device *tz, u32 *max_power); +int power_actor_get_min_power(struct thermal_cooling_device *, + struct thermal_zone_device *tz, u32 *min_power); int power_actor_set_power(struct thermal_cooling_device *, struct thermal_instance *, u32); struct thermal_zone_device *thermal_zone_device_register(const char *, int, int, @@ -415,6 +417,10 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) static inline int power_actor_get_max_power(struct thermal_cooling_device *cdev, struct thermal_zone_device *tz, u32 *max_power) { return 0; } +static inline int power_actor_get_min_power(struct thermal_cooling_device *cdev, + struct thermal_zone_device *tz, + u32 *min_power) +{ return -ENODEV; } static inline int power_actor_set_power(struct thermal_cooling_device *cdev, struct thermal_instance *tz, u32 power) { return 0; } -- cgit v1.2.3 From 63cdbc06b357dcb3a7104a421ee4a4550d7fadfd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 14 Sep 2015 17:06:27 +0200 Subject: netfilter: bridge: fix routing of bridge frames with call-iptables=1 We can't re-use the physoutdev storage area. 1. When using NFQUEUE in PREROUTING, we attempt to bump a bogus refcnt since nf_bridge->physoutdev is garbage (ipv4/ipv6 address) 2. for same reason, we crash in physdev match in FORWARD or later if skb is routed instead of bridged. This increases nf_bridge_info to 40 bytes, but we have no other choice. Fixes: 72b1e5e4cac7 ("netfilter: bridge: reduce nf_bridge_info to 32 bytes again") Reported-by: Sander Eikelenboom Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2738d355cdf9..9987af080fa0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -179,6 +179,9 @@ struct nf_bridge_info { u8 bridged_dnat:1; __u16 frag_max_size; struct net_device *physindev; + + /* always valid & non-NULL from FORWARD on, for physdev match */ + struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; @@ -189,9 +192,6 @@ struct nf_bridge_info { * skb is out in neigh layer. */ char neigh_header[8]; - - /* always valid & non-NULL from FORWARD on, for physdev match */ - struct net_device *physoutdev; }; }; #endif -- cgit v1.2.3 From bcb2b0b2bae2de744223c68521cd51c57feb486c Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 14 Sep 2015 16:01:55 +0100 Subject: ACPI: Eliminate CONFIG_.*{, _MODULE} #ifdef in favor of IS_ENABLED() This commit removes all CONFIG_.*{,_MODULE} in ACPI code, replacing it with IS_ENABLED(). Signed-off-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki --- drivers/acpi/bus.c | 12 ++++-------- drivers/acpi/int340x_thermal.c | 9 ++++----- include/acpi/button.h | 4 ++-- include/acpi/video.h | 2 +- 4 files changed, 11 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 46506e7687cd..a212cefae524 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -315,14 +315,10 @@ static void acpi_bus_osc_support(void) capbuf[OSC_QUERY_DWORD] = OSC_QUERY_ENABLE; capbuf[OSC_SUPPORT_DWORD] = OSC_SB_PR3_SUPPORT; /* _PR3 is in use */ -#if defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR) ||\ - defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR_MODULE) - capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PAD_SUPPORT; -#endif - -#if defined(CONFIG_ACPI_PROCESSOR) || defined(CONFIG_ACPI_PROCESSOR_MODULE) - capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PPC_OST_SUPPORT; -#endif + if (IS_ENABLED(CONFIG_ACPI_PROCESSOR_AGGREGATOR)) + capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PAD_SUPPORT; + if (IS_ENABLED(CONFIG_ACPI_PROCESSOR)) + capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PPC_OST_SUPPORT; capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_HOTPLUG_OST_SUPPORT; diff --git a/drivers/acpi/int340x_thermal.c b/drivers/acpi/int340x_thermal.c index 6c7c7975f72e..33505c651f62 100644 --- a/drivers/acpi/int340x_thermal.c +++ b/drivers/acpi/int340x_thermal.c @@ -33,13 +33,12 @@ static const struct acpi_device_id int340x_thermal_device_ids[] = { static int int340x_thermal_handler_attach(struct acpi_device *adev, const struct acpi_device_id *id) { -#if defined(CONFIG_INT340X_THERMAL) || defined(CONFIG_INT340X_THERMAL_MODULE) - acpi_create_platform_device(adev); -#elif defined(CONFIG_INTEL_SOC_DTS_THERMAL) || defined(CONFIG_INTEL_SOC_DTS_THERMAL_MODULE) + if (IS_ENABLED(CONFIG_INT340X_THERMAL)) + acpi_create_platform_device(adev); /* Intel SoC DTS thermal driver needs INT3401 to set IRQ descriptor */ - if (id->driver_data == INT3401_DEVICE) + else if (IS_ENABLED(CONFIG_INTEL_SOC_DTS_THERMAL) && + id->driver_data == INT3401_DEVICE) acpi_create_platform_device(adev); -#endif return 1; } diff --git a/include/acpi/button.h b/include/acpi/button.h index 97eea0e4c016..1cad8b2d460c 100644 --- a/include/acpi/button.h +++ b/include/acpi/button.h @@ -3,7 +3,7 @@ #include -#if defined(CONFIG_ACPI_BUTTON) || defined(CONFIG_ACPI_BUTTON_MODULE) +#if IS_ENABLED(CONFIG_ACPI_BUTTON) extern int acpi_lid_notifier_register(struct notifier_block *nb); extern int acpi_lid_notifier_unregister(struct notifier_block *nb); extern int acpi_lid_open(void); @@ -20,6 +20,6 @@ static inline int acpi_lid_open(void) { return 1; } -#endif /* defined(CONFIG_ACPI_BUTTON) || defined(CONFIG_ACPI_BUTTON_MODULE) */ +#endif /* IS_ENABLED(CONFIG_ACPI_BUTTON) */ #endif /* ACPI_BUTTON_H */ diff --git a/include/acpi/video.h b/include/acpi/video.h index e840b294c6f5..c62392d9b52a 100644 --- a/include/acpi/video.h +++ b/include/acpi/video.h @@ -24,7 +24,7 @@ enum acpi_backlight_type { acpi_backlight_native, }; -#if (defined CONFIG_ACPI_VIDEO || defined CONFIG_ACPI_VIDEO_MODULE) +#if IS_ENABLED(CONFIG_ACPI_VIDEO) extern int acpi_video_register(void); extern void acpi_video_unregister(void); extern int acpi_video_get_edid(struct acpi_device *device, int type, -- cgit v1.2.3 From 1975dbc276c6ab62230cf4f9df5ddc9ff0e0e473 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Mon, 14 Sep 2015 17:11:05 -0600 Subject: locking/static_keys: Fix up the static keys documentation Fix a few small mistakes in the static key documentation and delete an unneeded sentence. Suggested-by: Jason Baron Signed-off-by: Jonathan Corbet Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20150914171105.511e1e21@lwn.net Signed-off-by: Ingo Molnar --- Documentation/static-keys.txt | 4 ++-- include/linux/jump_label.h | 10 ++++------ 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/Documentation/static-keys.txt b/Documentation/static-keys.txt index ec911583f6c5..477927becacb 100644 --- a/Documentation/static-keys.txt +++ b/Documentation/static-keys.txt @@ -15,8 +15,8 @@ The updated API replacements are: DEFINE_STATIC_KEY_TRUE(key); DEFINE_STATIC_KEY_FALSE(key); -static_key_likely() -static_key_unlikely() +static_branch_likely() +static_branch_unlikely() 0) Abstract diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 0684bd3a48fc..f1094238ab2a 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -21,8 +21,8 @@ * * DEFINE_STATIC_KEY_TRUE(key); * DEFINE_STATIC_KEY_FALSE(key); - * static_key_likely() - * static_key_unlikely() + * static_branch_likely() + * static_branch_unlikely() * * Jump labels provide an interface to generate dynamic branches using * self-modifying code. Assuming toolchain and architecture support, if we @@ -45,12 +45,10 @@ * statement, setting the key to true requires us to patch in a jump * to the out-of-line of true branch. * - * In addtion to static_branch_{enable,disable}, we can also reference count + * In addition to static_branch_{enable,disable}, we can also reference count * the key or branch direction via static_branch_{inc,dec}. Thus, * static_branch_inc() can be thought of as a 'make more true' and - * static_branch_dec() as a 'make more false'. The inc()/dec() - * interface is meant to be used exclusively from the inc()/dec() for a given - * key. + * static_branch_dec() as a 'make more false'. * * Since this relies on modifying code, the branch modifying functions * must be considered absolute slow paths (machine wide synchronization etc.). -- cgit v1.2.3 From 3829c664b1eec243f2a355829efa40f0f414de8d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 15 Sep 2015 13:47:24 +0200 Subject: genirq: Remove stale comment Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 6f8b34066442..72a6b2feb7bf 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -151,10 +151,6 @@ struct irq_common_data { * methods, to allow shared chip implementations * @msi_desc: MSI descriptor * @affinity: IRQ affinity on SMP - * - * The fields here need to overlay the ones in irq_desc until we - * cleaned up the direct references and switched everything over to - * irq_data. */ struct irq_data { u32 mask; -- cgit v1.2.3 From 6584d84c3e504c76ad291cc2e381bbeed59798ab Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Tue, 1 Sep 2015 10:35:50 +0800 Subject: genirq: Update the comment for generic_handle_irq_desc __do_IRQ() was removed by commit 1c77ff2 "genirq: Remove __do_IRQ", but the comment referring to __do_IRQ() was left. Update the comment for generic_handle_irq_desc(). Signed-off-by: Huang Shijie Cc: jiang.liu@linux.intel.com Cc: peterz@infradead.org Cc: rafael.j.wysocki@intel.com Cc: jason@lakedaemon.net Cc: marc.zyngier@arm.com Link: http://lkml.kernel.org/r/1441074950-3893-1-git-send-email-shijie.huang@arm.com Signed-off-by: Thomas Gleixner --- include/linux/irqdesc.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 5acfa26602e1..0593c691d091 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -137,9 +137,7 @@ static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) /* * Architectures call this to let the generic IRQ layer - * handle an interrupt. If the descriptor is attached to an - * irqchip-style controller then we call the ->handle_irq() handler, - * and it calls __do_IRQ() if it's attached to an irqtype-style controller. + * handle an interrupt. */ static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc) { -- cgit v1.2.3 From f230d1e891ba1da5953460516960894154f265db Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 15 Sep 2015 14:30:06 -0700 Subject: ipv6: Rename the dst_cache helper functions in ip6_tunnel It is a prep work to fix the dst_entry refcnt bugs in ip6_tunnel. This patch rename: 1. ip6_tnl_dst_check() to ip6_tnl_dst_get() to better reflect that it will take a dst refcnt in the next patch. 2. ip6_tnl_dst_store() to ip6_tnl_dst_set() to have a more conventional name matching with ip6_tnl_dst_get(). Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/ip6_tunnel.h | 4 ++-- net/ipv6/ip6_gre.c | 4 ++-- net/ipv6/ip6_tunnel.c | 12 ++++++------ 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index b8529aa1dae7..979b081a47e8 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -60,9 +60,9 @@ struct ipv6_tlv_tnl_enc_lim { __u8 encap_limit; /* tunnel encapsulation limit */ } __packed; -struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t); +struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t); void ip6_tnl_dst_reset(struct ip6_tnl *t); -void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst); +void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst); int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr); int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index af60d46129c1..24f5dd8f76a8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -634,7 +634,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, } if (!fl6->flowi6_mark) - dst = ip6_tnl_dst_check(tunnel); + dst = ip6_tnl_dst_get(tunnel); if (!dst) { ndst = ip6_route_output(net, NULL, fl6); @@ -763,7 +763,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, ip6tunnel_xmit(NULL, skb, dev); if (ndst) - ip6_tnl_dst_store(tunnel, ndst); + ip6_tnl_dst_set(tunnel, ndst); return 0; tx_err_link_failure: stats->tx_carrier_errors++; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index b0ab420612bc..599b0b419fbc 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -126,7 +126,7 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) * Locking : hash tables are protected by RCU and RTNL */ -struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) +struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t) { struct dst_entry *dst = t->dst_cache; @@ -139,7 +139,7 @@ struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) return dst; } -EXPORT_SYMBOL_GPL(ip6_tnl_dst_check); +EXPORT_SYMBOL_GPL(ip6_tnl_dst_get); void ip6_tnl_dst_reset(struct ip6_tnl *t) { @@ -148,14 +148,14 @@ void ip6_tnl_dst_reset(struct ip6_tnl *t) } EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset); -void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) +void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *) dst; t->dst_cookie = rt6_get_cookie(rt); dst_release(t->dst_cache); t->dst_cache = dst; } -EXPORT_SYMBOL_GPL(ip6_tnl_dst_store); +EXPORT_SYMBOL_GPL(ip6_tnl_dst_set); /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses @@ -1010,7 +1010,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); } else if (!fl6->flowi6_mark) - dst = ip6_tnl_dst_check(t); + dst = ip6_tnl_dst_get(t); if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr)) goto tx_err_link_failure; @@ -1102,7 +1102,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, ipv6h->daddr = fl6->daddr; ip6tunnel_xmit(NULL, skb, dev); if (ndst) - ip6_tnl_dst_store(t, ndst); + ip6_tnl_dst_set(t, ndst); return 0; tx_err_link_failure: stats->tx_carrier_errors++; -- cgit v1.2.3 From cdf3464e6c6bd764277cbbe992cd12da735b92fb Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 15 Sep 2015 14:30:07 -0700 Subject: ipv6: Fix dst_entry refcnt bugs in ip6_tunnel Problems in the current dst_entry cache in the ip6_tunnel: 1. ip6_tnl_dst_set is racy. There is no lock to protect it: - One major problem is that the dst refcnt gets messed up. F.e. the same dst_cache can be released multiple times and then triggering the infamous dst refcnt < 0 warning message. - Another issue is the inconsistency between dst_cache and dst_cookie. It can be reproduced by adding and removing the ip6gre tunnel while running a super_netperf TCP_CRR test. 2. ip6_tnl_dst_get does not take the dst refcnt before returning the dst. This patch: 1. Create a percpu dst_entry cache in ip6_tnl 2. Use a spinlock to protect the dst_cache operations 3. ip6_tnl_dst_get always takes the dst refcnt before returning Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/ip6_tunnel.h | 11 ++++- net/ipv6/ip6_gre.c | 38 ++++++++------- net/ipv6/ip6_tunnel.c | 122 +++++++++++++++++++++++++++++++++++------------ 3 files changed, 123 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 979b081a47e8..60b4f402f78c 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -32,6 +32,12 @@ struct __ip6_tnl_parm { __be32 o_key; }; +struct ip6_tnl_dst { + spinlock_t lock; + struct dst_entry *dst; + u32 cookie; +}; + /* IPv6 tunnel */ struct ip6_tnl { struct ip6_tnl __rcu *next; /* next tunnel in list */ @@ -39,8 +45,7 @@ struct ip6_tnl { struct net *net; /* netns for packet i/o */ struct __ip6_tnl_parm parms; /* tunnel configuration parameters */ struct flowi fl; /* flowi template for xmit */ - struct dst_entry *dst_cache; /* cached dst */ - u32 dst_cookie; + struct ip6_tnl_dst __percpu *dst_cache; /* cached dst */ int err_count; unsigned long err_time; @@ -61,6 +66,8 @@ struct ipv6_tlv_tnl_enc_lim { } __packed; struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t); +int ip6_tnl_dst_init(struct ip6_tnl *t); +void ip6_tnl_dst_destroy(struct ip6_tnl *t); void ip6_tnl_dst_reset(struct ip6_tnl *t); void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst); int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 24f5dd8f76a8..646512488c28 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -637,17 +637,17 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, dst = ip6_tnl_dst_get(tunnel); if (!dst) { - ndst = ip6_route_output(net, NULL, fl6); + dst = ip6_route_output(net, NULL, fl6); - if (ndst->error) + if (dst->error) goto tx_err_link_failure; - ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(fl6), NULL, 0); - if (IS_ERR(ndst)) { - err = PTR_ERR(ndst); - ndst = NULL; + dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; goto tx_err_link_failure; } - dst = ndst; + ndst = dst; } tdev = dst->dev; @@ -702,12 +702,9 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb = new_skb; } - if (fl6->flowi6_mark) { - skb_dst_set(skb, dst); - ndst = NULL; - } else { - skb_dst_set_noref(skb, dst); - } + if (!fl6->flowi6_mark && ndst) + ip6_tnl_dst_set(tunnel, ndst); + skb_dst_set(skb, dst); proto = NEXTHDR_GRE; if (encap_limit >= 0) { @@ -762,14 +759,12 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb_set_inner_protocol(skb, protocol); ip6tunnel_xmit(NULL, skb, dev); - if (ndst) - ip6_tnl_dst_set(tunnel, ndst); return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: - dst_release(ndst); + dst_release(dst); return err; } @@ -1223,6 +1218,9 @@ static const struct net_device_ops ip6gre_netdev_ops = { static void ip6gre_dev_free(struct net_device *dev) { + struct ip6_tnl *t = netdev_priv(dev); + + ip6_tnl_dst_destroy(t); free_percpu(dev->tstats); free_netdev(dev); } @@ -1248,6 +1246,7 @@ static void ip6gre_tunnel_setup(struct net_device *dev) static int ip6gre_tunnel_init_common(struct net_device *dev) { struct ip6_tnl *tunnel; + int ret; tunnel = netdev_priv(dev); @@ -1259,6 +1258,13 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) if (!dev->tstats) return -ENOMEM; + ret = ip6_tnl_dst_init(tunnel); + if (ret) { + free_percpu(dev->tstats); + dev->tstats = NULL; + return ret; + } + return 0; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 599b0b419fbc..851cf6d1eb45 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -126,37 +126,90 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) * Locking : hash tables are protected by RCU and RTNL */ -struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t) +static void __ip6_tnl_per_cpu_dst_set(struct ip6_tnl_dst *idst, + struct dst_entry *dst) { - struct dst_entry *dst = t->dst_cache; - - if (dst && dst->obsolete && - !dst->ops->check(dst, t->dst_cookie)) { - t->dst_cache = NULL; - dst_release(dst); - return NULL; + dst_release(idst->dst); + if (dst) { + dst_hold(dst); + idst->cookie = rt6_get_cookie((struct rt6_info *)dst); + } else { + idst->cookie = 0; } + idst->dst = dst; +} + +static void ip6_tnl_per_cpu_dst_set(struct ip6_tnl_dst *idst, + struct dst_entry *dst) +{ + spin_lock_bh(&idst->lock); + __ip6_tnl_per_cpu_dst_set(idst, dst); + spin_unlock_bh(&idst->lock); +} + +struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t) +{ + struct ip6_tnl_dst *idst; + struct dst_entry *dst; + + idst = raw_cpu_ptr(t->dst_cache); + spin_lock_bh(&idst->lock); + dst = idst->dst; + if (dst) { + if (!dst->obsolete || dst->ops->check(dst, idst->cookie)) { + dst_hold(idst->dst); + } else { + __ip6_tnl_per_cpu_dst_set(idst, NULL); + dst = NULL; + } + } + spin_unlock_bh(&idst->lock); return dst; } EXPORT_SYMBOL_GPL(ip6_tnl_dst_get); void ip6_tnl_dst_reset(struct ip6_tnl *t) { - dst_release(t->dst_cache); - t->dst_cache = NULL; + int i; + + for_each_possible_cpu(i) + ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), NULL); } EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset); void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst) { - struct rt6_info *rt = (struct rt6_info *) dst; - t->dst_cookie = rt6_get_cookie(rt); - dst_release(t->dst_cache); - t->dst_cache = dst; + ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), dst); + } EXPORT_SYMBOL_GPL(ip6_tnl_dst_set); +void ip6_tnl_dst_destroy(struct ip6_tnl *t) +{ + if (!t->dst_cache) + return; + + ip6_tnl_dst_reset(t); + free_percpu(t->dst_cache); +} +EXPORT_SYMBOL_GPL(ip6_tnl_dst_destroy); + +int ip6_tnl_dst_init(struct ip6_tnl *t) +{ + int i; + + t->dst_cache = alloc_percpu(struct ip6_tnl_dst); + if (!t->dst_cache) + return -ENOMEM; + + for_each_possible_cpu(i) + spin_lock_init(&per_cpu_ptr(t->dst_cache, i)->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(ip6_tnl_dst_init); + /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses * @remote: the address of the tunnel exit-point @@ -271,6 +324,9 @@ ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) static void ip6_dev_free(struct net_device *dev) { + struct ip6_tnl *t = netdev_priv(dev); + + ip6_tnl_dst_destroy(t); free_percpu(dev->tstats); free_netdev(dev); } @@ -1016,17 +1072,17 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, goto tx_err_link_failure; if (!dst) { - ndst = ip6_route_output(net, NULL, fl6); + dst = ip6_route_output(net, NULL, fl6); - if (ndst->error) + if (dst->error) goto tx_err_link_failure; - ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(fl6), NULL, 0); - if (IS_ERR(ndst)) { - err = PTR_ERR(ndst); - ndst = NULL; + dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; goto tx_err_link_failure; } - dst = ndst; + ndst = dst; } tdev = dst->dev; @@ -1072,12 +1128,11 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, consume_skb(skb); skb = new_skb; } - if (fl6->flowi6_mark) { - skb_dst_set(skb, dst); - ndst = NULL; - } else { - skb_dst_set_noref(skb, dst); - } + + if (!fl6->flowi6_mark && ndst) + ip6_tnl_dst_set(t, ndst); + skb_dst_set(skb, dst); + skb->transport_header = skb->network_header; proto = fl6->flowi6_proto; @@ -1101,14 +1156,12 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, ipv6h->saddr = fl6->saddr; ipv6h->daddr = fl6->daddr; ip6tunnel_xmit(NULL, skb, dev); - if (ndst) - ip6_tnl_dst_set(t, ndst); return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: - dst_release(ndst); + dst_release(dst); return err; } @@ -1573,12 +1626,21 @@ static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); + int ret; t->dev = dev; t->net = dev_net(dev); dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; + + ret = ip6_tnl_dst_init(t); + if (ret) { + free_percpu(dev->tstats); + dev->tstats = NULL; + return ret; + } + return 0; } -- cgit v1.2.3 From 70da5b5c532f0ec8aa76b4f46158da5f010f34b3 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 15 Sep 2015 14:30:09 -0700 Subject: ipv6: Replace spinlock with seqlock and rcu in ip6_tunnel This patch uses a seqlock to ensure consistency between idst->dst and idst->cookie. It also makes dst freeing from fib tree to undergo a rcu grace period. Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/ip6_tunnel.h | 4 ++-- net/ipv6/ip6_fib.c | 9 +++++++-- net/ipv6/ip6_tunnel.c | 51 +++++++++++++++++++++++++----------------------- 3 files changed, 36 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 60b4f402f78c..65c2a9397b3c 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -33,8 +33,8 @@ struct __ip6_tnl_parm { }; struct ip6_tnl_dst { - spinlock_t lock; - struct dst_entry *dst; + seqlock_t lock; + struct dst_entry __rcu *dst; u32 cookie; }; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index e68350bf838b..8a9ec01f4d01 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -155,6 +155,11 @@ static void node_free(struct fib6_node *fn) kmem_cache_free(fib6_node_kmem, fn); } +static void rt6_rcu_free(struct rt6_info *rt) +{ + call_rcu(&rt->dst.rcu_head, dst_rcu_free); +} + static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) { int cpu; @@ -169,7 +174,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu); pcpu_rt = *ppcpu_rt; if (pcpu_rt) { - dst_free(&pcpu_rt->dst); + rt6_rcu_free(pcpu_rt); *ppcpu_rt = NULL; } } @@ -181,7 +186,7 @@ static void rt6_release(struct rt6_info *rt) { if (atomic_dec_and_test(&rt->rt6i_ref)) { rt6_free_pcpu(rt); - dst_free(&rt->dst); + rt6_rcu_free(rt); } } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 851cf6d1eb45..983f0d20f96d 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -126,45 +126,48 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) * Locking : hash tables are protected by RCU and RTNL */ -static void __ip6_tnl_per_cpu_dst_set(struct ip6_tnl_dst *idst, - struct dst_entry *dst) +static void ip6_tnl_per_cpu_dst_set(struct ip6_tnl_dst *idst, + struct dst_entry *dst) { - dst_release(idst->dst); + write_seqlock_bh(&idst->lock); + dst_release(rcu_dereference_protected( + idst->dst, + lockdep_is_held(&idst->lock.lock))); if (dst) { dst_hold(dst); idst->cookie = rt6_get_cookie((struct rt6_info *)dst); } else { idst->cookie = 0; } - idst->dst = dst; -} - -static void ip6_tnl_per_cpu_dst_set(struct ip6_tnl_dst *idst, - struct dst_entry *dst) -{ - - spin_lock_bh(&idst->lock); - __ip6_tnl_per_cpu_dst_set(idst, dst); - spin_unlock_bh(&idst->lock); + rcu_assign_pointer(idst->dst, dst); + write_sequnlock_bh(&idst->lock); } struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t) { struct ip6_tnl_dst *idst; struct dst_entry *dst; + unsigned int seq; + u32 cookie; idst = raw_cpu_ptr(t->dst_cache); - spin_lock_bh(&idst->lock); - dst = idst->dst; - if (dst) { - if (!dst->obsolete || dst->ops->check(dst, idst->cookie)) { - dst_hold(idst->dst); - } else { - __ip6_tnl_per_cpu_dst_set(idst, NULL); - dst = NULL; - } + + rcu_read_lock(); + do { + seq = read_seqbegin(&idst->lock); + dst = rcu_dereference(idst->dst); + cookie = idst->cookie; + } while (read_seqretry(&idst->lock, seq)); + + if (dst && !atomic_inc_not_zero(&dst->__refcnt)) + dst = NULL; + rcu_read_unlock(); + + if (dst && dst->obsolete && !dst->ops->check(dst, cookie)) { + ip6_tnl_per_cpu_dst_set(idst, NULL); + dst_release(dst); + dst = NULL; } - spin_unlock_bh(&idst->lock); return dst; } EXPORT_SYMBOL_GPL(ip6_tnl_dst_get); @@ -204,7 +207,7 @@ int ip6_tnl_dst_init(struct ip6_tnl *t) return -ENOMEM; for_each_possible_cpu(i) - spin_lock_init(&per_cpu_ptr(t->dst_cache, i)->lock); + seqlock_init(&per_cpu_ptr(t->dst_cache, i)->lock); return 0; } -- cgit v1.2.3 From 1f0bd44e937468446d080b98b5669844744c24a1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 16 Sep 2015 02:17:49 +0200 Subject: cpufreq: acpi-cpufreq: Use cpufreq_cpu_get_raw() in ->get() cpufreq_cpu_get() called by get_cur_freq_on_cpu() is overkill, because the ->get() callback is always invoked in a context in which all of the conditions checked by cpufreq_cpu_get() are guaranteed to be satisfied. Use cpufreq_cpu_get_raw() instead of it and drop the corresponding cpufreq_cpu_put() from get_cur_freq_on_cpu(). Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- drivers/cpufreq/acpi-cpufreq.c | 3 +-- drivers/cpufreq/cpufreq.c | 4 ++-- include/linux/cpufreq.h | 5 +++++ 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 15b921a9248c..798277227de7 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -375,12 +375,11 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu) pr_debug("get_cur_freq_on_cpu (%d)\n", cpu); - policy = cpufreq_cpu_get(cpu); + policy = cpufreq_cpu_get_raw(cpu); if (unlikely(!policy)) return 0; data = policy->driver_data; - cpufreq_cpu_put(policy); if (unlikely(!data || !data->freq_table)) return 0; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 6633b3fa996e..ef5ed9470de9 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -238,13 +238,13 @@ int cpufreq_generic_init(struct cpufreq_policy *policy, } EXPORT_SYMBOL_GPL(cpufreq_generic_init); -/* Only for cpufreq core internal use */ -static struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu) +struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu) { struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); return policy && cpumask_test_cpu(cpu, policy->cpus) ? policy : NULL; } +EXPORT_SYMBOL_GPL(cpufreq_cpu_get_raw); unsigned int cpufreq_generic_get(unsigned int cpu) { diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 430efcbea48e..dca22de98d94 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -127,9 +127,14 @@ struct cpufreq_policy { #define CPUFREQ_SHARED_TYPE_ANY (3) /* Freq can be set from any dependent CPU*/ #ifdef CONFIG_CPU_FREQ +struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu); struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); void cpufreq_cpu_put(struct cpufreq_policy *policy); #else +static inline struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu) +{ + return NULL; +} static inline struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) { return NULL; -- cgit v1.2.3 From e902e14549e04c040fb6e15785efd35f810a223a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Sep 2015 12:36:04 +0200 Subject: genirq: Remove __irq_set_chip_handler_name_locked() All users converted to irq_set_chip_handler_name_locked() Signed-off-by: Thomas Gleixner --- include/linux/irqdesc.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 0593c691d091..29741382593c 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -184,19 +184,6 @@ static inline void __irq_set_handler_locked(unsigned int irq, desc->handle_irq = handler; } -/* caller has locked the irq_desc and both params are valid */ -static inline void -__irq_set_chip_handler_name_locked(unsigned int irq, struct irq_chip *chip, - irq_flow_handler_t handler, const char *name) -{ - struct irq_desc *desc; - - desc = irq_to_desc(irq); - irq_desc_get_irq_data(desc)->chip = chip; - desc->handle_irq = handler; - desc->name = name; -} - /** * irq_set_handler_locked - Set irq handler from a locked region * @data: Pointer to the irq_data structure which identifies the irq -- cgit v1.2.3 From 123236ccacc933daac3b39c5eb1f0011c70d41d8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Sep 2015 12:54:23 +0200 Subject: genirq: Remove __irq_set_handler_locked() All users converted to irq_set_handler_locked() Signed-off-by: Thomas Gleixner --- include/linux/irqdesc.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 29741382593c..dce395cd67de 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -174,16 +174,6 @@ static inline int irq_has_action(unsigned int irq) return irq_desc_has_action(irq_to_desc(irq)); } -/* caller has locked the irq_desc and both params are valid */ -static inline void __irq_set_handler_locked(unsigned int irq, - irq_flow_handler_t handler) -{ - struct irq_desc *desc; - - desc = irq_to_desc(irq); - desc->handle_irq = handler; -} - /** * irq_set_handler_locked - Set irq handler from a locked region * @data: Pointer to the irq_data structure which identifies the irq -- cgit v1.2.3 From 755d119a6204974b2005a98549a48a75a7f5010b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Sep 2015 14:37:12 +0200 Subject: genirq: Simplify irq_data_to_desc() Avoid the lookup of irq_desc and use the same mechanism for hierarchical and flat irqdomains. Based-on-a-patch-from: Jiang Liu Signed-off-by: Thomas Gleixner --- include/linux/irqdesc.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index dce395cd67de..1fc5304641a1 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -98,11 +98,7 @@ extern struct irq_desc irq_desc[NR_IRQS]; static inline struct irq_desc *irq_data_to_desc(struct irq_data *data) { -#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY - return irq_to_desc(data->irq); -#else - return container_of(data, struct irq_desc, irq_data); -#endif + return container_of(data->common, struct irq_desc, irq_common_data); } static inline unsigned int irq_desc_get_irq(struct irq_desc *desc) -- cgit v1.2.3 From fc5697126aa074c289df5e8baae28e115963023f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 15 Sep 2015 12:33:42 +0200 Subject: genirq: Provide IRQD_FORWARDED_TO_VCPU status flag Provide a irq data flag to mark an irq forwarded to a VCPU along with the accessor functions. Signed-off-by: Thomas Gleixner Acked-by: Marc Zyngier --- include/linux/irq.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 72a6b2feb7bf..e54ae8295460 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -186,6 +186,7 @@ struct irq_data { * IRQD_IRQ_MASKED - Masked state of the interrupt * IRQD_IRQ_INPROGRESS - In progress state of the interrupt * IRQD_WAKEUP_ARMED - Wakeup mode armed + * IRQD_FORWARDED_TO_VCPU - The interrupt is forwarded to a VCPU */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -200,6 +201,7 @@ enum { IRQD_IRQ_MASKED = (1 << 17), IRQD_IRQ_INPROGRESS = (1 << 18), IRQD_WAKEUP_ARMED = (1 << 19), + IRQD_FORWARDED_TO_VCPU = (1 << 20), }; #define __irqd_to_state(d) ((d)->common->state_use_accessors) @@ -278,6 +280,20 @@ static inline bool irqd_is_wakeup_armed(struct irq_data *d) return __irqd_to_state(d) & IRQD_WAKEUP_ARMED; } +static inline bool irqd_is_forwarded_to_vcpu(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_FORWARDED_TO_VCPU; +} + +static inline void irqd_set_forwarded_to_vcpu(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_FORWARDED_TO_VCPU; +} + +static inline void irqd_clr_forwarded_to_vcpu(struct irq_data *d) +{ + __irqd_to_state(d) &= ~IRQD_FORWARDED_TO_VCPU; +} /* * Functions for chained handlers which can be enabled/disabled by the -- cgit v1.2.3 From 449e9cae58b06be1293858ec8e5d8cb728238baa Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 1 Jun 2015 16:05:16 +0800 Subject: genirq: Move field 'node' from irq_data into irq_common_data NUMA node information is per-irq instead of per-irqchip, so move it into struct irq_common_data. Also use CONFIG_NUMA to guard irq_common_data.node. Signed-off-by: Jiang Liu Cc: Konrad Rzeszutek Wilk Cc: Tony Luck Cc: Bjorn Helgaas Cc: Benjamin Herrenschmidt Cc: Randy Dunlap Cc: Yinghai Lu Cc: Borislav Petkov Cc: Jason Cooper Cc: Kevin Cernekee Cc: Arnd Bergmann Link: http://lkml.kernel.org/r/1433145945-789-8-git-send-email-jiang.liu@linux.intel.com Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 17 ++++++++++++++--- kernel/irq/internals.h | 2 +- kernel/irq/irqdesc.c | 4 +++- kernel/irq/irqdomain.c | 1 - 4 files changed, 18 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index e54ae8295460..ebcc5c6745eb 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -129,9 +129,13 @@ struct irq_domain; * struct irq_common_data - per irq data shared by all irqchips * @state_use_accessors: status information for irq chip functions. * Use accessor functions to deal with it + * @node: node index useful for balancing */ struct irq_common_data { unsigned int state_use_accessors; +#ifdef CONFIG_NUMA + unsigned int node; +#endif }; /** @@ -139,7 +143,6 @@ struct irq_common_data { * @mask: precomputed bitmask for accessing the chip registers * @irq: interrupt number * @hwirq: hardware interrupt number, local to the interrupt domain - * @node: node index useful for balancing * @common: point to data shared by all irqchips * @chip: low level interrupt hardware access * @domain: Interrupt translation domain; responsible for mapping @@ -156,7 +159,6 @@ struct irq_data { u32 mask; unsigned int irq; unsigned long hwirq; - unsigned int node; struct irq_common_data *common; struct irq_chip *chip; struct irq_domain *domain; @@ -664,9 +666,18 @@ static inline u32 irq_get_trigger_type(unsigned int irq) return d ? irqd_get_trigger_type(d) : 0; } -static inline int irq_data_get_node(struct irq_data *d) +static inline int irq_common_data_get_node(struct irq_common_data *d) { +#ifdef CONFIG_NUMA return d->node; +#else + return 0; +#endif +} + +static inline int irq_data_get_node(struct irq_data *d) +{ + return irq_common_data_get_node(d->common); } static inline struct cpumask *irq_get_affinity_mask(int irq) diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index eee4b385cffb..5ef0c2dbe930 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -194,7 +194,7 @@ static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc) static inline int irq_desc_get_node(struct irq_desc *desc) { - return irq_data_get_node(&desc->irq_data); + return irq_common_data_get_node(&desc->irq_common_data); } #ifdef CONFIG_PM_SLEEP diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 0a2a4b697bcb..7f3e9faa6e4d 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -52,11 +52,13 @@ static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) static void desc_smp_init(struct irq_desc *desc, int node) { - desc->irq_data.node = node; cpumask_copy(desc->irq_data.affinity, irq_default_affinity); #ifdef CONFIG_GENERIC_PENDING_IRQ cpumask_clear(desc->pending_mask); #endif +#ifdef CONFIG_NUMA + desc->irq_common_data.node = node; +#endif } #else diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 79baaf8a7813..dc9d27c0c158 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -844,7 +844,6 @@ static struct irq_data *irq_domain_insert_irq_data(struct irq_domain *domain, child->parent_data = irq_data; irq_data->irq = child->irq; irq_data->common = child->common; - irq_data->node = child->node; irq_data->domain = domain; } -- cgit v1.2.3 From af7080e040d223b5e7d0a8de28f7cea24ef017c4 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 1 Jun 2015 16:05:21 +0800 Subject: genirq: Move field 'handler_data' from irq_data into irq_common_data Handler data (handler_data) is per-irq instead of per irqchip, so move it into struct irq_common_data. Signed-off-by: Jiang Liu Cc: Konrad Rzeszutek Wilk Cc: Tony Luck Cc: Bjorn Helgaas Cc: Benjamin Herrenschmidt Cc: Randy Dunlap Cc: Yinghai Lu Cc: Borislav Petkov Cc: Jason Cooper Cc: Kevin Cernekee Cc: Arnd Bergmann Cc: Marc Zyngier Link: http://lkml.kernel.org/r/1433145945-789-13-git-send-email-jiang.liu@linux.intel.com Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 8 ++++---- include/linux/irqdesc.h | 2 +- kernel/irq/chip.c | 4 ++-- kernel/irq/irqdesc.c | 3 ++- 4 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index ebcc5c6745eb..516aadbfc072 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -130,12 +130,14 @@ struct irq_domain; * @state_use_accessors: status information for irq chip functions. * Use accessor functions to deal with it * @node: node index useful for balancing + * @handler_data: per-IRQ data for the irq_chip methods */ struct irq_common_data { unsigned int state_use_accessors; #ifdef CONFIG_NUMA unsigned int node; #endif + void *handler_data; }; /** @@ -149,7 +151,6 @@ struct irq_common_data { * between hwirq number and linux irq number. * @parent_data: pointer to parent struct irq_data to support hierarchy * irq_domain - * @handler_data: per-IRQ data for the irq_chip methods * @chip_data: platform-specific per-chip private data for the chip * methods, to allow shared chip implementations * @msi_desc: MSI descriptor @@ -165,7 +166,6 @@ struct irq_data { #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_data *parent_data; #endif - void *handler_data; void *chip_data; struct msi_desc *msi_desc; cpumask_var_t affinity; @@ -641,12 +641,12 @@ static inline void *irq_data_get_irq_chip_data(struct irq_data *d) static inline void *irq_get_handler_data(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); - return d ? d->handler_data : NULL; + return d ? d->common->handler_data : NULL; } static inline void *irq_data_get_irq_handler_data(struct irq_data *d) { - return d->handler_data; + return d->common->handler_data; } static inline struct msi_desc *irq_get_msi_desc(unsigned int irq) diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 1fc5304641a1..c7b3e1cc6d59 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -123,7 +123,7 @@ static inline void *irq_desc_get_chip_data(struct irq_desc *desc) static inline void *irq_desc_get_handler_data(struct irq_desc *desc) { - return desc->irq_data.handler_data; + return desc->irq_common_data.handler_data; } static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 6e40a9539763..a48e00e345d7 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -83,7 +83,7 @@ int irq_set_handler_data(unsigned int irq, void *data) if (!desc) return -EINVAL; - desc->irq_data.handler_data = data; + desc->irq_common_data.handler_data = data; irq_put_desc_unlock(desc, flags); return 0; } @@ -796,7 +796,7 @@ irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle, return; __irq_do_set_handler(desc, handle, 1, NULL); - desc->irq_data.handler_data = data; + desc->irq_common_data.handler_data = data; irq_put_desc_busunlock(desc, flags); } diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 7f3e9faa6e4d..594b3e349aac 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -72,11 +72,12 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, { int cpu; + desc->irq_common_data.handler_data = NULL; + desc->irq_data.common = &desc->irq_common_data; desc->irq_data.irq = irq; desc->irq_data.chip = &no_irq_chip; desc->irq_data.chip_data = NULL; - desc->irq_data.handler_data = NULL; desc->irq_data.msi_desc = NULL; irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS); irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); -- cgit v1.2.3 From 9df872faa7e1619e9278bec00ceaed2236533530 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Wed, 3 Jun 2015 11:47:50 +0800 Subject: genirq: Move field 'affinity' from irq_data into irq_common_data Irq affinity mask is per-irq instead of per irqchip, so move it into struct irq_common_data. Signed-off-by: Jiang Liu Cc: Konrad Rzeszutek Wilk Cc: Tony Luck Cc: Bjorn Helgaas Cc: Benjamin Herrenschmidt Cc: Randy Dunlap Cc: Yinghai Lu Cc: Borislav Petkov Cc: Jason Cooper Cc: Kevin Cernekee Cc: Arnd Bergmann Link: http://lkml.kernel.org/r/1433303281-27688-1-git-send-email-jiang.liu@linux.intel.com Signed-off-by: Thomas Gleixner --- arch/x86/kernel/apic/vector.c | 4 +--- include/linux/irq.h | 12 ++++++------ kernel/irq/irqdesc.c | 9 +++++---- kernel/irq/manage.c | 12 ++++++------ kernel/irq/proc.c | 2 +- 5 files changed, 19 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 1bbd0fe2c806..836d11b92811 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -489,10 +489,8 @@ static int apic_set_affinity(struct irq_data *irq_data, err = assign_irq_vector(irq, data, dest); if (err) { - struct irq_data *top = irq_get_irq_data(irq); - if (assign_irq_vector(irq, data, - irq_data_get_affinity_mask(top))) + irq_data_get_affinity_mask(irq_data))) pr_err("Failed to recover vector for irq %d\n", irq); return err; } diff --git a/include/linux/irq.h b/include/linux/irq.h index 516aadbfc072..75d50544a18f 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -110,8 +110,8 @@ enum { /* * Return value for chip->irq_set_affinity() * - * IRQ_SET_MASK_OK - OK, core updates irq_data.affinity - * IRQ_SET_MASK_NOCPY - OK, chip did update irq_data.affinity + * IRQ_SET_MASK_OK - OK, core updates irq_common_data.affinity + * IRQ_SET_MASK_NOCPY - OK, chip did update irq_common_data.affinity * IRQ_SET_MASK_OK_DONE - Same as IRQ_SET_MASK_OK for core. Special code to * support stacked irqchips, which indicates skipping * all descendent irqchips. @@ -131,6 +131,7 @@ struct irq_domain; * Use accessor functions to deal with it * @node: node index useful for balancing * @handler_data: per-IRQ data for the irq_chip methods + * @affinity: IRQ affinity on SMP */ struct irq_common_data { unsigned int state_use_accessors; @@ -138,6 +139,7 @@ struct irq_common_data { unsigned int node; #endif void *handler_data; + cpumask_var_t affinity; }; /** @@ -154,7 +156,6 @@ struct irq_common_data { * @chip_data: platform-specific per-chip private data for the chip * methods, to allow shared chip implementations * @msi_desc: MSI descriptor - * @affinity: IRQ affinity on SMP */ struct irq_data { u32 mask; @@ -168,7 +169,6 @@ struct irq_data { #endif void *chip_data; struct msi_desc *msi_desc; - cpumask_var_t affinity; }; /* @@ -684,12 +684,12 @@ static inline struct cpumask *irq_get_affinity_mask(int irq) { struct irq_data *d = irq_get_irq_data(irq); - return d ? d->affinity : NULL; + return d ? d->common->affinity : NULL; } static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) { - return d->affinity; + return d->common->affinity; } unsigned int arch_dynirq_lower_bound(unsigned int from); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 594b3e349aac..bb48a5c1964e 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -38,12 +38,13 @@ static void __init init_irq_default_affinity(void) #ifdef CONFIG_SMP static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { - if (!zalloc_cpumask_var_node(&desc->irq_data.affinity, gfp, node)) + if (!zalloc_cpumask_var_node(&desc->irq_common_data.affinity, + gfp, node)) return -ENOMEM; #ifdef CONFIG_GENERIC_PENDING_IRQ if (!zalloc_cpumask_var_node(&desc->pending_mask, gfp, node)) { - free_cpumask_var(desc->irq_data.affinity); + free_cpumask_var(desc->irq_common_data.affinity); return -ENOMEM; } #endif @@ -52,7 +53,7 @@ static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) static void desc_smp_init(struct irq_desc *desc, int node) { - cpumask_copy(desc->irq_data.affinity, irq_default_affinity); + cpumask_copy(desc->irq_common_data.affinity, irq_default_affinity); #ifdef CONFIG_GENERIC_PENDING_IRQ cpumask_clear(desc->pending_mask); #endif @@ -124,7 +125,7 @@ static void free_masks(struct irq_desc *desc) #ifdef CONFIG_GENERIC_PENDING_IRQ free_cpumask_var(desc->pending_mask); #endif - free_cpumask_var(desc->irq_data.affinity); + free_cpumask_var(desc->irq_common_data.affinity); } #else static inline void free_masks(struct irq_desc *desc) { } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index ad1b064f94fe..f9a59f6cabd2 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -192,7 +192,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: - cpumask_copy(data->affinity, mask); + cpumask_copy(desc->irq_common_data.affinity, mask); case IRQ_SET_MASK_OK_NOCOPY: irq_set_thread_affinity(desc); ret = 0; @@ -304,7 +304,7 @@ static void irq_affinity_notify(struct work_struct *work) if (irq_move_pending(&desc->irq_data)) irq_get_pending(cpumask, desc); else - cpumask_copy(cpumask, desc->irq_data.affinity); + cpumask_copy(cpumask, desc->irq_common_data.affinity); raw_spin_unlock_irqrestore(&desc->lock, flags); notify->notify(notify, cpumask); @@ -375,9 +375,9 @@ static int setup_affinity(struct irq_desc *desc, struct cpumask *mask) * one of the targets is online. */ if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) { - if (cpumask_intersects(desc->irq_data.affinity, + if (cpumask_intersects(desc->irq_common_data.affinity, cpu_online_mask)) - set = desc->irq_data.affinity; + set = desc->irq_common_data.affinity; else irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET); } @@ -829,8 +829,8 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) * This code is triggered unconditionally. Check the affinity * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out. */ - if (desc->irq_data.affinity) - cpumask_copy(mask, desc->irq_data.affinity); + if (desc->irq_common_data.affinity) + cpumask_copy(mask, desc->irq_common_data.affinity); else valid = false; raw_spin_unlock_irq(&desc->lock); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 0e97c142ce40..e3a8c9577ba6 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -39,7 +39,7 @@ static struct proc_dir_entry *root_irq_dir; static int show_irq_affinity(int type, struct seq_file *m, void *v) { struct irq_desc *desc = irq_to_desc((long)m->private); - const struct cpumask *mask = desc->irq_data.affinity; + const struct cpumask *mask = desc->irq_common_data.affinity; #ifdef CONFIG_GENERIC_PENDING_IRQ if (irqd_is_setaffinity_pending(&desc->irq_data)) -- cgit v1.2.3 From b237721c5d95082a803c0be686f56d2dd1de995b Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 1 Jun 2015 16:05:43 +0800 Subject: genirq: Move field 'msi_desc' from irq_data into irq_common_data MSI descriptors are per-irq instead of per irqchip, so move it into struct irq_common_data. Signed-off-by: Jiang Liu Cc: Konrad Rzeszutek Wilk Cc: Tony Luck Cc: Bjorn Helgaas Cc: Benjamin Herrenschmidt Cc: Randy Dunlap Cc: Yinghai Lu Cc: Borislav Petkov Cc: Jason Cooper Cc: Kevin Cernekee Cc: Arnd Bergmann Cc: Marc Zyngier Link: http://lkml.kernel.org/r/1433145945-789-35-git-send-email-jiang.liu@linux.intel.com Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 8 ++++---- include/linux/irqdesc.h | 2 +- kernel/irq/chip.c | 2 +- kernel/irq/irqdesc.c | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 75d50544a18f..4913c32db942 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -132,6 +132,7 @@ struct irq_domain; * @node: node index useful for balancing * @handler_data: per-IRQ data for the irq_chip methods * @affinity: IRQ affinity on SMP + * @msi_desc: MSI descriptor */ struct irq_common_data { unsigned int state_use_accessors; @@ -139,6 +140,7 @@ struct irq_common_data { unsigned int node; #endif void *handler_data; + struct msi_desc *msi_desc; cpumask_var_t affinity; }; @@ -155,7 +157,6 @@ struct irq_common_data { * irq_domain * @chip_data: platform-specific per-chip private data for the chip * methods, to allow shared chip implementations - * @msi_desc: MSI descriptor */ struct irq_data { u32 mask; @@ -168,7 +169,6 @@ struct irq_data { struct irq_data *parent_data; #endif void *chip_data; - struct msi_desc *msi_desc; }; /* @@ -652,12 +652,12 @@ static inline void *irq_data_get_irq_handler_data(struct irq_data *d) static inline struct msi_desc *irq_get_msi_desc(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); - return d ? d->msi_desc : NULL; + return d ? d->common->msi_desc : NULL; } static inline struct msi_desc *irq_data_get_msi_desc(struct irq_data *d) { - return d->msi_desc; + return d->common->msi_desc; } static inline u32 irq_get_trigger_type(unsigned int irq) diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index c7b3e1cc6d59..fbb4d5afc32b 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -128,7 +128,7 @@ static inline void *irq_desc_get_handler_data(struct irq_desc *desc) static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) { - return desc->irq_data.msi_desc; + return desc->irq_common_data.msi_desc; } /* diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index a48e00e345d7..8c55d545558f 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -105,7 +105,7 @@ int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset, if (!desc) return -EINVAL; - desc->irq_data.msi_desc = entry; + desc->irq_common_data.msi_desc = entry; if (entry && !irq_offset) entry->irq = irq_base; irq_put_desc_unlock(desc, flags); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index bb48a5c1964e..596669436f7a 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -74,12 +74,12 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, int cpu; desc->irq_common_data.handler_data = NULL; + desc->irq_common_data.msi_desc = NULL; desc->irq_data.common = &desc->irq_common_data; desc->irq_data.irq = irq; desc->irq_data.chip = &no_irq_chip; desc->irq_data.chip_data = NULL; - desc->irq_data.msi_desc = NULL; irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS); irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); desc->handle_irq = handle_bad_irq; -- cgit v1.2.3 From bd0b9ac405e1794d72533c3d487aa65b6b955a0c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 14 Sep 2015 10:42:37 +0200 Subject: genirq: Remove irq argument from irq flow handlers Most interrupt flow handlers do not use the irq argument. Those few which use it can retrieve the irq number from the irq descriptor. Remove the argument. Search and replace was done with coccinelle and some extra helper scripts around it. Thanks to Julia for her help! Signed-off-by: Thomas Gleixner Cc: Julia Lawall Cc: Jiang Liu --- arch/alpha/kernel/irq.c | 2 +- arch/arc/kernel/mcip.c | 2 +- arch/arm/common/it8152.c | 2 +- arch/arm/common/locomo.c | 2 +- arch/arm/common/sa1111.c | 6 ++---- arch/arm/include/asm/hardware/it8152.h | 2 +- arch/arm/include/asm/mach/irq.h | 4 ++-- arch/arm/mach-dove/irq.c | 6 +++--- arch/arm/mach-footbridge/isa-irq.c | 5 ++--- arch/arm/mach-gemini/gpio.c | 2 +- arch/arm/mach-imx/3ds_debugboard.c | 2 +- arch/arm/mach-imx/mach-mx31ads.c | 2 +- arch/arm/mach-iop13xx/msi.c | 2 +- arch/arm/mach-lpc32xx/irq.c | 4 ++-- arch/arm/mach-netx/generic.c | 3 +-- arch/arm/mach-omap1/fpga.c | 2 +- arch/arm/mach-omap2/prm_common.c | 2 +- arch/arm/mach-pxa/balloon3.c | 2 +- arch/arm/mach-pxa/cm-x2xx-pci.c | 5 ++--- arch/arm/mach-pxa/lpd270.c | 2 +- arch/arm/mach-pxa/pcm990-baseboard.c | 2 +- arch/arm/mach-pxa/viper.c | 2 +- arch/arm/mach-pxa/zeus.c | 2 +- arch/arm/mach-rpc/ecard.c | 3 +-- arch/arm/mach-s3c24xx/bast-irq.c | 4 +--- arch/arm/mach-s3c64xx/common.c | 8 ++++---- arch/arm/mach-sa1100/neponset.c | 2 +- arch/arm/plat-orion/gpio.c | 2 +- arch/avr32/mach-at32ap/extint.c | 2 +- arch/avr32/mach-at32ap/pio.c | 2 +- arch/blackfin/include/asm/irq_handler.h | 4 ++-- arch/blackfin/kernel/irqchip.c | 2 +- arch/blackfin/mach-bf537/ints-priority.c | 10 +++------ arch/blackfin/mach-common/ints-priority.c | 5 ++--- arch/c6x/platforms/megamod-pic.c | 2 +- arch/m68k/amiga/amiints.c | 8 ++++---- arch/m68k/coldfire/intc-5272.c | 6 ++---- arch/m68k/include/asm/irq.h | 3 +-- arch/m68k/include/asm/mac_via.h | 2 +- arch/m68k/mac/baboon.c | 2 +- arch/m68k/mac/oss.c | 4 ++-- arch/m68k/mac/psc.c | 2 +- arch/m68k/mac/via.c | 6 +++--- arch/metag/kernel/irq.c | 4 +--- arch/mips/alchemy/common/irq.c | 4 ++-- arch/mips/alchemy/devboards/bcsr.c | 2 +- arch/mips/ath25/ar2315.c | 2 +- arch/mips/ath25/ar5312.c | 2 +- arch/mips/ath79/irq.c | 8 ++++---- arch/mips/cavium-octeon/octeon-irq.c | 2 +- arch/mips/include/asm/netlogic/common.h | 4 ++-- arch/mips/jz4740/gpio.c | 2 +- arch/mips/netlogic/common/smp.c | 4 ++-- arch/mips/pci/pci-ar2315.c | 2 +- arch/mips/pci/pci-ar71xx.c | 2 +- arch/mips/pci/pci-ar724x.c | 2 +- arch/mips/pci/pci-rt3883.c | 2 +- arch/mips/ralink/irq.c | 2 +- arch/powerpc/include/asm/qe_ic.h | 23 +++++++++------------ arch/powerpc/include/asm/tsi108_pci.h | 2 +- arch/powerpc/platforms/512x/mpc5121_ads_cpld.c | 3 +-- arch/powerpc/platforms/52xx/media5200.c | 2 +- arch/powerpc/platforms/52xx/mpc52xx_gpt.c | 2 +- arch/powerpc/platforms/82xx/pq2ads-pci-pic.c | 2 +- arch/powerpc/platforms/85xx/common.c | 2 +- arch/powerpc/platforms/85xx/mpc85xx_cds.c | 6 ++---- arch/powerpc/platforms/85xx/mpc85xx_ds.c | 2 +- arch/powerpc/platforms/85xx/socrates_fpga_pic.c | 2 +- arch/powerpc/platforms/86xx/pic.c | 2 +- arch/powerpc/platforms/8xx/m8xx_setup.c | 2 +- arch/powerpc/platforms/cell/axon_msi.c | 2 +- arch/powerpc/platforms/cell/interrupt.c | 2 +- arch/powerpc/platforms/cell/spider-pic.c | 2 +- arch/powerpc/platforms/chrp/setup.c | 2 +- arch/powerpc/platforms/embedded6xx/hlwd-pic.c | 3 +-- arch/powerpc/platforms/embedded6xx/mvme5100.c | 2 +- arch/powerpc/platforms/pseries/setup.c | 2 +- arch/powerpc/sysdev/ge/ge_pic.c | 2 +- arch/powerpc/sysdev/ge/ge_pic.h | 2 -- arch/powerpc/sysdev/mpic.c | 2 +- arch/powerpc/sysdev/qe_lib/qe_ic.c | 4 ++-- arch/powerpc/sysdev/tsi108_pci.c | 2 +- arch/powerpc/sysdev/uic.c | 2 +- arch/powerpc/sysdev/xilinx_intc.c | 2 +- arch/sh/boards/mach-se/7343/irq.c | 2 +- arch/sh/boards/mach-se/7722/irq.c | 2 +- arch/sh/boards/mach-se/7724/irq.c | 2 +- arch/sh/boards/mach-x3proto/gpio.c | 2 +- arch/sh/cchips/hd6446x/hd64461.c | 2 +- arch/sparc/kernel/leon_kernel.c | 2 +- arch/sparc/kernel/leon_pci_grpci1.c | 2 +- arch/sparc/kernel/leon_pci_grpci2.c | 2 +- arch/tile/kernel/pci_gx.c | 5 ++--- arch/unicore32/kernel/irq.c | 2 +- arch/x86/kernel/irq_32.c | 19 +++++++---------- arch/x86/kernel/irq_64.c | 2 +- arch/x86/lguest/boot.c | 2 +- drivers/dma/ipu/ipu_irq.c | 2 +- drivers/gpio/gpio-altera.c | 6 ++---- drivers/gpio/gpio-bcm-kona.c | 2 +- drivers/gpio/gpio-brcmstb.c | 2 +- drivers/gpio/gpio-davinci.c | 3 +-- drivers/gpio/gpio-dwapb.c | 2 +- drivers/gpio/gpio-ep93xx.c | 5 ++--- drivers/gpio/gpio-intel-mid.c | 2 +- drivers/gpio/gpio-lynxpoint.c | 2 +- drivers/gpio/gpio-mpc8xxx.c | 2 +- drivers/gpio/gpio-msic.c | 2 +- drivers/gpio/gpio-msm-v2.c | 2 +- drivers/gpio/gpio-mvebu.c | 2 +- drivers/gpio/gpio-mxc.c | 4 ++-- drivers/gpio/gpio-mxs.c | 2 +- drivers/gpio/gpio-omap.c | 2 +- drivers/gpio/gpio-pl061.c | 2 +- drivers/gpio/gpio-pxa.c | 2 +- drivers/gpio/gpio-sa1100.c | 3 +-- drivers/gpio/gpio-tegra.c | 2 +- drivers/gpio/gpio-timberdale.c | 2 +- drivers/gpio/gpio-tz1090.c | 4 ++-- drivers/gpio/gpio-vf610.c | 2 +- drivers/gpio/gpio-zx.c | 2 +- drivers/gpio/gpio-zynq.c | 2 +- drivers/gpu/ipu-v3/ipu-common.c | 4 ++-- drivers/irqchip/exynos-combiner.c | 6 ++---- drivers/irqchip/irq-armada-370-xp.c | 3 +-- drivers/irqchip/irq-bcm2835.c | 4 ++-- drivers/irqchip/irq-bcm7038-l1.c | 2 +- drivers/irqchip/irq-bcm7120-l2.c | 2 +- drivers/irqchip/irq-brcmstb-l2.c | 7 +++---- drivers/irqchip/irq-dw-apb-ictl.c | 2 +- drivers/irqchip/irq-gic.c | 4 ++-- drivers/irqchip/irq-i8259.c | 2 +- drivers/irqchip/irq-imgpdc.c | 4 ++-- drivers/irqchip/irq-keystone.c | 2 +- drivers/irqchip/irq-metag-ext.c | 2 +- drivers/irqchip/irq-metag.c | 2 +- drivers/irqchip/irq-mips-gic.c | 2 +- drivers/irqchip/irq-mmp.c | 2 +- drivers/irqchip/irq-orion.c | 2 +- drivers/irqchip/irq-s3c24xx.c | 2 +- drivers/irqchip/irq-sunxi-nmi.c | 2 +- drivers/irqchip/irq-tb10x.c | 2 +- drivers/irqchip/irq-versatile-fpga.c | 8 ++++---- drivers/irqchip/irq-vic.c | 2 +- drivers/irqchip/spear-shirq.c | 2 +- drivers/mfd/asic3.c | 2 +- drivers/mfd/ezx-pcap.c | 2 +- drivers/mfd/htc-egpio.c | 2 +- drivers/mfd/jz4740-adc.c | 2 +- drivers/mfd/pm8921-core.c | 2 +- drivers/mfd/t7l66xb.c | 2 +- drivers/mfd/tc6393xb.c | 3 +-- drivers/mfd/ucb1x00-core.c | 2 +- drivers/pci/host/pci-keystone.c | 5 ++--- drivers/pci/host/pci-xgene-msi.c | 2 +- drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c | 2 +- drivers/pinctrl/intel/pinctrl-baytrail.c | 2 +- drivers/pinctrl/intel/pinctrl-cherryview.c | 2 +- drivers/pinctrl/intel/pinctrl-intel.c | 2 +- drivers/pinctrl/mediatek/pinctrl-mtk-common.c | 2 +- drivers/pinctrl/nomadik/pinctrl-nomadik.c | 4 ++-- drivers/pinctrl/pinctrl-adi2.c | 3 +-- drivers/pinctrl/pinctrl-amd.c | 6 +++--- drivers/pinctrl/pinctrl-at91.c | 2 +- drivers/pinctrl/pinctrl-coh901.c | 2 +- drivers/pinctrl/pinctrl-pistachio.c | 6 ++---- drivers/pinctrl/pinctrl-rockchip.c | 2 +- drivers/pinctrl/pinctrl-single.c | 2 +- drivers/pinctrl/pinctrl-st.c | 4 ++-- drivers/pinctrl/qcom/pinctrl-msm.c | 5 ++--- drivers/pinctrl/samsung/pinctrl-exynos.c | 4 ++-- drivers/pinctrl/samsung/pinctrl-s3c24xx.c | 8 ++++---- drivers/pinctrl/samsung/pinctrl-s3c64xx.c | 10 ++++----- drivers/pinctrl/sirf/pinctrl-atlas7.c | 4 ++-- drivers/pinctrl/sirf/pinctrl-sirf.c | 4 ++-- drivers/pinctrl/spear/pinctrl-plgpio.c | 2 +- drivers/pinctrl/sunxi/pinctrl-sunxi.c | 2 +- drivers/sh/intc/core.c | 2 +- drivers/sh/intc/virq.c | 4 ++-- drivers/soc/dove/pmu.c | 4 ++-- drivers/spmi/spmi-pmic-arb.c | 2 +- include/linux/irq.h | 16 +++++++-------- include/linux/irqdesc.h | 4 ++-- include/linux/irqhandler.h | 2 +- kernel/irq/chip.c | 27 ++++++++----------------- kernel/irq/handle.c | 4 +++- kernel/irq/irqdesc.c | 2 +- kernel/irq/resend.c | 2 +- 188 files changed, 281 insertions(+), 340 deletions(-) (limited to 'include') diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c index 2804648c8ff4..2d6efcff3bf3 100644 --- a/arch/alpha/kernel/irq.c +++ b/arch/alpha/kernel/irq.c @@ -117,6 +117,6 @@ handle_irq(int irq) } irq_enter(); - generic_handle_irq_desc(irq, desc); + generic_handle_irq_desc(desc); irq_exit(); } diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index d9e44b62df05..4ffd1855f1bd 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -252,7 +252,7 @@ static struct irq_chip idu_irq_chip = { static int idu_first_irq; -static void idu_cascade_isr(unsigned int __core_irq, struct irq_desc *desc) +static void idu_cascade_isr(struct irq_desc *desc) { struct irq_domain *domain = irq_desc_get_handler_data(desc); unsigned int core_irq = irq_desc_get_irq(desc); diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c index 96dabcb6c621..996aed3b4eee 100644 --- a/arch/arm/common/it8152.c +++ b/arch/arm/common/it8152.c @@ -95,7 +95,7 @@ void it8152_init_irq(void) } } -void it8152_irq_demux(unsigned int irq, struct irq_desc *desc) +void it8152_irq_demux(struct irq_desc *desc) { int bits_pd, bits_lp, bits_ld; int i; diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c index 304adea4bc52..0e97b4b871f9 100644 --- a/arch/arm/common/locomo.c +++ b/arch/arm/common/locomo.c @@ -138,7 +138,7 @@ static struct locomo_dev_info locomo_devices[] = { }, }; -static void locomo_handler(unsigned int __irq, struct irq_desc *desc) +static void locomo_handler(struct irq_desc *desc) { struct locomo *lchip = irq_desc_get_chip_data(desc); int req, i; diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c index 4f290250fa93..3d224941b541 100644 --- a/arch/arm/common/sa1111.c +++ b/arch/arm/common/sa1111.c @@ -196,10 +196,8 @@ static struct sa1111_dev_info sa1111_devices[] = { * active IRQs causes the interrupt output to pulse, the upper levels * will call us again if there are more interrupts to process. */ -static void -sa1111_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void sa1111_irq_handler(struct irq_desc *desc) { - unsigned int irq = irq_desc_get_irq(desc); unsigned int stat0, stat1, i; struct sa1111 *sachip = irq_desc_get_handler_data(desc); void __iomem *mapbase = sachip->base + SA1111_INTC; @@ -214,7 +212,7 @@ sa1111_irq_handler(unsigned int __irq, struct irq_desc *desc) sa1111_writel(stat1, mapbase + SA1111_INTSTATCLR1); if (stat0 == 0 && stat1 == 0) { - do_bad_IRQ(irq, desc); + do_bad_IRQ(desc); return; } diff --git a/arch/arm/include/asm/hardware/it8152.h b/arch/arm/include/asm/hardware/it8152.h index d36a73d7c0e8..076777ff3daa 100644 --- a/arch/arm/include/asm/hardware/it8152.h +++ b/arch/arm/include/asm/hardware/it8152.h @@ -106,7 +106,7 @@ extern void __iomem *it8152_base_address; struct pci_dev; struct pci_sys_data; -extern void it8152_irq_demux(unsigned int irq, struct irq_desc *desc); +extern void it8152_irq_demux(struct irq_desc *desc); extern void it8152_init_irq(void); extern int it8152_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin); extern int it8152_pci_setup(int nr, struct pci_sys_data *sys); diff --git a/arch/arm/include/asm/mach/irq.h b/arch/arm/include/asm/mach/irq.h index 2092ee1e1300..de4634b51456 100644 --- a/arch/arm/include/asm/mach/irq.h +++ b/arch/arm/include/asm/mach/irq.h @@ -23,10 +23,10 @@ extern int show_fiq_list(struct seq_file *, int); /* * This is for easy migration, but should be changed in the source */ -#define do_bad_IRQ(irq,desc) \ +#define do_bad_IRQ(desc) \ do { \ raw_spin_lock(&desc->lock); \ - handle_bad_irq(irq, desc); \ + handle_bad_irq(desc); \ raw_spin_unlock(&desc->lock); \ } while(0) diff --git a/arch/arm/mach-dove/irq.c b/arch/arm/mach-dove/irq.c index 305d7c6242bb..bfb3703357c5 100644 --- a/arch/arm/mach-dove/irq.c +++ b/arch/arm/mach-dove/irq.c @@ -69,14 +69,14 @@ static struct irq_chip pmu_irq_chip = { .irq_ack = pmu_irq_ack, }; -static void pmu_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void pmu_irq_handler(struct irq_desc *desc) { - unsigned int irq = irq_desc_get_irq(desc); unsigned long cause = readl(PMU_INTERRUPT_CAUSE); + unsigned int irq; cause &= readl(PMU_INTERRUPT_MASK); if (cause == 0) { - do_bad_IRQ(irq, desc); + do_bad_IRQ(desc); return; } diff --git a/arch/arm/mach-footbridge/isa-irq.c b/arch/arm/mach-footbridge/isa-irq.c index fcd79bc3a3e1..c01fca11b224 100644 --- a/arch/arm/mach-footbridge/isa-irq.c +++ b/arch/arm/mach-footbridge/isa-irq.c @@ -87,13 +87,12 @@ static struct irq_chip isa_hi_chip = { .irq_unmask = isa_unmask_pic_hi_irq, }; -static void -isa_irq_handler(unsigned int irq, struct irq_desc *desc) +static void isa_irq_handler(struct irq_desc *desc) { unsigned int isa_irq = *(unsigned char *)PCIIACK_BASE; if (isa_irq < _ISA_IRQ(0) || isa_irq >= _ISA_IRQ(16)) { - do_bad_IRQ(isa_irq, desc); + do_bad_IRQ(desc); return; } diff --git a/arch/arm/mach-gemini/gpio.c b/arch/arm/mach-gemini/gpio.c index 220333ed741d..2478d9f4d92d 100644 --- a/arch/arm/mach-gemini/gpio.c +++ b/arch/arm/mach-gemini/gpio.c @@ -126,7 +126,7 @@ static int gpio_set_irq_type(struct irq_data *d, unsigned int type) return 0; } -static void gpio_irq_handler(unsigned int irq, struct irq_desc *desc) +static void gpio_irq_handler(struct irq_desc *desc) { unsigned int port = (unsigned int)irq_desc_get_handler_data(desc); unsigned int gpio_irq_no, irq_stat; diff --git a/arch/arm/mach-imx/3ds_debugboard.c b/arch/arm/mach-imx/3ds_debugboard.c index 45903be6e7b3..16496a071ecb 100644 --- a/arch/arm/mach-imx/3ds_debugboard.c +++ b/arch/arm/mach-imx/3ds_debugboard.c @@ -85,7 +85,7 @@ static struct platform_device smsc_lan9217_device = { .resource = smsc911x_resources, }; -static void mxc_expio_irq_handler(u32 irq, struct irq_desc *desc) +static void mxc_expio_irq_handler(struct irq_desc *desc) { u32 imr_val; u32 int_valid; diff --git a/arch/arm/mach-imx/mach-mx31ads.c b/arch/arm/mach-imx/mach-mx31ads.c index 2c0853560bd2..2b147e4bf9c9 100644 --- a/arch/arm/mach-imx/mach-mx31ads.c +++ b/arch/arm/mach-imx/mach-mx31ads.c @@ -154,7 +154,7 @@ static inline void mxc_init_imx_uart(void) imx31_add_imx_uart0(&uart_pdata); } -static void mx31ads_expio_irq_handler(u32 irq, struct irq_desc *desc) +static void mx31ads_expio_irq_handler(struct irq_desc *desc) { u32 imr_val; u32 int_valid; diff --git a/arch/arm/mach-iop13xx/msi.c b/arch/arm/mach-iop13xx/msi.c index 9f89e76dfbb9..f6235b28578c 100644 --- a/arch/arm/mach-iop13xx/msi.c +++ b/arch/arm/mach-iop13xx/msi.c @@ -91,7 +91,7 @@ static void (*write_imipr[])(u32) = { write_imipr_3, }; -static void iop13xx_msi_handler(unsigned int irq, struct irq_desc *desc) +static void iop13xx_msi_handler(struct irq_desc *desc) { int i, j; unsigned long status; diff --git a/arch/arm/mach-lpc32xx/irq.c b/arch/arm/mach-lpc32xx/irq.c index cce4cef12b6e..2ae431e8bc1b 100644 --- a/arch/arm/mach-lpc32xx/irq.c +++ b/arch/arm/mach-lpc32xx/irq.c @@ -370,7 +370,7 @@ static struct irq_chip lpc32xx_irq_chip = { .irq_set_wake = lpc32xx_irq_wake }; -static void lpc32xx_sic1_handler(unsigned int irq, struct irq_desc *desc) +static void lpc32xx_sic1_handler(struct irq_desc *desc) { unsigned long ints = __raw_readl(LPC32XX_INTC_STAT(LPC32XX_SIC1_BASE)); @@ -383,7 +383,7 @@ static void lpc32xx_sic1_handler(unsigned int irq, struct irq_desc *desc) } } -static void lpc32xx_sic2_handler(unsigned int irq, struct irq_desc *desc) +static void lpc32xx_sic2_handler(struct irq_desc *desc) { unsigned long ints = __raw_readl(LPC32XX_INTC_STAT(LPC32XX_SIC2_BASE)); diff --git a/arch/arm/mach-netx/generic.c b/arch/arm/mach-netx/generic.c index 6373e2bff203..842302df99c1 100644 --- a/arch/arm/mach-netx/generic.c +++ b/arch/arm/mach-netx/generic.c @@ -69,8 +69,7 @@ static struct platform_device *devices[] __initdata = { #define DEBUG_IRQ(fmt...) while (0) {} #endif -static void -netx_hif_demux_handler(unsigned int irq_unused, struct irq_desc *desc) +static void netx_hif_demux_handler(struct irq_desc *desc) { unsigned int irq = NETX_IRQ_HIF_CHAINED(0); unsigned int stat; diff --git a/arch/arm/mach-omap1/fpga.c b/arch/arm/mach-omap1/fpga.c index dfec671b1639..39e20d0ead08 100644 --- a/arch/arm/mach-omap1/fpga.c +++ b/arch/arm/mach-omap1/fpga.c @@ -87,7 +87,7 @@ static void fpga_mask_ack_irq(struct irq_data *d) fpga_ack_irq(d); } -static void innovator_fpga_IRQ_demux(unsigned int irq, struct irq_desc *desc) +static void innovator_fpga_IRQ_demux(struct irq_desc *desc) { u32 stat; int fpga_irq; diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c index 257e98c26618..3fc2cbe52113 100644 --- a/arch/arm/mach-omap2/prm_common.c +++ b/arch/arm/mach-omap2/prm_common.c @@ -102,7 +102,7 @@ static void omap_prcm_events_filter_priority(unsigned long *events, * dispatched accordingly. Clearing of the wakeup events should be * done by the SoC specific individual handlers. */ -static void omap_prcm_irq_handler(unsigned int irq, struct irq_desc *desc) +static void omap_prcm_irq_handler(struct irq_desc *desc) { unsigned long pending[OMAP_PRCM_MAX_NR_PENDING_REG]; unsigned long priority_pending[OMAP_PRCM_MAX_NR_PENDING_REG]; diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c index 70366b35d299..a3ebb517cca1 100644 --- a/arch/arm/mach-pxa/balloon3.c +++ b/arch/arm/mach-pxa/balloon3.c @@ -496,7 +496,7 @@ static struct irq_chip balloon3_irq_chip = { .irq_unmask = balloon3_unmask_irq, }; -static void balloon3_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void balloon3_irq_handler(struct irq_desc *desc) { unsigned long pending = __raw_readl(BALLOON3_INT_CONTROL_REG) & balloon3_irq_enabled; diff --git a/arch/arm/mach-pxa/cm-x2xx-pci.c b/arch/arm/mach-pxa/cm-x2xx-pci.c index 1fa79f1f832d..3221ae15bef7 100644 --- a/arch/arm/mach-pxa/cm-x2xx-pci.c +++ b/arch/arm/mach-pxa/cm-x2xx-pci.c @@ -29,13 +29,12 @@ void __iomem *it8152_base_address; static int cmx2xx_it8152_irq_gpio; -static void cmx2xx_it8152_irq_demux(unsigned int __irq, struct irq_desc *desc) +static void cmx2xx_it8152_irq_demux(struct irq_desc *desc) { - unsigned int irq = irq_desc_get_irq(desc); /* clear our parent irq */ desc->irq_data.chip->irq_ack(&desc->irq_data); - it8152_irq_demux(irq, desc); + it8152_irq_demux(desc); } void __cmx2xx_pci_init_irq(int irq_gpio) diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c index b070167deef2..4823d972e647 100644 --- a/arch/arm/mach-pxa/lpd270.c +++ b/arch/arm/mach-pxa/lpd270.c @@ -120,7 +120,7 @@ static struct irq_chip lpd270_irq_chip = { .irq_unmask = lpd270_unmask_irq, }; -static void lpd270_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void lpd270_irq_handler(struct irq_desc *desc) { unsigned int irq; unsigned long pending; diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c index 9a0c8affdadb..d8319b54299a 100644 --- a/arch/arm/mach-pxa/pcm990-baseboard.c +++ b/arch/arm/mach-pxa/pcm990-baseboard.c @@ -284,7 +284,7 @@ static struct irq_chip pcm990_irq_chip = { .irq_unmask = pcm990_unmask_irq, }; -static void pcm990_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void pcm990_irq_handler(struct irq_desc *desc) { unsigned int irq; unsigned long pending; diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c index 4841d6cefe76..8ab26370107e 100644 --- a/arch/arm/mach-pxa/viper.c +++ b/arch/arm/mach-pxa/viper.c @@ -276,7 +276,7 @@ static inline unsigned long viper_irq_pending(void) viper_irq_enabled_mask; } -static void viper_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void viper_irq_handler(struct irq_desc *desc) { unsigned int irq; unsigned long pending; diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c index 6f94dd7b4dee..30e62a3f0701 100644 --- a/arch/arm/mach-pxa/zeus.c +++ b/arch/arm/mach-pxa/zeus.c @@ -105,7 +105,7 @@ static inline unsigned long zeus_irq_pending(void) return __raw_readw(ZEUS_CPLD_ISA_IRQ) & zeus_irq_enabled_mask; } -static void zeus_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void zeus_irq_handler(struct irq_desc *desc) { unsigned int irq; unsigned long pending; diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c index f726d4c4e6dd..dc67a7fb3831 100644 --- a/arch/arm/mach-rpc/ecard.c +++ b/arch/arm/mach-rpc/ecard.c @@ -551,8 +551,7 @@ static void ecard_check_lockup(struct irq_desc *desc) } } -static void -ecard_irq_handler(unsigned int irq, struct irq_desc *desc) +static void ecard_irq_handler(struct irq_desc *desc) { ecard_t *ec; int called = 0; diff --git a/arch/arm/mach-s3c24xx/bast-irq.c b/arch/arm/mach-s3c24xx/bast-irq.c index ced1ab86ac83..2bb08961e934 100644 --- a/arch/arm/mach-s3c24xx/bast-irq.c +++ b/arch/arm/mach-s3c24xx/bast-irq.c @@ -100,9 +100,7 @@ static struct irq_chip bast_pc104_chip = { .irq_ack = bast_pc104_maskack }; -static void -bast_irq_pc104_demux(unsigned int irq, - struct irq_desc *desc) +static void bast_irq_pc104_demux(struct irq_desc *desc) { unsigned int stat; unsigned int irqno; diff --git a/arch/arm/mach-s3c64xx/common.c b/arch/arm/mach-s3c64xx/common.c index fd63ecfb2f81..ddb30b8434c5 100644 --- a/arch/arm/mach-s3c64xx/common.c +++ b/arch/arm/mach-s3c64xx/common.c @@ -388,22 +388,22 @@ static inline void s3c_irq_demux_eint(unsigned int start, unsigned int end) } } -static void s3c_irq_demux_eint0_3(unsigned int irq, struct irq_desc *desc) +static void s3c_irq_demux_eint0_3(struct irq_desc *desc) { s3c_irq_demux_eint(0, 3); } -static void s3c_irq_demux_eint4_11(unsigned int irq, struct irq_desc *desc) +static void s3c_irq_demux_eint4_11(struct irq_desc *desc) { s3c_irq_demux_eint(4, 11); } -static void s3c_irq_demux_eint12_19(unsigned int irq, struct irq_desc *desc) +static void s3c_irq_demux_eint12_19(struct irq_desc *desc) { s3c_irq_demux_eint(12, 19); } -static void s3c_irq_demux_eint20_27(unsigned int irq, struct irq_desc *desc) +static void s3c_irq_demux_eint20_27(struct irq_desc *desc) { s3c_irq_demux_eint(20, 27); } diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c index 6d237b4f7a8e..8411985af9ff 100644 --- a/arch/arm/mach-sa1100/neponset.c +++ b/arch/arm/mach-sa1100/neponset.c @@ -166,7 +166,7 @@ static struct sa1100_port_fns neponset_port_fns = { * ensure that the IRQ signal is deasserted before returning. This * is rather unfortunate. */ -static void neponset_irq_handler(unsigned int irq, struct irq_desc *desc) +static void neponset_irq_handler(struct irq_desc *desc) { struct neponset_drvdata *d = irq_desc_get_handler_data(desc); unsigned int irr; diff --git a/arch/arm/plat-orion/gpio.c b/arch/arm/plat-orion/gpio.c index 79c33eca09a3..7bd22d8e5b11 100644 --- a/arch/arm/plat-orion/gpio.c +++ b/arch/arm/plat-orion/gpio.c @@ -407,7 +407,7 @@ static int gpio_irq_set_type(struct irq_data *d, u32 type) return 0; } -static void gpio_irq_handler(unsigned __irq, struct irq_desc *desc) +static void gpio_irq_handler(struct irq_desc *desc) { struct orion_gpio_chip *ochip = irq_desc_get_handler_data(desc); u32 cause, type; diff --git a/arch/avr32/mach-at32ap/extint.c b/arch/avr32/mach-at32ap/extint.c index d51ff8f1c541..96cabad68489 100644 --- a/arch/avr32/mach-at32ap/extint.c +++ b/arch/avr32/mach-at32ap/extint.c @@ -144,7 +144,7 @@ static struct irq_chip eic_chip = { .irq_set_type = eic_set_irq_type, }; -static void demux_eic_irq(unsigned int irq, struct irq_desc *desc) +static void demux_eic_irq(struct irq_desc *desc) { struct eic *eic = irq_desc_get_handler_data(desc); unsigned long status, pending; diff --git a/arch/avr32/mach-at32ap/pio.c b/arch/avr32/mach-at32ap/pio.c index 157a5e0e789f..4f61378c3453 100644 --- a/arch/avr32/mach-at32ap/pio.c +++ b/arch/avr32/mach-at32ap/pio.c @@ -281,7 +281,7 @@ static struct irq_chip gpio_irqchip = { .irq_set_type = gpio_irq_type, }; -static void gpio_irq_handler(unsigned irq, struct irq_desc *desc) +static void gpio_irq_handler(struct irq_desc *desc) { struct pio_device *pio = irq_desc_get_chip_data(desc); unsigned gpio_irq; diff --git a/arch/blackfin/include/asm/irq_handler.h b/arch/blackfin/include/asm/irq_handler.h index 4b2a992794d7..d2f90c72378e 100644 --- a/arch/blackfin/include/asm/irq_handler.h +++ b/arch/blackfin/include/asm/irq_handler.h @@ -60,7 +60,7 @@ extern void bfin_internal_mask_irq(unsigned int irq); extern void bfin_internal_unmask_irq(unsigned int irq); struct irq_desc; -extern void bfin_demux_mac_status_irq(unsigned int, struct irq_desc *); -extern void bfin_demux_gpio_irq(unsigned int, struct irq_desc *); +extern void bfin_demux_mac_status_irq(struct irq_desc *); +extern void bfin_demux_gpio_irq(struct irq_desc *); #endif diff --git a/arch/blackfin/kernel/irqchip.c b/arch/blackfin/kernel/irqchip.c index 0ba25764b8c0..052cde5ed2e4 100644 --- a/arch/blackfin/kernel/irqchip.c +++ b/arch/blackfin/kernel/irqchip.c @@ -107,7 +107,7 @@ asmlinkage void asm_do_IRQ(unsigned int irq, struct pt_regs *regs) * than crashing, do something sensible. */ if (irq >= NR_IRQS) - handle_bad_irq(irq, &bad_irq_desc); + handle_bad_irq(&bad_irq_desc); else generic_handle_irq(irq); diff --git a/arch/blackfin/mach-bf537/ints-priority.c b/arch/blackfin/mach-bf537/ints-priority.c index 14b2f74554dc..a48baae4384d 100644 --- a/arch/blackfin/mach-bf537/ints-priority.c +++ b/arch/blackfin/mach-bf537/ints-priority.c @@ -89,8 +89,7 @@ static struct irq_chip bf537_generic_error_irqchip = { .irq_unmask = bf537_generic_error_unmask_irq, }; -static void bf537_demux_error_irq(unsigned int int_err_irq, - struct irq_desc *inta_desc) +static void bf537_demux_error_irq(struct irq_desc *inta_desc) { int irq = 0; @@ -182,15 +181,12 @@ static struct irq_chip bf537_mac_rx_irqchip = { .irq_unmask = bf537_mac_rx_unmask_irq, }; -static void bf537_demux_mac_rx_irq(unsigned int __int_irq, - struct irq_desc *desc) +static void bf537_demux_mac_rx_irq(struct irq_desc *desc) { - unsigned int int_irq = irq_desc_get_irq(desc); - if (bfin_read_DMA1_IRQ_STATUS() & (DMA_DONE | DMA_ERR)) bfin_handle_irq(IRQ_MAC_RX); else - bfin_demux_gpio_irq(int_irq, desc); + bfin_demux_gpio_irq(desc); } #endif diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c index a6d1b03cdf36..e8d4d748d0fd 100644 --- a/arch/blackfin/mach-common/ints-priority.c +++ b/arch/blackfin/mach-common/ints-priority.c @@ -656,8 +656,7 @@ static struct irq_chip bfin_mac_status_irqchip = { .irq_set_wake = bfin_mac_status_set_wake, }; -void bfin_demux_mac_status_irq(unsigned int int_err_irq, - struct irq_desc *inta_desc) +void bfin_demux_mac_status_irq(struct irq_desc *inta_desc) { int i, irq = 0; u32 status = bfin_read_EMAC_SYSTAT(); @@ -825,7 +824,7 @@ static void bfin_demux_gpio_block(unsigned int irq) } } -void bfin_demux_gpio_irq(unsigned int __inta_irq, struct irq_desc *desc) +void bfin_demux_gpio_irq(struct irq_desc *desc) { unsigned int inta_irq = irq_desc_get_irq(desc); unsigned int irq; diff --git a/arch/c6x/platforms/megamod-pic.c b/arch/c6x/platforms/megamod-pic.c index d487698e978a..ddcb45d7dfa7 100644 --- a/arch/c6x/platforms/megamod-pic.c +++ b/arch/c6x/platforms/megamod-pic.c @@ -93,7 +93,7 @@ static struct irq_chip megamod_chip = { .irq_unmask = unmask_megamod, }; -static void megamod_irq_cascade(unsigned int __irq, struct irq_desc *desc) +static void megamod_irq_cascade(struct irq_desc *desc) { struct megamod_cascade_data *cascade; struct megamod_pic *pic; diff --git a/arch/m68k/amiga/amiints.c b/arch/m68k/amiga/amiints.c index 47b5f90002ab..7ff739e94896 100644 --- a/arch/m68k/amiga/amiints.c +++ b/arch/m68k/amiga/amiints.c @@ -46,7 +46,7 @@ static struct irq_chip amiga_irq_chip = { * The builtin Amiga hardware interrupt handlers. */ -static void ami_int1(unsigned int irq, struct irq_desc *desc) +static void ami_int1(struct irq_desc *desc) { unsigned short ints = amiga_custom.intreqr & amiga_custom.intenar; @@ -69,7 +69,7 @@ static void ami_int1(unsigned int irq, struct irq_desc *desc) } } -static void ami_int3(unsigned int irq, struct irq_desc *desc) +static void ami_int3(struct irq_desc *desc) { unsigned short ints = amiga_custom.intreqr & amiga_custom.intenar; @@ -92,7 +92,7 @@ static void ami_int3(unsigned int irq, struct irq_desc *desc) } } -static void ami_int4(unsigned int irq, struct irq_desc *desc) +static void ami_int4(struct irq_desc *desc) { unsigned short ints = amiga_custom.intreqr & amiga_custom.intenar; @@ -121,7 +121,7 @@ static void ami_int4(unsigned int irq, struct irq_desc *desc) } } -static void ami_int5(unsigned int irq, struct irq_desc *desc) +static void ami_int5(struct irq_desc *desc) { unsigned short ints = amiga_custom.intreqr & amiga_custom.intenar; diff --git a/arch/m68k/coldfire/intc-5272.c b/arch/m68k/coldfire/intc-5272.c index 47371de60427..b0a19e207a63 100644 --- a/arch/m68k/coldfire/intc-5272.c +++ b/arch/m68k/coldfire/intc-5272.c @@ -143,12 +143,10 @@ static int intc_irq_set_type(struct irq_data *d, unsigned int type) * We need to be careful with the masking/acking due to the side effects * of masking an interrupt. */ -static void intc_external_irq(unsigned int __irq, struct irq_desc *desc) +static void intc_external_irq(struct irq_desc *desc) { - unsigned int irq = irq_desc_get_irq(desc); - irq_desc_get_chip(desc)->irq_ack(&desc->irq_data); - handle_simple_irq(irq, desc); + handle_simple_irq(desc); } static struct irq_chip intc_irq_chip = { diff --git a/arch/m68k/include/asm/irq.h b/arch/m68k/include/asm/irq.h index 81ca118d58af..a644f4a53b94 100644 --- a/arch/m68k/include/asm/irq.h +++ b/arch/m68k/include/asm/irq.h @@ -64,8 +64,7 @@ extern void m68k_setup_auto_interrupt(void (*handler)(unsigned int, struct pt_regs *)); extern void m68k_setup_user_interrupt(unsigned int vec, unsigned int cnt); extern void m68k_setup_irq_controller(struct irq_chip *, - void (*handle)(unsigned int irq, - struct irq_desc *desc), + void (*handle)(struct irq_desc *desc), unsigned int irq, unsigned int cnt); extern unsigned int irq_canonicalize(unsigned int irq); diff --git a/arch/m68k/include/asm/mac_via.h b/arch/m68k/include/asm/mac_via.h index fe3fc9ae1b69..53c632c85b03 100644 --- a/arch/m68k/include/asm/mac_via.h +++ b/arch/m68k/include/asm/mac_via.h @@ -261,7 +261,7 @@ extern void via_irq_enable(int); extern void via_irq_disable(int); extern void via_nubus_irq_startup(int irq); extern void via_nubus_irq_shutdown(int irq); -extern void via1_irq(unsigned int irq, struct irq_desc *desc); +extern void via1_irq(struct irq_desc *desc); extern void via1_set_head(int); extern int via2_scsi_drq_pending(void); diff --git a/arch/m68k/mac/baboon.c b/arch/m68k/mac/baboon.c index 3fe0e43d44f6..f6f7d42713ec 100644 --- a/arch/m68k/mac/baboon.c +++ b/arch/m68k/mac/baboon.c @@ -45,7 +45,7 @@ void __init baboon_init(void) * Baboon interrupt handler. This works a lot like a VIA. */ -static void baboon_irq(unsigned int irq, struct irq_desc *desc) +static void baboon_irq(struct irq_desc *desc) { int irq_bit, irq_num; unsigned char events; diff --git a/arch/m68k/mac/oss.c b/arch/m68k/mac/oss.c index 191610d97689..55d6592783f5 100644 --- a/arch/m68k/mac/oss.c +++ b/arch/m68k/mac/oss.c @@ -63,7 +63,7 @@ void __init oss_nubus_init(void) * Handle miscellaneous OSS interrupts. */ -static void oss_irq(unsigned int __irq, struct irq_desc *desc) +static void oss_irq(struct irq_desc *desc) { int events = oss->irq_pending & (OSS_IP_IOPSCC | OSS_IP_SCSI | OSS_IP_IOPISM); @@ -99,7 +99,7 @@ static void oss_irq(unsigned int __irq, struct irq_desc *desc) * Unlike the VIA/RBV this is on its own autovector interrupt level. */ -static void oss_nubus_irq(unsigned int irq, struct irq_desc *desc) +static void oss_nubus_irq(struct irq_desc *desc) { int events, irq_bit, i; diff --git a/arch/m68k/mac/psc.c b/arch/m68k/mac/psc.c index 3b9e302e7a37..cd38f29955c8 100644 --- a/arch/m68k/mac/psc.c +++ b/arch/m68k/mac/psc.c @@ -113,7 +113,7 @@ void __init psc_init(void) * PSC interrupt handler. It's a lot like the VIA interrupt handler. */ -static void psc_irq(unsigned int __irq, struct irq_desc *desc) +static void psc_irq(struct irq_desc *desc) { unsigned int offset = (unsigned int)irq_desc_get_handler_data(desc); unsigned int irq = irq_desc_get_irq(desc); diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c index e198dec868e4..ce56e04386e7 100644 --- a/arch/m68k/mac/via.c +++ b/arch/m68k/mac/via.c @@ -446,7 +446,7 @@ void via_nubus_irq_shutdown(int irq) * via6522.c :-), disable/pending masks added. */ -void via1_irq(unsigned int irq, struct irq_desc *desc) +void via1_irq(struct irq_desc *desc) { int irq_num; unsigned char irq_bit, events; @@ -467,7 +467,7 @@ void via1_irq(unsigned int irq, struct irq_desc *desc) } while (events >= irq_bit); } -static void via2_irq(unsigned int irq, struct irq_desc *desc) +static void via2_irq(struct irq_desc *desc) { int irq_num; unsigned char irq_bit, events; @@ -493,7 +493,7 @@ static void via2_irq(unsigned int irq, struct irq_desc *desc) * VIA2 dispatcher as a fast interrupt handler. */ -void via_nubus_irq(unsigned int irq, struct irq_desc *desc) +static void via_nubus_irq(struct irq_desc *desc) { int slot_irq; unsigned char slot_bit, events; diff --git a/arch/metag/kernel/irq.c b/arch/metag/kernel/irq.c index a336094a7a6c..3074b64793e6 100644 --- a/arch/metag/kernel/irq.c +++ b/arch/metag/kernel/irq.c @@ -94,13 +94,11 @@ void do_IRQ(int irq, struct pt_regs *regs) "MOV D0.5,%0\n" "MOV D1Ar1,%1\n" "MOV D1RtP,%2\n" - "MOV D0Ar2,%3\n" "SWAP A0StP,D0.5\n" "SWAP PC,D1RtP\n" "MOV A0StP,D0.5\n" : - : "r" (isp), "r" (irq), "r" (desc->handle_irq), - "r" (desc) + : "r" (isp), "r" (desc), "r" (desc->handle_irq) : "memory", "cc", "D1Ar1", "D0Ar2", "D1Ar3", "D0Ar4", "D1Ar5", "D0Ar6", "D0Re0", "D1Re0", "D0.4", "D1RtP", "D0.5" diff --git a/arch/mips/alchemy/common/irq.c b/arch/mips/alchemy/common/irq.c index 4c496c50edf6..da9f9220048f 100644 --- a/arch/mips/alchemy/common/irq.c +++ b/arch/mips/alchemy/common/irq.c @@ -851,7 +851,7 @@ static struct syscore_ops alchemy_gpic_pmops = { /* create chained handlers for the 4 IC requests to the MIPS IRQ ctrl */ #define DISP(name, base, addr) \ -static void au1000_##name##_dispatch(unsigned int irq, struct irq_desc *d) \ +static void au1000_##name##_dispatch(struct irq_desc *d) \ { \ unsigned long r = __raw_readl((void __iomem *)KSEG1ADDR(addr)); \ if (likely(r)) \ @@ -865,7 +865,7 @@ DISP(ic0r1, AU1000_INTC0_INT_BASE, AU1000_IC0_PHYS_ADDR + IC_REQ1INT) DISP(ic1r0, AU1000_INTC1_INT_BASE, AU1000_IC1_PHYS_ADDR + IC_REQ0INT) DISP(ic1r1, AU1000_INTC1_INT_BASE, AU1000_IC1_PHYS_ADDR + IC_REQ1INT) -static void alchemy_gpic_dispatch(unsigned int irq, struct irq_desc *d) +static void alchemy_gpic_dispatch(struct irq_desc *d) { int i = __raw_readl(AU1300_GPIC_ADDR + AU1300_GPIC_PRIENC); generic_handle_irq(ALCHEMY_GPIC_INT_BASE + i); diff --git a/arch/mips/alchemy/devboards/bcsr.c b/arch/mips/alchemy/devboards/bcsr.c index 324ad72d7c36..faeddf119fd4 100644 --- a/arch/mips/alchemy/devboards/bcsr.c +++ b/arch/mips/alchemy/devboards/bcsr.c @@ -86,7 +86,7 @@ EXPORT_SYMBOL_GPL(bcsr_mod); /* * DB1200/PB1200 CPLD IRQ muxer */ -static void bcsr_csc_handler(unsigned int irq, struct irq_desc *d) +static void bcsr_csc_handler(struct irq_desc *d) { unsigned short bisr = __raw_readw(bcsr_virt + BCSR_REG_INTSTAT); struct irq_chip *chip = irq_desc_get_chip(d); diff --git a/arch/mips/ath25/ar2315.c b/arch/mips/ath25/ar2315.c index ec9a371f1e62..8da996142d6a 100644 --- a/arch/mips/ath25/ar2315.c +++ b/arch/mips/ath25/ar2315.c @@ -69,7 +69,7 @@ static struct irqaction ar2315_ahb_err_interrupt = { .name = "ar2315-ahb-error", }; -static void ar2315_misc_irq_handler(unsigned irq, struct irq_desc *desc) +static void ar2315_misc_irq_handler(struct irq_desc *desc) { u32 pending = ar2315_rst_reg_read(AR2315_ISR) & ar2315_rst_reg_read(AR2315_IMR); diff --git a/arch/mips/ath25/ar5312.c b/arch/mips/ath25/ar5312.c index e63e38fa4880..acd55a9cffe3 100644 --- a/arch/mips/ath25/ar5312.c +++ b/arch/mips/ath25/ar5312.c @@ -73,7 +73,7 @@ static struct irqaction ar5312_ahb_err_interrupt = { .name = "ar5312-ahb-error", }; -static void ar5312_misc_irq_handler(unsigned irq, struct irq_desc *desc) +static void ar5312_misc_irq_handler(struct irq_desc *desc) { u32 pending = ar5312_rst_reg_read(AR5312_ISR) & ar5312_rst_reg_read(AR5312_IMR); diff --git a/arch/mips/ath79/irq.c b/arch/mips/ath79/irq.c index 807132b838b2..15ecb4831e12 100644 --- a/arch/mips/ath79/irq.c +++ b/arch/mips/ath79/irq.c @@ -26,7 +26,7 @@ #include "common.h" #include "machtypes.h" -static void ath79_misc_irq_handler(unsigned int irq, struct irq_desc *desc) +static void ath79_misc_irq_handler(struct irq_desc *desc) { void __iomem *base = ath79_reset_base; u32 pending; @@ -119,7 +119,7 @@ static void __init ath79_misc_irq_init(void) irq_set_chained_handler(ATH79_CPU_IRQ(6), ath79_misc_irq_handler); } -static void ar934x_ip2_irq_dispatch(unsigned int irq, struct irq_desc *desc) +static void ar934x_ip2_irq_dispatch(struct irq_desc *desc) { u32 status; @@ -148,7 +148,7 @@ static void ar934x_ip2_irq_init(void) irq_set_chained_handler(ATH79_CPU_IRQ(2), ar934x_ip2_irq_dispatch); } -static void qca955x_ip2_irq_dispatch(unsigned int irq, struct irq_desc *desc) +static void qca955x_ip2_irq_dispatch(struct irq_desc *desc) { u32 status; @@ -171,7 +171,7 @@ static void qca955x_ip2_irq_dispatch(unsigned int irq, struct irq_desc *desc) } } -static void qca955x_ip3_irq_dispatch(unsigned int irq, struct irq_desc *desc) +static void qca955x_ip3_irq_dispatch(struct irq_desc *desc) { u32 status; diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index f26c3c661cca..0352bc8d56b3 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -2221,7 +2221,7 @@ static irqreturn_t octeon_irq_cib_handler(int my_irq, void *data) if (irqd_get_trigger_type(irq_data) & IRQ_TYPE_EDGE_BOTH) cvmx_write_csr(host_data->raw_reg, 1ull << i); - generic_handle_irq_desc(irq, desc); + generic_handle_irq_desc(desc); } } diff --git a/arch/mips/include/asm/netlogic/common.h b/arch/mips/include/asm/netlogic/common.h index 2a4c128277e4..be52c2125d71 100644 --- a/arch/mips/include/asm/netlogic/common.h +++ b/arch/mips/include/asm/netlogic/common.h @@ -57,8 +57,8 @@ #include struct irq_desc; -void nlm_smp_function_ipi_handler(unsigned int irq, struct irq_desc *desc); -void nlm_smp_resched_ipi_handler(unsigned int irq, struct irq_desc *desc); +void nlm_smp_function_ipi_handler(struct irq_desc *desc); +void nlm_smp_resched_ipi_handler(struct irq_desc *desc); void nlm_smp_irq_init(int hwcpuid); void nlm_boot_secondary_cpus(void); int nlm_wakeup_secondary_cpus(void); diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c index 6cd69fdaa1c5..a74e181058b0 100644 --- a/arch/mips/jz4740/gpio.c +++ b/arch/mips/jz4740/gpio.c @@ -291,7 +291,7 @@ static void jz_gpio_check_trigger_both(struct jz_gpio_chip *chip, unsigned int i writel(mask, reg); } -static void jz_gpio_irq_demux_handler(unsigned int irq, struct irq_desc *desc) +static void jz_gpio_irq_demux_handler(struct irq_desc *desc) { uint32_t flag; unsigned int gpio_irq; diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c index 0136b4f9c9cd..10d86d54880a 100644 --- a/arch/mips/netlogic/common/smp.c +++ b/arch/mips/netlogic/common/smp.c @@ -82,7 +82,7 @@ void nlm_send_ipi_mask(const struct cpumask *mask, unsigned int action) } /* IRQ_IPI_SMP_FUNCTION Handler */ -void nlm_smp_function_ipi_handler(unsigned int __irq, struct irq_desc *desc) +void nlm_smp_function_ipi_handler(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); clear_c0_eimr(irq); @@ -92,7 +92,7 @@ void nlm_smp_function_ipi_handler(unsigned int __irq, struct irq_desc *desc) } /* IRQ_IPI_SMP_RESCHEDULE handler */ -void nlm_smp_resched_ipi_handler(unsigned int __irq, struct irq_desc *desc) +void nlm_smp_resched_ipi_handler(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); clear_c0_eimr(irq); diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c index f8d0acb4f973..b4fa6413c4e5 100644 --- a/arch/mips/pci/pci-ar2315.c +++ b/arch/mips/pci/pci-ar2315.c @@ -318,7 +318,7 @@ static int ar2315_pci_host_setup(struct ar2315_pci_ctrl *apc) return 0; } -static void ar2315_pci_irq_handler(unsigned irq, struct irq_desc *desc) +static void ar2315_pci_irq_handler(struct irq_desc *desc) { struct ar2315_pci_ctrl *apc = irq_desc_get_handler_data(desc); u32 pending = ar2315_pci_reg_read(apc, AR2315_PCI_ISR) & diff --git a/arch/mips/pci/pci-ar71xx.c b/arch/mips/pci/pci-ar71xx.c index ad35a5e6a56c..7db963deec73 100644 --- a/arch/mips/pci/pci-ar71xx.c +++ b/arch/mips/pci/pci-ar71xx.c @@ -226,7 +226,7 @@ static struct pci_ops ar71xx_pci_ops = { .write = ar71xx_pci_write_config, }; -static void ar71xx_pci_irq_handler(unsigned int irq, struct irq_desc *desc) +static void ar71xx_pci_irq_handler(struct irq_desc *desc) { struct ar71xx_pci_controller *apc; void __iomem *base = ath79_reset_base; diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c index 907d11dd921b..2013dad700df 100644 --- a/arch/mips/pci/pci-ar724x.c +++ b/arch/mips/pci/pci-ar724x.c @@ -225,7 +225,7 @@ static struct pci_ops ar724x_pci_ops = { .write = ar724x_pci_write, }; -static void ar724x_pci_irq_handler(unsigned int irq, struct irq_desc *desc) +static void ar724x_pci_irq_handler(struct irq_desc *desc) { struct ar724x_pci_controller *apc; void __iomem *base; diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c index 53c8efaf1572..ed6732f9aa87 100644 --- a/arch/mips/pci/pci-rt3883.c +++ b/arch/mips/pci/pci-rt3883.c @@ -129,7 +129,7 @@ static void rt3883_pci_write_cfg32(struct rt3883_pci_controller *rpc, rt3883_pci_w32(rpc, val, RT3883_PCI_REG_CFGDATA); } -static void rt3883_pci_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void rt3883_pci_irq_handler(struct irq_desc *desc) { struct rt3883_pci_controller *rpc; u32 pending; diff --git a/arch/mips/ralink/irq.c b/arch/mips/ralink/irq.c index 8c624a8b9ea2..4cf77f358395 100644 --- a/arch/mips/ralink/irq.c +++ b/arch/mips/ralink/irq.c @@ -96,7 +96,7 @@ unsigned int get_c0_compare_int(void) return CP0_LEGACY_COMPARE_IRQ; } -static void ralink_intc_irq_handler(unsigned int irq, struct irq_desc *desc) +static void ralink_intc_irq_handler(struct irq_desc *desc) { u32 pending = rt_intc_r32(INTC_REG_STATUS0); diff --git a/arch/powerpc/include/asm/qe_ic.h b/arch/powerpc/include/asm/qe_ic.h index 25784cc959a0..1e155ca6d33c 100644 --- a/arch/powerpc/include/asm/qe_ic.h +++ b/arch/powerpc/include/asm/qe_ic.h @@ -59,14 +59,14 @@ enum qe_ic_grp_id { #ifdef CONFIG_QUICC_ENGINE void qe_ic_init(struct device_node *node, unsigned int flags, - void (*low_handler)(unsigned int irq, struct irq_desc *desc), - void (*high_handler)(unsigned int irq, struct irq_desc *desc)); + void (*low_handler)(struct irq_desc *desc), + void (*high_handler)(struct irq_desc *desc)); unsigned int qe_ic_get_low_irq(struct qe_ic *qe_ic); unsigned int qe_ic_get_high_irq(struct qe_ic *qe_ic); #else static inline void qe_ic_init(struct device_node *node, unsigned int flags, - void (*low_handler)(unsigned int irq, struct irq_desc *desc), - void (*high_handler)(unsigned int irq, struct irq_desc *desc)) + void (*low_handler)(struct irq_desc *desc), + void (*high_handler)(struct irq_desc *desc)) {} static inline unsigned int qe_ic_get_low_irq(struct qe_ic *qe_ic) { return 0; } @@ -78,8 +78,7 @@ void qe_ic_set_highest_priority(unsigned int virq, int high); int qe_ic_set_priority(unsigned int virq, unsigned int priority); int qe_ic_set_high_priority(unsigned int virq, unsigned int priority, int high); -static inline void qe_ic_cascade_low_ipic(unsigned int irq, - struct irq_desc *desc) +static inline void qe_ic_cascade_low_ipic(struct irq_desc *desc) { struct qe_ic *qe_ic = irq_desc_get_handler_data(desc); unsigned int cascade_irq = qe_ic_get_low_irq(qe_ic); @@ -88,8 +87,7 @@ static inline void qe_ic_cascade_low_ipic(unsigned int irq, generic_handle_irq(cascade_irq); } -static inline void qe_ic_cascade_high_ipic(unsigned int irq, - struct irq_desc *desc) +static inline void qe_ic_cascade_high_ipic(struct irq_desc *desc) { struct qe_ic *qe_ic = irq_desc_get_handler_data(desc); unsigned int cascade_irq = qe_ic_get_high_irq(qe_ic); @@ -98,8 +96,7 @@ static inline void qe_ic_cascade_high_ipic(unsigned int irq, generic_handle_irq(cascade_irq); } -static inline void qe_ic_cascade_low_mpic(unsigned int irq, - struct irq_desc *desc) +static inline void qe_ic_cascade_low_mpic(struct irq_desc *desc) { struct qe_ic *qe_ic = irq_desc_get_handler_data(desc); unsigned int cascade_irq = qe_ic_get_low_irq(qe_ic); @@ -111,8 +108,7 @@ static inline void qe_ic_cascade_low_mpic(unsigned int irq, chip->irq_eoi(&desc->irq_data); } -static inline void qe_ic_cascade_high_mpic(unsigned int irq, - struct irq_desc *desc) +static inline void qe_ic_cascade_high_mpic(struct irq_desc *desc) { struct qe_ic *qe_ic = irq_desc_get_handler_data(desc); unsigned int cascade_irq = qe_ic_get_high_irq(qe_ic); @@ -124,8 +120,7 @@ static inline void qe_ic_cascade_high_mpic(unsigned int irq, chip->irq_eoi(&desc->irq_data); } -static inline void qe_ic_cascade_muxed_mpic(unsigned int irq, - struct irq_desc *desc) +static inline void qe_ic_cascade_muxed_mpic(struct irq_desc *desc) { struct qe_ic *qe_ic = irq_desc_get_handler_data(desc); unsigned int cascade_irq; diff --git a/arch/powerpc/include/asm/tsi108_pci.h b/arch/powerpc/include/asm/tsi108_pci.h index 5653d7cc3e24..ae59d5b672b0 100644 --- a/arch/powerpc/include/asm/tsi108_pci.h +++ b/arch/powerpc/include/asm/tsi108_pci.h @@ -39,7 +39,7 @@ extern int tsi108_setup_pci(struct device_node *dev, u32 cfg_phys, int primary); extern void tsi108_pci_int_init(struct device_node *node); -extern void tsi108_irq_cascade(unsigned int irq, struct irq_desc *desc); +extern void tsi108_irq_cascade(struct irq_desc *desc); extern void tsi108_clear_pci_cfg_error(void); #endif /* _ASM_POWERPC_TSI108_PCI_H */ diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c index cf8287487157..0035d146df73 100644 --- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c +++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c @@ -104,8 +104,7 @@ cpld_pic_get_irq(int offset, u8 ignore, u8 __iomem *statusp, return irq_linear_revmap(cpld_pic_host, cpld_irq); } -static void -cpld_pic_cascade(unsigned int __irq, struct irq_desc *desc) +static void cpld_pic_cascade(struct irq_desc *desc) { unsigned int irq; diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c index 32cae33c4266..8fb95480fd73 100644 --- a/arch/powerpc/platforms/52xx/media5200.c +++ b/arch/powerpc/platforms/52xx/media5200.c @@ -80,7 +80,7 @@ static struct irq_chip media5200_irq_chip = { .irq_mask_ack = media5200_irq_mask, }; -void media5200_irq_cascade(unsigned int virq, struct irq_desc *desc) +static void media5200_irq_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); int sub_virq, val; diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index 63016621aff8..78ac19aefa4d 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -191,7 +191,7 @@ static struct irq_chip mpc52xx_gpt_irq_chip = { .irq_set_type = mpc52xx_gpt_irq_set_type, }; -void mpc52xx_gpt_irq_cascade(unsigned int virq, struct irq_desc *desc) +static void mpc52xx_gpt_irq_cascade(struct irq_desc *desc) { struct mpc52xx_gpt_priv *gpt = irq_desc_get_handler_data(desc); int sub_virq; diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c index 74861a7fb807..60e89fc9c753 100644 --- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c +++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c @@ -78,7 +78,7 @@ static struct irq_chip pq2ads_pci_ic = { .irq_disable = pq2ads_pci_mask_irq }; -static void pq2ads_pci_irq_demux(unsigned int irq, struct irq_desc *desc) +static void pq2ads_pci_irq_demux(struct irq_desc *desc) { struct pq2ads_pci_pic *priv = irq_desc_get_handler_data(desc); u32 stat, mask, pend; diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c index 7bfb9b184dd4..23791de7b688 100644 --- a/arch/powerpc/platforms/85xx/common.c +++ b/arch/powerpc/platforms/85xx/common.c @@ -49,7 +49,7 @@ int __init mpc85xx_common_publish_devices(void) return of_platform_bus_probe(NULL, mpc85xx_common_ids, NULL); } #ifdef CONFIG_CPM2 -static void cpm2_cascade(unsigned int irq, struct irq_desc *desc) +static void cpm2_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); int cascade_irq; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c index 13a8d1a3d55c..5ac70de3e48a 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c @@ -192,10 +192,8 @@ void mpc85xx_cds_fixup_bus(struct pci_bus *bus) } #ifdef CONFIG_PPC_I8259 -static void mpc85xx_8259_cascade_handler(unsigned int __irq, - struct irq_desc *desc) +static void mpc85xx_8259_cascade_handler(struct irq_desc *desc) { - unsigned int irq = irq_desc_get_irq(desc); unsigned int cascade_irq = i8259_irq(); if (cascade_irq != NO_IRQ) @@ -203,7 +201,7 @@ static void mpc85xx_8259_cascade_handler(unsigned int __irq, generic_handle_irq(cascade_irq); /* check for any interrupts from the shared IRQ line */ - handle_fasteoi_irq(irq, desc); + handle_fasteoi_irq(desc); } static irqreturn_t mpc85xx_8259_cascade_action(int irq, void *dev_id) diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index ffdf02121a7c..f858306dba6a 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -46,7 +46,7 @@ #endif #ifdef CONFIG_PPC_I8259 -static void mpc85xx_8259_cascade(unsigned int irq, struct irq_desc *desc) +static void mpc85xx_8259_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = i8259_irq(); diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c index d78fda892e8b..b02d6a5bb035 100644 --- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c +++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c @@ -91,7 +91,7 @@ static inline unsigned int socrates_fpga_pic_get_irq(unsigned int irq) (irq_hw_number_t)i); } -void socrates_fpga_pic_cascade(unsigned int __irq, struct irq_desc *desc) +static void socrates_fpga_pic_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int irq = irq_desc_get_irq(desc); diff --git a/arch/powerpc/platforms/86xx/pic.c b/arch/powerpc/platforms/86xx/pic.c index d5b98c0f958a..845defa1fd19 100644 --- a/arch/powerpc/platforms/86xx/pic.c +++ b/arch/powerpc/platforms/86xx/pic.c @@ -17,7 +17,7 @@ #include #ifdef CONFIG_PPC_I8259 -static void mpc86xx_8259_cascade(unsigned int irq, struct irq_desc *desc) +static void mpc86xx_8259_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = i8259_irq(); diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c index d3037747031d..c289fc77b4ba 100644 --- a/arch/powerpc/platforms/8xx/m8xx_setup.c +++ b/arch/powerpc/platforms/8xx/m8xx_setup.c @@ -214,7 +214,7 @@ void mpc8xx_restart(char *cmd) panic("Restart failed\n"); } -static void cpm_cascade(unsigned int irq, struct irq_desc *desc) +static void cpm_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); int cascade_irq = cpm_get_irq(); diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index 306888acb737..e0e68a1c0d3c 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -93,7 +93,7 @@ static void msic_dcr_write(struct axon_msic *msic, unsigned int dcr_n, u32 val) dcr_write(msic->dcr_host, dcr_n, val); } -static void axon_msi_cascade(unsigned int irq, struct irq_desc *desc) +static void axon_msi_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct axon_msic *msic = irq_desc_get_handler_data(desc); diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 6558e7e8ee50..9f609fc8d331 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -99,7 +99,7 @@ static void iic_ioexc_eoi(struct irq_data *d) { } -static void iic_ioexc_cascade(unsigned int __irq, struct irq_desc *desc) +static void iic_ioexc_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct cbe_iic_regs __iomem *node_iic = diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c index 1f72f4ab6353..9d27de62dc62 100644 --- a/arch/powerpc/platforms/cell/spider-pic.c +++ b/arch/powerpc/platforms/cell/spider-pic.c @@ -199,7 +199,7 @@ static const struct irq_domain_ops spider_host_ops = { .xlate = spider_host_xlate, }; -static void spider_irq_cascade(unsigned int irq, struct irq_desc *desc) +static void spider_irq_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct spider_pic *pic = irq_desc_get_handler_data(desc); diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index 15ebc4e8a151..987d1b8d68e3 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -363,7 +363,7 @@ void __init chrp_setup_arch(void) if (ppc_md.progress) ppc_md.progress("Linux/PPC "UTS_RELEASE"\n", 0x0); } -static void chrp_8259_cascade(unsigned int irq, struct irq_desc *desc) +static void chrp_8259_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = i8259_irq(); diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c index 9dd154d6f89a..9b7975706bfc 100644 --- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c +++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c @@ -120,8 +120,7 @@ static unsigned int __hlwd_pic_get_irq(struct irq_domain *h) return irq_linear_revmap(h, irq); } -static void hlwd_pic_irq_cascade(unsigned int cascade_virq, - struct irq_desc *desc) +static void hlwd_pic_irq_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct irq_domain *irq_domain = irq_desc_get_handler_data(desc); diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c b/arch/powerpc/platforms/embedded6xx/mvme5100.c index 1613303177e6..8f65aa3747f5 100644 --- a/arch/powerpc/platforms/embedded6xx/mvme5100.c +++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c @@ -42,7 +42,7 @@ static phys_addr_t pci_membase; static u_char *restart; -static void mvme5100_8259_cascade(unsigned int irq, struct irq_desc *desc) +static void mvme5100_8259_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = i8259_irq(); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 39a74fad3e04..9a83eb71b030 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -111,7 +111,7 @@ static void __init fwnmi_init(void) fwnmi_active = 1; } -static void pseries_8259_cascade(unsigned int irq, struct irq_desc *desc) +static void pseries_8259_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = i8259_irq(); diff --git a/arch/powerpc/sysdev/ge/ge_pic.c b/arch/powerpc/sysdev/ge/ge_pic.c index 2bcb78bb3a15..d57b77573068 100644 --- a/arch/powerpc/sysdev/ge/ge_pic.c +++ b/arch/powerpc/sysdev/ge/ge_pic.c @@ -91,7 +91,7 @@ static int gef_pic_cascade_irq; * should be masked out. */ -void gef_pic_cascade(unsigned int irq, struct irq_desc *desc) +static void gef_pic_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq; diff --git a/arch/powerpc/sysdev/ge/ge_pic.h b/arch/powerpc/sysdev/ge/ge_pic.h index 908dbd9826b6..5bf7e4b81e36 100644 --- a/arch/powerpc/sysdev/ge/ge_pic.h +++ b/arch/powerpc/sysdev/ge/ge_pic.h @@ -1,8 +1,6 @@ #ifndef __GEF_PIC_H__ #define __GEF_PIC_H__ - -void gef_pic_cascade(unsigned int, struct irq_desc *); unsigned int gef_pic_get_irq(void); void gef_pic_init(struct device_node *); diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 97a8ae8f94dd..537e5db85a06 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -1181,7 +1181,7 @@ static int mpic_host_xlate(struct irq_domain *h, struct device_node *ct, } /* IRQ handler for a secondary MPIC cascaded from another IRQ controller */ -static void mpic_cascade(unsigned int irq, struct irq_desc *desc) +static void mpic_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct mpic *mpic = irq_desc_get_handler_data(desc); diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c index 47b352e4bc74..fbcc1f855a7f 100644 --- a/arch/powerpc/sysdev/qe_lib/qe_ic.c +++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c @@ -311,8 +311,8 @@ unsigned int qe_ic_get_high_irq(struct qe_ic *qe_ic) } void __init qe_ic_init(struct device_node *node, unsigned int flags, - void (*low_handler)(unsigned int irq, struct irq_desc *desc), - void (*high_handler)(unsigned int irq, struct irq_desc *desc)) + void (*low_handler)(struct irq_desc *desc), + void (*high_handler)(struct irq_desc *desc)) { struct qe_ic *qe_ic; struct resource res; diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c index 57b54476e747..379de955aae3 100644 --- a/arch/powerpc/sysdev/tsi108_pci.c +++ b/arch/powerpc/sysdev/tsi108_pci.c @@ -428,7 +428,7 @@ void __init tsi108_pci_int_init(struct device_node *node) init_pci_source(); } -void tsi108_irq_cascade(unsigned int irq, struct irq_desc *desc) +void tsi108_irq_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = get_pci_source(); diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c index d77345338671..6893d8f236df 100644 --- a/arch/powerpc/sysdev/uic.c +++ b/arch/powerpc/sysdev/uic.c @@ -194,7 +194,7 @@ static const struct irq_domain_ops uic_host_ops = { .xlate = irq_domain_xlate_twocell, }; -void uic_irq_cascade(unsigned int virq, struct irq_desc *desc) +static void uic_irq_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct irq_data *idata = irq_desc_get_irq_data(desc); diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c index 43b8b275bc5c..0f52d7955796 100644 --- a/arch/powerpc/sysdev/xilinx_intc.c +++ b/arch/powerpc/sysdev/xilinx_intc.c @@ -222,7 +222,7 @@ int xilinx_intc_get_irq(void) /* * Support code for cascading to 8259 interrupt controllers */ -static void xilinx_i8259_cascade(unsigned int irq, struct irq_desc *desc) +static void xilinx_i8259_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = i8259_irq(); diff --git a/arch/sh/boards/mach-se/7343/irq.c b/arch/sh/boards/mach-se/7343/irq.c index 6f97a8f0d0d6..6129aef6db76 100644 --- a/arch/sh/boards/mach-se/7343/irq.c +++ b/arch/sh/boards/mach-se/7343/irq.c @@ -29,7 +29,7 @@ static void __iomem *se7343_irq_regs; struct irq_domain *se7343_irq_domain; -static void se7343_irq_demux(unsigned int irq, struct irq_desc *desc) +static void se7343_irq_demux(struct irq_desc *desc) { struct irq_data *data = irq_desc_get_irq_data(desc); struct irq_chip *chip = irq_data_get_irq_chip(data); diff --git a/arch/sh/boards/mach-se/7722/irq.c b/arch/sh/boards/mach-se/7722/irq.c index 60aebd14ccf8..24c74a88290c 100644 --- a/arch/sh/boards/mach-se/7722/irq.c +++ b/arch/sh/boards/mach-se/7722/irq.c @@ -28,7 +28,7 @@ static void __iomem *se7722_irq_regs; struct irq_domain *se7722_irq_domain; -static void se7722_irq_demux(unsigned int irq, struct irq_desc *desc) +static void se7722_irq_demux(struct irq_desc *desc) { struct irq_data *data = irq_desc_get_irq_data(desc); struct irq_chip *chip = irq_data_get_irq_chip(data); diff --git a/arch/sh/boards/mach-se/7724/irq.c b/arch/sh/boards/mach-se/7724/irq.c index 9f2033898652..64e681e66c57 100644 --- a/arch/sh/boards/mach-se/7724/irq.c +++ b/arch/sh/boards/mach-se/7724/irq.c @@ -92,7 +92,7 @@ static struct irq_chip se7724_irq_chip __read_mostly = { .irq_unmask = enable_se7724_irq, }; -static void se7724_irq_demux(unsigned int __irq, struct irq_desc *desc) +static void se7724_irq_demux(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct fpga_irq set = get_fpga_irq(irq); diff --git a/arch/sh/boards/mach-x3proto/gpio.c b/arch/sh/boards/mach-x3proto/gpio.c index 24555c364d5b..1fb2cbee25f2 100644 --- a/arch/sh/boards/mach-x3proto/gpio.c +++ b/arch/sh/boards/mach-x3proto/gpio.c @@ -60,7 +60,7 @@ static int x3proto_gpio_to_irq(struct gpio_chip *chip, unsigned gpio) return virq; } -static void x3proto_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) +static void x3proto_gpio_irq_handler(struct irq_desc *desc) { struct irq_data *data = irq_desc_get_irq_data(desc); struct irq_chip *chip = irq_data_get_irq_chip(data); diff --git a/arch/sh/cchips/hd6446x/hd64461.c b/arch/sh/cchips/hd6446x/hd64461.c index e9735616bdc8..8180092502f7 100644 --- a/arch/sh/cchips/hd6446x/hd64461.c +++ b/arch/sh/cchips/hd6446x/hd64461.c @@ -56,7 +56,7 @@ static struct irq_chip hd64461_irq_chip = { .irq_unmask = hd64461_unmask_irq, }; -static void hd64461_irq_demux(unsigned int irq, struct irq_desc *desc) +static void hd64461_irq_demux(struct irq_desc *desc) { unsigned short intv = __raw_readw(HD64461_NIRR); unsigned int ext_irq = HD64461_IRQBASE; diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c index 0299f052a2ef..42efcf85f721 100644 --- a/arch/sparc/kernel/leon_kernel.c +++ b/arch/sparc/kernel/leon_kernel.c @@ -53,7 +53,7 @@ static inline unsigned int leon_eirq_get(int cpu) } /* Handle one or multiple IRQs from the extended interrupt controller */ -static void leon_handle_ext_irq(unsigned int irq, struct irq_desc *desc) +static void leon_handle_ext_irq(struct irq_desc *desc) { unsigned int eirq; struct irq_bucket *p; diff --git a/arch/sparc/kernel/leon_pci_grpci1.c b/arch/sparc/kernel/leon_pci_grpci1.c index 3382f7b3eeef..1e77128a8f88 100644 --- a/arch/sparc/kernel/leon_pci_grpci1.c +++ b/arch/sparc/kernel/leon_pci_grpci1.c @@ -357,7 +357,7 @@ static struct irq_chip grpci1_irq = { }; /* Handle one or multiple IRQs from the PCI core */ -static void grpci1_pci_flow_irq(unsigned int irq, struct irq_desc *desc) +static void grpci1_pci_flow_irq(struct irq_desc *desc) { struct grpci1_priv *priv = grpci1priv; int i, ack = 0; diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c index 814fb1729b12..f727c4de1316 100644 --- a/arch/sparc/kernel/leon_pci_grpci2.c +++ b/arch/sparc/kernel/leon_pci_grpci2.c @@ -498,7 +498,7 @@ static struct irq_chip grpci2_irq = { }; /* Handle one or multiple IRQs from the PCI core */ -static void grpci2_pci_flow_irq(unsigned int irq, struct irq_desc *desc) +static void grpci2_pci_flow_irq(struct irq_desc *desc) { struct grpci2_priv *priv = grpci2priv; int i, ack = 0; diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c index b3f73fd764a3..4c017d0d2de8 100644 --- a/arch/tile/kernel/pci_gx.c +++ b/arch/tile/kernel/pci_gx.c @@ -304,17 +304,16 @@ static struct irq_chip tilegx_legacy_irq_chip = { * to Linux which just calls handle_level_irq() after clearing the * MAC INTx Assert status bit associated with this interrupt. */ -static void trio_handle_level_irq(unsigned int __irq, struct irq_desc *desc) +static void trio_handle_level_irq(struct irq_desc *desc) { struct pci_controller *controller = irq_desc_get_handler_data(desc); gxio_trio_context_t *trio_context = controller->trio; uint64_t intx = (uint64_t)irq_desc_get_chip_data(desc); - unsigned int irq = irq_desc_get_irq(desc); int mac = controller->mac; unsigned int reg_offset; uint64_t level_mask; - handle_level_irq(irq, desc); + handle_level_irq(desc); /* * Clear the INTx Level status, otherwise future interrupts are diff --git a/arch/unicore32/kernel/irq.c b/arch/unicore32/kernel/irq.c index c53729d92e8d..eb1fd0030359 100644 --- a/arch/unicore32/kernel/irq.c +++ b/arch/unicore32/kernel/irq.c @@ -112,7 +112,7 @@ static struct irq_chip puv3_low_gpio_chip = { * irq_controller_lock held, and IRQs disabled. Decode the IRQ * and call the handler. */ -static void puv3_gpio_handler(unsigned int __irq, struct irq_desc *desc) +static void puv3_gpio_handler(struct irq_desc *desc) { unsigned int mask, irq; diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index c80cf6699678..38da8f29a9c8 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -68,11 +68,10 @@ static inline void *current_stack(void) return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); } -static inline int -execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) +static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) { struct irq_stack *curstk, *irqstk; - u32 *isp, *prev_esp, arg1, arg2; + u32 *isp, *prev_esp, arg1; curstk = (struct irq_stack *) current_stack(); irqstk = __this_cpu_read(hardirq_stack); @@ -98,8 +97,8 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) asm volatile("xchgl %%ebx,%%esp \n" "call *%%edi \n" "movl %%ebx,%%esp \n" - : "=a" (arg1), "=d" (arg2), "=b" (isp) - : "0" (irq), "1" (desc), "2" (isp), + : "=a" (arg1), "=b" (isp) + : "0" (desc), "1" (isp), "D" (desc->handle_irq) : "memory", "cc", "ecx"); return 1; @@ -150,19 +149,15 @@ void do_softirq_own_stack(void) bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) { - unsigned int irq; - int overflow; - - overflow = check_stack_overflow(); + int overflow = check_stack_overflow(); if (IS_ERR_OR_NULL(desc)) return false; - irq = irq_desc_get_irq(desc); - if (user_mode(regs) || !execute_on_irq_stack(overflow, desc, irq)) { + if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) { if (unlikely(overflow)) print_stack_overflow(); - generic_handle_irq_desc(irq, desc); + generic_handle_irq_desc(desc); } return true; diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index ff16ccb918f2..c767cf2bc80a 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -75,6 +75,6 @@ bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) if (unlikely(IS_ERR_OR_NULL(desc))) return false; - generic_handle_irq_desc(irq_desc_get_irq(desc), desc); + generic_handle_irq_desc(desc); return true; } diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 161804de124a..a0d09f6c6533 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1015,7 +1015,7 @@ static struct clock_event_device lguest_clockevent = { * This is the Guest timer interrupt handler (hardware interrupt 0). We just * call the clockevent infrastructure and it does whatever needs doing. */ -static void lguest_time_irq(unsigned int irq, struct irq_desc *desc) +static void lguest_time_irq(struct irq_desc *desc) { unsigned long flags; diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c index 4768a829253a..2bf37e68ad0f 100644 --- a/drivers/dma/ipu/ipu_irq.c +++ b/drivers/dma/ipu/ipu_irq.c @@ -266,7 +266,7 @@ int ipu_irq_unmap(unsigned int source) } /* Chained IRQ handler for IPU function and error interrupt */ -static void ipu_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void ipu_irq_handler(struct irq_desc *desc) { struct ipu *ipu = irq_desc_get_handler_data(desc); u32 status; diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c index 9b7e0b3db387..1b44941574fa 100644 --- a/drivers/gpio/gpio-altera.c +++ b/drivers/gpio/gpio-altera.c @@ -201,8 +201,7 @@ static int altera_gpio_direction_output(struct gpio_chip *gc, return 0; } -static void altera_gpio_irq_edge_handler(unsigned int irq, - struct irq_desc *desc) +static void altera_gpio_irq_edge_handler(struct irq_desc *desc) { struct altera_gpio_chip *altera_gc; struct irq_chip *chip; @@ -231,8 +230,7 @@ static void altera_gpio_irq_edge_handler(unsigned int irq, } -static void altera_gpio_irq_leveL_high_handler(unsigned int irq, - struct irq_desc *desc) +static void altera_gpio_irq_leveL_high_handler(struct irq_desc *desc) { struct altera_gpio_chip *altera_gc; struct irq_chip *chip; diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c index 31b90ac15204..33a1f9779b86 100644 --- a/drivers/gpio/gpio-bcm-kona.c +++ b/drivers/gpio/gpio-bcm-kona.c @@ -433,7 +433,7 @@ static int bcm_kona_gpio_irq_set_type(struct irq_data *d, unsigned int type) return 0; } -static void bcm_kona_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) +static void bcm_kona_gpio_irq_handler(struct irq_desc *desc) { void __iomem *reg_base; int bit, bank_id; diff --git a/drivers/gpio/gpio-brcmstb.c b/drivers/gpio/gpio-brcmstb.c index 9ea86d2ac054..4c64627c6bb5 100644 --- a/drivers/gpio/gpio-brcmstb.c +++ b/drivers/gpio/gpio-brcmstb.c @@ -236,7 +236,7 @@ static void brcmstb_gpio_irq_bank_handler(struct brcmstb_gpio_bank *bank) } /* Each UPG GIO block has one IRQ for all banks */ -static void brcmstb_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) +static void brcmstb_gpio_irq_handler(struct irq_desc *desc) { struct gpio_chip *gc = irq_desc_get_handler_data(desc); struct brcmstb_gpio_priv *priv = brcmstb_gpio_gc_to_priv(gc); diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 94b0ab709721..5e715388803d 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -326,8 +326,7 @@ static struct irq_chip gpio_irqchip = { .flags = IRQCHIP_SET_TYPE_MASKED, }; -static void -gpio_irq_handler(unsigned __irq, struct irq_desc *desc) +static void gpio_irq_handler(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct davinci_gpio_regs __iomem *g; diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index c5be4b9b8baf..fcd5b0acfc72 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -147,7 +147,7 @@ static u32 dwapb_do_irq(struct dwapb_gpio *gpio) return ret; } -static void dwapb_irq_handler(u32 irq, struct irq_desc *desc) +static void dwapb_irq_handler(struct irq_desc *desc) { struct dwapb_gpio *gpio = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); diff --git a/drivers/gpio/gpio-ep93xx.c b/drivers/gpio/gpio-ep93xx.c index 9d90366ea259..3e3947b35c83 100644 --- a/drivers/gpio/gpio-ep93xx.c +++ b/drivers/gpio/gpio-ep93xx.c @@ -78,7 +78,7 @@ static void ep93xx_gpio_int_debounce(unsigned int irq, bool enable) EP93XX_GPIO_REG(int_debounce_register_offset[port])); } -static void ep93xx_gpio_ab_irq_handler(unsigned int irq, struct irq_desc *desc) +static void ep93xx_gpio_ab_irq_handler(struct irq_desc *desc) { unsigned char status; int i; @@ -100,8 +100,7 @@ static void ep93xx_gpio_ab_irq_handler(unsigned int irq, struct irq_desc *desc) } } -static void ep93xx_gpio_f_irq_handler(unsigned int __irq, - struct irq_desc *desc) +static void ep93xx_gpio_f_irq_handler(struct irq_desc *desc) { /* * map discontiguous hw irq range to continuous sw irq range: diff --git a/drivers/gpio/gpio-intel-mid.c b/drivers/gpio/gpio-intel-mid.c index aa28c65eb6b4..70097472b02c 100644 --- a/drivers/gpio/gpio-intel-mid.c +++ b/drivers/gpio/gpio-intel-mid.c @@ -301,7 +301,7 @@ static const struct pci_device_id intel_gpio_ids[] = { }; MODULE_DEVICE_TABLE(pci, intel_gpio_ids); -static void intel_mid_irq_handler(unsigned irq, struct irq_desc *desc) +static void intel_mid_irq_handler(struct irq_desc *desc) { struct gpio_chip *gc = irq_desc_get_handler_data(desc); struct intel_mid_gpio *priv = to_intel_gpio_priv(gc); diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c index 153af464c7a7..127c37b380ae 100644 --- a/drivers/gpio/gpio-lynxpoint.c +++ b/drivers/gpio/gpio-lynxpoint.c @@ -234,7 +234,7 @@ static int lp_gpio_direction_output(struct gpio_chip *chip, return 0; } -static void lp_gpio_irq_handler(unsigned hwirq, struct irq_desc *desc) +static void lp_gpio_irq_handler(struct irq_desc *desc) { struct irq_data *data = irq_desc_get_irq_data(desc); struct gpio_chip *gc = irq_desc_get_handler_data(desc); diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c index 8ef7a12de983..48ef368347ab 100644 --- a/drivers/gpio/gpio-mpc8xxx.c +++ b/drivers/gpio/gpio-mpc8xxx.c @@ -194,7 +194,7 @@ static int mpc8xxx_gpio_to_irq(struct gpio_chip *gc, unsigned offset) return -ENXIO; } -static void mpc8xxx_gpio_irq_cascade(unsigned int irq, struct irq_desc *desc) +static void mpc8xxx_gpio_irq_cascade(struct irq_desc *desc) { struct mpc8xxx_gpio_chip *mpc8xxx_gc = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); diff --git a/drivers/gpio/gpio-msic.c b/drivers/gpio/gpio-msic.c index 7bcfb87a5fa6..22523aae8abe 100644 --- a/drivers/gpio/gpio-msic.c +++ b/drivers/gpio/gpio-msic.c @@ -232,7 +232,7 @@ static struct irq_chip msic_irqchip = { .irq_bus_sync_unlock = msic_bus_sync_unlock, }; -static void msic_gpio_irq_handler(unsigned irq, struct irq_desc *desc) +static void msic_gpio_irq_handler(struct irq_desc *desc) { struct irq_data *data = irq_desc_get_irq_data(desc); struct msic_gpio *mg = irq_data_get_irq_handler_data(data); diff --git a/drivers/gpio/gpio-msm-v2.c b/drivers/gpio/gpio-msm-v2.c index d2012cfb5571..4b4222145f10 100644 --- a/drivers/gpio/gpio-msm-v2.c +++ b/drivers/gpio/gpio-msm-v2.c @@ -305,7 +305,7 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int flow_type) * which have been set as summary IRQ lines and which are triggered, * and to call their interrupt handlers. */ -static void msm_summary_irq_handler(unsigned int irq, struct irq_desc *desc) +static void msm_summary_irq_handler(struct irq_desc *desc) { unsigned long i; struct irq_chip *chip = irq_desc_get_chip(desc); diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index b396bf3bf294..df418b81456d 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -458,7 +458,7 @@ static int mvebu_gpio_irq_set_type(struct irq_data *d, unsigned int type) return 0; } -static void mvebu_gpio_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void mvebu_gpio_irq_handler(struct irq_desc *desc) { struct mvebu_gpio_chip *mvchip = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c index b752b560126e..5e3235a73bf9 100644 --- a/drivers/gpio/gpio-mxc.c +++ b/drivers/gpio/gpio-mxc.c @@ -272,7 +272,7 @@ static void mxc_gpio_irq_handler(struct mxc_gpio_port *port, u32 irq_stat) } /* MX1 and MX3 has one interrupt *per* gpio port */ -static void mx3_gpio_irq_handler(u32 irq, struct irq_desc *desc) +static void mx3_gpio_irq_handler(struct irq_desc *desc) { u32 irq_stat; struct mxc_gpio_port *port = irq_desc_get_handler_data(desc); @@ -288,7 +288,7 @@ static void mx3_gpio_irq_handler(u32 irq, struct irq_desc *desc) } /* MX2 has one interrupt *for all* gpio ports */ -static void mx2_gpio_irq_handler(u32 irq, struct irq_desc *desc) +static void mx2_gpio_irq_handler(struct irq_desc *desc) { u32 irq_msk, irq_stat; struct mxc_gpio_port *port; diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c index b7f383eb18d9..b7763f078b23 100644 --- a/drivers/gpio/gpio-mxs.c +++ b/drivers/gpio/gpio-mxs.c @@ -154,7 +154,7 @@ static void mxs_flip_edge(struct mxs_gpio_port *port, u32 gpio) } /* MXS has one interrupt *per* gpio port */ -static void mxs_gpio_irq_handler(u32 irq, struct irq_desc *desc) +static void mxs_gpio_irq_handler(struct irq_desc *desc) { u32 irq_stat; struct mxs_gpio_port *port = irq_desc_get_handler_data(desc); diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index 2ae0d47e9554..9df014c0e3e4 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -709,7 +709,7 @@ static void omap_gpio_free(struct gpio_chip *chip, unsigned offset) * line's interrupt handler has been run, we may miss some nested * interrupts. */ -static void omap_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) +static void omap_gpio_irq_handler(struct irq_desc *desc) { void __iomem *isr_reg = NULL; u32 isr; diff --git a/drivers/gpio/gpio-pl061.c b/drivers/gpio/gpio-pl061.c index 04756130437f..229ef653e0f8 100644 --- a/drivers/gpio/gpio-pl061.c +++ b/drivers/gpio/gpio-pl061.c @@ -187,7 +187,7 @@ static int pl061_irq_type(struct irq_data *d, unsigned trigger) return 0; } -static void pl061_irq_handler(unsigned irq, struct irq_desc *desc) +static void pl061_irq_handler(struct irq_desc *desc) { unsigned long pending; int offset; diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c index 55a11de3d5b7..df2ce550f309 100644 --- a/drivers/gpio/gpio-pxa.c +++ b/drivers/gpio/gpio-pxa.c @@ -401,7 +401,7 @@ static int pxa_gpio_irq_type(struct irq_data *d, unsigned int type) return 0; } -static void pxa_gpio_demux_handler(unsigned int irq, struct irq_desc *desc) +static void pxa_gpio_demux_handler(struct irq_desc *desc) { struct pxa_gpio_chip *c; int loop, gpio, gpio_base, n; diff --git a/drivers/gpio/gpio-sa1100.c b/drivers/gpio/gpio-sa1100.c index 67bd2f5d89e8..990fa9023e22 100644 --- a/drivers/gpio/gpio-sa1100.c +++ b/drivers/gpio/gpio-sa1100.c @@ -172,8 +172,7 @@ static struct irq_domain *sa1100_gpio_irqdomain; * irq_controller_lock held, and IRQs disabled. Decode the IRQ * and call the handler. */ -static void -sa1100_gpio_handler(unsigned int __irq, struct irq_desc *desc) +static void sa1100_gpio_handler(struct irq_desc *desc) { unsigned int irq, mask; diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c index 9b14aafb576d..027e5f47dd28 100644 --- a/drivers/gpio/gpio-tegra.c +++ b/drivers/gpio/gpio-tegra.c @@ -266,7 +266,7 @@ static void tegra_gpio_irq_shutdown(struct irq_data *d) gpiochip_unlock_as_irq(&tegra_gpio_chip, gpio); } -static void tegra_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) +static void tegra_gpio_irq_handler(struct irq_desc *desc) { int port; int pin; diff --git a/drivers/gpio/gpio-timberdale.c b/drivers/gpio/gpio-timberdale.c index 5a492054589f..30653e6319e9 100644 --- a/drivers/gpio/gpio-timberdale.c +++ b/drivers/gpio/gpio-timberdale.c @@ -192,7 +192,7 @@ out: return ret; } -static void timbgpio_irq(unsigned int irq, struct irq_desc *desc) +static void timbgpio_irq(struct irq_desc *desc) { struct timbgpio *tgpio = irq_desc_get_handler_data(desc); struct irq_data *data = irq_desc_get_irq_data(desc); diff --git a/drivers/gpio/gpio-tz1090.c b/drivers/gpio/gpio-tz1090.c index bbac92ae4c32..87bb1b1eee8d 100644 --- a/drivers/gpio/gpio-tz1090.c +++ b/drivers/gpio/gpio-tz1090.c @@ -375,7 +375,7 @@ static int gpio_set_irq_wake(struct irq_data *data, unsigned int on) #define gpio_set_irq_wake NULL #endif -static void tz1090_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) +static void tz1090_gpio_irq_handler(struct irq_desc *desc) { irq_hw_number_t hw; unsigned int irq_stat, irq_no; @@ -400,7 +400,7 @@ static void tz1090_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) == IRQ_TYPE_EDGE_BOTH) tz1090_gpio_irq_next_edge(bank, hw); - generic_handle_irq_desc(irq_no, child_desc); + generic_handle_irq_desc(child_desc); } } diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c index 7a6640b51911..069f9e4b7daa 100644 --- a/drivers/gpio/gpio-vf610.c +++ b/drivers/gpio/gpio-vf610.c @@ -120,7 +120,7 @@ static int vf610_gpio_direction_output(struct gpio_chip *chip, unsigned gpio, return pinctrl_gpio_direction_output(chip->base + gpio); } -static void vf610_gpio_irq_handler(u32 irq, struct irq_desc *desc) +static void vf610_gpio_irq_handler(struct irq_desc *desc) { struct vf610_gpio_port *port = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); diff --git a/drivers/gpio/gpio-zx.c b/drivers/gpio/gpio-zx.c index 12ee1969298c..4b8a26910705 100644 --- a/drivers/gpio/gpio-zx.c +++ b/drivers/gpio/gpio-zx.c @@ -177,7 +177,7 @@ static int zx_irq_type(struct irq_data *d, unsigned trigger) return 0; } -static void zx_irq_handler(unsigned irq, struct irq_desc *desc) +static void zx_irq_handler(struct irq_desc *desc) { unsigned long pending; int offset; diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c index 27348e7cb705..1d1a5865ede9 100644 --- a/drivers/gpio/gpio-zynq.c +++ b/drivers/gpio/gpio-zynq.c @@ -514,7 +514,7 @@ static void zynq_gpio_handle_bank_irq(struct zynq_gpio *gpio, * application for that pin. * Note: A bug is reported if no handler is set for the gpio pin. */ -static void zynq_gpio_irqhandler(unsigned int irq, struct irq_desc *desc) +static void zynq_gpio_irqhandler(struct irq_desc *desc) { u32 int_sts, int_enb; unsigned int bank_num; diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index 243f99a80253..649d03be2f38 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -912,7 +912,7 @@ static void ipu_irq_handle(struct ipu_soc *ipu, const int *regs, int num_regs) } } -static void ipu_irq_handler(unsigned int irq, struct irq_desc *desc) +static void ipu_irq_handler(struct irq_desc *desc) { struct ipu_soc *ipu = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); @@ -925,7 +925,7 @@ static void ipu_irq_handler(unsigned int irq, struct irq_desc *desc) chained_irq_exit(chip, desc); } -static void ipu_err_irq_handler(unsigned int irq, struct irq_desc *desc) +static void ipu_err_irq_handler(struct irq_desc *desc) { struct ipu_soc *ipu = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); diff --git a/drivers/irqchip/exynos-combiner.c b/drivers/irqchip/exynos-combiner.c index e9c6f2a5b52d..94ddc96f2f7d 100644 --- a/drivers/irqchip/exynos-combiner.c +++ b/drivers/irqchip/exynos-combiner.c @@ -65,12 +65,10 @@ static void combiner_unmask_irq(struct irq_data *data) __raw_writel(mask, combiner_base(data) + COMBINER_ENABLE_SET); } -static void combiner_handle_cascade_irq(unsigned int __irq, - struct irq_desc *desc) +static void combiner_handle_cascade_irq(struct irq_desc *desc) { struct combiner_chip_data *chip_data = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); - unsigned int irq = irq_desc_get_irq(desc); unsigned int cascade_irq, combiner_irq; unsigned long status; @@ -88,7 +86,7 @@ static void combiner_handle_cascade_irq(unsigned int __irq, cascade_irq = irq_find_mapping(combiner_irq_domain, combiner_irq); if (unlikely(!cascade_irq)) - handle_bad_irq(irq, desc); + handle_bad_irq(desc); else generic_handle_irq(cascade_irq); diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 39b72da0c143..693b9fb879bd 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -447,8 +447,7 @@ static void armada_370_xp_handle_msi_irq(struct pt_regs *regs, bool is_chained) static void armada_370_xp_handle_msi_irq(struct pt_regs *r, bool b) {} #endif -static void armada_370_xp_mpic_handle_cascade_irq(unsigned int irq, - struct irq_desc *desc) +static void armada_370_xp_mpic_handle_cascade_irq(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); unsigned long irqmap, irqn, irqsrc, cpuid; diff --git a/drivers/irqchip/irq-bcm2835.c b/drivers/irqchip/irq-bcm2835.c index ed4ca9deca70..56c9cf488e6c 100644 --- a/drivers/irqchip/irq-bcm2835.c +++ b/drivers/irqchip/irq-bcm2835.c @@ -96,7 +96,7 @@ struct armctrl_ic { static struct armctrl_ic intc __read_mostly; static void __exception_irq_entry bcm2835_handle_irq( struct pt_regs *regs); -static void bcm2836_chained_handle_irq(unsigned int irq, struct irq_desc *desc); +static void bcm2836_chained_handle_irq(struct irq_desc *desc); static void armctrl_mask_irq(struct irq_data *d) { @@ -245,7 +245,7 @@ static void __exception_irq_entry bcm2835_handle_irq( handle_IRQ(irq_linear_revmap(intc.domain, hwirq), regs); } -static void bcm2836_chained_handle_irq(unsigned int irq, struct irq_desc *desc) +static void bcm2836_chained_handle_irq(struct irq_desc *desc) { u32 hwirq; diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c index 409bdc6366c2..0fea985ef1dc 100644 --- a/drivers/irqchip/irq-bcm7038-l1.c +++ b/drivers/irqchip/irq-bcm7038-l1.c @@ -115,7 +115,7 @@ static inline void l1_writel(u32 val, void __iomem *reg) writel(val, reg); } -static void bcm7038_l1_irq_handle(unsigned int irq, struct irq_desc *desc) +static void bcm7038_l1_irq_handle(struct irq_desc *desc) { struct bcm7038_l1_chip *intc = irq_desc_get_handler_data(desc); struct bcm7038_l1_cpu *cpu; diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c index d3f976913a6f..61b18ab33ad9 100644 --- a/drivers/irqchip/irq-bcm7120-l2.c +++ b/drivers/irqchip/irq-bcm7120-l2.c @@ -56,7 +56,7 @@ struct bcm7120_l2_intc_data { const __be32 *map_mask_prop; }; -static void bcm7120_l2_intc_irq_handle(unsigned int irq, struct irq_desc *desc) +static void bcm7120_l2_intc_irq_handle(struct irq_desc *desc) { struct bcm7120_l1_intc_data *data = irq_desc_get_handler_data(desc); struct bcm7120_l2_intc_data *b = data->b; diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index aedda06191eb..65cd341f331a 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -49,13 +49,12 @@ struct brcmstb_l2_intc_data { u32 saved_mask; /* for suspend/resume */ }; -static void brcmstb_l2_intc_irq_handle(unsigned int __irq, - struct irq_desc *desc) +static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc) { struct brcmstb_l2_intc_data *b = irq_desc_get_handler_data(desc); struct irq_chip_generic *gc = irq_get_domain_generic_chip(b->domain, 0); struct irq_chip *chip = irq_desc_get_chip(desc); - unsigned int irq = irq_desc_get_irq(desc); + unsigned int irq; u32 status; chained_irq_enter(chip, desc); @@ -65,7 +64,7 @@ static void brcmstb_l2_intc_irq_handle(unsigned int __irq, if (status == 0) { raw_spin_lock(&desc->lock); - handle_bad_irq(irq, desc); + handle_bad_irq(desc); raw_spin_unlock(&desc->lock); goto out; } diff --git a/drivers/irqchip/irq-dw-apb-ictl.c b/drivers/irqchip/irq-dw-apb-ictl.c index efd95d9955e7..052f266364c0 100644 --- a/drivers/irqchip/irq-dw-apb-ictl.c +++ b/drivers/irqchip/irq-dw-apb-ictl.c @@ -26,7 +26,7 @@ #define APB_INT_FINALSTATUS_H 0x34 #define APB_INT_BASE_OFFSET 0x04 -static void dw_apb_ictl_handler(unsigned int irq, struct irq_desc *desc) +static void dw_apb_ictl_handler(struct irq_desc *desc) { struct irq_domain *d = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 9bccdd295769..00bb7c05a55e 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -341,7 +341,7 @@ static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) } while (1); } -static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc) +static void gic_handle_cascade_irq(struct irq_desc *desc) { struct gic_chip_data *chip_data = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); @@ -360,7 +360,7 @@ static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc) cascade_irq = irq_find_mapping(chip_data->domain, gic_irq); if (unlikely(gic_irq < 32 || gic_irq > 1020)) - handle_bad_irq(cascade_irq, desc); + handle_bad_irq(desc); else generic_handle_irq(cascade_irq); diff --git a/drivers/irqchip/irq-i8259.c b/drivers/irqchip/irq-i8259.c index 4836102ba312..e484fd255321 100644 --- a/drivers/irqchip/irq-i8259.c +++ b/drivers/irqchip/irq-i8259.c @@ -352,7 +352,7 @@ void __init init_i8259_irqs(void) __init_i8259_irqs(NULL); } -static void i8259_irq_dispatch(unsigned int __irq, struct irq_desc *desc) +static void i8259_irq_dispatch(struct irq_desc *desc) { struct irq_domain *domain = irq_desc_get_handler_data(desc); int hwirq = i8259_irq(); diff --git a/drivers/irqchip/irq-imgpdc.c b/drivers/irqchip/irq-imgpdc.c index 841604b81004..c02d29c9dc05 100644 --- a/drivers/irqchip/irq-imgpdc.c +++ b/drivers/irqchip/irq-imgpdc.c @@ -218,7 +218,7 @@ static int pdc_irq_set_wake(struct irq_data *data, unsigned int on) return 0; } -static void pdc_intc_perip_isr(unsigned int __irq, struct irq_desc *desc) +static void pdc_intc_perip_isr(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct pdc_intc_priv *priv; @@ -240,7 +240,7 @@ found: generic_handle_irq(irq_no); } -static void pdc_intc_syswake_isr(unsigned int irq, struct irq_desc *desc) +static void pdc_intc_syswake_isr(struct irq_desc *desc) { struct pdc_intc_priv *priv; unsigned int syswake, irq_no; diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c index c1517267b5db..7b784b692f3c 100644 --- a/drivers/irqchip/irq-keystone.c +++ b/drivers/irqchip/irq-keystone.c @@ -83,7 +83,7 @@ static void keystone_irq_ack(struct irq_data *d) /* nothing to do here */ } -static void keystone_irq_handler(unsigned __irq, struct irq_desc *desc) +static void keystone_irq_handler(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct keystone_irq_device *kirq = irq_desc_get_handler_data(desc); diff --git a/drivers/irqchip/irq-metag-ext.c b/drivers/irqchip/irq-metag-ext.c index 5f4c52928d16..8c38b3d92e1c 100644 --- a/drivers/irqchip/irq-metag-ext.c +++ b/drivers/irqchip/irq-metag-ext.c @@ -446,7 +446,7 @@ static int meta_intc_irq_set_type(struct irq_data *data, unsigned int flow_type) * Whilst using TR2 to detect external interrupts is a software convention it is * (hopefully) unlikely to change. */ -static void meta_intc_irq_demux(unsigned int irq, struct irq_desc *desc) +static void meta_intc_irq_demux(struct irq_desc *desc) { struct meta_intc_priv *priv = &meta_intc_priv; irq_hw_number_t hw; diff --git a/drivers/irqchip/irq-metag.c b/drivers/irqchip/irq-metag.c index 3d23ce3edb5c..a5f053bd2f44 100644 --- a/drivers/irqchip/irq-metag.c +++ b/drivers/irqchip/irq-metag.c @@ -220,7 +220,7 @@ static int metag_internal_irq_set_affinity(struct irq_data *data, * occurred. It is this function's job to demux this irq and * figure out exactly which trigger needs servicing. */ -static void metag_internal_irq_demux(unsigned int irq, struct irq_desc *desc) +static void metag_internal_irq_demux(struct irq_desc *desc) { struct metag_internal_irq_priv *priv = irq_desc_get_handler_data(desc); irq_hw_number_t hw; diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 1764bcf8ee6b..af2f16bb8a94 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -546,7 +546,7 @@ static void __gic_irq_dispatch(void) gic_handle_shared_int(false); } -static void gic_irq_dispatch(unsigned int irq, struct irq_desc *desc) +static void gic_irq_dispatch(struct irq_desc *desc) { gic_handle_local_int(true); gic_handle_shared_int(true); diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c index 781ed6e71dbb..ea6e3a96f3b3 100644 --- a/drivers/irqchip/irq-mmp.c +++ b/drivers/irqchip/irq-mmp.c @@ -129,7 +129,7 @@ struct irq_chip icu_irq_chip = { .irq_unmask = icu_unmask_irq, }; -static void icu_mux_irq_demux(unsigned int __irq, struct irq_desc *desc) +static void icu_mux_irq_demux(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct irq_domain *domain; diff --git a/drivers/irqchip/irq-orion.c b/drivers/irqchip/irq-orion.c index 5ea999a724b5..be4c5a8c9659 100644 --- a/drivers/irqchip/irq-orion.c +++ b/drivers/irqchip/irq-orion.c @@ -106,7 +106,7 @@ IRQCHIP_DECLARE(orion_intc, "marvell,orion-intc", orion_irq_init); #define ORION_BRIDGE_IRQ_CAUSE 0x00 #define ORION_BRIDGE_IRQ_MASK 0x04 -static void orion_bridge_irq_handler(unsigned int irq, struct irq_desc *desc) +static void orion_bridge_irq_handler(struct irq_desc *desc) { struct irq_domain *d = irq_desc_get_handler_data(desc); diff --git a/drivers/irqchip/irq-s3c24xx.c b/drivers/irqchip/irq-s3c24xx.c index 506d9f20ca51..e47572a9bbb2 100644 --- a/drivers/irqchip/irq-s3c24xx.c +++ b/drivers/irqchip/irq-s3c24xx.c @@ -298,7 +298,7 @@ static struct irq_chip s3c_irq_eint0t4 = { .irq_set_type = s3c_irqext0_type, }; -static void s3c_irq_demux(unsigned int __irq, struct irq_desc *desc) +static void s3c_irq_demux(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct s3c_irq_data *irq_data = irq_desc_get_chip_data(desc); diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c index 772a82cacbf7..c143dd58410c 100644 --- a/drivers/irqchip/irq-sunxi-nmi.c +++ b/drivers/irqchip/irq-sunxi-nmi.c @@ -58,7 +58,7 @@ static inline u32 sunxi_sc_nmi_read(struct irq_chip_generic *gc, u32 off) return irq_reg_readl(gc, off); } -static void sunxi_sc_nmi_handle_irq(unsigned int irq, struct irq_desc *desc) +static void sunxi_sc_nmi_handle_irq(struct irq_desc *desc) { struct irq_domain *domain = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); diff --git a/drivers/irqchip/irq-tb10x.c b/drivers/irqchip/irq-tb10x.c index 331829661366..848d782a2a3b 100644 --- a/drivers/irqchip/irq-tb10x.c +++ b/drivers/irqchip/irq-tb10x.c @@ -97,7 +97,7 @@ static int tb10x_irq_set_type(struct irq_data *data, unsigned int flow_type) return IRQ_SET_MASK_OK; } -static void tb10x_irq_cascade(unsigned int __irq, struct irq_desc *desc) +static void tb10x_irq_cascade(struct irq_desc *desc) { struct irq_domain *domain = irq_desc_get_handler_data(desc); unsigned int irq = irq_desc_get_irq(desc); diff --git a/drivers/irqchip/irq-versatile-fpga.c b/drivers/irqchip/irq-versatile-fpga.c index 16123f688768..1b1c63e8d249 100644 --- a/drivers/irqchip/irq-versatile-fpga.c +++ b/drivers/irqchip/irq-versatile-fpga.c @@ -65,19 +65,19 @@ static void fpga_irq_unmask(struct irq_data *d) writel(mask, f->base + IRQ_ENABLE_SET); } -static void fpga_irq_handle(unsigned int __irq, struct irq_desc *desc) +static void fpga_irq_handle(struct irq_desc *desc) { struct fpga_irq_data *f = irq_desc_get_handler_data(desc); - unsigned int irq = irq_desc_get_irq(desc); u32 status = readl(f->base + IRQ_STATUS); if (status == 0) { - do_bad_IRQ(irq, desc); + do_bad_IRQ(desc); return; } do { - irq = ffs(status) - 1; + unsigned int irq = ffs(status) - 1; + status &= ~(1 << irq); generic_handle_irq(irq_find_mapping(f->domain, irq)); } while (status); diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c index 03846dff4212..cb85504c2ff1 100644 --- a/drivers/irqchip/irq-vic.c +++ b/drivers/irqchip/irq-vic.c @@ -225,7 +225,7 @@ static int handle_one_vic(struct vic_device *vic, struct pt_regs *regs) return handled; } -static void vic_handle_irq_cascaded(unsigned int irq, struct irq_desc *desc) +static void vic_handle_irq_cascaded(struct irq_desc *desc) { u32 stat, hwirq; struct irq_chip *host_chip = irq_desc_get_chip(desc); diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c index 4cbd9c5dc1e6..c838c9286ea5 100644 --- a/drivers/irqchip/spear-shirq.c +++ b/drivers/irqchip/spear-shirq.c @@ -182,7 +182,7 @@ static struct spear_shirq *spear320_shirq_blocks[] = { &spear320_shirq_intrcomm_ras, }; -static void shirq_handler(unsigned __irq, struct irq_desc *desc) +static void shirq_handler(struct irq_desc *desc) { struct spear_shirq *shirq = irq_desc_get_handler_data(desc); u32 pend; diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c index 4b54128bc78e..a726f01e3b02 100644 --- a/drivers/mfd/asic3.c +++ b/drivers/mfd/asic3.c @@ -138,7 +138,7 @@ static void asic3_irq_flip_edge(struct asic3 *asic, spin_unlock_irqrestore(&asic->lock, flags); } -static void asic3_irq_demux(unsigned int irq, struct irq_desc *desc) +static void asic3_irq_demux(struct irq_desc *desc) { struct asic3 *asic = irq_desc_get_handler_data(desc); struct irq_data *data = irq_desc_get_irq_data(desc); diff --git a/drivers/mfd/ezx-pcap.c b/drivers/mfd/ezx-pcap.c index a76eb6ef47a0..b279205659a4 100644 --- a/drivers/mfd/ezx-pcap.c +++ b/drivers/mfd/ezx-pcap.c @@ -205,7 +205,7 @@ static void pcap_isr_work(struct work_struct *work) } while (gpio_get_value(pdata->gpio)); } -static void pcap_irq_handler(unsigned int irq, struct irq_desc *desc) +static void pcap_irq_handler(struct irq_desc *desc) { struct pcap_chip *pcap = irq_desc_get_handler_data(desc); diff --git a/drivers/mfd/htc-egpio.c b/drivers/mfd/htc-egpio.c index 9131cdcdc64a..6ccaf90d98fd 100644 --- a/drivers/mfd/htc-egpio.c +++ b/drivers/mfd/htc-egpio.c @@ -98,7 +98,7 @@ static struct irq_chip egpio_muxed_chip = { .irq_unmask = egpio_unmask, }; -static void egpio_handler(unsigned int irq, struct irq_desc *desc) +static void egpio_handler(struct irq_desc *desc) { struct egpio_info *ei = irq_desc_get_handler_data(desc); int irqpin; diff --git a/drivers/mfd/jz4740-adc.c b/drivers/mfd/jz4740-adc.c index 5bb49f08955d..798e44306382 100644 --- a/drivers/mfd/jz4740-adc.c +++ b/drivers/mfd/jz4740-adc.c @@ -65,7 +65,7 @@ struct jz4740_adc { spinlock_t lock; }; -static void jz4740_adc_irq_demux(unsigned int irq, struct irq_desc *desc) +static void jz4740_adc_irq_demux(struct irq_desc *desc) { struct irq_chip_generic *gc = irq_desc_get_handler_data(desc); uint8_t status; diff --git a/drivers/mfd/pm8921-core.c b/drivers/mfd/pm8921-core.c index 59502d02cd15..1b7ec0870c2a 100644 --- a/drivers/mfd/pm8921-core.c +++ b/drivers/mfd/pm8921-core.c @@ -156,7 +156,7 @@ static int pm8xxx_irq_master_handler(struct pm_irq_chip *chip, int master) return ret; } -static void pm8xxx_irq_handler(unsigned int irq, struct irq_desc *desc) +static void pm8xxx_irq_handler(struct irq_desc *desc) { struct pm_irq_chip *chip = irq_desc_get_handler_data(desc); struct irq_chip *irq_chip = irq_desc_get_chip(desc); diff --git a/drivers/mfd/t7l66xb.c b/drivers/mfd/t7l66xb.c index 16fc1adc4fa3..94bd89cb1f06 100644 --- a/drivers/mfd/t7l66xb.c +++ b/drivers/mfd/t7l66xb.c @@ -185,7 +185,7 @@ static struct mfd_cell t7l66xb_cells[] = { /*--------------------------------------------------------------------------*/ /* Handle the T7L66XB interrupt mux */ -static void t7l66xb_irq(unsigned int irq, struct irq_desc *desc) +static void t7l66xb_irq(struct irq_desc *desc) { struct t7l66xb *t7l66xb = irq_desc_get_handler_data(desc); unsigned int isr; diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c index 775b9aca871a..8c84a513016b 100644 --- a/drivers/mfd/tc6393xb.c +++ b/drivers/mfd/tc6393xb.c @@ -522,8 +522,7 @@ static int tc6393xb_register_gpio(struct tc6393xb *tc6393xb, int gpio_base) /*--------------------------------------------------------------------------*/ -static void -tc6393xb_irq(unsigned int irq, struct irq_desc *desc) +static void tc6393xb_irq(struct irq_desc *desc) { struct tc6393xb *tc6393xb = irq_desc_get_handler_data(desc); unsigned int isr; diff --git a/drivers/mfd/ucb1x00-core.c b/drivers/mfd/ucb1x00-core.c index 9a2302129711..f691d7ecad52 100644 --- a/drivers/mfd/ucb1x00-core.c +++ b/drivers/mfd/ucb1x00-core.c @@ -282,7 +282,7 @@ void ucb1x00_adc_disable(struct ucb1x00 *ucb) * SIBCLK to talk to the chip. We leave the clock running until * we have finished processing all interrupts from the chip. */ -static void ucb1x00_irq(unsigned int __irq, struct irq_desc *desc) +static void ucb1x00_irq(struct irq_desc *desc) { struct ucb1x00 *ucb = irq_desc_get_handler_data(desc); unsigned int isr, i; diff --git a/drivers/pci/host/pci-keystone.c b/drivers/pci/host/pci-keystone.c index 81253e70b1c5..0aa81bd3de12 100644 --- a/drivers/pci/host/pci-keystone.c +++ b/drivers/pci/host/pci-keystone.c @@ -110,7 +110,7 @@ static int ks_pcie_establish_link(struct keystone_pcie *ks_pcie) return -EINVAL; } -static void ks_pcie_msi_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void ks_pcie_msi_irq_handler(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc); @@ -138,8 +138,7 @@ static void ks_pcie_msi_irq_handler(unsigned int __irq, struct irq_desc *desc) * Traverse through pending legacy interrupts and invoke handler for each. Also * takes care of interrupt controller level mask/ack operation. */ -static void ks_pcie_legacy_irq_handler(unsigned int __irq, - struct irq_desc *desc) +static void ks_pcie_legacy_irq_handler(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc); diff --git a/drivers/pci/host/pci-xgene-msi.c b/drivers/pci/host/pci-xgene-msi.c index 996327cfa1e1..e491681daf22 100644 --- a/drivers/pci/host/pci-xgene-msi.c +++ b/drivers/pci/host/pci-xgene-msi.c @@ -295,7 +295,7 @@ static int xgene_msi_init_allocator(struct xgene_msi *xgene_msi) return 0; } -static void xgene_msi_isr(unsigned int irq, struct irq_desc *desc) +static void xgene_msi_isr(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct xgene_msi_group *msi_groups; diff --git a/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c b/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c index 7d9482bf8252..1ca783098e47 100644 --- a/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c +++ b/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c @@ -143,7 +143,7 @@ static inline bool cygnus_get_bit(struct cygnus_gpio *chip, unsigned int reg, return !!(readl(chip->base + offset) & BIT(shift)); } -static void cygnus_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) +static void cygnus_gpio_irq_handler(struct irq_desc *desc) { struct gpio_chip *gc = irq_desc_get_handler_data(desc); struct cygnus_gpio *chip = to_cygnus_gpio(gc); diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index dac4865f3203..f79ea430f651 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -425,7 +425,7 @@ static void byt_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) } } -static void byt_gpio_irq_handler(unsigned irq, struct irq_desc *desc) +static void byt_gpio_irq_handler(struct irq_desc *desc) { struct irq_data *data = irq_desc_get_irq_data(desc); struct byt_gpio *vg = to_byt_gpio(irq_desc_get_handler_data(desc)); diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 2d5d3ddc36e5..270c127e03ea 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1414,7 +1414,7 @@ static struct irq_chip chv_gpio_irqchip = { .flags = IRQCHIP_SKIP_SET_WAKE, }; -static void chv_gpio_irq_handler(unsigned irq, struct irq_desc *desc) +static void chv_gpio_irq_handler(struct irq_desc *desc) { struct gpio_chip *gc = irq_desc_get_handler_data(desc); struct chv_pinctrl *pctrl = gpiochip_to_pinctrl(gc); diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index bb377c110541..54848b8decef 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -836,7 +836,7 @@ static void intel_gpio_community_irq_handler(struct gpio_chip *gc, } } -static void intel_gpio_irq_handler(unsigned irq, struct irq_desc *desc) +static void intel_gpio_irq_handler(struct irq_desc *desc) { struct gpio_chip *gc = irq_desc_get_handler_data(desc); struct intel_pinctrl *pctrl = gpiochip_to_pinctrl(gc); diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c index 7726c6caaf83..1b22f96ba839 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c @@ -1190,7 +1190,7 @@ mtk_eint_debounce_process(struct mtk_pinctrl *pctl, int index) } } -static void mtk_eint_irq_handler(unsigned irq, struct irq_desc *desc) +static void mtk_eint_irq_handler(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct mtk_pinctrl *pctl = irq_desc_get_handler_data(desc); diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c index 352ede13a9e9..96cf03908e93 100644 --- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c +++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c @@ -860,7 +860,7 @@ static void __nmk_gpio_irq_handler(struct irq_desc *desc, u32 status) chained_irq_exit(host_chip, desc); } -static void nmk_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) +static void nmk_gpio_irq_handler(struct irq_desc *desc) { struct gpio_chip *chip = irq_desc_get_handler_data(desc); struct nmk_gpio_chip *nmk_chip = container_of(chip, struct nmk_gpio_chip, chip); @@ -873,7 +873,7 @@ static void nmk_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) __nmk_gpio_irq_handler(desc, status); } -static void nmk_gpio_latent_irq_handler(unsigned int irq, struct irq_desc *desc) +static void nmk_gpio_latent_irq_handler(struct irq_desc *desc) { struct gpio_chip *chip = irq_desc_get_handler_data(desc); struct nmk_gpio_chip *nmk_chip = container_of(chip, struct nmk_gpio_chip, chip); diff --git a/drivers/pinctrl/pinctrl-adi2.c b/drivers/pinctrl/pinctrl-adi2.c index a5976ebc4482..f6be68518c87 100644 --- a/drivers/pinctrl/pinctrl-adi2.c +++ b/drivers/pinctrl/pinctrl-adi2.c @@ -530,8 +530,7 @@ static inline void preflow_handler(struct irq_desc *desc) static inline void preflow_handler(struct irq_desc *desc) { } #endif -static void adi_gpio_handle_pint_irq(unsigned int inta_irq, - struct irq_desc *desc) +static void adi_gpio_handle_pint_irq(struct irq_desc *desc) { u32 request; u32 level_mask, hwirq; diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 5e86bb8ca80e..3318f1d6193c 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -492,15 +492,15 @@ static struct irq_chip amd_gpio_irqchip = { .irq_set_type = amd_gpio_irq_set_type, }; -static void amd_gpio_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void amd_gpio_irq_handler(struct irq_desc *desc) { - unsigned int irq = irq_desc_get_irq(desc); u32 i; u32 off; u32 reg; u32 pin_reg; u64 reg64; int handled = 0; + unsigned int irq; unsigned long flags; struct irq_chip *chip = irq_desc_get_chip(desc); struct gpio_chip *gc = irq_desc_get_handler_data(desc); @@ -541,7 +541,7 @@ static void amd_gpio_irq_handler(unsigned int __irq, struct irq_desc *desc) } if (handled == 0) - handle_bad_irq(irq, desc); + handle_bad_irq(desc); spin_lock_irqsave(&gpio_dev->lock, flags); reg = readl(gpio_dev->base + WAKE_INT_MASTER_REG); diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c index bae0012ee356..b0fde0f385e6 100644 --- a/drivers/pinctrl/pinctrl-at91.c +++ b/drivers/pinctrl/pinctrl-at91.c @@ -1585,7 +1585,7 @@ static struct irq_chip gpio_irqchip = { .irq_set_wake = gpio_irq_set_wake, }; -static void gpio_irq_handler(unsigned irq, struct irq_desc *desc) +static void gpio_irq_handler(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct gpio_chip *gpio_chip = irq_desc_get_handler_data(desc); diff --git a/drivers/pinctrl/pinctrl-coh901.c b/drivers/pinctrl/pinctrl-coh901.c index 3731cc67a88b..9c9b88934bcc 100644 --- a/drivers/pinctrl/pinctrl-coh901.c +++ b/drivers/pinctrl/pinctrl-coh901.c @@ -519,7 +519,7 @@ static struct irq_chip u300_gpio_irqchip = { .irq_set_type = u300_gpio_irq_type, }; -static void u300_gpio_irq_handler(unsigned __irq, struct irq_desc *desc) +static void u300_gpio_irq_handler(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct irq_chip *parent_chip = irq_desc_get_chip(desc); diff --git a/drivers/pinctrl/pinctrl-pistachio.c b/drivers/pinctrl/pinctrl-pistachio.c index f22d585d9300..952b1c623887 100644 --- a/drivers/pinctrl/pinctrl-pistachio.c +++ b/drivers/pinctrl/pinctrl-pistachio.c @@ -1310,13 +1310,11 @@ static int pistachio_gpio_irq_set_type(struct irq_data *data, unsigned int type) return 0; } -static void pistachio_gpio_irq_handler(unsigned int __irq, - struct irq_desc *desc) +static void pistachio_gpio_irq_handler(struct irq_desc *desc) { - unsigned int irq = irq_desc_get_irq(desc); struct gpio_chip *gc = irq_desc_get_handler_data(desc); struct pistachio_gpio_bank *bank = gc_to_bank(gc); - struct irq_chip *chip = irq_get_chip(irq); + struct irq_chip *chip = irq_desc_get_chip(desc); unsigned long pending; unsigned int pin; diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index c5246c05f70c..88bb707e107a 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -1475,7 +1475,7 @@ static const struct gpio_chip rockchip_gpiolib_chip = { * Interrupt handling */ -static void rockchip_irq_demux(unsigned int __irq, struct irq_desc *desc) +static void rockchip_irq_demux(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct rockchip_pin_bank *bank = irq_desc_get_handler_data(desc); diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index bf548c2a7a9d..ef04b962c3d5 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -1679,7 +1679,7 @@ static irqreturn_t pcs_irq_handler(int irq, void *d) * Use this if you have a separate interrupt for each * pinctrl-single instance. */ -static void pcs_irq_chain_handler(unsigned int irq, struct irq_desc *desc) +static void pcs_irq_chain_handler(struct irq_desc *desc) { struct pcs_soc_data *pcs_soc = irq_desc_get_handler_data(desc); struct irq_chip *chip; diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c index f8338d2e6b6b..389526e704fb 100644 --- a/drivers/pinctrl/pinctrl-st.c +++ b/drivers/pinctrl/pinctrl-st.c @@ -1460,7 +1460,7 @@ static void __gpio_irq_handler(struct st_gpio_bank *bank) } } -static void st_gpio_irq_handler(unsigned irq, struct irq_desc *desc) +static void st_gpio_irq_handler(struct irq_desc *desc) { /* interrupt dedicated per bank */ struct irq_chip *chip = irq_desc_get_chip(desc); @@ -1472,7 +1472,7 @@ static void st_gpio_irq_handler(unsigned irq, struct irq_desc *desc) chained_irq_exit(chip, desc); } -static void st_gpio_irqmux_handler(unsigned irq, struct irq_desc *desc) +static void st_gpio_irqmux_handler(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct st_pinctrl *info = irq_desc_get_handler_data(desc); diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 492cdd51dc5c..a0c7407c1cac 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -765,9 +765,8 @@ static struct irq_chip msm_gpio_irq_chip = { .irq_set_wake = msm_gpio_irq_set_wake, }; -static void msm_gpio_irq_handler(unsigned int __irq, struct irq_desc *desc) +static void msm_gpio_irq_handler(struct irq_desc *desc) { - unsigned int irq = irq_desc_get_irq(desc); struct gpio_chip *gc = irq_desc_get_handler_data(desc); const struct msm_pingroup *g; struct msm_pinctrl *pctrl = to_msm_pinctrl(gc); @@ -795,7 +794,7 @@ static void msm_gpio_irq_handler(unsigned int __irq, struct irq_desc *desc) /* No interrupts were flagged */ if (handled == 0) - handle_bad_irq(irq, desc); + handle_bad_irq(desc); chained_irq_exit(chip, desc); } diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c index 5f45caaef46d..71ccf6a90b22 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos.c @@ -419,7 +419,7 @@ static const struct of_device_id exynos_wkup_irq_ids[] = { }; /* interrupt handler for wakeup interrupts 0..15 */ -static void exynos_irq_eint0_15(unsigned int irq, struct irq_desc *desc) +static void exynos_irq_eint0_15(struct irq_desc *desc) { struct exynos_weint_data *eintd = irq_desc_get_handler_data(desc); struct samsung_pin_bank *bank = eintd->bank; @@ -451,7 +451,7 @@ static inline void exynos_irq_demux_eint(unsigned long pend, } /* interrupt handler for wakeup interrupt 16 */ -static void exynos_irq_demux_eint16_31(unsigned int irq, struct irq_desc *desc) +static void exynos_irq_demux_eint16_31(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct exynos_muxed_weint_data *eintd = irq_desc_get_handler_data(desc); diff --git a/drivers/pinctrl/samsung/pinctrl-s3c24xx.c b/drivers/pinctrl/samsung/pinctrl-s3c24xx.c index 019844d479bb..b3cd9ae3f4a2 100644 --- a/drivers/pinctrl/samsung/pinctrl-s3c24xx.c +++ b/drivers/pinctrl/samsung/pinctrl-s3c24xx.c @@ -240,7 +240,7 @@ static struct irq_chip s3c2410_eint0_3_chip = { .irq_set_type = s3c24xx_eint_type, }; -static void s3c2410_demux_eint0_3(unsigned int irq, struct irq_desc *desc) +static void s3c2410_demux_eint0_3(struct irq_desc *desc) { struct irq_data *data = irq_desc_get_irq_data(desc); struct s3c24xx_eint_data *eint_data = irq_desc_get_handler_data(desc); @@ -295,7 +295,7 @@ static struct irq_chip s3c2412_eint0_3_chip = { .irq_set_type = s3c24xx_eint_type, }; -static void s3c2412_demux_eint0_3(unsigned int irq, struct irq_desc *desc) +static void s3c2412_demux_eint0_3(struct irq_desc *desc) { struct s3c24xx_eint_data *eint_data = irq_desc_get_handler_data(desc); struct irq_data *data = irq_desc_get_irq_data(desc); @@ -388,12 +388,12 @@ static inline void s3c24xx_demux_eint(struct irq_desc *desc, chained_irq_exit(chip, desc); } -static void s3c24xx_demux_eint4_7(unsigned int irq, struct irq_desc *desc) +static void s3c24xx_demux_eint4_7(struct irq_desc *desc) { s3c24xx_demux_eint(desc, 0, 0xf0); } -static void s3c24xx_demux_eint8_23(unsigned int irq, struct irq_desc *desc) +static void s3c24xx_demux_eint8_23(struct irq_desc *desc) { s3c24xx_demux_eint(desc, 8, 0xffff00); } diff --git a/drivers/pinctrl/samsung/pinctrl-s3c64xx.c b/drivers/pinctrl/samsung/pinctrl-s3c64xx.c index f5ea40a69711..43407ab248f5 100644 --- a/drivers/pinctrl/samsung/pinctrl-s3c64xx.c +++ b/drivers/pinctrl/samsung/pinctrl-s3c64xx.c @@ -407,7 +407,7 @@ static const struct irq_domain_ops s3c64xx_gpio_irqd_ops = { .xlate = irq_domain_xlate_twocell, }; -static void s3c64xx_eint_gpio_irq(unsigned int irq, struct irq_desc *desc) +static void s3c64xx_eint_gpio_irq(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct s3c64xx_eint_gpio_data *data = irq_desc_get_handler_data(desc); @@ -631,22 +631,22 @@ static inline void s3c64xx_irq_demux_eint(struct irq_desc *desc, u32 range) chained_irq_exit(chip, desc); } -static void s3c64xx_demux_eint0_3(unsigned int irq, struct irq_desc *desc) +static void s3c64xx_demux_eint0_3(struct irq_desc *desc) { s3c64xx_irq_demux_eint(desc, 0xf); } -static void s3c64xx_demux_eint4_11(unsigned int irq, struct irq_desc *desc) +static void s3c64xx_demux_eint4_11(struct irq_desc *desc) { s3c64xx_irq_demux_eint(desc, 0xff0); } -static void s3c64xx_demux_eint12_19(unsigned int irq, struct irq_desc *desc) +static void s3c64xx_demux_eint12_19(struct irq_desc *desc) { s3c64xx_irq_demux_eint(desc, 0xff000); } -static void s3c64xx_demux_eint20_27(unsigned int irq, struct irq_desc *desc) +static void s3c64xx_demux_eint20_27(struct irq_desc *desc) { s3c64xx_irq_demux_eint(desc, 0xff00000); } diff --git a/drivers/pinctrl/sirf/pinctrl-atlas7.c b/drivers/pinctrl/sirf/pinctrl-atlas7.c index 9df0c5f25824..0d24d9e4b70c 100644 --- a/drivers/pinctrl/sirf/pinctrl-atlas7.c +++ b/drivers/pinctrl/sirf/pinctrl-atlas7.c @@ -4489,7 +4489,7 @@ static struct irq_chip atlas7_gpio_irq_chip = { .irq_set_type = atlas7_gpio_irq_type, }; -static void atlas7_gpio_handle_irq(unsigned int __irq, struct irq_desc *desc) +static void atlas7_gpio_handle_irq(struct irq_desc *desc) { struct gpio_chip *gc = irq_desc_get_handler_data(desc); struct atlas7_gpio_chip *a7gc = to_atlas7_gpio(gc); @@ -4512,7 +4512,7 @@ static void atlas7_gpio_handle_irq(unsigned int __irq, struct irq_desc *desc) if (!status) { pr_warn("%s: gpio [%s] status %#x no interrupt is flaged\n", __func__, gc->label, status); - handle_bad_irq(irq, desc); + handle_bad_irq(desc); return; } diff --git a/drivers/pinctrl/sirf/pinctrl-sirf.c b/drivers/pinctrl/sirf/pinctrl-sirf.c index f8bd9fb52033..2a8d69725de8 100644 --- a/drivers/pinctrl/sirf/pinctrl-sirf.c +++ b/drivers/pinctrl/sirf/pinctrl-sirf.c @@ -545,7 +545,7 @@ static struct irq_chip sirfsoc_irq_chip = { .irq_set_type = sirfsoc_gpio_irq_type, }; -static void sirfsoc_gpio_handle_irq(unsigned int __irq, struct irq_desc *desc) +static void sirfsoc_gpio_handle_irq(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct gpio_chip *gc = irq_desc_get_handler_data(desc); @@ -570,7 +570,7 @@ static void sirfsoc_gpio_handle_irq(unsigned int __irq, struct irq_desc *desc) printk(KERN_WARNING "%s: gpio id %d status %#x no interrupt is flagged\n", __func__, bank->id, status); - handle_bad_irq(irq, desc); + handle_bad_irq(desc); return; } diff --git a/drivers/pinctrl/spear/pinctrl-plgpio.c b/drivers/pinctrl/spear/pinctrl-plgpio.c index ae8f29fb5536..1f0af250dbb5 100644 --- a/drivers/pinctrl/spear/pinctrl-plgpio.c +++ b/drivers/pinctrl/spear/pinctrl-plgpio.c @@ -356,7 +356,7 @@ static struct irq_chip plgpio_irqchip = { .irq_set_type = plgpio_irq_set_type, }; -static void plgpio_irq_handler(unsigned irq, struct irq_desc *desc) +static void plgpio_irq_handler(struct irq_desc *desc) { struct gpio_chip *gc = irq_desc_get_handler_data(desc); struct plgpio *plgpio = container_of(gc, struct plgpio, chip); diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index 31af97d89272..38e0c7bdd2ac 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -740,7 +740,7 @@ static struct irq_domain_ops sunxi_pinctrl_irq_domain_ops = { .xlate = sunxi_pinctrl_irq_of_xlate, }; -static void sunxi_pinctrl_irq_handler(unsigned __irq, struct irq_desc *desc) +static void sunxi_pinctrl_irq_handler(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct irq_chip *chip = irq_desc_get_chip(desc); diff --git a/drivers/sh/intc/core.c b/drivers/sh/intc/core.c index 043419dcee92..8e72bcbd3d6d 100644 --- a/drivers/sh/intc/core.c +++ b/drivers/sh/intc/core.c @@ -65,7 +65,7 @@ void intc_set_prio_level(unsigned int irq, unsigned int level) raw_spin_unlock_irqrestore(&intc_big_lock, flags); } -static void intc_redirect_irq(unsigned int irq, struct irq_desc *desc) +static void intc_redirect_irq(struct irq_desc *desc) { generic_handle_irq((unsigned int)irq_desc_get_handler_data(desc)); } diff --git a/drivers/sh/intc/virq.c b/drivers/sh/intc/virq.c index bafc51c6f0ba..e7899624aa0b 100644 --- a/drivers/sh/intc/virq.c +++ b/drivers/sh/intc/virq.c @@ -109,7 +109,7 @@ static int add_virq_to_pirq(unsigned int irq, unsigned int virq) return 0; } -static void intc_virq_handler(unsigned int __irq, struct irq_desc *desc) +static void intc_virq_handler(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct irq_data *data = irq_desc_get_irq_data(desc); @@ -127,7 +127,7 @@ static void intc_virq_handler(unsigned int __irq, struct irq_desc *desc) handle = (unsigned long)irq_desc_get_handler_data(vdesc); addr = INTC_REG(d, _INTC_ADDR_E(handle), 0); if (intc_reg_fns[_INTC_FN(handle)](addr, handle, 0)) - generic_handle_irq_desc(entry->irq, vdesc); + generic_handle_irq_desc(vdesc); } } diff --git a/drivers/soc/dove/pmu.c b/drivers/soc/dove/pmu.c index 6bc13f99489a..052aecf29893 100644 --- a/drivers/soc/dove/pmu.c +++ b/drivers/soc/dove/pmu.c @@ -222,7 +222,7 @@ static void __pmu_domain_register(struct pmu_domain *domain, } /* PMU IRQ controller */ -static void pmu_irq_handler(unsigned int irq, struct irq_desc *desc) +static void pmu_irq_handler(struct irq_desc *desc) { struct pmu_data *pmu = irq_desc_get_handler_data(desc); struct irq_chip_generic *gc = pmu->irq_gc; @@ -232,7 +232,7 @@ static void pmu_irq_handler(unsigned int irq, struct irq_desc *desc) u32 done = ~0; if (stat == 0) { - handle_bad_irq(irq_desc_get_irq(desc), desc); + handle_bad_irq(desc); return; } diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c index bdfb3c84c3cb..4a3cf9ba152f 100644 --- a/drivers/spmi/spmi-pmic-arb.c +++ b/drivers/spmi/spmi-pmic-arb.c @@ -451,7 +451,7 @@ static void periph_interrupt(struct spmi_pmic_arb_dev *pa, u8 apid) } } -static void pmic_arb_chained_irq(unsigned int irq, struct irq_desc *desc) +static void pmic_arb_chained_irq(struct irq_desc *desc) { struct spmi_pmic_arb_dev *pa = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); diff --git a/include/linux/irq.h b/include/linux/irq.h index 4913c32db942..11bf09288ddb 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -475,14 +475,14 @@ static inline int irq_set_parent(int irq, int parent_irq) * Built-in IRQ handlers for various IRQ types, * callable via desc->handle_irq() */ -extern void handle_level_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_edge_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_simple_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_percpu_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc); +extern void handle_level_irq(struct irq_desc *desc); +extern void handle_fasteoi_irq(struct irq_desc *desc); +extern void handle_edge_irq(struct irq_desc *desc); +extern void handle_edge_eoi_irq(struct irq_desc *desc); +extern void handle_simple_irq(struct irq_desc *desc); +extern void handle_percpu_irq(struct irq_desc *desc); +extern void handle_percpu_devid_irq(struct irq_desc *desc); +extern void handle_bad_irq(struct irq_desc *desc); extern void handle_nested_irq(unsigned int irq); extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index fbb4d5afc32b..a587a33363c7 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -135,9 +135,9 @@ static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) * Architectures call this to let the generic IRQ layer * handle an interrupt. */ -static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc) +static inline void generic_handle_irq_desc(struct irq_desc *desc) { - desc->handle_irq(irq, desc); + desc->handle_irq(desc); } int generic_handle_irq(unsigned int irq); diff --git a/include/linux/irqhandler.h b/include/linux/irqhandler.h index 62d543004197..661bed0ed1f3 100644 --- a/include/linux/irqhandler.h +++ b/include/linux/irqhandler.h @@ -8,7 +8,7 @@ struct irq_desc; struct irq_data; -typedef void (*irq_flow_handler_t)(unsigned int irq, struct irq_desc *desc); +typedef void (*irq_flow_handler_t)(struct irq_desc *desc); typedef void (*irq_preflow_handler_t)(struct irq_data *data); #endif diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 8c55d545558f..e28169dd1c36 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -372,7 +372,6 @@ static bool irq_may_run(struct irq_desc *desc) /** * handle_simple_irq - Simple and software-decoded IRQs. - * @irq: the interrupt number * @desc: the interrupt description structure for this irq * * Simple interrupts are either sent from a demultiplexing interrupt @@ -382,8 +381,7 @@ static bool irq_may_run(struct irq_desc *desc) * Note: The caller is expected to handle the ack, clear, mask and * unmask issues if necessary. */ -void -handle_simple_irq(unsigned int irq, struct irq_desc *desc) +void handle_simple_irq(struct irq_desc *desc) { raw_spin_lock(&desc->lock); @@ -425,7 +423,6 @@ static void cond_unmask_irq(struct irq_desc *desc) /** * handle_level_irq - Level type irq handler - * @irq: the interrupt number * @desc: the interrupt description structure for this irq * * Level type interrupts are active as long as the hardware line has @@ -433,8 +430,7 @@ static void cond_unmask_irq(struct irq_desc *desc) * it after the associated handler has acknowledged the device, so the * interrupt line is back to inactive. */ -void -handle_level_irq(unsigned int irq, struct irq_desc *desc) +void handle_level_irq(struct irq_desc *desc) { raw_spin_lock(&desc->lock); mask_ack_irq(desc); @@ -496,7 +492,6 @@ static void cond_unmask_eoi_irq(struct irq_desc *desc, struct irq_chip *chip) /** * handle_fasteoi_irq - irq handler for transparent controllers - * @irq: the interrupt number * @desc: the interrupt description structure for this irq * * Only a single callback will be issued to the chip: an ->eoi() @@ -504,8 +499,7 @@ static void cond_unmask_eoi_irq(struct irq_desc *desc, struct irq_chip *chip) * for modern forms of interrupt handlers, which handle the flow * details in hardware, transparently. */ -void -handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc) +void handle_fasteoi_irq(struct irq_desc *desc) { struct irq_chip *chip = desc->irq_data.chip; @@ -546,7 +540,6 @@ EXPORT_SYMBOL_GPL(handle_fasteoi_irq); /** * handle_edge_irq - edge type IRQ handler - * @irq: the interrupt number * @desc: the interrupt description structure for this irq * * Interrupt occures on the falling and/or rising edge of a hardware @@ -560,8 +553,7 @@ EXPORT_SYMBOL_GPL(handle_fasteoi_irq); * the handler was running. If all pending interrupts are handled, the * loop is left. */ -void -handle_edge_irq(unsigned int irq, struct irq_desc *desc) +void handle_edge_irq(struct irq_desc *desc) { raw_spin_lock(&desc->lock); @@ -618,13 +610,12 @@ EXPORT_SYMBOL(handle_edge_irq); #ifdef CONFIG_IRQ_EDGE_EOI_HANDLER /** * handle_edge_eoi_irq - edge eoi type IRQ handler - * @irq: the interrupt number * @desc: the interrupt description structure for this irq * * Similar as the above handle_edge_irq, but using eoi and w/o the * mask/unmask logic. */ -void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc) +void handle_edge_eoi_irq(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); @@ -665,13 +656,11 @@ out_eoi: /** * handle_percpu_irq - Per CPU local irq handler - * @irq: the interrupt number * @desc: the interrupt description structure for this irq * * Per CPU interrupts on SMP machines without locking requirements */ -void -handle_percpu_irq(unsigned int irq, struct irq_desc *desc) +void handle_percpu_irq(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); @@ -688,7 +677,6 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc) /** * handle_percpu_devid_irq - Per CPU local irq handler with per cpu dev ids - * @irq: the interrupt number * @desc: the interrupt description structure for this irq * * Per CPU interrupts on SMP machines without locking requirements. Same as @@ -698,11 +686,12 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc) * contain the real device id for the cpu on which this handler is * called */ -void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc) +void handle_percpu_devid_irq(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct irqaction *action = desc->action; void *dev_id = raw_cpu_ptr(action->percpu_dev_id); + unsigned int irq = irq_desc_get_irq(desc); irqreturn_t res; kstat_incr_irqs_this_cpu(desc); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index b6eeea8a80c5..de41a68fc038 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -27,8 +27,10 @@ * * Handles spurious and unhandled IRQ's. It also prints a debugmessage. */ -void handle_bad_irq(unsigned int irq, struct irq_desc *desc) +void handle_bad_irq(struct irq_desc *desc) { + unsigned int irq = irq_desc_get_irq(desc); + print_irq_desc(irq, desc); kstat_incr_irqs_this_cpu(desc); ack_bad_irq(irq); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 596669436f7a..239e2ae2c947 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -347,7 +347,7 @@ int generic_handle_irq(unsigned int irq) if (!desc) return -EINVAL; - generic_handle_irq_desc(irq, desc); + generic_handle_irq_desc(desc); return 0; } EXPORT_SYMBOL_GPL(generic_handle_irq); diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c index dd95f44f99b2..b86886beee4f 100644 --- a/kernel/irq/resend.c +++ b/kernel/irq/resend.c @@ -38,7 +38,7 @@ static void resend_irqs(unsigned long arg) clear_bit(irq, irqs_resend); desc = irq_to_desc(irq); local_irq_disable(); - desc->handle_irq(irq, desc); + desc->handle_irq(desc); local_irq_enable(); } } -- cgit v1.2.3 From 0c986253b939cc14c69d4adbe2b4121bdf4aa220 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 16 Sep 2015 11:51:12 -0400 Subject: Revert "sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem" This reverts commit d59cfc09c32a2ae31f1c3bc2983a0cd79afb3f14. d59cfc09c32a ("sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem") and b5ba75b5fc0e ("cgroup: simplify threadgroup locking") changed how cgroup synchronizes against task fork and exits so that it uses global percpu_rwsem instead of per-process rwsem; unfortunately, the write [un]lock paths of percpu_rwsem always involve synchronize_rcu_expedited() which turned out to be too expensive. Improvements for percpu_rwsem are scheduled to be merged in the coming v4.4-rc1 merge window which alleviates this issue. For now, revert the two commits to restore per-process rwsem. They will be re-applied for the v4.4-rc1 merge window. Signed-off-by: Tejun Heo Link: http://lkml.kernel.org/g/55F8097A.7000206@de.ibm.com Reported-by: Christian Borntraeger Cc: Oleg Nesterov Cc: "Paul E. McKenney" Cc: Peter Zijlstra Cc: Paolo Bonzini Cc: stable@vger.kernel.org # v4.2+ --- include/linux/cgroup-defs.h | 27 ++-------------- include/linux/init_task.h | 8 +++++ include/linux/sched.h | 12 +++++++ kernel/cgroup.c | 77 +++++++++++++++++++++++++++++++++------------ kernel/fork.c | 4 +++ 5 files changed, 83 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4d8fcf2187dc..8492721b39be 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -473,31 +473,8 @@ struct cgroup_subsys { unsigned int depends_on; }; -extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; - -/** - * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups - * @tsk: target task - * - * Called from threadgroup_change_begin() and allows cgroup operations to - * synchronize against threadgroup changes using a percpu_rw_semaphore. - */ -static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) -{ - percpu_down_read(&cgroup_threadgroup_rwsem); -} - -/** - * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups - * @tsk: target task - * - * Called from threadgroup_change_end(). Counterpart of - * cgroup_threadcgroup_change_begin(). - */ -static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) -{ - percpu_up_read(&cgroup_threadgroup_rwsem); -} +void cgroup_threadgroup_change_begin(struct task_struct *tsk); +void cgroup_threadgroup_change_end(struct task_struct *tsk); #else /* CONFIG_CGROUPS */ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index d0b380ee7d67..e38681f4912d 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -25,6 +25,13 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; +#ifdef CONFIG_CGROUPS +#define INIT_GROUP_RWSEM(sig) \ + .group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem), +#else +#define INIT_GROUP_RWSEM(sig) +#endif + #ifdef CONFIG_CPUSETS #define INIT_CPUSET_SEQ(tsk) \ .mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq), @@ -57,6 +64,7 @@ extern struct fs_struct init_fs; INIT_PREV_CPUTIME(sig) \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ + INIT_GROUP_RWSEM(sig) \ } extern struct nsproxy init_nsproxy; diff --git a/include/linux/sched.h b/include/linux/sched.h index a4ab9daa387c..b7b9501b41af 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -762,6 +762,18 @@ struct signal_struct { unsigned audit_tty_log_passwd; struct tty_audit_buf *tty_audit_buf; #endif +#ifdef CONFIG_CGROUPS + /* + * group_rwsem prevents new tasks from entering the threadgroup and + * member tasks from exiting,a more specifically, setting of + * PF_EXITING. fork and exit paths are protected with this rwsem + * using threadgroup_change_begin/end(). Users which require + * threadgroup to remain stable should use threadgroup_[un]lock() + * which also takes care of exec path. Currently, cgroup is the + * only user. + */ + struct rw_semaphore group_rwsem; +#endif oom_flags_t oom_flags; short oom_score_adj; /* OOM kill score adjustment */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 115091efa889..2c9eae6ad970 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -46,7 +46,6 @@ #include #include #include -#include #include #include #include @@ -104,8 +103,6 @@ static DEFINE_SPINLOCK(cgroup_idr_lock); */ static DEFINE_SPINLOCK(release_agent_path_lock); -struct percpu_rw_semaphore cgroup_threadgroup_rwsem; - #define cgroup_assert_mutex_or_rcu_locked() \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&cgroup_mutex), \ @@ -874,6 +871,48 @@ static struct css_set *find_css_set(struct css_set *old_cset, return cset; } +void cgroup_threadgroup_change_begin(struct task_struct *tsk) +{ + down_read(&tsk->signal->group_rwsem); +} + +void cgroup_threadgroup_change_end(struct task_struct *tsk) +{ + up_read(&tsk->signal->group_rwsem); +} + +/** + * threadgroup_lock - lock threadgroup + * @tsk: member task of the threadgroup to lock + * + * Lock the threadgroup @tsk belongs to. No new task is allowed to enter + * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or + * change ->group_leader/pid. This is useful for cases where the threadgroup + * needs to stay stable across blockable operations. + * + * fork and exit explicitly call threadgroup_change_{begin|end}() for + * synchronization. While held, no new task will be added to threadgroup + * and no existing live task will have its PF_EXITING set. + * + * de_thread() does threadgroup_change_{begin|end}() when a non-leader + * sub-thread becomes a new leader. + */ +static void threadgroup_lock(struct task_struct *tsk) +{ + down_write(&tsk->signal->group_rwsem); +} + +/** + * threadgroup_unlock - unlock threadgroup + * @tsk: member task of the threadgroup to unlock + * + * Reverse threadgroup_lock(). + */ +static inline void threadgroup_unlock(struct task_struct *tsk) +{ + up_write(&tsk->signal->group_rwsem); +} + static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) { struct cgroup *root_cgrp = kf_root->kn->priv; @@ -2074,9 +2113,9 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp, lockdep_assert_held(&css_set_rwsem); /* - * We are synchronized through cgroup_threadgroup_rwsem against - * PF_EXITING setting such that we can't race against cgroup_exit() - * changing the css_set to init_css_set and dropping the old one. + * We are synchronized through threadgroup_lock() against PF_EXITING + * setting such that we can't race against cgroup_exit() changing the + * css_set to init_css_set and dropping the old one. */ WARN_ON_ONCE(tsk->flags & PF_EXITING); old_cset = task_css_set(tsk); @@ -2133,11 +2172,10 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets) * @src_cset and add it to @preloaded_csets, which should later be cleaned * up by cgroup_migrate_finish(). * - * This function may be called without holding cgroup_threadgroup_rwsem - * even if the target is a process. Threads may be created and destroyed - * but as long as cgroup_mutex is not dropped, no new css_set can be put - * into play and the preloaded css_sets are guaranteed to cover all - * migrations. + * This function may be called without holding threadgroup_lock even if the + * target is a process. Threads may be created and destroyed but as long + * as cgroup_mutex is not dropped, no new css_set can be put into play and + * the preloaded css_sets are guaranteed to cover all migrations. */ static void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, @@ -2240,7 +2278,7 @@ err: * @threadgroup: whether @leader points to the whole process or a single task * * Migrate a process or task denoted by @leader to @cgrp. If migrating a - * process, the caller must be holding cgroup_threadgroup_rwsem. The + * process, the caller must be holding threadgroup_lock of @leader. The * caller is also responsible for invoking cgroup_migrate_add_src() and * cgroup_migrate_prepare_dst() on the targets before invoking this * function and following up with cgroup_migrate_finish(). @@ -2368,7 +2406,7 @@ out_release_tset: * @leader: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * - * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. + * Call holding cgroup_mutex and threadgroup_lock of @leader. */ static int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup) @@ -2490,7 +2528,7 @@ retry_find_task: get_task_struct(tsk); rcu_read_unlock(); - percpu_down_write(&cgroup_threadgroup_rwsem); + threadgroup_lock(tsk); if (threadgroup) { if (!thread_group_leader(tsk)) { /* @@ -2500,7 +2538,7 @@ retry_find_task: * try again; this is * "double-double-toil-and-trouble-check locking". */ - percpu_up_write(&cgroup_threadgroup_rwsem); + threadgroup_unlock(tsk); put_task_struct(tsk); goto retry_find_task; } @@ -2510,7 +2548,7 @@ retry_find_task: if (!ret) ret = cgroup_attach_task(cgrp, tsk, threadgroup); - percpu_up_write(&cgroup_threadgroup_rwsem); + threadgroup_unlock(tsk); put_task_struct(tsk); out_unlock_cgroup: @@ -2713,17 +2751,17 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) goto out_finish; last_task = task; - percpu_down_write(&cgroup_threadgroup_rwsem); + threadgroup_lock(task); /* raced against de_thread() from another thread? */ if (!thread_group_leader(task)) { - percpu_up_write(&cgroup_threadgroup_rwsem); + threadgroup_unlock(task); put_task_struct(task); continue; } ret = cgroup_migrate(src_cset->dfl_cgrp, task, true); - percpu_up_write(&cgroup_threadgroup_rwsem); + threadgroup_unlock(task); put_task_struct(task); if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret)) @@ -5045,7 +5083,6 @@ int __init cgroup_init(void) unsigned long key; int ssid, err; - BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files)); diff --git a/kernel/fork.c b/kernel/fork.c index 7d5f0f118a63..2845623fb582 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1149,6 +1149,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) tty_audit_fork(sig); sched_autogroup_fork(sig); +#ifdef CONFIG_CGROUPS + init_rwsem(&sig->group_rwsem); +#endif + sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; -- cgit v1.2.3 From 0243ed44ad4a25dbd2e92ad97e5e12a1a6c72d6c Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Tue, 15 Sep 2015 04:59:21 -0700 Subject: spi: fix kernel-doc warnings in spi.h Fix the following 'make htmldocs' warnings: .//include/linux/spi/spi.h:71: warning: No description found for parameter 'lock' .//include/linux/spi/spi.h:71: warning: Excess struct/union/enum/typedef member 'clock' description in 'spi_statistics' Signed-off-by: Geliang Tang Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 269e8afd3e2a..6b00f18f5e6b 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -34,7 +34,7 @@ extern struct bus_type spi_bus_type; /** * struct spi_statistics - statistics for spi transfers - * @clock: lock protecting this structure + * @lock: lock protecting this structure * * @messages: number of spi-messages handled * @transfers: number of spi_transfers handled -- cgit v1.2.3 From 4e478098ac0ac1b6ef9a70fcdc2ec8b93f1b59a1 Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Mon, 14 Sep 2015 23:23:05 -0700 Subject: ipvs: add sysctl to ignore tunneled packets This is a way to avoid nasty routing loops when multiple ipvs instances can forward to eachother. Signed-off-by: Alex Gartrell Signed-off-by: Simon Horman --- Documentation/networking/ipvs-sysctl.txt | 10 ++++++++++ include/net/ip_vs.h | 11 +++++++++++ net/netfilter/ipvs/ip_vs_core.c | 10 +++++++++- net/netfilter/ipvs/ip_vs_ctl.c | 7 +++++++ 4 files changed, 37 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt index 3ba709531adb..e6b1c025fdd8 100644 --- a/Documentation/networking/ipvs-sysctl.txt +++ b/Documentation/networking/ipvs-sysctl.txt @@ -157,6 +157,16 @@ expire_quiescent_template - BOOLEAN persistence template if it is to be used to schedule a new connection and the destination server is quiescent. +ignore_tunneled - BOOLEAN + 0 - disabled (default) + not 0 - enabled + + If set, ipvs will set the ipvs_property on all packets which are of + unrecognized protocols. This prevents us from routing tunneled + protocols like ipip, which is useful to prevent rescheduling + packets that have been tunneled to the ipvs host (i.e. to prevent + ipvs routing loops when ipvs is also acting as a real server). + nat_icmp_send - BOOLEAN 0 - disabled (default) not 0 - enabled diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 47677f0493c7..1096a71ab6ed 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -998,6 +998,7 @@ struct netns_ipvs { int sysctl_backup_only; int sysctl_conn_reuse_mode; int sysctl_schedule_icmp; + int sysctl_ignore_tunneled; /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1121,6 +1122,11 @@ static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) return ipvs->sysctl_schedule_icmp; } +static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_ignore_tunneled; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1198,6 +1204,11 @@ static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) return 0; } +static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs) +{ + return 0; +} + #endif /* IPVS core functions diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 99be6801c795..453972c6909e 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1760,8 +1760,16 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) /* Protocol supported? */ pd = ip_vs_proto_data_get(net, iph.protocol); - if (unlikely(!pd)) + if (unlikely(!pd)) { + /* The only way we'll see this packet again is if it's + * encapsulated, so mark it with ipvs_property=1 so we + * skip it if we're ignoring tunneled packets + */ + if (sysctl_ignore_tunneled(ipvs)) + skb->ipvs_property = 1; + return NF_ACCEPT; + } pp = pd->pp; /* * Check if the packet belongs to an existing connection entry diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 31d80e203863..7338827ee5e9 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1850,6 +1850,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "ignore_tunneled", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -3902,6 +3908,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) ipvs->sysctl_conn_reuse_mode = 1; tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode; tbl[idx++].data = &ipvs->sysctl_schedule_icmp; + tbl[idx++].data = &ipvs->sysctl_ignore_tunneled; ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); if (ipvs->sysctl_hdr == NULL) { -- cgit v1.2.3 From 6f558b70fb39fc8272fc513ecf191b3ad87d867b Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Sun, 30 Aug 2015 18:16:55 +0200 Subject: Bluetooth: Add bt_dev logging macros Add specific bluetooth device logging macros since hci device name is repeatedly referred in bluetooth subsystem logs. Signed-off-by: Loic Poulain Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 38d8a34d3589..fcf2ae7dbfa0 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -128,6 +128,13 @@ void bt_err(const char *fmt, ...); #define BT_ERR(fmt, ...) bt_err(fmt "\n", ##__VA_ARGS__) #define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__) +#define bt_dev_info(hdev, fmt, ...) \ + BT_INFO("%s: " fmt, (hdev)->name, ##__VA_ARGS__) +#define bt_dev_err(hdev, fmt, ...) \ + BT_ERR("%s: " fmt, (hdev)->name, ##__VA_ARGS__) +#define bt_dev_dbg(hdev, fmt, ...) \ + BT_DBG("%s: " fmt, (hdev)->name, ##__VA_ARGS__) + /* Connection and socket states */ enum { BT_CONNECTED = 1, /* Equal to TCP_ESTABLISHED to make net code happy */ -- cgit v1.2.3 From 6b3cc1db68ac83647d37f7d16f0261621eda24aa Mon Sep 17 00:00:00 2001 From: Simon Fels Date: Wed, 2 Sep 2015 12:10:12 +0200 Subject: Bluetooth: close HCI device when user channel socket gets closed With 9380f9eacfbbee701daa416edd6625efcd3e29e1 the order of unsetting the HCI_USER_CHANNEL flag of the HCI device was reverted to ensure the device is first closed before making it available again. Due to hci_dev_close checking for HCI_USER_CHANNEL being set on the device it was never really closed and was kept opened. We're now calling hci_dev_do_close directly to make sure the device is correctly closed and we keep the correct order to unset the flag on our device object. Signed-off-by: Simon Fels Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 1 + net/bluetooth/hci_core.c | 2 +- net/bluetooth/hci_sock.c | 11 ++++++++++- 3 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 9e1a59e01fa2..256e6734c1fb 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -987,6 +987,7 @@ int hci_resume_dev(struct hci_dev *hdev); int hci_reset_dev(struct hci_dev *hdev); int hci_dev_open(__u16 dev); int hci_dev_close(__u16 dev); +int hci_dev_do_close(struct hci_dev *hdev); int hci_dev_reset(__u16 dev); int hci_dev_reset_stat(__u16 dev); int hci_dev_cmd(unsigned int cmd, void __user *arg); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 5a3602046a8b..a7cdd99ec3f1 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1549,7 +1549,7 @@ static void hci_pend_le_actions_clear(struct hci_dev *hdev) BT_DBG("All LE pending actions cleared"); } -static int hci_dev_do_close(struct hci_dev *hdev) +int hci_dev_do_close(struct hci_dev *hdev) { BT_DBG("%s %p", hdev->name, hdev); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index f2d30d1156c9..150556345263 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -503,7 +503,16 @@ static int hci_sock_release(struct socket *sock) if (hdev) { if (hci_pi(sk)->channel == HCI_CHANNEL_USER) { - hci_dev_close(hdev->id); + /* When releasing an user channel exclusive access, + * call hci_dev_do_close directly instead of calling + * hci_dev_close to ensure the exclusive access will + * be released and the controller brought back down. + * + * The checking of HCI_AUTO_OFF is not needed in this + * case since it will have been cleared already when + * opening the user channel. + */ + hci_dev_do_close(hdev); hci_dev_clear_flag(hdev, HCI_USER_CHANNEL); mgmt_index_added(hdev); } -- cgit v1.2.3 From 72a5e6bb5120d6464c9e7855c5a22555ede819dc Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 2 Sep 2015 14:21:25 +0200 Subject: ieee820154: 6lowpan: dispatch evaluation rework This patch complete reworks the evaluation of 6lowpan dispatch value by introducing a receive handler mechanism for each dispatch value. A list of changes: - Doing uncompression on-the-fly when FRAG1 is received, this require some special handling for 802.15.4 lltype in generic 6lowpan branch for setting the payload length correct. - Fix dispatch mask for fragmentation. - Add IPv6 dispatch evaluation for FRAG1. - Add skb_unshare for dispatch which might manipulate the skb data buffer. Cc: Jukka Rissanen Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 31 ++++-- net/6lowpan/iphc.c | 13 ++- net/6lowpan/nhc_udp.c | 13 ++- net/ieee802154/6lowpan/6lowpan_i.h | 12 +++ net/ieee802154/6lowpan/reassembly.c | 142 +++++++++++++++++++-------- net/ieee802154/6lowpan/rx.c | 188 ++++++++++++++++++++++++------------ 6 files changed, 288 insertions(+), 111 deletions(-) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index a2f59ec98d24..35098411dbb4 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -126,13 +126,19 @@ (((a)[6]) == 0xFF) && \ (((a)[7]) == 0xFF)) -#define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */ -#define LOWPAN_DISPATCH_HC1 0x42 /* 01000010 = 66 */ -#define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */ -#define LOWPAN_DISPATCH_FRAG1 0xc0 /* 11000xxx */ -#define LOWPAN_DISPATCH_FRAGN 0xe0 /* 11100xxx */ +#define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */ +#define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */ +#define LOWPAN_DISPATCH_IPHC_MASK 0xe0 -#define LOWPAN_DISPATCH_MASK 0xf8 /* 11111000 */ +static inline bool lowpan_is_ipv6(u8 dispatch) +{ + return dispatch == LOWPAN_DISPATCH_IPV6; +} + +static inline bool lowpan_is_iphc(u8 dispatch) +{ + return (dispatch & LOWPAN_DISPATCH_IPHC_MASK) == LOWPAN_DISPATCH_IPHC; +} #define LOWPAN_FRAG_TIMEOUT (HZ * 60) /* time-out 60 sec */ @@ -218,6 +224,19 @@ struct lowpan_priv *lowpan_priv(const struct net_device *dev) return netdev_priv(dev); } +struct lowpan_802154_cb { + u16 d_tag; + unsigned int d_size; + u8 d_offset; +}; + +static inline +struct lowpan_802154_cb *lowpan_802154_cb(const struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct lowpan_802154_cb) > sizeof(skb->cb)); + return (struct lowpan_802154_cb *)skb->cb; +} + #ifdef DEBUG /* print data in line */ static inline void raw_dump_inline(const char *caller, char *msg, diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c index 1e0071fdcf72..78c8a495b571 100644 --- a/net/6lowpan/iphc.c +++ b/net/6lowpan/iphc.c @@ -366,7 +366,18 @@ lowpan_header_decompress(struct sk_buff *skb, struct net_device *dev, return err; } - hdr.payload_len = htons(skb->len); + switch (lowpan_priv(dev)->lltype) { + case LOWPAN_LLTYPE_IEEE802154: + if (lowpan_802154_cb(skb)->d_size) + hdr.payload_len = htons(lowpan_802154_cb(skb)->d_size - + sizeof(struct ipv6hdr)); + else + hdr.payload_len = htons(skb->len); + break; + default: + hdr.payload_len = htons(skb->len); + break; + } pr_debug("skb headroom size = %d, data length = %d\n", skb_headroom(skb), skb->len); diff --git a/net/6lowpan/nhc_udp.c b/net/6lowpan/nhc_udp.c index c6bcaeb428ae..72d0b57eb6e5 100644 --- a/net/6lowpan/nhc_udp.c +++ b/net/6lowpan/nhc_udp.c @@ -71,7 +71,18 @@ static int udp_uncompress(struct sk_buff *skb, size_t needed) * here, we obtain the hint from the remaining size of the * frame */ - uh.len = htons(skb->len + sizeof(struct udphdr)); + switch (lowpan_priv(skb->dev)->lltype) { + case LOWPAN_LLTYPE_IEEE802154: + if (lowpan_802154_cb(skb)->d_size) + uh.len = htons(lowpan_802154_cb(skb)->d_size - + sizeof(struct ipv6hdr)); + else + uh.len = htons(skb->len + sizeof(struct udphdr)); + break; + default: + uh.len = htons(skb->len + sizeof(struct udphdr)); + break; + } pr_debug("uncompressed UDP length: src = %d", ntohs(uh.len)); /* replace the compressed UDP head by the uncompressed UDP diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h index 9aa7b62b87fa..b4e17a7c0df0 100644 --- a/net/ieee802154/6lowpan/6lowpan_i.h +++ b/net/ieee802154/6lowpan/6lowpan_i.h @@ -7,6 +7,15 @@ #include #include +typedef unsigned __bitwise__ lowpan_rx_result; +#define RX_CONTINUE ((__force lowpan_rx_result) 0u) +#define RX_DROP_UNUSABLE ((__force lowpan_rx_result) 1u) +#define RX_DROP ((__force lowpan_rx_result) 2u) +#define RX_QUEUED ((__force lowpan_rx_result) 3u) + +#define LOWPAN_DISPATCH_FRAG1 0xc0 +#define LOWPAN_DISPATCH_FRAGN 0xe0 + struct lowpan_create_arg { u16 tag; u16 d_size; @@ -62,4 +71,7 @@ int lowpan_header_create(struct sk_buff *skb, struct net_device *dev, const void *_saddr, unsigned int len); netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev); +int lowpan_iphc_decompress(struct sk_buff *skb); +lowpan_rx_result lowpan_rx_h_ipv6(struct sk_buff *skb); + #endif /* __IEEE802154_6LOWPAN_I_H__ */ diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 0fc3350ace5a..12e8cf4bda9f 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -32,17 +32,6 @@ static const char lowpan_frags_cache_name[] = "lowpan-frags"; -struct lowpan_frag_info { - u16 d_tag; - u16 d_size; - u8 d_offset; -}; - -static struct lowpan_frag_info *lowpan_cb(struct sk_buff *skb) -{ - return (struct lowpan_frag_info *)skb->cb; -} - static struct inet_frags lowpan_frags; static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, @@ -111,7 +100,7 @@ out: } static inline struct lowpan_frag_queue * -fq_find(struct net *net, const struct lowpan_frag_info *frag_info, +fq_find(struct net *net, const struct lowpan_802154_cb *cb, const struct ieee802154_addr *src, const struct ieee802154_addr *dst) { @@ -121,12 +110,12 @@ fq_find(struct net *net, const struct lowpan_frag_info *frag_info, struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); - arg.tag = frag_info->d_tag; - arg.d_size = frag_info->d_size; + arg.tag = cb->d_tag; + arg.d_size = cb->d_size; arg.src = src; arg.dst = dst; - hash = lowpan_hash_frag(frag_info->d_tag, frag_info->d_size, src, dst); + hash = lowpan_hash_frag(cb->d_tag, cb->d_size, src, dst); q = inet_frag_find(&ieee802154_lowpan->frags, &lowpan_frags, &arg, hash); @@ -138,7 +127,7 @@ fq_find(struct net *net, const struct lowpan_frag_info *frag_info, } static int lowpan_frag_queue(struct lowpan_frag_queue *fq, - struct sk_buff *skb, const u8 frag_type) + struct sk_buff *skb, u8 frag_type) { struct sk_buff *prev, *next; struct net_device *ldev; @@ -147,8 +136,8 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, if (fq->q.flags & INET_FRAG_COMPLETE) goto err; - offset = lowpan_cb(skb)->d_offset << 3; - end = lowpan_cb(skb)->d_size; + offset = lowpan_802154_cb(skb)->d_offset << 3; + end = lowpan_802154_cb(skb)->d_size; /* Is this the final fragment? */ if (offset + skb->len == end) { @@ -174,13 +163,16 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, * this fragment, right? */ prev = fq->q.fragments_tail; - if (!prev || lowpan_cb(prev)->d_offset < lowpan_cb(skb)->d_offset) { + if (!prev || + lowpan_802154_cb(prev)->d_offset < + lowpan_802154_cb(skb)->d_offset) { next = NULL; goto found; } prev = NULL; for (next = fq->q.fragments; next != NULL; next = next->next) { - if (lowpan_cb(next)->d_offset >= lowpan_cb(skb)->d_offset) + if (lowpan_802154_cb(next)->d_offset >= + lowpan_802154_cb(skb)->d_offset) break; /* bingo! */ prev = next; } @@ -200,13 +192,10 @@ found: skb->dev = NULL; fq->q.stamp = skb->tstamp; - if (frag_type == LOWPAN_DISPATCH_FRAG1) { - /* Calculate uncomp. 6lowpan header to estimate full size */ - fq->q.meat += lowpan_uncompress_size(skb, NULL); + if (frag_type == LOWPAN_DISPATCH_FRAG1) fq->q.flags |= INET_FRAG_FIRST_IN; - } else { - fq->q.meat += skb->len; - } + + fq->q.meat += skb->len; add_frag_mem_limit(fq->q.net, skb->truesize); if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && @@ -325,24 +314,87 @@ out_oom: return -1; } -static int lowpan_get_frag_info(struct sk_buff *skb, const u8 frag_type, - struct lowpan_frag_info *frag_info) +static int lowpan_frag_rx_handlers_result(struct sk_buff *skb, + lowpan_rx_result res) +{ + switch (res) { + case RX_QUEUED: + return NET_RX_SUCCESS; + case RX_CONTINUE: + /* nobody cared about this packet */ + net_warn_ratelimited("%s: received unknown dispatch\n", + __func__); + + /* fall-through */ + default: + /* all others failure */ + return NET_RX_DROP; + } +} + +static lowpan_rx_result lowpan_frag_rx_h_iphc(struct sk_buff *skb) +{ + int ret; + + if (!lowpan_is_iphc(*skb_network_header(skb))) + return RX_CONTINUE; + + ret = lowpan_iphc_decompress(skb); + if (ret < 0) + return RX_DROP; + + return RX_QUEUED; +} + +static int lowpan_invoke_frag_rx_handlers(struct sk_buff *skb) +{ + lowpan_rx_result res; + +#define CALL_RXH(rxh) \ + do { \ + res = rxh(skb); \ + if (res != RX_CONTINUE) \ + goto rxh_next; \ + } while (0) + + /* likely at first */ + CALL_RXH(lowpan_frag_rx_h_iphc); + CALL_RXH(lowpan_rx_h_ipv6); + +rxh_next: + return lowpan_frag_rx_handlers_result(skb, res); +#undef CALL_RXH +} + +#define LOWPAN_FRAG_DGRAM_SIZE_HIGH_MASK 0x07 +#define LOWPAN_FRAG_DGRAM_SIZE_HIGH_SHIFT 8 + +static int lowpan_get_cb(struct sk_buff *skb, u8 frag_type, + struct lowpan_802154_cb *cb) { bool fail; - u8 pattern = 0, low = 0; + u8 high = 0, low = 0; __be16 d_tag = 0; - fail = lowpan_fetch_skb(skb, &pattern, 1); + fail = lowpan_fetch_skb(skb, &high, 1); fail |= lowpan_fetch_skb(skb, &low, 1); - frag_info->d_size = (pattern & 7) << 8 | low; + /* remove the dispatch value and use first three bits as high value + * for the datagram size + */ + cb->d_size = (high & LOWPAN_FRAG_DGRAM_SIZE_HIGH_MASK) << + LOWPAN_FRAG_DGRAM_SIZE_HIGH_SHIFT | low; fail |= lowpan_fetch_skb(skb, &d_tag, 2); - frag_info->d_tag = ntohs(d_tag); + cb->d_tag = ntohs(d_tag); if (frag_type == LOWPAN_DISPATCH_FRAGN) { - fail |= lowpan_fetch_skb(skb, &frag_info->d_offset, 1); + fail |= lowpan_fetch_skb(skb, &cb->d_offset, 1); } else { skb_reset_network_header(skb); - frag_info->d_offset = 0; + cb->d_offset = 0; + /* check if datagram_size has ipv6hdr on FRAG1 */ + fail |= cb->d_size < sizeof(struct ipv6hdr); + /* check if we can dereference the dispatch value */ + fail |= !skb->len; } if (unlikely(fail)) @@ -351,27 +403,33 @@ static int lowpan_get_frag_info(struct sk_buff *skb, const u8 frag_type, return 0; } -int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type) +int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type) { struct lowpan_frag_queue *fq; struct net *net = dev_net(skb->dev); - struct lowpan_frag_info *frag_info = lowpan_cb(skb); - struct ieee802154_addr source, dest; + struct lowpan_802154_cb *cb = lowpan_802154_cb(skb); + struct ieee802154_hdr hdr; int err; - source = mac_cb(skb)->source; - dest = mac_cb(skb)->dest; + if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) + goto err; - err = lowpan_get_frag_info(skb, frag_type, frag_info); + err = lowpan_get_cb(skb, frag_type, cb); if (err < 0) goto err; - if (frag_info->d_size > IPV6_MIN_MTU) { + if (frag_type == LOWPAN_DISPATCH_FRAG1) { + err = lowpan_invoke_frag_rx_handlers(skb); + if (err == NET_RX_DROP) + goto err; + } + + if (cb->d_size > IPV6_MIN_MTU) { net_warn_ratelimited("lowpan_frag_rcv: datagram size exceeds MTU\n"); goto err; } - fq = fq_find(net, frag_info, &source, &dest); + fq = fq_find(net, cb, &hdr.source, &hdr.dest); if (fq != NULL) { int ret; diff --git a/net/ieee802154/6lowpan/rx.c b/net/ieee802154/6lowpan/rx.c index f9cb70b6749f..fded1099fae0 100644 --- a/net/ieee802154/6lowpan/rx.c +++ b/net/ieee802154/6lowpan/rx.c @@ -15,8 +15,9 @@ #include "6lowpan_i.h" -static int lowpan_give_skb_to_device(struct sk_buff *skb, - struct net_device *wdev) +#define LOWPAN_DISPATCH_FRAG_MASK 0xf8 + +static int lowpan_give_skb_to_device(struct sk_buff *skb) { skb->protocol = htons(ETH_P_IPV6); skb->pkt_type = PACKET_HOST; @@ -24,21 +25,77 @@ static int lowpan_give_skb_to_device(struct sk_buff *skb, return netif_rx(skb); } -static int -iphc_decompress(struct sk_buff *skb, const struct ieee802154_hdr *hdr) +static int lowpan_rx_handlers_result(struct sk_buff *skb, lowpan_rx_result res) +{ + switch (res) { + case RX_CONTINUE: + /* nobody cared about this packet */ + net_warn_ratelimited("%s: received unknown dispatch\n", + __func__); + + /* fall-through */ + case RX_DROP_UNUSABLE: + kfree_skb(skb); + + /* fall-through */ + case RX_DROP: + return NET_RX_DROP; + case RX_QUEUED: + return lowpan_give_skb_to_device(skb); + default: + break; + } + + return NET_RX_DROP; +} + +static inline bool lowpan_is_frag1(u8 dispatch) +{ + return (dispatch & LOWPAN_DISPATCH_FRAG_MASK) == LOWPAN_DISPATCH_FRAG1; +} + +static inline bool lowpan_is_fragn(u8 dispatch) +{ + return (dispatch & LOWPAN_DISPATCH_FRAG_MASK) == LOWPAN_DISPATCH_FRAGN; +} + +static lowpan_rx_result lowpan_rx_h_frag(struct sk_buff *skb) +{ + int ret; + + if (!(lowpan_is_frag1(*skb_network_header(skb)) || + lowpan_is_fragn(*skb_network_header(skb)))) + return RX_CONTINUE; + + ret = lowpan_frag_rcv(skb, *skb_network_header(skb) & + LOWPAN_DISPATCH_FRAG_MASK); + if (ret == 1) + return RX_QUEUED; + + /* Packet is freed by lowpan_frag_rcv on error or put into the frag + * bucket. + */ + return RX_DROP; +} + +int lowpan_iphc_decompress(struct sk_buff *skb) { - u8 iphc0, iphc1; struct ieee802154_addr_sa sa, da; + struct ieee802154_hdr hdr; + u8 iphc0, iphc1; void *sap, *dap; + if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) + return -EINVAL; + raw_dump_table(__func__, "raw skb data dump", skb->data, skb->len); if (lowpan_fetch_skb_u8(skb, &iphc0) || lowpan_fetch_skb_u8(skb, &iphc1)) return -EINVAL; - ieee802154_addr_to_sa(&sa, &hdr->source); - ieee802154_addr_to_sa(&da, &hdr->dest); + ieee802154_addr_to_sa(&sa, &hdr.source); + ieee802154_addr_to_sa(&da, &hdr.dest); if (sa.addr_type == IEEE802154_ADDR_SHORT) sap = &sa.short_addr; @@ -55,78 +112,87 @@ iphc_decompress(struct sk_buff *skb, const struct ieee802154_hdr *hdr) IEEE802154_ADDR_LEN, iphc0, iphc1); } +static lowpan_rx_result lowpan_rx_h_iphc(struct sk_buff *skb) +{ + int ret; + + if (!lowpan_is_iphc(*skb_network_header(skb))) + return RX_CONTINUE; + + /* Setting datagram_offset to zero indicates non frag handling + * while doing lowpan_header_decompress. + */ + lowpan_802154_cb(skb)->d_size = 0; + + ret = lowpan_iphc_decompress(skb); + if (ret < 0) + return RX_DROP_UNUSABLE; + + return RX_QUEUED; +} + +lowpan_rx_result lowpan_rx_h_ipv6(struct sk_buff *skb) +{ + if (!lowpan_is_ipv6(*skb_network_header(skb))) + return RX_CONTINUE; + + /* Pull off the 1-byte of 6lowpan header. */ + skb_pull(skb, 1); + return RX_QUEUED; +} + +static int lowpan_invoke_rx_handlers(struct sk_buff *skb) +{ + lowpan_rx_result res; + +#define CALL_RXH(rxh) \ + do { \ + res = rxh(skb); \ + if (res != RX_CONTINUE) \ + goto rxh_next; \ + } while (0) + + /* likely at first */ + CALL_RXH(lowpan_rx_h_iphc); + CALL_RXH(lowpan_rx_h_frag); + CALL_RXH(lowpan_rx_h_ipv6); + +rxh_next: + return lowpan_rx_handlers_result(skb, res); +#undef CALL_RXH +} + static int lowpan_rcv(struct sk_buff *skb, struct net_device *wdev, struct packet_type *pt, struct net_device *orig_wdev) { - struct ieee802154_hdr hdr; struct net_device *ldev; - int ret; if (wdev->type != ARPHRD_IEEE802154 || skb->pkt_type == PACKET_OTHERHOST) - goto drop; + return NET_RX_DROP; ldev = wdev->ieee802154_ptr->lowpan_dev; if (!ldev || !netif_running(ldev)) - goto drop; + return NET_RX_DROP; /* Replacing skb->dev and followed rx handlers will manipulate skb. */ skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) - goto drop; + return NET_RX_DROP; skb->dev = ldev; - if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) - goto drop_skb; - - /* check that it's our buffer */ - if (skb->data[0] == LOWPAN_DISPATCH_IPV6) { - /* Pull off the 1-byte of 6lowpan header. */ - skb_pull(skb, 1); - return lowpan_give_skb_to_device(skb, wdev); - } else { - switch (skb->data[0] & 0xe0) { - case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */ - ret = iphc_decompress(skb, &hdr); - if (ret < 0) - goto drop_skb; - - return lowpan_give_skb_to_device(skb, wdev); - case LOWPAN_DISPATCH_FRAG1: /* first fragment header */ - ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAG1); - if (ret == 1) { - ret = iphc_decompress(skb, &hdr); - if (ret < 0) - goto drop_skb; - - return lowpan_give_skb_to_device(skb, wdev); - } else if (ret == -1) { - return NET_RX_DROP; - } else { - return NET_RX_SUCCESS; - } - case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */ - ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAGN); - if (ret == 1) { - ret = iphc_decompress(skb, &hdr); - if (ret < 0) - goto drop_skb; - - return lowpan_give_skb_to_device(skb, wdev); - } else if (ret == -1) { - return NET_RX_DROP; - } else { - return NET_RX_SUCCESS; - } - default: - break; - } + /* When receive frag1 it's likely that we manipulate the buffer. + * When recevie iphc we manipulate the data buffer. So we need + * to unshare the buffer. + */ + if (lowpan_is_frag1(*skb_network_header(skb)) || + lowpan_is_iphc(*skb_network_header(skb))) { + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) + return RX_DROP; } -drop_skb: - kfree_skb(skb); -drop: - return NET_RX_DROP; + return lowpan_invoke_rx_handlers(skb); } static struct packet_type lowpan_packet_type = { -- cgit v1.2.3 From 54552d03023cfd485cedf8d7471d1554139d58aa Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 2 Sep 2015 14:21:29 +0200 Subject: ieee802154: 6lowpan: check on valid 802.15.4 frame This patch adds frame control checks to check if the received frame is something which could contain a 6LoWPAN packet. Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/linux/ieee802154.h | 25 +++++++++++++++++++++++++ include/net/mac802154.h | 15 +++++++++++++++ net/ieee802154/6lowpan/rx.c | 8 ++++++++ 3 files changed, 48 insertions(+) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 1dc1f4ed4001..db01492814d3 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -205,6 +205,31 @@ enum { IEEE802154_SCAN_IN_PROGRESS = 0xfc, }; +/* frame control handling */ +#define IEEE802154_FCTL_FTYPE 0x0003 +#define IEEE802154_FCTL_INTRA_PAN 0x0040 + +#define IEEE802154_FTYPE_DATA 0x0001 + +/* + * ieee802154_is_data - check if type is IEEE802154_FTYPE_DATA + * @fc: frame control bytes in little-endian byteorder + */ +static inline int ieee802154_is_data(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE802154_FCTL_FTYPE)) == + cpu_to_le16(IEEE802154_FTYPE_DATA); +} + +/** + * ieee802154_is_intra_pan - check if intra pan id communication + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee802154_is_intra_pan(__le16 fc) +{ + return fc & cpu_to_le16(IEEE802154_FCTL_INTRA_PAN); +} + /** * ieee802154_is_valid_psdu_len - check if psdu len is valid * available lengths: diff --git a/include/net/mac802154.h b/include/net/mac802154.h index b7f99615224b..32bd7c0467d4 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -249,6 +249,21 @@ struct ieee802154_ops { const bool on); }; +/** + * ieee802154_get_fc_from_skb - get the frame control field from an skb + * @skb: skb where the frame control field will be get from + */ +static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) +{ + /* return some invalid fc on failure */ + if (unlikely(skb->mac_len < 2)) { + WARN_ON(1); + return cpu_to_le16(0); + } + + return (__force __le16)__get_unaligned_memmove16(skb_mac_header(skb)); +} + /** * ieee802154_be64_to_le64 - copies and convert be64 to le64 * @le64_dst: le64 destination pointer diff --git a/net/ieee802154/6lowpan/rx.c b/net/ieee802154/6lowpan/rx.c index 45ce121369c2..f7eb091203a8 100644 --- a/net/ieee802154/6lowpan/rx.c +++ b/net/ieee802154/6lowpan/rx.c @@ -11,6 +11,7 @@ #include #include +#include #include #include "6lowpan_i.h" @@ -280,6 +281,13 @@ static inline bool lowpan_is_reserved(u8 dispatch) */ static inline bool lowpan_rx_h_check(struct sk_buff *skb) { + __le16 fc = ieee802154_get_fc_from_skb(skb); + + /* check on ieee802154 conform 6LoWPAN header */ + if (!ieee802154_is_data(fc) || + !ieee802154_is_intra_pan(fc)) + return false; + /* check if we can dereference the dispatch */ if (unlikely(!skb->len)) return false; -- cgit v1.2.3 From 187625e18498ff0f3738a059778a8578171f06c8 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 2 Sep 2015 14:21:31 +0200 Subject: ieee802154: 6lowpan: remove tx full-size calc workaround This patch removes a workaround for datagram_size calculation while doing fragmentation on transmit. Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 113 -------------------------------------------- net/ieee802154/6lowpan/tx.c | 18 ++++--- 2 files changed, 11 insertions(+), 120 deletions(-) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index 35098411dbb4..eeae5eb58754 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -299,119 +299,6 @@ static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data, *hc_ptr += len; } -static inline u8 lowpan_addr_mode_size(const u8 addr_mode) -{ - static const u8 addr_sizes[] = { - [LOWPAN_IPHC_ADDR_00] = 16, - [LOWPAN_IPHC_ADDR_01] = 8, - [LOWPAN_IPHC_ADDR_02] = 2, - [LOWPAN_IPHC_ADDR_03] = 0, - }; - return addr_sizes[addr_mode]; -} - -static inline u8 lowpan_next_hdr_size(const u8 h_enc, u16 *uncomp_header) -{ - u8 ret = 1; - - if ((h_enc & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) { - *uncomp_header += sizeof(struct udphdr); - - switch (h_enc & LOWPAN_NHC_UDP_CS_P_11) { - case LOWPAN_NHC_UDP_CS_P_00: - ret += 4; - break; - case LOWPAN_NHC_UDP_CS_P_01: - case LOWPAN_NHC_UDP_CS_P_10: - ret += 3; - break; - case LOWPAN_NHC_UDP_CS_P_11: - ret++; - break; - default: - break; - } - - if (!(h_enc & LOWPAN_NHC_UDP_CS_C)) - ret += 2; - } - - return ret; -} - -/** - * lowpan_uncompress_size - returns skb->len size with uncompressed header - * @skb: sk_buff with 6lowpan header inside - * @datagram_offset: optional to get the datagram_offset value - * - * Returns the skb->len with uncompressed header - */ -static inline u16 -lowpan_uncompress_size(const struct sk_buff *skb, u16 *dgram_offset) -{ - u16 ret = 2, uncomp_header = sizeof(struct ipv6hdr); - u8 iphc0, iphc1, h_enc; - - iphc0 = skb_network_header(skb)[0]; - iphc1 = skb_network_header(skb)[1]; - - switch ((iphc0 & LOWPAN_IPHC_TF) >> 3) { - case 0: - ret += 4; - break; - case 1: - ret += 3; - break; - case 2: - ret++; - break; - default: - break; - } - - if (!(iphc0 & LOWPAN_IPHC_NH_C)) - ret++; - - if (!(iphc0 & 0x03)) - ret++; - - ret += lowpan_addr_mode_size((iphc1 & LOWPAN_IPHC_SAM) >> - LOWPAN_IPHC_SAM_BIT); - - if (iphc1 & LOWPAN_IPHC_M) { - switch ((iphc1 & LOWPAN_IPHC_DAM_11) >> - LOWPAN_IPHC_DAM_BIT) { - case LOWPAN_IPHC_DAM_00: - ret += 16; - break; - case LOWPAN_IPHC_DAM_01: - ret += 6; - break; - case LOWPAN_IPHC_DAM_10: - ret += 4; - break; - case LOWPAN_IPHC_DAM_11: - ret++; - break; - default: - break; - } - } else { - ret += lowpan_addr_mode_size((iphc1 & LOWPAN_IPHC_DAM_11) >> - LOWPAN_IPHC_DAM_BIT); - } - - if (iphc0 & LOWPAN_IPHC_NH_C) { - h_enc = skb_network_header(skb)[ret]; - ret += lowpan_next_hdr_size(h_enc, &uncomp_header); - } - - if (dgram_offset) - *dgram_offset = uncomp_header; - - return skb->len + uncomp_header - ret; -} - void lowpan_netdev_setup(struct net_device *dev, enum lowpan_lltypes lltype); int diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c index 9a2147e7f600..54939d031ea5 100644 --- a/net/ieee802154/6lowpan/tx.c +++ b/net/ieee802154/6lowpan/tx.c @@ -123,16 +123,14 @@ lowpan_xmit_fragment(struct sk_buff *skb, const struct ieee802154_hdr *wpan_hdr, static int lowpan_xmit_fragmented(struct sk_buff *skb, struct net_device *ldev, - const struct ieee802154_hdr *wpan_hdr) + const struct ieee802154_hdr *wpan_hdr, u16 dgram_size, + u16 dgram_offset) { - u16 dgram_size, dgram_offset; __be16 frag_tag; u8 frag_hdr[5]; int frag_cap, frag_len, payload_cap, rc; int skb_unprocessed, skb_offset; - dgram_size = lowpan_uncompress_size(skb, &dgram_offset) - - skb->mac_len; frag_tag = htons(lowpan_dev_info(ldev)->fragment_tag); lowpan_dev_info(ldev)->fragment_tag++; @@ -187,7 +185,8 @@ err: return rc; } -static int lowpan_header(struct sk_buff *skb, struct net_device *ldev) +static int lowpan_header(struct sk_buff *skb, struct net_device *ldev, + u16 *dgram_size, u16 *dgram_offset) { struct wpan_dev *wpan_dev = lowpan_dev_info(ldev)->wdev->ieee802154_ptr; struct ieee802154_addr sa, da; @@ -201,7 +200,10 @@ static int lowpan_header(struct sk_buff *skb, struct net_device *ldev) daddr = &info.daddr.u.extended_addr; saddr = &info.saddr.u.extended_addr; + *dgram_size = skb->len; lowpan_header_compress(skb, ldev, ETH_P_IPV6, daddr, saddr, skb->len); + /* dgram_offset = (saved bytes after compression) + lowpan header len */ + *dgram_offset = (*dgram_size - skb->len) + skb_network_header_len(skb); cb->type = IEEE802154_FC_TYPE_DATA; @@ -234,6 +236,7 @@ netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev) { struct ieee802154_hdr wpan_hdr; int max_single, ret; + u16 dgram_size, dgram_offset; pr_debug("package xmit\n"); @@ -244,7 +247,7 @@ netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev) if (!skb) return NET_XMIT_DROP; - ret = lowpan_header(skb, ldev); + ret = lowpan_header(skb, ldev, &dgram_size, &dgram_offset); if (ret < 0) { kfree_skb(skb); return NET_XMIT_DROP; @@ -264,7 +267,8 @@ netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev) netdev_tx_t rc; pr_debug("frame is too big, fragmentation is needed\n"); - rc = lowpan_xmit_fragmented(skb, ldev, &wpan_hdr); + rc = lowpan_xmit_fragmented(skb, ldev, &wpan_hdr, dgram_size, + dgram_offset); return rc < 0 ? NET_XMIT_DROP : rc; } -- cgit v1.2.3 From bfe08a875a8903c0abb1ef5d57722252d14ede2e Mon Sep 17 00:00:00 2001 From: Stefan Schmidt Date: Thu, 3 Sep 2015 16:31:35 +0200 Subject: ieee802154: af_ieee802154: fix typo in comment. Signed-off-by: Stefan Schmidt Acked-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/af_ieee802154.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/af_ieee802154.h b/include/net/af_ieee802154.h index 7d38e2ffd256..a5563d27a3eb 100644 --- a/include/net/af_ieee802154.h +++ b/include/net/af_ieee802154.h @@ -1,5 +1,5 @@ /* - * IEEE 802.15.4 inteface for userspace + * IEEE 802.15.4 interface for userspace * * Copyright 2007, 2008 Siemens AG * -- cgit v1.2.3 From ef748917b529847277f07c98c55e1c0ce416449f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 2 Sep 2015 14:31:21 +0800 Subject: arm/arm64: KVM: Remove 'config KVM_ARM_MAX_VCPUS' This patch removes config option of KVM_ARM_MAX_VCPUS, and like other ARCHs, just choose the maximum allowed value from hardware, and follows the reasons: 1) from distribution view, the option has to be defined as the max allowed value because it need to meet all kinds of virtulization applications and need to support most of SoCs; 2) using a bigger value doesn't introduce extra memory consumption, and the help text in Kconfig isn't accurate because kvm_vpu structure isn't allocated until request of creating VCPU is sent from QEMU; 3) the main effect is that the field of vcpus[] in 'struct kvm' becomes a bit bigger(sizeof(void *) per vcpu) and need more cache lines to hold the structure, but 'struct kvm' is one generic struct, and it has worked well on other ARCHs already in this way. Also, the world switch frequecy is often low, for example, it is ~2000 when running kernel building load in VM from APM xgene KVM host, so the effect is very small, and the difference can't be observed in my test at all. Cc: Dann Frazier Signed-off-by: Ming Lei Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- arch/arm/include/asm/kvm_host.h | 8 ++------ arch/arm/kvm/Kconfig | 11 ----------- arch/arm64/include/asm/kvm_host.h | 8 ++------ arch/arm64/kvm/Kconfig | 11 ----------- include/kvm/arm_vgic.h | 6 +----- virt/kvm/arm/vgic-v3.c | 2 +- 6 files changed, 6 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index dcba0fa5176e..c8c226a19dbe 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -29,12 +29,6 @@ #define __KVM_HAVE_ARCH_INTC_INITIALIZED -#if defined(CONFIG_KVM_ARM_MAX_VCPUS) -#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS -#else -#define KVM_MAX_VCPUS 0 -#endif - #define KVM_USER_MEM_SLOTS 32 #define KVM_PRIVATE_MEM_SLOTS 4 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -44,6 +38,8 @@ #include +#define KVM_MAX_VCPUS VGIC_V2_MAX_CPUS + u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode); int __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index bfb915d05665..210eccadb69a 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -45,15 +45,4 @@ config KVM_ARM_HOST ---help--- Provides host support for ARM processors. -config KVM_ARM_MAX_VCPUS - int "Number maximum supported virtual CPUs per VM" - depends on KVM_ARM_HOST - default 4 - help - Static number of max supported virtual CPUs per VM. - - If you choose a high number, the vcpu structures will be quite - large, so only choose a reasonable number that you expect to - actually use. - endif # VIRTUALIZATION diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 415938dc45cf..3fb58ea944eb 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -30,12 +30,6 @@ #define __KVM_HAVE_ARCH_INTC_INITIALIZED -#if defined(CONFIG_KVM_ARM_MAX_VCPUS) -#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS -#else -#define KVM_MAX_VCPUS 0 -#endif - #define KVM_USER_MEM_SLOTS 32 #define KVM_PRIVATE_MEM_SLOTS 4 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -43,6 +37,8 @@ #include #include +#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS + #define KVM_VCPU_MAX_FEATURES 3 int __attribute_const__ kvm_target_cpu(void); diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index bfffe8f4bd53..5c7e920e4861 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -41,15 +41,4 @@ config KVM_ARM_HOST ---help--- Provides host support for ARM processors. -config KVM_ARM_MAX_VCPUS - int "Number maximum supported virtual CPUs per VM" - depends on KVM_ARM_HOST - default 4 - help - Static number of max supported virtual CPUs per VM. - - If you choose a high number, the vcpu structures will be quite - large, so only choose a reasonable number that you expect to - actually use. - endif # VIRTUALIZATION diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index d901f1a47be6..4e14dac282bb 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -35,11 +35,7 @@ #define VGIC_V3_MAX_LRS 16 #define VGIC_MAX_IRQS 1024 #define VGIC_V2_MAX_CPUS 8 - -/* Sanity checks... */ -#if (KVM_MAX_VCPUS > 255) -#error Too many KVM VCPUs, the VGIC only supports up to 255 VCPUs for now -#endif +#define VGIC_V3_MAX_CPUS 255 #if (VGIC_NR_IRQS_LEGACY & 31) #error "VGIC_NR_IRQS must be a multiple of 32" diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c index afbf925b00f4..7dd5d62f10a1 100644 --- a/virt/kvm/arm/vgic-v3.c +++ b/virt/kvm/arm/vgic-v3.c @@ -288,7 +288,7 @@ int vgic_v3_probe(struct device_node *vgic_node, vgic->vctrl_base = NULL; vgic->type = VGIC_V3; - vgic->max_gic_vcpus = KVM_MAX_VCPUS; + vgic->max_gic_vcpus = VGIC_V3_MAX_CPUS; kvm_info("%s@%llx IRQ%d\n", vgic_node->name, vcpu_res.start, vgic->maint_irq); -- cgit v1.2.3 From 7f61f545657281a3a1b0faf68993165ebdecc51b Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 14 Sep 2015 16:01:05 +0300 Subject: libceph: don't access invalid memory in keepalive2 path This struct ceph_timespec ceph_ts; ... con_out_kvec_add(con, sizeof(ceph_ts), &ceph_ts); wraps ceph_ts into a kvec and adds it to con->out_kvec array, yet ceph_ts becomes invalid on return from prepare_write_keepalive(). As a result, we send out bogus keepalive2 stamps. Fix this by encoding into a ceph_timespec member, similar to how acks are read and written. Signed-off-by: Ilya Dryomov Reviewed-by: Yan, Zheng --- include/linux/ceph/messenger.h | 4 +++- net/ceph/messenger.c | 9 +++++---- 2 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 7e1252e97a30..b2371d9b51fa 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -238,6 +238,8 @@ struct ceph_connection { bool out_kvec_is_msg; /* kvec refers to out_msg */ int out_more; /* there is more data after the kvecs */ __le64 out_temp_ack; /* for writing an ack */ + struct ceph_timespec out_temp_keepalive2; /* for writing keepalive2 + stamp */ /* message in temps */ struct ceph_msg_header in_hdr; @@ -248,7 +250,7 @@ struct ceph_connection { int in_base_pos; /* bytes read */ __le64 in_temp_ack; /* for reading an ack */ - struct timespec last_keepalive_ack; + struct timespec last_keepalive_ack; /* keepalive2 ack stamp */ struct delayed_work work; /* send|recv work */ unsigned long delay; /* current delay interval */ diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 525f454f7531..b9b0e3b5da49 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1353,11 +1353,12 @@ static void prepare_write_keepalive(struct ceph_connection *con) dout("prepare_write_keepalive %p\n", con); con_out_kvec_reset(con); if (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2) { - struct timespec ts = CURRENT_TIME; - struct ceph_timespec ceph_ts; - ceph_encode_timespec(&ceph_ts, &ts); + struct timespec now = CURRENT_TIME; + con_out_kvec_add(con, sizeof(tag_keepalive2), &tag_keepalive2); - con_out_kvec_add(con, sizeof(ceph_ts), &ceph_ts); + ceph_encode_timespec(&con->out_temp_keepalive2, &now); + con_out_kvec_add(con, sizeof(con->out_temp_keepalive2), + &con->out_temp_keepalive2); } else { con_out_kvec_add(con, sizeof(tag_keepalive), &tag_keepalive); } -- cgit v1.2.3 From 335c25858218e76ef47f92ecb9d22e919d36140d Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 14 Sep 2015 12:44:22 +0300 Subject: libceph: advertise support for keepalive2 We are the client, but advertise keepalive2 anyway - for consistency, if nothing else. In the future the server might want to know whether its clients support keepalive2. Signed-off-by: Ilya Dryomov Reviewed-by: Yan, Zheng --- include/linux/ceph/ceph_features.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 4763ad64e832..f89b31d45cc8 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -107,6 +107,7 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_OSDMAP_ENC | \ CEPH_FEATURE_CRUSH_TUNABLES3 | \ CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ + CEPH_FEATURE_MSGR_KEEPALIVE2 | \ CEPH_FEATURE_CRUSH_V4) #define CEPH_FEATURES_REQUIRED_DEFAULT \ -- cgit v1.2.3 From 37a1d3611c126fd9782ce5235791f898f053e763 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Sun, 13 Sep 2015 10:18:33 -0700 Subject: ipv6: include NLM_F_REPLACE in route replace notifications This patch adds NLM_F_REPLACE flag to ipv6 route replace notifications. This makes nlm_flags in ipv6 replace notifications consistent with ipv4. Signed-off-by: Roopa Prabhu Acked-by: Nicolas Dichtel Reviewed-by: Michal Kubecek Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 3 ++- net/ipv6/ip6_fib.c | 6 +++--- net/ipv6/route.c | 5 +++-- 3 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 063d30474cf6..aaf9700fc9e5 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -275,7 +275,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info, struct mx6_config *mxc); int fib6_del(struct rt6_info *rt, struct nl_info *info); -void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info); +void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info, + unsigned int flags); void fib6_run_gc(unsigned long expires, struct net *net, bool force); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 8a9ec01f4d01..7d2e0023c72d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -851,7 +851,7 @@ add: *ins = rt; rt->rt6i_node = fn; atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, info); + inet6_rt_notify(RTM_NEWROUTE, rt, info, 0); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; if (!(fn->fn_flags & RTN_RTINFO)) { @@ -877,7 +877,7 @@ add: rt->rt6i_node = fn; rt->dst.rt6_next = iter->dst.rt6_next; atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, info); + inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; @@ -1422,7 +1422,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, fib6_purge_rt(rt, fn, net); - inet6_rt_notify(RTM_DELROUTE, rt, info); + inet6_rt_notify(RTM_DELROUTE, rt, info, 0); rt6_release(rt); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3d3c1b294725..d5fa50297f80 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3304,7 +3304,8 @@ errout: return err; } -void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) +void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info, + unsigned int nlm_flags) { struct sk_buff *skb; struct net *net = info->nl_net; @@ -3319,7 +3320,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, 0, - event, info->portid, seq, 0, 0, 0); + event, info->portid, seq, 0, 0, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); -- cgit v1.2.3 From 0fdea1e8a2853f79d39b8555cc9de16a7e0ab26f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 16 Sep 2015 23:43:17 -0400 Subject: SUNRPC: Ensure that we wait for connections to complete before retrying Commit 718ba5b87343, moved the responsibility for unlocking the socket to xs_tcp_setup_socket, meaning that the socket will be unlocked before we know that it has finished trying to connect. The following patch is based on an initial patch by Russell King to ensure that we delay clearing the XPRT_CONNECTING flag until we either know that we failed to initiate a connection attempt, or the connection attempt itself failed. Fixes: 718ba5b87343 ("SUNRPC: Add helpers to prevent socket create from racing") Reported-by: Russell King Reported-by: Russell King Tested-by: Russell King Tested-by: Benjamin Coddington Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 3 +++ net/sunrpc/xprtsock.c | 11 ++++++++--- 2 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 7591788e9fbf..357e44c1a46b 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -42,6 +42,7 @@ struct sock_xprt { /* * Connection of transports */ + unsigned long sock_state; struct delayed_work connect_worker; struct sockaddr_storage srcaddr; unsigned short srcport; @@ -76,6 +77,8 @@ struct sock_xprt { */ #define TCP_RPC_REPLY (1UL << 6) +#define XPRT_SOCK_CONNECTING 1U + #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index d2dfbd043bea..c35038511686 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1438,6 +1438,7 @@ out: static void xs_tcp_state_change(struct sock *sk) { struct rpc_xprt *xprt; + struct sock_xprt *transport; read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) @@ -1449,13 +1450,12 @@ static void xs_tcp_state_change(struct sock *sk) sock_flag(sk, SOCK_ZAPPED), sk->sk_shutdown); + transport = container_of(xprt, struct sock_xprt, xprt); trace_rpc_socket_state_change(xprt, sk->sk_socket); switch (sk->sk_state) { case TCP_ESTABLISHED: spin_lock(&xprt->transport_lock); if (!xprt_test_and_set_connected(xprt)) { - struct sock_xprt *transport = container_of(xprt, - struct sock_xprt, xprt); /* Reset TCP record info */ transport->tcp_offset = 0; @@ -1464,6 +1464,8 @@ static void xs_tcp_state_change(struct sock *sk) transport->tcp_flags = TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID; xprt->connect_cookie++; + clear_bit(XPRT_SOCK_CONNECTING, &transport->sock_state); + xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, -EAGAIN); } @@ -1499,6 +1501,9 @@ static void xs_tcp_state_change(struct sock *sk) smp_mb__after_atomic(); break; case TCP_CLOSE: + if (test_and_clear_bit(XPRT_SOCK_CONNECTING, + &transport->sock_state)) + xprt_clear_connecting(xprt); xs_sock_mark_closed(xprt); } out: @@ -2182,6 +2187,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) /* Tell the socket layer to start connecting... */ xprt->stat.connect_count++; xprt->stat.connect_start = jiffies; + set_bit(XPRT_SOCK_CONNECTING, &transport->sock_state); ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK); switch (ret) { case 0: @@ -2243,7 +2249,6 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EINPROGRESS: case -EALREADY: xprt_unlock_connect(xprt, transport); - xprt_clear_connecting(xprt); return; case -EINVAL: /* Happens, for instance, if the user specified a link -- cgit v1.2.3 From 58189ca7b27411c3dc9a5cb9eeee0906da684c59 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 15 Sep 2015 15:10:50 -0700 Subject: net: Fix vti use case with oif in dst lookups Steffen reported that the recent change to add oif to dst lookups breaks the VTI use case. The problem is that with the oif set in the flow struct the comparison to the nh_oif is triggered. Fix by splitting the FLOWI_FLAG_VRFSRC into 2 flags -- one that triggers the vrf device cache bypass (FLOWI_FLAG_VRFSRC) and another telling the lookup to not compare nh oif (FLOWI_FLAG_SKIP_NH_OIF). Fixes: 42a7b32b73d6 ("xfrm: Add oif to dst lookups") Signed-off-by: David Ahern Acked-by: Steffen Klassert Signed-off-by: David S. Miller --- drivers/net/vrf.c | 3 ++- include/net/flow.h | 1 + include/net/route.h | 2 +- net/ipv4/fib_trie.c | 2 +- net/ipv4/udp.c | 3 ++- net/ipv4/xfrm4_policy.c | 2 ++ 6 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index e7094fbd7568..488c6f50df73 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -193,7 +193,8 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, .flowi4_oif = vrf_dev->ifindex, .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_tos = RT_TOS(ip4h->tos), - .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC, + .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC | + FLOWI_FLAG_SKIP_NH_OIF, .daddr = ip4h->daddr, }; diff --git a/include/net/flow.h b/include/net/flow.h index acd6a096250e..9b85db85f13c 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -35,6 +35,7 @@ struct flowi_common { #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_KNOWN_NH 0x02 #define FLOWI_FLAG_VRFSRC 0x04 +#define FLOWI_FLAG_SKIP_NH_OIF 0x08 __u32 flowic_secid; struct flowi_tunnel flowic_tun_key; }; diff --git a/include/net/route.h b/include/net/route.h index cc61cb95f059..f46af256880c 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -255,7 +255,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 flow_flags |= FLOWI_FLAG_ANYSRC; if (netif_index_is_vrf(sock_net(sk), oif)) - flow_flags |= FLOWI_FLAG_VRFSRC; + flow_flags |= FLOWI_FLAG_VRFSRC | FLOWI_FLAG_SKIP_NH_OIF; flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, protocol, flow_flags, dst, src, dport, sport); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 26d6ffb6d23c..6c2af797f2f9 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1426,7 +1426,7 @@ found: nh->nh_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) continue; - if (!(flp->flowi4_flags & FLOWI_FLAG_VRFSRC)) { + if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) { if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif) continue; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c0a15e7f359f..f7d1d5e19e95 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1024,7 +1024,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (netif_index_is_vrf(net, ipc.oif)) { flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, - (flow_flags | FLOWI_FLAG_VRFSRC), + (flow_flags | FLOWI_FLAG_VRFSRC | + FLOWI_FLAG_SKIP_NH_OIF), faddr, saddr, dport, inet->inet_sport); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index bb919b28619f..c10a9ee68433 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -33,6 +33,8 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, if (saddr) fl4->saddr = saddr->a4; + fl4->flowi4_flags = FLOWI_FLAG_SKIP_NH_OIF; + rt = __ip_route_output_key(net, fl4); if (!IS_ERR(rt)) return &rt->dst; -- cgit v1.2.3 From e781b7f7fcc141d69f63d4eef70d249549dfaeda Mon Sep 17 00:00:00 2001 From: Szymon Janc Date: Wed, 16 Sep 2015 20:21:53 +0200 Subject: Bluetooth: Add BT_ERR_RATELIMITED This patch adds ratelimited version of the BT_ERR macro. Signed-off-by: Szymon Janc Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 4 ++++ net/bluetooth/lib.c | 16 ++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index fcf2ae7dbfa0..f5ade8573393 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -123,11 +123,15 @@ __printf(1, 2) void bt_info(const char *fmt, ...); __printf(1, 2) void bt_err(const char *fmt, ...); +__printf(1, 2) +void bt_err_ratelimited(const char *fmt, ...); #define BT_INFO(fmt, ...) bt_info(fmt "\n", ##__VA_ARGS__) #define BT_ERR(fmt, ...) bt_err(fmt "\n", ##__VA_ARGS__) #define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__) +#define BT_ERR_RATELIMITED(fmt, ...) bt_err_ratelimited(fmt "\n", ##__VA_ARGS__) + #define bt_dev_info(hdev, fmt, ...) \ BT_INFO("%s: " fmt, (hdev)->name, ##__VA_ARGS__) #define bt_dev_err(hdev, fmt, ...) \ diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c index b36bc0415854..8b4cdce3f62e 100644 --- a/net/bluetooth/lib.c +++ b/net/bluetooth/lib.c @@ -166,3 +166,19 @@ void bt_err(const char *format, ...) va_end(args); } EXPORT_SYMBOL(bt_err); + +void bt_err_ratelimited(const char *format, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, format); + + vaf.fmt = format; + vaf.va = &args; + + pr_err_ratelimited("%pV", &vaf); + + va_end(args); +} +EXPORT_SYMBOL(bt_err_ratelimited); -- cgit v1.2.3 From aadfc3b2042d69a6b4b8d719d4221b988d7f31a5 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 9 Sep 2015 01:28:21 -0400 Subject: IB/hfi1: fix pstateinfo from returning improperly byteswapped value Byteswap link_width_downgrade_*_active values before sending on the wire. In addition properly define the Port State Info structure. Reviewed-by: Dennis Dalessandro Reviewed-by: Christian Gomez Signed-off-by: Rimmer, Todd Signed-off-by: Ira Weiny Acked-by: Mike Marciniszyn Signed-off-by: Doug Ledford --- drivers/staging/rdma/hfi1/mad.c | 4 ++-- include/rdma/opa_port_info.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/staging/rdma/hfi1/mad.c b/drivers/staging/rdma/hfi1/mad.c index 37269eb90c34..b2c1b72d38ce 100644 --- a/drivers/staging/rdma/hfi1/mad.c +++ b/drivers/staging/rdma/hfi1/mad.c @@ -1717,9 +1717,9 @@ static int __subn_get_opa_psi(struct opa_smp *smp, u32 am, u8 *data, psi->port_states.portphysstate_portstate = (hfi1_ibphys_portstate(ppd) << 4) | (lstate & 0xf); psi->link_width_downgrade_tx_active = - ppd->link_width_downgrade_tx_active; + cpu_to_be16(ppd->link_width_downgrade_tx_active); psi->link_width_downgrade_rx_active = - ppd->link_width_downgrade_rx_active; + cpu_to_be16(ppd->link_width_downgrade_rx_active); if (resp_len) *resp_len += sizeof(struct opa_port_state_info); diff --git a/include/rdma/opa_port_info.h b/include/rdma/opa_port_info.h index 391dae1931c0..a0fa975cd1c1 100644 --- a/include/rdma/opa_port_info.h +++ b/include/rdma/opa_port_info.h @@ -294,8 +294,8 @@ struct opa_port_states { struct opa_port_state_info { struct opa_port_states port_states; - u16 link_width_downgrade_tx_active; - u16 link_width_downgrade_rx_active; + __be16 link_width_downgrade_tx_active; + __be16 link_width_downgrade_rx_active; }; struct opa_port_info { -- cgit v1.2.3 From 97b59c3a91d5ee4777658ff2136d1fdf13bd23d0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:32:54 -0500 Subject: netfilter: ebtables: Simplify the arguments to ebt_do_table Nearly everything thing of interest to ebt_do_table is already present in nf_hook_state. Simplify ebt_do_table by just passing in the skb, nf_hook_state, and the table. This make the code easier to read and maintenance easier. To support this create an nf_hook_state on the stack in ebt_broute (the only caller without a nf_hook_state already available). This new nf_hook_state adds no new computations to ebt_broute, but does use a few more bytes of stack. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge/ebtables.h | 6 +++--- net/bridge/netfilter/ebtable_broute.c | 8 ++++++-- net/bridge/netfilter/ebtable_filter.c | 6 ++---- net/bridge/netfilter/ebtable_nat.c | 6 ++---- net/bridge/netfilter/ebtables.c | 13 +++++++------ 5 files changed, 20 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 8ca6d6464ea3..2ea517c7c6b9 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -111,9 +111,9 @@ struct ebt_table { extern struct ebt_table *ebt_register_table(struct net *net, const struct ebt_table *table); extern void ebt_unregister_table(struct net *net, struct ebt_table *table); -extern unsigned int ebt_do_table(unsigned int hook, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - struct ebt_table *table); +extern unsigned int ebt_do_table(struct sk_buff *skb, + const struct nf_hook_state *state, + struct ebt_table *table); /* Used in the kernel match() functions */ #define FWINV(bool,invflg) ((bool) ^ !!(info->invflags & invflg)) diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index d2cdf5d6e98c..ec94c6f1ae88 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -50,10 +50,14 @@ static const struct ebt_table broute_table = { static int ebt_broute(struct sk_buff *skb) { + struct nf_hook_state state; int ret; - ret = ebt_do_table(NF_BR_BROUTING, skb, skb->dev, NULL, - dev_net(skb->dev)->xt.broute_table); + nf_hook_state_init(&state, NULL, NF_BR_BROUTING, INT_MIN, + NFPROTO_BRIDGE, skb->dev, NULL, NULL, + dev_net(skb->dev), NULL); + + ret = ebt_do_table(skb, &state, state.net->xt.broute_table); if (ret == NF_DROP) return 1; /* route it */ return 0; /* bridge it */ diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index ab20d6ed6e2f..118ce40ac181 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -60,16 +60,14 @@ static unsigned int ebt_in_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, state->in, state->out, - state->net->xt.frame_filter); + return ebt_do_table(skb, state, state->net->xt.frame_filter); } static unsigned int ebt_out_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, state->in, state->out, - state->net->xt.frame_filter); + return ebt_do_table(skb, state, state->net->xt.frame_filter); } static struct nf_hook_ops ebt_ops_filter[] __read_mostly = { diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index ad81a5a65644..56c3329d6c37 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -60,16 +60,14 @@ static unsigned int ebt_nat_in(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, state->in, state->out, - state->net->xt.frame_nat); + return ebt_do_table(skb, state, state->net->xt.frame_nat); } static unsigned int ebt_nat_out(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, state->in, state->out, - state->net->xt.frame_nat); + return ebt_do_table(skb, state, state->net->xt.frame_nat); } static struct nf_hook_ops ebt_ops_nat[] __read_mostly = { diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 48b6b01295de..8d5a3975b963 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -183,10 +183,11 @@ struct ebt_entry *ebt_next_entry(const struct ebt_entry *entry) } /* Do some firewalling */ -unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - struct ebt_table *table) +unsigned int ebt_do_table(struct sk_buff *skb, + const struct nf_hook_state *state, + struct ebt_table *table) { + unsigned int hook = state->hook; int i, nentries; struct ebt_entry *point; struct ebt_counter *counter_base, *cb_base; @@ -199,8 +200,8 @@ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, struct xt_action_param acpar; acpar.family = NFPROTO_BRIDGE; - acpar.in = in; - acpar.out = out; + acpar.in = state->in; + acpar.out = state->out; acpar.hotdrop = false; acpar.hooknum = hook; @@ -220,7 +221,7 @@ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, base = private->entries; i = 0; while (i < nentries) { - if (ebt_basic_match(point, skb, in, out)) + if (ebt_basic_match(point, skb, state->in, state->out)) goto letscontinue; if (EBT_MATCH_ITERATE(point, ebt_do_match, skb, &acpar) != 0) -- cgit v1.2.3 From 6cb8ff3f1a535b1d8eb5ea318932513d08eb3da7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:32:55 -0500 Subject: inet netfilter: Remove hook from ip6t_do_table, arp_do_table, ipt_do_table The values of ops->hooknum and state->hook are guaraneted to be equal making the hook argument to ip6t_do_table, arp_do_table, and ipt_do_table is unnecessary. Remove the unnecessary hook argument. In the callers use state->hook instead of ops->hooknum for clarity and to reduce the number of cachelines the callers touch. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_arp/arp_tables.h | 1 - include/linux/netfilter_ipv4/ip_tables.h | 1 - include/linux/netfilter_ipv6/ip6_tables.h | 1 - net/ipv4/netfilter/arp_tables.c | 2 +- net/ipv4/netfilter/arptable_filter.c | 3 +-- net/ipv4/netfilter/ip_tables.c | 2 +- net/ipv4/netfilter/iptable_filter.c | 5 ++--- net/ipv4/netfilter/iptable_mangle.c | 12 +++++------- net/ipv4/netfilter/iptable_nat.c | 3 +-- net/ipv4/netfilter/iptable_raw.c | 5 ++--- net/ipv4/netfilter/iptable_security.c | 5 ++--- net/ipv6/netfilter/ip6_tables.c | 2 +- net/ipv6/netfilter/ip6table_filter.c | 3 +-- net/ipv6/netfilter/ip6table_mangle.c | 12 +++++------- net/ipv6/netfilter/ip6table_nat.c | 3 +-- net/ipv6/netfilter/ip6table_raw.c | 3 +-- net/ipv6/netfilter/ip6table_security.c | 3 +-- 17 files changed, 25 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index c22a7fb8d0df..6f074db2f23d 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -53,7 +53,6 @@ extern struct xt_table *arpt_register_table(struct net *net, const struct arpt_replace *repl); extern void arpt_unregister_table(struct xt_table *table); extern unsigned int arpt_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 4073510da485..aa598f942c01 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -64,7 +64,6 @@ struct ipt_error { extern void *ipt_alloc_initial_table(const struct xt_table *); extern unsigned int ipt_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index b40d2b635778..0f76e5c674f9 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -30,7 +30,6 @@ extern struct xt_table *ip6t_register_table(struct net *net, const struct ip6t_replace *repl); extern void ip6t_unregister_table(struct net *net, struct xt_table *table); extern unsigned int ip6t_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 8f87fc38ccde..10eb2b297450 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -247,10 +247,10 @@ struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry) } unsigned int arpt_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table) { + unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); unsigned int verdict = NF_DROP; const struct arphdr *arp; diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index d217e4c19645..1352e12d4068 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -30,8 +30,7 @@ static unsigned int arptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - return arpt_do_table(skb, ops->hooknum, state, - state->net->ipv4.arptable_filter); + return arpt_do_table(skb, state, state->net->ipv4.arptable_filter); } static struct nf_hook_ops *arpfilter_ops __read_mostly; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 5d514eac4c31..2b049e135de8 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -285,10 +285,10 @@ struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry) /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ipt_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table) { + unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); const struct iphdr *ip; /* Initializing verdict to NF_DROP keeps gcc happy. */ diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 32feff32b116..02d4c5395d6e 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -36,14 +36,13 @@ static unsigned int iptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - if (ops->hooknum == NF_INET_LOCAL_OUT && + if (state->hook == NF_INET_LOCAL_OUT && (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr))) /* root is playing with raw sockets. */ return NF_ACCEPT; - return ipt_do_table(skb, ops->hooknum, state, - state->net->ipv4.iptable_filter); + return ipt_do_table(skb, state, state->net->ipv4.iptable_filter); } static struct nf_hook_ops *filter_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 4a5150fc9510..dc2ff6884999 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -58,8 +58,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) daddr = iph->daddr; tos = iph->tos; - ret = ipt_do_table(skb, NF_INET_LOCAL_OUT, state, - state->net->ipv4.iptable_mangle); + ret = ipt_do_table(skb, state, state->net->ipv4.iptable_mangle); /* Reroute for ANY change. */ if (ret != NF_DROP && ret != NF_STOLEN) { iph = ip_hdr(skb); @@ -83,14 +82,13 @@ iptable_mangle_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - if (ops->hooknum == NF_INET_LOCAL_OUT) + if (state->hook == NF_INET_LOCAL_OUT) return ipt_mangle_out(skb, state); - if (ops->hooknum == NF_INET_POST_ROUTING) - return ipt_do_table(skb, ops->hooknum, state, + if (state->hook == NF_INET_POST_ROUTING) + return ipt_do_table(skb, state, state->net->ipv4.iptable_mangle); /* PREROUTING/INPUT/FORWARD: */ - return ipt_do_table(skb, ops->hooknum, state, - state->net->ipv4.iptable_mangle); + return ipt_do_table(skb, state, state->net->ipv4.iptable_mangle); } static struct nf_hook_ops *mangle_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 4f4c64f81169..8ff63ac1f0d6 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -33,8 +33,7 @@ static unsigned int iptable_nat_do_chain(const struct nf_hook_ops *ops, const struct nf_hook_state *state, struct nf_conn *ct) { - return ipt_do_table(skb, ops->hooknum, state, - state->net->ipv4.nat_table); + return ipt_do_table(skb, state, state->net->ipv4.nat_table); } static unsigned int iptable_nat_ipv4_fn(const struct nf_hook_ops *ops, diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 20126e469ffb..bbb0523d87de 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -23,14 +23,13 @@ static unsigned int iptable_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - if (ops->hooknum == NF_INET_LOCAL_OUT && + if (state->hook == NF_INET_LOCAL_OUT && (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr))) /* root is playing with raw sockets. */ return NF_ACCEPT; - return ipt_do_table(skb, ops->hooknum, state, - state->net->ipv4.iptable_raw); + return ipt_do_table(skb, state, state->net->ipv4.iptable_raw); } static struct nf_hook_ops *rawtable_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 82fefd609b85..b92417038705 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -40,14 +40,13 @@ static unsigned int iptable_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - if (ops->hooknum == NF_INET_LOCAL_OUT && + if (state->hook == NF_INET_LOCAL_OUT && (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr))) /* Somebody is playing with raw sockets. */ return NF_ACCEPT; - return ipt_do_table(skb, ops->hooknum, state, - state->net->ipv4.iptable_security); + return ipt_do_table(skb, state, state->net->ipv4.iptable_security); } static struct nf_hook_ops *sectbl_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index cd9b401231d3..da6446b6e3f9 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -314,10 +314,10 @@ ip6t_next_entry(const struct ip6t_entry *entry) /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ip6t_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table) { + unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 2449005fb5dc..a7327f61b90c 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -35,8 +35,7 @@ static unsigned int ip6table_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip6t_do_table(skb, ops->hooknum, state, - state->net->ipv6.ip6table_filter); + return ip6t_do_table(skb, state, state->net->ipv6.ip6table_filter); } static struct nf_hook_ops *filter_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index a46dbf097d29..c2e061dcedf3 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -57,8 +57,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u_int32_t *)ipv6_hdr(skb)); - ret = ip6t_do_table(skb, NF_INET_LOCAL_OUT, state, - state->net->ipv6.ip6table_mangle); + ret = ip6t_do_table(skb, state, state->net->ipv6.ip6table_mangle); if (ret != NF_DROP && ret != NF_STOLEN && (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) || @@ -79,14 +78,13 @@ static unsigned int ip6table_mangle_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - if (ops->hooknum == NF_INET_LOCAL_OUT) + if (state->hook == NF_INET_LOCAL_OUT) return ip6t_mangle_out(skb, state); - if (ops->hooknum == NF_INET_POST_ROUTING) - return ip6t_do_table(skb, ops->hooknum, state, + if (state->hook == NF_INET_POST_ROUTING) + return ip6t_do_table(skb, state, state->net->ipv6.ip6table_mangle); /* INPUT/FORWARD */ - return ip6t_do_table(skb, ops->hooknum, state, - state->net->ipv6.ip6table_mangle); + return ip6t_do_table(skb, state, state->net->ipv6.ip6table_mangle); } static struct nf_hook_ops *mangle_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index a56451de127f..efa6754c4d06 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -35,8 +35,7 @@ static unsigned int ip6table_nat_do_chain(const struct nf_hook_ops *ops, const struct nf_hook_state *state, struct nf_conn *ct) { - return ip6t_do_table(skb, ops->hooknum, state, - state->net->ipv6.ip6table_nat); + return ip6t_do_table(skb, state, state->net->ipv6.ip6table_nat); } static unsigned int ip6table_nat_fn(const struct nf_hook_ops *ops, diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 18e831e35782..fac6ad7c0a7c 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -22,8 +22,7 @@ static unsigned int ip6table_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip6t_do_table(skb, ops->hooknum, state, - state->net->ipv6.ip6table_raw); + return ip6t_do_table(skb, state, state->net->ipv6.ip6table_raw); } static struct nf_hook_ops *rawtable_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 83bc96ae5d73..96c94fc240c8 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -39,8 +39,7 @@ static unsigned int ip6table_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip6t_do_table(skb, ops->hooknum, state, - state->net->ipv6.ip6table_security); + return ip6t_do_table(skb, state, state->net->ipv6.ip6table_security); } static struct nf_hook_ops *sectbl_ops __read_mostly; -- cgit v1.2.3 From 6aa187f21ca2d8ade791f01fd8fab908b1f27673 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:32:57 -0500 Subject: netfilter: nf_tables: kill nft_pktinfo.ops - Add nft_pktinfo.pf to replace ops->pf - Add nft_pktinfo.hook to replace ops->hooknum This simplifies the code, makes it more readable, and likely reduces cache line misses. Maintainability is enhanced as the details of nft_hook_ops are of no concern to the recpients of nft_pktinfo. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 9 ++++----- include/net/netfilter/nf_tables_ipv4.h | 3 +-- include/net/netfilter/nf_tables_ipv6.h | 3 +-- net/bridge/netfilter/nf_tables_bridge.c | 16 +++++++--------- net/bridge/netfilter/nft_reject_bridge.c | 12 ++++++------ net/ipv4/netfilter/nf_tables_arp.c | 2 +- net/ipv4/netfilter/nf_tables_ipv4.c | 2 +- net/ipv4/netfilter/nft_chain_nat_ipv4.c | 2 +- net/ipv4/netfilter/nft_chain_route_ipv4.c | 2 +- net/ipv4/netfilter/nft_dup_ipv4.c | 2 +- net/ipv4/netfilter/nft_masq_ipv4.c | 2 +- net/ipv4/netfilter/nft_redir_ipv4.c | 2 +- net/ipv4/netfilter/nft_reject_ipv4.c | 5 ++--- net/ipv6/netfilter/nf_tables_ipv6.c | 2 +- net/ipv6/netfilter/nft_chain_nat_ipv6.c | 2 +- net/ipv6/netfilter/nft_chain_route_ipv6.c | 2 +- net/ipv6/netfilter/nft_dup_ipv6.c | 2 +- net/ipv6/netfilter/nft_redir_ipv6.c | 3 +-- net/ipv6/netfilter/nft_reject_ipv6.c | 5 ++--- net/netfilter/nf_tables_core.c | 2 +- net/netfilter/nf_tables_netdev.c | 16 +++++++--------- net/netfilter/nft_log.c | 2 +- net/netfilter/nft_meta.c | 4 ++-- net/netfilter/nft_queue.c | 2 +- net/netfilter/nft_reject_inet.c | 14 +++++++------- 25 files changed, 54 insertions(+), 64 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index aa8bee72c9d3..c0899f97ff8d 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -16,7 +16,8 @@ struct nft_pktinfo { struct sk_buff *skb; const struct net_device *in; const struct net_device *out; - const struct nf_hook_ops *ops; + u8 pf; + u8 hook; u8 nhoff; u8 thoff; u8 tprot; @@ -25,16 +26,14 @@ struct nft_pktinfo { }; static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { pkt->skb = skb; pkt->in = pkt->xt.in = state->in; pkt->out = pkt->xt.out = state->out; - pkt->ops = ops; - pkt->xt.hooknum = ops->hooknum; - pkt->xt.family = ops->pf; + pkt->hook = pkt->xt.hooknum = state->hook; + pkt->pf = pkt->xt.family = state->pf; } /** diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index 2df7f96902ee..ca6ef6bf775e 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -6,13 +6,12 @@ static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { struct iphdr *ip; - nft_set_pktinfo(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); ip = ip_hdr(pkt->skb); pkt->tprot = ip->protocol; diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index 97db2e3a5e65..8ad39a6a5fe1 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -6,14 +6,13 @@ static inline int nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { int protohdr, thoff = 0; unsigned short frag_off; - nft_set_pktinfo(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); /* If malformed, drop it */ diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c index a343e62442b1..318d825e4207 100644 --- a/net/bridge/netfilter/nf_tables_bridge.c +++ b/net/bridge/netfilter/nf_tables_bridge.c @@ -65,27 +65,25 @@ int nft_bridge_ip6hdr_validate(struct sk_buff *skb) EXPORT_SYMBOL_GPL(nft_bridge_ip6hdr_validate); static inline void nft_bridge_set_pktinfo_ipv4(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { if (nft_bridge_iphdr_validate(skb)) - nft_set_pktinfo_ipv4(pkt, ops, skb, state); + nft_set_pktinfo_ipv4(pkt, skb, state); else - nft_set_pktinfo(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); } static inline void nft_bridge_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { #if IS_ENABLED(CONFIG_IPV6) if (nft_bridge_ip6hdr_validate(skb) && - nft_set_pktinfo_ipv6(pkt, ops, skb, state) == 0) + nft_set_pktinfo_ipv6(pkt, skb, state) == 0) return; #endif - nft_set_pktinfo(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); } static unsigned int @@ -97,13 +95,13 @@ nft_do_chain_bridge(const struct nf_hook_ops *ops, switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): - nft_bridge_set_pktinfo_ipv4(&pkt, ops, skb, state); + nft_bridge_set_pktinfo_ipv4(&pkt, skb, state); break; case htons(ETH_P_IPV6): - nft_bridge_set_pktinfo_ipv6(&pkt, ops, skb, state); + nft_bridge_set_pktinfo_ipv6(&pkt, skb, state); break; default: - nft_set_pktinfo(&pkt, ops, skb, state); + nft_set_pktinfo(&pkt, skb, state); break; } diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 858d848564ee..cee92612b2cc 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -273,16 +273,16 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr, switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: nft_reject_br_send_v4_unreach(pkt->skb, pkt->in, - pkt->ops->hooknum, + pkt->hook, priv->icmp_code); break; case NFT_REJECT_TCP_RST: nft_reject_br_send_v4_tcp_reset(pkt->skb, pkt->in, - pkt->ops->hooknum); + pkt->hook); break; case NFT_REJECT_ICMPX_UNREACH: nft_reject_br_send_v4_unreach(pkt->skb, pkt->in, - pkt->ops->hooknum, + pkt->hook, nft_reject_icmp_code(priv->icmp_code)); break; } @@ -291,16 +291,16 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr, switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: nft_reject_br_send_v6_unreach(net, pkt->skb, pkt->in, - pkt->ops->hooknum, + pkt->hook, priv->icmp_code); break; case NFT_REJECT_TCP_RST: nft_reject_br_send_v6_tcp_reset(net, pkt->skb, pkt->in, - pkt->ops->hooknum); + pkt->hook); break; case NFT_REJECT_ICMPX_UNREACH: nft_reject_br_send_v6_unreach(net, pkt->skb, pkt->in, - pkt->ops->hooknum, + pkt->hook, nft_reject_icmpv6_code(priv->icmp_code)); break; } diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c index 8412268bbad1..883bbf83fe09 100644 --- a/net/ipv4/netfilter/nf_tables_arp.c +++ b/net/ipv4/netfilter/nf_tables_arp.c @@ -21,7 +21,7 @@ nft_do_chain_arp(const struct nf_hook_ops *ops, { struct nft_pktinfo pkt; - nft_set_pktinfo(&pkt, ops, skb, state); + nft_set_pktinfo(&pkt, skb, state); return nft_do_chain(&pkt, ops); } diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c index aa180d3a69a5..805be5c9fcc3 100644 --- a/net/ipv4/netfilter/nf_tables_ipv4.c +++ b/net/ipv4/netfilter/nf_tables_ipv4.c @@ -24,7 +24,7 @@ static unsigned int nft_do_chain_ipv4(const struct nf_hook_ops *ops, { struct nft_pktinfo pkt; - nft_set_pktinfo_ipv4(&pkt, ops, skb, state); + nft_set_pktinfo_ipv4(&pkt, skb, state); return nft_do_chain(&pkt, ops); } diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c index bf5c30ae14e4..c3ffecf28d38 100644 --- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c @@ -33,7 +33,7 @@ static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops, { struct nft_pktinfo pkt; - nft_set_pktinfo_ipv4(&pkt, ops, skb, state); + nft_set_pktinfo_ipv4(&pkt, skb, state); return nft_do_chain(&pkt, ops); } diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c index e335b0afdaf3..2a1e3d8a3e43 100644 --- a/net/ipv4/netfilter/nft_chain_route_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c @@ -37,7 +37,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - nft_set_pktinfo_ipv4(&pkt, ops, skb, state); + nft_set_pktinfo_ipv4(&pkt, skb, state); mark = skb->mark; iph = ip_hdr(skb); diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index b45932d43b69..30bcf820e8bd 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -30,7 +30,7 @@ static void nft_dup_ipv4_eval(const struct nft_expr *expr, }; int oif = regs->data[priv->sreg_dev]; - nf_dup_ipv4(pkt->skb, pkt->ops->hooknum, &gw, oif); + nf_dup_ipv4(pkt->skb, pkt->hook, &gw, oif); } static int nft_dup_ipv4_init(const struct nft_ctx *ctx, diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c index 40e414c4ca56..b72ffc58e255 100644 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ b/net/ipv4/netfilter/nft_masq_ipv4.c @@ -26,7 +26,7 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); range.flags = priv->flags; - regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, pkt->ops->hooknum, + regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, pkt->hook, &range, pkt->out); } diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c index d8d795df9c13..c09d4381427e 100644 --- a/net/ipv4/netfilter/nft_redir_ipv4.c +++ b/net/ipv4/netfilter/nft_redir_ipv4.c @@ -36,7 +36,7 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr, mr.range[0].flags |= priv->flags; regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &mr, - pkt->ops->hooknum); + pkt->hook); } static struct nft_expr_type nft_redir_ipv4_type; diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index b07e58b51158..c1582e03b628 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -27,11 +27,10 @@ static void nft_reject_ipv4_eval(const struct nft_expr *expr, switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nf_send_unreach(pkt->skb, priv->icmp_code, - pkt->ops->hooknum); + nf_send_unreach(pkt->skb, priv->icmp_code, pkt->hook); break; case NFT_REJECT_TCP_RST: - nf_send_reset(pkt->skb, pkt->ops->hooknum); + nf_send_reset(pkt->skb, pkt->hook); break; default: break; diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c index c8148ba76d1a..41340b794f9b 100644 --- a/net/ipv6/netfilter/nf_tables_ipv6.c +++ b/net/ipv6/netfilter/nf_tables_ipv6.c @@ -23,7 +23,7 @@ static unsigned int nft_do_chain_ipv6(const struct nf_hook_ops *ops, struct nft_pktinfo pkt; /* malformed packet, drop it */ - if (nft_set_pktinfo_ipv6(&pkt, ops, skb, state) < 0) + if (nft_set_pktinfo_ipv6(&pkt, skb, state) < 0) return NF_DROP; return nft_do_chain(&pkt, ops); diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c index 951bb458b7bd..e96feaefeb14 100644 --- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c @@ -31,7 +31,7 @@ static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops, { struct nft_pktinfo pkt; - nft_set_pktinfo_ipv6(&pkt, ops, skb, state); + nft_set_pktinfo_ipv6(&pkt, skb, state); return nft_do_chain(&pkt, ops); } diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c index 0dafdaac5e17..d1bcd2ed7bcc 100644 --- a/net/ipv6/netfilter/nft_chain_route_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c @@ -33,7 +33,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, u32 mark, flowlabel; /* malformed packet, drop it */ - if (nft_set_pktinfo_ipv6(&pkt, ops, skb, state) < 0) + if (nft_set_pktinfo_ipv6(&pkt, skb, state) < 0) return NF_DROP; /* save source/dest address, mark, hoplimit, flowlabel, priority */ diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index 0eaa4f65fdea..c81204faf15d 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -28,7 +28,7 @@ static void nft_dup_ipv6_eval(const struct nft_expr *expr, struct in6_addr *gw = (struct in6_addr *)®s->data[priv->sreg_addr]; int oif = regs->data[priv->sreg_dev]; - nf_dup_ipv6(pkt->skb, pkt->ops->hooknum, gw, oif); + nf_dup_ipv6(pkt->skb, pkt->hook, gw, oif); } static int nft_dup_ipv6_init(const struct nft_ctx *ctx, diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c index effd393bd517..aca44e89a881 100644 --- a/net/ipv6/netfilter/nft_redir_ipv6.c +++ b/net/ipv6/netfilter/nft_redir_ipv6.c @@ -35,8 +35,7 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr, range.flags |= priv->flags; - regs->verdict.code = nf_nat_redirect_ipv6(pkt->skb, &range, - pkt->ops->hooknum); + regs->verdict.code = nf_nat_redirect_ipv6(pkt->skb, &range, pkt->hook); } static struct nft_expr_type nft_redir_ipv6_type; diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c index d0d1540ecf87..ffcac7d5da43 100644 --- a/net/ipv6/netfilter/nft_reject_ipv6.c +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -28,11 +28,10 @@ static void nft_reject_ipv6_eval(const struct nft_expr *expr, switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nf_send_unreach6(net, pkt->skb, priv->icmp_code, - pkt->ops->hooknum); + nf_send_unreach6(net, pkt->skb, priv->icmp_code, pkt->hook); break; case NFT_REJECT_TCP_RST: - nf_send_reset6(net, pkt->skb, pkt->ops->hooknum); + nf_send_reset6(net, pkt->skb, pkt->hook); break; default: break; diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 05d0b03530f6..539083099c0d 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -50,7 +50,7 @@ static void __nft_trace_packet(const struct nft_pktinfo *pkt, { struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); - nf_log_trace(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in, + nf_log_trace(net, pkt->pf, pkt->hook, pkt->skb, pkt->in, pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", chain->table->name, chain->name, comments[type], rulenum); diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c index 2cae4d4a03b7..db416a3396e9 100644 --- a/net/netfilter/nf_tables_netdev.c +++ b/net/netfilter/nf_tables_netdev.c @@ -17,13 +17,13 @@ static inline void nft_netdev_set_pktinfo_ipv4(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, + struct sk_buff *skb, const struct nf_hook_state *state) { struct iphdr *iph, _iph; u32 len, thoff; - nft_set_pktinfo(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph), &_iph); @@ -48,7 +48,6 @@ nft_netdev_set_pktinfo_ipv4(struct nft_pktinfo *pkt, static inline void __nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -82,12 +81,11 @@ __nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, } static inline void nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - nft_set_pktinfo(pkt, ops, skb, state); - __nft_netdev_set_pktinfo_ipv6(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); + __nft_netdev_set_pktinfo_ipv6(pkt, skb, state); } static unsigned int @@ -98,13 +96,13 @@ nft_do_chain_netdev(const struct nf_hook_ops *ops, struct sk_buff *skb, switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): - nft_netdev_set_pktinfo_ipv4(&pkt, ops, skb, state); + nft_netdev_set_pktinfo_ipv4(&pkt, skb, state); break; case htons(ETH_P_IPV6): - nft_netdev_set_pktinfo_ipv6(&pkt, ops, skb, state); + nft_netdev_set_pktinfo_ipv6(&pkt, skb, state); break; default: - nft_set_pktinfo(&pkt, ops, skb, state); + nft_set_pktinfo(&pkt, skb, state); break; } diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index a13d6a386d63..c7c7df85f0b7 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -33,7 +33,7 @@ static void nft_log_eval(const struct nft_expr *expr, const struct nft_log *priv = nft_expr_priv(expr); struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); - nf_log_packet(net, pkt->ops->pf, pkt->ops->hooknum, pkt->skb, pkt->in, + nf_log_packet(net, pkt->pf, pkt->hook, pkt->skb, pkt->in, pkt->out, &priv->loginfo, "%s", priv->prefix); } diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index cb2f13ebb5a6..e4ad2c24bc41 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -42,7 +42,7 @@ void nft_meta_get_eval(const struct nft_expr *expr, *(__be16 *)dest = skb->protocol; break; case NFT_META_NFPROTO: - *dest = pkt->ops->pf; + *dest = pkt->pf; break; case NFT_META_L4PROTO: *dest = pkt->tprot; @@ -135,7 +135,7 @@ void nft_meta_get_eval(const struct nft_expr *expr, break; } - switch (pkt->ops->pf) { + switch (pkt->pf) { case NFPROTO_IPV4: if (ipv4_is_multicast(ip_hdr(skb)->daddr)) *dest = PACKET_MULTICAST; diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index 96805d21d618..61d216eb7917 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -42,7 +42,7 @@ static void nft_queue_eval(const struct nft_expr *expr, queue = priv->queuenum + cpu % priv->queues_total; } else { queue = nfqueue_hash(pkt->skb, queue, - priv->queues_total, pkt->ops->pf, + priv->queues_total, pkt->pf, jhash_initval); } } diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 635dbba93d01..dea6750af6ff 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -24,20 +24,20 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, struct nft_reject *priv = nft_expr_priv(expr); struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out); - switch (pkt->ops->pf) { + switch (pkt->pf) { case NFPROTO_IPV4: switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: nf_send_unreach(pkt->skb, priv->icmp_code, - pkt->ops->hooknum); + pkt->hook); break; case NFT_REJECT_TCP_RST: - nf_send_reset(pkt->skb, pkt->ops->hooknum); + nf_send_reset(pkt->skb, pkt->hook); break; case NFT_REJECT_ICMPX_UNREACH: nf_send_unreach(pkt->skb, nft_reject_icmp_code(priv->icmp_code), - pkt->ops->hooknum); + pkt->hook); break; } break; @@ -45,15 +45,15 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: nf_send_unreach6(net, pkt->skb, priv->icmp_code, - pkt->ops->hooknum); + pkt->hook); break; case NFT_REJECT_TCP_RST: - nf_send_reset6(net, pkt->skb, pkt->ops->hooknum); + nf_send_reset6(net, pkt->skb, pkt->hook); break; case NFT_REJECT_ICMPX_UNREACH: nf_send_unreach6(net, pkt->skb, nft_reject_icmpv6_code(priv->icmp_code), - pkt->ops->hooknum); + pkt->hook); break; } break; -- cgit v1.2.3 From 156c196f6038610770588a708b9e0f7df2ead74a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:32:58 -0500 Subject: netfilter: x_tables: Pass struct net in xt_action_param As xt_action_param lives on the stack this does not bloat any persistent data structures. This is a first step in making netfilter code that needs to know which network namespace it is executing in simpler. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 3 ++- include/net/netfilter/nf_tables.h | 1 + net/bridge/netfilter/ebtables.c | 1 + net/ipv4/netfilter/arp_tables.c | 1 + net/ipv4/netfilter/ip_tables.c | 1 + net/ipv6/netfilter/ip6_tables.c | 1 + net/sched/act_ipt.c | 1 + net/sched/em_ipset.c | 1 + 8 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index b006b719183f..c5577410c25d 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -13,6 +13,7 @@ * @target: the target extension * @matchinfo: per-match data * @targetinfo: per-target data + * @net network namespace through which the action was invoked * @in: input netdevice * @out: output netdevice * @fragoff: packet is a fragment, this is the data offset @@ -24,7 +25,6 @@ * Fields written to by extensions: * * @hotdrop: drop packet if we had inspection problems - * Network namespace obtainable using dev_net(in/out) */ struct xt_action_param { union { @@ -34,6 +34,7 @@ struct xt_action_param { union { const void *matchinfo, *targinfo; }; + struct net *net; const struct net_device *in, *out; int fragoff; unsigned int thoff; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c0899f97ff8d..c0516529e8a0 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -30,6 +30,7 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_state *state) { pkt->skb = skb; + pkt->xt.net = state->net; pkt->in = pkt->xt.in = state->in; pkt->out = pkt->xt.out = state->out; pkt->hook = pkt->xt.hooknum = state->hook; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 8d5a3975b963..f46ca417bf2d 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -200,6 +200,7 @@ unsigned int ebt_do_table(struct sk_buff *skb, struct xt_action_param acpar; acpar.family = NFPROTO_BRIDGE; + acpar.net = state->net; acpar.in = state->in; acpar.out = state->out; acpar.hotdrop = false; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 10eb2b297450..2dad3e1c5f11 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -285,6 +285,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, */ e = get_entry(table_base, private->hook_entry[hook]); + acpar.net = state->net; acpar.in = state->in; acpar.out = state->out; acpar.hooknum = hook; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2b049e135de8..42d0946956db 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -315,6 +315,7 @@ ipt_do_table(struct sk_buff *skb, acpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET; acpar.thoff = ip_hdrlen(skb); acpar.hotdrop = false; + acpar.net = state->net; acpar.in = state->in; acpar.out = state->out; acpar.family = NFPROTO_IPV4; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index da6446b6e3f9..80e3bd72b715 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -340,6 +340,7 @@ ip6t_do_table(struct sk_buff *skb, * rule is also a fragment-specific rule, non-fragments won't * match it. */ acpar.hotdrop = false; + acpar.net = state->net; acpar.in = state->in; acpar.out = state->out; acpar.family = NFPROTO_IPV6; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 99c9cc1c7af9..d05869646515 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -189,6 +189,7 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, * worry later - danger - this API seems to have changed * from earlier kernels */ + par.net = dev_net(skb->dev); par.in = skb->dev; par.out = NULL; par.hooknum = ipt->tcfi_hook; diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c index df0328ba6a48..c66ca9400ab4 100644 --- a/net/sched/em_ipset.c +++ b/net/sched/em_ipset.c @@ -95,6 +95,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em, if (skb->skb_iif) indev = dev_get_by_index_rcu(em->net, skb->skb_iif); + acpar.net = em->net; acpar.in = indev ? indev : dev; acpar.out = dev; -- cgit v1.2.3 From 46448d0093ba18a212e314fd9ea029e740baa476 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:33:00 -0500 Subject: netfilter: nf_tables: Pass struct net in nft_pktinfo nft_pktinfo is passed on the stack so this does not bloat any in core data structures. By centrally computing this information this makes maintence of the code simpler, and understading of the code easier. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c0516529e8a0..42e239e55aa3 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -14,6 +14,7 @@ struct nft_pktinfo { struct sk_buff *skb; + struct net *net; const struct net_device *in; const struct net_device *out; u8 pf; @@ -30,7 +31,7 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_state *state) { pkt->skb = skb; - pkt->xt.net = state->net; + pkt->net = pkt->xt.net = state->net; pkt->in = pkt->xt.in = state->in; pkt->out = pkt->xt.out = state->out; pkt->hook = pkt->xt.hooknum = state->hook; -- cgit v1.2.3 From 206e8c00752fbe9cc463184236ac64b2a532cda5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:33:02 -0500 Subject: netfilter: Pass net to nf_dup_ipv4 and nf_dup_ipv6 This allows them to stop guessing the network namespace with pick_net. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/ipv4/nf_dup_ipv4.h | 2 +- include/net/netfilter/ipv6/nf_dup_ipv6.h | 2 +- net/ipv4/netfilter/nf_dup_ipv4.c | 23 ++++------------------- net/ipv4/netfilter/nft_dup_ipv4.c | 2 +- net/ipv6/netfilter/nf_dup_ipv6.c | 23 ++++------------------- net/ipv6/netfilter/nft_dup_ipv6.c | 2 +- net/netfilter/xt_TEE.c | 4 ++-- 7 files changed, 14 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/ipv4/nf_dup_ipv4.h b/include/net/netfilter/ipv4/nf_dup_ipv4.h index 42008f10dfc4..0a14733e8b82 100644 --- a/include/net/netfilter/ipv4/nf_dup_ipv4.h +++ b/include/net/netfilter/ipv4/nf_dup_ipv4.h @@ -1,7 +1,7 @@ #ifndef _NF_DUP_IPV4_H_ #define _NF_DUP_IPV4_H_ -void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum, +void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in_addr *gw, int oif); #endif /* _NF_DUP_IPV4_H_ */ diff --git a/include/net/netfilter/ipv6/nf_dup_ipv6.h b/include/net/netfilter/ipv6/nf_dup_ipv6.h index ed6bd66fa5a0..fa6237b382a3 100644 --- a/include/net/netfilter/ipv6/nf_dup_ipv6.h +++ b/include/net/netfilter/ipv6/nf_dup_ipv6.h @@ -1,7 +1,7 @@ #ifndef _NF_DUP_IPV6_H_ #define _NF_DUP_IPV6_H_ -void nf_dup_ipv6(struct sk_buff *skb, unsigned int hooknum, +void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in6_addr *gw, int oif); #endif /* _NF_DUP_IPV6_H_ */ diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c index 2d79e6e8d934..ce2a59e5c665 100644 --- a/net/ipv4/netfilter/nf_dup_ipv4.c +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -23,25 +23,10 @@ #include #endif -static struct net *pick_net(struct sk_buff *skb) -{ -#ifdef CONFIG_NET_NS - const struct dst_entry *dst; - - if (skb->dev != NULL) - return dev_net(skb->dev); - dst = skb_dst(skb); - if (dst != NULL && dst->dev != NULL) - return dev_net(dst->dev); -#endif - return &init_net; -} - -static bool nf_dup_ipv4_route(struct sk_buff *skb, const struct in_addr *gw, - int oif) +static bool nf_dup_ipv4_route(struct net *net, struct sk_buff *skb, + const struct in_addr *gw, int oif) { const struct iphdr *iph = ip_hdr(skb); - struct net *net = pick_net(skb); struct rtable *rt; struct flowi4 fl4; @@ -65,7 +50,7 @@ static bool nf_dup_ipv4_route(struct sk_buff *skb, const struct in_addr *gw, return true; } -void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum, +void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in_addr *gw, int oif) { struct iphdr *iph; @@ -105,7 +90,7 @@ void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum, --iph->ttl; ip_send_check(iph); - if (nf_dup_ipv4_route(skb, gw, oif)) { + if (nf_dup_ipv4_route(net, skb, gw, oif)) { __this_cpu_write(nf_skb_duplicated, true); ip_local_out(skb); __this_cpu_write(nf_skb_duplicated, false); diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index 30bcf820e8bd..bf855e64fc45 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -30,7 +30,7 @@ static void nft_dup_ipv4_eval(const struct nft_expr *expr, }; int oif = regs->data[priv->sreg_dev]; - nf_dup_ipv4(pkt->skb, pkt->hook, &gw, oif); + nf_dup_ipv4(pkt->net, pkt->skb, pkt->hook, &gw, oif); } static int nft_dup_ipv4_init(const struct nft_ctx *ctx, diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c index c8ab626556a0..ee0d9a5b16c3 100644 --- a/net/ipv6/netfilter/nf_dup_ipv6.c +++ b/net/ipv6/netfilter/nf_dup_ipv6.c @@ -19,25 +19,10 @@ #include #endif -static struct net *pick_net(struct sk_buff *skb) -{ -#ifdef CONFIG_NET_NS - const struct dst_entry *dst; - - if (skb->dev != NULL) - return dev_net(skb->dev); - dst = skb_dst(skb); - if (dst != NULL && dst->dev != NULL) - return dev_net(dst->dev); -#endif - return &init_net; -} - -static bool nf_dup_ipv6_route(struct sk_buff *skb, const struct in6_addr *gw, - int oif) +static bool nf_dup_ipv6_route(struct net *net, struct sk_buff *skb, + const struct in6_addr *gw, int oif) { const struct ipv6hdr *iph = ipv6_hdr(skb); - struct net *net = pick_net(skb); struct dst_entry *dst; struct flowi6 fl6; @@ -61,7 +46,7 @@ static bool nf_dup_ipv6_route(struct sk_buff *skb, const struct in6_addr *gw, return true; } -void nf_dup_ipv6(struct sk_buff *skb, unsigned int hooknum, +void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in6_addr *gw, int oif) { if (this_cpu_read(nf_skb_duplicated)) @@ -81,7 +66,7 @@ void nf_dup_ipv6(struct sk_buff *skb, unsigned int hooknum, struct ipv6hdr *iph = ipv6_hdr(skb); --iph->hop_limit; } - if (nf_dup_ipv6_route(skb, gw, oif)) { + if (nf_dup_ipv6_route(net, skb, gw, oif)) { __this_cpu_write(nf_skb_duplicated, true); ip6_local_out(skb); __this_cpu_write(nf_skb_duplicated, false); diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index c81204faf15d..8bfd470cbe72 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -28,7 +28,7 @@ static void nft_dup_ipv6_eval(const struct nft_expr *expr, struct in6_addr *gw = (struct in6_addr *)®s->data[priv->sreg_addr]; int oif = regs->data[priv->sreg_dev]; - nf_dup_ipv6(pkt->skb, pkt->hook, gw, oif); + nf_dup_ipv6(pkt->net, pkt->skb, pkt->hook, gw, oif); } static int nft_dup_ipv6_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index fd980aa7715d..899b06115fc5 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -32,7 +32,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; - nf_dup_ipv4(skb, par->hooknum, &info->gw.in, info->priv->oif); + nf_dup_ipv4(par->net, skb, par->hooknum, &info->gw.in, info->priv->oif); return XT_CONTINUE; } @@ -43,7 +43,7 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; - nf_dup_ipv6(skb, par->hooknum, &info->gw.in6, info->priv->oif); + nf_dup_ipv6(par->net, skb, par->hooknum, &info->gw.in6, info->priv->oif); return XT_CONTINUE; } -- cgit v1.2.3 From a4ffe319ae72034e3f3332698a2fd83b6f063b18 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:33:03 -0500 Subject: act_connmark: Remember the struct net instead of guessing it. Stop guessing the struct net instead of remember it. Guessing is just silly and will be problematic in the future when I implement routes between network namespaces. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/tc_act/tc_connmark.h | 1 + net/sched/act_connmark.c | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tc_act/tc_connmark.h b/include/net/tc_act/tc_connmark.h index 5c1104c2e24f..02caa406611b 100644 --- a/include/net/tc_act/tc_connmark.h +++ b/include/net/tc_act/tc_connmark.h @@ -5,6 +5,7 @@ struct tcf_connmark_info { struct tcf_common common; + struct net *net; u16 zone; }; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 5019a47b9270..413ac39147d8 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -74,7 +74,7 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, zone.id = ca->zone; zone.dir = NF_CT_DEFAULT_ZONE_DIR; - thash = nf_conntrack_find_get(dev_net(skb->dev), &zone, &tuple); + thash = nf_conntrack_find_get(ca->net, &zone, &tuple); if (!thash) goto out; @@ -119,6 +119,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, ci = to_connmark(a); ci->tcf_action = parm->action; + ci->net = net; ci->zone = parm->zone; tcf_hash_insert(a); -- cgit v1.2.3 From a31f1adc0948930fba9ab5a111ccd735a5d864c6 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:33:04 -0500 Subject: netfilter: nf_conntrack: Add a struct net parameter to l4_pkt_to_tuple As gre does not have the srckey in the packet gre_pkt_to_tuple needs to perform a lookup in it's per network namespace tables. Pass in the proper network namespace to all pkt_to_tuple implementations to ensure gre (and any similar protocols) can get this right. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 3 ++- include/net/netfilter/nf_conntrack_core.h | 1 + include/net/netfilter/nf_conntrack_l4proto.h | 2 +- net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 4 ++-- net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 3 ++- net/netfilter/nf_conntrack_core.c | 10 ++++++---- net/netfilter/nf_conntrack_proto_dccp.c | 2 +- net/netfilter/nf_conntrack_proto_generic.c | 2 +- net/netfilter/nf_conntrack_proto_gre.c | 3 +-- net/netfilter/nf_conntrack_proto_sctp.c | 2 +- net/netfilter/nf_conntrack_proto_tcp.c | 2 +- net/netfilter/nf_conntrack_proto_udp.c | 1 + net/netfilter/nf_conntrack_proto_udplite.c | 1 + net/netfilter/xt_connlimit.c | 2 +- net/openvswitch/conntrack.c | 2 +- net/sched/act_connmark.c | 2 +- 16 files changed, 24 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index e8ad46834df8..d642f68a7c73 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -191,7 +191,8 @@ int nf_conntrack_hash_check_insert(struct nf_conn *ct); bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report); bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, - u_int16_t l3num, struct nf_conntrack_tuple *tuple); + u_int16_t l3num, struct net *net, + struct nf_conntrack_tuple *tuple); bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig); diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index c03f9c42b3cd..788ef58a66b9 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -41,6 +41,7 @@ void nf_conntrack_cleanup_end(void); bool nf_ct_get_tuple(const struct sk_buff *skb, unsigned int nhoff, unsigned int dataoff, u_int16_t l3num, u_int8_t protonum, + struct net *net, struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto); diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 1f7061313d54..956d8a6ac069 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -26,7 +26,7 @@ struct nf_conntrack_l4proto { /* Try to fill in the third arg: dataoff is offset past network protocol hdr. Return true if possible. */ bool (*pkt_to_tuple)(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple); + struct net *net, struct nf_conntrack_tuple *tuple); /* Invert the per-proto part of the tuple: ie. turn xmit into reply. * Some packets can't be inverted: return 0 in that case. diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index cdde3ec496e9..c567e1b5d799 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -30,7 +30,7 @@ static inline struct nf_icmp_net *icmp_pernet(struct net *net) } static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple) + struct net *net, struct nf_conntrack_tuple *tuple) { const struct icmphdr *hp; struct icmphdr _hdr; @@ -144,7 +144,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb) + ip_hdrlen(skb) + sizeof(struct icmphdr), - PF_INET, &origtuple)) { + PF_INET, net, &origtuple)) { pr_debug("icmp_error_message: failed to get tuple\n"); return -NF_ACCEPT; } diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 0e6fae103d33..d3b797446cea 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -36,6 +36,7 @@ static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple) { const struct icmp6hdr *hp; @@ -159,7 +160,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, skb_network_offset(skb) + sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr), - PF_INET6, &origtuple)) { + PF_INET6, net, &origtuple)) { pr_debug("icmpv6_error: Can't get tuple\n"); return -NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c09d6c7198f6..09d1d19b2ab9 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -168,6 +168,7 @@ nf_ct_get_tuple(const struct sk_buff *skb, unsigned int dataoff, u_int16_t l3num, u_int8_t protonum, + struct net *net, struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto) @@ -181,12 +182,13 @@ nf_ct_get_tuple(const struct sk_buff *skb, tuple->dst.protonum = protonum; tuple->dst.dir = IP_CT_DIR_ORIGINAL; - return l4proto->pkt_to_tuple(skb, dataoff, tuple); + return l4proto->pkt_to_tuple(skb, dataoff, net, tuple); } EXPORT_SYMBOL_GPL(nf_ct_get_tuple); bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, - u_int16_t l3num, struct nf_conntrack_tuple *tuple) + u_int16_t l3num, + struct net *net, struct nf_conntrack_tuple *tuple) { struct nf_conntrack_l3proto *l3proto; struct nf_conntrack_l4proto *l4proto; @@ -205,7 +207,7 @@ bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, l4proto = __nf_ct_l4proto_find(l3num, protonum); - ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, tuple, + ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple, l3proto, l4proto); rcu_read_unlock(); @@ -1029,7 +1031,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, u32 hash; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), - dataoff, l3num, protonum, &tuple, l3proto, + dataoff, l3num, protonum, net, &tuple, l3proto, l4proto)) { pr_debug("resolve_normal_ct: Can't get tuple\n"); return NULL; diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 6dd995c7c72b..fce1b1cca32d 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -398,7 +398,7 @@ static inline struct dccp_net *dccp_pernet(struct net *net) } static bool dccp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple) + struct net *net, struct nf_conntrack_tuple *tuple) { struct dccp_hdr _hdr, *dh; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 2281be419a74..86dc752e5349 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -45,7 +45,7 @@ static inline struct nf_generic_net *generic_pernet(struct net *net) static bool generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple) + struct net *net, struct nf_conntrack_tuple *tuple) { tuple->src.u.all = 0; tuple->dst.u.all = 0; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 7648674f29c3..a96451a7af20 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -190,9 +190,8 @@ static bool gre_invert_tuple(struct nf_conntrack_tuple *tuple, /* gre hdr info to tuple */ static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple) + struct net *net, struct nf_conntrack_tuple *tuple) { - struct net *net = dev_net(skb->dev ? skb->dev : skb_dst(skb)->dev); const struct gre_hdr_pptp *pgrehdr; struct gre_hdr_pptp _pgrehdr; __be16 srckey; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 67197731eb68..9578a7c371ef 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -156,7 +156,7 @@ static inline struct sctp_net *sctp_pernet(struct net *net) } static bool sctp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple) + struct net *net, struct nf_conntrack_tuple *tuple) { const struct sctphdr *hp; struct sctphdr _hdr; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 70383de72054..278f3b9356ef 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -277,7 +277,7 @@ static inline struct nf_tcp_net *tcp_pernet(struct net *net) } static bool tcp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple) + struct net *net, struct nf_conntrack_tuple *tuple) { const struct tcphdr *hp; struct tcphdr _hdr; diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 6957281ffee5..478f92f834b6 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -38,6 +38,7 @@ static inline struct nf_udp_net *udp_pernet(struct net *net) static bool udp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple) { const struct udphdr *hp; diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index c5903d1649f9..1ac8ee13a873 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -48,6 +48,7 @@ static inline struct udplite_net *udplite_pernet(struct net *net) static bool udplite_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple) { const struct udphdr *hp; diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 213db252e5be..99bbc829868d 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -332,7 +332,7 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; zone = nf_ct_zone(ct); } else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), - par->family, &tuple)) { + par->family, net, &tuple)) { goto hotdrop; } diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index e8e524ad8a01..aaf5cbd6d9ae 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -345,7 +345,7 @@ ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone, { struct nf_conntrack_tuple tuple; - if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, &tuple)) + if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, net, &tuple)) return NULL; return __nf_ct_expect_find(net, zone, &tuple); } diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 413ac39147d8..bb41699c6c49 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -68,7 +68,7 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, } if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), - proto, &tuple)) + proto, ca->net, &tuple)) goto out; zone.id = ca->zone; -- cgit v1.2.3 From 06198b34a3e09e06d9aecaa3727e0d37206cea77 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:33:06 -0500 Subject: netfilter: Pass priv instead of nf_hook_ops to netfilter hooks Only pass the void *priv parameter out of the nf_hook_ops. That is all any of the functions are interested now, and by limiting what is passed it becomes simpler to change implementation details. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 +- include/net/netfilter/br_netfilter.h | 2 +- include/net/netfilter/nf_nat_l3proto.h | 32 +++++++++++++------------- include/net/netfilter/nf_tables.h | 3 +-- net/bridge/br_netfilter_hooks.c | 14 +++++------ net/bridge/br_netfilter_ipv6.c | 2 +- net/bridge/netfilter/ebtable_filter.c | 4 ++-- net/bridge/netfilter/ebtable_nat.c | 4 ++-- net/bridge/netfilter/nf_tables_bridge.c | 4 ++-- net/decnet/netfilter/dn_rtmsg.c | 2 +- net/ipv4/netfilter/arptable_filter.c | 2 +- net/ipv4/netfilter/ipt_CLUSTERIP.c | 2 +- net/ipv4/netfilter/ipt_SYNPROXY.c | 2 +- net/ipv4/netfilter/iptable_filter.c | 2 +- net/ipv4/netfilter/iptable_mangle.c | 2 +- net/ipv4/netfilter/iptable_nat.c | 18 +++++++-------- net/ipv4/netfilter/iptable_raw.c | 2 +- net/ipv4/netfilter/iptable_security.c | 2 +- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 8 +++---- net/ipv4/netfilter/nf_defrag_ipv4.c | 2 +- net/ipv4/netfilter/nf_nat_l3proto_ipv4.c | 24 +++++++++---------- net/ipv4/netfilter/nf_tables_arp.c | 4 ++-- net/ipv4/netfilter/nf_tables_ipv4.c | 8 +++---- net/ipv4/netfilter/nft_chain_nat_ipv4.c | 20 ++++++++-------- net/ipv4/netfilter/nft_chain_route_ipv4.c | 4 ++-- net/ipv6/netfilter/ip6t_SYNPROXY.c | 2 +- net/ipv6/netfilter/ip6table_filter.c | 2 +- net/ipv6/netfilter/ip6table_mangle.c | 2 +- net/ipv6/netfilter/ip6table_nat.c | 18 +++++++-------- net/ipv6/netfilter/ip6table_raw.c | 2 +- net/ipv6/netfilter/ip6table_security.c | 2 +- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 8 +++---- net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 2 +- net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 24 +++++++++---------- net/ipv6/netfilter/nf_tables_ipv6.c | 8 +++---- net/ipv6/netfilter/nft_chain_nat_ipv6.c | 20 ++++++++-------- net/ipv6/netfilter/nft_chain_route_ipv6.c | 4 ++-- net/netfilter/core.c | 2 +- net/netfilter/ipvs/ip_vs_core.c | 24 +++++++++---------- net/netfilter/nf_tables_core.c | 4 ++-- net/netfilter/nf_tables_netdev.c | 4 ++-- security/selinux/hooks.c | 10 ++++---- security/smack/smack_netfilter.c | 4 ++-- 43 files changed, 156 insertions(+), 157 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 0b4d4560f33d..987c74cd523c 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -80,7 +80,7 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, p->okfn = okfn; } -typedef unsigned int nf_hookfn(const struct nf_hook_ops *ops, +typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index 8fe266504900..c93c75fa41ad 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -46,7 +46,7 @@ void br_netfilter_enable(void); #if IS_ENABLED(CONFIG_IPV6) int br_validate_ipv6(struct sk_buff *skb); -unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, +unsigned int br_nf_pre_routing_ipv6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); #else diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h index a3127325f624..aef3e5fc9fd9 100644 --- a/include/net/netfilter/nf_nat_l3proto.h +++ b/include/net/netfilter/nf_nat_l3proto.h @@ -43,31 +43,31 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum); -unsigned int nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv4_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, +unsigned int nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); @@ -76,31 +76,31 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, unsigned int hdrlen); -unsigned int nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, +unsigned int nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 42e239e55aa3..c9149cc0a02d 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -816,8 +816,7 @@ int nft_register_basechain(struct nft_base_chain *basechain, void nft_unregister_basechain(struct nft_base_chain *basechain, unsigned int hook_nops); -unsigned int nft_do_chain(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops); +unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); /** * struct nft_table - nf_tables table diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index e6e76bbdc82f..e21e44c13e07 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -464,7 +464,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb) * receiving device) to make netfilter happy, the REDIRECT * target in particular. Save the original destination IP * address to be able to detect DNAT afterwards. */ -static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, +static unsigned int br_nf_pre_routing(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -486,7 +486,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, return NF_ACCEPT; nf_bridge_pull_encap_header_rcsum(skb); - return br_nf_pre_routing_ipv6(ops, skb, state); + return br_nf_pre_routing_ipv6(priv, skb, state); } if (!brnf_call_iptables && !br->nf_call_iptables) @@ -526,7 +526,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, * took place when the packet entered the bridge), but we * register an IPv4 PRE_ROUTING 'sabotage' hook that will * prevent this from happening. */ -static unsigned int br_nf_local_in(const struct nf_hook_ops *ops, +static unsigned int br_nf_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -570,7 +570,7 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff * but we are still able to filter on the 'real' indev/outdev * because of the physdev module. For ARP, indev and outdev are the * bridge ports. */ -static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, +static unsigned int br_nf_forward_ip(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -633,7 +633,7 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, return NF_STOLEN; } -static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops, +static unsigned int br_nf_forward_arp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -801,7 +801,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff } /* PF_BRIDGE/POST_ROUTING ********************************************/ -static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, +static unsigned int br_nf_post_routing(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -850,7 +850,7 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, /* IP/SABOTAGE *****************************************************/ /* Don't hand locally destined packets to PF_INET(6)/PRE_ROUTING * for the second time. */ -static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops, +static unsigned int ip_sabotage_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index e4dbbe44c724..c51cc3fd50d9 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -218,7 +218,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc /* Replicate the checks that IPv6 does on packet reception and pass the packet * to ip6tables. */ -unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, +unsigned int br_nf_pre_routing_ipv6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 118ce40ac181..f9242dffa65e 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -57,14 +57,14 @@ static const struct ebt_table frame_filter = { }; static unsigned int -ebt_in_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +ebt_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ebt_do_table(skb, state, state->net->xt.frame_filter); } static unsigned int -ebt_out_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +ebt_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ebt_do_table(skb, state, state->net->xt.frame_filter); diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 56c3329d6c37..4bbefe03ab58 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -57,14 +57,14 @@ static struct ebt_table frame_nat = { }; static unsigned int -ebt_nat_in(const struct nf_hook_ops *ops, struct sk_buff *skb, +ebt_nat_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ebt_do_table(skb, state, state->net->xt.frame_nat); } static unsigned int -ebt_nat_out(const struct nf_hook_ops *ops, struct sk_buff *skb, +ebt_nat_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ebt_do_table(skb, state, state->net->xt.frame_nat); diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c index 318d825e4207..62f6b1b19589 100644 --- a/net/bridge/netfilter/nf_tables_bridge.c +++ b/net/bridge/netfilter/nf_tables_bridge.c @@ -87,7 +87,7 @@ static inline void nft_bridge_set_pktinfo_ipv6(struct nft_pktinfo *pkt, } static unsigned int -nft_do_chain_bridge(const struct nf_hook_ops *ops, +nft_do_chain_bridge(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -105,7 +105,7 @@ nft_do_chain_bridge(const struct nf_hook_ops *ops, break; } - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } static struct nft_af_info nft_af_bridge __read_mostly = { diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index af34fc9bdf69..85f2fdc360c2 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -87,7 +87,7 @@ static void dnrmg_send_peer(struct sk_buff *skb) } -static unsigned int dnrmg_hook(const struct nf_hook_ops *ops, +static unsigned int dnrmg_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 1352e12d4068..1897ee160920 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -27,7 +27,7 @@ static const struct xt_table packet_filter = { /* The work comes in here from netfilter.c */ static unsigned int -arptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +arptable_filter_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return arpt_do_table(skb, state, state->net->ipv4.arptable_filter); diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 69157d8eba95..3f32c03e8b2e 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -507,7 +507,7 @@ static void arp_print(struct arp_payload *payload) #endif static unsigned int -arp_mangle(const struct nf_hook_ops *ops, +arp_mangle(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index dfab314981e9..d7021f28c3f0 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -299,7 +299,7 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -static unsigned int ipv4_synproxy_hook(const struct nf_hook_ops *ops, +static unsigned int ipv4_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs) { diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 02d4c5395d6e..397ef2dd133e 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -33,7 +33,7 @@ static const struct xt_table packet_filter = { }; static unsigned int -iptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +iptable_filter_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { if (state->hook == NF_INET_LOCAL_OUT && diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index dc2ff6884999..2d6fc911866f 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -78,7 +78,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) /* The work comes in here from netfilter.c. */ static unsigned int -iptable_mangle_hook(const struct nf_hook_ops *ops, +iptable_mangle_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 8ff63ac1f0d6..3a2e4d830a0b 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -28,7 +28,7 @@ static const struct xt_table nf_nat_ipv4_table = { .af = NFPROTO_IPV4, }; -static unsigned int iptable_nat_do_chain(const struct nf_hook_ops *ops, +static unsigned int iptable_nat_do_chain(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct) @@ -36,32 +36,32 @@ static unsigned int iptable_nat_do_chain(const struct nf_hook_ops *ops, return ipt_do_table(skb, state, state->net->ipv4.nat_table); } -static unsigned int iptable_nat_ipv4_fn(const struct nf_hook_ops *ops, +static unsigned int iptable_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_fn(ops, skb, state, iptable_nat_do_chain); + return nf_nat_ipv4_fn(priv, skb, state, iptable_nat_do_chain); } -static unsigned int iptable_nat_ipv4_in(const struct nf_hook_ops *ops, +static unsigned int iptable_nat_ipv4_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_in(ops, skb, state, iptable_nat_do_chain); + return nf_nat_ipv4_in(priv, skb, state, iptable_nat_do_chain); } -static unsigned int iptable_nat_ipv4_out(const struct nf_hook_ops *ops, +static unsigned int iptable_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_out(ops, skb, state, iptable_nat_do_chain); + return nf_nat_ipv4_out(priv, skb, state, iptable_nat_do_chain); } -static unsigned int iptable_nat_ipv4_local_fn(const struct nf_hook_ops *ops, +static unsigned int iptable_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_local_fn(ops, skb, state, iptable_nat_do_chain); + return nf_nat_ipv4_local_fn(priv, skb, state, iptable_nat_do_chain); } static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = { diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index bbb0523d87de..1ba02811acb0 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -20,7 +20,7 @@ static const struct xt_table packet_raw = { /* The work comes in here from netfilter.c. */ static unsigned int -iptable_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +iptable_raw_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { if (state->hook == NF_INET_LOCAL_OUT && diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index b92417038705..f534e2f05bad 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -37,7 +37,7 @@ static const struct xt_table security_table = { }; static unsigned int -iptable_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +iptable_security_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { if (state->hook == NF_INET_LOCAL_OUT && diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 15749cc5cf2b..752fb40adcf8 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -92,7 +92,7 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, return NF_ACCEPT; } -static unsigned int ipv4_helper(const struct nf_hook_ops *ops, +static unsigned int ipv4_helper(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -119,7 +119,7 @@ static unsigned int ipv4_helper(const struct nf_hook_ops *ops, ct, ctinfo); } -static unsigned int ipv4_confirm(const struct nf_hook_ops *ops, +static unsigned int ipv4_confirm(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -143,14 +143,14 @@ out: return nf_conntrack_confirm(skb); } -static unsigned int ipv4_conntrack_in(const struct nf_hook_ops *ops, +static unsigned int ipv4_conntrack_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return nf_conntrack_in(state->net, PF_INET, state->hook, skb); } -static unsigned int ipv4_conntrack_local(const struct nf_hook_ops *ops, +static unsigned int ipv4_conntrack_local(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 8aea536d2e83..b246346ee849 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -61,7 +61,7 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum, return IP_DEFRAG_CONNTRACK_OUT + zone_id; } -static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops, +static unsigned int ipv4_conntrack_defrag(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index 16da45a76dac..8593a9d88619 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -255,9 +255,9 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); unsigned int -nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -308,7 +308,7 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, if (!nf_nat_initialized(ct, maniptype)) { unsigned int ret; - ret = do_chain(ops, skb, state, ct); + ret = do_chain(priv, skb, state, ct); if (ret != NF_ACCEPT) return ret; @@ -345,9 +345,9 @@ oif_changed: EXPORT_SYMBOL_GPL(nf_nat_ipv4_fn); unsigned int -nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv4_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -355,7 +355,7 @@ nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; - ret = nf_nat_ipv4_fn(ops, skb, state, do_chain); + ret = nf_nat_ipv4_fn(priv, skb, state, do_chain); if (ret != NF_DROP && ret != NF_STOLEN && daddr != ip_hdr(skb)->daddr) skb_dst_drop(skb); @@ -365,9 +365,9 @@ nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_ipv4_in); unsigned int -nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -384,7 +384,7 @@ nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - ret = nf_nat_ipv4_fn(ops, skb, state, do_chain); + ret = nf_nat_ipv4_fn(priv, skb, state, do_chain); #ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && @@ -407,9 +407,9 @@ nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_ipv4_out); unsigned int -nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -424,7 +424,7 @@ nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - ret = nf_nat_ipv4_fn(ops, skb, state, do_chain); + ret = nf_nat_ipv4_fn(priv, skb, state, do_chain); if (ret != NF_DROP && ret != NF_STOLEN && (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c index 883bbf83fe09..9d09d4f59545 100644 --- a/net/ipv4/netfilter/nf_tables_arp.c +++ b/net/ipv4/netfilter/nf_tables_arp.c @@ -15,7 +15,7 @@ #include static unsigned int -nft_do_chain_arp(const struct nf_hook_ops *ops, +nft_do_chain_arp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -23,7 +23,7 @@ nft_do_chain_arp(const struct nf_hook_ops *ops, nft_set_pktinfo(&pkt, skb, state); - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } static struct nft_af_info nft_af_arp __read_mostly = { diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c index 805be5c9fcc3..ca9dc3c46c4f 100644 --- a/net/ipv4/netfilter/nf_tables_ipv4.c +++ b/net/ipv4/netfilter/nf_tables_ipv4.c @@ -18,7 +18,7 @@ #include #include -static unsigned int nft_do_chain_ipv4(const struct nf_hook_ops *ops, +static unsigned int nft_do_chain_ipv4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -26,10 +26,10 @@ static unsigned int nft_do_chain_ipv4(const struct nf_hook_ops *ops, nft_set_pktinfo_ipv4(&pkt, skb, state); - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } -static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops, +static unsigned int nft_ipv4_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -41,7 +41,7 @@ static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops, return NF_ACCEPT; } - return nft_do_chain_ipv4(ops, skb, state); + return nft_do_chain_ipv4(priv, skb, state); } struct nft_af_info nft_af_ipv4 __read_mostly = { diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c index c3ffecf28d38..f5c66a7a4bf2 100644 --- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c @@ -26,7 +26,7 @@ #include #include -static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops, +static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct) @@ -35,35 +35,35 @@ static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops, nft_set_pktinfo_ipv4(&pkt, skb, state); - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } -static unsigned int nft_nat_ipv4_fn(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_fn(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv4_fn(priv, skb, state, nft_nat_do_chain); } -static unsigned int nft_nat_ipv4_in(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv4_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_in(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv4_in(priv, skb, state, nft_nat_do_chain); } -static unsigned int nft_nat_ipv4_out(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_out(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv4_out(priv, skb, state, nft_nat_do_chain); } -static unsigned int nft_nat_ipv4_local_fn(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_local_fn(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv4_local_fn(priv, skb, state, nft_nat_do_chain); } static const struct nf_chain_type nft_chain_nat_ipv4 = { diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c index 2a1e3d8a3e43..9f486b302108 100644 --- a/net/ipv4/netfilter/nft_chain_route_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c @@ -21,7 +21,7 @@ #include #include -static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, +static unsigned int nf_route_table_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -45,7 +45,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, daddr = iph->daddr; tos = iph->tos; - ret = nft_do_chain(&pkt, ops); + ret = nft_do_chain(&pkt, priv); if (ret != NF_DROP && ret != NF_QUEUE) { iph = ip_hdr(skb); diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index 41451809b37c..c2356602158a 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -316,7 +316,7 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -static unsigned int ipv6_synproxy_hook(const struct nf_hook_ops *ops, +static unsigned int ipv6_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs) { diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index a7327f61b90c..8b277b983ca5 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -32,7 +32,7 @@ static const struct xt_table packet_filter = { /* The work comes in here from netfilter.c. */ static unsigned int -ip6table_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip6table_filter_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip6t_do_table(skb, state, state->net->ipv6.ip6table_filter); diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index c2e061dcedf3..8745b592b2f6 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -75,7 +75,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) /* The work comes in here from netfilter.c. */ static unsigned int -ip6table_mangle_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip6table_mangle_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { if (state->hook == NF_INET_LOCAL_OUT) diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index efa6754c4d06..abea175d5853 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -30,7 +30,7 @@ static const struct xt_table nf_nat_ipv6_table = { .af = NFPROTO_IPV6, }; -static unsigned int ip6table_nat_do_chain(const struct nf_hook_ops *ops, +static unsigned int ip6table_nat_do_chain(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct) @@ -38,32 +38,32 @@ static unsigned int ip6table_nat_do_chain(const struct nf_hook_ops *ops, return ip6t_do_table(skb, state, state->net->ipv6.ip6table_nat); } -static unsigned int ip6table_nat_fn(const struct nf_hook_ops *ops, +static unsigned int ip6table_nat_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_fn(ops, skb, state, ip6table_nat_do_chain); + return nf_nat_ipv6_fn(priv, skb, state, ip6table_nat_do_chain); } -static unsigned int ip6table_nat_in(const struct nf_hook_ops *ops, +static unsigned int ip6table_nat_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_in(ops, skb, state, ip6table_nat_do_chain); + return nf_nat_ipv6_in(priv, skb, state, ip6table_nat_do_chain); } -static unsigned int ip6table_nat_out(const struct nf_hook_ops *ops, +static unsigned int ip6table_nat_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_out(ops, skb, state, ip6table_nat_do_chain); + return nf_nat_ipv6_out(priv, skb, state, ip6table_nat_do_chain); } -static unsigned int ip6table_nat_local_fn(const struct nf_hook_ops *ops, +static unsigned int ip6table_nat_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_local_fn(ops, skb, state, ip6table_nat_do_chain); + return nf_nat_ipv6_local_fn(priv, skb, state, ip6table_nat_do_chain); } static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index fac6ad7c0a7c..9021963565c3 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -19,7 +19,7 @@ static const struct xt_table packet_raw = { /* The work comes in here from netfilter.c. */ static unsigned int -ip6table_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip6table_raw_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip6t_do_table(skb, state, state->net->ipv6.ip6table_raw); diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 96c94fc240c8..0d856fedfeb0 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -36,7 +36,7 @@ static const struct xt_table security_table = { }; static unsigned int -ip6table_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip6table_security_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip6t_do_table(skb, state, state->net->ipv6.ip6table_security); diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 339be1d59afc..dd83ad42f8f6 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -95,7 +95,7 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, return NF_ACCEPT; } -static unsigned int ipv6_helper(const struct nf_hook_ops *ops, +static unsigned int ipv6_helper(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -131,7 +131,7 @@ static unsigned int ipv6_helper(const struct nf_hook_ops *ops, return helper->help(skb, protoff, ct, ctinfo); } -static unsigned int ipv6_confirm(const struct nf_hook_ops *ops, +static unsigned int ipv6_confirm(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -165,14 +165,14 @@ out: return nf_conntrack_confirm(skb); } -static unsigned int ipv6_conntrack_in(const struct nf_hook_ops *ops, +static unsigned int ipv6_conntrack_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return nf_conntrack_in(state->net, PF_INET6, state->hook, skb); } -static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops, +static unsigned int ipv6_conntrack_local(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index a9c08520596b..a99baf63eccf 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -51,7 +51,7 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, return IP6_DEFRAG_CONNTRACK_OUT + zone_id; } -static unsigned int ipv6_defrag(const struct nf_hook_ops *ops, +static unsigned int ipv6_defrag(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 8bc94907dbd9..357f57ba47e4 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -262,9 +262,9 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); unsigned int -nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -317,7 +317,7 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, if (!nf_nat_initialized(ct, maniptype)) { unsigned int ret; - ret = do_chain(ops, skb, state, ct); + ret = do_chain(priv, skb, state, ct); if (ret != NF_ACCEPT) return ret; @@ -353,9 +353,9 @@ oif_changed: EXPORT_SYMBOL_GPL(nf_nat_ipv6_fn); unsigned int -nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -363,7 +363,7 @@ nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, unsigned int ret; struct in6_addr daddr = ipv6_hdr(skb)->daddr; - ret = nf_nat_ipv6_fn(ops, skb, state, do_chain); + ret = nf_nat_ipv6_fn(priv, skb, state, do_chain); if (ret != NF_DROP && ret != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); @@ -373,9 +373,9 @@ nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_ipv6_in); unsigned int -nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -391,7 +391,7 @@ nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, if (skb->len < sizeof(struct ipv6hdr)) return NF_ACCEPT; - ret = nf_nat_ipv6_fn(ops, skb, state, do_chain); + ret = nf_nat_ipv6_fn(priv, skb, state, do_chain); #ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && @@ -414,9 +414,9 @@ nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_ipv6_out); unsigned int -nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -430,7 +430,7 @@ nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, if (skb->len < sizeof(struct ipv6hdr)) return NF_ACCEPT; - ret = nf_nat_ipv6_fn(ops, skb, state, do_chain); + ret = nf_nat_ipv6_fn(priv, skb, state, do_chain); if (ret != NF_DROP && ret != NF_STOLEN && (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c index 41340b794f9b..120ea9131be0 100644 --- a/net/ipv6/netfilter/nf_tables_ipv6.c +++ b/net/ipv6/netfilter/nf_tables_ipv6.c @@ -16,7 +16,7 @@ #include #include -static unsigned int nft_do_chain_ipv6(const struct nf_hook_ops *ops, +static unsigned int nft_do_chain_ipv6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -26,10 +26,10 @@ static unsigned int nft_do_chain_ipv6(const struct nf_hook_ops *ops, if (nft_set_pktinfo_ipv6(&pkt, skb, state) < 0) return NF_DROP; - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } -static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops, +static unsigned int nft_ipv6_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -40,7 +40,7 @@ static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops, return NF_ACCEPT; } - return nft_do_chain_ipv6(ops, skb, state); + return nft_do_chain_ipv6(priv, skb, state); } struct nft_af_info nft_af_ipv6 __read_mostly = { diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c index e96feaefeb14..443cd306c0b0 100644 --- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c @@ -24,7 +24,7 @@ #include #include -static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops, +static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct) @@ -33,35 +33,35 @@ static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops, nft_set_pktinfo_ipv6(&pkt, skb, state); - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } -static unsigned int nft_nat_ipv6_fn(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_fn(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv6_fn(priv, skb, state, nft_nat_do_chain); } -static unsigned int nft_nat_ipv6_in(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_in(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv6_in(priv, skb, state, nft_nat_do_chain); } -static unsigned int nft_nat_ipv6_out(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_out(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv6_out(priv, skb, state, nft_nat_do_chain); } -static unsigned int nft_nat_ipv6_local_fn(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_local_fn(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv6_local_fn(priv, skb, state, nft_nat_do_chain); } static const struct nf_chain_type nft_chain_nat_ipv6 = { diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c index d1bcd2ed7bcc..d42bbc1d7555 100644 --- a/net/ipv6/netfilter/nft_chain_route_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c @@ -22,7 +22,7 @@ #include #include -static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, +static unsigned int nf_route_table_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -45,7 +45,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u32 *)ipv6_hdr(skb)); - ret = nft_do_chain(&pkt, ops); + ret = nft_do_chain(&pkt, priv); if (ret != NF_DROP && ret != NF_QUEUE && (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 8e47f8113495..2e907335ee81 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -269,7 +269,7 @@ unsigned int nf_iterate(struct list_head *head, /* Optimization: we don't need to hold module reference here, since function can't sleep. --RR */ repeat: - verdict = (*elemp)->hook(*elemp, skb, state); + verdict = (*elemp)->hook((*elemp)->priv, skb, state); if (verdict != NF_ACCEPT) { #ifdef CONFIG_NETFILTER_DEBUG if (unlikely((verdict & NF_VERDICT_MASK) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 40e3c85f83b5..1fa12edccbcc 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1311,7 +1311,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) * Check if packet is reply for established ip_vs_conn. */ static unsigned int -ip_vs_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_reply4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(state->hook, skb, AF_INET); @@ -1322,7 +1322,7 @@ ip_vs_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, * Check if packet is reply for established ip_vs_conn. */ static unsigned int -ip_vs_local_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_local_reply4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(state->hook, skb, AF_INET); @@ -1336,7 +1336,7 @@ ip_vs_local_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, * Check if packet is reply for established ip_vs_conn. */ static unsigned int -ip_vs_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_reply6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(state->hook, skb, AF_INET6); @@ -1347,7 +1347,7 @@ ip_vs_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb, * Check if packet is reply for established ip_vs_conn. */ static unsigned int -ip_vs_local_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_local_reply6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(state->hook, skb, AF_INET6); @@ -1847,7 +1847,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) * Schedule and forward packets from remote clients */ static unsigned int -ip_vs_remote_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_remote_request4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(state->hook, skb, AF_INET); @@ -1858,7 +1858,7 @@ ip_vs_remote_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, * Schedule and forward packets from local clients */ static unsigned int -ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_local_request4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(state->hook, skb, AF_INET); @@ -1871,7 +1871,7 @@ ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, * Schedule and forward packets from remote clients */ static unsigned int -ip_vs_remote_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_remote_request6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(state->hook, skb, AF_INET6); @@ -1882,7 +1882,7 @@ ip_vs_remote_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, * Schedule and forward packets from local clients */ static unsigned int -ip_vs_local_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_local_request6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(state->hook, skb, AF_INET6); @@ -1901,7 +1901,7 @@ ip_vs_local_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, * and send them to ip_vs_in_icmp. */ static unsigned int -ip_vs_forward_icmp(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int r; @@ -1917,12 +1917,12 @@ ip_vs_forward_icmp(const struct nf_hook_ops *ops, struct sk_buff *skb, if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; - return ip_vs_in_icmp(skb, &r, ops->hooknum); + return ip_vs_in_icmp(skb, &r, state->hook); } #ifdef CONFIG_IP_VS_IPV6 static unsigned int -ip_vs_forward_icmp_v6(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int r; @@ -1940,7 +1940,7 @@ ip_vs_forward_icmp_v6(const struct nf_hook_ops *ops, struct sk_buff *skb, if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; - return ip_vs_in_icmp_v6(skb, &r, ops->hooknum, &iphdr); + return ip_vs_in_icmp_v6(skb, &r, state->hook, &iphdr); } #endif diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index e5c1f332e45e..f3695a497408 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -109,9 +109,9 @@ struct nft_jumpstack { }; unsigned int -nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) +nft_do_chain(struct nft_pktinfo *pkt, void *priv) { - const struct nft_chain *chain = ops->priv, *basechain = chain; + const struct nft_chain *chain = priv, *basechain = chain; const struct net *net = pkt->net; const struct nft_rule *rule; const struct nft_expr *expr, *last; diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c index db416a3396e9..7b9c053ba750 100644 --- a/net/netfilter/nf_tables_netdev.c +++ b/net/netfilter/nf_tables_netdev.c @@ -89,7 +89,7 @@ static inline void nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, } static unsigned int -nft_do_chain_netdev(const struct nf_hook_ops *ops, struct sk_buff *skb, +nft_do_chain_netdev(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; @@ -106,7 +106,7 @@ nft_do_chain_netdev(const struct nf_hook_ops *ops, struct sk_buff *skb, break; } - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } static struct nft_af_info nft_af_netdev __read_mostly = { diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index e4369d86e588..64340160f4ac 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4866,7 +4866,7 @@ static unsigned int selinux_ip_forward(struct sk_buff *skb, return NF_ACCEPT; } -static unsigned int selinux_ipv4_forward(const struct nf_hook_ops *ops, +static unsigned int selinux_ipv4_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -4874,7 +4874,7 @@ static unsigned int selinux_ipv4_forward(const struct nf_hook_ops *ops, } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static unsigned int selinux_ipv6_forward(const struct nf_hook_ops *ops, +static unsigned int selinux_ipv6_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -4924,7 +4924,7 @@ static unsigned int selinux_ip_output(struct sk_buff *skb, return NF_ACCEPT; } -static unsigned int selinux_ipv4_output(const struct nf_hook_ops *ops, +static unsigned int selinux_ipv4_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -5099,7 +5099,7 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, return NF_ACCEPT; } -static unsigned int selinux_ipv4_postroute(const struct nf_hook_ops *ops, +static unsigned int selinux_ipv4_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -5107,7 +5107,7 @@ static unsigned int selinux_ipv4_postroute(const struct nf_hook_ops *ops, } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static unsigned int selinux_ipv6_postroute(const struct nf_hook_ops *ops, +static unsigned int selinux_ipv6_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/security/smack/smack_netfilter.c b/security/smack/smack_netfilter.c index a455cfc9ec1f..a9e41da05d28 100644 --- a/security/smack/smack_netfilter.c +++ b/security/smack/smack_netfilter.c @@ -21,7 +21,7 @@ #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static unsigned int smack_ipv6_output(const struct nf_hook_ops *ops, +static unsigned int smack_ipv6_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -38,7 +38,7 @@ static unsigned int smack_ipv6_output(const struct nf_hook_ops *ops, } #endif /* IPV6 */ -static unsigned int smack_ipv4_output(const struct nf_hook_ops *ops, +static unsigned int smack_ipv4_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { -- cgit v1.2.3 From c7af6483b9f7f3eaba01b2e62d3d8a70cd89bdaf Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:33:07 -0500 Subject: netfilter: Pass net into nf_xfrm_me_harder Instead of calling dev_net on a likley looking network device pass state->net into nf_xfrm_me_harder. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_nat_core.h | 2 +- net/ipv4/netfilter/nf_nat_l3proto_ipv4.c | 4 ++-- net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 4 ++-- net/netfilter/nf_nat_core.c | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h index fbfd1ba4254e..186c54138f35 100644 --- a/include/net/netfilter/nf_nat_core.h +++ b/include/net/netfilter/nf_nat_core.h @@ -10,7 +10,7 @@ unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, struct sk_buff *skb); -int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family); +int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family); static inline int nf_nat_initialized(struct nf_conn *ct, enum nf_nat_manip_type manip) diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index 8593a9d88619..bc3b9dcbf080 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -396,7 +396,7 @@ nf_nat_ipv4_out(void *priv, struct sk_buff *skb, (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { - err = nf_xfrm_me_harder(skb, AF_INET); + err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } @@ -440,7 +440,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { - err = nf_xfrm_me_harder(skb, AF_INET); + err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 357f57ba47e4..18e835ffbef3 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -403,7 +403,7 @@ nf_nat_ipv6_out(void *priv, struct sk_buff *skb, (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { - err = nf_xfrm_me_harder(skb, AF_INET6); + err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } @@ -446,7 +446,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { - err = nf_xfrm_me_harder(skb, AF_INET6); + err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 5113dfd39df9..06a9f45771ab 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -83,7 +83,7 @@ out: rcu_read_unlock(); } -int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family) +int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) { struct flowi fl; unsigned int hh_len; @@ -99,7 +99,7 @@ int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family) dst = ((struct xfrm_dst *)dst)->route; dst_hold(dst); - dst = xfrm_lookup(dev_net(dst->dev), dst, &fl, skb->sk, 0); + dst = xfrm_lookup(net, dst, &fl, skb->sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); -- cgit v1.2.3 From ae4f976968896f8f41b3a7aa21be6146492211e5 Mon Sep 17 00:00:00 2001 From: Tyler Baker Date: Sat, 19 Sep 2015 03:58:10 -0400 Subject: mm: fix type cast in __pfn_to_phys() The various definitions of __pfn_to_phys() have been consolidated to use a generic macro in include/asm-generic/memory_model.h. This hit mainline in the form of 012dcef3f058 "mm: move __phys_to_pfn and __pfn_to_phys to asm/generic/memory_model.h". When the generic macro was implemented the type cast to phys_addr_t was dropped which caused boot regressions on ARM platforms with more than 4GB of memory and LPAE enabled. It was suggested to use PFN_PHYS() defined in include/linux/pfn.h as provides the correct logic and avoids further duplication. Reported-by: kernelci.org bot Suggested-by: Dan Williams Signed-off-by: Tyler Baker Signed-off-by: Dan Williams --- include/asm-generic/memory_model.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h index f20f407ce45d..4b4b056a6eb0 100644 --- a/include/asm-generic/memory_model.h +++ b/include/asm-generic/memory_model.h @@ -73,7 +73,7 @@ * Convert a physical address to a Page Frame Number and back */ #define __phys_to_pfn(paddr) ((unsigned long)((paddr) >> PAGE_SHIFT)) -#define __pfn_to_phys(pfn) ((pfn) << PAGE_SHIFT) +#define __pfn_to_phys(pfn) PFN_PHYS(pfn) #define page_to_pfn __page_to_pfn #define pfn_to_page __pfn_to_page -- cgit v1.2.3 From b7f76ea2ef6739ee484a165ffbac98deb855d3d3 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 18 Sep 2015 23:41:23 +0200 Subject: security: fix typo in security_task_prctl Signed-off-by: Jann Horn Reviewed-by: Andy Lutomirski Signed-off-by: Linus Torvalds --- include/linux/security.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/security.h b/include/linux/security.h index 79d85ddf8093..2f4c1f7aa7db 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -946,7 +946,7 @@ static inline int security_task_prctl(int option, unsigned long arg2, unsigned long arg4, unsigned long arg5) { - return cap_task_prctl(option, arg2, arg3, arg3, arg5); + return cap_task_prctl(option, arg2, arg3, arg4, arg5); } static inline void security_task_to_inode(struct task_struct *p, struct inode *inode) -- cgit v1.2.3 From 66e8c57da6bf6b847a48a5a6fda59512f733ed78 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 25 Aug 2015 20:45:18 +0200 Subject: rcu: Change _wait_rcu_gp() to work around GCC bug 67055 Code like this in inline functions confuses some recent versions of gcc: const int n = const-expr; whatever_t array[n]; For more details, see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67055#c13 This compiler bug results in the following failure after 114b7fd4b (rcu: Create rcu_sync infrastructure): In file included from include/linux/rcupdate.h:429:0, from include/linux/rcu_sync.h:5, from kernel/rcu/sync.c:1: include/linux/rcutiny.h: In function 'rcu_barrier_sched': include/linux/rcutiny.h:55:20: internal compiler error: Segmentation fault static inline void rcu_barrier_sched(void) This commit therefore eliminates the constant local variable in favor of direct use of the expression. Reported-and-tested-by: Mark Salter Reported-by: Guenter Roeck Signed-off-by: Oleg Nesterov Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index ff476515f716..581abf848566 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -230,12 +230,11 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, struct rcu_synchronize *rs_array); #define _wait_rcu_gp(checktiny, ...) \ -do { \ - call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ - const int __n = ARRAY_SIZE(__crcu_array); \ - struct rcu_synchronize __rs_array[__n]; \ - \ - __wait_rcu_gp(checktiny, __n, __crcu_array, __rs_array); \ +do { \ + call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ + struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ + __wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array), \ + __crcu_array, __rs_array); \ } while (0) #define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) -- cgit v1.2.3 From 0315e382704817b279e5693dca8ab9d89aa20b3f Mon Sep 17 00:00:00 2001 From: Nikola Forró Date: Thu, 17 Sep 2015 16:01:32 +0200 Subject: net: Fix behaviour of unreachable, blackhole and prohibit routes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Man page of ip-route(8) says following about route types: unreachable - these destinations are unreachable. Packets are dis‐ carded and the ICMP message host unreachable is generated. The local senders get an EHOSTUNREACH error. blackhole - these destinations are unreachable. Packets are dis‐ carded silently. The local senders get an EINVAL error. prohibit - these destinations are unreachable. Packets are discarded and the ICMP message communication administratively prohibited is generated. The local senders get an EACCES error. In the inet6 address family, this was correct, except the local senders got ENETUNREACH error instead of EHOSTUNREACH in case of unreachable route. In the inet address family, all three route types generated ICMP message net unreachable, and the local senders got ENETUNREACH error. In both address families all three route types now behave consistently with documentation. Signed-off-by: Nikola Forró Signed-off-by: David S. Miller --- include/net/ip_fib.h | 30 +++++++++++++++++++----------- net/ipv4/route.c | 6 ++++-- net/ipv6/route.c | 4 +++- 3 files changed, 26 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index a37d0432bebd..727d6e9a9685 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -236,8 +236,11 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp, rcu_read_lock(); tb = fib_get_table(net, RT_TABLE_MAIN); - if (tb && !fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF)) - err = 0; + if (tb) + err = fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF); + + if (err == -EAGAIN) + err = -ENETUNREACH; rcu_read_unlock(); @@ -258,7 +261,7 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; - int err; + int err = -ENETUNREACH; flags |= FIB_LOOKUP_NOREF; if (net->ipv4.fib_has_custom_rules) @@ -268,15 +271,20 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp, res->tclassid = 0; - for (err = 0; !err; err = -ENETUNREACH) { - tb = rcu_dereference_rtnl(net->ipv4.fib_main); - if (tb && !fib_table_lookup(tb, flp, res, flags)) - break; + tb = rcu_dereference_rtnl(net->ipv4.fib_main); + if (tb) + err = fib_table_lookup(tb, flp, res, flags); + + if (!err) + goto out; + + tb = rcu_dereference_rtnl(net->ipv4.fib_default); + if (tb) + err = fib_table_lookup(tb, flp, res, flags); - tb = rcu_dereference_rtnl(net->ipv4.fib_default); - if (tb && !fib_table_lookup(tb, flp, res, flags)) - break; - } +out: + if (err == -EAGAIN) + err = -ENETUNREACH; rcu_read_unlock(); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 5f4a5565ad8b..c6ad99ad0ffb 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2045,6 +2045,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) struct fib_result res; struct rtable *rth; int orig_oif; + int err = -ENETUNREACH; res.tclassid = 0; res.fi = NULL; @@ -2153,7 +2154,8 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) goto make_route; } - if (fib_lookup(net, fl4, &res, 0)) { + err = fib_lookup(net, fl4, &res, 0); + if (err) { res.fi = NULL; res.table = NULL; if (fl4->flowi4_oif) { @@ -2181,7 +2183,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) res.type = RTN_UNICAST; goto make_route; } - rth = ERR_PTR(-ENETUNREACH); + rth = ERR_PTR(err); goto out; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d5fa50297f80..f204089e854c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1885,9 +1885,11 @@ int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret) rt->dst.input = ip6_pkt_prohibit; break; case RTN_THROW: + case RTN_UNREACHABLE: default: rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN - : -ENETUNREACH; + : (cfg->fc_type == RTN_UNREACHABLE) + ? -EHOSTUNREACH : -ENETUNREACH; rt->dst.output = ip6_pkt_discard_out; rt->dst.input = ip6_pkt_discard; break; -- cgit v1.2.3 From 83cf9a2521b0934a5f9d04082c9bb4f554fddcd4 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 18 Sep 2015 11:47:41 +0200 Subject: ip6tunnel: make rx/tx bytes counters consistent Like the previous patch, which fixes ipv4 tunnels, here is the ipv6 part. Before the patch, the external ipv6 header + gre header were included on tx. After the patch: $ ping -c1 192.168.6.121 ; ip -s l ls dev ip6gre1 PING 192.168.6.121 (192.168.6.121) 56(84) bytes of data. 64 bytes from 192.168.6.121: icmp_req=1 ttl=64 time=1.92 ms --- 192.168.6.121 ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 1.923/1.923/1.923/0.000 ms 7: ip6gre1@NONE: mtu 1440 qdisc noqueue state UNKNOWN mode DEFAULT group default link/gre6 20:01:06:60:30:08:c1:c3:00:00:00:00:00:00:01:23 peer 20:01:06:60:30:08:c1:c3:00:00:00:00:00:00:01:21 RX: bytes packets errors dropped overrun mcast 84 1 0 0 0 0 TX: bytes packets errors dropped carrier collsns 84 1 0 0 0 0 $ ping -c1 192.168.1.121 ; ip -s l ls dev ip6tnl1 PING 192.168.1.121 (192.168.1.121) 56(84) bytes of data. 64 bytes from 192.168.1.121: icmp_req=1 ttl=64 time=2.28 ms --- 192.168.1.121 ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 2.288/2.288/2.288/0.000 ms 8: ip6tnl1@NONE: mtu 1452 qdisc noqueue state UNKNOWN mode DEFAULT group default link/tunnel6 2001:660:3008:c1c3::123 peer 2001:660:3008:c1c3::121 RX: bytes packets errors dropped overrun mcast 84 1 0 0 0 0 TX: bytes packets errors dropped carrier collsns 84 1 0 0 0 0 Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/net/ip6_tunnel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 65c2a9397b3c..fa915fa0f703 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -86,7 +86,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, struct net_device_stats *stats = &dev->stats; int pkt_len, err; - pkt_len = skb->len; + pkt_len = skb->len - skb_inner_network_offset(skb); err = ip6_local_out_sk(sk, skb); if (net_xmit_eval(err) == 0) { -- cgit v1.2.3 From 2785968cd122b22b289db565b7438f2200984044 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Sat, 9 May 2015 17:47:52 +0200 Subject: can: headers: make header files self contained This patch adds the missing #include-s to the dev.h and led.h, so that they can be used without including further header files. Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 3 ++- include/linux/can/led.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index c3a9c8fc60fa..56dcadd83716 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -14,9 +14,10 @@ #define _CAN_DEV_H #include -#include #include #include +#include +#include /* * CAN mode diff --git a/include/linux/can/led.h b/include/linux/can/led.h index 146de4506d21..2746f7c2f87d 100644 --- a/include/linux/can/led.h +++ b/include/linux/can/led.h @@ -11,6 +11,7 @@ #include #include +#include enum can_led_event { CAN_LED_EVENT_OPEN, -- cgit v1.2.3 From 91e60eb60bdf078fc58b8d2fd1ac12f3c09bb893 Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Fri, 18 Sep 2015 16:06:52 +0200 Subject: s390/iucv: do not use arrays as argument The iucv code uses arrays as arguments. Even though this does not really cause a problem, it could be misleading, since the compiler turns array arguments into just a pointer argument. To be more precise this patch changes the array arguments into pointers. Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- drivers/s390/char/monreader.c | 4 ++-- drivers/s390/char/vmlogrdr.c | 8 ++++---- drivers/s390/net/netiucv.c | 21 ++++++++++----------- drivers/s390/net/smsgiucv.c | 5 ++--- drivers/tty/hvc/hvc_iucv.c | 10 +++++----- include/net/iucv/iucv.h | 20 ++++++++++---------- net/iucv/af_iucv.c | 9 ++++----- net/iucv/iucv.c | 12 ++++++------ 8 files changed, 43 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/drivers/s390/char/monreader.c b/drivers/s390/char/monreader.c index b7d60306b0bc..fc94bfdceb95 100644 --- a/drivers/s390/char/monreader.c +++ b/drivers/s390/char/monreader.c @@ -229,7 +229,7 @@ static struct mon_msg *mon_next_message(struct mon_private *monpriv) /****************************************************************************** * IUCV handler * *****************************************************************************/ -static void mon_iucv_path_complete(struct iucv_path *path, u8 ipuser[16]) +static void mon_iucv_path_complete(struct iucv_path *path, u8 *ipuser) { struct mon_private *monpriv = path->private; @@ -237,7 +237,7 @@ static void mon_iucv_path_complete(struct iucv_path *path, u8 ipuser[16]) wake_up(&mon_conn_wait_queue); } -static void mon_iucv_path_severed(struct iucv_path *path, u8 ipuser[16]) +static void mon_iucv_path_severed(struct iucv_path *path, u8 *ipuser) { struct mon_private *monpriv = path->private; diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c index 9bb48d70957c..799c1524c779 100644 --- a/drivers/s390/char/vmlogrdr.c +++ b/drivers/s390/char/vmlogrdr.c @@ -99,8 +99,8 @@ static const struct file_operations vmlogrdr_fops = { }; -static void vmlogrdr_iucv_path_complete(struct iucv_path *, u8 ipuser[16]); -static void vmlogrdr_iucv_path_severed(struct iucv_path *, u8 ipuser[16]); +static void vmlogrdr_iucv_path_complete(struct iucv_path *, u8 *ipuser); +static void vmlogrdr_iucv_path_severed(struct iucv_path *, u8 *ipuser); static void vmlogrdr_iucv_message_pending(struct iucv_path *, struct iucv_message *); @@ -160,7 +160,7 @@ static struct cdev *vmlogrdr_cdev = NULL; static int recording_class_AB; -static void vmlogrdr_iucv_path_complete(struct iucv_path *path, u8 ipuser[16]) +static void vmlogrdr_iucv_path_complete(struct iucv_path *path, u8 *ipuser) { struct vmlogrdr_priv_t * logptr = path->private; @@ -171,7 +171,7 @@ static void vmlogrdr_iucv_path_complete(struct iucv_path *path, u8 ipuser[16]) } -static void vmlogrdr_iucv_path_severed(struct iucv_path *path, u8 ipuser[16]) +static void vmlogrdr_iucv_path_severed(struct iucv_path *path, u8 *ipuser) { struct vmlogrdr_priv_t * logptr = path->private; u8 reason = (u8) ipuser[8]; diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c index 33f7040d711d..0ba3a2f81750 100644 --- a/drivers/s390/net/netiucv.c +++ b/drivers/s390/net/netiucv.c @@ -149,12 +149,11 @@ static struct device_driver netiucv_driver = { .pm = &netiucv_pm_ops, }; -static int netiucv_callback_connreq(struct iucv_path *, - u8 ipvmid[8], u8 ipuser[16]); -static void netiucv_callback_connack(struct iucv_path *, u8 ipuser[16]); -static void netiucv_callback_connrej(struct iucv_path *, u8 ipuser[16]); -static void netiucv_callback_connsusp(struct iucv_path *, u8 ipuser[16]); -static void netiucv_callback_connres(struct iucv_path *, u8 ipuser[16]); +static int netiucv_callback_connreq(struct iucv_path *, u8 *, u8 *); +static void netiucv_callback_connack(struct iucv_path *, u8 *); +static void netiucv_callback_connrej(struct iucv_path *, u8 *); +static void netiucv_callback_connsusp(struct iucv_path *, u8 *); +static void netiucv_callback_connres(struct iucv_path *, u8 *); static void netiucv_callback_rx(struct iucv_path *, struct iucv_message *); static void netiucv_callback_txdone(struct iucv_path *, struct iucv_message *); @@ -556,8 +555,8 @@ static void netiucv_callback_connack(struct iucv_path *path, u8 ipuser[16]) fsm_event(conn->fsm, CONN_EVENT_CONN_ACK, conn); } -static int netiucv_callback_connreq(struct iucv_path *path, - u8 ipvmid[8], u8 ipuser[16]) +static int netiucv_callback_connreq(struct iucv_path *path, u8 *ipvmid, + u8 *ipuser) { struct iucv_connection *conn = path->private; struct iucv_event ev; @@ -587,21 +586,21 @@ static int netiucv_callback_connreq(struct iucv_path *path, return rc; } -static void netiucv_callback_connrej(struct iucv_path *path, u8 ipuser[16]) +static void netiucv_callback_connrej(struct iucv_path *path, u8 *ipuser) { struct iucv_connection *conn = path->private; fsm_event(conn->fsm, CONN_EVENT_CONN_REJ, conn); } -static void netiucv_callback_connsusp(struct iucv_path *path, u8 ipuser[16]) +static void netiucv_callback_connsusp(struct iucv_path *path, u8 *ipuser) { struct iucv_connection *conn = path->private; fsm_event(conn->fsm, CONN_EVENT_CONN_SUS, conn); } -static void netiucv_callback_connres(struct iucv_path *path, u8 ipuser[16]) +static void netiucv_callback_connres(struct iucv_path *path, u8 *ipuser) { struct iucv_connection *conn = path->private; diff --git a/drivers/s390/net/smsgiucv.c b/drivers/s390/net/smsgiucv.c index d8f990b6b332..a851d34c642b 100644 --- a/drivers/s390/net/smsgiucv.c +++ b/drivers/s390/net/smsgiucv.c @@ -49,7 +49,7 @@ static DEFINE_SPINLOCK(smsg_list_lock); static LIST_HEAD(smsg_list); static int iucv_path_connected; -static int smsg_path_pending(struct iucv_path *, u8 ipvmid[8], u8 ipuser[16]); +static int smsg_path_pending(struct iucv_path *, u8 *, u8 *); static void smsg_message_pending(struct iucv_path *, struct iucv_message *); static struct iucv_handler smsg_handler = { @@ -57,8 +57,7 @@ static struct iucv_handler smsg_handler = { .message_pending = smsg_message_pending, }; -static int smsg_path_pending(struct iucv_path *path, u8 ipvmid[8], - u8 ipuser[16]) +static int smsg_path_pending(struct iucv_path *path, u8 *ipvmid, u8 *ipuser) { if (strncmp(ipvmid, "*MSG ", 8) != 0) return -EINVAL; diff --git a/drivers/tty/hvc/hvc_iucv.c b/drivers/tty/hvc/hvc_iucv.c index bb809cf36617..8b70a1627356 100644 --- a/drivers/tty/hvc/hvc_iucv.c +++ b/drivers/tty/hvc/hvc_iucv.c @@ -88,8 +88,8 @@ struct iucv_tty_buffer { }; /* IUCV callback handler */ -static int hvc_iucv_path_pending(struct iucv_path *, u8[8], u8[16]); -static void hvc_iucv_path_severed(struct iucv_path *, u8[16]); +static int hvc_iucv_path_pending(struct iucv_path *, u8 *, u8 *); +static void hvc_iucv_path_severed(struct iucv_path *, u8 *); static void hvc_iucv_msg_pending(struct iucv_path *, struct iucv_message *); static void hvc_iucv_msg_complete(struct iucv_path *, struct iucv_message *); @@ -782,8 +782,8 @@ static int hvc_iucv_filter_connreq(u8 ipvmid[8]) * * Locking: struct hvc_iucv_private->lock */ -static int hvc_iucv_path_pending(struct iucv_path *path, - u8 ipvmid[8], u8 ipuser[16]) +static int hvc_iucv_path_pending(struct iucv_path *path, u8 *ipvmid, + u8 *ipuser) { struct hvc_iucv_private *priv, *tmp; u8 wildcard[9] = "lnxhvc "; @@ -881,7 +881,7 @@ out_path_handled: * * Locking: struct hvc_iucv_private->lock */ -static void hvc_iucv_path_severed(struct iucv_path *path, u8 ipuser[16]) +static void hvc_iucv_path_severed(struct iucv_path *path, u8 *ipuser) { struct hvc_iucv_private *priv = path->private; diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index 0894ced31957..b867b0cf79e8 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -141,14 +141,14 @@ struct iucv_handler { * called is the order of the registration of the iucv handlers * to the base code. */ - int (*path_pending)(struct iucv_path *, u8 ipvmid[8], u8 ipuser[16]); + int (*path_pending)(struct iucv_path *, u8 *ipvmid, u8 *ipuser); /* * The path_complete function is called after an iucv interrupt * type 0x02 has been received for a path that has been established * for this handler with iucv_path_connect and got accepted by the * peer with iucv_path_accept. */ - void (*path_complete)(struct iucv_path *, u8 ipuser[16]); + void (*path_complete)(struct iucv_path *, u8 *ipuser); /* * The path_severed function is called after an iucv interrupt * type 0x03 has been received. The communication peer shutdown @@ -156,20 +156,20 @@ struct iucv_handler { * remaining messages can be received until a iucv_path_sever * shuts down the other end of the path as well. */ - void (*path_severed)(struct iucv_path *, u8 ipuser[16]); + void (*path_severed)(struct iucv_path *, u8 *ipuser); /* * The path_quiesced function is called after an icuv interrupt * type 0x04 has been received. The communication peer has quiesced * the path. Delivery of messages is stopped until iucv_path_resume * has been called. */ - void (*path_quiesced)(struct iucv_path *, u8 ipuser[16]); + void (*path_quiesced)(struct iucv_path *, u8 *ipuser); /* * The path_resumed function is called after an icuv interrupt * type 0x05 has been received. The communication peer has resumed * the path. */ - void (*path_resumed)(struct iucv_path *, u8 ipuser[16]); + void (*path_resumed)(struct iucv_path *, u8 *ipuser); /* * The message_pending function is called after an icuv interrupt * type 0x06 or type 0x07 has been received. A new message is @@ -256,7 +256,7 @@ static inline void iucv_path_free(struct iucv_path *path) * Returns the result of the CP IUCV call. */ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, - u8 userdata[16], void *private); + u8 *userdata, void *private); /** * iucv_path_connect @@ -274,7 +274,7 @@ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, * Returns the result of the CP IUCV call. */ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, - u8 userid[8], u8 system[8], u8 userdata[16], + u8 *userid, u8 *system, u8 *userdata, void *private); /** @@ -287,7 +287,7 @@ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, * * Returns the result from the CP IUCV call. */ -int iucv_path_quiesce(struct iucv_path *path, u8 userdata[16]); +int iucv_path_quiesce(struct iucv_path *path, u8 *userdata); /** * iucv_path_resume: @@ -299,7 +299,7 @@ int iucv_path_quiesce(struct iucv_path *path, u8 userdata[16]); * * Returns the result from the CP IUCV call. */ -int iucv_path_resume(struct iucv_path *path, u8 userdata[16]); +int iucv_path_resume(struct iucv_path *path, u8 *userdata); /** * iucv_path_sever @@ -310,7 +310,7 @@ int iucv_path_resume(struct iucv_path *path, u8 userdata[16]); * * Returns the result from the CP IUCV call. */ -int iucv_path_sever(struct iucv_path *path, u8 userdata[16]); +int iucv_path_sever(struct iucv_path *path, u8 *userdata); /** * iucv_message_purge diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 918151c11348..fcb2752419c6 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -95,11 +95,10 @@ static void afiucv_hs_callback_txnotify(struct sk_buff *, enum iucv_tx_notify); /* Call Back functions */ static void iucv_callback_rx(struct iucv_path *, struct iucv_message *); static void iucv_callback_txdone(struct iucv_path *, struct iucv_message *); -static void iucv_callback_connack(struct iucv_path *, u8 ipuser[16]); -static int iucv_callback_connreq(struct iucv_path *, u8 ipvmid[8], - u8 ipuser[16]); -static void iucv_callback_connrej(struct iucv_path *, u8 ipuser[16]); -static void iucv_callback_shutdown(struct iucv_path *, u8 ipuser[16]); +static void iucv_callback_connack(struct iucv_path *, u8 *); +static int iucv_callback_connreq(struct iucv_path *, u8 *, u8 *); +static void iucv_callback_connrej(struct iucv_path *, u8 *); +static void iucv_callback_shutdown(struct iucv_path *, u8 *); static struct iucv_sock_list iucv_sk_list = { .lock = __RW_LOCK_UNLOCKED(iucv_sk_list.lock), diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 2a6a1fdd62c0..7eaa000c9258 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -713,7 +713,7 @@ static struct notifier_block __refdata iucv_cpu_notifier = { * * Sever an iucv path to free up the pathid. Used internally. */ -static int iucv_sever_pathid(u16 pathid, u8 userdata[16]) +static int iucv_sever_pathid(u16 pathid, u8 *userdata) { union iucv_param *parm; @@ -876,7 +876,7 @@ static struct notifier_block iucv_reboot_notifier = { * Returns the result of the CP IUCV call. */ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, - u8 userdata[16], void *private) + u8 *userdata, void *private) { union iucv_param *parm; int rc; @@ -923,7 +923,7 @@ EXPORT_SYMBOL(iucv_path_accept); * Returns the result of the CP IUCV call. */ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, - u8 userid[8], u8 system[8], u8 userdata[16], + u8 *userid, u8 *system, u8 *userdata, void *private) { union iucv_param *parm; @@ -985,7 +985,7 @@ EXPORT_SYMBOL(iucv_path_connect); * * Returns the result from the CP IUCV call. */ -int iucv_path_quiesce(struct iucv_path *path, u8 userdata[16]) +int iucv_path_quiesce(struct iucv_path *path, u8 *userdata) { union iucv_param *parm; int rc; @@ -1017,7 +1017,7 @@ EXPORT_SYMBOL(iucv_path_quiesce); * * Returns the result from the CP IUCV call. */ -int iucv_path_resume(struct iucv_path *path, u8 userdata[16]) +int iucv_path_resume(struct iucv_path *path, u8 *userdata) { union iucv_param *parm; int rc; @@ -1047,7 +1047,7 @@ out: * * Returns the result from the CP IUCV call. */ -int iucv_path_sever(struct iucv_path *path, u8 userdata[16]) +int iucv_path_sever(struct iucv_path *path, u8 *userdata) { int rc; -- cgit v1.2.3 From 0f1c28ae74bb1a34d36fca2db5161611d58b3148 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 18 Sep 2015 11:36:14 -0700 Subject: tcp: usec resolution SYN/ACK RTT Currently SYN/ACK RTT is measured in jiffies. For LAN the SYN/ACK RTT is often measured as 0ms or sometimes 1ms, which would affect RTT estimation and min RTT samping used by some congestion control. This patch improves SYN/ACK RTT to be usec resolution if platform supports it. While the timestamping of SYN/ACK is done in request sock, the RTT measurement is carefully arranged to avoid storing another u64 timestamp in tcp_sock. For regular handshake w/o SYNACK retransmission, the RTT is sampled right after the child socket is created and right before the request sock is released (tcp_check_req() in tcp_minisocks.c) For Fast Open the child socket is already created when SYN/ACK was sent, the RTT is sampled in tcp_rcv_state_process() after processing the final ACK an right before the request socket is released. If the SYN/ACK was retransmistted or SYN-cookie was used, we rely on TCP timestamps to measure the RTT. The sample is taken at the same place in tcp_rcv_state_process() after the timestamp values are validated in tcp_validate_incoming(). Note that we do not store TS echo value in request_sock for SYN-cookies, because the value is already stored in tp->rx_opt used by tcp_ack_update_rtt(). One side benefit is that the RTT measurement now happens before initializing congestion control (of the passive side). Therefore the congestion control can use the SYN/ACK RTT. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- include/net/tcp.h | 1 + net/ipv4/syncookies.c | 2 +- net/ipv4/tcp_input.c | 29 ++++++++++++++--------------- net/ipv4/tcp_minisocks.c | 3 ++- net/ipv6/syncookies.c | 2 +- 6 files changed, 20 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 937b97893d5f..fcb573be75d9 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -112,11 +112,11 @@ struct tcp_request_sock_ops; struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; + struct skb_mstamp snt_synack; /* first SYNACK sent time */ bool tfo_listener; u32 txhash; u32 rcv_isn; u32 snt_isn; - u32 snt_synack; /* synack sent time */ u32 last_oow_ack_time; /* last SYNACK */ u32 rcv_nxt; /* the ack # by SYNACK. For * FastOpen it's the seq# diff --git a/include/net/tcp.h b/include/net/tcp.h index 0cab28cd43a9..5cf9672c13e2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -565,6 +565,7 @@ bool tcp_schedule_loss_probe(struct sock *sk); /* tcp_input.c */ void tcp_resume_early_retransmit(struct sock *sk); void tcp_rearm_rto(struct sock *sk); +void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk); /* tcp_timer.c */ diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index d70b1f603692..6595affded20 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -345,7 +345,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; + treq->snt_synack.v64 = 0; treq->tfo_listener = false; ireq->ir_iif = sk->sk_bound_dev_if; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a62e9c76d485..497adf58a6b8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2953,21 +2953,21 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, } /* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */ -static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp) +void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) { - struct tcp_sock *tp = tcp_sk(sk); - long seq_rtt_us = -1L; + long rtt_us = -1L; - if (synack_stamp && !tp->total_retrans) - seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - synack_stamp); + if (req && !req->num_retrans && tcp_rsk(req)->snt_synack.v64) { + struct skb_mstamp now; - /* If the ACK acks both the SYNACK and the (Fast Open'd) data packets - * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack() - */ - if (!tp->srtt_us) - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt_us, -1L); + skb_mstamp_get(&now); + rtt_us = skb_mstamp_us_delta(&now, &tcp_rsk(req)->snt_synack); + } + + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L); } + static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -5706,7 +5706,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, struct request_sock *req; int queued = 0; bool acceptable; - u32 synack_stamp; tp->rx_opt.saw_tstamp = 0; @@ -5785,15 +5784,16 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (!acceptable) return 1; + if (!tp->srtt_us) + tcp_synack_rtt_meas(sk, req); + /* Once we leave TCP_SYN_RECV, we no longer need req * so release it. */ if (req) { - synack_stamp = tcp_rsk(req)->snt_synack; tp->total_retrans = req->num_retrans; reqsk_fastopen_remove(sk, req, false); } else { - synack_stamp = tp->lsndtime; /* Make sure socket is routed, for correct metrics. */ icsk->icsk_af_ops->rebuild_header(sk); tcp_init_congestion_control(sk); @@ -5816,7 +5816,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, tp->snd_una = TCP_SKB_CB(skb)->ack_seq; tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); - tcp_synack_rtt_meas(sk, synack_stamp); if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; @@ -6027,7 +6026,7 @@ static void tcp_openreq_init(struct request_sock *req, req->cookie_ts = 0; tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - tcp_rsk(req)->snt_synack = tcp_time_stamp; + skb_mstamp_get(&tcp_rsk(req)->snt_synack); tcp_rsk(req)->last_oow_ack_time = 0; req->mss = rx_opt->mss_clamp; req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6d8795b066ac..10933d01b982 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -470,7 +470,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tcp_enable_early_retrans(newtp); newtp->tlp_high_seq = 0; - newtp->lsndtime = treq->snt_synack; + newtp->lsndtime = treq->snt_synack.stamp_jiffies; newtp->last_oow_ack_time = 0; newtp->total_retrans = req->num_retrans; @@ -760,6 +760,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!child) goto listen_overflow; + tcp_synack_rtt_meas(child, req); inet_csk_reqsk_queue_drop(sk, req); inet_csk_reqsk_queue_add(sk, req, child); /* Warning: caller must not call reqsk_put(req); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 0909f4e0d53c..2461b3ff9551 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -210,7 +210,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; + treq->snt_synack.v64 = 0; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; -- cgit v1.2.3 From ed2e923945892a8372ab70d2f61d364b0b6d9054 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 19 Sep 2015 09:08:34 -0700 Subject: tcp/dccp: fix timewait races in timer handling When creating a timewait socket, we need to arm the timer before allowing other cpus to find it. The signal allowing cpus to find the socket is setting tw_refcnt to non zero value. As we set tw_refcnt in __inet_twsk_hashdance(), we therefore need to call inet_twsk_schedule() first. This also means we need to remove tw_refcnt changes from inet_twsk_schedule() and let the caller handle it. Note that because we use mod_timer_pinned(), we have the guarantee the timer wont expire before we set tw_refcnt as we run in BH context. To make things more readable I introduced inet_twsk_reschedule() helper. When rearming the timer, we can use mod_timer_pending() to make sure we do not rearm a canceled timer. Note: This bug can possibly trigger if packets of a flow can hit multiple cpus. This does not normally happen, unless flow steering is broken somehow. This explains this bug was spotted ~5 months after its introduction. A similar fix is needed for SYN_RECV sockets in reqsk_queue_hash_req(), but will be provided in a separate patch for proper tracking. Fixes: 789f558cfb36 ("tcp/dccp: get rid of central timewait timer") Signed-off-by: Eric Dumazet Reported-by: Ying Cai Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 14 +++++++++++++- net/dccp/minisocks.c | 4 ++-- net/ipv4/inet_timewait_sock.c | 16 ++++++++++------ net/ipv4/tcp_minisocks.c | 13 ++++++------- 4 files changed, 31 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 879d6e5a973b..186f3a1e1b1f 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -110,7 +110,19 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, struct inet_hashinfo *hashinfo); -void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo); +void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, + bool rearm); + +static void inline inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo) +{ + __inet_twsk_schedule(tw, timeo, false); +} + +static void inline inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo) +{ + __inet_twsk_schedule(tw, timeo, true); +} + void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); void inet_twsk_purge(struct inet_hashinfo *hashinfo, diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 30addee2dd03..838f524cf11a 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -48,8 +48,6 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) tw->tw_ipv6only = sk->sk_ipv6only; } #endif - /* Linkage updates. */ - __inet_twsk_hashdance(tw, sk, &dccp_hashinfo); /* Get the TIME_WAIT timeout firing. */ if (timeo < rto) @@ -60,6 +58,8 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) timeo = DCCP_TIMEWAIT_LEN; inet_twsk_schedule(tw, timeo); + /* Linkage updates. */ + __inet_twsk_hashdance(tw, sk, &dccp_hashinfo); inet_twsk_put(tw); } else { /* Sorry, if we're out of memory, just CLOSE this diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index ae22cc24fbe8..c67f9bd7699c 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -123,13 +123,15 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, /* * Step 2: Hash TW into tcp ehash chain. * Notes : - * - tw_refcnt is set to 3 because : + * - tw_refcnt is set to 4 because : * - We have one reference from bhash chain. * - We have one reference from ehash chain. + * - We have one reference from timer. + * - One reference for ourself (our caller will release it). * We can use atomic_set() because prior spin_lock()/spin_unlock() * committed into memory all tw fields. */ - atomic_set(&tw->tw_refcnt, 1 + 1 + 1); + atomic_set(&tw->tw_refcnt, 4); inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ @@ -217,7 +219,7 @@ void inet_twsk_deschedule_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL(inet_twsk_deschedule_put); -void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) +void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) { /* timeout := RTO * 3.5 * @@ -245,12 +247,14 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) */ tw->tw_kill = timeo <= 4*HZ; - if (!mod_timer_pinned(&tw->tw_timer, jiffies + timeo)) { - atomic_inc(&tw->tw_refcnt); + if (!rearm) { + BUG_ON(mod_timer_pinned(&tw->tw_timer, jiffies + timeo)); atomic_inc(&tw->tw_dr->tw_count); + } else { + mod_timer_pending(&tw->tw_timer, jiffies + timeo); } } -EXPORT_SYMBOL_GPL(inet_twsk_schedule); +EXPORT_SYMBOL_GPL(__inet_twsk_schedule); void inet_twsk_purge(struct inet_hashinfo *hashinfo, struct inet_timewait_death_row *twdr, int family) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6d8795b066ac..def765911ff8 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -162,9 +162,9 @@ kill_with_rst: if (tcp_death_row.sysctl_tw_recycle && tcptw->tw_ts_recent_stamp && tcp_tw_remember_stamp(tw)) - inet_twsk_schedule(tw, tw->tw_timeout); + inet_twsk_reschedule(tw, tw->tw_timeout); else - inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); return TCP_TW_ACK; } @@ -201,7 +201,7 @@ kill: return TCP_TW_SUCCESS; } } - inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); if (tmp_opt.saw_tstamp) { tcptw->tw_ts_recent = tmp_opt.rcv_tsval; @@ -251,7 +251,7 @@ kill: * Do not reschedule in the last case. */ if (paws_reject || th->ack) - inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); return tcp_timewait_check_oow_rate_limit( tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT); @@ -322,9 +322,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } while (0); #endif - /* Linkage updates. */ - __inet_twsk_hashdance(tw, sk, &tcp_hashinfo); - /* Get the TIME_WAIT timeout firing. */ if (timeo < rto) timeo = rto; @@ -338,6 +335,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } inet_twsk_schedule(tw, timeo); + /* Linkage updates. */ + __inet_twsk_hashdance(tw, sk, &tcp_hashinfo); inet_twsk_put(tw); } else { /* Sorry, if we're out of memory, just CLOSE this -- cgit v1.2.3 From a1da67b8117ddbe88c770b48b5b1527393b8c9c0 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 18 Sep 2015 11:30:41 +0200 Subject: ieee802154: header_ops: fix frame control setting Sometimes upper-layer protocols wants to generate a new mac header by filling "struct ieee802154_hdr" only. These upper-layers sets for the address settings the source and dest fields, but not the fc fields for indicate the source and dest address mode. This patch changes the "ieee802154_hdr_push" function so the fc address fields are set according the source and dest fields of "struct ieee802154_hdr". Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/ieee802154_netdev.h | 2 +- net/ieee802154/header_ops.c | 18 +++++++++--------- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index 2c10a9f0c6d9..95a71bc113b3 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -99,7 +99,7 @@ struct ieee802154_hdr { * hdr->fc will be ignored. this includes the INTRA_PAN bit and the frame * version, if SECEN is set. */ -int ieee802154_hdr_push(struct sk_buff *skb, const struct ieee802154_hdr *hdr); +int ieee802154_hdr_push(struct sk_buff *skb, struct ieee802154_hdr *hdr); /* pulls the entire 802.15.4 header off of the skb, including the security * header, and performs pan id decompression diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c index a051b6993177..d8443b057022 100644 --- a/net/ieee802154/header_ops.c +++ b/net/ieee802154/header_ops.c @@ -83,35 +83,35 @@ ieee802154_hdr_push_sechdr(u8 *buf, const struct ieee802154_sechdr *hdr) } int -ieee802154_hdr_push(struct sk_buff *skb, const struct ieee802154_hdr *hdr) +ieee802154_hdr_push(struct sk_buff *skb, struct ieee802154_hdr *hdr) { u8 buf[MAC802154_FRAME_HARD_HEADER_LEN]; int pos = 2; int rc; - struct ieee802154_hdr_fc fc = hdr->fc; + struct ieee802154_hdr_fc *fc = &hdr->fc; buf[pos++] = hdr->seq; - fc.dest_addr_mode = hdr->dest.mode; + fc->dest_addr_mode = hdr->dest.mode; rc = ieee802154_hdr_push_addr(buf + pos, &hdr->dest, false); if (rc < 0) return -EINVAL; pos += rc; - fc.source_addr_mode = hdr->source.mode; + fc->source_addr_mode = hdr->source.mode; if (hdr->source.pan_id == hdr->dest.pan_id && hdr->dest.mode != IEEE802154_ADDR_NONE) - fc.intra_pan = true; + fc->intra_pan = true; - rc = ieee802154_hdr_push_addr(buf + pos, &hdr->source, fc.intra_pan); + rc = ieee802154_hdr_push_addr(buf + pos, &hdr->source, fc->intra_pan); if (rc < 0) return -EINVAL; pos += rc; - if (fc.security_enabled) { - fc.version = 1; + if (fc->security_enabled) { + fc->version = 1; rc = ieee802154_hdr_push_sechdr(buf + pos, &hdr->sec); if (rc < 0) @@ -120,7 +120,7 @@ ieee802154_hdr_push(struct sk_buff *skb, const struct ieee802154_hdr *hdr) pos += rc; } - memcpy(buf, &fc, 2); + memcpy(buf, fc, 2); memcpy(skb_push(skb, pos), buf, pos); -- cgit v1.2.3 From 838b83d63d2909f9136f3030dc4fffa8230c31da Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 18 Sep 2015 11:30:42 +0200 Subject: ieee802154: introduce wpan_dev_header_ops The current header_ops callback structure of net device are used mostly from 802.15.4 upper-layers. Because this callback structure is a very generic one, which is also used by e.g. DGRAM AF_PACKET sockets, we can't make this callback structure 802.15.4 specific which is currently is. I saw the smallest "constraint" for calling this callback with dev_hard_header/dev_parse_header by AF_PACKET which assign a 8 byte array for address void pointers. Currently 802.15.4 specific protocols like af802154 and 6LoWPAN will assign the "struct ieee802154_addr" as these parameters which is greater than 8 bytes. The current callback implementation for header_ops.create assumes always a complete "struct ieee802154_addr" which AF_PACKET can't never handled and is greater than 8 bytes. For that reason we introduce now a "generic" create/parse header_ops callback which allows handling with intra-pan extended addresses only. This allows a small use-case with AF_PACKET to send "somehow" a valid dataframe over DGRAM. To keeping the current dev_hard_header behaviour we introduce a similar callback structure "wpan_dev_header_ops" which contains 802.15.4 specific upper-layer header creation functionality, which can be called by wpan_dev_hard_header. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/cfg802154.h | 33 +++++++++++++++ include/net/ieee802154_netdev.h | 9 ---- net/ieee802154/6lowpan/tx.c | 8 ++-- net/ieee802154/socket.c | 4 +- net/mac802154/iface.c | 91 +++++++++++++++++++++++++++++++++++------ 5 files changed, 118 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 76b1ffaea863..242273ccf34b 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -167,6 +167,26 @@ struct wpan_phy { char priv[0] __aligned(NETDEV_ALIGN); }; +struct ieee802154_addr { + u8 mode; + __le16 pan_id; + union { + __le16 short_addr; + __le64 extended_addr; + }; +}; + +struct wpan_dev_header_ops { + /* TODO create callback currently assumes ieee802154_mac_cb inside + * skb->cb. This should be changed to give these information as + * parameter. + */ + int (*create)(struct sk_buff *skb, struct net_device *dev, + const struct ieee802154_addr *daddr, + const struct ieee802154_addr *saddr, + unsigned int len); +}; + struct wpan_dev { struct wpan_phy *wpan_phy; int iftype; @@ -175,6 +195,8 @@ struct wpan_dev { struct list_head list; struct net_device *netdev; + const struct wpan_dev_header_ops *header_ops; + /* lowpan interface, set when the wpan_dev belongs to one lowpan_dev */ struct net_device *lowpan_dev; @@ -205,6 +227,17 @@ struct wpan_dev { #define to_phy(_dev) container_of(_dev, struct wpan_phy, dev) +static inline int +wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, + const struct ieee802154_addr *daddr, + const struct ieee802154_addr *saddr, + unsigned int len) +{ + struct wpan_dev *wpan_dev = dev->ieee802154_ptr; + + return wpan_dev->header_ops->create(skb, dev, daddr, saddr, len); +} + struct wpan_phy * wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size); static inline void wpan_phy_set_dev(struct wpan_phy *phy, struct device *dev) diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index 95a71bc113b3..aebb9d8d7a11 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -50,15 +50,6 @@ struct ieee802154_sechdr { }; }; -struct ieee802154_addr { - u8 mode; - __le16 pan_id; - union { - __le16 short_addr; - __le64 extended_addr; - }; -}; - struct ieee802154_hdr_fc { #if defined(__LITTLE_ENDIAN_BITFIELD) u16 type:3, diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c index 54939d031ea5..6067e064a3fe 100644 --- a/net/ieee802154/6lowpan/tx.c +++ b/net/ieee802154/6lowpan/tx.c @@ -87,8 +87,8 @@ lowpan_alloc_frag(struct sk_buff *skb, int size, skb_reset_network_header(frag); *mac_cb(frag) = *mac_cb(skb); - rc = dev_hard_header(frag, wdev, 0, &master_hdr->dest, - &master_hdr->source, size); + rc = wpan_dev_hard_header(frag, wdev, &master_hdr->dest, + &master_hdr->source, size); if (rc < 0) { kfree_skb(frag); return ERR_PTR(rc); @@ -228,8 +228,8 @@ static int lowpan_header(struct sk_buff *skb, struct net_device *ldev, cb->ackreq = wpan_dev->ackreq; } - return dev_hard_header(skb, lowpan_dev_info(ldev)->wdev, ETH_P_IPV6, - (void *)&da, (void *)&sa, 0); + return wpan_dev_hard_header(skb, lowpan_dev_info(ldev)->wdev, &da, &sa, + 0); } netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev) diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index b6eacf30ee7a..be77f211ce87 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -676,8 +676,8 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) cb->seclevel = ro->seclevel; cb->seclevel_override = ro->seclevel_override; - err = dev_hard_header(skb, dev, ETH_P_IEEE802154, &dst_addr, - ro->bound ? &ro->src_addr : NULL, size); + err = wpan_dev_hard_header(skb, dev, &dst_addr, + ro->bound ? &ro->src_addr : NULL, size); if (err < 0) goto out_skb; diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index ed26952f9e14..8afe26d72971 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -367,12 +367,11 @@ static int mac802154_set_header_security(struct ieee802154_sub_if_data *sdata, return 0; } -static int mac802154_header_create(struct sk_buff *skb, - struct net_device *dev, - unsigned short type, - const void *daddr, - const void *saddr, - unsigned len) +static int ieee802154_header_create(struct sk_buff *skb, + struct net_device *dev, + const struct ieee802154_addr *daddr, + const struct ieee802154_addr *saddr, + unsigned len) { struct ieee802154_hdr hdr; struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); @@ -423,24 +422,91 @@ static int mac802154_header_create(struct sk_buff *skb, return hlen; } +static const struct wpan_dev_header_ops ieee802154_header_ops = { + .create = ieee802154_header_create, +}; + +/* This header create functionality assumes a 8 byte array for + * source and destination pointer at maximum. To adapt this for + * the 802.15.4 dataframe header we use extended address handling + * here only and intra pan connection. fc fields are mostly fallback + * handling. For provide dev_hard_header for dgram sockets. + */ +static int mac802154_header_create(struct sk_buff *skb, + struct net_device *dev, + unsigned short type, + const void *daddr, + const void *saddr, + unsigned len) +{ + struct ieee802154_hdr hdr; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + struct wpan_dev *wpan_dev = &sdata->wpan_dev; + struct ieee802154_mac_cb cb = { }; + int hlen; + + if (!daddr) + return -EINVAL; + + memset(&hdr.fc, 0, sizeof(hdr.fc)); + hdr.fc.type = IEEE802154_FC_TYPE_DATA; + hdr.fc.ack_request = wpan_dev->ackreq; + hdr.seq = atomic_inc_return(&dev->ieee802154_ptr->dsn) & 0xFF; + + /* TODO currently a workaround to give zero cb block to set + * security parameters defaults according MIB. + */ + if (mac802154_set_header_security(sdata, &hdr, &cb) < 0) + return -EINVAL; + + hdr.dest.pan_id = wpan_dev->pan_id; + hdr.dest.mode = IEEE802154_ADDR_LONG; + memcpy(&hdr.dest.extended_addr, daddr, IEEE802154_EXTENDED_ADDR_LEN); + + hdr.source.pan_id = hdr.dest.pan_id; + hdr.source.mode = IEEE802154_ADDR_LONG; + + if (!saddr) + hdr.source.extended_addr = wpan_dev->extended_addr; + else + memcpy(&hdr.source.extended_addr, saddr, + IEEE802154_EXTENDED_ADDR_LEN); + + hlen = ieee802154_hdr_push(skb, &hdr); + if (hlen < 0) + return -EINVAL; + + skb_reset_mac_header(skb); + skb->mac_len = hlen; + + if (len > ieee802154_max_payload(&hdr)) + return -EMSGSIZE; + + return hlen; +} + static int mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr) { struct ieee802154_hdr hdr; - struct ieee802154_addr *addr = (struct ieee802154_addr *)haddr; if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) { pr_debug("malformed packet\n"); return 0; } - *addr = hdr.source; - return sizeof(*addr); + if (hdr.source.mode == IEEE802154_ADDR_LONG) { + memcpy(haddr, &hdr.source.extended_addr, + IEEE802154_EXTENDED_ADDR_LEN); + return IEEE802154_EXTENDED_ADDR_LEN; + } + + return 0; } -static struct header_ops mac802154_header_ops = { - .create = mac802154_header_create, - .parse = mac802154_header_parse, +static const struct header_ops mac802154_header_ops = { + .create = mac802154_header_create, + .parse = mac802154_header_parse, }; static const struct net_device_ops mac802154_wpan_ops = { @@ -513,6 +579,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, sdata->dev->netdev_ops = &mac802154_wpan_ops; sdata->dev->ml_priv = &mac802154_mlme_wpan; wpan_dev->promiscuous_mode = false; + wpan_dev->header_ops = &ieee802154_header_ops; mutex_init(&sdata->sec_mtx); -- cgit v1.2.3 From 87a93e4eceb495f93e3f37b100334d2641765b6c Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 18 Sep 2015 11:30:43 +0200 Subject: ieee802154: change needed headroom/tailroom This patch cleanups needed_headroom, needed_tailroom and hard_header_len fields for wpan and lowpan interfaces. For wpan interfaces the worst case mac header len should be part of needed_headroom, currently this is set as hard_header_len, but hard_header_len should be set to the minimum header length which xmit call assumes and this is the minimum frame length of 802.15.4. The hard_header_len value will check inside send callbacl of AF_PACKET raw sockets. For lowpan interfaces, if fragmentation isn't needed the skb will call dev_hard_header for 802154 layer and queue it afterwards. This happens without new skb allocation, so we need the same headroom and tailroom lengths like 802154 inside 802154 6lowpan layer. At least we assume as minimum header length an ipv6 header size. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/linux/ieee802154.h | 11 +++++++++++ include/net/6lowpan.h | 8 ++++++++ include/net/mac802154.h | 8 -------- net/6lowpan/nhc.h | 2 -- net/ieee802154/6lowpan/core.c | 14 +++++++++++--- net/ieee802154/6lowpan/tx.c | 12 ++++++++++-- net/ieee802154/header_ops.c | 2 +- net/mac802154/iface.c | 17 ++++++++++++++--- net/mac802154/tx.c | 3 --- 9 files changed, 55 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index db01492814d3..205ce4e1ac32 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -31,6 +31,17 @@ #define IEEE802154_ACK_PSDU_LEN 5 #define IEEE802154_MIN_PSDU_LEN 9 #define IEEE802154_FCS_LEN 2 +#define IEEE802154_MAX_AUTH_TAG_LEN 16 + +/* General MAC frame format: + * 2 bytes: Frame Control + * 1 byte: Sequence Number + * 20 bytes: Addressing fields + * 14 bytes: Auxiliary Security Header + */ +#define IEEE802154_MAX_HEADER_LEN (2 + 1 + 20 + 14) +#define IEEE802154_MIN_HEADER_LEN (IEEE802154_ACK_PSDU_LEN - \ + IEEE802154_FCS_LEN) #define IEEE802154_PAN_ID_BROADCAST 0xffff #define IEEE802154_ADDR_SHORT_BROADCAST 0xffff diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index eeae5eb58754..c17f556644fc 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -61,6 +61,14 @@ #define UIP_PROTO_UDP 17 /* ipv6 next header value for UDP */ #define UIP_FRAGH_LEN 8 /* ipv6 fragment header size */ +#define LOWPAN_NHC_MAX_ID_LEN 1 +/* Max IPHC Header len without IPv6 hdr specific inline data. + * Useful for getting the "extra" bytes we need at worst case compression. + * + * LOWPAN_IPHC + CID + LOWPAN_NHC_MAX_ID_LEN + */ +#define LOWPAN_IPHC_MAX_HEADER_LEN (2 + 1 + LOWPAN_NHC_MAX_ID_LEN) + /* * ipv6 address based on mac * second bit-flip (Universe/Local) is done according RFC2464 diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 32bd7c0467d4..2c478501ad14 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -23,14 +23,6 @@ #include -/* General MAC frame format: - * 2 bytes: Frame Control - * 1 byte: Sequence Number - * 20 bytes: Addressing fields - * 14 bytes: Auxiliary Security Header - */ -#define MAC802154_FRAME_HARD_HEADER_LEN (2 + 1 + 20 + 14) - /** * enum ieee802154_hw_addr_filt_flags - hardware address filtering flags * diff --git a/net/6lowpan/nhc.h b/net/6lowpan/nhc.h index ed44938eb5de..c249f17fa37b 100644 --- a/net/6lowpan/nhc.h +++ b/net/6lowpan/nhc.h @@ -8,8 +8,6 @@ #include #include -#define LOWPAN_NHC_MAX_ID_LEN 1 - /** * LOWPAN_NHC - helper macro to generate nh id fields and lowpan_nhc struct * diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 9f0cfa598e3a..44420ed95574 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -104,9 +104,8 @@ static void lowpan_setup(struct net_device *ldev) ldev->addr_len = IEEE802154_ADDR_LEN; memset(ldev->broadcast, 0xff, IEEE802154_ADDR_LEN); ldev->type = ARPHRD_6LOWPAN; - /* Frame Control + Sequence Number + Address fields + Security Header */ - ldev->hard_header_len = 2 + 1 + 20 + 14; - ldev->needed_tailroom = 2; /* FCS */ + /* We need an ipv6hdr as minimum len when calling xmit */ + ldev->hard_header_len = sizeof(struct ipv6hdr); ldev->mtu = IPV6_MIN_MTU; ldev->priv_flags |= IFF_NO_QUEUE; ldev->flags = IFF_BROADCAST | IFF_MULTICAST; @@ -156,6 +155,15 @@ static int lowpan_newlink(struct net *src_net, struct net_device *ldev, lowpan_dev_info(ldev)->wdev = wdev; /* Set the lowpan hardware address to the wpan hardware address. */ memcpy(ldev->dev_addr, wdev->dev_addr, IEEE802154_ADDR_LEN); + /* We need headroom for possible wpan_dev_hard_header call and tailroom + * for encryption/fcs handling. The lowpan interface will replace + * the IPv6 header with 6LoWPAN header. At worst case the 6LoWPAN + * header has LOWPAN_IPHC_MAX_HEADER_LEN more bytes than the IPv6 + * header. + */ + ldev->needed_headroom = LOWPAN_IPHC_MAX_HEADER_LEN + + wdev->needed_headroom; + ldev->needed_tailroom = wdev->needed_tailroom; lowpan_netdev_setup(ldev, LOWPAN_LLTYPE_IEEE802154); diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c index 6067e064a3fe..7e0563eaea98 100644 --- a/net/ieee802154/6lowpan/tx.c +++ b/net/ieee802154/6lowpan/tx.c @@ -10,6 +10,7 @@ #include #include +#include #include "6lowpan_i.h" @@ -36,6 +37,13 @@ lowpan_addr_info *lowpan_skb_priv(const struct sk_buff *skb) sizeof(struct lowpan_addr_info)); } +/* This callback will be called from AF_PACKET and IPv6 stack, the AF_PACKET + * sockets gives an 8 byte array for addresses only! + * + * TODO I think AF_PACKET DGRAM (sending/receiving) RAW (sending) makes no + * sense here. We should disable it, the right use-case would be AF_INET6 + * RAW/DGRAM sockets. + */ int lowpan_header_create(struct sk_buff *skb, struct net_device *ldev, unsigned short type, const void *_daddr, const void *_saddr, unsigned int len) @@ -77,13 +85,13 @@ lowpan_alloc_frag(struct sk_buff *skb, int size, struct sk_buff *frag; int rc; - frag = alloc_skb(wdev->hard_header_len + wdev->needed_tailroom + size, + frag = alloc_skb(wdev->needed_headroom + wdev->needed_tailroom + size, GFP_ATOMIC); if (likely(frag)) { frag->dev = wdev; frag->priority = skb->priority; - skb_reserve(frag, wdev->hard_header_len); + skb_reserve(frag, wdev->needed_headroom); skb_reset_network_header(frag); *mac_cb(frag) = *mac_cb(skb); diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c index d8443b057022..c7439f0fbbdf 100644 --- a/net/ieee802154/header_ops.c +++ b/net/ieee802154/header_ops.c @@ -85,7 +85,7 @@ ieee802154_hdr_push_sechdr(u8 *buf, const struct ieee802154_sechdr *hdr) int ieee802154_hdr_push(struct sk_buff *skb, struct ieee802154_hdr *hdr) { - u8 buf[MAC802154_FRAME_HARD_HEADER_LEN]; + u8 buf[IEEE802154_MAX_HEADER_LEN]; int pos = 2; int rc; struct ieee802154_hdr_fc *fc = &hdr->fc; diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 8afe26d72971..b5a0936ce514 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -537,8 +537,18 @@ static void ieee802154_if_setup(struct net_device *dev) dev->addr_len = IEEE802154_EXTENDED_ADDR_LEN; memset(dev->broadcast, 0xff, IEEE802154_EXTENDED_ADDR_LEN); - dev->hard_header_len = MAC802154_FRAME_HARD_HEADER_LEN; - dev->needed_tailroom = 2 + 16; /* FCS + MIC */ + /* Let hard_header_len set to IEEE802154_MIN_HEADER_LEN. AF_PACKET + * will not send frames without any payload, but ack frames + * has no payload, so substract one that we can send a 3 bytes + * frame. The xmit callback assumes at least a hard header where two + * bytes fc and sequence field are set. + */ + dev->hard_header_len = IEEE802154_MIN_HEADER_LEN - 1; + /* The auth_tag header is for security and places in private payload + * room of mac frame which stucks between payload and FCS field. + */ + dev->needed_tailroom = IEEE802154_MAX_AUTH_TAG_LEN + + IEEE802154_FCS_LEN; dev->mtu = IEEE802154_MTU; dev->tx_queue_len = 300; dev->flags = IFF_NOARP | IFF_BROADCAST; @@ -617,7 +627,8 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name, if (!ndev) return ERR_PTR(-ENOMEM); - ndev->needed_headroom = local->hw.extra_tx_headroom; + ndev->needed_headroom = local->hw.extra_tx_headroom + + IEEE802154_MAX_HEADER_LEN; ret = dev_alloc_name(ndev, ndev->name); if (ret < 0) diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 7ed439172f30..66d7ecb7c56b 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -77,9 +77,6 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) put_unaligned_le16(crc, skb_put(skb, 2)); } - if (skb_cow_head(skb, local->hw.extra_tx_headroom)) - goto err_tx; - /* Stop the netif queue on each sub_if_data object. */ ieee802154_stop_queue(&local->hw); -- cgit v1.2.3 From 79750ac4257763ff595a8b2cdc7ba580f0b0c8e0 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 21 Sep 2015 11:24:33 +0200 Subject: ieee802154: add helpers for frame control checks This patch introduce two static inline functions. The first to get the frame control field from an sk_buff. The second is for checking on the acknowledgment request bit on the frame control field. Later we can introduce more functions to check on the frame control fields. These will deprecate the current behaviour which requires a host-byteorder conversion and manually bit handling. Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/linux/ieee802154.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 205ce4e1ac32..aca228b81464 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -25,6 +25,8 @@ #include #include +#include +#include #include #define IEEE802154_MTU 127 @@ -218,6 +220,7 @@ enum { /* frame control handling */ #define IEEE802154_FCTL_FTYPE 0x0003 +#define IEEE802154_FCTL_ACKREQ 0x0020 #define IEEE802154_FCTL_INTRA_PAN 0x0040 #define IEEE802154_FTYPE_DATA 0x0001 @@ -232,6 +235,15 @@ static inline int ieee802154_is_data(__le16 fc) cpu_to_le16(IEEE802154_FTYPE_DATA); } +/** + * ieee802154_is_ackreq - check if acknowledgment request bit is set + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee802154_is_ackreq(__le16 fc) +{ + return fc & cpu_to_le16(IEEE802154_FCTL_ACKREQ); +} + /** * ieee802154_is_intra_pan - check if intra pan id communication * @fc: frame control bytes in little-endian byteorder -- cgit v1.2.3 From 7bdbe400d1b2aac116513f90b75969ad2365fba6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 15 Aug 2015 22:39:49 +0300 Subject: nl80211: support vendor dumpit commands In order to transfer many items in vendor commands, support the dumpit netlink method for them. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 9 +++ net/wireless/nl80211.c | 192 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 201 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f0889a247643..0f54c9ef4c7d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2971,12 +2971,21 @@ enum wiphy_vendor_command_flags { * @doit: callback for the operation, note that wdev is %NULL if the * flags didn't ask for a wdev and non-%NULL otherwise; the data * pointer may be %NULL if userspace provided no data at all + * @dumpit: dump callback, for transferring bigger/multiple items. The + * @storage points to cb->args[5], ie. is preserved over the multiple + * dumpit calls. + * It's recommended to not have the same sub command with both @doit and + * @dumpit, so that userspace can assume certain ones are get and others + * are used with dump requests. */ struct wiphy_vendor_command { struct nl80211_vendor_cmd_info info; u32 flags; int (*doit)(struct wiphy *wiphy, struct wireless_dev *wdev, const void *data, int data_len); + int (*dumpit)(struct wiphy *wiphy, struct wireless_dev *wdev, + struct sk_buff *skb, const void *data, int data_len, + unsigned long *storage); }; /** diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5d8748b4c8a2..a4e6c951950f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3,6 +3,7 @@ * * Copyright 2006-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright 2015 Intel Deutschland GmbH */ #include @@ -9938,6 +9939,9 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info) if (!wdev->netdev && !wdev->p2p_started) return -ENETDOWN; } + + if (!vcmd->doit) + return -EOPNOTSUPP; } else { wdev = NULL; } @@ -9957,6 +9961,193 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; } +static int nl80211_prepare_vendor_dump(struct sk_buff *skb, + struct netlink_callback *cb, + struct cfg80211_registered_device **rdev, + struct wireless_dev **wdev) +{ + u32 vid, subcmd; + unsigned int i; + int vcmd_idx = -1; + int err; + void *data = NULL; + unsigned int data_len = 0; + + rtnl_lock(); + + if (cb->args[0]) { + /* subtract the 1 again here */ + struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1); + struct wireless_dev *tmp; + + if (!wiphy) { + err = -ENODEV; + goto out_unlock; + } + *rdev = wiphy_to_rdev(wiphy); + *wdev = NULL; + + if (cb->args[1]) { + list_for_each_entry(tmp, &(*rdev)->wdev_list, list) { + if (tmp->identifier == cb->args[1] - 1) { + *wdev = tmp; + break; + } + } + } + + /* keep rtnl locked in successful case */ + return 0; + } + + err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, + nl80211_fam.attrbuf, nl80211_fam.maxattr, + nl80211_policy); + if (err) + goto out_unlock; + + if (!nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_ID] || + !nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) { + err = -EINVAL; + goto out_unlock; + } + + *wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk), + nl80211_fam.attrbuf); + if (IS_ERR(*wdev)) + *wdev = NULL; + + *rdev = __cfg80211_rdev_from_attrs(sock_net(skb->sk), + nl80211_fam.attrbuf); + if (IS_ERR(*rdev)) { + err = PTR_ERR(*rdev); + goto out_unlock; + } + + vid = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_ID]); + subcmd = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD]); + + for (i = 0; i < (*rdev)->wiphy.n_vendor_commands; i++) { + const struct wiphy_vendor_command *vcmd; + + vcmd = &(*rdev)->wiphy.vendor_commands[i]; + + if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd) + continue; + + if (!vcmd->dumpit) { + err = -EOPNOTSUPP; + goto out_unlock; + } + + vcmd_idx = i; + break; + } + + if (vcmd_idx < 0) { + err = -EOPNOTSUPP; + goto out_unlock; + } + + if (nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_DATA]) { + data = nla_data(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_DATA]); + data_len = nla_len(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_DATA]); + } + + /* 0 is the first index - add 1 to parse only once */ + cb->args[0] = (*rdev)->wiphy_idx + 1; + /* add 1 to know if it was NULL */ + cb->args[1] = *wdev ? (*wdev)->identifier + 1 : 0; + cb->args[2] = vcmd_idx; + cb->args[3] = (unsigned long)data; + cb->args[4] = data_len; + + /* keep rtnl locked in successful case */ + return 0; + out_unlock: + rtnl_unlock(); + return err; +} + +static int nl80211_vendor_cmd_dump(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct cfg80211_registered_device *rdev; + struct wireless_dev *wdev; + unsigned int vcmd_idx; + const struct wiphy_vendor_command *vcmd; + void *data; + int data_len; + int err; + struct nlattr *vendor_data; + + err = nl80211_prepare_vendor_dump(skb, cb, &rdev, &wdev); + if (err) + return err; + + vcmd_idx = cb->args[2]; + data = (void *)cb->args[3]; + data_len = cb->args[4]; + vcmd = &rdev->wiphy.vendor_commands[vcmd_idx]; + + if (vcmd->flags & (WIPHY_VENDOR_CMD_NEED_WDEV | + WIPHY_VENDOR_CMD_NEED_NETDEV)) { + if (!wdev) + return -EINVAL; + if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_NETDEV && + !wdev->netdev) + return -EINVAL; + + if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) { + if (wdev->netdev && + !netif_running(wdev->netdev)) + return -ENETDOWN; + if (!wdev->netdev && !wdev->p2p_started) + return -ENETDOWN; + } + } + + while (1) { + void *hdr = nl80211hdr_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + NL80211_CMD_VENDOR); + if (!hdr) + break; + + if (nla_put_u32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + (wdev && nla_put_u64(skb, NL80211_ATTR_WDEV, + wdev_id(wdev)))) { + genlmsg_cancel(skb, hdr); + break; + } + + vendor_data = nla_nest_start(skb, NL80211_ATTR_VENDOR_DATA); + if (!vendor_data) { + genlmsg_cancel(skb, hdr); + break; + } + + err = vcmd->dumpit(&rdev->wiphy, wdev, skb, data, data_len, + (unsigned long *)&cb->args[5]); + nla_nest_end(skb, vendor_data); + + if (err == -ENOBUFS || err == -ENOENT) { + genlmsg_cancel(skb, hdr); + break; + } else if (err) { + genlmsg_cancel(skb, hdr); + goto out; + } + + genlmsg_end(skb, hdr); + } + + err = skb->len; + out: + rtnl_unlock(); + return err; +} + struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy, enum nl80211_commands cmd, enum nl80211_attrs attr, @@ -10994,6 +11185,7 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_VENDOR, .doit = nl80211_vendor_cmd, + .dumpit = nl80211_vendor_cmd_dump, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WIPHY | -- cgit v1.2.3 From 1b09b5568e5f46c6dfb781d7c1dfad431a6d8ec1 Mon Sep 17 00:00:00 2001 From: Andrei Otcheretianski Date: Sat, 15 Aug 2015 22:39:50 +0300 Subject: mac80211: introduce per vif frame registration API Currently the cfg80211's frame registration api receives wdev, however mac80211 assumes per device filter configuration and ignores wdev. Per device filtering is too wasteful, especially for multi-channel devices. Introduce new per vif frame registration API and use it for probe request registrations in ieee80211_mgmt_frame_register() Also call directly to ieee80211_configure_filter instead of using a work since it is now allowed to sleep in ieee80211_mgmt_frame_register. Signed-off-by: Andrei Otcheretianski Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 16 ++++++++++++++++ net/mac80211/cfg.c | 22 ++++++++++++++++++---- net/mac80211/driver-ops.h | 16 ++++++++++++++++ net/mac80211/trace.h | 30 ++++++++++++++++++++++++++++++ 4 files changed, 80 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e3314e516681..167864503138 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5,6 +5,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright (C) 2015 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1358,6 +1359,8 @@ enum ieee80211_vif_flags { * @debugfs_dir: debugfs dentry, can be used by drivers to create own per * interface debug files. Note that it will be NULL for the virtual * monitor interface (if that is requested.) + * @probe_req_reg: probe requests should be reported to mac80211 for this + * interface. * @drv_priv: data area for driver use, will always be aligned to * sizeof(void *). * @txq: the multicast data TX queue (if driver uses the TXQ abstraction) @@ -1382,6 +1385,8 @@ struct ieee80211_vif { struct dentry *debugfs_dir; #endif + unsigned int probe_req_reg; + /* must be last */ u8 drv_priv[0] __aligned(sizeof(void *)); }; @@ -2825,6 +2830,13 @@ enum ieee80211_reconfig_type { * See the section "Frame filtering" for more information. * This callback must be implemented and can sleep. * + * @config_iface_filter: Configure the interface's RX filter. + * This callback is optional and is used to configure which frames + * should be passed to mac80211. The filter_flags is the combination + * of FIF_* flags. The changed_flags is a bit mask that indicates + * which flags are changed. + * This callback can sleep. + * * @set_tim: Set TIM bit. mac80211 calls this function when a TIM bit * must be set or cleared for a given STA. Must be atomic. * @@ -3264,6 +3276,10 @@ struct ieee80211_ops { unsigned int changed_flags, unsigned int *total_flags, u64 multicast); + void (*config_iface_filter)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + unsigned int filter_flags, + unsigned int changed_flags); int (*set_tim)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, bool set); int (*set_key)(struct ieee80211_hw *hw, enum set_key_cmd cmd, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 1ca972e5418b..9eab783701aa 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -3516,18 +3516,32 @@ static void ieee80211_mgmt_frame_register(struct wiphy *wiphy, u16 frame_type, bool reg) { struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); switch (frame_type) { case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ: - if (reg) + if (reg) { local->probe_req_reg++; - else - local->probe_req_reg--; + sdata->vif.probe_req_reg++; + } else { + if (local->probe_req_reg) + local->probe_req_reg--; + + if (sdata->vif.probe_req_reg) + sdata->vif.probe_req_reg--; + } if (!local->open_count) break; - ieee80211_queue_work(&local->hw, &local->reconfig_filter); + if (sdata->vif.probe_req_reg == 1) + drv_config_iface_filter(local, sdata, FIF_PROBE_REQ, + FIF_PROBE_REQ); + else if (sdata->vif.probe_req_reg == 0) + drv_config_iface_filter(local, sdata, 0, + FIF_PROBE_REQ); + + ieee80211_configure_filter(local); break; default: break; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 02d91332d7dd..157b20baf752 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -260,6 +260,22 @@ static inline void drv_configure_filter(struct ieee80211_local *local, trace_drv_return_void(local); } +static inline void drv_config_iface_filter(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + unsigned int filter_flags, + unsigned int changed_flags) +{ + might_sleep(); + + trace_drv_config_iface_filter(local, sdata, filter_flags, + changed_flags); + if (local->ops->config_iface_filter) + local->ops->config_iface_filter(&local->hw, &sdata->vif, + filter_flags, + changed_flags); + trace_drv_return_void(local); +} + static inline int drv_set_tim(struct ieee80211_local *local, struct ieee80211_sta *sta, bool set) { diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 6f14591d8ca9..b5960b948f60 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -497,6 +497,36 @@ TRACE_EVENT(drv_configure_filter, ) ); +TRACE_EVENT(drv_config_iface_filter, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + unsigned int filter_flags, + unsigned int changed_flags), + + TP_ARGS(local, sdata, filter_flags, changed_flags), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + __field(unsigned int, filter_flags) + __field(unsigned int, changed_flags) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + __entry->filter_flags = filter_flags; + __entry->changed_flags = changed_flags; + ), + + TP_printk( + LOCAL_PR_FMT VIF_PR_FMT + " filter_flags: %#x changed_flags: %#x", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->filter_flags, + __entry->changed_flags + ) +); + TRACE_EVENT(drv_set_tim, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sta *sta, bool set), -- cgit v1.2.3 From e3abc8ff0fc18b3925fd5d5c5fbd1613856f4e7c Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 16 Aug 2015 11:13:22 +0300 Subject: mac80211: allow to transmit A-MSDU within A-MPDU Advertise the capability to send A-MSDU within A-MPDU in the AddBA request sent by mac80211. Let the driver know about the peer's capabilities. Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- drivers/net/wireless/ath/ath10k/mac.c | 2 +- drivers/net/wireless/ath/ath9k/htc_drv_main.c | 2 +- drivers/net/wireless/ath/ath9k/main.c | 2 +- drivers/net/wireless/ath/carl9170/main.c | 2 +- drivers/net/wireless/ath/wcn36xx/main.c | 2 +- drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c | 2 +- drivers/net/wireless/cw1200/sta.c | 2 +- drivers/net/wireless/cw1200/sta.h | 2 +- drivers/net/wireless/iwlegacy/4965-mac.c | 2 +- drivers/net/wireless/iwlegacy/4965.h | 2 +- drivers/net/wireless/iwlwifi/dvm/mac80211.c | 2 +- drivers/net/wireless/iwlwifi/mvm/mac80211.c | 2 +- drivers/net/wireless/mac80211_hwsim.c | 2 +- drivers/net/wireless/mediatek/mt7601u/main.c | 3 ++- drivers/net/wireless/mwl8k.c | 2 +- drivers/net/wireless/rsi/rsi_91x_mac80211.c | 4 +++- drivers/net/wireless/rt2x00/rt2800lib.c | 2 +- drivers/net/wireless/rt2x00/rt2800lib.h | 2 +- drivers/net/wireless/rtlwifi/core.c | 2 +- drivers/net/wireless/ti/wlcore/main.c | 2 +- include/linux/ieee80211.h | 1 + include/net/mac80211.h | 5 ++++- net/mac80211/agg-rx.c | 4 ++-- net/mac80211/agg-tx.c | 15 ++++++++++----- net/mac80211/driver-ops.h | 7 ++++--- net/mac80211/sta_info.h | 2 ++ net/mac80211/trace.h | 10 ++++++---- 27 files changed, 52 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 64674c955d44..b04e7694c105 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -6144,7 +6144,7 @@ static int ath10k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size) + u8 buf_size, bool amsdu) { struct ath10k *ar = hw->priv; struct ath10k_vif *arvif = ath10k_vif_to_arvif(vif); diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c index 172a9ff4aaab..a680a970b7f7 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c @@ -1659,7 +1659,7 @@ static int ath9k_htc_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, - u16 tid, u16 *ssn, u8 buf_size) + u16 tid, u16 *ssn, u8 buf_size, bool amsdu) { struct ath9k_htc_priv *priv = hw->priv; struct ath9k_htc_sta *ista; diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index c27143ba9ffb..323eb33c3c6e 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -1856,7 +1856,7 @@ static int ath9k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, - u16 tid, u16 *ssn, u8 buf_size) + u16 tid, u16 *ssn, u8 buf_size, bool amsdu) { struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c index 170c209f99b8..19d3d64416bf 100644 --- a/drivers/net/wireless/ath/carl9170/main.c +++ b/drivers/net/wireless/ath/carl9170/main.c @@ -1415,7 +1415,7 @@ static int carl9170_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, - u16 tid, u16 *ssn, u8 buf_size) + u16 tid, u16 *ssn, u8 buf_size, bool amsdu) { struct ar9170 *ar = hw->priv; struct carl9170_sta_info *sta_info = (void *) sta->drv_priv; diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c index 900e72a089d8..7c169abdbafe 100644 --- a/drivers/net/wireless/ath/wcn36xx/main.c +++ b/drivers/net/wireless/ath/wcn36xx/main.c @@ -859,7 +859,7 @@ static int wcn36xx_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size) + u8 buf_size, bool amsdu) { struct wcn36xx *wcn = hw->priv; struct wcn36xx_sta *sta_priv = NULL; diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c index d2c5747e3ac9..bec2dc1ca2e4 100644 --- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c +++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c @@ -820,7 +820,7 @@ brcms_ops_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size) + u8 buf_size, bool amsdu) { struct brcms_info *wl = hw->priv; struct scb *scb = &wl->wlc->pri_scb; diff --git a/drivers/net/wireless/cw1200/sta.c b/drivers/net/wireless/cw1200/sta.c index b86500b4418f..95a7fdb3cc1c 100644 --- a/drivers/net/wireless/cw1200/sta.c +++ b/drivers/net/wireless/cw1200/sta.c @@ -2137,7 +2137,7 @@ int cw1200_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size) + u8 buf_size, bool amsdu) { /* Aggregation is implemented fully in firmware, * including block ack negotiation. Do not allow diff --git a/drivers/net/wireless/cw1200/sta.h b/drivers/net/wireless/cw1200/sta.h index b7e386b7662b..bebb3379017f 100644 --- a/drivers/net/wireless/cw1200/sta.h +++ b/drivers/net/wireless/cw1200/sta.h @@ -111,7 +111,7 @@ int cw1200_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size); + u8 buf_size, bool amsdu); void cw1200_suspend_resume(struct cw1200_common *priv, struct wsm_suspend_resume *arg); diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c index 44fa422f255e..6656215a13a9 100644 --- a/drivers/net/wireless/iwlegacy/4965-mac.c +++ b/drivers/net/wireless/iwlegacy/4965-mac.c @@ -5984,7 +5984,7 @@ int il4965_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 * ssn, - u8 buf_size) + u8 buf_size, bool amsdu) { struct il_priv *il = hw->priv; int ret = -EINVAL; diff --git a/drivers/net/wireless/iwlegacy/4965.h b/drivers/net/wireless/iwlegacy/4965.h index 3a57f71b8ed5..8ab8706f9422 100644 --- a/drivers/net/wireless/iwlegacy/4965.h +++ b/drivers/net/wireless/iwlegacy/4965.h @@ -184,7 +184,7 @@ void il4965_mac_update_tkip_key(struct ieee80211_hw *hw, int il4965_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 * ssn, - u8 buf_size); + u8 buf_size, bool amsdu); int il4965_mac_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void diff --git a/drivers/net/wireless/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/iwlwifi/dvm/mac80211.c index 453f7c315ab5..b3ad34e8bf5a 100644 --- a/drivers/net/wireless/iwlwifi/dvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/dvm/mac80211.c @@ -731,7 +731,7 @@ static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size) + u8 buf_size, bool amsdu) { struct iwl_priv *priv = IWL_MAC80211_GET_DVM(hw); int ret = -EINVAL; diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c index aa8c2b7f23c7..f70452c41d63 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c @@ -820,7 +820,7 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, - u16 *ssn, u8 buf_size) + u16 *ssn, u8 buf_size, bool amsdu) { struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); int ret; diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 520bef80747f..2af2f3d0cc31 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1819,7 +1819,7 @@ static int mac80211_hwsim_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size) + u8 buf_size, bool amsdu) { switch (action) { case IEEE80211_AMPDU_TX_START: diff --git a/drivers/net/wireless/mediatek/mt7601u/main.c b/drivers/net/wireless/mediatek/mt7601u/main.c index 169384b48b27..f715eee39851 100644 --- a/drivers/net/wireless/mediatek/mt7601u/main.c +++ b/drivers/net/wireless/mediatek/mt7601u/main.c @@ -335,7 +335,8 @@ static int mt7601u_set_rts_threshold(struct ieee80211_hw *hw, u32 value) static int mt76_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, u8 buf_size) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, u8 buf_size, + bool amsdu) { struct mt7601u_dev *dev = hw->priv; struct mt76_sta *msta = (struct mt76_sta *) sta->drv_priv; diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c index 9420fc61c2e6..30e3aaae32e2 100644 --- a/drivers/net/wireless/mwl8k.c +++ b/drivers/net/wireless/mwl8k.c @@ -5423,7 +5423,7 @@ static int mwl8k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size) + u8 buf_size, bool amsdu) { int i, rc = 0; diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index 7e804324bfa7..b5bcc933a2a6 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -664,6 +664,7 @@ static int rsi_mac80211_set_key(struct ieee80211_hw *hw, * @tid: Traffic identifier. * @ssn: Pointer to ssn value. * @buf_size: Buffer size (for kernel version > 2.6.38). + * @amsdu: is AMSDU in AMPDU allowed * * Return: status: 0 on success, negative error code on failure. */ @@ -673,7 +674,8 @@ static int rsi_mac80211_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_sta *sta, unsigned short tid, unsigned short *ssn, - unsigned char buf_size) + unsigned char buf_size, + bool amsdu) { int status = -EOPNOTSUPP; struct rsi_hw *adapter = hw->priv; diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c index 9524564f873b..9733b31a780d 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/rt2x00/rt2800lib.c @@ -7937,7 +7937,7 @@ EXPORT_SYMBOL_GPL(rt2800_get_tsf); int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size) + u8 buf_size, bool amsdu) { struct rt2x00_sta *sta_priv = (struct rt2x00_sta *)sta->drv_priv; int ret = 0; diff --git a/drivers/net/wireless/rt2x00/rt2800lib.h b/drivers/net/wireless/rt2x00/rt2800lib.h index 1609b8a7f7eb..440790b92b19 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.h +++ b/drivers/net/wireless/rt2x00/rt2800lib.h @@ -220,7 +220,7 @@ u64 rt2800_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size); + u8 buf_size, bool amsdu); int rt2800_get_survey(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void rt2800_disable_wpdma(struct rt2x00_dev *rt2x00dev); diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c index 585d0883c7e5..c925a4dff599 100644 --- a/drivers/net/wireless/rtlwifi/core.c +++ b/drivers/net/wireless/rtlwifi/core.c @@ -1373,7 +1373,7 @@ static int rtl_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size) + u8 buf_size, bool amsdu) { struct rtl_priv *rtlpriv = rtl_priv(hw); diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index e819369d8f8f..ec7f6af3fab2 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -5263,7 +5263,7 @@ static int wl1271_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size) + u8 buf_size, bool amsdu) { struct wl1271 *wl = hw->priv; struct wl12xx_vif *wlvif = wl12xx_vif_to_data(vif); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index cfa906f28b7a..19eb9ecd6cf3 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1379,6 +1379,7 @@ struct ieee80211_ht_operation { /* block-ack parameters */ +#define IEEE80211_ADDBA_PARAM_AMSDU_MASK 0x0001 #define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002 #define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C #define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0 diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 167864503138..f28cbc0988eb 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3026,6 +3026,9 @@ enum ieee80211_reconfig_type { * buffer size of 8. Correct ways to retransmit #1 would be: * - TX: 1 or 18 or 81 * Even "189" would be wrong since 1 could be lost again. + * The @amsdu parameter is valid when the action is set to + * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's ability + * to receive A-MSDU within A-MPDU. * * Returns a negative error code on failure. * The callback can sleep. @@ -3363,7 +3366,7 @@ struct ieee80211_ops { struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size); + u8 buf_size, bool amsdu); int (*get_survey)(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 5c564a68fb50..6ebe8611eca5 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -79,7 +79,7 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, (int)reason); if (drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_STOP, - &sta->sta, tid, NULL, 0)) + &sta->sta, tid, NULL, 0, false)) sdata_info(sta->sdata, "HW problem - can not stop rx aggregation for %pM tid %d\n", sta->sta.addr, tid); @@ -321,7 +321,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, __skb_queue_head_init(&tid_agg_rx->reorder_buf[i]); ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_START, - &sta->sta, tid, &start_seq_num, 0); + &sta->sta, tid, &start_seq_num, 0, false); ht_dbg(sta->sdata, "Rx A-MPDU request on %pM tid %d result %d\n", sta->sta.addr, tid, ret); if (ret) { diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index c8ba2e77737c..a758eb84e8f0 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -97,7 +97,8 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata, mgmt->u.action.u.addba_req.action_code = WLAN_ACTION_ADDBA_REQ; mgmt->u.action.u.addba_req.dialog_token = dialog_token; - capab = (u16)(1 << 1); /* bit 1 aggregation policy */ + capab = (u16)(1 << 0); /* bit 0 A-MSDU support */ + capab |= (u16)(1 << 1); /* bit 1 aggregation policy */ capab |= (u16)(tid << 2); /* bit 5:2 TID number */ capab |= (u16)(agg_size << 6); /* bit 15:6 max size of aggergation */ @@ -331,7 +332,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, return -EALREADY; ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_TX_STOP_FLUSH_CONT, - &sta->sta, tid, NULL, 0); + &sta->sta, tid, NULL, 0, false); WARN_ON_ONCE(ret); return 0; } @@ -381,7 +382,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, tid_tx->tx_stop = reason == AGG_STOP_LOCAL_REQUEST; ret = drv_ampdu_action(local, sta->sdata, action, - &sta->sta, tid, NULL, 0); + &sta->sta, tid, NULL, 0, false); /* HW shall not deny going back to legacy */ if (WARN_ON(ret)) { @@ -469,7 +470,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) start_seq_num = sta->tid_seq[tid] >> 4; ret = drv_ampdu_action(local, sdata, IEEE80211_AMPDU_TX_START, - &sta->sta, tid, &start_seq_num, 0); + &sta->sta, tid, &start_seq_num, 0, false); if (ret) { ht_dbg(sdata, "BA request denied - HW unavailable for %pM tid %d\n", @@ -693,7 +694,8 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local, drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_TX_OPERATIONAL, - &sta->sta, tid, NULL, tid_tx->buf_size); + &sta->sta, tid, NULL, tid_tx->buf_size, + tid_tx->amsdu); /* * synchronize with TX path, while splicing the TX path @@ -918,8 +920,10 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, struct tid_ampdu_tx *tid_tx; u16 capab, tid; u8 buf_size; + bool amsdu; capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab); + amsdu = capab & IEEE80211_ADDBA_PARAM_AMSDU_MASK; tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2; buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6; @@ -968,6 +972,7 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, } tid_tx->buf_size = buf_size; + tid_tx->amsdu = amsdu; if (test_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state)) ieee80211_agg_tx_operational(local, sta, tid); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 157b20baf752..31482e2cd25f 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -734,7 +734,7 @@ static inline int drv_ampdu_action(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, - u16 *ssn, u8 buf_size) + u16 *ssn, u8 buf_size, bool amsdu) { int ret = -EOPNOTSUPP; @@ -744,11 +744,12 @@ static inline int drv_ampdu_action(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return -EIO; - trace_drv_ampdu_action(local, sdata, action, sta, tid, ssn, buf_size); + trace_drv_ampdu_action(local, sdata, action, sta, tid, + ssn, buf_size, amsdu); if (local->ops->ampdu_action) ret = local->ops->ampdu_action(&local->hw, &sdata->vif, action, - sta, tid, ssn, buf_size); + sta, tid, ssn, buf_size, amsdu); trace_drv_return_int(local, ret); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index b087c71ff7fe..d5ded8749ac4 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -133,6 +133,7 @@ enum ieee80211_agg_stop_reason { * @buf_size: reorder buffer size at receiver * @failed_bar_ssn: ssn of the last failed BAR tx attempt * @bar_pending: BAR needs to be re-sent + * @amsdu: support A-MSDU withing A-MDPU * * This structure's lifetime is managed by RCU, assignments to * the array holding it must hold the aggregation mutex. @@ -158,6 +159,7 @@ struct tid_ampdu_tx { u16 failed_bar_ssn; bool bar_pending; + bool amsdu; }; /** diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index b5960b948f60..314e3bd7fbdb 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -974,9 +974,9 @@ TRACE_EVENT(drv_ampdu_action, struct ieee80211_sub_if_data *sdata, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, - u16 *ssn, u8 buf_size), + u16 *ssn, u8 buf_size, bool amsdu), - TP_ARGS(local, sdata, action, sta, tid, ssn, buf_size), + TP_ARGS(local, sdata, action, sta, tid, ssn, buf_size, amsdu), TP_STRUCT__entry( LOCAL_ENTRY @@ -985,6 +985,7 @@ TRACE_EVENT(drv_ampdu_action, __field(u16, tid) __field(u16, ssn) __field(u8, buf_size) + __field(bool, amsdu) VIF_ENTRY ), @@ -996,12 +997,13 @@ TRACE_EVENT(drv_ampdu_action, __entry->tid = tid; __entry->ssn = ssn ? *ssn : 0; __entry->buf_size = buf_size; + __entry->amsdu = amsdu; ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d buf:%d", + LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d buf:%d amsdu:%d", LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->action, - __entry->tid, __entry->buf_size + __entry->tid, __entry->buf_size, __entry->amsdu ) ); -- cgit v1.2.3 From 99e7ca44bb910f0cbfda5d9008e8517df0ebc939 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sat, 15 Aug 2015 22:39:51 +0300 Subject: mac80211: allow the driver to advertise A-MSDU within A-MPDU Rx support Drivers may be interested in receiving A-MSDU within A-MDPU. Not all the devices may be able to do so, make it configurable. Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++++ net/mac80211/agg-rx.c | 4 +++- net/mac80211/debugfs.c | 1 + 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f28cbc0988eb..d62d6f41548b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1897,6 +1897,9 @@ struct ieee80211_txq { * @IEEE80211_HW_TDLS_WIDER_BW: The device/driver supports wider bandwidth * than then BSS bandwidth for a TDLS link on the base channel. * + * @IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU: The driver supports receiving A-MSDUs + * within A-MPDU. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -1930,6 +1933,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_CLONED_SKBS, IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS, IEEE80211_HW_TDLS_WIDER_BW, + IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 6ebe8611eca5..10ad4ac1fa0b 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -189,6 +189,7 @@ static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *d struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; + bool amsdu = ieee80211_hw_check(&local->hw, SUPPORTS_AMSDU_IN_AMPDU); u16 capab; skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom); @@ -217,7 +218,8 @@ static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *d mgmt->u.action.u.addba_resp.action_code = WLAN_ACTION_ADDBA_RESP; mgmt->u.action.u.addba_resp.dialog_token = dialog_token; - capab = (u16)(policy << 1); /* bit 1 aggregation policy */ + capab = (u16)(amsdu << 0); /* bit 0 A-MSDU support */ + capab |= (u16)(policy << 1); /* bit 1 aggregation policy */ capab |= (u16)(tid << 2); /* bit 5:2 TID number */ capab |= (u16)(buf_size << 6); /* bit 15:6 max size of aggregation */ diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index ced6bf3be8d6..41726fd4bb78 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -123,6 +123,7 @@ static const char *hw_flag_names[NUM_IEEE80211_HW_FLAGS + 1] = { FLAG(SUPPORTS_CLONED_SKBS), FLAG(SINGLE_SCAN_ON_ALL_BANDS), FLAG(TDLS_WIDER_BW), + FLAG(SUPPORTS_AMSDU_IN_AMPDU), /* keep last for the build bug below */ (void *)0x1 -- cgit v1.2.3 From 0edd5faeb07bfd3ec5402f9467e4c169dcd131e8 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 28 Aug 2015 14:31:48 +0200 Subject: wireless: mark element IDs 8 and 9 reserved These were never used in the tree, and are marked as reserved in the IEEE 802.11 documentation (ANA). Signed-off-by: Johannes Berg --- drivers/net/wireless/ipw2x00/libipw_rx.c | 2 -- include/linux/ieee80211.h | 3 +-- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/ipw2x00/libipw_rx.c b/drivers/net/wireless/ipw2x00/libipw_rx.c index a6877dd6ba73..cef7f7d79cd9 100644 --- a/drivers/net/wireless/ipw2x00/libipw_rx.c +++ b/drivers/net/wireless/ipw2x00/libipw_rx.c @@ -1091,8 +1091,6 @@ static const char *get_info_element_string(u16 id) MFIE_STRING(TIM); MFIE_STRING(IBSS_PARAMS); MFIE_STRING(COUNTRY); - MFIE_STRING(HP_PARAMS); - MFIE_STRING(HP_TABLE); MFIE_STRING(REQUEST); MFIE_STRING(CHALLENGE); MFIE_STRING(PWR_CONSTRAINT); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 19eb9ecd6cf3..f79a02a69d26 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1746,8 +1746,7 @@ enum ieee80211_eid { WLAN_EID_TIM = 5, WLAN_EID_IBSS_PARAMS = 6, WLAN_EID_COUNTRY = 7, - WLAN_EID_HP_PARAMS = 8, - WLAN_EID_HP_TABLE = 9, + /* 8, 9 reserved */ WLAN_EID_REQUEST = 10, WLAN_EID_QBSS_LOAD = 11, WLAN_EID_EDCA_PARAM_SET = 12, -- cgit v1.2.3 From 5359d112dcb081fd7a5f2de287fa995f6ba0800c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 14 Sep 2015 13:56:17 +0200 Subject: Revert "mac80211: add pointer for driver use to key" This reverts commit f9a060f4b2003eb7350762e60dfc576447e44bad. No driver has turned up needing this functionality, and I've just implemented the functionality I wanted this for in a different way. Thus, remove it again, until somebody shows up with a need for having it. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d62d6f41548b..3424ac6efb2a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1497,10 +1497,8 @@ enum ieee80211_key_flags { * - Temporal Authenticator Rx MIC Key (64 bits) * @icv_len: The ICV length for this key type * @iv_len: The IV length for this key type - * @drv_priv: pointer for driver use */ struct ieee80211_key_conf { - void *drv_priv; atomic64_t tx_pn; u32 cipher; u8 icv_len; -- cgit v1.2.3 From ac5be6b47e8bd25b62bed2c82cda7398999f59e9 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Tue, 22 Sep 2015 14:58:49 -0700 Subject: userfaultfd: revert "userfaultfd: waitqueue: add nr wake parameter to __wake_up_locked_key" This reverts commit 51360155eccb907ff8635bd10fc7de876408c2e0 and adapts fs/userfaultfd.c to use the old version of that function. It didn't look robust to call __wake_up_common with "nr == 1" when we absolutely require wakeall semantics, but we've full control of what we insert in the two waitqueue heads of the blocked userfaults. No exclusive waitqueue risks to be inserted into those two waitqueue heads so we can as well stick to "nr == 1" of the old code and we can rely purely on the fact no waitqueue inserted in one of the two waitqueue heads we must enforce as wakeall, has wait->flags WQ_FLAG_EXCLUSIVE set. Signed-off-by: Andrea Arcangeli Cc: Dr. David Alan Gilbert Cc: Michael Ellerman Cc: Shuah Khan Cc: Thierry Reding Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/userfaultfd.c | 8 ++++---- include/linux/wait.h | 5 ++--- kernel/sched/wait.c | 7 +++---- net/sunrpc/sched.c | 2 +- 4 files changed, 10 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index f9aeb40a7197..50311703135b 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -467,8 +467,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * the fault_*wqh. */ spin_lock(&ctx->fault_pending_wqh.lock); - __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0, &range); - __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, &range); + __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range); + __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, &range); spin_unlock(&ctx->fault_pending_wqh.lock); wake_up_poll(&ctx->fd_wqh, POLLHUP); @@ -650,10 +650,10 @@ static void __wake_userfault(struct userfaultfd_ctx *ctx, spin_lock(&ctx->fault_pending_wqh.lock); /* wake all in the range and autoremove */ if (waitqueue_active(&ctx->fault_pending_wqh)) - __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0, + __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, range); if (waitqueue_active(&ctx->fault_wqh)) - __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, range); + __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, range); spin_unlock(&ctx->fault_pending_wqh.lock); } diff --git a/include/linux/wait.h b/include/linux/wait.h index d3d077228d4c..1e1bf9f963a9 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -147,8 +147,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) typedef int wait_bit_action_f(struct wait_bit_key *); void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr, - void *key); +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); @@ -180,7 +179,7 @@ wait_queue_head_t *bit_waitqueue(void *, int); #define wake_up_poll(x, m) \ __wake_up(x, TASK_NORMAL, 1, (void *) (m)) #define wake_up_locked_poll(x, m) \ - __wake_up_locked_key((x), TASK_NORMAL, 1, (void *) (m)) + __wake_up_locked_key((x), TASK_NORMAL, (void *) (m)) #define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m)) #define wake_up_interruptible_sync_poll(x, m) \ diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 272d9322bc5d..052e02672d12 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -106,10 +106,9 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr) } EXPORT_SYMBOL_GPL(__wake_up_locked); -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr, - void *key) +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) { - __wake_up_common(q, mode, nr, 0, key); + __wake_up_common(q, mode, 1, 0, key); } EXPORT_SYMBOL_GPL(__wake_up_locked_key); @@ -284,7 +283,7 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, if (!list_empty(&wait->task_list)) list_del_init(&wait->task_list); else if (waitqueue_active(q)) - __wake_up_locked_key(q, mode, 1, key); + __wake_up_locked_key(q, mode, key); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL(abort_exclusive_wait); diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index b140c092d226..337ca851a350 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -297,7 +297,7 @@ static int rpc_complete_task(struct rpc_task *task) clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate); ret = atomic_dec_and_test(&task->tk_count); if (waitqueue_active(wq)) - __wake_up_locked_key(wq, TASK_NORMAL, 1, &k); + __wake_up_locked_key(wq, TASK_NORMAL, &k); spin_unlock_irqrestore(&wq->lock, flags); return ret; } -- cgit v1.2.3 From 09f7298100ea9767324298ab0c7979f6d7463183 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Tue, 22 Sep 2015 14:59:09 -0700 Subject: userfaultfd: register uapi generic syscall (aarch64) Add the userfaultfd syscalls to uapi asm-generic, it was tested with postcopy live migration on aarch64 with both 4k and 64k pagesize kernels. Signed-off-by: Dr. David Alan Gilbert Signed-off-by: Andrea Arcangeli Cc: Michael Ellerman Cc: Shuah Khan Cc: Thierry Reding Cc: Mathieu Desnoyers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/asm-generic/unistd.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 8da542a2874d..ee124009e12a 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -709,17 +709,19 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create) __SYSCALL(__NR_bpf, sys_bpf) #define __NR_execveat 281 __SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat) -#define __NR_membarrier 282 +#define __NR_userfaultfd 282 +__SYSCALL(__NR_userfaultfd, sys_userfaultfd) +#define __NR_membarrier 283 __SYSCALL(__NR_membarrier, sys_membarrier) #undef __NR_syscalls -#define __NR_syscalls 283 +#define __NR_syscalls 284 /* * All syscalls below here should go away really, * these are provided for both review and as a porting * help for the C library version. -* + * * Last chance: are any of these important enough to * enable by default? */ -- cgit v1.2.3 From 37587fadff8ce8f40a6952f0383c571a89b29d1d Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 30 Jul 2015 13:22:43 -0700 Subject: arcnet: fix indentation of if_arcnet.h Standardized spacing is easier to read. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/uapi/linux/if_arcnet.h | 55 ++++++++++++++++++++---------------------- 1 file changed, 26 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h index 46e34bd0e783..cfb642f8e7bd 100644 --- a/include/uapi/linux/if_arcnet.h +++ b/include/uapi/linux/if_arcnet.h @@ -19,7 +19,6 @@ #include #include - /* * These are the defined ARCnet Protocol ID's. */ @@ -57,42 +56,40 @@ * The RFC1201-specific components of an arcnet packet header. */ struct arc_rfc1201 { - __u8 proto; /* protocol ID field - varies */ - __u8 split_flag; /* for use with split packets */ - __be16 sequence; /* sequence number */ - __u8 payload[0]; /* space remaining in packet (504 bytes)*/ + __u8 proto; /* protocol ID field - varies */ + __u8 split_flag; /* for use with split packets */ + __be16 sequence; /* sequence number */ + __u8 payload[0]; /* space remaining in packet (504 bytes)*/ }; #define RFC1201_HDR_SIZE 4 - /* * The RFC1051-specific components. */ struct arc_rfc1051 { - __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ - __u8 payload[0]; /* 507 bytes */ + __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ + __u8 payload[0]; /* 507 bytes */ }; #define RFC1051_HDR_SIZE 1 - /* * The ethernet-encap-specific components. We have a real ethernet header * and some data. */ struct arc_eth_encap { - __u8 proto; /* Always ARC_P_ETHER */ - struct ethhdr eth; /* standard ethernet header (yuck!) */ - __u8 payload[0]; /* 493 bytes */ + __u8 proto; /* Always ARC_P_ETHER */ + struct ethhdr eth; /* standard ethernet header (yuck!) */ + __u8 payload[0]; /* 493 bytes */ }; #define ETH_ENCAP_HDR_SIZE 14 - struct arc_cap { __u8 proto; - __u8 cookie[sizeof(int)]; /* Actually NOT sent over the network */ + __u8 cookie[sizeof(int)]; + /* Actually NOT sent over the network */ union { __u8 ack; - __u8 raw[0]; /* 507 bytes */ + __u8 raw[0]; /* 507 bytes */ } mes; }; @@ -105,9 +102,9 @@ struct arc_cap { * driver. */ struct arc_hardware { - __u8 source, /* source ARCnet - filled in automagically */ - dest, /* destination ARCnet - 0 for broadcast */ - offset[2]; /* offset bytes (some weird semantics) */ + __u8 source; /* source ARCnet - filled in automagically */ + __u8 dest; /* destination ARCnet - 0 for broadcast */ + __u8 offset[2]; /* offset bytes (some weird semantics) */ }; #define ARC_HDR_SIZE 4 @@ -116,17 +113,17 @@ struct arc_hardware { * when you do a raw packet capture). */ struct archdr { - /* hardware requirements */ - struct arc_hardware hard; - - /* arcnet encapsulation-specific bits */ - union { - struct arc_rfc1201 rfc1201; - struct arc_rfc1051 rfc1051; - struct arc_eth_encap eth_encap; - struct arc_cap cap; - __u8 raw[0]; /* 508 bytes */ - } soft; + /* hardware requirements */ + struct arc_hardware hard; + + /* arcnet encapsulation-specific bits */ + union { + struct arc_rfc1201 rfc1201; + struct arc_rfc1051 rfc1051; + struct arc_eth_encap eth_encap; + struct arc_cap cap; + __u8 raw[0]; /* 508 bytes */ + } soft; }; #endif /* _LINUX_IF_ARCNET_H */ -- cgit v1.2.3 From cb334648a10c7fa6f0f163c22602f4dc1c6d56b4 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:05:47 -0700 Subject: arcnet: Use normal kernel spacing style Standardized spacing is easier to read. git diff -w shows no differences. objdiff shows no differences. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- drivers/net/arcnet/arc-rawmode.c | 10 +- drivers/net/arcnet/arc-rimi.c | 30 ++-- drivers/net/arcnet/arcnet.c | 170 ++++++++++----------- drivers/net/arcnet/capmode.c | 36 ++--- drivers/net/arcnet/com20020-isa.c | 2 +- drivers/net/arcnet/com20020-pci.c | 2 +- drivers/net/arcnet/com20020.c | 38 ++--- drivers/net/arcnet/com20020_cs.c | 306 +++++++++++++++++++------------------- drivers/net/arcnet/com90io.c | 24 +-- drivers/net/arcnet/com90xx.c | 32 ++-- drivers/net/arcnet/rfc1051.c | 12 +- drivers/net/arcnet/rfc1201.c | 36 ++--- include/linux/arcdevice.h | 90 +++++------ 13 files changed, 394 insertions(+), 394 deletions(-) (limited to 'include') diff --git a/drivers/net/arcnet/arc-rawmode.c b/drivers/net/arcnet/arc-rawmode.c index 705e6ce2eb90..49f5819a0367 100644 --- a/drivers/net/arcnet/arc-rawmode.c +++ b/drivers/net/arcnet/arc-rawmode.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - "raw mode" packet encapsulation (no soft headers) - * + * * Written 1994-1999 by Avery Pennarun. * Derived from skeleton.c by Donald Becker. * @@ -109,7 +109,7 @@ static void rx(struct net_device *dev, int bufnum, skb_put(skb, length + ARC_HDR_SIZE); skb->dev = dev; - pkt = (struct archdr *) skb->data; + pkt = (struct archdr *)skb->data; skb_reset_mac_header(skb); skb_pull(skb, ARC_HDR_SIZE); @@ -136,7 +136,7 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, uint8_t daddr) { int hdr_size = ARC_HDR_SIZE; - struct archdr *pkt = (struct archdr *) skb_push(skb, hdr_size); + struct archdr *pkt = (struct archdr *)skb_push(skb, hdr_size); /* * Set the source hardware address. @@ -150,7 +150,7 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, /* see linux/net/ethernet/eth.c to see where I got the following */ if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) { - /* + /* * FIXME: fill in the last byte of the dest ipaddr here to better * comply with RFC1051 in "noarp" mode. */ @@ -192,7 +192,7 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, hard->offset[0] = ofs = 256 - length; BUGMSG(D_DURING, "prepare_tx: length=%d ofs=%d\n", - length,ofs); + length, ofs); lp->hw.copy_to_card(dev, bufnum, 0, hard, ARC_HDR_SIZE); lp->hw.copy_to_card(dev, bufnum, ofs, &pkt->soft, length); diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index b8b4c7ba884f..4644d46b6a5f 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - "RIM I" (entirely mem-mapped) cards - * + * * Written 1994-1999 by Avery Pennarun. * Written 1999-2000 by Martin Mares . * Derived from skeleton.c by Donald Becker. @@ -56,27 +56,27 @@ static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, int offse /* Handy defines for ARCnet specific stuff */ /* Amount of I/O memory used by the card */ -#define BUFFER_SIZE (512) -#define MIRROR_SIZE (BUFFER_SIZE*4) +#define BUFFER_SIZE (512) +#define MIRROR_SIZE (BUFFER_SIZE * 4) /* COM 9026 controller chip --> ARCnet register addresses */ -#define _INTMASK (ioaddr+0) /* writable */ -#define _STATUS (ioaddr+0) /* readable */ -#define _COMMAND (ioaddr+1) /* writable, returns random vals on read (?) */ -#define _RESET (ioaddr+8) /* software reset (on read) */ -#define _MEMDATA (ioaddr+12) /* Data port for IO-mapped memory */ -#define _ADDR_HI (ioaddr+15) /* Control registers for said */ -#define _ADDR_LO (ioaddr+14) -#define _CONFIG (ioaddr+2) /* Configuration register */ +#define _INTMASK (ioaddr + 0) /* writable */ +#define _STATUS (ioaddr + 0) /* readable */ +#define _COMMAND (ioaddr + 1) /* writable, returns random vals on read (?) */ +#define _RESET (ioaddr + 8) /* software reset (on read) */ +#define _MEMDATA (ioaddr + 12) /* Data port for IO-mapped memory */ +#define _ADDR_HI (ioaddr + 15) /* Control registers for said */ +#define _ADDR_LO (ioaddr + 14) +#define _CONFIG (ioaddr + 2) /* Configuration register */ #undef ASTATUS #undef ACOMMAND #undef AINTMASK #define ASTATUS() readb(_STATUS) -#define ACOMMAND(cmd) writeb((cmd),_COMMAND) -#define AINTMASK(msk) writeb((msk),_INTMASK) -#define SETCONF() writeb(lp->config,_CONFIG) +#define ACOMMAND(cmd) writeb((cmd), _COMMAND) +#define AINTMASK(msk) writeb((msk), _INTMASK) +#define SETCONF() writeb(lp->config, _CONFIG) /* @@ -90,7 +90,7 @@ static int __init arcrimi_probe(struct net_device *dev) BUGLVL(D_NORMAL) printk("E-mail me if you actually test the RIM I driver, please!\n"); BUGLVL(D_NORMAL) printk("Given: node %02Xh, shmem %lXh, irq %d\n", - dev->dev_addr[0], dev->mem_start, dev->irq); + dev->dev_addr[0], dev->mem_start, dev->irq); if (dev->mem_start <= 0 || dev->irq <= 0) { BUGLVL(D_NORMAL) printk("No autoprobe for RIM I; you " diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index 10f71c732b59..2a594d1c4b55 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - device-independent routines - * + * * Written 1997 by David Woodhouse. * Written 1994-1999 by Avery Pennarun. * Written 1999-2000 by Martin Mares . @@ -20,12 +20,12 @@ * modified by SRC, incorporated herein by reference. * * ********************** - * + * * The change log is now in a file called ChangeLog in this directory. * * Sources: * - Crynwr arcnet.com/arcether.com packet drivers. - * - arcnet.c v0.00 dated 1/1/94 and apparently by + * - arcnet.c v0.00 dated 1/1/94 and apparently by * Donald Becker - it didn't work :) * - skeleton.c v0.05 dated 11/16/93 by Donald Becker * (from Linux Kernel 1.1.45) @@ -69,8 +69,8 @@ static void arcnet_rx(struct net_device *dev, int bufnum); * arc_proto_default instead. It also must not be NULL; if you would like * to set it to NULL, set it to &arc_proto_null instead. */ - struct ArcProto *arc_proto_map[256], *arc_proto_default, - *arc_bcast_proto, *arc_raw_proto; +struct ArcProto *arc_proto_map[256], *arc_proto_default, + *arc_bcast_proto, *arc_raw_proto; static struct ArcProto arc_proto_null = { @@ -136,8 +136,8 @@ static int __init arcnet_init(void) BUGLVL(D_DURING) printk("arcnet: struct sizes: %Zd %Zd %Zd %Zd %Zd\n", - sizeof(struct arc_hardware), sizeof(struct arc_rfc1201), - sizeof(struct arc_rfc1051), sizeof(struct arc_eth_encap), + sizeof(struct arc_hardware), sizeof(struct arc_rfc1201), + sizeof(struct arc_rfc1051), sizeof(struct arc_eth_encap), sizeof(struct archdr)); return 0; @@ -184,11 +184,11 @@ static void arcnet_dump_packet(struct net_device *dev, int bufnum, /* hw.copy_from_card expects IRQ context so take the IRQ lock to keep it single threaded */ - if(take_arcnet_lock) + if (take_arcnet_lock) spin_lock_irqsave(&lp->lock, flags); lp->hw.copy_from_card(dev, bufnum, 0, buf, 512); - if(take_arcnet_lock) + if (take_arcnet_lock) spin_unlock_irqrestore(&lp->lock, flags); /* if the offset[0] byte is nonzero, this is a 256-byte packet */ @@ -202,7 +202,7 @@ static void arcnet_dump_packet(struct net_device *dev, int bufnum, #else -#define arcnet_dump_packet(dev, bufnum, desc,take_arcnet_lock) do { } while (0) +#define arcnet_dump_packet(dev, bufnum, desc, take_arcnet_lock) do { } while (0) #endif @@ -233,7 +233,7 @@ void arcnet_unregister_proto(struct ArcProto *proto) /* * Add a buffer to the queue. Only the interrupt handler is allowed to do * this, unless interrupts are disabled. - * + * * Note: we don't check for a full queue, since there aren't enough buffers * to more than fill it. */ @@ -248,7 +248,7 @@ static void release_arcbuf(struct net_device *dev, int bufnum) BUGLVL(D_DURING) { BUGMSG(D_DURING, "release_arcbuf: freed #%d; buffer queue is now: ", bufnum); - for (i = lp->next_buf; i != lp->first_free_buf; i = (i+1) % 5) + for (i = lp->next_buf; i != lp->first_free_buf; i = (i + 1) % 5) BUGMSG2(D_DURING, "#%d ", lp->buf_queue[i]); BUGMSG2(D_DURING, "\n"); } @@ -284,7 +284,7 @@ static int get_arcbuf(struct net_device *dev) BUGLVL(D_DURING) { BUGMSG(D_DURING, "get_arcbuf: got #%d; buffer queue is now: ", buf); - for (i = lp->next_buf; i != lp->first_free_buf; i = (i+1) % 5) + for (i = lp->next_buf; i != lp->first_free_buf; i = (i + 1) % 5) BUGMSG2(D_DURING, "#%d ", lp->buf_queue[i]); BUGMSG2(D_DURING, "\n"); } @@ -346,7 +346,7 @@ struct net_device *alloc_arcdev(const char *name) dev = alloc_netdev(sizeof(struct arcnet_local), name && *name ? name : "arc%d", NET_NAME_UNKNOWN, arcdev_setup); - if(dev) { + if (dev) { struct arcnet_local *lp = netdev_priv(dev); spin_lock_init(&lp->lock); } @@ -367,7 +367,7 @@ int arcnet_open(struct net_device *dev) struct arcnet_local *lp = netdev_priv(dev); int count, newmtu, error; - BUGMSG(D_INIT,"opened."); + BUGMSG(D_INIT, "opened."); if (!try_module_get(lp->hw.owner)) return -ENODEV; @@ -431,24 +431,24 @@ int arcnet_open(struct net_device *dev) BUGMSG(D_NORMAL, "WARNING! Station address FF may confuse " "DOS networking programs!\n"); - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); if (ASTATUS() & RESETflag) { - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); ACOMMAND(CFLAGScmd | RESETclear); } - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); /* make sure we're ready to receive IRQ's. */ AINTMASK(0); udelay(1); /* give it time to set the mask before * we reset it again. (may not even be * necessary) */ - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); lp->intmask = NORXflag | RECONflag; AINTMASK(lp->intmask); - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); netif_start_queue(dev); @@ -489,29 +489,29 @@ static int arcnet_header(struct sk_buff *skb, struct net_device *dev, struct ArcProto *proto; BUGMSG(D_DURING, - "create header from %d to %d; protocol %d (%Xh); size %u.\n", - saddr ? *(uint8_t *) saddr : -1, - daddr ? *(uint8_t *) daddr : -1, + "create header from %d to %d; protocol %d (%Xh); size %u.\n", + saddr ? *(uint8_t *)saddr : -1, + daddr ? *(uint8_t *)daddr : -1, type, type, len); - if (skb->len!=0 && len != skb->len) + if (skb->len != 0 && len != skb->len) BUGMSG(D_NORMAL, "arcnet_header: Yikes! skb->len(%d) != len(%d)!\n", skb->len, len); - /* Type is host order - ? */ - if(type == ETH_P_ARCNET) { - proto = arc_raw_proto; - BUGMSG(D_DEBUG, "arc_raw_proto used. proto='%c'\n",proto->suffix); - _daddr = daddr ? *(uint8_t *) daddr : 0; - } + /* Type is host order - ? */ + if (type == ETH_P_ARCNET) { + proto = arc_raw_proto; + BUGMSG(D_DEBUG, "arc_raw_proto used. proto='%c'\n", proto->suffix); + _daddr = daddr ? *(uint8_t *)daddr : 0; + } else if (!daddr) { /* * if the dest addr isn't provided, we can't choose an encapsulation! * Store the packet type (eg. ETH_P_IP) for now, and we'll push on a * real header when we do rebuild_header. */ - *(uint16_t *) skb_push(skb, 2) = type; + *(uint16_t *)skb_push(skb, 2) = type; /* * XXX: Why not use skb->mac_len? */ @@ -522,7 +522,7 @@ static int arcnet_header(struct sk_buff *skb, struct net_device *dev, } else { /* otherwise, we can just add the header as usual. */ - _daddr = *(uint8_t *) daddr; + _daddr = *(uint8_t *)daddr; proto_num = lp->default_proto[_daddr]; proto = arc_proto_map[proto_num]; BUGMSG(D_DURING, "building header for %02Xh using protocol '%c'\n", @@ -538,7 +538,7 @@ static int arcnet_header(struct sk_buff *skb, struct net_device *dev, /* Called by the kernel in order to transmit a packet. */ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, - struct net_device *dev) + struct net_device *dev) { struct arcnet_local *lp = netdev_priv(dev); struct archdr *pkt; @@ -550,14 +550,14 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, BUGMSG(D_DURING, "transmit requested (status=%Xh, txbufs=%d/%d, len=%d, protocol %x)\n", - ASTATUS(), lp->cur_tx, lp->next_tx, skb->len,skb->protocol); + ASTATUS(), lp->cur_tx, lp->next_tx, skb->len, skb->protocol); - pkt = (struct archdr *) skb->data; + pkt = (struct archdr *)skb->data; soft = &pkt->soft.rfc1201; proto = arc_proto_map[soft->proto]; BUGMSG(D_SKB_SIZE, "skb: transmitting %d bytes to %02X\n", - skb->len, pkt->hard.dest); + skb->len, pkt->hard.dest); BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "tx"); /* fits in one packet? */ @@ -572,7 +572,7 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, spin_lock_irqsave(&lp->lock, flags); AINTMASK(0); - if(lp->next_tx == -1) + if (lp->next_tx == -1) txbuf = get_arcbuf(dev); else { txbuf = -1; @@ -594,9 +594,9 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, if (proto->continue_tx && proto->continue_tx(dev, txbuf)) { - BUGMSG(D_NORMAL, - "bug! continue_tx finished the first time! " - "(proto='%c')\n", proto->suffix); + BUGMSG(D_NORMAL, + "bug! continue_tx finished the first time! " + "(proto='%c')\n", proto->suffix); } } retval = NETDEV_TX_OK; @@ -606,14 +606,14 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, freeskb = 0; } - BUGMSG(D_DEBUG, "%s: %d: %s, status: %x\n",__FILE__,__LINE__,__func__,ASTATUS()); + BUGMSG(D_DEBUG, "%s: %d: %s, status: %x\n", __FILE__, __LINE__, __func__, ASTATUS()); /* make sure we didn't ignore a TX IRQ while we were in here */ AINTMASK(0); - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); - lp->intmask |= TXFREEflag|EXCNAKflag; + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + lp->intmask |= TXFREEflag | EXCNAKflag; AINTMASK(lp->intmask); - BUGMSG(D_DEBUG, "%s: %d: %s, status: %x\n",__FILE__,__LINE__,__func__,ASTATUS()); + BUGMSG(D_DEBUG, "%s: %d: %s, status: %x\n", __FILE__, __LINE__, __func__, ASTATUS()); spin_unlock_irqrestore(&lp->lock, flags); if (freeskb) { @@ -649,7 +649,7 @@ static int go_tx(struct net_device *dev) lp->lasttrans_dest = lp->lastload_dest; lp->lastload_dest = 0; lp->excnak_pending = 0; - lp->intmask |= TXFREEflag|EXCNAKflag; + lp->intmask |= TXFREEflag | EXCNAKflag; return 1; } @@ -676,12 +676,12 @@ void arcnet_timeout(struct net_device *dev) /* make sure we didn't miss a TX or a EXC NAK IRQ */ AINTMASK(0); - lp->intmask |= TXFREEflag|EXCNAKflag; + lp->intmask |= TXFREEflag | EXCNAKflag; AINTMASK(lp->intmask); - + spin_unlock_irqrestore(&lp->lock, flags); - if (time_after(jiffies, lp->last_timeout + 10*HZ)) { + if (time_after(jiffies, lp->last_timeout + 10 * HZ)) { BUGMSG(D_EXTRA, "tx timed out%s (status=%Xh, intmask=%Xh, dest=%02Xh)\n", msg, status, lp->intmask, lp->lasttrans_dest); lp->last_timeout = jiffies; @@ -710,7 +710,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) lp = netdev_priv(dev); BUG_ON(!lp); - + spin_lock(&lp->lock); /* @@ -731,16 +731,16 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) boguscount = 5; do { status = ASTATUS(); - diagstatus = (status >> 8) & 0xFF; + diagstatus = (status >> 8) & 0xFF; BUGMSG(D_DEBUG, "%s: %d: %s: status=%x\n", - __FILE__,__LINE__,__func__,status); + __FILE__, __LINE__, __func__, status); didsomething = 0; /* * RESET flag was enabled - card is resetting and if RX is * disabled, it's NOT because we just got a packet. - * + * * The card is in an undefined state. Clear it out and start over. */ if (status & RESETflag) { @@ -751,14 +751,14 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) /* get out of the interrupt handler! */ break; } - /* + /* * RX is inhibited - we must have received something. Prepare to * receive into the next buffer. - * + * * We don't actually copy the received packet from the card until * after the transmit handler runs (and possibly launches the next * tx); this should improve latency slightly if we get both types - * of interrupts at once. + * of interrupts at once. */ recbuf = -1; if (status & lp->intmask & NORXflag) { @@ -775,27 +775,27 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) didsomething++; } - if((diagstatus & EXCNAKflag)) { + if ((diagstatus & EXCNAKflag)) { BUGMSG(D_DURING, "EXCNAK IRQ (diagstat=%Xh)\n", diagstatus); - ACOMMAND(NOTXcmd); /* disable transmit */ - lp->excnak_pending = 1; + ACOMMAND(NOTXcmd); /* disable transmit */ + lp->excnak_pending = 1; - ACOMMAND(EXCNAKclear); + ACOMMAND(EXCNAKclear); lp->intmask &= ~(EXCNAKflag); - didsomething++; - } + didsomething++; + } /* a transmit finished, and we're interested in it. */ if ((status & lp->intmask & TXFREEflag) || lp->timed_out) { - lp->intmask &= ~(TXFREEflag|EXCNAKflag); + lp->intmask &= ~(TXFREEflag | EXCNAKflag); BUGMSG(D_DURING, "TX IRQ (stat=%Xh)\n", status); if (lp->cur_tx != -1 && !lp->timed_out) { - if(!(status & TXACKflag)) { + if (!(status & TXACKflag)) { if (lp->lasttrans_dest != 0) { BUGMSG(D_EXTRA, "transmit was not acknowledged! " @@ -813,16 +813,16 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) if (lp->outgoing.proto && lp->outgoing.proto->ack_tx) { - int ackstatus; - if(status & TXACKflag) - ackstatus=2; - else if(lp->excnak_pending) - ackstatus=1; - else - ackstatus=0; - - lp->outgoing.proto - ->ack_tx(dev, ackstatus); + int ackstatus; + if (status & TXACKflag) + ackstatus = 2; + else if (lp->excnak_pending) + ackstatus = 1; + else + ackstatus = 0; + + lp->outgoing.proto + ->ack_tx(dev, ackstatus); } } if (lp->cur_tx != -1) @@ -842,11 +842,11 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) if (lp->outgoing.proto->continue_tx(dev, txbuf)) { /* that was the last segment */ dev->stats.tx_bytes += lp->outgoing.skb->len; - if(!lp->outgoing.proto->ack_tx) - { - dev_kfree_skb_irq(lp->outgoing.skb); - lp->outgoing.proto = NULL; - } + if (!lp->outgoing.proto->ack_tx) + { + dev_kfree_skb_irq(lp->outgoing.skb); + lp->outgoing.proto = NULL; + } } lp->next_tx = txbuf; } @@ -871,8 +871,8 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) BUGMSG(D_RECON, "Network reconfiguration detected (status=%Xh)\n", status); /* MYRECON bit is at bit 7 of diagstatus */ - if(diagstatus & 0x80) - BUGMSG(D_RECON,"Put out that recon myself\n"); + if (diagstatus & 0x80) + BUGMSG(D_RECON, "Put out that recon myself\n"); /* is the RECON info empty or old? */ if (!lp->first_recon || !lp->last_recon || @@ -889,7 +889,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) BUGMSG(D_DURING, "recon: counter=%d, time=%lds, net=%d\n", lp->num_recons, - (lp->last_recon - lp->first_recon) / HZ, + (lp->last_recon - lp->first_recon) / HZ, lp->network_down); /* if network is marked up; @@ -911,7 +911,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) } } } else if (lp->network_down && - time_after(jiffies, lp->last_recon + HZ * 10)) { + time_after(jiffies, lp->last_recon + HZ * 10)) { if (lp->network_down) BUGMSG(D_NORMAL, "cabling restored?\n"); lp->first_recon = lp->last_recon = 0; @@ -920,7 +920,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) BUGMSG(D_DURING, "not recon: clearing counters anyway.\n"); } - if(didsomething) { + if (didsomething) { retval |= IRQ_HANDLED; } } @@ -934,7 +934,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) AINTMASK(0); udelay(1); AINTMASK(lp->intmask); - + spin_unlock(&lp->lock); return retval; } @@ -1007,7 +1007,7 @@ static void null_rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length) { BUGMSG(D_PROTO, - "rx: don't know how to deal with proto %02Xh from host %02Xh.\n", + "rx: don't know how to deal with proto %02Xh from host %02Xh.\n", pkthdr->soft.rfc1201.proto, pkthdr->hard.source); } diff --git a/drivers/net/arcnet/capmode.c b/drivers/net/arcnet/capmode.c index 42fce91b71fc..95a6cf07965c 100644 --- a/drivers/net/arcnet/capmode.c +++ b/drivers/net/arcnet/capmode.c @@ -71,12 +71,12 @@ static void rx(struct net_device *dev, int bufnum, /* use these variables to be sure we count in bytes, not in sizeof(struct archdr) */ - pktbuf=(char*)pkt; - pkthdrbuf=(char*)pkthdr; - memcpy(pktbuf, pkthdrbuf, ARC_HDR_SIZE+sizeof(pkt->soft.cap.proto)); - memcpy(pktbuf+ARC_HDR_SIZE+sizeof(pkt->soft.cap.proto)+sizeof(int), - pkthdrbuf+ARC_HDR_SIZE+sizeof(pkt->soft.cap.proto), - sizeof(struct archdr)-ARC_HDR_SIZE-sizeof(pkt->soft.cap.proto)); + pktbuf = (char *)pkt; + pkthdrbuf = (char *)pkthdr; + memcpy(pktbuf, pkthdrbuf, ARC_HDR_SIZE + sizeof(pkt->soft.cap.proto)); + memcpy(pktbuf + ARC_HDR_SIZE + sizeof(pkt->soft.cap.proto) + sizeof(int), + pkthdrbuf + ARC_HDR_SIZE + sizeof(pkt->soft.cap.proto), + sizeof(struct archdr) - ARC_HDR_SIZE - sizeof(pkt->soft.cap.proto)); if (length > sizeof(pkt->soft)) lp->hw.copy_from_card(dev, bufnum, ofs + sizeof(pkt->soft), @@ -101,10 +101,10 @@ static int build_header(struct sk_buff *skb, uint8_t daddr) { int hdr_size = ARC_HDR_SIZE; - struct archdr *pkt = (struct archdr *) skb_push(skb, hdr_size); + struct archdr *pkt = (struct archdr *)skb_push(skb, hdr_size); BUGMSG(D_PROTO, "Preparing header for cap packet %x.\n", - *((int*)&pkt->soft.cap.cookie[0])); + *((int *)&pkt->soft.cap.cookie[0])); /* * Set the source hardware address. * @@ -148,7 +148,7 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, lp->next_tx, lp->cur_tx, bufnum); BUGMSG(D_PROTO, "Sending for cap packet %x.\n", - *((int*)&pkt->soft.cap.cookie[0])); + *((int *)&pkt->soft.cap.cookie[0])); if (length > XMTU) { /* should never happen! other people already check for this. */ @@ -166,7 +166,7 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, hard->offset[0] = ofs = 256 - length; BUGMSG(D_DURING, "prepare_tx: length=%d ofs=%d\n", - length,ofs); + length, ofs); /* Copy the arcnet-header + the protocol byte down: */ lp->hw.copy_to_card(dev, bufnum, 0, hard, ARC_HDR_SIZE); @@ -175,8 +175,8 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, /* Skip the extra integer we have written into it as a cookie but write the rest of the message: */ - lp->hw.copy_to_card(dev, bufnum, ofs+1, - ((unsigned char*)&pkt->soft.cap.mes),length-1); + lp->hw.copy_to_card(dev, bufnum, ofs + 1, + ((unsigned char *)&pkt->soft.cap.mes), length - 1); lp->lastload_dest = hard->dest; @@ -188,21 +188,21 @@ static int ack_tx(struct net_device *dev, int acked) struct arcnet_local *lp = netdev_priv(dev); struct sk_buff *ackskb; struct archdr *ackpkt; - int length=sizeof(struct arc_cap); + int length = sizeof(struct arc_cap); BUGMSG(D_DURING, "capmode: ack_tx: protocol: %x: result: %d\n", - lp->outgoing.skb->protocol, acked); + lp->outgoing.skb->protocol, acked); BUGLVL(D_SKB) arcnet_dump_skb(dev, lp->outgoing.skb, "ack_tx"); /* Now alloc a skb to send back up through the layers: */ - ackskb = alloc_skb(length + ARC_HDR_SIZE , GFP_ATOMIC); + ackskb = alloc_skb(length + ARC_HDR_SIZE, GFP_ATOMIC); if (ackskb == NULL) { BUGMSG(D_NORMAL, "Memory squeeze, can't acknowledge.\n"); goto free_outskb; } - skb_put(ackskb, length + ARC_HDR_SIZE ); + skb_put(ackskb, length + ARC_HDR_SIZE); ackskb->dev = dev; skb_reset_mac_header(ackskb); @@ -212,10 +212,10 @@ static int ack_tx(struct net_device *dev, int acked) skb_copy_from_linear_data(lp->outgoing.skb, ackpkt, ARC_HDR_SIZE + sizeof(struct arc_cap)); ackpkt->soft.cap.proto = 0; /* using protocol 0 for acknowledge */ - ackpkt->soft.cap.mes.ack=acked; + ackpkt->soft.cap.mes.ack = acked; BUGMSG(D_PROTO, "Ackknowledge for cap packet %x.\n", - *((int*)&ackpkt->soft.cap.cookie[0])); + *((int *)&ackpkt->soft.cap.cookie[0])); ackskb->protocol = cpu_to_be16(ETH_P_ARCNET); diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index 45c61a2c5fbd..d8746caf8e7a 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - COM20020 chipset support - * + * * Written 1997 by David Woodhouse. * Written 1994-1999 by Avery Pennarun. * Written 1999-2000 by Martin Mares . diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 96edc1346124..e0f489a117f1 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -1,7 +1,7 @@ /* * Linux ARCnet driver - COM20020 PCI support * Contemporary Controls PCI20 and SOHARD SH-ARC PCI - * + * * Written 1994-1999 by Avery Pennarun, * based on an ISA version by David Woodhouse. * Written 1999-2000 by Martin Mares . diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c index 1a8437842fbc..cd2a5ca56ce5 100644 --- a/drivers/net/arcnet/com20020.c +++ b/drivers/net/arcnet/com20020.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - COM20020 chipset support - * + * * Written 1997 by David Woodhouse. * Written 1994-1999 by Avery Pennarun. * Written 1999 by Martin Mares . @@ -108,7 +108,7 @@ int com20020_check(struct net_device *dev) { SET_SUBADR(SUB_SETUP2); outb(lp->setup2, _XREG); - + /* must now write the magic "restart operation" command */ mdelay(1); outb(0x18, _COMMAND); @@ -117,7 +117,7 @@ int com20020_check(struct net_device *dev) lp->config = 0x21 | (lp->timeout << 3) | (lp->backplane << 2); /* set node ID to 0x42 (but transmitter is disabled, so it's okay) */ SETCONF; - outb(0x42, ioaddr + BUS_ALIGN*7); + outb(0x42, ioaddr + BUS_ALIGN * 7); status = ASTATUS(); @@ -129,7 +129,7 @@ int com20020_check(struct net_device *dev) /* Enable TX */ outb(0x39, _CONFIG); - outb(inb(ioaddr + BUS_ALIGN*8), ioaddr + BUS_ALIGN*7); + outb(inb(ioaddr + BUS_ALIGN * 8), ioaddr + BUS_ALIGN * 7); ACOMMAND(CFLAGScmd | RESETclear | CONFIGclear); @@ -193,7 +193,7 @@ int com20020_found(struct net_device *dev, int shared) lp->hw.close = com20020_close; if (!dev->dev_addr[0]) - dev->dev_addr[0] = inb(ioaddr + BUS_ALIGN*8); /* FIXME: do this some other way! */ + dev->dev_addr[0] = inb(ioaddr + BUS_ALIGN * 8); /* FIXME: do this some other way! */ SET_SUBADR(SUB_SETUP1); outb(lp->setup, _XREG); @@ -202,7 +202,7 @@ int com20020_found(struct net_device *dev, int shared) { SET_SUBADR(SUB_SETUP2); outb(lp->setup2, _XREG); - + /* must now write the magic "restart operation" command */ mdelay(1); outb(0x18, _COMMAND); @@ -232,7 +232,7 @@ int com20020_found(struct net_device *dev, int shared) BUGMSG(D_NORMAL, "Using extended timeout value of %d.\n", lp->timeout); BUGMSG(D_NORMAL, "Using CKP %d - data rate %s.\n", - lp->setup >> 1, + lp->setup >> 1, clockrates[3 - ((lp->setup2 & 0xF0) >> 4) + ((lp->setup & 0x0F) >> 1)]); if (register_netdev(dev)) { @@ -243,9 +243,9 @@ int com20020_found(struct net_device *dev, int shared) } -/* +/* * Do a hardware reset on the card, and set up necessary registers. - * + * * This should be called as little as possible, because it disrupts the * token on the network (causes a RECON) and requires a significant delay. * @@ -258,15 +258,15 @@ static int com20020_reset(struct net_device *dev, int really_reset) u_char inbyte; BUGMSG(D_DEBUG, "%s: %d: %s: dev: %p, lp: %p, dev->name: %s\n", - __FILE__,__LINE__,__func__,dev,lp,dev->name); + __FILE__, __LINE__, __func__, dev, lp, dev->name); BUGMSG(D_INIT, "Resetting %s (status=%02Xh)\n", dev->name, ASTATUS()); - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); lp->config = TXENcfg | (lp->timeout << 3) | (lp->backplane << 2); /* power-up defaults */ SETCONF; - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); if (really_reset) { /* reset the card */ @@ -274,22 +274,22 @@ static int com20020_reset(struct net_device *dev, int really_reset) mdelay(RESETtime * 2); /* COM20020 seems to be slower sometimes */ } /* clear flags & end reset */ - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); ACOMMAND(CFLAGScmd | RESETclear | CONFIGclear); /* verify that the ARCnet signature byte is present */ - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); com20020_copy_from_card(dev, 0, 0, &inbyte, 1); - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); if (inbyte != TESTvalue) { - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); BUGMSG(D_NORMAL, "reset failed: TESTvalue not present.\n"); return 1; } /* enable extended (512-byte) packets */ ACOMMAND(CONFIGcmd | EXTconf); - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); /* done! return success. */ return 0; @@ -299,7 +299,7 @@ static int com20020_reset(struct net_device *dev, int really_reset) static void com20020_setmask(struct net_device *dev, int mask) { u_int ioaddr = dev->base_addr; - BUGMSG(D_DURING, "Setting mask to %x at %x\n",mask,ioaddr); + BUGMSG(D_DURING, "Setting mask to %x at %x\n", mask, ioaddr); AINTMASK(mask); } @@ -315,7 +315,7 @@ static int com20020_status(struct net_device *dev) { u_int ioaddr = dev->base_addr; - return ASTATUS() + (ADIAGSTATUS()<<8); + return ASTATUS() + (ADIAGSTATUS() << 8); } static void com20020_close(struct net_device *dev) diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c index 057d9582132a..f68752102379 100644 --- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - COM20020 PCMCIA support - * + * * Written 1994-1999 by Avery Pennarun, * based on an ISA version by David Woodhouse. * Derived from ibmtr_cs.c by Steve Kipisz (pcmcia-cs 3.1.4) @@ -19,14 +19,14 @@ * Director, National Security Agency. This software may only be used * and distributed according to the terms of the GNU General Public License as * modified by SRC, incorporated herein by reference. - * + * * ********************** * Changes: * Arnaldo Carvalho de Melo - 08/08/2000 * - reorganize kmallocs in com20020_attach, checking all for failure * and releasing the previous allocations if one fails * ********************** - * + * * For more details, see drivers/net/arcnet.c * * ********************** @@ -53,33 +53,33 @@ static void regdump(struct net_device *dev) { #ifdef DEBUG - int ioaddr = dev->base_addr; - int count; - - netdev_dbg(dev, "register dump:\n"); - for (count = ioaddr; count < ioaddr + 16; count++) - { - if (!(count % 16)) - pr_cont("%04X:", count); - pr_cont(" %02X", inb(count)); - } - pr_cont("\n"); - - netdev_dbg(dev, "buffer0 dump:\n"); + int ioaddr = dev->base_addr; + int count; + + netdev_dbg(dev, "register dump:\n"); + for (count = ioaddr; count < ioaddr + 16; count++) + { + if (!(count % 16)) + pr_cont("%04X:", count); + pr_cont(" %02X", inb(count)); + } + pr_cont("\n"); + + netdev_dbg(dev, "buffer0 dump:\n"); /* set up the address register */ - count = 0; + count = 0; outb((count >> 8) | RDDATAflag | AUTOINCflag, _ADDR_HI); outb(count & 0xff, _ADDR_LO); - - for (count = 0; count < 256+32; count++) - { - if (!(count % 16)) - pr_cont("%04X:", count); - - /* copy the data */ - pr_cont(" %02X", inb(_MEMDATA)); - } - pr_cont("\n"); + + for (count = 0; count < 256 + 32; count++) + { + if (!(count % 16)) + pr_cont("%04X:", count); + + /* copy the data */ + pr_cont(" %02X", inb(_MEMDATA)); + } + pr_cont("\n"); #endif } @@ -114,169 +114,169 @@ static void com20020_detach(struct pcmcia_device *p_dev); static int com20020_probe(struct pcmcia_device *p_dev) { - struct com20020_dev *info; - struct net_device *dev; - struct arcnet_local *lp; + struct com20020_dev *info; + struct net_device *dev; + struct arcnet_local *lp; - dev_dbg(&p_dev->dev, "com20020_attach()\n"); + dev_dbg(&p_dev->dev, "com20020_attach()\n"); - /* Create new network device */ - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) - goto fail_alloc_info; + /* Create new network device */ + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + goto fail_alloc_info; - dev = alloc_arcdev(""); - if (!dev) - goto fail_alloc_dev; + dev = alloc_arcdev(""); + if (!dev) + goto fail_alloc_dev; - lp = netdev_priv(dev); - lp->timeout = timeout; - lp->backplane = backplane; - lp->clockp = clockp; - lp->clockm = clockm & 3; - lp->hw.owner = THIS_MODULE; + lp = netdev_priv(dev); + lp->timeout = timeout; + lp->backplane = backplane; + lp->clockp = clockp; + lp->clockm = clockm & 3; + lp->hw.owner = THIS_MODULE; - /* fill in our module parameters as defaults */ - dev->dev_addr[0] = node; + /* fill in our module parameters as defaults */ + dev->dev_addr[0] = node; - p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8; - p_dev->resource[0]->end = 16; - p_dev->config_flags |= CONF_ENABLE_IRQ; + p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8; + p_dev->resource[0]->end = 16; + p_dev->config_flags |= CONF_ENABLE_IRQ; - info->dev = dev; - p_dev->priv = info; + info->dev = dev; + p_dev->priv = info; - return com20020_config(p_dev); + return com20020_config(p_dev); fail_alloc_dev: - kfree(info); + kfree(info); fail_alloc_info: - return -ENOMEM; + return -ENOMEM; } /* com20020_attach */ static void com20020_detach(struct pcmcia_device *link) { - struct com20020_dev *info = link->priv; - struct net_device *dev = info->dev; + struct com20020_dev *info = link->priv; + struct net_device *dev = info->dev; - dev_dbg(&link->dev, "detach...\n"); + dev_dbg(&link->dev, "detach...\n"); - dev_dbg(&link->dev, "com20020_detach\n"); + dev_dbg(&link->dev, "com20020_detach\n"); - dev_dbg(&link->dev, "unregister...\n"); + dev_dbg(&link->dev, "unregister...\n"); - unregister_netdev(dev); + unregister_netdev(dev); - /* - * this is necessary because we register our IRQ separately - * from card services. - */ - if (dev->irq) - free_irq(dev->irq, dev); + /* + * this is necessary because we register our IRQ separately + * from card services. + */ + if (dev->irq) + free_irq(dev->irq, dev); - com20020_release(link); + com20020_release(link); - /* Unlink device structure, free bits */ - dev_dbg(&link->dev, "unlinking...\n"); - if (link->priv) - { - dev = info->dev; - if (dev) + /* Unlink device structure, free bits */ + dev_dbg(&link->dev, "unlinking...\n"); + if (link->priv) { - dev_dbg(&link->dev, "kfree...\n"); - free_netdev(dev); + dev = info->dev; + if (dev) + { + dev_dbg(&link->dev, "kfree...\n"); + free_netdev(dev); + } + dev_dbg(&link->dev, "kfree2...\n"); + kfree(info); } - dev_dbg(&link->dev, "kfree2...\n"); - kfree(info); - } } /* com20020_detach */ static int com20020_config(struct pcmcia_device *link) { - struct arcnet_local *lp; - struct com20020_dev *info; - struct net_device *dev; - int i, ret; - int ioaddr; + struct arcnet_local *lp; + struct com20020_dev *info; + struct net_device *dev; + int i, ret; + int ioaddr; + + info = link->priv; + dev = info->dev; - info = link->priv; - dev = info->dev; + dev_dbg(&link->dev, "config...\n"); - dev_dbg(&link->dev, "config...\n"); + dev_dbg(&link->dev, "com20020_config\n"); - dev_dbg(&link->dev, "com20020_config\n"); + dev_dbg(&link->dev, "baseport1 is %Xh\n", + (unsigned int)link->resource[0]->start); - dev_dbg(&link->dev, "baseport1 is %Xh\n", - (unsigned int) link->resource[0]->start); + i = -ENODEV; + link->io_lines = 16; - i = -ENODEV; - link->io_lines = 16; + if (!link->resource[0]->start) + { + for (ioaddr = 0x100; ioaddr < 0x400; ioaddr += 0x10) + { + link->resource[0]->start = ioaddr; + i = pcmcia_request_io(link); + if (i == 0) + break; + } + } + else + i = pcmcia_request_io(link); + + if (i != 0) + { + dev_dbg(&link->dev, "requestIO failed totally!\n"); + goto failed; + } + + ioaddr = dev->base_addr = link->resource[0]->start; + dev_dbg(&link->dev, "got ioaddr %Xh\n", ioaddr); + + dev_dbg(&link->dev, "request IRQ %d\n", + link->irq); + if (!link->irq) + { + dev_dbg(&link->dev, "requestIRQ failed totally!\n"); + goto failed; + } - if (!link->resource[0]->start) - { - for (ioaddr = 0x100; ioaddr < 0x400; ioaddr += 0x10) + dev->irq = link->irq; + + ret = pcmcia_enable_device(link); + if (ret) + goto failed; + + if (com20020_check(dev)) { - link->resource[0]->start = ioaddr; - i = pcmcia_request_io(link); - if (i == 0) - break; + regdump(dev); + goto failed; } - } - else - i = pcmcia_request_io(link); - - if (i != 0) - { - dev_dbg(&link->dev, "requestIO failed totally!\n"); - goto failed; - } - - ioaddr = dev->base_addr = link->resource[0]->start; - dev_dbg(&link->dev, "got ioaddr %Xh\n", ioaddr); - - dev_dbg(&link->dev, "request IRQ %d\n", - link->irq); - if (!link->irq) - { - dev_dbg(&link->dev, "requestIRQ failed totally!\n"); - goto failed; - } - - dev->irq = link->irq; - - ret = pcmcia_enable_device(link); - if (ret) - goto failed; - - if (com20020_check(dev)) - { - regdump(dev); - goto failed; - } - - lp = netdev_priv(dev); - lp->card_name = "PCMCIA COM20020"; - lp->card_flags = ARC_CAN_10MBIT; /* pretend all of them can 10Mbit */ - - SET_NETDEV_DEV(dev, &link->dev); - - i = com20020_found(dev, 0); /* calls register_netdev */ - - if (i != 0) { - dev_notice(&link->dev, - "com20020_found() failed\n"); - goto failed; - } - - netdev_dbg(dev, "port %#3lx, irq %d\n", - dev->base_addr, dev->irq); - return 0; + + lp = netdev_priv(dev); + lp->card_name = "PCMCIA COM20020"; + lp->card_flags = ARC_CAN_10MBIT; /* pretend all of them can 10Mbit */ + + SET_NETDEV_DEV(dev, &link->dev); + + i = com20020_found(dev, 0); /* calls register_netdev */ + + if (i != 0) { + dev_notice(&link->dev, + "com20020_found() failed\n"); + goto failed; + } + + netdev_dbg(dev, "port %#3lx, irq %d\n", + dev->base_addr, dev->irq); + return 0; failed: - dev_dbg(&link->dev, "com20020_config failed...\n"); - com20020_release(link); - return -ENODEV; + dev_dbg(&link->dev, "com20020_config failed...\n"); + com20020_release(link); + return -ENODEV; } /* com20020_config */ static void com20020_release(struct pcmcia_device *link) @@ -312,9 +312,9 @@ static int com20020_resume(struct pcmcia_device *link) static const struct pcmcia_device_id com20020_ids[] = { PCMCIA_DEVICE_PROD_ID12("Contemporary Control Systems, Inc.", - "PCM20 Arcnet Adapter", 0x59991666, 0x95dfffaf), + "PCM20 Arcnet Adapter", 0x59991666, 0x95dfffaf), PCMCIA_DEVICE_PROD_ID12("SoHard AG", - "SH ARC PCMCIA", 0xf8991729, 0x69dff0c7), + "SH ARC PCMCIA", 0xf8991729, 0x69dff0c7), PCMCIA_DEVICE_NULL }; MODULE_DEVICE_TABLE(pcmcia, com20020_ids); diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 487d780ebbdf..23ac9edbe91c 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - COM90xx chipset (IO-mapped buffers) - * + * * Written 1997 by David Woodhouse. * Written 1994-1999 by Avery Pennarun. * Written 1999-2000 by Martin Mares . @@ -60,23 +60,23 @@ static void com90io_copy_from_card(struct net_device *dev, int bufnum, int offse #define ARCNET_TOTAL_SIZE 16 /* COM 9026 controller chip --> ARCnet register addresses */ -#define _INTMASK (ioaddr+0) /* writable */ -#define _STATUS (ioaddr+0) /* readable */ -#define _COMMAND (ioaddr+1) /* writable, returns random vals on read (?) */ -#define _RESET (ioaddr+8) /* software reset (on read) */ -#define _MEMDATA (ioaddr+12) /* Data port for IO-mapped memory */ -#define _ADDR_HI (ioaddr+15) /* Control registers for said */ -#define _ADDR_LO (ioaddr+14) -#define _CONFIG (ioaddr+2) /* Configuration register */ +#define _INTMASK (ioaddr + 0) /* writable */ +#define _STATUS (ioaddr + 0) /* readable */ +#define _COMMAND (ioaddr + 1) /* writable, returns random vals on read (?) */ +#define _RESET (ioaddr + 8) /* software reset (on read) */ +#define _MEMDATA (ioaddr + 12) /* Data port for IO-mapped memory */ +#define _ADDR_HI (ioaddr + 15) /* Control registers for said */ +#define _ADDR_LO (ioaddr + 14) +#define _CONFIG (ioaddr + 2) /* Configuration register */ #undef ASTATUS #undef ACOMMAND #undef AINTMASK #define ASTATUS() inb(_STATUS) -#define ACOMMAND(cmd) outb((cmd),_COMMAND) -#define AINTMASK(msk) outb((msk),_INTMASK) -#define SETCONF() outb((lp->config),_CONFIG) +#define ACOMMAND(cmd) outb((cmd), _COMMAND) +#define AINTMASK(msk) outb((msk), _INTMASK) +#define SETCONF() outb((lp->config), _CONFIG) /**************************************************************************** diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index b80fbe40aa0e..a4c5d5909b13 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - COM90xx chipset (memory-mapped buffers) - * + * * Written 1994-1999 by Avery Pennarun. * Written 1999 by Martin Mares . * Derived from skeleton.c by Donald Becker. @@ -77,25 +77,25 @@ static int numcards; /* Amount of I/O memory used by the card */ #define BUFFER_SIZE (512) -#define MIRROR_SIZE (BUFFER_SIZE*4) +#define MIRROR_SIZE (BUFFER_SIZE * 4) /* COM 9026 controller chip --> ARCnet register addresses */ -#define _INTMASK (ioaddr+0) /* writable */ -#define _STATUS (ioaddr+0) /* readable */ -#define _COMMAND (ioaddr+1) /* writable, returns random vals on read (?) */ -#define _CONFIG (ioaddr+2) /* Configuration register */ -#define _RESET (ioaddr+8) /* software reset (on read) */ -#define _MEMDATA (ioaddr+12) /* Data port for IO-mapped memory */ -#define _ADDR_HI (ioaddr+15) /* Control registers for said */ -#define _ADDR_LO (ioaddr+14) +#define _INTMASK (ioaddr + 0) /* writable */ +#define _STATUS (ioaddr + 0) /* readable */ +#define _COMMAND (ioaddr + 1) /* writable, returns random vals on read (?) */ +#define _CONFIG (ioaddr + 2) /* Configuration register */ +#define _RESET (ioaddr + 8) /* software reset (on read) */ +#define _MEMDATA (ioaddr + 12) /* Data port for IO-mapped memory */ +#define _ADDR_HI (ioaddr + 15) /* Control registers for said */ +#define _ADDR_LO (ioaddr + 14) #undef ASTATUS #undef ACOMMAND #undef AINTMASK #define ASTATUS() inb(_STATUS) -#define ACOMMAND(cmd) outb((cmd),_COMMAND) -#define AINTMASK(msk) outb((msk),_INTMASK) +#define ACOMMAND(cmd) outb((cmd), _COMMAND) +#define AINTMASK(msk) outb((msk), _INTMASK) static int com90xx_skip_probe __initdata = 0; @@ -127,12 +127,12 @@ static void __init com90xx_probe(void) if (!io && !irq && !shmem && !*device && com90xx_skip_probe) return; - shmems = kzalloc(((0x100000-0xa0000) / 0x800) * sizeof(unsigned long), + shmems = kzalloc(((0x100000 - 0xa0000) / 0x800) * sizeof(unsigned long), GFP_KERNEL); if (!shmems) return; - iomem = kzalloc(((0x100000-0xa0000) / 0x800) * sizeof(void __iomem *), - GFP_KERNEL); + iomem = kzalloc(((0x100000 - 0xa0000) / 0x800) * sizeof(void __iomem *), + GFP_KERNEL); if (!iomem) { kfree(shmems); return; @@ -579,7 +579,7 @@ static void com90xx_setmask(struct net_device *dev, int mask) /* * Do a hardware reset on the card, and set up necessary registers. - * + * * This should be called as little as possible, because it disrupts the * token on the network (causes a RECON) and requires a significant delay. * diff --git a/drivers/net/arcnet/rfc1051.c b/drivers/net/arcnet/rfc1051.c index f81db4070a57..ae1ded286897 100644 --- a/drivers/net/arcnet/rfc1051.c +++ b/drivers/net/arcnet/rfc1051.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - RFC1051 ("simple" standard) packet encapsulation - * + * * Written 1994-1999 by Avery Pennarun. * Derived from skeleton.c by Donald Becker. * @@ -84,12 +84,12 @@ MODULE_LICENSE("GPL"); /* * Determine a packet's protocol ID. - * + * * With ARCnet we have to convert everything to Ethernet-style stuff. */ static __be16 type_trans(struct sk_buff *skb, struct net_device *dev) { - struct archdr *pkt = (struct archdr *) skb->data; + struct archdr *pkt = (struct archdr *)skb->data; struct arc_rfc1051 *soft = &pkt->soft.rfc1051; int hdr_size = ARC_HDR_SIZE + RFC1051_HDR_SIZE; @@ -146,7 +146,7 @@ static void rx(struct net_device *dev, int bufnum, skb_put(skb, length + ARC_HDR_SIZE); skb->dev = dev; - pkt = (struct archdr *) skb->data; + pkt = (struct archdr *)skb->data; /* up to sizeof(pkt->soft) has already been copied from the card */ memcpy(pkt, pkthdr, sizeof(struct archdr)); @@ -169,7 +169,7 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, uint8_t daddr) { int hdr_size = ARC_HDR_SIZE + RFC1051_HDR_SIZE; - struct archdr *pkt = (struct archdr *) skb_push(skb, hdr_size); + struct archdr *pkt = (struct archdr *)skb_push(skb, hdr_size); struct arc_rfc1051 *soft = &pkt->soft.rfc1051; /* set the protocol ID according to RFC1051 */ @@ -201,7 +201,7 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, /* see linux/net/ethernet/eth.c to see where I got the following */ if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) { - /* + /* * FIXME: fill in the last byte of the dest ipaddr here to better * comply with RFC1051 in "noarp" mode. */ diff --git a/drivers/net/arcnet/rfc1201.c b/drivers/net/arcnet/rfc1201.c index b71431aae084..bf2a8cb3f0e2 100644 --- a/drivers/net/arcnet/rfc1201.c +++ b/drivers/net/arcnet/rfc1201.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - RFC1201 (standard) packet encapsulation - * + * * Written 1994-1999 by Avery Pennarun. * Derived from skeleton.c by Donald Becker. * @@ -86,12 +86,12 @@ module_exit(arcnet_rfc1201_exit); /* * Determine a packet's protocol ID. - * + * * With ARCnet we have to convert everything to Ethernet-style stuff. */ static __be16 type_trans(struct sk_buff *skb, struct net_device *dev) { - struct archdr *pkt = (struct archdr *) skb->data; + struct archdr *pkt = (struct archdr *)skb->data; struct arc_rfc1201 *soft = &pkt->soft.rfc1201; int hdr_size = ARC_HDR_SIZE + RFC1201_HDR_SIZE; @@ -169,7 +169,7 @@ static void rx(struct net_device *dev, int bufnum, if (in->skb) { /* already assembling one! */ BUGMSG(D_EXTRA, "aborting assembly (seq=%d) for unsplit packet (splitflag=%d, seq=%d)\n", - in->sequence, soft->split_flag, soft->sequence); + in->sequence, soft->split_flag, soft->sequence); lp->rfc1201.aborted_seq = soft->sequence; dev_kfree_skb_irq(in->skb); dev->stats.rx_errors++; @@ -187,7 +187,7 @@ static void rx(struct net_device *dev, int bufnum, skb_put(skb, length + ARC_HDR_SIZE); skb->dev = dev; - pkt = (struct archdr *) skb->data; + pkt = (struct archdr *)skb->data; soft = &pkt->soft.rfc1201; /* up to sizeof(pkt->soft) has already been copied from the card */ @@ -203,11 +203,11 @@ static void rx(struct net_device *dev, int bufnum, * (which is impossible to fumble) and insert it ourselves. */ if (soft->proto == ARC_P_ARP) { - struct arphdr *arp = (struct arphdr *) soft->payload; + struct arphdr *arp = (struct arphdr *)soft->payload; /* make sure addresses are the right length */ if (arp->ar_hln == 1 && arp->ar_pln == 4) { - uint8_t *cptr = (uint8_t *) arp + sizeof(struct arphdr); + uint8_t *cptr = (uint8_t *)arp + sizeof(struct arphdr); if (!*cptr) { /* is saddr = 00? */ BUGMSG(D_EXTRA, @@ -274,7 +274,7 @@ static void rx(struct net_device *dev, int bufnum, dev_kfree_skb_irq(in->skb); } in->sequence = soft->sequence; - in->numpackets = ((unsigned) soft->split_flag >> 1) + 2; + in->numpackets = ((unsigned)soft->split_flag >> 1) + 2; in->lastpacket = 1; if (in->numpackets > 16) { @@ -294,7 +294,7 @@ static void rx(struct net_device *dev, int bufnum, return; } skb->dev = dev; - pkt = (struct archdr *) skb->data; + pkt = (struct archdr *)skb->data; soft = &pkt->soft.rfc1201; memcpy(pkt, pkthdr, ARC_HDR_SIZE + RFC1201_HDR_SIZE); @@ -302,7 +302,7 @@ static void rx(struct net_device *dev, int bufnum, soft->split_flag = 0; /* end result won't be split */ } else { /* not first packet */ - int packetnum = ((unsigned) soft->split_flag >> 1) + 1; + int packetnum = ((unsigned)soft->split_flag >> 1) + 1; /* * if we're not assembling, there's no point trying to @@ -341,7 +341,7 @@ static void rx(struct net_device *dev, int bufnum, in->lastpacket = in->numpackets = 0; return; } - pkt = (struct archdr *) in->skb->data; + pkt = (struct archdr *)in->skb->data; soft = &pkt->soft.rfc1201; } @@ -357,10 +357,10 @@ static void rx(struct net_device *dev, int bufnum, in->skb = NULL; in->lastpacket = in->numpackets = 0; - BUGMSG(D_SKB_SIZE, "skb: received %d bytes from %02X (unsplit)\n", - skb->len, pkt->hard.source); - BUGMSG(D_SKB_SIZE, "skb: received %d bytes from %02X (split)\n", - skb->len, pkt->hard.source); + BUGMSG(D_SKB_SIZE, "skb: received %d bytes from %02X (unsplit)\n", + skb->len, pkt->hard.source); + BUGMSG(D_SKB_SIZE, "skb: received %d bytes from %02X (split)\n", + skb->len, pkt->hard.source); BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "rx"); skb->protocol = type_trans(skb, dev); @@ -376,7 +376,7 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, { struct arcnet_local *lp = netdev_priv(dev); int hdr_size = ARC_HDR_SIZE + RFC1201_HDR_SIZE; - struct archdr *pkt = (struct archdr *) skb_push(skb, hdr_size); + struct archdr *pkt = (struct archdr *)skb_push(skb, hdr_size); struct arc_rfc1201 *soft = &pkt->soft.rfc1201; /* set the protocol ID according to RFC1201 */ @@ -424,7 +424,7 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, /* see linux/net/ethernet/eth.c to see where I got the following */ if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) { - /* + /* * FIXME: fill in the last byte of the dest ipaddr here to better * comply with RFC1051 in "noarp" mode. For now, always broadcasting * will probably at least get packets sent out :) @@ -517,7 +517,7 @@ static int continue_tx(struct net_device *dev, int bufnum) int seglen; BUGMSG(D_DURING, - "rfc1201 continue_tx: loading segment %d(+1) of %d (seq=%d)\n", + "rfc1201 continue_tx: loading segment %d(+1) of %d (seq=%d)\n", out->segnum, out->numsegs, soft->sequence); /* the "new" soft header comes right before the data chunk */ diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index df0356220730..ccfd1d2f984b 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -51,7 +51,7 @@ /* * Debugging bitflags: each option can be enabled individually. - * + * * Note: only debug flags included in the ARCNET_DEBUG_MAX define will * actually be available. GCC will (at least, GCC 2.7.0 will) notice * lines using a BUGLVL not in ARCNET_DEBUG_MAX and automatically optimize @@ -77,33 +77,33 @@ #endif #ifndef ARCNET_DEBUG -#define ARCNET_DEBUG (D_NORMAL|D_EXTRA) +#define ARCNET_DEBUG (D_NORMAL | D_EXTRA) #endif extern int arcnet_debug; /* macros to simplify debug checking */ -#define BUGLVL(x) if ((ARCNET_DEBUG_MAX)&arcnet_debug&(x)) -#define BUGMSG2(x,msg,args...) do { BUGLVL(x) printk(msg, ## args); } while (0) -#define BUGMSG(x,msg,args...) \ - BUGMSG2(x, "%s%6s: " msg, \ - x==D_NORMAL ? KERN_WARNING \ - : x < D_DURING ? KERN_INFO : KERN_DEBUG, \ - dev->name , ## args) +#define BUGLVL(x) if ((ARCNET_DEBUG_MAX) & arcnet_debug & (x)) +#define BUGMSG2(x, msg, args...) do { BUGLVL(x) printk(msg, ## args); } while (0) +#define BUGMSG(x, msg, args...) \ + BUGMSG2(x, "%s%6s: " msg, \ + x == D_NORMAL ? KERN_WARNING \ + : x < D_DURING ? KERN_INFO : KERN_DEBUG, \ + dev->name, ## args) /* see how long a function call takes to run, expressed in CPU cycles */ -#define TIME(name, bytes, call) BUGLVL(D_TIMING) { \ - unsigned long _x, _y; \ - _x = get_cycles(); \ - call; \ - _y = get_cycles(); \ - BUGMSG(D_TIMING, \ - "%s: %d bytes in %lu cycles == " \ - "%lu Kbytes/100Mcycle\n",\ - name, bytes, _y - _x, \ - 100000000 / 1024 * bytes / (_y - _x + 1));\ - } \ - else { \ - call;\ +#define TIME(name, bytes, call) BUGLVL(D_TIMING) { \ + unsigned long _x, _y; \ + _x = get_cycles(); \ + call; \ + _y = get_cycles(); \ + BUGMSG(D_TIMING, \ + "%s: %d bytes in %lu cycles == " \ + "%lu Kbytes/100Mcycle\n", \ + name, bytes, _y - _x, \ + 100000000 / 1024 * bytes / (_y - _x + 1)); \ + } \ + else { \ + call; \ } @@ -189,16 +189,16 @@ struct ArcProto { int mtu; /* largest possible packet */ int is_ip; /* This is a ip plugin - not a raw thing */ - void (*rx) (struct net_device * dev, int bufnum, - struct archdr * pkthdr, int length); - int (*build_header) (struct sk_buff * skb, struct net_device *dev, - unsigned short ethproto, uint8_t daddr); + void (*rx)(struct net_device *dev, int bufnum, + struct archdr *pkthdr, int length); + int (*build_header)(struct sk_buff *skb, struct net_device *dev, + unsigned short ethproto, uint8_t daddr); /* these functions return '1' if the skb can now be freed */ - int (*prepare_tx) (struct net_device * dev, struct archdr * pkt, int length, - int bufnum); - int (*continue_tx) (struct net_device * dev, int bufnum); - int (*ack_tx) (struct net_device * dev, int acked); + int (*prepare_tx)(struct net_device *dev, struct archdr *pkt, int length, + int bufnum); + int (*continue_tx)(struct net_device *dev, int bufnum); + int (*ack_tx)(struct net_device *dev, int acked); }; extern struct ArcProto *arc_proto_map[256], *arc_proto_default, @@ -263,13 +263,13 @@ struct arcnet_local { * situations in which we (for example) want to pre-load a transmit * buffer, or start receiving while we copy a received packet to * memory. - * + * * The rules: only the interrupt handler is allowed to _add_ buffers to * the queue; thus, this doesn't require a lock. Both the interrupt * handler and the transmit function will want to _remove_ buffers, so * we need to handle the situation where they try to do it at the same * time. - * + * * If next_buf == first_free_buf, the queue is empty. Since there are * only four possible buffers, the queue should never be full. */ @@ -298,17 +298,17 @@ struct arcnet_local { /* hardware-specific functions */ struct { struct module *owner; - void (*command) (struct net_device * dev, int cmd); - int (*status) (struct net_device * dev); - void (*intmask) (struct net_device * dev, int mask); - int (*reset) (struct net_device * dev, int really_reset); - void (*open) (struct net_device * dev); - void (*close) (struct net_device * dev); - - void (*copy_to_card) (struct net_device * dev, int bufnum, int offset, - void *buf, int count); - void (*copy_from_card) (struct net_device * dev, int bufnum, int offset, - void *buf, int count); + void (*command)(struct net_device *dev, int cmd); + int (*status)(struct net_device *dev); + void (*intmask)(struct net_device *dev, int mask); + int (*reset)(struct net_device *dev, int really_reset); + void (*open)(struct net_device *dev); + void (*close)(struct net_device *dev); + + void (*copy_to_card)(struct net_device *dev, int bufnum, int offset, + void *buf, int count); + void (*copy_from_card)(struct net_device *dev, int bufnum, int offset, + void *buf, int count); } hw; void __iomem *mem_start; /* pointer to ioremap'ed MMIO */ @@ -325,7 +325,7 @@ struct arcnet_local { #if ARCNET_DEBUG_MAX & D_SKB void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); #else -#define arcnet_dump_skb(dev,skb,desc) ; +#define arcnet_dump_skb(dev, skb, desc) ; #endif void arcnet_unregister_proto(struct ArcProto *proto); @@ -335,7 +335,7 @@ struct net_device *alloc_arcdev(const char *name); int arcnet_open(struct net_device *dev); int arcnet_close(struct net_device *dev); netdev_tx_t arcnet_send_packet(struct sk_buff *skb, - struct net_device *dev); + struct net_device *dev); void arcnet_timeout(struct net_device *dev); #endif /* __KERNEL__ */ -- cgit v1.2.3 From 01a1d5ac4e1a5890fd6c0d0ae900e1b6e4f851d6 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:05:48 -0700 Subject: arcnet: Add and remove blank lines Use a more current kernel line style. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- drivers/net/arcnet/arc-rawmode.c | 5 ----- drivers/net/arcnet/arc-rimi.c | 8 +++----- drivers/net/arcnet/arcnet.c | 23 +++-------------------- drivers/net/arcnet/capmode.c | 3 --- drivers/net/arcnet/com20020-isa.c | 1 - drivers/net/arcnet/com20020-pci.c | 2 -- drivers/net/arcnet/com20020.c | 8 ++------ drivers/net/arcnet/com20020_cs.c | 4 +--- drivers/net/arcnet/com90io.c | 12 +----------- drivers/net/arcnet/com90xx.c | 13 +++---------- drivers/net/arcnet/rfc1051.c | 7 ------- drivers/net/arcnet/rfc1201.c | 8 -------- include/linux/arcdevice.h | 12 ------------ 13 files changed, 13 insertions(+), 93 deletions(-) (limited to 'include') diff --git a/drivers/net/arcnet/arc-rawmode.c b/drivers/net/arcnet/arc-rawmode.c index 49f5819a0367..251a98b0bf78 100644 --- a/drivers/net/arcnet/arc-rawmode.c +++ b/drivers/net/arcnet/arc-rawmode.c @@ -35,7 +35,6 @@ #define VERSION "arcnet: raw mode (`r') encapsulation support loaded.\n" - static void rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length); static int build_header(struct sk_buff *skb, struct net_device *dev, @@ -54,7 +53,6 @@ static struct ArcProto rawmode_proto = .ack_tx = NULL }; - static int __init arcnet_raw_init(void) { int count; @@ -83,7 +81,6 @@ module_exit(arcnet_raw_exit); MODULE_LICENSE("GPL"); - /* packet receiver */ static void rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length) @@ -127,7 +124,6 @@ static void rx(struct net_device *dev, int bufnum, netif_rx(skb); } - /* * Create the ARCnet hard/soft headers for raw mode. * There aren't any soft headers in raw mode - not even the protocol id. @@ -163,7 +159,6 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, return hdr_size; /* success */ } - static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum) { diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index 4644d46b6a5f..e8c15016bb8e 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -36,10 +36,8 @@ #include #include - #define VERSION "arcnet: RIM I (entirely mem-mapped) support\n" - /* Internal function declarations */ static int arcrimi_probe(struct net_device *dev); @@ -78,7 +76,6 @@ static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, int offse #define AINTMASK(msk) writeb((msk), _INTMASK) #define SETCONF() writeb(lp->config, _CONFIG) - /* * We cannot probe for a RIM I card; one reason is I don't know how to reset * them. In fact, we can't even get their node ID automatically. So, we @@ -249,7 +246,6 @@ err_free_irq: return -EIO; } - /* * Do a hardware reset on the card, and set up necessary registers. * @@ -308,15 +304,16 @@ static void arcrimi_copy_to_card(struct net_device *dev, int bufnum, int offset, { struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + 0x800 + bufnum * 512 + offset; + TIME("memcpy_toio", count, memcpy_toio(memaddr, buf, count)); } - static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, int offset, void *buf, int count) { struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + 0x800 + bufnum * 512 + offset; + TIME("memcpy_fromio", count, memcpy_fromio(buf, memaddr, count)); } @@ -374,6 +371,7 @@ static void __exit arc_rimi_exit(void) static int __init arcrimi_setup(char *s) { int ints[8]; + s = get_options(s, 8, ints); if (!ints[0]) return 1; diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index 2a594d1c4b55..bb49753f8203 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -168,7 +168,6 @@ void arcnet_dump_skb(struct net_device *dev, EXPORT_SYMBOL(arcnet_dump_skb); #endif - /* * Dump the contents of an ARCnet buffer */ @@ -206,7 +205,6 @@ static void arcnet_dump_packet(struct net_device *dev, int bufnum, #endif - /* * Unregister a protocol driver from the arc_proto_map. Protocol drivers * are responsible for registering themselves, but the unregister routine @@ -229,7 +227,6 @@ void arcnet_unregister_proto(struct ArcProto *proto) } } - /* * Add a buffer to the queue. Only the interrupt handler is allowed to do * this, unless interrupts are disabled. @@ -254,7 +251,6 @@ static void release_arcbuf(struct net_device *dev, int bufnum) } } - /* * Get a buffer from the queue. If this returns -1, there are no buffers * available. @@ -281,7 +277,6 @@ static int get_arcbuf(struct net_device *dev) } } - BUGLVL(D_DURING) { BUGMSG(D_DURING, "get_arcbuf: got #%d; buffer queue is now: ", buf); for (i = lp->next_buf; i != lp->first_free_buf; i = (i + 1) % 5) @@ -293,7 +288,6 @@ static int get_arcbuf(struct net_device *dev) return buf; } - static int choose_mtu(void) { int count, mtu = 65535; @@ -348,6 +342,7 @@ struct net_device *alloc_arcdev(const char *name) arcdev_setup); if (dev) { struct arcnet_local *lp = netdev_priv(dev); + spin_lock_init(&lp->lock); } @@ -380,7 +375,6 @@ int arcnet_open(struct net_device *dev) BUGMSG2(D_PROTO, "\n"); } - BUGMSG(D_INIT, "arcnet_open: resetting card.\n"); /* try to put the card in a defined state - if it fails the first @@ -437,7 +431,6 @@ int arcnet_open(struct net_device *dev) ACOMMAND(CFLAGScmd | RESETclear); } - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); /* make sure we're ready to receive IRQ's. */ AINTMASK(0); @@ -459,7 +452,6 @@ int arcnet_open(struct net_device *dev) return error; } - /* The inverse routine to arcnet_open - shuts down the card. */ int arcnet_close(struct net_device *dev) { @@ -479,7 +471,6 @@ int arcnet_close(struct net_device *dev) return 0; } - static int arcnet_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len) @@ -498,7 +489,6 @@ static int arcnet_header(struct sk_buff *skb, struct net_device *dev, BUGMSG(D_NORMAL, "arcnet_header: Yikes! skb->len(%d) != len(%d)!\n", skb->len, len); - /* Type is host order - ? */ if (type == ETH_P_ARCNET) { proto = arc_raw_proto; @@ -622,7 +612,6 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, return retval; /* no need to try again */ } - /* * Actually start transmitting a packet that was loaded into a buffer * by prepare_tx. This should _only_ be called by the interrupt handler. @@ -654,7 +643,6 @@ static int go_tx(struct net_device *dev) return 1; } - /* Called by the kernel when transmit times out */ void arcnet_timeout(struct net_device *dev) { @@ -691,7 +679,6 @@ void arcnet_timeout(struct net_device *dev) netif_wake_queue(dev); } - /* * The typical workload of the driver: Handle the network interface * interrupts. Establish which device needs attention, and call the correct @@ -787,7 +774,6 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) didsomething++; } - /* a transmit finished, and we're interested in it. */ if ((status & lp->intmask & TXFREEflag) || lp->timed_out) { lp->intmask &= ~(TXFREEflag | EXCNAKflag); @@ -814,6 +800,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) if (lp->outgoing.proto && lp->outgoing.proto->ack_tx) { int ackstatus; + if (status & TXACKflag) ackstatus = 2; else if (lp->excnak_pending) @@ -838,6 +825,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) /* continue a split packet, if any */ if (lp->outgoing.proto && lp->outgoing.proto->continue_tx) { int txbuf = get_arcbuf(dev); + if (txbuf != -1) { if (lp->outgoing.proto->continue_tx(dev, txbuf)) { /* that was the last segment */ @@ -930,7 +918,6 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) ASTATUS(), boguscount); BUGMSG(D_DURING, "\n"); - AINTMASK(0); udelay(1); AINTMASK(lp->intmask); @@ -939,7 +926,6 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) return retval; } - /* * This is a generic packet receiver that calls arcnet??_rx depending on the * protocol ID found. @@ -1002,7 +988,6 @@ static void arcnet_rx(struct net_device *dev, int bufnum) arc_proto_map[soft->proto]->rx(dev, bufnum, &pkt, length); } - static void null_rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length) { @@ -1011,7 +996,6 @@ static void null_rx(struct net_device *dev, int bufnum, pkthdr->soft.rfc1201.proto, pkthdr->hard.source); } - static int null_build_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, uint8_t daddr) { @@ -1025,7 +1009,6 @@ static int null_build_header(struct sk_buff *skb, struct net_device *dev, return 0; } - /* the "do nothing" prepare_tx function warns that there's nothing to do. */ static int null_prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum) diff --git a/drivers/net/arcnet/capmode.c b/drivers/net/arcnet/capmode.c index 95a6cf07965c..02815ff891f2 100644 --- a/drivers/net/arcnet/capmode.c +++ b/drivers/net/arcnet/capmode.c @@ -90,7 +90,6 @@ static void rx(struct net_device *dev, int bufnum, netif_rx(skb); } - /* * Create the ARCnet hard/soft headers for cap mode. * There aren't any soft headers in cap mode - not even the protocol id. @@ -130,7 +129,6 @@ static int build_header(struct sk_buff *skb, return hdr_size; /* success */ } - static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum) { @@ -138,7 +136,6 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, struct arc_hardware *hard = &pkt->hard; int ofs; - /* hard header is not included in packet length */ length -= ARC_HDR_SIZE; /* And neither is the cookie field */ diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index d8746caf8e7a..c7d3377a45fe 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -43,7 +43,6 @@ #define VERSION "arcnet: COM20020 ISA support (by David Woodhouse et al.)\n" - /* * We cannot (yet) probe for an IO mapped card, although we can check that * it's where we were told it was, and even do autoirq. diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index e0f489a117f1..06621e95bd38 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -42,7 +42,6 @@ #include - #define VERSION "arcnet: COM20020 PCI support\n" /* Module parameters */ @@ -86,7 +85,6 @@ static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *i INIT_LIST_HEAD(&priv->list_dev); - for (i = 0; i < ci->devcount; i++) { struct com20020_pci_channel_map *cm = &ci->chan_map_tbl[i]; struct com20020_dev *card; diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c index cd2a5ca56ce5..c749af6db94e 100644 --- a/drivers/net/arcnet/com20020.c +++ b/drivers/net/arcnet/com20020.c @@ -70,7 +70,6 @@ static void com20020_copy_from_card(struct net_device *dev, int bufnum, TIME("insb", count, insb(_MEMDATA, buf, count)); } - static void com20020_copy_to_card(struct net_device *dev, int bufnum, int offset, void *buf, int count) { @@ -84,7 +83,6 @@ static void com20020_copy_to_card(struct net_device *dev, int bufnum, TIME("outsb", count, outsb(_MEMDATA, buf, count)); } - /* Reset the card and check some basic stuff during the detection stage. */ int com20020_check(struct net_device *dev) { @@ -242,7 +240,6 @@ int com20020_found(struct net_device *dev, int shared) return 0; } - /* * Do a hardware reset on the card, and set up necessary registers. * @@ -295,22 +292,21 @@ static int com20020_reset(struct net_device *dev, int really_reset) return 0; } - static void com20020_setmask(struct net_device *dev, int mask) { u_int ioaddr = dev->base_addr; + BUGMSG(D_DURING, "Setting mask to %x at %x\n", mask, ioaddr); AINTMASK(mask); } - static void com20020_command(struct net_device *dev, int cmd) { u_int ioaddr = dev->base_addr; + ACOMMAND(cmd); } - static int com20020_status(struct net_device *dev) { u_int ioaddr = dev->base_addr; diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c index f68752102379..2eafb298626b 100644 --- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -49,7 +49,6 @@ #define VERSION "arcnet: COM20020 PCMCIA support loaded.\n" - static void regdump(struct net_device *dev) { #ifdef DEBUG @@ -83,8 +82,6 @@ static void regdump(struct net_device *dev) #endif } - - /*====================================================================*/ /* Parameters that can be set with 'insmod' */ @@ -304,6 +301,7 @@ static int com20020_resume(struct pcmcia_device *link) if (link->open) { int ioaddr = dev->base_addr; struct arcnet_local *lp = netdev_priv(dev); + ARCRESET; } diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 23ac9edbe91c..11d2d0b4ccea 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -37,10 +37,8 @@ #include #include - #define VERSION "arcnet: COM90xx IO-mapped mode support (by David Woodhouse et el.)\n" - /* Internal function declarations */ static int com90io_found(struct net_device *dev); @@ -53,7 +51,6 @@ static void com90io_copy_to_card(struct net_device *dev, int bufnum, int offset, static void com90io_copy_from_card(struct net_device *dev, int bufnum, int offset, void *buf, int count); - /* Handy defines for ARCnet specific stuff */ /* The number of low I/O ports used by the card. */ @@ -78,7 +75,6 @@ static void com90io_copy_from_card(struct net_device *dev, int bufnum, int offse #define AINTMASK(msk) outb((msk), _INTMASK) #define SETCONF() outb((lp->config), _CONFIG) - /**************************************************************************** * * * IO-mapped operation routines * @@ -111,7 +107,6 @@ static void put_buffer_byte(struct net_device *dev, unsigned offset, u_char datu #endif - static void get_whole_buffer(struct net_device *dev, unsigned offset, unsigned length, char *dest) { int ioaddr = dev->base_addr; @@ -227,7 +222,6 @@ err_out: return -ENODEV; } - /* Set up the struct net_device associated with this card. Called after * probing succeeds. */ @@ -279,7 +273,6 @@ static int __init com90io_found(struct net_device *dev) return 0; } - /* * Do a hardware reset on the card, and set up necessary registers. * @@ -319,7 +312,6 @@ static int com90io_reset(struct net_device *dev, int really_reset) return 0; } - static void com90io_command(struct net_device *dev, int cmd) { short ioaddr = dev->base_addr; @@ -327,7 +319,6 @@ static void com90io_command(struct net_device *dev, int cmd) ACOMMAND(cmd); } - static int com90io_status(struct net_device *dev) { short ioaddr = dev->base_addr; @@ -335,7 +326,6 @@ static int com90io_status(struct net_device *dev) return ASTATUS(); } - static void com90io_setmask(struct net_device *dev, int mask) { short ioaddr = dev->base_addr; @@ -349,7 +339,6 @@ static void com90io_copy_to_card(struct net_device *dev, int bufnum, int offset, TIME("put_whole_buffer", count, put_whole_buffer(dev, bufnum * 512 + offset, count, buf)); } - static void com90io_copy_from_card(struct net_device *dev, int bufnum, int offset, void *buf, int count) { @@ -369,6 +358,7 @@ MODULE_LICENSE("GPL"); static int __init com90io_setup(char *s) { int ints[4]; + s = get_options(s, 4, ints); if (!ints[0]) return 0; diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index a4c5d5909b13..f0f06a274045 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -35,10 +35,8 @@ #include #include - #define VERSION "arcnet: COM90xx chipset support\n" - /* Define this to speed up the autoprobe by assuming if only one io port and * shmem are left in the list at Stage 5, they must correspond to each * other. @@ -53,7 +51,6 @@ */ #undef FAST_PROBE - /* Internal function declarations */ static int com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem *); static void com90xx_command(struct net_device *dev, int command); @@ -97,7 +94,6 @@ static int numcards; #define ACOMMAND(cmd) outb((cmd), _COMMAND) #define AINTMASK(msk) outb((msk), _INTMASK) - static int com90xx_skip_probe __initdata = 0; /* Module parameters */ @@ -308,6 +304,7 @@ static void __init com90xx_probe(void) numprint = -1; for (port = &ports[0]; port < ports + numports; port++) { int found = 0; + numprint++; numprint %= 8; if (!numprint) { @@ -552,7 +549,6 @@ err_free_dev: return -EIO; } - static void com90xx_command(struct net_device *dev, int cmd) { short ioaddr = dev->base_addr; @@ -560,7 +556,6 @@ static void com90xx_command(struct net_device *dev, int cmd) ACOMMAND(cmd); } - static int com90xx_status(struct net_device *dev) { short ioaddr = dev->base_addr; @@ -568,7 +563,6 @@ static int com90xx_status(struct net_device *dev) return ASTATUS(); } - static void com90xx_setmask(struct net_device *dev, int mask) { short ioaddr = dev->base_addr; @@ -576,7 +570,6 @@ static void com90xx_setmask(struct net_device *dev, int mask) AINTMASK(mask); } - /* * Do a hardware reset on the card, and set up necessary registers. * @@ -625,19 +618,19 @@ static void com90xx_copy_to_card(struct net_device *dev, int bufnum, int offset, { struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + bufnum * 512 + offset; + TIME("memcpy_toio", count, memcpy_toio(memaddr, buf, count)); } - static void com90xx_copy_from_card(struct net_device *dev, int bufnum, int offset, void *buf, int count) { struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + bufnum * 512 + offset; + TIME("memcpy_fromio", count, memcpy_fromio(buf, memaddr, count)); } - MODULE_LICENSE("GPL"); static int __init com90xx_init(void) diff --git a/drivers/net/arcnet/rfc1051.c b/drivers/net/arcnet/rfc1051.c index ae1ded286897..49d35c972bca 100644 --- a/drivers/net/arcnet/rfc1051.c +++ b/drivers/net/arcnet/rfc1051.c @@ -34,7 +34,6 @@ #define VERSION "arcnet: RFC1051 \"simple standard\" (`s') encapsulation support loaded.\n" - static __be16 type_trans(struct sk_buff *skb, struct net_device *dev); static void rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length); @@ -43,7 +42,6 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum); - static struct ArcProto rfc1051_proto = { .suffix = 's', @@ -56,7 +54,6 @@ static struct ArcProto rfc1051_proto = .ack_tx = NULL }; - static int __init arcnet_rfc1051_init(void) { printk(VERSION); @@ -120,7 +117,6 @@ static __be16 type_trans(struct sk_buff *skb, struct net_device *dev) return htons(ETH_P_IP); } - /* packet receiver */ static void rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length) @@ -161,7 +157,6 @@ static void rx(struct net_device *dev, int bufnum, netif_rx(skb); } - /* * Create the ARCnet hard/soft headers for RFC1051. */ @@ -188,7 +183,6 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, return 0; } - /* * Set the source hardware address. * @@ -214,7 +208,6 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, return hdr_size; /* success */ } - static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum) { diff --git a/drivers/net/arcnet/rfc1201.c b/drivers/net/arcnet/rfc1201.c index bf2a8cb3f0e2..15f103a8a9db 100644 --- a/drivers/net/arcnet/rfc1201.c +++ b/drivers/net/arcnet/rfc1201.c @@ -34,7 +34,6 @@ MODULE_LICENSE("GPL"); #define VERSION "arcnet: RFC1201 \"standard\" (`a') encapsulation support loaded.\n" - static __be16 type_trans(struct sk_buff *skb, struct net_device *dev); static void rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length); @@ -56,7 +55,6 @@ static struct ArcProto rfc1201_proto = .ack_tx = NULL }; - static int __init arcnet_rfc1201_init(void) { printk(VERSION); @@ -129,7 +127,6 @@ static __be16 type_trans(struct sk_buff *skb, struct net_device *dev) return htons(ETH_P_IP); } - /* packet receiver */ static void rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length) @@ -369,7 +366,6 @@ static void rx(struct net_device *dev, int bufnum, } } - /* Create the ARCnet hard/soft headers for RFC1201. */ static int build_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, uint8_t daddr) @@ -437,7 +433,6 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, return hdr_size; } - static void load_pkt(struct net_device *dev, struct arc_hardware *hard, struct arc_rfc1201 *soft, int softlen, int bufnum) { @@ -470,7 +465,6 @@ static void load_pkt(struct net_device *dev, struct arc_hardware *hard, lp->lastload_dest = hard->dest; } - static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum) { @@ -478,7 +472,6 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, const int maxsegsize = XMTU - RFC1201_HDR_SIZE; struct Outgoing *out; - BUGMSG(D_DURING, "prepare_tx: txbufs=%d/%d/%d\n", lp->next_tx, lp->cur_tx, bufnum); @@ -506,7 +499,6 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, return 1; /* done */ } - static int continue_tx(struct net_device *dev, int bufnum) { struct arcnet_local *lp = netdev_priv(dev); diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index ccfd1d2f984b..78687885eb81 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -34,7 +34,6 @@ */ #define RECON_THRESHOLD 30 - /* * Define this to the minimum "timeout" value. If a transmit takes longer * than TX_TIMEOUT jiffies, Linux will abort the TX and retry. On a large @@ -44,11 +43,9 @@ */ #define TX_TIMEOUT (HZ * 200 / 1000) - /* Display warnings about the driver being an ALPHA version. */ #undef ALPHA_WARNING - /* * Debugging bitflags: each option can be enabled individually. * @@ -106,7 +103,6 @@ extern int arcnet_debug; call; \ } - /* * Time needed to reset the card - in ms (milliseconds). This works on my * SMC PC100. I can't find a reference that tells me just how long I @@ -182,7 +178,6 @@ extern int arcnet_debug; #define ARC_CAN_10MBIT 2 /* card uses COM20022, supporting 10MBit, but default is 2.5MBit. */ - /* information needed to define an encapsulation driver */ struct ArcProto { char suffix; /* a for RFC1201, e for ether-encap, etc. */ @@ -204,7 +199,6 @@ struct ArcProto { extern struct ArcProto *arc_proto_map[256], *arc_proto_default, *arc_bcast_proto, *arc_raw_proto; - /* * "Incoming" is information needed for each address that could be sending * to us. Mostly for partially-received split packets. @@ -216,7 +210,6 @@ struct Incoming { numpackets; /* number of packets in split */ }; - /* only needed for RFC1201 */ struct Outgoing { struct ArcProto *proto; /* protocol driver that owns this: @@ -230,7 +223,6 @@ struct Outgoing { numsegs; /* number of segments */ }; - struct arcnet_local { uint8_t config, /* current value of CONFIG register */ timeout, /* Extended timeout for COM20020 */ @@ -251,7 +243,6 @@ struct arcnet_local { char *card_name; /* card ident string */ int card_flags; /* special card features */ - /* On preemtive and SMB a lock is needed */ spinlock_t lock; @@ -314,14 +305,11 @@ struct arcnet_local { void __iomem *mem_start; /* pointer to ioremap'ed MMIO */ }; - #define ARCRESET(x) (lp->hw.reset(dev, (x))) #define ACOMMAND(x) (lp->hw.command(dev, (x))) #define ASTATUS() (lp->hw.status(dev)) #define AINTMASK(x) (lp->hw.intmask(dev, (x))) - - #if ARCNET_DEBUG_MAX & D_SKB void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); #else -- cgit v1.2.3 From d77510f3436e0db9b5e72fa8159ce26c3ac88d2d Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:05:53 -0700 Subject: arcnet: Neaten BUGMSG macro defines These macros are actually printk and pr_cont uses with a flag. Add a new BUGLVL_TEST macro which is just the "should use" test and not an odd "if ()" macro to simplify uses in a new patch. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/linux/arcdevice.h | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index 78687885eb81..ad610208fbba 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -78,14 +78,24 @@ #endif extern int arcnet_debug; +#define BUGLVL_TEST(x) ((x) & ARCNET_DEBUG_MAX & arcnet_debug) +#define BUGLVL(x) if (BUGLVL_TEST(x)) + /* macros to simplify debug checking */ -#define BUGLVL(x) if ((ARCNET_DEBUG_MAX) & arcnet_debug & (x)) -#define BUGMSG2(x, msg, args...) do { BUGLVL(x) printk(msg, ## args); } while (0) -#define BUGMSG(x, msg, args...) \ - BUGMSG2(x, "%s%6s: " msg, \ - x == D_NORMAL ? KERN_WARNING \ - : x < D_DURING ? KERN_INFO : KERN_DEBUG, \ - dev->name, ## args) +#define BUGMSG(x, fmt, ...) \ +do { \ + if (BUGLVL_TEST(x)) \ + printk("%s%6s: " fmt, \ + (x) == D_NORMAL ? KERN_WARNING : \ + (x) < D_DURING ? KERN_INFO : KERN_DEBUG, \ + dev->name, ##__VA_ARGS__); \ +} while (0) + +#define BUGMSG2(x, fmt, ...) \ +do { \ + if (BUGLVL_TEST(x)) \ + printk(fmt, ##__VA_ARGS__); \ +} while (0) /* see how long a function call takes to run, expressed in CPU cycles */ #define TIME(name, bytes, call) BUGLVL(D_TIMING) { \ -- cgit v1.2.3 From 72aeea4841c037b9b3abf65859673cbd7b6664a9 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:05:54 -0700 Subject: arcnet: Expand odd BUGLVL macro with if and uses Don't hide what should be obvious. Make the macro a simple test instead of using if and test. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- drivers/net/arcnet/arc-rawmode.c | 3 ++- drivers/net/arcnet/arc-rimi.c | 20 +++++++++------- drivers/net/arcnet/arcnet.c | 29 ++++++++++++----------- drivers/net/arcnet/capmode.c | 9 ++++--- drivers/net/arcnet/com20020-isa.c | 3 ++- drivers/net/arcnet/com20020-pci.c | 3 ++- drivers/net/arcnet/com20020.c | 3 ++- drivers/net/arcnet/com90io.c | 6 +++-- drivers/net/arcnet/com90xx.c | 49 +++++++++++++++++++++++++-------------- drivers/net/arcnet/rfc1051.c | 3 ++- drivers/net/arcnet/rfc1201.c | 6 +++-- include/linux/arcdevice.h | 17 +++++++------- 12 files changed, 93 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/drivers/net/arcnet/arc-rawmode.c b/drivers/net/arcnet/arc-rawmode.c index efdd8e95a2bf..998c8356e576 100644 --- a/drivers/net/arcnet/arc-rawmode.c +++ b/drivers/net/arcnet/arc-rawmode.c @@ -117,7 +117,8 @@ static void rx(struct net_device *dev, int bufnum, pkt->soft.raw + sizeof(pkt->soft), length - sizeof(pkt->soft)); - BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "rx"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, skb, "rx"); skb->protocol = cpu_to_be16(ETH_P_ARCNET); netif_rx(skb); diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index c7ab23e8ec6a..cd47a1b3008c 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -82,18 +82,21 @@ static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, int offse */ static int __init arcrimi_probe(struct net_device *dev) { - BUGLVL(D_NORMAL) printk(VERSION); - BUGLVL(D_NORMAL) printk("E-mail me if you actually test the RIM I driver, please!\n"); - - BUGLVL(D_NORMAL) printk("Given: node %02Xh, shmem %lXh, irq %d\n", - dev->dev_addr[0], dev->mem_start, dev->irq); + if (BUGLVL(D_NORMAL)) { + printk(VERSION); + printk("E-mail me if you actually test the RIM I driver, please!\n"); + printk("Given: node %02Xh, shmem %lXh, irq %d\n", + dev->dev_addr[0], dev->mem_start, dev->irq); + } if (dev->mem_start <= 0 || dev->irq <= 0) { - BUGLVL(D_NORMAL) printk("No autoprobe for RIM I; you must specify the shmem and irq!\n"); + if (BUGLVL(D_NORMAL)) + printk("No autoprobe for RIM I; you must specify the shmem and irq!\n"); return -ENODEV; } if (dev->dev_addr[0] == 0) { - BUGLVL(D_NORMAL) printk("You need to specify your card's station ID!\n"); + if (BUGLVL(D_NORMAL)) + printk("You need to specify your card's station ID!\n"); return -ENODEV; } /* Grab the memory region at mem_start for MIRROR_SIZE bytes. @@ -102,7 +105,8 @@ static int __init arcrimi_probe(struct net_device *dev) * will be taken. */ if (!request_mem_region(dev->mem_start, MIRROR_SIZE, "arcnet (90xx)")) { - BUGLVL(D_NORMAL) printk("Card memory already allocated\n"); + if (BUGLVL(D_NORMAL)) + printk("Card memory already allocated\n"); return -ENODEV; } return arcrimi_found(dev); diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index 605b4a7abecc..7a90b8a45a37 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -117,7 +117,7 @@ static int __init arcnet_init(void) printk("arcnet loaded.\n"); #ifdef ALPHA_WARNING - BUGLVL(D_EXTRA) { + if (BUGLVL(D_EXTRA)) { printk("arcnet: ***\n" "arcnet: * Read arcnet.txt for important release notes!\n" "arcnet: *\n" @@ -132,11 +132,11 @@ static int __init arcnet_init(void) for (count = 0; count < 256; count++) arc_proto_map[count] = arc_proto_default; - BUGLVL(D_DURING) - printk("arcnet: struct sizes: %Zd %Zd %Zd %Zd %Zd\n", - sizeof(struct arc_hardware), sizeof(struct arc_rfc1201), - sizeof(struct arc_rfc1051), sizeof(struct arc_eth_encap), - sizeof(struct archdr)); + if (BUGLVL(D_DURING)) + printk("arcnet: struct sizes: %Zd %Zd %Zd %Zd %Zd\n", + sizeof(struct arc_hardware), sizeof(struct arc_rfc1201), + sizeof(struct arc_rfc1051), sizeof(struct arc_eth_encap), + sizeof(struct archdr)); return 0; } @@ -235,7 +235,7 @@ static void release_arcbuf(struct net_device *dev, int bufnum) lp->buf_queue[lp->first_free_buf++] = bufnum; lp->first_free_buf %= 5; - BUGLVL(D_DURING) { + if (BUGLVL(D_DURING)) { BUGMSG(D_DURING, "release_arcbuf: freed #%d; buffer queue is now: ", bufnum); for (i = lp->next_buf; i != lp->first_free_buf; i = (i + 1) % 5) @@ -268,7 +268,7 @@ static int get_arcbuf(struct net_device *dev) } } - BUGLVL(D_DURING) { + if (BUGLVL(D_DURING)) { BUGMSG(D_DURING, "get_arcbuf: got #%d; buffer queue is now: ", buf); for (i = lp->next_buf; i != lp->first_free_buf; i = (i + 1) % 5) BUGMSG2(D_DURING, "#%d ", lp->buf_queue[i]); @@ -356,7 +356,7 @@ int arcnet_open(struct net_device *dev) if (!try_module_get(lp->hw.owner)) return -ENODEV; - BUGLVL(D_PROTO) { + if (BUGLVL(D_PROTO)) { BUGMSG(D_PROTO, "protocol map (default is '%c'): ", arc_proto_default->suffix); for (count = 0; count < 256; count++) @@ -531,7 +531,8 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, BUGMSG(D_SKB_SIZE, "skb: transmitting %d bytes to %02X\n", skb->len, pkt->hard.dest); - BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "tx"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, skb, "tx"); /* fits in one packet? */ if (skb->len - ARC_HDR_SIZE > XMTU && !proto->continue_tx) { @@ -609,7 +610,8 @@ static int go_tx(struct net_device *dev) if (lp->cur_tx != -1 || lp->next_tx == -1) return 0; - BUGLVL(D_TX) arcnet_dump_packet(dev, lp->next_tx, "go_tx", 0); + if (BUGLVL(D_TX)) + arcnet_dump_packet(dev, lp->next_tx, "go_tx", 0); lp->cur_tx = lp->next_tx; lp->next_tx = -1; @@ -822,7 +824,8 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) } /* now process the received packet, if any */ if (recbuf != -1) { - BUGLVL(D_RX) arcnet_dump_packet(dev, recbuf, "rx irq", 0); + if (BUGLVL(D_RX)) + arcnet_dump_packet(dev, recbuf, "rx irq", 0); arcnet_rx(dev, recbuf); release_arcbuf(dev, recbuf); @@ -938,7 +941,7 @@ static void arcnet_rx(struct net_device *dev, int bufnum) /* call the right receiver for the protocol */ if (arc_proto_map[soft->proto]->is_ip) { - BUGLVL(D_PROTO) { + if (BUGLVL(D_PROTO)) { struct ArcProto *oldp = arc_proto_map[lp->default_proto[pkt.hard.source]], *newp = arc_proto_map[soft->proto]; diff --git a/drivers/net/arcnet/capmode.c b/drivers/net/arcnet/capmode.c index 8391324f684b..e7ec907f4680 100644 --- a/drivers/net/arcnet/capmode.c +++ b/drivers/net/arcnet/capmode.c @@ -84,7 +84,8 @@ static void rx(struct net_device *dev, int bufnum, + sizeof(int), length - sizeof(pkt->soft)); - BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "rx"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, skb, "rx"); skb->protocol = cpu_to_be16(ETH_P_ARCNET); netif_rx(skb); @@ -190,7 +191,8 @@ static int ack_tx(struct net_device *dev, int acked) BUGMSG(D_DURING, "capmode: ack_tx: protocol: %x: result: %d\n", lp->outgoing.skb->protocol, acked); - BUGLVL(D_SKB) arcnet_dump_skb(dev, lp->outgoing.skb, "ack_tx"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, lp->outgoing.skb, "ack_tx"); /* Now alloc a skb to send back up through the layers: */ ackskb = alloc_skb(length + ARC_HDR_SIZE, GFP_ATOMIC); @@ -216,7 +218,8 @@ static int ack_tx(struct net_device *dev, int acked) ackskb->protocol = cpu_to_be16(ETH_P_ARCNET); - BUGLVL(D_SKB) arcnet_dump_skb(dev, ackskb, "ack_tx_recv"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, ackskb, "ack_tx_recv"); netif_rx(ackskb); free_outskb: diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index 6e38a19d7210..af87c7482478 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -53,7 +53,8 @@ static int __init com20020isa_probe(struct net_device *dev) struct arcnet_local *lp = netdev_priv(dev); int err; - BUGLVL(D_NORMAL) printk(VERSION); + if (BUGLVL(D_NORMAL)) + printk(VERSION); ioaddr = dev->base_addr; if (!ioaddr) { diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 72334b59aa26..c8184de4480d 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -402,7 +402,8 @@ static struct pci_driver com20020pci_driver = { static int __init com20020pci_init(void) { - BUGLVL(D_NORMAL) printk(VERSION); + if (BUGLVL(D_NORMAL)) + printk(VERSION); return pci_register_driver(&com20020pci_driver); } diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c index 63697272f146..3170e8ebb7fa 100644 --- a/drivers/net/arcnet/com20020.c +++ b/drivers/net/arcnet/com20020.c @@ -365,7 +365,8 @@ MODULE_LICENSE("GPL"); static int __init com20020_module_init(void) { - BUGLVL(D_NORMAL) printk(VERSION); + if (BUGLVL(D_NORMAL)) + printk(VERSION); return 0; } diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 6ec36f9975ba..33a8531e90c7 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -145,8 +145,10 @@ static int __init com90io_probe(struct net_device *dev) int ioaddr = dev->base_addr, status; unsigned long airqmask; - BUGLVL(D_NORMAL) printk(VERSION); - BUGLVL(D_NORMAL) printk("E-mail me if you actually test this driver, please!\n"); + if (BUGLVL(D_NORMAL)) { + printk(VERSION); + printk("E-mail me if you actually test this driver, please!\n"); + } if (!ioaddr) { BUGMSG(D_NORMAL, "No autoprobe for IO mapped cards; you must specify the base address!\n"); diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index 4781cd696dd1..b5e1c1904f13 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -133,7 +133,8 @@ static void __init com90xx_probe(void) return; } - BUGLVL(D_NORMAL) printk(VERSION); + if (BUGLVL(D_NORMAL)) + printk(VERSION); /* set up the arrays where we'll store the possible probe addresses */ numports = numshmems = 0; @@ -166,14 +167,16 @@ static void __init com90xx_probe(void) if (!request_region(*port, ARCNET_TOTAL_SIZE, "arcnet (90xx)")) { BUGMSG2(D_INIT_REASONS, "(request_region)\n"); BUGMSG2(D_INIT_REASONS, "S1: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; *port-- = ports[--numports]; continue; } if (ASTATUS() == 0xFF) { BUGMSG2(D_INIT_REASONS, "(empty)\n"); BUGMSG2(D_INIT_REASONS, "S1: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; release_region(*port, ARCNET_TOTAL_SIZE); *port-- = ports[--numports]; continue; @@ -182,7 +185,8 @@ static void __init com90xx_probe(void) BUGMSG2(D_INIT_REASONS, "\n"); BUGMSG2(D_INIT_REASONS, "S1: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; } BUGMSG2(D_INIT, "\n"); @@ -227,21 +231,24 @@ static void __init com90xx_probe(void) if (!request_mem_region(*p, MIRROR_SIZE, "arcnet (90xx)")) { BUGMSG2(D_INIT_REASONS, "(request_mem_region)\n"); BUGMSG2(D_INIT_REASONS, "Stage 3: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; goto out; } base = ioremap(*p, MIRROR_SIZE); if (!base) { BUGMSG2(D_INIT_REASONS, "(ioremap)\n"); BUGMSG2(D_INIT_REASONS, "Stage 3: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; goto out1; } if (readb(base) != TESTvalue) { BUGMSG2(D_INIT_REASONS, "(%02Xh != %02Xh)\n", readb(base), TESTvalue); BUGMSG2(D_INIT_REASONS, "S3: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; goto out2; } /* By writing 0x42 to the TESTvalue location, we also make @@ -257,7 +264,8 @@ static void __init com90xx_probe(void) } BUGMSG2(D_INIT_REASONS, "\n"); BUGMSG2(D_INIT_REASONS, "S3: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; iomem[index] = base; continue; out2: @@ -319,7 +327,8 @@ static void __init com90xx_probe(void) != (NORXflag | RECONflag | TXFREEflag | RESETflag)) { BUGMSG2(D_INIT_REASONS, "(status=%Xh)\n", status); BUGMSG2(D_INIT_REASONS, "S5: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; release_region(*port, ARCNET_TOTAL_SIZE); *port-- = ports[--numports]; continue; @@ -330,7 +339,8 @@ static void __init com90xx_probe(void) BUGMSG2(D_INIT_REASONS, " (eternal reset, status=%Xh)\n", status); BUGMSG2(D_INIT_REASONS, "S5: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; release_region(*port, ARCNET_TOTAL_SIZE); *port-- = ports[--numports]; continue; @@ -352,7 +362,8 @@ static void __init com90xx_probe(void) if (airq <= 0) { BUGMSG2(D_INIT_REASONS, "(airq=%d)\n", airq); BUGMSG2(D_INIT_REASONS, "S5: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; release_region(*port, ARCNET_TOTAL_SIZE); *port-- = ports[--numports]; continue; @@ -406,16 +417,20 @@ static void __init com90xx_probe(void) } if (openparen) { - BUGLVL(D_INIT) printk("no matching shmem)\n"); - BUGLVL(D_INIT_REASONS) printk("S5: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (BUGLVL(D_INIT)) + printk("no matching shmem)\n"); + if (BUGLVL(D_INIT_REASONS)) { + printk("S5: "); + numprint = 0; + } } if (!found) release_region(*port, ARCNET_TOTAL_SIZE); *port-- = ports[--numports]; } - BUGLVL(D_INIT_REASONS) printk("\n"); + if (BUGLVL(D_INIT_REASONS)) + printk("\n"); /* Now put back TESTvalue on all leftover shmems. */ for (index = 0; index < numshmems; index++) { @@ -603,8 +618,8 @@ static int com90xx_reset(struct net_device *dev, int really_reset) ACOMMAND(CONFIGcmd | EXTconf); /* clean out all the memory to make debugging make more sense :) */ - BUGLVL(D_DURING) - memset_io(lp->mem_start, 0x42, 2048); + if (BUGLVL(D_DURING)) + memset_io(lp->mem_start, 0x42, 2048); /* done! return success. */ return 0; diff --git a/drivers/net/arcnet/rfc1051.c b/drivers/net/arcnet/rfc1051.c index e78b76535acc..824d71fcfd53 100644 --- a/drivers/net/arcnet/rfc1051.c +++ b/drivers/net/arcnet/rfc1051.c @@ -149,7 +149,8 @@ static void rx(struct net_device *dev, int bufnum, pkt->soft.raw + sizeof(pkt->soft), length - sizeof(pkt->soft)); - BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "rx"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, skb, "rx"); skb->protocol = type_trans(skb, dev); netif_rx(skb); diff --git a/drivers/net/arcnet/rfc1201.c b/drivers/net/arcnet/rfc1201.c index 4ebfbcbe5de3..d052976ebdfa 100644 --- a/drivers/net/arcnet/rfc1201.c +++ b/drivers/net/arcnet/rfc1201.c @@ -221,7 +221,8 @@ static void rx(struct net_device *dev, int bufnum, dev->stats.rx_crc_errors++; } } - BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "rx"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, skb, "rx"); skb->protocol = type_trans(skb, dev); netif_rx(skb); @@ -353,7 +354,8 @@ static void rx(struct net_device *dev, int bufnum, skb->len, pkt->hard.source); BUGMSG(D_SKB_SIZE, "skb: received %d bytes from %02X (split)\n", skb->len, pkt->hard.source); - BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "rx"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, skb, "rx"); skb->protocol = type_trans(skb, dev); netif_rx(skb); diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index ad610208fbba..f07c66383b88 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -78,13 +78,12 @@ #endif extern int arcnet_debug; -#define BUGLVL_TEST(x) ((x) & ARCNET_DEBUG_MAX & arcnet_debug) -#define BUGLVL(x) if (BUGLVL_TEST(x)) +#define BUGLVL(x) ((x) & ARCNET_DEBUG_MAX & arcnet_debug) /* macros to simplify debug checking */ #define BUGMSG(x, fmt, ...) \ do { \ - if (BUGLVL_TEST(x)) \ + if (BUGLVL(x)) \ printk("%s%6s: " fmt, \ (x) == D_NORMAL ? KERN_WARNING : \ (x) < D_DURING ? KERN_INFO : KERN_DEBUG, \ @@ -93,12 +92,14 @@ do { \ #define BUGMSG2(x, fmt, ...) \ do { \ - if (BUGLVL_TEST(x)) \ + if (BUGLVL(x)) \ printk(fmt, ##__VA_ARGS__); \ } while (0) /* see how long a function call takes to run, expressed in CPU cycles */ -#define TIME(name, bytes, call) BUGLVL(D_TIMING) { \ +#define TIME(name, bytes, call) \ +do { \ + if (BUGLVL(D_TIMING)) { \ unsigned long _x, _y; \ _x = get_cycles(); \ call; \ @@ -108,10 +109,10 @@ do { \ "%lu Kbytes/100Mcycle\n", \ name, bytes, _y - _x, \ 100000000 / 1024 * bytes / (_y - _x + 1)); \ - } \ - else { \ + } else { \ call; \ - } + } \ +} while (0) /* * Time needed to reset the card - in ms (milliseconds). This works on my -- cgit v1.2.3 From a34c0932c3b2f28542825ffc5280d562c49ad42d Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:05:55 -0700 Subject: arcnet: Convert BUGMSG and BUGMSG2 to arc_prink and arc_cont These macros don't actually represent BUG uses but are more commonly used as logging macros, so use a more kernel style macro. Convert the BUGMSG from a netdev_ like use to actually use netdev_. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- drivers/net/arcnet/arc-rawmode.c | 16 +-- drivers/net/arcnet/arc-rimi.c | 24 +++-- drivers/net/arcnet/arcnet.c | 212 ++++++++++++++++++++------------------ drivers/net/arcnet/capmode.c | 35 ++++--- drivers/net/arcnet/com20020-isa.c | 15 +-- drivers/net/arcnet/com20020-pci.c | 2 +- drivers/net/arcnet/com20020.c | 64 ++++++------ drivers/net/arcnet/com90io.c | 43 ++++---- drivers/net/arcnet/com90xx.c | 119 ++++++++++----------- drivers/net/arcnet/rfc1051.c | 16 +-- drivers/net/arcnet/rfc1201.c | 104 ++++++++++--------- include/linux/arcdevice.h | 32 +++--- 12 files changed, 355 insertions(+), 327 deletions(-) (limited to 'include') diff --git a/drivers/net/arcnet/arc-rawmode.c b/drivers/net/arcnet/arc-rawmode.c index 998c8356e576..034c8988f987 100644 --- a/drivers/net/arcnet/arc-rawmode.c +++ b/drivers/net/arcnet/arc-rawmode.c @@ -89,7 +89,7 @@ static void rx(struct net_device *dev, int bufnum, struct archdr *pkt = pkthdr; int ofs; - BUGMSG(D_DURING, "it's a raw packet (length=%d)\n", length); + arc_printk(D_DURING, dev, "it's a raw packet (length=%d)\n", length); if (length > MTU) ofs = 512 - length; @@ -98,7 +98,7 @@ static void rx(struct net_device *dev, int bufnum, skb = alloc_skb(length + ARC_HDR_SIZE, GFP_ATOMIC); if (skb == NULL) { - BUGMSG(D_NORMAL, "Memory squeeze, dropping packet.\n"); + arc_printk(D_NORMAL, dev, "Memory squeeze, dropping packet\n"); dev->stats.rx_dropped++; return; } @@ -163,15 +163,15 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, struct arc_hardware *hard = &pkt->hard; int ofs; - BUGMSG(D_DURING, "prepare_tx: txbufs=%d/%d/%d\n", - lp->next_tx, lp->cur_tx, bufnum); + arc_printk(D_DURING, dev, "prepare_tx: txbufs=%d/%d/%d\n", + lp->next_tx, lp->cur_tx, bufnum); length -= ARC_HDR_SIZE; /* hard header is not included in packet length */ if (length > XMTU) { /* should never happen! other people already check for this. */ - BUGMSG(D_NORMAL, "Bug! prepare_tx with size %d (> %d)\n", - length, XMTU); + arc_printk(D_NORMAL, dev, "Bug! prepare_tx with size %d (> %d)\n", + length, XMTU); length = XMTU; } if (length >= MinTU) { @@ -184,8 +184,8 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, hard->offset[0] = ofs = 256 - length; } - BUGMSG(D_DURING, "prepare_tx: length=%d ofs=%d\n", - length, ofs); + arc_printk(D_DURING, dev, "prepare_tx: length=%d ofs=%d\n", + length, ofs); lp->hw.copy_to_card(dev, bufnum, 0, hard, ARC_HDR_SIZE); lp->hw.copy_to_card(dev, bufnum, ofs, &pkt->soft, length); diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index cd47a1b3008c..25f84b7437f3 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -147,7 +147,7 @@ static int __init arcrimi_found(struct net_device *dev) p = ioremap(dev->mem_start, MIRROR_SIZE); if (!p) { release_mem_region(dev->mem_start, MIRROR_SIZE); - BUGMSG(D_NORMAL, "Can't ioremap\n"); + arc_printk(D_NORMAL, dev, "Can't ioremap\n"); return -ENODEV; } @@ -155,7 +155,7 @@ static int __init arcrimi_found(struct net_device *dev) if (request_irq(dev->irq, arcnet_interrupt, 0, "arcnet (RIM I)", dev)) { iounmap(p); release_mem_region(dev->mem_start, MIRROR_SIZE); - BUGMSG(D_NORMAL, "Can't get IRQ %d!\n", dev->irq); + arc_printk(D_NORMAL, dev, "Can't get IRQ %d!\n", dev->irq); return -ENODEV; } @@ -210,23 +210,24 @@ static int __init arcrimi_found(struct net_device *dev) if (!request_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1, "arcnet (90xx)")) { - BUGMSG(D_NORMAL, "Card memory already allocated\n"); + arc_printk(D_NORMAL, dev, "Card memory already allocated\n"); goto err_free_irq; } lp->mem_start = ioremap(dev->mem_start, dev->mem_end - dev->mem_start + 1); if (!lp->mem_start) { - BUGMSG(D_NORMAL, "Can't remap device memory!\n"); + arc_printk(D_NORMAL, dev, "Can't remap device memory!\n"); goto err_release_mem; } /* get and check the station ID from offset 1 in shmem */ dev->dev_addr[0] = readb(lp->mem_start + 1); - BUGMSG(D_NORMAL, "ARCnet RIM I: station %02Xh found at IRQ %d, ShMem %lXh (%ld*%d bytes)\n", - dev->dev_addr[0], - dev->irq, dev->mem_start, - (dev->mem_end - dev->mem_start + 1) / mirror_size, mirror_size); + arc_printk(D_NORMAL, dev, "ARCnet RIM I: station %02Xh found at IRQ %d, ShMem %lXh (%ld*%d bytes)\n", + dev->dev_addr[0], + dev->irq, dev->mem_start, + (dev->mem_end - dev->mem_start + 1) / mirror_size, + mirror_size); err = register_netdev(dev); if (err) @@ -255,7 +256,8 @@ static int arcrimi_reset(struct net_device *dev, int really_reset) struct arcnet_local *lp = netdev_priv(dev); void __iomem *ioaddr = lp->mem_start + 0x800; - BUGMSG(D_INIT, "Resetting %s (status=%02Xh)\n", dev->name, ASTATUS()); + arc_printk(D_INIT, dev, "Resetting %s (status=%02Xh)\n", + dev->name, ASTATUS()); if (really_reset) { writeb(TESTvalue, ioaddr - 0x800); /* fake reset */ @@ -301,7 +303,7 @@ static void arcrimi_copy_to_card(struct net_device *dev, int bufnum, int offset, struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + 0x800 + bufnum * 512 + offset; - TIME("memcpy_toio", count, memcpy_toio(memaddr, buf, count)); + TIME(dev, "memcpy_toio", count, memcpy_toio(memaddr, buf, count)); } static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, int offset, @@ -310,7 +312,7 @@ static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, int offse struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + 0x800 + bufnum * 512 + offset; - TIME("memcpy_fromio", count, memcpy_fromio(buf, memaddr, count)); + TIME(dev, "memcpy_fromio", count, memcpy_fromio(buf, memaddr, count)); } static int node; diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index 7a90b8a45a37..2aab7e2f7e4a 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -236,11 +236,11 @@ static void release_arcbuf(struct net_device *dev, int bufnum) lp->first_free_buf %= 5; if (BUGLVL(D_DURING)) { - BUGMSG(D_DURING, "release_arcbuf: freed #%d; buffer queue is now: ", - bufnum); + arc_printk(D_DURING, dev, "release_arcbuf: freed #%d; buffer queue is now: ", + bufnum); for (i = lp->next_buf; i != lp->first_free_buf; i = (i + 1) % 5) - BUGMSG2(D_DURING, "#%d ", lp->buf_queue[i]); - BUGMSG2(D_DURING, "\n"); + arc_cont(D_DURING, "#%d ", lp->buf_queue[i]); + arc_cont(D_DURING, "\n"); } } @@ -254,14 +254,14 @@ static int get_arcbuf(struct net_device *dev) if (!atomic_dec_and_test(&lp->buf_lock)) { /* already in this function */ - BUGMSG(D_NORMAL, "get_arcbuf: overlap (%d)!\n", - lp->buf_lock.counter); + arc_printk(D_NORMAL, dev, "get_arcbuf: overlap (%d)!\n", + lp->buf_lock.counter); } else { /* we can continue */ if (lp->next_buf >= 5) lp->next_buf -= 5; if (lp->next_buf == lp->first_free_buf) { - BUGMSG(D_NORMAL, "get_arcbuf: BUG: no buffers are available??\n"); + arc_printk(D_NORMAL, dev, "get_arcbuf: BUG: no buffers are available??\n"); } else { buf = lp->buf_queue[lp->next_buf++]; lp->next_buf %= 5; @@ -269,10 +269,11 @@ static int get_arcbuf(struct net_device *dev) } if (BUGLVL(D_DURING)) { - BUGMSG(D_DURING, "get_arcbuf: got #%d; buffer queue is now: ", buf); + arc_printk(D_DURING, dev, "get_arcbuf: got #%d; buffer queue is now: ", + buf); for (i = lp->next_buf; i != lp->first_free_buf; i = (i + 1) % 5) - BUGMSG2(D_DURING, "#%d ", lp->buf_queue[i]); - BUGMSG2(D_DURING, "\n"); + arc_cont(D_DURING, "#%d ", lp->buf_queue[i]); + arc_cont(D_DURING, "\n"); } atomic_inc(&lp->buf_lock); @@ -351,20 +352,20 @@ int arcnet_open(struct net_device *dev) struct arcnet_local *lp = netdev_priv(dev); int count, newmtu, error; - BUGMSG(D_INIT, "opened."); + arc_printk(D_INIT, dev, "opened."); if (!try_module_get(lp->hw.owner)) return -ENODEV; if (BUGLVL(D_PROTO)) { - BUGMSG(D_PROTO, "protocol map (default is '%c'): ", - arc_proto_default->suffix); + arc_printk(D_PROTO, dev, "protocol map (default is '%c'): ", + arc_proto_default->suffix); for (count = 0; count < 256; count++) - BUGMSG2(D_PROTO, "%c", arc_proto_map[count]->suffix); - BUGMSG2(D_PROTO, "\n"); + arc_cont(D_PROTO, "%c", arc_proto_map[count]->suffix); + arc_cont(D_PROTO, "\n"); } - BUGMSG(D_INIT, "arcnet_open: resetting card.\n"); + arc_printk(D_INIT, dev, "arcnet_open: resetting card.\n"); /* try to put the card in a defined state - if it fails the first * time, actually reset it. @@ -377,7 +378,7 @@ int arcnet_open(struct net_device *dev) if (newmtu < dev->mtu) dev->mtu = newmtu; - BUGMSG(D_INIT, "arcnet_open: mtu: %d.\n", dev->mtu); + arc_printk(D_INIT, dev, "arcnet_open: mtu: %d.\n", dev->mtu); /* autodetect the encapsulation for each host. */ memset(lp->default_proto, 0, sizeof(lp->default_proto)); @@ -408,27 +409,28 @@ int arcnet_open(struct net_device *dev) lp->hw.open(dev); if (dev->dev_addr[0] == 0) - BUGMSG(D_NORMAL, "WARNING! Station address 00 is reserved for broadcasts!\n"); + arc_printk(D_NORMAL, dev, "WARNING! Station address 00 is reserved for broadcasts!\n"); else if (dev->dev_addr[0] == 255) - BUGMSG(D_NORMAL, "WARNING! Station address FF may confuse DOS networking programs!\n"); + arc_printk(D_NORMAL, dev, "WARNING! Station address FF may confuse DOS networking programs!\n"); - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); if (ASTATUS() & RESETflag) { - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", + __FILE__, __LINE__, __func__); ACOMMAND(CFLAGScmd | RESETclear); } - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); /* make sure we're ready to receive IRQ's. */ AINTMASK(0); udelay(1); /* give it time to set the mask before * we reset it again. (may not even be * necessary) */ - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); lp->intmask = NORXflag | RECONflag; AINTMASK(lp->intmask); - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); netif_start_queue(dev); @@ -466,20 +468,21 @@ static int arcnet_header(struct sk_buff *skb, struct net_device *dev, uint8_t _daddr, proto_num; struct ArcProto *proto; - BUGMSG(D_DURING, - "create header from %d to %d; protocol %d (%Xh); size %u.\n", - saddr ? *(uint8_t *)saddr : -1, - daddr ? *(uint8_t *)daddr : -1, - type, type, len); + arc_printk(D_DURING, dev, + "create header from %d to %d; protocol %d (%Xh); size %u.\n", + saddr ? *(uint8_t *)saddr : -1, + daddr ? *(uint8_t *)daddr : -1, + type, type, len); if (skb->len != 0 && len != skb->len) - BUGMSG(D_NORMAL, "arcnet_header: Yikes! skb->len(%d) != len(%d)!\n", - skb->len, len); + arc_printk(D_NORMAL, dev, "arcnet_header: Yikes! skb->len(%d) != len(%d)!\n", + skb->len, len); /* Type is host order - ? */ if (type == ETH_P_ARCNET) { proto = arc_raw_proto; - BUGMSG(D_DEBUG, "arc_raw_proto used. proto='%c'\n", proto->suffix); + arc_printk(D_DEBUG, dev, "arc_raw_proto used. proto='%c'\n", + proto->suffix); _daddr = daddr ? *(uint8_t *)daddr : 0; } else if (!daddr) { /* if the dest addr isn't provided, we can't choose an @@ -490,19 +493,19 @@ static int arcnet_header(struct sk_buff *skb, struct net_device *dev, *(uint16_t *)skb_push(skb, 2) = type; /* XXX: Why not use skb->mac_len? */ if (skb->network_header - skb->mac_header != 2) - BUGMSG(D_NORMAL, "arcnet_header: Yikes! diff (%d) is not 2!\n", - (int)(skb->network_header - skb->mac_header)); + arc_printk(D_NORMAL, dev, "arcnet_header: Yikes! diff (%u) is not 2!\n", + skb->network_header - skb->mac_header); return -2; /* return error -- can't transmit yet! */ } else { /* otherwise, we can just add the header as usual. */ _daddr = *(uint8_t *)daddr; proto_num = lp->default_proto[_daddr]; proto = arc_proto_map[proto_num]; - BUGMSG(D_DURING, "building header for %02Xh using protocol '%c'\n", - proto_num, proto->suffix); + arc_printk(D_DURING, dev, "building header for %02Xh using protocol '%c'\n", + proto_num, proto->suffix); if (proto == &arc_proto_null && arc_bcast_proto != proto) { - BUGMSG(D_DURING, "actually, let's use '%c' instead.\n", - arc_bcast_proto->suffix); + arc_printk(D_DURING, dev, "actually, let's use '%c' instead.\n", + arc_bcast_proto->suffix); proto = arc_bcast_proto; } } @@ -521,22 +524,22 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, unsigned long flags; int freeskb, retval; - BUGMSG(D_DURING, - "transmit requested (status=%Xh, txbufs=%d/%d, len=%d, protocol %x)\n", - ASTATUS(), lp->cur_tx, lp->next_tx, skb->len, skb->protocol); + arc_printk(D_DURING, dev, + "transmit requested (status=%Xh, txbufs=%d/%d, len=%d, protocol %x)\n", + ASTATUS(), lp->cur_tx, lp->next_tx, skb->len, skb->protocol); pkt = (struct archdr *)skb->data; soft = &pkt->soft.rfc1201; proto = arc_proto_map[soft->proto]; - BUGMSG(D_SKB_SIZE, "skb: transmitting %d bytes to %02X\n", - skb->len, pkt->hard.dest); + arc_printk(D_SKB_SIZE, dev, "skb: transmitting %d bytes to %02X\n", + skb->len, pkt->hard.dest); if (BUGLVL(D_SKB)) arcnet_dump_skb(dev, skb, "tx"); /* fits in one packet? */ if (skb->len - ARC_HDR_SIZE > XMTU && !proto->continue_tx) { - BUGMSG(D_NORMAL, "fixme: packet too large: compensating badly!\n"); + arc_printk(D_NORMAL, dev, "fixme: packet too large: compensating badly!\n"); dev_kfree_skb(skb); return NETDEV_TX_OK; /* don't try again */ } @@ -569,9 +572,9 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, if (proto->continue_tx && proto->continue_tx(dev, txbuf)) { - BUGMSG(D_NORMAL, - "bug! continue_tx finished the first time! (proto='%c')\n", - proto->suffix); + arc_printk(D_NORMAL, dev, + "bug! continue_tx finished the first time! (proto='%c')\n", + proto->suffix); } } retval = NETDEV_TX_OK; @@ -581,14 +584,16 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, freeskb = 0; } - BUGMSG(D_DEBUG, "%s: %d: %s, status: %x\n", __FILE__, __LINE__, __func__, ASTATUS()); + arc_printk(D_DEBUG, dev, "%s: %d: %s, status: %x\n", + __FILE__, __LINE__, __func__, ASTATUS()); /* make sure we didn't ignore a TX IRQ while we were in here */ AINTMASK(0); - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); lp->intmask |= TXFREEflag | EXCNAKflag; AINTMASK(lp->intmask); - BUGMSG(D_DEBUG, "%s: %d: %s, status: %x\n", __FILE__, __LINE__, __func__, ASTATUS()); + arc_printk(D_DEBUG, dev, "%s: %d: %s, status: %x\n", + __FILE__, __LINE__, __func__, ASTATUS()); spin_unlock_irqrestore(&lp->lock, flags); if (freeskb) @@ -604,8 +609,8 @@ static int go_tx(struct net_device *dev) { struct arcnet_local *lp = netdev_priv(dev); - BUGMSG(D_DURING, "go_tx: status=%Xh, intmask=%Xh, next_tx=%d, cur_tx=%d\n", - ASTATUS(), lp->intmask, lp->next_tx, lp->cur_tx); + arc_printk(D_DURING, dev, "go_tx: status=%Xh, intmask=%Xh, next_tx=%d, cur_tx=%d\n", + ASTATUS(), lp->intmask, lp->next_tx, lp->cur_tx); if (lp->cur_tx != -1 || lp->next_tx == -1) return 0; @@ -655,8 +660,8 @@ void arcnet_timeout(struct net_device *dev) spin_unlock_irqrestore(&lp->lock, flags); if (time_after(jiffies, lp->last_timeout + 10 * HZ)) { - BUGMSG(D_EXTRA, "tx timed out%s (status=%Xh, intmask=%Xh, dest=%02Xh)\n", - msg, status, lp->intmask, lp->lasttrans_dest); + arc_printk(D_EXTRA, dev, "tx timed out%s (status=%Xh, intmask=%Xh, dest=%02Xh)\n", + msg, status, lp->intmask, lp->lasttrans_dest); lp->last_timeout = jiffies; } @@ -675,9 +680,9 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) int recbuf, status, diagstatus, didsomething, boguscount; int retval = IRQ_NONE; - BUGMSG(D_DURING, "\n"); + arc_printk(D_DURING, dev, "\n"); - BUGMSG(D_DURING, "in arcnet_interrupt\n"); + arc_printk(D_DURING, dev, "in arcnet_interrupt\n"); lp = netdev_priv(dev); BUG_ON(!lp); @@ -695,16 +700,16 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) return retval; } - BUGMSG(D_DURING, "in arcnet_inthandler (status=%Xh, intmask=%Xh)\n", - ASTATUS(), lp->intmask); + arc_printk(D_DURING, dev, "in arcnet_inthandler (status=%Xh, intmask=%Xh)\n", + ASTATUS(), lp->intmask); boguscount = 5; do { status = ASTATUS(); diagstatus = (status >> 8) & 0xFF; - BUGMSG(D_DEBUG, "%s: %d: %s: status=%x\n", - __FILE__, __LINE__, __func__, status); + arc_printk(D_DEBUG, dev, "%s: %d: %s: status=%x\n", + __FILE__, __LINE__, __func__, status); didsomething = 0; /* RESET flag was enabled - card is resetting and if RX is @@ -714,7 +719,8 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) * Clear it out and start over. */ if (status & RESETflag) { - BUGMSG(D_NORMAL, "spurious reset (status=%Xh)\n", status); + arc_printk(D_NORMAL, dev, "spurious reset (status=%Xh)\n", + status); arcnet_close(dev); arcnet_open(dev); @@ -732,21 +738,21 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) recbuf = -1; if (status & lp->intmask & NORXflag) { recbuf = lp->cur_rx; - BUGMSG(D_DURING, "Buffer #%d: receive irq (status=%Xh)\n", - recbuf, status); + arc_printk(D_DURING, dev, "Buffer #%d: receive irq (status=%Xh)\n", + recbuf, status); lp->cur_rx = get_arcbuf(dev); if (lp->cur_rx != -1) { - BUGMSG(D_DURING, "enabling receive to buffer #%d\n", - lp->cur_rx); + arc_printk(D_DURING, dev, "enabling receive to buffer #%d\n", + lp->cur_rx); ACOMMAND(RXcmd | (lp->cur_rx << 3) | RXbcasts); } didsomething++; } if ((diagstatus & EXCNAKflag)) { - BUGMSG(D_DURING, "EXCNAK IRQ (diagstat=%Xh)\n", - diagstatus); + arc_printk(D_DURING, dev, "EXCNAK IRQ (diagstat=%Xh)\n", + diagstatus); ACOMMAND(NOTXcmd); /* disable transmit */ lp->excnak_pending = 1; @@ -760,20 +766,22 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) if ((status & lp->intmask & TXFREEflag) || lp->timed_out) { lp->intmask &= ~(TXFREEflag | EXCNAKflag); - BUGMSG(D_DURING, "TX IRQ (stat=%Xh)\n", status); + arc_printk(D_DURING, dev, "TX IRQ (stat=%Xh)\n", status); if (lp->cur_tx != -1 && !lp->timed_out) { if (!(status & TXACKflag)) { if (lp->lasttrans_dest != 0) { - BUGMSG(D_EXTRA, - "transmit was not acknowledged! (status=%Xh, dest=%02Xh)\n", - status, lp->lasttrans_dest); + arc_printk(D_EXTRA, dev, + "transmit was not acknowledged! (status=%Xh, dest=%02Xh)\n", + status, + lp->lasttrans_dest); dev->stats.tx_errors++; dev->stats.tx_carrier_errors++; } else { - BUGMSG(D_DURING, - "broadcast was not acknowledged; that's normal (status=%Xh, dest=%02Xh)\n", - status, lp->lasttrans_dest); + arc_printk(D_DURING, dev, + "broadcast was not acknowledged; that's normal (status=%Xh, dest=%02Xh)\n", + status, + lp->lasttrans_dest); } } @@ -836,29 +844,29 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) ACOMMAND(CFLAGScmd | CONFIGclear); dev->stats.tx_carrier_errors++; - BUGMSG(D_RECON, "Network reconfiguration detected (status=%Xh)\n", - status); + arc_printk(D_RECON, dev, "Network reconfiguration detected (status=%Xh)\n", + status); /* MYRECON bit is at bit 7 of diagstatus */ if (diagstatus & 0x80) - BUGMSG(D_RECON, "Put out that recon myself\n"); + arc_printk(D_RECON, dev, "Put out that recon myself\n"); /* is the RECON info empty or old? */ if (!lp->first_recon || !lp->last_recon || time_after(jiffies, lp->last_recon + HZ * 10)) { if (lp->network_down) - BUGMSG(D_NORMAL, "reconfiguration detected: cabling restored?\n"); + arc_printk(D_NORMAL, dev, "reconfiguration detected: cabling restored?\n"); lp->first_recon = lp->last_recon = jiffies; lp->num_recons = lp->network_down = 0; - BUGMSG(D_DURING, "recon: clearing counters.\n"); + arc_printk(D_DURING, dev, "recon: clearing counters.\n"); } else { /* add to current RECON counter */ lp->last_recon = jiffies; lp->num_recons++; - BUGMSG(D_DURING, "recon: counter=%d, time=%lds, net=%d\n", - lp->num_recons, - (lp->last_recon - lp->first_recon) / HZ, - lp->network_down); + arc_printk(D_DURING, dev, "recon: counter=%d, time=%lds, net=%d\n", + lp->num_recons, + (lp->last_recon - lp->first_recon) / HZ, + lp->network_down); /* if network is marked up; * and first_recon and last_recon are 60+ apart; @@ -870,7 +878,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) (lp->last_recon - lp->first_recon) <= HZ * 60 && lp->num_recons >= RECON_THRESHOLD) { lp->network_down = 1; - BUGMSG(D_NORMAL, "many reconfigurations detected: cabling problem?\n"); + arc_printk(D_NORMAL, dev, "many reconfigurations detected: cabling problem?\n"); } else if (!lp->network_down && lp->last_recon - lp->first_recon > HZ * 60) { /* reset counters if we've gone for over a minute. */ @@ -881,20 +889,20 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) } else if (lp->network_down && time_after(jiffies, lp->last_recon + HZ * 10)) { if (lp->network_down) - BUGMSG(D_NORMAL, "cabling restored?\n"); + arc_printk(D_NORMAL, dev, "cabling restored?\n"); lp->first_recon = lp->last_recon = 0; lp->num_recons = lp->network_down = 0; - BUGMSG(D_DURING, "not recon: clearing counters anyway.\n"); + arc_printk(D_DURING, dev, "not recon: clearing counters anyway.\n"); } if (didsomething) retval |= IRQ_HANDLED; } while (--boguscount && didsomething); - BUGMSG(D_DURING, "arcnet_interrupt complete (status=%Xh, count=%d)\n", - ASTATUS(), boguscount); - BUGMSG(D_DURING, "\n"); + arc_printk(D_DURING, dev, "arcnet_interrupt complete (status=%Xh, count=%d)\n", + ASTATUS(), boguscount); + arc_printk(D_DURING, dev, "\n"); AINTMASK(0); udelay(1); @@ -933,8 +941,8 @@ static void arcnet_rx(struct net_device *dev, int bufnum) lp->hw.copy_from_card(dev, bufnum, ofs, soft, length); } - BUGMSG(D_DURING, "Buffer #%d: received packet from %02Xh to %02Xh (%d+4 bytes)\n", - bufnum, pkt.hard.source, pkt.hard.dest, length); + arc_printk(D_DURING, dev, "Buffer #%d: received packet from %02Xh to %02Xh (%d+4 bytes)\n", + bufnum, pkt.hard.source, pkt.hard.dest, length); dev->stats.rx_packets++; dev->stats.rx_bytes += length + ARC_HDR_SIZE; @@ -947,10 +955,10 @@ static void arcnet_rx(struct net_device *dev, int bufnum) *newp = arc_proto_map[soft->proto]; if (oldp != newp) { - BUGMSG(D_PROTO, - "got protocol %02Xh; encap for host %02Xh is now '%c' (was '%c')\n", - soft->proto, pkt.hard.source, - newp->suffix, oldp->suffix); + arc_printk(D_PROTO, dev, + "got protocol %02Xh; encap for host %02Xh is now '%c' (was '%c')\n", + soft->proto, pkt.hard.source, + newp->suffix, oldp->suffix); } } @@ -967,9 +975,9 @@ static void arcnet_rx(struct net_device *dev, int bufnum) static void null_rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length) { - BUGMSG(D_PROTO, - "rx: don't know how to deal with proto %02Xh from host %02Xh.\n", - pkthdr->soft.rfc1201.proto, pkthdr->hard.source); + arc_printk(D_PROTO, dev, + "rx: don't know how to deal with proto %02Xh from host %02Xh.\n", + pkthdr->soft.rfc1201.proto, pkthdr->hard.source); } static int null_build_header(struct sk_buff *skb, struct net_device *dev, @@ -977,9 +985,9 @@ static int null_build_header(struct sk_buff *skb, struct net_device *dev, { struct arcnet_local *lp = netdev_priv(dev); - BUGMSG(D_PROTO, - "tx: can't build header for encap %02Xh; load a protocol driver.\n", - lp->default_proto[daddr]); + arc_printk(D_PROTO, dev, + "tx: can't build header for encap %02Xh; load a protocol driver.\n", + lp->default_proto[daddr]); /* always fails */ return 0; @@ -992,7 +1000,7 @@ static int null_prepare_tx(struct net_device *dev, struct archdr *pkt, struct arcnet_local *lp = netdev_priv(dev); struct arc_hardware newpkt; - BUGMSG(D_PROTO, "tx: no encap for this host; load a protocol driver.\n"); + arc_printk(D_PROTO, dev, "tx: no encap for this host; load a protocol driver.\n"); /* send a packet to myself -- will never get received, of course */ newpkt.source = newpkt.dest = dev->dev_addr[0]; diff --git a/drivers/net/arcnet/capmode.c b/drivers/net/arcnet/capmode.c index e7ec907f4680..d62d1accf4b6 100644 --- a/drivers/net/arcnet/capmode.c +++ b/drivers/net/arcnet/capmode.c @@ -47,7 +47,8 @@ static void rx(struct net_device *dev, int bufnum, char *pktbuf, *pkthdrbuf; int ofs; - BUGMSG(D_DURING, "it's a raw(cap) packet (length=%d)\n", length); + arc_printk(D_DURING, dev, "it's a raw(cap) packet (length=%d)\n", + length); if (length >= MinTU) ofs = 512 - length; @@ -56,7 +57,7 @@ static void rx(struct net_device *dev, int bufnum, skb = alloc_skb(length + ARC_HDR_SIZE + sizeof(int), GFP_ATOMIC); if (skb == NULL) { - BUGMSG(D_NORMAL, "Memory squeeze, dropping packet.\n"); + arc_printk(D_NORMAL, dev, "Memory squeeze, dropping packet\n"); dev->stats.rx_dropped++; return; } @@ -102,8 +103,8 @@ static int build_header(struct sk_buff *skb, int hdr_size = ARC_HDR_SIZE; struct archdr *pkt = (struct archdr *)skb_push(skb, hdr_size); - BUGMSG(D_PROTO, "Preparing header for cap packet %x.\n", - *((int *)&pkt->soft.cap.cookie[0])); + arc_printk(D_PROTO, dev, "Preparing header for cap packet %x.\n", + *((int *)&pkt->soft.cap.cookie[0])); /* Set the source hardware address. * @@ -140,16 +141,16 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, /* And neither is the cookie field */ length -= sizeof(int); - BUGMSG(D_DURING, "prepare_tx: txbufs=%d/%d/%d\n", - lp->next_tx, lp->cur_tx, bufnum); + arc_printk(D_DURING, dev, "prepare_tx: txbufs=%d/%d/%d\n", + lp->next_tx, lp->cur_tx, bufnum); - BUGMSG(D_PROTO, "Sending for cap packet %x.\n", - *((int *)&pkt->soft.cap.cookie[0])); + arc_printk(D_PROTO, dev, "Sending for cap packet %x.\n", + *((int *)&pkt->soft.cap.cookie[0])); if (length > XMTU) { /* should never happen! other people already check for this. */ - BUGMSG(D_NORMAL, "Bug! prepare_tx with size %d (> %d)\n", - length, XMTU); + arc_printk(D_NORMAL, dev, "Bug! prepare_tx with size %d (> %d)\n", + length, XMTU); length = XMTU; } if (length > MinTU) { @@ -162,8 +163,8 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, hard->offset[0] = ofs = 256 - length; } - BUGMSG(D_DURING, "prepare_tx: length=%d ofs=%d\n", - length, ofs); + arc_printk(D_DURING, dev, "prepare_tx: length=%d ofs=%d\n", + length, ofs); /* Copy the arcnet-header + the protocol byte down: */ lp->hw.copy_to_card(dev, bufnum, 0, hard, ARC_HDR_SIZE); @@ -188,8 +189,8 @@ static int ack_tx(struct net_device *dev, int acked) struct archdr *ackpkt; int length = sizeof(struct arc_cap); - BUGMSG(D_DURING, "capmode: ack_tx: protocol: %x: result: %d\n", - lp->outgoing.skb->protocol, acked); + arc_printk(D_DURING, dev, "capmode: ack_tx: protocol: %x: result: %d\n", + lp->outgoing.skb->protocol, acked); if (BUGLVL(D_SKB)) arcnet_dump_skb(dev, lp->outgoing.skb, "ack_tx"); @@ -197,7 +198,7 @@ static int ack_tx(struct net_device *dev, int acked) /* Now alloc a skb to send back up through the layers: */ ackskb = alloc_skb(length + ARC_HDR_SIZE, GFP_ATOMIC); if (ackskb == NULL) { - BUGMSG(D_NORMAL, "Memory squeeze, can't acknowledge.\n"); + arc_printk(D_NORMAL, dev, "Memory squeeze, can't acknowledge\n"); goto free_outskb; } @@ -213,8 +214,8 @@ static int ack_tx(struct net_device *dev, int acked) ackpkt->soft.cap.proto = 0; /* using protocol 0 for acknowledge */ ackpkt->soft.cap.mes.ack = acked; - BUGMSG(D_PROTO, "Ackknowledge for cap packet %x.\n", - *((int *)&ackpkt->soft.cap.cookie[0])); + arc_printk(D_PROTO, dev, "Ackknowledge for cap packet %x.\n", + *((int *)&ackpkt->soft.cap.cookie[0])); ackskb->protocol = cpu_to_be16(ETH_P_ARCNET); diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index af87c7482478..c3748f7c5081 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -58,16 +58,16 @@ static int __init com20020isa_probe(struct net_device *dev) ioaddr = dev->base_addr; if (!ioaddr) { - BUGMSG(D_NORMAL, "No autoprobe (yet) for IO mapped cards; you must specify the base address!\n"); + arc_printk(D_NORMAL, dev, "No autoprobe (yet) for IO mapped cards; you must specify the base address!\n"); return -ENODEV; } if (!request_region(ioaddr, ARCNET_TOTAL_SIZE, "arcnet (COM20020)")) { - BUGMSG(D_NORMAL, "IO region %xh-%xh already allocated.\n", - ioaddr, ioaddr + ARCNET_TOTAL_SIZE - 1); + arc_printk(D_NORMAL, dev, "IO region %xh-%xh already allocated.\n", + ioaddr, ioaddr + ARCNET_TOTAL_SIZE - 1); return -ENXIO; } if (ASTATUS() == 0xFF) { - BUGMSG(D_NORMAL, "IO address %x empty\n", ioaddr); + arc_printk(D_NORMAL, dev, "IO address %x empty\n", ioaddr); err = -ENODEV; goto out; } @@ -81,7 +81,8 @@ static int __init com20020isa_probe(struct net_device *dev) * card has just reset and the NORXflag is on until * we tell it to start receiving. */ - BUGMSG(D_INIT_REASONS, "intmask was %02Xh\n", inb(_INTMASK)); + arc_printk(D_INIT_REASONS, dev, "intmask was %02Xh\n", + inb(_INTMASK)); outb(0, _INTMASK); airqmask = probe_irq_on(); outb(NORXflag, _INTMASK); @@ -90,14 +91,14 @@ static int __init com20020isa_probe(struct net_device *dev) dev->irq = probe_irq_off(airqmask); if ((int)dev->irq <= 0) { - BUGMSG(D_INIT_REASONS, "Autoprobe IRQ failed first time\n"); + arc_printk(D_INIT_REASONS, dev, "Autoprobe IRQ failed first time\n"); airqmask = probe_irq_on(); outb(NORXflag, _INTMASK); udelay(5); outb(0, _INTMASK); dev->irq = probe_irq_off(airqmask); if ((int)dev->irq <= 0) { - BUGMSG(D_NORMAL, "Autoprobe IRQ failed.\n"); + arc_printk(D_NORMAL, dev, "Autoprobe IRQ failed.\n"); err = -ENODEV; goto out; } diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index c8184de4480d..0d0cc6a9c618 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -99,7 +99,7 @@ static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *i lp = netdev_priv(dev); - BUGMSG(D_NORMAL, "%s Controls\n", ci->name); + arc_printk(D_NORMAL, dev, "%s Controls\n", ci->name); ioaddr = pci_resource_start(pdev, cm->bar) + cm->offset; r = devm_request_region(&pdev->dev, ioaddr, cm->size, diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c index 3170e8ebb7fa..b0b8a0be08e5 100644 --- a/drivers/net/arcnet/com20020.c +++ b/drivers/net/arcnet/com20020.c @@ -68,7 +68,7 @@ static void com20020_copy_from_card(struct net_device *dev, int bufnum, outb(ofs & 0xff, _ADDR_LO); /* copy the data */ - TIME("insb", count, insb(_MEMDATA, buf, count)); + TIME(dev, "insb", count, insb(_MEMDATA, buf, count)); } static void com20020_copy_to_card(struct net_device *dev, int bufnum, @@ -81,7 +81,7 @@ static void com20020_copy_to_card(struct net_device *dev, int bufnum, outb(ofs & 0xff, _ADDR_LO); /* copy the data */ - TIME("outsb", count, outsb(_MEMDATA, buf, count)); + TIME(dev, "outsb", count, outsb(_MEMDATA, buf, count)); } /* Reset the card and check some basic stuff during the detection stage. */ @@ -120,10 +120,10 @@ int com20020_check(struct net_device *dev) status = ASTATUS(); if ((status & 0x99) != (NORXflag | TXFREEflag | RESETflag)) { - BUGMSG(D_NORMAL, "status invalid (%Xh).\n", status); + arc_printk(D_NORMAL, dev, "status invalid (%Xh).\n", status); return -ENODEV; } - BUGMSG(D_INIT_REASONS, "status after reset: %X\n", status); + arc_printk(D_INIT_REASONS, dev, "status after reset: %X\n", status); /* Enable TX */ outb(0x39, _CONFIG); @@ -132,16 +132,16 @@ int com20020_check(struct net_device *dev) ACOMMAND(CFLAGScmd | RESETclear | CONFIGclear); status = ASTATUS(); - BUGMSG(D_INIT_REASONS, "status after reset acknowledged: %X\n", - status); + arc_printk(D_INIT_REASONS, dev, "status after reset acknowledged: %X\n", + status); /* Read first location of memory */ outb(0 | RDDATAflag | AUTOINCflag, _ADDR_HI); outb(0, _ADDR_LO); if ((status = inb(_MEMDATA)) != TESTvalue) { - BUGMSG(D_NORMAL, "Signature byte not found (%02Xh != D1h).\n", - status); + arc_printk(D_NORMAL, dev, "Signature byte not found (%02Xh != D1h).\n", + status); return -ENODEV; } return 0; @@ -213,24 +213,25 @@ int com20020_found(struct net_device *dev, int shared) /* reserve the irq */ if (request_irq(dev->irq, arcnet_interrupt, shared, "arcnet (COM20020)", dev)) { - BUGMSG(D_NORMAL, "Can't get IRQ %d!\n", dev->irq); + arc_printk(D_NORMAL, dev, "Can't get IRQ %d!\n", dev->irq); return -ENODEV; } dev->base_addr = ioaddr; - BUGMSG(D_NORMAL, "%s: station %02Xh found at %03lXh, IRQ %d.\n", - lp->card_name, dev->dev_addr[0], dev->base_addr, dev->irq); + arc_printk(D_NORMAL, dev, "%s: station %02Xh found at %03lXh, IRQ %d.\n", + lp->card_name, dev->dev_addr[0], dev->base_addr, dev->irq); if (lp->backplane) - BUGMSG(D_NORMAL, "Using backplane mode.\n"); + arc_printk(D_NORMAL, dev, "Using backplane mode.\n"); if (lp->timeout != 3) - BUGMSG(D_NORMAL, "Using extended timeout value of %d.\n", lp->timeout); + arc_printk(D_NORMAL, dev, "Using extended timeout value of %d\n", + lp->timeout); - BUGMSG(D_NORMAL, "Using CKP %d - data rate %s.\n", - lp->setup >> 1, - clockrates[3 - ((lp->setup2 & 0xF0) >> 4) + ((lp->setup & 0x0F) >> 1)]); + arc_printk(D_NORMAL, dev, "Using CKP %d - data rate %s\n", + lp->setup >> 1, + clockrates[3 - ((lp->setup2 & 0xF0) >> 4) + ((lp->setup & 0x0F) >> 1)]); if (register_netdev(dev)) { free_irq(dev->irq, dev); @@ -252,16 +253,16 @@ static int com20020_reset(struct net_device *dev, int really_reset) u_int ioaddr = dev->base_addr; u_char inbyte; - BUGMSG(D_DEBUG, "%s: %d: %s: dev: %p, lp: %p, dev->name: %s\n", - __FILE__, __LINE__, __func__, dev, lp, dev->name); - BUGMSG(D_INIT, "Resetting %s (status=%02Xh)\n", - dev->name, ASTATUS()); + arc_printk(D_DEBUG, dev, "%s: %d: %s: dev: %p, lp: %p, dev->name: %s\n", + __FILE__, __LINE__, __func__, dev, lp, dev->name); + arc_printk(D_INIT, dev, "Resetting %s (status=%02Xh)\n", + dev->name, ASTATUS()); - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); lp->config = TXENcfg | (lp->timeout << 3) | (lp->backplane << 2); /* power-up defaults */ SETCONF; - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); if (really_reset) { /* reset the card */ @@ -269,22 +270,23 @@ static int com20020_reset(struct net_device *dev, int really_reset) mdelay(RESETtime * 2); /* COM20020 seems to be slower sometimes */ } /* clear flags & end reset */ - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); ACOMMAND(CFLAGScmd | RESETclear | CONFIGclear); /* verify that the ARCnet signature byte is present */ - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); com20020_copy_from_card(dev, 0, 0, &inbyte, 1); - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); if (inbyte != TESTvalue) { - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); - BUGMSG(D_NORMAL, "reset failed: TESTvalue not present.\n"); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", + __FILE__, __LINE__, __func__); + arc_printk(D_NORMAL, dev, "reset failed: TESTvalue not present.\n"); return 1; } /* enable extended (512-byte) packets */ ACOMMAND(CONFIGcmd | EXTconf); - BUGMSG(D_DEBUG, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); /* done! return success. */ return 0; @@ -294,7 +296,7 @@ static void com20020_setmask(struct net_device *dev, int mask) { u_int ioaddr = dev->base_addr; - BUGMSG(D_DURING, "Setting mask to %x at %x\n", mask, ioaddr); + arc_printk(D_DURING, dev, "Setting mask to %x at %x\n", mask, ioaddr); AINTMASK(mask); } @@ -336,7 +338,7 @@ static void com20020_set_mc_list(struct net_device *dev) if ((dev->flags & IFF_PROMISC) && (dev->flags & IFF_UP)) { /* Enable promiscuous mode */ if (!(lp->setup & PROMISCset)) - BUGMSG(D_NORMAL, "Setting promiscuous flag...\n"); + arc_printk(D_NORMAL, dev, "Setting promiscuous flag...\n"); SET_SUBADR(SUB_SETUP1); lp->setup |= PROMISCset; outb(lp->setup, _XREG); @@ -344,7 +346,7 @@ static void com20020_set_mc_list(struct net_device *dev) /* Disable promiscuous mode, use normal mode */ { if ((lp->setup & PROMISCset)) - BUGMSG(D_NORMAL, "Resetting promiscuous flag...\n"); + arc_printk(D_NORMAL, dev, "Resetting promiscuous flag...\n"); SET_SUBADR(SUB_SETUP1); lp->setup &= ~PROMISCset; outb(lp->setup, _XREG); diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 33a8531e90c7..ec2db8527862 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -151,16 +151,17 @@ static int __init com90io_probe(struct net_device *dev) } if (!ioaddr) { - BUGMSG(D_NORMAL, "No autoprobe for IO mapped cards; you must specify the base address!\n"); + arc_printk(D_NORMAL, dev, "No autoprobe for IO mapped cards; you must specify the base address!\n"); return -ENODEV; } if (!request_region(ioaddr, ARCNET_TOTAL_SIZE, "com90io probe")) { - BUGMSG(D_INIT_REASONS, "IO request_region %x-%x failed.\n", - ioaddr, ioaddr + ARCNET_TOTAL_SIZE - 1); + arc_printk(D_INIT_REASONS, dev, "IO request_region %x-%x failed\n", + ioaddr, ioaddr + ARCNET_TOTAL_SIZE - 1); return -ENXIO; } if (ASTATUS() == 0xFF) { - BUGMSG(D_INIT_REASONS, "IO address %x empty\n", ioaddr); + arc_printk(D_INIT_REASONS, dev, "IO address %x empty\n", + ioaddr); goto err_out; } inb(_RESET); @@ -169,19 +170,22 @@ static int __init com90io_probe(struct net_device *dev) status = ASTATUS(); if ((status & 0x9D) != (NORXflag | RECONflag | TXFREEflag | RESETflag)) { - BUGMSG(D_INIT_REASONS, "Status invalid (%Xh).\n", status); + arc_printk(D_INIT_REASONS, dev, "Status invalid (%Xh)\n", + status); goto err_out; } - BUGMSG(D_INIT_REASONS, "Status after reset: %X\n", status); + arc_printk(D_INIT_REASONS, dev, "Status after reset: %X\n", status); ACOMMAND(CFLAGScmd | RESETclear | CONFIGclear); - BUGMSG(D_INIT_REASONS, "Status after reset acknowledged: %X\n", status); + arc_printk(D_INIT_REASONS, dev, "Status after reset acknowledged: %X\n", + status); status = ASTATUS(); if (status & RESETflag) { - BUGMSG(D_INIT_REASONS, "Eternal reset (status=%Xh)\n", status); + arc_printk(D_INIT_REASONS, dev, "Eternal reset (status=%Xh)\n", + status); goto err_out; } outb((0x16 | IOMAPflag) & ~ENABLE16flag, _CONFIG); @@ -192,8 +196,8 @@ static int __init com90io_probe(struct net_device *dev) outb(0, _ADDR_LO); if ((status = inb(_MEMDATA)) != 0xd1) { - BUGMSG(D_INIT_REASONS, "Signature byte not found (%Xh instead).\n", - status); + arc_printk(D_INIT_REASONS, dev, "Signature byte not found (%Xh instead).\n", + status); goto err_out; } if (!dev->irq) { @@ -209,7 +213,7 @@ static int __init com90io_probe(struct net_device *dev) dev->irq = probe_irq_off(airqmask); if ((int)dev->irq <= 0) { - BUGMSG(D_INIT_REASONS, "Autoprobe IRQ failed\n"); + arc_printk(D_INIT_REASONS, dev, "Autoprobe IRQ failed\n"); goto err_out; } } @@ -232,7 +236,7 @@ static int __init com90io_found(struct net_device *dev) /* Reserve the irq */ if (request_irq(dev->irq, arcnet_interrupt, 0, "arcnet (COM90xx-IO)", dev)) { - BUGMSG(D_NORMAL, "Can't get IRQ %d!\n", dev->irq); + arc_printk(D_NORMAL, dev, "Can't get IRQ %d!\n", dev->irq); return -ENODEV; } /* Reserve the I/O region */ @@ -266,8 +270,8 @@ static int __init com90io_found(struct net_device *dev) return err; } - BUGMSG(D_NORMAL, "COM90IO: station %02Xh found at %03lXh, IRQ %d.\n", - dev->dev_addr[0], dev->base_addr, dev->irq); + arc_printk(D_NORMAL, dev, "COM90IO: station %02Xh found at %03lXh, IRQ %d.\n", + dev->dev_addr[0], dev->base_addr, dev->irq); return 0; } @@ -284,7 +288,8 @@ static int com90io_reset(struct net_device *dev, int really_reset) struct arcnet_local *lp = netdev_priv(dev); short ioaddr = dev->base_addr; - BUGMSG(D_INIT, "Resetting %s (status=%02Xh)\n", dev->name, ASTATUS()); + arc_printk(D_INIT, dev, "Resetting %s (status=%02Xh)\n", + dev->name, ASTATUS()); if (really_reset) { /* reset the card */ @@ -300,7 +305,7 @@ static int com90io_reset(struct net_device *dev, int really_reset) /* verify that the ARCnet signature byte is present */ if (get_buffer_byte(dev, 0) != TESTvalue) { - BUGMSG(D_NORMAL, "reset failed: TESTvalue not present.\n"); + arc_printk(D_NORMAL, dev, "reset failed: TESTvalue not present.\n"); return 1; } /* enable extended (512-byte) packets */ @@ -334,13 +339,15 @@ static void com90io_setmask(struct net_device *dev, int mask) static void com90io_copy_to_card(struct net_device *dev, int bufnum, int offset, void *buf, int count) { - TIME("put_whole_buffer", count, put_whole_buffer(dev, bufnum * 512 + offset, count, buf)); + TIME(dev, "put_whole_buffer", count, + put_whole_buffer(dev, bufnum * 512 + offset, count, buf)); } static void com90io_copy_from_card(struct net_device *dev, int bufnum, int offset, void *buf, int count) { - TIME("get_whole_buffer", count, get_whole_buffer(dev, bufnum * 512 + offset, count, buf)); + TIME(dev, "get_whole_buffer", count, + get_whole_buffer(dev, bufnum * 512 + offset, count, buf)); } static int io; /* use the insmod io= irq= shmem= options */ diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index b5e1c1904f13..12534a3cb4ce 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -157,24 +157,24 @@ static void __init com90xx_probe(void) numprint++; numprint %= 8; if (!numprint) { - BUGMSG2(D_INIT, "\n"); - BUGMSG2(D_INIT, "S1: "); + arc_cont(D_INIT, "\n"); + arc_cont(D_INIT, "S1: "); } - BUGMSG2(D_INIT, "%Xh ", *port); + arc_cont(D_INIT, "%Xh ", *port); ioaddr = *port; if (!request_region(*port, ARCNET_TOTAL_SIZE, "arcnet (90xx)")) { - BUGMSG2(D_INIT_REASONS, "(request_region)\n"); - BUGMSG2(D_INIT_REASONS, "S1: "); + arc_cont(D_INIT_REASONS, "(request_region)\n"); + arc_cont(D_INIT_REASONS, "S1: "); if (BUGLVL(D_INIT_REASONS)) numprint = 0; *port-- = ports[--numports]; continue; } if (ASTATUS() == 0xFF) { - BUGMSG2(D_INIT_REASONS, "(empty)\n"); - BUGMSG2(D_INIT_REASONS, "S1: "); + arc_cont(D_INIT_REASONS, "(empty)\n"); + arc_cont(D_INIT_REASONS, "S1: "); if (BUGLVL(D_INIT_REASONS)) numprint = 0; release_region(*port, ARCNET_TOTAL_SIZE); @@ -183,15 +183,15 @@ static void __init com90xx_probe(void) } inb(_RESET); /* begin resetting card */ - BUGMSG2(D_INIT_REASONS, "\n"); - BUGMSG2(D_INIT_REASONS, "S1: "); + arc_cont(D_INIT_REASONS, "\n"); + arc_cont(D_INIT_REASONS, "S1: "); if (BUGLVL(D_INIT_REASONS)) numprint = 0; } - BUGMSG2(D_INIT, "\n"); + arc_cont(D_INIT, "\n"); if (!numports) { - BUGMSG2(D_NORMAL, "S1: No ARCnet cards found.\n"); + arc_cont(D_NORMAL, "S1: No ARCnet cards found.\n"); kfree(shmems); kfree(iomem); return; @@ -205,12 +205,12 @@ static void __init com90xx_probe(void) numprint++; numprint %= 8; if (!numprint) { - BUGMSG2(D_INIT, "\n"); - BUGMSG2(D_INIT, "S2: "); + arc_cont(D_INIT, "\n"); + arc_cont(D_INIT, "S2: "); } - BUGMSG2(D_INIT, "%Xh ", *port); + arc_cont(D_INIT, "%Xh ", *port); } - BUGMSG2(D_INIT, "\n"); + arc_cont(D_INIT, "\n"); mdelay(RESETtime); /* Stage 3: abandon any shmem addresses that don't have the signature @@ -223,30 +223,30 @@ static void __init com90xx_probe(void) numprint++; numprint %= 8; if (!numprint) { - BUGMSG2(D_INIT, "\n"); - BUGMSG2(D_INIT, "S3: "); + arc_cont(D_INIT, "\n"); + arc_cont(D_INIT, "S3: "); } - BUGMSG2(D_INIT, "%lXh ", *p); + arc_cont(D_INIT, "%lXh ", *p); if (!request_mem_region(*p, MIRROR_SIZE, "arcnet (90xx)")) { - BUGMSG2(D_INIT_REASONS, "(request_mem_region)\n"); - BUGMSG2(D_INIT_REASONS, "Stage 3: "); + arc_cont(D_INIT_REASONS, "(request_mem_region)\n"); + arc_cont(D_INIT_REASONS, "Stage 3: "); if (BUGLVL(D_INIT_REASONS)) numprint = 0; goto out; } base = ioremap(*p, MIRROR_SIZE); if (!base) { - BUGMSG2(D_INIT_REASONS, "(ioremap)\n"); - BUGMSG2(D_INIT_REASONS, "Stage 3: "); + arc_cont(D_INIT_REASONS, "(ioremap)\n"); + arc_cont(D_INIT_REASONS, "Stage 3: "); if (BUGLVL(D_INIT_REASONS)) numprint = 0; goto out1; } if (readb(base) != TESTvalue) { - BUGMSG2(D_INIT_REASONS, "(%02Xh != %02Xh)\n", - readb(base), TESTvalue); - BUGMSG2(D_INIT_REASONS, "S3: "); + arc_cont(D_INIT_REASONS, "(%02Xh != %02Xh)\n", + readb(base), TESTvalue); + arc_cont(D_INIT_REASONS, "S3: "); if (BUGLVL(D_INIT_REASONS)) numprint = 0; goto out2; @@ -258,12 +258,12 @@ static void __init com90xx_probe(void) */ writeb(0x42, base); if (readb(base) != 0x42) { - BUGMSG2(D_INIT_REASONS, "(read only)\n"); - BUGMSG2(D_INIT_REASONS, "S3: "); + arc_cont(D_INIT_REASONS, "(read only)\n"); + arc_cont(D_INIT_REASONS, "S3: "); goto out2; } - BUGMSG2(D_INIT_REASONS, "\n"); - BUGMSG2(D_INIT_REASONS, "S3: "); + arc_cont(D_INIT_REASONS, "\n"); + arc_cont(D_INIT_REASONS, "S3: "); if (BUGLVL(D_INIT_REASONS)) numprint = 0; iomem[index] = base; @@ -276,10 +276,10 @@ static void __init com90xx_probe(void) *p-- = shmems[--numshmems]; index--; } - BUGMSG2(D_INIT, "\n"); + arc_cont(D_INIT, "\n"); if (!numshmems) { - BUGMSG2(D_NORMAL, "S3: No ARCnet cards found.\n"); + arc_cont(D_NORMAL, "S3: No ARCnet cards found.\n"); for (port = &ports[0]; port < ports + numports; port++) release_region(*port, ARCNET_TOTAL_SIZE); kfree(shmems); @@ -294,12 +294,12 @@ static void __init com90xx_probe(void) numprint++; numprint %= 8; if (!numprint) { - BUGMSG2(D_INIT, "\n"); - BUGMSG2(D_INIT, "S4: "); + arc_cont(D_INIT, "\n"); + arc_cont(D_INIT, "S4: "); } - BUGMSG2(D_INIT, "%lXh ", *p); + arc_cont(D_INIT, "%lXh ", *p); } - BUGMSG2(D_INIT, "\n"); + arc_cont(D_INIT, "\n"); /* Stage 5: for any ports that have the correct status, can disable * the RESET flag, and (if no irq is given) generate an autoirq, @@ -315,18 +315,18 @@ static void __init com90xx_probe(void) numprint++; numprint %= 8; if (!numprint) { - BUGMSG2(D_INIT, "\n"); - BUGMSG2(D_INIT, "S5: "); + arc_cont(D_INIT, "\n"); + arc_cont(D_INIT, "S5: "); } - BUGMSG2(D_INIT, "%Xh ", *port); + arc_cont(D_INIT, "%Xh ", *port); ioaddr = *port; status = ASTATUS(); if ((status & 0x9D) != (NORXflag | RECONflag | TXFREEflag | RESETflag)) { - BUGMSG2(D_INIT_REASONS, "(status=%Xh)\n", status); - BUGMSG2(D_INIT_REASONS, "S5: "); + arc_cont(D_INIT_REASONS, "(status=%Xh)\n", status); + arc_cont(D_INIT_REASONS, "S5: "); if (BUGLVL(D_INIT_REASONS)) numprint = 0; release_region(*port, ARCNET_TOTAL_SIZE); @@ -336,9 +336,9 @@ static void __init com90xx_probe(void) ACOMMAND(CFLAGScmd | RESETclear | CONFIGclear); status = ASTATUS(); if (status & RESETflag) { - BUGMSG2(D_INIT_REASONS, " (eternal reset, status=%Xh)\n", - status); - BUGMSG2(D_INIT_REASONS, "S5: "); + arc_cont(D_INIT_REASONS, " (eternal reset, status=%Xh)\n", + status); + arc_cont(D_INIT_REASONS, "S5: "); if (BUGLVL(D_INIT_REASONS)) numprint = 0; release_region(*port, ARCNET_TOTAL_SIZE); @@ -360,8 +360,8 @@ static void __init com90xx_probe(void) airq = probe_irq_off(airqmask); if (airq <= 0) { - BUGMSG2(D_INIT_REASONS, "(airq=%d)\n", airq); - BUGMSG2(D_INIT_REASONS, "S5: "); + arc_cont(D_INIT_REASONS, "(airq=%d)\n", airq); + arc_cont(D_INIT_REASONS, "S5: "); if (BUGLVL(D_INIT_REASONS)) numprint = 0; release_region(*port, ARCNET_TOTAL_SIZE); @@ -372,7 +372,7 @@ static void __init com90xx_probe(void) airq = irq; } - BUGMSG2(D_INIT, "(%d,", airq); + arc_cont(D_INIT, "(%d,", airq); openparen = 1; /* Everything seems okay. But which shmem, if any, puts @@ -399,7 +399,7 @@ static void __init com90xx_probe(void) void __iomem *base = iomem[index]; if (readb(base) == TESTvalue) { /* found one */ - BUGMSG2(D_INIT, "%lXh)\n", *p); + arc_cont(D_INIT, "%lXh)\n", *p); openparen = 0; /* register the card */ @@ -412,7 +412,7 @@ static void __init com90xx_probe(void) iomem[index] = iomem[numshmems]; break; /* go to the next I/O port */ } else { - BUGMSG2(D_INIT_REASONS, "%Xh-", readb(base)); + arc_cont(D_INIT_REASONS, "%Xh-", readb(base)); } } @@ -476,7 +476,7 @@ static int __init com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem /* allocate struct net_device */ dev = alloc_arcdev(device); if (!dev) { - BUGMSG2(D_NORMAL, "com90xx: Can't allocate device!\n"); + arc_cont(D_NORMAL, "com90xx: Can't allocate device!\n"); iounmap(p); release_mem_region(shmem, MIRROR_SIZE); return -ENOMEM; @@ -515,7 +515,7 @@ static int __init com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem /* reserve the irq */ if (request_irq(airq, arcnet_interrupt, 0, "arcnet (90xx)", dev)) { - BUGMSG(D_NORMAL, "Can't get IRQ %d!\n", airq); + arc_printk(D_NORMAL, dev, "Can't get IRQ %d!\n", airq); goto err_release_mem; } dev->irq = airq; @@ -531,7 +531,7 @@ static int __init com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem lp->hw.copy_from_card = com90xx_copy_from_card; lp->mem_start = ioremap(dev->mem_start, dev->mem_end - dev->mem_start + 1); if (!lp->mem_start) { - BUGMSG(D_NORMAL, "Can't remap device memory!\n"); + arc_printk(D_NORMAL, dev, "Can't remap device memory!\n"); goto err_free_irq; } @@ -540,10 +540,11 @@ static int __init com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem dev->base_addr = ioaddr; - BUGMSG(D_NORMAL, "COM90xx station %02Xh found at %03lXh, IRQ %d, ShMem %lXh (%ld*%xh).\n", - dev->dev_addr[0], - dev->base_addr, dev->irq, dev->mem_start, - (dev->mem_end - dev->mem_start + 1) / mirror_size, mirror_size); + arc_printk(D_NORMAL, dev, "COM90xx station %02Xh found at %03lXh, IRQ %d, ShMem %lXh (%ld*%xh).\n", + dev->dev_addr[0], + dev->base_addr, dev->irq, dev->mem_start, + (dev->mem_end - dev->mem_start + 1) / mirror_size, + mirror_size); if (register_netdev(dev)) goto err_unmap; @@ -595,7 +596,7 @@ static int com90xx_reset(struct net_device *dev, int really_reset) struct arcnet_local *lp = netdev_priv(dev); short ioaddr = dev->base_addr; - BUGMSG(D_INIT, "Resetting (status=%02Xh)\n", ASTATUS()); + arc_printk(D_INIT, dev, "Resetting (status=%02Xh)\n", ASTATUS()); if (really_reset) { /* reset the card */ @@ -611,7 +612,7 @@ static int com90xx_reset(struct net_device *dev, int really_reset) /* verify that the ARCnet signature byte is present */ if (readb(lp->mem_start) != TESTvalue) { if (really_reset) - BUGMSG(D_NORMAL, "reset failed: TESTvalue not present.\n"); + arc_printk(D_NORMAL, dev, "reset failed: TESTvalue not present.\n"); return 1; } /* enable extended (512-byte) packets */ @@ -631,7 +632,7 @@ static void com90xx_copy_to_card(struct net_device *dev, int bufnum, int offset, struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + bufnum * 512 + offset; - TIME("memcpy_toio", count, memcpy_toio(memaddr, buf, count)); + TIME(dev, "memcpy_toio", count, memcpy_toio(memaddr, buf, count)); } static void com90xx_copy_from_card(struct net_device *dev, int bufnum, int offset, @@ -640,7 +641,7 @@ static void com90xx_copy_from_card(struct net_device *dev, int bufnum, int offse struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + bufnum * 512 + offset; - TIME("memcpy_fromio", count, memcpy_fromio(buf, memaddr, count)); + TIME(dev, "memcpy_fromio", count, memcpy_fromio(buf, memaddr, count)); } MODULE_LICENSE("GPL"); diff --git a/drivers/net/arcnet/rfc1051.c b/drivers/net/arcnet/rfc1051.c index 824d71fcfd53..47c7d1a4ef4c 100644 --- a/drivers/net/arcnet/rfc1051.c +++ b/drivers/net/arcnet/rfc1051.c @@ -124,7 +124,7 @@ static void rx(struct net_device *dev, int bufnum, struct archdr *pkt = pkthdr; int ofs; - BUGMSG(D_DURING, "it's a raw packet (length=%d)\n", length); + arc_printk(D_DURING, dev, "it's a raw packet (length=%d)\n", length); if (length >= MinTU) ofs = 512 - length; @@ -133,7 +133,7 @@ static void rx(struct net_device *dev, int bufnum, skb = alloc_skb(length + ARC_HDR_SIZE, GFP_ATOMIC); if (skb == NULL) { - BUGMSG(D_NORMAL, "Memory squeeze, dropping packet.\n"); + arc_printk(D_NORMAL, dev, "Memory squeeze, dropping packet\n"); dev->stats.rx_dropped++; return; } @@ -173,8 +173,8 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, soft->proto = ARC_P_ARP_RFC1051; break; default: - BUGMSG(D_NORMAL, "RFC1051: I don't understand protocol %d (%Xh)\n", - type, type); + arc_printk(D_NORMAL, dev, "RFC1051: I don't understand protocol %d (%Xh)\n", + type, type); dev->stats.tx_errors++; dev->stats.tx_aborted_errors++; return 0; @@ -210,15 +210,15 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, struct arc_hardware *hard = &pkt->hard; int ofs; - BUGMSG(D_DURING, "prepare_tx: txbufs=%d/%d/%d\n", - lp->next_tx, lp->cur_tx, bufnum); + arc_printk(D_DURING, dev, "prepare_tx: txbufs=%d/%d/%d\n", + lp->next_tx, lp->cur_tx, bufnum); length -= ARC_HDR_SIZE; /* hard header is not included in packet length */ if (length > XMTU) { /* should never happen! other people already check for this. */ - BUGMSG(D_NORMAL, "Bug! prepare_tx with size %d (> %d)\n", - length, XMTU); + arc_printk(D_NORMAL, dev, "Bug! prepare_tx with size %d (> %d)\n", + length, XMTU); length = XMTU; } if (length > MinTU) { diff --git a/drivers/net/arcnet/rfc1201.c b/drivers/net/arcnet/rfc1201.c index d052976ebdfa..97af7d92c020 100644 --- a/drivers/net/arcnet/rfc1201.c +++ b/drivers/net/arcnet/rfc1201.c @@ -136,7 +136,8 @@ static void rx(struct net_device *dev, int bufnum, int saddr = pkt->hard.source, ofs; struct Incoming *in = &lp->rfc1201.incoming[saddr]; - BUGMSG(D_DURING, "it's an RFC1201 packet (length=%d)\n", length); + arc_printk(D_DURING, dev, "it's an RFC1201 packet (length=%d)\n", + length); if (length >= MinTU) ofs = 512 - length; @@ -145,10 +146,10 @@ static void rx(struct net_device *dev, int bufnum, if (soft->split_flag == 0xFF) { /* Exception Packet */ if (length >= 4 + RFC1201_HDR_SIZE) { - BUGMSG(D_DURING, "compensating for exception packet\n"); + arc_printk(D_DURING, dev, "compensating for exception packet\n"); } else { - BUGMSG(D_EXTRA, "short RFC1201 exception packet from %02Xh", - saddr); + arc_printk(D_EXTRA, dev, "short RFC1201 exception packet from %02Xh", + saddr); return; } @@ -159,12 +160,13 @@ static void rx(struct net_device *dev, int bufnum, soft, sizeof(pkt->soft)); } if (!soft->split_flag) { /* not split */ - BUGMSG(D_RX, "incoming is not split (splitflag=%d)\n", - soft->split_flag); + arc_printk(D_RX, dev, "incoming is not split (splitflag=%d)\n", + soft->split_flag); if (in->skb) { /* already assembling one! */ - BUGMSG(D_EXTRA, "aborting assembly (seq=%d) for unsplit packet (splitflag=%d, seq=%d)\n", - in->sequence, soft->split_flag, soft->sequence); + arc_printk(D_EXTRA, dev, "aborting assembly (seq=%d) for unsplit packet (splitflag=%d, seq=%d)\n", + in->sequence, soft->split_flag, + soft->sequence); lp->rfc1201.aborted_seq = soft->sequence; dev_kfree_skb_irq(in->skb); dev->stats.rx_errors++; @@ -175,7 +177,7 @@ static void rx(struct net_device *dev, int bufnum, skb = alloc_skb(length + ARC_HDR_SIZE, GFP_ATOMIC); if (skb == NULL) { - BUGMSG(D_NORMAL, "Memory squeeze, dropping packet.\n"); + arc_printk(D_NORMAL, dev, "Memory squeeze, dropping packet\n"); dev->stats.rx_dropped++; return; } @@ -205,18 +207,18 @@ static void rx(struct net_device *dev, int bufnum, uint8_t *cptr = (uint8_t *)arp + sizeof(struct arphdr); if (!*cptr) { /* is saddr = 00? */ - BUGMSG(D_EXTRA, - "ARP source address was 00h, set to %02Xh.\n", - saddr); + arc_printk(D_EXTRA, dev, + "ARP source address was 00h, set to %02Xh\n", + saddr); dev->stats.rx_crc_errors++; *cptr = saddr; } else { - BUGMSG(D_DURING, "ARP source address (%Xh) is fine.\n", - *cptr); + arc_printk(D_DURING, dev, "ARP source address (%Xh) is fine.\n", + *cptr); } } else { - BUGMSG(D_NORMAL, "funny-shaped ARP packet. (%Xh, %Xh)\n", - arp->ar_hln, arp->ar_pln); + arc_printk(D_NORMAL, dev, "funny-shaped ARP packet. (%Xh, %Xh)\n", + arp->ar_hln, arp->ar_pln); dev->stats.rx_errors++; dev->stats.rx_crc_errors++; } @@ -245,13 +247,13 @@ static void rx(struct net_device *dev, int bufnum, * other way to be reliable. */ - BUGMSG(D_RX, "packet is split (splitflag=%d, seq=%d)\n", - soft->split_flag, in->sequence); + arc_printk(D_RX, dev, "packet is split (splitflag=%d, seq=%d)\n", + soft->split_flag, in->sequence); if (in->skb && in->sequence != soft->sequence) { - BUGMSG(D_EXTRA, "wrong seq number (saddr=%d, expected=%d, seq=%d, splitflag=%d)\n", - saddr, in->sequence, soft->sequence, - soft->split_flag); + arc_printk(D_EXTRA, dev, "wrong seq number (saddr=%d, expected=%d, seq=%d, splitflag=%d)\n", + saddr, in->sequence, soft->sequence, + soft->split_flag); dev_kfree_skb_irq(in->skb); in->skb = NULL; dev->stats.rx_errors++; @@ -259,12 +261,12 @@ static void rx(struct net_device *dev, int bufnum, in->lastpacket = in->numpackets = 0; } if (soft->split_flag & 1) { /* first packet in split */ - BUGMSG(D_RX, "brand new splitpacket (splitflag=%d)\n", - soft->split_flag); + arc_printk(D_RX, dev, "brand new splitpacket (splitflag=%d)\n", + soft->split_flag); if (in->skb) { /* already assembling one! */ - BUGMSG(D_EXTRA, "aborting previous (seq=%d) assembly (splitflag=%d, seq=%d)\n", - in->sequence, soft->split_flag, - soft->sequence); + arc_printk(D_EXTRA, dev, "aborting previous (seq=%d) assembly (splitflag=%d, seq=%d)\n", + in->sequence, soft->split_flag, + soft->sequence); dev->stats.rx_errors++; dev->stats.rx_missed_errors++; dev_kfree_skb_irq(in->skb); @@ -274,8 +276,8 @@ static void rx(struct net_device *dev, int bufnum, in->lastpacket = 1; if (in->numpackets > 16) { - BUGMSG(D_EXTRA, "incoming packet more than 16 segments; dropping. (splitflag=%d)\n", - soft->split_flag); + arc_printk(D_EXTRA, dev, "incoming packet more than 16 segments; dropping. (splitflag=%d)\n", + soft->split_flag); lp->rfc1201.aborted_seq = soft->sequence; dev->stats.rx_errors++; dev->stats.rx_length_errors++; @@ -284,7 +286,7 @@ static void rx(struct net_device *dev, int bufnum, in->skb = skb = alloc_skb(508 * in->numpackets + ARC_HDR_SIZE, GFP_ATOMIC); if (skb == NULL) { - BUGMSG(D_NORMAL, "(split) memory squeeze, dropping packet.\n"); + arc_printk(D_NORMAL, dev, "(split) memory squeeze, dropping packet.\n"); lp->rfc1201.aborted_seq = soft->sequence; dev->stats.rx_dropped++; return; @@ -305,9 +307,10 @@ static void rx(struct net_device *dev, int bufnum, */ if (!in->skb) { if (lp->rfc1201.aborted_seq != soft->sequence) { - BUGMSG(D_EXTRA, "can't continue split without starting first! (splitflag=%d, seq=%d, aborted=%d)\n", - soft->split_flag, soft->sequence, - lp->rfc1201.aborted_seq); + arc_printk(D_EXTRA, dev, "can't continue split without starting first! (splitflag=%d, seq=%d, aborted=%d)\n", + soft->split_flag, + soft->sequence, + lp->rfc1201.aborted_seq); dev->stats.rx_errors++; dev->stats.rx_missed_errors++; } @@ -317,15 +320,16 @@ static void rx(struct net_device *dev, int bufnum, if (packetnum != in->lastpacket) { /* not the right flag! */ /* harmless duplicate? ignore. */ if (packetnum <= in->lastpacket - 1) { - BUGMSG(D_EXTRA, "duplicate splitpacket ignored! (splitflag=%d)\n", - soft->split_flag); + arc_printk(D_EXTRA, dev, "duplicate splitpacket ignored! (splitflag=%d)\n", + soft->split_flag); dev->stats.rx_errors++; dev->stats.rx_frame_errors++; return; } /* "bad" duplicate, kill reassembly */ - BUGMSG(D_EXTRA, "out-of-order splitpacket, reassembly (seq=%d) aborted (splitflag=%d, seq=%d)\n", - in->sequence, soft->split_flag, soft->sequence); + arc_printk(D_EXTRA, dev, "out-of-order splitpacket, reassembly (seq=%d) aborted (splitflag=%d, seq=%d)\n", + in->sequence, soft->split_flag, + soft->sequence); lp->rfc1201.aborted_seq = soft->sequence; dev_kfree_skb_irq(in->skb); in->skb = NULL; @@ -350,10 +354,10 @@ static void rx(struct net_device *dev, int bufnum, in->skb = NULL; in->lastpacket = in->numpackets = 0; - BUGMSG(D_SKB_SIZE, "skb: received %d bytes from %02X (unsplit)\n", - skb->len, pkt->hard.source); - BUGMSG(D_SKB_SIZE, "skb: received %d bytes from %02X (split)\n", - skb->len, pkt->hard.source); + arc_printk(D_SKB_SIZE, dev, "skb: received %d bytes from %02X (unsplit)\n", + skb->len, pkt->hard.source); + arc_printk(D_SKB_SIZE, dev, "skb: received %d bytes from %02X (split)\n", + skb->len, pkt->hard.source); if (BUGLVL(D_SKB)) arcnet_dump_skb(dev, skb, "rx"); @@ -395,8 +399,8 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, soft->proto = ARC_P_ATALK; break; default: - BUGMSG(D_NORMAL, "RFC1201: I don't understand protocol %d (%Xh)\n", - type, type); + arc_printk(D_NORMAL, dev, "RFC1201: I don't understand protocol %d (%Xh)\n", + type, type); dev->stats.tx_errors++; dev->stats.tx_aborted_errors++; return 0; @@ -469,8 +473,8 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, const int maxsegsize = XMTU - RFC1201_HDR_SIZE; struct Outgoing *out; - BUGMSG(D_DURING, "prepare_tx: txbufs=%d/%d/%d\n", - lp->next_tx, lp->cur_tx, bufnum); + arc_printk(D_DURING, dev, "prepare_tx: txbufs=%d/%d/%d\n", + lp->next_tx, lp->cur_tx, bufnum); length -= ARC_HDR_SIZE; /* hard header is not included in packet length */ pkt->soft.rfc1201.split_flag = 0; @@ -484,9 +488,9 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, out->numsegs = (out->dataleft + maxsegsize - 1) / maxsegsize; out->segnum = 0; - BUGMSG(D_DURING, "rfc1201 prep_tx: ready for %d-segment split (%d bytes, seq=%d)\n", - out->numsegs, out->length, - pkt->soft.rfc1201.sequence); + arc_printk(D_DURING, dev, "rfc1201 prep_tx: ready for %d-segment split (%d bytes, seq=%d)\n", + out->numsegs, out->length, + pkt->soft.rfc1201.sequence); return 0; /* not done */ } @@ -505,9 +509,9 @@ static int continue_tx(struct net_device *dev, int bufnum) int maxsegsize = XMTU - RFC1201_HDR_SIZE; int seglen; - BUGMSG(D_DURING, - "rfc1201 continue_tx: loading segment %d(+1) of %d (seq=%d)\n", - out->segnum, out->numsegs, soft->sequence); + arc_printk(D_DURING, dev, + "rfc1201 continue_tx: loading segment %d(+1) of %d (seq=%d)\n", + out->segnum, out->numsegs, soft->sequence); /* the "new" soft header comes right before the data chunk */ newsoft = (struct arc_rfc1201 *) diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index f07c66383b88..a678027ff6c2 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -81,34 +81,36 @@ extern int arcnet_debug; #define BUGLVL(x) ((x) & ARCNET_DEBUG_MAX & arcnet_debug) /* macros to simplify debug checking */ -#define BUGMSG(x, fmt, ...) \ +#define arc_printk(x, dev, fmt, ...) \ do { \ - if (BUGLVL(x)) \ - printk("%s%6s: " fmt, \ - (x) == D_NORMAL ? KERN_WARNING : \ - (x) < D_DURING ? KERN_INFO : KERN_DEBUG, \ - dev->name, ##__VA_ARGS__); \ + if (BUGLVL(x)) { \ + if ((x) == D_NORMAL) \ + netdev_warn(dev, fmt, ##__VA_ARGS__); \ + else if ((x) < D_DURING) \ + netdev_info(dev, fmt, ##__VA_ARGS__); \ + else \ + netdev_dbg(dev, fmt, ##__VA_ARGS__); \ + } \ } while (0) -#define BUGMSG2(x, fmt, ...) \ +#define arc_cont(x, fmt, ...) \ do { \ - if (BUGLVL(x)) \ - printk(fmt, ##__VA_ARGS__); \ + if (BUGLVL(x)) \ + pr_cont(fmt, ##__VA_ARGS__); \ } while (0) /* see how long a function call takes to run, expressed in CPU cycles */ -#define TIME(name, bytes, call) \ +#define TIME(dev, name, bytes, call) \ do { \ if (BUGLVL(D_TIMING)) { \ unsigned long _x, _y; \ _x = get_cycles(); \ call; \ _y = get_cycles(); \ - BUGMSG(D_TIMING, \ - "%s: %d bytes in %lu cycles == " \ - "%lu Kbytes/100Mcycle\n", \ - name, bytes, _y - _x, \ - 100000000 / 1024 * bytes / (_y - _x + 1)); \ + arc_printk(D_TIMING, dev, \ + "%s: %d bytes in %lu cycles == %lu Kbytes/100Mcycle\n", \ + name, bytes, _y - _x, \ + 100000000 / 1024 * bytes / (_y - _x + 1)); \ } else { \ call; \ } \ -- cgit v1.2.3 From 83df99b50f901cb7c72cf132a83f43bbaeb01362 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:06:01 -0700 Subject: arcnet: Convert arcnet_dump_skb macro to static inline Make sure the arguments are tested appropriately when not using this function. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/linux/arcdevice.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index a678027ff6c2..1d8e36e13616 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -326,7 +326,10 @@ struct arcnet_local { #if ARCNET_DEBUG_MAX & D_SKB void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); #else -#define arcnet_dump_skb(dev, skb, desc) ; +static inline +void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc) +{ +} #endif void arcnet_unregister_proto(struct ArcProto *proto); -- cgit v1.2.3 From d6d7d3ed56e3bfe7fd34108dbe23f0610e3d8621 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:06:02 -0700 Subject: arcnet: Wrap some long lines Just neatening. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- drivers/net/arcnet/arc-rawmode.c | 3 ++- drivers/net/arcnet/arc-rimi.c | 11 ++++++----- drivers/net/arcnet/arcnet.c | 10 +++++++--- drivers/net/arcnet/capmode.c | 3 ++- drivers/net/arcnet/com20020-pci.c | 3 ++- drivers/net/arcnet/com20020.c | 14 ++++++++------ drivers/net/arcnet/com90io.c | 31 +++++++++++++++++++------------ drivers/net/arcnet/com90xx.c | 28 +++++++++++++++++----------- drivers/net/arcnet/rfc1051.c | 3 ++- drivers/net/arcnet/rfc1201.c | 15 ++++++++++----- include/linux/arcdevice.h | 12 ++++++------ 11 files changed, 81 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/drivers/net/arcnet/arc-rawmode.c b/drivers/net/arcnet/arc-rawmode.c index 40035ee8cb40..59b3083c19f9 100644 --- a/drivers/net/arcnet/arc-rawmode.c +++ b/drivers/net/arcnet/arc-rawmode.c @@ -165,7 +165,8 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, arc_printk(D_DURING, dev, "prepare_tx: txbufs=%d/%d/%d\n", lp->next_tx, lp->cur_tx, bufnum); - length -= ARC_HDR_SIZE; /* hard header is not included in packet length */ + /* hard header is not included in packet length */ + length -= ARC_HDR_SIZE; if (length > XMTU) { /* should never happen! other people already check for this. */ diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index 7360214e3d3f..8fa5eb43f308 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -49,8 +49,8 @@ static void arcrimi_setmask(struct net_device *dev, int mask); static int arcrimi_reset(struct net_device *dev, int really_reset); static void arcrimi_copy_to_card(struct net_device *dev, int bufnum, int offset, void *buf, int count); -static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count); +static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count); /* Handy defines for ARCnet specific stuff */ @@ -215,7 +215,8 @@ static int __init arcrimi_found(struct net_device *dev) goto err_free_irq; } - lp->mem_start = ioremap(dev->mem_start, dev->mem_end - dev->mem_start + 1); + lp->mem_start = ioremap(dev->mem_start, + dev->mem_end - dev->mem_start + 1); if (!lp->mem_start) { arc_printk(D_NORMAL, dev, "Can't remap device memory!\n"); goto err_release_mem; @@ -307,8 +308,8 @@ static void arcrimi_copy_to_card(struct net_device *dev, int bufnum, int offset, TIME(dev, "memcpy_toio", count, memcpy_toio(memaddr, buf, count)); } -static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count) +static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count) { struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + 0x800 + bufnum * 512 + offset; diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index a9535ec9c236..00074e781353 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -759,7 +759,8 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) if ((status & lp->intmask & TXFREEflag) || lp->timed_out) { lp->intmask &= ~(TXFREEflag | EXCNAKflag); - arc_printk(D_DURING, dev, "TX IRQ (stat=%Xh)\n", status); + arc_printk(D_DURING, dev, "TX IRQ (stat=%Xh)\n", + status); if (lp->cur_tx != -1 && !lp->timed_out) { if (!(status & TXACKflag)) { @@ -804,7 +805,8 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) go_tx(dev); /* continue a split packet, if any */ - if (lp->outgoing.proto && lp->outgoing.proto->continue_tx) { + if (lp->outgoing.proto && + lp->outgoing.proto->continue_tx) { int txbuf = get_arcbuf(dev); if (txbuf != -1) { @@ -874,7 +876,9 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) arc_printk(D_NORMAL, dev, "many reconfigurations detected: cabling problem?\n"); } else if (!lp->network_down && lp->last_recon - lp->first_recon > HZ * 60) { - /* reset counters if we've gone for over a minute. */ + /* reset counters if we've gone for + * over a minute. + */ lp->first_recon = lp->last_recon; lp->num_recons = 1; } diff --git a/drivers/net/arcnet/capmode.c b/drivers/net/arcnet/capmode.c index a898647ab05d..46a76dcc21aa 100644 --- a/drivers/net/arcnet/capmode.c +++ b/drivers/net/arcnet/capmode.c @@ -222,7 +222,8 @@ static int ack_tx(struct net_device *dev, int acked) free_outskb: dev_kfree_skb_irq(lp->outgoing.skb); - lp->outgoing.proto = NULL; /* We are always finished when in this protocol */ + lp->outgoing.proto = NULL; + /* We are always finished when in this protocol */ return 0; } diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index fc6809b43f8f..a28887dfcc9e 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -64,7 +64,8 @@ MODULE_LICENSE("GPL"); static void com20020pci_remove(struct pci_dev *pdev); -static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +static int com20020pci_probe(struct pci_dev *pdev, + const struct pci_device_id *id) { struct com20020_pci_card_info *ci; struct net_device *dev; diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c index bea386222149..00f910cf7b81 100644 --- a/drivers/net/arcnet/com20020.c +++ b/drivers/net/arcnet/com20020.c @@ -192,8 +192,9 @@ int com20020_found(struct net_device *dev, int shared) lp->hw.copy_from_card = com20020_copy_from_card; lp->hw.close = com20020_close; + /* FIXME: do this some other way! */ if (!dev->dev_addr[0]) - dev->dev_addr[0] = inb(ioaddr + BUS_ALIGN * 8); /* FIXME: do this some other way! */ + dev->dev_addr[0] = inb(ioaddr + BUS_ALIGN * 8); SET_SUBADR(SUB_SETUP1); outb(lp->setup, _XREG); @@ -269,7 +270,8 @@ static int com20020_reset(struct net_device *dev, int really_reset) if (really_reset) { /* reset the card */ ARCRESET; - mdelay(RESETtime * 2); /* COM20020 seems to be slower sometimes */ + mdelay(RESETtime * 2); + /* COM20020 seems to be slower sometimes */ } /* clear flags & end reset */ arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); @@ -338,15 +340,15 @@ static void com20020_set_mc_list(struct net_device *dev) struct arcnet_local *lp = netdev_priv(dev); int ioaddr = dev->base_addr; - if ((dev->flags & IFF_PROMISC) && (dev->flags & IFF_UP)) { /* Enable promiscuous mode */ + if ((dev->flags & IFF_PROMISC) && (dev->flags & IFF_UP)) { + /* Enable promiscuous mode */ if (!(lp->setup & PROMISCset)) arc_printk(D_NORMAL, dev, "Setting promiscuous flag...\n"); SET_SUBADR(SUB_SETUP1); lp->setup |= PROMISCset; outb(lp->setup, _XREG); - } else + } else { /* Disable promiscuous mode, use normal mode */ - { if ((lp->setup & PROMISCset)) arc_printk(D_NORMAL, dev, "Resetting promiscuous flag...\n"); SET_SUBADR(SUB_SETUP1); @@ -370,7 +372,7 @@ MODULE_LICENSE("GPL"); static int __init com20020_module_init(void) { if (BUGLVL(D_NORMAL)) - pr_info("%s\n", "COM20020 chipset support (by David Woodhouse et al.)\n"); + pr_info("%s\n", "COM20020 chipset support (by David Woodhouse et al.)"); return 0; } diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 11bc589aa8d1..9e779a53035d 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -49,8 +49,8 @@ static void com90io_setmask(struct net_device *dev, int mask); static int com90io_reset(struct net_device *dev, int really_reset); static void com90io_copy_to_card(struct net_device *dev, int bufnum, int offset, void *buf, int count); -static void com90io_copy_from_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count); +static void com90io_copy_from_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count); /* Handy defines for ARCnet specific stuff */ @@ -96,7 +96,8 @@ static u_char get_buffer_byte(struct net_device *dev, unsigned offset) } #ifdef ONE_AT_A_TIME_TX -static void put_buffer_byte(struct net_device *dev, unsigned offset, u_char datum) +static void put_buffer_byte(struct net_device *dev, unsigned offset, + u_char datum) { int ioaddr = dev->base_addr; @@ -108,7 +109,8 @@ static void put_buffer_byte(struct net_device *dev, unsigned offset, u_char datu #endif -static void get_whole_buffer(struct net_device *dev, unsigned offset, unsigned length, char *dest) +static void get_whole_buffer(struct net_device *dev, unsigned offset, + unsigned length, char *dest) { int ioaddr = dev->base_addr; @@ -123,7 +125,8 @@ static void get_whole_buffer(struct net_device *dev, unsigned offset, unsigned l #endif } -static void put_whole_buffer(struct net_device *dev, unsigned offset, unsigned length, char *dest) +static void put_whole_buffer(struct net_device *dev, unsigned offset, + unsigned length, char *dest) { int ioaddr = dev->base_addr; @@ -237,12 +240,14 @@ static int __init com90io_found(struct net_device *dev) int err; /* Reserve the irq */ - if (request_irq(dev->irq, arcnet_interrupt, 0, "arcnet (COM90xx-IO)", dev)) { + if (request_irq(dev->irq, arcnet_interrupt, 0, + "arcnet (COM90xx-IO)", dev)) { arc_printk(D_NORMAL, dev, "Can't get IRQ %d!\n", dev->irq); return -ENODEV; } /* Reserve the I/O region */ - if (!request_region(dev->base_addr, ARCNET_TOTAL_SIZE, "arcnet (COM90xx-IO)")) { + if (!request_region(dev->base_addr, ARCNET_TOTAL_SIZE, + "arcnet (COM90xx-IO)")) { free_irq(dev->irq, dev); return -EBUSY; } @@ -338,15 +343,15 @@ static void com90io_setmask(struct net_device *dev, int mask) AINTMASK(mask); } -static void com90io_copy_to_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count) +static void com90io_copy_to_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count) { TIME(dev, "put_whole_buffer", count, put_whole_buffer(dev, bufnum * 512 + offset, count, buf)); } -static void com90io_copy_from_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count) +static void com90io_copy_from_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count) { TIME(dev, "get_whole_buffer", count, get_whole_buffer(dev, bufnum * 512 + offset, count, buf)); @@ -418,7 +423,9 @@ static void __exit com90io_exit(void) unregister_netdev(dev); - /* Set the thing back to MMAP mode, in case the old driver is loaded later */ + /* In case the old driver is loaded later, + * set the thing back to MMAP mode + */ outb((inb(_CONFIG) & ~IOMAPflag), _CONFIG); free_irq(dev->irq, dev); diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index 50c346b5d907..62100acfb6a7 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -60,8 +60,8 @@ static void com90xx_setmask(struct net_device *dev, int mask); static int com90xx_reset(struct net_device *dev, int really_reset); static void com90xx_copy_to_card(struct net_device *dev, int bufnum, int offset, void *buf, int count); -static void com90xx_copy_from_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count); +static void com90xx_copy_from_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count); /* Known ARCnet cards */ @@ -165,7 +165,8 @@ static void __init com90xx_probe(void) ioaddr = *port; - if (!request_region(*port, ARCNET_TOTAL_SIZE, "arcnet (90xx)")) { + if (!request_region(*port, ARCNET_TOTAL_SIZE, + "arcnet (90xx)")) { arc_cont(D_INIT_REASONS, "(request_region)\n"); arc_cont(D_INIT_REASONS, "S1: "); if (BUGLVL(D_INIT_REASONS)) @@ -467,7 +468,8 @@ static int check_mirror(unsigned long addr, size_t size) /* Set up the struct net_device associated with this card. Called after * probing succeeds. */ -static int __init com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem *p) +static int __init com90xx_found(int ioaddr, int airq, u_long shmem, + void __iomem *p) { struct net_device *dev = NULL; struct arcnet_local *lp; @@ -511,7 +513,9 @@ static int __init com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem iounmap(p); release_mem_region(shmem, MIRROR_SIZE); - if (!request_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1, "arcnet (90xx)")) + if (!request_mem_region(dev->mem_start, + dev->mem_end - dev->mem_start + 1, + "arcnet (90xx)")) goto err_free_dev; /* reserve the irq */ @@ -530,7 +534,8 @@ static int __init com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem lp->hw.owner = THIS_MODULE; lp->hw.copy_to_card = com90xx_copy_to_card; lp->hw.copy_from_card = com90xx_copy_from_card; - lp->mem_start = ioremap(dev->mem_start, dev->mem_end - dev->mem_start + 1); + lp->mem_start = ioremap(dev->mem_start, + dev->mem_end - dev->mem_start + 1); if (!lp->mem_start) { arc_printk(D_NORMAL, dev, "Can't remap device memory!\n"); goto err_free_irq; @@ -627,8 +632,8 @@ static int com90xx_reset(struct net_device *dev, int really_reset) return 0; } -static void com90xx_copy_to_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count) +static void com90xx_copy_to_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count) { struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + bufnum * 512 + offset; @@ -636,8 +641,8 @@ static void com90xx_copy_to_card(struct net_device *dev, int bufnum, int offset, TIME(dev, "memcpy_toio", count, memcpy_toio(memaddr, buf, count)); } -static void com90xx_copy_from_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count) +static void com90xx_copy_from_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count) { struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + bufnum * 512 + offset; @@ -671,7 +676,8 @@ static void __exit com90xx_exit(void) free_irq(dev->irq, dev); iounmap(lp->mem_start); release_region(dev->base_addr, ARCNET_TOTAL_SIZE); - release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1); + release_mem_region(dev->mem_start, + dev->mem_end - dev->mem_start + 1); free_netdev(dev); } } diff --git a/drivers/net/arcnet/rfc1051.c b/drivers/net/arcnet/rfc1051.c index b76e458b19e0..691bee5bcd42 100644 --- a/drivers/net/arcnet/rfc1051.c +++ b/drivers/net/arcnet/rfc1051.c @@ -213,7 +213,8 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, arc_printk(D_DURING, dev, "prepare_tx: txbufs=%d/%d/%d\n", lp->next_tx, lp->cur_tx, bufnum); - length -= ARC_HDR_SIZE; /* hard header is not included in packet length */ + /* hard header is not included in packet length */ + length -= ARC_HDR_SIZE; if (length > XMTU) { /* should never happen! other people already check for this. */ diff --git a/drivers/net/arcnet/rfc1201.c b/drivers/net/arcnet/rfc1201.c index 1d777c1e8383..aaa1966593aa 100644 --- a/drivers/net/arcnet/rfc1201.c +++ b/drivers/net/arcnet/rfc1201.c @@ -188,11 +188,14 @@ static void rx(struct net_device *dev, int bufnum, pkt = (struct archdr *)skb->data; soft = &pkt->soft.rfc1201; - /* up to sizeof(pkt->soft) has already been copied from the card */ + /* up to sizeof(pkt->soft) has already + * been copied from the card + */ memcpy(pkt, pkthdr, sizeof(struct archdr)); if (length > sizeof(pkt->soft)) - lp->hw.copy_from_card(dev, bufnum, ofs + sizeof(pkt->soft), - pkt->soft.raw + sizeof(pkt->soft), + lp->hw.copy_from_card(dev, bufnum, + ofs + sizeof(pkt->soft), + pkt->soft.raw + sizeof(pkt->soft), length - sizeof(pkt->soft)); /* ARP packets have problems when sent from some DOS systems: @@ -318,7 +321,8 @@ static void rx(struct net_device *dev, int bufnum, return; } in->lastpacket++; - if (packetnum != in->lastpacket) { /* not the right flag! */ + /* if not the right flag */ + if (packetnum != in->lastpacket) { /* harmless duplicate? ignore. */ if (packetnum <= in->lastpacket - 1) { arc_printk(D_EXTRA, dev, "duplicate splitpacket ignored! (splitflag=%d)\n", @@ -477,7 +481,8 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, arc_printk(D_DURING, dev, "prepare_tx: txbufs=%d/%d/%d\n", lp->next_tx, lp->cur_tx, bufnum); - length -= ARC_HDR_SIZE; /* hard header is not included in packet length */ + /* hard header is not included in packet length */ + length -= ARC_HDR_SIZE; pkt->soft.rfc1201.split_flag = 0; /* need to do a split packet? */ diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index 1d8e36e13616..9ca135d0f114 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -203,8 +203,8 @@ struct ArcProto { unsigned short ethproto, uint8_t daddr); /* these functions return '1' if the skb can now be freed */ - int (*prepare_tx)(struct net_device *dev, struct archdr *pkt, int length, - int bufnum); + int (*prepare_tx)(struct net_device *dev, struct archdr *pkt, + int length, int bufnum); int (*continue_tx)(struct net_device *dev, int bufnum); int (*ack_tx)(struct net_device *dev, int acked); }; @@ -309,10 +309,10 @@ struct arcnet_local { void (*open)(struct net_device *dev); void (*close)(struct net_device *dev); - void (*copy_to_card)(struct net_device *dev, int bufnum, int offset, - void *buf, int count); - void (*copy_from_card)(struct net_device *dev, int bufnum, int offset, - void *buf, int count); + void (*copy_to_card)(struct net_device *dev, int bufnum, + int offset, void *buf, int count); + void (*copy_from_card)(struct net_device *dev, int bufnum, + int offset, void *buf, int count); } hw; void __iomem *mem_start; /* pointer to ioremap'ed MMIO */ -- cgit v1.2.3 From 26c6d281688e8bb8154fa78c60e551d024f5d0b8 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:06:03 -0700 Subject: arcnet: Move files out of include/linux These #include files don't need to be in the include/linux directory as they can be local to drivers/net/arcnet/ Move them and update the #include statements. Update the MAINTAINERS file pattern by deleting arcdevice from the NETWORKING block as arcnet is currently unmaintained. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- MAINTAINERS | 1 - drivers/net/arcnet/arc-rawmode.c | 3 +- drivers/net/arcnet/arc-rimi.c | 3 +- drivers/net/arcnet/arcdevice.h | 346 ++++++++++++++++++++++++++++++++++++++ drivers/net/arcnet/arcnet.c | 3 +- drivers/net/arcnet/capmode.c | 3 +- drivers/net/arcnet/com20020-isa.c | 6 +- drivers/net/arcnet/com20020-pci.c | 6 +- drivers/net/arcnet/com20020.c | 6 +- drivers/net/arcnet/com20020.h | 145 ++++++++++++++++ drivers/net/arcnet/com20020_cs.c | 7 +- drivers/net/arcnet/com90io.c | 3 +- drivers/net/arcnet/com90xx.c | 3 +- drivers/net/arcnet/rfc1051.c | 3 +- drivers/net/arcnet/rfc1201.c | 3 +- include/linux/arcdevice.h | 346 -------------------------------------- include/linux/com20020.h | 145 ---------------- 17 files changed, 519 insertions(+), 513 deletions(-) create mode 100644 drivers/net/arcnet/arcdevice.h create mode 100644 drivers/net/arcnet/com20020.h delete mode 100644 include/linux/arcdevice.h delete mode 100644 include/linux/com20020.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 310da4295c70..c978a257f4aa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7292,7 +7292,6 @@ S: Odd Fixes F: drivers/net/ F: include/linux/if_* F: include/linux/netdevice.h -F: include/linux/arcdevice.h F: include/linux/etherdevice.h F: include/linux/fcdevice.h F: include/linux/fddidevice.h diff --git a/drivers/net/arcnet/arc-rawmode.c b/drivers/net/arcnet/arc-rawmode.c index 59b3083c19f9..35a747a7329e 100644 --- a/drivers/net/arcnet/arc-rawmode.c +++ b/drivers/net/arcnet/arc-rawmode.c @@ -33,7 +33,8 @@ #include #include #include -#include + +#include "arcdevice.h" static void rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length); diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index 8fa5eb43f308..37406fffc001 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -37,7 +37,8 @@ #include #include #include -#include + +#include "arcdevice.h" /* Internal function declarations */ diff --git a/drivers/net/arcnet/arcdevice.h b/drivers/net/arcnet/arcdevice.h new file mode 100644 index 000000000000..9ca135d0f114 --- /dev/null +++ b/drivers/net/arcnet/arcdevice.h @@ -0,0 +1,346 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. NET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Definitions used by the ARCnet driver. + * + * Authors: Avery Pennarun and David Woodhouse + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ +#ifndef _LINUX_ARCDEVICE_H +#define _LINUX_ARCDEVICE_H + +#include +#include + +#ifdef __KERNEL__ +#include + +/* + * RECON_THRESHOLD is the maximum number of RECON messages to receive + * within one minute before printing a "cabling problem" warning. The + * default value should be fine. + * + * After that, a "cabling restored" message will be printed on the next IRQ + * if no RECON messages have been received for 10 seconds. + * + * Do not define RECON_THRESHOLD at all if you want to disable this feature. + */ +#define RECON_THRESHOLD 30 + +/* + * Define this to the minimum "timeout" value. If a transmit takes longer + * than TX_TIMEOUT jiffies, Linux will abort the TX and retry. On a large + * network, or one with heavy network traffic, this timeout may need to be + * increased. The larger it is, though, the longer it will be between + * necessary transmits - don't set this too high. + */ +#define TX_TIMEOUT (HZ * 200 / 1000) + +/* Display warnings about the driver being an ALPHA version. */ +#undef ALPHA_WARNING + +/* + * Debugging bitflags: each option can be enabled individually. + * + * Note: only debug flags included in the ARCNET_DEBUG_MAX define will + * actually be available. GCC will (at least, GCC 2.7.0 will) notice + * lines using a BUGLVL not in ARCNET_DEBUG_MAX and automatically optimize + * them out. + */ +#define D_NORMAL 1 /* important operational info */ +#define D_EXTRA 2 /* useful, but non-vital information */ +#define D_INIT 4 /* show init/probe messages */ +#define D_INIT_REASONS 8 /* show reasons for discarding probes */ +#define D_RECON 32 /* print a message whenever token is lost */ +#define D_PROTO 64 /* debug auto-protocol support */ +/* debug levels below give LOTS of output during normal operation! */ +#define D_DURING 128 /* trace operations (including irq's) */ +#define D_TX 256 /* show tx packets */ +#define D_RX 512 /* show rx packets */ +#define D_SKB 1024 /* show skb's */ +#define D_SKB_SIZE 2048 /* show skb sizes */ +#define D_TIMING 4096 /* show time needed to copy buffers to card */ +#define D_DEBUG 8192 /* Very detailed debug line for line */ + +#ifndef ARCNET_DEBUG_MAX +#define ARCNET_DEBUG_MAX (127) /* change to ~0 if you want detailed debugging */ +#endif + +#ifndef ARCNET_DEBUG +#define ARCNET_DEBUG (D_NORMAL | D_EXTRA) +#endif +extern int arcnet_debug; + +#define BUGLVL(x) ((x) & ARCNET_DEBUG_MAX & arcnet_debug) + +/* macros to simplify debug checking */ +#define arc_printk(x, dev, fmt, ...) \ +do { \ + if (BUGLVL(x)) { \ + if ((x) == D_NORMAL) \ + netdev_warn(dev, fmt, ##__VA_ARGS__); \ + else if ((x) < D_DURING) \ + netdev_info(dev, fmt, ##__VA_ARGS__); \ + else \ + netdev_dbg(dev, fmt, ##__VA_ARGS__); \ + } \ +} while (0) + +#define arc_cont(x, fmt, ...) \ +do { \ + if (BUGLVL(x)) \ + pr_cont(fmt, ##__VA_ARGS__); \ +} while (0) + +/* see how long a function call takes to run, expressed in CPU cycles */ +#define TIME(dev, name, bytes, call) \ +do { \ + if (BUGLVL(D_TIMING)) { \ + unsigned long _x, _y; \ + _x = get_cycles(); \ + call; \ + _y = get_cycles(); \ + arc_printk(D_TIMING, dev, \ + "%s: %d bytes in %lu cycles == %lu Kbytes/100Mcycle\n", \ + name, bytes, _y - _x, \ + 100000000 / 1024 * bytes / (_y - _x + 1)); \ + } else { \ + call; \ + } \ +} while (0) + +/* + * Time needed to reset the card - in ms (milliseconds). This works on my + * SMC PC100. I can't find a reference that tells me just how long I + * should wait. + */ +#define RESETtime (300) + +/* + * These are the max/min lengths of packet payload, not including the + * arc_hardware header, but definitely including the soft header. + * + * Note: packet sizes 254, 255, 256 are impossible because of the way + * ARCnet registers work That's why RFC1201 defines "exception" packets. + * In non-RFC1201 protocols, we have to just tack some extra bytes on the + * end. + */ +#define MTU 253 /* normal packet max size */ +#define MinTU 257 /* extended packet min size */ +#define XMTU 508 /* extended packet max size */ + +/* status/interrupt mask bit fields */ +#define TXFREEflag 0x01 /* transmitter available */ +#define TXACKflag 0x02 /* transmitted msg. ackd */ +#define RECONflag 0x04 /* network reconfigured */ +#define TESTflag 0x08 /* test flag */ +#define EXCNAKflag 0x08 /* excesive nak flag */ +#define RESETflag 0x10 /* power-on-reset */ +#define RES1flag 0x20 /* reserved - usually set by jumper */ +#define RES2flag 0x40 /* reserved - usually set by jumper */ +#define NORXflag 0x80 /* receiver inhibited */ + +/* Flags used for IO-mapped memory operations */ +#define AUTOINCflag 0x40 /* Increase location with each access */ +#define IOMAPflag 0x02 /* (for 90xx) Use IO mapped memory, not mmap */ +#define ENABLE16flag 0x80 /* (for 90xx) Enable 16-bit mode */ + +/* in the command register, the following bits have these meanings: + * 0-2 command + * 3-4 page number (for enable rcv/xmt command) + * 7 receive broadcasts + */ +#define NOTXcmd 0x01 /* disable transmitter */ +#define NORXcmd 0x02 /* disable receiver */ +#define TXcmd 0x03 /* enable transmitter */ +#define RXcmd 0x04 /* enable receiver */ +#define CONFIGcmd 0x05 /* define configuration */ +#define CFLAGScmd 0x06 /* clear flags */ +#define TESTcmd 0x07 /* load test flags */ + +/* flags for "clear flags" command */ +#define RESETclear 0x08 /* power-on-reset */ +#define CONFIGclear 0x10 /* system reconfigured */ + +#define EXCNAKclear 0x0E /* Clear and acknowledge the excive nak bit */ + +/* flags for "load test flags" command */ +#define TESTload 0x08 /* test flag (diagnostic) */ + +/* byte deposited into first address of buffers on reset */ +#define TESTvalue 0321 /* that's octal for 0xD1 :) */ + +/* for "enable receiver" command */ +#define RXbcasts 0x80 /* receive broadcasts */ + +/* flags for "define configuration" command */ +#define NORMALconf 0x00 /* 1-249 byte packets */ +#define EXTconf 0x08 /* 250-504 byte packets */ + +/* card feature flags, set during auto-detection. + * (currently only used by com20020pci) + */ +#define ARC_IS_5MBIT 1 /* card default speed is 5MBit */ +#define ARC_CAN_10MBIT 2 /* card uses COM20022, supporting 10MBit, + but default is 2.5MBit. */ + +/* information needed to define an encapsulation driver */ +struct ArcProto { + char suffix; /* a for RFC1201, e for ether-encap, etc. */ + int mtu; /* largest possible packet */ + int is_ip; /* This is a ip plugin - not a raw thing */ + + void (*rx)(struct net_device *dev, int bufnum, + struct archdr *pkthdr, int length); + int (*build_header)(struct sk_buff *skb, struct net_device *dev, + unsigned short ethproto, uint8_t daddr); + + /* these functions return '1' if the skb can now be freed */ + int (*prepare_tx)(struct net_device *dev, struct archdr *pkt, + int length, int bufnum); + int (*continue_tx)(struct net_device *dev, int bufnum); + int (*ack_tx)(struct net_device *dev, int acked); +}; + +extern struct ArcProto *arc_proto_map[256], *arc_proto_default, + *arc_bcast_proto, *arc_raw_proto; + +/* + * "Incoming" is information needed for each address that could be sending + * to us. Mostly for partially-received split packets. + */ +struct Incoming { + struct sk_buff *skb; /* packet data buffer */ + __be16 sequence; /* sequence number of assembly */ + uint8_t lastpacket, /* number of last packet (from 1) */ + numpackets; /* number of packets in split */ +}; + +/* only needed for RFC1201 */ +struct Outgoing { + struct ArcProto *proto; /* protocol driver that owns this: + * if NULL, no packet is pending. + */ + struct sk_buff *skb; /* buffer from upper levels */ + struct archdr *pkt; /* a pointer into the skb */ + uint16_t length, /* bytes total */ + dataleft, /* bytes left */ + segnum, /* segment being sent */ + numsegs; /* number of segments */ +}; + +struct arcnet_local { + uint8_t config, /* current value of CONFIG register */ + timeout, /* Extended timeout for COM20020 */ + backplane, /* Backplane flag for COM20020 */ + clockp, /* COM20020 clock divider */ + clockm, /* COM20020 clock multiplier flag */ + setup, /* Contents of setup1 register */ + setup2, /* Contents of setup2 register */ + intmask; /* current value of INTMASK register */ + uint8_t default_proto[256]; /* default encap to use for each host */ + int cur_tx, /* buffer used by current transmit, or -1 */ + next_tx, /* buffer where a packet is ready to send */ + cur_rx; /* current receive buffer */ + int lastload_dest, /* can last loaded packet be acked? */ + lasttrans_dest; /* can last TX'd packet be acked? */ + int timed_out; /* need to process TX timeout and drop packet */ + unsigned long last_timeout; /* time of last reported timeout */ + char *card_name; /* card ident string */ + int card_flags; /* special card features */ + + /* On preemtive and SMB a lock is needed */ + spinlock_t lock; + + /* + * Buffer management: an ARCnet card has 4 x 512-byte buffers, each of + * which can be used for either sending or receiving. The new dynamic + * buffer management routines use a simple circular queue of available + * buffers, and take them as they're needed. This way, we simplify + * situations in which we (for example) want to pre-load a transmit + * buffer, or start receiving while we copy a received packet to + * memory. + * + * The rules: only the interrupt handler is allowed to _add_ buffers to + * the queue; thus, this doesn't require a lock. Both the interrupt + * handler and the transmit function will want to _remove_ buffers, so + * we need to handle the situation where they try to do it at the same + * time. + * + * If next_buf == first_free_buf, the queue is empty. Since there are + * only four possible buffers, the queue should never be full. + */ + atomic_t buf_lock; + int buf_queue[5]; + int next_buf, first_free_buf; + + /* network "reconfiguration" handling */ + unsigned long first_recon; /* time of "first" RECON message to count */ + unsigned long last_recon; /* time of most recent RECON */ + int num_recons; /* number of RECONs between first and last. */ + int network_down; /* do we think the network is down? */ + + int excnak_pending; /* We just got an excesive nak interrupt */ + + struct { + uint16_t sequence; /* sequence number (incs with each packet) */ + __be16 aborted_seq; + + struct Incoming incoming[256]; /* one from each address */ + } rfc1201; + + /* really only used by rfc1201, but we'll pretend it's not */ + struct Outgoing outgoing; /* packet currently being sent */ + + /* hardware-specific functions */ + struct { + struct module *owner; + void (*command)(struct net_device *dev, int cmd); + int (*status)(struct net_device *dev); + void (*intmask)(struct net_device *dev, int mask); + int (*reset)(struct net_device *dev, int really_reset); + void (*open)(struct net_device *dev); + void (*close)(struct net_device *dev); + + void (*copy_to_card)(struct net_device *dev, int bufnum, + int offset, void *buf, int count); + void (*copy_from_card)(struct net_device *dev, int bufnum, + int offset, void *buf, int count); + } hw; + + void __iomem *mem_start; /* pointer to ioremap'ed MMIO */ +}; + +#define ARCRESET(x) (lp->hw.reset(dev, (x))) +#define ACOMMAND(x) (lp->hw.command(dev, (x))) +#define ASTATUS() (lp->hw.status(dev)) +#define AINTMASK(x) (lp->hw.intmask(dev, (x))) + +#if ARCNET_DEBUG_MAX & D_SKB +void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); +#else +static inline +void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc) +{ +} +#endif + +void arcnet_unregister_proto(struct ArcProto *proto); +irqreturn_t arcnet_interrupt(int irq, void *dev_id); +struct net_device *alloc_arcdev(const char *name); + +int arcnet_open(struct net_device *dev); +int arcnet_close(struct net_device *dev); +netdev_tx_t arcnet_send_packet(struct sk_buff *skb, + struct net_device *dev); +void arcnet_timeout(struct net_device *dev); + +#endif /* __KERNEL__ */ +#endif /* _LINUX_ARCDEVICE_H */ diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index 00074e781353..c8423ee24e71 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -50,9 +50,10 @@ #include #include #include -#include #include +#include "arcdevice.h" + /* "do nothing" functions for protocol drivers */ static void null_rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length); diff --git a/drivers/net/arcnet/capmode.c b/drivers/net/arcnet/capmode.c index 46a76dcc21aa..2f2d0d94a80d 100644 --- a/drivers/net/arcnet/capmode.c +++ b/drivers/net/arcnet/capmode.c @@ -35,7 +35,8 @@ #include #include #include -#include + +#include "arcdevice.h" /* packet receiver */ static void rx(struct net_device *dev, int bufnum, diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index 352500b8d875..ab5202b506a6 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -39,11 +39,11 @@ #include #include #include -#include -#include - #include +#include "arcdevice.h" +#include "com20020.h" + /* We cannot (yet) probe for an IO mapped card, although we can check that * it's where we were told it was, and even do autoirq. */ diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index a28887dfcc9e..1a75a6982031 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -39,12 +39,12 @@ #include #include #include -#include -#include #include - #include +#include "arcdevice.h" +#include "com20020.h" + /* Module parameters */ static int node; diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c index 00f910cf7b81..f46e22093c54 100644 --- a/drivers/net/arcnet/com20020.c +++ b/drivers/net/arcnet/com20020.c @@ -37,11 +37,11 @@ #include #include #include -#include -#include - #include +#include "arcdevice.h" +#include "com20020.h" + static char *clockrates[] = { "XXXXXXX", "XXXXXXXX", "XXXXXX", "2.5 Mb/s", "1.25Mb/s", "625 Kb/s", "312.5 Kb/s", diff --git a/drivers/net/arcnet/com20020.h b/drivers/net/arcnet/com20020.h new file mode 100644 index 000000000000..85898995b234 --- /dev/null +++ b/drivers/net/arcnet/com20020.h @@ -0,0 +1,145 @@ +/* + * Linux ARCnet driver - COM20020 chipset support - function declarations + * + * Written 1997 by David Woodhouse. + * Written 1994-1999 by Avery Pennarun. + * Derived from skeleton.c by Donald Becker. + * + * Special thanks to Contemporary Controls, Inc. (www.ccontrols.com) + * for sponsoring the further development of this driver. + * + * ********************** + * + * The original copyright of skeleton.c was as follows: + * + * skeleton.c Written 1993 by Donald Becker. + * Copyright 1993 United States Government as represented by the + * Director, National Security Agency. This software may only be used + * and distributed according to the terms of the GNU General Public License as + * modified by SRC, incorporated herein by reference. + * + * ********************** + * + * For more details, see drivers/net/arcnet.c + * + * ********************** + */ +#ifndef __COM20020_H +#define __COM20020_H + +int com20020_check(struct net_device *dev); +int com20020_found(struct net_device *dev, int shared); +extern const struct net_device_ops com20020_netdev_ops; + +/* The number of low I/O ports used by the card. */ +#define ARCNET_TOTAL_SIZE 8 + +/* various register addresses */ +#ifdef CONFIG_SA1100_CT6001 +#define BUS_ALIGN 2 /* 8 bit device on a 16 bit bus - needs padding */ +#else +#define BUS_ALIGN 1 +#endif + +#define PLX_PCI_MAX_CARDS 2 + +struct com20020_pci_channel_map { + u32 bar; + u32 offset; + u32 size; /* 0x00 - auto, e.g. length of entire bar */ +}; + +struct com20020_pci_card_info { + const char *name; + int devcount; + + struct com20020_pci_channel_map chan_map_tbl[PLX_PCI_MAX_CARDS]; + + unsigned int flags; +}; + +struct com20020_priv { + struct com20020_pci_card_info *ci; + struct list_head list_dev; +}; + +struct com20020_dev { + struct list_head list; + struct net_device *dev; + + struct com20020_priv *pci_priv; + int index; +}; + +#define _INTMASK (ioaddr+BUS_ALIGN*0) /* writable */ +#define _STATUS (ioaddr+BUS_ALIGN*0) /* readable */ +#define _COMMAND (ioaddr+BUS_ALIGN*1) /* standard arcnet commands */ +#define _DIAGSTAT (ioaddr+BUS_ALIGN*1) /* diagnostic status register */ +#define _ADDR_HI (ioaddr+BUS_ALIGN*2) /* control registers for IO-mapped memory */ +#define _ADDR_LO (ioaddr+BUS_ALIGN*3) +#define _MEMDATA (ioaddr+BUS_ALIGN*4) /* data port for IO-mapped memory */ +#define _SUBADR (ioaddr+BUS_ALIGN*5) /* the extended port _XREG refers to */ +#define _CONFIG (ioaddr+BUS_ALIGN*6) /* configuration register */ +#define _XREG (ioaddr+BUS_ALIGN*7) /* extra registers (indexed by _CONFIG + or _SUBADR) */ + +/* in the ADDR_HI register */ +#define RDDATAflag 0x80 /* next access is a read (not a write) */ + +/* in the DIAGSTAT register */ +#define NEWNXTIDflag 0x02 /* ID to which token is passed has changed */ + +/* in the CONFIG register */ +#define RESETcfg 0x80 /* put card in reset state */ +#define TXENcfg 0x20 /* enable TX */ + +/* in SETUP register */ +#define PROMISCset 0x10 /* enable RCV_ALL */ +#define P1MODE 0x80 /* enable P1-MODE for Backplane */ +#define SLOWARB 0x01 /* enable Slow Arbitration for >=5Mbps */ + +/* COM2002x */ +#define SUB_TENTATIVE 0 /* tentative node ID */ +#define SUB_NODE 1 /* node ID */ +#define SUB_SETUP1 2 /* various options */ +#define SUB_TEST 3 /* test/diag register */ + +/* COM20022 only */ +#define SUB_SETUP2 4 /* sundry options */ +#define SUB_BUSCTL 5 /* bus control options */ +#define SUB_DMACOUNT 6 /* DMA count options */ + +#define SET_SUBADR(x) do { \ + if ((x) < 4) \ + { \ + lp->config = (lp->config & ~0x03) | (x); \ + SETCONF; \ + } \ + else \ + { \ + outb(x, _SUBADR); \ + } \ +} while (0) + +#undef ARCRESET +#undef ASTATUS +#undef ACOMMAND +#undef AINTMASK + +#define ARCRESET { outb(lp->config | 0x80, _CONFIG); \ + udelay(5); \ + outb(lp->config , _CONFIG); \ + } +#define ARCRESET0 { outb(0x18 | 0x80, _CONFIG); \ + udelay(5); \ + outb(0x18 , _CONFIG); \ + } + +#define ASTATUS() inb(_STATUS) +#define ADIAGSTATUS() inb(_DIAGSTAT) +#define ACOMMAND(cmd) outb((cmd),_COMMAND) +#define AINTMASK(msk) outb((msk),_INTMASK) + +#define SETCONF outb(lp->config, _CONFIG) + +#endif /* __COM20020_H */ diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c index 854169489b68..5fdde6946427 100644 --- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -42,13 +42,12 @@ #include #include #include -#include -#include - +#include #include #include -#include +#include "arcdevice.h" +#include "com20020.h" static void regdump(struct net_device *dev) { diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 9e779a53035d..ce15d1911048 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -38,7 +38,8 @@ #include #include #include -#include + +#include "arcdevice.h" /* Internal function declarations */ diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index 62100acfb6a7..b672795acaa7 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -36,7 +36,8 @@ #include #include #include -#include + +#include "arcdevice.h" /* Define this to speed up the autoprobe by assuming if only one io port and * shmem are left in the list at Stage 5, they must correspond to each diff --git a/drivers/net/arcnet/rfc1051.c b/drivers/net/arcnet/rfc1051.c index 691bee5bcd42..4b1a75469cb1 100644 --- a/drivers/net/arcnet/rfc1051.c +++ b/drivers/net/arcnet/rfc1051.c @@ -33,7 +33,8 @@ #include #include #include -#include + +#include "arcdevice.h" static __be16 type_trans(struct sk_buff *skb, struct net_device *dev); static void rx(struct net_device *dev, int bufnum, diff --git a/drivers/net/arcnet/rfc1201.c b/drivers/net/arcnet/rfc1201.c index aaa1966593aa..566da5ecdc9d 100644 --- a/drivers/net/arcnet/rfc1201.c +++ b/drivers/net/arcnet/rfc1201.c @@ -32,7 +32,8 @@ #include #include #include -#include + +#include "arcdevice.h" MODULE_LICENSE("GPL"); diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h deleted file mode 100644 index 9ca135d0f114..000000000000 --- a/include/linux/arcdevice.h +++ /dev/null @@ -1,346 +0,0 @@ -/* - * INET An implementation of the TCP/IP protocol suite for the LINUX - * operating system. NET is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * Definitions used by the ARCnet driver. - * - * Authors: Avery Pennarun and David Woodhouse - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ -#ifndef _LINUX_ARCDEVICE_H -#define _LINUX_ARCDEVICE_H - -#include -#include - -#ifdef __KERNEL__ -#include - -/* - * RECON_THRESHOLD is the maximum number of RECON messages to receive - * within one minute before printing a "cabling problem" warning. The - * default value should be fine. - * - * After that, a "cabling restored" message will be printed on the next IRQ - * if no RECON messages have been received for 10 seconds. - * - * Do not define RECON_THRESHOLD at all if you want to disable this feature. - */ -#define RECON_THRESHOLD 30 - -/* - * Define this to the minimum "timeout" value. If a transmit takes longer - * than TX_TIMEOUT jiffies, Linux will abort the TX and retry. On a large - * network, or one with heavy network traffic, this timeout may need to be - * increased. The larger it is, though, the longer it will be between - * necessary transmits - don't set this too high. - */ -#define TX_TIMEOUT (HZ * 200 / 1000) - -/* Display warnings about the driver being an ALPHA version. */ -#undef ALPHA_WARNING - -/* - * Debugging bitflags: each option can be enabled individually. - * - * Note: only debug flags included in the ARCNET_DEBUG_MAX define will - * actually be available. GCC will (at least, GCC 2.7.0 will) notice - * lines using a BUGLVL not in ARCNET_DEBUG_MAX and automatically optimize - * them out. - */ -#define D_NORMAL 1 /* important operational info */ -#define D_EXTRA 2 /* useful, but non-vital information */ -#define D_INIT 4 /* show init/probe messages */ -#define D_INIT_REASONS 8 /* show reasons for discarding probes */ -#define D_RECON 32 /* print a message whenever token is lost */ -#define D_PROTO 64 /* debug auto-protocol support */ -/* debug levels below give LOTS of output during normal operation! */ -#define D_DURING 128 /* trace operations (including irq's) */ -#define D_TX 256 /* show tx packets */ -#define D_RX 512 /* show rx packets */ -#define D_SKB 1024 /* show skb's */ -#define D_SKB_SIZE 2048 /* show skb sizes */ -#define D_TIMING 4096 /* show time needed to copy buffers to card */ -#define D_DEBUG 8192 /* Very detailed debug line for line */ - -#ifndef ARCNET_DEBUG_MAX -#define ARCNET_DEBUG_MAX (127) /* change to ~0 if you want detailed debugging */ -#endif - -#ifndef ARCNET_DEBUG -#define ARCNET_DEBUG (D_NORMAL | D_EXTRA) -#endif -extern int arcnet_debug; - -#define BUGLVL(x) ((x) & ARCNET_DEBUG_MAX & arcnet_debug) - -/* macros to simplify debug checking */ -#define arc_printk(x, dev, fmt, ...) \ -do { \ - if (BUGLVL(x)) { \ - if ((x) == D_NORMAL) \ - netdev_warn(dev, fmt, ##__VA_ARGS__); \ - else if ((x) < D_DURING) \ - netdev_info(dev, fmt, ##__VA_ARGS__); \ - else \ - netdev_dbg(dev, fmt, ##__VA_ARGS__); \ - } \ -} while (0) - -#define arc_cont(x, fmt, ...) \ -do { \ - if (BUGLVL(x)) \ - pr_cont(fmt, ##__VA_ARGS__); \ -} while (0) - -/* see how long a function call takes to run, expressed in CPU cycles */ -#define TIME(dev, name, bytes, call) \ -do { \ - if (BUGLVL(D_TIMING)) { \ - unsigned long _x, _y; \ - _x = get_cycles(); \ - call; \ - _y = get_cycles(); \ - arc_printk(D_TIMING, dev, \ - "%s: %d bytes in %lu cycles == %lu Kbytes/100Mcycle\n", \ - name, bytes, _y - _x, \ - 100000000 / 1024 * bytes / (_y - _x + 1)); \ - } else { \ - call; \ - } \ -} while (0) - -/* - * Time needed to reset the card - in ms (milliseconds). This works on my - * SMC PC100. I can't find a reference that tells me just how long I - * should wait. - */ -#define RESETtime (300) - -/* - * These are the max/min lengths of packet payload, not including the - * arc_hardware header, but definitely including the soft header. - * - * Note: packet sizes 254, 255, 256 are impossible because of the way - * ARCnet registers work That's why RFC1201 defines "exception" packets. - * In non-RFC1201 protocols, we have to just tack some extra bytes on the - * end. - */ -#define MTU 253 /* normal packet max size */ -#define MinTU 257 /* extended packet min size */ -#define XMTU 508 /* extended packet max size */ - -/* status/interrupt mask bit fields */ -#define TXFREEflag 0x01 /* transmitter available */ -#define TXACKflag 0x02 /* transmitted msg. ackd */ -#define RECONflag 0x04 /* network reconfigured */ -#define TESTflag 0x08 /* test flag */ -#define EXCNAKflag 0x08 /* excesive nak flag */ -#define RESETflag 0x10 /* power-on-reset */ -#define RES1flag 0x20 /* reserved - usually set by jumper */ -#define RES2flag 0x40 /* reserved - usually set by jumper */ -#define NORXflag 0x80 /* receiver inhibited */ - -/* Flags used for IO-mapped memory operations */ -#define AUTOINCflag 0x40 /* Increase location with each access */ -#define IOMAPflag 0x02 /* (for 90xx) Use IO mapped memory, not mmap */ -#define ENABLE16flag 0x80 /* (for 90xx) Enable 16-bit mode */ - -/* in the command register, the following bits have these meanings: - * 0-2 command - * 3-4 page number (for enable rcv/xmt command) - * 7 receive broadcasts - */ -#define NOTXcmd 0x01 /* disable transmitter */ -#define NORXcmd 0x02 /* disable receiver */ -#define TXcmd 0x03 /* enable transmitter */ -#define RXcmd 0x04 /* enable receiver */ -#define CONFIGcmd 0x05 /* define configuration */ -#define CFLAGScmd 0x06 /* clear flags */ -#define TESTcmd 0x07 /* load test flags */ - -/* flags for "clear flags" command */ -#define RESETclear 0x08 /* power-on-reset */ -#define CONFIGclear 0x10 /* system reconfigured */ - -#define EXCNAKclear 0x0E /* Clear and acknowledge the excive nak bit */ - -/* flags for "load test flags" command */ -#define TESTload 0x08 /* test flag (diagnostic) */ - -/* byte deposited into first address of buffers on reset */ -#define TESTvalue 0321 /* that's octal for 0xD1 :) */ - -/* for "enable receiver" command */ -#define RXbcasts 0x80 /* receive broadcasts */ - -/* flags for "define configuration" command */ -#define NORMALconf 0x00 /* 1-249 byte packets */ -#define EXTconf 0x08 /* 250-504 byte packets */ - -/* card feature flags, set during auto-detection. - * (currently only used by com20020pci) - */ -#define ARC_IS_5MBIT 1 /* card default speed is 5MBit */ -#define ARC_CAN_10MBIT 2 /* card uses COM20022, supporting 10MBit, - but default is 2.5MBit. */ - -/* information needed to define an encapsulation driver */ -struct ArcProto { - char suffix; /* a for RFC1201, e for ether-encap, etc. */ - int mtu; /* largest possible packet */ - int is_ip; /* This is a ip plugin - not a raw thing */ - - void (*rx)(struct net_device *dev, int bufnum, - struct archdr *pkthdr, int length); - int (*build_header)(struct sk_buff *skb, struct net_device *dev, - unsigned short ethproto, uint8_t daddr); - - /* these functions return '1' if the skb can now be freed */ - int (*prepare_tx)(struct net_device *dev, struct archdr *pkt, - int length, int bufnum); - int (*continue_tx)(struct net_device *dev, int bufnum); - int (*ack_tx)(struct net_device *dev, int acked); -}; - -extern struct ArcProto *arc_proto_map[256], *arc_proto_default, - *arc_bcast_proto, *arc_raw_proto; - -/* - * "Incoming" is information needed for each address that could be sending - * to us. Mostly for partially-received split packets. - */ -struct Incoming { - struct sk_buff *skb; /* packet data buffer */ - __be16 sequence; /* sequence number of assembly */ - uint8_t lastpacket, /* number of last packet (from 1) */ - numpackets; /* number of packets in split */ -}; - -/* only needed for RFC1201 */ -struct Outgoing { - struct ArcProto *proto; /* protocol driver that owns this: - * if NULL, no packet is pending. - */ - struct sk_buff *skb; /* buffer from upper levels */ - struct archdr *pkt; /* a pointer into the skb */ - uint16_t length, /* bytes total */ - dataleft, /* bytes left */ - segnum, /* segment being sent */ - numsegs; /* number of segments */ -}; - -struct arcnet_local { - uint8_t config, /* current value of CONFIG register */ - timeout, /* Extended timeout for COM20020 */ - backplane, /* Backplane flag for COM20020 */ - clockp, /* COM20020 clock divider */ - clockm, /* COM20020 clock multiplier flag */ - setup, /* Contents of setup1 register */ - setup2, /* Contents of setup2 register */ - intmask; /* current value of INTMASK register */ - uint8_t default_proto[256]; /* default encap to use for each host */ - int cur_tx, /* buffer used by current transmit, or -1 */ - next_tx, /* buffer where a packet is ready to send */ - cur_rx; /* current receive buffer */ - int lastload_dest, /* can last loaded packet be acked? */ - lasttrans_dest; /* can last TX'd packet be acked? */ - int timed_out; /* need to process TX timeout and drop packet */ - unsigned long last_timeout; /* time of last reported timeout */ - char *card_name; /* card ident string */ - int card_flags; /* special card features */ - - /* On preemtive and SMB a lock is needed */ - spinlock_t lock; - - /* - * Buffer management: an ARCnet card has 4 x 512-byte buffers, each of - * which can be used for either sending or receiving. The new dynamic - * buffer management routines use a simple circular queue of available - * buffers, and take them as they're needed. This way, we simplify - * situations in which we (for example) want to pre-load a transmit - * buffer, or start receiving while we copy a received packet to - * memory. - * - * The rules: only the interrupt handler is allowed to _add_ buffers to - * the queue; thus, this doesn't require a lock. Both the interrupt - * handler and the transmit function will want to _remove_ buffers, so - * we need to handle the situation where they try to do it at the same - * time. - * - * If next_buf == first_free_buf, the queue is empty. Since there are - * only four possible buffers, the queue should never be full. - */ - atomic_t buf_lock; - int buf_queue[5]; - int next_buf, first_free_buf; - - /* network "reconfiguration" handling */ - unsigned long first_recon; /* time of "first" RECON message to count */ - unsigned long last_recon; /* time of most recent RECON */ - int num_recons; /* number of RECONs between first and last. */ - int network_down; /* do we think the network is down? */ - - int excnak_pending; /* We just got an excesive nak interrupt */ - - struct { - uint16_t sequence; /* sequence number (incs with each packet) */ - __be16 aborted_seq; - - struct Incoming incoming[256]; /* one from each address */ - } rfc1201; - - /* really only used by rfc1201, but we'll pretend it's not */ - struct Outgoing outgoing; /* packet currently being sent */ - - /* hardware-specific functions */ - struct { - struct module *owner; - void (*command)(struct net_device *dev, int cmd); - int (*status)(struct net_device *dev); - void (*intmask)(struct net_device *dev, int mask); - int (*reset)(struct net_device *dev, int really_reset); - void (*open)(struct net_device *dev); - void (*close)(struct net_device *dev); - - void (*copy_to_card)(struct net_device *dev, int bufnum, - int offset, void *buf, int count); - void (*copy_from_card)(struct net_device *dev, int bufnum, - int offset, void *buf, int count); - } hw; - - void __iomem *mem_start; /* pointer to ioremap'ed MMIO */ -}; - -#define ARCRESET(x) (lp->hw.reset(dev, (x))) -#define ACOMMAND(x) (lp->hw.command(dev, (x))) -#define ASTATUS() (lp->hw.status(dev)) -#define AINTMASK(x) (lp->hw.intmask(dev, (x))) - -#if ARCNET_DEBUG_MAX & D_SKB -void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); -#else -static inline -void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc) -{ -} -#endif - -void arcnet_unregister_proto(struct ArcProto *proto); -irqreturn_t arcnet_interrupt(int irq, void *dev_id); -struct net_device *alloc_arcdev(const char *name); - -int arcnet_open(struct net_device *dev); -int arcnet_close(struct net_device *dev); -netdev_tx_t arcnet_send_packet(struct sk_buff *skb, - struct net_device *dev); -void arcnet_timeout(struct net_device *dev); - -#endif /* __KERNEL__ */ -#endif /* _LINUX_ARCDEVICE_H */ diff --git a/include/linux/com20020.h b/include/linux/com20020.h deleted file mode 100644 index 85898995b234..000000000000 --- a/include/linux/com20020.h +++ /dev/null @@ -1,145 +0,0 @@ -/* - * Linux ARCnet driver - COM20020 chipset support - function declarations - * - * Written 1997 by David Woodhouse. - * Written 1994-1999 by Avery Pennarun. - * Derived from skeleton.c by Donald Becker. - * - * Special thanks to Contemporary Controls, Inc. (www.ccontrols.com) - * for sponsoring the further development of this driver. - * - * ********************** - * - * The original copyright of skeleton.c was as follows: - * - * skeleton.c Written 1993 by Donald Becker. - * Copyright 1993 United States Government as represented by the - * Director, National Security Agency. This software may only be used - * and distributed according to the terms of the GNU General Public License as - * modified by SRC, incorporated herein by reference. - * - * ********************** - * - * For more details, see drivers/net/arcnet.c - * - * ********************** - */ -#ifndef __COM20020_H -#define __COM20020_H - -int com20020_check(struct net_device *dev); -int com20020_found(struct net_device *dev, int shared); -extern const struct net_device_ops com20020_netdev_ops; - -/* The number of low I/O ports used by the card. */ -#define ARCNET_TOTAL_SIZE 8 - -/* various register addresses */ -#ifdef CONFIG_SA1100_CT6001 -#define BUS_ALIGN 2 /* 8 bit device on a 16 bit bus - needs padding */ -#else -#define BUS_ALIGN 1 -#endif - -#define PLX_PCI_MAX_CARDS 2 - -struct com20020_pci_channel_map { - u32 bar; - u32 offset; - u32 size; /* 0x00 - auto, e.g. length of entire bar */ -}; - -struct com20020_pci_card_info { - const char *name; - int devcount; - - struct com20020_pci_channel_map chan_map_tbl[PLX_PCI_MAX_CARDS]; - - unsigned int flags; -}; - -struct com20020_priv { - struct com20020_pci_card_info *ci; - struct list_head list_dev; -}; - -struct com20020_dev { - struct list_head list; - struct net_device *dev; - - struct com20020_priv *pci_priv; - int index; -}; - -#define _INTMASK (ioaddr+BUS_ALIGN*0) /* writable */ -#define _STATUS (ioaddr+BUS_ALIGN*0) /* readable */ -#define _COMMAND (ioaddr+BUS_ALIGN*1) /* standard arcnet commands */ -#define _DIAGSTAT (ioaddr+BUS_ALIGN*1) /* diagnostic status register */ -#define _ADDR_HI (ioaddr+BUS_ALIGN*2) /* control registers for IO-mapped memory */ -#define _ADDR_LO (ioaddr+BUS_ALIGN*3) -#define _MEMDATA (ioaddr+BUS_ALIGN*4) /* data port for IO-mapped memory */ -#define _SUBADR (ioaddr+BUS_ALIGN*5) /* the extended port _XREG refers to */ -#define _CONFIG (ioaddr+BUS_ALIGN*6) /* configuration register */ -#define _XREG (ioaddr+BUS_ALIGN*7) /* extra registers (indexed by _CONFIG - or _SUBADR) */ - -/* in the ADDR_HI register */ -#define RDDATAflag 0x80 /* next access is a read (not a write) */ - -/* in the DIAGSTAT register */ -#define NEWNXTIDflag 0x02 /* ID to which token is passed has changed */ - -/* in the CONFIG register */ -#define RESETcfg 0x80 /* put card in reset state */ -#define TXENcfg 0x20 /* enable TX */ - -/* in SETUP register */ -#define PROMISCset 0x10 /* enable RCV_ALL */ -#define P1MODE 0x80 /* enable P1-MODE for Backplane */ -#define SLOWARB 0x01 /* enable Slow Arbitration for >=5Mbps */ - -/* COM2002x */ -#define SUB_TENTATIVE 0 /* tentative node ID */ -#define SUB_NODE 1 /* node ID */ -#define SUB_SETUP1 2 /* various options */ -#define SUB_TEST 3 /* test/diag register */ - -/* COM20022 only */ -#define SUB_SETUP2 4 /* sundry options */ -#define SUB_BUSCTL 5 /* bus control options */ -#define SUB_DMACOUNT 6 /* DMA count options */ - -#define SET_SUBADR(x) do { \ - if ((x) < 4) \ - { \ - lp->config = (lp->config & ~0x03) | (x); \ - SETCONF; \ - } \ - else \ - { \ - outb(x, _SUBADR); \ - } \ -} while (0) - -#undef ARCRESET -#undef ASTATUS -#undef ACOMMAND -#undef AINTMASK - -#define ARCRESET { outb(lp->config | 0x80, _CONFIG); \ - udelay(5); \ - outb(lp->config , _CONFIG); \ - } -#define ARCRESET0 { outb(0x18 | 0x80, _CONFIG); \ - udelay(5); \ - outb(0x18 , _CONFIG); \ - } - -#define ASTATUS() inb(_STATUS) -#define ADIAGSTATUS() inb(_DIAGSTAT) -#define ACOMMAND(cmd) outb((cmd),_COMMAND) -#define AINTMASK(msk) outb((msk),_INTMASK) - -#define SETCONF outb(lp->config, _CONFIG) - -#endif /* __COM20020_H */ -- cgit v1.2.3 From 2d8bff12699abc3a9bf886bb0b79f44d94d81496 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Wed, 23 Sep 2015 14:57:58 -0400 Subject: netpoll: Close race condition between poll_one_napi and napi_disable Drivers might call napi_disable while not holding the napi instance poll_lock. In those instances, its possible for a race condition to exist between poll_one_napi and napi_disable. That is to say, poll_one_napi only tests the NAPI_STATE_SCHED bit to see if there is work to do during a poll, and as such the following may happen: CPU0 CPU1 ndo_tx_timeout napi_poll_dev napi_disable poll_one_napi test_and_set_bit (ret 0) test_bit (ret 1) reset adapter napi_poll_routine If the adapter gets a tx timeout without a napi instance scheduled, its possible for the adapter to think it has exclusive access to the hardware (as the napi instance is now scheduled via the napi_disable call), while the netpoll code thinks there is simply work to do. The result is parallel hardware access leading to corrupt data structures in the driver, and a crash. Additionaly, there is another, more critical race between netpoll and napi_disable. The disabled napi state is actually identical to the scheduled state for a given napi instance. The implication being that, if a napi instance is disabled, a netconsole instance would see the napi state of the device as having been scheduled, and poll it, likely while the driver was dong something requiring exclusive access. In the case above, its fairly clear that not having the rings in a state ready to be polled will cause any number of crashes. The fix should be pretty easy. netpoll uses its own bit to indicate that that the napi instance is in a state of being serviced by netpoll (NAPI_STATE_NPSVC). We can just gate disabling on that bit as well as the sched bit. That should prevent netpoll from conducting a napi poll if we convert its set bit to a test_and_set_bit operation to provide mutual exclusion Change notes: V2) Remove a trailing whtiespace Resubmit with proper subject prefix V3) Clean up spacing nits Signed-off-by: Neil Horman CC: "David S. Miller" CC: jmaxwell@redhat.com Tested-by: jmaxwell@redhat.com Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/core/dev.c | 2 ++ net/core/netpoll.c | 10 ++++++++-- 3 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 88a00694eda5..2d15e3831440 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -507,6 +507,7 @@ static inline void napi_enable(struct napi_struct *n) BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); smp_mb__before_atomic(); clear_bit(NAPI_STATE_SCHED, &n->state); + clear_bit(NAPI_STATE_NPSVC, &n->state); } #ifdef CONFIG_SMP diff --git a/net/core/dev.c b/net/core/dev.c index 877c84834d81..6bb6470f5b7b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4713,6 +4713,8 @@ void napi_disable(struct napi_struct *n) while (test_and_set_bit(NAPI_STATE_SCHED, &n->state)) msleep(1); + while (test_and_set_bit(NAPI_STATE_NPSVC, &n->state)) + msleep(1); hrtimer_cancel(&n->timer); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 6aa3db8dfc3b..8bdada242a7d 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -142,7 +142,7 @@ static void queue_process(struct work_struct *work) */ static int poll_one_napi(struct napi_struct *napi, int budget) { - int work; + int work = 0; /* net_rx_action's ->poll() invocations and our's are * synchronized by this test which is only made while @@ -151,7 +151,12 @@ static int poll_one_napi(struct napi_struct *napi, int budget) if (!test_bit(NAPI_STATE_SCHED, &napi->state)) return budget; - set_bit(NAPI_STATE_NPSVC, &napi->state); + /* If we set this bit but see that it has already been set, + * that indicates that napi has been disabled and we need + * to abort this operation + */ + if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state)) + goto out; work = napi->poll(napi, budget); WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll); @@ -159,6 +164,7 @@ static int poll_one_napi(struct napi_struct *napi, int budget) clear_bit(NAPI_STATE_NPSVC, &napi->state); +out: return budget - work; } -- cgit v1.2.3 From a79e88d9fbbe2e3ecb9d883fb59dca7468d42d79 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Wed, 23 Sep 2015 08:39:16 -0700 Subject: bridge: define some min/max/default ageing time constants Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 6 ++++++ net/bridge/br_device.c | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index dad8b00beed2..a338a688ee4a 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -46,6 +46,12 @@ struct br_ip_list { #define BR_LEARNING_SYNC BIT(9) #define BR_PROXYARP_WIFI BIT(10) +/* values as per ieee8021QBridgeFdbAgingTime */ +#define BR_MIN_AGEING_TIME (10 * HZ) +#define BR_MAX_AGEING_TIME (1000000 * HZ) + +#define BR_DEFAULT_AGEING_TIME (300 * HZ) + extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); typedef int br_should_route_hook_t(struct sk_buff *skb); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 6ed2feb51e3c..2f81624a8257 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -391,7 +391,7 @@ void br_dev_setup(struct net_device *dev) br->bridge_max_age = br->max_age = 20 * HZ; br->bridge_hello_time = br->hello_time = 2 * HZ; br->bridge_forward_delay = br->forward_delay = 15 * HZ; - br->ageing_time = 300 * HZ; + br->ageing_time = BR_DEFAULT_AGEING_TIME; br_netfilter_rtable_init(br); br_stp_timer_init(br); -- cgit v1.2.3 From 06e60e5912c0373b15143cc52e4a11fafeaafff3 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Tue, 22 Sep 2015 14:27:16 +0300 Subject: net/ethoc: support big-endian register layout Signed-off-by: Max Filippov Signed-off-by: David S. Miller --- drivers/net/ethernet/ethoc.c | 14 ++++++++++++-- include/net/ethoc.h | 1 + 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index a2c96fd88393..ff665493ca97 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -201,6 +201,7 @@ struct ethoc { void __iomem *membase; int dma_alloc; resource_size_t io_region_size; + bool big_endian; unsigned int num_bd; unsigned int num_tx; @@ -236,12 +237,18 @@ struct ethoc_bd { static inline u32 ethoc_read(struct ethoc *dev, loff_t offset) { - return ioread32(dev->iobase + offset); + if (dev->big_endian) + return ioread32be(dev->iobase + offset); + else + return ioread32(dev->iobase + offset); } static inline void ethoc_write(struct ethoc *dev, loff_t offset, u32 data) { - iowrite32(data, dev->iobase + offset); + if (dev->big_endian) + iowrite32be(data, dev->iobase + offset); + else + iowrite32(data, dev->iobase + offset); } static inline void ethoc_read_bd(struct ethoc *dev, int index, @@ -1106,6 +1113,9 @@ static int ethoc_probe(struct platform_device *pdev) priv->dma_alloc = buffer_size; } + priv->big_endian = pdata ? pdata->big_endian : + of_device_is_big_endian(pdev->dev.of_node); + /* calculate the number of TX/RX buffers, maximum 128 supported */ num_bd = min_t(unsigned int, 128, (netdev->mem_end - netdev->mem_start + 1) / ETHOC_BUFSIZ); diff --git a/include/net/ethoc.h b/include/net/ethoc.h index 2a2d6bb34eb8..bb7f467da7fc 100644 --- a/include/net/ethoc.h +++ b/include/net/ethoc.h @@ -17,6 +17,7 @@ struct ethoc_platform_data { u8 hwaddr[IFHWADDRLEN]; s8 phy_id; u32 eth_clkfreq; + bool big_endian; }; #endif /* !LINUX_NET_ETHOC_H */ -- cgit v1.2.3 From 58dbc6f2604a2cbff9e6ec144d1bb9d000a1a1ec Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:41 -0500 Subject: ipvs: Store ipvs not net in struct ip_vs_conn In practice struct netns_ipvs is as meaningful as struct net and more useful as it holds the ipvs specific data. So store a pointer to struct netns_ipvs. Update the accesses of conn->net to access conn->ipvs->net instead. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 31 +------------------------------ net/netfilter/ipvs/ip_vs_conn.c | 30 +++++++++++++++--------------- net/netfilter/ipvs/ip_vs_ftp.c | 6 +++--- net/netfilter/ipvs/ip_vs_nfct.c | 3 +-- net/netfilter/ipvs/ip_vs_proto_sctp.c | 2 +- net/netfilter/ipvs/ip_vs_proto_tcp.c | 2 +- net/netfilter/ipvs/ip_vs_proto_udp.c | 2 +- net/netfilter/ipvs/ip_vs_xmit.c | 4 ++-- 8 files changed, 25 insertions(+), 55 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 1096a71ab6ed..3bf6da8fdaf1 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -572,9 +572,7 @@ struct ip_vs_conn { volatile __u32 flags; /* status flags */ __u16 protocol; /* Which protocol (TCP/UDP) */ __u16 daf; /* Address family of the dest */ -#ifdef CONFIG_NET_NS - struct net *net; /* Name space */ -#endif + struct netns_ipvs *ipvs; /* counter and timer */ atomic_t refcnt; /* reference count */ @@ -621,33 +619,6 @@ struct ip_vs_conn { struct rcu_head rcu_head; }; -/* To save some memory in conn table when name space is disabled. */ -static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp) -{ -#ifdef CONFIG_NET_NS - return cp->net; -#else - return &init_net; -#endif -} - -static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net) -{ -#ifdef CONFIG_NET_NS - cp->net = net; -#endif -} - -static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp, - struct net *net) -{ -#ifdef CONFIG_NET_NS - return cp->net == net; -#else - return 1; -#endif -} - /* Extended internal versions of struct ip_vs_service_user and ip_vs_dest_user * for IPv6 support. * diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index f71b3146a5a1..dd8e5a12d545 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -148,7 +148,7 @@ static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp) { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(ip_vs_conn_net(cp), cp->af, cp->protocol, + ip_vs_conn_fill_param(cp->ipvs->net, cp->af, cp->protocol, &cp->caddr, cp->cport, NULL, 0, &p); if (cp->pe) { @@ -279,7 +279,7 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p) ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) && ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) && p->protocol == cp->protocol && - ip_vs_conn_net_eq(cp, p->net)) { + net_eq(cp->ipvs->net, p->net)) { if (!__ip_vs_conn_get(cp)) continue; /* HIT */ @@ -359,7 +359,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (unlikely(p->pe_data && p->pe->ct_match)) { - if (!ip_vs_conn_net_eq(cp, p->net)) + if (!net_eq(cp->ipvs->net, p->net)) continue; if (p->pe == cp->pe && p->pe->ct_match(p, cp)) { if (__ip_vs_conn_get(cp)) @@ -377,7 +377,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) p->vport == cp->vport && p->cport == cp->cport && cp->flags & IP_VS_CONN_F_TEMPLATE && p->protocol == cp->protocol && - ip_vs_conn_net_eq(cp, p->net)) { + net_eq(cp->ipvs->net, p->net)) { if (__ip_vs_conn_get(cp)) goto out; } @@ -418,7 +418,7 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) && ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) && p->protocol == cp->protocol && - ip_vs_conn_net_eq(cp, p->net)) { + net_eq(cp->ipvs->net, p->net)) { if (!__ip_vs_conn_get(cp)) continue; /* HIT */ @@ -638,7 +638,7 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp) * so we can make the assumption that the svc_af is the same as the * dest_af */ - dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, cp->af, &cp->daddr, + dest = ip_vs_find_dest(cp->ipvs->net, cp->af, cp->af, &cp->daddr, cp->dport, &cp->vaddr, cp->vport, cp->protocol, cp->fwmark, cp->flags); if (dest) { @@ -668,7 +668,7 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp) #endif ip_vs_bind_xmit(cp); - pd = ip_vs_proto_data_get(ip_vs_conn_net(cp), cp->protocol); + pd = ip_vs_proto_data_get(cp->ipvs->net, cp->protocol); if (pd && atomic_read(&pd->appcnt)) ip_vs_bind_app(cp, pd->pp); } @@ -746,7 +746,7 @@ static int expire_quiescent_template(struct netns_ipvs *ipvs, int ip_vs_check_template(struct ip_vs_conn *ct) { struct ip_vs_dest *dest = ct->dest; - struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(ct)); + struct netns_ipvs *ipvs = ct->ipvs; /* * Checking the dest server status. @@ -800,8 +800,8 @@ static void ip_vs_conn_rcu_free(struct rcu_head *head) static void ip_vs_conn_expire(unsigned long data) { struct ip_vs_conn *cp = (struct ip_vs_conn *)data; - struct net *net = ip_vs_conn_net(cp); - struct netns_ipvs *ipvs = net_ipvs(net); + struct netns_ipvs *ipvs = cp->ipvs; + struct net *net = ipvs->net; /* * do I control anybody? @@ -887,7 +887,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, INIT_HLIST_NODE(&cp->c_list); setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp); - ip_vs_conn_net_set(cp, p->net); + cp->ipvs = ipvs; cp->af = p->af; cp->daf = dest_af; cp->protocol = p->protocol; @@ -1061,7 +1061,7 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) size_t len = 0; char dbuf[IP_VS_ADDRSTRLEN]; - if (!ip_vs_conn_net_eq(cp, net)) + if (!net_eq(cp->ipvs->net, net)) return 0; if (cp->pe_data) { pe_data[0] = ' '; @@ -1146,7 +1146,7 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v) const struct ip_vs_conn *cp = v; struct net *net = seq_file_net(seq); - if (!ip_vs_conn_net_eq(cp, net)) + if (!net_eq(cp->ipvs->net, net)) return 0; #ifdef CONFIG_IP_VS_IPV6 @@ -1256,7 +1256,7 @@ void ip_vs_random_dropentry(struct net *net) if (cp->flags & IP_VS_CONN_F_TEMPLATE) /* connection template */ continue; - if (!ip_vs_conn_net_eq(cp, net)) + if (!net_eq(cp->ipvs->net, net)) continue; if (cp->protocol == IPPROTO_TCP) { switch(cp->state) { @@ -1319,7 +1319,7 @@ flush_again: for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { - if (!ip_vs_conn_net_eq(cp, net)) + if (cp->ipvs != ipvs) continue; IP_VS_DBG(4, "del connection\n"); ip_vs_conn_expire_now(cp); diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 5d3daae98bf0..5ccbf3c16dd4 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -223,14 +223,14 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, */ { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET, + ip_vs_conn_fill_param(cp->ipvs->net, AF_INET, iph->protocol, &from, port, &cp->caddr, 0, &p); n_cp = ip_vs_conn_out_get(&p); } if (!n_cp) { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(ip_vs_conn_net(cp), + ip_vs_conn_fill_param(cp->ipvs->net, AF_INET, IPPROTO_TCP, &cp->caddr, 0, &cp->vaddr, port, &p); /* As above, this is ipv4 only */ @@ -392,7 +392,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET, + ip_vs_conn_fill_param(cp->ipvs->net, AF_INET, iph->protocol, &to, port, &cp->vaddr, htons(ntohs(cp->vport)-1), &p); n_cp = ip_vs_conn_in_get(&p); diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index 136184572fc9..dae3c069966f 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -274,8 +274,7 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) " for conn " FMT_CONN "\n", __func__, ARG_TUPLE(&tuple), ARG_CONN(cp)); - h = nf_conntrack_find_get(ip_vs_conn_net(cp), &nf_ct_zone_dflt, - &tuple); + h = nf_conntrack_find_get(cp->ipvs->net, &nf_ct_zone_dflt, &tuple); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); /* Show what happens instead of calling nf_ct_kill() */ diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index ac628a9afdb5..ce615866bd63 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -521,7 +521,7 @@ static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc) static int sctp_app_conn_bind(struct ip_vs_conn *cp) { - struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); + struct netns_ipvs *ipvs = cp->ipvs; int hash; struct ip_vs_app *inc; int result = 0; diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 8f43cf6044e9..e00623a88518 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -633,7 +633,7 @@ tcp_unregister_app(struct net *net, struct ip_vs_app *inc) static int tcp_app_conn_bind(struct ip_vs_conn *cp) { - struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); + struct netns_ipvs *ipvs = cp->ipvs; int hash; struct ip_vs_app *inc; int result = 0; diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index f3aa821efb89..3b0a2dc1826b 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -400,7 +400,7 @@ udp_unregister_app(struct net *net, struct ip_vs_app *inc) static int udp_app_conn_bind(struct ip_vs_conn *cp) { - struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); + struct netns_ipvs *ipvs = cp->ipvs; int hash; struct ip_vs_app *inc; int result = 0; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 9dbb7ccadecb..5b5ec0b688de 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -574,7 +574,7 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, skb_forward_csum(skb); if (!skb->sk) skb_sender_cpu_clear(skb); - NF_HOOK(pf, NF_INET_LOCAL_OUT, ip_vs_conn_net(cp), NULL, skb, + NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output_okfn); } else ret = NF_ACCEPT; @@ -596,7 +596,7 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, skb_forward_csum(skb); if (!skb->sk) skb_sender_cpu_clear(skb); - NF_HOOK(pf, NF_INET_LOCAL_OUT, ip_vs_conn_net(cp), NULL, skb, + NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output_okfn); } else ret = NF_ACCEPT; -- cgit v1.2.3 From e64e2b460cedadf93d05a23e9ad397cc0386568c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:42 -0500 Subject: ipvs: Store ipvs not net in struct ip_vs_conn_param In practice struct netns_ipvs is as meaningful as struct net and more useful as it holds the ipvs specific data. So store a pointer to struct netns_ipvs. Update the accesses of param->net to access param->ipvs->net instead. When lookup up struct ip_vs_conn in a hash table replace comparisons of cp->net with comparisons of cp->ipvs which is possible now that ipvs is present in ip_vs_conn_param. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- net/netfilter/ipvs/ip_vs_conn.c | 14 +++++++------- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 3bf6da8fdaf1..8cca99bbe15b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -545,7 +545,7 @@ struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net, unsigned short proto); struct ip_vs_conn_param { - struct net *net; + struct netns_ipvs *ipvs; const union nf_inet_addr *caddr; const union nf_inet_addr *vaddr; __be16 cport; @@ -1208,7 +1208,7 @@ static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol, __be16 vport, struct ip_vs_conn_param *p) { - p->net = net; + p->ipvs = net_ipvs(net); p->af = af; p->protocol = protocol; p->caddr = caddr; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index dd8e5a12d545..72c47ee2f9f5 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -141,7 +141,7 @@ static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p, port = p->vport; } - return ip_vs_conn_hashkey(p->net, p->af, p->protocol, addr, port); + return ip_vs_conn_hashkey(p->ipvs->net, p->af, p->protocol, addr, port); } static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp) @@ -279,7 +279,7 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p) ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) && ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) && p->protocol == cp->protocol && - net_eq(cp->ipvs->net, p->net)) { + cp->ipvs == p->ipvs) { if (!__ip_vs_conn_get(cp)) continue; /* HIT */ @@ -359,7 +359,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (unlikely(p->pe_data && p->pe->ct_match)) { - if (!net_eq(cp->ipvs->net, p->net)) + if (cp->ipvs != p->ipvs) continue; if (p->pe == cp->pe && p->pe->ct_match(p, cp)) { if (__ip_vs_conn_get(cp)) @@ -377,7 +377,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) p->vport == cp->vport && p->cport == cp->cport && cp->flags & IP_VS_CONN_F_TEMPLATE && p->protocol == cp->protocol && - net_eq(cp->ipvs->net, p->net)) { + cp->ipvs == p->ipvs) { if (__ip_vs_conn_get(cp)) goto out; } @@ -418,7 +418,7 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) && ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) && p->protocol == cp->protocol && - net_eq(cp->ipvs->net, p->net)) { + cp->ipvs == p->ipvs) { if (!__ip_vs_conn_get(cp)) continue; /* HIT */ @@ -875,8 +875,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, struct ip_vs_dest *dest, __u32 fwmark) { struct ip_vs_conn *cp; - struct netns_ipvs *ipvs = net_ipvs(p->net); - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->net, + struct netns_ipvs *ipvs = p->ipvs; + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->ipvs->net, p->protocol); cp = kmem_cache_alloc(ip_vs_conn_cachep, GFP_ATOMIC); -- cgit v1.2.3 From 19913dec1bc1d1aa5afe26db858507d4c3042665 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:43 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_fill_conn ipvs is what is actually desired so change the parameter and the modify the callers to pass struct netns_ipvs. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- net/netfilter/ipvs/ip_vs_conn.c | 8 ++++---- net/netfilter/ipvs/ip_vs_core.c | 8 ++++---- net/netfilter/ipvs/ip_vs_ftp.c | 6 +++--- net/netfilter/ipvs/ip_vs_nfct.c | 2 +- net/netfilter/ipvs/ip_vs_proto_ah_esp.c | 14 +++++++------- net/netfilter/ipvs/ip_vs_sync.c | 16 ++++++++-------- 7 files changed, 29 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 8cca99bbe15b..83e2aea63db2 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1201,14 +1201,14 @@ enum { IP_VS_DIR_LAST, }; -static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol, +static inline void ip_vs_conn_fill_param(struct netns_ipvs *ipvs, int af, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { - p->ipvs = net_ipvs(net); + p->ipvs = ipvs; p->af = af; p->protocol = protocol; p->caddr = caddr; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 72c47ee2f9f5..3e277093ec45 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -148,7 +148,7 @@ static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp) { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(cp->ipvs->net, cp->af, cp->protocol, + ip_vs_conn_fill_param(cp->ipvs, cp->af, cp->protocol, &cp->caddr, cp->cport, NULL, 0, &p); if (cp->pe) { @@ -319,17 +319,17 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb, struct ip_vs_conn_param *p) { __be16 _ports[2], *pptr; - struct net *net = skb_net(skb); + struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph); if (pptr == NULL) return 1; if (likely(!ip_vs_iph_inverse(iph))) - ip_vs_conn_fill_param(net, af, iph->protocol, &iph->saddr, + ip_vs_conn_fill_param(ipvs, af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1], p); else - ip_vs_conn_fill_param(net, af, iph->protocol, &iph->daddr, + ip_vs_conn_fill_param(ipvs, af, iph->protocol, &iph->daddr, pptr[1], &iph->saddr, pptr[0], p); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 3f33a076aaec..fd02aec0a11a 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -215,7 +215,7 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { - ip_vs_conn_fill_param(svc->net, svc->af, protocol, caddr, cport, vaddr, + ip_vs_conn_fill_param(net_ipvs(svc->net), svc->af, protocol, caddr, cport, vaddr, vport, p); p->pe = rcu_dereference(svc->pe); if (p->pe && p->pe->fill_param) @@ -376,7 +376,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, /* * Create a new connection according to the template */ - ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, src_addr, + ip_vs_conn_fill_param(net_ipvs(svc->net), svc->af, iph->protocol, src_addr, src_port, dst_addr, dst_port, ¶m); cp = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, flags, dest, @@ -524,7 +524,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, + ip_vs_conn_fill_param(net_ipvs(svc->net), svc->af, iph->protocol, caddr, cport, vaddr, vport, &p); cp = ip_vs_conn_new(&p, dest->af, &dest->addr, dest->port ? dest->port : vport, @@ -600,7 +600,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, + ip_vs_conn_fill_param(net_ipvs(svc->net), svc->af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1], &p); cp = ip_vs_conn_new(&p, svc->af, &daddr, 0, diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 5ccbf3c16dd4..cf0cba956a21 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -223,14 +223,14 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, */ { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(cp->ipvs->net, AF_INET, + ip_vs_conn_fill_param(cp->ipvs, AF_INET, iph->protocol, &from, port, &cp->caddr, 0, &p); n_cp = ip_vs_conn_out_get(&p); } if (!n_cp) { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(cp->ipvs->net, + ip_vs_conn_fill_param(cp->ipvs, AF_INET, IPPROTO_TCP, &cp->caddr, 0, &cp->vaddr, port, &p); /* As above, this is ipv4 only */ @@ -392,7 +392,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(cp->ipvs->net, AF_INET, + ip_vs_conn_fill_param(cp->ipvs, AF_INET, iph->protocol, &to, port, &cp->vaddr, htons(ntohs(cp->vport)-1), &p); n_cp = ip_vs_conn_in_get(&p); diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index dae3c069966f..30434fb133df 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -161,7 +161,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct, /* RS->CLIENT */ orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; - ip_vs_conn_fill_param(net, exp->tuple.src.l3num, orig->dst.protonum, + ip_vs_conn_fill_param(net_ipvs(net), exp->tuple.src.l3num, orig->dst.protonum, &orig->src.u3, orig->src.u.tcp.port, &orig->dst.u3, orig->dst.u.tcp.port, &p); cp = ip_vs_conn_out_get(&p); diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index be1791d1c03f..406d9a433d92 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -41,16 +41,16 @@ struct isakmp_hdr { #define PORT_ISAKMP 500 static void -ah_esp_conn_fill_param_proto(struct net *net, int af, +ah_esp_conn_fill_param_proto(struct netns_ipvs *ipvs, int af, const struct ip_vs_iphdr *iph, struct ip_vs_conn_param *p) { if (likely(!ip_vs_iph_inverse(iph))) - ip_vs_conn_fill_param(net, af, IPPROTO_UDP, + ip_vs_conn_fill_param(ipvs, af, IPPROTO_UDP, &iph->saddr, htons(PORT_ISAKMP), &iph->daddr, htons(PORT_ISAKMP), p); else - ip_vs_conn_fill_param(net, af, IPPROTO_UDP, + ip_vs_conn_fill_param(ipvs, af, IPPROTO_UDP, &iph->daddr, htons(PORT_ISAKMP), &iph->saddr, htons(PORT_ISAKMP), p); } @@ -61,9 +61,9 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, { struct ip_vs_conn *cp; struct ip_vs_conn_param p; - struct net *net = skb_net(skb); + struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); - ah_esp_conn_fill_param_proto(net, af, iph, &p); + ah_esp_conn_fill_param_proto(ipvs, af, iph, &p); cp = ip_vs_conn_in_get(&p); if (!cp) { /* @@ -88,9 +88,9 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb, { struct ip_vs_conn *cp; struct ip_vs_conn_param p; - struct net *net = skb_net(skb); + struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); - ah_esp_conn_fill_param_proto(net, af, iph, &p); + ah_esp_conn_fill_param_proto(ipvs, af, iph, &p); cp = ip_vs_conn_out_get(&p); if (!cp) { IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet " diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 43f140950075..f8bc2027a6c4 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -784,21 +784,21 @@ control: * fill_param used by version 1 */ static inline int -ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc, +ip_vs_conn_fill_param_sync(struct netns_ipvs *ipvs, int af, union ip_vs_sync_conn *sc, struct ip_vs_conn_param *p, __u8 *pe_data, unsigned int pe_data_len, __u8 *pe_name, unsigned int pe_name_len) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) - ip_vs_conn_fill_param(net, af, sc->v6.protocol, + ip_vs_conn_fill_param(ipvs, af, sc->v6.protocol, (const union nf_inet_addr *)&sc->v6.caddr, sc->v6.cport, (const union nf_inet_addr *)&sc->v6.vaddr, sc->v6.vport, p); else #endif - ip_vs_conn_fill_param(net, af, sc->v4.protocol, + ip_vs_conn_fill_param(ipvs, af, sc->v4.protocol, (const union nf_inet_addr *)&sc->v4.caddr, sc->v4.cport, (const union nf_inet_addr *)&sc->v4.vaddr, @@ -953,7 +953,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, /* * Process received multicast message for Version 0 */ -static void ip_vs_process_message_v0(struct net *net, const char *buffer, +static void ip_vs_process_message_v0(struct netns_ipvs *ipvs, const char *buffer, const size_t buflen) { struct ip_vs_sync_mesg_v0 *m = (struct ip_vs_sync_mesg_v0 *)buffer; @@ -1009,14 +1009,14 @@ static void ip_vs_process_message_v0(struct net *net, const char *buffer, } } - ip_vs_conn_fill_param(net, AF_INET, s->protocol, + ip_vs_conn_fill_param(ipvs, AF_INET, s->protocol, (const union nf_inet_addr *)&s->caddr, s->cport, (const union nf_inet_addr *)&s->vaddr, s->vport, ¶m); /* Send timeout as Zero */ - ip_vs_proc_conn(net, ¶m, flags, state, s->protocol, AF_INET, + ip_vs_proc_conn(ipvs->net, ¶m, flags, state, s->protocol, AF_INET, (union nf_inet_addr *)&s->daddr, s->dport, 0, 0, opt); } @@ -1171,7 +1171,7 @@ static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end) state = 0; } } - if (ip_vs_conn_fill_param_sync(net, af, s, ¶m, pe_data, + if (ip_vs_conn_fill_param_sync(net_ipvs(net), af, s, ¶m, pe_data, pe_data_len, pe_name, pe_name_len)) { retc = 50; goto out; @@ -1268,7 +1268,7 @@ static void ip_vs_process_message(struct net *net, __u8 *buffer, } } else { /* Old type of message */ - ip_vs_process_message_v0(net, buffer, buflen); + ip_vs_process_message_v0(ipvs, buffer, buflen); return; } } -- cgit v1.2.3 From 3109d2f2d1fe068f1cc3b1f74f5022ab4aef52a7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:44 -0500 Subject: ipvs: Store ipvs not net in struct ip_vs_service In practice struct netns_ipvs is as meaningful as struct net and more useful as it holds the ipvs specific data. So store a pointer to struct netns_ipvs. Update the accesses of param->net to access param->ipvs->net instead. In functions where we are searching for an svc and filtering by net filter by ipvs instead. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_core.c | 10 +++---- net/netfilter/ipvs/ip_vs_ctl.c | 64 ++++++++++++++++++++++------------------ net/netfilter/ipvs/ip_vs_lblc.c | 3 +- net/netfilter/ipvs/ip_vs_lblcr.c | 3 +- 5 files changed, 43 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 83e2aea63db2..2c22380b9ad7 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -678,7 +678,7 @@ struct ip_vs_service { unsigned int flags; /* service status flags */ unsigned int timeout; /* persistent timeout in ticks */ __be32 netmask; /* grouping granularity, mask/plen */ - struct net *net; + struct netns_ipvs *ipvs; struct list_head destinations; /* real server d-linked list */ __u32 num_dests; /* number of servers */ diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index fd02aec0a11a..583199c2bcdc 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -179,7 +179,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) static inline void ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) { - struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct netns_ipvs *ipvs = svc->ipvs; struct ip_vs_cpu_stats *s; s = this_cpu_ptr(cp->dest->stats.cpustats); @@ -215,7 +215,7 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { - ip_vs_conn_fill_param(net_ipvs(svc->net), svc->af, protocol, caddr, cport, vaddr, + ip_vs_conn_fill_param(svc->ipvs, svc->af, protocol, caddr, cport, vaddr, vport, p); p->pe = rcu_dereference(svc->pe); if (p->pe && p->pe->fill_param) @@ -376,7 +376,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, /* * Create a new connection according to the template */ - ip_vs_conn_fill_param(net_ipvs(svc->net), svc->af, iph->protocol, src_addr, + ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, src_addr, src_port, dst_addr, dst_port, ¶m); cp = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, flags, dest, @@ -524,7 +524,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(net_ipvs(svc->net), svc->af, iph->protocol, + ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, caddr, cport, vaddr, vport, &p); cp = ip_vs_conn_new(&p, dest->af, &dest->addr, dest->port ? dest->port : vport, @@ -600,7 +600,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(net_ipvs(svc->net), svc->af, iph->protocol, + ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1], &p); cp = ip_vs_conn_new(&p, svc->af, &daddr, 0, diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 6162ae56e47a..7132e83617b6 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -309,14 +309,14 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) /* * Hash it by in ip_vs_svc_table */ - hash = ip_vs_svc_hashkey(svc->net, svc->af, svc->protocol, + hash = ip_vs_svc_hashkey(svc->ipvs->net, svc->af, svc->protocol, &svc->addr, svc->port); hlist_add_head_rcu(&svc->s_list, &ip_vs_svc_table[hash]); } else { /* * Hash it by fwmark in svc_fwm_table */ - hash = ip_vs_svc_fwm_hashkey(svc->net, svc->fwmark); + hash = ip_vs_svc_fwm_hashkey(svc->ipvs->net, svc->fwmark); hlist_add_head_rcu(&svc->f_list, &ip_vs_svc_fwm_table[hash]); } @@ -360,6 +360,7 @@ static inline struct ip_vs_service * __ip_vs_service_find(struct net *net, int af, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport) { + struct netns_ipvs *ipvs = net_ipvs(net); unsigned int hash; struct ip_vs_service *svc; @@ -371,7 +372,7 @@ __ip_vs_service_find(struct net *net, int af, __u16 protocol, && ip_vs_addr_equal(af, &svc->addr, vaddr) && (svc->port == vport) && (svc->protocol == protocol) - && net_eq(svc->net, net)) { + && (svc->ipvs == ipvs)) { /* HIT */ return svc; } @@ -387,6 +388,7 @@ __ip_vs_service_find(struct net *net, int af, __u16 protocol, static inline struct ip_vs_service * __ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark) { + struct netns_ipvs *ipvs = net_ipvs(net); unsigned int hash; struct ip_vs_service *svc; @@ -395,7 +397,7 @@ __ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark) hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[hash], f_list) { if (svc->fwmark == fwmark && svc->af == af - && net_eq(svc->net, net)) { + && (svc->ipvs == ipvs)) { /* HIT */ return svc; } @@ -660,7 +662,7 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af, const union nf_inet_addr *daddr, __be16 dport) { struct ip_vs_dest *dest; - struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct netns_ipvs *ipvs = svc->ipvs; /* * Find the destination in trash @@ -788,7 +790,7 @@ static void __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct ip_vs_dest_user_kern *udest, int add) { - struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct netns_ipvs *ipvs = svc->ipvs; struct ip_vs_service *old_svc; struct ip_vs_scheduler *sched; int conn_flags; @@ -843,7 +845,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, spin_unlock_bh(&dest->dst_lock); if (add) { - ip_vs_start_estimator(svc->net, &dest->stats); + ip_vs_start_estimator(svc->ipvs->net, &dest->stats); list_add_rcu(&dest->n_list, &svc->destinations); svc->num_dests++; sched = rcu_dereference_protected(svc->scheduler, 1); @@ -874,12 +876,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, atype = ipv6_addr_type(&udest->addr.in6); if ((!(atype & IPV6_ADDR_UNICAST) || atype & IPV6_ADDR_LINKLOCAL) && - !__ip_vs_addr_is_local_v6(svc->net, &udest->addr.in6)) + !__ip_vs_addr_is_local_v6(svc->ipvs->net, &udest->addr.in6)) return -EINVAL; } else #endif { - atype = inet_addr_type(svc->net, udest->addr.ip); + atype = inet_addr_type(svc->ipvs->net, udest->addr.ip); if (atype != RTN_LOCAL && atype != RTN_UNICAST) return -EINVAL; } @@ -1079,7 +1081,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc, svc->num_dests--; if (dest->af != svc->af) - net_ipvs(svc->net)->mixed_address_family_dests--; + svc->ipvs->mixed_address_family_dests--; if (svcupd) { struct ip_vs_scheduler *sched; @@ -1120,7 +1122,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) /* * Delete the destination */ - __ip_vs_del_dest(svc->net, dest, false); + __ip_vs_del_dest(svc->ipvs->net, dest, false); LeaveFunction(2); @@ -1237,7 +1239,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, svc->flags = u->flags; svc->timeout = u->timeout * HZ; svc->netmask = u->netmask; - svc->net = net; + svc->ipvs = ipvs; INIT_LIST_HEAD(&svc->destinations); spin_lock_init(&svc->sched_lock); @@ -1381,7 +1383,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) struct ip_vs_dest *dest, *nxt; struct ip_vs_scheduler *old_sched; struct ip_vs_pe *old_pe; - struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct netns_ipvs *ipvs = svc->ipvs; pr_info("%s: enter\n", __func__); @@ -1389,7 +1391,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) if (svc->af == AF_INET) ipvs->num_services--; - ip_vs_stop_estimator(svc->net, &svc->stats); + ip_vs_stop_estimator(svc->ipvs->net, &svc->stats); /* Unbind scheduler */ old_sched = rcu_dereference_protected(svc->scheduler, 1); @@ -1405,7 +1407,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) */ list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) { __ip_vs_unlink_dest(svc, dest, 0); - __ip_vs_del_dest(svc->net, dest, cleanup); + __ip_vs_del_dest(svc->ipvs->net, dest, cleanup); } /* @@ -1458,6 +1460,7 @@ static int ip_vs_del_service(struct ip_vs_service *svc) */ static int ip_vs_flush(struct net *net, bool cleanup) { + struct netns_ipvs *ipvs = net_ipvs(net); int idx; struct ip_vs_service *svc; struct hlist_node *n; @@ -1468,7 +1471,7 @@ static int ip_vs_flush(struct net *net, bool cleanup) for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry_safe(svc, n, &ip_vs_svc_table[idx], s_list) { - if (net_eq(svc->net, net)) + if (svc->ipvs == ipvs) ip_vs_unlink_service(svc, cleanup); } } @@ -1479,7 +1482,7 @@ static int ip_vs_flush(struct net *net, bool cleanup) for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry_safe(svc, n, &ip_vs_svc_fwm_table[idx], f_list) { - if (net_eq(svc->net, net)) + if (svc->ipvs == ipvs) ip_vs_unlink_service(svc, cleanup); } } @@ -1540,7 +1543,7 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, mutex_lock(&__ip_vs_mutex); for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { - if (net_eq(svc->net, net)) { + if (svc->ipvs == ipvs) { list_for_each_entry(dest, &svc->destinations, n_list) { ip_vs_forget_dev(dest, dev); @@ -1549,7 +1552,7 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, } hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { - if (net_eq(svc->net, net)) { + if (svc->ipvs == ipvs) { list_for_each_entry(dest, &svc->destinations, n_list) { ip_vs_forget_dev(dest, dev); @@ -1585,24 +1588,25 @@ static int ip_vs_zero_service(struct ip_vs_service *svc) static int ip_vs_zero_all(struct net *net) { + struct netns_ipvs *ipvs = net_ipvs(net); int idx; struct ip_vs_service *svc; for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { - if (net_eq(svc->net, net)) + if (svc->ipvs == ipvs) ip_vs_zero_service(svc); } } for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { - if (net_eq(svc->net, net)) + if (svc->ipvs == ipvs) ip_vs_zero_service(svc); } } - ip_vs_zero_stats(&net_ipvs(net)->tot_stats); + ip_vs_zero_stats(&ipvs->tot_stats); return 0; } @@ -1901,6 +1905,7 @@ static inline const char *ip_vs_fwd_name(unsigned int flags) static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_iter *iter = seq->private; int idx; struct ip_vs_service *svc; @@ -1908,7 +1913,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) /* look in hash by protocol */ for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[idx], s_list) { - if (net_eq(svc->net, net) && pos-- == 0) { + if ((svc->ipvs == ipvs) && pos-- == 0) { iter->table = ip_vs_svc_table; iter->bucket = idx; return svc; @@ -1920,7 +1925,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[idx], f_list) { - if (net_eq(svc->net, net) && pos-- == 0) { + if ((svc->ipvs == ipvs) && pos-- == 0) { iter->table = ip_vs_svc_fwm_table; iter->bucket = idx; return svc; @@ -2487,6 +2492,7 @@ __ip_vs_get_service_entries(struct net *net, const struct ip_vs_get_services *get, struct ip_vs_get_services __user *uptr) { + struct netns_ipvs *ipvs = net_ipvs(net); int idx, count=0; struct ip_vs_service *svc; struct ip_vs_service_entry entry; @@ -2495,7 +2501,7 @@ __ip_vs_get_service_entries(struct net *net, for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { /* Only expose IPv4 entries to old interface */ - if (svc->af != AF_INET || !net_eq(svc->net, net)) + if (svc->af != AF_INET || (svc->ipvs != ipvs)) continue; if (count >= get->num_services) @@ -2514,7 +2520,7 @@ __ip_vs_get_service_entries(struct net *net, for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { /* Only expose IPv4 entries to old interface */ - if (svc->af != AF_INET || !net_eq(svc->net, net)) + if (svc->af != AF_INET || (svc->ipvs != ipvs)) continue; if (count >= get->num_services) @@ -3008,12 +3014,12 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb, int idx = 0, i; int start = cb->args[0]; struct ip_vs_service *svc; - struct net *net = skb_sknet(skb); + struct netns_ipvs *ipvs = net_ipvs(skb_sknet(skb)); mutex_lock(&__ip_vs_mutex); for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { hlist_for_each_entry(svc, &ip_vs_svc_table[i], s_list) { - if (++idx <= start || !net_eq(svc->net, net)) + if (++idx <= start || (svc->ipvs != ipvs)) continue; if (ip_vs_genl_dump_service(skb, svc, cb) < 0) { idx--; @@ -3024,7 +3030,7 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb, for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) { - if (++idx <= start || !net_eq(svc->net, net)) + if (++idx <= start || (svc->ipvs != ipvs)) continue; if (ip_vs_genl_dump_service(skb, svc, cb) < 0) { idx--; diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 127f14046c51..cccf4d637412 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -250,8 +250,7 @@ static void ip_vs_lblc_flush(struct ip_vs_service *svc) static int sysctl_lblc_expiration(struct ip_vs_service *svc) { #ifdef CONFIG_SYSCTL - struct netns_ipvs *ipvs = net_ipvs(svc->net); - return ipvs->sysctl_lblc_expiration; + return svc->ipvs->sysctl_lblc_expiration; #else return DEFAULT_EXPIRATION; #endif diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 2229d2d8bbe0..796d70e47ddd 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -415,8 +415,7 @@ static void ip_vs_lblcr_flush(struct ip_vs_service *svc) static int sysctl_lblcr_expiration(struct ip_vs_service *svc) { #ifdef CONFIG_SYSCTL - struct netns_ipvs *ipvs = net_ipvs(svc->net); - return ipvs->sysctl_lblcr_expiration; + return svc->ipvs->sysctl_lblcr_expiration; #else return DEFAULT_EXPIRATION; #endif -- cgit v1.2.3 From 0a4fd6ce92460ec325f7e56813645e4308da170e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:49 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_service_find Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_ctl.c | 5 ++--- net/netfilter/ipvs/ip_vs_proto_sctp.c | 4 ++-- net/netfilter/ipvs/ip_vs_proto_tcp.c | 4 ++-- net/netfilter/ipvs/ip_vs_proto_udp.c | 6 ++++-- 5 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 2c22380b9ad7..828b19b23e02 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1410,7 +1410,7 @@ extern struct ip_vs_stats ip_vs_stats; extern int sysctl_ip_vs_sync_ver; struct ip_vs_service * -ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol, +ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport); bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol, diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index fd8de5ceffca..67fe0c92e3f7 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -406,11 +406,10 @@ __ip_vs_svc_fwm_find(struct netns_ipvs *ipvs, int af, __u32 fwmark) /* Find service, called under RCU lock */ struct ip_vs_service * -ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol, +ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport) { struct ip_vs_service *svc; - struct netns_ipvs *ipvs = net_ipvs(net); /* * Check the table hashed by fwmark first @@ -612,7 +611,7 @@ struct ip_vs_dest *ip_vs_find_dest(struct net *net, int svc_af, int dest_af, struct ip_vs_service *svc; __be16 port = dport; - svc = ip_vs_service_find(net, svc_af, fwmark, protocol, vaddr, vport); + svc = ip_vs_service_find(net_ipvs(net), svc_af, fwmark, protocol, vaddr, vport); if (!svc) return NULL; if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index ce615866bd63..373a4751c328 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -45,10 +45,10 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, rcu_read_lock(); if (likely(!ip_vs_iph_inverse(iph))) - svc = ip_vs_service_find(net, af, skb->mark, iph->protocol, + svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->daddr, ports[1]); else - svc = ip_vs_service_find(net, af, skb->mark, iph->protocol, + svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->saddr, ports[0]); if (svc) { int ignored; diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index e00623a88518..48af3ca6be03 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -70,10 +70,10 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, rcu_read_lock(); if (likely(!ip_vs_iph_inverse(iph))) - svc = ip_vs_service_find(net, af, skb->mark, iph->protocol, + svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->daddr, ports[1]); else - svc = ip_vs_service_find(net, af, skb->mark, iph->protocol, + svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->saddr, ports[0]); if (svc) { diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 3b0a2dc1826b..e9f5f7e30bef 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -34,6 +34,7 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph) { struct net *net; + struct netns_ipvs *ipvs; struct ip_vs_service *svc; struct udphdr _udph, *uh; __be16 _ports[2], *ports = NULL; @@ -54,12 +55,13 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, } net = skb_net(skb); + ipvs = net_ipvs(net); rcu_read_lock(); if (likely(!ip_vs_iph_inverse(iph))) - svc = ip_vs_service_find(net, af, skb->mark, iph->protocol, + svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->daddr, ports[1]); else - svc = ip_vs_service_find(net, af, skb->mark, iph->protocol, + svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->saddr, ports[0]); if (svc) { -- cgit v1.2.3 From 48aed1b029597d5f33316b1e978392fe30814f8d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:50 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_has_real_service Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_core.c | 6 ++++-- net/netfilter/ipvs/ip_vs_ctl.c | 3 +-- 3 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 828b19b23e02..b93ee28fb011 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1413,7 +1413,7 @@ struct ip_vs_service * ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport); -bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol, +bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); int ip_vs_use_count_inc(void); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 583199c2bcdc..c22e0692e22d 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1186,6 +1186,7 @@ static unsigned int ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) { struct net *net = NULL; + struct netns_ipvs *ipvs; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; @@ -1211,7 +1212,8 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) return NF_ACCEPT; net = skb_net(skb); - if (!net_ipvs(net)->enable) + ipvs = net_ipvs(net); + if (!ipvs->enable) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, false, &iph); @@ -1269,7 +1271,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) sizeof(_ports), _ports, &iph); if (pptr == NULL) return NF_ACCEPT; /* Not for me */ - if (ip_vs_has_real_service(net, af, iph.protocol, &iph.saddr, + if (ip_vs_has_real_service(ipvs, af, iph.protocol, &iph.saddr, pptr[0])) { /* * Notify the real server: there is no diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 67fe0c92e3f7..8f914b67b41a 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -542,10 +542,9 @@ static void ip_vs_rs_unhash(struct ip_vs_dest *dest) } /* Check if real service by is present */ -bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol, +bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport) { - struct netns_ipvs *ipvs = net_ipvs(net); unsigned int hash; struct ip_vs_dest *dest; -- cgit v1.2.3 From dc2add6f2e35916afd6ffcd7819a06ce9b28063d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:51 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_find_dest Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_conn.c | 2 +- net/netfilter/ipvs/ip_vs_ctl.c | 4 ++-- net/netfilter/ipvs/ip_vs_sync.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b93ee28fb011..b54a19eaa630 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1423,7 +1423,7 @@ void ip_vs_unregister_nl_ioctl(void); int ip_vs_control_init(void); void ip_vs_control_cleanup(void); struct ip_vs_dest * -ip_vs_find_dest(struct net *net, int svc_af, int dest_af, +ip_vs_find_dest(struct netns_ipvs *ipvs, int svc_af, int dest_af, const union nf_inet_addr *daddr, __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol, __u32 fwmark, __u32 flags); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 3e277093ec45..ce788f8781f4 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -638,7 +638,7 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp) * so we can make the assumption that the svc_af is the same as the * dest_af */ - dest = ip_vs_find_dest(cp->ipvs->net, cp->af, cp->af, &cp->daddr, + dest = ip_vs_find_dest(cp->ipvs, cp->af, cp->af, &cp->daddr, cp->dport, &cp->vaddr, cp->vport, cp->protocol, cp->fwmark, cp->flags); if (dest) { diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 8f914b67b41a..24dceaccb0a1 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -599,7 +599,7 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, int dest_af, * on the backup. * Called under RCU lock, no refcnt is returned. */ -struct ip_vs_dest *ip_vs_find_dest(struct net *net, int svc_af, int dest_af, +struct ip_vs_dest *ip_vs_find_dest(struct netns_ipvs *ipvs, int svc_af, int dest_af, const union nf_inet_addr *daddr, __be16 dport, const union nf_inet_addr *vaddr, @@ -610,7 +610,7 @@ struct ip_vs_dest *ip_vs_find_dest(struct net *net, int svc_af, int dest_af, struct ip_vs_service *svc; __be16 port = dport; - svc = ip_vs_service_find(net_ipvs(net), svc_af, fwmark, protocol, vaddr, vport); + svc = ip_vs_service_find(ipvs, svc_af, fwmark, protocol, vaddr, vport); if (!svc) return NULL; if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index f8bc2027a6c4..9a49c3899f2e 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -904,7 +904,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, * with synchronization, so we can make the assumption that * the svc_af is the same as the dest_af */ - dest = ip_vs_find_dest(net, type, type, daddr, dport, + dest = ip_vs_find_dest(ipvs, type, type, daddr, dport, param->vaddr, param->vport, protocol, fwmark, flags); -- cgit v1.2.3 From 56d2169b7734f9b5cb2a4e66887ce6dc33d53632 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:58 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_service_net_cleanup Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_core.c | 6 ++++-- net/netfilter/ipvs/ip_vs_ctl.c | 3 +-- 3 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b54a19eaa630..3c7040a313b5 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1335,7 +1335,7 @@ void ip_vs_protocol_net_cleanup(struct net *net); void ip_vs_control_net_cleanup(struct net *net); void ip_vs_estimator_net_cleanup(struct net *net); void ip_vs_sync_net_cleanup(struct net *net); -void ip_vs_service_net_cleanup(struct net *net); +void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs); /* IPVS application functions * (from ip_vs_app.c) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index c22e0692e22d..787d561e200b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2110,13 +2110,15 @@ estimator_fail: static void __net_exit __ip_vs_cleanup(struct net *net) { - ip_vs_service_net_cleanup(net); /* ip_vs_flush() with locks */ + struct netns_ipvs *ipvs = net_ipvs(net); + + ip_vs_service_net_cleanup(ipvs); /* ip_vs_flush() with locks */ ip_vs_conn_net_cleanup(net); ip_vs_app_net_cleanup(net); ip_vs_protocol_net_cleanup(net); ip_vs_control_net_cleanup(net); ip_vs_estimator_net_cleanup(net); - IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); + IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen); net->ipvs = NULL; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index d9ff59a4bc6e..a281961a1840 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1484,9 +1484,8 @@ static int ip_vs_flush(struct netns_ipvs *ipvs, bool cleanup) * Delete service by {netns} in the service table. * Called by __ip_vs_cleanup() */ -void ip_vs_service_net_cleanup(struct net *net) +void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); EnterFunction(2); /* Check for "full" addressed entries */ mutex_lock(&__ip_vs_mutex); -- cgit v1.2.3 From 18d6ade63c8d796c272e2b4922d649cf108d7980 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:01 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_proto_data_get Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_conn.c | 4 ++-- net/netfilter/ipvs/ip_vs_core.c | 8 ++++---- net/netfilter/ipvs/ip_vs_ctl.c | 12 +++++++----- net/netfilter/ipvs/ip_vs_proto.c | 12 ++---------- net/netfilter/ipvs/ip_vs_proto_sctp.c | 4 ++-- net/netfilter/ipvs/ip_vs_proto_tcp.c | 6 +++--- net/netfilter/ipvs/ip_vs_proto_udp.c | 4 ++-- net/netfilter/ipvs/ip_vs_sync.c | 2 +- 9 files changed, 24 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 3c7040a313b5..3c077e8a038c 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -541,7 +541,7 @@ struct ip_vs_proto_data { }; struct ip_vs_protocol *ip_vs_proto_get(unsigned short proto); -struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net, +struct ip_vs_proto_data *ip_vs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto); struct ip_vs_conn_param { diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index ce788f8781f4..d0d57f14bc76 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -668,7 +668,7 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp) #endif ip_vs_bind_xmit(cp); - pd = ip_vs_proto_data_get(cp->ipvs->net, cp->protocol); + pd = ip_vs_proto_data_get(cp->ipvs, cp->protocol); if (pd && atomic_read(&pd->appcnt)) ip_vs_bind_app(cp, pd->pp); } @@ -876,7 +876,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, { struct ip_vs_conn *cp; struct netns_ipvs *ipvs = p->ipvs; - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->ipvs->net, + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->ipvs, p->protocol); cp = kmem_cache_alloc(ip_vs_conn_cachep, GFP_ATOMIC); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 77dcd3ed27de..2e96500c6f3f 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1237,7 +1237,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) return verdict; } - pd = ip_vs_proto_data_get(net, iph.protocol); + pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) return NF_ACCEPT; pp = pd->pp; @@ -1470,7 +1470,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) ipip = true; } - pd = ip_vs_proto_data_get(net, cih->protocol); + pd = ip_vs_proto_data_get(ipvs, cih->protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; @@ -1633,7 +1633,7 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, net = skb_net(skb); ipvs = net_ipvs(net); - pd = ip_vs_proto_data_get(net, ciph.protocol); + pd = ip_vs_proto_data_get(ipvs, ciph.protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; @@ -1765,7 +1765,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } /* Protocol supported? */ - pd = ip_vs_proto_data_get(net, iph.protocol); + pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) { /* The only way we'll see this packet again is if it's * encapsulated, so mark it with ipvs_property=1 so we diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 0b7749ae1e8d..eb3911c69037 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2205,6 +2205,7 @@ static const struct file_operations ip_vs_stats_percpu_fops = { static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u) { #if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd; #endif @@ -2215,13 +2216,13 @@ static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u) #ifdef CONFIG_IP_VS_PROTO_TCP if (u->tcp_timeout) { - pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] = u->tcp_timeout * HZ; } if (u->tcp_fin_timeout) { - pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] = u->tcp_fin_timeout * HZ; } @@ -2229,7 +2230,7 @@ static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u) #ifdef CONFIG_IP_VS_PROTO_UDP if (u->udp_timeout) { - pd = ip_vs_proto_data_get(net, IPPROTO_UDP); + pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); pd->timeout_table[IP_VS_UDP_S_NORMAL] = u->udp_timeout * HZ; } @@ -2589,18 +2590,19 @@ static inline void __ip_vs_get_timeouts(struct net *net, struct ip_vs_timeout_user *u) { #if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd; #endif memset(u, 0, sizeof (*u)); #ifdef CONFIG_IP_VS_PROTO_TCP - pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ; u->tcp_fin_timeout = pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ; #endif #ifdef CONFIG_IP_VS_PROTO_UDP - pd = ip_vs_proto_data_get(net, IPPROTO_UDP); + pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); u->udp_timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL] / HZ; #endif diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index 939f7fbe9b46..82ccfd2f235c 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -156,8 +156,8 @@ EXPORT_SYMBOL(ip_vs_proto_get); /* * get ip_vs_protocol object data by netns and proto */ -static struct ip_vs_proto_data * -__ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto) +struct ip_vs_proto_data * +ip_vs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto) { struct ip_vs_proto_data *pd; unsigned int hash = IP_VS_PROTO_HASH(proto); @@ -169,14 +169,6 @@ __ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto) return NULL; } - -struct ip_vs_proto_data * -ip_vs_proto_data_get(struct net *net, unsigned short proto) -{ - struct netns_ipvs *ipvs = net_ipvs(net); - - return __ipvs_proto_data_get(ipvs, proto); -} EXPORT_SYMBOL(ip_vs_proto_data_get); /* diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 373a4751c328..8f39e0266ade 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -494,7 +494,7 @@ static int sctp_register_app(struct net *net, struct ip_vs_app *inc) __be16 port = inc->port; int ret = 0; struct netns_ipvs *ipvs = net_ipvs(net); - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_SCTP); hash = sctp_app_hashkey(port); @@ -513,7 +513,7 @@ out: static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc) { - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net_ipvs(net), IPPROTO_SCTP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 48af3ca6be03..975aa69eec9c 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -602,7 +602,7 @@ static int tcp_register_app(struct net *net, struct ip_vs_app *inc) __be16 port = inc->port; int ret = 0; struct netns_ipvs *ipvs = net_ipvs(net); - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); hash = tcp_app_hashkey(port); @@ -623,7 +623,7 @@ static int tcp_register_app(struct net *net, struct ip_vs_app *inc) static void tcp_unregister_app(struct net *net, struct ip_vs_app *inc) { - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net_ipvs(net), IPPROTO_TCP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); @@ -679,7 +679,7 @@ tcp_app_conn_bind(struct ip_vs_conn *cp) */ void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp) { - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net_ipvs(net), IPPROTO_TCP); spin_lock_bh(&cp->lock); cp->state = IP_VS_TCP_S_LISTEN; diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index e9f5f7e30bef..1baa7494446a 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -372,7 +372,7 @@ static int udp_register_app(struct net *net, struct ip_vs_app *inc) __be16 port = inc->port; int ret = 0; struct netns_ipvs *ipvs = net_ipvs(net); - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); hash = udp_app_hashkey(port); @@ -393,7 +393,7 @@ static int udp_register_app(struct net *net, struct ip_vs_app *inc) static void udp_unregister_app(struct net *net, struct ip_vs_app *inc) { - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net_ipvs(net), IPPROTO_UDP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 9a49c3899f2e..d158e0713ab9 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -941,7 +941,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, } else { struct ip_vs_proto_data *pd; - pd = ip_vs_proto_data_get(net, protocol); + pd = ip_vs_proto_data_get(ipvs, protocol); if (!(flags & IP_VS_CONN_F_TEMPLATE) && pd && pd->timeout_table) cp->timeout = pd->timeout_table[state]; else -- cgit v1.2.3 From 6ac121d710697cee894d6981b804583b0a66ed38 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:10 -0500 Subject: ipvs: Pass ipvs not net to start_sync_thread Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_ctl.c | 4 ++-- net/netfilter/ipvs/ip_vs_sync.c | 11 +++++------ 3 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 3c077e8a038c..dd7cd3a48fd4 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1449,7 +1449,7 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest) /* IPVS sync daemon data and function prototypes * (from ip_vs_sync.c) */ -int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *cfg, +int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *cfg, int state); int stop_sync_thread(struct net *net, int state); void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 08d772c289d7..b63b4c186040 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2350,7 +2350,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) cfg.syncid = dm->syncid; rtnl_lock(); mutex_lock(&ipvs->sync_mutex); - ret = start_sync_thread(net, &cfg, dm->state); + ret = start_sync_thread(ipvs, &cfg, dm->state); mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); } else { @@ -3432,7 +3432,7 @@ static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs) rtnl_lock(); mutex_lock(&ipvs->sync_mutex); - ret = start_sync_thread(ipvs->net, &c, + ret = start_sync_thread(ipvs, &c, nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index d158e0713ab9..90c455c0b42b 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1778,13 +1778,12 @@ static int sync_thread_backup(void *data) } -int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c, +int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, int state) { struct ip_vs_sync_thread_data *tinfo; struct task_struct **array = NULL, *task; struct socket *sock; - struct netns_ipvs *ipvs = net_ipvs(net); struct net_device *dev; char *name; int (*threadfn)(void *data); @@ -1811,7 +1810,7 @@ int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c, if (!c->mcast_ttl) c->mcast_ttl = 1; - dev = __dev_get_by_name(net, c->mcast_ifn); + dev = __dev_get_by_name(ipvs->net, c->mcast_ifn); if (!dev) { pr_err("Unknown mcast interface: %s\n", c->mcast_ifn); return -ENODEV; @@ -1873,9 +1872,9 @@ int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c, tinfo = NULL; for (id = 0; id < count; id++) { if (state == IP_VS_STATE_MASTER) - sock = make_send_sock(net, id); + sock = make_send_sock(ipvs->net, id); else - sock = make_receive_sock(net, id); + sock = make_receive_sock(ipvs->net, id); if (IS_ERR(sock)) { result = PTR_ERR(sock); goto outtinfo; @@ -1883,7 +1882,7 @@ int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c, tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL); if (!tinfo) goto outsocket; - tinfo->net = net; + tinfo->net = ipvs->net; tinfo->sock = sock; if (state == IP_VS_STATE_BACKUP) { tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen, -- cgit v1.2.3 From b3cf3cbfb57c273cf9f88230416fcc5b97287862 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:11 -0500 Subject: ipvs: Pass ipvs not net to stop_sync_thread Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_ctl.c | 4 ++-- net/netfilter/ipvs/ip_vs_sync.c | 7 +++---- 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index dd7cd3a48fd4..71f4d338c208 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1451,7 +1451,7 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest) */ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *cfg, int state); -int stop_sync_thread(struct net *net, int state); +int stop_sync_thread(struct netns_ipvs *ipvs, int state); void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts); /* IPVS rate estimator prototypes (from ip_vs_est.c) */ diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index b63b4c186040..dba75ec2ed53 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2355,7 +2355,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) rtnl_unlock(); } else { mutex_lock(&ipvs->sync_mutex); - ret = stop_sync_thread(net, dm->state); + ret = stop_sync_thread(ipvs, dm->state); mutex_unlock(&ipvs->sync_mutex); } goto out_dec; @@ -3447,7 +3447,7 @@ static int ip_vs_genl_del_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs) return -EINVAL; mutex_lock(&ipvs->sync_mutex); - ret = stop_sync_thread(ipvs->net, + ret = stop_sync_thread(ipvs, nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); mutex_unlock(&ipvs->sync_mutex); return ret; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 90c455c0b42b..0b2e01aa764a 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1946,9 +1946,8 @@ out: } -int stop_sync_thread(struct net *net, int state) +int stop_sync_thread(struct netns_ipvs *ipvs, int state) { - struct netns_ipvs *ipvs = net_ipvs(net); struct task_struct **array; int id; int retc = -EINVAL; @@ -2030,11 +2029,11 @@ void ip_vs_sync_net_cleanup(struct net *net) struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&ipvs->sync_mutex); - retc = stop_sync_thread(net, IP_VS_STATE_MASTER); + retc = stop_sync_thread(ipvs, IP_VS_STATE_MASTER); if (retc && retc != -ESRCH) pr_err("Failed to stop Master Daemon\n"); - retc = stop_sync_thread(net, IP_VS_STATE_BACKUP); + retc = stop_sync_thread(ipvs, IP_VS_STATE_BACKUP); if (retc && retc != -ESRCH) pr_err("Failed to stop Backup Daemon\n"); mutex_unlock(&ipvs->sync_mutex); -- cgit v1.2.3 From b61a8c1a40c2a9417eb6f710cce54353d195c9c7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:17 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_sync_conn Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_conn.c | 3 +-- net/netfilter/ipvs/ip_vs_core.c | 2 +- net/netfilter/ipvs/ip_vs_sync.c | 5 ++--- 4 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 71f4d338c208..b10b337ce974 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1452,7 +1452,7 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest) int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *cfg, int state); int stop_sync_thread(struct netns_ipvs *ipvs, int state); -void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts); +void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts); /* IPVS rate estimator prototypes (from ip_vs_est.c) */ void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index d0d57f14bc76..06809db5eef6 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -801,7 +801,6 @@ static void ip_vs_conn_expire(unsigned long data) { struct ip_vs_conn *cp = (struct ip_vs_conn *)data; struct netns_ipvs *ipvs = cp->ipvs; - struct net *net = ipvs->net; /* * do I control anybody? @@ -847,7 +846,7 @@ static void ip_vs_conn_expire(unsigned long data) cp->timeout = 60*HZ; if (ipvs->sync_state & IP_VS_STATE_MASTER) - ip_vs_sync_conn(net, cp, sysctl_sync_threshold(ipvs)); + ip_vs_sync_conn(ipvs, cp, sysctl_sync_threshold(ipvs)); ip_vs_conn_put(cp); } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 2e96500c6f3f..a8128b06f73b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1842,7 +1842,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) pkts = atomic_add_return(1, &cp->in_pkts); if (ipvs->sync_state & IP_VS_STATE_MASTER) - ip_vs_sync_conn(net, cp, pkts); + ip_vs_sync_conn(ipvs, cp, pkts); ip_vs_conn_put(cp); return ret; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 58ec7850ab06..a0808f230cd6 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -614,7 +614,7 @@ static void ip_vs_sync_conn_v0(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, pkts = atomic_add_return(1, &cp->in_pkts); else pkts = sysctl_sync_threshold(ipvs); - ip_vs_sync_conn(ipvs->net, cp, pkts); + ip_vs_sync_conn(ipvs, cp, pkts); } } @@ -623,9 +623,8 @@ static void ip_vs_sync_conn_v0(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, * Called by ip_vs_in. * Sending Version 1 messages */ -void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts) +void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_sync_mesg *m; union ip_vs_sync_conn *s; struct ip_vs_sync_buff *buff; -- cgit v1.2.3 From 802cb43703d080bd6269578bf6747189b654cc24 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:20 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_sync_net_init Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_core.c | 2 +- net/netfilter/ipvs/ip_vs_sync.c | 4 +--- 3 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b10b337ce974..47a4cddb7c33 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1328,7 +1328,7 @@ int ip_vs_control_net_init(struct net *net); int ip_vs_protocol_net_init(struct net *net); int ip_vs_app_net_init(struct net *net); int ip_vs_conn_net_init(struct net *net); -int ip_vs_sync_net_init(struct net *net); +int ip_vs_sync_net_init(struct netns_ipvs *ipvs); void ip_vs_conn_net_cleanup(struct net *net); void ip_vs_app_net_cleanup(struct net *net); void ip_vs_protocol_net_cleanup(struct net *net); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index a8128b06f73b..5a5a6d63b3d9 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2087,7 +2087,7 @@ static int __net_init __ip_vs_init(struct net *net) if (ip_vs_conn_net_init(net) < 0) goto conn_fail; - if (ip_vs_sync_net_init(net) < 0) + if (ip_vs_sync_net_init(ipvs) < 0) goto sync_fail; printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n", diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index e3f72cbc1204..11b4f17e2e1a 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -2007,10 +2007,8 @@ int stop_sync_thread(struct netns_ipvs *ipvs, int state) /* * Initialize data struct for each netns */ -int __net_init ip_vs_sync_net_init(struct net *net) +int __net_init ip_vs_sync_net_init(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); - __mutex_init(&ipvs->sync_mutex, "ipvs->sync_mutex", &__ipvs_sync_key); spin_lock_init(&ipvs->sync_lock); spin_lock_init(&ipvs->sync_buff_lock); -- cgit v1.2.3 From ebea1f7c0b8c0bb02045c87e4b548a31fc5612a6 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:21 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_sync_net_cleanup Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_core.c | 5 +++-- net/netfilter/ipvs/ip_vs_sync.c | 3 +-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 47a4cddb7c33..f3ddf7696d68 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1334,7 +1334,7 @@ void ip_vs_app_net_cleanup(struct net *net); void ip_vs_protocol_net_cleanup(struct net *net); void ip_vs_control_net_cleanup(struct net *net); void ip_vs_estimator_net_cleanup(struct net *net); -void ip_vs_sync_net_cleanup(struct net *net); +void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs); /* IPVS application functions diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 5a5a6d63b3d9..cae395fc6523 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2128,10 +2128,11 @@ static void __net_exit __ip_vs_cleanup(struct net *net) static void __net_exit __ip_vs_dev_cleanup(struct net *net) { + struct netns_ipvs *ipvs = net_ipvs(net); EnterFunction(2); - net_ipvs(net)->enable = 0; /* Disable packet reception */ + ipvs->enable = 0; /* Disable packet reception */ smp_wmb(); - ip_vs_sync_net_cleanup(net); + ip_vs_sync_net_cleanup(ipvs); LeaveFunction(2); } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 11b4f17e2e1a..803001a45aa1 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -2015,10 +2015,9 @@ int __net_init ip_vs_sync_net_init(struct netns_ipvs *ipvs) return 0; } -void ip_vs_sync_net_cleanup(struct net *net) +void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs) { int retc; - struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&ipvs->sync_mutex); retc = stop_sync_thread(ipvs, IP_VS_STATE_MASTER); -- cgit v1.2.3 From 0f34d54bf48892f23e2abef2f9fd8d0237db4623 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:23 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_start_estimator aned ip_vs_stop_estimator Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- net/netfilter/ipvs/ip_vs_ctl.c | 12 ++++++------ net/netfilter/ipvs/ip_vs_est.c | 6 ++---- 3 files changed, 10 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index f3ddf7696d68..2d49357b328c 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1455,8 +1455,8 @@ int stop_sync_thread(struct netns_ipvs *ipvs, int state); void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts); /* IPVS rate estimator prototypes (from ip_vs_est.c) */ -void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats); -void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats); +void ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); +void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); void ip_vs_zero_estimator(struct ip_vs_stats *stats); void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 4042a6f449cb..f43b894f3ef6 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -840,7 +840,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, spin_unlock_bh(&dest->dst_lock); if (add) { - ip_vs_start_estimator(svc->ipvs->net, &dest->stats); + ip_vs_start_estimator(svc->ipvs, &dest->stats); list_add_rcu(&dest->n_list, &svc->destinations); svc->num_dests++; sched = rcu_dereference_protected(svc->scheduler, 1); @@ -1036,7 +1036,7 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest, bool cleanup) { - ip_vs_stop_estimator(ipvs->net, &dest->stats); + ip_vs_stop_estimator(ipvs, &dest->stats); /* * Remove it from the d-linked list with the real services. @@ -1254,7 +1254,7 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, else if (svc->port == 0) atomic_inc(&ipvs->nullsvc_counter); - ip_vs_start_estimator(ipvs->net, &svc->stats); + ip_vs_start_estimator(ipvs, &svc->stats); /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) @@ -1382,7 +1382,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) if (svc->af == AF_INET) ipvs->num_services--; - ip_vs_stop_estimator(svc->ipvs->net, &svc->stats); + ip_vs_stop_estimator(svc->ipvs, &svc->stats); /* Unbind scheduler */ old_sched = rcu_dereference_protected(svc->scheduler, 1); @@ -3917,7 +3917,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) kfree(tbl); return -ENOMEM; } - ip_vs_start_estimator(net, &ipvs->tot_stats); + ip_vs_start_estimator(ipvs, &ipvs->tot_stats); ipvs->sysctl_tbl = tbl; /* Schedule defense work */ INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler); @@ -3933,7 +3933,7 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) cancel_delayed_work_sync(&ipvs->defense_work); cancel_work_sync(&ipvs->defense_work.work); unregister_net_sysctl_table(ipvs->sysctl_hdr); - ip_vs_stop_estimator(net, &ipvs->tot_stats); + ip_vs_stop_estimator(ipvs, &ipvs->tot_stats); if (!net_eq(net, &init_net)) kfree(ipvs->sysctl_tbl); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index ef0eb0a8d552..638a301f7ee4 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -140,9 +140,8 @@ static void estimation_timer(unsigned long arg) mod_timer(&ipvs->est_timer, jiffies + 2*HZ); } -void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats) +void ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_estimator *est = &stats->est; INIT_LIST_HEAD(&est->list); @@ -152,9 +151,8 @@ void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats) spin_unlock_bh(&ipvs->est_lock); } -void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats) +void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_estimator *est = &stats->est; spin_lock_bh(&ipvs->est_lock); -- cgit v1.2.3 From 423b55954de222380a6b63c5b6ae7b6686e98e63 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:24 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_random_drop_entry Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_conn.c | 4 ++-- net/netfilter/ipvs/ip_vs_ctl.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 2d49357b328c..c88a3bf85f98 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1258,7 +1258,7 @@ const char *ip_vs_state_name(__u16 proto, int state); void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp); int ip_vs_check_template(struct ip_vs_conn *ct); -void ip_vs_random_dropentry(struct net *net); +void ip_vs_random_dropentry(struct netns_ipvs *ipvs); int ip_vs_conn_init(void); void ip_vs_conn_cleanup(void); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 06809db5eef6..bbe9e69e3eeb 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1239,7 +1239,7 @@ static inline int todrop_entry(struct ip_vs_conn *cp) } /* Called from keventd and must protect itself from softirqs */ -void ip_vs_random_dropentry(struct net *net) +void ip_vs_random_dropentry(struct netns_ipvs *ipvs) { int idx; struct ip_vs_conn *cp, *cp_c; @@ -1255,7 +1255,7 @@ void ip_vs_random_dropentry(struct net *net) if (cp->flags & IP_VS_CONN_F_TEMPLATE) /* connection template */ continue; - if (!net_eq(cp->ipvs->net, net)) + if (cp->ipvs != ipvs) continue; if (cp->protocol == IPPROTO_TCP) { switch(cp->state) { diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index f43b894f3ef6..93b7bd39bcb9 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -228,7 +228,7 @@ static void defense_work_handler(struct work_struct *work) update_defense_level(ipvs); if (atomic_read(&ipvs->dropentry)) - ip_vs_random_dropentry(ipvs->net); + ip_vs_random_dropentry(ipvs); schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD); } #endif -- cgit v1.2.3 From 3d99376689ee40d4e88c90d26588268a4fccb383 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:26 -0500 Subject: ipvs: Pass ipvs not net into ip_vs_control_net_(init|cleanup) Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- net/netfilter/ipvs/ip_vs_core.c | 6 +++--- net/netfilter/ipvs/ip_vs_ctl.c | 8 ++++---- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index c88a3bf85f98..38c1fca0c1a7 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1324,7 +1324,7 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) /* IPVS netns init & cleanup functions */ int ip_vs_estimator_net_init(struct net *net); -int ip_vs_control_net_init(struct net *net); +int ip_vs_control_net_init(struct netns_ipvs *ipvs); int ip_vs_protocol_net_init(struct net *net); int ip_vs_app_net_init(struct net *net); int ip_vs_conn_net_init(struct net *net); @@ -1332,7 +1332,7 @@ int ip_vs_sync_net_init(struct netns_ipvs *ipvs); void ip_vs_conn_net_cleanup(struct net *net); void ip_vs_app_net_cleanup(struct net *net); void ip_vs_protocol_net_cleanup(struct net *net); -void ip_vs_control_net_cleanup(struct net *net); +void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_estimator_net_cleanup(struct net *net); void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index cae395fc6523..b5f451f20f52 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2075,7 +2075,7 @@ static int __net_init __ip_vs_init(struct net *net) if (ip_vs_estimator_net_init(net) < 0) goto estimator_fail; - if (ip_vs_control_net_init(net) < 0) + if (ip_vs_control_net_init(ipvs) < 0) goto control_fail; if (ip_vs_protocol_net_init(net) < 0) @@ -2104,7 +2104,7 @@ conn_fail: app_fail: ip_vs_protocol_net_cleanup(net); protocol_fail: - ip_vs_control_net_cleanup(net); + ip_vs_control_net_cleanup(ipvs); control_fail: ip_vs_estimator_net_cleanup(net); estimator_fail: @@ -2120,7 +2120,7 @@ static void __net_exit __ip_vs_cleanup(struct net *net) ip_vs_conn_net_cleanup(net); ip_vs_app_net_cleanup(net); ip_vs_protocol_net_cleanup(net); - ip_vs_control_net_cleanup(net); + ip_vs_control_net_cleanup(ipvs); ip_vs_estimator_net_cleanup(net); IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen); net->ipvs = NULL; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index f0d72d6375e7..b7a0bd274085 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3950,10 +3950,10 @@ static struct notifier_block ip_vs_dst_notifier = { .notifier_call = ip_vs_dst_event, }; -int __net_init ip_vs_control_net_init(struct net *net) +int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) { + struct net *net = ipvs->net; int i, idx; - struct netns_ipvs *ipvs = net_ipvs(net); /* Initialize rs_table */ for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++) @@ -3994,9 +3994,9 @@ err: return -ENOMEM; } -void __net_exit ip_vs_control_net_cleanup(struct net *net) +void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); + struct net *net = ipvs->net; ip_vs_trash_cleanup(ipvs); ip_vs_control_net_cleanup_sysctl(ipvs); -- cgit v1.2.3 From a4dd0360c623e5beac011f3674ff7e13b35b5b05 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:28 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_estimator_net_init and ip_vs_estimator_cleanup Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- net/netfilter/ipvs/ip_vs_core.c | 6 +++--- net/netfilter/ipvs/ip_vs_est.c | 8 +++----- 3 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 38c1fca0c1a7..02734eaae679 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1323,7 +1323,7 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) } /* IPVS netns init & cleanup functions */ -int ip_vs_estimator_net_init(struct net *net); +int ip_vs_estimator_net_init(struct netns_ipvs *ipvs); int ip_vs_control_net_init(struct netns_ipvs *ipvs); int ip_vs_protocol_net_init(struct net *net); int ip_vs_app_net_init(struct net *net); @@ -1333,7 +1333,7 @@ void ip_vs_conn_net_cleanup(struct net *net); void ip_vs_app_net_cleanup(struct net *net); void ip_vs_protocol_net_cleanup(struct net *net); void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs); -void ip_vs_estimator_net_cleanup(struct net *net); +void ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index b5f451f20f52..ec6f022fba6a 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2072,7 +2072,7 @@ static int __net_init __ip_vs_init(struct net *net) atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; - if (ip_vs_estimator_net_init(net) < 0) + if (ip_vs_estimator_net_init(ipvs) < 0) goto estimator_fail; if (ip_vs_control_net_init(ipvs) < 0) @@ -2106,7 +2106,7 @@ app_fail: protocol_fail: ip_vs_control_net_cleanup(ipvs); control_fail: - ip_vs_estimator_net_cleanup(net); + ip_vs_estimator_net_cleanup(ipvs); estimator_fail: net->ipvs = NULL; return -ENOMEM; @@ -2121,7 +2121,7 @@ static void __net_exit __ip_vs_cleanup(struct net *net) ip_vs_app_net_cleanup(net); ip_vs_protocol_net_cleanup(net); ip_vs_control_net_cleanup(ipvs); - ip_vs_estimator_net_cleanup(net); + ip_vs_estimator_net_cleanup(ipvs); IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen); net->ipvs = NULL; } diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index c86dc456c8f4..457c6c193e13 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -188,10 +188,8 @@ void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats) dst->outbps = (e->outbps + 0xF) >> 5; } -int __net_init ip_vs_estimator_net_init(struct net *net) +int __net_init ip_vs_estimator_net_init(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); - INIT_LIST_HEAD(&ipvs->est_list); spin_lock_init(&ipvs->est_lock); setup_timer(&ipvs->est_timer, estimation_timer, (unsigned long)ipvs); @@ -199,7 +197,7 @@ int __net_init ip_vs_estimator_net_init(struct net *net) return 0; } -void __net_exit ip_vs_estimator_net_cleanup(struct net *net) +void __net_exit ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs) { - del_timer_sync(&net_ipvs(net)->est_timer); + del_timer_sync(&ipvs->est_timer); } -- cgit v1.2.3 From 19648918fbf245ab2dda8c7842c9a83fd412ac35 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:29 -0500 Subject: ipvs: Pass ipvs not net into register_app and unregister_app Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- net/netfilter/ipvs/ip_vs_app.c | 6 ++++-- net/netfilter/ipvs/ip_vs_proto_sctp.c | 7 +++---- net/netfilter/ipvs/ip_vs_proto_tcp.c | 7 +++---- net/netfilter/ipvs/ip_vs_proto_udp.c | 7 +++---- 5 files changed, 15 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 02734eaae679..a7275ae18b96 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -517,9 +517,9 @@ struct ip_vs_protocol { const struct sk_buff *skb, struct ip_vs_proto_data *pd); - int (*register_app)(struct net *net, struct ip_vs_app *inc); + int (*register_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc); - void (*unregister_app)(struct net *net, struct ip_vs_app *inc); + void (*unregister_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc); int (*app_conn_bind)(struct ip_vs_conn *cp); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index dfd7b65b3d2a..f20f72c4ac80 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -78,6 +78,7 @@ static int ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto, __u16 port) { + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_protocol *pp; struct ip_vs_app *inc; int ret; @@ -107,7 +108,7 @@ ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto, } } - ret = pp->register_app(net, inc); + ret = pp->register_app(ipvs, inc); if (ret) goto out; @@ -129,13 +130,14 @@ ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto, static void ip_vs_app_inc_release(struct net *net, struct ip_vs_app *inc) { + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_protocol *pp; if (!(pp = ip_vs_proto_get(inc->protocol))) return; if (pp->unregister_app) - pp->unregister_app(net, inc); + pp->unregister_app(ipvs, inc); IP_VS_DBG(9, "%s App %s:%u unregistered\n", pp->name, inc->name, ntohs(inc->port)); diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 8f39e0266ade..345fc7485f2e 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -487,13 +487,12 @@ static inline __u16 sctp_app_hashkey(__be16 port) & SCTP_APP_TAB_MASK; } -static int sctp_register_app(struct net *net, struct ip_vs_app *inc) +static int sctp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_SCTP); hash = sctp_app_hashkey(port); @@ -511,9 +510,9 @@ out: return ret; } -static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc) +static void sctp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net_ipvs(net), IPPROTO_SCTP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_SCTP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 975aa69eec9c..94bea31ec388 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -595,13 +595,12 @@ static inline __u16 tcp_app_hashkey(__be16 port) } -static int tcp_register_app(struct net *net, struct ip_vs_app *inc) +static int tcp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); hash = tcp_app_hashkey(port); @@ -621,9 +620,9 @@ static int tcp_register_app(struct net *net, struct ip_vs_app *inc) static void -tcp_unregister_app(struct net *net, struct ip_vs_app *inc) +tcp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net_ipvs(net), IPPROTO_TCP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 1baa7494446a..234521ec9703 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -365,13 +365,12 @@ static inline __u16 udp_app_hashkey(__be16 port) } -static int udp_register_app(struct net *net, struct ip_vs_app *inc) +static int udp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); hash = udp_app_hashkey(port); @@ -391,9 +390,9 @@ static int udp_register_app(struct net *net, struct ip_vs_app *inc) static void -udp_unregister_app(struct net *net, struct ip_vs_app *inc) +udp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net_ipvs(net), IPPROTO_UDP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); -- cgit v1.2.3 From 3250dc9c52045dd3f38297d1e189cc147a8db884 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:31 -0500 Subject: ipvs: Pass ipvs not net to register_ip_vs_app_inc Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_app.c | 3 +-- net/netfilter/ipvs/ip_vs_ftp.c | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a7275ae18b96..c06bad39958d 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1345,7 +1345,7 @@ struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app); void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app); int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp); void ip_vs_unbind_app(struct ip_vs_conn *cp); -int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto, +int register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto, __u16 port); int ip_vs_app_inc_get(struct ip_vs_app *inc); void ip_vs_app_inc_put(struct ip_vs_app *inc); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 951516b7783b..20cb947a3ddd 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -176,10 +176,9 @@ void ip_vs_app_inc_put(struct ip_vs_app *inc) * Register an application incarnation in protocol applications */ int -register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto, +register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto, __u16 port) { - struct netns_ipvs *ipvs = net_ipvs(net); int result; mutex_lock(&__ip_vs_app_mutex); diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index cf0cba956a21..24bab8e5a507 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -454,7 +454,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net) for (i = 0; i < ports_count; i++) { if (!ports[i]) continue; - ret = register_ip_vs_app_inc(net, app, app->protocol, ports[i]); + ret = register_ip_vs_app_inc(ipvs, app, app->protocol, ports[i]); if (ret) goto err_unreg; pr_info("%s: loaded support on port[%d] = %d\n", -- cgit v1.2.3 From 9f8128a56ef241753ea038e92948fe13beacf59f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:32 -0500 Subject: ipvs: Pass ipvs not net to register_ip_vs_app and unregister_ip_vs_app Also move the tests for net_ipvs being NULL into __ip_vs_ftp_init and __ip_vs_ftp_exit. The only places where they possibly make sense. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- net/netfilter/ipvs/ip_vs_app.c | 17 ++++++----------- net/netfilter/ipvs/ip_vs_ftp.c | 11 ++++++++--- 3 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index c06bad39958d..5caafed5af2e 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1341,8 +1341,8 @@ void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs); * (from ip_vs_app.c) */ #define IP_VS_APP_MAX_PORTS 8 -struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app); -void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app); +struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app); +void unregister_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app); int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp); void ip_vs_unbind_app(struct ip_vs_conn *cp); int register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto, diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 20cb947a3ddd..a0cc08337a2c 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -192,15 +192,11 @@ register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 pro /* Register application for netns */ -struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app) +struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_app *a; int err = 0; - if (!ipvs) - return ERR_PTR(-ENOENT); - mutex_lock(&__ip_vs_app_mutex); list_for_each_entry(a, &ipvs->app_list, a_list) { @@ -231,13 +227,10 @@ out_unlock: * We are sure there are no app incarnations attached to services * Caller should use synchronize_rcu() or rcu_barrier() */ -void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app) +void unregister_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_app *a, *anxt, *inc, *nxt; - - if (!ipvs) - return; + struct net *net = ipvs->net; mutex_lock(&__ip_vs_app_mutex); @@ -623,6 +616,8 @@ int __net_init ip_vs_app_net_init(struct net *net) void __net_exit ip_vs_app_net_cleanup(struct net *net) { - unregister_ip_vs_app(net, NULL /* all */); + struct netns_ipvs *ipvs = net_ipvs(net); + + unregister_ip_vs_app(ipvs, NULL /* all */); remove_proc_entry("ip_vs_app", net->proc_net); } diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 24bab8e5a507..508544aff36d 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -447,7 +447,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net) if (!ipvs) return -ENOENT; - app = register_ip_vs_app(net, &ip_vs_ftp); + app = register_ip_vs_app(ipvs, &ip_vs_ftp); if (IS_ERR(app)) return PTR_ERR(app); @@ -463,7 +463,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net) return 0; err_unreg: - unregister_ip_vs_app(net, &ip_vs_ftp); + unregister_ip_vs_app(ipvs, &ip_vs_ftp); return ret; } /* @@ -471,7 +471,12 @@ err_unreg: */ static void __ip_vs_ftp_exit(struct net *net) { - unregister_ip_vs_app(net, &ip_vs_ftp); + struct netns_ipvs *ipvs = net_ipvs(net); + + if (!ipvs) + return; + + unregister_ip_vs_app(ipvs, &ip_vs_ftp); } static struct pernet_operations ip_vs_ftp_ops = { -- cgit v1.2.3 From b5dd212cc147603372d39dbe52480d687c98da7d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:34 -0500 Subject: ipvs: Pass ipvs not net into ip_vs_app_net_init and ip_vs_app_net_cleanup Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- net/netfilter/ipvs/ip_vs_app.c | 8 ++++---- net/netfilter/ipvs/ip_vs_core.c | 6 +++--- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 5caafed5af2e..728a670d69fd 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1326,11 +1326,11 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) int ip_vs_estimator_net_init(struct netns_ipvs *ipvs); int ip_vs_control_net_init(struct netns_ipvs *ipvs); int ip_vs_protocol_net_init(struct net *net); -int ip_vs_app_net_init(struct net *net); +int ip_vs_app_net_init(struct netns_ipvs *ipvs); int ip_vs_conn_net_init(struct net *net); int ip_vs_sync_net_init(struct netns_ipvs *ipvs); void ip_vs_conn_net_cleanup(struct net *net); -void ip_vs_app_net_cleanup(struct net *net); +void ip_vs_app_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_protocol_net_cleanup(struct net *net); void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 42220a0efda2..0328f7250693 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -603,18 +603,18 @@ static const struct file_operations ip_vs_app_fops = { }; #endif -int __net_init ip_vs_app_net_init(struct net *net) +int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); + struct net *net = ipvs->net; INIT_LIST_HEAD(&ipvs->app_list); proc_create("ip_vs_app", 0, net->proc_net, &ip_vs_app_fops); return 0; } -void __net_exit ip_vs_app_net_cleanup(struct net *net) +void __net_exit ip_vs_app_net_cleanup(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); + struct net *net = ipvs->net; unregister_ip_vs_app(ipvs, NULL /* all */); remove_proc_entry("ip_vs_app", net->proc_net); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index ec6f022fba6a..01398eb757fa 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2081,7 +2081,7 @@ static int __net_init __ip_vs_init(struct net *net) if (ip_vs_protocol_net_init(net) < 0) goto protocol_fail; - if (ip_vs_app_net_init(net) < 0) + if (ip_vs_app_net_init(ipvs) < 0) goto app_fail; if (ip_vs_conn_net_init(net) < 0) @@ -2100,7 +2100,7 @@ static int __net_init __ip_vs_init(struct net *net) sync_fail: ip_vs_conn_net_cleanup(net); conn_fail: - ip_vs_app_net_cleanup(net); + ip_vs_app_net_cleanup(ipvs); app_fail: ip_vs_protocol_net_cleanup(net); protocol_fail: @@ -2118,7 +2118,7 @@ static void __net_exit __ip_vs_cleanup(struct net *net) ip_vs_service_net_cleanup(ipvs); /* ip_vs_flush() with locks */ ip_vs_conn_net_cleanup(net); - ip_vs_app_net_cleanup(net); + ip_vs_app_net_cleanup(ipvs); ip_vs_protocol_net_cleanup(net); ip_vs_control_net_cleanup(ipvs); ip_vs_estimator_net_cleanup(ipvs); -- cgit v1.2.3 From 1281a9c2d181a932ae2f59f5711ae087a58f1c13 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:36 -0500 Subject: ipvs: Pass ipvs not net into init_netns and exit_netns Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- net/netfilter/ipvs/ip_vs_proto.c | 4 ++-- net/netfilter/ipvs/ip_vs_proto_sctp.c | 6 ++---- net/netfilter/ipvs/ip_vs_proto_tcp.c | 6 ++---- net/netfilter/ipvs/ip_vs_proto_udp.c | 6 ++---- 5 files changed, 10 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 728a670d69fd..fe3373c9bb3b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -483,9 +483,9 @@ struct ip_vs_protocol { void (*exit)(struct ip_vs_protocol *pp); - int (*init_netns)(struct net *net, struct ip_vs_proto_data *pd); + int (*init_netns)(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd); - void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd); + void (*exit_netns)(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd); int (*conn_schedule)(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index fb581babe5e2..f05ee668a1d1 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -78,7 +78,7 @@ register_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_protocol *pp) atomic_set(&pd->appcnt, 0); /* Init app counter */ if (pp->init_netns != NULL) { - int ret = pp->init_netns(ipvs->net, pd); + int ret = pp->init_netns(ipvs, pd); if (ret) { /* unlink an free proto data */ ipvs->proto_data_table[hash] = pd->next; @@ -125,7 +125,7 @@ unregister_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_proto_data *p if (*pd_p == pd) { *pd_p = pd->next; if (pd->pp->exit_netns != NULL) - pd->pp->exit_netns(ipvs->net, pd); + pd->pp->exit_netns(ipvs, pd); kfree(pd); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 345fc7485f2e..3e9418ab276a 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -561,10 +561,8 @@ out: * timeouts is netns related now. * --------------------------------------------- */ -static int __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) +static int __ip_vs_sctp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { - struct netns_ipvs *ipvs = net_ipvs(net); - ip_vs_init_hash_table(ipvs->sctp_apps, SCTP_APP_TAB_SIZE); pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts, sizeof(sctp_timeouts)); @@ -573,7 +571,7 @@ static int __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) return 0; } -static void __ip_vs_sctp_exit(struct net *net, struct ip_vs_proto_data *pd) +static void __ip_vs_sctp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { kfree(pd->timeout_table); } diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 94bea31ec388..93ba6b1fe9d1 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -691,10 +691,8 @@ void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp) * timeouts is netns related now. * --------------------------------------------- */ -static int __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd) +static int __ip_vs_tcp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { - struct netns_ipvs *ipvs = net_ipvs(net); - ip_vs_init_hash_table(ipvs->tcp_apps, TCP_APP_TAB_SIZE); pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts, sizeof(tcp_timeouts)); @@ -704,7 +702,7 @@ static int __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd) return 0; } -static void __ip_vs_tcp_exit(struct net *net, struct ip_vs_proto_data *pd) +static void __ip_vs_tcp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { kfree(pd->timeout_table); } diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 234521ec9703..382dcc9cfe11 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -472,10 +472,8 @@ udp_state_transition(struct ip_vs_conn *cp, int direction, cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL]; } -static int __udp_init(struct net *net, struct ip_vs_proto_data *pd) +static int __udp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { - struct netns_ipvs *ipvs = net_ipvs(net); - ip_vs_init_hash_table(ipvs->udp_apps, UDP_APP_TAB_SIZE); pd->timeout_table = ip_vs_create_timeout_table((int *)udp_timeouts, sizeof(udp_timeouts)); @@ -484,7 +482,7 @@ static int __udp_init(struct net *net, struct ip_vs_proto_data *pd) return 0; } -static void __udp_exit(struct net *net, struct ip_vs_proto_data *pd) +static void __udp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { kfree(pd->timeout_table); } -- cgit v1.2.3 From ab161976421585812bcdab6592852b1b5b7dec1f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:38 -0500 Subject: ipvs: Pass ipvs into .conn_in_get and ip_vs_conn_in_get_proto Stop relying on "net_ipvs(skb_net(skb))" to derive the ipvs as skb_net is a hack. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 6 ++++-- net/netfilter/ipvs/ip_vs_conn.c | 4 ++-- net/netfilter/ipvs/ip_vs_core.c | 8 ++++---- net/netfilter/ipvs/ip_vs_proto_ah_esp.c | 3 +-- 4 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index fe3373c9bb3b..5c26383542e3 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -493,7 +493,8 @@ struct ip_vs_protocol { struct ip_vs_iphdr *iph); struct ip_vs_conn * - (*conn_in_get)(int af, + (*conn_in_get)(struct netns_ipvs *ipvs, + int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph); @@ -1222,7 +1223,8 @@ static inline void ip_vs_conn_fill_param(struct netns_ipvs *ipvs, int af, int pr struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p); -struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, +struct ip_vs_conn * ip_vs_conn_in_get_proto(struct netns_ipvs *ipvs, int af, + const struct sk_buff *skb, const struct ip_vs_iphdr *iph); struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 6754e3595a72..439d6fb8bc29 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -335,10 +335,10 @@ ip_vs_conn_fill_param_proto(struct netns_ipvs *ipvs, } struct ip_vs_conn * -ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, +ip_vs_conn_in_get_proto(struct netns_ipvs *ipvs, int af, + const struct sk_buff *skb, const struct ip_vs_iphdr *iph) { - struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); struct ip_vs_conn_param p; if (ip_vs_conn_fill_param_proto(ipvs, af, skb, iph, &p)) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 01398eb757fa..9b5c2af7b63a 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -469,7 +469,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, */ if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK)) { iph->hdr_flags ^= IP_VS_HDR_INVERSE; - cp = pp->conn_in_get(svc->af, skb, iph); + cp = pp->conn_in_get(svc->ipvs, svc->af, skb, iph); iph->hdr_flags ^= IP_VS_HDR_INVERSE; if (cp) { @@ -1490,7 +1490,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) /* The embedded headers contain source and dest in reverse order. * For IPIP this is error for request, not for reply. */ - cp = pp->conn_in_get(AF_INET, skb, &ciph); + cp = pp->conn_in_get(ipvs, AF_INET, skb, &ciph); if (!cp) { int v; @@ -1648,7 +1648,7 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, /* The embedded headers contain source and dest in reverse order * if not from localhost */ - cp = pp->conn_in_get(AF_INET6, skb, &ciph); + cp = pp->conn_in_get(ipvs, AF_INET6, skb, &ciph); if (!cp) { int v; @@ -1780,7 +1780,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) /* * Check if the packet belongs to an existing connection entry */ - cp = pp->conn_in_get(af, skb, &iph); + cp = pp->conn_in_get(ipvs, af, skb, &iph); conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); if (conn_reuse_mode && !iph.fragoffs && diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index 406d9a433d92..a96d93d11807 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -56,12 +56,11 @@ ah_esp_conn_fill_param_proto(struct netns_ipvs *ipvs, int af, } static struct ip_vs_conn * -ah_esp_conn_in_get(int af, const struct sk_buff *skb, +ah_esp_conn_in_get(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; - struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); ah_esp_conn_fill_param_proto(ipvs, af, iph, &p); cp = ip_vs_conn_in_get(&p); -- cgit v1.2.3 From 0cf705c8c2e8333aff5b472cfff13f9542620500 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:39 -0500 Subject: ipvs: Pass ipvs into conn_out_get Move the hack of relying on "net_ipvs(skb_net(skb))" to derive the ipvs up a layer. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 6 ++++-- net/netfilter/ipvs/ip_vs_conn.c | 4 ++-- net/netfilter/ipvs/ip_vs_core.c | 8 +++++--- net/netfilter/ipvs/ip_vs_proto_ah_esp.c | 3 +-- net/netfilter/xt_ipvs.c | 3 ++- 5 files changed, 14 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 5c26383542e3..0ca436ef7dad 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -499,7 +499,8 @@ struct ip_vs_protocol { const struct ip_vs_iphdr *iph); struct ip_vs_conn * - (*conn_out_get)(int af, + (*conn_out_get)(struct netns_ipvs *ipvs, + int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph); @@ -1229,7 +1230,8 @@ struct ip_vs_conn * ip_vs_conn_in_get_proto(struct netns_ipvs *ipvs, int af, struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); -struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, +struct ip_vs_conn * ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af, + const struct sk_buff *skb, const struct ip_vs_iphdr *iph); /* Get reference to gain full access to conn. diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 439d6fb8bc29..7a4d1d8e8f0c 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -440,10 +440,10 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) } struct ip_vs_conn * -ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, +ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af, + const struct sk_buff *skb, const struct ip_vs_iphdr *iph) { - struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); struct ip_vs_conn_param p; if (ip_vs_conn_fill_param_proto(ipvs, af, skb, iph, &p)) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 9b5c2af7b63a..f0369e7602a0 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -912,6 +912,7 @@ out: static int ip_vs_out_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) { + struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ @@ -974,7 +975,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(AF_INET, skb, &ciph); + cp = pp->conn_out_get(ipvs, AF_INET, skb, &ciph); if (!cp) return NF_ACCEPT; @@ -987,6 +988,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *ipvsh) { + struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; @@ -1029,7 +1031,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, return NF_ACCEPT; /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(AF_INET6, skb, &ciph); + cp = pp->conn_out_get(ipvs, AF_INET6, skb, &ciph); if (!cp) return NF_ACCEPT; @@ -1257,7 +1259,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(af, skb, &iph); + cp = pp->conn_out_get(ipvs, af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index a96d93d11807..e924455de5c0 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -82,12 +82,11 @@ ah_esp_conn_in_get(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb, static struct ip_vs_conn * -ah_esp_conn_out_get(int af, const struct sk_buff *skb, +ah_esp_conn_out_get(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; - struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); ah_esp_conn_fill_param_proto(ipvs, af, iph, &p); cp = ip_vs_conn_out_get(&p); diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c index 452ba2a3e7ae..71a9d95e0a81 100644 --- a/net/netfilter/xt_ipvs.c +++ b/net/netfilter/xt_ipvs.c @@ -48,6 +48,7 @@ static bool ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_ipvs_mtinfo *data = par->matchinfo; + struct netns_ipvs *ipvs = net_ipvs(par->net); /* ipvs_mt_check ensures that family is only NFPROTO_IPV[46]. */ const u_int8_t family = par->family; struct ip_vs_iphdr iph; @@ -85,7 +86,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par) /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(family, skb, &iph); + cp = pp->conn_out_get(ipvs, family, skb, &iph); if (unlikely(cp == NULL)) { match = false; goto out; -- cgit v1.2.3 From 2f3edc6a5bb2a570f491e8e8a4a16526aff3675b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:42 -0500 Subject: ipvs: Pass ipvs not net into ip_vs_conn_net_init and ip_vs_conn_net_cleanup Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- net/netfilter/ipvs/ip_vs_conn.c | 8 ++++---- net/netfilter/ipvs/ip_vs_core.c | 6 +++--- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 0ca436ef7dad..5ad04be64895 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1331,9 +1331,9 @@ int ip_vs_estimator_net_init(struct netns_ipvs *ipvs); int ip_vs_control_net_init(struct netns_ipvs *ipvs); int ip_vs_protocol_net_init(struct net *net); int ip_vs_app_net_init(struct netns_ipvs *ipvs); -int ip_vs_conn_net_init(struct net *net); +int ip_vs_conn_net_init(struct netns_ipvs *ipvs); int ip_vs_sync_net_init(struct netns_ipvs *ipvs); -void ip_vs_conn_net_cleanup(struct net *net); +void ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_app_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_protocol_net_cleanup(struct net *net); void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 4bb1b7d1286d..d1d168c7fc68 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1345,9 +1345,9 @@ flush_again: /* * per netns init and exit */ -int __net_init ip_vs_conn_net_init(struct net *net) +int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); + struct net *net = ipvs->net; atomic_set(&ipvs->conn_count, 0); @@ -1356,9 +1356,9 @@ int __net_init ip_vs_conn_net_init(struct net *net) return 0; } -void __net_exit ip_vs_conn_net_cleanup(struct net *net) +void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); + struct net *net = ipvs->net; /* flush all the connection entries first */ ip_vs_conn_flush(ipvs); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index f0369e7602a0..9b37fe30dcac 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2086,7 +2086,7 @@ static int __net_init __ip_vs_init(struct net *net) if (ip_vs_app_net_init(ipvs) < 0) goto app_fail; - if (ip_vs_conn_net_init(net) < 0) + if (ip_vs_conn_net_init(ipvs) < 0) goto conn_fail; if (ip_vs_sync_net_init(ipvs) < 0) @@ -2100,7 +2100,7 @@ static int __net_init __ip_vs_init(struct net *net) */ sync_fail: - ip_vs_conn_net_cleanup(net); + ip_vs_conn_net_cleanup(ipvs); conn_fail: ip_vs_app_net_cleanup(ipvs); app_fail: @@ -2119,7 +2119,7 @@ static void __net_exit __ip_vs_cleanup(struct net *net) struct netns_ipvs *ipvs = net_ipvs(net); ip_vs_service_net_cleanup(ipvs); /* ip_vs_flush() with locks */ - ip_vs_conn_net_cleanup(net); + ip_vs_conn_net_cleanup(ipvs); ip_vs_app_net_cleanup(ipvs); ip_vs_protocol_net_cleanup(net); ip_vs_control_net_cleanup(ipvs); -- cgit v1.2.3 From d8f44c335a1111d647f41e9fa6ae65b18db112e4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:43 -0500 Subject: ipvs: Pass ipvs into .conn_schedule and ip_vs_try_to_schedule This moves the hack "net_ipvs(skb_net(skb))" up one level where it will be easier to remove. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 3 ++- net/netfilter/ipvs/ip_vs_core.c | 11 ++++++----- net/netfilter/ipvs/ip_vs_proto_ah_esp.c | 3 ++- net/netfilter/ipvs/ip_vs_proto_sctp.c | 8 ++------ net/netfilter/ipvs/ip_vs_proto_tcp.c | 8 ++------ net/netfilter/ipvs/ip_vs_proto_udp.c | 9 +++------ 6 files changed, 17 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 5ad04be64895..c68c2c8ae48a 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -487,7 +487,8 @@ struct ip_vs_protocol { void (*exit_netns)(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd); - int (*conn_schedule)(int af, struct sk_buff *skb, + int (*conn_schedule)(struct netns_ipvs *ipvs, + int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 9b37fe30dcac..514596b7a324 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1360,7 +1360,8 @@ ip_vs_local_reply6(void *priv, struct sk_buff *skb, #endif static unsigned int -ip_vs_try_to_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, +ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { @@ -1372,7 +1373,7 @@ ip_vs_try_to_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, */ /* Schedule and create new connection entry into cpp */ - if (!pp->conn_schedule(af, skb, pd, verdict, cpp, iph)) + if (!pp->conn_schedule(ipvs, af, skb, pd, verdict, cpp, iph)) return 0; } @@ -1500,7 +1501,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) if (!sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; - if (!ip_vs_try_to_schedule(AF_INET, skb, pd, &v, &cp, &ciph)) + if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph)) return v; new_cp = true; } @@ -1658,7 +1659,7 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, if (!sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; - if (!ip_vs_try_to_schedule(AF_INET6, skb, pd, &v, &cp, &ciph)) + if (!ip_vs_try_to_schedule(ipvs, AF_INET6, skb, pd, &v, &cp, &ciph)) return v; new_cp = true; @@ -1799,7 +1800,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) if (unlikely(!cp)) { int v; - if (!ip_vs_try_to_schedule(af, skb, pd, &v, &cp, &iph)) + if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph)) return v; } diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index e924455de5c0..5320d39976e1 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -104,7 +104,8 @@ ah_esp_conn_out_get(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb, static int -ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, +ah_esp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 3e9418ab276a..010ddeec135f 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -9,20 +9,16 @@ #include static int -sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, +sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { - struct net *net; struct ip_vs_service *svc; - struct netns_ipvs *ipvs; sctp_chunkhdr_t _schunkh, *sch; sctp_sctphdr_t *sh, _sctph; __be16 _ports[2], *ports = NULL; - net = skb_net(skb); - ipvs = net_ipvs(net); - if (likely(!ip_vs_iph_icmp(iph))) { sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph); if (sh) { diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 93ba6b1fe9d1..c913c2d00caf 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -32,19 +32,15 @@ #include static int -tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, +tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { - struct net *net; struct ip_vs_service *svc; struct tcphdr _tcph, *th; - struct netns_ipvs *ipvs; __be16 _ports[2], *ports = NULL; - net = skb_net(skb); - ipvs = net_ipvs(net); - /* In the event of icmp, we're only guaranteed to have the first 8 * bytes of the transport header, so we only check the rest of the * TCP packet for non-ICMP packets diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 382dcc9cfe11..e494e9a88c7f 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -29,12 +29,11 @@ #include static int -udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, +udp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { - struct net *net; - struct netns_ipvs *ipvs; struct ip_vs_service *svc; struct udphdr _udph, *uh; __be16 _ports[2], *ports = NULL; @@ -54,8 +53,6 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, return 0; } - net = skb_net(skb); - ipvs = net_ipvs(net); rcu_read_lock(); if (likely(!ip_vs_iph_inverse(iph))) svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, @@ -67,7 +64,7 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, if (svc) { int ignored; - if (ip_vs_todrop(net_ipvs(net))) { + if (ip_vs_todrop(ipvs)) { /* * It seems that we are very loaded. * We have to drop this packet :( -- cgit v1.2.3 From 570329487437d4531eb806accdf98726923367ae Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:49 -0500 Subject: ipvs: Wrap sysctl_cache_bypass and remove ifdefs in ip_vs_leave With sysctl_cache_bypass now a compile time constant the compiler can figue out that it can elimiate all of the code that depends on sysctl_cache_bypass being true. Also remove the duplicate computation of net previously necessitated by #ifdef CONFIG_SYSCTL Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 10 ++++++++++ net/netfilter/ipvs/ip_vs_core.c | 13 +++---------- 2 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index c68c2c8ae48a..dacd873e8bb9 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1101,6 +1101,11 @@ static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs) return ipvs->sysctl_ignore_tunneled; } +static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_cache_bypass; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1183,6 +1188,11 @@ static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs) return 0; } +static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs) +{ + return 0; +} + #endif /* IPVS core functions diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 1c9c52349b7c..7e9ee1dece19 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -568,17 +568,14 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph) { __be16 _ports[2], *pptr, dport; -#ifdef CONFIG_SYSCTL struct net *net; struct netns_ipvs *ipvs; -#endif pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph); if (!pptr) return NF_DROP; dport = likely(!ip_vs_iph_inverse(iph)) ? pptr[1] : pptr[0]; -#ifdef CONFIG_SYSCTL net = skb_net(skb); @@ -586,7 +583,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, and the destination is a non-local unicast, then create a cache_bypass connection entry */ ipvs = net_ipvs(net); - if (ipvs->sysctl_cache_bypass && svc->fwmark && + if (sysctl_cache_bypass(ipvs) && svc->fwmark && !(iph->hdr_flags & (IP_VS_HDR_INVERSE | IP_VS_HDR_ICMP)) && ip_vs_addr_is_unicast(net, svc->af, &iph->daddr)) { int ret; @@ -624,7 +621,6 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_conn_put(cp); return ret; } -#endif /* * When the virtual ftp service is presented, packets destined @@ -647,11 +643,8 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) { - if (!skb->dev) { - struct net *net_ = dev_net(skb_dst(skb)->dev); - - skb->dev = net_->loopback_dev; - } + if (!skb->dev) + skb->dev = net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); } else #endif -- cgit v1.2.3 From 69f390934b26154573fc7c360645ced8b0c7871a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:57 -0500 Subject: ipvs: Remove net argument from ip_vs_tcp_conn_listen The argument is unnecessary and in practice confusing, and has caused the callers to do all manner of silly things. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_ftp.c | 8 ++------ net/netfilter/ipvs/ip_vs_proto_tcp.c | 4 ++-- 3 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index dacd873e8bb9..f0a39ce3bf0e 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1271,7 +1271,7 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp); const char *ip_vs_state_name(__u16 proto, int state); -void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp); +void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp); int ip_vs_check_template(struct ip_vs_conn *ct); void ip_vs_random_dropentry(struct netns_ipvs *ipvs); int ip_vs_conn_init(void); diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 508544aff36d..d30c327bb578 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -181,7 +181,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, int ret = 0; enum ip_conntrack_info ctinfo; struct nf_conn *ct; - struct net *net; *diff = 0; @@ -289,9 +288,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, * would be adjusted twice. */ - net = skb_net(skb); cp->app_data = NULL; - ip_vs_tcp_conn_listen(net, n_cp); + ip_vs_tcp_conn_listen(n_cp); ip_vs_conn_put(n_cp); return ret; } @@ -320,7 +318,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, union nf_inet_addr to; __be16 port; struct ip_vs_conn *n_cp; - struct net *net; /* no diff required for incoming packets */ *diff = 0; @@ -413,8 +410,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, /* * Move tunnel to listen state */ - net = skb_net(skb); - ip_vs_tcp_conn_listen(net, n_cp); + ip_vs_tcp_conn_listen(n_cp); ip_vs_conn_put(n_cp); return 1; diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index c913c2d00caf..d7024b2ed769 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -672,9 +672,9 @@ tcp_app_conn_bind(struct ip_vs_conn *cp) /* * Set LISTEN timeout. (ip_vs_conn_put will setup timer) */ -void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp) +void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp) { - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net_ipvs(net), IPPROTO_TCP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(cp->ipvs, IPPROTO_TCP); spin_lock_bh(&cp->lock); cp->state = IP_VS_TCP_S_LISTEN; -- cgit v1.2.3 From 7d1f88eca0ae7228bdbd971f060603b3a1270693 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:58 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_protocol_net_(init|cleanup) Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- net/netfilter/ipvs/ip_vs_core.c | 6 +++--- net/netfilter/ipvs/ip_vs_proto.c | 8 +++----- 3 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index f0a39ce3bf0e..00318d63a565 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1340,13 +1340,13 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) /* IPVS netns init & cleanup functions */ int ip_vs_estimator_net_init(struct netns_ipvs *ipvs); int ip_vs_control_net_init(struct netns_ipvs *ipvs); -int ip_vs_protocol_net_init(struct net *net); +int ip_vs_protocol_net_init(struct netns_ipvs *ipvs); int ip_vs_app_net_init(struct netns_ipvs *ipvs); int ip_vs_conn_net_init(struct netns_ipvs *ipvs); int ip_vs_sync_net_init(struct netns_ipvs *ipvs); void ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_app_net_cleanup(struct netns_ipvs *ipvs); -void ip_vs_protocol_net_cleanup(struct net *net); +void ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 22eae0231cbb..ab85ae0f531f 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2052,7 +2052,7 @@ static int __net_init __ip_vs_init(struct net *net) if (ip_vs_control_net_init(ipvs) < 0) goto control_fail; - if (ip_vs_protocol_net_init(net) < 0) + if (ip_vs_protocol_net_init(ipvs) < 0) goto protocol_fail; if (ip_vs_app_net_init(ipvs) < 0) @@ -2076,7 +2076,7 @@ sync_fail: conn_fail: ip_vs_app_net_cleanup(ipvs); app_fail: - ip_vs_protocol_net_cleanup(net); + ip_vs_protocol_net_cleanup(ipvs); protocol_fail: ip_vs_control_net_cleanup(ipvs); control_fail: @@ -2093,7 +2093,7 @@ static void __net_exit __ip_vs_cleanup(struct net *net) ip_vs_service_net_cleanup(ipvs); /* ip_vs_flush() with locks */ ip_vs_conn_net_cleanup(ipvs); ip_vs_app_net_cleanup(ipvs); - ip_vs_protocol_net_cleanup(net); + ip_vs_protocol_net_cleanup(ipvs); ip_vs_control_net_cleanup(ipvs); ip_vs_estimator_net_cleanup(ipvs); IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen); diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index f05ee668a1d1..8ae480715cea 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -307,7 +307,7 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, /* * per network name-space init */ -int __net_init ip_vs_protocol_net_init(struct net *net) +int __net_init ip_vs_protocol_net_init(struct netns_ipvs *ipvs) { int i, ret; static struct ip_vs_protocol *protos[] = { @@ -327,7 +327,6 @@ int __net_init ip_vs_protocol_net_init(struct net *net) &ip_vs_protocol_esp, #endif }; - struct netns_ipvs *ipvs = net_ipvs(net); for (i = 0; i < ARRAY_SIZE(protos); i++) { ret = register_ip_vs_proto_netns(ipvs, protos[i]); @@ -337,13 +336,12 @@ int __net_init ip_vs_protocol_net_init(struct net *net) return 0; cleanup: - ip_vs_protocol_net_cleanup(net); + ip_vs_protocol_net_cleanup(ipvs); return ret; } -void __net_exit ip_vs_protocol_net_cleanup(struct net *net) +void __net_exit ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd; int i; -- cgit v1.2.3 From 7c6c21ee94452081a5219667851d2084a45c5009 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:59 -0500 Subject: ipvs: Remove skb_net This hack has no more users so remove it. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 31 ------------------------------- 1 file changed, 31 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 00318d63a565..d621330d423c 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -38,37 +38,6 @@ static inline struct netns_ipvs *net_ipvs(struct net* net) return net->ipvs; } -/* Get net ptr from skb in traffic cases - * use skb_sknet when call is from userland (ioctl or netlink) - */ -static inline struct net *skb_net(const struct sk_buff *skb) -{ -#ifdef CONFIG_NET_NS -#ifdef CONFIG_IP_VS_DEBUG - /* - * This is used for debug only. - * Start with the most likely hit - * End with BUG - */ - if (likely(skb->dev && dev_net(skb->dev))) - return dev_net(skb->dev); - if (skb_dst(skb) && skb_dst(skb)->dev) - return dev_net(skb_dst(skb)->dev); - WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n", - __func__, __LINE__); - if (likely(skb->sk && sock_net(skb->sk))) - return sock_net(skb->sk); - pr_err("There is no net ptr to find in the skb in %s() line:%d\n", - __func__, __LINE__); - BUG(); -#else - return dev_net(skb->dev ? : skb_dst(skb)->dev); -#endif -#else - return &init_net; -#endif -} - static inline struct net *skb_sknet(const struct sk_buff *skb) { #ifdef CONFIG_NET_NS -- cgit v1.2.3 From 9cfdd75b7c049895317aebb0e27f8112e7e31593 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:03:00 -0500 Subject: ipvs: Remove skb_sknet This function adds no real value and it obscures what the code is doing. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 22 ---------------------- net/netfilter/ipvs/ip_vs_ctl.c | 25 ++++++++++--------------- 2 files changed, 10 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d621330d423c..0816c872b689 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -38,28 +38,6 @@ static inline struct netns_ipvs *net_ipvs(struct net* net) return net->ipvs; } -static inline struct net *skb_sknet(const struct sk_buff *skb) -{ -#ifdef CONFIG_NET_NS -#ifdef CONFIG_IP_VS_DEBUG - /* Start with the most likely hit */ - if (likely(skb->sk && sock_net(skb->sk))) - return sock_net(skb->sk); - WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n", - __func__, __LINE__); - if (likely(skb->dev && dev_net(skb->dev))) - return dev_net(skb->dev); - pr_err("There is no net ptr to find in the skb in %s() line:%d\n", - __func__, __LINE__); - BUG(); -#else - return sock_net(skb->sk); -#endif -#else - return &init_net; -#endif -} - /* This one needed for single_open_net since net is stored directly in * private not as a struct i.e. seq_file_net can't be used. */ diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index b7a0bd274085..e7c1b052c2a3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3002,7 +3002,8 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb, int idx = 0, i; int start = cb->args[0]; struct ip_vs_service *svc; - struct netns_ipvs *ipvs = net_ipvs(skb_sknet(skb)); + struct net *net = sock_net(skb->sk); + struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&__ip_vs_mutex); for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { @@ -3201,7 +3202,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb, struct ip_vs_service *svc; struct ip_vs_dest *dest; struct nlattr *attrs[IPVS_CMD_ATTR_MAX + 1]; - struct net *net = skb_sknet(skb); + struct net *net = sock_net(skb->sk); struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&__ip_vs_mutex); @@ -3348,7 +3349,7 @@ nla_put_failure: static int ip_vs_genl_dump_daemons(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb_sknet(skb); + struct net *net = sock_net(skb->sk); struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&ipvs->sync_mutex); @@ -3475,11 +3476,9 @@ static int ip_vs_genl_set_config(struct netns_ipvs *ipvs, struct nlattr **attrs) static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info) { int ret = -EINVAL, cmd; - struct net *net; - struct netns_ipvs *ipvs; + struct net *net = sock_net(skb->sk); + struct netns_ipvs *ipvs = net_ipvs(net); - net = skb_sknet(skb); - ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; if (cmd == IPVS_CMD_NEW_DAEMON || cmd == IPVS_CMD_DEL_DAEMON) { @@ -3508,11 +3507,9 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) struct ip_vs_dest_user_kern udest; int ret = 0, cmd; int need_full_svc = 0, need_full_dest = 0; - struct net *net; - struct netns_ipvs *ipvs; + struct net *net = sock_net(skb->sk); + struct netns_ipvs *ipvs = net_ipvs(net); - net = skb_sknet(skb); - ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; mutex_lock(&__ip_vs_mutex); @@ -3632,11 +3629,9 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) struct sk_buff *msg; void *reply; int ret, cmd, reply_cmd; - struct net *net; - struct netns_ipvs *ipvs; + struct net *net = sock_net(skb->sk); + struct netns_ipvs *ipvs = net_ipvs(net); - net = skb_sknet(skb); - ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; if (cmd == IPVS_CMD_GET_SERVICE) -- cgit v1.2.3 From 594b31ea7dc6101519deee1b31483fce2e1a7414 Mon Sep 17 00:00:00 2001 From: Frederic Danis Date: Wed, 23 Sep 2015 18:18:07 +0200 Subject: Bluetooth: Add BT_WARN and bt_dev_warn logging macros Add warning logging macros to bluetooth subsystem logs. Signed-off-by: Frederic Danis Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 5 +++++ net/bluetooth/lib.c | 16 ++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index f5ade8573393..c4defef319d5 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -122,11 +122,14 @@ struct bt_voice { __printf(1, 2) void bt_info(const char *fmt, ...); __printf(1, 2) +void bt_warn(const char *fmt, ...); +__printf(1, 2) void bt_err(const char *fmt, ...); __printf(1, 2) void bt_err_ratelimited(const char *fmt, ...); #define BT_INFO(fmt, ...) bt_info(fmt "\n", ##__VA_ARGS__) +#define BT_WARN(fmt, ...) bt_warn(fmt "\n", ##__VA_ARGS__) #define BT_ERR(fmt, ...) bt_err(fmt "\n", ##__VA_ARGS__) #define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__) @@ -134,6 +137,8 @@ void bt_err_ratelimited(const char *fmt, ...); #define bt_dev_info(hdev, fmt, ...) \ BT_INFO("%s: " fmt, (hdev)->name, ##__VA_ARGS__) +#define bt_dev_warn(hdev, fmt, ...) \ + BT_WARN("%s: " fmt, (hdev)->name, ##__VA_ARGS__) #define bt_dev_err(hdev, fmt, ...) \ BT_ERR("%s: " fmt, (hdev)->name, ##__VA_ARGS__) #define bt_dev_dbg(hdev, fmt, ...) \ diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c index 8b4cdce3f62e..aa4cf64e32a6 100644 --- a/net/bluetooth/lib.c +++ b/net/bluetooth/lib.c @@ -151,6 +151,22 @@ void bt_info(const char *format, ...) } EXPORT_SYMBOL(bt_info); +void bt_warn(const char *format, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, format); + + vaf.fmt = format; + vaf.va = &args; + + pr_warn("%pV", &vaf); + + va_end(args); +} +EXPORT_SYMBOL(bt_warn); + void bt_err(const char *format, ...) { struct va_format vaf; -- cgit v1.2.3 From f856f21dbcd162a53e30987a91d75d5ab54a7f80 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Thu, 24 Sep 2015 09:37:10 +0200 Subject: ieee802154: remove unnecessary includes This patch removes some unnecessary includes from ieee802154 header, which was introduced by commit b609fb54adfa ("ieee802154: add helpers for frame control checks"). Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/linux/ieee802154.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index aca228b81464..d3e415674dac 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -25,9 +25,6 @@ #include #include -#include -#include -#include #define IEEE802154_MTU 127 #define IEEE802154_ACK_PSDU_LEN 5 -- cgit v1.2.3 From 92c14d9b5ee86fd6cf136c01b6a87353522aebdd Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 22 Sep 2015 18:56:43 +0200 Subject: genetlink: simplify genl_notify The genl_notify function has too many arguments for no real reason - all callers use genl_info to get them anyway. Just pass the genl_info down to genl_notify. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/wireless/mac80211_hwsim.c | 5 ++--- include/net/genetlink.h | 5 ++--- net/netlink/genetlink.c | 12 ++++++------ net/openvswitch/datapath.c | 3 +-- 4 files changed, 11 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 520bef80747f..66c963dbc3fd 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2190,9 +2190,8 @@ static void hwsim_mcast_config_msg(struct sk_buff *mcast_skb, struct genl_info *info) { if (info) - genl_notify(&hwsim_genl_family, mcast_skb, - genl_info_net(info), info->snd_portid, - HWSIM_MCGRP_CONFIG, info->nlhdr, GFP_KERNEL); + genl_notify(&hwsim_genl_family, mcast_skb, info, + HWSIM_MCGRP_CONFIG, GFP_KERNEL); else genlmsg_multicast(&hwsim_genl_family, mcast_skb, 0, HWSIM_MCGRP_CONFIG, GFP_KERNEL); diff --git a/include/net/genetlink.h b/include/net/genetlink.h index a9af1cc8c1bc..1b6b6dcb018d 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -183,9 +183,8 @@ _genl_register_family_with_ops_grps(struct genl_family *family, (grps), ARRAY_SIZE(grps)) int genl_unregister_family(struct genl_family *family); -void genl_notify(struct genl_family *family, - struct sk_buff *skb, struct net *net, u32 portid, - u32 group, struct nlmsghdr *nlh, gfp_t flags); +void genl_notify(struct genl_family *family, struct sk_buff *skb, + struct genl_info *info, u32 group, gfp_t flags); struct sk_buff *genlmsg_new_unicast(size_t payload, struct genl_info *info, gfp_t flags); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 2ed5f964772e..75724a96aef2 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1136,19 +1136,19 @@ int genlmsg_multicast_allns(struct genl_family *family, struct sk_buff *skb, } EXPORT_SYMBOL(genlmsg_multicast_allns); -void genl_notify(struct genl_family *family, - struct sk_buff *skb, struct net *net, u32 portid, u32 group, - struct nlmsghdr *nlh, gfp_t flags) +void genl_notify(struct genl_family *family, struct sk_buff *skb, + struct genl_info *info, u32 group, gfp_t flags) { + struct net *net = genl_info_net(info); struct sock *sk = net->genl_sock; int report = 0; - if (nlh) - report = nlmsg_report(nlh); + if (info->nlhdr) + report = nlmsg_report(info->nlhdr); if (WARN_ON_ONCE(group >= family->n_mcgrps)) return; group = family->mcgrp_offset + group; - nlmsg_notify(sk, skb, portid, group, report, flags); + nlmsg_notify(sk, skb, info->snd_portid, group, report, flags); } EXPORT_SYMBOL(genl_notify); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 6fbd2decb19e..2913594c5123 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -91,8 +91,7 @@ static bool ovs_must_notify(struct genl_family *family, struct genl_info *info, static void ovs_notify(struct genl_family *family, struct sk_buff *skb, struct genl_info *info) { - genl_notify(family, skb, genl_info_net(info), info->snd_portid, - 0, info->nlhdr, GFP_KERNEL); + genl_notify(family, skb, info, 0, GFP_KERNEL); } /** -- cgit v1.2.3 From 38cf595b195552276e1cf1826434e05782de4be8 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 22 Sep 2015 18:57:13 +0200 Subject: ipv6: remove unused neigh parameter from ndisc functions Since commit 12fd84f4383b1 ("ipv6: Remove unused neigh argument for icmp6_dst_alloc() and its callers."), the neigh parameter of ndisc_send_na and ndisc_send_ns is unused. CC: YOSHIFUJI Hideaki Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/usb/cdc_mbim.c | 2 +- include/net/addrconf.h | 3 +-- include/net/ndisc.h | 6 ++---- net/ipv6/addrconf.c | 2 +- net/ipv6/ndisc.c | 17 +++++++---------- net/ipv6/route.c | 2 +- 6 files changed, 13 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index efc18e05af0a..bbde9884ab8a 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -342,7 +342,7 @@ static void do_neigh_solicit(struct usbnet *dev, u8 *buf, u16 tci) in6_dev_put(in6_dev); /* ipv6_stub != NULL if in6_dev_get returned an inet6_dev */ - ipv6_stub->ndisc_send_na(netdev, NULL, &iph->saddr, &msg->target, + ipv6_stub->ndisc_send_na(netdev, &iph->saddr, &msg->target, is_router /* router */, true /* solicited */, false /* override */, diff --git a/include/net/addrconf.h b/include/net/addrconf.h index b5474b1fcd83..78003dfb8539 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -192,8 +192,7 @@ struct ipv6_stub { int (*ipv6_dst_lookup)(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); void (*udpv6_encap_enable)(void); - void (*ndisc_send_na)(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *daddr, + void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt); struct neigh_table *nd_tbl; diff --git a/include/net/ndisc.h b/include/net/ndisc.h index aba5695fadb0..bf3937431030 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -180,15 +180,13 @@ void ndisc_cleanup(void); int ndisc_rcv(struct sk_buff *skb); -void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *solicit, +void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, struct sk_buff *oskb); void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); -void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *daddr, +void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 75d3dde32c69..759d28ad16b7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3625,7 +3625,7 @@ static void addrconf_dad_work(struct work_struct *w) /* send a neighbour solicitation for our addr */ addrconf_addr_solict_mult(&ifp->addr, &mcaddr); - ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any, NULL); + ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any, NULL); out: in6_ifa_put(ifp); rtnl_unlock(); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index dde5a1e5875a..7089c305245c 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -474,8 +474,7 @@ static void ndisc_send_skb(struct sk_buff *skb, rcu_read_unlock(); } -void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *daddr, +void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt) { @@ -541,7 +540,7 @@ static void ndisc_send_unsol_na(struct net_device *dev) read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { - ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &ifa->addr, + ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); @@ -551,8 +550,7 @@ static void ndisc_send_unsol_na(struct net_device *dev) in6_dev_put(idev); } -void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *solicit, +void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, struct sk_buff *oskb) { @@ -679,12 +677,12 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) "%s: trying to ucast probe in NUD_INVALID: %pI6\n", __func__, target); } - ndisc_send_ns(dev, neigh, target, target, saddr, skb); + ndisc_send_ns(dev, target, target, saddr, skb); } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); } else { addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(dev, NULL, target, &mcaddr, saddr, skb); + ndisc_send_ns(dev, target, &mcaddr, saddr, skb); } } @@ -828,7 +826,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) is_router = idev->cnf.forwarding; if (dad) { - ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &msg->target, + ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target, !!is_router, false, (ifp != NULL), true); goto out; } @@ -849,8 +847,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE); if (neigh || !dev->header_ops) { - ndisc_send_na(dev, neigh, saddr, &msg->target, - !!is_router, + ndisc_send_na(dev, saddr, &msg->target, !!is_router, true, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 111deadc1c06..118f8fa1a809 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -514,7 +514,7 @@ static void rt6_probe_deferred(struct work_struct *w) container_of(w, struct __rt6_probe_work, work); addrconf_addr_solict_mult(&work->target, &mcaddr); - ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL, NULL); + ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, NULL); dev_put(work->dev); kfree(work); } -- cgit v1.2.3 From 9badce000e2ce68ba74838a3cd356dde58221c2f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 23 Sep 2015 17:07:29 -0400 Subject: cgroup, writeback: don't enable cgroup writeback on traditional hierarchies inode_cgwb_enabled() gates cgroup writeback support. If it returns true, each inode is attached to the corresponding memory domain which gets mapped to io domain. It currently only tests whether the filesystem and bdi support cgroup writeback; however, cgroup writeback support doesn't work on traditional hierarchies and thus it should also test whether memcg and iocg are on the default hierarchy. This caused traditional hierarchy setups to hit the cgroup writeback path inadvertently and ended up creating separate writeback domains for each memcg and mapping them all to the root iocg uncovering a couple issues in the cgroup writeback path. cgroup writeback was never meant to be enabled on traditional hierarchies. Make inode_cgwb_enabled() test whether both memcg and iocg are on the default hierarchy. Signed-off-by: Tejun Heo Reported-by: Artem Bityutskiy Reported-by: Dexuan Cui Link: http://lkml.kernel.org/g/1443012552.19983.209.camel@gmail.com Link: http://lkml.kernel.org/g/f30d4a6aa8a546ff88f73021d026a453@SIXPR30MB031.064d.mgd.msft.net --- include/linux/backing-dev.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 5a5d79ee256f..d5eb4ad1c534 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -252,13 +253,19 @@ int inode_congested(struct inode *inode, int cong_bits); * @inode: inode of interest * * cgroup writeback requires support from both the bdi and filesystem. - * Test whether @inode has both. + * Also, both memcg and iocg have to be on the default hierarchy. Test + * whether all conditions are met. + * + * Note that the test result may change dynamically on the same inode + * depending on how memcg and iocg are configured. */ static inline bool inode_cgwb_enabled(struct inode *inode) { struct backing_dev_info *bdi = inode_to_bdi(inode); - return bdi_cap_account_dirty(bdi) && + return cgroup_on_dfl(mem_cgroup_root_css->cgroup) && + cgroup_on_dfl(blkcg_root_css->cgroup) && + bdi_cap_account_dirty(bdi) && (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } -- cgit v1.2.3 From 6ae459bdaaeebc632b16e54dcbabb490c6931d61 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Tue, 22 Sep 2015 12:57:53 -0700 Subject: skbuff: Fix skb checksum flag on skb pull VXLAN device can receive skb with checksum partial. But the checksum offset could be in outer header which is pulled on receive. This results in negative checksum offset for the skb. Such skb can cause the assert failure in skb_checksum_help(). Following patch fixes the bug by setting checksum-none while pulling outer header. Following is the kernel panic msg from old kernel hitting the bug. ------------[ cut here ]------------ kernel BUG at net/core/dev.c:1906! RIP: 0010:[] skb_checksum_help+0x144/0x150 Call Trace: [] queue_userspace_packet+0x408/0x470 [openvswitch] [] ovs_dp_upcall+0x5d/0x60 [openvswitch] [] ovs_dp_process_packet_with_key+0xe6/0x100 [openvswitch] [] ovs_dp_process_received_packet+0x4b/0x80 [openvswitch] [] ovs_vport_receive+0x2a/0x30 [openvswitch] [] vxlan_rcv+0x53/0x60 [openvswitch] [] vxlan_udp_encap_recv+0x8b/0xf0 [openvswitch] [] udp_queue_rcv_skb+0x2dc/0x3b0 [] __udp4_lib_rcv+0x1cf/0x6c0 [] udp_rcv+0x1a/0x20 [] ip_local_deliver_finish+0xdd/0x280 [] ip_local_deliver+0x88/0x90 [] ip_rcv_finish+0x10d/0x370 [] ip_rcv+0x235/0x300 [] __netif_receive_skb+0x55d/0x620 [] netif_receive_skb+0x80/0x90 [] virtnet_poll+0x555/0x6f0 [] net_rx_action+0x134/0x290 [] __do_softirq+0xa8/0x210 [] call_softirq+0x1c/0x30 [] do_softirq+0x65/0xa0 [] irq_exit+0x8e/0xb0 [] do_IRQ+0x63/0xe0 [] common_interrupt+0x6e/0x6e Reported-by: Anupam Chanda Signed-off-by: Pravin B Shelar Acked-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9987af080fa0..2b0a30a6e31c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2707,6 +2707,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); + else if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) <= len) + skb->ip_summed = CHECKSUM_NONE; } unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); -- cgit v1.2.3 From 63d008a4e9ee86614ca5671b7f3ba447df007190 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 22 Sep 2015 18:12:11 +0200 Subject: ipv4: send arp replies to the correct tunnel When using ip lwtunnels, the additional data for xmit (basically, the actual tunnel to use) are carried in ip_tunnel_info either in dst->lwtstate or in metadata dst. When replying to ARP requests, we need to send the reply to the same tunnel the request came from. This means we need to construct proper metadata dst for ARP replies. We could perform another route lookup to get a dst entry with the correct lwtstate. However, this won't always ensure that the outgoing tunnel is the same as the incoming one, and it won't work anyway for IPv4 duplicate address detection. The only thing to do is to "reverse" the ip_tunnel_info. Signed-off-by: Jiri Benc Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 2 ++ net/ipv4/arp.c | 39 +++++++++++++++++++++++++-------------- net/ipv4/ip_tunnel_core.c | 28 ++++++++++++++++++++++++++++ 3 files changed, 55 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 9a6a3ba888e8..f6dafec9102c 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -276,6 +276,8 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto); int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, u8 proto, u8 tos, u8 ttl, __be16 df, bool xnet); +struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, + gfp_t flags); struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum, int gso_type_mask); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 30409b75e925..f03db8b7abee 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -113,6 +113,8 @@ #include #include #include +#include +#include #include @@ -296,7 +298,8 @@ static void arp_send_dst(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, - const unsigned char *target_hw, struct sk_buff *oskb) + const unsigned char *target_hw, + struct dst_entry *dst) { struct sk_buff *skb; @@ -309,9 +312,7 @@ static void arp_send_dst(int type, int ptype, __be32 dest_ip, if (!skb) return; - if (oskb) - skb_dst_copy(skb, oskb); - + skb_dst_set(skb, dst); arp_xmit(skb); } @@ -333,6 +334,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) __be32 target = *(__be32 *)neigh->primary_key; int probes = atomic_read(&neigh->probes); struct in_device *in_dev; + struct dst_entry *dst = NULL; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); @@ -381,9 +383,10 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) } } + if (skb && !(dev->priv_flags & IFF_XMIT_DST_RELEASE)) + dst = dst_clone(skb_dst(skb)); arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, - dst_hw, dev->dev_addr, NULL, - dev->priv_flags & IFF_XMIT_DST_RELEASE ? NULL : skb); + dst_hw, dev->dev_addr, NULL, dst); } static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) @@ -649,6 +652,7 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) int addr_type; struct neighbour *n; struct net *net = dev_net(dev); + struct dst_entry *reply_dst = NULL; bool is_garp = false; /* arp_rcv below verifies the ARP header and verifies the device @@ -749,13 +753,18 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) * cache. */ + if (arp->ar_op == htons(ARPOP_REQUEST) && skb_metadata_dst(skb)) + reply_dst = (struct dst_entry *) + iptunnel_metadata_reply(skb_metadata_dst(skb), + GFP_ATOMIC); + /* Special case: IPv4 duplicate address detection packet (RFC2131) */ if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) - arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, - dev->dev_addr, sha); + arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, + sha, dev->dev_addr, sha, reply_dst); goto out; } @@ -774,9 +783,10 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) if (!dont_send) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) { - arp_send(ARPOP_REPLY, ETH_P_ARP, sip, - dev, tip, sha, dev->dev_addr, - sha); + arp_send_dst(ARPOP_REPLY, ETH_P_ARP, + sip, dev, tip, sha, + dev->dev_addr, sha, + reply_dst); neigh_release(n); } } @@ -794,9 +804,10 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED || skb->pkt_type == PACKET_HOST || NEIGH_VAR(in_dev->arp_parms, PROXY_DELAY) == 0) { - arp_send(ARPOP_REPLY, ETH_P_ARP, sip, - dev, tip, sha, dev->dev_addr, - sha); + arp_send_dst(ARPOP_REPLY, ETH_P_ARP, + sip, dev, tip, sha, + dev->dev_addr, sha, + reply_dst); } else { pneigh_enqueue(&arp_tbl, in_dev->arp_parms, skb); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 9b97204b8c81..ce3a1e728606 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -46,6 +46,7 @@ #include #include #include +#include int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, __u8 proto, @@ -119,6 +120,33 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) } EXPORT_SYMBOL_GPL(iptunnel_pull_header); +struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, + gfp_t flags) +{ + struct metadata_dst *res; + struct ip_tunnel_info *dst, *src; + + if (!md || md->u.tun_info.mode & IP_TUNNEL_INFO_TX) + return NULL; + + res = metadata_dst_alloc(0, flags); + if (!res) + return NULL; + + dst = &res->u.tun_info; + src = &md->u.tun_info; + dst->key.tun_id = src->key.tun_id; + if (src->mode & IP_TUNNEL_INFO_IPV6) + memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src, + sizeof(struct in6_addr)); + else + dst->key.u.ipv4.dst = src->key.u.ipv4.src; + dst->mode = src->mode | IP_TUNNEL_INFO_TX; + + return res; +} +EXPORT_SYMBOL_GPL(iptunnel_metadata_reply); + struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool csum_help, int gso_type_mask) -- cgit v1.2.3 From b194f30c61efb0767a98f47a64530baa8b731670 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 22 Sep 2015 18:12:12 +0200 Subject: lwtunnel: remove source and destination UDP port config option The UDP tunnel config is asymmetric wrt. to the ports used. The source and destination ports from one direction of the tunnel are not related to the ports of the other direction. We need to be able to respond to ARP requests using the correct ports without involving routing. As the consequence, UDP ports need to be fixed property of the tunnel interface and cannot be set per route. Remove the ability to set ports per route. This is still okay to do, as no kernel has been released with these attributes yet. Note that the ability to specify source and destination ports is preserved for other users of the lwtunnel API which don't use routes for tunnel key specification (like openvswitch). If in the future we rework ARP handling to allow port specification, the attributes can be added back. Signed-off-by: Jiri Benc Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/uapi/linux/lwtunnel.h | 4 ---- net/ipv4/ip_tunnel_core.c | 24 ------------------------ 2 files changed, 28 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h index 34141a5dfe74..f8b01887a495 100644 --- a/include/uapi/linux/lwtunnel.h +++ b/include/uapi/linux/lwtunnel.h @@ -21,8 +21,6 @@ enum lwtunnel_ip_t { LWTUNNEL_IP_SRC, LWTUNNEL_IP_TTL, LWTUNNEL_IP_TOS, - LWTUNNEL_IP_SPORT, - LWTUNNEL_IP_DPORT, LWTUNNEL_IP_FLAGS, __LWTUNNEL_IP_MAX, }; @@ -36,8 +34,6 @@ enum lwtunnel_ip6_t { LWTUNNEL_IP6_SRC, LWTUNNEL_IP6_HOPLIMIT, LWTUNNEL_IP6_TC, - LWTUNNEL_IP6_SPORT, - LWTUNNEL_IP6_DPORT, LWTUNNEL_IP6_FLAGS, __LWTUNNEL_IP6_MAX, }; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index ce3a1e728606..84dce6a92f93 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -226,8 +226,6 @@ static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = { [LWTUNNEL_IP_SRC] = { .type = NLA_U32 }, [LWTUNNEL_IP_TTL] = { .type = NLA_U8 }, [LWTUNNEL_IP_TOS] = { .type = NLA_U8 }, - [LWTUNNEL_IP_SPORT] = { .type = NLA_U16 }, - [LWTUNNEL_IP_DPORT] = { .type = NLA_U16 }, [LWTUNNEL_IP_FLAGS] = { .type = NLA_U16 }, }; @@ -267,12 +265,6 @@ static int ip_tun_build_state(struct net_device *dev, struct nlattr *attr, if (tb[LWTUNNEL_IP_TOS]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]); - if (tb[LWTUNNEL_IP_SPORT]) - tun_info->key.tp_src = nla_get_be16(tb[LWTUNNEL_IP_SPORT]); - - if (tb[LWTUNNEL_IP_DPORT]) - tun_info->key.tp_dst = nla_get_be16(tb[LWTUNNEL_IP_DPORT]); - if (tb[LWTUNNEL_IP_FLAGS]) tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP_FLAGS]); @@ -294,8 +286,6 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb, nla_put_be32(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) || - nla_put_u16(skb, LWTUNNEL_IP_SPORT, tun_info->key.tp_src) || - nla_put_u16(skb, LWTUNNEL_IP_DPORT, tun_info->key.tp_dst) || nla_put_u16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags)) return -ENOMEM; @@ -309,8 +299,6 @@ static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate) + nla_total_size(4) /* LWTUNNEL_IP_SRC */ + nla_total_size(1) /* LWTUNNEL_IP_TOS */ + nla_total_size(1) /* LWTUNNEL_IP_TTL */ - + nla_total_size(2) /* LWTUNNEL_IP_SPORT */ - + nla_total_size(2) /* LWTUNNEL_IP_DPORT */ + nla_total_size(2); /* LWTUNNEL_IP_FLAGS */ } @@ -333,8 +321,6 @@ static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { [LWTUNNEL_IP6_SRC] = { .len = sizeof(struct in6_addr) }, [LWTUNNEL_IP6_HOPLIMIT] = { .type = NLA_U8 }, [LWTUNNEL_IP6_TC] = { .type = NLA_U8 }, - [LWTUNNEL_IP6_SPORT] = { .type = NLA_U16 }, - [LWTUNNEL_IP6_DPORT] = { .type = NLA_U16 }, [LWTUNNEL_IP6_FLAGS] = { .type = NLA_U16 }, }; @@ -374,12 +360,6 @@ static int ip6_tun_build_state(struct net_device *dev, struct nlattr *attr, if (tb[LWTUNNEL_IP6_TC]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]); - if (tb[LWTUNNEL_IP6_SPORT]) - tun_info->key.tp_src = nla_get_be16(tb[LWTUNNEL_IP6_SPORT]); - - if (tb[LWTUNNEL_IP6_DPORT]) - tun_info->key.tp_dst = nla_get_be16(tb[LWTUNNEL_IP6_DPORT]); - if (tb[LWTUNNEL_IP6_FLAGS]) tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP6_FLAGS]); @@ -401,8 +381,6 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb, nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.ttl) || - nla_put_u16(skb, LWTUNNEL_IP6_SPORT, tun_info->key.tp_src) || - nla_put_u16(skb, LWTUNNEL_IP6_DPORT, tun_info->key.tp_dst) || nla_put_u16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags)) return -ENOMEM; @@ -416,8 +394,6 @@ static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate) + nla_total_size(16) /* LWTUNNEL_IP6_SRC */ + nla_total_size(1) /* LWTUNNEL_IP6_HOPLIMIT */ + nla_total_size(1) /* LWTUNNEL_IP6_TC */ - + nla_total_size(2) /* LWTUNNEL_IP6_SPORT */ - + nla_total_size(2) /* LWTUNNEL_IP6_DPORT */ + nla_total_size(2); /* LWTUNNEL_IP6_FLAGS */ } -- cgit v1.2.3 From 69f5df491e0becb75d2d795add7481a35218d657 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:40 +0200 Subject: switchdev: rename "trans" to "trans_ph". This is temporary, name "trans" will be used for something else and "trans_ph" will eventually disappear. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 382 +++++++++++++++++------------------ include/net/switchdev.h | 6 +- net/dsa/slave.c | 8 +- net/switchdev/switchdev.c | 12 +- 4 files changed, 204 insertions(+), 204 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 32c5429ea5fe..cf03b077311e 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -343,7 +343,7 @@ static bool rocker_port_is_ovsed(const struct rocker_port *rocker_port) #define ROCKER_OP_FLAG_REFRESH BIT(3) static void *__rocker_port_mem_alloc(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, size_t size) { struct list_head *elem = NULL; @@ -359,7 +359,7 @@ static void *__rocker_port_mem_alloc(struct rocker_port *rocker_port, * memory used in the commit phase. */ - switch (trans) { + switch (trans_ph) { case SWITCHDEV_TRANS_PREPARE: elem = kzalloc(size + sizeof(*elem), gfp_flags); if (!elem) @@ -384,20 +384,20 @@ static void *__rocker_port_mem_alloc(struct rocker_port *rocker_port, } static void *rocker_port_kzalloc(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, size_t size) { - return __rocker_port_mem_alloc(rocker_port, trans, flags, size); + return __rocker_port_mem_alloc(rocker_port, trans_ph, flags, size); } static void *rocker_port_kcalloc(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, size_t n, size_t size) { - return __rocker_port_mem_alloc(rocker_port, trans, flags, n * size); + return __rocker_port_mem_alloc(rocker_port, trans_ph, flags, n * size); } -static void rocker_port_kfree(enum switchdev_trans trans, const void *mem) +static void rocker_port_kfree(enum switchdev_trans_ph trans_ph, const void *mem) { struct list_head *elem; @@ -406,7 +406,7 @@ static void rocker_port_kfree(enum switchdev_trans trans, const void *mem) * commit phase. */ - if (trans == SWITCHDEV_TRANS_PREPARE) + if (trans_ph == SWITCHDEV_TRANS_PREPARE) return; elem = (struct list_head *)mem - 1; @@ -433,22 +433,22 @@ static void rocker_wait_init(struct rocker_wait *wait) } static struct rocker_wait *rocker_wait_create(struct rocker_port *rocker_port, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, int flags) { struct rocker_wait *wait; - wait = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*wait)); + wait = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*wait)); if (!wait) return NULL; rocker_wait_init(wait); return wait; } -static void rocker_wait_destroy(enum switchdev_trans trans, +static void rocker_wait_destroy(enum switchdev_trans_ph trans_ph, struct rocker_wait *wait) { - rocker_port_kfree(trans, wait); + rocker_port_kfree(trans_ph, wait); } static bool rocker_wait_event_timeout(struct rocker_wait *wait, @@ -1466,7 +1466,7 @@ static int rocker_event_link_change(const struct rocker *rocker, } static int rocker_port_fdb(struct rocker_port *rocker_port, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, const unsigned char *addr, __be16 vlan_id, int flags); @@ -1585,7 +1585,7 @@ typedef int (*rocker_cmd_proc_cb_t)(const struct rocker_port *rocker_port, void *priv); static int rocker_cmd_exec(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, rocker_cmd_prep_cb_t prepare, void *prepare_priv, rocker_cmd_proc_cb_t process, void *process_priv) { @@ -1596,7 +1596,7 @@ static int rocker_cmd_exec(struct rocker_port *rocker_port, unsigned long lock_flags; int err; - wait = rocker_wait_create(rocker_port, trans, flags); + wait = rocker_wait_create(rocker_port, trans_ph, flags); if (!wait) return -ENOMEM; wait->nowait = nowait; @@ -1618,7 +1618,7 @@ static int rocker_cmd_exec(struct rocker_port *rocker_port, rocker_desc_cookie_ptr_set(desc_info, wait); - if (trans != SWITCHDEV_TRANS_PREPARE) + if (trans_ph != SWITCHDEV_TRANS_PREPARE) rocker_desc_head_set(rocker, &rocker->cmd_ring, desc_info); spin_unlock_irqrestore(&rocker->cmd_ring_lock, lock_flags); @@ -1626,7 +1626,7 @@ static int rocker_cmd_exec(struct rocker_port *rocker_port, if (nowait) return 0; - if (trans != SWITCHDEV_TRANS_PREPARE) + if (trans_ph != SWITCHDEV_TRANS_PREPARE) if (!rocker_wait_event_timeout(wait, HZ / 10)) return -EIO; @@ -1639,7 +1639,7 @@ static int rocker_cmd_exec(struct rocker_port *rocker_port, rocker_desc_gen_clear(desc_info); out: - rocker_wait_destroy(trans, wait); + rocker_wait_destroy(trans_ph, wait); return err; } @@ -1918,9 +1918,9 @@ static int rocker_cmd_set_port_settings_mtu(struct rocker_port *rocker_port, } static int rocker_port_set_learning(struct rocker_port *rocker_port, - enum switchdev_trans trans) + enum switchdev_trans_ph trans_ph) { - return rocker_cmd_exec(rocker_port, trans, 0, + return rocker_cmd_exec(rocker_port, trans_ph, 0, rocker_cmd_set_port_learning_prep, NULL, NULL, NULL); } @@ -2436,7 +2436,7 @@ rocker_flow_tbl_find(const struct rocker *rocker, } static int rocker_flow_tbl_add(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, struct rocker_flow_tbl_entry *match) { struct rocker *rocker = rocker_port->rocker; @@ -2452,9 +2452,9 @@ static int rocker_flow_tbl_add(struct rocker_port *rocker_port, if (found) { match->cookie = found->cookie; - if (trans != SWITCHDEV_TRANS_PREPARE) + if (trans_ph != SWITCHDEV_TRANS_PREPARE) hash_del(&found->entry); - rocker_port_kfree(trans, found); + rocker_port_kfree(trans_ph, found); found = match; found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_MOD; } else { @@ -2463,17 +2463,17 @@ static int rocker_flow_tbl_add(struct rocker_port *rocker_port, found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_ADD; } - if (trans != SWITCHDEV_TRANS_PREPARE) + if (trans_ph != SWITCHDEV_TRANS_PREPARE) hash_add(rocker->flow_tbl, &found->entry, found->key_crc32); spin_unlock_irqrestore(&rocker->flow_tbl_lock, lock_flags); - return rocker_cmd_exec(rocker_port, trans, flags, + return rocker_cmd_exec(rocker_port, trans_ph, flags, rocker_cmd_flow_tbl_add, found, NULL, NULL); } static int rocker_flow_tbl_del(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, struct rocker_flow_tbl_entry *match) { struct rocker *rocker = rocker_port->rocker; @@ -2489,43 +2489,43 @@ static int rocker_flow_tbl_del(struct rocker_port *rocker_port, found = rocker_flow_tbl_find(rocker, match); if (found) { - if (trans != SWITCHDEV_TRANS_PREPARE) + if (trans_ph != SWITCHDEV_TRANS_PREPARE) hash_del(&found->entry); found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_DEL; } spin_unlock_irqrestore(&rocker->flow_tbl_lock, lock_flags); - rocker_port_kfree(trans, match); + rocker_port_kfree(trans_ph, match); if (found) { - err = rocker_cmd_exec(rocker_port, trans, flags, + err = rocker_cmd_exec(rocker_port, trans_ph, flags, rocker_cmd_flow_tbl_del, found, NULL, NULL); - rocker_port_kfree(trans, found); + rocker_port_kfree(trans_ph, found); } return err; } static int rocker_flow_tbl_do(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, struct rocker_flow_tbl_entry *entry) { if (flags & ROCKER_OP_FLAG_REMOVE) - return rocker_flow_tbl_del(rocker_port, trans, flags, entry); + return rocker_flow_tbl_del(rocker_port, trans_ph, flags, entry); else - return rocker_flow_tbl_add(rocker_port, trans, flags, entry); + return rocker_flow_tbl_add(rocker_port, trans_ph, flags, entry); } static int rocker_flow_tbl_ig_port(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, u32 in_pport, u32 in_pport_mask, enum rocker_of_dpa_table_id goto_tbl) { struct rocker_flow_tbl_entry *entry; - entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry)); + entry = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2535,11 +2535,11 @@ static int rocker_flow_tbl_ig_port(struct rocker_port *rocker_port, entry->key.ig_port.in_pport_mask = in_pport_mask; entry->key.ig_port.goto_tbl = goto_tbl; - return rocker_flow_tbl_do(rocker_port, trans, flags, entry); + return rocker_flow_tbl_do(rocker_port, trans_ph, flags, entry); } static int rocker_flow_tbl_vlan(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, u32 in_pport, __be16 vlan_id, __be16 vlan_id_mask, enum rocker_of_dpa_table_id goto_tbl, @@ -2547,7 +2547,7 @@ static int rocker_flow_tbl_vlan(struct rocker_port *rocker_port, { struct rocker_flow_tbl_entry *entry; - entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry)); + entry = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2561,11 +2561,11 @@ static int rocker_flow_tbl_vlan(struct rocker_port *rocker_port, entry->key.vlan.untagged = untagged; entry->key.vlan.new_vlan_id = new_vlan_id; - return rocker_flow_tbl_do(rocker_port, trans, flags, entry); + return rocker_flow_tbl_do(rocker_port, trans_ph, flags, entry); } static int rocker_flow_tbl_term_mac(struct rocker_port *rocker_port, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, u32 in_pport, u32 in_pport_mask, __be16 eth_type, const u8 *eth_dst, const u8 *eth_dst_mask, __be16 vlan_id, @@ -2574,7 +2574,7 @@ static int rocker_flow_tbl_term_mac(struct rocker_port *rocker_port, { struct rocker_flow_tbl_entry *entry; - entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry)); + entry = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2598,11 +2598,11 @@ static int rocker_flow_tbl_term_mac(struct rocker_port *rocker_port, entry->key.term_mac.vlan_id_mask = vlan_id_mask; entry->key.term_mac.copy_to_cpu = copy_to_cpu; - return rocker_flow_tbl_do(rocker_port, trans, flags, entry); + return rocker_flow_tbl_do(rocker_port, trans_ph, flags, entry); } static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, const u8 *eth_dst, const u8 *eth_dst_mask, __be16 vlan_id, u32 tunnel_id, enum rocker_of_dpa_table_id goto_tbl, @@ -2614,7 +2614,7 @@ static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port, bool dflt = !eth_dst || (eth_dst && eth_dst_mask); bool wild = false; - entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry)); + entry = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2652,11 +2652,11 @@ static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port, entry->key.bridge.group_id = group_id; entry->key.bridge.copy_to_cpu = copy_to_cpu; - return rocker_flow_tbl_do(rocker_port, trans, flags, entry); + return rocker_flow_tbl_do(rocker_port, trans_ph, flags, entry); } static int rocker_flow_tbl_ucast4_routing(struct rocker_port *rocker_port, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, __be16 eth_type, __be32 dst, __be32 dst_mask, u32 priority, enum rocker_of_dpa_table_id goto_tbl, @@ -2664,7 +2664,7 @@ static int rocker_flow_tbl_ucast4_routing(struct rocker_port *rocker_port, { struct rocker_flow_tbl_entry *entry; - entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry)); + entry = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2678,11 +2678,11 @@ static int rocker_flow_tbl_ucast4_routing(struct rocker_port *rocker_port, entry->key_len = offsetof(struct rocker_flow_tbl_key, ucast_routing.group_id); - return rocker_flow_tbl_do(rocker_port, trans, flags, entry); + return rocker_flow_tbl_do(rocker_port, trans_ph, flags, entry); } static int rocker_flow_tbl_acl(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, u32 in_pport, u32 in_pport_mask, const u8 *eth_src, const u8 *eth_src_mask, const u8 *eth_dst, const u8 *eth_dst_mask, @@ -2694,7 +2694,7 @@ static int rocker_flow_tbl_acl(struct rocker_port *rocker_port, u32 priority; struct rocker_flow_tbl_entry *entry; - entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry)); + entry = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2729,7 +2729,7 @@ static int rocker_flow_tbl_acl(struct rocker_port *rocker_port, entry->key.acl.ip_tos_mask = ip_tos_mask; entry->key.acl.group_id = group_id; - return rocker_flow_tbl_do(rocker_port, trans, flags, entry); + return rocker_flow_tbl_do(rocker_port, trans_ph, flags, entry); } static struct rocker_group_tbl_entry * @@ -2747,22 +2747,22 @@ rocker_group_tbl_find(const struct rocker *rocker, return NULL; } -static void rocker_group_tbl_entry_free(enum switchdev_trans trans, +static void rocker_group_tbl_entry_free(enum switchdev_trans_ph trans_ph, struct rocker_group_tbl_entry *entry) { switch (ROCKER_GROUP_TYPE_GET(entry->group_id)) { case ROCKER_OF_DPA_GROUP_TYPE_L2_FLOOD: case ROCKER_OF_DPA_GROUP_TYPE_L2_MCAST: - rocker_port_kfree(trans, entry->group_ids); + rocker_port_kfree(trans_ph, entry->group_ids); break; default: break; } - rocker_port_kfree(trans, entry); + rocker_port_kfree(trans_ph, entry); } static int rocker_group_tbl_add(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, struct rocker_group_tbl_entry *match) { struct rocker *rocker = rocker_port->rocker; @@ -2774,9 +2774,9 @@ static int rocker_group_tbl_add(struct rocker_port *rocker_port, found = rocker_group_tbl_find(rocker, match); if (found) { - if (trans != SWITCHDEV_TRANS_PREPARE) + if (trans_ph != SWITCHDEV_TRANS_PREPARE) hash_del(&found->entry); - rocker_group_tbl_entry_free(trans, found); + rocker_group_tbl_entry_free(trans_ph, found); found = match; found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_MOD; } else { @@ -2784,17 +2784,17 @@ static int rocker_group_tbl_add(struct rocker_port *rocker_port, found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_ADD; } - if (trans != SWITCHDEV_TRANS_PREPARE) + if (trans_ph != SWITCHDEV_TRANS_PREPARE) hash_add(rocker->group_tbl, &found->entry, found->group_id); spin_unlock_irqrestore(&rocker->group_tbl_lock, lock_flags); - return rocker_cmd_exec(rocker_port, trans, flags, + return rocker_cmd_exec(rocker_port, trans_ph, flags, rocker_cmd_group_tbl_add, found, NULL, NULL); } static int rocker_group_tbl_del(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, struct rocker_group_tbl_entry *match) { struct rocker *rocker = rocker_port->rocker; @@ -2807,95 +2807,95 @@ static int rocker_group_tbl_del(struct rocker_port *rocker_port, found = rocker_group_tbl_find(rocker, match); if (found) { - if (trans != SWITCHDEV_TRANS_PREPARE) + if (trans_ph != SWITCHDEV_TRANS_PREPARE) hash_del(&found->entry); found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_DEL; } spin_unlock_irqrestore(&rocker->group_tbl_lock, lock_flags); - rocker_group_tbl_entry_free(trans, match); + rocker_group_tbl_entry_free(trans_ph, match); if (found) { - err = rocker_cmd_exec(rocker_port, trans, flags, + err = rocker_cmd_exec(rocker_port, trans_ph, flags, rocker_cmd_group_tbl_del, found, NULL, NULL); - rocker_group_tbl_entry_free(trans, found); + rocker_group_tbl_entry_free(trans_ph, found); } return err; } static int rocker_group_tbl_do(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, struct rocker_group_tbl_entry *entry) { if (flags & ROCKER_OP_FLAG_REMOVE) - return rocker_group_tbl_del(rocker_port, trans, flags, entry); + return rocker_group_tbl_del(rocker_port, trans_ph, flags, entry); else - return rocker_group_tbl_add(rocker_port, trans, flags, entry); + return rocker_group_tbl_add(rocker_port, trans_ph, flags, entry); } static int rocker_group_l2_interface(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, __be16 vlan_id, u32 out_pport, int pop_vlan) { struct rocker_group_tbl_entry *entry; - entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry)); + entry = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*entry)); if (!entry) return -ENOMEM; entry->group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, out_pport); entry->l2_interface.pop_vlan = pop_vlan; - return rocker_group_tbl_do(rocker_port, trans, flags, entry); + return rocker_group_tbl_do(rocker_port, trans_ph, flags, entry); } static int rocker_group_l2_fan_out(struct rocker_port *rocker_port, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, int flags, u8 group_count, const u32 *group_ids, u32 group_id) { struct rocker_group_tbl_entry *entry; - entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry)); + entry = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*entry)); if (!entry) return -ENOMEM; entry->group_id = group_id; entry->group_count = group_count; - entry->group_ids = rocker_port_kcalloc(rocker_port, trans, flags, + entry->group_ids = rocker_port_kcalloc(rocker_port, trans_ph, flags, group_count, sizeof(u32)); if (!entry->group_ids) { - rocker_port_kfree(trans, entry); + rocker_port_kfree(trans_ph, entry); return -ENOMEM; } memcpy(entry->group_ids, group_ids, group_count * sizeof(u32)); - return rocker_group_tbl_do(rocker_port, trans, flags, entry); + return rocker_group_tbl_do(rocker_port, trans_ph, flags, entry); } static int rocker_group_l2_flood(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, __be16 vlan_id, u8 group_count, const u32 *group_ids, u32 group_id) { - return rocker_group_l2_fan_out(rocker_port, trans, flags, + return rocker_group_l2_fan_out(rocker_port, trans_ph, flags, group_count, group_ids, group_id); } static int rocker_group_l3_unicast(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, u32 index, const u8 *src_mac, const u8 *dst_mac, __be16 vlan_id, bool ttl_check, u32 pport) { struct rocker_group_tbl_entry *entry; - entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry)); + entry = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2908,7 +2908,7 @@ static int rocker_group_l3_unicast(struct rocker_port *rocker_port, entry->l3_unicast.ttl_check = ttl_check; entry->l3_unicast.group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, pport); - return rocker_group_tbl_do(rocker_port, trans, flags, entry); + return rocker_group_tbl_do(rocker_port, trans_ph, flags, entry); } static struct rocker_neigh_tbl_entry * @@ -2925,43 +2925,43 @@ rocker_neigh_tbl_find(const struct rocker *rocker, __be32 ip_addr) } static void _rocker_neigh_add(struct rocker *rocker, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, struct rocker_neigh_tbl_entry *entry) { - if (trans != SWITCHDEV_TRANS_COMMIT) + if (trans_ph != SWITCHDEV_TRANS_COMMIT) entry->index = rocker->neigh_tbl_next_index++; - if (trans == SWITCHDEV_TRANS_PREPARE) + if (trans_ph == SWITCHDEV_TRANS_PREPARE) return; entry->ref_count++; hash_add(rocker->neigh_tbl, &entry->entry, be32_to_cpu(entry->ip_addr)); } -static void _rocker_neigh_del(enum switchdev_trans trans, +static void _rocker_neigh_del(enum switchdev_trans_ph trans_ph, struct rocker_neigh_tbl_entry *entry) { - if (trans == SWITCHDEV_TRANS_PREPARE) + if (trans_ph == SWITCHDEV_TRANS_PREPARE) return; if (--entry->ref_count == 0) { hash_del(&entry->entry); - rocker_port_kfree(trans, entry); + rocker_port_kfree(trans_ph, entry); } } static void _rocker_neigh_update(struct rocker_neigh_tbl_entry *entry, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, const u8 *eth_dst, bool ttl_check) { if (eth_dst) { ether_addr_copy(entry->eth_dst, eth_dst); entry->ttl_check = ttl_check; - } else if (trans != SWITCHDEV_TRANS_PREPARE) { + } else if (trans_ph != SWITCHDEV_TRANS_PREPARE) { entry->ref_count++; } } static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, int flags, __be32 ip_addr, const u8 *eth_dst) { struct rocker *rocker = rocker_port->rocker; @@ -2978,7 +2978,7 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, bool removing; int err = 0; - entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry)); + entry = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2995,12 +2995,12 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, entry->dev = rocker_port->dev; ether_addr_copy(entry->eth_dst, eth_dst); entry->ttl_check = true; - _rocker_neigh_add(rocker, trans, entry); + _rocker_neigh_add(rocker, trans_ph, entry); } else if (removing) { memcpy(entry, found, sizeof(*entry)); - _rocker_neigh_del(trans, found); + _rocker_neigh_del(trans_ph, found); } else if (updating) { - _rocker_neigh_update(found, trans, eth_dst, true); + _rocker_neigh_update(found, trans_ph, eth_dst, true); memcpy(entry, found, sizeof(*entry)); } else { err = -ENOENT; @@ -3017,7 +3017,7 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, * other routes' nexthops. */ - err = rocker_group_l3_unicast(rocker_port, trans, flags, + err = rocker_group_l3_unicast(rocker_port, trans_ph, flags, entry->index, rocker_port->dev->dev_addr, entry->eth_dst, @@ -3033,7 +3033,7 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, if (adding || removing) { group_id = ROCKER_GROUP_L3_UNICAST(entry->index); - err = rocker_flow_tbl_ucast4_routing(rocker_port, trans, + err = rocker_flow_tbl_ucast4_routing(rocker_port, trans_ph, eth_type, ip_addr, inet_make_mask(32), priority, goto_tbl, @@ -3047,13 +3047,13 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, err_out: if (!adding) - rocker_port_kfree(trans, entry); + rocker_port_kfree(trans_ph, entry); return err; } static int rocker_port_ipv4_resolve(struct rocker_port *rocker_port, - enum switchdev_trans trans, __be32 ip_addr) + enum switchdev_trans_ph trans_ph, __be32 ip_addr) { struct net_device *dev = rocker_port->dev; struct neighbour *n = __ipv4_neigh_lookup(dev, (__force u32)ip_addr); @@ -3071,7 +3071,7 @@ static int rocker_port_ipv4_resolve(struct rocker_port *rocker_port, */ if (n->nud_state & NUD_VALID) - err = rocker_port_ipv4_neigh(rocker_port, trans, 0, + err = rocker_port_ipv4_neigh(rocker_port, trans_ph, 0, ip_addr, n->ha); else neigh_event_send(n, NULL); @@ -3081,7 +3081,7 @@ static int rocker_port_ipv4_resolve(struct rocker_port *rocker_port, } static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, __be32 ip_addr, u32 *index) { struct rocker *rocker = rocker_port->rocker; @@ -3094,7 +3094,7 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, bool resolved = true; int err = 0; - entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry)); + entry = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -3111,13 +3111,13 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, if (adding) { entry->ip_addr = ip_addr; entry->dev = rocker_port->dev; - _rocker_neigh_add(rocker, trans, entry); + _rocker_neigh_add(rocker, trans_ph, entry); *index = entry->index; resolved = false; } else if (removing) { - _rocker_neigh_del(trans, found); + _rocker_neigh_del(trans_ph, found); } else if (updating) { - _rocker_neigh_update(found, trans, NULL, false); + _rocker_neigh_update(found, trans_ph, NULL, false); resolved = !is_zero_ether_addr(found->eth_dst); } else { err = -ENOENT; @@ -3126,7 +3126,7 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, spin_unlock_irqrestore(&rocker->neigh_tbl_lock, lock_flags); if (!adding) - rocker_port_kfree(trans, entry); + rocker_port_kfree(trans_ph, entry); if (err) return err; @@ -3134,13 +3134,13 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, /* Resolved means neigh ip_addr is resolved to neigh mac. */ if (!resolved) - err = rocker_port_ipv4_resolve(rocker_port, trans, ip_addr); + err = rocker_port_ipv4_resolve(rocker_port, trans_ph, ip_addr); return err; } static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, int flags, __be16 vlan_id) { struct rocker_port *p; @@ -3151,7 +3151,7 @@ static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, int err = 0; int i; - group_ids = rocker_port_kcalloc(rocker_port, trans, flags, + group_ids = rocker_port_kcalloc(rocker_port, trans_ph, flags, rocker->port_count, sizeof(u32)); if (!group_ids) return -ENOMEM; @@ -3177,19 +3177,19 @@ static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, if (group_count == 0) goto no_ports_in_vlan; - err = rocker_group_l2_flood(rocker_port, trans, flags, vlan_id, + err = rocker_group_l2_flood(rocker_port, trans_ph, flags, vlan_id, group_count, group_ids, group_id); if (err) netdev_err(rocker_port->dev, "Error (%d) port VLAN l2 flood group\n", err); no_ports_in_vlan: - rocker_port_kfree(trans, group_ids); + rocker_port_kfree(trans_ph, group_ids); return err; } static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, __be16 vlan_id, bool pop_vlan) { const struct rocker *rocker = rocker_port->rocker; @@ -3207,7 +3207,7 @@ static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port, if (rocker_port->stp_state == BR_STATE_LEARNING || rocker_port->stp_state == BR_STATE_FORWARDING) { out_pport = rocker_port->pport; - err = rocker_group_l2_interface(rocker_port, trans, flags, + err = rocker_group_l2_interface(rocker_port, trans_ph, flags, vlan_id, out_pport, pop_vlan); if (err) { netdev_err(rocker_port->dev, @@ -3232,7 +3232,7 @@ static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port, return 0; out_pport = 0; - err = rocker_group_l2_interface(rocker_port, trans, flags, + err = rocker_group_l2_interface(rocker_port, trans_ph, flags, vlan_id, out_pport, pop_vlan); if (err) { netdev_err(rocker_port->dev, @@ -3295,7 +3295,7 @@ static struct rocker_ctrl { }; static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, const struct rocker_ctrl *ctrl, __be16 vlan_id) { u32 in_pport = rocker_port->pport; @@ -3311,7 +3311,7 @@ static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port, u32 group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, out_pport); int err; - err = rocker_flow_tbl_acl(rocker_port, trans, flags, + err = rocker_flow_tbl_acl(rocker_port, trans_ph, flags, in_pport, in_pport_mask, eth_src, eth_src_mask, ctrl->eth_dst, ctrl->eth_dst_mask, @@ -3328,7 +3328,7 @@ static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port, } static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, const struct rocker_ctrl *ctrl, __be16 vlan_id) { @@ -3341,7 +3341,7 @@ static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port, if (!rocker_port_is_bridged(rocker_port)) return 0; - err = rocker_flow_tbl_bridge(rocker_port, trans, flags, + err = rocker_flow_tbl_bridge(rocker_port, trans_ph, flags, ctrl->eth_dst, ctrl->eth_dst_mask, vlan_id, tunnel_id, goto_tbl, group_id, ctrl->copy_to_cpu); @@ -3353,7 +3353,7 @@ static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port, } static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, const struct rocker_ctrl *ctrl, __be16 vlan_id) { u32 in_pport_mask = 0xffffffff; @@ -3363,7 +3363,7 @@ static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port, if (ntohs(vlan_id) == 0) vlan_id = rocker_port->internal_vlan_id; - err = rocker_flow_tbl_term_mac(rocker_port, trans, + err = rocker_flow_tbl_term_mac(rocker_port, trans_ph, rocker_port->pport, in_pport_mask, ctrl->eth_type, ctrl->eth_dst, ctrl->eth_dst_mask, vlan_id, @@ -3377,25 +3377,25 @@ static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port, } static int rocker_port_ctrl_vlan(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, const struct rocker_ctrl *ctrl, __be16 vlan_id) { if (ctrl->acl) - return rocker_port_ctrl_vlan_acl(rocker_port, trans, flags, + return rocker_port_ctrl_vlan_acl(rocker_port, trans_ph, flags, ctrl, vlan_id); if (ctrl->bridge) - return rocker_port_ctrl_vlan_bridge(rocker_port, trans, flags, + return rocker_port_ctrl_vlan_bridge(rocker_port, trans_ph, flags, ctrl, vlan_id); if (ctrl->term) - return rocker_port_ctrl_vlan_term(rocker_port, trans, flags, + return rocker_port_ctrl_vlan_term(rocker_port, trans_ph, flags, ctrl, vlan_id); return -EOPNOTSUPP; } static int rocker_port_ctrl_vlan_add(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, __be16 vlan_id) { int err = 0; @@ -3403,7 +3403,7 @@ static int rocker_port_ctrl_vlan_add(struct rocker_port *rocker_port, for (i = 0; i < ROCKER_CTRL_MAX; i++) { if (rocker_port->ctrls[i]) { - err = rocker_port_ctrl_vlan(rocker_port, trans, flags, + err = rocker_port_ctrl_vlan(rocker_port, trans_ph, flags, &rocker_ctrls[i], vlan_id); if (err) return err; @@ -3414,7 +3414,7 @@ static int rocker_port_ctrl_vlan_add(struct rocker_port *rocker_port, } static int rocker_port_ctrl(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, const struct rocker_ctrl *ctrl) { u16 vid; @@ -3423,7 +3423,7 @@ static int rocker_port_ctrl(struct rocker_port *rocker_port, for (vid = 1; vid < VLAN_N_VID; vid++) { if (!test_bit(vid, rocker_port->vlan_bitmap)) continue; - err = rocker_port_ctrl_vlan(rocker_port, trans, flags, + err = rocker_port_ctrl_vlan(rocker_port, trans_ph, flags, ctrl, htons(vid)); if (err) break; @@ -3433,7 +3433,7 @@ static int rocker_port_ctrl(struct rocker_port *rocker_port, } static int rocker_port_vlan(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, u16 vid) + enum switchdev_trans_ph trans_ph, int flags, u16 vid) { enum rocker_of_dpa_table_id goto_tbl = ROCKER_OF_DPA_TABLE_ID_TERMINATION_MAC; @@ -3457,7 +3457,7 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, change_bit(ntohs(internal_vlan_id), rocker_port->vlan_bitmap); if (adding) { - err = rocker_port_ctrl_vlan_add(rocker_port, trans, flags, + err = rocker_port_ctrl_vlan_add(rocker_port, trans_ph, flags, internal_vlan_id); if (err) { netdev_err(rocker_port->dev, @@ -3466,7 +3466,7 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, } } - err = rocker_port_vlan_l2_groups(rocker_port, trans, flags, + err = rocker_port_vlan_l2_groups(rocker_port, trans_ph, flags, internal_vlan_id, untagged); if (err) { netdev_err(rocker_port->dev, @@ -3474,7 +3474,7 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, goto err_out; } - err = rocker_port_vlan_flood_group(rocker_port, trans, flags, + err = rocker_port_vlan_flood_group(rocker_port, trans_ph, flags, internal_vlan_id); if (err) { netdev_err(rocker_port->dev, @@ -3482,7 +3482,7 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, goto err_out; } - err = rocker_flow_tbl_vlan(rocker_port, trans, flags, + err = rocker_flow_tbl_vlan(rocker_port, trans_ph, flags, in_pport, vlan_id, vlan_id_mask, goto_tbl, untagged, internal_vlan_id); if (err) @@ -3490,14 +3490,14 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, "Error (%d) port VLAN table\n", err); err_out: - if (trans == SWITCHDEV_TRANS_PREPARE) + if (trans_ph == SWITCHDEV_TRANS_PREPARE) change_bit(ntohs(internal_vlan_id), rocker_port->vlan_bitmap); return err; } static int rocker_port_ig_tbl(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags) + enum switchdev_trans_ph trans_ph, int flags) { enum rocker_of_dpa_table_id goto_tbl; u32 in_pport; @@ -3512,7 +3512,7 @@ static int rocker_port_ig_tbl(struct rocker_port *rocker_port, in_pport_mask = 0xffff0000; goto_tbl = ROCKER_OF_DPA_TABLE_ID_VLAN; - err = rocker_flow_tbl_ig_port(rocker_port, trans, flags, + err = rocker_flow_tbl_ig_port(rocker_port, trans_ph, flags, in_pport, in_pport_mask, goto_tbl); if (err) @@ -3525,7 +3525,7 @@ static int rocker_port_ig_tbl(struct rocker_port *rocker_port, struct rocker_fdb_learn_work { struct work_struct work; struct rocker_port *rocker_port; - enum switchdev_trans trans; + enum switchdev_trans_ph trans_ph; int flags; u8 addr[ETH_ALEN]; u16 vid; @@ -3549,11 +3549,11 @@ static void rocker_port_fdb_learn_work(struct work_struct *work) call_switchdev_notifiers(SWITCHDEV_FDB_ADD, lw->rocker_port->dev, &info.info); - rocker_port_kfree(lw->trans, work); + rocker_port_kfree(lw->trans_ph, work); } static int rocker_port_fdb_learn(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, const u8 *addr, __be16 vlan_id) { struct rocker_fdb_learn_work *lw; @@ -3570,7 +3570,7 @@ static int rocker_port_fdb_learn(struct rocker_port *rocker_port, group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, out_pport); if (!(flags & ROCKER_OP_FLAG_REFRESH)) { - err = rocker_flow_tbl_bridge(rocker_port, trans, flags, addr, + err = rocker_flow_tbl_bridge(rocker_port, trans_ph, flags, addr, NULL, vlan_id, tunnel_id, goto_tbl, group_id, copy_to_cpu); if (err) @@ -3583,20 +3583,20 @@ static int rocker_port_fdb_learn(struct rocker_port *rocker_port, if (!rocker_port_is_bridged(rocker_port)) return 0; - lw = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*lw)); + lw = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*lw)); if (!lw) return -ENOMEM; INIT_WORK(&lw->work, rocker_port_fdb_learn_work); lw->rocker_port = rocker_port; - lw->trans = trans; + lw->trans_ph = trans_ph; lw->flags = flags; ether_addr_copy(lw->addr, addr); lw->vid = rocker_port_vlan_to_vid(rocker_port, vlan_id); - if (trans == SWITCHDEV_TRANS_PREPARE) - rocker_port_kfree(trans, lw); + if (trans_ph == SWITCHDEV_TRANS_PREPARE) + rocker_port_kfree(trans_ph, lw); else schedule_work(&lw->work); @@ -3617,7 +3617,7 @@ rocker_fdb_tbl_find(const struct rocker *rocker, } static int rocker_port_fdb(struct rocker_port *rocker_port, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, const unsigned char *addr, __be16 vlan_id, int flags) { @@ -3627,7 +3627,7 @@ static int rocker_port_fdb(struct rocker_port *rocker_port, bool removing = (flags & ROCKER_OP_FLAG_REMOVE); unsigned long lock_flags; - fdb = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*fdb)); + fdb = rocker_port_kzalloc(rocker_port, trans_ph, flags, sizeof(*fdb)); if (!fdb) return -ENOMEM; @@ -3645,12 +3645,12 @@ static int rocker_port_fdb(struct rocker_port *rocker_port, if (found) { found->touched = jiffies; if (removing) { - rocker_port_kfree(trans, fdb); - if (trans != SWITCHDEV_TRANS_PREPARE) + rocker_port_kfree(trans_ph, fdb); + if (trans_ph != SWITCHDEV_TRANS_PREPARE) hash_del(&found->entry); } } else if (!removing) { - if (trans != SWITCHDEV_TRANS_PREPARE) + if (trans_ph != SWITCHDEV_TRANS_PREPARE) hash_add(rocker->fdb_tbl, &fdb->entry, fdb->key_crc32); } @@ -3659,18 +3659,18 @@ static int rocker_port_fdb(struct rocker_port *rocker_port, /* Check if adding and already exists, or removing and can't find */ if (!found != !removing) { - rocker_port_kfree(trans, fdb); + rocker_port_kfree(trans_ph, fdb); if (!found && removing) return 0; /* Refreshing existing to update aging timers */ flags |= ROCKER_OP_FLAG_REFRESH; } - return rocker_port_fdb_learn(rocker_port, trans, flags, addr, vlan_id); + return rocker_port_fdb_learn(rocker_port, trans_ph, flags, addr, vlan_id); } static int rocker_port_fdb_flush(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags) + enum switchdev_trans_ph trans_ph, int flags) { struct rocker *rocker = rocker_port->rocker; struct rocker_fdb_tbl_entry *found; @@ -3692,12 +3692,12 @@ static int rocker_port_fdb_flush(struct rocker_port *rocker_port, continue; if (!found->learned) continue; - err = rocker_port_fdb_learn(rocker_port, trans, flags, + err = rocker_port_fdb_learn(rocker_port, trans_ph, flags, found->key.addr, found->key.vlan_id); if (err) goto err_out; - if (trans != SWITCHDEV_TRANS_PREPARE) + if (trans_ph != SWITCHDEV_TRANS_PREPARE) hash_del(&found->entry); } @@ -3743,7 +3743,7 @@ static void rocker_fdb_cleanup(unsigned long data) } static int rocker_port_router_mac(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, __be16 vlan_id) { u32 in_pport_mask = 0xffffffff; @@ -3757,7 +3757,7 @@ static int rocker_port_router_mac(struct rocker_port *rocker_port, vlan_id = rocker_port->internal_vlan_id; eth_type = htons(ETH_P_IP); - err = rocker_flow_tbl_term_mac(rocker_port, trans, + err = rocker_flow_tbl_term_mac(rocker_port, trans_ph, rocker_port->pport, in_pport_mask, eth_type, rocker_port->dev->dev_addr, dst_mac_mask, vlan_id, vlan_id_mask, @@ -3766,7 +3766,7 @@ static int rocker_port_router_mac(struct rocker_port *rocker_port, return err; eth_type = htons(ETH_P_IPV6); - err = rocker_flow_tbl_term_mac(rocker_port, trans, + err = rocker_flow_tbl_term_mac(rocker_port, trans_ph, rocker_port->pport, in_pport_mask, eth_type, rocker_port->dev->dev_addr, dst_mac_mask, vlan_id, vlan_id_mask, @@ -3776,7 +3776,7 @@ static int rocker_port_router_mac(struct rocker_port *rocker_port, } static int rocker_port_fwding(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags) + enum switchdev_trans_ph trans_ph, int flags) { bool pop_vlan; u32 out_pport; @@ -3801,7 +3801,7 @@ static int rocker_port_fwding(struct rocker_port *rocker_port, continue; vlan_id = htons(vid); pop_vlan = rocker_vlan_id_is_internal(vlan_id); - err = rocker_group_l2_interface(rocker_port, trans, flags, + err = rocker_group_l2_interface(rocker_port, trans_ph, flags, vlan_id, out_pport, pop_vlan); if (err) { netdev_err(rocker_port->dev, @@ -3815,7 +3815,7 @@ static int rocker_port_fwding(struct rocker_port *rocker_port, } static int rocker_port_stp_update(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + enum switchdev_trans_ph trans_ph, int flags, u8 state) { bool want[ROCKER_CTRL_MAX] = { 0, }; @@ -3824,7 +3824,7 @@ static int rocker_port_stp_update(struct rocker_port *rocker_port, int err; int i; - if (trans == SWITCHDEV_TRANS_PREPARE) { + if (trans_ph == SWITCHDEV_TRANS_PREPARE) { memcpy(prev_ctrls, rocker_port->ctrls, sizeof(prev_ctrls)); prev_state = rocker_port->stp_state; } @@ -3861,7 +3861,7 @@ static int rocker_port_stp_update(struct rocker_port *rocker_port, if (want[i] != rocker_port->ctrls[i]) { int ctrl_flags = flags | (want[i] ? 0 : ROCKER_OP_FLAG_REMOVE); - err = rocker_port_ctrl(rocker_port, trans, ctrl_flags, + err = rocker_port_ctrl(rocker_port, trans_ph, ctrl_flags, &rocker_ctrls[i]); if (err) goto err_out; @@ -3869,14 +3869,14 @@ static int rocker_port_stp_update(struct rocker_port *rocker_port, } } - err = rocker_port_fdb_flush(rocker_port, trans, flags); + err = rocker_port_fdb_flush(rocker_port, trans_ph, flags); if (err) goto err_out; - err = rocker_port_fwding(rocker_port, trans, flags); + err = rocker_port_fwding(rocker_port, trans_ph, flags); err_out: - if (trans == SWITCHDEV_TRANS_PREPARE) { + if (trans_ph == SWITCHDEV_TRANS_PREPARE) { memcpy(rocker_port->ctrls, prev_ctrls, sizeof(prev_ctrls)); rocker_port->stp_state = prev_state; } @@ -3885,26 +3885,26 @@ err_out: } static int rocker_port_fwd_enable(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags) + enum switchdev_trans_ph trans_ph, int flags) { if (rocker_port_is_bridged(rocker_port)) /* bridge STP will enable port */ return 0; /* port is not bridged, so simulate going to FORWARDING state */ - return rocker_port_stp_update(rocker_port, trans, flags, + return rocker_port_stp_update(rocker_port, trans_ph, flags, BR_STATE_FORWARDING); } static int rocker_port_fwd_disable(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags) + enum switchdev_trans_ph trans_ph, int flags) { if (rocker_port_is_bridged(rocker_port)) /* bridge STP will disable port */ return 0; /* port is not bridged, so simulate going to DISABLED state */ - return rocker_port_stp_update(rocker_port, trans, flags, + return rocker_port_stp_update(rocker_port, trans_ph, flags, BR_STATE_DISABLED); } @@ -3995,7 +3995,7 @@ not_found: } static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, - enum switchdev_trans trans, __be32 dst, + enum switchdev_trans_ph trans_ph, __be32 dst, int dst_len, const struct fib_info *fi, u32 tb_id, int flags) { @@ -4019,7 +4019,7 @@ static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, has_gw = !!nh->nh_gw; if (has_gw && nh_on_port) { - err = rocker_port_ipv4_nh(rocker_port, trans, flags, + err = rocker_port_ipv4_nh(rocker_port, trans_ph, flags, nh->nh_gw, &index); if (err) return err; @@ -4030,7 +4030,7 @@ static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, group_id = ROCKER_GROUP_L2_INTERFACE(internal_vlan_id, 0); } - err = rocker_flow_tbl_ucast4_routing(rocker_port, trans, eth_type, dst, + err = rocker_flow_tbl_ucast4_routing(rocker_port, trans_ph, eth_type, dst, dst_mask, priority, goto_tbl, group_id, flags); if (err) @@ -4365,7 +4365,7 @@ static void rocker_port_trans_abort(const struct rocker_port *rocker_port) } static int rocker_port_brport_flags_set(struct rocker_port *rocker_port, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, unsigned long brport_flags) { unsigned long orig_flags; @@ -4374,9 +4374,9 @@ static int rocker_port_brport_flags_set(struct rocker_port *rocker_port, orig_flags = rocker_port->brport_flags; rocker_port->brport_flags = brport_flags; if ((orig_flags ^ rocker_port->brport_flags) & BR_LEARNING) - err = rocker_port_set_learning(rocker_port, trans); + err = rocker_port_set_learning(rocker_port, trans_ph); - if (trans == SWITCHDEV_TRANS_PREPARE) + if (trans_ph == SWITCHDEV_TRANS_PREPARE) rocker_port->brport_flags = orig_flags; return err; @@ -4388,7 +4388,7 @@ static int rocker_port_attr_set(struct net_device *dev, struct rocker_port *rocker_port = netdev_priv(dev); int err = 0; - switch (attr->trans) { + switch (attr->trans_ph) { case SWITCHDEV_TRANS_PREPARE: BUG_ON(!list_empty(&rocker_port->trans_mem)); break; @@ -4401,12 +4401,12 @@ static int rocker_port_attr_set(struct net_device *dev, switch (attr->id) { case SWITCHDEV_ATTR_PORT_STP_STATE: - err = rocker_port_stp_update(rocker_port, attr->trans, + err = rocker_port_stp_update(rocker_port, attr->trans_ph, ROCKER_OP_FLAG_NOWAIT, attr->u.stp_state); break; case SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS: - err = rocker_port_brport_flags_set(rocker_port, attr->trans, + err = rocker_port_brport_flags_set(rocker_port, attr->trans_ph, attr->u.brport_flags); break; default: @@ -4418,33 +4418,33 @@ static int rocker_port_attr_set(struct net_device *dev, } static int rocker_port_vlan_add(struct rocker_port *rocker_port, - enum switchdev_trans trans, u16 vid, u16 flags) + enum switchdev_trans_ph trans_ph, u16 vid, u16 flags) { int err; /* XXX deal with flags for PVID and untagged */ - err = rocker_port_vlan(rocker_port, trans, 0, vid); + err = rocker_port_vlan(rocker_port, trans_ph, 0, vid); if (err) return err; - err = rocker_port_router_mac(rocker_port, trans, 0, htons(vid)); + err = rocker_port_router_mac(rocker_port, trans_ph, 0, htons(vid)); if (err) - rocker_port_vlan(rocker_port, trans, + rocker_port_vlan(rocker_port, trans_ph, ROCKER_OP_FLAG_REMOVE, vid); return err; } static int rocker_port_vlans_add(struct rocker_port *rocker_port, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, const struct switchdev_obj_vlan *vlan) { u16 vid; int err; for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { - err = rocker_port_vlan_add(rocker_port, trans, + err = rocker_port_vlan_add(rocker_port, trans_ph, vid, vlan->flags); if (err) return err; @@ -4454,7 +4454,7 @@ static int rocker_port_vlans_add(struct rocker_port *rocker_port, } static int rocker_port_fdb_add(struct rocker_port *rocker_port, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, const struct switchdev_obj_fdb *fdb) { __be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, fdb->vid, NULL); @@ -4463,7 +4463,7 @@ static int rocker_port_fdb_add(struct rocker_port *rocker_port, if (!rocker_port_is_bridged(rocker_port)) return -EINVAL; - return rocker_port_fdb(rocker_port, trans, fdb->addr, vlan_id, flags); + return rocker_port_fdb(rocker_port, trans_ph, fdb->addr, vlan_id, flags); } static int rocker_port_obj_add(struct net_device *dev, @@ -4473,7 +4473,7 @@ static int rocker_port_obj_add(struct net_device *dev, const struct switchdev_obj_ipv4_fib *fib4; int err = 0; - switch (obj->trans) { + switch (obj->trans_ph) { case SWITCHDEV_TRANS_PREPARE: BUG_ON(!list_empty(&rocker_port->trans_mem)); break; @@ -4486,17 +4486,17 @@ static int rocker_port_obj_add(struct net_device *dev, switch (obj->id) { case SWITCHDEV_OBJ_PORT_VLAN: - err = rocker_port_vlans_add(rocker_port, obj->trans, + err = rocker_port_vlans_add(rocker_port, obj->trans_ph, &obj->u.vlan); break; case SWITCHDEV_OBJ_IPV4_FIB: fib4 = &obj->u.ipv4_fib; - err = rocker_port_fib_ipv4(rocker_port, obj->trans, + err = rocker_port_fib_ipv4(rocker_port, obj->trans_ph, htonl(fib4->dst), fib4->dst_len, fib4->fi, fib4->tb_id, 0); break; case SWITCHDEV_OBJ_PORT_FDB: - err = rocker_port_fdb_add(rocker_port, obj->trans, &obj->u.fdb); + err = rocker_port_fdb_add(rocker_port, obj->trans_ph, &obj->u.fdb); break; default: err = -EOPNOTSUPP; @@ -4536,7 +4536,7 @@ static int rocker_port_vlans_del(struct rocker_port *rocker_port, } static int rocker_port_fdb_del(struct rocker_port *rocker_port, - enum switchdev_trans trans, + enum switchdev_trans_ph trans_ph, const struct switchdev_obj_fdb *fdb) { __be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, fdb->vid, NULL); @@ -4545,7 +4545,7 @@ static int rocker_port_fdb_del(struct rocker_port *rocker_port, if (!rocker_port_is_bridged(rocker_port)) return -EINVAL; - return rocker_port_fdb(rocker_port, trans, fdb->addr, vlan_id, flags); + return rocker_port_fdb(rocker_port, trans_ph, fdb->addr, vlan_id, flags); } static int rocker_port_obj_del(struct net_device *dev, @@ -4567,7 +4567,7 @@ static int rocker_port_obj_del(struct net_device *dev, ROCKER_OP_FLAG_REMOVE); break; case SWITCHDEV_OBJ_PORT_FDB: - err = rocker_port_fdb_del(rocker_port, obj->trans, &obj->u.fdb); + err = rocker_port_fdb_del(rocker_port, obj->trans_ph, &obj->u.fdb); break; default: err = -EOPNOTSUPP; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 319baab3b48e..494f51097dc6 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -16,7 +16,7 @@ #define SWITCHDEV_F_NO_RECURSE BIT(0) -enum switchdev_trans { +enum switchdev_trans_ph { SWITCHDEV_TRANS_NONE, SWITCHDEV_TRANS_PREPARE, SWITCHDEV_TRANS_ABORT, @@ -32,7 +32,7 @@ enum switchdev_attr_id { struct switchdev_attr { enum switchdev_attr_id id; - enum switchdev_trans trans; + enum switchdev_trans_ph trans_ph; u32 flags; union { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ @@ -52,7 +52,7 @@ enum switchdev_obj_id { struct switchdev_obj { enum switchdev_obj_id id; - enum switchdev_trans trans; + enum switchdev_trans_ph trans_ph; int (*cb)(struct net_device *dev, struct switchdev_obj *obj); union { struct switchdev_obj_vlan { /* PORT_VLAN */ diff --git a/net/dsa/slave.c b/net/dsa/slave.c index cce97385f743..7f50b7443402 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -250,7 +250,7 @@ static int dsa_slave_port_vlan_add(struct net_device *dev, u16 vid; int err; - switch (obj->trans) { + switch (obj->trans_ph) { case SWITCHDEV_TRANS_PREPARE: if (!ds->drv->port_vlan_add || !ds->drv->port_pvid_set) return -EOPNOTSUPP; @@ -354,9 +354,9 @@ static int dsa_slave_port_fdb_add(struct net_device *dev, struct dsa_switch *ds = p->parent; int ret = -EOPNOTSUPP; - if (obj->trans == SWITCHDEV_TRANS_PREPARE) + if (obj->trans_ph == SWITCHDEV_TRANS_PREPARE) ret = ds->drv->port_fdb_add ? 0 : -EOPNOTSUPP; - else if (obj->trans == SWITCHDEV_TRANS_COMMIT) + else if (obj->trans_ph == SWITCHDEV_TRANS_COMMIT) ret = ds->drv->port_fdb_add(ds, p->port, fdb->addr, fdb->vid); return ret; @@ -462,7 +462,7 @@ static int dsa_slave_port_attr_set(struct net_device *dev, switch (attr->id) { case SWITCHDEV_ATTR_PORT_STP_STATE: - if (attr->trans == SWITCHDEV_TRANS_COMMIT) + if (attr->trans_ph == SWITCHDEV_TRANS_COMMIT) ret = dsa_slave_stp_update(dev, attr->u.stp_state); break; default: diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index fda38f830a10..df5a5446ff4c 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -163,7 +163,7 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) * but should not commit the attr. */ - attr->trans = SWITCHDEV_TRANS_PREPARE; + attr->trans_ph = SWITCHDEV_TRANS_PREPARE; err = __switchdev_port_attr_set(dev, attr); if (err) { /* Prepare phase failed: abort the transaction. Any @@ -172,7 +172,7 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) */ if (err != -EOPNOTSUPP) { - attr->trans = SWITCHDEV_TRANS_ABORT; + attr->trans_ph = SWITCHDEV_TRANS_ABORT; __switchdev_port_attr_set(dev, attr); } @@ -184,7 +184,7 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) * because the driver said everythings was OK in phase I. */ - attr->trans = SWITCHDEV_TRANS_COMMIT; + attr->trans_ph = SWITCHDEV_TRANS_COMMIT; err = __switchdev_port_attr_set(dev, attr); WARN(err, "%s: Commit of attribute (id=%d) failed.\n", dev->name, attr->id); @@ -243,7 +243,7 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) * but should not commit the obj. */ - obj->trans = SWITCHDEV_TRANS_PREPARE; + obj->trans_ph = SWITCHDEV_TRANS_PREPARE; err = __switchdev_port_obj_add(dev, obj); if (err) { /* Prepare phase failed: abort the transaction. Any @@ -252,7 +252,7 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) */ if (err != -EOPNOTSUPP) { - obj->trans = SWITCHDEV_TRANS_ABORT; + obj->trans_ph = SWITCHDEV_TRANS_ABORT; __switchdev_port_obj_add(dev, obj); } @@ -264,7 +264,7 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) * because the driver said everythings was OK in phase I. */ - obj->trans = SWITCHDEV_TRANS_COMMIT; + obj->trans_ph = SWITCHDEV_TRANS_COMMIT; err = __switchdev_port_obj_add(dev, obj); WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); -- cgit v1.2.3 From 7ea6eb3f56f45cf4babae8b9a7421868e5005f17 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:41 +0200 Subject: switchdev: introduce transaction item queue for attr_set and obj_add Now, the memory allocation in prepare/commit state is done separatelly in each driver (rocker). Introduce the similar mechanism in generic switchdev code, in form of queue. That can be used not only for memory allocations, but also for different items. Abort item destruction is handled as well. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/switchdev.txt | 19 ++++++ drivers/net/ethernet/rocker/rocker.c | 6 +- include/net/switchdev.h | 24 ++++++- net/dsa/slave.c | 6 +- net/switchdev/switchdev.c | 111 +++++++++++++++++++++++++++++---- 5 files changed, 146 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 67e43ee7840a..9f9e2587b347 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -369,3 +369,22 @@ The driver can monitor for updates to arp_tbl using the netevent notifier NETEVENT_NEIGH_UPDATE. The device can be programmed with resolved nexthops for the routes as arp_tbl updates. The driver implements ndo_neigh_destroy to know when arp_tbl neighbor entries are purged from the port. + +Transaction item queue +^^^^^^^^^^^^^^^^^^^^^^ + +For switchdev ops attr_set and obj_add, there is a 2 phase transaction model +used. First phase is to "prepare" anything needed, including various checks, +memory allocation, etc. The goal is to handle the stuff that is not unlikely +to fail here. The second phase is to "commit" the actual changes. + +Switchdev provides an inftrastructure for sharing items (for example memory +allocations) between the two phases. + +The object created by a driver in "prepare" phase and it is queued up by: +switchdev_trans_item_enqueue() +During the "commit" phase, the driver gets the object by: +switchdev_trans_item_dequeue() + +If a transaction is aborted during "prepare" phase, switchdev code will handle +cleanup of the queued-up objects. diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index cf03b077311e..dcc6f3fd13c9 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4383,7 +4383,8 @@ static int rocker_port_brport_flags_set(struct rocker_port *rocker_port, } static int rocker_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr) + struct switchdev_attr *attr, + struct switchdev_trans *trans) { struct rocker_port *rocker_port = netdev_priv(dev); int err = 0; @@ -4467,7 +4468,8 @@ static int rocker_port_fdb_add(struct rocker_port *rocker_port, } static int rocker_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj) + struct switchdev_obj *obj, + struct switchdev_trans *trans) { struct rocker_port *rocker_port = netdev_priv(dev); const struct switchdev_obj_ipv4_fib *fib4; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 494f51097dc6..1e394f1176b6 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -1,6 +1,6 @@ /* * include/net/switchdev.h - Switch device API - * Copyright (c) 2014 Jiri Pirko + * Copyright (c) 2014-2015 Jiri Pirko * Copyright (c) 2014-2015 Scott Feldman * * This program is free software; you can redistribute it and/or modify @@ -13,6 +13,7 @@ #include #include +#include #define SWITCHDEV_F_NO_RECURSE BIT(0) @@ -23,6 +24,16 @@ enum switchdev_trans_ph { SWITCHDEV_TRANS_COMMIT, }; +struct switchdev_trans_item { + struct list_head list; + void *data; + void (*destructor)(const void *data); +}; + +struct switchdev_trans { + struct list_head item_list; +}; + enum switchdev_attr_id { SWITCHDEV_ATTR_UNDEFINED, SWITCHDEV_ATTR_PORT_PARENT_ID, @@ -77,6 +88,11 @@ struct switchdev_obj { } u; }; +void switchdev_trans_item_enqueue(struct switchdev_trans *trans, + void *data, void (*destructor)(void const *), + struct switchdev_trans_item *tritem); +void *switchdev_trans_item_dequeue(struct switchdev_trans *trans); + /** * struct switchdev_ops - switchdev operations * @@ -94,9 +110,11 @@ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, struct switchdev_attr *attr); int (*switchdev_port_attr_set)(struct net_device *dev, - struct switchdev_attr *attr); + struct switchdev_attr *attr, + struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, - struct switchdev_obj *obj); + struct switchdev_obj *obj, + struct switchdev_trans *trans); int (*switchdev_port_obj_del)(struct net_device *dev, struct switchdev_obj *obj); int (*switchdev_port_obj_dump)(struct net_device *dev, diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 7f50b7443402..ac76fd15ad8b 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -456,7 +456,8 @@ static int dsa_slave_stp_update(struct net_device *dev, u8 state) } static int dsa_slave_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr) + struct switchdev_attr *attr, + struct switchdev_trans *trans) { int ret = 0; @@ -474,7 +475,8 @@ static int dsa_slave_port_attr_set(struct net_device *dev, } static int dsa_slave_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj) + struct switchdev_obj *obj, + struct switchdev_trans *trans) { int err; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index df5a5446ff4c..35e2967ffa18 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -1,6 +1,6 @@ /* * net/switchdev/switchdev.c - Switch device API - * Copyright (c) 2014 Jiri Pirko + * Copyright (c) 2014-2015 Jiri Pirko * Copyright (c) 2014-2015 Scott Feldman * * This program is free software; you can redistribute it and/or modify @@ -16,9 +16,82 @@ #include #include #include +#include #include #include +/** + * switchdev_trans_item_enqueue - Enqueue data item to transaction queue + * + * @trans: transaction + * @data: pointer to data being queued + * @destructor: data destructor + * @tritem: transaction item being queued + * + * Enqeueue data item to transaction queue. tritem is typically placed in + * cointainter pointed at by data pointer. Destructor is called on + * transaction abort and after successful commit phase in case + * the caller did not dequeue the item before. + */ +void switchdev_trans_item_enqueue(struct switchdev_trans *trans, + void *data, void (*destructor)(void const *), + struct switchdev_trans_item *tritem) +{ + tritem->data = data; + tritem->destructor = destructor; + list_add_tail(&tritem->list, &trans->item_list); +} +EXPORT_SYMBOL_GPL(switchdev_trans_item_enqueue); + +static struct switchdev_trans_item * +__switchdev_trans_item_dequeue(struct switchdev_trans *trans) +{ + struct switchdev_trans_item *tritem; + + if (list_empty(&trans->item_list)) + return NULL; + tritem = list_first_entry(&trans->item_list, + struct switchdev_trans_item, list); + list_del(&tritem->list); + return tritem; +} + +/** + * switchdev_trans_item_dequeue - Dequeue data item from transaction queue + * + * @trans: transaction + */ +void *switchdev_trans_item_dequeue(struct switchdev_trans *trans) +{ + struct switchdev_trans_item *tritem; + + tritem = __switchdev_trans_item_dequeue(trans); + BUG_ON(!tritem); + return tritem->data; +} +EXPORT_SYMBOL_GPL(switchdev_trans_item_dequeue); + +static void switchdev_trans_init(struct switchdev_trans *trans) +{ + INIT_LIST_HEAD(&trans->item_list); +} + +static void switchdev_trans_items_destroy(struct switchdev_trans *trans) +{ + struct switchdev_trans_item *tritem; + + while ((tritem = __switchdev_trans_item_dequeue(trans))) + tritem->destructor(tritem->data); +} + +static void switchdev_trans_items_warn_destroy(struct net_device *dev, + struct switchdev_trans *trans) +{ + WARN(!list_empty(&trans->item_list), "%s: transaction item queue is not empty.\n", + dev->name); + switchdev_trans_items_destroy(trans); +} + /** * switchdev_port_attr_get - Get port attribute * @@ -62,7 +135,8 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) EXPORT_SYMBOL_GPL(switchdev_port_attr_get); static int __switchdev_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr) + struct switchdev_attr *attr, + struct switchdev_trans *trans) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; @@ -70,7 +144,7 @@ static int __switchdev_port_attr_set(struct net_device *dev, int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_attr_set) - return ops->switchdev_port_attr_set(dev, attr); + return ops->switchdev_port_attr_set(dev, attr, trans); if (attr->flags & SWITCHDEV_F_NO_RECURSE) return err; @@ -81,7 +155,7 @@ static int __switchdev_port_attr_set(struct net_device *dev, */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = __switchdev_port_attr_set(lower_dev, attr); + err = __switchdev_port_attr_set(lower_dev, attr, trans); if (err) break; } @@ -144,6 +218,7 @@ static int switchdev_port_attr_set_defer(struct net_device *dev, */ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) { + struct switchdev_trans trans; int err; if (!rtnl_is_locked()) { @@ -156,6 +231,8 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) return switchdev_port_attr_set_defer(dev, attr); } + switchdev_trans_init(&trans); + /* Phase I: prepare for attr set. Driver/device should fail * here if there are going to be issues in the commit phase, * such as lack of resources or support. The driver/device @@ -164,7 +241,7 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) */ attr->trans_ph = SWITCHDEV_TRANS_PREPARE; - err = __switchdev_port_attr_set(dev, attr); + err = __switchdev_port_attr_set(dev, attr, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any * resources reserved in the prepare phase are @@ -173,7 +250,8 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) if (err != -EOPNOTSUPP) { attr->trans_ph = SWITCHDEV_TRANS_ABORT; - __switchdev_port_attr_set(dev, attr); + __switchdev_port_attr_set(dev, attr, &trans); + switchdev_trans_items_destroy(&trans); } return err; @@ -185,16 +263,18 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) */ attr->trans_ph = SWITCHDEV_TRANS_COMMIT; - err = __switchdev_port_attr_set(dev, attr); + err = __switchdev_port_attr_set(dev, attr, &trans); WARN(err, "%s: Commit of attribute (id=%d) failed.\n", dev->name, attr->id); + switchdev_trans_items_warn_destroy(dev, &trans); return err; } EXPORT_SYMBOL_GPL(switchdev_port_attr_set); static int __switchdev_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj) + struct switchdev_obj *obj, + struct switchdev_trans *trans) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; @@ -202,7 +282,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_add) - return ops->switchdev_port_obj_add(dev, obj); + return ops->switchdev_port_obj_add(dev, obj, trans); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to add object on @@ -210,7 +290,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = __switchdev_port_obj_add(lower_dev, obj); + err = __switchdev_port_obj_add(lower_dev, obj, trans); if (err) break; } @@ -232,10 +312,13 @@ static int __switchdev_port_obj_add(struct net_device *dev, */ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) { + struct switchdev_trans trans; int err; ASSERT_RTNL(); + switchdev_trans_init(&trans); + /* Phase I: prepare for obj add. Driver/device should fail * here if there are going to be issues in the commit phase, * such as lack of resources or support. The driver/device @@ -244,7 +327,7 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) */ obj->trans_ph = SWITCHDEV_TRANS_PREPARE; - err = __switchdev_port_obj_add(dev, obj); + err = __switchdev_port_obj_add(dev, obj, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any * resources reserved in the prepare phase are @@ -253,7 +336,8 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) if (err != -EOPNOTSUPP) { obj->trans_ph = SWITCHDEV_TRANS_ABORT; - __switchdev_port_obj_add(dev, obj); + __switchdev_port_obj_add(dev, obj, &trans); + switchdev_trans_items_destroy(&trans); } return err; @@ -265,8 +349,9 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) */ obj->trans_ph = SWITCHDEV_TRANS_COMMIT; - err = __switchdev_port_obj_add(dev, obj); + err = __switchdev_port_obj_add(dev, obj, &trans); WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); + switchdev_trans_items_warn_destroy(dev, &trans); return err; } -- cgit v1.2.3 From f8db83486e316ff50f97961a82b614985645508e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:42 +0200 Subject: switchdev: move transaction phase enum under transaction structure Before it disappears completely, move transaction phase enum under transaction structure and make attr/obj structures a bit cleaner. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 17 +++++++++-------- include/net/switchdev.h | 3 +-- net/dsa/slave.c | 18 ++++++++++-------- net/switchdev/switchdev.c | 12 ++++++------ 4 files changed, 26 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index dcc6f3fd13c9..c348f86d9b8d 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4389,7 +4389,7 @@ static int rocker_port_attr_set(struct net_device *dev, struct rocker_port *rocker_port = netdev_priv(dev); int err = 0; - switch (attr->trans_ph) { + switch (trans->ph) { case SWITCHDEV_TRANS_PREPARE: BUG_ON(!list_empty(&rocker_port->trans_mem)); break; @@ -4402,12 +4402,12 @@ static int rocker_port_attr_set(struct net_device *dev, switch (attr->id) { case SWITCHDEV_ATTR_PORT_STP_STATE: - err = rocker_port_stp_update(rocker_port, attr->trans_ph, + err = rocker_port_stp_update(rocker_port, trans->ph, ROCKER_OP_FLAG_NOWAIT, attr->u.stp_state); break; case SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS: - err = rocker_port_brport_flags_set(rocker_port, attr->trans_ph, + err = rocker_port_brport_flags_set(rocker_port, trans->ph, attr->u.brport_flags); break; default: @@ -4475,7 +4475,7 @@ static int rocker_port_obj_add(struct net_device *dev, const struct switchdev_obj_ipv4_fib *fib4; int err = 0; - switch (obj->trans_ph) { + switch (trans->ph) { case SWITCHDEV_TRANS_PREPARE: BUG_ON(!list_empty(&rocker_port->trans_mem)); break; @@ -4488,17 +4488,17 @@ static int rocker_port_obj_add(struct net_device *dev, switch (obj->id) { case SWITCHDEV_OBJ_PORT_VLAN: - err = rocker_port_vlans_add(rocker_port, obj->trans_ph, + err = rocker_port_vlans_add(rocker_port, trans->ph, &obj->u.vlan); break; case SWITCHDEV_OBJ_IPV4_FIB: fib4 = &obj->u.ipv4_fib; - err = rocker_port_fib_ipv4(rocker_port, obj->trans_ph, + err = rocker_port_fib_ipv4(rocker_port, trans->ph, htonl(fib4->dst), fib4->dst_len, fib4->fi, fib4->tb_id, 0); break; case SWITCHDEV_OBJ_PORT_FDB: - err = rocker_port_fdb_add(rocker_port, obj->trans_ph, &obj->u.fdb); + err = rocker_port_fdb_add(rocker_port, trans->ph, &obj->u.fdb); break; default: err = -EOPNOTSUPP; @@ -4569,7 +4569,8 @@ static int rocker_port_obj_del(struct net_device *dev, ROCKER_OP_FLAG_REMOVE); break; case SWITCHDEV_OBJ_PORT_FDB: - err = rocker_port_fdb_del(rocker_port, obj->trans_ph, &obj->u.fdb); + err = rocker_port_fdb_del(rocker_port, SWITCHDEV_TRANS_NONE, + &obj->u.fdb); break; default: err = -EOPNOTSUPP; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 1e394f1176b6..368a6429198d 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -32,6 +32,7 @@ struct switchdev_trans_item { struct switchdev_trans { struct list_head item_list; + enum switchdev_trans_ph ph; }; enum switchdev_attr_id { @@ -43,7 +44,6 @@ enum switchdev_attr_id { struct switchdev_attr { enum switchdev_attr_id id; - enum switchdev_trans_ph trans_ph; u32 flags; union { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ @@ -63,7 +63,6 @@ enum switchdev_obj_id { struct switchdev_obj { enum switchdev_obj_id id; - enum switchdev_trans_ph trans_ph; int (*cb)(struct net_device *dev, struct switchdev_obj *obj); union { struct switchdev_obj_vlan { /* PORT_VLAN */ diff --git a/net/dsa/slave.c b/net/dsa/slave.c index ac76fd15ad8b..748cc6394bbb 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -242,7 +242,8 @@ static int dsa_bridge_check_vlan_range(struct dsa_switch *ds, } static int dsa_slave_port_vlan_add(struct net_device *dev, - struct switchdev_obj *obj) + struct switchdev_obj *obj, + struct switchdev_trans *trans) { struct switchdev_obj_vlan *vlan = &obj->u.vlan; struct dsa_slave_priv *p = netdev_priv(dev); @@ -250,7 +251,7 @@ static int dsa_slave_port_vlan_add(struct net_device *dev, u16 vid; int err; - switch (obj->trans_ph) { + switch (trans->ph) { case SWITCHDEV_TRANS_PREPARE: if (!ds->drv->port_vlan_add || !ds->drv->port_pvid_set) return -EOPNOTSUPP; @@ -347,16 +348,17 @@ static int dsa_slave_port_vlan_dump(struct net_device *dev, } static int dsa_slave_port_fdb_add(struct net_device *dev, - struct switchdev_obj *obj) + struct switchdev_obj *obj, + struct switchdev_trans *trans) { struct switchdev_obj_fdb *fdb = &obj->u.fdb; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; int ret = -EOPNOTSUPP; - if (obj->trans_ph == SWITCHDEV_TRANS_PREPARE) + if (trans->ph == SWITCHDEV_TRANS_PREPARE) ret = ds->drv->port_fdb_add ? 0 : -EOPNOTSUPP; - else if (obj->trans_ph == SWITCHDEV_TRANS_COMMIT) + else if (trans->ph == SWITCHDEV_TRANS_COMMIT) ret = ds->drv->port_fdb_add(ds, p->port, fdb->addr, fdb->vid); return ret; @@ -463,7 +465,7 @@ static int dsa_slave_port_attr_set(struct net_device *dev, switch (attr->id) { case SWITCHDEV_ATTR_PORT_STP_STATE: - if (attr->trans_ph == SWITCHDEV_TRANS_COMMIT) + if (trans->ph == SWITCHDEV_TRANS_COMMIT) ret = dsa_slave_stp_update(dev, attr->u.stp_state); break; default: @@ -487,10 +489,10 @@ static int dsa_slave_port_obj_add(struct net_device *dev, switch (obj->id) { case SWITCHDEV_OBJ_PORT_FDB: - err = dsa_slave_port_fdb_add(dev, obj); + err = dsa_slave_port_fdb_add(dev, obj, trans); break; case SWITCHDEV_OBJ_PORT_VLAN: - err = dsa_slave_port_vlan_add(dev, obj); + err = dsa_slave_port_vlan_add(dev, obj, trans); break; default: err = -EOPNOTSUPP; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 35e2967ffa18..d1c7d51620b1 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -240,7 +240,7 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) * but should not commit the attr. */ - attr->trans_ph = SWITCHDEV_TRANS_PREPARE; + trans.ph = SWITCHDEV_TRANS_PREPARE; err = __switchdev_port_attr_set(dev, attr, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any @@ -249,7 +249,7 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) */ if (err != -EOPNOTSUPP) { - attr->trans_ph = SWITCHDEV_TRANS_ABORT; + trans.ph = SWITCHDEV_TRANS_ABORT; __switchdev_port_attr_set(dev, attr, &trans); switchdev_trans_items_destroy(&trans); } @@ -262,7 +262,7 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) * because the driver said everythings was OK in phase I. */ - attr->trans_ph = SWITCHDEV_TRANS_COMMIT; + trans.ph = SWITCHDEV_TRANS_COMMIT; err = __switchdev_port_attr_set(dev, attr, &trans); WARN(err, "%s: Commit of attribute (id=%d) failed.\n", dev->name, attr->id); @@ -326,7 +326,7 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) * but should not commit the obj. */ - obj->trans_ph = SWITCHDEV_TRANS_PREPARE; + trans.ph = SWITCHDEV_TRANS_PREPARE; err = __switchdev_port_obj_add(dev, obj, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any @@ -335,7 +335,7 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) */ if (err != -EOPNOTSUPP) { - obj->trans_ph = SWITCHDEV_TRANS_ABORT; + trans.ph = SWITCHDEV_TRANS_ABORT; __switchdev_port_obj_add(dev, obj, &trans); switchdev_trans_items_destroy(&trans); } @@ -348,7 +348,7 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) * because the driver said everythings was OK in phase I. */ - obj->trans_ph = SWITCHDEV_TRANS_COMMIT; + trans.ph = SWITCHDEV_TRANS_COMMIT; err = __switchdev_port_obj_add(dev, obj, &trans); WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); switchdev_trans_items_warn_destroy(dev, &trans); -- cgit v1.2.3 From 8bdb427206f077cdb567bf34da2e7212ecb2603c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:43 +0200 Subject: switchdev: add switchdev_trans_ph_prepare/commit helpers Add helpers which should be used int attr_set/obj_add switchdev ops to check the phase of transaction. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 368a6429198d..f84ecf4e5d77 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -35,6 +35,16 @@ struct switchdev_trans { enum switchdev_trans_ph ph; }; +static inline bool switchdev_trans_ph_prepare(struct switchdev_trans *trans) +{ + return trans && trans->ph == SWITCHDEV_TRANS_PREPARE; +} + +static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans) +{ + return trans && trans->ph == SWITCHDEV_TRANS_COMMIT; +} + enum switchdev_attr_id { SWITCHDEV_ATTR_UNDEFINED, SWITCHDEV_ATTR_PORT_PARENT_ID, -- cgit v1.2.3 From 2b8a61a6fd5fdd161ae16e4f76bfb09d6de95ddd Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:46 +0200 Subject: switchdev: remove "NONE" transaction phase Shouldn't have been there in the first place. Now it is unused, kill it. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index f84ecf4e5d77..f61ee38c7c96 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -18,7 +18,6 @@ #define SWITCHDEV_F_NO_RECURSE BIT(0) enum switchdev_trans_ph { - SWITCHDEV_TRANS_NONE, SWITCHDEV_TRANS_PREPARE, SWITCHDEV_TRANS_ABORT, SWITCHDEV_TRANS_COMMIT, -- cgit v1.2.3 From 9f6467cf229a0e8a7580401b07de2a76e4c8618d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:47 +0200 Subject: switchdev: remove "ABORT" transaction phase No longer used by drivers, as transaction queue with item destructors takes care of abort phase internally in switchdev code. So kill it. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 - net/switchdev/switchdev.c | 10 ++-------- 2 files changed, 2 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index f61ee38c7c96..9cf372fe1365 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -19,7 +19,6 @@ enum switchdev_trans_ph { SWITCHDEV_TRANS_PREPARE, - SWITCHDEV_TRANS_ABORT, SWITCHDEV_TRANS_COMMIT, }; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index d1c7d51620b1..1adeedade0fb 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -248,11 +248,8 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) * released. */ - if (err != -EOPNOTSUPP) { - trans.ph = SWITCHDEV_TRANS_ABORT; - __switchdev_port_attr_set(dev, attr, &trans); + if (err != -EOPNOTSUPP) switchdev_trans_items_destroy(&trans); - } return err; } @@ -334,11 +331,8 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) * released. */ - if (err != -EOPNOTSUPP) { - trans.ph = SWITCHDEV_TRANS_ABORT; - __switchdev_port_obj_add(dev, obj, &trans); + if (err != -EOPNOTSUPP) switchdev_trans_items_destroy(&trans); - } return err; } -- cgit v1.2.3 From f623ab7f51b1bfb523c9cd492747392abf3c4421 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:49 +0200 Subject: switchdev: reduce transaction phase enum down to a boolean Now, since we have only 2 values for transaction phase, just use bool. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 11 +++-------- net/switchdev/switchdev.c | 8 ++++---- 2 files changed, 7 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 9cf372fe1365..18207878e407 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -17,11 +17,6 @@ #define SWITCHDEV_F_NO_RECURSE BIT(0) -enum switchdev_trans_ph { - SWITCHDEV_TRANS_PREPARE, - SWITCHDEV_TRANS_COMMIT, -}; - struct switchdev_trans_item { struct list_head list; void *data; @@ -30,17 +25,17 @@ struct switchdev_trans_item { struct switchdev_trans { struct list_head item_list; - enum switchdev_trans_ph ph; + bool ph_prepare; }; static inline bool switchdev_trans_ph_prepare(struct switchdev_trans *trans) { - return trans && trans->ph == SWITCHDEV_TRANS_PREPARE; + return trans && trans->ph_prepare; } static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans) { - return trans && trans->ph == SWITCHDEV_TRANS_COMMIT; + return trans && !trans->ph_prepare; } enum switchdev_attr_id { diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 1adeedade0fb..00ee547ba45b 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -240,7 +240,7 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) * but should not commit the attr. */ - trans.ph = SWITCHDEV_TRANS_PREPARE; + trans.ph_prepare = true; err = __switchdev_port_attr_set(dev, attr, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any @@ -259,7 +259,7 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) * because the driver said everythings was OK in phase I. */ - trans.ph = SWITCHDEV_TRANS_COMMIT; + trans.ph_prepare = false; err = __switchdev_port_attr_set(dev, attr, &trans); WARN(err, "%s: Commit of attribute (id=%d) failed.\n", dev->name, attr->id); @@ -323,7 +323,7 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) * but should not commit the obj. */ - trans.ph = SWITCHDEV_TRANS_PREPARE; + trans.ph_prepare = true; err = __switchdev_port_obj_add(dev, obj, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any @@ -342,7 +342,7 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) * because the driver said everythings was OK in phase I. */ - trans.ph = SWITCHDEV_TRANS_COMMIT; + trans.ph_prepare = false; err = __switchdev_port_obj_add(dev, obj, &trans); WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); switchdev_trans_items_warn_destroy(dev, &trans); -- cgit v1.2.3 From 3e3aaf649416988ca8be4ad2c52dc24d8be7b46e Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 24 Sep 2015 20:36:02 +0100 Subject: phy: fix mdiobus module safety Re-implement the mdiobus module refcounting to ensure that we actually ensure that the mdiobus module code does not go away while we might call into it. The old scheme using bus->dev.driver was buggy, because bus->dev is a class device which never has a struct device_driver associated with it, and hence the associated code trying to obtain a refcount did nothing useful. Instead, take the approach that other subsystems do: pass the module when calling mdiobus_register(), and record that in the mii_bus struct. When we need to increment the module use count in the phy code, use this stored pointer. When the phy is deteched, drop the module refcount, remembering that the phy device might go away at that point. This doesn't stop the mii_bus going away while there are in-use phys - it merely stops the underlying code vanishing. Signed-off-by: Russell King Signed-off-by: David S. Miller --- drivers/net/phy/mdio_bus.c | 5 +++-- drivers/net/phy/phy_device.c | 32 ++++++++++++++++++-------------- include/linux/phy.h | 5 ++++- 3 files changed, 25 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 67553e13bd36..992406624b7c 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -244,7 +244,7 @@ static inline void of_mdiobus_link_phydev(struct mii_bus *mdio, * * Returns 0 on success or < 0 on error. */ -int mdiobus_register(struct mii_bus *bus) +int __mdiobus_register(struct mii_bus *bus, struct module *owner) { int i, err; @@ -255,6 +255,7 @@ int mdiobus_register(struct mii_bus *bus) BUG_ON(bus->state != MDIOBUS_ALLOCATED && bus->state != MDIOBUS_UNREGISTERED); + bus->owner = owner; bus->dev.parent = bus->parent; bus->dev.class = &mdio_bus_class; bus->dev.groups = NULL; @@ -296,7 +297,7 @@ error: device_del(&bus->dev); return err; } -EXPORT_SYMBOL(mdiobus_register); +EXPORT_SYMBOL(__mdiobus_register); void mdiobus_unregister(struct mii_bus *bus) { diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index c0f211127274..03adf328f49b 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -582,10 +582,15 @@ EXPORT_SYMBOL(phy_init_hw); int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, u32 flags, phy_interface_t interface) { + struct mii_bus *bus = phydev->bus; struct device *d = &phydev->dev; - struct module *bus_module; int err; + if (!try_module_get(bus->owner)) { + dev_err(&dev->dev, "failed to get the bus module\n"); + return -EIO; + } + /* Assume that if there is no driver, that it doesn't * exist, and we should use the genphy driver. */ @@ -600,20 +605,13 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, err = device_bind_driver(d); if (err) - return err; + goto error; } if (phydev->attached_dev) { dev_err(&dev->dev, "PHY already attached\n"); - return -EBUSY; - } - - /* Increment the bus module reference count */ - bus_module = phydev->bus->dev.driver ? - phydev->bus->dev.driver->owner : NULL; - if (!try_module_get(bus_module)) { - dev_err(&dev->dev, "failed to get the bus module\n"); - return -EIO; + err = -EBUSY; + goto error; } phydev->attached_dev = dev; @@ -636,6 +634,10 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, phy_resume(phydev); return err; + +error: + module_put(bus->owner); + return err; } EXPORT_SYMBOL(phy_attach_direct); @@ -680,11 +682,9 @@ EXPORT_SYMBOL(phy_attach); */ void phy_detach(struct phy_device *phydev) { + struct mii_bus *bus; int i; - if (phydev->bus->dev.driver) - module_put(phydev->bus->dev.driver->owner); - phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; phy_suspend(phydev); @@ -700,6 +700,10 @@ void phy_detach(struct phy_device *phydev) break; } } + + bus = phydev->bus; + + module_put(bus->owner); } EXPORT_SYMBOL(phy_detach); diff --git a/include/linux/phy.h b/include/linux/phy.h index 962387a192f1..11bce44f6d65 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -153,6 +154,7 @@ struct sk_buff; * PHYs should register using this structure */ struct mii_bus { + struct module *owner; const char *name; char id[MII_BUS_ID_SIZE]; void *priv; @@ -198,7 +200,8 @@ static inline struct mii_bus *mdiobus_alloc(void) return mdiobus_alloc_size(0); } -int mdiobus_register(struct mii_bus *bus); +int __mdiobus_register(struct mii_bus *bus, struct module *owner); +#define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); -- cgit v1.2.3 From 38737e490d4ea91660d3cec83ef88c4e6d360ae4 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 24 Sep 2015 20:36:28 +0100 Subject: phy: add phy_device_remove() Add a phy_device_remove() function to complement phy_device_register(), which undoes the effects of phy_device_register() by removing the phy device from visibility, but not freeing it. This allows these details to be moved out of the mdio bus code into the phy code where this action belongs. Signed-off-by: Russell King Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/gianfar.c | 5 +++-- drivers/net/phy/mdio_bus.c | 15 ++++++++++----- drivers/net/phy/phy_device.c | 18 ++++++++++++++++++ include/linux/phy.h | 1 + 4 files changed, 32 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index a5cf4332d307..710715fcb23d 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1702,7 +1702,6 @@ static void gfar_configure_serdes(struct net_device *dev) tbiphy = of_phy_find_device(priv->tbi_node); if (!tbiphy) { dev_err(&dev->dev, "error: Could not get TBI device\n"); - put_device(&tbiphy->dev); return; } @@ -1711,8 +1710,10 @@ static void gfar_configure_serdes(struct net_device *dev) * everything for us? Resetting it takes the link down and requires * several seconds for it to come back. */ - if (phy_read(tbiphy, MII_BMSR) & BMSR_LSTATUS) + if (phy_read(tbiphy, MII_BMSR) & BMSR_LSTATUS) { + put_device(&tbiphy->dev); return; + } /* Single clk mode, mii mode off(for serdes communication) */ phy_write(tbiphy, MII_TBICON, TBICON_CLK_SELECT); diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 992406624b7c..c340e412b38f 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -291,8 +291,11 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) error: while (--i >= 0) { - if (bus->phy_map[i]) - device_unregister(&bus->phy_map[i]->dev); + struct phy_device *phydev = bus->phy_map[i]; + if (phydev) { + phy_device_remove(phydev); + phy_device_free(phydev); + } } device_del(&bus->dev); return err; @@ -307,9 +310,11 @@ void mdiobus_unregister(struct mii_bus *bus) bus->state = MDIOBUS_UNREGISTERED; for (i = 0; i < PHY_MAX_ADDR; i++) { - if (bus->phy_map[i]) - device_unregister(&bus->phy_map[i]->dev); - bus->phy_map[i] = NULL; + struct phy_device *phydev = bus->phy_map[i]; + if (phydev) { + phy_device_remove(phydev); + phy_device_free(phydev); + } } device_del(&bus->dev); } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 97a4f52addac..f761288abe66 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -383,6 +383,24 @@ int phy_device_register(struct phy_device *phydev) } EXPORT_SYMBOL(phy_device_register); +/** + * phy_device_remove - Remove a previously registered phy device from the MDIO bus + * @phydev: phy_device structure to remove + * + * This doesn't free the phy_device itself, it merely reverses the effects + * of phy_device_register(). Use phy_device_free() to free the device + * after calling this function. + */ +void phy_device_remove(struct phy_device *phydev) +{ + struct mii_bus *bus = phydev->bus; + int addr = phydev->addr; + + device_del(&phydev->dev); + bus->phy_map[addr] = NULL; +} +EXPORT_SYMBOL(phy_device_remove); + /** * phy_find_first - finds the first PHY device on the bus * @bus: the target MII bus diff --git a/include/linux/phy.h b/include/linux/phy.h index 11bce44f6d65..4a4e3a092337 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -745,6 +745,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, struct phy_c45_device_ids *c45_ids); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); +void phy_device_remove(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); -- cgit v1.2.3 From eeeb9522231118138be418ff527dc8c9050f4707 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Tue, 15 Sep 2015 17:27:35 -0700 Subject: target: Propigate backend read-only to core_tpg_add_lun This patch adds a DF_READ_ONLY flag that is used by IBLOCK to signal when a backend has been set to read-only mode, in order to propigate read-only status up to core_tpg_add_lun() for all future LUN fabric exports. With this is place, existing emulation for reporting read-only in spc_emulate_modesense() and normal transport_lookup_cmd_lun() TCM_WRITE_PROTECTED status checking just works as expected. Reported-by: Joeue Deng Reported-by: Andy Grover Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_iblock.c | 2 ++ drivers/target/target_core_tpg.c | 5 ++++- include/target/target_core_base.h | 1 + 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 5a9982f5d5d6..0f19e11acac2 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -105,6 +105,8 @@ static int iblock_configure_device(struct se_device *dev) mode = FMODE_READ|FMODE_EXCL; if (!ib_dev->ibd_readonly) mode |= FMODE_WRITE; + else + dev->dev_flags |= DF_READ_ONLY; bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev); if (IS_ERR(bd)) { diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index 2d0381dd105c..5fb9dd7f08bb 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -668,7 +668,10 @@ int core_tpg_add_lun( list_add_tail(&lun->lun_dev_link, &dev->dev_sep_list); spin_unlock(&dev->se_port_lock); - lun->lun_access = lun_access; + if (dev->dev_flags & DF_READ_ONLY) + lun->lun_access = TRANSPORT_LUNFLAGS_READ_ONLY; + else + lun->lun_access = lun_access; if (!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) hlist_add_head_rcu(&lun->link, &tpg->tpg_lun_hlist); mutex_unlock(&tpg->tpg_lun_mutex); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index ac9bf1c0e42d..5f48754dc36a 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -730,6 +730,7 @@ struct se_device { #define DF_EMULATED_VPD_UNIT_SERIAL 0x00000004 #define DF_USING_UDEV_PATH 0x00000008 #define DF_USING_ALIAS 0x00000010 +#define DF_READ_ONLY 0x00000020 /* Physical device queue depth */ u32 queue_depth; /* Used for SPC-2 reservations enforce of ISIDs */ -- cgit v1.2.3 From c6790aa9f4fdc26b1246ba36da2fd749663beb65 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 24 Sep 2015 10:34:23 +0300 Subject: IB/mlx5: Remove support for IB_DEVICE_LOCAL_DMA_LKEY Commit 96249d70dd70 ("IB/core: Guarantee that a local_dma_lkey is available") allows ULPs that make use of the local dma key to keep working as before by allocating a DMA MR with local permissions and converted these consumers to use the MR associated with the PD rather then device->local_dma_lkey. ConnectIB has some known issues with memory registration using the local_dma_lkey (SEND, RDMA, RECV seems to work ok). Thus don't expose support for it (remove device->local_dma_lkey setting), and take advantage of the above commit such that no regression is introduced to working systems. The local_dma_lkey support will be restored in CX4 depending on FW capability query. Signed-off-by: Sagi Grimberg Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 10 +--------- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 22 ---------------------- include/linux/mlx5/device.h | 11 ----------- include/linux/mlx5/driver.h | 1 - 4 files changed, 1 insertion(+), 43 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 41d6911e244e..0ab9625911a1 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -245,7 +245,6 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, props->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR; if (MLX5_CAP_GEN(mdev, apm)) props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG; - props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY; if (MLX5_CAP_GEN(mdev, xrc)) props->device_cap_flags |= IB_DEVICE_XRC; props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS; @@ -1245,18 +1244,10 @@ static int create_dev_resources(struct mlx5_ib_resources *devr) struct ib_srq_init_attr attr; struct mlx5_ib_dev *dev; struct ib_cq_init_attr cq_attr = {.cqe = 1}; - u32 rsvd_lkey; int ret = 0; dev = container_of(devr, struct mlx5_ib_dev, devr); - ret = mlx5_core_query_special_context(dev->mdev, &rsvd_lkey); - if (ret) { - pr_err("Failed to query special context %d\n", ret); - return ret; - } - dev->ib_dev.local_dma_lkey = rsvd_lkey; - devr->p0 = mlx5_ib_alloc_pd(&dev->ib_dev, NULL, NULL); if (IS_ERR(devr->p0)) { ret = PTR_ERR(devr->p0); @@ -1418,6 +1409,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) strlcpy(dev->ib_dev.name, "mlx5_%d", IB_DEVICE_NAME_MAX); dev->ib_dev.owner = THIS_MODULE; dev->ib_dev.node_type = RDMA_NODE_IB_CA; + dev->ib_dev.local_dma_lkey = 0 /* not supported for now */; dev->num_ports = MLX5_CAP_GEN(mdev, num_ports); dev->ib_dev.phys_port_cnt = dev->num_ports; dev->ib_dev.num_comp_vectors = diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index aa0d5ffe92d8..9335e5ae18cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -200,25 +200,3 @@ int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev) return err; } - -int mlx5_core_query_special_context(struct mlx5_core_dev *dev, u32 *rsvd_lkey) -{ - struct mlx5_cmd_query_special_contexts_mbox_in in; - struct mlx5_cmd_query_special_contexts_mbox_out out; - int err; - - memset(&in, 0, sizeof(in)); - memset(&out, 0, sizeof(out)); - in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS); - err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); - if (err) - return err; - - if (out.hdr.status) - err = mlx5_cmd_status_to_err(&out.hdr); - - *rsvd_lkey = be32_to_cpu(out.resd_lkey); - - return err; -} -EXPORT_SYMBOL(mlx5_core_query_special_context); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 8eb3b19af2a4..250b1ff8b48d 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -402,17 +402,6 @@ struct mlx5_cmd_teardown_hca_mbox_out { u8 rsvd[8]; }; -struct mlx5_cmd_query_special_contexts_mbox_in { - struct mlx5_inbox_hdr hdr; - u8 rsvd[8]; -}; - -struct mlx5_cmd_query_special_contexts_mbox_out { - struct mlx5_outbox_hdr hdr; - __be32 dump_fill_mkey; - __be32 resd_lkey; -}; - struct mlx5_cmd_layout { u8 type; u8 rsvd0[3]; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 27b53f9a24ad..8b6d6f2154a4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -845,7 +845,6 @@ void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol); int mlx5_register_interface(struct mlx5_interface *intf); void mlx5_unregister_interface(struct mlx5_interface *intf); int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id); -int mlx5_core_query_special_context(struct mlx5_core_dev *dev, u32 *rsvd_lkey); struct mlx5_profile { u64 mask; -- cgit v1.2.3 From b40cf18ef7961b6d67732e234780586590510ce1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:08 -0700 Subject: tcp: constify listener socket in tcp_v[46]_init_req() Soon, listener socket spinlock will no longer be held, add const arguments to tcp_v[46]_init_req() to make clear these functions can not mess socket fields. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 3 ++- net/ipv4/tcp_ipv4.c | 3 ++- net/ipv6/tcp_ipv6.c | 9 +++++---- 3 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 5cf9672c13e2..c006255a0df1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1705,7 +1705,8 @@ struct tcp_request_sock_ops { const struct sock *sk, const struct sk_buff *skb); #endif - void (*init_req)(struct request_sock *req, struct sock *sk, + void (*init_req)(struct request_sock *req, + const struct sock *sk_listener, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES __u32 (*cookie_init_seq)(struct sock *sk, const struct sk_buff *skb, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7e2646542312..9d968ca7b669 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1168,7 +1168,8 @@ static bool tcp_v4_inbound_md5_hash(struct sock *sk, } #endif -static void tcp_v4_init_req(struct request_sock *req, struct sock *sk_listener, +static void tcp_v4_init_req(struct request_sock *req, + const struct sock *sk_listener, struct sk_buff *skb) { struct inet_request_sock *ireq = inet_rsk(req); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index a004e0b0b3e9..9016797445a2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -663,22 +663,23 @@ static bool tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) } #endif -static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, +static void tcp_v6_init_req(struct request_sock *req, + const struct sock *sk_listener, struct sk_buff *skb) { struct inet_request_sock *ireq = inet_rsk(req); - struct ipv6_pinfo *np = inet6_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk_listener); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; /* So that link locals have meaning */ - if (!sk->sk_bound_dev_if && + if (!sk_listener->sk_bound_dev_if && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = tcp_v6_iif(skb); if (!TCP_SKB_CB(skb)->tcp_tw_isn && - (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) || + (ipv6_opt_accepted(sk_listener, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || np->repflow)) { -- cgit v1.2.3 From b1964b5fce389a5660139ca39c25ff294da07b4f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:09 -0700 Subject: tcp: constify tcp_openreq_init_rwin() Soon, listener socket wont be locked when tcp_openreq_init_rwin() is called. We need to read socket fields once, as their value could change under us. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 3 ++- net/ipv4/tcp_minisocks.c | 28 ++++++++++++++++++---------- 2 files changed, 20 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index c006255a0df1..d37ad0c3ea9c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1207,7 +1207,8 @@ static inline int tcp_full_space(const struct sock *sk) } extern void tcp_openreq_init_rwin(struct request_sock *req, - struct sock *sk, struct dst_entry *dst); + const struct sock *sk_listener, + const struct dst_entry *dst); void tcp_enter_memory_pressure(struct sock *sk); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 85830bb92d04..e0a87c238882 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -362,27 +362,35 @@ void tcp_twsk_destructor(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_twsk_destructor); +/* Warning : This function is called without sk_listener being locked. + * Be sure to read socket fields once, as their value could change under us. + */ void tcp_openreq_init_rwin(struct request_sock *req, - struct sock *sk, struct dst_entry *dst) + const struct sock *sk_listener, + const struct dst_entry *dst) { struct inet_request_sock *ireq = inet_rsk(req); - struct tcp_sock *tp = tcp_sk(sk); - __u8 rcv_wscale; + const struct tcp_sock *tp = tcp_sk(sk_listener); + u16 user_mss = READ_ONCE(tp->rx_opt.user_mss); + int full_space = tcp_full_space(sk_listener); int mss = dst_metric_advmss(dst); + u32 window_clamp; + __u8 rcv_wscale; - if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) - mss = tp->rx_opt.user_mss; + if (user_mss && user_mss < mss) + mss = user_mss; + window_clamp = READ_ONCE(tp->window_clamp); /* Set this up on the first call only */ - req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW); + req->window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW); /* limit the window selection if the user enforce a smaller rx buffer */ - if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && - (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0)) - req->window_clamp = tcp_full_space(sk); + if (sk_listener->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->window_clamp > full_space || req->window_clamp == 0)) + req->window_clamp = full_space; /* tcp_full_space because it is guaranteed to be the first packet */ - tcp_select_initial_window(tcp_full_space(sk), + tcp_select_initial_window(full_space, mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), &req->rcv_wnd, &req->window_clamp, -- cgit v1.2.3 From 6f9c961546699ff8bc5e1c1c52200616867ec68a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:10 -0700 Subject: inet: constify ip_route_output_flow() socket argument Very soon, TCP stack might call inet_csk_route_req(), which calls inet_csk_route_req() with an unlocked listener socket, so we need to make sure ip_route_output_flow() is not trying to change any field from its socket argument. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/dst.h | 9 +++++---- include/net/route.h | 2 +- net/ipv4/route.c | 2 +- net/xfrm/xfrm_policy.c | 6 +++--- 4 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index df0481a07029..779206c15f8b 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -489,7 +489,8 @@ struct flowi; #ifndef CONFIG_XFRM static inline struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, - const struct flowi *fl, struct sock *sk, + const struct flowi *fl, + const struct sock *sk, int flags) { return dst_orig; @@ -498,7 +499,7 @@ static inline struct dst_entry *xfrm_lookup(struct net *net, static inline struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, - struct sock *sk, + const struct sock *sk, int flags) { return dst_orig; @@ -511,11 +512,11 @@ static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) #else struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, - const struct flowi *fl, struct sock *sk, + const struct flowi *fl, const struct sock *sk, int flags); struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, - const struct flowi *fl, struct sock *sk, + const struct flowi *fl, const struct sock *sk, int flags); /* skb attached with this dst needs transformation if dst->xfrm is valid */ diff --git a/include/net/route.h b/include/net/route.h index 10a7d21a211c..414beadc619f 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -114,7 +114,7 @@ void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp); struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, - struct sock *sk); + const struct sock *sk); struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 80f7c5b7b832..f7afcba8b1a1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2291,7 +2291,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or } struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, - struct sock *sk) + const struct sock *sk) { struct rtable *rt = __ip_route_output_key(net, flp4); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e7f64bcb78a8..418daa038edf 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1208,7 +1208,7 @@ static inline int policy_to_flow_dir(int dir) } } -static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, +static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, const struct flowi *fl) { struct xfrm_policy *pol; @@ -2185,7 +2185,7 @@ static struct dst_entry *make_blackhole(struct net *net, u16 family, */ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, - struct sock *sk, int flags) + const struct sock *sk, int flags) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; struct flow_cache_object *flo; @@ -2333,7 +2333,7 @@ EXPORT_SYMBOL(xfrm_lookup); */ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, - struct sock *sk, int flags) + const struct sock *sk, int flags) { struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, flags | XFRM_LOOKUP_QUEUE | -- cgit v1.2.3 From e5895bc600ccba1fde4ea0741813f9c33b5b4021 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:11 -0700 Subject: inet: constify inet_csk_route_req() socket argument This is used by TCP listener core, and listener socket shall not be modified by inet_csk_route_req(). Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 2 +- net/ipv4/inet_connection_sock.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 0320bbb7d7b5..00c3ced6ee55 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -266,7 +266,7 @@ int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); int inet_csk_get_port(struct sock *sk, unsigned short snum); -struct dst_entry *inet_csk_route_req(struct sock *sk, struct flowi4 *fl4, +struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req); struct dst_entry *inet_csk_route_child_sock(struct sock *sk, struct sock *newsk, const struct request_sock *req); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 134957159c27..ad087c14f020 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -408,7 +408,7 @@ void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len) } EXPORT_SYMBOL(inet_csk_reset_keepalive_timer); -struct dst_entry *inet_csk_route_req(struct sock *sk, +struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req) { -- cgit v1.2.3 From 3aef934f4d4b97532c333d9c1f5f73fb80aeb459 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:12 -0700 Subject: ipv6: constify ip6_dst_lookup_{flow|tail}() sock arguments ip6_dst_lookup_flow() and ip6_dst_lookup_tail() do not touch socket, lets add a const qualifier. This will permit the same change in inet6_csk_route_req() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ipv6.h | 2 +- net/ipv6/ip6_output.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 384a93cf07d6..9877b68ad207 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -849,7 +849,7 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk) int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); -struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 291a07be5dfb..6b0d86f3fbfc 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -883,7 +883,7 @@ out: return dst; } -static int ip6_dst_lookup_tail(struct net *net, struct sock *sk, +static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD @@ -1014,7 +1014,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup); * It returns a valid dst pointer on success, or a pointer encoded * error code. */ -struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { struct dst_entry *dst = NULL; -- cgit v1.2.3 From 30d50c61df94bc8d7700272ea09a716e0af8b58b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:13 -0700 Subject: ipv6: constify inet6_csk_route_req() socket argument socket is not modified, make it const so that callers can do the same if they need. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 2 +- net/ipv6/inet6_connection_sock.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 6d539e4e5ba7..81d937e820c4 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -25,7 +25,7 @@ struct sockaddr; int inet6_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); -struct dst_entry *inet6_csk_route_req(struct sock *sk, struct flowi6 *fl6, +struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, const struct request_sock *req); struct request_sock *inet6_csk_search_req(struct sock *sk, diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 6927f3fb5597..91b7d33f508b 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -65,7 +65,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, } EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict); -struct dst_entry *inet6_csk_route_req(struct sock *sk, +struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, const struct request_sock *req) { -- cgit v1.2.3 From 4e3f5d727d60939c890a6e86944da52b3a1625ce Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:14 -0700 Subject: inet: constify ip_dont_fragment() arguments ip_dont_fragment() can accept const socket and dst Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 9b9ca2839399..525dc0778926 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -282,10 +282,12 @@ int ip_decrease_ttl(struct iphdr *iph) } static inline -int ip_dont_fragment(struct sock *sk, struct dst_entry *dst) +int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) { - return inet_sk(sk)->pmtudisc == IP_PMTUDISC_DO || - (inet_sk(sk)->pmtudisc == IP_PMTUDISC_WANT && + u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc); + + return pmtudisc == IP_PMTUDISC_DO || + (pmtudisc == IP_PMTUDISC_WANT && !(dst_metric_locked(dst, RTAX_MTU))); } -- cgit v1.2.3 From b83e3deb974ca2c11e21256fe602e517afb83247 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:15 -0700 Subject: tcp: md5: constify tcp_md5_do_lookup() socket argument When TCP new listener is done, these functions will be called without socket lock being held. Make sure they don't change anything. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 10 +++++----- net/ipv4/tcp_ipv4.c | 6 +++--- net/ipv6/tcp_ipv6.c | 4 ++-- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index d37ad0c3ea9c..45bc3c63c3fd 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1372,16 +1372,16 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family); -struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, +struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG -struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, +struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, const union tcp_md5_addr *addr, int family); #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else -static inline struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, +static inline struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, const union tcp_md5_addr *addr, int family) { @@ -1684,7 +1684,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, /* TCP af-specific functions */ struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, + struct tcp_md5sig_key *(*md5_lookup) (const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash)(char *location, const struct tcp_md5sig_key *md5, @@ -1699,7 +1699,7 @@ struct tcp_sock_af_ops { struct tcp_request_sock_ops { u16 mss_clamp; #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *(*req_md5_lookup)(struct sock *sk, + struct tcp_md5sig_key *(*req_md5_lookup)(const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash) (char *location, const struct tcp_md5sig_key *md5, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9d968ca7b669..1c1009d783f5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -865,7 +865,7 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) */ /* Find the Key structure for an address. */ -struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, +struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, const union tcp_md5_addr *addr, int family) { @@ -877,7 +877,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, sock_owned_by_user(sk) || - lockdep_is_held(&sk->sk_lock.slock)); + lockdep_is_held((spinlock_t *)&sk->sk_lock.slock)); if (!md5sig) return NULL; #if IS_ENABLED(CONFIG_IPV6) @@ -894,7 +894,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, } EXPORT_SYMBOL(tcp_md5_do_lookup); -struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, +struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { const union tcp_md5_addr *addr; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 9016797445a2..1071131a6c53 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -476,13 +476,13 @@ static void tcp_v6_reqsk_destructor(struct request_sock *req) } #ifdef CONFIG_TCP_MD5SIG -static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, +static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, const struct in6_addr *addr) { return tcp_md5_do_lookup(sk, (union tcp_md5_addr *)addr, AF_INET6); } -static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk, +static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr); -- cgit v1.2.3 From cfe673b0ae4754ffc051482f4a948b67ddbeec10 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:16 -0700 Subject: ip: constify ip_build_and_send_pkt() socket argument This function is used to build and send SYNACK packets, possibly on behalf of unlocked listener socket. Make sure we did not miss a write by making this socket const. We no longer can use ip_select_ident() and have to either set iph->id to 0 or directly call __ip_select_ident() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- net/ipv4/ip_output.c | 14 ++++++++------ 2 files changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 525dc0778926..91a6b2c88341 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -100,7 +100,7 @@ int igmp_mc_init(void); * Functions provided by ip.c */ -int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, +int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt); int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 09a6b7bb7ea3..06d2c87ed505 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -137,7 +137,7 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) * Add an ip header to a skbuff and send it out. * */ -int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, +int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt) { struct inet_sock *inet = inet_sk(sk); @@ -151,15 +151,17 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->version = 4; iph->ihl = 5; iph->tos = inet->tos; - if (ip_dont_fragment(sk, &rt->dst)) - iph->frag_off = htons(IP_DF); - else - iph->frag_off = 0; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - ip_select_ident(sock_net(sk), skb, sk); + if (ip_dont_fragment(sk, &rt->dst)) { + iph->frag_off = htons(IP_DF); + iph->id = 0; + } else { + iph->frag_off = 0; + __ip_select_ident(sock_net(sk), iph, 1); + } if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; -- cgit v1.2.3 From 5d062de7f8ea1ca7c635957ff1144fba815ba34c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:19 -0700 Subject: tcp: constify tcp_make_synack() socket argument listener socket is not locked when tcp_make_synack() is called. We better make sure no field is written. There is one exception : Since SYNACK packets are attached to the listener at this moment (or SYN_RECV child in case of Fast Open), sock_wmalloc() needs to update sk->sk_wmem_alloc, but this is done using atomic operations so this is safe. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- net/ipv4/tcp_output.c | 24 +++++++++++++++--------- 2 files changed, 16 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 45bc3c63c3fd..19f23590baa0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -461,7 +461,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int tcp_connect(struct sock *sk); -struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, +struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc); int tcp_disconnect(struct sock *sk, int flags); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index ba6194152d39..9eb67a8933f1 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2944,20 +2944,25 @@ int tcp_send_synack(struct sock *sk) * Allocate one skb and build a SYNACK packet. * @dst is consumed : Caller should not use it again. */ -struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, +struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc) { - struct tcp_out_options opts; struct inet_request_sock *ireq = inet_rsk(req); - struct tcp_sock *tp = tcp_sk(sk); - struct tcphdr *th; - struct sk_buff *skb; + const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *md5 = NULL; + struct tcp_out_options opts; + struct sk_buff *skb; int tcp_header_size; + struct tcphdr *th; + u16 user_mss; int mss; - skb = sock_wmalloc(sk, MAX_TCP_HEADER, 1, GFP_ATOMIC); + /* sk is a const pointer, because we want to express multiple cpus + * might call us concurrently. + * sock_wmalloc() will change sk->sk_wmem_alloc in an atomic way. + */ + skb = sock_wmalloc((struct sock *)sk, MAX_TCP_HEADER, 1, GFP_ATOMIC); if (unlikely(!skb)) { dst_release(dst); return NULL; @@ -2968,8 +2973,9 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, skb_dst_set(skb, dst); mss = dst_metric_advmss(dst); - if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) - mss = tp->rx_opt.user_mss; + user_mss = READ_ONCE(tp->rx_opt.user_mss); + if (user_mss && user_mss < mss) + mss = user_mss; memset(&opts, 0, sizeof(opts)); #ifdef CONFIG_SYN_COOKIES @@ -3009,7 +3015,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rcv_wnd, 65535U)); - tcp_options_write((__be32 *)(th + 1), tp, &opts); + tcp_options_write((__be32 *)(th + 1), NULL, &opts); th->doff = (tcp_header_size >> 2); TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS); -- cgit v1.2.3 From 1c1e9d2b67897316770fc8a2e1acdd9f2787838d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:20 -0700 Subject: ipv6: constify ip6_xmit() sock argument This is to document that socket lock might not be held at this point. skb_set_owner_w() and ipv6_local_error() are using proper atomic ops or spinlocks, so we promote the socket to non const when calling them. netfilter hooks should never assume socket lock is held, we also promote the socket to non const. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ipv6.h | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/ip6_output.c | 26 +++++++++++++++++++------- 3 files changed, 21 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 9877b68ad207..3dde042bcd3f 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -812,7 +812,7 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); /* * upper-layer output functions */ -int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, +int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, struct ipv6_txoptions *opt, int tclass); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 9aadd57808a5..d70b0238f468 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -263,7 +263,7 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) { - struct ipv6_pinfo *np = inet6_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; struct ipv6hdr *iph; struct sk_buff *skb; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 6b0d86f3fbfc..60c565309d0a 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -150,14 +150,16 @@ int ip6_output(struct sock *sk, struct sk_buff *skb) } /* - * xmit an sk_buff (used by TCP, SCTP and DCCP) + * xmit an sk_buff (used by TCP, SCTP and DCCP) + * Note : socket lock is not held for SYNACK packets, but might be modified + * by calls to skb_set_owner_w() and ipv6_local_error(), + * which are using proper atomic operations or spinlocks. */ - -int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, +int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, struct ipv6_txoptions *opt, int tclass) { struct net *net = sock_net(sk); - struct ipv6_pinfo *np = inet6_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr; @@ -186,7 +188,10 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, } consume_skb(skb); skb = skb2; - skb_set_owner_w(skb, sk); + /* skb_set_owner_w() changes sk->sk_wmem_alloc atomically, + * it is safe to call in our context (socket lock not held) + */ + skb_set_owner_w(skb, (struct sock *)sk); } if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); @@ -224,13 +229,20 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUT, skb->len); + /* hooks should never assume socket lock is held. + * we promote our socket to non const + */ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, - net, sk, skb, NULL, dst->dev, + net, (struct sock *)sk, skb, NULL, dst->dev, dst_output_okfn); } skb->dev = dst->dev; - ipv6_local_error(sk, EMSGSIZE, fl6, mtu); + /* ipv6_local_error() does not require socket lock, + * we promote our socket to non const + */ + ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; -- cgit v1.2.3 From 0f935dbedc49a5044ebff08b47eef35a2f2bbe92 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:21 -0700 Subject: tcp: constify tcp_v{4|6}_send_synack() socket argument This documents fact that listener lock might not be held at the time SYNACK are sent. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 19f23590baa0..868c53532169 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1717,7 +1717,7 @@ struct tcp_request_sock_ops { const struct request_sock *req, bool *strict); __u32 (*init_seq)(const struct sk_buff *skb); - int (*send_synack)(struct sock *sk, struct dst_entry *dst, + int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, u16 queue_mapping, struct tcp_fastopen_cookie *foc); void (*queue_hash_add)(struct sock *sk, struct request_sock *req, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1c1009d783f5..a23ba7daecbf 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -818,7 +818,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, * This still operates on a request_sock only, not on a big * socket. */ -static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, +static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, u16 queue_mapping, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 1071131a6c53..16fb299dcab8 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -434,7 +434,7 @@ out: } -static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, +static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, u16 queue_mapping, -- cgit v1.2.3 From ea3bea3a1d38aab1542176b2ff11a99ce3db9656 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:23 -0700 Subject: tcp/dccp: constify rtx_synack() and friends This is done to make sure we do not change listener socket while sending SYNACK packets while socket lock is not held. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 2 +- include/net/tcp.h | 2 +- net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 2 +- net/ipv4/tcp_output.c | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 87935cad2f7b..ff7ce1e53ed4 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -32,7 +32,7 @@ struct request_sock_ops { int obj_size; struct kmem_cache *slab; char *slab_name; - int (*rtx_syn_ack)(struct sock *sk, + int (*rtx_syn_ack)(const struct sock *sk, struct request_sock *req); void (*send_ack)(struct sock *sk, struct sk_buff *skb, struct request_sock *req); diff --git a/include/net/tcp.h b/include/net/tcp.h index 868c53532169..6630ab180f5c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1676,7 +1676,7 @@ int tcp4_proc_init(void); void tcp4_proc_exit(void); #endif -int tcp_rtx_synack(struct sock *sk, struct request_sock *req); +int tcp_rtx_synack(const struct sock *sk, struct request_sock *req); int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index ccf4c5629b3c..a46ae9c69ccf 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -498,7 +498,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, return &rt->dst; } -static int dccp_v4_send_response(struct sock *sk, struct request_sock *req) +static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req) { int err = -1; struct sk_buff *skb; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 5165571f397a..4fa199dc69a3 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -181,7 +181,7 @@ out: } -static int dccp_v6_send_response(struct sock *sk, struct request_sock *req) +static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req) { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9eb67a8933f1..53ce6cf55598 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3502,7 +3502,7 @@ void tcp_send_probe0(struct sock *sk) TCP_RTO_MAX); } -int tcp_rtx_synack(struct sock *sk, struct request_sock *req) +int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) { const struct tcp_request_sock_ops *af_ops = tcp_rsk(req)->af_specific; struct flowi fl; -- cgit v1.2.3 From 1b70e977cef6ce7e7411c9bbec21f9adc8e29097 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:24 -0700 Subject: inet: constify inet_rtx_syn_ack() sock argument SYNACK packets are sent on behalf on unlocked listeners or fastopen sockets. Mark socket as const to catch future changes that might break the assumption. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 2 +- net/ipv4/inet_connection_sock.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index ff7ce1e53ed4..181f97f9fe1c 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -42,7 +42,7 @@ struct request_sock_ops { void (*syn_ack_timeout)(const struct request_sock *req); }; -int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req); +int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req); /* struct request_sock - mini sock to represent a connection request */ diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index ad087c14f020..bac205136e1c 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -563,7 +563,7 @@ static inline void syn_ack_recalc(struct request_sock *req, const int thresh, req->num_timeout >= rskq_defer_accept - 1; } -int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req) +int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) { int err = req->rsk_ops->rtx_syn_ack(parent, req); -- cgit v1.2.3 From 5ebc76035303016ec41bb752bec156ea9fde7c34 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Thu, 17 Sep 2015 14:02:45 +0800 Subject: ACPI, PCI, irq: Do not share PCI IRQ with ISA IRQ Avoid IRQs occupied by ISA IRQs when allocating IRQs for PCI link devices, otherwise it may cause interrupt storm due to incompatible pin attributes. This issue was triggered on a KVM virtual machine, which 1) uses IRQ9 for SCI in high level mode. 2) defines an PCI interrupt link device (LNKS) with IRQ9 as the only possible irq. 3) has an PCI device referring to link device LNKS. So it causes interrupt storm when enabling the PCI device because PCI IRQ works in low level mode. Signed-off-by: Jiang Liu Acked-by: Bjorn Helgaas Signed-off-by: Rafael J. Wysocki --- drivers/acpi/pci_irq.c | 1 + drivers/acpi/pci_link.c | 13 +++++++++++++ include/linux/acpi.h | 1 + 3 files changed, 15 insertions(+) (limited to 'include') diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index 6da0f9beab19..c9336751e5e3 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -372,6 +372,7 @@ static int acpi_isa_register_gsi(struct pci_dev *dev) /* Interrupt Line values above 0xF are forbidden */ if (dev->irq > 0 && (dev->irq <= 0xF) && + acpi_isa_irq_available(dev->irq) && (acpi_isa_irq_to_gsi(dev->irq, &dev_gsi) == 0)) { dev_warn(&dev->dev, "PCI INT %c: no GSI - using ISA IRQ %d\n", pin_name(dev->pin), dev->irq); diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index 3b4ea98e3ea0..246e50d22120 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -553,6 +553,13 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link) irq = link->irq.possible[i]; } } + if (acpi_irq_penalty[irq] >= PIRQ_PENALTY_ISA_ALWAYS) { + printk(KERN_ERR PREFIX "No IRQ available for %s [%s]. " + "Try pci=noacpi or acpi=off\n", + acpi_device_name(link->device), + acpi_device_bid(link->device)); + return -ENODEV; + } /* Attempt to enable the link device at this IRQ. */ if (acpi_pci_link_set(link, irq)) { @@ -821,6 +828,12 @@ void acpi_penalize_isa_irq(int irq, int active) } } +bool acpi_isa_irq_available(int irq) +{ + return irq >= 0 && (irq >= ARRAY_SIZE(acpi_irq_penalty) || + acpi_irq_penalty[irq] < PIRQ_PENALTY_ISA_ALWAYS); +} + /* * Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict with * PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be use for diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 7235c4851460..43856d19cf4d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -217,6 +217,7 @@ struct pci_dev; int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); +bool acpi_isa_irq_available(int irq); void acpi_penalize_sci_irq(int irq, int trigger, int polarity); void acpi_pci_irq_disable (struct pci_dev *dev); -- cgit v1.2.3 From b1be00a6c39fda2ec380e168d7bcf96fb8c9da42 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Thu, 24 Sep 2015 13:50:02 +0200 Subject: vxlan: support both IPv4 and IPv6 sockets in a single vxlan device For metadata based vxlan interface, open both IPv4 and IPv6 socket. This is much more user friendly: it's not necessary to create two vxlan interfaces and pay attention to using the right one in routing rules. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 128 +++++++++++++++++++++++++++++------------- include/net/vxlan.h | 14 ++++- net/openvswitch/vport-vxlan.c | 3 +- 3 files changed, 103 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index a86613011977..ce704df7681b 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -993,19 +993,30 @@ static bool vxlan_snoop(struct net_device *dev, static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev) { struct vxlan_dev *vxlan; + unsigned short family = dev->default_dst.remote_ip.sa.sa_family; /* The vxlan_sock is only used by dev, leaving group has * no effect on other vxlan devices. */ - if (atomic_read(&dev->vn_sock->refcnt) == 1) + if (family == AF_INET && dev->vn4_sock && + atomic_read(&dev->vn4_sock->refcnt) == 1) return false; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6 && dev->vn6_sock && + atomic_read(&dev->vn6_sock->refcnt) == 1) + return false; +#endif list_for_each_entry(vxlan, &vn->vxlan_list, next) { if (!netif_running(vxlan->dev) || vxlan == dev) continue; - if (vxlan->vn_sock != dev->vn_sock) + if (family == AF_INET && vxlan->vn4_sock != dev->vn4_sock) continue; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6 && vxlan->vn6_sock != dev->vn6_sock) + continue; +#endif if (!vxlan_addr_equal(&vxlan->default_dst.remote_ip, &dev->default_dst.remote_ip)) @@ -1021,16 +1032,16 @@ static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev) return false; } -static void vxlan_sock_release(struct vxlan_dev *vxlan) +static void __vxlan_sock_release(struct vxlan_sock *vs) { - struct vxlan_sock *vs = vxlan->vn_sock; - struct sock *sk = vs->sock->sk; - struct net *net = sock_net(sk); - struct vxlan_net *vn = net_generic(net, vxlan_net_id); + struct vxlan_net *vn; + if (!vs) + return; if (!atomic_dec_and_test(&vs->refcnt)) return; + vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id); spin_lock(&vn->sock_lock); hlist_del_rcu(&vs->hlist); vxlan_notify_del_rx_port(vs); @@ -1039,32 +1050,43 @@ static void vxlan_sock_release(struct vxlan_dev *vxlan) queue_work(vxlan_wq, &vs->del_work); } +static void vxlan_sock_release(struct vxlan_dev *vxlan) +{ + __vxlan_sock_release(vxlan->vn4_sock); +#if IS_ENABLED(CONFIG_IPV6) + __vxlan_sock_release(vxlan->vn6_sock); +#endif +} + /* Update multicast group membership when first VNI on * multicast address is brought up */ static int vxlan_igmp_join(struct vxlan_dev *vxlan) { - struct vxlan_sock *vs = vxlan->vn_sock; - struct sock *sk = vs->sock->sk; + struct sock *sk; union vxlan_addr *ip = &vxlan->default_dst.remote_ip; int ifindex = vxlan->default_dst.remote_ifindex; int ret = -EINVAL; - lock_sock(sk); if (ip->sa.sa_family == AF_INET) { struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr, .imr_ifindex = ifindex, }; + sk = vxlan->vn4_sock->sock->sk; + lock_sock(sk); ret = ip_mc_join_group(sk, &mreq); + release_sock(sk); #if IS_ENABLED(CONFIG_IPV6) } else { + sk = vxlan->vn6_sock->sock->sk; + lock_sock(sk); ret = ipv6_stub->ipv6_sock_mc_join(sk, ifindex, &ip->sin6.sin6_addr); + release_sock(sk); #endif } - release_sock(sk); return ret; } @@ -1072,27 +1094,30 @@ static int vxlan_igmp_join(struct vxlan_dev *vxlan) /* Inverse of vxlan_igmp_join when last VNI is brought down */ static int vxlan_igmp_leave(struct vxlan_dev *vxlan) { - struct vxlan_sock *vs = vxlan->vn_sock; - struct sock *sk = vs->sock->sk; + struct sock *sk; union vxlan_addr *ip = &vxlan->default_dst.remote_ip; int ifindex = vxlan->default_dst.remote_ifindex; int ret = -EINVAL; - lock_sock(sk); if (ip->sa.sa_family == AF_INET) { struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr, .imr_ifindex = ifindex, }; + sk = vxlan->vn4_sock->sock->sk; + lock_sock(sk); ret = ip_mc_leave_group(sk, &mreq); + release_sock(sk); #if IS_ENABLED(CONFIG_IPV6) } else { + sk = vxlan->vn6_sock->sock->sk; + lock_sock(sk); ret = ipv6_stub->ipv6_sock_mc_drop(sk, ifindex, &ip->sin6.sin6_addr); + release_sock(sk); #endif } - release_sock(sk); return ret; } @@ -1873,8 +1898,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, { struct ip_tunnel_info *info; struct vxlan_dev *vxlan = netdev_priv(dev); - struct sock *sk = vxlan->vn_sock->sock->sk; - unsigned short family = vxlan_get_sk_family(vxlan->vn_sock); + struct sock *sk; struct rtable *rt = NULL; const struct iphdr *old_iph; struct flowi4 fl4; @@ -1901,13 +1925,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dev->name); goto drop; } - if (family != ip_tunnel_info_af(info)) - goto drop; - dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; vni = be64_to_cpu(info->key.tun_id); - remote_ip.sa.sa_family = family; - if (family == AF_INET) + remote_ip.sa.sa_family = ip_tunnel_info_af(info); + if (remote_ip.sa.sa_family == AF_INET) remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst; else remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst; @@ -1952,6 +1973,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } if (dst->sa.sa_family == AF_INET) { + if (!vxlan->vn4_sock) + goto drop; + sk = vxlan->vn4_sock->sock->sk; + if (info && (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)) df = htons(IP_DF); @@ -2013,6 +2038,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct flowi6 fl6; u32 rt6i_flags; + if (!vxlan->vn6_sock) + goto drop; + sk = vxlan->vn6_sock->sock->sk; + memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = rdst ? rdst->remote_ifindex : 0; fl6.daddr = dst->sin6.sin6_addr; @@ -2204,7 +2233,6 @@ static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan) struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); __u32 vni = vxlan->default_dst.remote_vni; - vxlan->vn_sock = vs; spin_lock(&vn->sock_lock); hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni)); spin_unlock(&vn->sock_lock); @@ -2535,14 +2563,13 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6, } /* Create new listen socket if needed */ -static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port, - u32 flags) +static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, + __be16 port, u32 flags) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_sock *vs; struct socket *sock; unsigned int h; - bool ipv6 = !!(flags & VXLAN_F_IPV6); struct udp_tunnel_sock_cfg tunnel_cfg; vs = kzalloc(sizeof(*vs), GFP_KERNEL); @@ -2587,11 +2614,10 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port, return vs; } -static int vxlan_sock_add(struct vxlan_dev *vxlan) +static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); struct vxlan_sock *vs = NULL; - bool ipv6 = vxlan->flags & VXLAN_F_IPV6; if (!vxlan->cfg.no_share) { spin_lock(&vn->sock_lock); @@ -2604,20 +2630,46 @@ static int vxlan_sock_add(struct vxlan_dev *vxlan) spin_unlock(&vn->sock_lock); } if (!vs) - vs = vxlan_socket_create(vxlan->net, vxlan->cfg.dst_port, - vxlan->flags); + vs = vxlan_socket_create(vxlan->net, ipv6, + vxlan->cfg.dst_port, vxlan->flags); if (IS_ERR(vs)) return PTR_ERR(vs); +#if IS_ENABLED(CONFIG_IPV6) + if (ipv6) + vxlan->vn6_sock = vs; + else +#endif + vxlan->vn4_sock = vs; vxlan_vs_add_dev(vs, vxlan); return 0; } +static int vxlan_sock_add(struct vxlan_dev *vxlan) +{ + bool ipv6 = vxlan->flags & VXLAN_F_IPV6; + bool metadata = vxlan->flags & VXLAN_F_COLLECT_METADATA; + int ret = 0; + + vxlan->vn4_sock = NULL; +#if IS_ENABLED(CONFIG_IPV6) + vxlan->vn6_sock = NULL; + if (ipv6 || metadata) + ret = __vxlan_sock_add(vxlan, true); +#endif + if (!ret && (!ipv6 || metadata)) + ret = __vxlan_sock_add(vxlan, false); + if (ret < 0) + vxlan_sock_release(vxlan); + return ret; +} + static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, struct vxlan_config *conf) { struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; + unsigned short needed_headroom = ETH_HLEN; int err; bool use_ipv6 = false; __be16 default_port = vxlan->cfg.dst_port; @@ -2637,6 +2689,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, if (!IS_ENABLED(CONFIG_IPV6)) return -EPFNOSUPPORT; use_ipv6 = true; + vxlan->flags |= VXLAN_F_IPV6; } if (conf->remote_ifindex) { @@ -2657,22 +2710,21 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, pr_info("IPv6 is disabled via sysctl\n"); return -EPERM; } - vxlan->flags |= VXLAN_F_IPV6; } #endif if (!conf->mtu) dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); - dev->needed_headroom = lowerdev->hard_header_len + - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); - } else if (use_ipv6) { - vxlan->flags |= VXLAN_F_IPV6; - dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM; - } else { - dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM; + needed_headroom = lowerdev->hard_header_len; } + if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA) + needed_headroom += VXLAN6_HEADROOM; + else + needed_headroom += VXLAN_HEADROOM; + dev->needed_headroom = needed_headroom; + memcpy(&vxlan->cfg, conf, sizeof(*conf)); if (!vxlan->cfg.dst_port) vxlan->cfg.dst_port = default_port; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 480a319b4c92..c1c899c3a51b 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -152,7 +152,10 @@ struct vxlan_config { struct vxlan_dev { struct hlist_node hlist; /* vni hash table */ struct list_head next; /* vxlan's per namespace list */ - struct vxlan_sock *vn_sock; /* listening socket */ + struct vxlan_sock *vn4_sock; /* listening socket for IPv4 */ +#if IS_ENABLED(CONFIG_IPV6) + struct vxlan_sock *vn6_sock; /* listening socket for IPv6 */ +#endif struct net_device *dev; struct net *net; /* netns for packet i/o */ struct vxlan_rdst default_dst; /* default destination */ @@ -195,9 +198,14 @@ struct vxlan_dev { struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf); -static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan) +static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan, + unsigned short family) { - return inet_sk(vxlan->vn_sock->sock->sk)->inet_sport; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) + return inet_sk(vxlan->vn6_sock->sock->sk)->inet_sport; +#endif + return inet_sk(vxlan->vn4_sock->sock->sk)->inet_sport; } static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index c11413d5075f..fb3cdb85905d 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -151,7 +151,8 @@ static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, { struct vxlan_dev *vxlan = netdev_priv(vport->dev); struct net *net = ovs_dp_get_net(vport->dp); - __be16 dst_port = vxlan_dev_dst_port(vxlan); + unsigned short family = ip_tunnel_info_af(upcall->egress_tun_info); + __be16 dst_port = vxlan_dev_dst_port(vxlan, family); __be16 src_port; int port_min; int port_max; -- cgit v1.2.3 From 7c85af8810448d8ef59331be51e482413b5f503d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 24 Sep 2015 17:16:05 -0700 Subject: tcp: avoid reorders for TFO passive connections We found that a TCP Fast Open passive connection was vulnerable to reorders, as the exchange might look like [1] C -> S S [2] S -> C S. ack request [3] S -> C . packets [2] and [3] can be generated at almost the same time. If C receives the 3rd packet before the 2nd, it will drop it as the socket is in SYN_SENT state and expects a SYNACK. S will have to retransmit the answer. Current OOO avoidance in linux is defeated because SYNACK packets are attached to the LISTEN socket, while DATA packets are attached to the children. They might be sent by different cpus, and different TX queues might be selected. It turns out that for TFO, we created a child, which is a full blown socket in TCP_SYN_RECV state, and we simply can attach the SYNACK packet to this socket. This means that at the time tcp_sendmsg() pushes DATA packet, skb->ooo_okay will be set iff the SYNACK packet had been sent and TX completed. This removes the reorder source at the host level. We also removed the export of tcp_try_fastopen(), as it is no longer called from IPv6. Signed-off-by: Eric Dumazet Signed-off-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/net/tcp.h | 8 ++++---- net/ipv4/tcp_fastopen.c | 35 +++++++++++++++++++---------------- net/ipv4/tcp_input.c | 19 +++++++++++-------- 3 files changed, 34 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 6630ab180f5c..cdbf63d3c5cf 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1422,10 +1422,10 @@ void tcp_free_fastopen_req(struct tcp_sock *tp); extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; int tcp_fastopen_reset_cipher(void *key, unsigned int len); -bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct tcp_fastopen_cookie *foc, - struct dst_entry *dst); +struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct tcp_fastopen_cookie *foc, + struct dst_entry *dst); void tcp_fastopen_init_key_once(bool publish); #define TCP_FASTOPEN_KEY_LENGTH 16 diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index f9c0fb84e435..db43c6286cf7 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -124,10 +124,10 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, return false; } -static bool tcp_fastopen_create_child(struct sock *sk, - struct sk_buff *skb, - struct dst_entry *dst, - struct request_sock *req) +static struct sock *tcp_fastopen_create_child(struct sock *sk, + struct sk_buff *skb, + struct dst_entry *dst, + struct request_sock *req) { struct tcp_sock *tp; struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; @@ -140,7 +140,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); if (!child) - return false; + return NULL; spin_lock(&queue->fastopenq->lock); queue->fastopenq->qlen++; @@ -216,9 +216,11 @@ static bool tcp_fastopen_create_child(struct sock *sk, tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq; sk->sk_data_ready(sk); bh_unlock_sock(child); - sock_put(child); + /* Note: sock_put(child) will be done by tcp_conn_request() + * after SYNACK packet is sent. + */ WARN_ON(!req->sk); - return true; + return child; } static bool tcp_fastopen_queue_check(struct sock *sk) @@ -261,13 +263,14 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * may be updated and return the client in the SYN-ACK later. E.g., Fast Open * cookie request (foc->len == 0). */ -bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct tcp_fastopen_cookie *foc, - struct dst_entry *dst) +struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct tcp_fastopen_cookie *foc, + struct dst_entry *dst) { struct tcp_fastopen_cookie valid_foc = { .len = -1 }; bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; + struct sock *child; if (foc->len == 0) /* Client requests a cookie */ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD); @@ -276,7 +279,7 @@ bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, (syn_data || foc->len >= 0) && tcp_fastopen_queue_check(sk))) { foc->len = -1; - return false; + return NULL; } if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD)) @@ -296,11 +299,12 @@ bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, * data in SYN_RECV state. */ fastopen: - if (tcp_fastopen_create_child(sk, skb, dst, req)) { + child = tcp_fastopen_create_child(sk, skb, dst, req); + if (child) { foc->len = -1; NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE); - return true; + return child; } NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); } else if (foc->len > 0) /* Client presents an invalid cookie */ @@ -308,6 +312,5 @@ fastopen: valid_foc.exp = foc->exp; *foc = valid_foc; - return false; + return NULL; } -EXPORT_SYMBOL(tcp_try_fastopen); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 497adf58a6b8..4964d53907e9 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6111,14 +6111,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) { + struct tcp_fastopen_cookie foc = { .len = -1 }; + __u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn; struct tcp_options_received tmp_opt; - struct request_sock *req; struct tcp_sock *tp = tcp_sk(sk); + struct sock *fastopen_sk = NULL; struct dst_entry *dst = NULL; - __u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn; - bool want_cookie = false, fastopen; + struct request_sock *req; + bool want_cookie = false; struct flowi fl; - struct tcp_fastopen_cookie foc = { .len = -1 }; int err; @@ -6229,11 +6230,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->snt_isn = isn; tcp_rsk(req)->txhash = net_tx_rndhash(); tcp_openreq_init_rwin(req, sk, dst); - fastopen = !want_cookie && - tcp_try_fastopen(sk, skb, req, &foc, dst); - err = af_ops->send_synack(sk, dst, &fl, req, + if (!want_cookie) + fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst); + err = af_ops->send_synack(fastopen_sk ?: sk, dst, &fl, req, skb_get_queue_mapping(skb), &foc); - if (!fastopen) { + if (fastopen_sk) { + sock_put(fastopen_sk); + } else { if (err || want_cookie) goto drop_and_free; -- cgit v1.2.3 From 78ccb25861d76a8fc5c678d762180e6918834200 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Fri, 25 Sep 2015 10:49:15 +0300 Subject: net/mlx5_core: Fix wrong name in struct The name refers to syndrome so uset ext_synd instread of ext_sync. Signed-off-by: Eli Cohen Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 2 +- include/linux/mlx5/device.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 292d76f2a904..6e69de00cea8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -130,7 +130,7 @@ static void print_health_info(struct mlx5_core_dev *dev) pr_info("hw_id 0x%08x\n", read_be32(&h->hw_id)); pr_info("irisc_index %d\n", readb(&h->irisc_index)); pr_info("synd 0x%x: %s\n", readb(&h->synd), hsynd_str(readb(&h->synd))); - pr_info("ext_sync 0x%04x\n", read_be16(&h->ext_sync)); + pr_info("ext_sync 0x%04x\n", read_be16(&h->ext_synd)); } static void poll_health(unsigned long data) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 8eb3b19af2a4..41e9f3bd663c 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -440,7 +440,7 @@ struct health_buffer { __be32 rsvd2; u8 irisc_index; u8 synd; - __be16 ext_sync; + __be16 ext_synd; }; struct mlx5_init_seg { -- cgit v1.2.3 From 55acca90da52b85299c033354e51ddaa7b73e019 Mon Sep 17 00:00:00 2001 From: Hante Meuleman Date: Fri, 18 Sep 2015 22:08:17 +0200 Subject: brcmfmac: Add support for the BCM4365 and BCM4366 PCIE devices. This patch adds support for the BCM4365 and BCM4366 11ac Wave2 PCIE devices. Reviewed-by: Arend Van Spriel Reviewed-by: Pieter-Paul Giesberts Signed-off-by: Hante Meuleman Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo --- drivers/net/wireless/brcm80211/brcmfmac/chip.c | 110 +++++++++++++++++++-- drivers/net/wireless/brcm80211/brcmfmac/pcie.c | 22 +++++ .../net/wireless/brcm80211/include/brcm_hw_ids.h | 9 ++ include/linux/bcma/bcma.h | 2 + 4 files changed, 133 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/brcm80211/brcmfmac/chip.c index ff0c7c620c4e..ffc3ace24903 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/chip.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/chip.c @@ -208,6 +208,7 @@ struct sbsocramregs { }; #define SOCRAMREGOFFS(_f) offsetof(struct sbsocramregs, _f) +#define SYSMEMREGOFFS(_f) offsetof(struct sbsocramregs, _f) #define ARMCR4_CAP (0x04) #define ARMCR4_BANKIDX (0x40) @@ -516,6 +517,9 @@ static int brcmf_chip_cores_check(struct brcmf_chip_priv *ci) case BCMA_CORE_ARM_CR4: cpu_found = true; break; + case BCMA_CORE_ARM_CA7: + cpu_found = true; + break; default: break; } @@ -614,6 +618,29 @@ static void brcmf_chip_socram_ramsize(struct brcmf_core_priv *sr, u32 *ramsize, } } +/** Return the SYS MEM size */ +static u32 brcmf_chip_sysmem_ramsize(struct brcmf_core_priv *sysmem) +{ + u32 memsize = 0; + u32 coreinfo; + u32 idx; + u32 nb; + u32 banksize; + + if (!brcmf_chip_iscoreup(&sysmem->pub)) + brcmf_chip_resetcore(&sysmem->pub, 0, 0, 0); + + coreinfo = brcmf_chip_core_read32(sysmem, SYSMEMREGOFFS(coreinfo)); + nb = (coreinfo & SRCI_SRNB_MASK) >> SRCI_SRNB_SHIFT; + + for (idx = 0; idx < nb; idx++) { + brcmf_chip_socram_banksize(sysmem, idx, &banksize); + memsize += banksize; + } + + return memsize; +} + /** Return the TCM-RAM size of the ARMCR4 core. */ static u32 brcmf_chip_tcm_ramsize(struct brcmf_core_priv *cr4) { @@ -656,6 +683,9 @@ static u32 brcmf_chip_tcm_rambase(struct brcmf_chip_priv *ci) case BRCM_CC_4358_CHIP_ID: case BRCM_CC_43602_CHIP_ID: return 0x180000; + case BRCM_CC_4365_CHIP_ID: + case BRCM_CC_4366_CHIP_ID: + return 0x200000; default: brcmf_err("unknown chip: %s\n", ci->pub.name); break; @@ -678,10 +708,28 @@ static int brcmf_chip_get_raminfo(struct brcmf_chip_priv *ci) return -EINVAL; } } else { - mem = brcmf_chip_get_core(&ci->pub, BCMA_CORE_INTERNAL_MEM); - mem_core = container_of(mem, struct brcmf_core_priv, pub); - brcmf_chip_socram_ramsize(mem_core, &ci->pub.ramsize, - &ci->pub.srsize); + mem = brcmf_chip_get_core(&ci->pub, BCMA_CORE_SYS_MEM); + if (mem) { + mem_core = container_of(mem, struct brcmf_core_priv, + pub); + ci->pub.ramsize = brcmf_chip_sysmem_ramsize(mem_core); + ci->pub.rambase = brcmf_chip_tcm_rambase(ci); + if (!ci->pub.rambase) { + brcmf_err("RAM base not provided with ARM CA7 core\n"); + return -EINVAL; + } + } else { + mem = brcmf_chip_get_core(&ci->pub, + BCMA_CORE_INTERNAL_MEM); + if (!mem) { + brcmf_err("No memory cores found\n"); + return -ENOMEM; + } + mem_core = container_of(mem, struct brcmf_core_priv, + pub); + brcmf_chip_socram_ramsize(mem_core, &ci->pub.ramsize, + &ci->pub.srsize); + } } brcmf_dbg(INFO, "RAM: base=0x%x size=%d (0x%x) sr=%d (0x%x)\n", ci->pub.rambase, ci->pub.ramsize, ci->pub.ramsize, @@ -924,7 +972,7 @@ static int brcmf_chip_recognition(struct brcmf_chip_priv *ci) static void brcmf_chip_disable_arm(struct brcmf_chip_priv *chip, u16 id) { struct brcmf_core *core; - struct brcmf_core_priv *cr4; + struct brcmf_core_priv *cpu; u32 val; @@ -937,10 +985,11 @@ static void brcmf_chip_disable_arm(struct brcmf_chip_priv *chip, u16 id) brcmf_chip_coredisable(core, 0, 0); break; case BCMA_CORE_ARM_CR4: - cr4 = container_of(core, struct brcmf_core_priv, pub); + case BCMA_CORE_ARM_CA7: + cpu = container_of(core, struct brcmf_core_priv, pub); /* clear all IOCTL bits except HALT bit */ - val = chip->ops->read32(chip->ctx, cr4->wrapbase + BCMA_IOCTL); + val = chip->ops->read32(chip->ctx, cpu->wrapbase + BCMA_IOCTL); val &= ARMCR4_BCMA_IOCTL_CPUHALT; brcmf_chip_resetcore(core, val, ARMCR4_BCMA_IOCTL_CPUHALT, ARMCR4_BCMA_IOCTL_CPUHALT); @@ -1162,6 +1211,33 @@ static bool brcmf_chip_cr4_set_active(struct brcmf_chip_priv *chip, u32 rstvec) return true; } +static inline void +brcmf_chip_ca7_set_passive(struct brcmf_chip_priv *chip) +{ + struct brcmf_core *core; + + brcmf_chip_disable_arm(chip, BCMA_CORE_ARM_CA7); + + core = brcmf_chip_get_core(&chip->pub, BCMA_CORE_80211); + brcmf_chip_resetcore(core, D11_BCMA_IOCTL_PHYRESET | + D11_BCMA_IOCTL_PHYCLOCKEN, + D11_BCMA_IOCTL_PHYCLOCKEN, + D11_BCMA_IOCTL_PHYCLOCKEN); +} + +static bool brcmf_chip_ca7_set_active(struct brcmf_chip_priv *chip, u32 rstvec) +{ + struct brcmf_core *core; + + chip->ops->activate(chip->ctx, &chip->pub, rstvec); + + /* restore ARM */ + core = brcmf_chip_get_core(&chip->pub, BCMA_CORE_ARM_CA7); + brcmf_chip_resetcore(core, ARMCR4_BCMA_IOCTL_CPUHALT, 0, 0); + + return true; +} + void brcmf_chip_set_passive(struct brcmf_chip *pub) { struct brcmf_chip_priv *chip; @@ -1175,8 +1251,16 @@ void brcmf_chip_set_passive(struct brcmf_chip *pub) brcmf_chip_cr4_set_passive(chip); return; } - - brcmf_chip_cm3_set_passive(chip); + arm = brcmf_chip_get_core(pub, BCMA_CORE_ARM_CA7); + if (arm) { + brcmf_chip_ca7_set_passive(chip); + return; + } + arm = brcmf_chip_get_core(pub, BCMA_CORE_ARM_CM3); + if (arm) { + brcmf_chip_cm3_set_passive(chip); + return; + } } bool brcmf_chip_set_active(struct brcmf_chip *pub, u32 rstvec) @@ -1190,8 +1274,14 @@ bool brcmf_chip_set_active(struct brcmf_chip *pub, u32 rstvec) arm = brcmf_chip_get_core(pub, BCMA_CORE_ARM_CR4); if (arm) return brcmf_chip_cr4_set_active(chip, rstvec); + arm = brcmf_chip_get_core(pub, BCMA_CORE_ARM_CA7); + if (arm) + return brcmf_chip_ca7_set_active(chip, rstvec); + arm = brcmf_chip_get_core(pub, BCMA_CORE_ARM_CM3); + if (arm) + return brcmf_chip_cm3_set_active(chip); - return brcmf_chip_cm3_set_active(chip); + return false; } bool brcmf_chip_sr_capable(struct brcmf_chip *pub) diff --git a/drivers/net/wireless/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/brcm80211/brcmfmac/pcie.c index 451022e4cdea..30baf352e234 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/pcie.c @@ -55,6 +55,10 @@ enum brcmf_pcie_state { #define BRCMF_PCIE_43570_NVRAM_NAME "brcm/brcmfmac43570-pcie.txt" #define BRCMF_PCIE_4358_FW_NAME "brcm/brcmfmac4358-pcie.bin" #define BRCMF_PCIE_4358_NVRAM_NAME "brcm/brcmfmac4358-pcie.txt" +#define BRCMF_PCIE_4365_FW_NAME "brcm/brcmfmac4365b-pcie.bin" +#define BRCMF_PCIE_4365_NVRAM_NAME "brcm/brcmfmac4365b-pcie.txt" +#define BRCMF_PCIE_4366_FW_NAME "brcm/brcmfmac4366b-pcie.bin" +#define BRCMF_PCIE_4366_NVRAM_NAME "brcm/brcmfmac4366b-pcie.txt" #define BRCMF_PCIE_FW_UP_TIMEOUT 2000 /* msec */ @@ -204,6 +208,10 @@ MODULE_FIRMWARE(BRCMF_PCIE_43570_FW_NAME); MODULE_FIRMWARE(BRCMF_PCIE_43570_NVRAM_NAME); MODULE_FIRMWARE(BRCMF_PCIE_4358_FW_NAME); MODULE_FIRMWARE(BRCMF_PCIE_4358_NVRAM_NAME); +MODULE_FIRMWARE(BRCMF_PCIE_4365_FW_NAME); +MODULE_FIRMWARE(BRCMF_PCIE_4365_NVRAM_NAME); +MODULE_FIRMWARE(BRCMF_PCIE_4366_FW_NAME); +MODULE_FIRMWARE(BRCMF_PCIE_4366_NVRAM_NAME); struct brcmf_pcie_console { @@ -1440,6 +1448,14 @@ static int brcmf_pcie_get_fwnames(struct brcmf_pciedev_info *devinfo) fw_name = BRCMF_PCIE_4358_FW_NAME; nvram_name = BRCMF_PCIE_4358_NVRAM_NAME; break; + case BRCM_CC_4365_CHIP_ID: + fw_name = BRCMF_PCIE_4365_FW_NAME; + nvram_name = BRCMF_PCIE_4365_NVRAM_NAME; + break; + case BRCM_CC_4366_CHIP_ID: + fw_name = BRCMF_PCIE_4366_FW_NAME; + nvram_name = BRCMF_PCIE_4366_NVRAM_NAME; + break; default: brcmf_err("Unsupported chip 0x%04x\n", devinfo->ci->chip); return -ENODEV; @@ -1973,6 +1989,12 @@ static struct pci_device_id brcmf_pcie_devid_table[] = { BRCMF_PCIE_DEVICE(BRCM_PCIE_43602_2G_DEVICE_ID), BRCMF_PCIE_DEVICE(BRCM_PCIE_43602_5G_DEVICE_ID), BRCMF_PCIE_DEVICE(BRCM_PCIE_43602_RAW_DEVICE_ID), + BRCMF_PCIE_DEVICE(BRCM_PCIE_4365_DEVICE_ID), + BRCMF_PCIE_DEVICE(BRCM_PCIE_4365_2G_DEVICE_ID), + BRCMF_PCIE_DEVICE(BRCM_PCIE_4365_5G_DEVICE_ID), + BRCMF_PCIE_DEVICE(BRCM_PCIE_4366_DEVICE_ID), + BRCMF_PCIE_DEVICE(BRCM_PCIE_4366_2G_DEVICE_ID), + BRCMF_PCIE_DEVICE(BRCM_PCIE_4366_5G_DEVICE_ID), { /* end: all zeroes */ } }; diff --git a/drivers/net/wireless/brcm80211/include/brcm_hw_ids.h b/drivers/net/wireless/brcm80211/include/brcm_hw_ids.h index 8278376aee40..d823734a4713 100644 --- a/drivers/net/wireless/brcm80211/include/brcm_hw_ids.h +++ b/drivers/net/wireless/brcm80211/include/brcm_hw_ids.h @@ -48,6 +48,8 @@ #define BRCM_CC_43570_CHIP_ID 43570 #define BRCM_CC_4358_CHIP_ID 0x4358 #define BRCM_CC_43602_CHIP_ID 43602 +#define BRCM_CC_4365_CHIP_ID 0x4365 +#define BRCM_CC_4366_CHIP_ID 0x4366 /* USB Device IDs */ #define BRCM_USB_43143_DEVICE_ID 0xbd1e @@ -67,6 +69,13 @@ #define BRCM_PCIE_43602_2G_DEVICE_ID 0x43bb #define BRCM_PCIE_43602_5G_DEVICE_ID 0x43bc #define BRCM_PCIE_43602_RAW_DEVICE_ID 43602 +#define BRCM_PCIE_4365_DEVICE_ID 0x43ca +#define BRCM_PCIE_4365_2G_DEVICE_ID 0x43cb +#define BRCM_PCIE_4365_5G_DEVICE_ID 0x43cc +#define BRCM_PCIE_4366_DEVICE_ID 0x43c3 +#define BRCM_PCIE_4366_2G_DEVICE_ID 0x43c4 +#define BRCM_PCIE_4366_5G_DEVICE_ID 0x43c5 + /* brcmsmac IDs */ #define BCM4313_D11N2G_ID 0x4727 /* 4313 802.11n 2.4G device */ diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 2ff4a9961e1d..3feb1b2d75d8 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -151,6 +151,8 @@ struct bcma_host_ops { #define BCMA_CORE_PCIE2 0x83C /* PCI Express Gen2 */ #define BCMA_CORE_USB30_DEV 0x83D #define BCMA_CORE_ARM_CR4 0x83E +#define BCMA_CORE_ARM_CA7 0x847 +#define BCMA_CORE_SYS_MEM 0x849 #define BCMA_CORE_DEFAULT 0xFFF #define BCMA_MAX_NR_CORES 16 -- cgit v1.2.3 From fbef168fec837ae26c8725737cd4b49dc8a0f917 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 29 Sep 2015 15:05:44 +0200 Subject: Bluetooth: Add hci_cmd_sync function Send a HCI command and wait for command complete event. This function serializes the requests by grabbing the req_lock. Signed-off-by: Loic Poulain Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 3 +++ net/bluetooth/hci_core.c | 19 +++++++++++++++++++ 2 files changed, 22 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 256e6734c1fb..61dc786358be 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1349,6 +1349,9 @@ void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb); void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); +struct sk_buff *hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, u32 timeout); + /* ----- HCI Sockets ----- */ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index a7cdd99ec3f1..79356469c377 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3580,6 +3580,25 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) return hdev->sent_cmd->data + HCI_COMMAND_HDR_SIZE; } +/* Send HCI command and wait for command commplete event */ +struct sk_buff *hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, u32 timeout) +{ + struct sk_buff *skb; + + if (!test_bit(HCI_UP, &hdev->flags)) + return ERR_PTR(-ENETDOWN); + + bt_dev_dbg(hdev, "opcode 0x%4.4x plen %d", opcode, plen); + + hci_req_lock(hdev); + skb = __hci_cmd_sync(hdev, opcode, plen, param, timeout); + hci_req_unlock(hdev); + + return skb; +} +EXPORT_SYMBOL(hci_cmd_sync); + /* Send ACL data */ static void hci_add_acl_hdr(struct sk_buff *skb, __u16 handle, __u16 flags) { -- cgit v1.2.3 From 35afa588624c4f9e19a0edfbb51769b59c90bb0d Mon Sep 17 00:00:00 2001 From: Helmut Schaa Date: Wed, 9 Sep 2015 09:46:32 +0200 Subject: mac80211: Copy tx'ed beacons to monitor mode When debugging wireless powersave issues on the AP side it's quite helpful to see our own beacons that are transmitted by the hardware/driver. However, this is not that easy since beacons don't pass through the regular TX queues. Preferably drivers would call ieee80211_tx_status also for tx'ed beacons but that's not always possible. Hence, just send a copy of each beacon generated by ieee80211_beacon_get_tim to monitor devices when they are getting fetched by the driver. Also add a HW flag IEEE80211_HW_BEACON_TX_STATUS that can be used by drivers to indicate that they report TX status for beacons. Signed-off-by: Helmut Schaa (with a fix from Christian Lamparted rolled in) Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++++ net/mac80211/debugfs.c | 1 + net/mac80211/tx.c | 19 +++++++++++++++++++ 3 files changed, 24 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 3424ac6efb2a..301fceb2fd10 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1898,6 +1898,9 @@ struct ieee80211_txq { * @IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU: The driver supports receiving A-MSDUs * within A-MPDU. * + * @IEEE80211_HW_BEACON_TX_STATUS: The device/driver provides TX status + * for sent beacons. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -1932,6 +1935,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS, IEEE80211_HW_TDLS_WIDER_BW, IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU, + IEEE80211_HW_BEACON_TX_STATUS, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 41726fd4bb78..3636b45440ab 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -124,6 +124,7 @@ static const char *hw_flag_names[NUM_IEEE80211_HW_FLAGS + 1] = { FLAG(SINGLE_SCAN_ON_ALL_BANDS), FLAG(TDLS_WIDER_BW), FLAG(SUPPORTS_AMSDU_IN_AMPDU), + FLAG(BEACON_TX_STATUS), /* keep last for the build bug below */ (void *)0x1 diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 84e0e8c7fb23..73540723be37 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3512,6 +3512,12 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, { struct ieee80211_mutable_offsets offs = {}; struct sk_buff *bcn = __ieee80211_beacon_get(hw, vif, &offs, false); + struct sk_buff *copy; + struct ieee80211_supported_band *sband; + int shift; + + if (!bcn) + return bcn; if (tim_offset) *tim_offset = offs.tim_offset; @@ -3519,6 +3525,19 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, if (tim_length) *tim_length = offs.tim_length; + if (ieee80211_hw_check(hw, BEACON_TX_STATUS) || + !hw_to_local(hw)->monitors) + return bcn; + + /* send a copy to monitor interfaces */ + copy = skb_copy(bcn, GFP_ATOMIC); + if (!copy) + return bcn; + + shift = ieee80211_vif_get_shift(vif); + sband = hw->wiphy->bands[ieee80211_get_sdata_band(vif_to_sdata(vif))]; + ieee80211_tx_monitor(hw_to_local(hw), copy, sband, 1, shift, false); + return bcn; } EXPORT_SYMBOL(ieee80211_beacon_get_tim); -- cgit v1.2.3 From 47edb11b522561658fe719e56aa69a3c3098a3fe Mon Sep 17 00:00:00 2001 From: Ayala Beker Date: Mon, 21 Sep 2015 15:49:53 +0300 Subject: cfg80211: allow changing station capabilities for unassociated stations Currently, cfg80211 rejects capability updates for existing entries and as a result it's impossible to update entries that were added unassociated, but that is necessary to go through the full station states from userspace, adding a station before authentication etc. Fix this by allowing updates to capabilities for stations that the driver (or mac80211) assigned unassociated state. Drivers setting the full station state support flag must use the new station type for proper operation. Signed-off-by: Ayala Beker Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 3 +++ net/wireless/nl80211.c | 7 +++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0f54c9ef4c7d..90332a1838cc 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -858,6 +858,8 @@ struct station_del_parameters { /** * enum cfg80211_station_type - the type of station being modified * @CFG80211_STA_AP_CLIENT: client of an AP interface + * @CFG80211_STA_AP_CLIENT_UNASSOC: client of an AP interface that is still + * unassociated (update properties for this type of client is permitted) * @CFG80211_STA_AP_MLME_CLIENT: client of an AP interface that has * the AP MLME in the device * @CFG80211_STA_AP_STA: AP station on managed interface @@ -873,6 +875,7 @@ struct station_del_parameters { */ enum cfg80211_station_type { CFG80211_STA_AP_CLIENT, + CFG80211_STA_AP_CLIENT_UNASSOC, CFG80211_STA_AP_MLME_CLIENT, CFG80211_STA_AP_STA, CFG80211_STA_IBSS, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 50cd7707040c..f05ba8b7af61 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4009,7 +4009,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy, params->sta_flags_mask &= ~BIT(NL80211_STA_FLAG_TDLS_PEER); } - if (statype != CFG80211_STA_TDLS_PEER_SETUP) { + if (statype != CFG80211_STA_TDLS_PEER_SETUP && + statype != CFG80211_STA_AP_CLIENT_UNASSOC) { /* reject other things that can't change */ if (params->sta_modify_mask & STATION_PARAM_APPLY_UAPSD) return -EINVAL; @@ -4021,7 +4022,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy, return -EINVAL; } - if (statype != CFG80211_STA_AP_CLIENT) { + if (statype != CFG80211_STA_AP_CLIENT && + statype != CFG80211_STA_AP_CLIENT_UNASSOC) { if (params->vlan) return -EINVAL; } @@ -4033,6 +4035,7 @@ int cfg80211_check_station_change(struct wiphy *wiphy, return -EOPNOTSUPP; break; case CFG80211_STA_AP_CLIENT: + case CFG80211_STA_AP_CLIENT_UNASSOC: /* accept only the listed bits */ if (params->sta_flags_mask & ~(BIT(NL80211_STA_FLAG_AUTHORIZED) | -- cgit v1.2.3 From 372892ec1151c895c7dec362f3246f089690cfc7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 25 Sep 2015 15:07:27 -0500 Subject: ipv4: Push struct net down into nf_send_reset This is needed so struct net can be pushed down into ip_route_me_harder. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/ipv4/nf_reject.h | 2 +- net/ipv4/netfilter/ipt_REJECT.c | 2 +- net/ipv4/netfilter/nf_reject_ipv4.c | 2 +- net/ipv4/netfilter/nft_reject_ipv4.c | 2 +- net/netfilter/nft_reject_inet.c | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h index 77862c3645f0..df7ecd806aba 100644 --- a/include/net/netfilter/ipv4/nf_reject.h +++ b/include/net/netfilter/ipv4/nf_reject.h @@ -6,7 +6,7 @@ #include void nf_send_unreach(struct sk_buff *skb_in, int code, int hook); -void nf_send_reset(struct sk_buff *oldskb, int hook); +void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook); const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook); diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 87907d4bd259..1d16c0f28df0 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -59,7 +59,7 @@ reject_tg(struct sk_buff *skb, const struct xt_action_param *par) nf_send_unreach(skb, ICMP_PKT_FILTERED, hook); break; case IPT_TCP_RESET: - nf_send_reset(skb, hook); + nf_send_reset(par->net, skb, hook); case IPT_ICMP_ECHOREPLY: /* Doesn't happen. */ break; diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 3262e41ff76f..fb337406b1d2 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -99,7 +99,7 @@ void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put); /* Send RST reply */ -void nf_send_reset(struct sk_buff *oldskb, int hook) +void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) { struct sk_buff *nskb; const struct iphdr *oiph; diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index c1582e03b628..c24f41c816b3 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -30,7 +30,7 @@ static void nft_reject_ipv4_eval(const struct nft_expr *expr, nf_send_unreach(pkt->skb, priv->icmp_code, pkt->hook); break; case NFT_REJECT_TCP_RST: - nf_send_reset(pkt->skb, pkt->hook); + nf_send_reset(pkt->net, pkt->skb, pkt->hook); break; default: break; diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 0bc19f97e238..759ca5248a3d 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -31,7 +31,7 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, pkt->hook); break; case NFT_REJECT_TCP_RST: - nf_send_reset(pkt->skb, pkt->hook); + nf_send_reset(pkt->net, pkt->skb, pkt->hook); break; case NFT_REJECT_ICMPX_UNREACH: nf_send_unreach(pkt->skb, -- cgit v1.2.3 From d815d90bbbc08777c0e3a36f57b97fc4a4fb3150 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 25 Sep 2015 15:07:28 -0500 Subject: netfilter: Push struct net down into nf_afinfo.reroute The network namespace is needed when routing a packet. Stop making nf_afinfo.reroute guess which network namespace is the proper namespace to route the packet in. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 +- net/ipv4/netfilter.c | 2 +- net/ipv6/netfilter.c | 2 +- net/netfilter/nf_queue.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 987c74cd523c..165ab2d14734 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -283,7 +283,7 @@ struct nf_afinfo { struct flowi *fl, bool strict); void (*saveroute)(const struct sk_buff *skb, struct nf_queue_entry *entry); - int (*reroute)(struct sk_buff *skb, + int (*reroute)(struct net *net, struct sk_buff *skb, const struct nf_queue_entry *entry); int route_key_size; }; diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 61eafc9b4545..9e07e6f23398 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -104,7 +104,7 @@ static void nf_ip_saveroute(const struct sk_buff *skb, } } -static int nf_ip_reroute(struct sk_buff *skb, +static int nf_ip_reroute(struct net *net, struct sk_buff *skb, const struct nf_queue_entry *entry) { const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index b4de08a83e0b..26911b93dc7a 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -93,7 +93,7 @@ static void nf_ip6_saveroute(const struct sk_buff *skb, } } -static int nf_ip6_reroute(struct sk_buff *skb, +static int nf_ip6_reroute(struct net *net, struct sk_buff *skb, const struct nf_queue_entry *entry) { struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 9f3c3c25fa73..34f628e16a4c 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -199,7 +199,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) if (verdict == NF_ACCEPT) { afinfo = nf_get_afinfo(entry->state.pf); - if (!afinfo || afinfo->reroute(skb, entry) < 0) + if (!afinfo || afinfo->reroute(entry->state.net, skb, entry) < 0) verdict = NF_DROP; } -- cgit v1.2.3 From e45f50660ee5fd38a540afabb7c0f65d063db631 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 25 Sep 2015 15:07:30 -0500 Subject: ipv4: Pass struct net into ip_route_me_harder Don't make ip_route_me_harder guess which network namespace it is routing in, pass the network namespace in. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv4.h | 2 +- net/ipv4/netfilter.c | 5 ++--- net/ipv4/netfilter/ipt_SYNPROXY.c | 4 +++- net/ipv4/netfilter/iptable_mangle.c | 2 +- net/ipv4/netfilter/nf_nat_l3proto_ipv4.c | 2 +- net/ipv4/netfilter/nf_reject_ipv4.c | 2 +- net/ipv4/netfilter/nft_chain_route_ipv4.c | 2 +- net/netfilter/ipvs/ip_vs_core.c | 2 +- 8 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 6e4591bb54d4..98c03b2462b5 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -6,7 +6,7 @@ #include -int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type); +int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type); __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); #endif /*__LINUX_IP_NETFILTER_H*/ diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 9e07e6f23398..c3776ff6749f 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -17,9 +17,8 @@ #include /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ -int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type) +int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type) { - struct net *net = dev_net(skb_dst(skb)->dev); const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi4 fl4 = {}; @@ -116,7 +115,7 @@ static int nf_ip_reroute(struct net *net, struct sk_buff *skb, skb->mark == rt_info->mark && iph->daddr == rt_info->daddr && iph->saddr == rt_info->saddr)) - return ip_route_me_harder(skb, RTN_UNSPEC); + return ip_route_me_harder(net, skb, RTN_UNSPEC); } return 0; } diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 0060d9abd514..6a6e762ab27f 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -45,6 +45,8 @@ synproxy_send_tcp(const struct synproxy_net *snet, struct iphdr *niph, struct tcphdr *nth, unsigned int tcp_hdr_size) { + struct net *net = nf_ct_net(snet->tmpl); + nth->check = ~tcp_v4_check(tcp_hdr_size, niph->saddr, niph->daddr, 0); nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (unsigned char *)nth - nskb->head; @@ -52,7 +54,7 @@ synproxy_send_tcp(const struct synproxy_net *snet, skb_dst_set_noref(nskb, skb_dst(skb)); nskb->protocol = htons(ETH_P_IP); - if (ip_route_me_harder(nskb, RTN_UNSPEC)) + if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) goto free_nskb; if (nfct) { diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 2d6fc911866f..ba5d392a13c4 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -67,7 +67,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) iph->daddr != daddr || skb->mark != mark || iph->tos != tos) { - err = ip_route_me_harder(skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index bc3b9dcbf080..5075b7ecd26d 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -431,7 +431,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, if (ct->tuplehash[dir].tuple.dst.u3.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { - err = ip_route_me_harder(skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index fb337406b1d2..2f5e925d3264 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -129,7 +129,7 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) ip4_dst_hoplimit(skb_dst(nskb))); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); - if (ip_route_me_harder(nskb, RTN_UNSPEC)) + if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) goto free_nskb; /* "Never happens" */ diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c index 9f486b302108..2375b0a8be46 100644 --- a/net/ipv4/netfilter/nft_chain_route_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c @@ -53,7 +53,7 @@ static unsigned int nf_route_table_hook(void *priv, iph->daddr != daddr || skb->mark != mark || iph->tos != tos) - if (ip_route_me_harder(skb, RTN_UNSPEC)) + if (ip_route_me_harder(state->net, skb, RTN_UNSPEC)) ret = NF_DROP; } return ret; diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index fb6b6c87d841..800b085242a8 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -720,7 +720,7 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, } else #endif if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && - ip_route_me_harder(skb, RTN_LOCAL) != 0) + ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0) return 1; return 0; -- cgit v1.2.3 From 5f5d74d723146c5b97c7318b5851af15b30e3304 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 25 Sep 2015 15:07:31 -0500 Subject: ipv6: Pass struct net into ip6_route_me_harder Don't make ip6_route_me_harder guess which network namespace it is routing in, pass the network namespace in. Signed-off-by: Eric W. Biederman Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 2 +- net/ipv6/netfilter.c | 5 ++--- net/ipv6/netfilter/ip6table_mangle.c | 2 +- net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 2 +- net/ipv6/netfilter/nft_chain_route_ipv6.c | 2 +- net/netfilter/ipvs/ip_vs_core.c | 2 +- 6 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 771574677e83..2ac8369fa96c 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -22,7 +22,7 @@ struct nf_ipv6_ops { }; #ifdef CONFIG_NETFILTER -int ip6_route_me_harder(struct sk_buff *skb); +int ip6_route_me_harder(struct net *net, struct sk_buff *skb); __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 26911b93dc7a..d11c46833d61 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -18,9 +18,8 @@ #include #include -int ip6_route_me_harder(struct sk_buff *skb) +int ip6_route_me_harder(struct net *net, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); const struct ipv6hdr *iph = ipv6_hdr(skb); unsigned int hh_len; struct dst_entry *dst; @@ -103,7 +102,7 @@ static int nf_ip6_reroute(struct net *net, struct sk_buff *skb, if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) || !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) || skb->mark != rt_info->mark) - return ip6_route_me_harder(skb); + return ip6_route_me_harder(net, skb); } return 0; } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 8745b592b2f6..abe278b07932 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -65,7 +65,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { - err = ip6_route_me_harder(skb); + err = ip6_route_me_harder(state->net, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 18e835ffbef3..238e70c3f7b7 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -437,7 +437,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { - err = ip6_route_me_harder(skb); + err = ip6_route_me_harder(state->net, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c index d42bbc1d7555..9df75bd7c94a 100644 --- a/net/ipv6/netfilter/nft_chain_route_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c @@ -52,7 +52,7 @@ static unsigned int nf_route_table_hook(void *priv, skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) - return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP; + return ip6_route_me_harder(state->net, skb) == 0 ? ret : NF_DROP; return ret; } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 800b085242a8..37dd77a3d0fb 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -715,7 +715,7 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, struct dst_entry *dst = skb_dst(skb); if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && - ip6_route_me_harder(skb) != 0) + ip6_route_me_harder(ipvs->net, skb) != 0) return 1; } else #endif -- cgit v1.2.3 From c1444c6357217cea405415b4c96491d4057b0746 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 25 Sep 2015 16:52:51 -0500 Subject: bridge: Pass net into br_validate_ipv4 and br_validate_ipv6 The network namespace is easiliy available in state->net so use it. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/br_netfilter.h | 4 ++-- net/bridge/br_netfilter_hooks.c | 19 +++++++++---------- net/bridge/br_netfilter_ipv6.c | 11 +++++------ 3 files changed, 16 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index c93c75fa41ad..e8d1448425a7 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -45,12 +45,12 @@ struct net_device *setup_pre_routing(struct sk_buff *skb); void br_netfilter_enable(void); #if IS_ENABLED(CONFIG_IPV6) -int br_validate_ipv6(struct sk_buff *skb); +int br_validate_ipv6(struct net *net, struct sk_buff *skb); unsigned int br_nf_pre_routing_ipv6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); #else -static inline int br_validate_ipv6(struct sk_buff *skb) +static inline int br_validate_ipv6(struct net *net, struct sk_buff *skb) { return -1; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index e21e44c13e07..13f03671c88d 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -189,10 +189,9 @@ static inline void nf_bridge_pull_encap_header_rcsum(struct sk_buff *skb) * expected format */ -static int br_validate_ipv4(struct sk_buff *skb) +static int br_validate_ipv4(struct net *net, struct sk_buff *skb) { const struct iphdr *iph; - struct net_device *dev = skb->dev; u32 len; if (!pskb_may_pull(skb, sizeof(struct iphdr))) @@ -213,13 +212,13 @@ static int br_validate_ipv4(struct sk_buff *skb) len = ntohs(iph->tot_len); if (skb->len < len) { - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INTRUNCATEDPKTS); + IP_INC_STATS_BH(net, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } else if (len < (iph->ihl*4)) goto inhdr_error; if (pskb_trim_rcsum(skb, len)) { - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS); + IP_INC_STATS_BH(net, IPSTATS_MIB_INDISCARDS); goto drop; } @@ -232,7 +231,7 @@ static int br_validate_ipv4(struct sk_buff *skb) return 0; inhdr_error: - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS); + IP_INC_STATS_BH(net, IPSTATS_MIB_INHDRERRORS); drop: return -1; } @@ -497,7 +496,7 @@ static unsigned int br_nf_pre_routing(void *priv, nf_bridge_pull_encap_header_rcsum(skb); - if (br_validate_ipv4(skb)) + if (br_validate_ipv4(state->net, skb)) return NF_DROP; nf_bridge_put(skb->nf_bridge); @@ -609,13 +608,13 @@ static unsigned int br_nf_forward_ip(void *priv, } if (pf == NFPROTO_IPV4) { - if (br_validate_ipv4(skb)) + if (br_validate_ipv4(state->net, skb)) return NF_DROP; IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; } if (pf == NFPROTO_IPV6) { - if (br_validate_ipv6(skb)) + if (br_validate_ipv6(state->net, skb)) return NF_DROP; IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; } @@ -747,7 +746,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff if (skb->protocol == htons(ETH_P_IP)) { struct brnf_frag_data *data; - if (br_validate_ipv4(skb)) + if (br_validate_ipv4(net, skb)) goto drop; IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; @@ -772,7 +771,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); struct brnf_frag_data *data; - if (br_validate_ipv6(skb)) + if (br_validate_ipv6(net, skb)) goto drop; IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index c51cc3fd50d9..d61f56efc8dc 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -100,10 +100,9 @@ bad: return -1; } -int br_validate_ipv6(struct sk_buff *skb) +int br_validate_ipv6(struct net *net, struct sk_buff *skb) { const struct ipv6hdr *hdr; - struct net_device *dev = skb->dev; struct inet6_dev *idev = __in6_dev_get(skb->dev); u32 pkt_len; u8 ip6h_len = sizeof(struct ipv6hdr); @@ -123,12 +122,12 @@ int br_validate_ipv6(struct sk_buff *skb) if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) { if (pkt_len + ip6h_len > skb->len) { - IP6_INC_STATS_BH(dev_net(dev), idev, + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } if (pskb_trim_rcsum(skb, pkt_len + ip6h_len)) { - IP6_INC_STATS_BH(dev_net(dev), idev, + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } @@ -143,7 +142,7 @@ int br_validate_ipv6(struct sk_buff *skb) return 0; inhdr_error: - IP6_INC_STATS_BH(dev_net(dev), idev, IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); drop: return -1; } @@ -224,7 +223,7 @@ unsigned int br_nf_pre_routing_ipv6(void *priv, { struct nf_bridge_info *nf_bridge; - if (br_validate_ipv6(skb)) + if (br_validate_ipv6(state->net, skb)) return NF_DROP; nf_bridge_put(skb->nf_bridge); -- cgit v1.2.3 From 2594e9064a57634efc146ff4e89a5de562e05011 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 25 Sep 2015 19:00:11 +0200 Subject: bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 1 + net/bridge/br_device.c | 2 +- net/bridge/br_fdb.c | 76 ++--- net/bridge/br_forward.c | 15 +- net/bridge/br_input.c | 10 +- net/bridge/br_mdb.c | 24 +- net/bridge/br_netlink.c | 174 +++++----- net/bridge/br_private.h | 191 ++++++++--- net/bridge/br_vlan.c | 699 +++++++++++++++++++++++++---------------- 9 files changed, 732 insertions(+), 460 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 3635b7797508..18db14477bdd 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -127,6 +127,7 @@ enum { #define BRIDGE_VLAN_INFO_UNTAGGED (1<<2) /* VLAN egresses untagged */ #define BRIDGE_VLAN_INFO_RANGE_BEGIN (1<<3) /* VLAN is start of vlan range */ #define BRIDGE_VLAN_INFO_RANGE_END (1<<4) /* VLAN is end of vlan range */ +#define BRIDGE_VLAN_INFO_BRENTRY (1<<5) /* Global bridge VLAN entry */ struct bridge_vlan_info { __u16 flags; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 2f81624a8257..c915c5b408ea 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -56,7 +56,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb); skb_pull(skb, ETH_HLEN); - if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid)) + if (!br_allowed_ingress(br, skb, &vid)) goto out; if (is_broadcast_ether_addr(dest)) diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 6663cc0789a6..41de11e2eb11 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -163,22 +163,27 @@ static void fdb_delete_local(struct net_bridge *br, struct net_bridge_fdb_entry *f) { const unsigned char *addr = f->addr.addr; - u16 vid = f->vlan_id; + struct net_bridge_vlan_group *vg; + const struct net_bridge_vlan *v; struct net_bridge_port *op; + u16 vid = f->vlan_id; /* Maybe another port has same hw addr? */ list_for_each_entry(op, &br->port_list, list) { + vg = nbp_vlan_group(op); if (op != p && ether_addr_equal(op->dev->dev_addr, addr) && - (!vid || nbp_vlan_find(op, vid))) { + (!vid || br_vlan_find(vg, vid))) { f->dst = op; f->added_by_user = 0; return; } } + vg = br_vlan_group(br); + v = br_vlan_find(vg, vid); /* Maybe bridge device has same hw addr? */ if (p && ether_addr_equal(br->dev->dev_addr, addr) && - (!vid || br_vlan_find(br, vid))) { + (!vid || (v && br_vlan_should_use(v)))) { f->dst = NULL; f->added_by_user = 0; return; @@ -203,14 +208,14 @@ void br_fdb_find_delete_local(struct net_bridge *br, void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) { + struct net_bridge_vlan_group *vg; struct net_bridge *br = p->br; - struct net_port_vlans *pv = nbp_get_vlan_info(p); - bool no_vlan = !pv; + struct net_bridge_vlan *v; int i; - u16 vid; spin_lock_bh(&br->hash_lock); + vg = nbp_vlan_group(p); /* Search all chains since old address/hash is unknown */ for (i = 0; i < BR_HASH_SIZE; i++) { struct hlist_node *h; @@ -226,7 +231,7 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) * configured, we can safely be done at * this point. */ - if (no_vlan) + if (!vg || !vg->num_vlans) goto insert; } } @@ -236,15 +241,15 @@ insert: /* insert new address, may fail if invalid address or dup. */ fdb_insert(br, p, newaddr, 0); - if (no_vlan) + if (!vg || !vg->num_vlans) goto done; /* Now add entries for every VLAN configured on the port. * This function runs under RTNL so the bitmap will not change * from under us. */ - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) - fdb_insert(br, p, newaddr, vid); + list_for_each_entry(v, &vg->vlan_list, vlist) + fdb_insert(br, p, newaddr, v->vid); done: spin_unlock_bh(&br->hash_lock); @@ -252,9 +257,9 @@ done: void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) { + struct net_bridge_vlan_group *vg; struct net_bridge_fdb_entry *f; - struct net_port_vlans *pv; - u16 vid = 0; + struct net_bridge_vlan *v; spin_lock_bh(&br->hash_lock); @@ -264,20 +269,18 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, 0); - + vg = br_vlan_group(br); + if (!vg || !vg->num_vlans) + goto out; /* Now remove and add entries for every VLAN configured on the * bridge. This function runs under RTNL so the bitmap will not * change from under us. */ - pv = br_get_vlan_info(br); - if (!pv) - goto out; - - for_each_set_bit_from(vid, pv->vlan_bitmap, VLAN_N_VID) { - f = __br_fdb_get(br, br->dev->dev_addr, vid); + list_for_each_entry(v, &vg->vlan_list, vlist) { + f = __br_fdb_get(br, br->dev->dev_addr, v->vid); if (f && f->is_local && !f->dst) fdb_delete_local(br, NULL, f); - fdb_insert(br, NULL, newaddr, vid); + fdb_insert(br, NULL, newaddr, v->vid); } out: spin_unlock_bh(&br->hash_lock); @@ -844,9 +847,10 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlh_flags) { + struct net_bridge_vlan_group *vg; struct net_bridge_port *p; + struct net_bridge_vlan *v; int err = 0; - struct net_port_vlans *pv; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) { pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); @@ -865,9 +869,10 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return -EINVAL; } - pv = nbp_get_vlan_info(p); + vg = nbp_vlan_group(p); if (vid) { - if (!pv || !test_bit(vid, pv->vlan_bitmap)) { + v = br_vlan_find(vg, vid); + if (!v) { pr_info("bridge: RTM_NEWNEIGH with unconfigured " "vlan %d on port %s\n", vid, dev->name); return -EINVAL; @@ -877,15 +882,15 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); } else { err = __br_fdb_add(ndm, p, addr, nlh_flags, 0); - if (err || !pv) + if (err || !vg || !vg->num_vlans) goto out; /* We have vlans configured on this port and user didn't * specify a VLAN. To be nice, add/update entry for every * vlan on this port. */ - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); + list_for_each_entry(v, &vg->vlan_list, vlist) { + err = __br_fdb_add(ndm, p, addr, nlh_flags, v->vid); if (err) goto out; } @@ -927,9 +932,10 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid) { + struct net_bridge_vlan_group *vg; struct net_bridge_port *p; + struct net_bridge_vlan *v; int err; - struct net_port_vlans *pv; p = br_port_get_rtnl(dev); if (p == NULL) { @@ -938,9 +944,10 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], return -EINVAL; } - pv = nbp_get_vlan_info(p); + vg = nbp_vlan_group(p); if (vid) { - if (!pv || !test_bit(vid, pv->vlan_bitmap)) { + v = br_vlan_find(vg, vid); + if (!v) { pr_info("bridge: RTM_DELNEIGH with unconfigured " "vlan %d on port %s\n", vid, dev->name); return -EINVAL; @@ -950,16 +957,11 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], } else { err = -ENOENT; err &= __br_fdb_delete(p, addr, 0); - if (!pv) + if (!vg || !vg->num_vlans) goto out; - /* We have vlans configured on this port and user didn't - * specify a VLAN. To be nice, add/update entry for every - * vlan on this port. - */ - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - err &= __br_fdb_delete(p, addr, vid); - } + list_for_each_entry(v, &vg->vlan_list, vlist) + err &= __br_fdb_delete(p, addr, v->vid); } out: return err; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 48afca729ed7..6d5ed795c3e2 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -30,9 +30,11 @@ static int deliver_clone(const struct net_bridge_port *prev, static inline int should_deliver(const struct net_bridge_port *p, const struct sk_buff *skb) { + struct net_bridge_vlan_group *vg; + + vg = nbp_vlan_group(p); return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && - br_allowed_egress(p->br, nbp_get_vlan_info(p), skb) && - p->state == BR_STATE_FORWARDING; + br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING; } int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -76,7 +78,10 @@ EXPORT_SYMBOL_GPL(br_forward_finish); static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) { - skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb); + struct net_bridge_vlan_group *vg; + + vg = nbp_vlan_group(to); + skb = br_handle_vlan(to->br, vg, skb); if (!skb) return; @@ -99,6 +104,7 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) { + struct net_bridge_vlan_group *vg; struct net_device *indev; if (skb_warn_if_lro(skb)) { @@ -106,7 +112,8 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) return; } - skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb); + vg = nbp_vlan_group(to); + skb = br_handle_vlan(to->br, vg, skb); if (!skb) return; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 223f4040d9df..e27d0dfd2ee9 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -36,28 +36,28 @@ static int br_pass_frame_up(struct sk_buff *skb) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; struct net_bridge *br = netdev_priv(brdev); + struct net_bridge_vlan_group *vg; struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); - struct net_port_vlans *pv; u64_stats_update_begin(&brstats->syncp); brstats->rx_packets++; brstats->rx_bytes += skb->len; u64_stats_update_end(&brstats->syncp); + vg = br_vlan_group(br); /* Bridge is just like any other port. Make sure the * packet is allowed except in promisc modue when someone * may be running packet capture. */ - pv = br_get_vlan_info(br); if (!(brdev->flags & IFF_PROMISC) && - !br_allowed_egress(br, pv, skb)) { + !br_allowed_egress(vg, skb)) { kfree_skb(skb); return NET_RX_DROP; } indev = skb->dev; skb->dev = brdev; - skb = br_handle_vlan(br, pv, skb); + skb = br_handle_vlan(br, vg, skb); if (!skb) return NET_RX_DROP; @@ -140,7 +140,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (!p || p->state == BR_STATE_DISABLED) goto drop; - if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid)) + if (!nbp_allowed_ingress(p, skb, &vid)) goto out; /* insert into forwarding database after filtering to avoid spoofing */ diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index d747275fad18..cd8deea2d074 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -464,11 +464,11 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - unsigned short vid = VLAN_N_VID; + struct net_bridge_vlan_group *vg; struct net_device *dev, *pdev; struct br_mdb_entry *entry; struct net_bridge_port *p; - struct net_port_vlans *pv; + struct net_bridge_vlan *v; struct net_bridge *br; int err; @@ -489,10 +489,10 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) if (!p || p->br != br || p->state == BR_STATE_DISABLED) return -EINVAL; - pv = nbp_get_vlan_info(p); - if (br_vlan_enabled(br) && pv && entry->vid == 0) { - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - entry->vid = vid; + vg = nbp_vlan_group(p); + if (br_vlan_enabled(br) && vg && entry->vid == 0) { + list_for_each_entry(v, &vg->vlan_list, vlist) { + entry->vid = v->vid; err = __br_mdb_add(net, br, entry); if (err) break; @@ -566,11 +566,11 @@ unlock: static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - unsigned short vid = VLAN_N_VID; + struct net_bridge_vlan_group *vg; struct net_device *dev, *pdev; struct br_mdb_entry *entry; struct net_bridge_port *p; - struct net_port_vlans *pv; + struct net_bridge_vlan *v; struct net_bridge *br; int err; @@ -591,10 +591,10 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) if (!p || p->br != br || p->state == BR_STATE_DISABLED) return -EINVAL; - pv = nbp_get_vlan_info(p); - if (br_vlan_enabled(br) && pv && entry->vid == 0) { - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - entry->vid = vid; + vg = nbp_vlan_group(p); + if (br_vlan_enabled(br) && vg && entry->vid == 0) { + list_for_each_entry(v, &vg->vlan_list, vlist) { + entry->vid = v->vid; err = __br_mdb_del(br, entry); if (!err) __br_mdb_notify(dev, entry, RTM_DELMDB); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index ea748c93a07f..bb8bb7b36f04 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -21,36 +21,35 @@ #include "br_private.h" #include "br_private_stp.h" -static int br_get_num_vlan_infos(const struct net_port_vlans *pv, - u32 filter_mask) +static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, + u32 filter_mask, + u16 pvid) { - u16 vid_range_start = 0, vid_range_end = 0; - u16 vid_range_flags = 0; - u16 pvid, vid, flags; + struct net_bridge_vlan *v; + u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; + u16 flags; int num_vlans = 0; - if (filter_mask & RTEXT_FILTER_BRVLAN) - return pv->num_vlans; - if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; - /* Count number of vlan info's - */ - pvid = br_get_pvid(pv); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + /* Count number of vlan infos */ + list_for_each_entry(v, &vg->vlan_list, vlist) { flags = 0; - if (vid == pvid) + /* only a context, bridge vlan not activated */ + if (!br_vlan_should_use(v)) + continue; + if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; - if (test_bit(vid, pv->untagged_bitmap)) + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; - } else if ((vid - vid_range_end) == 1 && + } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { - vid_range_end = vid; + vid_range_end = v->vid; continue; } else { if ((vid_range_end - vid_range_start) > 0) @@ -59,8 +58,8 @@ static int br_get_num_vlan_infos(const struct net_port_vlans *pv, num_vlans += 1; } initvars: - vid_range_start = vid; - vid_range_end = vid; + vid_range_start = v->vid; + vid_range_end = v->vid; vid_range_flags = flags; } @@ -74,28 +73,40 @@ initvars: return num_vlans; } +static int br_get_num_vlan_infos(struct net_bridge_vlan_group *vg, + u32 filter_mask, u16 pvid) +{ + if (!vg) + return 0; + + if (filter_mask & RTEXT_FILTER_BRVLAN) + return vg->num_vlans; + + return __get_num_vlan_infos(vg, filter_mask, pvid); +} + static size_t br_get_link_af_size_filtered(const struct net_device *dev, u32 filter_mask) { - struct net_port_vlans *pv; + struct net_bridge_vlan_group *vg = NULL; + struct net_bridge_port *p; + struct net_bridge *br; int num_vlan_infos; + u16 pvid = 0; rcu_read_lock(); - if (br_port_exists(dev)) - pv = nbp_get_vlan_info(br_port_get_rcu(dev)); - else if (dev->priv_flags & IFF_EBRIDGE) - pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); - else - pv = NULL; - if (pv) - num_vlan_infos = br_get_num_vlan_infos(pv, filter_mask); - else - num_vlan_infos = 0; + if (br_port_exists(dev)) { + p = br_port_get_rcu(dev); + vg = nbp_vlan_group(p); + pvid = nbp_get_pvid(p); + } else if (dev->priv_flags & IFF_EBRIDGE) { + br = netdev_priv(dev); + vg = br_vlan_group(br); + pvid = br_get_pvid(br); + } + num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask, pvid); rcu_read_unlock(); - if (!num_vlan_infos) - return 0; - /* Each VLAN is returned in bridge_vlan_info along with flags */ return num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); } @@ -185,31 +196,33 @@ nla_put_failure: } static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, - const struct net_port_vlans *pv) + struct net_bridge_vlan_group *vg, + u16 pvid) { - u16 vid_range_start = 0, vid_range_end = 0; - u16 vid_range_flags = 0; - u16 pvid, vid, flags; + struct net_bridge_vlan *v; + u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; + u16 flags; int err = 0; /* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan * and mark vlan info with begin and end flags * if vlaninfo represents a range */ - pvid = br_get_pvid(pv); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + list_for_each_entry(v, &vg->vlan_list, vlist) { flags = 0; - if (vid == pvid) + if (!br_vlan_should_use(v)) + continue; + if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; - if (test_bit(vid, pv->untagged_bitmap)) + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; - } else if ((vid - vid_range_end) == 1 && + } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { - vid_range_end = vid; + vid_range_end = v->vid; continue; } else { err = br_fill_ifvlaninfo_range(skb, vid_range_start, @@ -220,8 +233,8 @@ static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, } initvars: - vid_range_start = vid; - vid_range_end = vid; + vid_range_start = v->vid; + vid_range_end = v->vid; vid_range_flags = flags; } @@ -238,19 +251,22 @@ initvars: } static int br_fill_ifvlaninfo(struct sk_buff *skb, - const struct net_port_vlans *pv) + struct net_bridge_vlan_group *vg, + u16 pvid) { struct bridge_vlan_info vinfo; - u16 pvid, vid; + struct net_bridge_vlan *v; - pvid = br_get_pvid(pv); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - vinfo.vid = vid; + list_for_each_entry(v, &vg->vlan_list, vlist) { + if (!br_vlan_should_use(v)) + continue; + + vinfo.vid = v->vid; vinfo.flags = 0; - if (vid == pvid) + if (v->vid == pvid) vinfo.flags |= BRIDGE_VLAN_INFO_PVID; - if (test_bit(vid, pv->untagged_bitmap)) + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, @@ -269,11 +285,11 @@ nla_put_failure: * Contains port and master info as well as carrier and bridge state. */ static int br_fill_ifinfo(struct sk_buff *skb, - const struct net_bridge_port *port, + struct net_bridge_port *port, u32 pid, u32 seq, int event, unsigned int flags, u32 filter_mask, const struct net_device *dev) { - const struct net_bridge *br; + struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; @@ -320,16 +336,20 @@ static int br_fill_ifinfo(struct sk_buff *skb, /* Check if the VID information is requested */ if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { - const struct net_port_vlans *pv; + struct net_bridge_vlan_group *vg; struct nlattr *af; + u16 pvid; int err; - if (port) - pv = nbp_get_vlan_info(port); - else - pv = br_get_vlan_info(br); + if (port) { + vg = nbp_vlan_group(port); + pvid = nbp_get_pvid(port); + } else { + vg = br_vlan_group(br); + pvid = br_get_pvid(br); + } - if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) + if (!vg || !vg->num_vlans) goto done; af = nla_nest_start(skb, IFLA_AF_SPEC); @@ -337,9 +357,9 @@ static int br_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) - err = br_fill_ifvlaninfo_compressed(skb, pv); + err = br_fill_ifvlaninfo_compressed(skb, vg, pvid); else - err = br_fill_ifvlaninfo(skb, pv); + err = br_fill_ifvlaninfo(skb, vg, pvid); if (err) goto nla_put_failure; nla_nest_end(skb, af); @@ -413,14 +433,14 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, switch (cmd) { case RTM_SETLINK: if (p) { + /* if the MASTER flag is set this will act on the global + * per-VLAN entry as well + */ err = nbp_vlan_add(p, vinfo->vid, vinfo->flags); if (err) break; - - if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) - err = br_vlan_add(p->br, vinfo->vid, - vinfo->flags); } else { + vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY; err = br_vlan_add(br, vinfo->vid, vinfo->flags); } break; @@ -857,20 +877,22 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) static size_t br_get_link_af_size(const struct net_device *dev) { - struct net_port_vlans *pv; - - if (br_port_exists(dev)) - pv = nbp_get_vlan_info(br_port_get_rtnl(dev)); - else if (dev->priv_flags & IFF_EBRIDGE) - pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); - else - return 0; + struct net_bridge_port *p; + struct net_bridge *br; + int num_vlans = 0; - if (!pv) - return 0; + if (br_port_exists(dev)) { + p = br_port_get_rtnl(dev); + num_vlans = br_get_num_vlan_infos(nbp_vlan_group(p), + RTEXT_FILTER_BRVLAN, 0); + } else if (dev->priv_flags & IFF_EBRIDGE) { + br = netdev_priv(dev); + num_vlans = br_get_num_vlan_infos(br_vlan_group(br), + RTEXT_FILTER_BRVLAN, 0); + } /* Each VLAN is returned in bridge_vlan_info along with flags */ - return pv->num_vlans * nla_total_size(sizeof(struct bridge_vlan_info)); + return num_vlans * nla_total_size(sizeof(struct bridge_vlan_info)); } static struct rtnl_af_ops br_af_ops __read_mostly = { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 74e99c75c8e4..cfe945f5ab8b 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -20,6 +20,7 @@ #include #include #include +#include #define BR_HASH_BITS 8 #define BR_HASH_SIZE (1 << BR_HASH_BITS) @@ -28,7 +29,6 @@ #define BR_PORT_BITS 10 #define BR_MAX_PORTS (1<bridge_id, &br->designated_root, 8); } +/* check if a VLAN entry is global */ +static inline bool br_vlan_is_master(const struct net_bridge_vlan *v) +{ + return v->flags & BRIDGE_VLAN_INFO_MASTER; +} + +/* check if a VLAN entry is used by the bridge */ +static inline bool br_vlan_is_brentry(const struct net_bridge_vlan *v) +{ + return v->flags & BRIDGE_VLAN_INFO_BRENTRY; +} + +/* check if we should use the vlan entry is usable */ +static inline bool br_vlan_should_use(const struct net_bridge_vlan *v) +{ + if (br_vlan_is_master(v)) { + if (br_vlan_is_brentry(v)) + return true; + else + return false; + } + + return true; +} + /* br_device.c */ void br_dev_setup(struct net_device *dev); void br_dev_delete(struct net_device *dev, struct list_head *list); @@ -601,18 +670,19 @@ static inline void br_mdb_uninit(void) /* br_vlan.c */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING -bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, - struct sk_buff *skb, u16 *vid); -bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v, +bool br_allowed_ingress(struct net_bridge *br, struct sk_buff *skb, u16 *vid); +bool nbp_allowed_ingress(struct net_bridge_port *p, struct sk_buff *skb, + u16 *vid); +bool br_allowed_egress(struct net_bridge_vlan_group *br, const struct sk_buff *skb); bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid); struct sk_buff *br_handle_vlan(struct net_bridge *br, - const struct net_port_vlans *v, + struct net_bridge_vlan_group *vg, struct sk_buff *skb); int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags); int br_vlan_delete(struct net_bridge *br, u16 vid); void br_vlan_flush(struct net_bridge *br); -bool br_vlan_find(struct net_bridge *br, u16 vid); +struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid); void br_recalculate_fwd_mask(struct net_bridge *br); int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); @@ -623,19 +693,19 @@ int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val); int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags); int nbp_vlan_delete(struct net_bridge_port *port, u16 vid); void nbp_vlan_flush(struct net_bridge_port *port); -bool nbp_vlan_find(struct net_bridge_port *port, u16 vid); int nbp_vlan_init(struct net_bridge_port *port); +int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask); -static inline struct net_port_vlans *br_get_vlan_info( - const struct net_bridge *br) +static inline struct net_bridge_vlan_group *br_vlan_group( + const struct net_bridge *br) { - return rcu_dereference_rtnl(br->vlan_info); + return br->vlgrp; } -static inline struct net_port_vlans *nbp_get_vlan_info( - const struct net_bridge_port *p) +static inline struct net_bridge_vlan_group *nbp_vlan_group( + const struct net_bridge_port *p) { - return rcu_dereference_rtnl(p->vlan_info); + return p->vlgrp; } /* Since bridge now depends on 8021Q module, but the time bridge sees the @@ -645,9 +715,9 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid) { int err = 0; - if (skb_vlan_tag_present(skb)) + if (skb_vlan_tag_present(skb)) { *vid = skb_vlan_tag_get(skb) & VLAN_VID_MASK; - else { + } else { *vid = 0; err = -EINVAL; } @@ -655,13 +725,22 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid) return err; } -static inline u16 br_get_pvid(const struct net_port_vlans *v) +static inline u16 br_get_pvid(const struct net_bridge *br) { - if (!v) + if (!br) return 0; smp_rmb(); - return v->pvid; + return br->pvid; +} + +static inline u16 nbp_get_pvid(const struct net_bridge_port *p) +{ + if (!p) + return 0; + + smp_rmb(); + return p->pvid; } static inline int br_vlan_enabled(struct net_bridge *br) @@ -670,15 +749,20 @@ static inline int br_vlan_enabled(struct net_bridge *br) } #else static inline bool br_allowed_ingress(struct net_bridge *br, - struct net_port_vlans *v, struct sk_buff *skb, u16 *vid) { return true; } -static inline bool br_allowed_egress(struct net_bridge *br, - const struct net_port_vlans *v, +static inline bool nbp_allowed_ingress(struct net_bridge_port *p, + struct sk_buff *skb, + u16 *vid) +{ + return true; +} + +static inline bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb) { return true; @@ -691,7 +775,7 @@ static inline bool br_should_learn(struct net_bridge_port *p, } static inline struct sk_buff *br_handle_vlan(struct net_bridge *br, - const struct net_port_vlans *v, + struct net_bridge_vlan_group *vg, struct sk_buff *skb) { return skb; @@ -711,11 +795,6 @@ static inline void br_vlan_flush(struct net_bridge *br) { } -static inline bool br_vlan_find(struct net_bridge *br, u16 vid) -{ - return false; -} - static inline void br_recalculate_fwd_mask(struct net_bridge *br) { } @@ -739,32 +818,28 @@ static inline void nbp_vlan_flush(struct net_bridge_port *port) { } -static inline struct net_port_vlans *br_get_vlan_info( - const struct net_bridge *br) -{ - return NULL; -} -static inline struct net_port_vlans *nbp_get_vlan_info( - const struct net_bridge_port *p) +static inline struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, + u16 vid) { return NULL; } -static inline bool nbp_vlan_find(struct net_bridge_port *port, u16 vid) +static inline int nbp_vlan_init(struct net_bridge_port *port) { - return false; + return 0; } -static inline int nbp_vlan_init(struct net_bridge_port *port) +static inline u16 br_vlan_get_tag(const struct sk_buff *skb, u16 *tag) { return 0; } -static inline u16 br_vlan_get_tag(const struct sk_buff *skb, u16 *tag) +static inline u16 br_get_pvid(const struct net_bridge *br) { return 0; } -static inline u16 br_get_pvid(const struct net_port_vlans *v) + +static inline u16 nbp_get_pvid(const struct net_bridge_port *p) { return 0; } @@ -779,6 +854,24 @@ static inline int __br_vlan_filter_toggle(struct net_bridge *br, { return -EOPNOTSUPP; } + +static inline int nbp_get_num_vlan_infos(struct net_bridge_port *p, + u32 filter_mask) +{ + return 0; +} + +static inline struct net_bridge_vlan_group *br_vlan_group( + const struct net_bridge *br) +{ + return NULL; +} + +static inline struct net_bridge_vlan_group *nbp_vlan_group( + const struct net_bridge_port *p) +{ + return NULL; +} #endif struct nf_br_ops { diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 5f5a02b49a99..8b392070051c 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -6,35 +6,65 @@ #include "br_private.h" -static void __vlan_add_pvid(struct net_port_vlans *v, u16 vid) +static inline int br_vlan_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) { - if (v->pvid == vid) + const struct net_bridge_vlan *vle = ptr; + u16 vid = *(u16 *)arg->key; + + return vle->vid != vid; +} + +static const struct rhashtable_params br_vlan_rht_params = { + .head_offset = offsetof(struct net_bridge_vlan, vnode), + .key_offset = offsetof(struct net_bridge_vlan, vid), + .key_len = sizeof(u16), + .max_size = VLAN_N_VID, + .obj_cmpfn = br_vlan_cmp, + .automatic_shrinking = true, +}; + +static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid) +{ + return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params); +} + +static void __vlan_add_pvid(u16 *pvid, u16 vid) +{ + if (*pvid == vid) return; smp_wmb(); - v->pvid = vid; + *pvid = vid; } -static void __vlan_delete_pvid(struct net_port_vlans *v, u16 vid) +static void __vlan_delete_pvid(u16 *pvid, u16 vid) { - if (v->pvid != vid) + if (*pvid != vid) return; smp_wmb(); - v->pvid = 0; + *pvid = 0; } -static void __vlan_add_flags(struct net_port_vlans *v, u16 vid, u16 flags) +static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags) { - if (flags & BRIDGE_VLAN_INFO_PVID) - __vlan_add_pvid(v, vid); - else - __vlan_delete_pvid(v, vid); + if (flags & BRIDGE_VLAN_INFO_PVID) { + if (br_vlan_is_master(v)) + __vlan_add_pvid(&v->br->pvid, v->vid); + else + __vlan_add_pvid(&v->port->pvid, v->vid); + } else { + if (br_vlan_is_master(v)) + __vlan_delete_pvid(&v->br->pvid, v->vid); + else + __vlan_delete_pvid(&v->port->pvid, v->vid); + } if (flags & BRIDGE_VLAN_INFO_UNTAGGED) - set_bit(vid, v->untagged_bitmap); + v->flags |= BRIDGE_VLAN_INFO_UNTAGGED; else - clear_bit(vid, v->untagged_bitmap); + v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED; } static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, @@ -67,54 +97,26 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, return err; } -static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags) +static void __vlan_add_list(struct net_bridge_vlan *v) { - struct net_bridge_port *p = NULL; - struct net_bridge *br; - struct net_device *dev; - int err; - - if (test_bit(vid, v->vlan_bitmap)) { - __vlan_add_flags(v, vid, flags); - return 0; - } - - if (v->port_idx) { - p = v->parent.port; - br = p->br; - dev = p->dev; - } else { - br = v->parent.br; - dev = br->dev; - } - - if (p) { - /* Add VLAN to the device filter if it is supported. - * This ensures tagged traffic enters the bridge when - * promiscuous mode is disabled by br_manage_promisc(). - */ - err = __vlan_vid_add(dev, br, vid, flags); - if (err) - return err; - } + struct list_head *headp, *hpos; + struct net_bridge_vlan *vent; - err = br_fdb_insert(br, p, dev->dev_addr, vid); - if (err) { - br_err(br, "failed insert local address into bridge " - "forwarding table\n"); - goto out_filt; + headp = br_vlan_is_master(v) ? &v->br->vlgrp->vlan_list : + &v->port->vlgrp->vlan_list; + list_for_each_prev(hpos, headp) { + vent = list_entry(hpos, struct net_bridge_vlan, vlist); + if (v->vid < vent->vid) + continue; + else + break; } + list_add(&v->vlist, hpos); +} - set_bit(vid, v->vlan_bitmap); - v->num_vlans++; - __vlan_add_flags(v, vid, flags); - - return 0; - -out_filt: - if (p) - vlan_vid_del(dev, br->vlan_proto, vid); - return err; +static void __vlan_del_list(struct net_bridge_vlan *v) +{ + list_del(&v->vlist); } static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, @@ -146,63 +148,195 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, return err; } -static int __vlan_del(struct net_port_vlans *v, u16 vid) +/* This is the shared VLAN add function which works for both ports and bridge + * devices. There are four possible calls to this function in terms of the + * vlan entry type: + * 1. vlan is being added on a port (no master flags, global entry exists) + * 2. vlan is being added on a bridge (both master and brvlan flags) + * 3. vlan is being added on a port, but a global entry didn't exist which + * is being created right now (master flag set, brvlan flag unset), the + * global entry is used for global per-vlan features, but not for filtering + * 4. same as 3 but with both master and brvlan flags set so the entry + * will be used for filtering in both the port and the bridge + */ +static int __vlan_add(struct net_bridge_vlan *v, u16 flags) { - if (!test_bit(vid, v->vlan_bitmap)) - return -EINVAL; + struct net_bridge_vlan *masterv = NULL; + struct net_bridge_port *p = NULL; + struct rhashtable *tbl; + struct net_device *dev; + struct net_bridge *br; + int err; + + if (br_vlan_is_master(v)) { + br = v->br; + dev = br->dev; + tbl = &br->vlgrp->vlan_hash; + } else { + p = v->port; + br = p->br; + dev = p->dev; + tbl = &p->vlgrp->vlan_hash; + } + + if (p) { + u16 master_flags = flags; + + /* Add VLAN to the device filter if it is supported. + * This ensures tagged traffic enters the bridge when + * promiscuous mode is disabled by br_manage_promisc(). + */ + err = __vlan_vid_add(dev, br, v->vid, flags); + if (err) + goto out; + + /* need to work on the master vlan too */ + if (flags & BRIDGE_VLAN_INFO_MASTER) { + master_flags |= BRIDGE_VLAN_INFO_BRENTRY; + err = br_vlan_add(br, v->vid, master_flags); + if (err) + goto out_filt; + } + + masterv = br_vlan_find(br->vlgrp, v->vid); + if (!masterv) { + /* missing global ctx, create it now */ + err = br_vlan_add(br, v->vid, master_flags); + if (err) + goto out_filt; + masterv = br_vlan_find(br->vlgrp, v->vid); + WARN_ON(!masterv); + } + atomic_inc(&masterv->refcnt); + v->brvlan = masterv; + } + + /* Add the dev mac only if it's a usable vlan */ + if (br_vlan_should_use(v)) { + err = br_fdb_insert(br, p, dev->dev_addr, v->vid); + if (err) { + br_err(br, "failed insert local address into bridge forwarding table\n"); + goto out_filt; + } + } + + err = rhashtable_lookup_insert_fast(tbl, &v->vnode, br_vlan_rht_params); + if (err) + goto out_fdb_insert; - __vlan_delete_pvid(v, vid); - clear_bit(vid, v->untagged_bitmap); + __vlan_add_list(v); + __vlan_add_flags(v, flags); + if (br_vlan_is_master(v)) { + if (br_vlan_is_brentry(v)) + br->vlgrp->num_vlans++; + } else { + p->vlgrp->num_vlans++; + } +out: + return err; + +out_fdb_insert: + br_fdb_find_delete_local(br, p, br->dev->dev_addr, v->vid); + +out_filt: + if (p) { + __vlan_vid_del(dev, br, v->vid); + if (masterv) { + atomic_dec(&masterv->refcnt); + v->brvlan = NULL; + } + } + + goto out; +} + +static int __vlan_del(struct net_bridge_vlan *v) +{ + struct net_bridge_vlan *masterv = v; + struct net_bridge_port *p = NULL; + struct net_bridge *br; + int err = 0; + struct rhashtable *tbl; + u16 *pvid; - if (v->port_idx) { - struct net_bridge_port *p = v->parent.port; - int err; + if (br_vlan_is_master(v)) { + br = v->br; + tbl = &v->br->vlgrp->vlan_hash; + pvid = &v->br->pvid; + } else { + p = v->port; + br = p->br; + tbl = &p->vlgrp->vlan_hash; + masterv = v->brvlan; + pvid = &p->pvid; + } - err = __vlan_vid_del(p->dev, p->br, vid); + __vlan_delete_pvid(pvid, v->vid); + if (p) { + err = __vlan_vid_del(p->dev, p->br, v->vid); if (err) - return err; + goto out; } - clear_bit(vid, v->vlan_bitmap); - v->num_vlans--; - if (bitmap_empty(v->vlan_bitmap, VLAN_N_VID)) { - if (v->port_idx) - RCU_INIT_POINTER(v->parent.port->vlan_info, NULL); - else - RCU_INIT_POINTER(v->parent.br->vlan_info, NULL); + if (br_vlan_is_master(v)) { + if (br_vlan_is_brentry(v)) { + v->flags &= ~BRIDGE_VLAN_INFO_BRENTRY; + br->vlgrp->num_vlans--; + } + } else { + p->vlgrp->num_vlans--; + } + + if (masterv != v) { + rhashtable_remove_fast(tbl, &v->vnode, br_vlan_rht_params); + __vlan_del_list(v); kfree_rcu(v, rcu); } - return 0; + + if (atomic_dec_and_test(&masterv->refcnt)) { + rhashtable_remove_fast(&masterv->br->vlgrp->vlan_hash, + &masterv->vnode, br_vlan_rht_params); + __vlan_del_list(masterv); + kfree_rcu(masterv, rcu); + } +out: + return err; } -static void __vlan_flush(struct net_port_vlans *v) +static void __vlan_flush(struct net_bridge_vlan_group *vlgrp, u16 *pvid) { - smp_wmb(); - v->pvid = 0; - bitmap_zero(v->vlan_bitmap, VLAN_N_VID); - if (v->port_idx) - RCU_INIT_POINTER(v->parent.port->vlan_info, NULL); - else - RCU_INIT_POINTER(v->parent.br->vlan_info, NULL); - kfree_rcu(v, rcu); + struct net_bridge_vlan *vlan, *tmp; + + __vlan_delete_pvid(pvid, *pvid); + list_for_each_entry_safe(vlan, tmp, &vlgrp->vlan_list, vlist) + __vlan_del(vlan); + rhashtable_destroy(&vlgrp->vlan_hash); + kfree(vlgrp); } struct sk_buff *br_handle_vlan(struct net_bridge *br, - const struct net_port_vlans *pv, + struct net_bridge_vlan_group *vg, struct sk_buff *skb) { + struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) goto out; - /* Vlan filter table must be configured at this point. The + /* At this point, we know that the frame was filtered and contains + * a valid vlan id. If the vlan id has untagged flag set, + * send untagged; otherwise, send tagged. + */ + br_vlan_get_tag(skb, &vid); + v = br_vlan_find(vg, vid); + /* Vlan entry must be configured at this point. The * only exception is the bridge is set in promisc mode and the * packet is destined for the bridge device. In this case * pass the packet as is. */ - if (!pv) { + if (!v || !br_vlan_should_use(v)) { if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) { goto out; } else { @@ -210,13 +344,7 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, return NULL; } } - - /* At this point, we know that the frame was filtered and contains - * a valid vlan id. If the vlan id is set in the untagged bitmap, - * send untagged; otherwise, send tagged. - */ - br_vlan_get_tag(skb, &vid); - if (test_bit(vid, pv->untagged_bitmap)) + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) skb->vlan_tci = 0; out: @@ -224,29 +352,13 @@ out: } /* Called under RCU */ -bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, - struct sk_buff *skb, u16 *vid) +static bool __allowed_ingress(struct rhashtable *tbl, u16 pvid, __be16 proto, + struct sk_buff *skb, u16 *vid) { + const struct net_bridge_vlan *v; bool tagged; - __be16 proto; - - /* If VLAN filtering is disabled on the bridge, all packets are - * permitted. - */ - if (!br->vlan_enabled) { - BR_INPUT_SKB_CB(skb)->vlan_filtered = false; - return true; - } - - /* If there are no vlan in the permitted list, all packets are - * rejected. - */ - if (!v) - goto drop; BR_INPUT_SKB_CB(skb)->vlan_filtered = true; - proto = br->vlan_proto; - /* If vlan tx offload is disabled on bridge device and frame was * sent from vlan device on the bridge device, it does not have * HW accelerated vlan tag. @@ -281,8 +393,6 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, } if (!*vid) { - u16 pvid = br_get_pvid(v); - /* Frame had a tag with VID 0 or did not have a tag. * See if pvid is set on this port. That tells us which * vlan untagged or priority-tagged traffic belongs to. @@ -309,29 +419,59 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, } /* Frame had a valid vlan tag. See if vlan is allowed */ - if (test_bit(*vid, v->vlan_bitmap)) + v = br_vlan_lookup(tbl, *vid); + if (v && br_vlan_should_use(v)) return true; drop: kfree_skb(skb); return false; } +bool br_allowed_ingress(struct net_bridge *br, struct sk_buff *skb, u16 *vid) +{ + /* If VLAN filtering is disabled on the bridge, all packets are + * permitted. + */ + if (!br->vlan_enabled) { + BR_INPUT_SKB_CB(skb)->vlan_filtered = false; + return true; + } + + return __allowed_ingress(&br->vlgrp->vlan_hash, br->pvid, + br->vlan_proto, skb, vid); +} + +bool nbp_allowed_ingress(struct net_bridge_port *p, struct sk_buff *skb, + u16 *vid) +{ + struct net_bridge *br = p->br; + + /* If VLAN filtering is disabled on the bridge, all packets are + * permitted. + */ + if (!br->vlan_enabled) { + BR_INPUT_SKB_CB(skb)->vlan_filtered = false; + return true; + } + + return __allowed_ingress(&p->vlgrp->vlan_hash, p->pvid, br->vlan_proto, + skb, vid); +} + /* Called under RCU. */ -bool br_allowed_egress(struct net_bridge *br, - const struct net_port_vlans *v, +bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb) { + const struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) return true; - if (!v) - return false; - br_vlan_get_tag(skb, &vid); - if (test_bit(vid, v->vlan_bitmap)) + v = br_vlan_find(vg, vid); + if (v && br_vlan_should_use(v)) return true; return false; @@ -341,28 +481,26 @@ bool br_allowed_egress(struct net_bridge *br, bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) { struct net_bridge *br = p->br; - struct net_port_vlans *v; /* If filtering was disabled at input, let it pass. */ if (!br->vlan_enabled) return true; - v = rcu_dereference(p->vlan_info); - if (!v) + if (!p->vlgrp->num_vlans) return false; if (!br_vlan_get_tag(skb, vid) && skb->vlan_proto != br->vlan_proto) *vid = 0; if (!*vid) { - *vid = br_get_pvid(v); + *vid = nbp_get_pvid(p); if (!*vid) return false; return true; } - if (test_bit(*vid, v->vlan_bitmap)) + if (br_vlan_find(p->vlgrp, *vid)) return true; return false; @@ -373,31 +511,47 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) */ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) { - struct net_port_vlans *pv = NULL; - int err; + struct net_bridge_vlan *vlan; + int ret; ASSERT_RTNL(); - pv = rtnl_dereference(br->vlan_info); - if (pv) - return __vlan_add(pv, vid, flags); + vlan = br_vlan_find(br->vlgrp, vid); + if (vlan) { + if (!br_vlan_is_brentry(vlan)) { + /* Trying to change flags of non-existent bridge vlan */ + if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) + return -EINVAL; + /* It was only kept for port vlans, now make it real */ + ret = br_fdb_insert(br, NULL, br->dev->dev_addr, + vlan->vid); + if (ret) { + br_err(br, "failed insert local address into bridge forwarding table\n"); + return ret; + } + atomic_inc(&vlan->refcnt); + vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; + br->vlgrp->num_vlans++; + } + __vlan_add_flags(vlan, flags); + return 0; + } - /* Create port vlan infomration - */ - pv = kzalloc(sizeof(*pv), GFP_KERNEL); - if (!pv) + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) return -ENOMEM; - pv->parent.br = br; - err = __vlan_add(pv, vid, flags); - if (err) - goto out; + vlan->vid = vid; + vlan->flags = flags | BRIDGE_VLAN_INFO_MASTER; + vlan->flags &= ~BRIDGE_VLAN_INFO_PVID; + vlan->br = br; + if (flags & BRIDGE_VLAN_INFO_BRENTRY) + atomic_set(&vlan->refcnt, 1); + ret = __vlan_add(vlan, flags); + if (ret) + kfree(vlan); - rcu_assign_pointer(br->vlan_info, pv); - return 0; -out: - kfree(pv); - return err; + return ret; } /* Must be protected by RTNL. @@ -405,49 +559,32 @@ out: */ int br_vlan_delete(struct net_bridge *br, u16 vid) { - struct net_port_vlans *pv; + struct net_bridge_vlan *v; ASSERT_RTNL(); - pv = rtnl_dereference(br->vlan_info); - if (!pv) - return -EINVAL; + v = br_vlan_find(br->vlgrp, vid); + if (!v || !br_vlan_is_brentry(v)) + return -ENOENT; br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid); - __vlan_del(pv, vid); - return 0; + return __vlan_del(v); } void br_vlan_flush(struct net_bridge *br) { - struct net_port_vlans *pv; - ASSERT_RTNL(); - pv = rtnl_dereference(br->vlan_info); - if (!pv) - return; - __vlan_flush(pv); + __vlan_flush(br_vlan_group(br), &br->pvid); } -bool br_vlan_find(struct net_bridge *br, u16 vid) +struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid) { - struct net_port_vlans *pv; - bool found = false; + if (!vg) + return NULL; - rcu_read_lock(); - pv = rcu_dereference(br->vlan_info); - - if (!pv) - goto out; - - if (test_bit(vid, pv->vlan_bitmap)) - found = true; - -out: - rcu_read_unlock(); - return found; + return br_vlan_lookup(&vg->vlan_hash, vid); } /* Must be protected by RTNL. */ @@ -505,21 +642,16 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) { int err = 0; struct net_bridge_port *p; - struct net_port_vlans *pv; + struct net_bridge_vlan *vlan; __be16 oldproto; - u16 vid, errvid; if (br->vlan_proto == proto) return 0; /* Add VLANs for the new proto to the device filter. */ list_for_each_entry(p, &br->port_list, list) { - pv = rtnl_dereference(p->vlan_info); - if (!pv) - continue; - - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - err = vlan_vid_add(p->dev, proto, vid); + list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) { + err = vlan_vid_add(p->dev, proto, vlan->vid); if (err) goto err_filt; } @@ -532,30 +664,19 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) br_recalculate_fwd_mask(br); /* Delete VLANs for the old proto from the device filter. */ - list_for_each_entry(p, &br->port_list, list) { - pv = rtnl_dereference(p->vlan_info); - if (!pv) - continue; - - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) - vlan_vid_del(p->dev, oldproto, vid); - } + list_for_each_entry(p, &br->port_list, list) + list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) + vlan_vid_del(p->dev, oldproto, vlan->vid); return 0; err_filt: - errvid = vid; - for_each_set_bit(vid, pv->vlan_bitmap, errvid) - vlan_vid_del(p->dev, proto, vid); - - list_for_each_entry_continue_reverse(p, &br->port_list, list) { - pv = rtnl_dereference(p->vlan_info); - if (!pv) - continue; + list_for_each_entry_continue_reverse(vlan, &p->vlgrp->vlan_list, vlist) + vlan_vid_del(p->dev, proto, vlan->vid); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) - vlan_vid_del(p->dev, proto, vid); - } + list_for_each_entry_continue_reverse(p, &br->port_list, list) + list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) + vlan_vid_del(p->dev, proto, vlan->vid); return err; } @@ -576,9 +697,20 @@ int br_vlan_set_proto(struct net_bridge *br, unsigned long val) return err; } -static bool vlan_default_pvid(struct net_port_vlans *pv, u16 vid) +static bool vlan_default_pvid(struct net_bridge_vlan_group *vg, u16 pvid, + u16 vid) { - return pv && vid == pv->pvid && test_bit(vid, pv->untagged_bitmap); + struct net_bridge_vlan *v; + + if (vid != pvid) + return false; + + v = br_vlan_lookup(&vg->vlan_hash, vid); + if (v && br_vlan_should_use(v) && + (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) + return true; + + return false; } static void br_vlan_disable_default_pvid(struct net_bridge *br) @@ -589,11 +721,11 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br) /* Disable default_pvid on all ports where it is still * configured. */ - if (vlan_default_pvid(br_get_vlan_info(br), pvid)) + if (vlan_default_pvid(br->vlgrp, br->pvid, pvid)) br_vlan_delete(br, pvid); list_for_each_entry(p, &br->port_list, list) { - if (vlan_default_pvid(nbp_get_vlan_info(p), pvid)) + if (vlan_default_pvid(p->vlgrp, p->pvid, pvid)) nbp_vlan_delete(p, pvid); } @@ -602,6 +734,7 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br) static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) { + const struct net_bridge_vlan *pvent; struct net_bridge_port *p; u16 old_pvid; int err = 0; @@ -617,11 +750,13 @@ static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) /* Update default_pvid config only if we do not conflict with * user configuration. */ - if ((!old_pvid || vlan_default_pvid(br_get_vlan_info(br), old_pvid)) && - !br_vlan_find(br, pvid)) { + pvent = br_vlan_find(br->vlgrp, pvid); + if ((!old_pvid || vlan_default_pvid(br->vlgrp, br->pvid, old_pvid)) && + (!pvent || !br_vlan_should_use(pvent))) { err = br_vlan_add(br, pvid, BRIDGE_VLAN_INFO_PVID | - BRIDGE_VLAN_INFO_UNTAGGED); + BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY); if (err) goto out; br_vlan_delete(br, old_pvid); @@ -633,8 +768,8 @@ static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) * user configuration. */ if ((old_pvid && - !vlan_default_pvid(nbp_get_vlan_info(p), old_pvid)) || - nbp_vlan_find(p, pvid)) + !vlan_default_pvid(p->vlgrp, p->pvid, old_pvid)) || + br_vlan_find(p->vlgrp, pvid)) continue; err = nbp_vlan_add(p, pvid, @@ -668,7 +803,8 @@ err_port: if (old_pvid) br_vlan_add(br, old_pvid, BRIDGE_VLAN_INFO_PVID | - BRIDGE_VLAN_INFO_UNTAGGED); + BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY); br_vlan_delete(br, pvid); } goto out; @@ -707,10 +843,62 @@ unlock: int br_vlan_init(struct net_bridge *br) { + int ret = -ENOMEM; + + br->vlgrp = kzalloc(sizeof(struct net_bridge_vlan_group), GFP_KERNEL); + if (!br->vlgrp) + goto out; + ret = rhashtable_init(&br->vlgrp->vlan_hash, &br_vlan_rht_params); + if (ret) + goto err_rhtbl; + INIT_LIST_HEAD(&br->vlgrp->vlan_list); br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; - return br_vlan_add(br, 1, - BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED); + ret = br_vlan_add(br, 1, + BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY); + if (ret) + goto err_vlan_add; + +out: + return ret; + +err_vlan_add: + rhashtable_destroy(&br->vlgrp->vlan_hash); +err_rhtbl: + kfree(br->vlgrp); + + goto out; +} + +int nbp_vlan_init(struct net_bridge_port *p) +{ + int ret = -ENOMEM; + + p->vlgrp = kzalloc(sizeof(struct net_bridge_vlan_group), GFP_KERNEL); + if (!p->vlgrp) + goto out; + + ret = rhashtable_init(&p->vlgrp->vlan_hash, &br_vlan_rht_params); + if (ret) + goto err_rhtbl; + INIT_LIST_HEAD(&p->vlgrp->vlan_list); + if (p->br->default_pvid) { + ret = nbp_vlan_add(p, p->br->default_pvid, + BRIDGE_VLAN_INFO_PVID | + BRIDGE_VLAN_INFO_UNTAGGED); + if (ret) + goto err_vlan_add; + } +out: + return ret; + +err_vlan_add: + rhashtable_destroy(&p->vlgrp->vlan_hash); +err_rhtbl: + kfree(p->vlgrp); + + goto out; } /* Must be protected by RTNL. @@ -718,35 +906,28 @@ int br_vlan_init(struct net_bridge *br) */ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) { - struct net_port_vlans *pv = NULL; - int err; + struct net_bridge_vlan *vlan; + int ret; ASSERT_RTNL(); - pv = rtnl_dereference(port->vlan_info); - if (pv) - return __vlan_add(pv, vid, flags); - - /* Create port vlan infomration - */ - pv = kzalloc(sizeof(*pv), GFP_KERNEL); - if (!pv) { - err = -ENOMEM; - goto clean_up; + vlan = br_vlan_find(port->vlgrp, vid); + if (vlan) { + __vlan_add_flags(vlan, flags); + return 0; } - pv->port_idx = port->port_no; - pv->parent.port = port; - err = __vlan_add(pv, vid, flags); - if (err) - goto clean_up; + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) + return -ENOMEM; - rcu_assign_pointer(port->vlan_info, pv); - return 0; + vlan->vid = vid; + vlan->port = port; + ret = __vlan_add(vlan, flags); + if (ret) + kfree(vlan); -clean_up: - kfree(pv); - return err; + return ret; } /* Must be protected by RTNL. @@ -754,61 +935,27 @@ clean_up: */ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) { - struct net_port_vlans *pv; + struct net_bridge_vlan *v; ASSERT_RTNL(); - pv = rtnl_dereference(port->vlan_info); - if (!pv) - return -EINVAL; - + v = br_vlan_find(port->vlgrp, vid); + if (!v) + return -ENOENT; br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); br_fdb_delete_by_port(port->br, port, vid, 0); - return __vlan_del(pv, vid); + return __vlan_del(v); } void nbp_vlan_flush(struct net_bridge_port *port) { - struct net_port_vlans *pv; - u16 vid; + struct net_bridge_vlan *vlan; ASSERT_RTNL(); - pv = rtnl_dereference(port->vlan_info); - if (!pv) - return; - - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) - vlan_vid_del(port->dev, port->br->vlan_proto, vid); - - __vlan_flush(pv); -} - -bool nbp_vlan_find(struct net_bridge_port *port, u16 vid) -{ - struct net_port_vlans *pv; - bool found = false; - - rcu_read_lock(); - pv = rcu_dereference(port->vlan_info); - - if (!pv) - goto out; + list_for_each_entry(vlan, &port->vlgrp->vlan_list, vlist) + vlan_vid_del(port->dev, port->br->vlan_proto, vlan->vid); - if (test_bit(vid, pv->vlan_bitmap)) - found = true; - -out: - rcu_read_unlock(); - return found; -} - -int nbp_vlan_init(struct net_bridge_port *p) -{ - return p->br->default_pvid ? - nbp_vlan_add(p, p->br->default_pvid, - BRIDGE_VLAN_INFO_PVID | - BRIDGE_VLAN_INFO_UNTAGGED) : - 0; + __vlan_flush(nbp_vlan_group(port), &port->pvid); } -- cgit v1.2.3 From 4613012db1d911f80897f9446a49de817b2c4c47 Mon Sep 17 00:00:00 2001 From: Aaron Conole Date: Sat, 26 Sep 2015 18:50:42 -0400 Subject: af_unix: Convert the unix_sk macro to an inline function for type safety As suggested by Eric Dumazet this change replaces the #define with a static inline function to enjoy complaints by the compiler when misusing the API. Signed-off-by: Aaron Conole Signed-off-by: David S. Miller --- include/net/af_unix.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 4a167b30a12f..cb1b9bbda332 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -63,7 +63,11 @@ struct unix_sock { #define UNIX_GC_MAYBE_CYCLE 1 struct socket_wq peer_wq; }; -#define unix_sk(__sk) ((struct unix_sock *)__sk) + +static inline struct unix_sock *unix_sk(struct sock *sk) +{ + return (struct unix_sock *)sk; +} #define peer_wait peer_wq.wait -- cgit v1.2.3 From 2094acbb714e24e464c810c2d8fa57493fcb25a6 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 28 Sep 2015 11:10:31 -0700 Subject: net/ipv4: Pass proto as u8 instead of u16 in ip_check_mc_rcu This patch updates ip_check_mc_rcu so that protocol is passed as a u8 instead of a u16. The motivation is just to avoid any unneeded type transitions since some systems will require an instruction to zero extend a u8 field to a u16. Also it makes it a bit more readable as to the fact that protocol is a u8 so there are no byte ordering changes needed to pass it. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 +- net/ipv4/igmp.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 908429216d9f..9c9de11549a7 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -110,7 +110,7 @@ struct ip_mc_list { #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) -extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u16 proto); +extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d38b8b61eaee..de6d4c8ba600 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2569,7 +2569,7 @@ void ip_mc_drop_socket(struct sock *sk) } /* called with rcu_read_lock() */ -int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 proto) +int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u8 proto) { struct ip_mc_list *im; struct ip_mc_list __rcu **mc_hash; -- cgit v1.2.3 From 31b33dfb0a144469dd805514c9e63f4993729a48 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Mon, 28 Sep 2015 17:24:25 -0700 Subject: skbuff: Fix skb checksum partial check. Earlier patch 6ae459bda tried to detect void ckecksum partial skb by comparing pull length to checksum offset. But it does not work for all cases since checksum-offset depends on updates to skb->data. Following patch fixes it by validating checksum start offset after skb-data pointer is updated. Negative value of checksum offset start means there is no need to checksum. Fixes: 6ae459bda ("skbuff: Fix skb checksum flag on skb pull") Reported-by: Andrew Vagin Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- net/core/skbuff.c | 9 +++++---- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2b0a30a6e31c..4398411236f1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2708,7 +2708,7 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); else if (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_start_offset(skb) <= len) + skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index dad4dd37e2aa..fab4599ba8b2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2958,11 +2958,12 @@ EXPORT_SYMBOL_GPL(skb_append_pagefrags); */ unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) { + unsigned char *data = skb->data; + BUG_ON(len > skb->len); - skb->len -= len; - BUG_ON(skb->len < skb->data_len); - skb_postpull_rcsum(skb, skb->data, len); - return skb->data += len; + __skb_pull(skb, len); + skb_postpull_rcsum(skb, data, len); + return skb->data; } EXPORT_SYMBOL_GPL(skb_pull_rcsum); -- cgit v1.2.3 From a00e74442bac5ad19a929d097370da7e07540ea6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:39 -0700 Subject: tcp/dccp: constify send_synack and send_reset socket argument None of these functions need to change the socket, make it const. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 4 ++-- net/dccp/dccp.h | 2 +- net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 2 +- net/dccp/minisocks.c | 2 +- net/ipv4/tcp_ipv4.c | 4 ++-- net/ipv6/tcp_ipv6.c | 12 ++++++------ 7 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 181f97f9fe1c..90247ec7955b 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -34,9 +34,9 @@ struct request_sock_ops { char *slab_name; int (*rtx_syn_ack)(const struct sock *sk, struct request_sock *req); - void (*send_ack)(struct sock *sk, struct sk_buff *skb, + void (*send_ack)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); - void (*send_reset)(struct sock *sk, + void (*send_reset)(const struct sock *sk, struct sk_buff *skb); void (*destructor)(struct request_sock *req); void (*syn_ack_timeout)(const struct request_sock *req); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 31e96df500d1..8ed1df2771bd 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -229,7 +229,7 @@ void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb); int dccp_retransmit_skb(struct sock *sk); void dccp_send_ack(struct sock *sk); -void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, +void dccp_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *rsk); void dccp_send_sync(struct sock *sk, const u64 seq, diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index a46ae9c69ccf..00a14fa4270a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -527,7 +527,7 @@ out: return err; } -static void dccp_v4_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) +static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) { int err; const struct iphdr *rxiph; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 4fa199dc69a3..aa719e700961 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -234,7 +234,7 @@ static void dccp_v6_reqsk_destructor(struct request_sock *req) kfree_skb(inet_rsk(req)->pktopts); } -static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) +static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) { const struct ipv6hdr *rxip6h; struct sk_buff *skb; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 838f524cf11a..9bfd0dc1e6cb 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -236,7 +236,7 @@ int dccp_child_process(struct sock *parent, struct sock *child, EXPORT_SYMBOL_GPL(dccp_child_process); -void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, +void dccp_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *rsk) { DCCP_BUG("DCCP-ACK packets are never sent in LISTEN/RESPOND state"); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a23ba7daecbf..4300d0132b9f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -576,7 +576,7 @@ EXPORT_SYMBOL(tcp_v4_send_check); * Exception: precedence violation. We do not implement it in any case. */ -static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) +static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); struct { @@ -795,7 +795,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) inet_twsk_put(tw); } -static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, +static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 16fb299dcab8..c47e5c87a2a8 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -70,8 +70,8 @@ #include #include -static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb); -static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, +static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb); +static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); @@ -724,7 +724,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .queue_hash_add = inet6_csk_reqsk_queue_hash_add, }; -static void tcp_v6_send_response(struct sock *sk, struct sk_buff *skb, u32 seq, +static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int rst, u8 tclass, u32 label) @@ -823,7 +823,7 @@ static void tcp_v6_send_response(struct sock *sk, struct sk_buff *skb, u32 seq, kfree_skb(buff); } -static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) +static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); u32 seq = 0, ack_seq = 0; @@ -894,7 +894,7 @@ release_sk1: #endif } -static void tcp_v6_send_ack(struct sock *sk, struct sk_buff *skb, u32 seq, +static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, u8 tclass, u32 label) @@ -917,7 +917,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) inet_twsk_put(tw); } -static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, +static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV -- cgit v1.2.3 From bda07a64c09c44ced789dbb815c71854f0c59839 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:40 -0700 Subject: tcp: remove unused len argument from tcp_rcv_state_process() Once we realize tcp_rcv_synsent_state_process() does not use its 'len' argument and we get rid of it, then it becomes clear this argument is no longer used in tcp_rcv_state_process() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- net/ipv4/tcp_input.c | 6 +++--- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_minisocks.c | 3 +-- net/ipv6/tcp_ipv6.c | 2 +- 5 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index cdbf63d3c5cf..1cfdedbe47e1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -366,7 +366,7 @@ void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th, unsigned int len); + const struct tcphdr *th); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len); void tcp_rcv_space_adjust(struct sock *sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4964d53907e9..dcbddf12f4b3 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5472,7 +5472,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, } static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th, unsigned int len) + const struct tcphdr *th) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -5699,7 +5699,7 @@ reset_and_undo: */ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th, unsigned int len) + const struct tcphdr *th) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); @@ -5749,7 +5749,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, goto discard; case TCP_SYN_SENT: - queued = tcp_rcv_synsent_state_process(sk, skb, th, len); + queued = tcp_rcv_synsent_state_process(sk, skb, th); if (queued >= 0) return queued; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4300d0132b9f..7e5ae1e01009 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1420,7 +1420,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) } else sock_rps_save_rxhash(sk, skb); - if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) { + if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb))) { rsk = sk; goto reset; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index e4fe62b6b106..9c7c61cf7462 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -821,8 +821,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, int state = child->sk_state; if (!sock_owned_by_user(child)) { - ret = tcp_rcv_state_process(child, skb, tcp_hdr(skb), - skb->len); + ret = tcp_rcv_state_process(child, skb, tcp_hdr(skb)); /* Wakeup parent, send SIGIO */ if (state == TCP_SYN_RECV && child->sk_state != state) parent->sk_data_ready(parent); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c47e5c87a2a8..b6e473f0f62e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1272,7 +1272,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) } else sock_rps_save_rxhash(sk, skb); - if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) + if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb))) goto reset; if (opt_skb) goto ipv6_pktoptions; -- cgit v1.2.3 From 72ab4a86f7a260d4c2a320b49662da107ce77a81 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:41 -0700 Subject: tcp: remove tcp_rcv_state_process() tcp_hdr argument Factorize code to get tcp header from skb. It makes no sense to duplicate code in callers. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 3 +-- net/ipv4/tcp_input.c | 4 ++-- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_minisocks.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 5 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 1cfdedbe47e1..1fe0bd458cb4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -365,8 +365,7 @@ void tcp_wfree(struct sk_buff *skb); void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); -int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th); +int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len); void tcp_rcv_space_adjust(struct sock *sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index dcbddf12f4b3..67b27aee8d28 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5698,11 +5698,11 @@ reset_and_undo: * address independent. */ -int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th) +int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcphdr *th = tcp_hdr(skb); struct request_sock *req; int queued = 0; bool acceptable; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7e5ae1e01009..67c0dc8bddbf 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1420,7 +1420,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) } else sock_rps_save_rxhash(sk, skb); - if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb))) { + if (tcp_rcv_state_process(sk, skb)) { rsk = sk; goto reset; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 9c7c61cf7462..139668cc2347 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -821,7 +821,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, int state = child->sk_state; if (!sock_owned_by_user(child)) { - ret = tcp_rcv_state_process(child, skb, tcp_hdr(skb)); + ret = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ if (state == TCP_SYN_RECV && child->sk_state != state) parent->sk_data_ready(parent); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b6e473f0f62e..334d548a0cf6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1272,7 +1272,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) } else sock_rps_save_rxhash(sk, skb); - if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb))) + if (tcp_rcv_state_process(sk, skb)) goto reset; if (opt_skb) goto ipv6_pktoptions; -- cgit v1.2.3 From f76b33c32b1913dd8909d8509f2726b1661aa6b1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:42 -0700 Subject: dccp: use inet6_csk_route_req() helper Before changing dccp_v6_request_recv_sock() sock argument to const, we need to get rid of security_sk_classify_flow(), and it seems doable by reusing inet6_csk_route_req() helper. We need to add a proto parameter to inet6_csk_route_req(), not assume it is TCP. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 2 +- net/dccp/ipv6.c | 17 +++-------------- net/ipv6/inet6_connection_sock.c | 8 +++++--- net/ipv6/tcp_ipv6.c | 7 ++++--- 4 files changed, 13 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 81d937e820c4..79b2a4c09ca6 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -26,7 +26,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, - const struct request_sock *req); + const struct request_sock *req, u8 proto); struct request_sock *inet6_csk_search_req(struct sock *sk, const __be16 rport, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index aa719e700961..0966bc08d362 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -462,22 +462,11 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, if (sk_acceptq_is_full(sk)) goto out_overflow; - if (dst == NULL) { - struct in6_addr *final_p, final; + if (!dst) { struct flowi6 fl6; - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_DCCP; - fl6.daddr = ireq->ir_v6_rmt_addr; - final_p = fl6_update_dst(&fl6, np->opt, &final); - fl6.saddr = ireq->ir_v6_loc_addr; - fl6.flowi6_oif = sk->sk_bound_dev_if; - fl6.fl6_dport = ireq->ir_rmt_port; - fl6.fl6_sport = htons(ireq->ir_num); - security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); - if (IS_ERR(dst)) + dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_DCCP); + if (!dst) goto out; } diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 91b7d33f508b..163bfef3e5db 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -67,15 +67,16 @@ EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict); struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, - const struct request_sock *req) + const struct request_sock *req, + u8 proto) { struct inet_request_sock *ireq = inet_rsk(req); - struct ipv6_pinfo *np = inet6_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *final_p, final; struct dst_entry *dst; memset(fl6, 0, sizeof(*fl6)); - fl6->flowi6_proto = IPPROTO_TCP; + fl6->flowi6_proto = proto; fl6->daddr = ireq->ir_v6_rmt_addr; final_p = fl6_update_dst(fl6, np->opt, &final); fl6->saddr = ireq->ir_v6_loc_addr; @@ -91,6 +92,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk, return dst; } +EXPORT_SYMBOL(inet6_csk_route_req); /* * request_sock (formerly open request) hash tables. diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 334d548a0cf6..092a23ef1feb 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -447,7 +447,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, int err = -ENOMEM; /* First, grab a route. */ - if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL) + if (!dst && (dst = inet6_csk_route_req(sk, fl6, req, + IPPROTO_TCP)) == NULL) goto done; skb = tcp_make_synack(sk, dst, req, foc); @@ -694,7 +695,7 @@ static struct dst_entry *tcp_v6_route_req(struct sock *sk, struct flowi *fl, { if (strict) *strict = true; - return inet6_csk_route_req(sk, &fl->u.ip6, req); + return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP); } struct request_sock_ops tcp6_request_sock_ops __read_mostly = { @@ -1058,7 +1059,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, goto out_overflow; if (!dst) { - dst = inet6_csk_route_req(sk, &fl6, req); + dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_TCP); if (!dst) goto out; } -- cgit v1.2.3 From a2432c4fa5e3c4c06df6efe0c406b6f575829a7b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:43 -0700 Subject: inet: constify inet_csk_route_child_sock() socket argument The socket points to the (shared) listener. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 ++- net/ipv4/inet_connection_sock.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 00c3ced6ee55..187cef7e56d5 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -268,7 +268,8 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum); struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req); -struct dst_entry *inet_csk_route_child_sock(struct sock *sk, struct sock *newsk, +struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, + struct sock *newsk, const struct request_sock *req); static inline void inet_csk_reqsk_queue_add(struct sock *sk, diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index ba2f90d90cb5..694a5e8f4f9f 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -439,7 +439,7 @@ no_route: } EXPORT_SYMBOL_GPL(inet_csk_route_req); -struct dst_entry *inet_csk_route_child_sock(struct sock *sk, +struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req) { -- cgit v1.2.3 From 1ce31c9e08997ea0fa62be0a7437f868be173f13 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:44 -0700 Subject: inet: constify __inet_inherit_port() sock argument socket is not touched, make it const. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 2 +- net/ipv4/inet_hashtables.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index b07d126694a7..3fb778d7c875 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -199,7 +199,7 @@ static inline int inet_sk_listen_hashfn(const struct sock *sk) } /* Caller must disable local BH processing. */ -int __inet_inherit_port(struct sock *sk, struct sock *child); +int __inet_inherit_port(const struct sock *sk, struct sock *child); void inet_put_port(struct sock *sk); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 89120196a949..56742e995dd3 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -126,7 +126,7 @@ void inet_put_port(struct sock *sk) } EXPORT_SYMBOL(inet_put_port); -int __inet_inherit_port(struct sock *sk, struct sock *child) +int __inet_inherit_port(const struct sock *sk, struct sock *child) { struct inet_hashinfo *table = sk->sk_prot->h.hashinfo; unsigned short port = inet_sk(child)->inet_num; -- cgit v1.2.3 From 87e002b21aafccfe71faeec62f3543d30600a518 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:45 -0700 Subject: net: constify sk_gfp_atomic() sock argument Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 94dff7f566f5..dfe2eb8e1132 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -759,7 +759,7 @@ static inline int sk_memalloc_socks(void) #endif -static inline gfp_t sk_gfp_atomic(struct sock *sk, gfp_t gfp_mask) +static inline gfp_t sk_gfp_atomic(const struct sock *sk, gfp_t gfp_mask) { return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC); } -- cgit v1.2.3 From c28c6f045945f53e842467bf0e86c5fac051643d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:47 -0700 Subject: tcp: constify tcp_create_openreq_child() socket argument This method does not touch the listener socket. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- net/ipv4/tcp_minisocks.c | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 1fe0bd458cb4..85995c1291d0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -450,7 +450,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); void tcp_req_err(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); -struct sock *tcp_create_openreq_child(struct sock *sk, +struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, struct sk_buff *skb); void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 139668cc2347..897e34273ba3 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -441,7 +441,9 @@ EXPORT_SYMBOL_GPL(tcp_ca_openreq_child); * Actually, we could lots of memory writes here. tp of listening * socket contains all necessary default parameters. */ -struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb) +struct sock *tcp_create_openreq_child(const struct sock *sk, + struct request_sock *req, + struct sk_buff *skb) { struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC); -- cgit v1.2.3 From 0c27171e66d94f9121fc00e87407ca7103bb6649 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:48 -0700 Subject: tcp/dccp: constify syn_recv_sock() method sock argument We'll soon no longer hold listener socket lock, these functions do not modify the socket in any way. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 2 +- include/net/tcp.h | 2 +- net/dccp/dccp.h | 2 +- net/dccp/ipv4.c | 3 ++- net/dccp/ipv6.c | 5 +++-- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/tcp_ipv6.c | 5 +++-- 7 files changed, 12 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 187cef7e56d5..ee54f21a8113 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -41,7 +41,7 @@ struct inet_connection_sock_af_ops { int (*rebuild_header)(struct sock *sk); void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb); int (*conn_request)(struct sock *sk, struct sk_buff *skb); - struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb, + struct sock *(*syn_recv_sock)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); u16 net_header_len; diff --git a/include/net/tcp.h b/include/net/tcp.h index 85995c1291d0..a1d2f5d6a430 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -454,7 +454,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, struct sk_buff *skb); void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst); -struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, +struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 2409619b7043..e1f823451565 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -276,7 +276,7 @@ struct sock *dccp_create_openreq_child(const struct sock *sk, int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); -struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, +struct sock *dccp_v4_request_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 00a14fa4270a..5b7818c63cec 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -390,7 +390,8 @@ static inline u64 dccp_v4_init_sequence(const struct sk_buff *skb) * * This is the equivalent of TCP's tcp_v4_syn_recv_sock */ -struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, +struct sock *dccp_v4_request_recv_sock(const struct sock *sk, + struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) { diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 0966bc08d362..e8753aa3b7a4 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -408,13 +408,14 @@ drop: return -1; } -static struct sock *dccp_v6_request_recv_sock(struct sock *sk, +static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) { struct inet_request_sock *ireq = inet_rsk(req); - struct ipv6_pinfo *newnp, *np = inet6_sk(sk); + struct ipv6_pinfo *newnp; + const struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *newinet; struct dccp6_sock *newdp6; struct sock *newsk; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 67c0dc8bddbf..ee0239e190cf 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1242,7 +1242,7 @@ EXPORT_SYMBOL(tcp_v4_conn_request); * The three way handshake has completed - we got a valid synack - * now create the new socket. */ -struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, +struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 092a23ef1feb..2330c7be6323 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -986,12 +986,13 @@ drop: return 0; /* don't send reset */ } -static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, +static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) { struct inet_request_sock *ireq; - struct ipv6_pinfo *newnp, *np = inet6_sk(sk); + struct ipv6_pinfo *newnp; + const struct ipv6_pinfo *np = inet6_sk(sk); struct tcp6_sock *newtcp6sk; struct inet_sock *newinet; struct tcp_sock *newtp; -- cgit v1.2.3 From 3f684b4b1f1c86e3a6ac63389d1032e239fddd79 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:49 -0700 Subject: tcp: cookie_init_sequence() cleanups Some common IPv4/IPv6 code can be factorized. Also constify cookie_init_sequence() socket argument. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 19 ++++++++++--------- net/ipv4/syncookies.c | 6 +----- net/ipv6/syncookies.c | 5 +---- 3 files changed, 12 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index a1d2f5d6a430..5aa6672c6f5b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -491,8 +491,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); /* syncookies: remember time of last synqueue overflow * But do not dirty this field too often (once per second is enough) + * It is racy as we do not hold a lock, but race is very minor. */ -static inline void tcp_synq_overflow(struct sock *sk) +static inline void tcp_synq_overflow(const struct sock *sk) { unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; unsigned long now = jiffies; @@ -519,8 +520,7 @@ static inline u32 tcp_cookie_time(void) u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); -__u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb, - __u16 *mss); +__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); __u32 cookie_init_timestamp(struct request_sock *req); bool cookie_timestamp_decode(struct tcp_options_received *opt); bool cookie_ecn_ok(const struct tcp_options_received *opt, @@ -533,8 +533,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp); -__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, - __u16 *mss); +__u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ @@ -1709,7 +1708,7 @@ struct tcp_request_sock_ops { const struct sock *sk_listener, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES - __u32 (*cookie_init_seq)(struct sock *sk, const struct sk_buff *skb, + __u32 (*cookie_init_seq)(const struct sk_buff *skb, __u16 *mss); #endif struct dst_entry *(*route_req)(struct sock *sk, struct flowi *fl, @@ -1725,14 +1724,16 @@ struct tcp_request_sock_ops { #ifdef CONFIG_SYN_COOKIES static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, - struct sock *sk, struct sk_buff *skb, + const struct sock *sk, struct sk_buff *skb, __u16 *mss) { - return ops->cookie_init_seq(sk, skb, mss); + tcp_synq_overflow(sk); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); + return ops->cookie_init_seq(skb, mss); } #else static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, - struct sock *sk, struct sk_buff *skb, + const struct sock *sk, struct sk_buff *skb, __u16 *mss) { return 0; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 6595affded20..6b97b5f6457c 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -192,15 +192,11 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, } EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence); -__u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb, - __u16 *mssp) +__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mssp) { const struct iphdr *iph = ip_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); - tcp_synq_overflow(sk); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); - return __cookie_v4_init_sequence(iph, th, mssp); } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 2461b3ff9551..7606eba83e7b 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -114,14 +114,11 @@ u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, } EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence); -__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, __u16 *mssp) +__u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mssp) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); - tcp_synq_overflow(sk); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); - return __cookie_v6_init_sequence(iph, th, mssp); } -- cgit v1.2.3 From f964629e3338d9e5a78c9b354380d5a1e2fa4617 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:50 -0700 Subject: tcp: constify tcp_v{4|6}_route_req() sock argument These functions do not change the listener socket. Goal is to make sure tcp_conn_request() is not messing with listener in a racy way. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- net/ipv4/tcp_ipv4.c | 3 ++- net/ipv6/tcp_ipv6.c | 3 ++- 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 5aa6672c6f5b..2c7dfe52f473 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1711,7 +1711,7 @@ struct tcp_request_sock_ops { __u32 (*cookie_init_seq)(const struct sk_buff *skb, __u16 *mss); #endif - struct dst_entry *(*route_req)(struct sock *sk, struct flowi *fl, + struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl, const struct request_sock *req, bool *strict); __u32 (*init_seq)(const struct sk_buff *skb); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ee0239e190cf..f551e9e862db 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1180,7 +1180,8 @@ static void tcp_v4_init_req(struct request_sock *req, ireq->opt = tcp_v4_save_options(skb); } -static struct dst_entry *tcp_v4_route_req(struct sock *sk, struct flowi *fl, +static struct dst_entry *tcp_v4_route_req(const struct sock *sk, + struct flowi *fl, const struct request_sock *req, bool *strict) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2330c7be6323..97bc26e0cd0f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -689,7 +689,8 @@ static void tcp_v6_init_req(struct request_sock *req, } } -static struct dst_entry *tcp_v6_route_req(struct sock *sk, struct flowi *fl, +static struct dst_entry *tcp_v6_route_req(const struct sock *sk, + struct flowi *fl, const struct request_sock *req, bool *strict) { -- cgit v1.2.3 From 2985aaac010ebd5e562ce1a22cc61acbb0e40cf2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:51 -0700 Subject: tcp: constify tcp_syn_flood_action() socket argument tcp_syn_flood_action() will soon be called with unlocked socket. In order to avoid SYN flood warning being emitted multiple times, use xchg(). Extend max_qlen_log and synflood_warned fields in struct listen_sock to u32 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 5 ++--- net/ipv4/tcp_input.c | 9 +++++---- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 90247ec7955b..c146b5284786 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -129,9 +129,8 @@ struct listen_sock { atomic_t qlen_dec; /* qlen = qlen_inc - qlen_dec */ atomic_t young_dec; - u8 max_qlen_log ____cacheline_aligned_in_smp; - u8 synflood_warned; - /* 2 bytes hole, try to use */ + u32 max_qlen_log ____cacheline_aligned_in_smp; + u32 synflood_warned; u32 hash_rnd; u32 nr_table_entries; struct request_sock *syn_table[0]; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 67b27aee8d28..e58cbcd2f07e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6064,7 +6064,7 @@ EXPORT_SYMBOL(inet_reqsk_alloc); /* * Return true if a syncookie should be sent */ -static bool tcp_syn_flood_action(struct sock *sk, +static bool tcp_syn_flood_action(const struct sock *sk, const struct sk_buff *skb, const char *proto) { @@ -6082,11 +6082,12 @@ static bool tcp_syn_flood_action(struct sock *sk, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; - if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) { - lopt->synflood_warned = 1; + if (!lopt->synflood_warned && + sysctl_tcp_syncookies != 2 && + xchg(&lopt->synflood_warned, 1) == 0) pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", proto, ntohs(tcp_hdr(skb)->dest), msg); - } + return want_cookie; } -- cgit v1.2.3 From 0536fcc039a8926ec12ec587f41a83f7acafeb82 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:52 -0700 Subject: tcp: prepare fastopen code for upcoming listener changes While auditing TCP stack for upcoming 'lockless' listener changes, I found I had to change fastopen_init_queue() to properly init the object before publishing it. Otherwise an other cpu could try to lock the spinlock before it gets properly initialized. Instead of adding appropriate barriers, just remove dynamic memory allocations : - Structure is 28 bytes on 64bit arches. Using additional 8 bytes for holding a pointer seems overkill. - Two listeners can share same cache line and performance would suffer. If we really want to save few bytes, we would instead dynamically allocate whole struct request_sock_queue in the future. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 22 ++++------------------ include/net/request_sock.h | 7 ++----- net/core/request_sock.c | 9 ++++++++- net/ipv4/af_inet.c | 10 +++------- net/ipv4/inet_connection_sock.c | 17 ++++++++--------- net/ipv4/tcp.c | 14 ++------------ net/ipv4/tcp_fastopen.c | 10 +++++----- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/tcp_ipv6.c | 4 ++-- 9 files changed, 35 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index fcb573be75d9..e442e6e9a365 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -382,25 +382,11 @@ static inline bool tcp_passive_fastopen(const struct sock *sk) tcp_sk(sk)->fastopen_rsk != NULL); } -extern void tcp_sock_destruct(struct sock *sk); - -static inline int fastopen_init_queue(struct sock *sk, int backlog) +static inline void fastopen_queue_tune(struct sock *sk, int backlog) { - struct request_sock_queue *queue = - &inet_csk(sk)->icsk_accept_queue; - - if (queue->fastopenq == NULL) { - queue->fastopenq = kzalloc( - sizeof(struct fastopen_queue), - sk->sk_allocation); - if (queue->fastopenq == NULL) - return -ENOMEM; - - sk->sk_destruct = tcp_sock_destruct; - spin_lock_init(&queue->fastopenq->lock); - } - queue->fastopenq->max_qlen = backlog; - return 0; + struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; + + queue->fastopenq.max_qlen = backlog; } static inline void tcp_saved_syn_free(struct tcp_sock *tp) diff --git a/include/net/request_sock.h b/include/net/request_sock.h index c146b5284786..d2544de329bd 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -180,11 +180,8 @@ struct request_sock_queue { struct request_sock *rskq_accept_tail; u8 rskq_defer_accept; struct listen_sock *listen_opt; - struct fastopen_queue *fastopenq; /* This is non-NULL iff TFO has been - * enabled on this listener. Check - * max_qlen != 0 in fastopen_queue - * to determine if TFO is enabled - * right at this moment. + struct fastopen_queue fastopenq; /* Check max_qlen != 0 to determine + * if TFO is enabled. */ /* temporary alignment, our goal is to get rid of this lock */ diff --git a/net/core/request_sock.c b/net/core/request_sock.c index b42f0e26f89e..e22cfa4ed25f 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -59,6 +59,13 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); spin_lock_init(&queue->syn_wait_lock); + + spin_lock_init(&queue->fastopenq.lock); + queue->fastopenq.rskq_rst_head = NULL; + queue->fastopenq.rskq_rst_tail = NULL; + queue->fastopenq.qlen = 0; + queue->fastopenq.max_qlen = 0; + queue->rskq_accept_head = NULL; lopt->nr_table_entries = nr_table_entries; lopt->max_qlen_log = ilog2(nr_table_entries); @@ -174,7 +181,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, struct sock *lsk = req->rsk_listener; struct fastopen_queue *fastopenq; - fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq; + fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq; tcp_sk(sk)->fastopen_rsk = NULL; spin_lock_bh(&fastopenq->lock); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8a556643b874..3af85eecbe11 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -219,17 +219,13 @@ int inet_listen(struct socket *sock, int backlog) * shutdown() (rather than close()). */ if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) != 0 && - !inet_csk(sk)->icsk_accept_queue.fastopenq) { + !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) != 0) - err = fastopen_init_queue(sk, backlog); + fastopen_queue_tune(sk, backlog); else if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT2) != 0) - err = fastopen_init_queue(sk, + fastopen_queue_tune(sk, ((uint)sysctl_tcp_fastopen) >> 16); - else - err = 0; - if (err) - goto out; tcp_fastopen_init_key_once(true); } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 694a5e8f4f9f..e1527882a578 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -335,9 +335,8 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) sk_acceptq_removed(sk); if (sk->sk_protocol == IPPROTO_TCP && - tcp_rsk(req)->tfo_listener && - queue->fastopenq) { - spin_lock_bh(&queue->fastopenq->lock); + tcp_rsk(req)->tfo_listener) { + spin_lock_bh(&queue->fastopenq.lock); if (tcp_rsk(req)->tfo_listener) { /* We are still waiting for the final ACK from 3WHS * so can't free req now. Instead, we set req->sk to @@ -348,7 +347,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) req->sk = NULL; req = NULL; } - spin_unlock_bh(&queue->fastopenq->lock); + spin_unlock_bh(&queue->fastopenq.lock); } out: release_sock(sk); @@ -886,12 +885,12 @@ void inet_csk_listen_stop(struct sock *sk) sk_acceptq_removed(sk); reqsk_put(req); } - if (queue->fastopenq) { + if (queue->fastopenq.rskq_rst_head) { /* Free all the reqs queued in rskq_rst_head. */ - spin_lock_bh(&queue->fastopenq->lock); - acc_req = queue->fastopenq->rskq_rst_head; - queue->fastopenq->rskq_rst_head = NULL; - spin_unlock_bh(&queue->fastopenq->lock); + spin_lock_bh(&queue->fastopenq.lock); + acc_req = queue->fastopenq.rskq_rst_head; + queue->fastopenq.rskq_rst_head = NULL; + spin_unlock_bh(&queue->fastopenq.lock); while ((req = acc_req) != NULL) { acc_req = req->dl_next; reqsk_put(req); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b8b8fa184f75..3c96fa87ff9e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2253,13 +2253,6 @@ int tcp_disconnect(struct sock *sk, int flags) } EXPORT_SYMBOL(tcp_disconnect); -void tcp_sock_destruct(struct sock *sk) -{ - inet_sock_destruct(sk); - - kfree(inet_csk(sk)->icsk_accept_queue.fastopenq); -} - static inline bool tcp_can_repair_sock(const struct sock *sk) { return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) && @@ -2581,7 +2574,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, TCPF_LISTEN))) { tcp_fastopen_init_key_once(true); - err = fastopen_init_queue(sk, val); + fastopen_queue_tune(sk, val); } else { err = -EINVAL; } @@ -2849,10 +2842,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_FASTOPEN: - if (icsk->icsk_accept_queue.fastopenq) - val = icsk->icsk_accept_queue.fastopenq->max_qlen; - else - val = 0; + val = icsk->icsk_accept_queue.fastopenq.max_qlen; break; case TCP_TIMESTAMP: diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index db43c6286cf7..f69f436fcbcc 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -142,9 +142,9 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, if (!child) return NULL; - spin_lock(&queue->fastopenq->lock); - queue->fastopenq->qlen++; - spin_unlock(&queue->fastopenq->lock); + spin_lock(&queue->fastopenq.lock); + queue->fastopenq.qlen++; + spin_unlock(&queue->fastopenq.lock); /* Initialize the child socket. Have to fix some values to take * into account the child is a Fast Open socket and is created @@ -237,8 +237,8 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * between qlen overflow causing Fast Open to be disabled * temporarily vs a server not supporting Fast Open at all. */ - fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq; - if (!fastopenq || fastopenq->max_qlen == 0) + fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; + if (fastopenq->max_qlen == 0) return false; if (fastopenq->qlen >= fastopenq->max_qlen) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f551e9e862db..64ece718d66c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2186,7 +2186,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); const struct inet_sock *inet = inet_sk(sk); - struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq; + const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 97bc26e0cd0f..0ac64f47f882 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1672,7 +1672,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) const struct inet_sock *inet = inet_sk(sp); const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); - struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq; + const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; dest = &sp->sk_v6_daddr; src = &sp->sk_v6_rcv_saddr; @@ -1716,7 +1716,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, sp->sk_state == TCP_LISTEN ? - (fastopenq ? fastopenq->max_qlen : 0) : + fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) ); } -- cgit v1.2.3 From 007979eaf94d1c888d8c7cf8a5250c2c6c9bd98e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:10 -0700 Subject: net: Rename IFF_VRF_MASTER to IFF_L3MDEV_MASTER Rename IFF_VRF_MASTER to IFF_L3MDEV_MASTER and update the name of the netif_is_vrf and netif_index_is_vrf macros. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/vrf.c | 6 +++--- include/linux/netdevice.h | 14 +++++++------- include/net/route.h | 2 +- include/net/vrf.h | 4 ++-- net/ipv4/ip_output.c | 2 +- net/ipv4/route.c | 2 +- net/ipv4/udp.c | 2 +- 7 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 4ecb3a3e516a..2d7418e0b908 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -438,7 +438,7 @@ out_fail: static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev) { - if (netif_is_vrf(port_dev) || vrf_is_slave(port_dev)) + if (netif_is_l3_master(port_dev) || vrf_is_slave(port_dev)) return -EINVAL; return do_vrf_add_slave(dev, port_dev); @@ -591,7 +591,7 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev, vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]); - dev->priv_flags |= IFF_VRF_MASTER; + dev->priv_flags |= IFF_L3MDEV_MASTER; err = -ENOMEM; vrf_ptr = kmalloc(sizeof(*dev->vrf_ptr), GFP_KERNEL); @@ -657,7 +657,7 @@ static int vrf_device_event(struct notifier_block *unused, struct net_vrf_dev *vrf_ptr = rtnl_dereference(dev->vrf_ptr); struct net_device *vrf_dev; - if (!vrf_ptr || netif_is_vrf(dev)) + if (!vrf_ptr || netif_is_l3_master(dev)) goto out; vrf_dev = netdev_master_upper_dev_get(dev); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d2ffeafc9998..99c33e83822f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1258,7 +1258,7 @@ struct net_device_ops { * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device - * @IFF_VRF_MASTER: device is a VRF master + * @IFF_L3MDEV_MASTER: device is an L3 master device * @IFF_NO_QUEUE: device can run without qdisc attached * @IFF_OPENVSWITCH: device is a Open vSwitch master */ @@ -1283,7 +1283,7 @@ enum netdev_priv_flags { IFF_XMIT_DST_RELEASE_PERM = 1<<17, IFF_IPVLAN_MASTER = 1<<18, IFF_IPVLAN_SLAVE = 1<<19, - IFF_VRF_MASTER = 1<<20, + IFF_L3MDEV_MASTER = 1<<20, IFF_NO_QUEUE = 1<<21, IFF_OPENVSWITCH = 1<<22, }; @@ -1308,7 +1308,7 @@ enum netdev_priv_flags { #define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM #define IFF_IPVLAN_MASTER IFF_IPVLAN_MASTER #define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE -#define IFF_VRF_MASTER IFF_VRF_MASTER +#define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER #define IFF_NO_QUEUE IFF_NO_QUEUE #define IFF_OPENVSWITCH IFF_OPENVSWITCH @@ -3824,9 +3824,9 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } -static inline bool netif_is_vrf(const struct net_device *dev) +static inline bool netif_is_l3_master(const struct net_device *dev) { - return dev->priv_flags & IFF_VRF_MASTER; + return dev->priv_flags & IFF_L3MDEV_MASTER; } static inline bool netif_is_bridge_master(const struct net_device *dev) @@ -3839,7 +3839,7 @@ static inline bool netif_is_ovs_master(const struct net_device *dev) return dev->priv_flags & IFF_OPENVSWITCH; } -static inline bool netif_index_is_vrf(struct net *net, int ifindex) +static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { bool rc = false; @@ -3853,7 +3853,7 @@ static inline bool netif_index_is_vrf(struct net *net, int ifindex) dev = dev_get_by_index_rcu(net, ifindex); if (dev) - rc = netif_is_vrf(dev); + rc = netif_is_l3_master(dev); rcu_read_unlock(); #endif diff --git a/include/net/route.h b/include/net/route.h index d1bd90bb3187..a565d0dad12c 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -256,7 +256,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; - if (netif_index_is_vrf(sock_net(sk), oif)) + if (netif_index_is_l3_master(sock_net(sk), oif)) flow_flags |= FLOWI_FLAG_VRFSRC | FLOWI_FLAG_SKIP_NH_OIF; flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, diff --git a/include/net/vrf.h b/include/net/vrf.h index 593e6094ddd4..34bb3f69def2 100644 --- a/include/net/vrf.h +++ b/include/net/vrf.h @@ -43,7 +43,7 @@ static inline int vrf_master_ifindex_rcu(const struct net_device *dev) if (!dev) return 0; - if (netif_is_vrf(dev)) { + if (netif_is_l3_master(dev)) { ifindex = dev->ifindex; } else { vrf_ptr = rcu_dereference(dev->vrf_ptr); @@ -125,7 +125,7 @@ static inline u32 vrf_dev_table_rtnl(const struct net_device *dev) return tb_id; } -/* caller has already checked netif_is_vrf(dev) */ +/* caller has already checked netif_is_l3_master(dev) */ static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) { struct rtable *rth = ERR_PTR(-ENETUNREACH); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 06d2c87ed505..aff6766922e8 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1571,7 +1571,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, } oif = arg->bound_dev_if; - if (!oif && netif_index_is_vrf(net, skb->skb_iif)) + if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) oif = skb->skb_iif; flowi4_init_output(&fl4, oif, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8c84a6664b30..a670f894ce13 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2124,7 +2124,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } - if (netif_is_vrf(dev_out) && + if (netif_is_l3_master(dev_out) && !(fl4->flowi4_flags & FLOWI_FLAG_VRFSRC)) { rth = vrf_dev_get_rth(dev_out); goto out; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f7d1d5e19e95..156ba75b6000 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1021,7 +1021,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) * device lookup source address from VRF table. This mimics * behavior of ip_route_connect{_init}. */ - if (netif_index_is_vrf(net, ipc.oif)) { + if (netif_index_is_l3_master(net, ipc.oif)) { flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, (flow_flags | FLOWI_FLAG_VRFSRC | -- cgit v1.2.3 From 1b69c6d0ae90b7f1a4f61d5c8209d5cb7a55f849 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:11 -0700 Subject: net: Introduce L3 Master device abstraction L3 master devices allow users of the abstraction to influence FIB lookups for enslaved devices. Current API provides a means for the master device to return a specific FIB table for an enslaved device, to return an rtable/custom dst and influence the OIF used for fib lookups. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- MAINTAINERS | 7 +++ include/linux/netdevice.h | 3 ++ include/net/l3mdev.h | 125 ++++++++++++++++++++++++++++++++++++++++++++++ net/Kconfig | 1 + net/Makefile | 3 ++ net/l3mdev/Kconfig | 10 ++++ net/l3mdev/Makefile | 5 ++ net/l3mdev/l3mdev.c | 92 ++++++++++++++++++++++++++++++++++ 8 files changed, 246 insertions(+) create mode 100644 include/net/l3mdev.h create mode 100644 net/l3mdev/Kconfig create mode 100644 net/l3mdev/Makefile create mode 100644 net/l3mdev/l3mdev.c (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index bcd263de4827..3f2d7a9d0bbf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6095,6 +6095,13 @@ F: Documentation/auxdisplay/ks0108 F: drivers/auxdisplay/ks0108.c F: include/linux/ks0108.h +L3MDEV +M: David Ahern +L: netdev@vger.kernel.org +S: Maintained +F: net/l3mdev +F: include/net/l3mdev.h + LAPB module L: linux-x25@vger.kernel.org S: Orphan diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 99c33e83822f..c7f14794fe14 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1587,6 +1587,9 @@ struct net_device { #ifdef CONFIG_NET_SWITCHDEV const struct switchdev_ops *switchdev_ops; #endif +#ifdef CONFIG_NET_L3_MASTER_DEV + const struct l3mdev_ops *l3mdev_ops; +#endif const struct header_ops *header_ops; diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h new file mode 100644 index 000000000000..e382c777bab8 --- /dev/null +++ b/include/net/l3mdev.h @@ -0,0 +1,125 @@ +/* + * include/net/l3mdev.h - L3 master device API + * Copyright (c) 2015 Cumulus Networks + * Copyright (c) 2015 David Ahern + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#ifndef _NET_L3MDEV_H_ +#define _NET_L3MDEV_H_ + +/** + * struct l3mdev_ops - l3mdev operations + * + * @l3mdev_fib_table: Get FIB table id to use for lookups + * + * @l3mdev_get_rtable: Get cached IPv4 rtable (dst_entry) for device + */ + +struct l3mdev_ops { + u32 (*l3mdev_fib_table)(const struct net_device *dev); + struct rtable * (*l3mdev_get_rtable)(const struct net_device *dev, + const struct flowi4 *fl4); +}; + +#ifdef CONFIG_NET_L3_MASTER_DEV + +int l3mdev_master_ifindex_rcu(struct net_device *dev); +static inline int l3mdev_master_ifindex(struct net_device *dev) +{ + int ifindex; + + rcu_read_lock(); + ifindex = l3mdev_master_ifindex_rcu(dev); + rcu_read_unlock(); + + return ifindex; +} + +/* get index of an interface to use for FIB lookups. For devices + * enslaved to an L3 master device FIB lookups are based on the + * master index + */ +static inline int l3mdev_fib_oif_rcu(struct net_device *dev) +{ + return l3mdev_master_ifindex_rcu(dev) ? : dev->ifindex; +} + +static inline int l3mdev_fib_oif(struct net_device *dev) +{ + int oif; + + rcu_read_lock(); + oif = l3mdev_fib_oif_rcu(dev); + rcu_read_unlock(); + + return oif; +} + +u32 l3mdev_fib_table_rcu(const struct net_device *dev); +u32 l3mdev_fib_table_by_index(struct net *net, int ifindex); +static inline u32 l3mdev_fib_table(const struct net_device *dev) +{ + u32 tb_id; + + rcu_read_lock(); + tb_id = l3mdev_fib_table_rcu(dev); + rcu_read_unlock(); + + return tb_id; +} + +static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev, + const struct flowi4 *fl4) +{ + if (netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_get_rtable) + return dev->l3mdev_ops->l3mdev_get_rtable(dev, fl4); + + return NULL; +} + +#else + +static inline int l3mdev_master_ifindex_rcu(struct net_device *dev) +{ + return 0; +} +static inline int l3mdev_master_ifindex(struct net_device *dev) +{ + return 0; +} + +static inline int l3mdev_fib_oif_rcu(struct net_device *dev) +{ + return dev ? dev->ifindex : 0; +} +static inline int l3mdev_fib_oif(struct net_device *dev) +{ + return dev ? dev->ifindex : 0; +} + +static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev) +{ + return 0; +} +static inline u32 l3mdev_fib_table(const struct net_device *dev) +{ + return 0; +} +static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) +{ + return 0; +} + +static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev, + const struct flowi4 *fl4) +{ + return NULL; +} + +#endif + +#endif /* _NET_L3MDEV_H_ */ diff --git a/net/Kconfig b/net/Kconfig index 7021c1bf44d6..127da94ae25e 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -232,6 +232,7 @@ source "net/netlink/Kconfig" source "net/mpls/Kconfig" source "net/hsr/Kconfig" source "net/switchdev/Kconfig" +source "net/l3mdev/Kconfig" config RPS bool diff --git a/net/Makefile b/net/Makefile index 3995613e5510..a5d04098dfce 100644 --- a/net/Makefile +++ b/net/Makefile @@ -74,3 +74,6 @@ obj-$(CONFIG_HSR) += hsr/ ifneq ($(CONFIG_NET_SWITCHDEV),) obj-y += switchdev/ endif +ifneq ($(CONFIG_NET_L3_MASTER_DEV),) +obj-y += l3mdev/ +endif diff --git a/net/l3mdev/Kconfig b/net/l3mdev/Kconfig new file mode 100644 index 000000000000..5d47325037bc --- /dev/null +++ b/net/l3mdev/Kconfig @@ -0,0 +1,10 @@ +# +# Configuration for L3 master device support +# + +config NET_L3_MASTER_DEV + bool "L3 Master device support" + depends on INET || IPV6 + ---help--- + This module provides glue between core networking code and device + drivers to support L3 master devices like VRF. diff --git a/net/l3mdev/Makefile b/net/l3mdev/Makefile new file mode 100644 index 000000000000..84a53a6f609a --- /dev/null +++ b/net/l3mdev/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the L3 device API +# + +obj-$(CONFIG_NET_L3_MASTER_DEV) += l3mdev.o diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c new file mode 100644 index 000000000000..ddf75ad41713 --- /dev/null +++ b/net/l3mdev/l3mdev.c @@ -0,0 +1,92 @@ +/* + * net/l3mdev/l3mdev.c - L3 master device implementation + * Copyright (c) 2015 Cumulus Networks + * Copyright (c) 2015 David Ahern + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include +#include + +/** + * l3mdev_master_ifindex - get index of L3 master device + * @dev: targeted interface + */ + +int l3mdev_master_ifindex_rcu(struct net_device *dev) +{ + int ifindex = 0; + + if (!dev) + return 0; + + if (netif_is_l3_master(dev)) { + ifindex = dev->ifindex; + } else if (dev->flags & IFF_SLAVE) { + struct net_device *master; + + master = netdev_master_upper_dev_get_rcu(dev); + if (master && netif_is_l3_master(master)) + ifindex = master->ifindex; + } + + return ifindex; +} +EXPORT_SYMBOL_GPL(l3mdev_master_ifindex_rcu); + +/** + * l3mdev_fib_table - get FIB table id associated with an L3 + * master interface + * @dev: targeted interface + */ + +u32 l3mdev_fib_table_rcu(const struct net_device *dev) +{ + u32 tb_id = 0; + + if (!dev) + return 0; + + if (netif_is_l3_master(dev)) { + if (dev->l3mdev_ops->l3mdev_fib_table) + tb_id = dev->l3mdev_ops->l3mdev_fib_table(dev); + } else if (dev->flags & IFF_SLAVE) { + /* Users of netdev_master_upper_dev_get_rcu need non-const, + * but current inet_*type functions take a const + */ + struct net_device *_dev = (struct net_device *) dev; + const struct net_device *master; + + master = netdev_master_upper_dev_get_rcu(_dev); + if (master && netif_is_l3_master(master) && + master->l3mdev_ops->l3mdev_fib_table) + tb_id = master->l3mdev_ops->l3mdev_fib_table(master); + } + + return tb_id; +} +EXPORT_SYMBOL_GPL(l3mdev_fib_table_rcu); + +u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) +{ + struct net_device *dev; + u32 tb_id = 0; + + if (!ifindex) + return 0; + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, ifindex); + if (dev) + tb_id = l3mdev_fib_table_rcu(dev); + + rcu_read_unlock(); + + return tb_id; +} +EXPORT_SYMBOL_GPL(l3mdev_fib_table_by_index); -- cgit v1.2.3 From 385add906b6155e8bc64035ad56fb8ccfef925f7 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:13 -0700 Subject: net: Replace vrf_master_ifindex{, _rcu} with l3mdev equivalents Replace calls to vrf_master_ifindex_rcu and vrf_master_ifindex with either l3mdev_master_ifindex_rcu or l3mdev_master_ifindex. The pattern: oif = vrf_master_ifindex(dev) ? : dev->ifindex; is replaced with oif = l3mdev_fib_oif(dev); And remove the now unused vrf macros. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/vrf.h | 41 ----------------------------------------- net/ipv4/fib_frontend.c | 5 +++-- net/ipv4/icmp.c | 8 ++++---- net/ipv4/ip_fragment.c | 6 +++--- net/ipv4/route.c | 7 ++++--- net/ipv4/xfrm4_policy.c | 8 +++----- net/ipv6/xfrm6_policy.c | 8 +++----- 7 files changed, 20 insertions(+), 63 deletions(-) (limited to 'include') diff --git a/include/net/vrf.h b/include/net/vrf.h index 34bb3f69def2..874a6c9e4217 100644 --- a/include/net/vrf.h +++ b/include/net/vrf.h @@ -34,37 +34,6 @@ struct net_vrf { #if IS_ENABLED(CONFIG_NET_VRF) -/* called with rcu_read_lock() */ -static inline int vrf_master_ifindex_rcu(const struct net_device *dev) -{ - struct net_vrf_dev *vrf_ptr; - int ifindex = 0; - - if (!dev) - return 0; - - if (netif_is_l3_master(dev)) { - ifindex = dev->ifindex; - } else { - vrf_ptr = rcu_dereference(dev->vrf_ptr); - if (vrf_ptr) - ifindex = vrf_ptr->ifindex; - } - - return ifindex; -} - -static inline int vrf_master_ifindex(const struct net_device *dev) -{ - int ifindex; - - rcu_read_lock(); - ifindex = vrf_master_ifindex_rcu(dev); - rcu_read_unlock(); - - return ifindex; -} - /* called with rcu_read_lock */ static inline u32 vrf_dev_table_rcu(const struct net_device *dev) { @@ -139,16 +108,6 @@ static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) } #else -static inline int vrf_master_ifindex_rcu(const struct net_device *dev) -{ - return 0; -} - -static inline int vrf_master_ifindex(const struct net_device *dev) -{ - return 0; -} - static inline u32 vrf_dev_table_rcu(const struct net_device *dev) { return 0; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 6fcbd215cdbc..b901b344f22d 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #ifndef CONFIG_IP_MULTIPLE_TABLES @@ -332,7 +333,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, bool dev_match; fl4.flowi4_oif = 0; - fl4.flowi4_iif = vrf_master_ifindex_rcu(dev); + fl4.flowi4_iif = l3mdev_master_ifindex_rcu(dev); if (!fl4.flowi4_iif) fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; @@ -366,7 +367,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, if (nh->nh_dev == dev) { dev_match = true; break; - } else if (vrf_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) { + } else if (l3mdev_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) { dev_match = true; break; } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index e5eb8ac4089d..6b96dee2800b 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -96,7 +96,7 @@ #include #include #include -#include +#include /* * Build xmit assembly blocks @@ -309,7 +309,7 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, rc = false; if (icmp_global_allow()) { - int vif = vrf_master_ifindex(dst->dev); + int vif = l3mdev_master_ifindex(dst->dev); struct inet_peer *peer; peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1); @@ -427,7 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) fl4.flowi4_mark = mark; fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_proto = IPPROTO_ICMP; - fl4.flowi4_oif = vrf_master_ifindex(skb->dev); + fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev); security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) @@ -461,7 +461,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; - fl4->flowi4_oif = vrf_master_ifindex(skb_in->dev); + fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = __ip_route_output_key(net, fl4); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index fa7f15305f9a..9772b789adf3 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -48,7 +48,7 @@ #include #include #include -#include +#include /* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6 * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c @@ -78,7 +78,7 @@ struct ipq { u8 ecn; /* RFC3168 support */ u16 max_df_size; /* largest frag with DF set seen */ int iif; - int vif; /* VRF device index */ + int vif; /* L3 master device index */ unsigned int rid; struct inet_peer *peer; }; @@ -657,7 +657,7 @@ out_fail: int ip_defrag(struct sk_buff *skb, u32 user) { struct net_device *dev = skb->dev ? : skb_dst(skb)->dev; - int vif = vrf_master_ifindex_rcu(dev); + int vif = l3mdev_master_ifindex_rcu(dev); struct net *net = dev_net(dev); struct ipq *qp; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a670f894ce13..ba466667c45c 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -113,6 +113,7 @@ #include #include #include +#include #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) @@ -847,7 +848,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) return; } log_martians = IN_DEV_LOG_MARTIANS(in_dev); - vif = vrf_master_ifindex_rcu(rt->dst.dev); + vif = l3mdev_master_ifindex_rcu(rt->dst.dev); rcu_read_unlock(); net = dev_net(rt->dst.dev); @@ -941,7 +942,7 @@ static int ip_error(struct sk_buff *skb) } peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, - vrf_master_ifindex(skb->dev), 1); + l3mdev_master_ifindex(skb->dev), 1); send = true; if (peer) { @@ -1739,7 +1740,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, * Now we are ready to route packet. */ fl4.flowi4_oif = 0; - fl4.flowi4_iif = vrf_master_ifindex_rcu(dev) ? : dev->ifindex; + fl4.flowi4_iif = l3mdev_fib_oif_rcu(dev); fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 0304d1680ca2..f2606b9056bb 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include static struct xfrm_policy_afinfo xfrm4_policy_afinfo; @@ -111,10 +111,8 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) struct flowi4 *fl4 = &fl->u.ip4; int oif = 0; - if (skb_dst(skb)) { - oif = vrf_master_ifindex(skb_dst(skb)->dev) ? - : skb_dst(skb)->dev->ifindex; - } + if (skb_dst(skb)) + oif = l3mdev_fib_oif(skb_dst(skb)->dev); memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 30caa289c5db..69cee4e0d728 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #if IS_ENABLED(CONFIG_IPV6_MIP6) #include #endif @@ -132,10 +132,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) nexthdr = nh[nhoff]; - if (skb_dst(skb)) { - oif = vrf_master_ifindex(skb_dst(skb)->dev) ? - : skb_dst(skb)->dev->ifindex; - } + if (skb_dst(skb)) + oif = l3mdev_fib_oif(skb_dst(skb)->dev); memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; -- cgit v1.2.3 From 3236b0042ba6555b45d75b6be12922922e17d66e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:14 -0700 Subject: net: Replace vrf_dev_table and friends Replace calls to vrf_dev_table and friends with l3mdev_fib_table and kin. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/vrf.h | 80 ------------------------------------------------- net/ipv4/af_inet.c | 4 +-- net/ipv4/fib_frontend.c | 7 ++--- 3 files changed, 5 insertions(+), 86 deletions(-) (limited to 'include') diff --git a/include/net/vrf.h b/include/net/vrf.h index 874a6c9e4217..b05b96646e2a 100644 --- a/include/net/vrf.h +++ b/include/net/vrf.h @@ -34,66 +34,6 @@ struct net_vrf { #if IS_ENABLED(CONFIG_NET_VRF) -/* called with rcu_read_lock */ -static inline u32 vrf_dev_table_rcu(const struct net_device *dev) -{ - u32 tb_id = 0; - - if (dev) { - struct net_vrf_dev *vrf_ptr; - - vrf_ptr = rcu_dereference(dev->vrf_ptr); - if (vrf_ptr) - tb_id = vrf_ptr->tb_id; - } - return tb_id; -} - -static inline u32 vrf_dev_table(const struct net_device *dev) -{ - u32 tb_id; - - rcu_read_lock(); - tb_id = vrf_dev_table_rcu(dev); - rcu_read_unlock(); - - return tb_id; -} - -static inline u32 vrf_dev_table_ifindex(struct net *net, int ifindex) -{ - struct net_device *dev; - u32 tb_id = 0; - - if (!ifindex) - return 0; - - rcu_read_lock(); - - dev = dev_get_by_index_rcu(net, ifindex); - if (dev) - tb_id = vrf_dev_table_rcu(dev); - - rcu_read_unlock(); - - return tb_id; -} - -/* called with rtnl */ -static inline u32 vrf_dev_table_rtnl(const struct net_device *dev) -{ - u32 tb_id = 0; - - if (dev) { - struct net_vrf_dev *vrf_ptr; - - vrf_ptr = rtnl_dereference(dev->vrf_ptr); - if (vrf_ptr) - tb_id = vrf_ptr->tb_id; - } - return tb_id; -} - /* caller has already checked netif_is_l3_master(dev) */ static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) { @@ -108,26 +48,6 @@ static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) } #else -static inline u32 vrf_dev_table_rcu(const struct net_device *dev) -{ - return 0; -} - -static inline u32 vrf_dev_table(const struct net_device *dev) -{ - return 0; -} - -static inline u32 vrf_dev_table_ifindex(struct net *net, int ifindex) -{ - return 0; -} - -static inline u32 vrf_dev_table_rtnl(const struct net_device *dev) -{ - return 0; -} - static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) { return ERR_PTR(-ENETUNREACH); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 3af85eecbe11..11c4ca13ec3b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -119,7 +119,7 @@ #ifdef CONFIG_IP_MROUTE #include #endif -#include +#include /* The inetsw table contains everything that inet_create needs to @@ -446,7 +446,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } - tb_id = vrf_dev_table_ifindex(net, sk->sk_bound_dev_if) ? : tb_id; + tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); /* Not specified by any standard per-se, however it breaks too diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index b901b344f22d..fac172370276 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -45,7 +45,6 @@ #include #include #include -#include #include #include @@ -256,7 +255,7 @@ EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { - u32 rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL; + u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, dev, addr, rt_table); } @@ -269,7 +268,7 @@ unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr) { - u32 rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL; + u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, NULL, addr, rt_table); } @@ -804,7 +803,7 @@ out: static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa) { struct net *net = dev_net(ifa->ifa_dev->dev); - u32 tb_id = vrf_dev_table_rtnl(ifa->ifa_dev->dev); + u32 tb_id = l3mdev_fib_table(ifa->ifa_dev->dev); struct fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, -- cgit v1.2.3 From 8e1ed7058b3c79b085cf5b1529698a157499074c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:15 -0700 Subject: net: Replace calls to vrf_dev_get_rth Replace calls to vrf_dev_get_rth with l3mdev_get_rtable. The check on the flow flags is handled in the l3mdev operation. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/vrf.h | 22 ---------------------- net/ipv4/route.c | 8 +++----- 2 files changed, 3 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/net/vrf.h b/include/net/vrf.h index b05b96646e2a..5bba1535ba73 100644 --- a/include/net/vrf.h +++ b/include/net/vrf.h @@ -32,26 +32,4 @@ struct net_vrf { u32 tb_id; }; - -#if IS_ENABLED(CONFIG_NET_VRF) -/* caller has already checked netif_is_l3_master(dev) */ -static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) -{ - struct rtable *rth = ERR_PTR(-ENETUNREACH); - struct net_vrf *vrf = netdev_priv(dev); - - if (vrf) { - rth = vrf->rth; - atomic_inc(&rth->dst.__refcnt); - } - return rth; -} - -#else -static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) -{ - return ERR_PTR(-ENETUNREACH); -} -#endif - #endif /* __LINUX_NET_VRF_H */ diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ba466667c45c..1441de1550e6 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -112,7 +112,6 @@ #endif #include #include -#include #include #define RT_FL_TOS(oldflp4) \ @@ -2125,11 +2124,10 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } - if (netif_is_l3_master(dev_out) && - !(fl4->flowi4_flags & FLOWI_FLAG_VRFSRC)) { - rth = vrf_dev_get_rth(dev_out); + + rth = l3mdev_get_rtable(dev_out, fl4); + if (rth) goto out; - } } if (!fl4->daddr) { -- cgit v1.2.3 From 93a7e7e837af6846052481da974320c19ab82e5c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:16 -0700 Subject: net: Remove the now unused vrf_ptr Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/vrf.c | 32 ++------------------------------ include/linux/netdevice.h | 2 -- include/net/vrf.h | 6 ------ 3 files changed, 2 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 72f1892ebad0..df872f4efb0d 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -396,18 +396,15 @@ static void __vrf_insert_slave(struct slave_queue *queue, struct slave *slave) static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) { - struct net_vrf_dev *vrf_ptr = kmalloc(sizeof(*vrf_ptr), GFP_KERNEL); struct slave *slave = kzalloc(sizeof(*slave), GFP_KERNEL); struct net_vrf *vrf = netdev_priv(dev); struct slave_queue *queue = &vrf->queue; int ret = -ENOMEM; - if (!slave || !vrf_ptr) + if (!slave) goto out_fail; slave->dev = port_dev; - vrf_ptr->ifindex = dev->ifindex; - vrf_ptr->tb_id = vrf->tb_id; /* register the packet handler for slave ports */ ret = netdev_rx_handler_register(port_dev, vrf_handle_frame, dev); @@ -424,7 +421,6 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) port_dev->flags |= IFF_SLAVE; __vrf_insert_slave(queue, slave); - rcu_assign_pointer(port_dev->vrf_ptr, vrf_ptr); cycle_netdev(port_dev); return 0; @@ -432,7 +428,6 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) out_unregister: netdev_rx_handler_unregister(port_dev); out_fail: - kfree(vrf_ptr); kfree(slave); return ret; } @@ -448,21 +443,15 @@ static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev) /* inverse of do_vrf_add_slave */ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { - struct net_vrf_dev *vrf_ptr = rtnl_dereference(port_dev->vrf_ptr); struct net_vrf *vrf = netdev_priv(dev); struct slave_queue *queue = &vrf->queue; struct slave *slave; - RCU_INIT_POINTER(port_dev->vrf_ptr, NULL); - netdev_upper_dev_unlink(port_dev, dev); port_dev->flags &= ~IFF_SLAVE; netdev_rx_handler_unregister(port_dev); - /* after netdev_rx_handler_unregister for synchronize_rcu */ - kfree(vrf_ptr); - cycle_netdev(port_dev); slave = __vrf_find_slave_dev(queue, port_dev); @@ -601,10 +590,6 @@ static int vrf_validate(struct nlattr *tb[], struct nlattr *data[]) static void vrf_dellink(struct net_device *dev, struct list_head *head) { - struct net_vrf_dev *vrf_ptr = rtnl_dereference(dev->vrf_ptr); - - RCU_INIT_POINTER(dev->vrf_ptr, NULL); - kfree_rcu(vrf_ptr, rcu); unregister_netdevice_queue(dev, head); } @@ -612,7 +597,6 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct net_vrf *vrf = netdev_priv(dev); - struct net_vrf_dev *vrf_ptr; int err; if (!data || !data[IFLA_VRF_TABLE]) @@ -622,24 +606,13 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev, dev->priv_flags |= IFF_L3MDEV_MASTER; - err = -ENOMEM; - vrf_ptr = kmalloc(sizeof(*dev->vrf_ptr), GFP_KERNEL); - if (!vrf_ptr) - goto out_fail; - - vrf_ptr->ifindex = dev->ifindex; - vrf_ptr->tb_id = vrf->tb_id; - err = register_netdevice(dev); if (err < 0) goto out_fail; - rcu_assign_pointer(dev->vrf_ptr, vrf_ptr); - return 0; out_fail: - kfree(vrf_ptr); free_netdev(dev); return err; } @@ -683,10 +656,9 @@ static int vrf_device_event(struct notifier_block *unused, /* only care about unregister events to drop slave references */ if (event == NETDEV_UNREGISTER) { - struct net_vrf_dev *vrf_ptr = rtnl_dereference(dev->vrf_ptr); struct net_device *vrf_dev; - if (!vrf_ptr || netif_is_l3_master(dev)) + if (netif_is_l3_master(dev)) goto out; vrf_dev = netdev_master_upper_dev_get(dev); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c7f14794fe14..72bf9e37a2f0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1427,7 +1427,6 @@ enum netdev_priv_flags { * @dn_ptr: DECnet specific data * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data - * @vrf_ptr: VRF specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * * @last_rx: Time of last Rx @@ -1649,7 +1648,6 @@ struct net_device { struct dn_dev __rcu *dn_ptr; struct inet6_dev __rcu *ip6_ptr; void *ax25_ptr; - struct net_vrf_dev __rcu *vrf_ptr; struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; #if IS_ENABLED(CONFIG_MPLS_ROUTING) diff --git a/include/net/vrf.h b/include/net/vrf.h index 5bba1535ba73..e83fc38770dd 100644 --- a/include/net/vrf.h +++ b/include/net/vrf.h @@ -11,12 +11,6 @@ #ifndef __LINUX_NET_VRF_H #define __LINUX_NET_VRF_H -struct net_vrf_dev { - struct rcu_head rcu; - int ifindex; /* ifindex of master dev */ - u32 tb_id; /* table id for VRF */ -}; - struct slave { struct list_head list; struct net_device *dev; -- cgit v1.2.3 From ec539514e56284b21c47468f23f7d01ff882f51b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:17 -0700 Subject: net: Remove vrf header file Move remaining structs to VRF driver and delete the vrf header file. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- MAINTAINERS | 1 - drivers/net/vrf.c | 16 +++++++++++++++- include/net/vrf.h | 29 ----------------------------- 3 files changed, 15 insertions(+), 31 deletions(-) delete mode 100644 include/net/vrf.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 3f2d7a9d0bbf..fa43fa2f30e4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11273,7 +11273,6 @@ M: Shrijeet Mukherjee L: netdev@vger.kernel.org S: Maintained F: drivers/net/vrf.c -F: include/net/vrf.h F: Documentation/networking/vrf.txt VT1211 HARDWARE MONITOR DRIVER diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index df872f4efb0d..64f2ab663ffe 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -34,7 +34,6 @@ #include #include #include -#include #include #define DRV_NAME "vrf" @@ -45,6 +44,21 @@ #define vrf_master_get_rcu(dev) \ ((struct net_device *)rcu_dereference(dev->rx_handler_data)) +struct slave { + struct list_head list; + struct net_device *dev; +}; + +struct slave_queue { + struct list_head all_slaves; +}; + +struct net_vrf { + struct slave_queue queue; + struct rtable *rth; + u32 tb_id; +}; + struct pcpu_dstats { u64 tx_pkts; u64 tx_bytes; diff --git a/include/net/vrf.h b/include/net/vrf.h deleted file mode 100644 index e83fc38770dd..000000000000 --- a/include/net/vrf.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * include/net/net_vrf.h - adds vrf dev structure definitions - * Copyright (c) 2015 Cumulus Networks - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#ifndef __LINUX_NET_VRF_H -#define __LINUX_NET_VRF_H - -struct slave { - struct list_head list; - struct net_device *dev; -}; - -struct slave_queue { - struct list_head all_slaves; -}; - -struct net_vrf { - struct slave_queue queue; - struct rtable *rth; - u32 tb_id; -}; - -#endif /* __LINUX_NET_VRF_H */ -- cgit v1.2.3 From 9478d12d33ad12d29c5343ae7346b51bc1f4c5a9 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:18 -0700 Subject: net: Move netif_index_is_l3_master to l3mdev.h Change CONFIG dependency to CONFIG_NET_L3_MASTER_DEV as well. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 21 --------------------- include/net/l3mdev.h | 24 ++++++++++++++++++++++++ include/net/route.h | 1 + 3 files changed, 25 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 72bf9e37a2f0..b9450784ae06 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3840,27 +3840,6 @@ static inline bool netif_is_ovs_master(const struct net_device *dev) return dev->priv_flags & IFF_OPENVSWITCH; } -static inline bool netif_index_is_l3_master(struct net *net, int ifindex) -{ - bool rc = false; - -#if IS_ENABLED(CONFIG_NET_VRF) - struct net_device *dev; - - if (ifindex == 0) - return false; - - rcu_read_lock(); - - dev = dev_get_by_index_rcu(net, ifindex); - if (dev) - rc = netif_is_l3_master(dev); - - rcu_read_unlock(); -#endif - return rc; -} - /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index e382c777bab8..87cee05a0a17 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -81,6 +81,25 @@ static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev, return NULL; } +static inline bool netif_index_is_l3_master(struct net *net, int ifindex) +{ + struct net_device *dev; + bool rc = false; + + if (ifindex == 0) + return false; + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, ifindex); + if (dev) + rc = netif_is_l3_master(dev); + + rcu_read_unlock(); + + return rc; +} + #else static inline int l3mdev_master_ifindex_rcu(struct net_device *dev) @@ -120,6 +139,11 @@ static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev, return NULL; } +static inline bool netif_index_is_l3_master(struct net *net, int ifindex) +{ + return false; +} + #endif #endif /* _NET_L3MDEV_H_ */ diff --git a/include/net/route.h b/include/net/route.h index a565d0dad12c..e211dc167db1 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 03d5fb18626aff95426a380aef0d1c6904cac7c9 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 29 Sep 2015 12:07:15 -0400 Subject: net: switchdev: remove dev from switchdev_obj cb The net_device associated to a dump operation does not have to be passed to the callback. switchdev stores it in a superset struct, if needed. Also some drivers (such as DSA drivers) may not have easy access to it. This will simplify pushing the callback function down to the drivers. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 4 ++-- include/net/switchdev.h | 2 +- net/dsa/slave.c | 4 ++-- net/switchdev/switchdev.c | 6 ++---- 4 files changed, 7 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index d3f663262184..78fd443f2ea1 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4556,7 +4556,7 @@ static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, fdb->ndm_state = NUD_REACHABLE; fdb->vid = rocker_port_vlan_to_vid(rocker_port, found->key.vlan_id); - err = obj->cb(rocker_port->dev, obj); + err = obj->cb(obj); if (err) break; } @@ -4579,7 +4579,7 @@ static int rocker_port_vlan_dump(const struct rocker_port *rocker_port, if (rocker_vlan_id_is_internal(htons(vid))) vlan->flags |= BRIDGE_VLAN_INFO_PVID; vlan->vid_begin = vlan->vid_end = vid; - err = obj->cb(rocker_port->dev, obj); + err = obj->cb(obj); if (err) break; } diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 18207878e407..9ef7c5635769 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -66,7 +66,7 @@ enum switchdev_obj_id { struct switchdev_obj { enum switchdev_obj_id id; - int (*cb)(struct net_device *dev, struct switchdev_obj *obj); + int (*cb)(struct switchdev_obj *obj); union { struct switchdev_obj_vlan { /* PORT_VLAN */ u16 flags; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index f18cae54a5d8..0b47647961e8 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -334,7 +334,7 @@ static int dsa_slave_port_vlan_dump(struct net_device *dev, if (test_bit(p->port, untagged)) vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED; - err = obj->cb(dev, obj); + err = obj->cb(obj); if (err) break; } @@ -397,7 +397,7 @@ static int dsa_slave_port_fdb_dump(struct net_device *dev, obj->u.fdb.vid = vid; obj->u.fdb.ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; - ret = obj->cb(dev, obj); + ret = obj->cb(obj); if (ret < 0) break; } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index c0e2047f8984..93f4971e68db 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -514,8 +514,7 @@ static int switchdev_port_vlan_dump_put(struct switchdev_vlan_dump *dump) return 0; } -static int switchdev_port_vlan_dump_cb(struct net_device *dev, - struct switchdev_obj *obj) +static int switchdev_port_vlan_dump_cb(struct switchdev_obj *obj) { struct switchdev_vlan_dump *dump = container_of(obj, struct switchdev_vlan_dump, obj); @@ -864,8 +863,7 @@ struct switchdev_fdb_dump { int idx; }; -static int switchdev_port_fdb_dump_cb(struct net_device *dev, - struct switchdev_obj *obj) +static int switchdev_port_fdb_dump_cb(struct switchdev_obj *obj) { struct switchdev_fdb_dump *dump = container_of(obj, struct switchdev_fdb_dump, obj); -- cgit v1.2.3 From 25f07adc473f05f850efc9414b9da3374563015f Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 29 Sep 2015 12:07:16 -0400 Subject: net: switchdev: pass callback to dump operation Similar to the notifier_call callback of a notifier_block, change the function signature of switchdev dump operation to: int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, void *obj, int (*cb)(void *obj)); This allows the caller to pass and expect back a specific switchdev_obj_* structure instead of the generic switchdev_obj one. Drivers implementation of dump operation can now expect this specific structure and call the callback with it. Drivers have been changed accordingly. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 21 +++++++++-------- include/net/switchdev.h | 9 +++++--- net/dsa/slave.c | 26 +++++++++++---------- net/switchdev/switchdev.c | 45 ++++++++++++++++++------------------ 4 files changed, 53 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 78fd443f2ea1..107adb6aee81 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4538,10 +4538,10 @@ static int rocker_port_obj_del(struct net_device *dev, } static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, - struct switchdev_obj *obj) + struct switchdev_obj_fdb *fdb, + int (*cb)(void *obj)) { struct rocker *rocker = rocker_port->rocker; - struct switchdev_obj_fdb *fdb = &obj->u.fdb; struct rocker_fdb_tbl_entry *found; struct hlist_node *tmp; unsigned long lock_flags; @@ -4556,7 +4556,7 @@ static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, fdb->ndm_state = NUD_REACHABLE; fdb->vid = rocker_port_vlan_to_vid(rocker_port, found->key.vlan_id); - err = obj->cb(obj); + err = cb(fdb); if (err) break; } @@ -4566,9 +4566,9 @@ static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, } static int rocker_port_vlan_dump(const struct rocker_port *rocker_port, - struct switchdev_obj *obj) + struct switchdev_obj_vlan *vlan, + int (*cb)(void *obj)) { - struct switchdev_obj_vlan *vlan = &obj->u.vlan; u16 vid; int err = 0; @@ -4579,7 +4579,7 @@ static int rocker_port_vlan_dump(const struct rocker_port *rocker_port, if (rocker_vlan_id_is_internal(htons(vid))) vlan->flags |= BRIDGE_VLAN_INFO_PVID; vlan->vid_begin = vlan->vid_end = vid; - err = obj->cb(obj); + err = cb(vlan); if (err) break; } @@ -4588,17 +4588,18 @@ static int rocker_port_vlan_dump(const struct rocker_port *rocker_port, } static int rocker_port_obj_dump(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, void *obj, + int (*cb)(void *obj)) { const struct rocker_port *rocker_port = netdev_priv(dev); int err = 0; - switch (obj->id) { + switch (id) { case SWITCHDEV_OBJ_PORT_FDB: - err = rocker_port_fdb_dump(rocker_port, obj); + err = rocker_port_fdb_dump(rocker_port, obj, cb); break; case SWITCHDEV_OBJ_PORT_VLAN: - err = rocker_port_vlan_dump(rocker_port, obj); + err = rocker_port_vlan_dump(rocker_port, obj, cb); break; default: err = -EOPNOTSUPP; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 9ef7c5635769..a2f57fb5f622 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -120,7 +120,8 @@ struct switchdev_ops { int (*switchdev_port_obj_del)(struct net_device *dev, struct switchdev_obj *obj); int (*switchdev_port_obj_dump)(struct net_device *dev, - struct switchdev_obj *obj); + enum switchdev_obj_id id, void *obj, + int (*cb)(void *obj)); }; enum switchdev_notifier_type { @@ -152,7 +153,8 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj); int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj); -int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj); +int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, + void *obj, int (*cb)(void *obj)); int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, @@ -209,7 +211,8 @@ static inline int switchdev_port_obj_del(struct net_device *dev, } static inline int switchdev_port_obj_dump(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, void *obj, + int (*cb)(void *obj)) { return -EOPNOTSUPP; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 0b47647961e8..c3b868c3373b 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -300,9 +300,9 @@ static int dsa_slave_port_vlan_del(struct net_device *dev, } static int dsa_slave_port_vlan_dump(struct net_device *dev, - struct switchdev_obj *obj) + struct switchdev_obj_vlan *vlan, + int (*cb)(void *obj)) { - struct switchdev_obj_vlan *vlan = &obj->u.vlan; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; DECLARE_BITMAP(members, DSA_MAX_PORTS); @@ -334,7 +334,7 @@ static int dsa_slave_port_vlan_dump(struct net_device *dev, if (test_bit(p->port, untagged)) vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED; - err = obj->cb(obj); + err = cb(vlan); if (err) break; } @@ -374,7 +374,8 @@ static int dsa_slave_port_fdb_del(struct net_device *dev, } static int dsa_slave_port_fdb_dump(struct net_device *dev, - struct switchdev_obj *obj) + struct switchdev_obj_fdb *fdb, + int (*cb)(void *obj)) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; @@ -393,11 +394,11 @@ static int dsa_slave_port_fdb_dump(struct net_device *dev, if (ret < 0) break; - obj->u.fdb.addr = addr; - obj->u.fdb.vid = vid; - obj->u.fdb.ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; + fdb->addr = addr; + fdb->vid = vid; + fdb->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; - ret = obj->cb(obj); + ret = cb(fdb); if (ret < 0) break; } @@ -518,16 +519,17 @@ static int dsa_slave_port_obj_del(struct net_device *dev, } static int dsa_slave_port_obj_dump(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, void *obj, + int (*cb)(void *obj)) { int err; - switch (obj->id) { + switch (id) { case SWITCHDEV_OBJ_PORT_FDB: - err = dsa_slave_port_fdb_dump(dev, obj); + err = dsa_slave_port_fdb_dump(dev, obj, cb); break; case SWITCHDEV_OBJ_PORT_VLAN: - err = dsa_slave_port_vlan_dump(dev, obj); + err = dsa_slave_port_vlan_dump(dev, obj, cb); break; default: err = -EOPNOTSUPP; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 93f4971e68db..2ef863c96359 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -386,9 +386,12 @@ EXPORT_SYMBOL_GPL(switchdev_port_obj_del); * switchdev_port_obj_dump - Dump port objects * * @dev: port device + * @id: object ID * @obj: object to dump + * @cb: function to call with a filled object */ -int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj) +int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, + void *obj, int (*cb)(void *obj)) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; @@ -396,7 +399,7 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj) int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_dump) - return ops->switchdev_port_obj_dump(dev, obj); + return ops->switchdev_port_obj_dump(dev, id, obj, cb); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to dump objects on @@ -404,7 +407,7 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj) */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = switchdev_port_obj_dump(lower_dev, obj); + err = switchdev_port_obj_dump(lower_dev, id, obj, cb); break; } @@ -476,7 +479,7 @@ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, EXPORT_SYMBOL_GPL(call_switchdev_notifiers); struct switchdev_vlan_dump { - struct switchdev_obj obj; + struct switchdev_obj_vlan vlan; struct sk_buff *skb; u32 filter_mask; u16 flags; @@ -514,11 +517,11 @@ static int switchdev_port_vlan_dump_put(struct switchdev_vlan_dump *dump) return 0; } -static int switchdev_port_vlan_dump_cb(struct switchdev_obj *obj) +static int switchdev_port_vlan_dump_cb(void *obj) { + struct switchdev_obj_vlan *vlan = obj; struct switchdev_vlan_dump *dump = - container_of(obj, struct switchdev_vlan_dump, obj); - struct switchdev_obj_vlan *vlan = &dump->obj.u.vlan; + container_of(vlan, struct switchdev_vlan_dump, vlan); int err = 0; if (vlan->vid_begin > vlan->vid_end) @@ -570,10 +573,6 @@ static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev, u32 filter_mask) { struct switchdev_vlan_dump dump = { - .obj = { - .id = SWITCHDEV_OBJ_PORT_VLAN, - .cb = switchdev_port_vlan_dump_cb, - }, .skb = skb, .filter_mask = filter_mask, }; @@ -581,7 +580,9 @@ static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev, if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { - err = switchdev_port_obj_dump(dev, &dump.obj); + err = switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_PORT_VLAN, + &dump.vlan, + switchdev_port_vlan_dump_cb); if (err) goto err_out; if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) @@ -856,17 +857,18 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], EXPORT_SYMBOL_GPL(switchdev_port_fdb_del); struct switchdev_fdb_dump { - struct switchdev_obj obj; + struct switchdev_obj_fdb fdb; struct net_device *dev; struct sk_buff *skb; struct netlink_callback *cb; int idx; }; -static int switchdev_port_fdb_dump_cb(struct switchdev_obj *obj) +static int switchdev_port_fdb_dump_cb(void *obj) { + struct switchdev_obj_fdb *fdb = obj; struct switchdev_fdb_dump *dump = - container_of(obj, struct switchdev_fdb_dump, obj); + container_of(fdb, struct switchdev_fdb_dump, fdb); u32 portid = NETLINK_CB(dump->cb->skb).portid; u32 seq = dump->cb->nlh->nlmsg_seq; struct nlmsghdr *nlh; @@ -887,12 +889,12 @@ static int switchdev_port_fdb_dump_cb(struct switchdev_obj *obj) ndm->ndm_flags = NTF_SELF; ndm->ndm_type = 0; ndm->ndm_ifindex = dump->dev->ifindex; - ndm->ndm_state = obj->u.fdb.ndm_state; + ndm->ndm_state = fdb->ndm_state; - if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, obj->u.fdb.addr)) + if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, fdb->addr)) goto nla_put_failure; - if (obj->u.fdb.vid && nla_put_u16(dump->skb, NDA_VLAN, obj->u.fdb.vid)) + if (fdb->vid && nla_put_u16(dump->skb, NDA_VLAN, fdb->vid)) goto nla_put_failure; nlmsg_end(dump->skb, nlh); @@ -922,17 +924,14 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *filter_dev, int idx) { struct switchdev_fdb_dump dump = { - .obj = { - .id = SWITCHDEV_OBJ_PORT_FDB, - .cb = switchdev_port_fdb_dump_cb, - }, .dev = dev, .skb = skb, .cb = cb, .idx = idx, }; - switchdev_port_obj_dump(dev, &dump.obj); + switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_PORT_FDB, &dump.fdb, + switchdev_port_fdb_dump_cb); return dump.idx; } EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump); -- cgit v1.2.3 From ab06900230181b5a717b1e1a39c44e96f6292e71 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 29 Sep 2015 12:07:17 -0400 Subject: net: switchdev: abstract object in add/del ops Similar to the notifier_call callback of a notifier_block, change the function signature of switchdev add and del operations to: int switchdev_port_obj_add/del(struct net_device *dev, enum switchdev_obj_id id, void *obj); This allows the caller to pass a specific switchdev_obj_* structure instead of the generic switchdev_obj one. Drivers implementation of these operations and switchdev have been changed accordingly. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 21 +++--- include/net/switchdev.h | 18 ++++-- net/bridge/br_fdb.c | 11 ++-- net/bridge/br_vlan.c | 24 +++---- net/dsa/slave.c | 20 +++--- net/switchdev/switchdev.c | 122 ++++++++++++++++------------------- 6 files changed, 99 insertions(+), 117 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 107adb6aee81..9773f5b65296 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4437,26 +4437,25 @@ static int rocker_port_fdb_add(struct rocker_port *rocker_port, } static int rocker_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj, + enum switchdev_obj_id id, const void *obj, struct switchdev_trans *trans) { struct rocker_port *rocker_port = netdev_priv(dev); const struct switchdev_obj_ipv4_fib *fib4; int err = 0; - switch (obj->id) { + switch (id) { case SWITCHDEV_OBJ_PORT_VLAN: - err = rocker_port_vlans_add(rocker_port, trans, - &obj->u.vlan); + err = rocker_port_vlans_add(rocker_port, trans, obj); break; case SWITCHDEV_OBJ_IPV4_FIB: - fib4 = &obj->u.ipv4_fib; + fib4 = obj; err = rocker_port_fib_ipv4(rocker_port, trans, htonl(fib4->dst), fib4->dst_len, fib4->fi, fib4->tb_id, 0); break; case SWITCHDEV_OBJ_PORT_FDB: - err = rocker_port_fdb_add(rocker_port, trans, &obj->u.fdb); + err = rocker_port_fdb_add(rocker_port, trans, obj); break; default: err = -EOPNOTSUPP; @@ -4509,25 +4508,25 @@ static int rocker_port_fdb_del(struct rocker_port *rocker_port, } static int rocker_port_obj_del(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, const void *obj) { struct rocker_port *rocker_port = netdev_priv(dev); const struct switchdev_obj_ipv4_fib *fib4; int err = 0; - switch (obj->id) { + switch (id) { case SWITCHDEV_OBJ_PORT_VLAN: - err = rocker_port_vlans_del(rocker_port, &obj->u.vlan); + err = rocker_port_vlans_del(rocker_port, obj); break; case SWITCHDEV_OBJ_IPV4_FIB: - fib4 = &obj->u.ipv4_fib; + fib4 = obj; err = rocker_port_fib_ipv4(rocker_port, NULL, htonl(fib4->dst), fib4->dst_len, fib4->fi, fib4->tb_id, ROCKER_OP_FLAG_REMOVE); break; case SWITCHDEV_OBJ_PORT_FDB: - err = rocker_port_fdb_del(rocker_port, NULL, &obj->u.fdb); + err = rocker_port_fdb_del(rocker_port, NULL, obj); break; default: err = -EOPNOTSUPP; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index a2f57fb5f622..bcadac33c29c 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -115,10 +115,12 @@ struct switchdev_ops { struct switchdev_attr *attr, struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, - struct switchdev_obj *obj, + enum switchdev_obj_id id, + const void *obj, struct switchdev_trans *trans); int (*switchdev_port_obj_del)(struct net_device *dev, - struct switchdev_obj *obj); + enum switchdev_obj_id id, + const void *obj); int (*switchdev_port_obj_dump)(struct net_device *dev, enum switchdev_obj_id id, void *obj, int (*cb)(void *obj)); @@ -151,8 +153,10 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr); -int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj); -int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj); +int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, + const void *obj); +int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, + const void *obj); int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, void *obj, int (*cb)(void *obj)); int register_switchdev_notifier(struct notifier_block *nb); @@ -199,13 +203,15 @@ static inline int switchdev_port_attr_set(struct net_device *dev, } static inline int switchdev_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, + const void *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_del(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, + const void *obj) { return -EOPNOTSUPP; } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 41de11e2eb11..7826782d62ab 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -133,15 +133,12 @@ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr) static void fdb_del_external_learn(struct net_bridge_fdb_entry *f) { - struct switchdev_obj obj = { - .id = SWITCHDEV_OBJ_PORT_FDB, - .u.fdb = { - .addr = f->addr.addr, - .vid = f->vlan_id, - }, + struct switchdev_obj_fdb fdb = { + .addr = f->addr.addr, + .vid = f->vlan_id, }; - switchdev_port_obj_del(f->dst->dev, &obj); + switchdev_port_obj_del(f->dst->dev, SWITCHDEV_OBJ_PORT_FDB, &fdb); } static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 8b392070051c..e227164bc3e1 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -80,16 +80,13 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, if (ops->ndo_vlan_rx_add_vid) { err = vlan_vid_add(dev, br->vlan_proto, vid); } else { - struct switchdev_obj vlan_obj = { - .id = SWITCHDEV_OBJ_PORT_VLAN, - .u.vlan = { - .flags = flags, - .vid_begin = vid, - .vid_end = vid, - }, + struct switchdev_obj_vlan v = { + .flags = flags, + .vid_begin = vid, + .vid_end = vid, }; - err = switchdev_port_obj_add(dev, &vlan_obj); + err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_PORT_VLAN, &v); if (err == -EOPNOTSUPP) err = 0; } @@ -132,15 +129,12 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, if (ops->ndo_vlan_rx_kill_vid) { vlan_vid_del(dev, br->vlan_proto, vid); } else { - struct switchdev_obj vlan_obj = { - .id = SWITCHDEV_OBJ_PORT_VLAN, - .u.vlan = { - .vid_begin = vid, - .vid_end = vid, - }, + struct switchdev_obj_vlan v = { + .vid_begin = vid, + .vid_end = vid, }; - err = switchdev_port_obj_del(dev, &vlan_obj); + err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_PORT_VLAN, &v); if (err == -EOPNOTSUPP) err = 0; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index c3b868c3373b..04f01535d2b6 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -242,10 +242,9 @@ static int dsa_bridge_check_vlan_range(struct dsa_switch *ds, } static int dsa_slave_port_vlan_add(struct net_device *dev, - struct switchdev_obj *obj, + const struct switchdev_obj_vlan *vlan, struct switchdev_trans *trans) { - struct switchdev_obj_vlan *vlan = &obj->u.vlan; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; u16 vid; @@ -279,9 +278,8 @@ static int dsa_slave_port_vlan_add(struct net_device *dev, } static int dsa_slave_port_vlan_del(struct net_device *dev, - struct switchdev_obj *obj) + const struct switchdev_obj_vlan *vlan) { - struct switchdev_obj_vlan *vlan = &obj->u.vlan; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; u16 vid; @@ -343,10 +341,9 @@ static int dsa_slave_port_vlan_dump(struct net_device *dev, } static int dsa_slave_port_fdb_add(struct net_device *dev, - struct switchdev_obj *obj, + const struct switchdev_obj_fdb *fdb, struct switchdev_trans *trans) { - struct switchdev_obj_fdb *fdb = &obj->u.fdb; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; int ret = -EOPNOTSUPP; @@ -360,9 +357,8 @@ static int dsa_slave_port_fdb_add(struct net_device *dev, } static int dsa_slave_port_fdb_del(struct net_device *dev, - struct switchdev_obj *obj) + const struct switchdev_obj_fdb *fdb) { - struct switchdev_obj_fdb *fdb = &obj->u.fdb; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; int ret = -EOPNOTSUPP; @@ -473,7 +469,7 @@ static int dsa_slave_port_attr_set(struct net_device *dev, } static int dsa_slave_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj, + enum switchdev_obj_id id, const void *obj, struct switchdev_trans *trans) { int err; @@ -483,7 +479,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev, * supported, return -EOPNOTSUPP. */ - switch (obj->id) { + switch (id) { case SWITCHDEV_OBJ_PORT_FDB: err = dsa_slave_port_fdb_add(dev, obj, trans); break; @@ -499,11 +495,11 @@ static int dsa_slave_port_obj_add(struct net_device *dev, } static int dsa_slave_port_obj_del(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, const void *obj) { int err; - switch (obj->id) { + switch (id) { case SWITCHDEV_OBJ_PORT_FDB: err = dsa_slave_port_fdb_del(dev, obj); break; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 2ef863c96359..fe82fab1d55c 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -270,7 +270,7 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) EXPORT_SYMBOL_GPL(switchdev_port_attr_set); static int __switchdev_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj, + enum switchdev_obj_id id, const void *obj, struct switchdev_trans *trans) { const struct switchdev_ops *ops = dev->switchdev_ops; @@ -279,7 +279,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_add) - return ops->switchdev_port_obj_add(dev, obj, trans); + return ops->switchdev_port_obj_add(dev, id, obj, trans); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to add object on @@ -287,7 +287,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = __switchdev_port_obj_add(lower_dev, obj, trans); + err = __switchdev_port_obj_add(lower_dev, id, obj, trans); if (err) break; } @@ -299,6 +299,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, * switchdev_port_obj_add - Add port object * * @dev: port device + * @id: object ID * @obj: object to add * * Use a 2-phase prepare-commit transaction model to ensure @@ -307,7 +308,8 @@ static int __switchdev_port_obj_add(struct net_device *dev, * * rtnl_lock must be held. */ -int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) +int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, + const void *obj) { struct switchdev_trans trans; int err; @@ -324,7 +326,7 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) */ trans.ph_prepare = true; - err = __switchdev_port_obj_add(dev, obj, &trans); + err = __switchdev_port_obj_add(dev, id, obj, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any * resources reserved in the prepare phase are @@ -343,8 +345,8 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) */ trans.ph_prepare = false; - err = __switchdev_port_obj_add(dev, obj, &trans); - WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); + err = __switchdev_port_obj_add(dev, id, obj, &trans); + WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, id); switchdev_trans_items_warn_destroy(dev, &trans); return err; @@ -355,9 +357,11 @@ EXPORT_SYMBOL_GPL(switchdev_port_obj_add); * switchdev_port_obj_del - Delete port object * * @dev: port device + * @id: object ID * @obj: object to delete */ -int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj) +int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, + const void *obj) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; @@ -365,7 +369,7 @@ int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj) int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_del) - return ops->switchdev_port_obj_del(dev, obj); + return ops->switchdev_port_obj_del(dev, id, obj); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to delete object on @@ -373,7 +377,7 @@ int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj) */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = switchdev_port_obj_del(lower_dev, obj); + err = switchdev_port_obj_del(lower_dev, id, obj); if (err) break; } @@ -695,14 +699,12 @@ static int switchdev_port_br_setlink_protinfo(struct net_device *dev, static int switchdev_port_br_afspec(struct net_device *dev, struct nlattr *afspec, int (*f)(struct net_device *dev, - struct switchdev_obj *obj)) + enum switchdev_obj_id id, + const void *obj)) { struct nlattr *attr; struct bridge_vlan_info *vinfo; - struct switchdev_obj obj = { - .id = SWITCHDEV_OBJ_PORT_VLAN, - }; - struct switchdev_obj_vlan *vlan = &obj.u.vlan; + struct switchdev_obj_vlan vlan = { 0 }; int rem; int err; @@ -712,30 +714,30 @@ static int switchdev_port_br_afspec(struct net_device *dev, if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo = nla_data(attr); - vlan->flags = vinfo->flags; + vlan.flags = vinfo->flags; if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { - if (vlan->vid_begin) + if (vlan.vid_begin) return -EINVAL; - vlan->vid_begin = vinfo->vid; + vlan.vid_begin = vinfo->vid; } else if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END) { - if (!vlan->vid_begin) + if (!vlan.vid_begin) return -EINVAL; - vlan->vid_end = vinfo->vid; - if (vlan->vid_end <= vlan->vid_begin) + vlan.vid_end = vinfo->vid; + if (vlan.vid_end <= vlan.vid_begin) return -EINVAL; - err = f(dev, &obj); + err = f(dev, SWITCHDEV_OBJ_PORT_VLAN, &vlan); if (err) return err; - memset(vlan, 0, sizeof(*vlan)); + memset(&vlan, 0, sizeof(vlan)); } else { - if (vlan->vid_begin) + if (vlan.vid_begin) return -EINVAL; - vlan->vid_begin = vinfo->vid; - vlan->vid_end = vinfo->vid; - err = f(dev, &obj); + vlan.vid_begin = vinfo->vid; + vlan.vid_end = vinfo->vid; + err = f(dev, SWITCHDEV_OBJ_PORT_VLAN, &vlan); if (err) return err; - memset(vlan, 0, sizeof(*vlan)); + memset(&vlan, 0, sizeof(vlan)); } } @@ -817,15 +819,12 @@ int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlm_flags) { - struct switchdev_obj obj = { - .id = SWITCHDEV_OBJ_PORT_FDB, - .u.fdb = { - .addr = addr, - .vid = vid, - }, + struct switchdev_obj_fdb fdb = { + .addr = addr, + .vid = vid, }; - return switchdev_port_obj_add(dev, &obj); + return switchdev_port_obj_add(dev, SWITCHDEV_OBJ_PORT_FDB, &fdb); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_add); @@ -844,15 +843,12 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid) { - struct switchdev_obj obj = { - .id = SWITCHDEV_OBJ_PORT_FDB, - .u.fdb = { - .addr = addr, - .vid = vid, - }, + struct switchdev_obj_fdb fdb = { + .addr = addr, + .vid = vid, }; - return switchdev_port_obj_del(dev, &obj); + return switchdev_port_obj_del(dev, SWITCHDEV_OBJ_PORT_FDB, &fdb); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_del); @@ -1009,17 +1005,14 @@ static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 nlflags, u32 tb_id) { - struct switchdev_obj fib_obj = { - .id = SWITCHDEV_OBJ_IPV4_FIB, - .u.ipv4_fib = { - .dst = dst, - .dst_len = dst_len, - .fi = fi, - .tos = tos, - .type = type, - .nlflags = nlflags, - .tb_id = tb_id, - }, + struct switchdev_obj_ipv4_fib ipv4_fib = { + .dst = dst, + .dst_len = dst_len, + .fi = fi, + .tos = tos, + .type = type, + .nlflags = nlflags, + .tb_id = tb_id, }; struct net_device *dev; int err = 0; @@ -1040,7 +1033,7 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; - err = switchdev_port_obj_add(dev, &fib_obj); + err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_IPV4_FIB, &ipv4_fib); if (!err) fi->fib_flags |= RTNH_F_OFFLOAD; @@ -1063,17 +1056,14 @@ EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_add); int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id) { - struct switchdev_obj fib_obj = { - .id = SWITCHDEV_OBJ_IPV4_FIB, - .u.ipv4_fib = { - .dst = dst, - .dst_len = dst_len, - .fi = fi, - .tos = tos, - .type = type, - .nlflags = 0, - .tb_id = tb_id, - }, + struct switchdev_obj_ipv4_fib ipv4_fib = { + .dst = dst, + .dst_len = dst_len, + .fi = fi, + .tos = tos, + .type = type, + .nlflags = 0, + .tb_id = tb_id, }; struct net_device *dev; int err = 0; @@ -1085,7 +1075,7 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; - err = switchdev_port_obj_del(dev, &fib_obj); + err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_IPV4_FIB, &ipv4_fib); if (!err) fi->fib_flags &= ~RTNH_F_OFFLOAD; -- cgit v1.2.3 From 44bbcf5c4a19a8be43ba35ca7e22310e171f022c Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 29 Sep 2015 12:07:18 -0400 Subject: net: switchdev: extract struct switchdev_obj_* Now that switchdev and its drivers directly use specific switchdev_obj_* structures, move them out of the switchdev_obj union and get rif of this outer structure. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 53 ++++++++++++++++++++++++------------------------- 1 file changed, 26 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index bcadac33c29c..e11425eb0735 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -64,30 +64,29 @@ enum switchdev_obj_id { SWITCHDEV_OBJ_PORT_FDB, }; -struct switchdev_obj { - enum switchdev_obj_id id; - int (*cb)(struct switchdev_obj *obj); - union { - struct switchdev_obj_vlan { /* PORT_VLAN */ - u16 flags; - u16 vid_begin; - u16 vid_end; - } vlan; - struct switchdev_obj_ipv4_fib { /* IPV4_FIB */ - u32 dst; - int dst_len; - struct fib_info *fi; - u8 tos; - u8 type; - u32 nlflags; - u32 tb_id; - } ipv4_fib; - struct switchdev_obj_fdb { /* PORT_FDB */ - const unsigned char *addr; - u16 vid; - u16 ndm_state; - } fdb; - } u; +/* SWITCHDEV_OBJ_PORT_VLAN */ +struct switchdev_obj_vlan { + u16 flags; + u16 vid_begin; + u16 vid_end; +}; + +/* SWITCHDEV_OBJ_IPV4_FIB */ +struct switchdev_obj_ipv4_fib { + u32 dst; + int dst_len; + struct fib_info *fi; + u8 tos; + u8 type; + u32 nlflags; + u32 tb_id; +}; + +/* SWITCHDEV_OBJ_PORT_FDB */ +struct switchdev_obj_fdb { + const unsigned char *addr; + u16 vid; + u16 ndm_state; }; void switchdev_trans_item_enqueue(struct switchdev_trans *trans, @@ -102,11 +101,11 @@ void *switchdev_trans_item_dequeue(struct switchdev_trans *trans); * * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr). * - * @switchdev_port_obj_add: Add an object to port (see switchdev_obj). + * @switchdev_port_obj_add: Add an object to port (see switchdev_obj_*). * - * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj). + * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj_*). * - * @switchdev_port_obj_dump: Dump port objects (see switchdev_obj). + * @switchdev_port_obj_dump: Dump port objects (see switchdev_obj_*). */ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, -- cgit v1.2.3 From 21fdd092acc7ebda0dfe682008592eb79c382707 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 09:32:03 -0700 Subject: net: Add support for filtering neigh dump by master device Add support for filtering neighbor dumps by master device by adding the NDA_MASTER attribute to the dump request. A new netlink flag, NLM_F_DUMP_FILTERED, is added to indicate the kernel supports the request and output is filtered as requested. Signed-off-by: David Ahern Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/uapi/linux/netlink.h | 1 + net/core/neighbour.c | 32 +++++++++++++++++++++++++++++++- 2 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 6f3fe16cd22a..f095155d8749 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -54,6 +54,7 @@ struct nlmsghdr { #define NLM_F_ACK 4 /* Reply with ack, with zero or error code */ #define NLM_F_ECHO 8 /* Echo this request */ #define NLM_F_DUMP_INTR 16 /* Dump was inconsistent due to sequence change */ +#define NLM_F_DUMP_FILTERED 32 /* Dump was filtered as requested */ /* Modifiers to GET request */ #define NLM_F_ROOT 0x100 /* specify tree root */ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2b515ba7e94f..8c57fdf4d68e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2235,14 +2235,42 @@ static void neigh_update_notify(struct neighbour *neigh) __neigh_notify(neigh, RTM_NEWNEIGH, 0); } +static bool neigh_master_filtered(struct net_device *dev, int master_idx) +{ + struct net_device *master; + + if (!master_idx) + return false; + + master = netdev_master_upper_dev_get(dev); + if (!master || master->ifindex != master_idx) + return true; + + return false; +} + static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); + const struct nlmsghdr *nlh = cb->nlh; + struct nlattr *tb[NDA_MAX + 1]; struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; struct neigh_hash_table *nht; + int filter_master_idx = 0; + unsigned int flags = NLM_F_MULTI; + int err; + + err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL); + if (!err) { + if (tb[NDA_MASTER]) + filter_master_idx = nla_get_u32(tb[NDA_MASTER]); + + if (filter_master_idx) + flags |= NLM_F_DUMP_FILTERED; + } rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); @@ -2255,12 +2283,14 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, n = rcu_dereference_bh(n->next)) { if (!net_eq(dev_net(n->dev), net)) continue; + if (neigh_master_filtered(n->dev, filter_master_idx)) + continue; if (idx < s_idx) goto next; if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, - NLM_F_MULTI) < 0) { + flags) < 0) { rc = -1; goto out; } -- cgit v1.2.3 From 694869b3c5440e0d821583ec8811b6cb5d03742d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 12 Jun 2015 21:55:31 -0500 Subject: ipv4: Pass struct net through ip_fragment Signed-off-by: "Eric W. Biederman" --- include/net/ip.h | 4 ++-- net/bridge/br_netfilter_hooks.c | 6 +++--- net/ipv4/ip_output.c | 44 +++++++++++++++++++---------------------- net/openvswitch/actions.c | 2 +- 4 files changed, 26 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 91a6b2c88341..b783141b0671 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -109,8 +109,8 @@ int ip_local_deliver(struct sk_buff *skb); int ip_mr_input(struct sk_buff *skb); int ip_output(struct sock *sk, struct sk_buff *skb); int ip_mc_output(struct sock *sk, struct sk_buff *skb); -int ip_do_fragment(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)); +int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); int __ip_local_out(struct sk_buff *skb); int ip_local_out_sk(struct sock *sk, struct sk_buff *skb); diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 13f03671c88d..00e356c236cf 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -701,7 +701,7 @@ static int br_nf_push_frag_xmit_sk(struct sock *sk, struct sk_buff *skb) #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) static int br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)) + int (*output)(struct net *, struct sock *, struct sk_buff *)) { unsigned int mtu = ip_skb_dst_mtu(skb); struct iphdr *iph = ip_hdr(skb); @@ -714,7 +714,7 @@ br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, return -EMSGSIZE; } - return ip_do_fragment(sk, skb, output); + return ip_do_fragment(net, sk, skb, output); } #endif @@ -763,7 +763,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff skb_copy_from_linear_data_offset(skb, -data->size, data->mac, data->size); - return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit_sk); + return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit); } #endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index aff6766922e8..911ea739049a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -83,9 +83,10 @@ int sysctl_ip_default_ttl __read_mostly = IPDEFTTL; EXPORT_SYMBOL(sysctl_ip_default_ttl); -static int ip_fragment(struct sock *sk, struct sk_buff *skb, - unsigned int mtu, - int (*output)(struct sock *, struct sk_buff *)); +static int +ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + unsigned int mtu, + int (*output)(struct net *, struct sock *, struct sk_buff *)); /* Generate a checksum for an outgoing IP datagram. */ void ip_send_check(struct iphdr *iph) @@ -176,12 +177,11 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, } EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); -static int ip_finish_output2(struct sock *sk, struct sk_buff *skb) +static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct rtable *)dst; struct net_device *dev = dst->dev; - struct net *net = dev_net(dev); unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; u32 nexthop; @@ -225,8 +225,8 @@ static int ip_finish_output2(struct sock *sk, struct sk_buff *skb) return -EINVAL; } -static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb, - unsigned int mtu) +static int ip_finish_output_gso(struct net *net, struct sock *sk, + struct sk_buff *skb, unsigned int mtu) { netdev_features_t features; struct sk_buff *segs; @@ -235,7 +235,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb, /* common case: locally created skb or seglen is <= mtu */ if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) || skb_gso_network_seglen(skb) <= mtu) - return ip_finish_output2(sk, skb); + return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length is exceeding the dst MTU. * @@ -258,7 +258,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb, int err; segs->next = NULL; - err = ip_fragment(sk, segs, mtu, ip_finish_output2); + err = ip_fragment(net, sk, segs, mtu, ip_finish_output2); if (err && ret == 0) ret = err; @@ -281,12 +281,12 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk #endif mtu = ip_skb_dst_mtu(skb); if (skb_is_gso(skb)) - return ip_finish_output_gso(sk, skb, mtu); + return ip_finish_output_gso(net, sk, skb, mtu); if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU)) - return ip_fragment(sk, skb, mtu, ip_finish_output2); + return ip_fragment(net, sk, skb, mtu, ip_finish_output2); - return ip_finish_output2(sk, skb); + return ip_finish_output2(net, sk, skb); } int ip_mc_output(struct sock *sk, struct sk_buff *skb) @@ -495,20 +495,18 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } -static int ip_fragment(struct sock *sk, struct sk_buff *skb, +static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, - int (*output)(struct sock *, struct sk_buff *)) + int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph = ip_hdr(skb); if ((iph->frag_off & htons(IP_DF)) == 0) - return ip_do_fragment(sk, skb, output); + return ip_do_fragment(net, sk, skb, output); if (unlikely(!skb->ignore_df || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { - struct net *net = dev_net(skb_rtable(skb)->dst.dev); - IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); @@ -516,7 +514,7 @@ static int ip_fragment(struct sock *sk, struct sk_buff *skb, return -EMSGSIZE; } - return ip_do_fragment(sk, skb, output); + return ip_do_fragment(net, sk, skb, output); } /* @@ -526,8 +524,8 @@ static int ip_fragment(struct sock *sk, struct sk_buff *skb, * single device frame, and queue such a frame for sending. */ -int ip_do_fragment(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)) +int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph; int ptr; @@ -537,11 +535,9 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb, int offset; __be16 not_last_frag; struct rtable *rt = skb_rtable(skb); - struct net *net; int err = 0; dev = rt->dst.dev; - net = dev_net(dev); /* * Point into the IP datagram header. @@ -631,7 +627,7 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb, ip_send_check(iph); } - err = output(sk, skb); + err = output(net, sk, skb); if (!err) IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); @@ -771,7 +767,7 @@ slow_path: ip_send_check(iph); - err = output(sk, skb2); + err = output(net, sk, skb2); if (err) goto fail; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index ba38662f9f5e..b281b2b76c3f 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -705,7 +705,7 @@ static void ovs_fragment(struct net *net, struct vport *vport, skb_dst_set_noref(skb, &ovs_dst); IPCB(skb)->frag_max_size = mru; - ip_do_fragment(skb->sk, skb, ovs_vport_output_sk); + ip_do_fragment(net, skb->sk, skb, ovs_vport_output); refdst_drop(orig_dst); } else if (ethertype == htons(ETH_P_IPV6)) { const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); -- cgit v1.2.3 From 7d8c6e391575ee86c870b88635a163743fca9eac Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 12 Jun 2015 22:12:04 -0500 Subject: ipv6: Pass struct net through ip6_fragment Signed-off-by: Eric W. Biederman --- include/linux/netfilter_ipv6.h | 4 ++-- include/net/ip6_route.h | 4 ++-- net/bridge/br_netfilter_hooks.c | 2 +- net/ipv6/ip6_output.c | 16 +++++++--------- net/ipv6/xfrm6_output.c | 10 ++++++++-- net/openvswitch/actions.c | 2 +- 6 files changed, 21 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 2ac8369fa96c..47c6b04c28c0 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -17,8 +17,8 @@ struct nf_ipv6_ops { int (*chk_addr)(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict); void (*route_input)(struct sk_buff *skb); - int (*fragment)(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)); + int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); }; #ifdef CONFIG_NETFILTER diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 297629aadb19..2bfb2ad2fab1 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -173,8 +173,8 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst, ipv6_addr_equal(&rt->rt6i_dst.addr, daddr)); } -int ip6_fragment(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)); +int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); static inline int ip6_skb_dst_mtu(struct sk_buff *skb) { diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 00e356c236cf..815994d5b02d 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -786,7 +786,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff data->size); if (v6ops) - return v6ops->fragment(sk, skb, br_nf_push_frag_xmit_sk); + return v6ops->fragment(net, sk, skb, br_nf_push_frag_xmit); kfree_skb(skb); return -EMSGSIZE; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a598fe2c0849..caf7d14a1bdd 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -56,11 +56,10 @@ #include #include -static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb) +static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; - struct net *net = dev_net(dev); struct neighbour *neigh; struct in6_addr *nexthop; int ret; @@ -126,9 +125,9 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)) || (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) - return ip6_fragment(sk, skb, ip6_finish_output2); + return ip6_fragment(net, sk, skb, ip6_finish_output2); else - return ip6_finish_output2(sk, skb); + return ip6_finish_output2(net, sk, skb); } int ip6_output(struct sock *sk, struct sk_buff *skb) @@ -554,8 +553,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } -int ip6_fragment(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)) +int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); @@ -568,7 +567,6 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, __be32 frag_id; int ptr, offset = 0, err = 0; u8 *prevhdr, nexthdr = 0; - struct net *net = dev_net(skb_dst(skb)->dev); hlen = ip6_find_1stfragopt(skb, &prevhdr); nexthdr = *prevhdr; @@ -688,7 +686,7 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, ip6_copy_metadata(frag, skb); } - err = output(sk, skb); + err = output(net, sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGCREATES); @@ -816,7 +814,7 @@ slow_path: /* * Put this fragment into the sending queue. */ - err = output(sk, frag); + err = output(net, sk, frag); if (err) goto fail; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 0c3e9ffcf231..335066a64b45 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -131,6 +131,12 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb) return xfrm_output(sk, skb); } +static int __xfrm6_output_finish(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct xfrm_state *x = skb_dst(skb)->xfrm; + return x->outer_mode->afinfo->output_finish(sk, skb); +} + static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -160,8 +166,8 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) if (x->props.mode == XFRM_MODE_TUNNEL && ((skb->len > mtu && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)))) { - return ip6_fragment(sk, skb, - x->outer_mode->afinfo->output_finish); + return ip6_fragment(net, sk, skb, + __xfrm6_output_finish); } return x->outer_mode->afinfo->output_finish(sk, skb); } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index b281b2b76c3f..f33c627f97b3 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -727,7 +727,7 @@ static void ovs_fragment(struct net *net, struct vport *vport, skb_dst_set_noref(skb, &ovs_rt.dst); IP6CB(skb)->frag_max_size = mru; - v6ops->fragment(skb->sk, skb, ovs_vport_output_sk); + v6ops->fragment(net, skb->sk, skb, ovs_vport_output); refdst_drop(orig_dst); } else { WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.", -- cgit v1.2.3 From c648a0138b8f79b6cb4bd092dfab761e4becb1c2 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 28 Sep 2015 09:00:23 +0200 Subject: netlink: add nla_get for le32 and le64 This patch adds missing inline wrappers for nla_get_le32 and nla_get_le64. The 802.15.4 MAC byteorder is little endian and we keep the byteorder for fields like address configuration in the same byteorder as it comes from the MAC layer. To provide these fields for nl802154 userspace applications, we need these inline wrappers for netlink. Cc: David S. Miller Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/netlink.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index 2a5dbcc90d1c..0e3172751755 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1003,6 +1003,15 @@ static inline __be32 nla_get_be32(const struct nlattr *nla) return *(__be32 *) nla_data(nla); } +/** + * nla_get_le32 - return payload of __le32 attribute + * @nla: __le32 netlink attribute + */ +static inline __le32 nla_get_le32(const struct nlattr *nla) +{ + return *(__le32 *) nla_data(nla); +} + /** * nla_get_u16 - return payload of u16 attribute * @nla: u16 netlink attribute @@ -1065,6 +1074,15 @@ static inline __be64 nla_get_be64(const struct nlattr *nla) return tmp; } +/** + * nla_get_le64 - return payload of __le64 attribute + * @nla: __le64 netlink attribute + */ +static inline __le64 nla_get_le64(const struct nlattr *nla) +{ + return *(__le64 *) nla_data(nla); +} + /** * nla_get_s32 - return payload of s32 attribute * @nla: s32 netlink attribute -- cgit v1.2.3 From a26c5fd7622d4951425131d54a8c99f076fe2068 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 28 Sep 2015 09:00:25 +0200 Subject: nl802154: add support for security layer This patch adds support for accessing mac802154 llsec implementation over nl802154. I added for a new Kconfig entry to provide this functionality CONFIG_IEEE802154_NL802154_EXPERIMENTAL. This interface is still in development. It provides to change security parameters and add/del/dump entries of security tables. Later we can add also a get to get an entry by unique identifier. Cc: Phoebe Buckheister Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/cfg802154.h | 131 ++++ include/net/ieee802154_netdev.h | 75 --- include/net/nl802154.h | 191 ++++++ net/ieee802154/Kconfig | 5 + net/ieee802154/core.c | 12 + net/ieee802154/core.h | 1 + net/ieee802154/nl802154.c | 1316 ++++++++++++++++++++++++++++++++++++--- net/ieee802154/rdev-ops.h | 109 ++++ net/mac802154/cfg.c | 205 ++++++ 9 files changed, 1876 insertions(+), 169 deletions(-) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 242273ccf34b..171cd76558fb 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -27,6 +27,16 @@ struct wpan_phy; struct wpan_phy_cca; +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL +struct ieee802154_llsec_device_key; +struct ieee802154_llsec_seclevel; +struct ieee802154_llsec_params; +struct ieee802154_llsec_device; +struct ieee802154_llsec_table; +struct ieee802154_llsec_key_id; +struct ieee802154_llsec_key; +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + struct cfg802154_ops { struct net_device * (*add_virtual_intf_deprecated)(struct wpan_phy *wpan_phy, const char *name, @@ -65,6 +75,51 @@ struct cfg802154_ops { struct wpan_dev *wpan_dev, bool mode); int (*set_ackreq_default)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, bool ackreq); +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + void (*get_llsec_table)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + struct ieee802154_llsec_table **table); + void (*lock_llsec_table)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev); + void (*unlock_llsec_table)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev); + /* TODO remove locking/get table callbacks, this is part of the + * nl802154 interface and should be accessible from ieee802154 layer. + */ + int (*get_llsec_params)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + struct ieee802154_llsec_params *params); + int (*set_llsec_params)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_params *params, + int changed); + int (*add_llsec_key)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_key_id *id, + const struct ieee802154_llsec_key *key); + int (*del_llsec_key)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_key_id *id); + int (*add_seclevel)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_seclevel *sl); + int (*del_seclevel)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_seclevel *sl); + int (*add_device)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_device *dev); + int (*del_device)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, __le64 extended_addr); + int (*add_devkey)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + __le64 extended_addr, + const struct ieee802154_llsec_device_key *key); + int (*del_devkey)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + __le64 extended_addr, + const struct ieee802154_llsec_device_key *key); +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ }; static inline bool @@ -176,6 +231,82 @@ struct ieee802154_addr { }; }; +struct ieee802154_llsec_key_id { + u8 mode; + u8 id; + union { + struct ieee802154_addr device_addr; + __le32 short_source; + __le64 extended_source; + }; +}; + +#define IEEE802154_LLSEC_KEY_SIZE 16 + +struct ieee802154_llsec_key { + u8 frame_types; + u32 cmd_frame_ids; + /* TODO replace with NL802154_KEY_SIZE */ + u8 key[IEEE802154_LLSEC_KEY_SIZE]; +}; + +struct ieee802154_llsec_key_entry { + struct list_head list; + + struct ieee802154_llsec_key_id id; + struct ieee802154_llsec_key *key; +}; + +struct ieee802154_llsec_params { + bool enabled; + + __be32 frame_counter; + u8 out_level; + struct ieee802154_llsec_key_id out_key; + + __le64 default_key_source; + + __le16 pan_id; + __le64 hwaddr; + __le64 coord_hwaddr; + __le16 coord_shortaddr; +}; + +struct ieee802154_llsec_table { + struct list_head keys; + struct list_head devices; + struct list_head security_levels; +}; + +struct ieee802154_llsec_seclevel { + struct list_head list; + + u8 frame_type; + u8 cmd_frame_id; + bool device_override; + u32 sec_levels; +}; + +struct ieee802154_llsec_device { + struct list_head list; + + __le16 pan_id; + __le16 short_addr; + __le64 hwaddr; + u32 frame_counter; + bool seclevel_exempt; + + u8 key_mode; + struct list_head keys; +}; + +struct ieee802154_llsec_device_key { + struct list_head list; + + struct ieee802154_llsec_key_id key_id; + u32 frame_counter; +}; + struct wpan_dev_header_ops { /* TODO create callback currently assumes ieee802154_mac_cb inside * skb->cb. This should be changed to give these information as diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index aebb9d8d7a11..a62a051a3a2f 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -234,38 +234,6 @@ static inline struct ieee802154_mac_cb *mac_cb_init(struct sk_buff *skb) return mac_cb(skb); } -#define IEEE802154_LLSEC_KEY_SIZE 16 - -struct ieee802154_llsec_key_id { - u8 mode; - u8 id; - union { - struct ieee802154_addr device_addr; - __le32 short_source; - __le64 extended_source; - }; -}; - -struct ieee802154_llsec_key { - u8 frame_types; - u32 cmd_frame_ids; - u8 key[IEEE802154_LLSEC_KEY_SIZE]; -}; - -struct ieee802154_llsec_key_entry { - struct list_head list; - - struct ieee802154_llsec_key_id id; - struct ieee802154_llsec_key *key; -}; - -struct ieee802154_llsec_device_key { - struct list_head list; - - struct ieee802154_llsec_key_id key_id; - u32 frame_counter; -}; - enum { IEEE802154_LLSEC_DEVKEY_IGNORE, IEEE802154_LLSEC_DEVKEY_RESTRICT, @@ -274,49 +242,6 @@ enum { __IEEE802154_LLSEC_DEVKEY_MAX, }; -struct ieee802154_llsec_device { - struct list_head list; - - __le16 pan_id; - __le16 short_addr; - __le64 hwaddr; - u32 frame_counter; - bool seclevel_exempt; - - u8 key_mode; - struct list_head keys; -}; - -struct ieee802154_llsec_seclevel { - struct list_head list; - - u8 frame_type; - u8 cmd_frame_id; - bool device_override; - u32 sec_levels; -}; - -struct ieee802154_llsec_params { - bool enabled; - - __be32 frame_counter; - u8 out_level; - struct ieee802154_llsec_key_id out_key; - - __le64 default_key_source; - - __le16 pan_id; - __le64 hwaddr; - __le64 coord_hwaddr; - __le16 coord_shortaddr; -}; - -struct ieee802154_llsec_table { - struct list_head keys; - struct list_head devices; - struct list_head security_levels; -}; - #define IEEE802154_MAC_SCAN_ED 0 #define IEEE802154_MAC_SCAN_ACTIVE 1 #define IEEE802154_MAC_SCAN_PASSIVE 2 diff --git a/include/net/nl802154.h b/include/net/nl802154.h index cf2713d8b975..32cb3e591e07 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -56,6 +56,22 @@ enum nl802154_commands { /* add new commands above here */ +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + NL802154_CMD_SET_SEC_PARAMS, + NL802154_CMD_GET_SEC_KEY, /* can dump */ + NL802154_CMD_NEW_SEC_KEY, + NL802154_CMD_DEL_SEC_KEY, + NL802154_CMD_GET_SEC_DEV, /* can dump */ + NL802154_CMD_NEW_SEC_DEV, + NL802154_CMD_DEL_SEC_DEV, + NL802154_CMD_GET_SEC_DEVKEY, /* can dump */ + NL802154_CMD_NEW_SEC_DEVKEY, + NL802154_CMD_DEL_SEC_DEVKEY, + NL802154_CMD_GET_SEC_LEVEL, /* can dump */ + NL802154_CMD_NEW_SEC_LEVEL, + NL802154_CMD_DEL_SEC_LEVEL, +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + /* used to define NL802154_CMD_MAX below */ __NL802154_CMD_AFTER_LAST, NL802154_CMD_MAX = __NL802154_CMD_AFTER_LAST - 1 @@ -110,6 +126,18 @@ enum nl802154_attrs { /* add attributes here, update the policy in nl802154.c */ +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + NL802154_ATTR_SEC_ENABLED, + NL802154_ATTR_SEC_OUT_LEVEL, + NL802154_ATTR_SEC_OUT_KEY_ID, + NL802154_ATTR_SEC_FRAME_COUNTER, + + NL802154_ATTR_SEC_LEVEL, + NL802154_ATTR_SEC_DEVICE, + NL802154_ATTR_SEC_DEVKEY, + NL802154_ATTR_SEC_KEY, +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + __NL802154_ATTR_AFTER_LAST, NL802154_ATTR_MAX = __NL802154_ATTR_AFTER_LAST - 1 }; @@ -247,4 +275,167 @@ enum nl802154_supported_bool_states { NL802154_SUPPORTED_BOOL_MAX = __NL802154_SUPPORTED_BOOL_AFTER_LAST - 1 }; +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + +enum nl802154_dev_addr_modes { + NL802154_DEV_ADDR_NONE, + __NL802154_DEV_ADDR_INVALID, + NL802154_DEV_ADDR_SHORT, + NL802154_DEV_ADDR_EXTENDED, + + /* keep last */ + __NL802154_DEV_ADDR_AFTER_LAST, + NL802154_DEV_ADDR_MAX = __NL802154_DEV_ADDR_AFTER_LAST - 1 +}; + +enum nl802154_dev_addr_attrs { + NL802154_DEV_ADDR_ATTR_UNSPEC, + + NL802154_DEV_ADDR_ATTR_PAN_ID, + NL802154_DEV_ADDR_ATTR_MODE, + NL802154_DEV_ADDR_ATTR_SHORT, + NL802154_DEV_ADDR_ATTR_EXTENDED, + + /* keep last */ + __NL802154_DEV_ADDR_ATTR_AFTER_LAST, + NL802154_DEV_ADDR_ATTR_MAX = __NL802154_DEV_ADDR_ATTR_AFTER_LAST - 1 +}; + +enum nl802154_key_id_modes { + NL802154_KEY_ID_MODE_IMPLICIT, + NL802154_KEY_ID_MODE_INDEX, + NL802154_KEY_ID_MODE_INDEX_SHORT, + NL802154_KEY_ID_MODE_INDEX_EXTENDED, + + /* keep last */ + __NL802154_KEY_ID_MODE_AFTER_LAST, + NL802154_KEY_ID_MODE_MAX = __NL802154_KEY_ID_MODE_AFTER_LAST - 1 +}; + +enum nl802154_key_id_attrs { + NL802154_KEY_ID_ATTR_UNSPEC, + + NL802154_KEY_ID_ATTR_MODE, + NL802154_KEY_ID_ATTR_INDEX, + NL802154_KEY_ID_ATTR_IMPLICIT, + NL802154_KEY_ID_ATTR_SOURCE_SHORT, + NL802154_KEY_ID_ATTR_SOURCE_EXTENDED, + + /* keep last */ + __NL802154_KEY_ID_ATTR_AFTER_LAST, + NL802154_KEY_ID_ATTR_MAX = __NL802154_KEY_ID_ATTR_AFTER_LAST - 1 +}; + +enum nl802154_seclevels { + NL802154_SECLEVEL_NONE, + NL802154_SECLEVEL_MIC32, + NL802154_SECLEVEL_MIC64, + NL802154_SECLEVEL_MIC128, + NL802154_SECLEVEL_ENC, + NL802154_SECLEVEL_ENC_MIC32, + NL802154_SECLEVEL_ENC_MIC64, + NL802154_SECLEVEL_ENC_MIC128, + + /* keep last */ + __NL802154_SECLEVEL_AFTER_LAST, + NL802154_SECLEVEL_MAX = __NL802154_SECLEVEL_AFTER_LAST - 1 +}; + +enum nl802154_frames { + NL802154_FRAME_BEACON, + NL802154_FRAME_DATA, + NL802154_FRAME_ACK, + NL802154_FRAME_CMD, + + /* keep last */ + __NL802154_FRAME_AFTER_LAST, + NL802154_FRAME_MAX = __NL802154_FRAME_AFTER_LAST - 1 +}; + +enum nl802154_cmd_frames { + __NL802154_CMD_FRAME_INVALID, + NL802154_CMD_FRAME_ASSOC_REQUEST, + NL802154_CMD_FRAME_ASSOC_RESPONSE, + NL802154_CMD_FRAME_DISASSOC_NOTIFY, + NL802154_CMD_FRAME_DATA_REQUEST, + NL802154_CMD_FRAME_PAN_ID_CONFLICT_NOTIFY, + NL802154_CMD_FRAME_ORPHAN_NOTIFY, + NL802154_CMD_FRAME_BEACON_REQUEST, + NL802154_CMD_FRAME_COORD_REALIGNMENT, + NL802154_CMD_FRAME_GTS_REQUEST, + + /* keep last */ + __NL802154_CMD_FRAME_AFTER_LAST, + NL802154_CMD_FRAME_MAX = __NL802154_CMD_FRAME_AFTER_LAST - 1 +}; + +enum nl802154_seclevel_attrs { + NL802154_SECLEVEL_ATTR_UNSPEC, + + NL802154_SECLEVEL_ATTR_LEVELS, + NL802154_SECLEVEL_ATTR_FRAME, + NL802154_SECLEVEL_ATTR_CMD_FRAME, + NL802154_SECLEVEL_ATTR_DEV_OVERRIDE, + + /* keep last */ + __NL802154_SECLEVEL_ATTR_AFTER_LAST, + NL802154_SECLEVEL_ATTR_MAX = __NL802154_SECLEVEL_ATTR_AFTER_LAST - 1 +}; + +/* TODO what is this? couldn't find in mib */ +enum { + NL802154_DEVKEY_IGNORE, + NL802154_DEVKEY_RESTRICT, + NL802154_DEVKEY_RECORD, + + /* keep last */ + __NL802154_DEVKEY_AFTER_LAST, + NL802154_DEVKEY_MAX = __NL802154_DEVKEY_AFTER_LAST - 1 +}; + +enum nl802154_dev { + NL802154_DEV_ATTR_UNSPEC, + + NL802154_DEV_ATTR_FRAME_COUNTER, + NL802154_DEV_ATTR_PAN_ID, + NL802154_DEV_ATTR_SHORT_ADDR, + NL802154_DEV_ATTR_EXTENDED_ADDR, + NL802154_DEV_ATTR_SECLEVEL_EXEMPT, + NL802154_DEV_ATTR_KEY_MODE, + + /* keep last */ + __NL802154_DEV_ATTR_AFTER_LAST, + NL802154_DEV_ATTR_MAX = __NL802154_DEV_ATTR_AFTER_LAST - 1 +}; + +enum nl802154_devkey { + NL802154_DEVKEY_ATTR_UNSPEC, + + NL802154_DEVKEY_ATTR_FRAME_COUNTER, + NL802154_DEVKEY_ATTR_EXTENDED_ADDR, + NL802154_DEVKEY_ATTR_ID, + + /* keep last */ + __NL802154_DEVKEY_ATTR_AFTER_LAST, + NL802154_DEVKEY_ATTR_MAX = __NL802154_DEVKEY_ATTR_AFTER_LAST - 1 +}; + +enum nl802154_key { + NL802154_KEY_ATTR_UNSPEC, + + NL802154_KEY_ATTR_ID, + NL802154_KEY_ATTR_USAGE_FRAMES, + NL802154_KEY_ATTR_USAGE_CMDS, + NL802154_KEY_ATTR_BYTES, + + /* keep last */ + __NL802154_KEY_ATTR_AFTER_LAST, + NL802154_KEY_ATTR_MAX = __NL802154_KEY_ATTR_AFTER_LAST - 1 +}; + +#define NL802154_KEY_SIZE 16 +#define NL802154_CMD_FRAME_NR_IDS 256 + +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + #endif /* __NL802154_H */ diff --git a/net/ieee802154/Kconfig b/net/ieee802154/Kconfig index 1370d5b0041b..188135bcb803 100644 --- a/net/ieee802154/Kconfig +++ b/net/ieee802154/Kconfig @@ -12,6 +12,11 @@ menuconfig IEEE802154 if IEEE802154 +config IEEE802154_NL802154_EXPERIMENTAL + bool "IEEE 802.15.4 experimental netlink support" + ---help--- + Adds experimental netlink support for nl802154. + config IEEE802154_SOCKET tristate "IEEE 802.15.4 socket interface" default y diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c index b0248e934230..c35fdfa6d04e 100644 --- a/net/ieee802154/core.c +++ b/net/ieee802154/core.c @@ -95,6 +95,18 @@ cfg802154_rdev_by_wpan_phy_idx(int wpan_phy_idx) return result; } +struct wpan_phy *wpan_phy_idx_to_wpan_phy(int wpan_phy_idx) +{ + struct cfg802154_registered_device *rdev; + + ASSERT_RTNL(); + + rdev = cfg802154_rdev_by_wpan_phy_idx(wpan_phy_idx); + if (!rdev) + return NULL; + return &rdev->wpan_phy; +} + struct wpan_phy * wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size) { diff --git a/net/ieee802154/core.h b/net/ieee802154/core.h index f3e95580caee..231fade959f3 100644 --- a/net/ieee802154/core.h +++ b/net/ieee802154/core.h @@ -42,5 +42,6 @@ extern int cfg802154_rdev_list_generation; void cfg802154_dev_free(struct cfg802154_registered_device *rdev); struct cfg802154_registered_device * cfg802154_rdev_by_wpan_phy_idx(int wpan_phy_idx); +struct wpan_phy *wpan_phy_idx_to_wpan_phy(int wpan_phy_idx); #endif /* __IEEE802154_CORE_H */ diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 51110a6d3674..1e9e86508441 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -232,8 +232,86 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = { [NL802154_ATTR_SUPPORTED_COMMANDS] = { .type = NLA_NESTED }, [NL802154_ATTR_ACKREQ_DEFAULT] = { .type = NLA_U8 }, + +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + [NL802154_ATTR_SEC_ENABLED] = { .type = NLA_U8, }, + [NL802154_ATTR_SEC_OUT_LEVEL] = { .type = NLA_U32, }, + [NL802154_ATTR_SEC_OUT_KEY_ID] = { .type = NLA_NESTED, }, + [NL802154_ATTR_SEC_FRAME_COUNTER] = { .type = NLA_U32 }, + + [NL802154_ATTR_SEC_LEVEL] = { .type = NLA_NESTED }, + [NL802154_ATTR_SEC_DEVICE] = { .type = NLA_NESTED }, + [NL802154_ATTR_SEC_DEVKEY] = { .type = NLA_NESTED }, + [NL802154_ATTR_SEC_KEY] = { .type = NLA_NESTED }, +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ }; +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL +static int +nl802154_prepare_wpan_dev_dump(struct sk_buff *skb, + struct netlink_callback *cb, + struct cfg802154_registered_device **rdev, + struct wpan_dev **wpan_dev) +{ + int err; + + rtnl_lock(); + + if (!cb->args[0]) { + err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl802154_fam.hdrsize, + nl802154_fam.attrbuf, nl802154_fam.maxattr, + nl802154_policy); + if (err) + goto out_unlock; + + *wpan_dev = __cfg802154_wpan_dev_from_attrs(sock_net(skb->sk), + nl802154_fam.attrbuf); + if (IS_ERR(*wpan_dev)) { + err = PTR_ERR(*wpan_dev); + goto out_unlock; + } + *rdev = wpan_phy_to_rdev((*wpan_dev)->wpan_phy); + /* 0 is the first index - add 1 to parse only once */ + cb->args[0] = (*rdev)->wpan_phy_idx + 1; + cb->args[1] = (*wpan_dev)->identifier; + } else { + /* subtract the 1 again here */ + struct wpan_phy *wpan_phy = wpan_phy_idx_to_wpan_phy(cb->args[0] - 1); + struct wpan_dev *tmp; + + if (!wpan_phy) { + err = -ENODEV; + goto out_unlock; + } + *rdev = wpan_phy_to_rdev(wpan_phy); + *wpan_dev = NULL; + + list_for_each_entry(tmp, &(*rdev)->wpan_dev_list, list) { + if (tmp->identifier == cb->args[1]) { + *wpan_dev = tmp; + break; + } + } + + if (!*wpan_dev) { + err = -ENODEV; + goto out_unlock; + } + } + + return 0; + out_unlock: + rtnl_unlock(); + return err; +} + +static void +nl802154_finish_wpan_dev_dump(struct cfg802154_registered_device *rdev) +{ + rtnl_unlock(); +} +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + /* message building helper */ static inline void *nl802154hdr_put(struct sk_buff *skb, u32 portid, u32 seq, int flags, u8 cmd) @@ -612,6 +690,107 @@ static inline u64 wpan_dev_id(struct wpan_dev *wpan_dev) ((u64)wpan_phy_to_rdev(wpan_dev->wpan_phy)->wpan_phy_idx << 32); } +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL +#include + +static int +ieee802154_llsec_send_key_id(struct sk_buff *msg, + const struct ieee802154_llsec_key_id *desc) +{ + struct nlattr *nl_dev_addr; + + if (nla_put_u32(msg, NL802154_KEY_ID_ATTR_MODE, desc->mode)) + return -ENOBUFS; + + switch (desc->mode) { + case NL802154_KEY_ID_MODE_IMPLICIT: + nl_dev_addr = nla_nest_start(msg, NL802154_KEY_ID_ATTR_IMPLICIT); + if (!nl_dev_addr) + return -ENOBUFS; + + if (nla_put_le16(msg, NL802154_DEV_ADDR_ATTR_PAN_ID, + desc->device_addr.pan_id) || + nla_put_u32(msg, NL802154_DEV_ADDR_ATTR_MODE, + desc->device_addr.mode)) + return -ENOBUFS; + + switch (desc->device_addr.mode) { + case NL802154_DEV_ADDR_SHORT: + if (nla_put_le16(msg, NL802154_DEV_ADDR_ATTR_SHORT, + desc->device_addr.short_addr)) + return -ENOBUFS; + break; + case NL802154_DEV_ADDR_EXTENDED: + if (nla_put_le64(msg, NL802154_DEV_ADDR_ATTR_EXTENDED, + desc->device_addr.extended_addr)) + return -ENOBUFS; + break; + default: + /* userspace should handle unknown */ + break; + } + + nla_nest_end(msg, nl_dev_addr); + break; + case NL802154_KEY_ID_MODE_INDEX: + break; + case NL802154_KEY_ID_MODE_INDEX_SHORT: + /* TODO renmae short_source? */ + if (nla_put_le32(msg, NL802154_KEY_ID_ATTR_SOURCE_SHORT, + desc->short_source)) + return -ENOBUFS; + break; + case NL802154_KEY_ID_MODE_INDEX_EXTENDED: + if (nla_put_le64(msg, NL802154_KEY_ID_ATTR_SOURCE_EXTENDED, + desc->extended_source)) + return -ENOBUFS; + break; + default: + /* userspace should handle unknown */ + break; + } + + /* TODO key_id to key_idx ? Check naming */ + if (desc->mode != NL802154_KEY_ID_MODE_IMPLICIT) { + if (nla_put_u8(msg, NL802154_KEY_ID_ATTR_INDEX, desc->id)) + return -ENOBUFS; + } + + return 0; +} + +static int nl802154_get_llsec_params(struct sk_buff *msg, + struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev) +{ + struct nlattr *nl_key_id; + struct ieee802154_llsec_params params; + int ret; + + ret = rdev_get_llsec_params(rdev, wpan_dev, ¶ms); + if (ret < 0) + return ret; + + if (nla_put_u8(msg, NL802154_ATTR_SEC_ENABLED, params.enabled) || + nla_put_u32(msg, NL802154_ATTR_SEC_OUT_LEVEL, params.out_level) || + nla_put_be32(msg, NL802154_ATTR_SEC_FRAME_COUNTER, + params.frame_counter)) + return -ENOBUFS; + + nl_key_id = nla_nest_start(msg, NL802154_ATTR_SEC_OUT_KEY_ID); + if (!nl_key_id) + return -ENOBUFS; + + ret = ieee802154_llsec_send_key_id(msg, ¶ms.out_key); + if (ret < 0) + return ret; + + nla_nest_end(msg, nl_key_id); + + return 0; +} +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + static int nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct cfg802154_registered_device *rdev, @@ -663,6 +842,11 @@ nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, if (nla_put_u8(msg, NL802154_ATTR_ACKREQ_DEFAULT, wpan_dev->ackreq)) goto nla_put_failure; +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + if (nl802154_get_llsec_params(msg, rdev, wpan_dev) < 0) + goto nla_put_failure; +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + genlmsg_end(msg, hdr); return 0; @@ -1073,122 +1257,953 @@ nl802154_set_ackreq_default(struct sk_buff *skb, struct genl_info *info) return rdev_set_ackreq_default(rdev, wpan_dev, ackreq); } -#define NL802154_FLAG_NEED_WPAN_PHY 0x01 -#define NL802154_FLAG_NEED_NETDEV 0x02 -#define NL802154_FLAG_NEED_RTNL 0x04 -#define NL802154_FLAG_CHECK_NETDEV_UP 0x08 -#define NL802154_FLAG_NEED_NETDEV_UP (NL802154_FLAG_NEED_NETDEV |\ - NL802154_FLAG_CHECK_NETDEV_UP) -#define NL802154_FLAG_NEED_WPAN_DEV 0x10 -#define NL802154_FLAG_NEED_WPAN_DEV_UP (NL802154_FLAG_NEED_WPAN_DEV |\ - NL802154_FLAG_CHECK_NETDEV_UP) +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL +static const struct nla_policy nl802154_dev_addr_policy[NL802154_DEV_ADDR_ATTR_MAX + 1] = { + [NL802154_DEV_ADDR_ATTR_PAN_ID] = { .type = NLA_U16 }, + [NL802154_DEV_ADDR_ATTR_MODE] = { .type = NLA_U32 }, + [NL802154_DEV_ADDR_ATTR_SHORT] = { .type = NLA_U16 }, + [NL802154_DEV_ADDR_ATTR_EXTENDED] = { .type = NLA_U64 }, +}; -static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, - struct genl_info *info) +static int +ieee802154_llsec_parse_dev_addr(struct nlattr *nla, + struct ieee802154_addr *addr) { - struct cfg802154_registered_device *rdev; - struct wpan_dev *wpan_dev; - struct net_device *dev; - bool rtnl = ops->internal_flags & NL802154_FLAG_NEED_RTNL; + struct nlattr *attrs[NL802154_DEV_ADDR_ATTR_MAX + 1]; - if (rtnl) - rtnl_lock(); + if (!nla || nla_parse_nested(attrs, NL802154_DEV_ADDR_ATTR_MAX, nla, + nl802154_dev_addr_policy)) + return -EINVAL; - if (ops->internal_flags & NL802154_FLAG_NEED_WPAN_PHY) { - rdev = cfg802154_get_dev_from_info(genl_info_net(info), info); - if (IS_ERR(rdev)) { - if (rtnl) - rtnl_unlock(); - return PTR_ERR(rdev); - } - info->user_ptr[0] = rdev; - } else if (ops->internal_flags & NL802154_FLAG_NEED_NETDEV || - ops->internal_flags & NL802154_FLAG_NEED_WPAN_DEV) { - ASSERT_RTNL(); - wpan_dev = __cfg802154_wpan_dev_from_attrs(genl_info_net(info), - info->attrs); - if (IS_ERR(wpan_dev)) { - if (rtnl) - rtnl_unlock(); - return PTR_ERR(wpan_dev); - } + if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] && + !attrs[NL802154_DEV_ADDR_ATTR_MODE] && + !(attrs[NL802154_DEV_ADDR_ATTR_SHORT] || + attrs[NL802154_DEV_ADDR_ATTR_EXTENDED])) + return -EINVAL; - dev = wpan_dev->netdev; - rdev = wpan_phy_to_rdev(wpan_dev->wpan_phy); + addr->pan_id = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_PAN_ID]); + addr->mode = nla_get_u32(attrs[NL802154_DEV_ADDR_ATTR_MODE]); + switch (addr->mode) { + case NL802154_DEV_ADDR_SHORT: + addr->short_addr = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_SHORT]); + break; + case NL802154_DEV_ADDR_EXTENDED: + addr->extended_addr = nla_get_le64(attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]); + break; + default: + return -EINVAL; + } - if (ops->internal_flags & NL802154_FLAG_NEED_NETDEV) { - if (!dev) { - if (rtnl) - rtnl_unlock(); - return -EINVAL; - } + return 0; +} - info->user_ptr[1] = dev; - } else { - info->user_ptr[1] = wpan_dev; - } +static const struct nla_policy nl802154_key_id_policy[NL802154_KEY_ID_ATTR_MAX + 1] = { + [NL802154_KEY_ID_ATTR_MODE] = { .type = NLA_U32 }, + [NL802154_KEY_ID_ATTR_INDEX] = { .type = NLA_U8 }, + [NL802154_KEY_ID_ATTR_IMPLICIT] = { .type = NLA_NESTED }, + [NL802154_KEY_ID_ATTR_SOURCE_SHORT] = { .type = NLA_U32 }, + [NL802154_KEY_ID_ATTR_SOURCE_EXTENDED] = { .type = NLA_U64 }, +}; - if (dev) { - if (ops->internal_flags & NL802154_FLAG_CHECK_NETDEV_UP && - !netif_running(dev)) { - if (rtnl) - rtnl_unlock(); - return -ENETDOWN; - } +static int +ieee802154_llsec_parse_key_id(struct nlattr *nla, + struct ieee802154_llsec_key_id *desc) +{ + struct nlattr *attrs[NL802154_KEY_ID_ATTR_MAX + 1]; - dev_hold(dev); - } + if (!nla || nla_parse_nested(attrs, NL802154_KEY_ID_ATTR_MAX, nla, + nl802154_key_id_policy)) + return -EINVAL; - info->user_ptr[0] = rdev; + if (!attrs[NL802154_KEY_ID_ATTR_MODE]) + return -EINVAL; + + desc->mode = nla_get_u32(attrs[NL802154_KEY_ID_ATTR_MODE]); + switch (desc->mode) { + case NL802154_KEY_ID_MODE_IMPLICIT: + if (!attrs[NL802154_KEY_ID_ATTR_IMPLICIT]) + return -EINVAL; + + if (ieee802154_llsec_parse_dev_addr(attrs[NL802154_KEY_ID_ATTR_IMPLICIT], + &desc->device_addr) < 0) + return -EINVAL; + break; + case NL802154_KEY_ID_MODE_INDEX: + break; + case NL802154_KEY_ID_MODE_INDEX_SHORT: + if (!attrs[NL802154_KEY_ID_ATTR_SOURCE_SHORT]) + return -EINVAL; + + desc->short_source = nla_get_le32(attrs[NL802154_KEY_ID_ATTR_SOURCE_SHORT]); + break; + case NL802154_KEY_ID_MODE_INDEX_EXTENDED: + if (!attrs[NL802154_KEY_ID_ATTR_SOURCE_EXTENDED]) + return -EINVAL; + + desc->extended_source = nla_get_le64(attrs[NL802154_KEY_ID_ATTR_SOURCE_EXTENDED]); + break; + default: + return -EINVAL; + } + + if (desc->mode != NL802154_KEY_ID_MODE_IMPLICIT) { + if (!attrs[NL802154_KEY_ID_ATTR_INDEX]) + return -EINVAL; + + /* TODO change id to idx */ + desc->id = nla_get_u8(attrs[NL802154_KEY_ID_ATTR_INDEX]); } return 0; } -static void nl802154_post_doit(const struct genl_ops *ops, struct sk_buff *skb, - struct genl_info *info) +static int nl802154_set_llsec_params(struct sk_buff *skb, + struct genl_info *info) { - if (info->user_ptr[1]) { - if (ops->internal_flags & NL802154_FLAG_NEED_WPAN_DEV) { - struct wpan_dev *wpan_dev = info->user_ptr[1]; + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wpan_dev *wpan_dev = dev->ieee802154_ptr; + struct ieee802154_llsec_params params; + u32 changed = 0; + int ret; - if (wpan_dev->netdev) - dev_put(wpan_dev->netdev); - } else { - dev_put(info->user_ptr[1]); + if (info->attrs[NL802154_ATTR_SEC_ENABLED]) { + u8 enabled; + + enabled = nla_get_u8(info->attrs[NL802154_ATTR_SEC_ENABLED]); + if (enabled != 0 && enabled != 1) + return -EINVAL; + + params.enabled = nla_get_u8(info->attrs[NL802154_ATTR_SEC_ENABLED]); + changed |= IEEE802154_LLSEC_PARAM_ENABLED; + } + + if (info->attrs[NL802154_ATTR_SEC_OUT_KEY_ID]) { + ret = ieee802154_llsec_parse_key_id(info->attrs[NL802154_ATTR_SEC_OUT_KEY_ID], + ¶ms.out_key); + if (ret < 0) + return ret; + + changed |= IEEE802154_LLSEC_PARAM_OUT_KEY; + } + + if (info->attrs[NL802154_ATTR_SEC_OUT_LEVEL]) { + params.out_level = nla_get_u32(info->attrs[NL802154_ATTR_SEC_OUT_LEVEL]); + if (params.out_level > NL802154_SECLEVEL_MAX) + return -EINVAL; + + changed |= IEEE802154_LLSEC_PARAM_OUT_LEVEL; + } + + if (info->attrs[NL802154_ATTR_SEC_FRAME_COUNTER]) { + params.frame_counter = nla_get_be32(info->attrs[NL802154_ATTR_SEC_FRAME_COUNTER]); + changed |= IEEE802154_LLSEC_PARAM_FRAME_COUNTER; + } + + return rdev_set_llsec_params(rdev, wpan_dev, ¶ms, changed); +} + +static int nl802154_send_key(struct sk_buff *msg, u32 cmd, u32 portid, + u32 seq, int flags, + struct cfg802154_registered_device *rdev, + struct net_device *dev, + const struct ieee802154_llsec_key_entry *key) +{ + void *hdr; + u32 commands[NL802154_CMD_FRAME_NR_IDS / 32]; + struct nlattr *nl_key, *nl_key_id; + + hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); + if (!hdr) + return -1; + + if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) + goto nla_put_failure; + + nl_key = nla_nest_start(msg, NL802154_ATTR_SEC_KEY); + if (!nl_key) + goto nla_put_failure; + + nl_key_id = nla_nest_start(msg, NL802154_KEY_ATTR_ID); + if (!nl_key_id) + goto nla_put_failure; + + if (ieee802154_llsec_send_key_id(msg, &key->id) < 0) + goto nla_put_failure; + + nla_nest_end(msg, nl_key_id); + + if (nla_put_u8(msg, NL802154_KEY_ATTR_USAGE_FRAMES, + key->key->frame_types)) + goto nla_put_failure; + + if (key->key->frame_types & BIT(NL802154_FRAME_CMD)) { + /* TODO for each nested */ + memset(commands, 0, sizeof(commands)); + commands[7] = key->key->cmd_frame_ids; + if (nla_put(msg, NL802154_KEY_ATTR_USAGE_CMDS, + sizeof(commands), commands)) + goto nla_put_failure; + } + + if (nla_put(msg, NL802154_KEY_ATTR_BYTES, NL802154_KEY_SIZE, + key->key->key)) + goto nla_put_failure; + + nla_nest_end(msg, nl_key); + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int +nl802154_dump_llsec_key(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct cfg802154_registered_device *rdev = NULL; + struct ieee802154_llsec_key_entry *key; + struct ieee802154_llsec_table *table; + struct wpan_dev *wpan_dev; + int err; + + err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); + if (err) + return err; + + if (!wpan_dev->netdev) { + err = -EINVAL; + goto out_err; + } + + rdev_lock_llsec_table(rdev, wpan_dev); + rdev_get_llsec_table(rdev, wpan_dev, &table); + + /* TODO make it like station dump */ + if (cb->args[2]) + goto out; + + list_for_each_entry(key, &table->keys, list) { + if (nl802154_send_key(skb, NL802154_CMD_NEW_SEC_KEY, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + rdev, wpan_dev->netdev, key) < 0) { + /* TODO */ + err = -EIO; + rdev_unlock_llsec_table(rdev, wpan_dev); + goto out_err; } } - if (ops->internal_flags & NL802154_FLAG_NEED_RTNL) - rtnl_unlock(); + cb->args[2] = 1; + +out: + rdev_unlock_llsec_table(rdev, wpan_dev); + err = skb->len; +out_err: + nl802154_finish_wpan_dev_dump(rdev); + + return err; } -static const struct genl_ops nl802154_ops[] = { - { - .cmd = NL802154_CMD_GET_WPAN_PHY, - .doit = nl802154_get_wpan_phy, - .dumpit = nl802154_dump_wpan_phy, - .done = nl802154_dump_wpan_phy_done, - .policy = nl802154_policy, - /* can be retrieved by unprivileged users */ - .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | - NL802154_FLAG_NEED_RTNL, - }, - { - .cmd = NL802154_CMD_GET_INTERFACE, - .doit = nl802154_get_interface, - .dumpit = nl802154_dump_interface, - .policy = nl802154_policy, - /* can be retrieved by unprivileged users */ - .internal_flags = NL802154_FLAG_NEED_WPAN_DEV | - NL802154_FLAG_NEED_RTNL, - }, - { - .cmd = NL802154_CMD_NEW_INTERFACE, - .doit = nl802154_new_interface, - .policy = nl802154_policy, - .flags = GENL_ADMIN_PERM, - .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | +static const struct nla_policy nl802154_key_policy[NL802154_KEY_ATTR_MAX + 1] = { + [NL802154_KEY_ATTR_ID] = { NLA_NESTED }, + /* TODO handle it as for_each_nested and NLA_FLAG? */ + [NL802154_KEY_ATTR_USAGE_FRAMES] = { NLA_U8 }, + /* TODO handle it as for_each_nested, not static array? */ + [NL802154_KEY_ATTR_USAGE_CMDS] = { .len = NL802154_CMD_FRAME_NR_IDS / 8 }, + [NL802154_KEY_ATTR_BYTES] = { .len = NL802154_KEY_SIZE }, +}; + +static int nl802154_add_llsec_key(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wpan_dev *wpan_dev = dev->ieee802154_ptr; + struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1]; + struct ieee802154_llsec_key key = { }; + struct ieee802154_llsec_key_id id = { }; + u32 commands[NL802154_CMD_FRAME_NR_IDS / 32] = { }; + + if (nla_parse_nested(attrs, NL802154_KEY_ATTR_MAX, + info->attrs[NL802154_ATTR_SEC_KEY], + nl802154_key_policy)) + return -EINVAL; + + if (!attrs[NL802154_KEY_ATTR_USAGE_FRAMES] || + !attrs[NL802154_KEY_ATTR_BYTES]) + + if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0) + return -ENOBUFS; + + key.frame_types = nla_get_u8(attrs[NL802154_KEY_ATTR_USAGE_FRAMES]); + if (key.frame_types > BIT(NL802154_FRAME_MAX) || + ((key.frame_types & BIT(NL802154_FRAME_CMD)) && + !attrs[NL802154_KEY_ATTR_USAGE_CMDS])) + return -EINVAL; + + if (attrs[NL802154_KEY_ATTR_USAGE_CMDS]) { + /* TODO for each nested */ + nla_memcpy(commands, attrs[NL802154_KEY_ATTR_USAGE_CMDS], + NL802154_CMD_FRAME_NR_IDS / 8); + + /* TODO understand the -EINVAL logic here? last condition */ + if (commands[0] || commands[1] || commands[2] || commands[3] || + commands[4] || commands[5] || commands[6] || + commands[7] > BIT(NL802154_CMD_FRAME_MAX)) + return -EINVAL; + + key.cmd_frame_ids = commands[7]; + } else { + key.cmd_frame_ids = 0; + } + + nla_memcpy(key.key, attrs[NL802154_KEY_ATTR_BYTES], NL802154_KEY_SIZE); + + if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0) + return -ENOBUFS; + + return rdev_add_llsec_key(rdev, wpan_dev, &id, &key); +} + +static int nl802154_del_llsec_key(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wpan_dev *wpan_dev = dev->ieee802154_ptr; + struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1]; + struct ieee802154_llsec_key_id id; + + if (nla_parse_nested(attrs, NL802154_KEY_ATTR_MAX, + info->attrs[NL802154_ATTR_SEC_KEY], + nl802154_key_policy)) + return -EINVAL; + + if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0) + return -ENOBUFS; + + return rdev_del_llsec_key(rdev, wpan_dev, &id); +} + +static int nl802154_send_device(struct sk_buff *msg, u32 cmd, u32 portid, + u32 seq, int flags, + struct cfg802154_registered_device *rdev, + struct net_device *dev, + const struct ieee802154_llsec_device *dev_desc) +{ + void *hdr; + struct nlattr *nl_device; + + hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); + if (!hdr) + return -1; + + if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) + goto nla_put_failure; + + nl_device = nla_nest_start(msg, NL802154_ATTR_SEC_DEVICE); + if (!nl_device) + goto nla_put_failure; + + if (nla_put_u32(msg, NL802154_DEV_ATTR_FRAME_COUNTER, + dev_desc->frame_counter) || + nla_put_le16(msg, NL802154_DEV_ATTR_PAN_ID, dev_desc->pan_id) || + nla_put_le16(msg, NL802154_DEV_ATTR_SHORT_ADDR, + dev_desc->short_addr) || + nla_put_le64(msg, NL802154_DEV_ATTR_EXTENDED_ADDR, + dev_desc->hwaddr) || + nla_put_u8(msg, NL802154_DEV_ATTR_SECLEVEL_EXEMPT, + dev_desc->seclevel_exempt) || + nla_put_u32(msg, NL802154_DEV_ATTR_KEY_MODE, dev_desc->key_mode)) + goto nla_put_failure; + + nla_nest_end(msg, nl_device); + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int +nl802154_dump_llsec_dev(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct cfg802154_registered_device *rdev = NULL; + struct ieee802154_llsec_device *dev; + struct ieee802154_llsec_table *table; + struct wpan_dev *wpan_dev; + int err; + + err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); + if (err) + return err; + + if (!wpan_dev->netdev) { + err = -EINVAL; + goto out_err; + } + + rdev_lock_llsec_table(rdev, wpan_dev); + rdev_get_llsec_table(rdev, wpan_dev, &table); + + /* TODO make it like station dump */ + if (cb->args[2]) + goto out; + + list_for_each_entry(dev, &table->devices, list) { + if (nl802154_send_device(skb, NL802154_CMD_NEW_SEC_LEVEL, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + rdev, wpan_dev->netdev, dev) < 0) { + /* TODO */ + err = -EIO; + rdev_unlock_llsec_table(rdev, wpan_dev); + goto out_err; + } + } + + cb->args[2] = 1; + +out: + rdev_unlock_llsec_table(rdev, wpan_dev); + err = skb->len; +out_err: + nl802154_finish_wpan_dev_dump(rdev); + + return err; +} + +static const struct nla_policy nl802154_dev_policy[NL802154_DEV_ATTR_MAX + 1] = { + [NL802154_DEV_ATTR_FRAME_COUNTER] = { NLA_U32 }, + [NL802154_DEV_ATTR_PAN_ID] = { .type = NLA_U16 }, + [NL802154_DEV_ATTR_SHORT_ADDR] = { .type = NLA_U16 }, + [NL802154_DEV_ATTR_EXTENDED_ADDR] = { .type = NLA_U64 }, + [NL802154_DEV_ATTR_SECLEVEL_EXEMPT] = { NLA_U8 }, + [NL802154_DEV_ATTR_KEY_MODE] = { NLA_U32 }, +}; + +static int +ieee802154_llsec_parse_device(struct nlattr *nla, + struct ieee802154_llsec_device *dev) +{ + struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1]; + + if (!nla || nla_parse_nested(attrs, NL802154_DEV_ATTR_MAX, nla, + nl802154_dev_policy)) + return -EINVAL; + + memset(dev, 0, sizeof(*dev)); + + if (!attrs[NL802154_DEV_ATTR_FRAME_COUNTER] || + !attrs[NL802154_DEV_ATTR_PAN_ID] || + !attrs[NL802154_DEV_ATTR_SHORT_ADDR] || + !attrs[NL802154_DEV_ATTR_EXTENDED_ADDR] || + !attrs[NL802154_DEV_ATTR_SECLEVEL_EXEMPT] || + !attrs[NL802154_DEV_ATTR_KEY_MODE]) + return -EINVAL; + + /* TODO be32 */ + dev->frame_counter = nla_get_u32(attrs[NL802154_DEV_ATTR_FRAME_COUNTER]); + dev->pan_id = nla_get_le16(attrs[NL802154_DEV_ATTR_PAN_ID]); + dev->short_addr = nla_get_le16(attrs[NL802154_DEV_ATTR_SHORT_ADDR]); + /* TODO rename hwaddr to extended_addr */ + dev->hwaddr = nla_get_le64(attrs[NL802154_DEV_ATTR_EXTENDED_ADDR]); + dev->seclevel_exempt = nla_get_u8(attrs[NL802154_DEV_ATTR_SECLEVEL_EXEMPT]); + dev->key_mode = nla_get_u32(attrs[NL802154_DEV_ATTR_KEY_MODE]); + + if (dev->key_mode > NL802154_DEVKEY_MAX || + (dev->seclevel_exempt != 0 && dev->seclevel_exempt != 1)) + return -EINVAL; + + return 0; +} + +static int nl802154_add_llsec_dev(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wpan_dev *wpan_dev = dev->ieee802154_ptr; + struct ieee802154_llsec_device dev_desc; + + if (ieee802154_llsec_parse_device(info->attrs[NL802154_ATTR_SEC_DEVICE], + &dev_desc) < 0) + return -EINVAL; + + return rdev_add_device(rdev, wpan_dev, &dev_desc); +} + +static int nl802154_del_llsec_dev(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wpan_dev *wpan_dev = dev->ieee802154_ptr; + struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1]; + __le64 extended_addr; + + if (nla_parse_nested(attrs, NL802154_DEV_ATTR_MAX, + info->attrs[NL802154_ATTR_SEC_DEVICE], + nl802154_dev_policy)) + return -EINVAL; + + if (!attrs[NL802154_DEV_ATTR_EXTENDED_ADDR]) + return -EINVAL; + + extended_addr = nla_get_le64(attrs[NL802154_DEV_ATTR_EXTENDED_ADDR]); + return rdev_del_device(rdev, wpan_dev, extended_addr); +} + +static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid, + u32 seq, int flags, + struct cfg802154_registered_device *rdev, + struct net_device *dev, __le64 extended_addr, + const struct ieee802154_llsec_device_key *devkey) +{ + void *hdr; + struct nlattr *nl_devkey, *nl_key_id; + + hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); + if (!hdr) + return -1; + + if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) + goto nla_put_failure; + + nl_devkey = nla_nest_start(msg, NL802154_ATTR_SEC_DEVKEY); + if (!nl_devkey) + goto nla_put_failure; + + if (nla_put_le64(msg, NL802154_DEVKEY_ATTR_EXTENDED_ADDR, + extended_addr) || + nla_put_u32(msg, NL802154_DEVKEY_ATTR_FRAME_COUNTER, + devkey->frame_counter)) + goto nla_put_failure; + + nl_key_id = nla_nest_start(msg, NL802154_DEVKEY_ATTR_ID); + if (!nl_key_id) + goto nla_put_failure; + + if (ieee802154_llsec_send_key_id(msg, &devkey->key_id) < 0) + goto nla_put_failure; + + nla_nest_end(msg, nl_key_id); + nla_nest_end(msg, nl_devkey); + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int +nl802154_dump_llsec_devkey(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct cfg802154_registered_device *rdev = NULL; + struct ieee802154_llsec_device_key *kpos; + struct ieee802154_llsec_device *dpos; + struct ieee802154_llsec_table *table; + struct wpan_dev *wpan_dev; + int err; + + err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); + if (err) + return err; + + if (!wpan_dev->netdev) { + err = -EINVAL; + goto out_err; + } + + rdev_lock_llsec_table(rdev, wpan_dev); + rdev_get_llsec_table(rdev, wpan_dev, &table); + + /* TODO make it like station dump */ + if (cb->args[2]) + goto out; + + /* TODO look if remove devkey and do some nested attribute */ + list_for_each_entry(dpos, &table->devices, list) { + list_for_each_entry(kpos, &dpos->keys, list) { + if (nl802154_send_devkey(skb, + NL802154_CMD_NEW_SEC_LEVEL, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, rdev, + wpan_dev->netdev, + dpos->hwaddr, + kpos) < 0) { + /* TODO */ + err = -EIO; + rdev_unlock_llsec_table(rdev, wpan_dev); + goto out_err; + } + } + } + + cb->args[2] = 1; + +out: + rdev_unlock_llsec_table(rdev, wpan_dev); + err = skb->len; +out_err: + nl802154_finish_wpan_dev_dump(rdev); + + return err; +} + +static const struct nla_policy nl802154_devkey_policy[NL802154_DEVKEY_ATTR_MAX + 1] = { + [NL802154_DEVKEY_ATTR_FRAME_COUNTER] = { NLA_U32 }, + [NL802154_DEVKEY_ATTR_EXTENDED_ADDR] = { NLA_U64 }, + [NL802154_DEVKEY_ATTR_ID] = { NLA_NESTED }, +}; + +static int nl802154_add_llsec_devkey(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wpan_dev *wpan_dev = dev->ieee802154_ptr; + struct nlattr *attrs[NL802154_DEVKEY_ATTR_MAX + 1]; + struct ieee802154_llsec_device_key key; + __le64 extended_addr; + + if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] || + nla_parse_nested(attrs, NL802154_DEVKEY_ATTR_MAX, + info->attrs[NL802154_ATTR_SEC_DEVKEY], + nl802154_devkey_policy) < 0) + return -EINVAL; + + if (!attrs[NL802154_DEVKEY_ATTR_FRAME_COUNTER] || + !attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]) + return -EINVAL; + + /* TODO change key.id ? */ + if (ieee802154_llsec_parse_key_id(attrs[NL802154_DEVKEY_ATTR_ID], + &key.key_id) < 0) + return -ENOBUFS; + + /* TODO be32 */ + key.frame_counter = nla_get_u32(attrs[NL802154_DEVKEY_ATTR_FRAME_COUNTER]); + /* TODO change naming hwaddr -> extended_addr + * check unique identifier short+pan OR extended_addr + */ + extended_addr = nla_get_le64(attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]); + return rdev_add_devkey(rdev, wpan_dev, extended_addr, &key); +} + +static int nl802154_del_llsec_devkey(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wpan_dev *wpan_dev = dev->ieee802154_ptr; + struct nlattr *attrs[NL802154_DEVKEY_ATTR_MAX + 1]; + struct ieee802154_llsec_device_key key; + __le64 extended_addr; + + if (nla_parse_nested(attrs, NL802154_DEVKEY_ATTR_MAX, + info->attrs[NL802154_ATTR_SEC_DEVKEY], + nl802154_devkey_policy)) + return -EINVAL; + + if (!attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]) + return -EINVAL; + + /* TODO change key.id ? */ + if (ieee802154_llsec_parse_key_id(attrs[NL802154_DEVKEY_ATTR_ID], + &key.key_id) < 0) + return -ENOBUFS; + + /* TODO change naming hwaddr -> extended_addr + * check unique identifier short+pan OR extended_addr + */ + extended_addr = nla_get_le64(attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]); + return rdev_del_devkey(rdev, wpan_dev, extended_addr, &key); +} + +static int nl802154_send_seclevel(struct sk_buff *msg, u32 cmd, u32 portid, + u32 seq, int flags, + struct cfg802154_registered_device *rdev, + struct net_device *dev, + const struct ieee802154_llsec_seclevel *sl) +{ + void *hdr; + struct nlattr *nl_seclevel; + + hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); + if (!hdr) + return -1; + + if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) + goto nla_put_failure; + + nl_seclevel = nla_nest_start(msg, NL802154_ATTR_SEC_LEVEL); + if (!nl_seclevel) + goto nla_put_failure; + + if (nla_put_u32(msg, NL802154_SECLEVEL_ATTR_FRAME, sl->frame_type) || + nla_put_u32(msg, NL802154_SECLEVEL_ATTR_LEVELS, sl->sec_levels) || + nla_put_u8(msg, NL802154_SECLEVEL_ATTR_DEV_OVERRIDE, + sl->device_override)) + goto nla_put_failure; + + if (sl->frame_type == NL802154_FRAME_CMD) { + if (nla_put_u32(msg, NL802154_SECLEVEL_ATTR_CMD_FRAME, + sl->cmd_frame_id)) + goto nla_put_failure; + } + + nla_nest_end(msg, nl_seclevel); + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int +nl802154_dump_llsec_seclevel(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct cfg802154_registered_device *rdev = NULL; + struct ieee802154_llsec_seclevel *sl; + struct ieee802154_llsec_table *table; + struct wpan_dev *wpan_dev; + int err; + + err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); + if (err) + return err; + + if (!wpan_dev->netdev) { + err = -EINVAL; + goto out_err; + } + + rdev_lock_llsec_table(rdev, wpan_dev); + rdev_get_llsec_table(rdev, wpan_dev, &table); + + /* TODO make it like station dump */ + if (cb->args[2]) + goto out; + + list_for_each_entry(sl, &table->security_levels, list) { + if (nl802154_send_seclevel(skb, NL802154_CMD_NEW_SEC_LEVEL, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + rdev, wpan_dev->netdev, sl) < 0) { + /* TODO */ + err = -EIO; + rdev_unlock_llsec_table(rdev, wpan_dev); + goto out_err; + } + } + + cb->args[2] = 1; + +out: + rdev_unlock_llsec_table(rdev, wpan_dev); + err = skb->len; +out_err: + nl802154_finish_wpan_dev_dump(rdev); + + return err; +} + +static const struct nla_policy nl802154_seclevel_policy[NL802154_SECLEVEL_ATTR_MAX + 1] = { + [NL802154_SECLEVEL_ATTR_LEVELS] = { .type = NLA_U8 }, + [NL802154_SECLEVEL_ATTR_FRAME] = { .type = NLA_U32 }, + [NL802154_SECLEVEL_ATTR_CMD_FRAME] = { .type = NLA_U32 }, + [NL802154_SECLEVEL_ATTR_DEV_OVERRIDE] = { .type = NLA_U8 }, +}; + +static int +llsec_parse_seclevel(struct nlattr *nla, struct ieee802154_llsec_seclevel *sl) +{ + struct nlattr *attrs[NL802154_SECLEVEL_ATTR_MAX + 1]; + + if (!nla || nla_parse_nested(attrs, NL802154_SECLEVEL_ATTR_MAX, nla, + nl802154_seclevel_policy)) + return -EINVAL; + + memset(sl, 0, sizeof(*sl)); + + if (!attrs[NL802154_SECLEVEL_ATTR_LEVELS] || + !attrs[NL802154_SECLEVEL_ATTR_FRAME] || + !attrs[NL802154_SECLEVEL_ATTR_DEV_OVERRIDE]) + return -EINVAL; + + sl->sec_levels = nla_get_u8(attrs[NL802154_SECLEVEL_ATTR_LEVELS]); + sl->frame_type = nla_get_u32(attrs[NL802154_SECLEVEL_ATTR_FRAME]); + sl->device_override = nla_get_u8(attrs[NL802154_SECLEVEL_ATTR_DEV_OVERRIDE]); + if (sl->frame_type > NL802154_FRAME_MAX || + (sl->device_override != 0 && sl->device_override != 1)) + return -EINVAL; + + if (sl->frame_type == NL802154_FRAME_CMD) { + if (!attrs[NL802154_SECLEVEL_ATTR_CMD_FRAME]) + return -EINVAL; + + sl->cmd_frame_id = nla_get_u32(attrs[NL802154_SECLEVEL_ATTR_CMD_FRAME]); + if (sl->cmd_frame_id > NL802154_CMD_FRAME_MAX) + return -EINVAL; + } + + return 0; +} + +static int nl802154_add_llsec_seclevel(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wpan_dev *wpan_dev = dev->ieee802154_ptr; + struct ieee802154_llsec_seclevel sl; + + if (llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], + &sl) < 0) + return -EINVAL; + + return rdev_add_seclevel(rdev, wpan_dev, &sl); +} + +static int nl802154_del_llsec_seclevel(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wpan_dev *wpan_dev = dev->ieee802154_ptr; + struct ieee802154_llsec_seclevel sl; + + if (!info->attrs[NL802154_ATTR_SEC_LEVEL] || + llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], + &sl) < 0) + return -EINVAL; + + return rdev_del_seclevel(rdev, wpan_dev, &sl); +} +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + +#define NL802154_FLAG_NEED_WPAN_PHY 0x01 +#define NL802154_FLAG_NEED_NETDEV 0x02 +#define NL802154_FLAG_NEED_RTNL 0x04 +#define NL802154_FLAG_CHECK_NETDEV_UP 0x08 +#define NL802154_FLAG_NEED_NETDEV_UP (NL802154_FLAG_NEED_NETDEV |\ + NL802154_FLAG_CHECK_NETDEV_UP) +#define NL802154_FLAG_NEED_WPAN_DEV 0x10 +#define NL802154_FLAG_NEED_WPAN_DEV_UP (NL802154_FLAG_NEED_WPAN_DEV |\ + NL802154_FLAG_CHECK_NETDEV_UP) + +static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg802154_registered_device *rdev; + struct wpan_dev *wpan_dev; + struct net_device *dev; + bool rtnl = ops->internal_flags & NL802154_FLAG_NEED_RTNL; + + if (rtnl) + rtnl_lock(); + + if (ops->internal_flags & NL802154_FLAG_NEED_WPAN_PHY) { + rdev = cfg802154_get_dev_from_info(genl_info_net(info), info); + if (IS_ERR(rdev)) { + if (rtnl) + rtnl_unlock(); + return PTR_ERR(rdev); + } + info->user_ptr[0] = rdev; + } else if (ops->internal_flags & NL802154_FLAG_NEED_NETDEV || + ops->internal_flags & NL802154_FLAG_NEED_WPAN_DEV) { + ASSERT_RTNL(); + wpan_dev = __cfg802154_wpan_dev_from_attrs(genl_info_net(info), + info->attrs); + if (IS_ERR(wpan_dev)) { + if (rtnl) + rtnl_unlock(); + return PTR_ERR(wpan_dev); + } + + dev = wpan_dev->netdev; + rdev = wpan_phy_to_rdev(wpan_dev->wpan_phy); + + if (ops->internal_flags & NL802154_FLAG_NEED_NETDEV) { + if (!dev) { + if (rtnl) + rtnl_unlock(); + return -EINVAL; + } + + info->user_ptr[1] = dev; + } else { + info->user_ptr[1] = wpan_dev; + } + + if (dev) { + if (ops->internal_flags & NL802154_FLAG_CHECK_NETDEV_UP && + !netif_running(dev)) { + if (rtnl) + rtnl_unlock(); + return -ENETDOWN; + } + + dev_hold(dev); + } + + info->user_ptr[0] = rdev; + } + + return 0; +} + +static void nl802154_post_doit(const struct genl_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + if (info->user_ptr[1]) { + if (ops->internal_flags & NL802154_FLAG_NEED_WPAN_DEV) { + struct wpan_dev *wpan_dev = info->user_ptr[1]; + + if (wpan_dev->netdev) + dev_put(wpan_dev->netdev); + } else { + dev_put(info->user_ptr[1]); + } + } + + if (ops->internal_flags & NL802154_FLAG_NEED_RTNL) + rtnl_unlock(); +} + +static const struct genl_ops nl802154_ops[] = { + { + .cmd = NL802154_CMD_GET_WPAN_PHY, + .doit = nl802154_get_wpan_phy, + .dumpit = nl802154_dump_wpan_phy, + .done = nl802154_dump_wpan_phy_done, + .policy = nl802154_policy, + /* can be retrieved by unprivileged users */ + .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_GET_INTERFACE, + .doit = nl802154_get_interface, + .dumpit = nl802154_dump_interface, + .policy = nl802154_policy, + /* can be retrieved by unprivileged users */ + .internal_flags = NL802154_FLAG_NEED_WPAN_DEV | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_NEW_INTERFACE, + .doit = nl802154_new_interface, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { @@ -1287,6 +2302,119 @@ static const struct genl_ops nl802154_ops[] = { .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + { + .cmd = NL802154_CMD_SET_SEC_PARAMS, + .doit = nl802154_set_llsec_params, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_GET_SEC_KEY, + /* TODO .doit by matching key id? */ + .dumpit = nl802154_dump_llsec_key, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_NEW_SEC_KEY, + .doit = nl802154_add_llsec_key, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_DEL_SEC_KEY, + .doit = nl802154_del_llsec_key, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, + /* TODO unique identifier must short+pan OR extended_addr */ + { + .cmd = NL802154_CMD_GET_SEC_DEV, + /* TODO .doit by matching extended_addr? */ + .dumpit = nl802154_dump_llsec_dev, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_NEW_SEC_DEV, + .doit = nl802154_add_llsec_dev, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_DEL_SEC_DEV, + .doit = nl802154_del_llsec_dev, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, + /* TODO remove complete devkey, put it as nested? */ + { + .cmd = NL802154_CMD_GET_SEC_DEVKEY, + /* TODO doit by matching ??? */ + .dumpit = nl802154_dump_llsec_devkey, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_NEW_SEC_DEVKEY, + .doit = nl802154_add_llsec_devkey, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_DEL_SEC_DEVKEY, + .doit = nl802154_del_llsec_devkey, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_GET_SEC_LEVEL, + /* TODO .doit by matching frame_type? */ + .dumpit = nl802154_dump_llsec_seclevel, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_NEW_SEC_LEVEL, + .doit = nl802154_add_llsec_seclevel, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_DEL_SEC_LEVEL, + /* TODO match frame_type only? */ + .doit = nl802154_del_llsec_seclevel, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ }; /* initialisation/exit functions */ diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h index 03b357501cc5..4441c63b3ea6 100644 --- a/net/ieee802154/rdev-ops.h +++ b/net/ieee802154/rdev-ops.h @@ -208,4 +208,113 @@ rdev_set_ackreq_default(struct cfg802154_registered_device *rdev, return ret; } +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL +/* TODO this is already a nl802154, so move into ieee802154 */ +static inline void +rdev_get_llsec_table(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, + struct ieee802154_llsec_table **table) +{ + rdev->ops->get_llsec_table(&rdev->wpan_phy, wpan_dev, table); +} + +static inline void +rdev_lock_llsec_table(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev) +{ + rdev->ops->lock_llsec_table(&rdev->wpan_phy, wpan_dev); +} + +static inline void +rdev_unlock_llsec_table(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev) +{ + rdev->ops->unlock_llsec_table(&rdev->wpan_phy, wpan_dev); +} + +static inline int +rdev_get_llsec_params(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, + struct ieee802154_llsec_params *params) +{ + return rdev->ops->get_llsec_params(&rdev->wpan_phy, wpan_dev, params); +} + +static inline int +rdev_set_llsec_params(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_params *params, + u32 changed) +{ + return rdev->ops->set_llsec_params(&rdev->wpan_phy, wpan_dev, params, + changed); +} + +static inline int +rdev_add_llsec_key(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_key_id *id, + const struct ieee802154_llsec_key *key) +{ + return rdev->ops->add_llsec_key(&rdev->wpan_phy, wpan_dev, id, key); +} + +static inline int +rdev_del_llsec_key(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_key_id *id) +{ + return rdev->ops->del_llsec_key(&rdev->wpan_phy, wpan_dev, id); +} + +static inline int +rdev_add_seclevel(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_seclevel *sl) +{ + return rdev->ops->add_seclevel(&rdev->wpan_phy, wpan_dev, sl); +} + +static inline int +rdev_del_seclevel(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_seclevel *sl) +{ + return rdev->ops->del_seclevel(&rdev->wpan_phy, wpan_dev, sl); +} + +static inline int +rdev_add_device(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_device *dev_desc) +{ + return rdev->ops->add_device(&rdev->wpan_phy, wpan_dev, dev_desc); +} + +static inline int +rdev_del_device(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, __le64 extended_addr) +{ + return rdev->ops->del_device(&rdev->wpan_phy, wpan_dev, extended_addr); +} + +static inline int +rdev_add_devkey(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, __le64 extended_addr, + const struct ieee802154_llsec_device_key *devkey) +{ + return rdev->ops->add_devkey(&rdev->wpan_phy, wpan_dev, extended_addr, + devkey); +} + +static inline int +rdev_del_devkey(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, __le64 extended_addr, + const struct ieee802154_llsec_device_key *devkey) +{ + return rdev->ops->del_devkey(&rdev->wpan_phy, wpan_dev, extended_addr, + devkey); +} +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + #endif /* __CFG802154_RDEV_OPS */ diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c index c865ebb2ace2..57b5e94471af 100644 --- a/net/mac802154/cfg.c +++ b/net/mac802154/cfg.c @@ -266,6 +266,195 @@ ieee802154_set_ackreq_default(struct wpan_phy *wpan_phy, return 0; } +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL +static void +ieee802154_get_llsec_table(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + struct ieee802154_llsec_table **table) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + + *table = &sdata->sec.table; +} + +static void +ieee802154_lock_llsec_table(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + + mutex_lock(&sdata->sec_mtx); +} + +static void +ieee802154_unlock_llsec_table(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + + mutex_unlock(&sdata->sec_mtx); +} + +static int +ieee802154_set_llsec_params(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_params *params, + int changed) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + int res; + + mutex_lock(&sdata->sec_mtx); + res = mac802154_llsec_set_params(&sdata->sec, params, changed); + mutex_unlock(&sdata->sec_mtx); + + return res; +} + +static int +ieee802154_get_llsec_params(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + struct ieee802154_llsec_params *params) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + int res; + + mutex_lock(&sdata->sec_mtx); + res = mac802154_llsec_get_params(&sdata->sec, params); + mutex_unlock(&sdata->sec_mtx); + + return res; +} + +static int +ieee802154_add_llsec_key(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_key_id *id, + const struct ieee802154_llsec_key *key) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + int res; + + mutex_lock(&sdata->sec_mtx); + res = mac802154_llsec_key_add(&sdata->sec, id, key); + mutex_unlock(&sdata->sec_mtx); + + return res; +} + +static int +ieee802154_del_llsec_key(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_key_id *id) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + int res; + + mutex_lock(&sdata->sec_mtx); + res = mac802154_llsec_key_del(&sdata->sec, id); + mutex_unlock(&sdata->sec_mtx); + + return res; +} + +static int +ieee802154_add_seclevel(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_seclevel *sl) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + int res; + + mutex_lock(&sdata->sec_mtx); + res = mac802154_llsec_seclevel_add(&sdata->sec, sl); + mutex_unlock(&sdata->sec_mtx); + + return res; +} + +static int +ieee802154_del_seclevel(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_seclevel *sl) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + int res; + + mutex_lock(&sdata->sec_mtx); + res = mac802154_llsec_seclevel_del(&sdata->sec, sl); + mutex_unlock(&sdata->sec_mtx); + + return res; +} + +static int +ieee802154_add_device(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_device *dev_desc) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + int res; + + mutex_lock(&sdata->sec_mtx); + res = mac802154_llsec_dev_add(&sdata->sec, dev_desc); + mutex_unlock(&sdata->sec_mtx); + + return res; +} + +static int +ieee802154_del_device(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + __le64 extended_addr) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + int res; + + mutex_lock(&sdata->sec_mtx); + res = mac802154_llsec_dev_del(&sdata->sec, extended_addr); + mutex_unlock(&sdata->sec_mtx); + + return res; +} + +static int +ieee802154_add_devkey(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + __le64 extended_addr, + const struct ieee802154_llsec_device_key *key) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + int res; + + mutex_lock(&sdata->sec_mtx); + res = mac802154_llsec_devkey_add(&sdata->sec, extended_addr, key); + mutex_unlock(&sdata->sec_mtx); + + return res; +} + +static int +ieee802154_del_devkey(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + __le64 extended_addr, + const struct ieee802154_llsec_device_key *key) +{ + struct net_device *dev = wpan_dev->netdev; + struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); + int res; + + mutex_lock(&sdata->sec_mtx); + res = mac802154_llsec_devkey_del(&sdata->sec, extended_addr, key); + mutex_unlock(&sdata->sec_mtx); + + return res; +} +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + const struct cfg802154_ops mac802154_config_ops = { .add_virtual_intf_deprecated = ieee802154_add_iface_deprecated, .del_virtual_intf_deprecated = ieee802154_del_iface_deprecated, @@ -284,4 +473,20 @@ const struct cfg802154_ops mac802154_config_ops = { .set_max_frame_retries = ieee802154_set_max_frame_retries, .set_lbt_mode = ieee802154_set_lbt_mode, .set_ackreq_default = ieee802154_set_ackreq_default, +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + .get_llsec_table = ieee802154_get_llsec_table, + .lock_llsec_table = ieee802154_lock_llsec_table, + .unlock_llsec_table = ieee802154_unlock_llsec_table, + /* TODO above */ + .set_llsec_params = ieee802154_set_llsec_params, + .get_llsec_params = ieee802154_get_llsec_params, + .add_llsec_key = ieee802154_add_llsec_key, + .del_llsec_key = ieee802154_del_llsec_key, + .add_seclevel = ieee802154_add_seclevel, + .del_seclevel = ieee802154_del_seclevel, + .add_device = ieee802154_add_device, + .del_device = ieee802154_del_device, + .add_devkey = ieee802154_add_devkey, + .del_devkey = ieee802154_del_devkey, +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ }; -- cgit v1.2.3 From 5f2ebb3b59c81a461ffd4921d12e9f6e09c32945 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 28 Sep 2015 19:59:48 +0200 Subject: mac802154: check on len instead mac_len This patch change the length check to len instead of mac_len for checking if the frame control field is available to dereference. We need to change it because I saw issues with af_packet raw sockets and the mrf24j40 which calls this functionality. The raw socket functionality doesn't set the mac_len but resets the skb_mac_header to skb->data which is still correct. The issue occur at mrf24j40 only, because the driver need to evaluate the fc fields. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/mac802154.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 2c478501ad14..5718765cbd95 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -248,7 +248,7 @@ struct ieee802154_ops { static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) { /* return some invalid fc on failure */ - if (unlikely(skb->mac_len < 2)) { + if (unlikely(skb->len < 2)) { WARN_ON(1); return cpu_to_le16(0); } -- cgit v1.2.3 From 9ff42d10c3b3e26d9555878f31b9a2e5c24efa57 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Thu, 1 Oct 2015 15:36:51 -0700 Subject: userfaultfd: remove kernel header include from uapi header As include/uapi/linux/userfaultfd.h is a user visible header file, it should not include kernel-exclusive header files. So trying to build the userfaultfd test program from the selftests directory fails, since it contains a reference to linux/compiler.h. As it turns out, that header is not really needed there, so we can simply remove it to fix that issue. Signed-off-by: Andre Przywara Cc: Andrea Arcangeli Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/userfaultfd.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index df0e09bb7dd5..9057d7af3ae1 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -11,8 +11,6 @@ #include -#include - #define UFFD_API ((__u64)0xAA) /* * After implementing the respective features it will become: -- cgit v1.2.3 From 0610c25daa3e76e38ad5a8fae683a89ff9f71798 Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Thu, 1 Oct 2015 15:37:02 -0700 Subject: memcg: fix dirty page migration The problem starts with a file backed dirty page which is charged to a memcg. Then page migration is used to move oldpage to newpage. Migration: - copies the oldpage's data to newpage - clears oldpage.PG_dirty - sets newpage.PG_dirty - uncharges oldpage from memcg - charges newpage to memcg Clearing oldpage.PG_dirty decrements the charged memcg's dirty page count. However, because newpage is not yet charged, setting newpage.PG_dirty does not increment the memcg's dirty page count. After migration completes newpage.PG_dirty is eventually cleared, often in account_page_cleaned(). At this time newpage is charged to a memcg so the memcg's dirty page count is decremented which causes underflow because the count was not previously incremented by migration. This underflow causes balance_dirty_pages() to see a very large unsigned number of dirty memcg pages which leads to aggressive throttling of buffered writes by processes in non root memcg. This issue: - can harm performance of non root memcg buffered writes. - can report too small (even negative) values in memory.stat[(total_)dirty] counters of all memcg, including the root. To avoid polluting migrate.c with #ifdef CONFIG_MEMCG checks, introduce page_memcg() and set_page_memcg() helpers. Test: 0) setup and enter limited memcg mkdir /sys/fs/cgroup/test echo 1G > /sys/fs/cgroup/test/memory.limit_in_bytes echo $$ > /sys/fs/cgroup/test/cgroup.procs 1) buffered writes baseline dd if=/dev/zero of=/data/tmp/foo bs=1M count=1k sync grep ^dirty /sys/fs/cgroup/test/memory.stat 2) buffered writes with compaction antagonist to induce migration yes 1 > /proc/sys/vm/compact_memory & rm -rf /data/tmp/foo dd if=/dev/zero of=/data/tmp/foo bs=1M count=1k kill % sync grep ^dirty /sys/fs/cgroup/test/memory.stat 3) buffered writes without antagonist, should match baseline rm -rf /data/tmp/foo dd if=/dev/zero of=/data/tmp/foo bs=1M count=1k sync grep ^dirty /sys/fs/cgroup/test/memory.stat (speed, dirty residue) unpatched patched 1) 841 MB/s 0 dirty pages 886 MB/s 0 dirty pages 2) 611 MB/s -33427456 dirty pages 793 MB/s 0 dirty pages 3) 114 MB/s -33427456 dirty pages 891 MB/s 0 dirty pages Notice that unpatched baseline performance (1) fell after migration (3): 841 -> 114 MB/s. In the patched kernel, post migration performance matches baseline. Fixes: c4843a7593a9 ("memcg: add per cgroup dirty page accounting") Signed-off-by: Greg Thelen Reported-by: Dave Hansen Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: [4.2+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 21 +++++++++++++++++++++ mm/migrate.c | 12 +++++++++++- 2 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 91c08f6f0dc9..80001de019ba 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -905,6 +905,27 @@ static inline void set_page_links(struct page *page, enum zone_type zone, #endif } +#ifdef CONFIG_MEMCG +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return page->mem_cgroup; +} + +static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg) +{ + page->mem_cgroup = memcg; +} +#else +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return NULL; +} + +static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg) +{ +} +#endif + /* * Some inline functions in vmstat.h depend on page_zone() */ diff --git a/mm/migrate.c b/mm/migrate.c index 7452a00bbb50..842ecd7aaf7f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -740,6 +740,15 @@ static int move_to_new_page(struct page *newpage, struct page *page, if (PageSwapBacked(page)) SetPageSwapBacked(newpage); + /* + * Indirectly called below, migrate_page_copy() copies PG_dirty and thus + * needs newpage's memcg set to transfer memcg dirty page accounting. + * So perform memcg migration in two steps: + * 1. set newpage->mem_cgroup (here) + * 2. clear page->mem_cgroup (below) + */ + set_page_memcg(newpage, page_memcg(page)); + mapping = page_mapping(page); if (!mapping) rc = migrate_page(mapping, newpage, page, mode); @@ -756,9 +765,10 @@ static int move_to_new_page(struct page *newpage, struct page *page, rc = fallback_migrate_page(mapping, newpage, page, mode); if (rc != MIGRATEPAGE_SUCCESS) { + set_page_memcg(newpage, NULL); newpage->mapping = NULL; } else { - mem_cgroup_migrate(page, newpage, false); + set_page_memcg(page, NULL); if (page_was_mapped) remove_migration_ptes(page, newpage); page->mapping = NULL; -- cgit v1.2.3 From ef510194cefe0cd369ef73419cd65b0a5bb4fb5b Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Thu, 1 Oct 2015 15:37:13 -0700 Subject: memcg: remove pcp_counter_lock Commit 733a572e66d2 ("memcg: make mem_cgroup_read_{stat|event}() iterate possible cpus instead of online") removed the last use of the per memcg pcp_counter_lock but forgot to remove the variable. Kill the vestigial variable. Signed-off-by: Greg Thelen Acked-by: Michal Hocko Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 1 - mm/memcontrol.c | 1 - 2 files changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ad800e62cb7a..6452ff4c463f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -242,7 +242,6 @@ struct mem_cgroup { * percpu counter. */ struct mem_cgroup_stat_cpu __percpu *stat; - spinlock_t pcp_counter_lock; #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) struct cg_proto tcp_mem; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 03cc0a742ff1..1fedbde68f59 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4185,7 +4185,6 @@ static struct mem_cgroup *mem_cgroup_alloc(void) if (memcg_wb_domain_init(memcg, GFP_KERNEL)) goto out_free_stat; - spin_lock_init(&memcg->pcp_counter_lock); return memcg; out_free_stat: -- cgit v1.2.3 From fff1f3001cc58b5064a0f1154a7ac09b76f29c44 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:23 -0700 Subject: tcp: add a spinlock to protect struct request_sock_queue struct request_sock_queue fields are currently protected by the listener 'lock' (not a real spinlock) We need to add a private spinlock instead, so that softirq handlers creating children do not have to worry with backlog notion that the listener 'lock' carries. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 37 ++++++++++++++++++------------------- net/core/request_sock.c | 1 + net/ipv4/inet_connection_sock.c | 21 +++++++-------------- 3 files changed, 26 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index d2544de329bd..202e36163ae3 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -176,9 +176,11 @@ struct fastopen_queue { * */ struct request_sock_queue { + spinlock_t rskq_lock; + u8 rskq_defer_accept; + struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; - u8 rskq_defer_accept; struct listen_sock *listen_opt; struct fastopen_queue fastopenq; /* Check max_qlen != 0 to determine * if TFO is enabled. @@ -196,16 +198,7 @@ void reqsk_queue_destroy(struct request_sock_queue *queue); void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, bool reset); -static inline struct request_sock * - reqsk_queue_yank_acceptq(struct request_sock_queue *queue) -{ - struct request_sock *req = queue->rskq_accept_head; - - queue->rskq_accept_head = NULL; - return req; -} - -static inline int reqsk_queue_empty(struct request_sock_queue *queue) +static inline bool reqsk_queue_empty(const struct request_sock_queue *queue) { return queue->rskq_accept_head == NULL; } @@ -215,6 +208,7 @@ static inline void reqsk_queue_add(struct request_sock_queue *queue, struct sock *parent, struct sock *child) { + spin_lock(&queue->rskq_lock); req->sk = child; sk_acceptq_added(parent); @@ -225,18 +219,23 @@ static inline void reqsk_queue_add(struct request_sock_queue *queue, queue->rskq_accept_tail = req; req->dl_next = NULL; + spin_unlock(&queue->rskq_lock); } -static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue) +static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue, + struct sock *parent) { - struct request_sock *req = queue->rskq_accept_head; - - WARN_ON(req == NULL); - - queue->rskq_accept_head = req->dl_next; - if (queue->rskq_accept_head == NULL) - queue->rskq_accept_tail = NULL; + struct request_sock *req; + spin_lock_bh(&queue->rskq_lock); + req = queue->rskq_accept_head; + if (req) { + sk_acceptq_removed(parent); + queue->rskq_accept_head = req->dl_next; + if (queue->rskq_accept_head == NULL) + queue->rskq_accept_tail = NULL; + } + spin_unlock_bh(&queue->rskq_lock); return req; } diff --git a/net/core/request_sock.c b/net/core/request_sock.c index e22cfa4ed25f..8d9fd31d3d06 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -58,6 +58,7 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, return -ENOMEM; get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); + spin_lock_init(&queue->rskq_lock); spin_lock_init(&queue->syn_wait_lock); spin_lock_init(&queue->fastopenq.lock); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index e1527882a578..0085612b9e49 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -330,10 +330,9 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) if (error) goto out_err; } - req = reqsk_queue_remove(queue); + req = reqsk_queue_remove(queue, sk); newsk = req->sk; - sk_acceptq_removed(sk); if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { spin_lock_bh(&queue->fastopenq.lock); @@ -832,11 +831,7 @@ void inet_csk_listen_stop(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; - struct request_sock *acc_req; - struct request_sock *req; - - /* make all the listen_opt local to us */ - acc_req = reqsk_queue_yank_acceptq(queue); + struct request_sock *next, *req; /* Following specs, it would be better either to send FIN * (and enter FIN-WAIT-1, it is normal close) @@ -848,11 +843,9 @@ void inet_csk_listen_stop(struct sock *sk) */ reqsk_queue_destroy(queue); - while ((req = acc_req) != NULL) { + while ((req = reqsk_queue_remove(queue, sk)) != NULL) { struct sock *child = req->sk; - acc_req = req->dl_next; - local_bh_disable(); bh_lock_sock(child); WARN_ON(sock_owned_by_user(child)); @@ -882,18 +875,18 @@ void inet_csk_listen_stop(struct sock *sk) local_bh_enable(); sock_put(child); - sk_acceptq_removed(sk); reqsk_put(req); } if (queue->fastopenq.rskq_rst_head) { /* Free all the reqs queued in rskq_rst_head. */ spin_lock_bh(&queue->fastopenq.lock); - acc_req = queue->fastopenq.rskq_rst_head; + req = queue->fastopenq.rskq_rst_head; queue->fastopenq.rskq_rst_head = NULL; spin_unlock_bh(&queue->fastopenq.lock); - while ((req = acc_req) != NULL) { - acc_req = req->dl_next; + while (req != NULL) { + next = req->dl_next; reqsk_put(req); + req = next; } } WARN_ON(sk->sk_ack_backlog); -- cgit v1.2.3 From aac065c50aba0c534a929aeb687eb68c58e523b8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:24 -0700 Subject: tcp: move qlen/young out of struct listen_sock qlen_inc & young_inc were protected by listener lock, while qlen_dec & young_dec were atomic fields. Everything needs to be atomic for upcoming lockless listener. Also move qlen/young in request_sock_queue as we'll get rid of struct listen_sock eventually. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 40 ++++++++++------------------------------ net/core/request_sock.c | 8 ++++---- net/ipv4/inet_connection_sock.c | 6 +++--- net/ipv4/inet_diag.c | 2 +- 4 files changed, 18 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 202e36163ae3..d128e7f89042 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -122,14 +122,7 @@ extern int sysctl_max_syn_backlog; * @max_qlen_log - log_2 of maximal queued SYNs/REQUESTs */ struct listen_sock { - int qlen_inc; /* protected by listener lock */ - int young_inc;/* protected by listener lock */ - - /* following fields can be updated by timer */ - atomic_t qlen_dec; /* qlen = qlen_inc - qlen_dec */ - atomic_t young_dec; - - u32 max_qlen_log ____cacheline_aligned_in_smp; + u32 max_qlen_log; u32 synflood_warned; u32 hash_rnd; u32 nr_table_entries; @@ -179,6 +172,9 @@ struct request_sock_queue { spinlock_t rskq_lock; u8 rskq_defer_accept; + atomic_t qlen; + atomic_t young; + struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; struct listen_sock *listen_opt; @@ -242,41 +238,25 @@ static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue static inline void reqsk_queue_removed(struct request_sock_queue *queue, const struct request_sock *req) { - struct listen_sock *lopt = queue->listen_opt; - if (req->num_timeout == 0) - atomic_inc(&lopt->young_dec); - atomic_inc(&lopt->qlen_dec); + atomic_dec(&queue->young); + atomic_dec(&queue->qlen); } static inline void reqsk_queue_added(struct request_sock_queue *queue) { - struct listen_sock *lopt = queue->listen_opt; - - lopt->young_inc++; - lopt->qlen_inc++; -} - -static inline int listen_sock_qlen(const struct listen_sock *lopt) -{ - return lopt->qlen_inc - atomic_read(&lopt->qlen_dec); -} - -static inline int listen_sock_young(const struct listen_sock *lopt) -{ - return lopt->young_inc - atomic_read(&lopt->young_dec); + atomic_inc(&queue->young); + atomic_inc(&queue->qlen); } static inline int reqsk_queue_len(const struct request_sock_queue *queue) { - const struct listen_sock *lopt = queue->listen_opt; - - return lopt ? listen_sock_qlen(lopt) : 0; + return atomic_read(&queue->qlen); } static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) { - return listen_sock_young(queue->listen_opt); + return atomic_read(&queue->young); } static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 8d9fd31d3d06..5ca624cea04c 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -102,7 +102,7 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) /* make all the listen_opt local to us */ struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue); - if (listen_sock_qlen(lopt) != 0) { + if (reqsk_queue_len(queue) != 0) { unsigned int i; for (i = 0; i < lopt->nr_table_entries; i++) { @@ -116,7 +116,7 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) * or risk a dead lock. */ spin_unlock_bh(&queue->syn_wait_lock); - atomic_inc(&lopt->qlen_dec); + atomic_dec(&queue->qlen); if (del_timer_sync(&req->rsk_timer)) reqsk_put(req); reqsk_put(req); @@ -126,8 +126,8 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) } } - if (WARN_ON(listen_sock_qlen(lopt) != 0)) - pr_err("qlen %u\n", listen_sock_qlen(lopt)); + if (WARN_ON(reqsk_queue_len(queue) != 0)) + pr_err("qlen %u\n", reqsk_queue_len(queue)); kvfree(lopt); } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 0085612b9e49..093ef04e6ebf 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -640,9 +640,9 @@ static void reqsk_timer_handler(unsigned long data) * embrions; and abort old ones without pity, if old * ones are about to clog our table. */ - qlen = listen_sock_qlen(lopt); + qlen = reqsk_queue_len(queue); if (qlen >> (lopt->max_qlen_log - 1)) { - int young = listen_sock_young(lopt) << 1; + int young = reqsk_queue_len_young(queue) << 1; while (thresh > 2) { if (qlen < young) @@ -664,7 +664,7 @@ static void reqsk_timer_handler(unsigned long data) unsigned long timeo; if (req->num_timeout++ == 0) - atomic_inc(&lopt->young_dec); + atomic_dec(&queue->young); timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); mod_timer_pinned(&req->rsk_timer, jiffies + timeo); return; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index c3b1f3a0f4cf..0ac1d68dc8a6 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -753,7 +753,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, spin_lock(&icsk->icsk_accept_queue.syn_wait_lock); lopt = icsk->icsk_accept_queue.listen_opt; - if (!lopt || !listen_sock_qlen(lopt)) + if (!lopt || !reqsk_queue_len(&icsk->icsk_accept_queue)) goto out; if (bc) { -- cgit v1.2.3 From 8d2675f1e464aa5cedda63849adecffd8d33fead Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:25 -0700 Subject: tcp: move synflood_warned into struct request_sock_queue long term plan is to remove struct listen_sock when its hash table is no longer there. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 2 +- net/ipv4/tcp_input.c | 7 +++---- 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index d128e7f89042..273fb7235ce3 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -123,7 +123,6 @@ extern int sysctl_max_syn_backlog; */ struct listen_sock { u32 max_qlen_log; - u32 synflood_warned; u32 hash_rnd; u32 nr_table_entries; struct request_sock *syn_table[0]; @@ -171,6 +170,7 @@ struct fastopen_queue { struct request_sock_queue { spinlock_t rskq_lock; u8 rskq_defer_accept; + u32 synflood_warned; atomic_t qlen; atomic_t young; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e58cbcd2f07e..8b0ce73c2049 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6068,9 +6068,9 @@ static bool tcp_syn_flood_action(const struct sock *sk, const struct sk_buff *skb, const char *proto) { + struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const char *msg = "Dropping request"; bool want_cookie = false; - struct listen_sock *lopt; #ifdef CONFIG_SYN_COOKIES if (sysctl_tcp_syncookies) { @@ -6081,10 +6081,9 @@ static bool tcp_syn_flood_action(const struct sock *sk, #endif NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); - lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; - if (!lopt->synflood_warned && + if (!queue->synflood_warned && sysctl_tcp_syncookies != 2 && - xchg(&lopt->synflood_warned, 1) == 0) + xchg(&queue->synflood_warned, 1) == 0) pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", proto, ntohs(tcp_hdr(skb)->dest), msg); -- cgit v1.2.3 From b267cdd1075d28501b7c05c7aeb8466775505e8d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:27 -0700 Subject: tcp/dccp: init sk_prot and call sk_node_init() in reqsk_alloc() We plan to use generic functions to insert request sockets into ehash table. sk_prot needs to be set (to retrieve sk_prot->h.hashinfo) sk_node needs to be cleared. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 273fb7235ce3..97c1ba61ed2d 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -69,6 +69,16 @@ struct request_sock { u32 peer_secid; }; +static inline struct request_sock *inet_reqsk(struct sock *sk) +{ + return (struct request_sock *)sk; +} + +static inline struct sock *req_to_sk(struct request_sock *req) +{ + return (struct sock *)req; +} + static inline struct request_sock * reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) { @@ -78,6 +88,8 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) req->rsk_ops = ops; sock_hold(sk_listener); req->rsk_listener = sk_listener; + req_to_sk(req)->sk_prot = sk_listener->sk_prot; + sk_node_init(&req_to_sk(req)->sk_node); req->saved_syn = NULL; /* Following is temporary. It is coupled with debugging * helpers in reqsk_put() & reqsk_free() @@ -87,16 +99,6 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) return req; } -static inline struct request_sock *inet_reqsk(struct sock *sk) -{ - return (struct request_sock *)sk; -} - -static inline struct sock *req_to_sk(struct request_sock *req) -{ - return (struct sock *)req; -} - static inline void reqsk_free(struct request_sock *req) { /* temporary debugging */ -- cgit v1.2.3 From aa3a0c8ce651b5e16124866b0a10d1b90b9ef022 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:30 -0700 Subject: tcp: get_openreq[46]() changes When request sockets are no longer in a per listener hash table but on regular TCP ehash, we need to access listener uid through req->rsk_listener get_openreq6() also gets a const for its request socket argument. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 1 - net/ipv4/tcp_ipv4.c | 8 ++++---- net/ipv6/tcp_ipv6.c | 7 ++++--- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 2c7dfe52f473..a26341d2ad67 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1637,7 +1637,6 @@ struct tcp_iter_state { enum tcp_seq_states state; struct sock *syn_wait_sk; int bucket, offset, sbucket, num; - kuid_t uid; loff_t last_pos; }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 56f8c6395966..a33101616215 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1871,7 +1871,6 @@ get_sk: spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); if (reqsk_queue_len(&icsk->icsk_accept_queue)) { start_req: - st->uid = sock_i_uid(sk); st->syn_wait_sk = sk; st->state = TCP_SEQ_STATE_OPENREQ; st->sbucket = 0; @@ -2151,7 +2150,7 @@ void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo) EXPORT_SYMBOL(tcp_proc_unregister); static void get_openreq4(const struct request_sock *req, - struct seq_file *f, int i, kuid_t uid) + struct seq_file *f, int i) { const struct inet_request_sock *ireq = inet_rsk(req); long delta = req->rsk_timer.expires - jiffies; @@ -2168,7 +2167,8 @@ static void get_openreq4(const struct request_sock *req, 1, /* timers active (only the expire timer) */ jiffies_delta_to_clock_t(delta), req->num_timeout, - from_kuid_munged(seq_user_ns(f), uid), + from_kuid_munged(seq_user_ns(f), + sock_i_uid(req->rsk_listener)), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, @@ -2278,7 +2278,7 @@ static int tcp4_seq_show(struct seq_file *seq, void *v) get_tcp4_sock(v, seq, st->num); break; case TCP_SEQ_STATE_OPENREQ: - get_openreq4(v, seq, st->num, st->uid); + get_openreq4(v, seq, st->num); break; } out: diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 65e797dba504..cadb44a2d34e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1635,7 +1635,7 @@ static void tcp_v6_destroy_sock(struct sock *sk) #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, - struct request_sock *req, int i, kuid_t uid) + const struct request_sock *req, int i) { long ttd = req->rsk_timer.expires - jiffies; const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr; @@ -1659,7 +1659,8 @@ static void get_openreq6(struct seq_file *seq, 1, /* timers active (only the expire timer) */ jiffies_to_clock_t(ttd), req->num_timeout, - from_kuid_munged(seq_user_ns(seq), uid), + from_kuid_munged(seq_user_ns(seq), + sock_i_uid(req->rsk_listener)), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); @@ -1773,7 +1774,7 @@ static int tcp6_seq_show(struct seq_file *seq, void *v) get_tcp6_sock(seq, v, st->num); break; case TCP_SEQ_STATE_OPENREQ: - get_openreq6(seq, v, st->num, st->uid); + get_openreq6(seq, v, st->num); break; } out: -- cgit v1.2.3 From 2feda34192a379f8b35a7c6c5826b2f23e884f32 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:31 -0700 Subject: tcp/dccp: remove inet_csk_reqsk_queue_added() timeout argument This is no longer used. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 +-- net/ipv4/inet_connection_sock.c | 2 +- net/ipv6/inet6_connection_sock.c | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index ee54f21a8113..b2e2e30befa9 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -282,8 +282,7 @@ static inline void inet_csk_reqsk_queue_add(struct sock *sk, void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); -static inline void inet_csk_reqsk_queue_added(struct sock *sk, - const unsigned long timeout) +static inline void inet_csk_reqsk_queue_added(struct sock *sk) { reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue); } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 093ef04e6ebf..e62f04775c93 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -531,7 +531,7 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, lopt->hash_rnd, lopt->nr_table_entries); reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout); - inet_csk_reqsk_queue_added(sk, timeout); + inet_csk_reqsk_queue_added(sk); } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 163bfef3e5db..ea915aa5e4e2 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -157,7 +157,7 @@ void inet6_csk_reqsk_queue_hash_add(struct sock *sk, lopt->hash_rnd, lopt->nr_table_entries); reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout); - inet_csk_reqsk_queue_added(sk, timeout); + inet_csk_reqsk_queue_added(sk); } EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add); -- cgit v1.2.3 From 079096f103faca2dd87342cca6f23d4b34da8871 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:32 -0700 Subject: tcp/dccp: install syn_recv requests into ehash table In this patch, we insert request sockets into TCP/DCCP regular ehash table (where ESTABLISHED and TIMEWAIT sockets are) instead of using the per listener hash table. ACK packets find SYN_RECV pseudo sockets without having to find and lock the listener. In nominal conditions, this halves pressure on listener lock. Note that this will allow for SO_REUSEPORT refinements, so that we can select a listener using cpu/numa affinities instead of the prior 'consistent hash', since only SYN packets will apply this selection logic. We will shrink listen_sock in the following patch to ease code review. Signed-off-by: Eric Dumazet Cc: Ying Cai Cc: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 4 -- include/net/inet_hashtables.h | 1 + include/net/request_sock.h | 4 -- include/net/tcp.h | 3 - net/core/request_sock.c | 28 +-------- net/dccp/ipv4.c | 64 +++++++------------- net/dccp/ipv6.c | 72 +++++++---------------- net/ipv4/inet_connection_sock.c | 103 +++++++------------------------- net/ipv4/inet_diag.c | 96 +++--------------------------- net/ipv4/inet_hashtables.c | 14 ++++- net/ipv4/syncookies.c | 4 ++ net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_ipv4.c | 117 +++++++++++-------------------------- net/ipv6/inet6_connection_sock.c | 67 --------------------- net/ipv6/tcp_ipv6.c | 82 ++++++++++++-------------- 15 files changed, 160 insertions(+), 501 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index b2e2e30befa9..730aa034cd3d 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -258,10 +258,6 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); -struct request_sock *inet_csk_search_req(struct sock *sk, - const __be16 rport, - const __be32 raddr, - const __be32 laddr); int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); int inet_csk_get_port(struct sock *sk, unsigned short snum); diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 3fb778d7c875..6683ada25fef 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -205,6 +205,7 @@ void inet_put_port(struct sock *sk); void inet_hashinfo_init(struct inet_hashinfo *h); +int inet_ehash_insert(struct sock *sk, struct sock *osk); void __inet_hash_nolisten(struct sock *sk, struct sock *osk); void __inet_hash(struct sock *sk, struct sock *osk); void inet_hash(struct sock *sk); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 97c1ba61ed2d..e1850923c4f5 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -266,8 +266,4 @@ static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) return reqsk_queue_len(queue) >> queue->listen_opt->max_qlen_log; } -void reqsk_queue_hash_req(struct request_sock_queue *queue, - u32 hash, struct request_sock *req, - unsigned long timeout); - #endif /* _REQUEST_SOCK_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index a26341d2ad67..225e9561af35 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1618,7 +1618,6 @@ static inline bool tcp_stream_is_thin(struct tcp_sock *tp) /* /proc */ enum tcp_seq_states { TCP_SEQ_STATE_LISTENING, - TCP_SEQ_STATE_OPENREQ, TCP_SEQ_STATE_ESTABLISHED, }; @@ -1717,8 +1716,6 @@ struct tcp_request_sock_ops { int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, u16 queue_mapping, struct tcp_fastopen_cookie *foc); - void (*queue_hash_add)(struct sock *sk, struct request_sock *req, - const unsigned long timeout); }; #ifdef CONFIG_SYN_COOKIES diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 5ca624cea04c..a4b305d8ca2b 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -99,35 +99,9 @@ static inline struct listen_sock *reqsk_queue_yank_listen_sk( void reqsk_queue_destroy(struct request_sock_queue *queue) { - /* make all the listen_opt local to us */ struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue); - if (reqsk_queue_len(queue) != 0) { - unsigned int i; - - for (i = 0; i < lopt->nr_table_entries; i++) { - struct request_sock *req; - - spin_lock_bh(&queue->syn_wait_lock); - while ((req = lopt->syn_table[i]) != NULL) { - lopt->syn_table[i] = req->dl_next; - /* Because of following del_timer_sync(), - * we must release the spinlock here - * or risk a dead lock. - */ - spin_unlock_bh(&queue->syn_wait_lock); - atomic_dec(&queue->qlen); - if (del_timer_sync(&req->rsk_timer)) - reqsk_put(req); - reqsk_put(req); - spin_lock_bh(&queue->syn_wait_lock); - } - spin_unlock_bh(&queue->syn_wait_lock); - } - } - - if (WARN_ON(reqsk_queue_len(queue) != 0)) - pr_err("qlen %u\n", reqsk_queue_len(queue)); + /* cleaning is done by req timers */ kvfree(lopt); } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 5b7818c63cec..8910c9567719 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -444,36 +444,6 @@ put_and_exit: } EXPORT_SYMBOL_GPL(dccp_v4_request_recv_sock); -static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) -{ - const struct dccp_hdr *dh = dccp_hdr(skb); - const struct iphdr *iph = ip_hdr(skb); - struct sock *nsk; - /* Find possible connection requests. */ - struct request_sock *req = inet_csk_search_req(sk, dh->dccph_sport, - iph->saddr, iph->daddr); - if (req) { - nsk = dccp_check_req(sk, skb, req); - if (!nsk) - reqsk_put(req); - return nsk; - } - nsk = inet_lookup_established(sock_net(sk), &dccp_hashinfo, - iph->saddr, dh->dccph_sport, - iph->daddr, dh->dccph_dport, - inet_iif(skb)); - if (nsk != NULL) { - if (nsk->sk_state != DCCP_TIME_WAIT) { - bh_lock_sock(nsk); - return nsk; - } - inet_twsk_put(inet_twsk(nsk)); - return NULL; - } - - return sk; -} - static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -705,18 +675,6 @@ int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) * NOTE: the check for the packet types is done in * dccp_rcv_state_process */ - if (sk->sk_state == DCCP_LISTEN) { - struct sock *nsk = dccp_v4_hnd_req(sk, skb); - - if (nsk == NULL) - goto discard; - - if (nsk != sk) { - if (dccp_child_process(sk, nsk, skb)) - goto reset; - return 0; - } - } if (dccp_rcv_state_process(sk, skb, dh, skb->len)) goto reset; @@ -724,7 +682,6 @@ int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) reset: dccp_v4_ctl_send_reset(sk, skb); -discard: kfree_skb(skb); return 0; } @@ -868,6 +825,27 @@ static int dccp_v4_rcv(struct sk_buff *skb) goto no_dccp_socket; } + if (sk->sk_state == DCCP_NEW_SYN_RECV) { + struct request_sock *req = inet_reqsk(sk); + struct sock *nsk = NULL; + + sk = req->rsk_listener; + if (sk->sk_state == DCCP_LISTEN) + nsk = dccp_check_req(sk, skb, req); + if (!nsk) { + reqsk_put(req); + goto discard_it; + } + if (nsk == sk) { + sock_hold(sk); + reqsk_put(req); + } else if (dccp_child_process(sk, nsk, skb)) { + dccp_v4_ctl_send_reset(sk, skb); + goto discard_it; + } else { + return 0; + } + } /* * RFC 4340, sec. 9.2.1: Minimum Checksum Coverage * o if MinCsCov = 0, only packets with CsCov = 0 are accepted diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index e8753aa3b7a4..1361a3f45df7 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -290,37 +290,6 @@ static struct request_sock_ops dccp6_request_sock_ops = { .syn_ack_timeout = dccp_syn_ack_timeout, }; -static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) -{ - const struct dccp_hdr *dh = dccp_hdr(skb); - const struct ipv6hdr *iph = ipv6_hdr(skb); - struct request_sock *req; - struct sock *nsk; - - req = inet6_csk_search_req(sk, dh->dccph_sport, &iph->saddr, - &iph->daddr, inet6_iif(skb)); - if (req) { - nsk = dccp_check_req(sk, skb, req); - if (!nsk) - reqsk_put(req); - return nsk; - } - nsk = __inet6_lookup_established(sock_net(sk), &dccp_hashinfo, - &iph->saddr, dh->dccph_sport, - &iph->daddr, ntohs(dh->dccph_dport), - inet6_iif(skb)); - if (nsk != NULL) { - if (nsk->sk_state != DCCP_TIME_WAIT) { - bh_lock_sock(nsk); - return nsk; - } - inet_twsk_put(inet_twsk(nsk)); - return NULL; - } - - return sk; -} - static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { struct request_sock *req; @@ -398,7 +367,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (dccp_v6_send_response(sk, req)) goto drop_and_free; - inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); + inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); return 0; drop_and_free: @@ -641,24 +610,6 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) * NOTE: the check for the packet types is done in * dccp_rcv_state_process */ - if (sk->sk_state == DCCP_LISTEN) { - struct sock *nsk = dccp_v6_hnd_req(sk, skb); - - if (nsk == NULL) - goto discard; - /* - * Queue it on the new socket if the new socket is active, - * otherwise we just shortcircuit this and continue with - * the new socket.. - */ - if (nsk != sk) { - if (dccp_child_process(sk, nsk, skb)) - goto reset; - if (opt_skb != NULL) - __kfree_skb(opt_skb); - return 0; - } - } if (dccp_rcv_state_process(sk, skb, dccp_hdr(skb), skb->len)) goto reset; @@ -732,6 +683,27 @@ static int dccp_v6_rcv(struct sk_buff *skb) goto no_dccp_socket; } + if (sk->sk_state == DCCP_NEW_SYN_RECV) { + struct request_sock *req = inet_reqsk(sk); + struct sock *nsk = NULL; + + sk = req->rsk_listener; + if (sk->sk_state == DCCP_LISTEN) + nsk = dccp_check_req(sk, skb, req); + if (!nsk) { + reqsk_put(req); + goto discard_it; + } + if (nsk == sk) { + sock_hold(sk); + reqsk_put(req); + } else if (dccp_child_process(sk, nsk, skb)) { + dccp_v6_ctl_send_reset(sk, skb); + goto discard_it; + } else { + return 0; + } + } /* * RFC 4340, sec. 9.2.1: Minimum Checksum Coverage * o if MinCsCov = 0, only packets with CsCov = 0 are accepted diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index e62f04775c93..80904df02187 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -476,65 +476,12 @@ no_route: } EXPORT_SYMBOL_GPL(inet_csk_route_child_sock); -static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport, - const u32 rnd, const u32 synq_hsize) -{ - return jhash_2words((__force u32)raddr, (__force u32)rport, rnd) & (synq_hsize - 1); -} - #if IS_ENABLED(CONFIG_IPV6) #define AF_INET_FAMILY(fam) ((fam) == AF_INET) #else #define AF_INET_FAMILY(fam) true #endif -/* Note: this is temporary : - * req sock will no longer be in listener hash table -*/ -struct request_sock *inet_csk_search_req(struct sock *sk, - const __be16 rport, - const __be32 raddr, - const __be32 laddr) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - struct request_sock *req; - u32 hash = inet_synq_hash(raddr, rport, lopt->hash_rnd, - lopt->nr_table_entries); - - spin_lock(&icsk->icsk_accept_queue.syn_wait_lock); - for (req = lopt->syn_table[hash]; req != NULL; req = req->dl_next) { - const struct inet_request_sock *ireq = inet_rsk(req); - - if (ireq->ir_rmt_port == rport && - ireq->ir_rmt_addr == raddr && - ireq->ir_loc_addr == laddr && - AF_INET_FAMILY(req->rsk_ops->family)) { - atomic_inc(&req->rsk_refcnt); - WARN_ON(req->sk); - break; - } - } - spin_unlock(&icsk->icsk_accept_queue.syn_wait_lock); - - return req; -} -EXPORT_SYMBOL_GPL(inet_csk_search_req); - -void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, - unsigned long timeout) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - const u32 h = inet_synq_hash(inet_rsk(req)->ir_rmt_addr, - inet_rsk(req)->ir_rmt_port, - lopt->hash_rnd, lopt->nr_table_entries); - - reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout); - inet_csk_reqsk_queue_added(sk); -} -EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); - /* Only thing we need from tcp.h */ extern int sysctl_tcp_synack_retries; @@ -571,26 +518,20 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) } EXPORT_SYMBOL(inet_rtx_syn_ack); -/* return true if req was found in the syn_table[] */ +/* return true if req was found in the ehash table */ static bool reqsk_queue_unlink(struct request_sock_queue *queue, struct request_sock *req) { - struct listen_sock *lopt = queue->listen_opt; - struct request_sock **prev; - bool found = false; + struct inet_hashinfo *hashinfo = req_to_sk(req)->sk_prot->h.hashinfo; + spinlock_t *lock; + bool found; - spin_lock(&queue->syn_wait_lock); + lock = inet_ehash_lockp(hashinfo, req->rsk_hash); - for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL; - prev = &(*prev)->dl_next) { - if (*prev == req) { - *prev = req->dl_next; - found = true; - break; - } - } + spin_lock(lock); + found = __sk_nulls_del_node_init_rcu(req_to_sk(req)); + spin_unlock(lock); - spin_unlock(&queue->syn_wait_lock); if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer)) reqsk_put(req); return found; @@ -616,10 +557,8 @@ static void reqsk_timer_handler(unsigned long data) int max_retries, thresh; u8 defer_accept; - if (sk_listener->sk_state != TCP_LISTEN || !lopt) { - reqsk_put(req); - return; - } + if (sk_listener->sk_state != TCP_LISTEN || !lopt) + goto drop; max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; thresh = max_retries; @@ -669,36 +608,36 @@ static void reqsk_timer_handler(unsigned long data) mod_timer_pinned(&req->rsk_timer, jiffies + timeo); return; } +drop: inet_csk_reqsk_queue_drop(sk_listener, req); reqsk_put(req); } -void reqsk_queue_hash_req(struct request_sock_queue *queue, - u32 hash, struct request_sock *req, - unsigned long timeout) +static void reqsk_queue_hash_req(struct request_sock *req, + unsigned long timeout) { - struct listen_sock *lopt = queue->listen_opt; - req->num_retrans = 0; req->num_timeout = 0; req->sk = NULL; setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req); mod_timer_pinned(&req->rsk_timer, jiffies + timeout); - req->rsk_hash = hash; + inet_ehash_insert(req_to_sk(req), NULL); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ smp_wmb(); atomic_set(&req->rsk_refcnt, 2); +} - spin_lock(&queue->syn_wait_lock); - req->dl_next = lopt->syn_table[hash]; - lopt->syn_table[hash] = req; - spin_unlock(&queue->syn_wait_lock); +void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, + unsigned long timeout) +{ + reqsk_queue_hash_req(req, timeout); + inet_csk_reqsk_queue_added(sk); } -EXPORT_SYMBOL(reqsk_queue_hash_req); +EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); /** * inet_csk_clone_lock - clone an inet socket, and lock its clone diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 0ac1d68dc8a6..ab9f8a66615d 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -730,91 +730,21 @@ static void twsk_build_assert(void) #endif } -static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, - struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, - const struct nlattr *bc) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct inet_sock *inet = inet_sk(sk); - struct inet_diag_entry entry; - int j, s_j, reqnum, s_reqnum; - struct listen_sock *lopt; - int err = 0; - - s_j = cb->args[3]; - s_reqnum = cb->args[4]; - - if (s_j > 0) - s_j--; - - entry.family = sk->sk_family; - - spin_lock(&icsk->icsk_accept_queue.syn_wait_lock); - - lopt = icsk->icsk_accept_queue.listen_opt; - if (!lopt || !reqsk_queue_len(&icsk->icsk_accept_queue)) - goto out; - - if (bc) { - entry.sport = inet->inet_num; - entry.userlocks = sk->sk_userlocks; - } - - for (j = s_j; j < lopt->nr_table_entries; j++) { - struct request_sock *req, *head = lopt->syn_table[j]; - - reqnum = 0; - for (req = head; req; reqnum++, req = req->dl_next) { - struct inet_request_sock *ireq = inet_rsk(req); - - if (reqnum < s_reqnum) - continue; - if (r->id.idiag_dport != ireq->ir_rmt_port && - r->id.idiag_dport) - continue; - - if (bc) { - /* Note: entry.sport and entry.userlocks are already set */ - entry_fill_addrs(&entry, req_to_sk(req)); - entry.dport = ntohs(ireq->ir_rmt_port); - - if (!inet_diag_bc_run(bc, &entry)) - continue; - } - - err = inet_req_diag_fill(req_to_sk(req), skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, cb->nlh); - if (err < 0) { - cb->args[3] = j + 1; - cb->args[4] = reqnum; - goto out; - } - } - - s_reqnum = 0; - } - -out: - spin_unlock(&icsk->icsk_accept_queue.syn_wait_lock); - - return err; -} - void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, struct nlattr *bc) { struct net *net = sock_net(skb->sk); int i, num, s_i, s_num; + u32 idiag_states = r->idiag_states; + if (idiag_states & TCPF_SYN_RECV) + idiag_states |= TCPF_NEW_SYN_RECV; s_i = cb->args[1]; s_num = num = cb->args[2]; if (cb->args[0] == 0) { - if (!(r->idiag_states & (TCPF_LISTEN | TCPF_SYN_RECV))) + if (!(idiag_states & TCPF_LISTEN)) goto skip_listen_ht; for (i = s_i; i < INET_LHTABLE_SIZE; i++) { @@ -844,21 +774,11 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, r->id.idiag_sport) goto next_listen; - if (!(r->idiag_states & TCPF_LISTEN) || - r->id.idiag_dport || + if (r->id.idiag_dport || cb->args[3] > 0) - goto syn_recv; - - if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) { - spin_unlock_bh(&ilb->lock); - goto done; - } - -syn_recv: - if (!(r->idiag_states & TCPF_SYN_RECV)) goto next_listen; - if (inet_diag_dump_reqs(skb, sk, cb, r, bc) < 0) { + if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) { spin_unlock_bh(&ilb->lock); goto done; } @@ -879,7 +799,7 @@ skip_listen_ht: s_i = num = s_num = 0; } - if (!(r->idiag_states & ~(TCPF_LISTEN | TCPF_SYN_RECV))) + if (!(idiag_states & ~TCPF_LISTEN)) goto out; for (i = s_i; i <= hashinfo->ehash_mask; i++) { @@ -906,7 +826,7 @@ skip_listen_ht: goto next_normal; state = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_substate : sk->sk_state; - if (!(r->idiag_states & (1 << state))) + if (!(idiag_states & (1 << state))) goto next_normal; if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 56742e995dd3..bed8886a4b6c 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -398,14 +398,18 @@ static u32 inet_sk_port_offset(const struct sock *sk) inet->inet_dport); } -void __inet_hash_nolisten(struct sock *sk, struct sock *osk) +/* insert a socket into ehash, and eventually remove another one + * (The another one can be a SYN_RECV or TIMEWAIT + */ +int inet_ehash_insert(struct sock *sk, struct sock *osk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_nulls_head *list; struct inet_ehash_bucket *head; spinlock_t *lock; + int ret = 0; - WARN_ON(!sk_unhashed(sk)); + WARN_ON_ONCE(!sk_unhashed(sk)); sk->sk_hash = sk_ehashfn(sk); head = inet_ehash_bucket(hashinfo, sk->sk_hash); @@ -419,6 +423,12 @@ void __inet_hash_nolisten(struct sock *sk, struct sock *osk) sk_nulls_del_node_init_rcu(osk); } spin_unlock(lock); + return ret; +} + +void __inet_hash_nolisten(struct sock *sk, struct sock *osk) +{ + inet_ehash_insert(sk, osk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); } EXPORT_SYMBOL_GPL(__inet_hash_nolisten); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 6b97b5f6457c..729ceb5f63c6 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -284,6 +284,10 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, } EXPORT_SYMBOL(cookie_ecn_ok); +/* On input, sk is a listener. + * Output is listener if incoming packet would not create a child + * NULL if memory could not be allocated. + */ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) { struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8b0ce73c2049..a56912772354 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6241,7 +6241,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_free; tcp_rsk(req)->tfo_listener = false; - af_ops->queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); } tcp_reqsk_record_syn(sk, req, skb); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a33101616215..bfe9d39ee87d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1224,7 +1224,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .route_req = tcp_v4_route_req, .init_seq = tcp_v4_init_sequence, .send_synack = tcp_v4_send_synack, - .queue_hash_add = inet_csk_reqsk_queue_hash_add, }; int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) @@ -1343,34 +1342,11 @@ put_and_exit: } EXPORT_SYMBOL(tcp_v4_syn_recv_sock); -static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) +static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb) { +#ifdef CONFIG_SYN_COOKIES const struct tcphdr *th = tcp_hdr(skb); - const struct iphdr *iph = ip_hdr(skb); - struct request_sock *req; - struct sock *nsk; - - req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr); - if (req) { - nsk = tcp_check_req(sk, skb, req, false); - if (!nsk || nsk == sk) - reqsk_put(req); - return nsk; - } - - nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr, - th->source, iph->daddr, th->dest, inet_iif(skb)); - - if (nsk) { - if (nsk->sk_state != TCP_TIME_WAIT) { - bh_lock_sock(nsk); - return nsk; - } - inet_twsk_put(inet_twsk(nsk)); - return NULL; - } -#ifdef CONFIG_SYN_COOKIES if (!th->syn) sk = cookie_v4_check(sk, skb); #endif @@ -1409,10 +1385,10 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) goto csum_err; if (sk->sk_state == TCP_LISTEN) { - struct sock *nsk = tcp_v4_hnd_req(sk, skb); + struct sock *nsk = tcp_v4_cookie_check(sk, skb); + if (!nsk) goto discard; - if (nsk != sk) { sock_rps_save_rxhash(nsk, skb); sk_mark_napi_id(nsk, skb); @@ -1603,6 +1579,29 @@ process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; + if (sk->sk_state == TCP_NEW_SYN_RECV) { + struct request_sock *req = inet_reqsk(sk); + struct sock *nsk = NULL; + + sk = req->rsk_listener; + if (tcp_v4_inbound_md5_hash(sk, skb)) + goto discard_and_relse; + if (sk->sk_state == TCP_LISTEN) + nsk = tcp_check_req(sk, skb, req, false); + if (!nsk) { + reqsk_put(req); + goto discard_it; + } + if (nsk == sk) { + sock_hold(sk); + reqsk_put(req); + } else if (tcp_child_process(sk, nsk, skb)) { + tcp_v4_send_reset(nsk, skb); + goto discard_it; + } else { + return 0; + } + } if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) { NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); goto discard_and_relse; @@ -1830,35 +1829,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur) ++st->num; ++st->offset; - if (st->state == TCP_SEQ_STATE_OPENREQ) { - struct request_sock *req = cur; - - icsk = inet_csk(st->syn_wait_sk); - req = req->dl_next; - while (1) { - while (req) { - if (req->rsk_ops->family == st->family) { - cur = req; - goto out; - } - req = req->dl_next; - } - if (++st->sbucket >= icsk->icsk_accept_queue.listen_opt->nr_table_entries) - break; -get_req: - req = icsk->icsk_accept_queue.listen_opt->syn_table[st->sbucket]; - } - sk = sk_nulls_next(st->syn_wait_sk); - st->state = TCP_SEQ_STATE_LISTENING; - spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); - } else { - icsk = inet_csk(sk); - spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); - if (reqsk_queue_len(&icsk->icsk_accept_queue)) - goto start_req; - spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); - sk = sk_nulls_next(sk); - } + sk = sk_nulls_next(sk); get_sk: sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) @@ -1868,15 +1839,6 @@ get_sk: goto out; } icsk = inet_csk(sk); - spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); - if (reqsk_queue_len(&icsk->icsk_accept_queue)) { -start_req: - st->syn_wait_sk = sk; - st->state = TCP_SEQ_STATE_OPENREQ; - st->sbucket = 0; - goto get_req; - } - spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } spin_unlock_bh(&ilb->lock); st->offset = 0; @@ -2008,7 +1970,6 @@ static void *tcp_seek_last_pos(struct seq_file *seq) void *rc = NULL; switch (st->state) { - case TCP_SEQ_STATE_OPENREQ: case TCP_SEQ_STATE_LISTENING: if (st->bucket >= INET_LHTABLE_SIZE) break; @@ -2067,7 +2028,6 @@ static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) } switch (st->state) { - case TCP_SEQ_STATE_OPENREQ: case TCP_SEQ_STATE_LISTENING: rc = listening_get_next(seq, v); if (!rc) { @@ -2092,11 +2052,6 @@ static void tcp_seq_stop(struct seq_file *seq, void *v) struct tcp_iter_state *st = seq->private; switch (st->state) { - case TCP_SEQ_STATE_OPENREQ: - if (v) { - struct inet_connection_sock *icsk = inet_csk(st->syn_wait_sk); - spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); - } case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) spin_unlock_bh(&tcp_hashinfo.listening_hash[st->bucket].lock); @@ -2269,18 +2224,12 @@ static int tcp4_seq_show(struct seq_file *seq, void *v) } st = seq->private; - switch (st->state) { - case TCP_SEQ_STATE_LISTENING: - case TCP_SEQ_STATE_ESTABLISHED: - if (sk->sk_state == TCP_TIME_WAIT) - get_timewait4_sock(v, seq, st->num); - else - get_tcp4_sock(v, seq, st->num); - break; - case TCP_SEQ_STATE_OPENREQ: + if (sk->sk_state == TCP_TIME_WAIT) + get_timewait4_sock(v, seq, st->num); + else if (sk->sk_state == TCP_NEW_SYN_RECV) get_openreq4(v, seq, st->num); - break; - } + else + get_tcp4_sock(v, seq, st->num); out: seq_pad(seq, '\n'); return 0; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index ea915aa5e4e2..5d1c7cee2cb2 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -94,73 +94,6 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk, } EXPORT_SYMBOL(inet6_csk_route_req); -/* - * request_sock (formerly open request) hash tables. - */ -static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, - const u32 rnd, const u32 synq_hsize) -{ - u32 c; - - c = jhash_3words((__force u32)raddr->s6_addr32[0], - (__force u32)raddr->s6_addr32[1], - (__force u32)raddr->s6_addr32[2], - rnd); - - c = jhash_2words((__force u32)raddr->s6_addr32[3], - (__force u32)rport, - c); - - return c & (synq_hsize - 1); -} - -struct request_sock *inet6_csk_search_req(struct sock *sk, - const __be16 rport, - const struct in6_addr *raddr, - const struct in6_addr *laddr, - const int iif) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - struct request_sock *req; - u32 hash = inet6_synq_hash(raddr, rport, lopt->hash_rnd, - lopt->nr_table_entries); - - spin_lock(&icsk->icsk_accept_queue.syn_wait_lock); - for (req = lopt->syn_table[hash]; req != NULL; req = req->dl_next) { - const struct inet_request_sock *ireq = inet_rsk(req); - - if (ireq->ir_rmt_port == rport && - req->rsk_ops->family == AF_INET6 && - ipv6_addr_equal(&ireq->ir_v6_rmt_addr, raddr) && - ipv6_addr_equal(&ireq->ir_v6_loc_addr, laddr) && - (!ireq->ir_iif || ireq->ir_iif == iif)) { - atomic_inc(&req->rsk_refcnt); - WARN_ON(req->sk != NULL); - break; - } - } - spin_unlock(&icsk->icsk_accept_queue.syn_wait_lock); - - return req; -} -EXPORT_SYMBOL_GPL(inet6_csk_search_req); - -void inet6_csk_reqsk_queue_hash_add(struct sock *sk, - struct request_sock *req, - const unsigned long timeout) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - const u32 h = inet6_synq_hash(&inet_rsk(req)->ir_v6_rmt_addr, - inet_rsk(req)->ir_rmt_port, - lopt->hash_rnd, lopt->nr_table_entries); - - reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout); - inet_csk_reqsk_queue_added(sk); -} -EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add); - void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr) { struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index cadb44a2d34e..a215614cfb2b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -727,7 +727,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .route_req = tcp_v6_route_req, .init_seq = tcp_v6_init_sequence, .send_synack = tcp_v6_send_synack, - .queue_hash_add = inet6_csk_reqsk_queue_hash_add, }; static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq, @@ -938,37 +937,11 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, } -static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) +static struct sock *tcp_v6_cookie_check(struct sock *sk, struct sk_buff *skb) { +#ifdef CONFIG_SYN_COOKIES const struct tcphdr *th = tcp_hdr(skb); - struct request_sock *req; - struct sock *nsk; - - /* Find possible connection requests. */ - req = inet6_csk_search_req(sk, th->source, - &ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb)); - if (req) { - nsk = tcp_check_req(sk, skb, req, false); - if (!nsk || nsk == sk) - reqsk_put(req); - return nsk; - } - nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, - &ipv6_hdr(skb)->saddr, th->source, - &ipv6_hdr(skb)->daddr, ntohs(th->dest), - tcp_v6_iif(skb)); - - if (nsk) { - if (nsk->sk_state != TCP_TIME_WAIT) { - bh_lock_sock(nsk); - return nsk; - } - inet_twsk_put(inet_twsk(nsk)); - return NULL; - } -#ifdef CONFIG_SYN_COOKIES if (!th->syn) sk = cookie_v6_check(sk, skb); #endif @@ -1258,15 +1231,11 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) goto csum_err; if (sk->sk_state == TCP_LISTEN) { - struct sock *nsk = tcp_v6_hnd_req(sk, skb); + struct sock *nsk = tcp_v6_cookie_check(sk, skb); + if (!nsk) goto discard; - /* - * Queue it on the new socket if the new socket is active, - * otherwise we just shortcircuit this and continue with - * the new socket.. - */ if (nsk != sk) { sock_rps_save_rxhash(nsk, skb); sk_mark_napi_id(nsk, skb); @@ -1402,6 +1371,33 @@ process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; + if (sk->sk_state == TCP_NEW_SYN_RECV) { + struct request_sock *req = inet_reqsk(sk); + struct sock *nsk = NULL; + + sk = req->rsk_listener; + tcp_v6_fill_cb(skb, hdr, th); + if (tcp_v6_inbound_md5_hash(sk, skb)) { + reqsk_put(req); + goto discard_it; + } + if (sk->sk_state == TCP_LISTEN) + nsk = tcp_check_req(sk, skb, req, false); + if (!nsk) { + reqsk_put(req); + goto discard_it; + } + if (nsk == sk) { + sock_hold(sk); + reqsk_put(req); + tcp_v6_restore_cb(skb); + } else if (tcp_child_process(sk, nsk, skb)) { + tcp_v6_send_reset(nsk, skb); + goto discard_it; + } else { + return 0; + } + } if (hdr->hop_limit < inet6_sk(sk)->min_hopcount) { NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); goto discard_and_relse; @@ -1765,18 +1761,12 @@ static int tcp6_seq_show(struct seq_file *seq, void *v) } st = seq->private; - switch (st->state) { - case TCP_SEQ_STATE_LISTENING: - case TCP_SEQ_STATE_ESTABLISHED: - if (sk->sk_state == TCP_TIME_WAIT) - get_timewait6_sock(seq, v, st->num); - else - get_tcp6_sock(seq, v, st->num); - break; - case TCP_SEQ_STATE_OPENREQ: + if (sk->sk_state == TCP_TIME_WAIT) + get_timewait6_sock(seq, v, st->num); + else if (sk->sk_state == TCP_NEW_SYN_RECV) get_openreq6(seq, v, st->num); - break; - } + else + get_tcp6_sock(seq, v, st->num); out: return 0; } -- cgit v1.2.3 From 81b496b31a4331415b6a644b485a329ec0b45155 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:33 -0700 Subject: tcp/dccp: shrink struct listen_sock We no longer use hash_rnd, nr_table_entries and syn_table[] For a listener with a backlog of 10 millions sockets, this saves 80 MBytes of vmalloced memory. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 3 --- net/core/request_sock.c | 14 +++----------- 2 files changed, 3 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index e1850923c4f5..353cb61bb399 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -125,9 +125,6 @@ extern int sysctl_max_syn_backlog; */ struct listen_sock { u32 max_qlen_log; - u32 hash_rnd; - u32 nr_table_entries; - struct request_sock *syn_table[0]; }; /* diff --git a/net/core/request_sock.c b/net/core/request_sock.c index a4b305d8ca2b..124f61c5bfef 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -46,18 +46,11 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog); nr_table_entries = max_t(u32, nr_table_entries, 8); nr_table_entries = roundup_pow_of_two(nr_table_entries + 1); - lopt_size += nr_table_entries * sizeof(struct request_sock *); - if (lopt_size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) - lopt = kzalloc(lopt_size, GFP_KERNEL | - __GFP_NOWARN | - __GFP_NORETRY); - if (!lopt) - lopt = vzalloc(lopt_size); + lopt = kzalloc(lopt_size, GFP_KERNEL); if (!lopt) return -ENOMEM; - get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); spin_lock_init(&queue->rskq_lock); spin_lock_init(&queue->syn_wait_lock); @@ -68,7 +61,6 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, queue->fastopenq.max_qlen = 0; queue->rskq_accept_head = NULL; - lopt->nr_table_entries = nr_table_entries; lopt->max_qlen_log = ilog2(nr_table_entries); spin_lock_bh(&queue->syn_wait_lock); @@ -81,7 +73,7 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, void __reqsk_queue_destroy(struct request_sock_queue *queue) { /* This is an error recovery path only, no locking needed */ - kvfree(queue->listen_opt); + kfree(queue->listen_opt); } static inline struct listen_sock *reqsk_queue_yank_listen_sk( @@ -102,7 +94,7 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue); /* cleaning is done by req timers */ - kvfree(lopt); + kfree(lopt); } /* -- cgit v1.2.3 From 1b33bc3e9e903f7293f7dfe80a875b2a5d0305aa Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:34 -0700 Subject: ipv6: remove obsolete inet6 functions inet6_csk_search_req() and inet6_csk_reqsk_queue_hash_add() no longer exist. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 79b2a4c09ca6..064cfbe639d0 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -28,15 +28,6 @@ int inet6_csk_bind_conflict(const struct sock *sk, struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, const struct request_sock *req, u8 proto); -struct request_sock *inet6_csk_search_req(struct sock *sk, - const __be16 rport, - const struct in6_addr *raddr, - const struct in6_addr *laddr, - const int iif); - -void inet6_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, - const unsigned long timeout); - void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); -- cgit v1.2.3 From ca6fb06518836ef9b65dc0aac02ff97704d52a05 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:35 -0700 Subject: tcp: attach SYNACK messages to request sockets instead of listener If a listen backlog is very big (to avoid syncookies), then the listener sk->sk_wmem_alloc is the main source of false sharing, as we need to touch it twice per SYNACK re-transmit and TX completion. (One SYN packet takes listener lock once, but up to 6 SYNACK are generated) By attaching the skb to the request socket, we remove this source of contention. Tested: listen(fd, 10485760); // single listener (no SO_REUSEPORT) 16 RX/TX queue NIC Sustain a SYNFLOOD attack of ~320,000 SYN per second, Sending ~1,400,000 SYNACK per second. Perf profiles now show listener spinlock being next bottleneck. 20.29% [kernel] [k] queued_spin_lock_slowpath 10.06% [kernel] [k] __inet_lookup_established 5.12% [kernel] [k] reqsk_timer_handler 3.22% [kernel] [k] get_next_timer_interrupt 3.00% [kernel] [k] tcp_make_synack 2.77% [kernel] [k] ipt_do_table 2.70% [kernel] [k] run_timer_softirq 2.50% [kernel] [k] ip_finish_output 2.04% [kernel] [k] cascade Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 6 ++++-- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/tcp_fastopen.c | 4 ++-- net/ipv4/tcp_input.c | 23 ++++++++++++----------- net/ipv4/tcp_ipv4.c | 5 +++-- net/ipv4/tcp_output.c | 22 +++++++++++++++------- net/ipv6/tcp_ipv6.c | 5 +++-- net/sched/sch_fq.c | 12 +++++++----- 8 files changed, 47 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 225e9561af35..a6be56d5f0e3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -462,7 +462,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int tcp_connect(struct sock *sk); struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, - struct tcp_fastopen_cookie *foc); + struct tcp_fastopen_cookie *foc, + bool attach_req); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); @@ -1715,7 +1716,8 @@ struct tcp_request_sock_ops { __u32 (*init_seq)(const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, - u16 queue_mapping, struct tcp_fastopen_cookie *foc); + u16 queue_mapping, struct tcp_fastopen_cookie *foc, + bool attach_req); }; #ifdef CONFIG_SYN_COOKIES diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 80904df02187..099e0ea9242a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -628,7 +628,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, * are committed to memory and refcnt initialized. */ smp_wmb(); - atomic_set(&req->rsk_refcnt, 2); + atomic_set(&req->rsk_refcnt, 2 + 1); } void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index f69f436fcbcc..410ac481fda0 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -161,13 +161,13 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, tp->snd_wnd = ntohs(tcp_hdr(skb)->window); /* Activate the retrans timer so that SYNACK can be retransmitted. - * The request socket is not added to the SYN table of the parent + * The request socket is not added to the ehash * because it's been added to the accept queue directly. */ inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, TCP_TIMEOUT_INIT, TCP_RTO_MAX); - atomic_set(&req->rsk_refcnt, 1); + atomic_set(&req->rsk_refcnt, 2); /* Add the child socket directly into the accept queue */ inet_csk_reqsk_queue_add(sk, req, child); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a56912772354..27108757c310 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6120,8 +6120,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct request_sock *req; bool want_cookie = false; struct flowi fl; - int err; - /* TW buckets are converted to open requests without * limitations, they conserve resources and peer is @@ -6230,21 +6228,24 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->snt_isn = isn; tcp_rsk(req)->txhash = net_tx_rndhash(); tcp_openreq_init_rwin(req, sk, dst); - if (!want_cookie) + if (!want_cookie) { fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst); - err = af_ops->send_synack(fastopen_sk ?: sk, dst, &fl, req, - skb_get_queue_mapping(skb), &foc); + tcp_reqsk_record_syn(sk, req, skb); + } if (fastopen_sk) { + af_ops->send_synack(fastopen_sk, dst, &fl, req, + skb_get_queue_mapping(skb), &foc, false); sock_put(fastopen_sk); } else { - if (err || want_cookie) - goto drop_and_free; - tcp_rsk(req)->tfo_listener = false; - inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + if (!want_cookie) + inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + af_ops->send_synack(sk, dst, &fl, req, + skb_get_queue_mapping(skb), &foc, !want_cookie); + if (want_cookie) + goto drop_and_free; } - tcp_reqsk_record_syn(sk, req, skb); - + reqsk_put(req); return 0; drop_and_release: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index bfe9d39ee87d..ac2ea73e9aaf 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -822,7 +822,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, u16 queue_mapping, - struct tcp_fastopen_cookie *foc) + struct tcp_fastopen_cookie *foc, + bool attach_req) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; @@ -833,7 +834,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; - skb = tcp_make_synack(sk, dst, req, foc); + skb = tcp_make_synack(sk, dst, req, foc, attach_req); if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 09bb082ca1a7..55ed3266b05f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2947,7 +2947,8 @@ int tcp_send_synack(struct sock *sk) */ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, - struct tcp_fastopen_cookie *foc) + struct tcp_fastopen_cookie *foc, + bool attach_req) { struct inet_request_sock *ireq = inet_rsk(req); const struct tcp_sock *tp = tcp_sk(sk); @@ -2959,11 +2960,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, u16 user_mss; int mss; - /* sk is a const pointer, because we want to express multiple cpus - * might call us concurrently. - * sock_wmalloc() will change sk->sk_wmem_alloc in an atomic way. - */ - skb = sock_wmalloc((struct sock *)sk, MAX_TCP_HEADER, 1, GFP_ATOMIC); + skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); if (unlikely(!skb)) { dst_release(dst); return NULL; @@ -2971,6 +2968,17 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, /* Reserve space for headers. */ skb_reserve(skb, MAX_TCP_HEADER); + if (attach_req) { + skb->destructor = sock_edemux; + sock_hold(req_to_sk(req)); + skb->sk = req_to_sk(req); + } else { + /* sk is a const pointer, because we want to express multiple + * cpu might call us concurrently. + * sk->sk_wmem_alloc in an atomic, we can promote to rw. + */ + skb_set_owner_w(skb, (struct sock *)sk); + } skb_dst_set(skb, dst); mss = dst_metric_advmss(dst); @@ -3510,7 +3518,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) int res; tcp_rsk(req)->txhash = net_tx_rndhash(); - res = af_ops->send_synack(sk, NULL, &fl, req, 0, NULL); + res = af_ops->send_synack(sk, NULL, &fl, req, 0, NULL, true); if (!res) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index a215614cfb2b..3d18571811c5 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -438,7 +438,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, u16 queue_mapping, - struct tcp_fastopen_cookie *foc) + struct tcp_fastopen_cookie *foc, + bool attach_req) { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); @@ -451,7 +452,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, IPPROTO_TCP)) == NULL) goto done; - skb = tcp_make_synack(sk, dst, req, foc); + skb = tcp_make_synack(sk, dst, req, foc, attach_req); if (skb) { __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index f377702d4b91..3386cce4751e 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -224,13 +224,15 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) if (unlikely((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL)) return &q->internal; - /* SYNACK messages are attached to a listener socket. - * 1) They are not part of a 'flow' yet - * 2) We do not want to rate limit them (eg SYNFLOOD attack), + /* SYNACK messages are attached to a TCP_NEW_SYN_RECV request socket + * 1) request sockets are not full blown, + * they do not contain sk_pacing_rate + * 2) They are not part of a 'flow' yet + * 3) We do not want to rate limit them (eg SYNFLOOD attack), * especially if the listener set SO_MAX_PACING_RATE - * 3) We pretend they are orphaned + * 4) We pretend they are orphaned */ - if (!sk || sk->sk_state == TCP_LISTEN) { + if (!sk || sk->sk_state == TCP_NEW_SYN_RECV) { unsigned long hash = skb_get_hash(skb) & q->orphan_mask; /* By forcing low order bit to 1, we make sure to not -- cgit v1.2.3 From 10cbc8f179177c1a6d5f56a46ebddc8f602ce5ac Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:36 -0700 Subject: tcp/dccp: remove struct listen_sock It is enough to check listener sk_state, no need for an extra condition. max_qlen_log can be moved into struct request_sock_queue We can remove syn_wait_lock and the alignment it enforced. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 26 ++++------------------- net/core/request_sock.c | 47 +++-------------------------------------- net/ipv4/inet_connection_sock.c | 14 ++++-------- 3 files changed, 11 insertions(+), 76 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 353cb61bb399..a66ab1345373 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -119,14 +119,6 @@ static inline void reqsk_put(struct request_sock *req) extern int sysctl_max_syn_backlog; -/** struct listen_sock - listen state - * - * @max_qlen_log - log_2 of maximal queued SYNs/REQUESTs - */ -struct listen_sock { - u32 max_qlen_log; -}; - /* * For a TCP Fast Open listener - * lock - protects the access to all the reqsk, which is co-owned by @@ -160,36 +152,26 @@ struct fastopen_queue { * @rskq_accept_head - FIFO head of established children * @rskq_accept_tail - FIFO tail of established children * @rskq_defer_accept - User waits for some data after accept() - * @syn_wait_lock - serializer - * - * %syn_wait_lock is necessary only to avoid proc interface having to grab the main - * lock sock while browsing the listening hash (otherwise it's deadlock prone). * */ struct request_sock_queue { spinlock_t rskq_lock; u8 rskq_defer_accept; + u8 max_qlen_log; u32 synflood_warned; - atomic_t qlen; atomic_t young; struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; - struct listen_sock *listen_opt; struct fastopen_queue fastopenq; /* Check max_qlen != 0 to determine * if TFO is enabled. */ - - /* temporary alignment, our goal is to get rid of this lock */ - spinlock_t syn_wait_lock ____cacheline_aligned_in_smp; }; -int reqsk_queue_alloc(struct request_sock_queue *queue, - unsigned int nr_table_entries); +void reqsk_queue_alloc(struct request_sock_queue *queue, + unsigned int nr_table_entries); -void __reqsk_queue_destroy(struct request_sock_queue *queue); -void reqsk_queue_destroy(struct request_sock_queue *queue); void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, bool reset); @@ -260,7 +242,7 @@ static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) { - return reqsk_queue_len(queue) >> queue->listen_opt->max_qlen_log; + return reqsk_queue_len(queue) >> queue->max_qlen_log; } #endif /* _REQUEST_SOCK_H */ diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 124f61c5bfef..ecf74189bd3f 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -37,22 +37,14 @@ int sysctl_max_syn_backlog = 256; EXPORT_SYMBOL(sysctl_max_syn_backlog); -int reqsk_queue_alloc(struct request_sock_queue *queue, - unsigned int nr_table_entries) +void reqsk_queue_alloc(struct request_sock_queue *queue, + unsigned int nr_table_entries) { - size_t lopt_size = sizeof(struct listen_sock); - struct listen_sock *lopt = NULL; - nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog); nr_table_entries = max_t(u32, nr_table_entries, 8); nr_table_entries = roundup_pow_of_two(nr_table_entries + 1); - lopt = kzalloc(lopt_size, GFP_KERNEL); - if (!lopt) - return -ENOMEM; - spin_lock_init(&queue->rskq_lock); - spin_lock_init(&queue->syn_wait_lock); spin_lock_init(&queue->fastopenq.lock); queue->fastopenq.rskq_rst_head = NULL; @@ -61,40 +53,7 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, queue->fastopenq.max_qlen = 0; queue->rskq_accept_head = NULL; - lopt->max_qlen_log = ilog2(nr_table_entries); - - spin_lock_bh(&queue->syn_wait_lock); - queue->listen_opt = lopt; - spin_unlock_bh(&queue->syn_wait_lock); - - return 0; -} - -void __reqsk_queue_destroy(struct request_sock_queue *queue) -{ - /* This is an error recovery path only, no locking needed */ - kfree(queue->listen_opt); -} - -static inline struct listen_sock *reqsk_queue_yank_listen_sk( - struct request_sock_queue *queue) -{ - struct listen_sock *lopt; - - spin_lock_bh(&queue->syn_wait_lock); - lopt = queue->listen_opt; - queue->listen_opt = NULL; - spin_unlock_bh(&queue->syn_wait_lock); - - return lopt; -} - -void reqsk_queue_destroy(struct request_sock_queue *queue) -{ - struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue); - - /* cleaning is done by req timers */ - kfree(lopt); + queue->max_qlen_log = ilog2(nr_table_entries); } /* diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 099e0ea9242a..775483283fa7 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -552,12 +552,11 @@ static void reqsk_timer_handler(unsigned long data) struct sock *sk_listener = req->rsk_listener; struct inet_connection_sock *icsk = inet_csk(sk_listener); struct request_sock_queue *queue = &icsk->icsk_accept_queue; - struct listen_sock *lopt = queue->listen_opt; int qlen, expire = 0, resend = 0; int max_retries, thresh; u8 defer_accept; - if (sk_listener->sk_state != TCP_LISTEN || !lopt) + if (sk_listener->sk_state != TCP_LISTEN) goto drop; max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; @@ -580,7 +579,7 @@ static void reqsk_timer_handler(unsigned long data) * ones are about to clog our table. */ qlen = reqsk_queue_len(queue); - if (qlen >> (lopt->max_qlen_log - 1)) { + if (qlen >> (queue->max_qlen_log - 1)) { int young = reqsk_queue_len_young(queue) << 1; while (thresh > 2) { @@ -730,12 +729,10 @@ EXPORT_SYMBOL(inet_csk_prepare_forced_close); int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) { - struct inet_sock *inet = inet_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); - int rc = reqsk_queue_alloc(&icsk->icsk_accept_queue, nr_table_entries); + struct inet_sock *inet = inet_sk(sk); - if (rc != 0) - return rc; + reqsk_queue_alloc(&icsk->icsk_accept_queue, nr_table_entries); sk->sk_max_ack_backlog = 0; sk->sk_ack_backlog = 0; @@ -757,7 +754,6 @@ int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) } sk->sk_state = TCP_CLOSE; - __reqsk_queue_destroy(&icsk->icsk_accept_queue); return -EADDRINUSE; } EXPORT_SYMBOL_GPL(inet_csk_listen_start); @@ -780,8 +776,6 @@ void inet_csk_listen_stop(struct sock *sk) * To be honest, we are not able to make either * of the variants now. --ANK */ - reqsk_queue_destroy(queue); - while ((req = reqsk_queue_remove(queue, sk)) != NULL) { struct sock *child = req->sk; -- cgit v1.2.3 From ef547f2ac16bd9d77a780a0e7c70857e69e8f23f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:37 -0700 Subject: tcp: remove max_qlen_log This control variable was set at first listen(fd, backlog) call, but not updated if application tried to increase or decrease backlog. It made sense at the time listener had a non resizeable hash table. Also rounding to powers of two was not very friendly. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 2 +- include/net/request_sock.h | 10 ++-------- net/core/request_sock.c | 8 +------- net/ipv4/inet_connection_sock.c | 4 ++-- 4 files changed, 6 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 730aa034cd3d..3208a65d1c28 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -295,7 +295,7 @@ static inline int inet_csk_reqsk_queue_young(const struct sock *sk) static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { - return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue); + return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog; } void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index a66ab1345373..bae6936d75c4 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -157,7 +157,7 @@ struct fastopen_queue { struct request_sock_queue { spinlock_t rskq_lock; u8 rskq_defer_accept; - u8 max_qlen_log; + u32 synflood_warned; atomic_t qlen; atomic_t young; @@ -169,8 +169,7 @@ struct request_sock_queue { */ }; -void reqsk_queue_alloc(struct request_sock_queue *queue, - unsigned int nr_table_entries); +void reqsk_queue_alloc(struct request_sock_queue *queue); void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, bool reset); @@ -240,9 +239,4 @@ static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) return atomic_read(&queue->young); } -static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) -{ - return reqsk_queue_len(queue) >> queue->max_qlen_log; -} - #endif /* _REQUEST_SOCK_H */ diff --git a/net/core/request_sock.c b/net/core/request_sock.c index ecf74189bd3f..15c853806518 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -37,13 +37,8 @@ int sysctl_max_syn_backlog = 256; EXPORT_SYMBOL(sysctl_max_syn_backlog); -void reqsk_queue_alloc(struct request_sock_queue *queue, - unsigned int nr_table_entries) +void reqsk_queue_alloc(struct request_sock_queue *queue) { - nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog); - nr_table_entries = max_t(u32, nr_table_entries, 8); - nr_table_entries = roundup_pow_of_two(nr_table_entries + 1); - spin_lock_init(&queue->rskq_lock); spin_lock_init(&queue->fastopenq.lock); @@ -53,7 +48,6 @@ void reqsk_queue_alloc(struct request_sock_queue *queue, queue->fastopenq.max_qlen = 0; queue->rskq_accept_head = NULL; - queue->max_qlen_log = ilog2(nr_table_entries); } /* diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 775483283fa7..5f6e31a4aeae 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -579,7 +579,7 @@ static void reqsk_timer_handler(unsigned long data) * ones are about to clog our table. */ qlen = reqsk_queue_len(queue); - if (qlen >> (queue->max_qlen_log - 1)) { + if ((qlen << 1) > sk_listener->sk_max_ack_backlog) { int young = reqsk_queue_len_young(queue) << 1; while (thresh > 2) { @@ -732,7 +732,7 @@ int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); - reqsk_queue_alloc(&icsk->icsk_accept_queue, nr_table_entries); + reqsk_queue_alloc(&icsk->icsk_accept_queue); sk->sk_max_ack_backlog = 0; sk->sk_ack_backlog = 0; -- cgit v1.2.3 From 57d80838dae55c1bc6ca629e471c84100513079a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:41 +0200 Subject: switchdev: rename SWITCHDEV_OBJ_* enum values to SWITCHDEV_OBJ_ID_* Suggested-by: Vivien Didelot Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- Documentation/networking/switchdev.txt | 6 +++--- drivers/net/ethernet/rocker/rocker.c | 16 ++++++++-------- include/net/switchdev.h | 14 +++++++------- net/bridge/br_fdb.c | 2 +- net/bridge/br_vlan.c | 6 ++++-- net/dsa/slave.c | 12 ++++++------ net/switchdev/switchdev.c | 16 ++++++++-------- 7 files changed, 37 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 9f9e2587b347..c150a87c774b 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -178,7 +178,7 @@ entries are installed, for example, using iproute2 bridge cmd: bridge fdb add ADDR dev DEV [vlan VID] [self] The driver should use the helper switchdev_port_fdb_xxx ops for ndo_fdb_xxx -ops, and handle add/delete/dump of SWITCHDEV_OBJ_PORT_FDB object using +ops, and handle add/delete/dump of SWITCHDEV_OBJ_ID_PORT_FDB object using switchdev_port_obj_xxx ops. XXX: what should be done if offloading this rule to hardware fails (for @@ -316,9 +316,9 @@ SWITCHDEV_OBJ_IPV[4|6]_FIB object using switchdev_port_obj_xxx ops. switchdev_port_obj_add is used for both adding a new FIB entry to the device, or modifying an existing entry on the device. -XXX: Currently, only SWITCHDEV_OBJ_IPV4_FIB objects are supported. +XXX: Currently, only SWITCHDEV_OBJ_ID_IPV4_FIB objects are supported. -SWITCHDEV_OBJ_IPV4_FIB object passes: +SWITCHDEV_OBJ_ID_IPV4_FIB object passes: struct switchdev_obj_ipv4_fib { /* IPV4_FIB */ u32 dst; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 9773f5b65296..9b2e8bed8f83 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4445,16 +4445,16 @@ static int rocker_port_obj_add(struct net_device *dev, int err = 0; switch (id) { - case SWITCHDEV_OBJ_PORT_VLAN: + case SWITCHDEV_OBJ_ID_PORT_VLAN: err = rocker_port_vlans_add(rocker_port, trans, obj); break; - case SWITCHDEV_OBJ_IPV4_FIB: + case SWITCHDEV_OBJ_ID_IPV4_FIB: fib4 = obj; err = rocker_port_fib_ipv4(rocker_port, trans, htonl(fib4->dst), fib4->dst_len, fib4->fi, fib4->tb_id, 0); break; - case SWITCHDEV_OBJ_PORT_FDB: + case SWITCHDEV_OBJ_ID_PORT_FDB: err = rocker_port_fdb_add(rocker_port, trans, obj); break; default: @@ -4515,17 +4515,17 @@ static int rocker_port_obj_del(struct net_device *dev, int err = 0; switch (id) { - case SWITCHDEV_OBJ_PORT_VLAN: + case SWITCHDEV_OBJ_ID_PORT_VLAN: err = rocker_port_vlans_del(rocker_port, obj); break; - case SWITCHDEV_OBJ_IPV4_FIB: + case SWITCHDEV_OBJ_ID_IPV4_FIB: fib4 = obj; err = rocker_port_fib_ipv4(rocker_port, NULL, htonl(fib4->dst), fib4->dst_len, fib4->fi, fib4->tb_id, ROCKER_OP_FLAG_REMOVE); break; - case SWITCHDEV_OBJ_PORT_FDB: + case SWITCHDEV_OBJ_ID_PORT_FDB: err = rocker_port_fdb_del(rocker_port, NULL, obj); break; default: @@ -4594,10 +4594,10 @@ static int rocker_port_obj_dump(struct net_device *dev, int err = 0; switch (id) { - case SWITCHDEV_OBJ_PORT_FDB: + case SWITCHDEV_OBJ_ID_PORT_FDB: err = rocker_port_fdb_dump(rocker_port, obj, cb); break; - case SWITCHDEV_OBJ_PORT_VLAN: + case SWITCHDEV_OBJ_ID_PORT_VLAN: err = rocker_port_vlan_dump(rocker_port, obj, cb); break; default: diff --git a/include/net/switchdev.h b/include/net/switchdev.h index e11425eb0735..11f9c706cf5c 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -58,20 +58,20 @@ struct switchdev_attr { struct fib_info; enum switchdev_obj_id { - SWITCHDEV_OBJ_UNDEFINED, - SWITCHDEV_OBJ_PORT_VLAN, - SWITCHDEV_OBJ_IPV4_FIB, - SWITCHDEV_OBJ_PORT_FDB, + SWITCHDEV_OBJ_ID_UNDEFINED, + SWITCHDEV_OBJ_ID_PORT_VLAN, + SWITCHDEV_OBJ_ID_IPV4_FIB, + SWITCHDEV_OBJ_ID_PORT_FDB, }; -/* SWITCHDEV_OBJ_PORT_VLAN */ +/* SWITCHDEV_OBJ_ID_PORT_VLAN */ struct switchdev_obj_vlan { u16 flags; u16 vid_begin; u16 vid_end; }; -/* SWITCHDEV_OBJ_IPV4_FIB */ +/* SWITCHDEV_OBJ_ID_IPV4_FIB */ struct switchdev_obj_ipv4_fib { u32 dst; int dst_len; @@ -82,7 +82,7 @@ struct switchdev_obj_ipv4_fib { u32 tb_id; }; -/* SWITCHDEV_OBJ_PORT_FDB */ +/* SWITCHDEV_OBJ_ID_PORT_FDB */ struct switchdev_obj_fdb { const unsigned char *addr; u16 vid; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 7826782d62ab..6fc8e71277d4 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -138,7 +138,7 @@ static void fdb_del_external_learn(struct net_bridge_fdb_entry *f) .vid = f->vlan_id, }; - switchdev_port_obj_del(f->dst->dev, SWITCHDEV_OBJ_PORT_FDB, &fdb); + switchdev_port_obj_del(f->dst->dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb); } static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 75214a51cf0e..68b5a1125667 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -88,7 +88,8 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, .vid_end = vid, }; - err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_PORT_VLAN, &v); + err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, + &v); if (err == -EOPNOTSUPP) err = 0; } @@ -136,7 +137,8 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, .vid_end = vid, }; - err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_PORT_VLAN, &v); + err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, + &v); if (err == -EOPNOTSUPP) err = 0; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 7b1d9ec74e09..a7060298b856 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -485,10 +485,10 @@ static int dsa_slave_port_obj_add(struct net_device *dev, */ switch (id) { - case SWITCHDEV_OBJ_PORT_FDB: + case SWITCHDEV_OBJ_ID_PORT_FDB: err = dsa_slave_port_fdb_add(dev, obj, trans); break; - case SWITCHDEV_OBJ_PORT_VLAN: + case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_slave_port_vlan_add(dev, obj, trans); break; default: @@ -505,10 +505,10 @@ static int dsa_slave_port_obj_del(struct net_device *dev, int err; switch (id) { - case SWITCHDEV_OBJ_PORT_FDB: + case SWITCHDEV_OBJ_ID_PORT_FDB: err = dsa_slave_port_fdb_del(dev, obj); break; - case SWITCHDEV_OBJ_PORT_VLAN: + case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_slave_port_vlan_del(dev, obj); break; default: @@ -526,10 +526,10 @@ static int dsa_slave_port_obj_dump(struct net_device *dev, int err; switch (id) { - case SWITCHDEV_OBJ_PORT_FDB: + case SWITCHDEV_OBJ_ID_PORT_FDB: err = dsa_slave_port_fdb_dump(dev, obj, cb); break; - case SWITCHDEV_OBJ_PORT_VLAN: + case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_slave_port_vlan_dump(dev, obj, cb); break; default: diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index fe82fab1d55c..5b1aa9f6f261 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -584,7 +584,7 @@ static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev, if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { - err = switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_PORT_VLAN, + err = switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, &dump.vlan, switchdev_port_vlan_dump_cb); if (err) @@ -725,7 +725,7 @@ static int switchdev_port_br_afspec(struct net_device *dev, vlan.vid_end = vinfo->vid; if (vlan.vid_end <= vlan.vid_begin) return -EINVAL; - err = f(dev, SWITCHDEV_OBJ_PORT_VLAN, &vlan); + err = f(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, &vlan); if (err) return err; memset(&vlan, 0, sizeof(vlan)); @@ -734,7 +734,7 @@ static int switchdev_port_br_afspec(struct net_device *dev, return -EINVAL; vlan.vid_begin = vinfo->vid; vlan.vid_end = vinfo->vid; - err = f(dev, SWITCHDEV_OBJ_PORT_VLAN, &vlan); + err = f(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, &vlan); if (err) return err; memset(&vlan, 0, sizeof(vlan)); @@ -824,7 +824,7 @@ int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], .vid = vid, }; - return switchdev_port_obj_add(dev, SWITCHDEV_OBJ_PORT_FDB, &fdb); + return switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_add); @@ -848,7 +848,7 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], .vid = vid, }; - return switchdev_port_obj_del(dev, SWITCHDEV_OBJ_PORT_FDB, &fdb); + return switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_del); @@ -926,7 +926,7 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, .idx = idx, }; - switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_PORT_FDB, &dump.fdb, + switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &dump.fdb, switchdev_port_fdb_dump_cb); return dump.idx; } @@ -1033,7 +1033,7 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; - err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_IPV4_FIB, &ipv4_fib); + err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_IPV4_FIB, &ipv4_fib); if (!err) fi->fib_flags |= RTNH_F_OFFLOAD; @@ -1075,7 +1075,7 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; - err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_IPV4_FIB, &ipv4_fib); + err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_IPV4_FIB, &ipv4_fib); if (!err) fi->fib_flags &= ~RTNH_F_OFFLOAD; -- cgit v1.2.3 From 1f86839874a50c9ee2009567d2f312b1e1949e24 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:42 +0200 Subject: switchdev: rename SWITCHDEV_ATTR_* enum values to SWITCHDEV_ATTR_ID_* To be aligned with obj. Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- Documentation/networking/switchdev.txt | 9 +++++---- drivers/net/ethernet/mellanox/mlxsw/switchx2.c | 2 +- drivers/net/ethernet/rocker/rocker.c | 8 ++++---- include/net/switchdev.h | 8 ++++---- net/bridge/br_stp.c | 2 +- net/core/net-sysfs.c | 2 +- net/core/rtnetlink.c | 2 +- net/dsa/slave.c | 4 ++-- net/switchdev/switchdev.c | 14 +++++++------- 9 files changed, 26 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index c150a87c774b..0714fe555016 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -115,7 +115,7 @@ Switch ID ^^^^^^^^^ The switchdev driver must implement the switchdev op switchdev_port_attr_get -for SWITCHDEV_ATTR_PORT_PARENT_ID for each port netdev, returning the same +for SWITCHDEV_ATTR_ID_PORT_PARENT_ID for each port netdev, returning the same physical ID for each port of a switch. The ID must be unique between switches on the same system. The ID does not need to be unique between switches on different systems. @@ -233,8 +233,9 @@ the bridge's FDB. It's possible, but not optimal, to enable learning on the device port and on the bridge port, and disable learning_sync. To support learning and learning_sync port attributes, the driver implements -switchdev op switchdev_port_attr_get/set for SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS. -The driver should initialize the attributes to the hardware defaults. +switchdev op switchdev_port_attr_get/set for +SWITCHDEV_ATTR_PORT_ID_BRIDGE_FLAGS. The driver should initialize the attributes +to the hardware defaults. FDB Ageing ^^^^^^^^^^ @@ -260,7 +261,7 @@ STP State Change on Port Internally or with a third-party STP protocol implementation (e.g. mstpd), the bridge driver maintains the STP state for ports, and will notify the switch driver of STP state change on a port using the switchdev op -switchdev_attr_port_set for SWITCHDEV_ATTR_PORT_STP_UPDATE. +switchdev_attr_port_set for SWITCHDEV_ATTR_PORT_ID_STP_UPDATE. State is one of BR_STATE_*. The switch driver can use STP state updates to update ingress packet filter list for the port. For example, if port is diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 3e52ee93438c..d448431bbc83 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -868,7 +868,7 @@ static int mlxsw_sx_port_attr_get(struct net_device *dev, struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; switch (attr->id) { - case SWITCHDEV_ATTR_PORT_PARENT_ID: + case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: attr->u.ppid.id_len = sizeof(mlxsw_sx->hw_id); memcpy(&attr->u.ppid.id, &mlxsw_sx->hw_id, attr->u.ppid.id_len); break; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 9b2e8bed8f83..4540ca63a434 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4329,11 +4329,11 @@ static int rocker_port_attr_get(struct net_device *dev, const struct rocker *rocker = rocker_port->rocker; switch (attr->id) { - case SWITCHDEV_ATTR_PORT_PARENT_ID: + case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: attr->u.ppid.id_len = sizeof(rocker->hw.id); memcpy(&attr->u.ppid.id, &rocker->hw.id, attr->u.ppid.id_len); break; - case SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS: + case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: attr->u.brport_flags = rocker_port->brport_flags; break; default: @@ -4369,12 +4369,12 @@ static int rocker_port_attr_set(struct net_device *dev, int err = 0; switch (attr->id) { - case SWITCHDEV_ATTR_PORT_STP_STATE: + case SWITCHDEV_ATTR_ID_PORT_STP_STATE: err = rocker_port_stp_update(rocker_port, trans, ROCKER_OP_FLAG_NOWAIT, attr->u.stp_state); break; - case SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS: + case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: err = rocker_port_brport_flags_set(rocker_port, trans, attr->u.brport_flags); break; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 11f9c706cf5c..612719b9618a 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -39,10 +39,10 @@ static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans) } enum switchdev_attr_id { - SWITCHDEV_ATTR_UNDEFINED, - SWITCHDEV_ATTR_PORT_PARENT_ID, - SWITCHDEV_ATTR_PORT_STP_STATE, - SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, + SWITCHDEV_ATTR_ID_UNDEFINED, + SWITCHDEV_ATTR_ID_PORT_PARENT_ID, + SWITCHDEV_ATTR_ID_PORT_STP_STATE, + SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, }; struct switchdev_attr { diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 3a7392e6010e..3a982c02599a 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -40,7 +40,7 @@ void br_log_state(const struct net_bridge_port *p) void br_set_state(struct net_bridge_port *p, unsigned int state) { struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_STP_STATE, + .id = SWITCHDEV_ATTR_ID_PORT_STP_STATE, .u.stp_state = state, }; int err; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 410c6e42bf1f..f88a62ab019d 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -471,7 +471,7 @@ static ssize_t phys_switch_id_show(struct device *dev, if (dev_isalive(netdev)) { struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 474a6da3b51a..b2258a36d894 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1025,7 +1025,7 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) { int err; struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index a7060298b856..8992568f5c0e 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -458,7 +458,7 @@ static int dsa_slave_port_attr_set(struct net_device *dev, int ret; switch (attr->id) { - case SWITCHDEV_ATTR_PORT_STP_STATE: + case SWITCHDEV_ATTR_ID_PORT_STP_STATE: if (switchdev_trans_ph_prepare(trans)) ret = ds->drv->port_stp_update ? 0 : -EOPNOTSUPP; else @@ -584,7 +584,7 @@ static int dsa_slave_port_attr_get(struct net_device *dev, struct dsa_switch *ds = p->parent; switch (attr->id) { - case SWITCHDEV_ATTR_PORT_PARENT_ID: + case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: attr->u.ppid.id_len = sizeof(ds->index); memcpy(&attr->u.ppid.id, &ds->index, attr->u.ppid.id_len); break; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 5b1aa9f6f261..c457c1f73d35 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -104,7 +104,7 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) struct net_device *lower_dev; struct list_head *iter; struct switchdev_attr first = { - .id = SWITCHDEV_ATTR_UNDEFINED + .id = SWITCHDEV_ATTR_ID_UNDEFINED }; int err = -EOPNOTSUPP; @@ -124,7 +124,7 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) err = switchdev_port_attr_get(lower_dev, attr); if (err) break; - if (first.id == SWITCHDEV_ATTR_UNDEFINED) + if (first.id == SWITCHDEV_ATTR_ID_UNDEFINED) first = *attr; else if (memcmp(&first, attr, sizeof(*attr))) return -ENODATA; @@ -611,7 +611,7 @@ int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, int nlflags) { struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, + .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, }; u16 mode = BRIDGE_MODE_UNDEF; u32 mask = BR_LEARNING | BR_LEARNING_SYNC; @@ -632,7 +632,7 @@ static int switchdev_port_br_setflag(struct net_device *dev, unsigned long brport_flag) { struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, + .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, }; u8 flag = nla_get_u8(nlattr); int err; @@ -958,7 +958,7 @@ static struct net_device *switchdev_get_lowest_dev(struct net_device *dev) static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) { struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, }; struct switchdev_attr prev_attr; struct net_device *dev = NULL; @@ -1107,11 +1107,11 @@ static bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b) { struct switchdev_attr a_attr = { - .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; struct switchdev_attr b_attr = { - .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; -- cgit v1.2.3 From 8f24f3095dcedaa4eb4719eee2bed738fe2ce4a0 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:43 +0200 Subject: switchdev: rename switchdev_obj_vlan to switchdev_obj_port_vlan Make the struct name in sync with object id name. Suggested-by: Vivien Didelot Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 6 +++--- include/net/switchdev.h | 2 +- net/bridge/br_vlan.c | 4 ++-- net/dsa/slave.c | 6 +++--- net/switchdev/switchdev.c | 6 +++--- 5 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 4540ca63a434..d75fc4b3baa9 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4408,7 +4408,7 @@ static int rocker_port_vlan_add(struct rocker_port *rocker_port, static int rocker_port_vlans_add(struct rocker_port *rocker_port, struct switchdev_trans *trans, - const struct switchdev_obj_vlan *vlan) + const struct switchdev_obj_port_vlan *vlan) { u16 vid; int err; @@ -4480,7 +4480,7 @@ static int rocker_port_vlan_del(struct rocker_port *rocker_port, } static int rocker_port_vlans_del(struct rocker_port *rocker_port, - const struct switchdev_obj_vlan *vlan) + const struct switchdev_obj_port_vlan *vlan) { u16 vid; int err; @@ -4565,7 +4565,7 @@ static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, } static int rocker_port_vlan_dump(const struct rocker_port *rocker_port, - struct switchdev_obj_vlan *vlan, + struct switchdev_obj_port_vlan *vlan, int (*cb)(void *obj)) { u16 vid; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 612719b9618a..0138f9b374e2 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -65,7 +65,7 @@ enum switchdev_obj_id { }; /* SWITCHDEV_OBJ_ID_PORT_VLAN */ -struct switchdev_obj_vlan { +struct switchdev_obj_port_vlan { u16 flags; u16 vid_begin; u16 vid_end; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 68b5a1125667..d4cb129557f4 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -82,7 +82,7 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, if (ops->ndo_vlan_rx_add_vid) { err = vlan_vid_add(dev, br->vlan_proto, vid); } else { - struct switchdev_obj_vlan v = { + struct switchdev_obj_port_vlan v = { .flags = flags, .vid_begin = vid, .vid_end = vid, @@ -132,7 +132,7 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, if (ops->ndo_vlan_rx_kill_vid) { vlan_vid_del(dev, br->vlan_proto, vid); } else { - struct switchdev_obj_vlan v = { + struct switchdev_obj_port_vlan v = { .vid_begin = vid, .vid_end = vid, }; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 8992568f5c0e..baf34f222115 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -242,7 +242,7 @@ static int dsa_bridge_check_vlan_range(struct dsa_switch *ds, } static int dsa_slave_port_vlan_add(struct net_device *dev, - const struct switchdev_obj_vlan *vlan, + const struct switchdev_obj_port_vlan *vlan, struct switchdev_trans *trans) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -278,7 +278,7 @@ static int dsa_slave_port_vlan_add(struct net_device *dev, } static int dsa_slave_port_vlan_del(struct net_device *dev, - const struct switchdev_obj_vlan *vlan) + const struct switchdev_obj_port_vlan *vlan) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; @@ -298,7 +298,7 @@ static int dsa_slave_port_vlan_del(struct net_device *dev, } static int dsa_slave_port_vlan_dump(struct net_device *dev, - struct switchdev_obj_vlan *vlan, + struct switchdev_obj_port_vlan *vlan, int (*cb)(void *obj)) { struct dsa_slave_priv *p = netdev_priv(dev); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index c457c1f73d35..02ee926ebde6 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -483,7 +483,7 @@ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, EXPORT_SYMBOL_GPL(call_switchdev_notifiers); struct switchdev_vlan_dump { - struct switchdev_obj_vlan vlan; + struct switchdev_obj_port_vlan vlan; struct sk_buff *skb; u32 filter_mask; u16 flags; @@ -523,7 +523,7 @@ static int switchdev_port_vlan_dump_put(struct switchdev_vlan_dump *dump) static int switchdev_port_vlan_dump_cb(void *obj) { - struct switchdev_obj_vlan *vlan = obj; + struct switchdev_obj_port_vlan *vlan = obj; struct switchdev_vlan_dump *dump = container_of(vlan, struct switchdev_vlan_dump, vlan); int err = 0; @@ -704,7 +704,7 @@ static int switchdev_port_br_afspec(struct net_device *dev, { struct nlattr *attr; struct bridge_vlan_info *vinfo; - struct switchdev_obj_vlan vlan = { 0 }; + struct switchdev_obj_port_vlan vlan = { 0 }; int rem; int err; -- cgit v1.2.3 From 52ba57cfdc4c90da3bf996dfbe0c5feb731eb477 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:44 +0200 Subject: switchdev: rename switchdev_obj_fdb to switchdev_obj_port_fdb Make the struct name in sync with object id name. Suggested-by: Vivien Didelot Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 6 +++--- include/net/switchdev.h | 2 +- net/bridge/br_fdb.c | 2 +- net/dsa/slave.c | 6 +++--- net/switchdev/switchdev.c | 8 ++++---- 5 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index d75fc4b3baa9..875f9b5b78a2 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4425,7 +4425,7 @@ static int rocker_port_vlans_add(struct rocker_port *rocker_port, static int rocker_port_fdb_add(struct rocker_port *rocker_port, struct switchdev_trans *trans, - const struct switchdev_obj_fdb *fdb) + const struct switchdev_obj_port_fdb *fdb) { __be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, fdb->vid, NULL); int flags = 0; @@ -4496,7 +4496,7 @@ static int rocker_port_vlans_del(struct rocker_port *rocker_port, static int rocker_port_fdb_del(struct rocker_port *rocker_port, struct switchdev_trans *trans, - const struct switchdev_obj_fdb *fdb) + const struct switchdev_obj_port_fdb *fdb) { __be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, fdb->vid, NULL); int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_REMOVE; @@ -4537,7 +4537,7 @@ static int rocker_port_obj_del(struct net_device *dev, } static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, - struct switchdev_obj_fdb *fdb, + struct switchdev_obj_port_fdb *fdb, int (*cb)(void *obj)) { struct rocker *rocker = rocker_port->rocker; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 0138f9b374e2..8d71fdbaa7a6 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -83,7 +83,7 @@ struct switchdev_obj_ipv4_fib { }; /* SWITCHDEV_OBJ_ID_PORT_FDB */ -struct switchdev_obj_fdb { +struct switchdev_obj_port_fdb { const unsigned char *addr; u16 vid; u16 ndm_state; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 6fc8e71277d4..36aab5e4784c 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -133,7 +133,7 @@ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr) static void fdb_del_external_learn(struct net_bridge_fdb_entry *f) { - struct switchdev_obj_fdb fdb = { + struct switchdev_obj_port_fdb fdb = { .addr = f->addr.addr, .vid = f->vlan_id, }; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index baf34f222115..6e8dc6a0102c 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -341,7 +341,7 @@ static int dsa_slave_port_vlan_dump(struct net_device *dev, } static int dsa_slave_port_fdb_add(struct net_device *dev, - const struct switchdev_obj_fdb *fdb, + const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -357,7 +357,7 @@ static int dsa_slave_port_fdb_add(struct net_device *dev, } static int dsa_slave_port_fdb_del(struct net_device *dev, - const struct switchdev_obj_fdb *fdb) + const struct switchdev_obj_port_fdb *fdb) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; @@ -370,7 +370,7 @@ static int dsa_slave_port_fdb_del(struct net_device *dev, } static int dsa_slave_port_fdb_dump(struct net_device *dev, - struct switchdev_obj_fdb *fdb, + struct switchdev_obj_port_fdb *fdb, int (*cb)(void *obj)) { struct dsa_slave_priv *p = netdev_priv(dev); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 02ee926ebde6..250d013d64c6 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -819,7 +819,7 @@ int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlm_flags) { - struct switchdev_obj_fdb fdb = { + struct switchdev_obj_port_fdb fdb = { .addr = addr, .vid = vid, }; @@ -843,7 +843,7 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid) { - struct switchdev_obj_fdb fdb = { + struct switchdev_obj_port_fdb fdb = { .addr = addr, .vid = vid, }; @@ -853,7 +853,7 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], EXPORT_SYMBOL_GPL(switchdev_port_fdb_del); struct switchdev_fdb_dump { - struct switchdev_obj_fdb fdb; + struct switchdev_obj_port_fdb fdb; struct net_device *dev; struct sk_buff *skb; struct netlink_callback *cb; @@ -862,7 +862,7 @@ struct switchdev_fdb_dump { static int switchdev_port_fdb_dump_cb(void *obj) { - struct switchdev_obj_fdb *fdb = obj; + struct switchdev_obj_port_fdb *fdb = obj; struct switchdev_fdb_dump *dump = container_of(fdb, struct switchdev_fdb_dump, fdb); u32 portid = NETLINK_CB(dump->cb->skb).portid; -- cgit v1.2.3 From 648b4a995a057187ddd77cdb181e6a0b24ab2959 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:45 +0200 Subject: switchdev: bring back switchdev_obj and use it as a generic object param Replace "void *obj" with a generic structure. Introduce couple of helpers along that. Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 41 +++++++++++++++++++++-------------- include/net/switchdev.h | 42 ++++++++++++++++++++++++++---------- net/bridge/br_fdb.c | 3 ++- net/bridge/br_vlan.c | 4 ++-- net/dsa/slave.c | 41 +++++++++++++++++++++++------------ net/switchdev/switchdev.c | 40 ++++++++++++++++++---------------- 6 files changed, 109 insertions(+), 62 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 875f9b5b78a2..2a577e5b8ca5 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4437,7 +4437,8 @@ static int rocker_port_fdb_add(struct rocker_port *rocker_port, } static int rocker_port_obj_add(struct net_device *dev, - enum switchdev_obj_id id, const void *obj, + enum switchdev_obj_id id, + const struct switchdev_obj *obj, struct switchdev_trans *trans) { struct rocker_port *rocker_port = netdev_priv(dev); @@ -4446,16 +4447,18 @@ static int rocker_port_obj_add(struct net_device *dev, switch (id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = rocker_port_vlans_add(rocker_port, trans, obj); + err = rocker_port_vlans_add(rocker_port, trans, + SWITCHDEV_OBJ_PORT_VLAN(obj)); break; case SWITCHDEV_OBJ_ID_IPV4_FIB: - fib4 = obj; + fib4 = SWITCHDEV_OBJ_IPV4_FIB(obj); err = rocker_port_fib_ipv4(rocker_port, trans, htonl(fib4->dst), fib4->dst_len, fib4->fi, fib4->tb_id, 0); break; case SWITCHDEV_OBJ_ID_PORT_FDB: - err = rocker_port_fdb_add(rocker_port, trans, obj); + err = rocker_port_fdb_add(rocker_port, trans, + SWITCHDEV_OBJ_PORT_FDB(obj)); break; default: err = -EOPNOTSUPP; @@ -4508,7 +4511,8 @@ static int rocker_port_fdb_del(struct rocker_port *rocker_port, } static int rocker_port_obj_del(struct net_device *dev, - enum switchdev_obj_id id, const void *obj) + enum switchdev_obj_id id, + const struct switchdev_obj *obj) { struct rocker_port *rocker_port = netdev_priv(dev); const struct switchdev_obj_ipv4_fib *fib4; @@ -4516,17 +4520,19 @@ static int rocker_port_obj_del(struct net_device *dev, switch (id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = rocker_port_vlans_del(rocker_port, obj); + err = rocker_port_vlans_del(rocker_port, + SWITCHDEV_OBJ_PORT_VLAN(obj)); break; case SWITCHDEV_OBJ_ID_IPV4_FIB: - fib4 = obj; + fib4 = SWITCHDEV_OBJ_IPV4_FIB(obj); err = rocker_port_fib_ipv4(rocker_port, NULL, htonl(fib4->dst), fib4->dst_len, fib4->fi, fib4->tb_id, ROCKER_OP_FLAG_REMOVE); break; case SWITCHDEV_OBJ_ID_PORT_FDB: - err = rocker_port_fdb_del(rocker_port, NULL, obj); + err = rocker_port_fdb_del(rocker_port, NULL, + SWITCHDEV_OBJ_PORT_FDB(obj)); break; default: err = -EOPNOTSUPP; @@ -4538,7 +4544,7 @@ static int rocker_port_obj_del(struct net_device *dev, static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(void *obj)) + switchdev_obj_dump_cb_t *cb) { struct rocker *rocker = rocker_port->rocker; struct rocker_fdb_tbl_entry *found; @@ -4555,7 +4561,7 @@ static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, fdb->ndm_state = NUD_REACHABLE; fdb->vid = rocker_port_vlan_to_vid(rocker_port, found->key.vlan_id); - err = cb(fdb); + err = cb(&fdb->obj); if (err) break; } @@ -4566,7 +4572,7 @@ static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, static int rocker_port_vlan_dump(const struct rocker_port *rocker_port, struct switchdev_obj_port_vlan *vlan, - int (*cb)(void *obj)) + switchdev_obj_dump_cb_t *cb) { u16 vid; int err = 0; @@ -4578,7 +4584,7 @@ static int rocker_port_vlan_dump(const struct rocker_port *rocker_port, if (rocker_vlan_id_is_internal(htons(vid))) vlan->flags |= BRIDGE_VLAN_INFO_PVID; vlan->vid_begin = vlan->vid_end = vid; - err = cb(vlan); + err = cb(&vlan->obj); if (err) break; } @@ -4587,18 +4593,21 @@ static int rocker_port_vlan_dump(const struct rocker_port *rocker_port, } static int rocker_port_obj_dump(struct net_device *dev, - enum switchdev_obj_id id, void *obj, - int (*cb)(void *obj)) + enum switchdev_obj_id id, + struct switchdev_obj *obj, + switchdev_obj_dump_cb_t *cb) { const struct rocker_port *rocker_port = netdev_priv(dev); int err = 0; switch (id) { case SWITCHDEV_OBJ_ID_PORT_FDB: - err = rocker_port_fdb_dump(rocker_port, obj, cb); + err = rocker_port_fdb_dump(rocker_port, + SWITCHDEV_OBJ_PORT_FDB(obj), cb); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = rocker_port_vlan_dump(rocker_port, obj, cb); + err = rocker_port_vlan_dump(rocker_port, + SWITCHDEV_OBJ_PORT_VLAN(obj), cb); break; default: err = -EOPNOTSUPP; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 8d71fdbaa7a6..3e1bd14cc0ab 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -64,15 +64,23 @@ enum switchdev_obj_id { SWITCHDEV_OBJ_ID_PORT_FDB, }; +struct switchdev_obj { +}; + /* SWITCHDEV_OBJ_ID_PORT_VLAN */ struct switchdev_obj_port_vlan { + struct switchdev_obj obj; u16 flags; u16 vid_begin; u16 vid_end; }; +#define SWITCHDEV_OBJ_PORT_VLAN(obj) \ + container_of(obj, struct switchdev_obj_port_vlan, obj) + /* SWITCHDEV_OBJ_ID_IPV4_FIB */ struct switchdev_obj_ipv4_fib { + struct switchdev_obj obj; u32 dst; int dst_len; struct fib_info *fi; @@ -82,18 +90,27 @@ struct switchdev_obj_ipv4_fib { u32 tb_id; }; +#define SWITCHDEV_OBJ_IPV4_FIB(obj) \ + container_of(obj, struct switchdev_obj_ipv4_fib, obj) + /* SWITCHDEV_OBJ_ID_PORT_FDB */ struct switchdev_obj_port_fdb { + struct switchdev_obj obj; const unsigned char *addr; u16 vid; u16 ndm_state; }; +#define SWITCHDEV_OBJ_PORT_FDB(obj) \ + container_of(obj, struct switchdev_obj_port_fdb, obj) + void switchdev_trans_item_enqueue(struct switchdev_trans *trans, void *data, void (*destructor)(void const *), struct switchdev_trans_item *tritem); void *switchdev_trans_item_dequeue(struct switchdev_trans *trans); +typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj); + /** * struct switchdev_ops - switchdev operations * @@ -115,14 +132,15 @@ struct switchdev_ops { struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, enum switchdev_obj_id id, - const void *obj, + const struct switchdev_obj *obj, struct switchdev_trans *trans); int (*switchdev_port_obj_del)(struct net_device *dev, enum switchdev_obj_id id, - const void *obj); + const struct switchdev_obj *obj); int (*switchdev_port_obj_dump)(struct net_device *dev, - enum switchdev_obj_id id, void *obj, - int (*cb)(void *obj)); + enum switchdev_obj_id id, + struct switchdev_obj *obj, + switchdev_obj_dump_cb_t *cb); }; enum switchdev_notifier_type { @@ -153,11 +171,12 @@ int switchdev_port_attr_get(struct net_device *dev, int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, - const void *obj); + const struct switchdev_obj *obj); int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, - const void *obj); + const struct switchdev_obj *obj); int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, - void *obj, int (*cb)(void *obj)); + struct switchdev_obj *obj, + switchdev_obj_dump_cb_t *cb); int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, @@ -203,21 +222,22 @@ static inline int switchdev_port_attr_set(struct net_device *dev, static inline int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, - const void *obj) + const struct switchdev_obj *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, - const void *obj) + const struct switchdev_obj *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_dump(struct net_device *dev, - enum switchdev_obj_id id, void *obj, - int (*cb)(void *obj)) + enum switchdev_obj_id id, + const struct switchdev_obj *obj, + switchdev_obj_dump_cb_t *cb) { return -EOPNOTSUPP; } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 36aab5e4784c..34b62df08d34 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -138,7 +138,8 @@ static void fdb_del_external_learn(struct net_bridge_fdb_entry *f) .vid = f->vlan_id, }; - switchdev_port_obj_del(f->dst->dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb); + switchdev_port_obj_del(f->dst->dev, SWITCHDEV_OBJ_ID_PORT_FDB, + &fdb.obj); } static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index d4cb129557f4..0b87cf6ccb46 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -89,7 +89,7 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, }; err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, - &v); + &v.obj); if (err == -EOPNOTSUPP) err = 0; } @@ -138,7 +138,7 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, }; err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, - &v); + &v.obj); if (err == -EOPNOTSUPP) err = 0; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 6e8dc6a0102c..3f6d79d03457 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -299,7 +299,7 @@ static int dsa_slave_port_vlan_del(struct net_device *dev, static int dsa_slave_port_vlan_dump(struct net_device *dev, struct switchdev_obj_port_vlan *vlan, - int (*cb)(void *obj)) + switchdev_obj_dump_cb_t *cb) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; @@ -332,7 +332,7 @@ static int dsa_slave_port_vlan_dump(struct net_device *dev, if (test_bit(p->port, untagged)) vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED; - err = cb(vlan); + err = cb(&vlan->obj); if (err) break; } @@ -371,7 +371,7 @@ static int dsa_slave_port_fdb_del(struct net_device *dev, static int dsa_slave_port_fdb_dump(struct net_device *dev, struct switchdev_obj_port_fdb *fdb, - int (*cb)(void *obj)) + switchdev_obj_dump_cb_t *cb) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; @@ -394,7 +394,7 @@ static int dsa_slave_port_fdb_dump(struct net_device *dev, fdb->vid = vid; fdb->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; - ret = cb(fdb); + ret = cb(&fdb->obj); if (ret < 0) break; } @@ -474,7 +474,8 @@ static int dsa_slave_port_attr_set(struct net_device *dev, } static int dsa_slave_port_obj_add(struct net_device *dev, - enum switchdev_obj_id id, const void *obj, + enum switchdev_obj_id id, + const struct switchdev_obj *obj, struct switchdev_trans *trans) { int err; @@ -486,10 +487,14 @@ static int dsa_slave_port_obj_add(struct net_device *dev, switch (id) { case SWITCHDEV_OBJ_ID_PORT_FDB: - err = dsa_slave_port_fdb_add(dev, obj, trans); + err = dsa_slave_port_fdb_add(dev, + SWITCHDEV_OBJ_PORT_FDB(obj), + trans); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = dsa_slave_port_vlan_add(dev, obj, trans); + err = dsa_slave_port_vlan_add(dev, + SWITCHDEV_OBJ_PORT_VLAN(obj), + trans); break; default: err = -EOPNOTSUPP; @@ -500,16 +505,19 @@ static int dsa_slave_port_obj_add(struct net_device *dev, } static int dsa_slave_port_obj_del(struct net_device *dev, - enum switchdev_obj_id id, const void *obj) + enum switchdev_obj_id id, + const struct switchdev_obj *obj) { int err; switch (id) { case SWITCHDEV_OBJ_ID_PORT_FDB: - err = dsa_slave_port_fdb_del(dev, obj); + err = dsa_slave_port_fdb_del(dev, + SWITCHDEV_OBJ_PORT_FDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = dsa_slave_port_vlan_del(dev, obj); + err = dsa_slave_port_vlan_del(dev, + SWITCHDEV_OBJ_PORT_VLAN(obj)); break; default: err = -EOPNOTSUPP; @@ -520,17 +528,22 @@ static int dsa_slave_port_obj_del(struct net_device *dev, } static int dsa_slave_port_obj_dump(struct net_device *dev, - enum switchdev_obj_id id, void *obj, - int (*cb)(void *obj)) + enum switchdev_obj_id id, + struct switchdev_obj *obj, + switchdev_obj_dump_cb_t *cb) { int err; switch (id) { case SWITCHDEV_OBJ_ID_PORT_FDB: - err = dsa_slave_port_fdb_dump(dev, obj, cb); + err = dsa_slave_port_fdb_dump(dev, + SWITCHDEV_OBJ_PORT_FDB(obj), + cb); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = dsa_slave_port_vlan_dump(dev, obj, cb); + err = dsa_slave_port_vlan_dump(dev, + SWITCHDEV_OBJ_PORT_VLAN(obj), + cb); break; default: err = -EOPNOTSUPP; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 250d013d64c6..0402b3633100 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -270,7 +270,8 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) EXPORT_SYMBOL_GPL(switchdev_port_attr_set); static int __switchdev_port_obj_add(struct net_device *dev, - enum switchdev_obj_id id, const void *obj, + enum switchdev_obj_id id, + const struct switchdev_obj *obj, struct switchdev_trans *trans) { const struct switchdev_ops *ops = dev->switchdev_ops; @@ -309,7 +310,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, * rtnl_lock must be held. */ int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, - const void *obj) + const struct switchdev_obj *obj) { struct switchdev_trans trans; int err; @@ -361,7 +362,7 @@ EXPORT_SYMBOL_GPL(switchdev_port_obj_add); * @obj: object to delete */ int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, - const void *obj) + const struct switchdev_obj *obj) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; @@ -395,7 +396,8 @@ EXPORT_SYMBOL_GPL(switchdev_port_obj_del); * @cb: function to call with a filled object */ int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, - void *obj, int (*cb)(void *obj)) + struct switchdev_obj *obj, + switchdev_obj_dump_cb_t *cb) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; @@ -521,9 +523,9 @@ static int switchdev_port_vlan_dump_put(struct switchdev_vlan_dump *dump) return 0; } -static int switchdev_port_vlan_dump_cb(void *obj) +static int switchdev_port_vlan_dump_cb(struct switchdev_obj *obj) { - struct switchdev_obj_port_vlan *vlan = obj; + struct switchdev_obj_port_vlan *vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); struct switchdev_vlan_dump *dump = container_of(vlan, struct switchdev_vlan_dump, vlan); int err = 0; @@ -585,7 +587,7 @@ static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev, if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { err = switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, - &dump.vlan, + &dump.vlan.obj, switchdev_port_vlan_dump_cb); if (err) goto err_out; @@ -700,11 +702,11 @@ static int switchdev_port_br_afspec(struct net_device *dev, struct nlattr *afspec, int (*f)(struct net_device *dev, enum switchdev_obj_id id, - const void *obj)) + const struct switchdev_obj *obj)) { struct nlattr *attr; struct bridge_vlan_info *vinfo; - struct switchdev_obj_port_vlan vlan = { 0 }; + struct switchdev_obj_port_vlan vlan = { {}, 0 }; int rem; int err; @@ -725,7 +727,7 @@ static int switchdev_port_br_afspec(struct net_device *dev, vlan.vid_end = vinfo->vid; if (vlan.vid_end <= vlan.vid_begin) return -EINVAL; - err = f(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, &vlan); + err = f(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, &vlan.obj); if (err) return err; memset(&vlan, 0, sizeof(vlan)); @@ -734,7 +736,7 @@ static int switchdev_port_br_afspec(struct net_device *dev, return -EINVAL; vlan.vid_begin = vinfo->vid; vlan.vid_end = vinfo->vid; - err = f(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, &vlan); + err = f(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, &vlan.obj); if (err) return err; memset(&vlan, 0, sizeof(vlan)); @@ -824,7 +826,7 @@ int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], .vid = vid, }; - return switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb); + return switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb.obj); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_add); @@ -848,7 +850,7 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], .vid = vid, }; - return switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb); + return switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb.obj); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_del); @@ -860,9 +862,9 @@ struct switchdev_fdb_dump { int idx; }; -static int switchdev_port_fdb_dump_cb(void *obj) +static int switchdev_port_fdb_dump_cb(struct switchdev_obj *obj) { - struct switchdev_obj_port_fdb *fdb = obj; + struct switchdev_obj_port_fdb *fdb = SWITCHDEV_OBJ_PORT_FDB(obj); struct switchdev_fdb_dump *dump = container_of(fdb, struct switchdev_fdb_dump, fdb); u32 portid = NETLINK_CB(dump->cb->skb).portid; @@ -926,7 +928,7 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, .idx = idx, }; - switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &dump.fdb, + switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &dump.fdb.obj, switchdev_port_fdb_dump_cb); return dump.idx; } @@ -1033,7 +1035,8 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; - err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_IPV4_FIB, &ipv4_fib); + err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_IPV4_FIB, + &ipv4_fib.obj); if (!err) fi->fib_flags |= RTNH_F_OFFLOAD; @@ -1075,7 +1078,8 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; - err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_IPV4_FIB, &ipv4_fib); + err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_IPV4_FIB, + &ipv4_fib.obj); if (!err) fi->fib_flags &= ~RTNH_F_OFFLOAD; -- cgit v1.2.3 From 9e8f4a548ab4710002c23c94c4b1bbde91b5e335 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:46 +0200 Subject: switchdev: push object ID back to object structure Suggested-by: Scott Feldman Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 9 ++---- include/net/switchdev.h | 14 +++------ net/bridge/br_fdb.c | 4 +-- net/bridge/br_vlan.c | 8 ++--- net/dsa/slave.c | 9 ++---- net/switchdev/switchdev.c | 57 ++++++++++++++++++------------------ 6 files changed, 45 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 2a577e5b8ca5..cf91ffc6c987 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4437,7 +4437,6 @@ static int rocker_port_fdb_add(struct rocker_port *rocker_port, } static int rocker_port_obj_add(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj, struct switchdev_trans *trans) { @@ -4445,7 +4444,7 @@ static int rocker_port_obj_add(struct net_device *dev, const struct switchdev_obj_ipv4_fib *fib4; int err = 0; - switch (id) { + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: err = rocker_port_vlans_add(rocker_port, trans, SWITCHDEV_OBJ_PORT_VLAN(obj)); @@ -4511,14 +4510,13 @@ static int rocker_port_fdb_del(struct rocker_port *rocker_port, } static int rocker_port_obj_del(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj) { struct rocker_port *rocker_port = netdev_priv(dev); const struct switchdev_obj_ipv4_fib *fib4; int err = 0; - switch (id) { + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: err = rocker_port_vlans_del(rocker_port, SWITCHDEV_OBJ_PORT_VLAN(obj)); @@ -4593,14 +4591,13 @@ static int rocker_port_vlan_dump(const struct rocker_port *rocker_port, } static int rocker_port_obj_dump(struct net_device *dev, - enum switchdev_obj_id id, struct switchdev_obj *obj, switchdev_obj_dump_cb_t *cb) { const struct rocker_port *rocker_port = netdev_priv(dev); int err = 0; - switch (id) { + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_FDB: err = rocker_port_fdb_dump(rocker_port, SWITCHDEV_OBJ_PORT_FDB(obj), cb); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 3e1bd14cc0ab..89266a3e473d 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -65,6 +65,7 @@ enum switchdev_obj_id { }; struct switchdev_obj { + enum switchdev_obj_id id; }; /* SWITCHDEV_OBJ_ID_PORT_VLAN */ @@ -131,14 +132,11 @@ struct switchdev_ops { struct switchdev_attr *attr, struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj, struct switchdev_trans *trans); int (*switchdev_port_obj_del)(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj); int (*switchdev_port_obj_dump)(struct net_device *dev, - enum switchdev_obj_id id, struct switchdev_obj *obj, switchdev_obj_dump_cb_t *cb); }; @@ -170,12 +168,11 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr); -int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, +int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj); -int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, +int switchdev_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj); -int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, - struct switchdev_obj *obj, +int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, switchdev_obj_dump_cb_t *cb); int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); @@ -221,21 +218,18 @@ static inline int switchdev_port_attr_set(struct net_device *dev, } static inline int switchdev_port_obj_add(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_del(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_dump(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj, switchdev_obj_dump_cb_t *cb) { diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 34b62df08d34..7f7d55132dd5 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -134,12 +134,12 @@ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr) static void fdb_del_external_learn(struct net_bridge_fdb_entry *f) { struct switchdev_obj_port_fdb fdb = { + .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, .addr = f->addr.addr, .vid = f->vlan_id, }; - switchdev_port_obj_del(f->dst->dev, SWITCHDEV_OBJ_ID_PORT_FDB, - &fdb.obj); + switchdev_port_obj_del(f->dst->dev, &fdb.obj); } static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 0b87cf6ccb46..1a79e199ca3b 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -83,13 +83,13 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, err = vlan_vid_add(dev, br->vlan_proto, vid); } else { struct switchdev_obj_port_vlan v = { + .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .flags = flags, .vid_begin = vid, .vid_end = vid, }; - err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, - &v.obj); + err = switchdev_port_obj_add(dev, &v.obj); if (err == -EOPNOTSUPP) err = 0; } @@ -133,12 +133,12 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, vlan_vid_del(dev, br->vlan_proto, vid); } else { struct switchdev_obj_port_vlan v = { + .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .vid_begin = vid, .vid_end = vid, }; - err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, - &v.obj); + err = switchdev_port_obj_del(dev, &v.obj); if (err == -EOPNOTSUPP) err = 0; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 3f6d79d03457..5f65f929902e 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -474,7 +474,6 @@ static int dsa_slave_port_attr_set(struct net_device *dev, } static int dsa_slave_port_obj_add(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj, struct switchdev_trans *trans) { @@ -485,7 +484,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev, * supported, return -EOPNOTSUPP. */ - switch (id) { + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_FDB: err = dsa_slave_port_fdb_add(dev, SWITCHDEV_OBJ_PORT_FDB(obj), @@ -505,12 +504,11 @@ static int dsa_slave_port_obj_add(struct net_device *dev, } static int dsa_slave_port_obj_del(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj) { int err; - switch (id) { + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_FDB: err = dsa_slave_port_fdb_del(dev, SWITCHDEV_OBJ_PORT_FDB(obj)); @@ -528,13 +526,12 @@ static int dsa_slave_port_obj_del(struct net_device *dev, } static int dsa_slave_port_obj_dump(struct net_device *dev, - enum switchdev_obj_id id, struct switchdev_obj *obj, switchdev_obj_dump_cb_t *cb) { int err; - switch (id) { + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_FDB: err = dsa_slave_port_fdb_dump(dev, SWITCHDEV_OBJ_PORT_FDB(obj), diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 0402b3633100..6e4a4f9ad927 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -270,7 +270,6 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) EXPORT_SYMBOL_GPL(switchdev_port_attr_set); static int __switchdev_port_obj_add(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj, struct switchdev_trans *trans) { @@ -280,7 +279,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_add) - return ops->switchdev_port_obj_add(dev, id, obj, trans); + return ops->switchdev_port_obj_add(dev, obj, trans); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to add object on @@ -288,7 +287,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = __switchdev_port_obj_add(lower_dev, id, obj, trans); + err = __switchdev_port_obj_add(lower_dev, obj, trans); if (err) break; } @@ -309,7 +308,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, * * rtnl_lock must be held. */ -int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, +int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj) { struct switchdev_trans trans; @@ -327,7 +326,7 @@ int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, */ trans.ph_prepare = true; - err = __switchdev_port_obj_add(dev, id, obj, &trans); + err = __switchdev_port_obj_add(dev, obj, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any * resources reserved in the prepare phase are @@ -346,8 +345,8 @@ int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, */ trans.ph_prepare = false; - err = __switchdev_port_obj_add(dev, id, obj, &trans); - WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, id); + err = __switchdev_port_obj_add(dev, obj, &trans); + WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); switchdev_trans_items_warn_destroy(dev, &trans); return err; @@ -361,7 +360,7 @@ EXPORT_SYMBOL_GPL(switchdev_port_obj_add); * @id: object ID * @obj: object to delete */ -int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, +int switchdev_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj) { const struct switchdev_ops *ops = dev->switchdev_ops; @@ -370,7 +369,7 @@ int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_del) - return ops->switchdev_port_obj_del(dev, id, obj); + return ops->switchdev_port_obj_del(dev, obj); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to delete object on @@ -378,7 +377,7 @@ int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = switchdev_port_obj_del(lower_dev, id, obj); + err = switchdev_port_obj_del(lower_dev, obj); if (err) break; } @@ -395,8 +394,7 @@ EXPORT_SYMBOL_GPL(switchdev_port_obj_del); * @obj: object to dump * @cb: function to call with a filled object */ -int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, - struct switchdev_obj *obj, +int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, switchdev_obj_dump_cb_t *cb) { const struct switchdev_ops *ops = dev->switchdev_ops; @@ -405,7 +403,7 @@ int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_dump) - return ops->switchdev_port_obj_dump(dev, id, obj, cb); + return ops->switchdev_port_obj_dump(dev, obj, cb); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to dump objects on @@ -413,7 +411,7 @@ int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = switchdev_port_obj_dump(lower_dev, id, obj, cb); + err = switchdev_port_obj_dump(lower_dev, obj, cb); break; } @@ -579,6 +577,7 @@ static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev, u32 filter_mask) { struct switchdev_vlan_dump dump = { + .vlan.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .skb = skb, .filter_mask = filter_mask, }; @@ -586,8 +585,7 @@ static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev, if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { - err = switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, - &dump.vlan.obj, + err = switchdev_port_obj_dump(dev, &dump.vlan.obj, switchdev_port_vlan_dump_cb); if (err) goto err_out; @@ -701,12 +699,13 @@ static int switchdev_port_br_setlink_protinfo(struct net_device *dev, static int switchdev_port_br_afspec(struct net_device *dev, struct nlattr *afspec, int (*f)(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj)) { struct nlattr *attr; struct bridge_vlan_info *vinfo; - struct switchdev_obj_port_vlan vlan = { {}, 0 }; + struct switchdev_obj_port_vlan vlan = { + .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, + }; int rem; int err; @@ -727,7 +726,7 @@ static int switchdev_port_br_afspec(struct net_device *dev, vlan.vid_end = vinfo->vid; if (vlan.vid_end <= vlan.vid_begin) return -EINVAL; - err = f(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, &vlan.obj); + err = f(dev, &vlan.obj); if (err) return err; memset(&vlan, 0, sizeof(vlan)); @@ -736,7 +735,7 @@ static int switchdev_port_br_afspec(struct net_device *dev, return -EINVAL; vlan.vid_begin = vinfo->vid; vlan.vid_end = vinfo->vid; - err = f(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, &vlan.obj); + err = f(dev, &vlan.obj); if (err) return err; memset(&vlan, 0, sizeof(vlan)); @@ -822,11 +821,12 @@ int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], u16 vid, u16 nlm_flags) { struct switchdev_obj_port_fdb fdb = { + .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, .addr = addr, .vid = vid, }; - return switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb.obj); + return switchdev_port_obj_add(dev, &fdb.obj); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_add); @@ -846,11 +846,12 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], u16 vid) { struct switchdev_obj_port_fdb fdb = { + .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, .addr = addr, .vid = vid, }; - return switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb.obj); + return switchdev_port_obj_del(dev, &fdb.obj); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_del); @@ -922,14 +923,14 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *filter_dev, int idx) { struct switchdev_fdb_dump dump = { + .fdb.obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, .dev = dev, .skb = skb, .cb = cb, .idx = idx, }; - switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &dump.fdb.obj, - switchdev_port_fdb_dump_cb); + switchdev_port_obj_dump(dev, &dump.fdb.obj, switchdev_port_fdb_dump_cb); return dump.idx; } EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump); @@ -1008,6 +1009,7 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 nlflags, u32 tb_id) { struct switchdev_obj_ipv4_fib ipv4_fib = { + .obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB, .dst = dst, .dst_len = dst_len, .fi = fi, @@ -1035,8 +1037,7 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; - err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_IPV4_FIB, - &ipv4_fib.obj); + err = switchdev_port_obj_add(dev, &ipv4_fib.obj); if (!err) fi->fib_flags |= RTNH_F_OFFLOAD; @@ -1060,6 +1061,7 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id) { struct switchdev_obj_ipv4_fib ipv4_fib = { + .obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB, .dst = dst, .dst_len = dst_len, .fi = fi, @@ -1078,8 +1080,7 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; - err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_IPV4_FIB, - &ipv4_fib.obj); + err = switchdev_port_obj_del(dev, &ipv4_fib.obj); if (!err) fi->fib_flags &= ~RTNH_F_OFFLOAD; -- cgit v1.2.3 From a91263d520246b63c63e75ddfb072ee6a853fe15 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Sep 2015 01:41:50 +0200 Subject: ebpf: migrate bpf_prog's flags to bitfield As we need to add further flags to the bpf_prog structure, lets migrate both bools to a bitfield representation. The size of the base structure (excluding insns) remains unchanged at 40 bytes. Add also tags for the kmemchecker, so that it doesn't throw false positives. Even in case gcc would generate suboptimal code, it's not being accessed in performance critical paths. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- arch/arm/net/bpf_jit_32.c | 2 +- arch/arm64/net/bpf_jit_comp.c | 2 +- arch/mips/net/bpf_jit.c | 2 +- arch/powerpc/net/bpf_jit_comp.c | 2 +- arch/s390/net/bpf_jit_comp.c | 2 +- arch/sparc/net/bpf_jit_comp.c | 2 +- arch/x86/net/bpf_jit_comp.c | 2 +- include/linux/filter.h | 6 ++++-- kernel/bpf/core.c | 4 ++++ kernel/bpf/syscall.c | 4 ++-- net/core/filter.c | 2 +- 11 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 876060bcceeb..0df5fd561513 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1047,7 +1047,7 @@ void bpf_jit_compile(struct bpf_prog *fp) set_memory_ro((unsigned long)header, header->pages); fp->bpf_func = (void *)ctx.target; - fp->jited = true; + fp->jited = 1; out: kfree(ctx.offsets); return; diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index c047598b09e0..a44e5293c6f5 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -744,7 +744,7 @@ void bpf_int_jit_compile(struct bpf_prog *prog) set_memory_ro((unsigned long)header, header->pages); prog->bpf_func = (void *)ctx.image; - prog->jited = true; + prog->jited = 1; out: kfree(ctx.offset); } diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 0c4a133f6216..77cb27309db2 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -1251,7 +1251,7 @@ void bpf_jit_compile(struct bpf_prog *fp) bpf_jit_dump(fp->len, alloc_size, 2, ctx.target); fp->bpf_func = (void *)ctx.target; - fp->jited = true; + fp->jited = 1; out: kfree(ctx.offsets); diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 17cea18a09d3..04782164ee67 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -679,7 +679,7 @@ void bpf_jit_compile(struct bpf_prog *fp) ((u64 *)image)[1] = local_paca->kernel_toc; #endif fp->bpf_func = (void *)image; - fp->jited = true; + fp->jited = 1; } out: kfree(addrs); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index eeda051442c3..9a0c4c22e536 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1310,7 +1310,7 @@ void bpf_int_jit_compile(struct bpf_prog *fp) if (jit.prg_buf) { set_memory_ro((unsigned long)header, header->pages); fp->bpf_func = (void *) jit.prg_buf; - fp->jited = true; + fp->jited = 1; } free_addrs: kfree(jit.addrs); diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index f8b9f71b9a2b..22564f5f2364 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -812,7 +812,7 @@ cond_branch: f_offset = addrs[i + filter[i].jf]; if (image) { bpf_flush_icache(image, image + proglen); fp->bpf_func = (void *)image; - fp->jited = true; + fp->jited = 1; } out: kfree(addrs); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 70efcd0940f9..75991979f667 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1109,7 +1109,7 @@ void bpf_int_jit_compile(struct bpf_prog *prog) bpf_flush_icache(header, image + proglen); set_memory_ro((unsigned long)header, header->pages); prog->bpf_func = (void *)image; - prog->jited = true; + prog->jited = 1; } out: kfree(addrs); diff --git a/include/linux/filter.h b/include/linux/filter.h index fa2cab985e57..bad618f316d7 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -326,8 +326,10 @@ struct bpf_binary_header { struct bpf_prog { u16 pages; /* Number of allocated pages */ - bool jited; /* Is our filter JIT'ed? */ - bool gpl_compatible; /* Is our filter GPL compatible? */ + kmemcheck_bitfield_begin(meta); + u16 jited:1, /* Is our filter JIT'ed? */ + gpl_compatible:1; /* Is filter GPL compatible? */ + kmemcheck_bitfield_end(meta); u32 len; /* Number of filter blocks */ enum bpf_prog_type type; /* Type of BPF program */ struct bpf_prog_aux *aux; /* Auxiliary fields */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 67c380cfa9ca..c8855c2a7a48 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -82,6 +82,8 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) if (fp == NULL) return NULL; + kmemcheck_annotate_bitfield(fp, meta); + aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags); if (aux == NULL) { vfree(fp); @@ -110,6 +112,8 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); if (fp != NULL) { + kmemcheck_annotate_bitfield(fp, meta); + memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); fp->pages = size / PAGE_SIZE; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 35bac8e8b071..2190ab14b763 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -553,10 +553,10 @@ static int bpf_prog_load(union bpf_attr *attr) goto free_prog; prog->orig_prog = NULL; - prog->jited = false; + prog->jited = 0; atomic_set(&prog->aux->refcnt, 1); - prog->gpl_compatible = is_gpl; + prog->gpl_compatible = is_gpl ? 1 : 0; /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); diff --git a/net/core/filter.c b/net/core/filter.c index 60e3fe7c59c0..04664acb86ce 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1001,7 +1001,7 @@ static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp, int err; fp->bpf_func = NULL; - fp->jited = false; + fp->jited = 0; err = bpf_check_classic(fp->insns, fp->len); if (err) { -- cgit v1.2.3 From c46646d0484f5d08e2bede9b45034ba5b8b489cc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Sep 2015 01:41:51 +0200 Subject: sched, bpf: add helper for retrieving routing realms Using routing realms as part of the classifier is quite useful, it can be viewed as a tag for one or multiple routing entries (think of an analogy to net_cls cgroup for processes), set by user space routing daemons or via iproute2 as an indicator for traffic classifiers and later on processed in the eBPF program. Unlike actions, the classifier can inspect device flags and enable netif_keep_dst() if necessary. tc actions don't have that possibility, but in case people know what they are doing, it can be used from there as well (e.g. via devs that must keep dsts by design anyway). If a realm is set, the handler returns the non-zero realm. User space can set the full 32bit realm for the dst. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 3 ++- include/uapi/linux/bpf.h | 7 +++++++ kernel/bpf/syscall.c | 2 ++ net/core/filter.c | 22 ++++++++++++++++++++++ net/sched/cls_bpf.c | 8 ++++++-- 5 files changed, 39 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index bad618f316d7..3d5fd24b321b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -328,7 +328,8 @@ struct bpf_prog { u16 pages; /* Number of allocated pages */ kmemcheck_bitfield_begin(meta); u16 jited:1, /* Is our filter JIT'ed? */ - gpl_compatible:1; /* Is filter GPL compatible? */ + gpl_compatible:1, /* Is filter GPL compatible? */ + dst_needed:1; /* Do we need dst entry? */ kmemcheck_bitfield_end(meta); u32 len; /* Number of filter blocks */ enum bpf_prog_type type; /* Type of BPF program */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4ec0b5488294..564f1f091991 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -280,6 +280,13 @@ enum bpf_func_id { * Return: TC_ACT_REDIRECT */ BPF_FUNC_redirect, + + /** + * bpf_get_route_realm(skb) - retrieve a dst's tclassid + * @skb: pointer to skb + * Return: realm if != 0 + */ + BPF_FUNC_get_route_realm, __BPF_FUNC_MAX_ID, }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2190ab14b763..5f35f420c12f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -402,6 +402,8 @@ static void fixup_bpf_calls(struct bpf_prog *prog) */ BUG_ON(!prog->aux->ops->get_func_proto); + if (insn->imm == BPF_FUNC_get_route_realm) + prog->dst_needed = 1; if (insn->imm == BPF_FUNC_tail_call) { /* mark bpf_tail_call as different opcode * to avoid conditional branch in diff --git a/net/core/filter.c b/net/core/filter.c index 04664acb86ce..45c69ce4c847 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -49,6 +49,7 @@ #include #include #include +#include /** * sk_filter - run a packet through a socket filter @@ -1478,6 +1479,25 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +static u64 bpf_get_route_realm(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ +#ifdef CONFIG_IP_ROUTE_CLASSID + const struct dst_entry *dst; + + dst = skb_dst((struct sk_buff *) (unsigned long) r1); + if (dst) + return dst->tclassid; +#endif + return 0; +} + +static const struct bpf_func_proto bpf_get_route_realm_proto = { + .func = bpf_get_route_realm, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5) { struct sk_buff *skb = (struct sk_buff *) (long) r1; @@ -1648,6 +1668,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return bpf_get_skb_set_tunnel_key_proto(); case BPF_FUNC_redirect: return &bpf_redirect_proto; + case BPF_FUNC_get_route_realm: + return &bpf_get_route_realm_proto; default: return sk_filter_func_proto(func_id); } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 7eeffaf69c75..5faaa5425f7b 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -262,7 +262,8 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) return 0; } -static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog) +static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, + const struct tcf_proto *tp) { struct bpf_prog *fp; char *name = NULL; @@ -294,6 +295,9 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog) prog->bpf_name = name; prog->filter = fp; + if (fp->dst_needed) + netif_keep_dst(qdisc_dev(tp->q)); + return 0; } @@ -330,7 +334,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, prog->exts_integrated = have_exts; ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : - cls_bpf_prog_from_efd(tb, prog); + cls_bpf_prog_from_efd(tb, prog, tp); if (ret < 0) { tcf_exts_destroy(&exts); return ret; -- cgit v1.2.3 From f3a6bd393c2c5d0e6b16624ba99a1c5fa07bdb0b Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 30 Sep 2015 15:15:52 +0900 Subject: phylib: Add phy_set_max_speed helper Add a helper to allow ethernet drivers to limit the speed of a phy (that they are attached to). This mainly involves factoring out the business-end of of_set_phy_supported() and exporting a new symbol. This code seems to be open coded in several places, in several different variants. It is is envisaged that this will be used in situations where setting the "max-speed" property in DT is not appropriate, e.g. because the maximum speed is not a property of the phy hardware. Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 59 ++++++++++++++++++++++++++++++-------------- include/linux/phy.h | 1 + 2 files changed, 41 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index f761288abe66..383389146099 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1239,6 +1239,44 @@ static int gen10g_resume(struct phy_device *phydev) return 0; } +static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) +{ + /* The default values for phydev->supported are provided by the PHY + * driver "features" member, we want to reset to sane defaults first + * before supporting higher speeds. + */ + phydev->supported &= PHY_DEFAULT_FEATURES; + + switch (max_speed) { + default: + return -ENOTSUPP; + case SPEED_1000: + phydev->supported |= PHY_1000BT_FEATURES; + /* fall through */ + case SPEED_100: + phydev->supported |= PHY_100BT_FEATURES; + /* fall through */ + case SPEED_10: + phydev->supported |= PHY_10BT_FEATURES; + } + + return 0; +} + +int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) +{ + int err; + + err = __set_phy_supported(phydev, max_speed); + if (err) + return err; + + phydev->advertising = phydev->supported; + + return 0; +} +EXPORT_SYMBOL(phy_set_max_speed); + static void of_set_phy_supported(struct phy_device *phydev) { struct device_node *node = phydev->dev.of_node; @@ -1250,25 +1288,8 @@ static void of_set_phy_supported(struct phy_device *phydev) if (!node) return; - if (!of_property_read_u32(node, "max-speed", &max_speed)) { - /* The default values for phydev->supported are provided by the PHY - * driver "features" member, we want to reset to sane defaults fist - * before supporting higher speeds. - */ - phydev->supported &= PHY_DEFAULT_FEATURES; - - switch (max_speed) { - default: - return; - - case SPEED_1000: - phydev->supported |= PHY_1000BT_FEATURES; - case SPEED_100: - phydev->supported |= PHY_100BT_FEATURES; - case SPEED_10: - phydev->supported |= PHY_10BT_FEATURES; - } - } + if (!of_property_read_u32(node, "max-speed", &max_speed)) + __set_phy_supported(phydev, max_speed); } /** diff --git a/include/linux/phy.h b/include/linux/phy.h index 4a4e3a092337..4c477e6ece33 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -798,6 +798,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); void phy_device_free(struct phy_device *phydev); +int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From e96f78ab2703f3b0d512f6b469bc685d2ef20475 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 3 Oct 2015 06:27:28 -0700 Subject: tcp/dccp: add SLAB_DESTROY_BY_RCU flag for request sockets Before letting request sockets being put in TCP/DCCP regular ehash table, we need to add either : - SLAB_DESTROY_BY_RCU flag to their kmem_cache - add RCU grace period before freeing them. Since we carefully respected the SLAB_DESTROY_BY_RCU protocol like ESTABLISH and TIMEWAIT sockets, use it here. req_prot_init() being only used by TCP and DCCP, I did not add a new slab_flags into their rsk_prot, but reuse prot->slab_flags Since all reqsk_alloc() users are correctly dealing with a failure, add the __GFP_NOWARN flag to avoid traces under pressure. Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 4 +++- net/core/sock.c | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index bae6936d75c4..dd423d840852 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -82,7 +82,9 @@ static inline struct sock *req_to_sk(struct request_sock *req) static inline struct request_sock * reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) { - struct request_sock *req = kmem_cache_alloc(ops->slab, GFP_ATOMIC); + struct request_sock *req; + + req = kmem_cache_alloc(ops->slab, GFP_ATOMIC | __GFP_NOWARN); if (req) { req->rsk_ops = ops; diff --git a/net/core/sock.c b/net/core/sock.c index 3307c02244d3..7dd1263e4c24 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2758,7 +2758,7 @@ static int req_prot_init(const struct proto *prot) rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name, rsk_prot->obj_size, 0, - 0, NULL); + prot->slab_flags, NULL); if (!rsk_prot->slab) { pr_crit("%s: Can't create request sock SLAB cache!\n", -- cgit v1.2.3 From 7910228b6bb35f3c8e0bc72a8d84c29616cb1b90 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:28 +0200 Subject: bridge: netlink: add group_fwd_mask support Add IFLA_BR_GROUP_FWD_MASK attribute to allow setting and retrieving the group_fwd_mask via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 14 +++++++++++++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 3a5f263cfc2f..f7f480613555 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -232,6 +232,7 @@ enum { IFLA_BR_PRIORITY, IFLA_BR_VLAN_FILTERING, IFLA_BR_VLAN_PROTOCOL, + IFLA_BR_GROUP_FWD_MASK, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index c3186198d46d..39b201a2bc12 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -764,6 +764,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, [IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 }, [IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 }, + [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -829,6 +830,14 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], } #endif + if (data[IFLA_BR_GROUP_FWD_MASK]) { + u16 fwd_mask = nla_get_u16(data[IFLA_BR_GROUP_FWD_MASK]); + + if (fwd_mask & BR_GROUPFWD_RESTRICTED) + return -EINVAL; + br->group_fwd_mask = fwd_mask; + } + return 0; } @@ -844,6 +853,7 @@ static size_t br_get_size(const struct net_device *brdev) #ifdef CONFIG_BRIDGE_VLAN_FILTERING nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */ #endif + nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ 0; } @@ -856,6 +866,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) u32 ageing_time = jiffies_to_clock_t(br->ageing_time); u32 stp_enabled = br->stp_enabled; u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; + u16 group_fwd_mask = br->group_fwd_mask; u8 vlan_enabled = br_vlan_enabled(br); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || @@ -864,7 +875,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) || nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || - nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled)) + nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || + nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, group_fwd_mask)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From 5127c81f84de0dd643d5840a2c7de571bc6aceb3 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:29 +0200 Subject: bridge: netlink: export root id Add IFLA_BR_ROOT_ID and export br->designated_root via netlink. For this purpose add struct ifla_bridge_id that would represent struct bridge_id. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 6 ++++++ net/bridge/br_netlink.c | 9 ++++++++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index f7f480613555..03814371df44 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -233,11 +233,17 @@ enum { IFLA_BR_VLAN_FILTERING, IFLA_BR_VLAN_PROTOCOL, IFLA_BR_GROUP_FWD_MASK, + IFLA_BR_ROOT_ID, __IFLA_BR_MAX, }; #define IFLA_BR_MAX (__IFLA_BR_MAX - 1) +struct ifla_bridge_id { + __u8 prio[2]; + __u8 addr[6]; /* ETH_ALEN */ +}; + enum { BRIDGE_MODE_UNSPEC, BRIDGE_MODE_HAIRPIN, diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 39b201a2bc12..7a3692469db6 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -854,6 +854,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */ #endif nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ + nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ 0; } @@ -868,6 +869,11 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; u16 group_fwd_mask = br->group_fwd_mask; u8 vlan_enabled = br_vlan_enabled(br); + struct ifla_bridge_id root_id; + + memset(&root_id, 0, sizeof(root_id)); + memcpy(root_id.prio, br->designated_root.prio, sizeof(root_id.prio)); + memcpy(root_id.addr, br->designated_root.addr, sizeof(root_id.addr)); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || @@ -876,7 +882,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || - nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, group_fwd_mask)) + nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, group_fwd_mask) || + nla_put(skb, IFLA_BR_ROOT_ID, sizeof(root_id), &root_id)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From 7599a2201fc71cdca16a92d350f14cce8730e03f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:30 +0200 Subject: bridge: netlink: export bridge id Add IFLA_BR_BRIDGE_ID and export br->bridge_id via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 9 +++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 03814371df44..748495438a8b 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -234,6 +234,7 @@ enum { IFLA_BR_VLAN_PROTOCOL, IFLA_BR_GROUP_FWD_MASK, IFLA_BR_ROOT_ID, + IFLA_BR_BRIDGE_ID, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 7a3692469db6..a63f944a7f12 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -855,6 +855,7 @@ static size_t br_get_size(const struct net_device *brdev) #endif nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ 0; } @@ -869,11 +870,14 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; u16 group_fwd_mask = br->group_fwd_mask; u8 vlan_enabled = br_vlan_enabled(br); - struct ifla_bridge_id root_id; + struct ifla_bridge_id root_id, bridge_id; + memset(&bridge_id, 0, sizeof(bridge_id)); memset(&root_id, 0, sizeof(root_id)); memcpy(root_id.prio, br->designated_root.prio, sizeof(root_id.prio)); memcpy(root_id.addr, br->designated_root.addr, sizeof(root_id.addr)); + memcpy(bridge_id.prio, br->bridge_id.prio, sizeof(bridge_id.prio)); + memcpy(bridge_id.addr, br->bridge_id.addr, sizeof(bridge_id.addr)); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || @@ -883,7 +887,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, group_fwd_mask) || - nla_put(skb, IFLA_BR_ROOT_ID, sizeof(root_id), &root_id)) + nla_put(skb, IFLA_BR_ROOT_ID, sizeof(root_id), &root_id) || + nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(bridge_id), &bridge_id)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From 8762ba680fe8d41b444fc92f90ce7194b2b8303b Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:31 +0200 Subject: bridge: netlink: export root port Add IFLA_BR_ROOT_PORT and export it via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 748495438a8b..172268a5767d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -235,6 +235,7 @@ enum { IFLA_BR_GROUP_FWD_MASK, IFLA_BR_ROOT_ID, IFLA_BR_BRIDGE_ID, + IFLA_BR_ROOT_PORT, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a63f944a7f12..652db1ca0acc 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -856,6 +856,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ + nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ 0; } @@ -888,7 +889,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, group_fwd_mask) || nla_put(skb, IFLA_BR_ROOT_ID, sizeof(root_id), &root_id) || - nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(bridge_id), &bridge_id)) + nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(bridge_id), &bridge_id) || + nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From 684dd248bee8c73eadb90706123bf1494d3218b8 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:32 +0200 Subject: bridge: netlink: export root path cost Add IFLA_BR_ROOT_PATH_COST and export it via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 172268a5767d..7d7236d143fb 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -236,6 +236,7 @@ enum { IFLA_BR_ROOT_ID, IFLA_BR_BRIDGE_ID, IFLA_BR_ROOT_PORT, + IFLA_BR_ROOT_PATH_COST, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 652db1ca0acc..cd0488b689d4 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -857,6 +857,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ 0; } @@ -890,7 +891,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, group_fwd_mask) || nla_put(skb, IFLA_BR_ROOT_ID, sizeof(root_id), &root_id) || nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(bridge_id), &bridge_id) || - nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port)) + nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port) || + nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From ed4163098e3090bb7b51421bde977e355275a554 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:33 +0200 Subject: bridge: netlink: export topology_change and topology_change_detected Add IFLA_BR_TOPOLOGY_CHANGE and IFLA_BR_TOPOLOGY_CHANGE_DETECTED and export them via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ net/bridge/br_netlink.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 7d7236d143fb..b00286ca1bfe 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -237,6 +237,8 @@ enum { IFLA_BR_BRIDGE_ID, IFLA_BR_ROOT_PORT, IFLA_BR_ROOT_PATH_COST, + IFLA_BR_TOPOLOGY_CHANGE, + IFLA_BR_TOPOLOGY_CHANGE_DETECTED, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index cd0488b689d4..8bcaa5171f35 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -858,6 +858,8 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ 0; } @@ -892,7 +894,10 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put(skb, IFLA_BR_ROOT_ID, sizeof(root_id), &root_id) || nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(bridge_id), &bridge_id) || nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port) || - nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost)) + nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost) || + nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE, br->topology_change) || + nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, + br->topology_change_detected)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From d76bd14e0f759040efc8ce142dd6d1f9eca33d39 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:34 +0200 Subject: bridge: netlink: export all timers Export the following bridge timers (also exported via sysfs): IFLA_BR_HELLO_TIMER, IFLA_BR_TCN_TIMER, IFLA_BR_TOPOLOGY_CHANGE_TIMER, IFLA_BR_GC_TIMER via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 4 ++++ net/bridge/br_netlink.c | 16 +++++++++++++++- 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b00286ca1bfe..a1e33282ab9d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -239,6 +239,10 @@ enum { IFLA_BR_ROOT_PATH_COST, IFLA_BR_TOPOLOGY_CHANGE, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, + IFLA_BR_HELLO_TIMER, + IFLA_BR_TCN_TIMER, + IFLA_BR_TOPOLOGY_CHANGE_TIMER, + IFLA_BR_GC_TIMER, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 8bcaa5171f35..755bfe0ab404 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -860,12 +860,17 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_HELLO_TIMER */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_GC_TIMER */ 0; } static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) { struct net_bridge *br = netdev_priv(brdev); + u64 hello_timer, tcn_timer, topology_change_timer, gc_timer; u32 forward_delay = jiffies_to_clock_t(br->forward_delay); u32 hello_time = jiffies_to_clock_t(br->hello_time); u32 age_time = jiffies_to_clock_t(br->max_age); @@ -882,6 +887,10 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) memcpy(root_id.addr, br->designated_root.addr, sizeof(root_id.addr)); memcpy(bridge_id.prio, br->bridge_id.prio, sizeof(bridge_id.prio)); memcpy(bridge_id.addr, br->bridge_id.addr, sizeof(bridge_id.addr)); + hello_timer = br_timer_value(&br->hello_timer); + tcn_timer = br_timer_value(&br->tcn_timer); + topology_change_timer = br_timer_value(&br->topology_change_timer); + gc_timer = br_timer_value(&br->gc_timer); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || @@ -897,7 +906,12 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE, br->topology_change) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, - br->topology_change_detected)) + br->topology_change_detected) || + nla_put_u64(skb, IFLA_BR_HELLO_TIMER, hello_timer) || + nla_put_u64(skb, IFLA_BR_TCN_TIMER, tcn_timer) || + nla_put_u64(skb, IFLA_BR_TOPOLOGY_CHANGE_TIMER, + topology_change_timer) || + nla_put_u64(skb, IFLA_BR_GC_TIMER, gc_timer)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From 111189abc5c3f0ea6f516a6c3e8d8c3a2cf391d9 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:35 +0200 Subject: bridge: netlink: add group_addr support Add IFLA_BR_GROUP_ADDR attribute to allow setting and retrieving the group_addr via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 25 ++++++++++++++++++++++++- 2 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index a1e33282ab9d..eaeaac17dfdd 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -243,6 +243,7 @@ enum { IFLA_BR_TCN_TIMER, IFLA_BR_TOPOLOGY_CHANGE_TIMER, IFLA_BR_GC_TIMER, + IFLA_BR_GROUP_ADDR, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 755bfe0ab404..a05a4306d42d 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -765,6 +765,8 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 }, [IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 }, [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 }, + [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY, + .len = ETH_ALEN }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -838,6 +840,25 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br->group_fwd_mask = fwd_mask; } + if (data[IFLA_BR_GROUP_ADDR]) { + u8 new_addr[ETH_ALEN]; + + if (nla_len(data[IFLA_BR_GROUP_ADDR]) != ETH_ALEN) + return -EINVAL; + memcpy(new_addr, nla_data(data[IFLA_BR_GROUP_ADDR]), ETH_ALEN); + if (!is_link_local_ether_addr(new_addr)) + return -EINVAL; + if (new_addr[5] == 1 || /* 802.3x Pause address */ + new_addr[5] == 2 || /* 802.3ad Slow protocols */ + new_addr[5] == 3) /* 802.1X PAE address */ + return -EINVAL; + spin_lock_bh(&br->lock); + memcpy(br->group_addr, new_addr, sizeof(br->group_addr)); + spin_unlock_bh(&br->lock); + br->group_addr_set = true; + br_recalculate_fwd_mask(br); + } + return 0; } @@ -864,6 +885,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */ nla_total_size(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ nla_total_size(sizeof(u64)) + /* IFLA_BR_GC_TIMER */ + nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */ 0; } @@ -911,7 +933,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u64(skb, IFLA_BR_TCN_TIMER, tcn_timer) || nla_put_u64(skb, IFLA_BR_TOPOLOGY_CHANGE_TIMER, topology_change_timer) || - nla_put_u64(skb, IFLA_BR_GC_TIMER, gc_timer)) + nla_put_u64(skb, IFLA_BR_GC_TIMER, gc_timer) || + nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From 150217c688217e549ef8a36ea4f6718977373765 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:36 +0200 Subject: bridge: netlink: add fdb flush Simple attribute that flushes the bridge's fdb. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index eaeaac17dfdd..9ca9bf8bfe04 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -244,6 +244,7 @@ enum { IFLA_BR_TOPOLOGY_CHANGE_TIMER, IFLA_BR_GC_TIMER, IFLA_BR_GROUP_ADDR, + IFLA_BR_FDB_FLUSH, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a05a4306d42d..5853c5737006 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -859,6 +859,9 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br_recalculate_fwd_mask(br); } + if (data[IFLA_BR_FDB_FLUSH]) + br_fdb_flush(br); + return 0; } -- cgit v1.2.3 From a9a6bc70f5f70b3835b081e401b469b88c7c8a3a Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:37 +0200 Subject: bridge: netlink: add support for multicast_router Add IFLA_BR_MCAST_ROUTER to allow setting and retrieving br->multicast_router when igmp snooping is enabled. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 9ca9bf8bfe04..5d2c92973afe 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -245,6 +245,7 @@ enum { IFLA_BR_GC_TIMER, IFLA_BR_GROUP_ADDR, IFLA_BR_FDB_FLUSH, + IFLA_BR_MCAST_ROUTER, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 5853c5737006..f4df609c1ad9 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -767,6 +767,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN }, + [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -862,6 +863,16 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (data[IFLA_BR_FDB_FLUSH]) br_fdb_flush(br); +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (data[IFLA_BR_MCAST_ROUTER]) { + u8 multicast_router = nla_get_u8(data[IFLA_BR_MCAST_ROUTER]); + + err = br_multicast_set_router(br, multicast_router); + if (err) + return err; + } +#endif + return 0; } @@ -889,6 +900,9 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ nla_total_size(sizeof(u64)) + /* IFLA_BR_GC_TIMER */ nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */ +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ +#endif 0; } @@ -945,6 +959,11 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) return -EMSGSIZE; #endif +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router)) + return -EMSGSIZE; +#endif + return 0; } -- cgit v1.2.3 From 89126327f921bd278c72284d38428443bbef344f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:38 +0200 Subject: bridge: netlink: add support for multicast_snooping Add IFLA_BR_MCAST_SNOOPING to allow enabling/disabling multicast snooping via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5d2c92973afe..22cb395a713d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -246,6 +246,7 @@ enum { IFLA_BR_GROUP_ADDR, IFLA_BR_FDB_FLUSH, IFLA_BR_MCAST_ROUTER, + IFLA_BR_MCAST_SNOOPING, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index f4df609c1ad9..25e1c66d70f1 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -768,6 +768,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, + [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -871,6 +872,14 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (err) return err; } + + if (data[IFLA_BR_MCAST_SNOOPING]) { + u8 mcast_snooping = nla_get_u8(data[IFLA_BR_MCAST_SNOOPING]); + + err = br_multicast_toggle(br, mcast_snooping); + if (err) + return err; + } #endif return 0; @@ -902,6 +911,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ #endif 0; } @@ -960,7 +970,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) #endif #ifdef CONFIG_BRIDGE_IGMP_SNOOPING - if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router)) + if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router) || + nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled)) return -EMSGSIZE; #endif -- cgit v1.2.3 From 295141d9049bdf4fa316b325d2e2501b210dbe06 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:39 +0200 Subject: bridge: netlink: add support for multicast_query_use_ifaddr Add IFLA_BR_MCAST_QUERY_USE_IFADDR to allow setting/getting br->multicast_query_use_ifaddr via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 22cb395a713d..7090b3977eac 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -247,6 +247,7 @@ enum { IFLA_BR_FDB_FLUSH, IFLA_BR_MCAST_ROUTER, IFLA_BR_MCAST_SNOOPING, + IFLA_BR_MCAST_QUERY_USE_IFADDR, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 25e1c66d70f1..12ef844273a7 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -769,6 +769,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { .len = ETH_ALEN }, [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, + [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -880,6 +881,13 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (err) return err; } + + if (data[IFLA_BR_MCAST_QUERY_USE_IFADDR]) { + u8 val; + + val = nla_get_u8(data[IFLA_BR_MCAST_QUERY_USE_IFADDR]); + br->multicast_query_use_ifaddr = !!val; + } #endif return 0; @@ -912,6 +920,7 @@ static size_t br_get_size(const struct net_device *brdev) #ifdef CONFIG_BRIDGE_IGMP_SNOOPING nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ #endif 0; } @@ -971,7 +980,9 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router) || - nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled)) + nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled) || + nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR, + br->multicast_query_use_ifaddr)) return -EMSGSIZE; #endif -- cgit v1.2.3 From ba062d7cc6a09a8194eba975d5ee635378a55bfc Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:40 +0200 Subject: bridge: netlink: add support for multicast_querier Add IFLA_BR_MCAST_QUERIER to allow setting/getting br->multicast_querier via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 7090b3977eac..fe5fac5c2a7f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -248,6 +248,7 @@ enum { IFLA_BR_MCAST_ROUTER, IFLA_BR_MCAST_SNOOPING, IFLA_BR_MCAST_QUERY_USE_IFADDR, + IFLA_BR_MCAST_QUERIER, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 12ef844273a7..e21296dacf42 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -770,6 +770,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, + [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -888,6 +889,14 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], val = nla_get_u8(data[IFLA_BR_MCAST_QUERY_USE_IFADDR]); br->multicast_query_use_ifaddr = !!val; } + + if (data[IFLA_BR_MCAST_QUERIER]) { + u8 mcast_querier = nla_get_u8(data[IFLA_BR_MCAST_QUERIER]); + + err = br_multicast_set_querier(br, mcast_querier); + if (err) + return err; + } #endif return 0; @@ -921,6 +930,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ #endif 0; } @@ -982,7 +992,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router) || nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled) || nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR, - br->multicast_query_use_ifaddr)) + br->multicast_query_use_ifaddr) || + nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier)) return -EMSGSIZE; #endif -- cgit v1.2.3 From 431db3c050af0be72b3b01fa7484982f35cb268f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:41 +0200 Subject: bridge: netlink: add support for igmp's hash_elasticity Add IFLA_BR_MCAST_HASH_ELASTICITY to allow setting/getting br->hash_elasticity via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 12 +++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index fe5fac5c2a7f..ca7ca766d8af 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -249,6 +249,7 @@ enum { IFLA_BR_MCAST_SNOOPING, IFLA_BR_MCAST_QUERY_USE_IFADDR, IFLA_BR_MCAST_QUERIER, + IFLA_BR_MCAST_HASH_ELASTICITY, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e21296dacf42..b210a639e8d1 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -771,6 +771,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, + [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -897,6 +898,12 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (err) return err; } + + if (data[IFLA_BR_MCAST_HASH_ELASTICITY]) { + u32 val = nla_get_u32(data[IFLA_BR_MCAST_HASH_ELASTICITY]); + + br->hash_elasticity = val; + } #endif return 0; @@ -931,6 +938,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ #endif 0; } @@ -993,7 +1001,9 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled) || nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR, br->multicast_query_use_ifaddr) || - nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier)) + nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier) || + nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, + br->hash_elasticity)) return -EMSGSIZE; #endif -- cgit v1.2.3 From 858079fdae16421d4908722140346cfdddedf343 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:42 +0200 Subject: bridge: netlink: add support for igmp's hash_max Add IFLA_BR_MCAST_HASH_MAX to allow setting/getting br->hash_max via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ca7ca766d8af..10a44a735512 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -250,6 +250,7 @@ enum { IFLA_BR_MCAST_QUERY_USE_IFADDR, IFLA_BR_MCAST_QUERIER, IFLA_BR_MCAST_HASH_ELASTICITY, + IFLA_BR_MCAST_HASH_MAX, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index b210a639e8d1..d6b61b0eeada 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -772,6 +772,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, + [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -904,6 +905,14 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br->hash_elasticity = val; } + + if (data[IFLA_BR_MCAST_HASH_MAX]) { + u32 hash_max = nla_get_u32(data[IFLA_BR_MCAST_HASH_MAX]); + + err = br_multicast_set_hash_max(br, hash_max); + if (err) + return err; + } #endif return 0; @@ -939,6 +948,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ #endif 0; } @@ -1003,7 +1013,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) br->multicast_query_use_ifaddr) || nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, - br->hash_elasticity)) + br->hash_elasticity) || + nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max)) return -EMSGSIZE; #endif -- cgit v1.2.3 From 79b859f573d6afa64e328cc7f50ad7a209e0c92d Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:43 +0200 Subject: bridge: netlink: add support for multicast_last_member_count Add IFLA_BR_MCAST_LAST_MEMBER_CNT to allow setting/getting br->multicast_last_member_count via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 12 +++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 10a44a735512..5409a461e47e 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -251,6 +251,7 @@ enum { IFLA_BR_MCAST_QUERIER, IFLA_BR_MCAST_HASH_ELASTICITY, IFLA_BR_MCAST_HASH_MAX, + IFLA_BR_MCAST_LAST_MEMBER_CNT, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index d6b61b0eeada..cf6ccaea8180 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -773,6 +773,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, + [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -913,6 +914,12 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (err) return err; } + + if (data[IFLA_BR_MCAST_LAST_MEMBER_CNT]) { + u32 val = nla_get_u32(data[IFLA_BR_MCAST_LAST_MEMBER_CNT]); + + br->multicast_last_member_count = val; + } #endif return 0; @@ -949,6 +956,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ #endif 0; } @@ -1014,7 +1022,9 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, br->hash_elasticity) || - nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max)) + nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) || + nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT, + br->multicast_last_member_count)) return -EMSGSIZE; #endif -- cgit v1.2.3 From b89e6babad4b7ca7298ad863c6c83dc76b0abdef Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:44 +0200 Subject: bridge: netlink: add support for multicast_startup_query_count Add IFLA_BR_MCAST_STARTUP_QUERY_CNT to allow setting/getting br->multicast_startup_query_count via netlink. Also align the ifla comments. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 22 ++++++++++++++++------ 2 files changed, 17 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5409a461e47e..fd841b5269c1 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -252,6 +252,7 @@ enum { IFLA_BR_MCAST_HASH_ELASTICITY, IFLA_BR_MCAST_HASH_MAX, IFLA_BR_MCAST_LAST_MEMBER_CNT, + IFLA_BR_MCAST_STARTUP_QUERY_CNT, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index cf6ccaea8180..6744e30120af 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -774,6 +774,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, + [IFLA_BR_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -920,6 +921,12 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br->multicast_last_member_count = val; } + + if (data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]) { + u32 val = nla_get_u32(data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]); + + br->multicast_startup_query_count = val; + } #endif return 0; @@ -942,8 +949,8 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ - nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ - nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ nla_total_size(sizeof(u64)) + /* IFLA_BR_HELLO_TIMER */ nla_total_size(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */ nla_total_size(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ @@ -954,9 +961,10 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ - nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ - nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ - nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_STARTUP_QUERY_CNT */ #endif 0; } @@ -1024,7 +1032,9 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) br->hash_elasticity) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) || nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT, - br->multicast_last_member_count)) + br->multicast_last_member_count) || + nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT, + br->multicast_startup_query_count)) return -EMSGSIZE; #endif -- cgit v1.2.3 From 7e4df51eb35deedd3ba8d4db92a6c36fb7eff90a Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:45 +0200 Subject: bridge: netlink: add support for igmp's intervals Add support to set/get all of the igmp's configurable intervals via netlink. These currently are: IFLA_BR_MCAST_LAST_MEMBER_INTVL IFLA_BR_MCAST_MEMBERSHIP_INTVL IFLA_BR_MCAST_QUERIER_INTVL IFLA_BR_MCAST_QUERY_INTVL IFLA_BR_MCAST_QUERY_RESPONSE_INTVL IFLA_BR_MCAST_STARTUP_QUERY_INTVL Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 6 ++++ net/bridge/br_netlink.c | 70 +++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 75 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index fd841b5269c1..b8c88aa19fef 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -253,6 +253,12 @@ enum { IFLA_BR_MCAST_HASH_MAX, IFLA_BR_MCAST_LAST_MEMBER_CNT, IFLA_BR_MCAST_STARTUP_QUERY_CNT, + IFLA_BR_MCAST_LAST_MEMBER_INTVL, + IFLA_BR_MCAST_MEMBERSHIP_INTVL, + IFLA_BR_MCAST_QUERIER_INTVL, + IFLA_BR_MCAST_QUERY_INTVL, + IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, + IFLA_BR_MCAST_STARTUP_QUERY_INTVL, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 6744e30120af..30def4fb5901 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -775,6 +775,12 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 }, + [IFLA_BR_MCAST_LAST_MEMBER_INTVL] = { .type = NLA_U64 }, + [IFLA_BR_MCAST_MEMBERSHIP_INTVL] = { .type = NLA_U64 }, + [IFLA_BR_MCAST_QUERIER_INTVL] = { .type = NLA_U64 }, + [IFLA_BR_MCAST_QUERY_INTVL] = { .type = NLA_U64 }, + [IFLA_BR_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 }, + [IFLA_BR_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -927,6 +933,42 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br->multicast_startup_query_count = val; } + + if (data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]) { + u64 val = nla_get_u64(data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]); + + br->multicast_last_member_interval = clock_t_to_jiffies(val); + } + + if (data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]) { + u64 val = nla_get_u64(data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]); + + br->multicast_membership_interval = clock_t_to_jiffies(val); + } + + if (data[IFLA_BR_MCAST_QUERIER_INTVL]) { + u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERIER_INTVL]); + + br->multicast_querier_interval = clock_t_to_jiffies(val); + } + + if (data[IFLA_BR_MCAST_QUERY_INTVL]) { + u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_INTVL]); + + br->multicast_query_interval = clock_t_to_jiffies(val); + } + + if (data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]) { + u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]); + + br->multicast_query_response_interval = clock_t_to_jiffies(val); + } + + if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) { + u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]); + + br->multicast_startup_query_interval = clock_t_to_jiffies(val); + } #endif return 0; @@ -965,6 +1007,12 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_STARTUP_QUERY_CNT */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_LAST_MEMBER_INTVL */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_MEMBERSHIP_INTVL */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERIER_INTVL */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */ #endif 0; } @@ -972,7 +1020,7 @@ static size_t br_get_size(const struct net_device *brdev) static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) { struct net_bridge *br = netdev_priv(brdev); - u64 hello_timer, tcn_timer, topology_change_timer, gc_timer; + u64 hello_timer, tcn_timer, topology_change_timer, gc_timer, clockval; u32 forward_delay = jiffies_to_clock_t(br->forward_delay); u32 hello_time = jiffies_to_clock_t(br->hello_time); u32 age_time = jiffies_to_clock_t(br->max_age); @@ -993,6 +1041,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) tcn_timer = br_timer_value(&br->tcn_timer); topology_change_timer = br_timer_value(&br->topology_change_timer); gc_timer = br_timer_value(&br->gc_timer); + clockval = 0; if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || @@ -1036,6 +1085,25 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT, br->multicast_startup_query_count)) return -EMSGSIZE; + + clockval = jiffies_to_clock_t(br->multicast_last_member_interval); + if (nla_put_u64(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval)) + return -EMSGSIZE; + clockval = jiffies_to_clock_t(br->multicast_membership_interval); + if (nla_put_u64(skb, IFLA_BR_MCAST_MEMBERSHIP_INTVL, clockval)) + return -EMSGSIZE; + clockval = jiffies_to_clock_t(br->multicast_querier_interval); + if (nla_put_u64(skb, IFLA_BR_MCAST_QUERIER_INTVL, clockval)) + return -EMSGSIZE; + clockval = jiffies_to_clock_t(br->multicast_query_interval); + if (nla_put_u64(skb, IFLA_BR_MCAST_QUERY_INTVL, clockval)) + return -EMSGSIZE; + clockval = jiffies_to_clock_t(br->multicast_query_response_interval); + if (nla_put_u64(skb, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, clockval)) + return -EMSGSIZE; + clockval = jiffies_to_clock_t(br->multicast_startup_query_interval); + if (nla_put_u64(skb, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, clockval)) + return -EMSGSIZE; #endif return 0; -- cgit v1.2.3 From 93870cc02a0af4392401713d14235accafc752bc Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:46 +0200 Subject: bridge: netlink: add support for netfilter tables config Add support to allow getting/setting netfilter tables settings. Currently these are IFLA_BR_NF_CALL_IPTABLES, IFLA_BR_NF_CALL_IP6TABLES and IFLA_BR_NF_CALL_ARPTABLES. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 3 +++ net/bridge/br_netlink.c | 37 ++++++++++++++++++++++++++++++++++++- 2 files changed, 39 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b8c88aa19fef..0200bed6e5d6 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -259,6 +259,9 @@ enum { IFLA_BR_MCAST_QUERY_INTVL, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, + IFLA_BR_NF_CALL_IPTABLES, + IFLA_BR_NF_CALL_IP6TABLES, + IFLA_BR_NF_CALL_ARPTABLES, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 30def4fb5901..fd37caf02b51 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -781,6 +781,9 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 }, + [IFLA_BR_NF_CALL_IPTABLES] = { .type = NLA_U8 }, + [IFLA_BR_NF_CALL_IP6TABLES] = { .type = NLA_U8 }, + [IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -970,6 +973,25 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br->multicast_startup_query_interval = clock_t_to_jiffies(val); } #endif +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + if (data[IFLA_BR_NF_CALL_IPTABLES]) { + u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IPTABLES]); + + br->nf_call_iptables = val ? true : false; + } + + if (data[IFLA_BR_NF_CALL_IP6TABLES]) { + u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IP6TABLES]); + + br->nf_call_ip6tables = val ? true : false; + } + + if (data[IFLA_BR_NF_CALL_ARPTABLES]) { + u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_ARPTABLES]); + + br->nf_call_arptables = val ? true : false; + } +#endif return 0; } @@ -1013,6 +1035,11 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */ nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */ nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */ +#endif +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IPTABLES */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IP6TABLES */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_ARPTABLES */ #endif 0; } @@ -1070,7 +1097,6 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto)) return -EMSGSIZE; #endif - #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router) || nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled) || @@ -1105,6 +1131,15 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) if (nla_put_u64(skb, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, clockval)) return -EMSGSIZE; #endif +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + if (nla_put_u8(skb, IFLA_BR_NF_CALL_IPTABLES, + br->nf_call_iptables ? 1 : 0) || + nla_put_u8(skb, IFLA_BR_NF_CALL_IP6TABLES, + br->nf_call_ip6tables ? 1 : 0) || + nla_put_u8(skb, IFLA_BR_NF_CALL_ARPTABLES, + br->nf_call_arptables ? 1 : 0)) + return -EMSGSIZE; +#endif return 0; } -- cgit v1.2.3 From 0f963b7592ef9e054974b6672b86ec1edd84b4bc Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:47 +0200 Subject: bridge: netlink: add support for default_pvid Add IFLA_BR_VLAN_DEFAULT_PVID to allow setting/getting bridge's default_pvid via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 13 ++++++++++++- net/bridge/br_private.h | 1 + net/bridge/br_vlan.c | 14 +++++++------- 4 files changed, 21 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 0200bed6e5d6..c5b15bfeabe2 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -262,6 +262,7 @@ enum { IFLA_BR_NF_CALL_IPTABLES, IFLA_BR_NF_CALL_IP6TABLES, IFLA_BR_NF_CALL_ARPTABLES, + IFLA_BR_VLAN_DEFAULT_PVID, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index fd37caf02b51..70efe2edde2b 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -784,6 +784,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_NF_CALL_IPTABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_IP6TABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 }, + [IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -847,6 +848,14 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (err) return err; } + + if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { + __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); + + err = __br_vlan_set_default_pvid(br, defpvid); + if (err) + return err; + } #endif if (data[IFLA_BR_GROUP_FWD_MASK]) { @@ -1007,6 +1016,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_FILTERING */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */ + nla_total_size(sizeof(u16)) + /* IFLA_BR_VLAN_DEFAULT_PVID */ #endif nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ @@ -1094,7 +1104,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING - if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto)) + if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto) || + nla_put_u16(skb, IFLA_BR_VLAN_DEFAULT_PVID, br->default_pvid)) return -EMSGSIZE; #endif #ifdef CONFIG_BRIDGE_IGMP_SNOOPING diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 1ff6a0faef3f..09d3ecbcb4f0 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -690,6 +690,7 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto); int br_vlan_set_proto(struct net_bridge *br, unsigned long val); int br_vlan_init(struct net_bridge *br); int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val); +int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid); int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags); int nbp_vlan_delete(struct net_bridge_port *port, u16 vid); void nbp_vlan_flush(struct net_bridge_port *port); diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index b879111582f0..eae07ee9bfe0 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -727,7 +727,7 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br) br->default_pvid = 0; } -static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) +int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) { const struct net_bridge_vlan *pvent; struct net_bridge_port *p; @@ -735,6 +735,11 @@ static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) int err = 0; unsigned long *changed; + if (!pvid) { + br_vlan_disable_default_pvid(br); + return 0; + } + changed = kcalloc(BITS_TO_LONGS(BR_MAX_PORTS), sizeof(unsigned long), GFP_KERNEL); if (!changed) @@ -825,12 +830,7 @@ int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val) err = -EPERM; goto unlock; } - - if (!pvid) - br_vlan_disable_default_pvid(br); - else - err = __br_vlan_set_default_pvid(br, pvid); - + err = __br_vlan_set_default_pvid(br, pvid); unlock: rtnl_unlock(); return err; -- cgit v1.2.3 From 4a3f95b7b62e50a1e42e42ba6571ec9e747f4861 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sun, 4 Oct 2015 23:34:00 +0200 Subject: Bluetooth: Introduce HCI_DEV_OPEN and HCI_DEV_CLOSE events When opening the HCI transport via hdev->open send HCI_DEV_OPEN event and when closing the HCI transport via hdev->close send HCI_DEV_CLOSE. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 2 ++ net/bluetooth/hci_core.c | 6 ++++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 7ca6690355ea..e7f938cac7c6 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -44,6 +44,8 @@ #define HCI_DEV_DOWN 4 #define HCI_DEV_SUSPEND 5 #define HCI_DEV_RESUME 6 +#define HCI_DEV_OPEN 7 +#define HCI_DEV_CLOSE 8 /* HCI notify events */ #define HCI_NOTIFY_CONN_ADD 1 diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 79356469c377..5af33c87cbba 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1385,6 +1385,8 @@ static int hci_dev_do_open(struct hci_dev *hdev) goto done; } + hci_notify(hdev, HCI_DEV_OPEN); + atomic_set(&hdev->cmd_cnt, 1); set_bit(HCI_INIT, &hdev->flags); @@ -1466,6 +1468,8 @@ static int hci_dev_do_open(struct hci_dev *hdev) hdev->sent_cmd = NULL; } + hci_notify(hdev, HCI_DEV_CLOSE); + hdev->close(hdev); hdev->flags &= BIT(HCI_RAW); } @@ -1649,6 +1653,8 @@ int hci_dev_do_close(struct hci_dev *hdev) hdev->sent_cmd = NULL; } + hci_notify(hdev, HCI_DEV_CLOSE); + /* After this point our queues are empty * and no tasks are scheduled. */ hdev->close(hdev); -- cgit v1.2.3 From 22db3cbcf9f91eef848db0986869822b4bf27193 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sun, 4 Oct 2015 23:34:03 +0200 Subject: Bluetooth: Send transport open and close monitor events When the core starts or shuts down the actual HCI transport, send a new monitor event that indicates that this is happening. These new events correspond to HCI_DEV_OPEN and HCI_DEV_CLOSE events. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_mon.h | 2 ++ net/bluetooth/hci_sock.c | 26 ++++++++++++++++++++++++++ 2 files changed, 28 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h index 77d1e5764185..37e4283d1d68 100644 --- a/include/net/bluetooth/hci_mon.h +++ b/include/net/bluetooth/hci_mon.h @@ -39,6 +39,8 @@ struct hci_mon_hdr { #define HCI_MON_ACL_RX_PKT 5 #define HCI_MON_SCO_TX_PKT 6 #define HCI_MON_SCO_RX_PKT 7 +#define HCI_MON_OPEN_INDEX 8 +#define HCI_MON_CLOSE_INDEX 9 struct hci_mon_new_index { __u8 type; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index d9ad68448173..64ebe84989d1 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -329,6 +329,22 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) opcode = cpu_to_le16(HCI_MON_DEL_INDEX); break; + case HCI_DEV_OPEN: + skb = bt_skb_alloc(0, GFP_ATOMIC); + if (!skb) + return NULL; + + opcode = cpu_to_le16(HCI_MON_OPEN_INDEX); + break; + + case HCI_DEV_CLOSE: + skb = bt_skb_alloc(0, GFP_ATOMIC); + if (!skb) + return NULL; + + opcode = cpu_to_le16(HCI_MON_CLOSE_INDEX); + break; + default: return NULL; } @@ -358,6 +374,16 @@ static void send_monitor_replay(struct sock *sk) if (sock_queue_rcv_skb(sk, skb)) kfree_skb(skb); + + if (!test_bit(HCI_RUNNING, &hdev->flags)) + continue; + + skb = create_monitor_event(hdev, HCI_DEV_OPEN); + if (!skb) + continue; + + if (sock_queue_rcv_skb(sk, skb)) + kfree_skb(skb); } read_unlock(&hci_dev_list_lock); -- cgit v1.2.3 From caf3f2676aaad395903d24a54e22f8ac4bc4823d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 4 Oct 2015 21:08:08 -0700 Subject: inet: ip_skb_dst_mtu() should use sk_fullsock() SYN_RECV & TIMEWAIT sockets are not full blown, do not even try to call ip_sk_use_pmtu() on them. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 91a6b2c88341..aa7811993276 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -323,12 +323,15 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb) { - if (!skb->sk || ip_sk_use_pmtu(skb->sk)) { + struct sock *sk = skb->sk; + + if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) { bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; + return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding); - } else { - return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU); } + + return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU); } u32 ip_idents_reserve(u32 hash, int segs); -- cgit v1.2.3 From e7eadb4de9e645e1b34539dc4128240b1e5f71dc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 4 Oct 2015 21:08:09 -0700 Subject: ipv6: inet6_sk() should use sk_fullsock() SYN_RECV & TIMEWAIT sockets are not full blown, they do not have a pinet6 pointer. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/ipv6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index f1f32af6d9b9..0ef2a97ccdb5 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -264,9 +264,9 @@ struct tcp6_timewait_sock { }; #if IS_ENABLED(CONFIG_IPV6) -static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) +static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { - return inet_sk(__sk)->pinet6; + return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL; } static inline struct raw6_sock *raw6_sk(const struct sock *sk) -- cgit v1.2.3 From 004a5d0140ce1d05c1f5fce5df4baa2717a330e0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 4 Oct 2015 21:08:10 -0700 Subject: net: use sk_fullsock() in __netdev_pick_tx() SYN_RECV & TIMEWAIT sockets are not full blown, they do not have a sk_dst_cache pointer. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 1 + net/core/dev.c | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index dd423d840852..f83669460d82 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -92,6 +92,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) req->rsk_listener = sk_listener; req_to_sk(req)->sk_prot = sk_listener->sk_prot; sk_node_init(&req_to_sk(req)->sk_node); + sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; /* Following is temporary. It is coupled with debugging * helpers in reqsk_put() & reqsk_free() diff --git a/net/core/dev.c b/net/core/dev.c index 323c04edd779..a229bf0d649d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2974,6 +2974,7 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) new_index = skb_tx_hash(dev, skb); if (queue_index != new_index && sk && + sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); -- cgit v1.2.3 From a1a5344ddbe8fd3e080013b317ac9a664490cfdf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 4 Oct 2015 21:08:11 -0700 Subject: tcp: avoid two atomic ops for syncookies inet_reqsk_alloc() is used to allocate a temporary request in order to generate a SYNACK with a cookie. Then later, syncookie validation also uses a temporary request. These paths already took a reference on listener refcount, we can avoid a couple of atomic operations. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 3 ++- include/net/request_sock.h | 11 ++++++++--- net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 2 +- net/ipv4/syncookies.c | 2 +- net/ipv4/tcp_input.c | 8 +++++--- net/ipv6/syncookies.c | 2 +- 7 files changed, 19 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 47eb67b08abd..f5bf7310e334 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -245,7 +245,8 @@ static inline unsigned int __inet_ehashfn(const __be32 laddr, } struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, - struct sock *sk_listener); + struct sock *sk_listener, + bool attach_listener); static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { diff --git a/include/net/request_sock.h b/include/net/request_sock.h index f83669460d82..95ab5d7aab96 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -80,7 +80,8 @@ static inline struct sock *req_to_sk(struct request_sock *req) } static inline struct request_sock * -reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) +reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, + bool attach_listener) { struct request_sock *req; @@ -88,8 +89,12 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) if (req) { req->rsk_ops = ops; - sock_hold(sk_listener); - req->rsk_listener = sk_listener; + if (attach_listener) { + sock_hold(sk_listener); + req->rsk_listener = sk_listener; + } else { + req->rsk_listener = NULL; + } req_to_sk(req)->sk_prot = sk_listener->sk_prot; sk_node_init(&req_to_sk(req)->sk_node); sk_tx_queue_clear(req_to_sk(req)); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8910c9567719..8e99681c8189 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -595,7 +595,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = inet_reqsk_alloc(&dccp_request_sock_ops, sk); + req = inet_reqsk_alloc(&dccp_request_sock_ops, sk, true); if (req == NULL) goto drop; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 1361a3f45df7..aed314f8c7c6 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -319,7 +319,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = inet_reqsk_alloc(&dccp6_request_sock_ops, sk); + req = inet_reqsk_alloc(&dccp6_request_sock_ops, sk, true); if (req == NULL) goto drop; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 729ceb5f63c6..8113c30ccf96 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -326,7 +326,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp_request_sock_ops, sk); /* for safety */ + req = inet_reqsk_alloc(&tcp_request_sock_ops, sk, false); /* for safety */ if (!req) goto out; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a95c8eb04ff7..ddadb318e850 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6042,9 +6042,11 @@ static void tcp_openreq_init(struct request_sock *req, } struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, - struct sock *sk_listener) + struct sock *sk_listener, + bool attach_listener) { - struct request_sock *req = reqsk_alloc(ops, sk_listener); + struct request_sock *req = reqsk_alloc(ops, sk_listener, + attach_listener); if (req) { struct inet_request_sock *ireq = inet_rsk(req); @@ -6143,7 +6145,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop; } - req = inet_reqsk_alloc(rsk_ops, sk); + req = inet_reqsk_alloc(rsk_ops, sk, !want_cookie); if (!req) goto drop; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7606eba83e7b..f610b5310b17 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -170,7 +170,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk); + req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk, false); if (!req) goto out; -- cgit v1.2.3 From 0e884c78ee19e902f300ed147083c28a0c6302f0 Mon Sep 17 00:00:00 2001 From: Peter Nørlund Date: Wed, 30 Sep 2015 10:12:21 +0200 Subject: ipv4: L3 hash-based multipath MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replaces the per-packet multipath with a hash-based multipath using source and destination address. Signed-off-by: Peter Nørlund Signed-off-by: David S. Miller --- include/net/ip_fib.h | 14 ++++- net/ipv4/fib_semantics.c | 140 +++++++++++++++++++++++++---------------------- net/ipv4/route.c | 16 ++++-- 3 files changed, 98 insertions(+), 72 deletions(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 727d6e9a9685..7a51fd8d99e4 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -79,7 +79,7 @@ struct fib_nh { unsigned char nh_scope; #ifdef CONFIG_IP_ROUTE_MULTIPATH int nh_weight; - int nh_power; + atomic_t nh_upper_bound; #endif #ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; @@ -118,7 +118,7 @@ struct fib_info { #define fib_advmss fib_metrics[RTAX_ADVMSS-1] int fib_nhs; #ifdef CONFIG_IP_ROUTE_MULTIPATH - int fib_power; + int fib_weight; #endif struct rcu_head rcu; struct fib_nh fib_nh[0]; @@ -320,7 +320,15 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev); int fib_sync_down_dev(struct net_device *dev, unsigned long event); int fib_sync_down_addr(struct net *net, __be32 local); int fib_sync_up(struct net_device *dev, unsigned int nh_flags); -void fib_select_multipath(struct fib_result *res); + +extern u32 fib_multipath_secret __read_mostly; + +static inline int fib_multipath_hash(__be32 saddr, __be32 daddr) +{ + return jhash_2words(saddr, daddr, fib_multipath_secret) >> 1; +} + +void fib_select_multipath(struct fib_result *res, int hash); /* Exported by fib_trie.c */ void fib_trie_init(void); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 064bd3caaa4f..0c49d2f3bbc0 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -57,8 +57,7 @@ static unsigned int fib_info_cnt; static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE]; #ifdef CONFIG_IP_ROUTE_MULTIPATH - -static DEFINE_SPINLOCK(fib_multipath_lock); +u32 fib_multipath_secret __read_mostly; #define for_nexthops(fi) { \ int nhsel; const struct fib_nh *nh; \ @@ -532,7 +531,67 @@ errout: return ret; } -#endif +static void fib_rebalance(struct fib_info *fi) +{ + int total; + int w; + struct in_device *in_dev; + + if (fi->fib_nhs < 2) + return; + + total = 0; + for_nexthops(fi) { + if (nh->nh_flags & RTNH_F_DEAD) + continue; + + in_dev = __in_dev_get_rcu(nh->nh_dev); + + if (in_dev && + IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && + nh->nh_flags & RTNH_F_LINKDOWN) + continue; + + total += nh->nh_weight; + } endfor_nexthops(fi); + + w = 0; + change_nexthops(fi) { + int upper_bound; + + in_dev = __in_dev_get_rcu(nexthop_nh->nh_dev); + + if (nexthop_nh->nh_flags & RTNH_F_DEAD) { + upper_bound = -1; + } else if (in_dev && + IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && + nexthop_nh->nh_flags & RTNH_F_LINKDOWN) { + upper_bound = -1; + } else { + w += nexthop_nh->nh_weight; + upper_bound = DIV_ROUND_CLOSEST(2147483648LL * w, + total) - 1; + } + + atomic_set(&nexthop_nh->nh_upper_bound, upper_bound); + } endfor_nexthops(fi); + + net_get_random_once(&fib_multipath_secret, + sizeof(fib_multipath_secret)); +} + +static inline void fib_add_weight(struct fib_info *fi, + const struct fib_nh *nh) +{ + fi->fib_weight += nh->nh_weight; +} + +#else /* CONFIG_IP_ROUTE_MULTIPATH */ + +#define fib_rebalance(fi) do { } while (0) +#define fib_add_weight(fi, nh) do { } while (0) + +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ static int fib_encap_match(struct net *net, u16 encap_type, struct nlattr *encap, @@ -1094,8 +1153,11 @@ struct fib_info *fib_create_info(struct fib_config *cfg) change_nexthops(fi) { fib_info_update_nh_saddr(net, nexthop_nh); + fib_add_weight(fi, nexthop_nh); } endfor_nexthops(fi) + fib_rebalance(fi); + link_it: ofi = fib_find_info(fi); if (ofi) { @@ -1317,12 +1379,6 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event) nexthop_nh->nh_flags |= RTNH_F_LINKDOWN; break; } -#ifdef CONFIG_IP_ROUTE_MULTIPATH - spin_lock_bh(&fib_multipath_lock); - fi->fib_power -= nexthop_nh->nh_power; - nexthop_nh->nh_power = 0; - spin_unlock_bh(&fib_multipath_lock); -#endif dead++; } #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -1345,6 +1401,8 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event) } ret++; } + + fib_rebalance(fi); } return ret; @@ -1467,20 +1525,15 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags) !__in_dev_get_rtnl(dev)) continue; alive++; -#ifdef CONFIG_IP_ROUTE_MULTIPATH - spin_lock_bh(&fib_multipath_lock); - nexthop_nh->nh_power = 0; - nexthop_nh->nh_flags &= ~nh_flags; - spin_unlock_bh(&fib_multipath_lock); -#else nexthop_nh->nh_flags &= ~nh_flags; -#endif } endfor_nexthops(fi) if (alive > 0) { fi->fib_flags &= ~nh_flags; ret++; } + + fib_rebalance(fi); } return ret; @@ -1488,62 +1541,19 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags) #ifdef CONFIG_IP_ROUTE_MULTIPATH -/* - * The algorithm is suboptimal, but it provides really - * fair weighted route distribution. - */ -void fib_select_multipath(struct fib_result *res) +void fib_select_multipath(struct fib_result *res, int hash) { struct fib_info *fi = res->fi; - struct in_device *in_dev; - int w; - - spin_lock_bh(&fib_multipath_lock); - if (fi->fib_power <= 0) { - int power = 0; - change_nexthops(fi) { - in_dev = __in_dev_get_rcu(nexthop_nh->nh_dev); - if (nexthop_nh->nh_flags & RTNH_F_DEAD) - continue; - if (in_dev && - IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && - nexthop_nh->nh_flags & RTNH_F_LINKDOWN) - continue; - power += nexthop_nh->nh_weight; - nexthop_nh->nh_power = nexthop_nh->nh_weight; - } endfor_nexthops(fi); - fi->fib_power = power; - if (power <= 0) { - spin_unlock_bh(&fib_multipath_lock); - /* Race condition: route has just become dead. */ - res->nh_sel = 0; - return; - } - } - - /* w should be random number [0..fi->fib_power-1], - * it is pretty bad approximation. - */ - - w = jiffies % fi->fib_power; + for_nexthops(fi) { + if (hash > atomic_read(&nh->nh_upper_bound)) + continue; - change_nexthops(fi) { - if (!(nexthop_nh->nh_flags & RTNH_F_DEAD) && - nexthop_nh->nh_power) { - w -= nexthop_nh->nh_power; - if (w <= 0) { - nexthop_nh->nh_power--; - fi->fib_power--; - res->nh_sel = nhsel; - spin_unlock_bh(&fib_multipath_lock); - return; - } - } + res->nh_sel = nhsel; + return; } endfor_nexthops(fi); /* Race condition: route has just become dead. */ res->nh_sel = 0; - spin_unlock_bh(&fib_multipath_lock); } #endif diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 76ca4e75f785..0cca44476b1e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1658,8 +1658,12 @@ static int ip_mkroute_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, u32 tos) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res->fi && res->fi->fib_nhs > 1) - fib_select_multipath(res); + if (res->fi && res->fi->fib_nhs > 1) { + int h; + + h = fib_multipath_hash(saddr, daddr); + fib_select_multipath(res, h); + } #endif /* create a routing cache entry */ @@ -2189,8 +2193,12 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) } #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0) - fib_select_multipath(&res); + if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0) { + int h; + + h = fib_multipath_hash(fl4->saddr, fl4->daddr); + fib_select_multipath(&res, h); + } else #endif if (!res.prefixlen && -- cgit v1.2.3 From 79a131592dbb81a2dba208622a2ffbfc53f28bc0 Mon Sep 17 00:00:00 2001 From: Peter Nørlund Date: Wed, 30 Sep 2015 10:12:22 +0200 Subject: ipv4: ICMP packet inspection for multipath MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ICMP packets are inspected to let them route together with the flow they belong to, minimizing the chance that a problematic path will affect flows on other paths, and so that anycast environments can work with ECMP. Signed-off-by: Peter Nørlund Signed-off-by: David S. Miller --- include/net/route.h | 11 +++++++++- net/ipv4/icmp.c | 19 ++++++++++++++++- net/ipv4/route.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++------- 3 files changed, 80 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index e211dc167db1..d32cb76f5302 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -113,7 +114,15 @@ struct in_device; int ip_rt_init(void); void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); -struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp); +struct rtable *__ip_route_output_key_hash(struct net *, struct flowi4 *flp, + int mp_hash); + +static inline struct rtable *__ip_route_output_key(struct net *net, + struct flowi4 *flp) +{ + return __ip_route_output_key_hash(net, flp, -1); +} + struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, const struct sock *sk); struct dst_entry *ipv4_blackhole_route(struct net *net, diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 6b96dee2800b..36e26977c908 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -440,6 +440,22 @@ out_unlock: icmp_xmit_unlock(sk); } +#ifdef CONFIG_IP_ROUTE_MULTIPATH + +/* Source and destination is swapped. See ip_multipath_icmp_hash */ +static int icmp_multipath_hash_skb(const struct sk_buff *skb) +{ + const struct iphdr *iph = ip_hdr(skb); + + return fib_multipath_hash(iph->daddr, iph->saddr); +} + +#else + +#define icmp_multipath_hash_skb(skb) (-1) + +#endif + static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, struct sk_buff *skb_in, @@ -464,7 +480,8 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); - rt = __ip_route_output_key(net, fl4); + rt = __ip_route_output_key_hash(net, fl4, + icmp_multipath_hash_skb(skb_in)); if (IS_ERR(rt)) return rt; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0cca44476b1e..54297d3a0559 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1651,6 +1651,48 @@ out: return err; } +#ifdef CONFIG_IP_ROUTE_MULTIPATH + +/* To make ICMP packets follow the right flow, the multipath hash is + * calculated from the inner IP addresses in reverse order. + */ +static int ip_multipath_icmp_hash(struct sk_buff *skb) +{ + const struct iphdr *outer_iph = ip_hdr(skb); + struct icmphdr _icmph; + const struct icmphdr *icmph; + struct iphdr _inner_iph; + const struct iphdr *inner_iph; + + if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0)) + goto standard_hash; + + icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph), + &_icmph); + if (!icmph) + goto standard_hash; + + if (icmph->type != ICMP_DEST_UNREACH && + icmph->type != ICMP_REDIRECT && + icmph->type != ICMP_TIME_EXCEEDED && + icmph->type != ICMP_PARAMETERPROB) { + goto standard_hash; + } + + inner_iph = skb_header_pointer(skb, + outer_iph->ihl * 4 + sizeof(_icmph), + sizeof(_inner_iph), &_inner_iph); + if (!inner_iph) + goto standard_hash; + + return fib_multipath_hash(inner_iph->daddr, inner_iph->saddr); + +standard_hash: + return fib_multipath_hash(outer_iph->saddr, outer_iph->daddr); +} + +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ + static int ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, const struct flowi4 *fl4, @@ -1661,7 +1703,10 @@ static int ip_mkroute_input(struct sk_buff *skb, if (res->fi && res->fi->fib_nhs > 1) { int h; - h = fib_multipath_hash(saddr, daddr); + if (unlikely(ip_hdr(skb)->protocol == IPPROTO_ICMP)) + h = ip_multipath_icmp_hash(skb); + else + h = fib_multipath_hash(saddr, daddr); fib_select_multipath(res, h); } #endif @@ -2030,7 +2075,8 @@ add: * Major route resolver routine. */ -struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) +struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, + int mp_hash) { struct net_device *dev_out = NULL; __u8 tos = RT_FL_TOS(fl4); @@ -2194,10 +2240,9 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0) { - int h; - - h = fib_multipath_hash(fl4->saddr, fl4->daddr); - fib_select_multipath(&res, h); + if (mp_hash < 0) + mp_hash = fib_multipath_hash(fl4->saddr, fl4->daddr); + fib_select_multipath(&res, mp_hash); } else #endif @@ -2220,7 +2265,7 @@ out: rcu_read_unlock(); return rth; } -EXPORT_SYMBOL_GPL(__ip_route_output_key); +EXPORT_SYMBOL_GPL(__ip_route_output_key_hash); static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) { -- cgit v1.2.3 From 70ba07b675b53782ad366ebc4d3a00eab9a06bc9 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 30 Sep 2015 17:32:01 +0200 Subject: atm: remove 'struct zatm_t_hist' The zatm_t_hist structure is not used anywhere in the kernel, but is exported to user space. As we are trying to eliminate uses of time_t in the kernel for y2038 compatibility, the current definition triggers checking tools because it contains 'struct timeval'. As pointed out by Chas Williams, the only user of this structure was the ZATM_GETHIST ioctl command that has been removed a long time ago, and we can remove the structure as well without breaking any user space. Signed-off-by: Arnd Bergmann Cc: Chas Williams <3chas3@gmail.com> Cc: linux-atm-general@lists.sourceforge.net Signed-off-by: David S. Miller --- include/uapi/linux/atm_zatm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h index 10f0fa29454f..9c9c6ad55f14 100644 --- a/include/uapi/linux/atm_zatm.h +++ b/include/uapi/linux/atm_zatm.h @@ -35,12 +35,6 @@ struct zatm_pool_req { struct zatm_pool_info info; /* actual information */ }; -struct zatm_t_hist { - struct timeval real; /* real (wall-clock) time */ - struct timeval expected; /* expected real time */ -}; - - #define ZATM_OAM_POOL 0 /* free buffer pool for OAM cells */ #define ZATM_AAL0_POOL 1 /* free buffer pool for AAL0 cells */ #define ZATM_AAL5_POOL_BASE 2 /* first AAL5 free buffer pool */ -- cgit v1.2.3 From 7741c373cf3ea1f5383fa97fb7a640a429d3dd7c Mon Sep 17 00:00:00 2001 From: Jon Ringle Date: Thu, 1 Oct 2015 07:43:20 -0400 Subject: regmap: Allow installing custom reg_update_bits function This commit allows installing a custom reg_update_bits function for cases where the hardware provides a mechanism to set or clear register bits without a read/modify/write cycle. Such is the case with the Microchip ENCX24J600. Signed-off-by: Jon Ringle Signed-off-by: David S. Miller --- drivers/base/regmap/internal.h | 3 +++ drivers/base/regmap/regmap.c | 25 +++++++++++++++++++++++++ include/linux/regmap.h | 4 ++++ 3 files changed, 32 insertions(+) (limited to 'include') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index cc557886ab23..4036d7a90f63 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -98,6 +98,9 @@ struct regmap { int (*reg_read)(void *context, unsigned int reg, unsigned int *val); int (*reg_write)(void *context, unsigned int reg, unsigned int val); + int (*reg_update_bits)(void *context, unsigned int reg, + unsigned int mask, unsigned int val, + bool *change, bool force_write); bool defer_caching; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index afaf56200674..70387c9f281b 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -619,6 +619,7 @@ struct regmap *__regmap_init(struct device *dev, goto skip_format_initialization; } else { map->reg_read = _regmap_bus_read; + map->reg_update_bits = bus->reg_update_bits; } reg_endian = regmap_get_reg_endian(bus, config); @@ -2509,6 +2510,30 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg, int ret; unsigned int tmp, orig; + if (map->reg_update_bits) { + ret = map->reg_update_bits(map->bus_context, reg, mask, val, + change, force_write); + if (ret != 0) + return ret; + + /* Fix up the cache by read/modify/write */ + if (!map->cache_bypass && !map->defer_caching) { + ret = regcache_read(map, reg, &orig); + if (ret != 0) + return ret; + + tmp = orig & ~mask; + tmp |= val & mask; + + ret = regcache_write(map, reg, tmp); + if (ret != 0) + return ret; + if (map->cache_only) + map->cache_dirty = true; + } + return ret; + } + ret = _regmap_read(map, reg, &orig); if (ret != 0) return ret; diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 8fc0bfd8edc4..4d3a3b1680bb 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -296,6 +296,9 @@ typedef int (*regmap_hw_reg_read)(void *context, unsigned int reg, unsigned int *val); typedef int (*regmap_hw_reg_write)(void *context, unsigned int reg, unsigned int val); +typedef int (*regmap_hw_reg_update_bits)(void *context, unsigned int reg, + unsigned int mask, unsigned int val, + bool *change, bool force_write); typedef struct regmap_async *(*regmap_hw_async_alloc)(void); typedef void (*regmap_hw_free_context)(void *context); @@ -335,6 +338,7 @@ struct regmap_bus { regmap_hw_gather_write gather_write; regmap_hw_async_write async_write; regmap_hw_reg_write reg_write; + regmap_hw_reg_update_bits reg_update_bits; regmap_hw_read read; regmap_hw_reg_read reg_read; regmap_hw_free_context free_context; -- cgit v1.2.3 From bab18991871545dfbd10c931eb0fe8f7637156a9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 2 Oct 2015 15:17:33 +0200 Subject: bpf, seccomp: prepare for upcoming criu support The current ongoing effort to dump existing cBPF seccomp filters back to user space requires to hold the pre-transformed instructions like we do in case of socket filters from sk_attach_filter() side, so they can be reloaded in original form at a later point in time by utilities such as criu. To prepare for this, simply extend the bpf_prog_create_from_user() API to hold a flag that tells whether we should store the original or not. Also, fanout filters could make use of that in future for things like diag. While fanout filters already use bpf_prog_destroy(), move seccomp over to them as well to handle original programs when present. Signed-off-by: Daniel Borkmann Cc: Tycho Andersen Cc: Pavel Emelyanov Cc: Kees Cook Cc: Andy Lutomirski Cc: Alexei Starovoitov Tested-by: Tycho Andersen Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 2 +- kernel/seccomp.c | 4 ++-- net/core/filter.c | 16 +++++++++++----- net/packet/af_packet.c | 2 +- 4 files changed, 15 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 3d5fd24b321b..1bbce14bcf17 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -411,7 +411,7 @@ typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter, int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, - bpf_aux_classic_check_t trans); + bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 5bd4779282df..06858a74bb9c 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -370,7 +370,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) return ERR_PTR(-ENOMEM); ret = bpf_prog_create_from_user(&sfilter->prog, fprog, - seccomp_check_filter); + seccomp_check_filter, false); if (ret < 0) { kfree(sfilter); return ERR_PTR(ret); @@ -469,7 +469,7 @@ void get_seccomp_filter(struct task_struct *tsk) static inline void seccomp_filter_free(struct seccomp_filter *filter) { if (filter) { - bpf_prog_free(filter->prog); + bpf_prog_destroy(filter->prog); kfree(filter); } } diff --git a/net/core/filter.c b/net/core/filter.c index 53a5036fb32d..da3e5357f138 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1084,16 +1084,18 @@ EXPORT_SYMBOL_GPL(bpf_prog_create); * @pfp: the unattached filter that is created * @fprog: the filter program * @trans: post-classic verifier transformation handler + * @save_orig: save classic BPF program * * This function effectively does the same as bpf_prog_create(), only * that it builds up its insns buffer from user space provided buffer. * It also allows for passing a bpf_aux_classic_check_t handler. */ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, - bpf_aux_classic_check_t trans) + bpf_aux_classic_check_t trans, bool save_orig) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; + int err; /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) @@ -1109,12 +1111,16 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, } fp->len = fprog->len; - /* Since unattached filters are not copied back to user - * space through sk_get_filter(), we do not need to hold - * a copy here, and can spare us the work. - */ fp->orig_prog = NULL; + if (save_orig) { + err = bpf_prog_store_orig_filter(fp, fprog); + if (err) { + __bpf_prog_free(fp); + return -ENOMEM; + } + } + /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index aa4b15c35884..81c900fbc4a4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1567,7 +1567,7 @@ static int fanout_set_data_cbpf(struct packet_sock *po, char __user *data, if (copy_from_user(&fprog, data, len)) return -EFAULT; - ret = bpf_prog_create_from_user(&new, &fprog, NULL); + ret = bpf_prog_create_from_user(&new, &fprog, NULL, false); if (ret) return ret; -- cgit v1.2.3 From 0cdf5640e4f6940bdbbefee4bb0adb7dffb185ec Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 2 Oct 2015 18:42:00 +0200 Subject: ebpf: include perf_event only where really needed Commit ea317b267e9d ("bpf: Add new bpf map type to store the pointer to struct perf_event") added perf_event.h to the main eBPF header, so it gets included for all users. perf_event.h is actually only needed from array map side, so lets sanitize this a bit. Signed-off-by: Daniel Borkmann Cc: Kaixu Xia Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 - kernel/bpf/arraymap.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f57d7fed9ec3..c915a6b54570 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -10,7 +10,6 @@ #include #include #include -#include struct bpf_map; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 29ace107f236..2fecc4aed119 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -15,6 +15,7 @@ #include #include #include +#include /* Called from syscall */ static struct bpf_map *array_map_alloc(union bpf_attr *attr) -- cgit v1.2.3 From 21c4c073f14509d685ed219aa3c76362a7bfa0ac Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 6 Oct 2015 06:25:43 -0700 Subject: Revert "regmap: Allow installing custom reg_update_bits function" This reverts commit 7741c373cf3ea1f5383fa97fb7a640a429d3dd7c. --- drivers/base/regmap/internal.h | 3 --- drivers/base/regmap/regmap.c | 25 ------------------------- include/linux/regmap.h | 4 ---- 3 files changed, 32 deletions(-) (limited to 'include') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 4036d7a90f63..cc557886ab23 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -98,9 +98,6 @@ struct regmap { int (*reg_read)(void *context, unsigned int reg, unsigned int *val); int (*reg_write)(void *context, unsigned int reg, unsigned int val); - int (*reg_update_bits)(void *context, unsigned int reg, - unsigned int mask, unsigned int val, - bool *change, bool force_write); bool defer_caching; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 70387c9f281b..afaf56200674 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -619,7 +619,6 @@ struct regmap *__regmap_init(struct device *dev, goto skip_format_initialization; } else { map->reg_read = _regmap_bus_read; - map->reg_update_bits = bus->reg_update_bits; } reg_endian = regmap_get_reg_endian(bus, config); @@ -2510,30 +2509,6 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg, int ret; unsigned int tmp, orig; - if (map->reg_update_bits) { - ret = map->reg_update_bits(map->bus_context, reg, mask, val, - change, force_write); - if (ret != 0) - return ret; - - /* Fix up the cache by read/modify/write */ - if (!map->cache_bypass && !map->defer_caching) { - ret = regcache_read(map, reg, &orig); - if (ret != 0) - return ret; - - tmp = orig & ~mask; - tmp |= val & mask; - - ret = regcache_write(map, reg, tmp); - if (ret != 0) - return ret; - if (map->cache_only) - map->cache_dirty = true; - } - return ret; - } - ret = _regmap_read(map, reg, &orig); if (ret != 0) return ret; diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4d3a3b1680bb..8fc0bfd8edc4 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -296,9 +296,6 @@ typedef int (*regmap_hw_reg_read)(void *context, unsigned int reg, unsigned int *val); typedef int (*regmap_hw_reg_write)(void *context, unsigned int reg, unsigned int val); -typedef int (*regmap_hw_reg_update_bits)(void *context, unsigned int reg, - unsigned int mask, unsigned int val, - bool *change, bool force_write); typedef struct regmap_async *(*regmap_hw_async_alloc)(void); typedef void (*regmap_hw_free_context)(void *context); @@ -338,7 +335,6 @@ struct regmap_bus { regmap_hw_gather_write gather_write; regmap_hw_async_write async_write; regmap_hw_reg_write reg_write; - regmap_hw_reg_update_bits reg_update_bits; regmap_hw_read read; regmap_hw_reg_read reg_read; regmap_hw_free_context free_context; -- cgit v1.2.3 From 77792b11409c9270d98e604b4314b85ce886ac7d Mon Sep 17 00:00:00 2001 From: Jon Ringle Date: Thu, 1 Oct 2015 12:38:07 -0400 Subject: regmap: Allow installing custom reg_update_bits function This commit allows installing a custom reg_update_bits function for cases where the hardware provides a mechanism to set or clear register bits without a read/modify/write cycle. Such is the case with the Microchip ENCX24J600. If a custom reg_update_bits function is provided, it will only be used against volatile registers. Signed-off-by: Jon Ringle Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 2 ++ drivers/base/regmap/regmap.c | 29 ++++++++++++++++++----------- include/linux/regmap.h | 3 +++ 3 files changed, 23 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index cc557886ab23..628ad7ac078b 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -98,6 +98,8 @@ struct regmap { int (*reg_read)(void *context, unsigned int reg, unsigned int *val); int (*reg_write)(void *context, unsigned int reg, unsigned int val); + int (*reg_update_bits)(void *context, unsigned int reg, + unsigned int mask, unsigned int val); bool defer_caching; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index afaf56200674..8cd155af3d63 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -619,6 +619,7 @@ struct regmap *__regmap_init(struct device *dev, goto skip_format_initialization; } else { map->reg_read = _regmap_bus_read; + map->reg_update_bits = bus->reg_update_bits; } reg_endian = regmap_get_reg_endian(bus, config); @@ -2509,20 +2510,26 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg, int ret; unsigned int tmp, orig; - ret = _regmap_read(map, reg, &orig); - if (ret != 0) - return ret; + if (change) + *change = false; - tmp = orig & ~mask; - tmp |= val & mask; - - if (force_write || (tmp != orig)) { - ret = _regmap_write(map, reg, tmp); - if (change) + if (regmap_volatile(map, reg) && map->reg_update_bits) { + ret = map->reg_update_bits(map->bus_context, reg, mask, val); + if (ret == 0 && change) *change = true; } else { - if (change) - *change = false; + ret = _regmap_read(map, reg, &orig); + if (ret != 0) + return ret; + + tmp = orig & ~mask; + tmp |= val & mask; + + if (force_write || (tmp != orig)) { + ret = _regmap_write(map, reg, tmp); + if (ret == 0 && change) + *change = true; + } } return ret; diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 8fc0bfd8edc4..b49d4133750e 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -296,6 +296,8 @@ typedef int (*regmap_hw_reg_read)(void *context, unsigned int reg, unsigned int *val); typedef int (*regmap_hw_reg_write)(void *context, unsigned int reg, unsigned int val); +typedef int (*regmap_hw_reg_update_bits)(void *context, unsigned int reg, + unsigned int mask, unsigned int val); typedef struct regmap_async *(*regmap_hw_async_alloc)(void); typedef void (*regmap_hw_free_context)(void *context); @@ -335,6 +337,7 @@ struct regmap_bus { regmap_hw_gather_write gather_write; regmap_hw_async_write async_write; regmap_hw_reg_write reg_write; + regmap_hw_reg_update_bits reg_update_bits; regmap_hw_read read; regmap_hw_reg_read reg_read; regmap_hw_free_context free_context; -- cgit v1.2.3 From 6b26ba3a7d952e611dcde1f3f77ce63bcc70540a Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Mon, 5 Oct 2015 13:09:47 +0200 Subject: openvswitch: netlink attributes for IPv6 tunneling Add netlink attributes for IPv6 tunnel addresses. This enables IPv6 support for tunnels. Signed-off-by: Jiri Benc Acked-by: Pravin B Shelar Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 + net/openvswitch/flow_netlink.c | 121 +++++++++++++++++++++++++++------------ 2 files changed, 86 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 32e07d8cbaf4..4036e1b1980f 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -349,6 +349,8 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_TP_SRC, /* be16 src Transport Port. */ OVS_TUNNEL_KEY_ATTR_TP_DST, /* be16 dst Transport Port. */ OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS, /* Nested OVS_VXLAN_EXT_* */ + OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */ + OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */ __OVS_TUNNEL_KEY_ATTR_MAX }; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 6be701f6b31b..77850f177a47 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -262,8 +262,8 @@ size_t ovs_tun_key_attr_size(void) * updating this function. */ return nla_total_size(8) /* OVS_TUNNEL_KEY_ATTR_ID */ - + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */ - + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */ + + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_SRC */ + + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_DST */ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TOS */ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */ @@ -323,6 +323,8 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_VARIABLE }, [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED, .next = ovs_vxlan_ext_key_lens }, + [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, + [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) }, }; /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ @@ -542,14 +544,14 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, return 0; } -static int ipv4_tun_from_nlattr(const struct nlattr *attr, - struct sw_flow_match *match, bool is_mask, - bool log) +static int ip_tun_from_nlattr(const struct nlattr *attr, + struct sw_flow_match *match, bool is_mask, + bool log) { struct nlattr *a; int rem; bool ttl = false; - __be16 tun_flags = 0; + __be16 tun_flags = 0, ipv4 = false, ipv6 = false; int opts_type = 0; nla_for_each_nested(a, attr, rem) { @@ -578,10 +580,22 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, case OVS_TUNNEL_KEY_ATTR_IPV4_SRC: SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src, nla_get_in_addr(a), is_mask); + ipv4 = true; break; case OVS_TUNNEL_KEY_ATTR_IPV4_DST: SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.dst, nla_get_in_addr(a), is_mask); + ipv4 = true; + break; + case OVS_TUNNEL_KEY_ATTR_IPV6_SRC: + SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst, + nla_get_in6_addr(a), is_mask); + ipv6 = true; + break; + case OVS_TUNNEL_KEY_ATTR_IPV6_DST: + SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst, + nla_get_in6_addr(a), is_mask); + ipv6 = true; break; case OVS_TUNNEL_KEY_ATTR_TOS: SW_FLOW_KEY_PUT(match, tun_key.tos, @@ -636,7 +650,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, opts_type = type; break; default: - OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d", + OVS_NLERR(log, "Unknown IP tunnel attribute %d", type); return -EINVAL; } @@ -646,22 +660,36 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, if (is_mask) SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true); else - SW_FLOW_KEY_PUT(match, tun_proto, AF_INET, false); + SW_FLOW_KEY_PUT(match, tun_proto, ipv6 ? AF_INET6 : AF_INET, + false); if (rem > 0) { - OVS_NLERR(log, "IPv4 tunnel attribute has %d unknown bytes.", + OVS_NLERR(log, "IP tunnel attribute has %d unknown bytes.", rem); return -EINVAL; } + if (ipv4 && ipv6) { + OVS_NLERR(log, "Mixed IPv4 and IPv6 tunnel attributes"); + return -EINVAL; + } + if (!is_mask) { - if (!match->key->tun_key.u.ipv4.dst) { + if (!ipv4 && !ipv6) { + OVS_NLERR(log, "IP tunnel dst address not specified"); + return -EINVAL; + } + if (ipv4 && !match->key->tun_key.u.ipv4.dst) { OVS_NLERR(log, "IPv4 tunnel dst address is zero"); return -EINVAL; } + if (ipv6 && ipv6_addr_any(&match->key->tun_key.u.ipv6.dst)) { + OVS_NLERR(log, "IPv6 tunnel dst address is zero"); + return -EINVAL; + } if (!ttl) { - OVS_NLERR(log, "IPv4 tunnel TTL not specified."); + OVS_NLERR(log, "IP tunnel TTL not specified."); return -EINVAL; } } @@ -686,21 +714,36 @@ static int vxlan_opt_to_nlattr(struct sk_buff *skb, return 0; } -static int __ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ip_tunnel_key *output, - const void *tun_opts, int swkey_tun_opts_len) +static int __ip_tun_to_nlattr(struct sk_buff *skb, + const struct ip_tunnel_key *output, + const void *tun_opts, int swkey_tun_opts_len, + unsigned short tun_proto) { if (output->tun_flags & TUNNEL_KEY && nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id)) return -EMSGSIZE; - if (output->u.ipv4.src && - nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, - output->u.ipv4.src)) - return -EMSGSIZE; - if (output->u.ipv4.dst && - nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, - output->u.ipv4.dst)) - return -EMSGSIZE; + switch (tun_proto) { + case AF_INET: + if (output->u.ipv4.src && + nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, + output->u.ipv4.src)) + return -EMSGSIZE; + if (output->u.ipv4.dst && + nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, + output->u.ipv4.dst)) + return -EMSGSIZE; + break; + case AF_INET6: + if (!ipv6_addr_any(&output->u.ipv6.src) && + nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_SRC, + &output->u.ipv6.src)) + return -EMSGSIZE; + if (!ipv6_addr_any(&output->u.ipv6.dst) && + nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_DST, + &output->u.ipv6.dst)) + return -EMSGSIZE; + break; + } if (output->tos && nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->tos)) return -EMSGSIZE; @@ -734,9 +777,10 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb, return 0; } -static int ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ip_tunnel_key *output, - const void *tun_opts, int swkey_tun_opts_len) +static int ip_tun_to_nlattr(struct sk_buff *skb, + const struct ip_tunnel_key *output, + const void *tun_opts, int swkey_tun_opts_len, + unsigned short tun_proto) { struct nlattr *nla; int err; @@ -745,7 +789,8 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb, if (!nla) return -EMSGSIZE; - err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len); + err = __ip_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len, + tun_proto); if (err) return err; @@ -757,9 +802,10 @@ int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb, const struct ip_tunnel_info *egress_tun_info, const void *egress_tun_opts) { - return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key, - egress_tun_opts, - egress_tun_info->options_len); + return __ip_tun_to_nlattr(skb, &egress_tun_info->key, + egress_tun_opts, + egress_tun_info->options_len, + ip_tunnel_info_af(egress_tun_info)); } static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, @@ -810,8 +856,8 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, *attrs &= ~(1 << OVS_KEY_ATTR_SKB_MARK); } if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) { - if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match, - is_mask, log) < 0) + if (ip_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match, + is_mask, log) < 0) return -EINVAL; *attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL); } @@ -1377,8 +1423,8 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT) opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len); - if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts, - swkey->tun_opts_len)) + if (ip_tun_to_nlattr(skb, &output->tun_key, opts, + swkey->tun_opts_len, swkey->tun_proto)) goto nla_put_failure; } @@ -1881,7 +1927,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, int err = 0, start, opts_type; ovs_match_init(&match, &key, NULL); - opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log); + opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log); if (opts_type < 0) return opts_type; @@ -2380,10 +2426,11 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) if (!start) return -EMSGSIZE; - err = ipv4_tun_to_nlattr(skb, &tun_info->key, - tun_info->options_len ? + err = ip_tun_to_nlattr(skb, &tun_info->key, + tun_info->options_len ? ip_tunnel_info_opts(tun_info) : NULL, - tun_info->options_len); + tun_info->options_len, + ip_tunnel_info_af(tun_info)); if (err) return err; nla_nest_end(skb, start); -- cgit v1.2.3 From 6e2895a8e3824eb5611c97a015a3b6d678b4503e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 5 Oct 2015 08:51:23 -0700 Subject: net: Rename FLOWI_FLAG_VRFSRC to FLOWI_FLAG_L3MDEV_SRC Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/vrf.c | 4 ++-- include/net/flow.h | 2 +- include/net/route.h | 2 +- net/ipv4/udp.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 474396353e7f..4fd5af1acff0 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -208,7 +208,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, .flowi4_oif = vrf_dev->ifindex, .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_tos = RT_TOS(ip4h->tos), - .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC | + .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF, .daddr = ip4h->daddr, }; @@ -545,7 +545,7 @@ static struct rtable *vrf_get_rtable(const struct net_device *dev, { struct rtable *rth = NULL; - if (!(fl4->flowi4_flags & FLOWI_FLAG_VRFSRC)) { + if (!(fl4->flowi4_flags & FLOWI_FLAG_L3MDEV_SRC)) { struct net_vrf *vrf = netdev_priv(dev); rth = vrf->rth; diff --git a/include/net/flow.h b/include/net/flow.h index 9b85db85f13c..83969eebebf3 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -34,7 +34,7 @@ struct flowi_common { __u8 flowic_flags; #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_KNOWN_NH 0x02 -#define FLOWI_FLAG_VRFSRC 0x04 +#define FLOWI_FLAG_L3MDEV_SRC 0x04 #define FLOWI_FLAG_SKIP_NH_OIF 0x08 __u32 flowic_secid; struct flowi_tunnel flowic_tun_key; diff --git a/include/net/route.h b/include/net/route.h index d32cb76f5302..3e18d90b3f4e 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -267,7 +267,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 flow_flags |= FLOWI_FLAG_ANYSRC; if (netif_index_is_l3_master(sock_net(sk), oif)) - flow_flags |= FLOWI_FLAG_VRFSRC | FLOWI_FLAG_SKIP_NH_OIF; + flow_flags |= FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF; flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, protocol, flow_flags, dst, src, dport, sport); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 156ba75b6000..b2882cfd3136 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1024,7 +1024,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (netif_index_is_l3_master(net, ipc.oif)) { flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, - (flow_flags | FLOWI_FLAG_VRFSRC | + (flow_flags | FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF), faddr, saddr, dport, inet->inet_sport); -- cgit v1.2.3 From fee6d4c777a125e56de9370db3b2bf359bf958d6 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 5 Oct 2015 08:51:24 -0700 Subject: net: Add netif_is_l3_slave IPv6 addrconf keys off of IFF_SLAVE so can not use it for L3 slave. Add a new private flag and add netif_is_l3_slave function for checking it. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/vrf.c | 10 ++++------ include/linux/netdevice.h | 7 +++++++ net/l3mdev/l3mdev.c | 8 ++++---- 3 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 4fd5af1acff0..8713317eed86 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -39,8 +39,6 @@ #define DRV_NAME "vrf" #define DRV_VERSION "1.0" -#define vrf_is_slave(dev) ((dev)->flags & IFF_SLAVE) - #define vrf_master_get_rcu(dev) \ ((struct net_device *)rcu_dereference(dev->rx_handler_data)) @@ -433,7 +431,7 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) if (ret < 0) goto out_unregister; - port_dev->flags |= IFF_SLAVE; + port_dev->priv_flags |= IFF_L3MDEV_SLAVE; __vrf_insert_slave(queue, slave); cycle_netdev(port_dev); @@ -448,7 +446,7 @@ out_fail: static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev) { - if (netif_is_l3_master(port_dev) || vrf_is_slave(port_dev)) + if (netif_is_l3_master(port_dev) || netif_is_l3_slave(port_dev)) return -EINVAL; return do_vrf_add_slave(dev, port_dev); @@ -462,7 +460,7 @@ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) struct slave *slave; netdev_upper_dev_unlink(port_dev, dev); - port_dev->flags &= ~IFF_SLAVE; + port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; netdev_rx_handler_unregister(port_dev); @@ -672,7 +670,7 @@ static int vrf_device_event(struct notifier_block *unused, if (event == NETDEV_UNREGISTER) { struct net_device *vrf_dev; - if (!vrf_is_slave(dev) || netif_is_l3_master(dev)) + if (!netif_is_l3_slave(dev)) goto out; vrf_dev = netdev_master_upper_dev_get(dev); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b9450784ae06..b3374402c1ea 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1261,6 +1261,7 @@ struct net_device_ops { * @IFF_L3MDEV_MASTER: device is an L3 master device * @IFF_NO_QUEUE: device can run without qdisc attached * @IFF_OPENVSWITCH: device is a Open vSwitch master + * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1286,6 +1287,7 @@ enum netdev_priv_flags { IFF_L3MDEV_MASTER = 1<<20, IFF_NO_QUEUE = 1<<21, IFF_OPENVSWITCH = 1<<22, + IFF_L3MDEV_SLAVE = 1<<23, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -3830,6 +3832,11 @@ static inline bool netif_is_l3_master(const struct net_device *dev) return dev->priv_flags & IFF_L3MDEV_MASTER; } +static inline bool netif_is_l3_slave(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_SLAVE; +} + static inline bool netif_is_bridge_master(const struct net_device *dev) { return dev->priv_flags & IFF_EBRIDGE; diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index ddf75ad41713..8e5ead366e7f 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -26,11 +26,11 @@ int l3mdev_master_ifindex_rcu(struct net_device *dev) if (netif_is_l3_master(dev)) { ifindex = dev->ifindex; - } else if (dev->flags & IFF_SLAVE) { + } else if (netif_is_l3_slave(dev)) { struct net_device *master; master = netdev_master_upper_dev_get_rcu(dev); - if (master && netif_is_l3_master(master)) + if (master) ifindex = master->ifindex; } @@ -54,7 +54,7 @@ u32 l3mdev_fib_table_rcu(const struct net_device *dev) if (netif_is_l3_master(dev)) { if (dev->l3mdev_ops->l3mdev_fib_table) tb_id = dev->l3mdev_ops->l3mdev_fib_table(dev); - } else if (dev->flags & IFF_SLAVE) { + } else if (netif_is_l3_slave(dev)) { /* Users of netdev_master_upper_dev_get_rcu need non-const, * but current inet_*type functions take a const */ @@ -62,7 +62,7 @@ u32 l3mdev_fib_table_rcu(const struct net_device *dev) const struct net_device *master; master = netdev_master_upper_dev_get_rcu(_dev); - if (master && netif_is_l3_master(master) && + if (master && master->l3mdev_ops->l3mdev_fib_table) tb_id = master->l3mdev_ops->l3mdev_fib_table(master); } -- cgit v1.2.3 From 3ce58d84358c7b477811b5100152fad848f936fc Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 5 Oct 2015 08:51:25 -0700 Subject: net: Refactor path selection in __ip_route_output_key_hash VRF device needs the same path selection following lookup to set source address. Rather than duplicating code, move existing code into a function that is exported to modules. Code move only; no functional change. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 2 ++ net/ipv4/fib_semantics.c | 21 +++++++++++++++++++++ net/ipv4/route.c | 16 +--------------- 3 files changed, 24 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 7a51fd8d99e4..ac5c6e80586a 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -329,6 +329,8 @@ static inline int fib_multipath_hash(__be32 saddr, __be32 daddr) } void fib_select_multipath(struct fib_result *res, int hash); +void fib_select_path(struct net *net, struct fib_result *res, + struct flowi4 *fl4, int mp_hash); /* Exported by fib_trie.c */ void fib_trie_init(void); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 7bd698c3bd3a..af77298c8b4f 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1557,3 +1557,24 @@ void fib_select_multipath(struct fib_result *res, int hash) res->nh_sel = 0; } #endif + +void fib_select_path(struct net *net, struct fib_result *res, + struct flowi4 *fl4, int mp_hash) +{ +#ifdef CONFIG_IP_ROUTE_MULTIPATH + if (res->fi->fib_nhs > 1 && fl4->flowi4_oif == 0) { + if (mp_hash < 0) + mp_hash = fib_multipath_hash(fl4->saddr, fl4->daddr); + fib_select_multipath(res, mp_hash); + } + else +#endif + if (!res->prefixlen && + res->table->tb_num_default > 1 && + res->type == RTN_UNICAST && !fl4->flowi4_oif) + fib_select_default(fl4, res); + + if (!fl4->saddr) + fl4->saddr = FIB_RES_PREFSRC(net, *res); +} +EXPORT_SYMBOL_GPL(fib_select_path); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 54297d3a0559..54e6f456a760 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2238,21 +2238,7 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, goto make_route; } -#ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0) { - if (mp_hash < 0) - mp_hash = fib_multipath_hash(fl4->saddr, fl4->daddr); - fib_select_multipath(&res, mp_hash); - } - else -#endif - if (!res.prefixlen && - res.table->tb_num_default > 1 && - res.type == RTN_UNICAST && !fl4->flowi4_oif) - fib_select_default(fl4, &res); - - if (!fl4->saddr) - fl4->saddr = FIB_RES_PREFSRC(net, res); + fib_select_path(net, &res, fl4, mp_hash); dev_out = FIB_RES_DEV(res); fl4->flowi4_oif = dev_out->ifindex; -- cgit v1.2.3 From 8cbb512c923d5f695ff6265b2b741b1718e3b444 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 5 Oct 2015 08:51:26 -0700 Subject: net: Add source address lookup op for VRF Add operation to l3mdev to lookup source address for a given flow. Add support for the operation to VRF driver and convert existing IPv4 hooks to use the new lookup. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/vrf.c | 35 +++++++++++++++++++++++++++++++++++ include/net/l3mdev.h | 27 +++++++++++++++++++++++++++ include/net/route.h | 7 ++++--- net/ipv4/udp.c | 22 +++------------------- 4 files changed, 69 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 8713317eed86..64499766e00f 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -36,6 +36,9 @@ #include #include +#define RT_FL_TOS(oldflp4) \ + ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) + #define DRV_NAME "vrf" #define DRV_VERSION "1.0" @@ -553,9 +556,41 @@ static struct rtable *vrf_get_rtable(const struct net_device *dev, return rth; } +/* called under rcu_read_lock */ +static void vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4) +{ + struct fib_result res = { .tclassid = 0 }; + struct net *net = dev_net(dev); + u32 orig_tos = fl4->flowi4_tos; + u8 flags = fl4->flowi4_flags; + u8 scope = fl4->flowi4_scope; + u8 tos = RT_FL_TOS(fl4); + + if (unlikely(!fl4->daddr)) + return; + + fl4->flowi4_flags |= FLOWI_FLAG_SKIP_NH_OIF; + fl4->flowi4_iif = LOOPBACK_IFINDEX; + fl4->flowi4_tos = tos & IPTOS_RT_MASK; + fl4->flowi4_scope = ((tos & RTO_ONLINK) ? + RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); + + if (!fib_lookup(net, fl4, &res, 0)) { + if (res.type == RTN_LOCAL) + fl4->saddr = res.fi->fib_prefsrc ? : fl4->daddr; + else + fib_select_path(net, &res, fl4, -1); + } + + fl4->flowi4_flags = flags; + fl4->flowi4_tos = orig_tos; + fl4->flowi4_scope = scope; +} + static const struct l3mdev_ops vrf_l3mdev_ops = { .l3mdev_fib_table = vrf_fib_table, .l3mdev_get_rtable = vrf_get_rtable, + .l3mdev_get_saddr = vrf_get_saddr, }; static void vrf_get_drvinfo(struct net_device *dev, diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 87cee05a0a17..44a19a171104 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -17,12 +17,16 @@ * @l3mdev_fib_table: Get FIB table id to use for lookups * * @l3mdev_get_rtable: Get cached IPv4 rtable (dst_entry) for device + * + * @l3mdev_get_saddr: Get source address for a flow */ struct l3mdev_ops { u32 (*l3mdev_fib_table)(const struct net_device *dev); struct rtable * (*l3mdev_get_rtable)(const struct net_device *dev, const struct flowi4 *fl4); + void (*l3mdev_get_saddr)(struct net_device *dev, + struct flowi4 *fl4); }; #ifdef CONFIG_NET_L3_MASTER_DEV @@ -100,6 +104,25 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex) return rc; } +static inline void l3mdev_get_saddr(struct net *net, int ifindex, + struct flowi4 *fl4) +{ + struct net_device *dev; + + if (ifindex) { + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, ifindex); + if (dev && netif_is_l3_master(dev) && + dev->l3mdev_ops->l3mdev_get_saddr) { + dev->l3mdev_ops->l3mdev_get_saddr(dev, fl4); + } + + rcu_read_unlock(); + } +} + #else static inline int l3mdev_master_ifindex_rcu(struct net_device *dev) @@ -144,6 +167,10 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex) return false; } +static inline void l3mdev_get_saddr(struct net *net, int ifindex, + struct flowi4 *fl4) +{ +} #endif #endif /* _NET_L3MDEV_H_ */ diff --git a/include/net/route.h b/include/net/route.h index 3e18d90b3f4e..ee81307863d5 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -266,9 +266,6 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; - if (netif_index_is_l3_master(sock_net(sk), oif)) - flow_flags |= FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF; - flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, protocol, flow_flags, dst, src, dport, sport); } @@ -285,6 +282,10 @@ static inline struct rtable *ip_route_connect(struct flowi4 *fl4, ip_route_connect_init(fl4, dst, src, tos, oif, protocol, sport, dport, sk); + if (!src && oif) { + l3mdev_get_saddr(net, oif, fl4); + src = fl4->saddr; + } if (!dst || !src) { rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index b2882cfd3136..e1fc129099ea 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1017,30 +1017,14 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl4 = &fl4_stack; - /* unconnected socket. If output device is enslaved to a VRF - * device lookup source address from VRF table. This mimics - * behavior of ip_route_connect{_init}. - */ - if (netif_index_is_l3_master(net, ipc.oif)) { - flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, - RT_SCOPE_UNIVERSE, sk->sk_protocol, - (flow_flags | FLOWI_FLAG_L3MDEV_SRC | - FLOWI_FLAG_SKIP_NH_OIF), - faddr, saddr, dport, - inet->inet_sport); - - rt = ip_route_output_flow(net, fl4, sk); - if (!IS_ERR(rt)) { - saddr = fl4->saddr; - ip_rt_put(rt); - } - } - flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, flow_flags, faddr, saddr, dport, inet->inet_sport); + if (!saddr && ipc.oif) + l3mdev_get_saddr(net, ipc.oif, fl4); + security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) { -- cgit v1.2.3 From 4ebc7660ab4559cad10b6595e05f70562bb26dc5 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:55 +0200 Subject: bridge: netlink: export port's root id Add IFLA_BRPORT_ROOT_ID to allow getting the designated root id via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index c5b15bfeabe2..c45c1d7894e7 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -292,6 +292,7 @@ enum { IFLA_BRPORT_PROXYARP, /* proxy ARP */ IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ + IFLA_BRPORT_ROOT_ID, /* designated root */ __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 330abf4b033a..cad4050310ee 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -127,6 +127,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + 0; } @@ -160,7 +161,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, - !!(p->flags & BR_PROXYARP_WIFI))) + !!(p->flags & BR_PROXYARP_WIFI)) || + nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id), + &p->designated_root)) return -EMSGSIZE; return 0; -- cgit v1.2.3 From 80df9a2692edf7afffda9282e716e7b1df198e07 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:56 +0200 Subject: bridge: netlink: export port's bridge id Add IFLA_BRPORT_BRIDGE_ID to allow getting the designated bridge id via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index c45c1d7894e7..e891c32c9993 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -293,6 +293,7 @@ enum { IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ IFLA_BRPORT_ROOT_ID, /* designated root */ + IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index cad4050310ee..c3e0b73d660d 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -128,6 +128,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + 0; } @@ -163,7 +164,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, !!(p->flags & BR_PROXYARP_WIFI)) || nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id), - &p->designated_root)) + &p->designated_root) || + nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id), + &p->designated_bridge)) return -EMSGSIZE; return 0; -- cgit v1.2.3 From 96f94e7f4a216282a24819968184c881e6343692 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:57 +0200 Subject: bridge: netlink: export port's designated cost and port Add IFLA_BRPORT_DESIGNATED_(COST|PORT) to allow getting the port's designated cost and port respectively via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ net/bridge/br_netlink.c | 6 +++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index e891c32c9993..837caf940135 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -294,6 +294,8 @@ enum { IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ IFLA_BRPORT_ROOT_ID, /* designated root */ IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ + IFLA_BRPORT_DESIGNATED_PORT, + IFLA_BRPORT_DESIGNATED_COST, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index c3e0b73d660d..678d22747044 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -129,6 +129,8 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ + + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */ + 0; } @@ -166,7 +168,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id), &p->designated_root) || nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id), - &p->designated_bridge)) + &p->designated_bridge) || + nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, p->designated_port) || + nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost)) return -EMSGSIZE; return 0; -- cgit v1.2.3 From 42d452c4b5e7bf0e3024fa9512ec462f70545ae5 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:58 +0200 Subject: bridge: netlink: export port's id and number Add IFLA_BRPORT_(ID|NO) to allow getting port's port_id and port_no respectively via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ net/bridge/br_netlink.c | 6 +++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 837caf940135..6857563eb27c 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -296,6 +296,8 @@ enum { IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ IFLA_BRPORT_DESIGNATED_PORT, IFLA_BRPORT_DESIGNATED_COST, + IFLA_BRPORT_ID, + IFLA_BRPORT_NO, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 678d22747044..e51332792c3c 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -131,6 +131,8 @@ static inline size_t br_port_info_size(void) + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */ + + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_ID */ + + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */ + 0; } @@ -170,7 +172,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id), &p->designated_bridge) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, p->designated_port) || - nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost)) + nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost) || + nla_put_u16(skb, IFLA_BRPORT_ID, p->port_id) || + nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no)) return -EMSGSIZE; return 0; -- cgit v1.2.3 From e08e838ac5707cb1f1294e0d53b31997a0367b99 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:59 +0200 Subject: bridge: netlink: export port's topology_change_ack and config_pending Add IFLA_BRPORT_TOPOLOGY_CHANGE_ACK and IFLA_BRPORT_CONFIG_PENDING to allow getting port's topology_change_ack and config_pending respectively via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ net/bridge/br_netlink.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 6857563eb27c..1d6aeb1bbe95 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -298,6 +298,8 @@ enum { IFLA_BRPORT_DESIGNATED_COST, IFLA_BRPORT_ID, IFLA_BRPORT_NO, + IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, + IFLA_BRPORT_CONFIG_PENDING, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e51332792c3c..433d632ad7d0 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -133,6 +133,8 @@ static inline size_t br_port_info_size(void) + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */ + + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_TOPOLOGY_CHANGE_ACK */ + + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_CONFIG_PENDING */ + 0; } @@ -174,7 +176,10 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, p->designated_port) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost) || nla_put_u16(skb, IFLA_BRPORT_ID, p->port_id) || - nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no)) + nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no) || + nla_put_u8(skb, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, + p->topology_change_ack) || + nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending)) return -EMSGSIZE; return 0; -- cgit v1.2.3 From 61c0a9a83e0b12c712cd686172446aba8ea48685 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:12:00 +0200 Subject: bridge: netlink: export port's timer values Add the following attributes in order to export port's timer values: IFLA_BRPORT_MESSAGE_AGE_TIMER, IFLA_BRPORT_FORWARD_DELAY_TIMER and IFLA_BRPORT_HOLD_TIMER. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 3 +++ net/bridge/br_netlink.c | 14 ++++++++++++++ 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 1d6aeb1bbe95..9c17f605e013 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -300,6 +300,9 @@ enum { IFLA_BRPORT_NO, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, IFLA_BRPORT_CONFIG_PENDING, + IFLA_BRPORT_MESSAGE_AGE_TIMER, + IFLA_BRPORT_FORWARD_DELAY_TIMER, + IFLA_BRPORT_HOLD_TIMER, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 433d632ad7d0..04b0e5072686 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -135,6 +135,9 @@ static inline size_t br_port_info_size(void) + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_TOPOLOGY_CHANGE_ACK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_CONFIG_PENDING */ + + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_MESSAGE_AGE_TIMER */ + + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_FORWARD_DELAY_TIMER */ + + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ + 0; } @@ -156,6 +159,7 @@ static int br_port_fill_attrs(struct sk_buff *skb, const struct net_bridge_port *p) { u8 mode = !!(p->flags & BR_HAIRPIN_MODE); + u64 timerval; if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) || nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) || @@ -182,6 +186,16 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending)) return -EMSGSIZE; + timerval = br_timer_value(&p->message_age_timer); + if (nla_put_u64(skb, IFLA_BRPORT_MESSAGE_AGE_TIMER, timerval)) + return -EMSGSIZE; + timerval = br_timer_value(&p->forward_delay_timer); + if (nla_put_u64(skb, IFLA_BRPORT_FORWARD_DELAY_TIMER, timerval)) + return -EMSGSIZE; + timerval = br_timer_value(&p->hold_timer); + if (nla_put_u64(skb, IFLA_BRPORT_HOLD_TIMER, timerval)) + return -EMSGSIZE; + return 0; } -- cgit v1.2.3 From 9b0c6e4deb3df91bf0aea8158ea77dc58c9d90b6 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:12:01 +0200 Subject: bridge: netlink: allow to flush port's fdb Add IFLA_BRPORT_FLUSH to allow flushing port's fdb similar to sysfs's flush. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 9c17f605e013..fcea39a56095 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -303,6 +303,7 @@ enum { IFLA_BRPORT_MESSAGE_AGE_TIMER, IFLA_BRPORT_FORWARD_DELAY_TIMER, IFLA_BRPORT_HOLD_TIMER, + IFLA_BRPORT_FLUSH, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 04b0e5072686..6468166d6bdc 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -631,6 +631,9 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) return err; } + if (tb[IFLA_BRPORT_FLUSH]) + br_fdb_delete_by_port(p->br, p, 0, 0); + br_port_flags_change(p, old_flags ^ p->flags); return 0; } -- cgit v1.2.3 From 5d6ae479ab7ddf77bb22bdf739268581453ff886 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:12:02 +0200 Subject: bridge: netlink: add support for port's multicast_router attribute Add IFLA_BRPORT_MULTICAST_ROUTER to allow setting/getting port's multicast_router via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index fcea39a56095..e3b6217f34f1 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -304,6 +304,7 @@ enum { IFLA_BRPORT_FORWARD_DELAY_TIMER, IFLA_BRPORT_HOLD_TIMER, IFLA_BRPORT_FLUSH, + IFLA_BRPORT_MULTICAST_ROUTER, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 6468166d6bdc..d78b4429505a 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -138,6 +138,9 @@ static inline size_t br_port_info_size(void) + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_MESSAGE_AGE_TIMER */ + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_FORWARD_DELAY_TIMER */ + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ +#endif + 0; } @@ -196,6 +199,12 @@ static int br_port_fill_attrs(struct sk_buff *skb, if (nla_put_u64(skb, IFLA_BRPORT_HOLD_TIMER, timerval)) return -EMSGSIZE; +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER, + p->multicast_router)) + return -EMSGSIZE; +#endif + return 0; } @@ -560,6 +569,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, + [IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 }, }; /* Change the state of the port and notify spanning tree */ @@ -634,6 +644,15 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) if (tb[IFLA_BRPORT_FLUSH]) br_fdb_delete_by_port(p->br, p, 0, 0); +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (tb[IFLA_BRPORT_MULTICAST_ROUTER]) { + u8 mcast_router = nla_get_u8(tb[IFLA_BRPORT_MULTICAST_ROUTER]); + + err = br_multicast_set_port_router(p, mcast_router); + if (err) + return err; + } +#endif br_port_flags_change(p, old_flags ^ p->flags); return 0; } -- cgit v1.2.3 From 6c566dd5a1253f73458ce6ba6cf3830e9d38c132 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Wed, 7 Oct 2015 15:32:13 +0200 Subject: Bluetooth: Send index information updates to monitor channel The Bluetooth public device address might change during controller setup and it makes it a lot simpler for monitoring tools if they just get told what the new address is. In addition include the manufacturer / company information of the controller. That allows for easy vendor specific HCI command and event handling. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_mon.h | 7 +++++++ net/bluetooth/hci_sock.c | 25 ++++++++++++++++++++++++- 2 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h index 37e4283d1d68..842bb754a078 100644 --- a/include/net/bluetooth/hci_mon.h +++ b/include/net/bluetooth/hci_mon.h @@ -41,6 +41,7 @@ struct hci_mon_hdr { #define HCI_MON_SCO_RX_PKT 7 #define HCI_MON_OPEN_INDEX 8 #define HCI_MON_CLOSE_INDEX 9 +#define HCI_MON_INDEX_INFO 10 struct hci_mon_new_index { __u8 type; @@ -50,4 +51,10 @@ struct hci_mon_new_index { } __packed; #define HCI_MON_NEW_INDEX_SIZE 16 +struct hci_mon_index_info { + bdaddr_t bdaddr; + __le16 manufacturer; +} __packed; +#define HCI_MON_INDEX_INFO_SIZE 8 + #endif /* __HCI_MON_H */ diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 64ebe84989d1..9bf30db89d89 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -303,6 +303,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) { struct hci_mon_hdr *hdr; struct hci_mon_new_index *ni; + struct hci_mon_index_info *ii; struct sk_buff *skb; __le16 opcode; @@ -312,7 +313,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) if (!skb) return NULL; - ni = (void *) skb_put(skb, HCI_MON_NEW_INDEX_SIZE); + ni = (void *)skb_put(skb, HCI_MON_NEW_INDEX_SIZE); ni->type = hdev->dev_type; ni->bus = hdev->bus; bacpy(&ni->bdaddr, &hdev->bdaddr); @@ -329,6 +330,18 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) opcode = cpu_to_le16(HCI_MON_DEL_INDEX); break; + case HCI_DEV_UP: + skb = bt_skb_alloc(HCI_MON_INDEX_INFO_SIZE, GFP_ATOMIC); + if (!skb) + return NULL; + + ii = (void *)skb_put(skb, HCI_MON_INDEX_INFO_SIZE); + bacpy(&ii->bdaddr, &hdev->bdaddr); + ii->manufacturer = cpu_to_le16(hdev->manufacturer); + + opcode = cpu_to_le16(HCI_MON_INDEX_INFO); + break; + case HCI_DEV_OPEN: skb = bt_skb_alloc(0, GFP_ATOMIC); if (!skb) @@ -384,6 +397,16 @@ static void send_monitor_replay(struct sock *sk) if (sock_queue_rcv_skb(sk, skb)) kfree_skb(skb); + + if (!test_bit(HCI_UP, &hdev->flags)) + continue; + + skb = create_monitor_event(hdev, HCI_DEV_UP); + if (!skb) + continue; + + if (sock_queue_rcv_skb(sk, skb)) + kfree_skb(skb); } read_unlock(&hci_dev_list_lock); -- cgit v1.2.3 From e875ff84079b9e7d3ce24b97e3396230d41044d4 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Wed, 7 Oct 2015 16:38:35 +0200 Subject: Bluetooth: Add support for vendor specific diagnostic channel Introduce hci_recv_diag function for HCI drivers to allow sending vendor specific diagnostic messages into the Bluetooth core stack. The messages are not processed, but they are forwarded to the monitor channel and can be retrieved by user space diagnostic tools. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + include/net/bluetooth/hci_core.h | 1 + include/net/bluetooth/hci_mon.h | 1 + net/bluetooth/hci_core.c | 15 +++++++++++++++ net/bluetooth/hci_sock.c | 3 +++ 5 files changed, 21 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index e7f938cac7c6..cf75c4391945 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -262,6 +262,7 @@ enum { #define HCI_ACLDATA_PKT 0x02 #define HCI_SCODATA_PKT 0x03 #define HCI_EVENT_PKT 0x04 +#define HCI_DIAG_PKT 0xf0 #define HCI_VENDOR_PKT 0xff /* HCI packet types */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 61dc786358be..d473b67a2c65 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1066,6 +1066,7 @@ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance); void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); +int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); void hci_init_sysfs(struct hci_dev *hdev); void hci_conn_init_sysfs(struct hci_conn *conn); diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h index 842bb754a078..2b67567cf28d 100644 --- a/include/net/bluetooth/hci_mon.h +++ b/include/net/bluetooth/hci_mon.h @@ -42,6 +42,7 @@ struct hci_mon_hdr { #define HCI_MON_OPEN_INDEX 8 #define HCI_MON_CLOSE_INDEX 9 #define HCI_MON_INDEX_INFO 10 +#define HCI_MON_VENDOR_DIAG 11 struct hci_mon_new_index { __u8 type; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 40a67017bd32..8193845a9b60 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3493,6 +3493,21 @@ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb) } EXPORT_SYMBOL(hci_recv_frame); +/* Receive diagnostic message from HCI drivers */ +int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb) +{ + /* Time stamp */ + __net_timestamp(skb); + + /* Mark as diagnostic packet and send to monitor */ + bt_cb(skb)->pkt_type = HCI_DIAG_PKT; + hci_send_to_monitor(hdev, skb); + + kfree_skb(skb); + return 0; +} +EXPORT_SYMBOL(hci_recv_diag); + /* ---- Interface to upper protocols ---- */ int hci_register_cb(struct hci_cb *cb) diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 9bf30db89d89..9a100c1fd7b5 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -279,6 +279,9 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) else opcode = cpu_to_le16(HCI_MON_SCO_TX_PKT); break; + case HCI_DIAG_PKT: + opcode = cpu_to_le16(HCI_MON_VENDOR_DIAG); + break; default: return; } -- cgit v1.2.3 From 4b4113d6dbdbdac095743c05f694af9b7cdc9a44 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Wed, 7 Oct 2015 19:52:35 +0200 Subject: Bluetooth: Add debugfs entry for setting vendor diagnostic mode This adds a new debugfs entry for enabling and disabling the vendor diagnostic mode. It is only exposed for drivers that provide the set_diag driver callback and actually have an option for vendor specific diagnostic information. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + include/net/bluetooth/hci_core.h | 1 + net/bluetooth/hci_core.c | 63 ++++++++++++++++++++++++++++++++++++++-- 3 files changed, 62 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index cf75c4391945..a26ff28ca878 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -240,6 +240,7 @@ enum { HCI_LE_SCAN_INTERRUPTED, HCI_DUT_MODE, + HCI_VENDOR_DIAG, HCI_FORCE_BREDR_SMP, HCI_FORCE_STATIC_ADDR, diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d473b67a2c65..f28470e59682 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -398,6 +398,7 @@ struct hci_dev { int (*send)(struct hci_dev *hdev, struct sk_buff *skb); void (*notify)(struct hci_dev *hdev, unsigned int evt); void (*hw_error)(struct hci_dev *hdev, u8 code); + int (*set_diag)(struct hci_dev *hdev, bool enable); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); }; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 8193845a9b60..e75bc545b48e 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -134,6 +134,56 @@ static const struct file_operations dut_mode_fops = { .llseek = default_llseek, }; +static ssize_t vendor_diag_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[3]; + + buf[0] = hci_dev_test_flag(hdev, HCI_VENDOR_DIAG) ? 'Y': 'N'; + buf[1] = '\n'; + buf[2] = '\0'; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static ssize_t vendor_diag_write(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[32]; + size_t buf_size = min(count, (sizeof(buf)-1)); + bool enable; + int err; + + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + if (strtobool(buf, &enable)) + return -EINVAL; + + hci_req_lock(hdev); + err = hdev->set_diag(hdev, enable); + hci_req_unlock(hdev); + + if (err < 0) + return err; + + if (enable) + hci_dev_set_flag(hdev, HCI_VENDOR_DIAG); + else + hci_dev_clear_flag(hdev, HCI_VENDOR_DIAG); + + return count; +} + +static const struct file_operations vendor_diag_fops = { + .open = simple_open, + .read = vendor_diag_read, + .write = vendor_diag_write, + .llseek = default_llseek, +}; + /* ---- HCI requests ---- */ static void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, @@ -850,12 +900,19 @@ static int __hci_init(struct hci_dev *hdev) if (err < 0) return err; - /* The Device Under Test (DUT) mode is special and available for - * all controller types. So just create it early on. - */ if (hci_dev_test_flag(hdev, HCI_SETUP)) { + /* The Device Under Test (DUT) mode is special and available + * for all controller types. So just create it early on. + */ debugfs_create_file("dut_mode", 0644, hdev->debugfs, hdev, &dut_mode_fops); + + /* When the driver supports the set_diag callback, then + * expose an entry to modify the vendor diagnostic setting. + */ + if (hdev->set_diag) + debugfs_create_file("vendor_diag", 0644, hdev->debugfs, + hdev, &vendor_diag_fops); } err = __hci_req_sync(hdev, hci_init2_req, 0, HCI_INIT_TIMEOUT); -- cgit v1.2.3 From 13206b6bff3b15b724926a222406476bf2c23c40 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:35 -0500 Subject: net: Pass net into dst_output and remove dst_output_okfn Replace dst_output_okfn with dst_output Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/dst.h | 6 +----- net/decnet/dn_nsp_out.c | 4 ++-- net/ipv4/ip_forward.c | 2 +- net/ipv4/ip_output.c | 7 ++++--- net/ipv4/ip_vti.c | 2 +- net/ipv4/ipmr.c | 2 +- net/ipv4/raw.c | 2 +- net/ipv4/xfrm4_output.c | 2 +- net/ipv6/ip6_output.c | 4 ++-- net/ipv6/ip6_vti.c | 2 +- net/ipv6/ip6mr.c | 2 +- net/ipv6/mcast.c | 4 ++-- net/ipv6/ndisc.c | 2 +- net/ipv6/output_core.c | 5 +++-- net/ipv6/raw.c | 2 +- net/ipv6/xfrm6_output.c | 2 +- net/netfilter/ipvs/ip_vs_xmit.c | 4 ++-- net/xfrm/xfrm_output.c | 2 +- net/xfrm/xfrm_policy.c | 2 +- 19 files changed, 28 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 779206c15f8b..fdd01fed1a7b 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -454,14 +454,10 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout) } /* Output packet to network from transport. */ -static inline int dst_output(struct sock *sk, struct sk_buff *skb) +static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return skb_dst(skb)->output(sk, skb); } -static inline int dst_output_okfn(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - return dst_output(sk, skb); -} /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 4b02dd300f50..849805e7af52 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -85,7 +85,7 @@ static void dn_nsp_send(struct sk_buff *skb) if (dst) { try_again: skb_dst_set(skb, dst); - dst_output(skb->sk, skb); + dst_output(&init_net, skb->sk, skb); return; } @@ -582,7 +582,7 @@ static __inline__ void dn_nsp_do_disc(struct sock *sk, unsigned char msgflg, * associations. */ skb_dst_set(skb, dst_clone(dst)); - dst_output(skb->sk, skb); + dst_output(&init_net, skb->sk, skb); } diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index d66cfb35ba74..da0d7ce85844 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -72,7 +72,7 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s ip_forward_options(skb); skb_sender_cpu_clear(skb); - return dst_output(sk, skb); + return dst_output(net, sk, skb); } int ip_forward(struct sk_buff *skb) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 1030f48d66e1..c94efb22f380 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -105,7 +105,7 @@ static int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb) ip_send_check(iph); return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, - dst_output_okfn); + dst_output); } int __ip_local_out(struct sk_buff *skb) @@ -115,11 +115,12 @@ int __ip_local_out(struct sk_buff *skb) int ip_local_out_sk(struct sock *sk, struct sk_buff *skb) { + struct net *net = dev_net(skb_dst(skb)->dev); int err; err = __ip_local_out_sk(sk, skb); if (likely(err == 1)) - err = dst_output(sk, skb); + err = dst_output(net, sk, skb); return err; } @@ -276,7 +277,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { IPCB(skb)->flags |= IPSKB_REROUTED; - return dst_output(sk, skb); + return dst_output(net, sk, skb); } #endif mtu = ip_skb_dst_mtu(skb); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 3b87ec5178f9..4d8f0b698777 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -197,7 +197,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; - err = dst_output(skb->sk, skb); + err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) err = skb->len; iptunnel_xmit_stats(err, &dev->stats, dev->tstats); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index cfcb996ec51b..fc42525d8694 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1689,7 +1689,7 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk, if (unlikely(opt->optlen)) ip_forward_options(skb); - return dst_output(sk, skb); + return dst_output(net, sk, skb); } /* diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 09a07e8b2f35..8c0d0bdc2a7c 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -413,7 +413,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, - dst_output_okfn); + dst_output); if (err > 0) err = net_xmit_errno(err); if (err) diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index cd6be736e19f..17db61f4b439 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -87,7 +87,7 @@ static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) #ifdef CONFIG_NETFILTER if (!x) { IPCB(skb)->flags |= IPSKB_REROUTED; - return dst_output(sk, skb); + return dst_output(net, sk, skb); } #endif diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index caf7d14a1bdd..0171e762e03c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -233,7 +233,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, */ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, (struct sock *)sk, skb, NULL, dst->dev, - dst_output_okfn); + dst_output); } skb->dev = dst->dev; @@ -333,7 +333,7 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { skb_sender_cpu_clear(skb); - return dst_output(sk, skb); + return dst_output(net, sk, skb); } static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index f96f1c19b4a8..0a8610b33d79 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -482,7 +482,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) return -EMSGSIZE; } - err = dst_output(skb->sk, skb); + err = dst_output(t->net, skb->sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 5e5d16e7ce85..ad19136086dd 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1991,7 +1991,7 @@ static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct IPSTATS_MIB_OUTFORWDATAGRAMS); IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTOCTETS, skb->len); - return dst_output(sk, skb); + return dst_output(net, sk, skb); } /* diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index a8bf57ca74d3..124338a39e29 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1646,7 +1646,7 @@ static void mld_sendpack(struct sk_buff *skb) err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, net->ipv6.igmp_sk, skb, NULL, skb->dev, - dst_output_okfn); + dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); @@ -2010,7 +2010,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) skb_dst_set(skb, dst); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb->dev, - dst_output_okfn); + dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 7089c305245c..b18012f9f9fc 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -465,7 +465,7 @@ static void ndisc_send_skb(struct sk_buff *skb, err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, dst->dev, - dst_output_okfn); + dst_output); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index e77102c4f804..4337147ee23d 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -151,7 +151,7 @@ static int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, - dst_output_okfn); + dst_output); } int __ip6_local_out(struct sk_buff *skb) @@ -162,11 +162,12 @@ EXPORT_SYMBOL_GPL(__ip6_local_out); int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) { + struct net *net = dev_net(skb_dst(skb)->dev); int err; err = __ip6_local_out_sk(sk, skb); if (likely(err == 1)) - err = dst_output(sk, skb); + err = dst_output(net, sk, skb); return err; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index fec0151522a2..dc65ec198f7c 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -655,7 +655,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, - NULL, rt->dst.dev, dst_output_okfn); + NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 4cefda009f53..c9a5bd5fea9c 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -147,7 +147,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) #ifdef CONFIG_NETFILTER if (!x) { IP6CB(skb)->flags |= IP6SKB_REROUTED; - return dst_output(sk, skb); + return dst_output(net, sk, skb); } #endif diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 77182b9750cd..504d1fcf5454 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -576,7 +576,7 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, if (!skb->sk) skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, - NULL, skb_dst(skb)->dev, dst_output_okfn); + NULL, skb_dst(skb)->dev, dst_output); } else ret = NF_ACCEPT; @@ -598,7 +598,7 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (!skb->sk) skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, - NULL, skb_dst(skb)->dev, dst_output_okfn); + NULL, skb_dst(skb)->dev, dst_output); } else ret = NF_ACCEPT; return ret; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index c48a4b8582bb..88752b0c07d8 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -141,7 +141,7 @@ int xfrm_output_resume(struct sk_buff *skb, int err) goto out; if (!skb_dst(skb)->xfrm) - return dst_output(skb->sk, skb); + return dst_output(net, skb->sk, skb); err = nf_hook(skb_dst(skb)->ops->family, NF_INET_POST_ROUTING, net, skb->sk, skb, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index be1776bc5673..f4f2d987f8f0 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1944,7 +1944,7 @@ static void xfrm_policy_queue_process(unsigned long arg) skb_dst_drop(skb); skb_dst_set(skb, dst); - dst_output(skb->sk, skb); + dst_output(net, skb->sk, skb); } out: -- cgit v1.2.3 From 4ebdfba73c09d8568d891bae87c40fad43dd7f41 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:36 -0500 Subject: dst: Pass a sk into .local_out For consistency with the other similar methods in the kernel pass a struct sock into the dst_ops .local_out method. Simplifying the socket passing case is needed a prequel to passing a struct net reference into .local_out. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- drivers/net/vrf.c | 4 ++-- include/net/dst_ops.h | 2 +- include/net/ip.h | 1 + include/net/ipv6.h | 1 + net/ipv4/ip_output.c | 2 +- net/ipv4/route.c | 2 +- net/ipv4/xfrm4_policy.c | 2 +- net/ipv6/output_core.c | 2 +- net/ipv6/route.c | 2 +- net/ipv6/xfrm6_policy.c | 2 +- net/xfrm/xfrm_output.c | 2 +- 11 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 64499766e00f..1039eb5f6c2a 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -74,9 +74,9 @@ static struct dst_entry *vrf_ip_check(struct dst_entry *dst, u32 cookie) return dst; } -static int vrf_ip_local_out(struct sk_buff *skb) +static int vrf_ip_local_out(struct sock *sk, struct sk_buff *skb) { - return ip_local_out(skb); + return ip_local_out_sk(sk, skb); } static unsigned int vrf_v4_mtu(const struct dst_entry *dst) diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index d64253914a6a..3f26a6af444e 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -28,7 +28,7 @@ struct dst_ops { struct sk_buff *skb, u32 mtu); void (*redirect)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); - int (*local_out)(struct sk_buff *skb); + int (*local_out)(struct sock *sk, struct sk_buff *skb); struct neighbour * (*neigh_lookup)(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); diff --git a/include/net/ip.h b/include/net/ip.h index dd06ab3669f9..ea1f721f7224 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -112,6 +112,7 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb); int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); +int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb); int __ip_local_out(struct sk_buff *skb); int ip_local_out_sk(struct sock *sk, struct sk_buff *skb); static inline int ip_local_out(struct sk_buff *skb) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 3dde042bcd3f..56920262dbe9 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -865,6 +865,7 @@ int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); +int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb); int __ip6_local_out(struct sk_buff *skb); int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct sk_buff *skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c94efb22f380..c38dfd7404fb 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -96,7 +96,7 @@ void ip_send_check(struct iphdr *iph) } EXPORT_SYMBOL(ip_send_check); -static int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb) +int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); struct iphdr *iph = ip_hdr(skb); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bf1486bd7e81..638b976008b7 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -165,7 +165,7 @@ static struct dst_ops ipv4_dst_ops = { .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, .redirect = ip_do_redirect, - .local_out = __ip_local_out, + .local_out = __ip_local_out_sk, .neigh_lookup = ipv4_neigh_lookup, }; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index f2606b9056bb..d46d99f9cabd 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -243,7 +243,7 @@ static struct dst_ops xfrm4_dst_ops = { .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm4_dst_destroy, .ifdown = xfrm4_dst_ifdown, - .local_out = __ip_local_out, + .local_out = __ip_local_out_sk, .gc_thresh = 32768, }; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 4337147ee23d..e5affb5fe095 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -138,7 +138,7 @@ int ip6_dst_hoplimit(struct dst_entry *dst) EXPORT_SYMBOL(ip6_dst_hoplimit); #endif -static int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) +int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); int len; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d3d946773a3e..b62a507cc1a5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -226,7 +226,7 @@ static struct dst_ops ip6_dst_ops_template = { .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, .redirect = rt6_do_redirect, - .local_out = __ip6_local_out, + .local_out = __ip6_local_out_sk, .neigh_lookup = ip6_neigh_lookup, }; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 08c9c93f3527..f7876830f263 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -285,7 +285,7 @@ static struct dst_ops xfrm6_dst_ops = { .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, - .local_out = __ip6_local_out, + .local_out = __ip6_local_out_sk, .gc_thresh = 32768, }; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 88752b0c07d8..a7a254fe7985 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -136,7 +136,7 @@ int xfrm_output_resume(struct sk_buff *skb, int err) while (likely((err = xfrm_output_one(skb, err)) == 0)) { nf_reset(skb); - err = skb_dst(skb)->ops->local_out(skb); + err = skb_dst(skb)->ops->local_out(skb->sk, skb); if (unlikely(err != 1)) goto out; -- cgit v1.2.3 From b92dacd45698e120104ff81066ceb534916090d9 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:37 -0500 Subject: ipv4: Merge __ip_local_out and __ip_local_out_sk Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/ip.h | 3 +-- net/ipv4/ip_output.c | 9 ++------- net/ipv4/route.c | 2 +- net/ipv4/xfrm4_policy.c | 2 +- 4 files changed, 5 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index ea1f721f7224..46272e04f3b6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -112,8 +112,7 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb); int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); -int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb); -int __ip_local_out(struct sk_buff *skb); +int __ip_local_out(struct sock *sk, struct sk_buff *skb); int ip_local_out_sk(struct sock *sk, struct sk_buff *skb); static inline int ip_local_out(struct sk_buff *skb) { diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c38dfd7404fb..66c627b85a91 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -96,7 +96,7 @@ void ip_send_check(struct iphdr *iph) } EXPORT_SYMBOL(ip_send_check); -int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb) +int __ip_local_out(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); struct iphdr *iph = ip_hdr(skb); @@ -108,17 +108,12 @@ int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb) dst_output); } -int __ip_local_out(struct sk_buff *skb) -{ - return __ip_local_out_sk(skb->sk, skb); -} - int ip_local_out_sk(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); int err; - err = __ip_local_out_sk(sk, skb); + err = __ip_local_out(sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 638b976008b7..bf1486bd7e81 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -165,7 +165,7 @@ static struct dst_ops ipv4_dst_ops = { .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, .redirect = ip_do_redirect, - .local_out = __ip_local_out_sk, + .local_out = __ip_local_out, .neigh_lookup = ipv4_neigh_lookup, }; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index d46d99f9cabd..f2606b9056bb 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -243,7 +243,7 @@ static struct dst_ops xfrm4_dst_ops = { .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm4_dst_destroy, .ifdown = xfrm4_dst_ifdown, - .local_out = __ip_local_out_sk, + .local_out = __ip_local_out, .gc_thresh = 32768, }; -- cgit v1.2.3 From e2cb77db089796f163092326ca25512845df7a3a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:38 -0500 Subject: ipv4: Merge ip_local_out and ip_local_out_sk It is confusing and silly hiding a parameter so modify all of the callers to pass in the appropriate socket or skb->sk if no socket is known. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_core.c | 2 +- drivers/net/ppp/pptp.c | 2 +- drivers/net/vrf.c | 4 ++-- include/net/ip.h | 6 +----- net/ipv4/igmp.c | 4 ++-- net/ipv4/ip_output.c | 10 +++++----- net/ipv4/ip_tunnel_core.c | 2 +- net/ipv4/netfilter/ipt_SYNPROXY.c | 2 +- net/ipv4/netfilter/nf_dup_ipv4.c | 2 +- net/ipv4/netfilter/nf_reject_ipv4.c | 2 +- net/netfilter/ipvs/ip_vs_xmit.c | 2 +- 11 files changed, 17 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 207f62e8de9a..c75ad39c752f 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -364,7 +364,7 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb) } skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); - err = ip_local_out(skb); + err = ip_local_out(skb->sk, skb); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; else diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 686f37daa262..6bef7be10671 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -282,7 +282,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) ip_select_ident(sock_net(sk), skb, NULL); ip_send_check(iph); - ip_local_out(skb); + ip_local_out(skb->sk, skb); return 1; tx_error: diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 1039eb5f6c2a..231f9d85d4eb 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -76,7 +76,7 @@ static struct dst_entry *vrf_ip_check(struct dst_entry *dst, u32 cookie) static int vrf_ip_local_out(struct sock *sk, struct sk_buff *skb) { - return ip_local_out_sk(sk, skb); + return ip_local_out(sk, skb); } static unsigned int vrf_v4_mtu(const struct dst_entry *dst) @@ -222,7 +222,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, RT_SCOPE_LINK); } - ret = ip_local_out(skb); + ret = ip_local_out(skb->sk, skb); if (unlikely(net_xmit_eval(ret))) vrf_dev->stats.tx_errors++; else diff --git a/include/net/ip.h b/include/net/ip.h index 46272e04f3b6..03e80f936847 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -113,11 +113,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); int __ip_local_out(struct sock *sk, struct sk_buff *skb); -int ip_local_out_sk(struct sock *sk, struct sk_buff *skb); -static inline int ip_local_out(struct sk_buff *skb) -{ - return ip_local_out_sk(skb->sk, skb); -} +int ip_local_out(struct sock *sk, struct sk_buff *skb); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); void ip_init(void); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index de6d4c8ba600..43375d9e02ab 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -397,7 +397,7 @@ static int igmpv3_sendpack(struct sk_buff *skb) pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); - return ip_local_out(skb); + return ip_local_out(skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) @@ -739,7 +739,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, ih->group = group; ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); - return ip_local_out(skb); + return ip_local_out(skb->sk, skb); } static void igmp_gq_timer_expire(unsigned long data) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 66c627b85a91..10366ee03bec 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -108,7 +108,7 @@ int __ip_local_out(struct sock *sk, struct sk_buff *skb) dst_output); } -int ip_local_out_sk(struct sock *sk, struct sk_buff *skb) +int ip_local_out(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); int err; @@ -119,7 +119,7 @@ int ip_local_out_sk(struct sock *sk, struct sk_buff *skb) return err; } -EXPORT_SYMBOL_GPL(ip_local_out_sk); +EXPORT_SYMBOL_GPL(ip_local_out); static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) { @@ -169,7 +169,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, skb->mark = sk->sk_mark; /* Send it out. */ - return ip_local_out(skb); + return ip_local_out(skb->sk, skb); } EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); @@ -456,7 +456,7 @@ packet_routed: skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - res = ip_local_out_sk(sk, skb); + res = ip_local_out(sk, skb); rcu_read_unlock(); return res; @@ -1436,7 +1436,7 @@ int ip_send_skb(struct net *net, struct sk_buff *skb) { int err; - err = ip_local_out(skb); + err = ip_local_out(skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 84dce6a92f93..8d85ecd1ced5 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -79,7 +79,7 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __ip_select_ident(dev_net(rt->dst.dev), iph, skb_shinfo(skb)->gso_segs ?: 1); - err = ip_local_out_sk(sk, skb); + err = ip_local_out(sk, skb); if (unlikely(net_xmit_eval(err))) pkt_len = 0; return pkt_len; diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 6a6e762ab27f..473faf73b194 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -63,7 +63,7 @@ synproxy_send_tcp(const struct synproxy_net *snet, nf_conntrack_get(nfct); } - ip_local_out(nskb); + ip_local_out(nskb->sk, nskb); return; free_nskb: diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c index ce2a59e5c665..0b9abfbf6577 100644 --- a/net/ipv4/netfilter/nf_dup_ipv4.c +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -92,7 +92,7 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, if (nf_dup_ipv4_route(net, skb, gw, oif)) { __this_cpu_write(nf_skb_duplicated, true); - ip_local_out(skb); + ip_local_out(skb->sk, skb); __this_cpu_write(nf_skb_duplicated, false); } else { kfree_skb(skb); diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 2f5e925d3264..dcc125cb0441 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -157,7 +157,7 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) dev_queue_xmit(nskb); } else #endif - ip_local_out(nskb); + ip_local_out(nskb->sk, nskb); return; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 504d1fcf5454..d77503e635d8 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1049,7 +1049,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, ret = ip_vs_tunnel_xmit_prepare(skb, cp); if (ret == NF_ACCEPT) - ip_local_out(skb); + ip_local_out(skb->sk, skb); else if (ret == NF_DROP) kfree_skb(skb); rcu_read_unlock(); -- cgit v1.2.3 From 9f8955cc468ddb7d08a0e614a45f9a82c4019b00 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:39 -0500 Subject: ipv6: Merge __ip6_local_out and __ip6_local_out_sk Only __ip6_local_out_sk has callers so rename __ip6_local_out_sk __ip6_local_out and remove the previous __ip6_local_out. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/ipv6.h | 3 +-- net/ipv6/output_core.c | 9 ++------- net/ipv6/route.c | 2 +- net/ipv6/xfrm6_policy.c | 2 +- 4 files changed, 5 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 56920262dbe9..be7e7689514b 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -865,8 +865,7 @@ int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); -int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb); -int __ip6_local_out(struct sk_buff *skb); +int __ip6_local_out(struct sock *sk, struct sk_buff *skb); int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct sk_buff *skb); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index e5affb5fe095..f93ae1515387 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -138,7 +138,7 @@ int ip6_dst_hoplimit(struct dst_entry *dst) EXPORT_SYMBOL(ip6_dst_hoplimit); #endif -int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) +int __ip6_local_out(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); int len; @@ -153,11 +153,6 @@ int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); } - -int __ip6_local_out(struct sk_buff *skb) -{ - return __ip6_local_out_sk(skb->sk, skb); -} EXPORT_SYMBOL_GPL(__ip6_local_out); int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) @@ -165,7 +160,7 @@ int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) struct net *net = dev_net(skb_dst(skb)->dev); int err; - err = __ip6_local_out_sk(sk, skb); + err = __ip6_local_out(sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b62a507cc1a5..d3d946773a3e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -226,7 +226,7 @@ static struct dst_ops ip6_dst_ops_template = { .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, .redirect = rt6_do_redirect, - .local_out = __ip6_local_out_sk, + .local_out = __ip6_local_out, .neigh_lookup = ip6_neigh_lookup, }; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index f7876830f263..08c9c93f3527 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -285,7 +285,7 @@ static struct dst_ops xfrm6_dst_ops = { .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, - .local_out = __ip6_local_out_sk, + .local_out = __ip6_local_out, .gc_thresh = 32768, }; -- cgit v1.2.3 From 792883303cdb3a7edd16017d7aba53926189ef41 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:40 -0500 Subject: ipv6: Merge ip6_local_out and ip6_local_out_sk Stop hidding the sk parameter with an inline helper function and make all of the callers pass it, so that it is clear what the function is doing. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_core.c | 2 +- include/net/ip6_tunnel.h | 2 +- include/net/ipv6.h | 3 +-- net/ipv6/ip6_output.c | 2 +- net/ipv6/netfilter/ip6t_SYNPROXY.c | 2 +- net/ipv6/netfilter/nf_dup_ipv6.c | 2 +- net/ipv6/netfilter/nf_reject_ipv6.c | 2 +- net/ipv6/output_core.c | 8 +------- net/netfilter/ipvs/ip_vs_xmit.c | 2 +- 9 files changed, 9 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index c75ad39c752f..75dcf36c0366 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -401,7 +401,7 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) } skb_dst_drop(skb); skb_dst_set(skb, dst); - err = ip6_local_out(skb); + err = ip6_local_out(skb->sk, skb); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; else diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index fa915fa0f703..8f18a8b126e9 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -87,7 +87,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, int pkt_len, err; pkt_len = skb->len - skb_inner_network_offset(skb); - err = ip6_local_out_sk(sk, skb); + err = ip6_local_out(sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index be7e7689514b..30eb1821c184 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -866,8 +866,7 @@ int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); int __ip6_local_out(struct sock *sk, struct sk_buff *skb); -int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb); -int ip6_local_out(struct sk_buff *skb); +int ip6_local_out(struct sock *sk, struct sk_buff *skb); /* * Extension header (options) processing diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 0171e762e03c..31c686b7fcc0 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1692,7 +1692,7 @@ int ip6_send_skb(struct sk_buff *skb) struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); int err; - err = ip6_local_out(skb); + err = ip6_local_out(skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index c2356602158a..c38c3411150b 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -76,7 +76,7 @@ synproxy_send_tcp(const struct synproxy_net *snet, nf_conntrack_get(nfct); } - ip6_local_out(nskb); + ip6_local_out(nskb->sk, nskb); return; free_nskb: diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c index ee0d9a5b16c3..64f3fe5e2719 100644 --- a/net/ipv6/netfilter/nf_dup_ipv6.c +++ b/net/ipv6/netfilter/nf_dup_ipv6.c @@ -68,7 +68,7 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, } if (nf_dup_ipv6_route(net, skb, gw, oif)) { __this_cpu_write(nf_skb_duplicated, true); - ip6_local_out(skb); + ip6_local_out(skb->sk, skb); __this_cpu_write(nf_skb_duplicated, false); } else { kfree_skb(skb); diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 94b4c6dfb400..a4f73e235ca5 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -206,7 +206,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) dev_queue_xmit(nskb); } else #endif - ip6_local_out(nskb); + ip6_local_out(nskb->sk, nskb); } EXPORT_SYMBOL_GPL(nf_send_reset6); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index f93ae1515387..12855811c6a0 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -155,7 +155,7 @@ int __ip6_local_out(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(__ip6_local_out); -int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) +int ip6_local_out(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); int err; @@ -166,10 +166,4 @@ int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) return err; } -EXPORT_SYMBOL_GPL(ip6_local_out_sk); - -int ip6_local_out(struct sk_buff *skb) -{ - return ip6_local_out_sk(skb->sk, skb); -} EXPORT_SYMBOL_GPL(ip6_local_out); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index d77503e635d8..2042b9303136 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1141,7 +1141,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, ret = ip_vs_tunnel_xmit_prepare(skb, cp); if (ret == NF_ACCEPT) - ip6_local_out(skb); + ip6_local_out(skb->sk, skb); else if (ret == NF_DROP) kfree_skb(skb); rcu_read_unlock(); -- cgit v1.2.3 From cf91a99daa4651d0c1f52b8c3d813fd44b43cada Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:45 -0500 Subject: ipv4, ipv6: Pass net into __ip_local_out and __ip6_local_out Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- drivers/net/vrf.c | 2 +- include/net/dst_ops.h | 3 ++- include/net/ip.h | 2 +- include/net/ipv6.h | 2 +- net/ipv4/ip_output.c | 5 ++--- net/ipv6/output_core.c | 5 ++--- net/xfrm/xfrm_output.c | 2 +- 7 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 231f9d85d4eb..b27dc11cd3f2 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -74,7 +74,7 @@ static struct dst_entry *vrf_ip_check(struct dst_entry *dst, u32 cookie) return dst; } -static int vrf_ip_local_out(struct sock *sk, struct sk_buff *skb) +static int vrf_ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { return ip_local_out(sk, skb); } diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 3f26a6af444e..a0d443ca16fc 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -9,6 +9,7 @@ struct kmem_cachep; struct net_device; struct sk_buff; struct sock; +struct net; struct dst_ops { unsigned short family; @@ -28,7 +29,7 @@ struct dst_ops { struct sk_buff *skb, u32 mtu); void (*redirect)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); - int (*local_out)(struct sock *sk, struct sk_buff *skb); + int (*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb); struct neighbour * (*neigh_lookup)(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); diff --git a/include/net/ip.h b/include/net/ip.h index 03e80f936847..34b40381fb9b 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -112,7 +112,7 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb); int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); -int __ip_local_out(struct sock *sk, struct sk_buff *skb); +int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_local_out(struct sock *sk, struct sk_buff *skb); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 30eb1821c184..42834039cf20 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -865,7 +865,7 @@ int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); -int __ip6_local_out(struct sock *sk, struct sk_buff *skb); +int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct sock *sk, struct sk_buff *skb); /* diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a7012f2fa68a..39d3fbe66c68 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -96,9 +96,8 @@ void ip_send_check(struct iphdr *iph) } EXPORT_SYMBOL(ip_send_check); -int __ip_local_out(struct sock *sk, struct sk_buff *skb) +int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); struct iphdr *iph = ip_hdr(skb); iph->tot_len = htons(skb->len); @@ -113,7 +112,7 @@ int ip_local_out(struct sock *sk, struct sk_buff *skb) struct net *net = dev_net(skb_dst(skb)->dev); int err; - err = __ip_local_out(sk, skb); + err = __ip_local_out(net, sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 12855811c6a0..7f64d67b637d 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -138,9 +138,8 @@ int ip6_dst_hoplimit(struct dst_entry *dst) EXPORT_SYMBOL(ip6_dst_hoplimit); #endif -int __ip6_local_out(struct sock *sk, struct sk_buff *skb) +int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); int len; len = skb->len - sizeof(struct ipv6hdr); @@ -160,7 +159,7 @@ int ip6_local_out(struct sock *sk, struct sk_buff *skb) struct net *net = dev_net(skb_dst(skb)->dev); int err; - err = __ip6_local_out(sk, skb); + err = __ip6_local_out(net, sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index a7a254fe7985..cc3676eb6239 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -136,7 +136,7 @@ int xfrm_output_resume(struct sk_buff *skb, int err) while (likely((err = xfrm_output_one(skb, err)) == 0)) { nf_reset(skb); - err = skb_dst(skb)->ops->local_out(skb->sk, skb); + err = skb_dst(skb)->ops->local_out(net, skb->sk, skb); if (unlikely(err != 1)) goto out; -- cgit v1.2.3 From 33224b16ffccb49cf798317670389e0bfba0024c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:46 -0500 Subject: ipv4, ipv6: Pass net into ip_local_out and ip6_local_out Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_core.c | 4 ++-- drivers/net/ppp/pptp.c | 2 +- drivers/net/vrf.c | 4 ++-- include/net/ip.h | 2 +- include/net/ip6_tunnel.h | 2 +- include/net/ipv6.h | 2 +- net/ipv4/igmp.c | 4 ++-- net/ipv4/ip_output.c | 9 ++++----- net/ipv4/ip_tunnel_core.c | 2 +- net/ipv4/netfilter/ipt_SYNPROXY.c | 2 +- net/ipv4/netfilter/nf_dup_ipv4.c | 2 +- net/ipv4/netfilter/nf_reject_ipv4.c | 2 +- net/ipv6/ip6_output.c | 2 +- net/ipv6/netfilter/ip6t_SYNPROXY.c | 2 +- net/ipv6/netfilter/nf_dup_ipv6.c | 2 +- net/ipv6/netfilter/nf_reject_ipv6.c | 2 +- net/ipv6/output_core.c | 3 +-- net/netfilter/ipvs/ip_vs_xmit.c | 4 ++-- 18 files changed, 25 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 976f30b291f6..24f8dbcf854f 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -365,7 +365,7 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb) } skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); - err = ip_local_out(skb->sk, skb); + err = ip_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; else @@ -403,7 +403,7 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) } skb_dst_drop(skb); skb_dst_set(skb, dst); - err = ip6_local_out(skb->sk, skb); + err = ip6_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; else diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 5243ab6ed4d4..fc69e41d0950 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -283,7 +283,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) ip_select_ident(net, skb, NULL); ip_send_check(iph); - ip_local_out(skb->sk, skb); + ip_local_out(net, skb->sk, skb); return 1; tx_error: diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index b27dc11cd3f2..21bb7deb6d58 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -76,7 +76,7 @@ static struct dst_entry *vrf_ip_check(struct dst_entry *dst, u32 cookie) static int vrf_ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { - return ip_local_out(sk, skb); + return ip_local_out(net, sk, skb); } static unsigned int vrf_v4_mtu(const struct dst_entry *dst) @@ -222,7 +222,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, RT_SCOPE_LINK); } - ret = ip_local_out(skb->sk, skb); + ret = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); if (unlikely(net_xmit_eval(ret))) vrf_dev->stats.tx_errors++; else diff --git a/include/net/ip.h b/include/net/ip.h index 34b40381fb9b..7febbab784cd 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -113,7 +113,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); -int ip_local_out(struct sock *sk, struct sk_buff *skb); +int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); void ip_init(void); diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 8f18a8b126e9..aaee6fa02cf1 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -87,7 +87,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, int pkt_len, err; pkt_len = skb->len - skb_inner_network_offset(skb); - err = ip6_local_out(sk, skb); + err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 42834039cf20..fce8120c2be3 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -866,7 +866,7 @@ int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); -int ip6_local_out(struct sock *sk, struct sk_buff *skb); +int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); /* * Extension header (options) processing diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 43375d9e02ab..64aaf3522a59 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -397,7 +397,7 @@ static int igmpv3_sendpack(struct sk_buff *skb) pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); - return ip_local_out(skb->sk, skb); + return ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) @@ -739,7 +739,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, ih->group = group; ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); - return ip_local_out(skb->sk, skb); + return ip_local_out(net, skb->sk, skb); } static void igmp_gq_timer_expire(unsigned long data) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 39d3fbe66c68..9fe100a41e5d 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -107,9 +107,8 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) dst_output); } -int ip_local_out(struct sock *sk, struct sk_buff *skb) +int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); int err; err = __ip_local_out(net, sk, skb); @@ -169,7 +168,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, skb->mark = sk->sk_mark; /* Send it out. */ - return ip_local_out(skb->sk, skb); + return ip_local_out(net, skb->sk, skb); } EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); @@ -457,7 +456,7 @@ packet_routed: skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - res = ip_local_out(sk, skb); + res = ip_local_out(net, sk, skb); rcu_read_unlock(); return res; @@ -1437,7 +1436,7 @@ int ip_send_skb(struct net *net, struct sk_buff *skb) { int err; - err = ip_local_out(skb->sk, skb); + err = ip_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index caef8e2c281d..6cb9009c3d96 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -79,7 +79,7 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, iph->ttl = ttl; __ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1); - err = ip_local_out(sk, skb); + err = ip_local_out(net, sk, skb); if (unlikely(net_xmit_eval(err))) pkt_len = 0; return pkt_len; diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 473faf73b194..f1a8df8ecc1f 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -63,7 +63,7 @@ synproxy_send_tcp(const struct synproxy_net *snet, nf_conntrack_get(nfct); } - ip_local_out(nskb->sk, nskb); + ip_local_out(net, nskb->sk, nskb); return; free_nskb: diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c index 0b9abfbf6577..ceb187308120 100644 --- a/net/ipv4/netfilter/nf_dup_ipv4.c +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -92,7 +92,7 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, if (nf_dup_ipv4_route(net, skb, gw, oif)) { __this_cpu_write(nf_skb_duplicated, true); - ip_local_out(skb->sk, skb); + ip_local_out(net, skb->sk, skb); __this_cpu_write(nf_skb_duplicated, false); } else { kfree_skb(skb); diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index dcc125cb0441..c747b2d9eb77 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -157,7 +157,7 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) dev_queue_xmit(nskb); } else #endif - ip_local_out(nskb->sk, nskb); + ip_local_out(net, nskb->sk, nskb); return; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 31c686b7fcc0..98510fac94e9 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1692,7 +1692,7 @@ int ip6_send_skb(struct sk_buff *skb) struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); int err; - err = ip6_local_out(skb->sk, skb); + err = ip6_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index c38c3411150b..a10a2a9e9f94 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -76,7 +76,7 @@ synproxy_send_tcp(const struct synproxy_net *snet, nf_conntrack_get(nfct); } - ip6_local_out(nskb->sk, nskb); + ip6_local_out(net, nskb->sk, nskb); return; free_nskb: diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c index 64f3fe5e2719..6989c70ae29f 100644 --- a/net/ipv6/netfilter/nf_dup_ipv6.c +++ b/net/ipv6/netfilter/nf_dup_ipv6.c @@ -68,7 +68,7 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, } if (nf_dup_ipv6_route(net, skb, gw, oif)) { __this_cpu_write(nf_skb_duplicated, true); - ip6_local_out(skb->sk, skb); + ip6_local_out(net, skb->sk, skb); __this_cpu_write(nf_skb_duplicated, false); } else { kfree_skb(skb); diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index a4f73e235ca5..7309e475f68b 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -206,7 +206,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) dev_queue_xmit(nskb); } else #endif - ip6_local_out(nskb->sk, nskb); + ip6_local_out(net, nskb->sk, nskb); } EXPORT_SYMBOL_GPL(nf_send_reset6); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 7f64d67b637d..462f2a76b5c2 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -154,9 +154,8 @@ int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(__ip6_local_out); -int ip6_local_out(struct sock *sk, struct sk_buff *skb) +int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); int err; err = __ip6_local_out(net, sk, skb); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 2042b9303136..3264cb49b333 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1049,7 +1049,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, ret = ip_vs_tunnel_xmit_prepare(skb, cp); if (ret == NF_ACCEPT) - ip_local_out(skb->sk, skb); + ip_local_out(net, skb->sk, skb); else if (ret == NF_DROP) kfree_skb(skb); rcu_read_unlock(); @@ -1141,7 +1141,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, ret = ip_vs_tunnel_xmit_prepare(skb, cp); if (ret == NF_ACCEPT) - ip6_local_out(skb->sk, skb); + ip6_local_out(cp->ipvs->net, skb->sk, skb); else if (ret == NF_DROP) kfree_skb(skb); rcu_read_unlock(); -- cgit v1.2.3 From ede2059dbaf9c6557a49d466c8c7778343b208ff Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:47 -0500 Subject: dst: Pass net into dst->output The network namespace is already passed into dst_output pass it into dst->output lwt->output and friends. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- drivers/net/vrf.c | 3 +-- include/net/dst.h | 8 ++++---- include/net/ip.h | 4 ++-- include/net/ipv6.h | 2 +- include/net/lwtunnel.h | 8 ++++---- include/net/xfrm.h | 6 +++--- net/core/dst.c | 14 +++++++------- net/core/lwtunnel.c | 4 ++-- net/decnet/dn_route.c | 6 +++--- net/ipv4/ip_output.c | 6 ++---- net/ipv4/route.c | 4 ++-- net/ipv4/xfrm4_output.c | 4 +--- net/ipv6/ila.c | 4 ++-- net/ipv6/ip6_output.c | 3 +-- net/ipv6/route.c | 14 +++++++------- net/ipv6/xfrm6_output.c | 4 +--- net/mpls/mpls_iptunnel.c | 2 +- net/xfrm/xfrm_policy.c | 2 +- 18 files changed, 45 insertions(+), 53 deletions(-) (limited to 'include') diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 21bb7deb6d58..191579aeab16 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -312,10 +312,9 @@ err: return ret; } -static int vrf_output(struct sock *sk, struct sk_buff *skb) +static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; - struct net *net = dev_net(dev); IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); diff --git a/include/net/dst.h b/include/net/dst.h index fdd01fed1a7b..1279f9b09791 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -45,7 +45,7 @@ struct dst_entry { void *__pad1; #endif int (*input)(struct sk_buff *); - int (*output)(struct sock *sk, struct sk_buff *skb); + int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); unsigned short flags; #define DST_HOST 0x0001 @@ -365,10 +365,10 @@ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, __skb_tunnel_rx(skb, dev, net); } -int dst_discard_sk(struct sock *sk, struct sk_buff *skb); +int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static inline int dst_discard(struct sk_buff *skb) { - return dst_discard_sk(skb->sk, skb); + return dst_discard_out(&init_net, skb->sk, skb); } void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref, int initial_obsolete, unsigned short flags); @@ -456,7 +456,7 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout) /* Output packet to network from transport. */ static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - return skb_dst(skb)->output(sk, skb); + return skb_dst(skb)->output(net, sk, skb); } /* Input packet from network to transport. */ diff --git a/include/net/ip.h b/include/net/ip.h index 7febbab784cd..3c904a28d5e5 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -107,8 +107,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); int ip_local_deliver(struct sk_buff *skb); int ip_mr_input(struct sk_buff *skb); -int ip_output(struct sock *sk, struct sk_buff *skb); -int ip_mc_output(struct sock *sk, struct sk_buff *skb); +int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb); +int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index fce8120c2be3..e1a10b0ac0b0 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -860,7 +860,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, * skb processing functions */ -int ip6_output(struct sock *sk, struct sk_buff *skb); +int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index fce0e35e74d0..66350ce3e955 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -18,7 +18,7 @@ struct lwtunnel_state { __u16 type; __u16 flags; atomic_t refcnt; - int (*orig_output)(struct sock *sk, struct sk_buff *skb); + int (*orig_output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*orig_input)(struct sk_buff *); int len; __u8 data[0]; @@ -28,7 +28,7 @@ struct lwtunnel_encap_ops { int (*build_state)(struct net_device *dev, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **ts); - int (*output)(struct sock *sk, struct sk_buff *skb); + int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*input)(struct sk_buff *skb); int (*fill_encap)(struct sk_buff *skb, struct lwtunnel_state *lwtstate); @@ -88,7 +88,7 @@ int lwtunnel_fill_encap(struct sk_buff *skb, int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate); struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len); int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b); -int lwtunnel_output(struct sock *sk, struct sk_buff *skb); +int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb); int lwtunnel_input(struct sk_buff *skb); #else @@ -160,7 +160,7 @@ static inline int lwtunnel_cmp_encap(struct lwtunnel_state *a, return 0; } -static inline int lwtunnel_output(struct sock *sk, struct sk_buff *skb) +static inline int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return -EOPNOTSUPP; } diff --git a/include/net/xfrm.h b/include/net/xfrm.h index fd176106909a..4a9c21f9b4ea 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -333,7 +333,7 @@ struct xfrm_state_afinfo { const xfrm_address_t *saddr); int (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n); int (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n); - int (*output)(struct sock *sk, struct sk_buff *skb); + int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*output_finish)(struct sock *sk, struct sk_buff *skb); int (*extract_input)(struct xfrm_state *x, struct sk_buff *skb); @@ -1527,7 +1527,7 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb); -int xfrm4_output(struct sock *sk, struct sk_buff *skb); +int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb); int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err); int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol); @@ -1552,7 +1552,7 @@ __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr); __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr); int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb); -int xfrm6_output(struct sock *sk, struct sk_buff *skb); +int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr); diff --git a/net/core/dst.c b/net/core/dst.c index 0771c8cb9307..2a1818065e12 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -144,12 +144,12 @@ loop: mutex_unlock(&dst_gc_mutex); } -int dst_discard_sk(struct sock *sk, struct sk_buff *skb) +int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } -EXPORT_SYMBOL(dst_discard_sk); +EXPORT_SYMBOL(dst_discard_out); const u32 dst_default_metrics[RTAX_MAX + 1] = { /* This initializer is needed to force linker to place this variable @@ -177,7 +177,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, dst->xfrm = NULL; #endif dst->input = dst_discard; - dst->output = dst_discard_sk; + dst->output = dst_discard_out; dst->error = 0; dst->obsolete = initial_obsolete; dst->header_len = 0; @@ -224,7 +224,7 @@ static void ___dst_free(struct dst_entry *dst) */ if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) { dst->input = dst_discard; - dst->output = dst_discard_sk; + dst->output = dst_discard_out; } dst->obsolete = DST_OBSOLETE_DEAD; } @@ -352,7 +352,7 @@ static struct dst_ops md_dst_ops = { .family = AF_UNSPEC, }; -static int dst_md_discard_sk(struct sock *sk, struct sk_buff *skb) +static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { WARN_ONCE(1, "Attempting to call output on metadata dst\n"); kfree_skb(skb); @@ -375,7 +375,7 @@ static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen) DST_METADATA | DST_NOCACHE | DST_NOCOUNT); dst->input = dst_md_discard; - dst->output = dst_md_discard_sk; + dst->output = dst_md_discard_out; memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); } @@ -430,7 +430,7 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, if (!unregister) { dst->input = dst_discard; - dst->output = dst_discard_sk; + dst->output = dst_discard_out; } else { dst->dev = dev_net(dst->dev)->loopback_dev; dev_hold(dst->dev); diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index dfb1a9ca0835..299cfc24d888 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -180,7 +180,7 @@ int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) } EXPORT_SYMBOL(lwtunnel_cmp_encap); -int lwtunnel_output(struct sock *sk, struct sk_buff *skb) +int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; @@ -199,7 +199,7 @@ int lwtunnel_output(struct sock *sk, struct sk_buff *skb) rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->output)) - ret = ops->output(sk, skb); + ret = ops->output(net, sk, skb); rcu_read_unlock(); if (ret == -EOPNOTSUPP) diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index e930321e2c1d..27fce283117b 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -744,7 +744,7 @@ out: return NET_RX_DROP; } -static int dn_output(struct sock *sk, struct sk_buff *skb) +static int dn_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *)dst; @@ -832,7 +832,7 @@ drop: * Used to catch bugs. This should never normally get * called. */ -static int dn_rt_bug_sk(struct sock *sk, struct sk_buff *skb) +static int dn_rt_bug_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); @@ -1469,7 +1469,7 @@ make_route: rt->n = neigh; rt->dst.lastuse = jiffies; - rt->dst.output = dn_rt_bug_sk; + rt->dst.output = dn_rt_bug_out; switch (res.type) { case RTN_UNICAST: rt->dst.input = dn_forward; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9fe100a41e5d..67404e1fe7d4 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -284,11 +284,10 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk return ip_finish_output2(net, sk, skb); } -int ip_mc_output(struct sock *sk, struct sk_buff *skb) +int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; - struct net *net = dev_net(dev); /* * If the indicated interface is up and running, send the packet. @@ -347,10 +346,9 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb) !(IPCB(skb)->flags & IPSKB_REROUTED)); } -int ip_output(struct sock *sk, struct sk_buff *skb) +int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; - struct net *net = dev_net(dev); IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bf1486bd7e81..4be5ff08f98d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1152,7 +1152,7 @@ static void ipv4_link_failure(struct sk_buff *skb) dst_set_expires(&rt->dst, 0); } -static int ip_rt_bug(struct sock *sk, struct sk_buff *skb) +static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb) { pr_debug("%s: %pI4 -> %pI4, %s\n", __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, @@ -2303,7 +2303,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or new->__use = 1; new->input = dst_discard; - new->output = dst_discard_sk; + new->output = dst_discard_out; new->dev = ort->dst.dev; if (new->dev) diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 17db61f4b439..9f298d0dc9a1 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -94,10 +94,8 @@ static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) return x->outer_mode->afinfo->output_finish(sk, skb); } -int xfrm4_output(struct sock *sk, struct sk_buff *skb) +int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, __xfrm4_output, diff --git a/net/ipv6/ila.c b/net/ipv6/ila.c index 678d2df4b8d9..1a6852e1ac69 100644 --- a/net/ipv6/ila.c +++ b/net/ipv6/ila.c @@ -91,7 +91,7 @@ static void update_ipv6_locator(struct sk_buff *skb, struct ila_params *p) *(__be64 *)&ip6h->daddr = p->locator; } -static int ila_output(struct sock *sk, struct sk_buff *skb) +static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -100,7 +100,7 @@ static int ila_output(struct sock *sk, struct sk_buff *skb) update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate)); - return dst->lwtstate->orig_output(sk, skb); + return dst->lwtstate->orig_output(net, sk, skb); drop: kfree_skb(skb); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 98510fac94e9..32583b507c2e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -130,11 +130,10 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s return ip6_finish_output2(net, sk, skb); } -int ip6_output(struct sock *sk, struct sk_buff *skb) +int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - struct net *net = dev_net(dev); if (unlikely(idev->cnf.disable_ipv6)) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d3d946773a3e..4320ddcac33f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -86,9 +86,9 @@ static void ip6_dst_ifdown(struct dst_entry *, static int ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); -static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb); +static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static int ip6_pkt_prohibit(struct sk_buff *skb); -static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb); +static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); @@ -308,7 +308,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = { .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, .input = dst_discard, - .output = dst_discard_sk, + .output = dst_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), .rt6i_protocol = RTPROT_KERNEL, @@ -1195,7 +1195,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori new->__use = 1; new->input = dst_discard; - new->output = dst_discard_sk; + new->output = dst_discard_out; if (dst_metrics_read_only(&ort->dst)) new->_metrics = ort->dst._metrics; @@ -1853,7 +1853,7 @@ int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret) switch (cfg->fc_type) { case RTN_BLACKHOLE: rt->dst.error = -EINVAL; - rt->dst.output = dst_discard_sk; + rt->dst.output = dst_discard_out; rt->dst.input = dst_discard; break; case RTN_PROHIBIT: @@ -2446,7 +2446,7 @@ static int ip6_pkt_discard(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES); } -static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb) +static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); @@ -2457,7 +2457,7 @@ static int ip6_pkt_prohibit(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); } -static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb) +static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index c9a5bd5fea9c..9db067a11b52 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -173,10 +173,8 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) return x->outer_mode->afinfo->output_finish(sk, skb); } -int xfrm6_output(struct sock *sk, struct sk_buff *skb) +int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); - return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, __xfrm6_output, diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 21e70bc9af98..67591aef9cae 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -37,7 +37,7 @@ static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en) return en->labels * sizeof(struct mpls_shim_hdr); } -int mpls_output(struct sock *sk, struct sk_buff *skb) +int mpls_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct mpls_iptunnel_encap *tun_encap_info; struct mpls_shim_hdr *hdr; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index f4f2d987f8f0..09bfcbac63bb 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1957,7 +1957,7 @@ purge_queue: xfrm_pol_put(pol); } -static int xdst_queue_output(struct sock *sk, struct sk_buff *skb) +static int xdst_queue_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned long sched_next; struct dst_entry *dst = skb_dst(skb); -- cgit v1.2.3 From a1cba5613edf50c2a213fa90c30aa10500b241b7 Mon Sep 17 00:00:00 2001 From: Arun Parameswaran Date: Tue, 6 Oct 2015 12:25:48 -0700 Subject: net: phy: Add Broadcom phy library for common interfaces This patch adds the Broadcom phy library to consolidate common interfaces shared by Broadcom phy's. Moved the common interfaces to the 'bcm-phy-lib.c' and updated the Broadcom PHY drivers to use the new APIs. Signed-off-by: Arun Parameswaran Signed-off-by: David S. Miller --- drivers/net/phy/Kconfig | 6 ++ drivers/net/phy/Makefile | 1 + drivers/net/phy/bcm-phy-lib.c | 208 ++++++++++++++++++++++++++++++++++++++++++ drivers/net/phy/bcm-phy-lib.h | 37 ++++++++ drivers/net/phy/bcm63xx.c | 38 +------- drivers/net/phy/bcm7xxx.c | 127 ++++++-------------------- drivers/net/phy/broadcom.c | 149 +++++++++--------------------- include/linux/brcmphy.h | 22 +---- 8 files changed, 332 insertions(+), 256 deletions(-) create mode 100644 drivers/net/phy/bcm-phy-lib.c create mode 100644 drivers/net/phy/bcm-phy-lib.h (limited to 'include') diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index b57f6c280cad..606fdc924768 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -69,8 +69,12 @@ config SMSC_PHY ---help--- Currently supports the LAN83C185, LAN8187 and LAN8700 PHYs +config BCM_NET_PHYLIB + tristate + config BROADCOM_PHY tristate "Drivers for Broadcom PHYs" + select BCM_NET_PHYLIB ---help--- Currently supports the BCM5411, BCM5421, BCM5461, BCM54616S, BCM5464, BCM5481 and BCM5482 PHYs. @@ -78,11 +82,13 @@ config BROADCOM_PHY config BCM63XX_PHY tristate "Drivers for Broadcom 63xx SOCs internal PHY" depends on BCM63XX + select BCM_NET_PHYLIB ---help--- Currently supports the 6348 and 6358 PHYs. config BCM7XXX_PHY tristate "Drivers for Broadcom 7xxx SOCs internal PHYs" + select BCM_NET_PHYLIB ---help--- Currently supports the BCM7366, BCM7439, BCM7445, and 40nm and 65nm generation of BCM7xxx Set Top Box SoCs. diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index f4e6eb9b2363..6932475a1a8a 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_QSEMI_PHY) += qsemi.o obj-$(CONFIG_SMSC_PHY) += smsc.o obj-$(CONFIG_TERANETICS_PHY) += teranetics.o obj-$(CONFIG_VITESSE_PHY) += vitesse.o +obj-$(CONFIG_BCM_NET_PHYLIB) += bcm-phy-lib.o obj-$(CONFIG_BROADCOM_PHY) += broadcom.o obj-$(CONFIG_BCM63XX_PHY) += bcm63xx.o obj-$(CONFIG_BCM7XXX_PHY) += bcm7xxx.o diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c new file mode 100644 index 000000000000..dd79ea6ba023 --- /dev/null +++ b/drivers/net/phy/bcm-phy-lib.c @@ -0,0 +1,208 @@ +/* + * Copyright (C) 2015 Broadcom Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include "bcm-phy-lib.h" +#include +#include +#include +#include + +#define MII_BCM_CHANNEL_WIDTH 0x2000 +#define BCM_CL45VEN_EEE_ADV 0x3c + +int bcm_phy_write_exp(struct phy_device *phydev, u16 reg, u16 val) +{ + int rc; + + rc = phy_write(phydev, MII_BCM54XX_EXP_SEL, reg); + if (rc < 0) + return rc; + + return phy_write(phydev, MII_BCM54XX_EXP_DATA, val); +} +EXPORT_SYMBOL_GPL(bcm_phy_write_exp); + +int bcm_phy_read_exp(struct phy_device *phydev, u16 reg) +{ + int val; + + val = phy_write(phydev, MII_BCM54XX_EXP_SEL, reg); + if (val < 0) + return val; + + val = phy_read(phydev, MII_BCM54XX_EXP_DATA); + + /* Restore default value. It's O.K. if this write fails. */ + phy_write(phydev, MII_BCM54XX_EXP_SEL, 0); + + return val; +} +EXPORT_SYMBOL_GPL(bcm_phy_read_exp); + +int bcm_phy_write_misc(struct phy_device *phydev, + u16 reg, u16 chl, u16 val) +{ + int rc; + int tmp; + + rc = phy_write(phydev, MII_BCM54XX_AUX_CTL, + MII_BCM54XX_AUXCTL_SHDWSEL_MISC); + if (rc < 0) + return rc; + + tmp = phy_read(phydev, MII_BCM54XX_AUX_CTL); + tmp |= MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA; + rc = phy_write(phydev, MII_BCM54XX_AUX_CTL, tmp); + if (rc < 0) + return rc; + + tmp = (chl * MII_BCM_CHANNEL_WIDTH) | reg; + rc = bcm_phy_write_exp(phydev, tmp, val); + + return rc; +} +EXPORT_SYMBOL_GPL(bcm_phy_write_misc); + +int bcm_phy_read_misc(struct phy_device *phydev, + u16 reg, u16 chl) +{ + int rc; + int tmp; + + rc = phy_write(phydev, MII_BCM54XX_AUX_CTL, + MII_BCM54XX_AUXCTL_SHDWSEL_MISC); + if (rc < 0) + return rc; + + tmp = phy_read(phydev, MII_BCM54XX_AUX_CTL); + tmp |= MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA; + rc = phy_write(phydev, MII_BCM54XX_AUX_CTL, tmp); + if (rc < 0) + return rc; + + tmp = (chl * MII_BCM_CHANNEL_WIDTH) | reg; + rc = bcm_phy_read_exp(phydev, tmp); + + return rc; +} +EXPORT_SYMBOL_GPL(bcm_phy_read_misc); + +int bcm_phy_ack_intr(struct phy_device *phydev) +{ + int reg; + + /* Clear pending interrupts. */ + reg = phy_read(phydev, MII_BCM54XX_ISR); + if (reg < 0) + return reg; + + return 0; +} +EXPORT_SYMBOL_GPL(bcm_phy_ack_intr); + +int bcm_phy_config_intr(struct phy_device *phydev) +{ + int reg; + + reg = phy_read(phydev, MII_BCM54XX_ECR); + if (reg < 0) + return reg; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + reg &= ~MII_BCM54XX_ECR_IM; + else + reg |= MII_BCM54XX_ECR_IM; + + return phy_write(phydev, MII_BCM54XX_ECR, reg); +} +EXPORT_SYMBOL_GPL(bcm_phy_config_intr); + +int bcm_phy_read_shadow(struct phy_device *phydev, u16 shadow) +{ + phy_write(phydev, MII_BCM54XX_SHD, MII_BCM54XX_SHD_VAL(shadow)); + return MII_BCM54XX_SHD_DATA(phy_read(phydev, MII_BCM54XX_SHD)); +} +EXPORT_SYMBOL_GPL(bcm_phy_read_shadow); + +int bcm_phy_write_shadow(struct phy_device *phydev, u16 shadow, + u16 val) +{ + return phy_write(phydev, MII_BCM54XX_SHD, + MII_BCM54XX_SHD_WRITE | + MII_BCM54XX_SHD_VAL(shadow) | + MII_BCM54XX_SHD_DATA(val)); +} +EXPORT_SYMBOL_GPL(bcm_phy_write_shadow); + +int bcm_phy_enable_apd(struct phy_device *phydev, bool dll_pwr_down) +{ + int val; + + if (dll_pwr_down) { + val = bcm_phy_read_shadow(phydev, BCM54XX_SHD_SCR3); + if (val < 0) + return val; + + val |= BCM54XX_SHD_SCR3_DLLAPD_DIS; + bcm_phy_write_shadow(phydev, BCM54XX_SHD_SCR3, val); + } + + val = bcm_phy_read_shadow(phydev, BCM54XX_SHD_APD); + if (val < 0) + return val; + + /* Clear APD bits */ + val &= BCM_APD_CLR_MASK; + + if (phydev->autoneg == AUTONEG_ENABLE) + val |= BCM54XX_SHD_APD_EN; + else + val |= BCM_NO_ANEG_APD_EN; + + /* Enable energy detect single link pulse for easy wakeup */ + val |= BCM_APD_SINGLELP_EN; + + /* Enable Auto Power-Down (APD) for the PHY */ + return bcm_phy_write_shadow(phydev, BCM54XX_SHD_APD, val); +} +EXPORT_SYMBOL_GPL(bcm_phy_enable_apd); + +int bcm_phy_enable_eee(struct phy_device *phydev) +{ + int val; + + /* Enable EEE at PHY level */ + val = phy_read_mmd_indirect(phydev, BRCM_CL45VEN_EEE_CONTROL, + MDIO_MMD_AN, phydev->addr); + if (val < 0) + return val; + + val |= LPI_FEATURE_EN | LPI_FEATURE_EN_DIG1000X; + + phy_write_mmd_indirect(phydev, BRCM_CL45VEN_EEE_CONTROL, + MDIO_MMD_AN, phydev->addr, (u32)val); + + /* Advertise EEE */ + val = phy_read_mmd_indirect(phydev, BCM_CL45VEN_EEE_ADV, + MDIO_MMD_AN, phydev->addr); + if (val < 0) + return val; + + val |= (MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T); + + phy_write_mmd_indirect(phydev, BCM_CL45VEN_EEE_ADV, + MDIO_MMD_AN, phydev->addr, (u32)val); + + return 0; +} +EXPORT_SYMBOL_GPL(bcm_phy_enable_eee); diff --git a/drivers/net/phy/bcm-phy-lib.h b/drivers/net/phy/bcm-phy-lib.h new file mode 100644 index 000000000000..b2091c88b44d --- /dev/null +++ b/drivers/net/phy/bcm-phy-lib.h @@ -0,0 +1,37 @@ +/* + * Copyright (C) 2015 Broadcom Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_BCM_PHY_LIB_H +#define _LINUX_BCM_PHY_LIB_H + +#include + +int bcm_phy_write_exp(struct phy_device *phydev, u16 reg, u16 val); +int bcm_phy_read_exp(struct phy_device *phydev, u16 reg); + +int bcm_phy_write_misc(struct phy_device *phydev, + u16 reg, u16 chl, u16 value); +int bcm_phy_read_misc(struct phy_device *phydev, + u16 reg, u16 chl); + +int bcm_phy_write_shadow(struct phy_device *phydev, u16 shadow, + u16 val); +int bcm_phy_read_shadow(struct phy_device *phydev, u16 shadow); + +int bcm_phy_ack_intr(struct phy_device *phydev); +int bcm_phy_config_intr(struct phy_device *phydev); + +int bcm_phy_enable_apd(struct phy_device *phydev, bool dll_pwr_down); + +int bcm_phy_enable_eee(struct phy_device *phydev); +#endif /* _LINUX_BCM_PHY_LIB_H */ diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c index 830ec31f952f..86b28052bf06 100644 --- a/drivers/net/phy/bcm63xx.c +++ b/drivers/net/phy/bcm63xx.c @@ -6,6 +6,7 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ +#include "bcm-phy-lib.h" #include #include @@ -42,35 +43,6 @@ static int bcm63xx_config_init(struct phy_device *phydev) return phy_write(phydev, MII_BCM63XX_IR, reg); } -static int bcm63xx_ack_interrupt(struct phy_device *phydev) -{ - int reg; - - /* Clear pending interrupts. */ - reg = phy_read(phydev, MII_BCM63XX_IR); - if (reg < 0) - return reg; - - return 0; -} - -static int bcm63xx_config_intr(struct phy_device *phydev) -{ - int reg, err; - - reg = phy_read(phydev, MII_BCM63XX_IR); - if (reg < 0) - return reg; - - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) - reg &= ~MII_BCM63XX_IR_GMASK; - else - reg |= MII_BCM63XX_IR_GMASK; - - err = phy_write(phydev, MII_BCM63XX_IR, reg); - return err; -} - static struct phy_driver bcm63xx_driver[] = { { .phy_id = 0x00406000, @@ -82,8 +54,8 @@ static struct phy_driver bcm63xx_driver[] = { .config_init = bcm63xx_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .ack_interrupt = bcm63xx_ack_interrupt, - .config_intr = bcm63xx_config_intr, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, .driver = { .owner = THIS_MODULE }, }, { /* same phy as above, with just a different OUI */ @@ -95,8 +67,8 @@ static struct phy_driver bcm63xx_driver[] = { .config_init = bcm63xx_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .ack_interrupt = bcm63xx_ack_interrupt, - .config_intr = bcm63xx_config_intr, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, .driver = { .owner = THIS_MODULE }, } }; diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 6b701b3ded74..efa31a655eb1 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -12,12 +12,12 @@ #include #include #include +#include "bcm-phy-lib.h" #include #include #include /* Broadcom BCM7xxx internal PHY registers */ -#define MII_BCM7XXX_CHANNEL_WIDTH 0x2000 /* 40nm only register definitions */ #define MII_BCM7XXX_100TX_AUX_CTL 0x10 @@ -48,37 +48,13 @@ #define CORE_EXPB0 0xb0 -static void phy_write_exp(struct phy_device *phydev, - u16 reg, u16 value) -{ - phy_write(phydev, MII_BCM54XX_EXP_SEL, MII_BCM54XX_EXP_SEL_ER | reg); - phy_write(phydev, MII_BCM54XX_EXP_DATA, value); -} - -static void phy_write_misc(struct phy_device *phydev, - u16 reg, u16 chl, u16 value) -{ - int tmp; - - phy_write(phydev, MII_BCM54XX_AUX_CTL, MII_BCM54XX_AUXCTL_SHDWSEL_MISC); - - tmp = phy_read(phydev, MII_BCM54XX_AUX_CTL); - tmp |= MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA; - phy_write(phydev, MII_BCM54XX_AUX_CTL, tmp); - - tmp = (chl * MII_BCM7XXX_CHANNEL_WIDTH) | reg; - phy_write(phydev, MII_BCM54XX_EXP_SEL, tmp); - - phy_write(phydev, MII_BCM54XX_EXP_DATA, value); -} - static void r_rc_cal_reset(struct phy_device *phydev) { /* Reset R_CAL/RC_CAL Engine */ - phy_write_exp(phydev, 0x00b0, 0x0010); + bcm_phy_write_exp(phydev, 0x00b0, 0x0010); /* Disable Reset R_AL/RC_CAL Engine */ - phy_write_exp(phydev, 0x00b0, 0x0000); + bcm_phy_write_exp(phydev, 0x00b0, 0x0000); } static int bcm7xxx_28nm_b0_afe_config_init(struct phy_device *phydev) @@ -86,18 +62,18 @@ static int bcm7xxx_28nm_b0_afe_config_init(struct phy_device *phydev) /* Increase VCO range to prevent unlocking problem of PLL at low * temp */ - phy_write_misc(phydev, PLL_PLLCTRL_1, 0x0048); + bcm_phy_write_misc(phydev, PLL_PLLCTRL_1, 0x0048); /* Change Ki to 011 */ - phy_write_misc(phydev, PLL_PLLCTRL_2, 0x021b); + bcm_phy_write_misc(phydev, PLL_PLLCTRL_2, 0x021b); /* Disable loading of TVCO buffer to bandgap, set bandgap trim * to 111 */ - phy_write_misc(phydev, PLL_PLLCTRL_4, 0x0e20); + bcm_phy_write_misc(phydev, PLL_PLLCTRL_4, 0x0e20); /* Adjust bias current trim by -3 */ - phy_write_misc(phydev, DSP_TAP10, 0x690b); + bcm_phy_write_misc(phydev, DSP_TAP10, 0x690b); /* Switch to CORE_BASE1E */ phy_write(phydev, MII_BCM7XXX_CORE_BASE1E, 0xd); @@ -105,19 +81,19 @@ static int bcm7xxx_28nm_b0_afe_config_init(struct phy_device *phydev) r_rc_cal_reset(phydev); /* write AFE_RXCONFIG_0 */ - phy_write_misc(phydev, AFE_RXCONFIG_0, 0xeb19); + bcm_phy_write_misc(phydev, AFE_RXCONFIG_0, 0xeb19); /* write AFE_RXCONFIG_1 */ - phy_write_misc(phydev, AFE_RXCONFIG_1, 0x9a3f); + bcm_phy_write_misc(phydev, AFE_RXCONFIG_1, 0x9a3f); /* write AFE_RX_LP_COUNTER */ - phy_write_misc(phydev, AFE_RX_LP_COUNTER, 0x7fc0); + bcm_phy_write_misc(phydev, AFE_RX_LP_COUNTER, 0x7fc0); /* write AFE_HPF_TRIM_OTHERS */ - phy_write_misc(phydev, AFE_HPF_TRIM_OTHERS, 0x000b); + bcm_phy_write_misc(phydev, AFE_HPF_TRIM_OTHERS, 0x000b); /* write AFTE_TX_CONFIG */ - phy_write_misc(phydev, AFE_TX_CONFIG, 0x0800); + bcm_phy_write_misc(phydev, AFE_TX_CONFIG, 0x0800); return 0; } @@ -125,36 +101,36 @@ static int bcm7xxx_28nm_b0_afe_config_init(struct phy_device *phydev) static int bcm7xxx_28nm_d0_afe_config_init(struct phy_device *phydev) { /* AFE_RXCONFIG_0 */ - phy_write_misc(phydev, AFE_RXCONFIG_0, 0xeb15); + bcm_phy_write_misc(phydev, AFE_RXCONFIG_0, 0xeb15); /* AFE_RXCONFIG_1 */ - phy_write_misc(phydev, AFE_RXCONFIG_1, 0x9b2f); + bcm_phy_write_misc(phydev, AFE_RXCONFIG_1, 0x9b2f); /* AFE_RXCONFIG_2, set rCal offset for HT=0 code and LT=-2 code */ - phy_write_misc(phydev, AFE_RXCONFIG_2, 0x2003); + bcm_phy_write_misc(phydev, AFE_RXCONFIG_2, 0x2003); /* AFE_RX_LP_COUNTER, set RX bandwidth to maximum */ - phy_write_misc(phydev, AFE_RX_LP_COUNTER, 0x7fc0); + bcm_phy_write_misc(phydev, AFE_RX_LP_COUNTER, 0x7fc0); /* AFE_TX_CONFIG, set 100BT Cfeed=011 to improve rise/fall time */ - phy_write_misc(phydev, AFE_TX_CONFIG, 0x431); + bcm_phy_write_misc(phydev, AFE_TX_CONFIG, 0x431); /* AFE_VDCA_ICTRL_0, set Iq=1101 instead of 0111 for AB symmetry */ - phy_write_misc(phydev, AFE_VDCA_ICTRL_0, 0xa7da); + bcm_phy_write_misc(phydev, AFE_VDCA_ICTRL_0, 0xa7da); /* AFE_VDAC_OTHERS_0, set 1000BT Cidac=010 for all ports */ - phy_write_misc(phydev, AFE_VDAC_OTHERS_0, 0xa020); + bcm_phy_write_misc(phydev, AFE_VDAC_OTHERS_0, 0xa020); /* AFE_HPF_TRIM_OTHERS, set 100Tx/10BT to -4.5% swing and set rCal * offset for HT=0 code */ - phy_write_misc(phydev, AFE_HPF_TRIM_OTHERS, 0x00e3); + bcm_phy_write_misc(phydev, AFE_HPF_TRIM_OTHERS, 0x00e3); /* CORE_BASE1E, force trim to overwrite and set I_ext trim to 0000 */ phy_write(phydev, MII_BCM7XXX_CORE_BASE1E, 0x0010); /* DSP_TAP10, adjust bias current trim (+0% swing, +0 tick) */ - phy_write_misc(phydev, DSP_TAP10, 0x011b); + bcm_phy_write_misc(phydev, DSP_TAP10, 0x011b); /* Reset R_CAL/RC_CAL engine */ r_rc_cal_reset(phydev); @@ -165,24 +141,24 @@ static int bcm7xxx_28nm_d0_afe_config_init(struct phy_device *phydev) static int bcm7xxx_28nm_e0_plus_afe_config_init(struct phy_device *phydev) { /* AFE_RXCONFIG_1, provide more margin for INL/DNL measurement */ - phy_write_misc(phydev, AFE_RXCONFIG_1, 0x9b2f); + bcm_phy_write_misc(phydev, AFE_RXCONFIG_1, 0x9b2f); /* AFE_TX_CONFIG, set 100BT Cfeed=011 to improve rise/fall time */ - phy_write_misc(phydev, AFE_TX_CONFIG, 0x431); + bcm_phy_write_misc(phydev, AFE_TX_CONFIG, 0x431); /* AFE_VDCA_ICTRL_0, set Iq=1101 instead of 0111 for AB symmetry */ - phy_write_misc(phydev, AFE_VDCA_ICTRL_0, 0xa7da); + bcm_phy_write_misc(phydev, AFE_VDCA_ICTRL_0, 0xa7da); /* AFE_HPF_TRIM_OTHERS, set 100Tx/10BT to -4.5% swing and set rCal * offset for HT=0 code */ - phy_write_misc(phydev, AFE_HPF_TRIM_OTHERS, 0x00e3); + bcm_phy_write_misc(phydev, AFE_HPF_TRIM_OTHERS, 0x00e3); /* CORE_BASE1E, force trim to overwrite and set I_ext trim to 0000 */ phy_write(phydev, MII_BCM7XXX_CORE_BASE1E, 0x0010); /* DSP_TAP10, adjust bias current trim (+0% swing, +0 tick) */ - phy_write_misc(phydev, DSP_TAP10, 0x011b); + bcm_phy_write_misc(phydev, DSP_TAP10, 0x011b); /* Reset R_CAL/RC_CAL engine */ r_rc_cal_reset(phydev); @@ -190,53 +166,6 @@ static int bcm7xxx_28nm_e0_plus_afe_config_init(struct phy_device *phydev) return 0; } -static int bcm7xxx_apd_enable(struct phy_device *phydev) -{ - int val; - - /* Enable powering down of the DLL during auto-power down */ - val = bcm54xx_shadow_read(phydev, BCM54XX_SHD_SCR3); - if (val < 0) - return val; - - val |= BCM54XX_SHD_SCR3_DLLAPD_DIS; - bcm54xx_shadow_write(phydev, BCM54XX_SHD_SCR3, val); - - /* Enable auto-power down */ - val = bcm54xx_shadow_read(phydev, BCM54XX_SHD_APD); - if (val < 0) - return val; - - val |= BCM54XX_SHD_APD_EN; - return bcm54xx_shadow_write(phydev, BCM54XX_SHD_APD, val); -} - -static int bcm7xxx_eee_enable(struct phy_device *phydev) -{ - int val; - - val = phy_read_mmd_indirect(phydev, BRCM_CL45VEN_EEE_CONTROL, - MDIO_MMD_AN, phydev->addr); - if (val < 0) - return val; - - /* Enable general EEE feature at the PHY level */ - val |= LPI_FEATURE_EN | LPI_FEATURE_EN_DIG1000X; - - phy_write_mmd_indirect(phydev, BRCM_CL45VEN_EEE_CONTROL, - MDIO_MMD_AN, phydev->addr, val); - - /* Advertise supported modes */ - val = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV, - MDIO_MMD_AN, phydev->addr); - - val |= (MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T); - phy_write_mmd_indirect(phydev, MDIO_AN_EEE_ADV, - MDIO_MMD_AN, phydev->addr, val); - - return 0; -} - static int bcm7xxx_28nm_config_init(struct phy_device *phydev) { u8 rev = PHY_BRCM_7XXX_REV(phydev->dev_flags); @@ -273,11 +202,11 @@ static int bcm7xxx_28nm_config_init(struct phy_device *phydev) if (ret) return ret; - ret = bcm7xxx_eee_enable(phydev); + ret = bcm_phy_enable_eee(phydev); if (ret) return ret; - return bcm7xxx_apd_enable(phydev); + return bcm_phy_enable_apd(phydev, true); } static int bcm7xxx_28nm_resume(struct phy_device *phydev) diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 9c71295f2fef..07a6119121c3 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -14,6 +14,7 @@ * 2 of the License, or (at your option) any later version. */ +#include "bcm-phy-lib.h" #include #include #include @@ -29,39 +30,6 @@ MODULE_DESCRIPTION("Broadcom PHY driver"); MODULE_AUTHOR("Maciej W. Rozycki"); MODULE_LICENSE("GPL"); -/* Indirect register access functions for the Expansion Registers */ -static int bcm54xx_exp_read(struct phy_device *phydev, u16 regnum) -{ - int val; - - val = phy_write(phydev, MII_BCM54XX_EXP_SEL, regnum); - if (val < 0) - return val; - - val = phy_read(phydev, MII_BCM54XX_EXP_DATA); - - /* Restore default value. It's O.K. if this write fails. */ - phy_write(phydev, MII_BCM54XX_EXP_SEL, 0); - - return val; -} - -static int bcm54xx_exp_write(struct phy_device *phydev, u16 regnum, u16 val) -{ - int ret; - - ret = phy_write(phydev, MII_BCM54XX_EXP_SEL, regnum); - if (ret < 0) - return ret; - - ret = phy_write(phydev, MII_BCM54XX_EXP_DATA, val); - - /* Restore default value. It's O.K. if this write fails. */ - phy_write(phydev, MII_BCM54XX_EXP_SEL, 0); - - return ret; -} - static int bcm54xx_auxctl_write(struct phy_device *phydev, u16 regnum, u16 val) { return phy_write(phydev, MII_BCM54XX_AUX_CTL, regnum | val); @@ -72,28 +40,28 @@ static int bcm50610_a0_workaround(struct phy_device *phydev) { int err; - err = bcm54xx_exp_write(phydev, MII_BCM54XX_EXP_AADJ1CH0, + err = bcm_phy_write_exp(phydev, MII_BCM54XX_EXP_AADJ1CH0, MII_BCM54XX_EXP_AADJ1CH0_SWP_ABCD_OEN | MII_BCM54XX_EXP_AADJ1CH0_SWSEL_THPF); if (err < 0) return err; - err = bcm54xx_exp_write(phydev, MII_BCM54XX_EXP_AADJ1CH3, - MII_BCM54XX_EXP_AADJ1CH3_ADCCKADJ); + err = bcm_phy_write_exp(phydev, MII_BCM54XX_EXP_AADJ1CH3, + MII_BCM54XX_EXP_AADJ1CH3_ADCCKADJ); if (err < 0) return err; - err = bcm54xx_exp_write(phydev, MII_BCM54XX_EXP_EXP75, + err = bcm_phy_write_exp(phydev, MII_BCM54XX_EXP_EXP75, MII_BCM54XX_EXP_EXP75_VDACCTRL); if (err < 0) return err; - err = bcm54xx_exp_write(phydev, MII_BCM54XX_EXP_EXP96, + err = bcm_phy_write_exp(phydev, MII_BCM54XX_EXP_EXP96, MII_BCM54XX_EXP_EXP96_MYST); if (err < 0) return err; - err = bcm54xx_exp_write(phydev, MII_BCM54XX_EXP_EXP97, + err = bcm_phy_write_exp(phydev, MII_BCM54XX_EXP_EXP97, MII_BCM54XX_EXP_EXP97_MYST); return err; @@ -114,7 +82,7 @@ static int bcm54xx_phydsp_config(struct phy_device *phydev) if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM50610 || BRCM_PHY_MODEL(phydev) == PHY_ID_BCM50610M) { /* Clear bit 9 to fix a phy interop issue. */ - err = bcm54xx_exp_write(phydev, MII_BCM54XX_EXP_EXP08, + err = bcm_phy_write_exp(phydev, MII_BCM54XX_EXP_EXP08, MII_BCM54XX_EXP_EXP08_RJCT_2MHZ); if (err < 0) goto error; @@ -129,12 +97,12 @@ static int bcm54xx_phydsp_config(struct phy_device *phydev) if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM57780) { int val; - val = bcm54xx_exp_read(phydev, MII_BCM54XX_EXP_EXP75); + val = bcm_phy_read_exp(phydev, MII_BCM54XX_EXP_EXP75); if (val < 0) goto error; val |= MII_BCM54XX_EXP_EXP75_CM_OSC; - err = bcm54xx_exp_write(phydev, MII_BCM54XX_EXP_EXP75, val); + err = bcm_phy_write_exp(phydev, MII_BCM54XX_EXP_EXP75, val); } error: @@ -159,7 +127,7 @@ static void bcm54xx_adjust_rxrefclk(struct phy_device *phydev) BRCM_PHY_MODEL(phydev) != PHY_ID_BCM50610M) return; - val = bcm54xx_shadow_read(phydev, BCM54XX_SHD_SCR3); + val = bcm_phy_read_shadow(phydev, BCM54XX_SHD_SCR3); if (val < 0) return; @@ -190,9 +158,9 @@ static void bcm54xx_adjust_rxrefclk(struct phy_device *phydev) val |= BCM54XX_SHD_SCR3_TRDDAPD; if (orig != val) - bcm54xx_shadow_write(phydev, BCM54XX_SHD_SCR3, val); + bcm_phy_write_shadow(phydev, BCM54XX_SHD_SCR3, val); - val = bcm54xx_shadow_read(phydev, BCM54XX_SHD_APD); + val = bcm_phy_read_shadow(phydev, BCM54XX_SHD_APD); if (val < 0) return; @@ -204,7 +172,7 @@ static void bcm54xx_adjust_rxrefclk(struct phy_device *phydev) val &= ~BCM54XX_SHD_APD_EN; if (orig != val) - bcm54xx_shadow_write(phydev, BCM54XX_SHD_APD, val); + bcm_phy_write_shadow(phydev, BCM54XX_SHD_APD, val); } static int bcm54xx_config_init(struct phy_device *phydev) @@ -232,7 +200,7 @@ static int bcm54xx_config_init(struct phy_device *phydev) if ((BRCM_PHY_MODEL(phydev) == PHY_ID_BCM50610 || BRCM_PHY_MODEL(phydev) == PHY_ID_BCM50610M) && (phydev->dev_flags & PHY_BRCM_CLEAR_RGMII_MODE)) - bcm54xx_shadow_write(phydev, BCM54XX_SHD_RGMII_MODE, 0); + bcm_phy_write_shadow(phydev, BCM54XX_SHD_RGMII_MODE, 0); if ((phydev->dev_flags & PHY_BRCM_RX_REFCLK_UNUSED) || (phydev->dev_flags & PHY_BRCM_DIS_TXCRXC_NOENRGY) || @@ -254,8 +222,8 @@ static int bcm5482_config_init(struct phy_device *phydev) /* * Enable secondary SerDes and its use as an LED source */ - reg = bcm54xx_shadow_read(phydev, BCM5482_SHD_SSD); - bcm54xx_shadow_write(phydev, BCM5482_SHD_SSD, + reg = bcm_phy_read_shadow(phydev, BCM5482_SHD_SSD); + bcm_phy_write_shadow(phydev, BCM5482_SHD_SSD, reg | BCM5482_SHD_SSD_LEDM | BCM5482_SHD_SSD_EN); @@ -264,10 +232,10 @@ static int bcm5482_config_init(struct phy_device *phydev) * Enable SGMII slave mode and auto-detection */ reg = BCM5482_SSD_SGMII_SLAVE | MII_BCM54XX_EXP_SEL_SSD; - err = bcm54xx_exp_read(phydev, reg); + err = bcm_phy_read_exp(phydev, reg); if (err < 0) return err; - err = bcm54xx_exp_write(phydev, reg, err | + err = bcm_phy_write_exp(phydev, reg, err | BCM5482_SSD_SGMII_SLAVE_EN | BCM5482_SSD_SGMII_SLAVE_AD); if (err < 0) @@ -277,10 +245,10 @@ static int bcm5482_config_init(struct phy_device *phydev) * Disable secondary SerDes powerdown */ reg = BCM5482_SSD_1000BX_CTL | MII_BCM54XX_EXP_SEL_SSD; - err = bcm54xx_exp_read(phydev, reg); + err = bcm_phy_read_exp(phydev, reg); if (err < 0) return err; - err = bcm54xx_exp_write(phydev, reg, + err = bcm_phy_write_exp(phydev, reg, err & ~BCM5482_SSD_1000BX_CTL_PWRDOWN); if (err < 0) return err; @@ -288,15 +256,15 @@ static int bcm5482_config_init(struct phy_device *phydev) /* * Select 1000BASE-X register set (primary SerDes) */ - reg = bcm54xx_shadow_read(phydev, BCM5482_SHD_MODE); - bcm54xx_shadow_write(phydev, BCM5482_SHD_MODE, + reg = bcm_phy_read_shadow(phydev, BCM5482_SHD_MODE); + bcm_phy_write_shadow(phydev, BCM5482_SHD_MODE, reg | BCM5482_SHD_MODE_1000BX); /* * LED1=ACTIVITYLED, LED3=LINKSPD[2] * (Use LED1 as secondary SerDes ACTIVITY LED) */ - bcm54xx_shadow_write(phydev, BCM5482_SHD_LEDS1, + bcm_phy_write_shadow(phydev, BCM5482_SHD_LEDS1, BCM5482_SHD_LEDS1_LED1(BCM_LED_SRC_ACTIVITYLED) | BCM5482_SHD_LEDS1_LED3(BCM_LED_SRC_LINKSPD2)); @@ -334,35 +302,6 @@ static int bcm5482_read_status(struct phy_device *phydev) return err; } -static int bcm54xx_ack_interrupt(struct phy_device *phydev) -{ - int reg; - - /* Clear pending interrupts. */ - reg = phy_read(phydev, MII_BCM54XX_ISR); - if (reg < 0) - return reg; - - return 0; -} - -static int bcm54xx_config_intr(struct phy_device *phydev) -{ - int reg, err; - - reg = phy_read(phydev, MII_BCM54XX_ECR); - if (reg < 0) - return reg; - - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) - reg &= ~MII_BCM54XX_ECR_IM; - else - reg |= MII_BCM54XX_ECR_IM; - - err = phy_write(phydev, MII_BCM54XX_ECR, reg); - return err; -} - static int bcm5481_config_aneg(struct phy_device *phydev) { int ret; @@ -519,8 +458,8 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .ack_interrupt = bcm54xx_ack_interrupt, - .config_intr = bcm54xx_config_intr, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, .driver = { .owner = THIS_MODULE }, }, { .phy_id = PHY_ID_BCM5421, @@ -532,8 +471,8 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .ack_interrupt = bcm54xx_ack_interrupt, - .config_intr = bcm54xx_config_intr, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, .driver = { .owner = THIS_MODULE }, }, { .phy_id = PHY_ID_BCM5461, @@ -545,8 +484,8 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .ack_interrupt = bcm54xx_ack_interrupt, - .config_intr = bcm54xx_config_intr, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, .driver = { .owner = THIS_MODULE }, }, { .phy_id = PHY_ID_BCM54616S, @@ -558,8 +497,8 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .ack_interrupt = bcm54xx_ack_interrupt, - .config_intr = bcm54xx_config_intr, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, .driver = { .owner = THIS_MODULE }, }, { .phy_id = PHY_ID_BCM5464, @@ -571,8 +510,8 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .ack_interrupt = bcm54xx_ack_interrupt, - .config_intr = bcm54xx_config_intr, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, .driver = { .owner = THIS_MODULE }, }, { .phy_id = PHY_ID_BCM5481, @@ -584,8 +523,8 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_aneg = bcm5481_config_aneg, .read_status = genphy_read_status, - .ack_interrupt = bcm54xx_ack_interrupt, - .config_intr = bcm54xx_config_intr, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, .driver = { .owner = THIS_MODULE }, }, { .phy_id = PHY_ID_BCM5482, @@ -597,8 +536,8 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm5482_config_init, .config_aneg = genphy_config_aneg, .read_status = bcm5482_read_status, - .ack_interrupt = bcm54xx_ack_interrupt, - .config_intr = bcm54xx_config_intr, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, .driver = { .owner = THIS_MODULE }, }, { .phy_id = PHY_ID_BCM50610, @@ -610,8 +549,8 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .ack_interrupt = bcm54xx_ack_interrupt, - .config_intr = bcm54xx_config_intr, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, .driver = { .owner = THIS_MODULE }, }, { .phy_id = PHY_ID_BCM50610M, @@ -623,8 +562,8 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .ack_interrupt = bcm54xx_ack_interrupt, - .config_intr = bcm54xx_config_intr, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, .driver = { .owner = THIS_MODULE }, }, { .phy_id = PHY_ID_BCM57780, @@ -636,8 +575,8 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .ack_interrupt = bcm54xx_ack_interrupt, - .config_intr = bcm54xx_config_intr, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, .driver = { .owner = THIS_MODULE }, }, { .phy_id = PHY_ID_BCMAC131, diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 697ca7795bd9..6a53ab91407c 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -138,7 +138,10 @@ /* 01010: Auto Power-Down */ #define BCM54XX_SHD_APD 0x0a +#define BCM_APD_CLR_MASK 0xFE9F /* clear bits 5, 6 & 8 */ #define BCM54XX_SHD_APD_EN 0x0020 +#define BCM_NO_ANEG_APD_EN 0x0060 /* bits 5 & 6 */ +#define BCM_APD_SINGLELP_EN 0x0100 /* Bit 8 */ #define BCM5482_SHD_LEDS1 0x0d /* 01101: LED Selector 1 */ /* LED3 / ~LINKSPD[2] selector */ @@ -209,25 +212,6 @@ #define MII_BRCM_FET_SHDW_AUXSTAT2 0x1b /* Auxiliary status 2 */ #define MII_BRCM_FET_SHDW_AS2_APDE 0x0020 /* Auto power down enable */ -/* - * Indirect register access functions for the 1000BASE-T/100BASE-TX/10BASE-T - * 0x1c shadow registers. - */ -static inline int bcm54xx_shadow_read(struct phy_device *phydev, u16 shadow) -{ - phy_write(phydev, MII_BCM54XX_SHD, MII_BCM54XX_SHD_VAL(shadow)); - return MII_BCM54XX_SHD_DATA(phy_read(phydev, MII_BCM54XX_SHD)); -} - -static inline int bcm54xx_shadow_write(struct phy_device *phydev, u16 shadow, - u16 val) -{ - return phy_write(phydev, MII_BCM54XX_SHD, - MII_BCM54XX_SHD_WRITE | - MII_BCM54XX_SHD_VAL(shadow) | - MII_BCM54XX_SHD_DATA(val)); -} - #define BRCM_CL45VEN_EEE_CONTROL 0x803d #define LPI_FEATURE_EN 0x8000 #define LPI_FEATURE_EN_DIG1000X 0x4000 -- cgit v1.2.3 From 8e185d6997bb67068f0ca8f062a50caa2608cf1b Mon Sep 17 00:00:00 2001 From: Arun Parameswaran Date: Tue, 6 Oct 2015 12:25:49 -0700 Subject: net: phy: Broadcom Cygnus internal Etherent PHY driver Add support for the Broadcom Cygnus SoCs internal PHY's. The PHYs are 1000M/100M/10M capable with support for 'EEE' and 'APD' (Auto Power Down). This driver supports the following Broadcom Cygnus SoCs: - BCM583XX (BCM58300, BCM58302, BCM58303, BCM58305) - BCM113XX (BCM11300, BCM11320, BCM11350, BCM11360) The PHY's on these SoC's require some workarounds for stable operation, both during configuration time and during suspend/resume. This driver handles the application of the workarounds. Signed-off-by: Arun Parameswaran Signed-off-by: David S. Miller --- drivers/net/phy/Kconfig | 13 ++++ drivers/net/phy/Makefile | 1 + drivers/net/phy/bcm-cygnus.c | 158 +++++++++++++++++++++++++++++++++++++++++++ include/linux/brcmphy.h | 7 ++ 4 files changed, 179 insertions(+) create mode 100644 drivers/net/phy/bcm-cygnus.c (limited to 'include') diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 606fdc924768..9d097ae54fb2 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -79,6 +79,19 @@ config BROADCOM_PHY Currently supports the BCM5411, BCM5421, BCM5461, BCM54616S, BCM5464, BCM5481 and BCM5482 PHYs. +config BCM_CYGNUS_PHY + tristate "Drivers for Broadcom Cygnus SoC internal PHY" + depends on ARCH_BCM_CYGNUS || COMPILE_TEST + depends on MDIO_BCM_IPROC + select BCM_NET_PHYLIB + ---help--- + This PHY driver is for the 1G internal PHYs of the Broadcom + Cygnus Family SoC. + + Currently supports internal PHY's used in the BCM11300, + BCM11320, BCM11350, BCM11360, BCM58300, BCM58302, + BCM58303 & BCM58305 Broadcom Cygnus SoCs. + config BCM63XX_PHY tristate "Drivers for Broadcom 63xx SOCs internal PHY" depends on BCM63XX diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 6932475a1a8a..7655d47ad8d8 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_BROADCOM_PHY) += broadcom.o obj-$(CONFIG_BCM63XX_PHY) += bcm63xx.o obj-$(CONFIG_BCM7XXX_PHY) += bcm7xxx.o obj-$(CONFIG_BCM87XX_PHY) += bcm87xx.o +obj-$(CONFIG_BCM_CYGNUS_PHY) += bcm-cygnus.o obj-$(CONFIG_ICPLUS_PHY) += icplus.o obj-$(CONFIG_REALTEK_PHY) += realtek.o obj-$(CONFIG_LSI_ET1011C_PHY) += et1011c.o diff --git a/drivers/net/phy/bcm-cygnus.c b/drivers/net/phy/bcm-cygnus.c new file mode 100644 index 000000000000..49bbc6826883 --- /dev/null +++ b/drivers/net/phy/bcm-cygnus.c @@ -0,0 +1,158 @@ +/* + * Copyright (C) 2015 Broadcom Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +/* Broadcom Cygnus SoC internal transceivers support. */ +#include "bcm-phy-lib.h" +#include +#include +#include +#include + +/* Broadcom Cygnus Phy specific registers */ +#define MII_BCM_CYGNUS_AFE_VDAC_ICTRL_0 0x91E5 /* VDAL Control register */ + +static int bcm_cygnus_afe_config(struct phy_device *phydev) +{ + int rc; + + /* ensure smdspclk is enabled */ + rc = phy_write(phydev, MII_BCM54XX_AUX_CTL, 0x0c30); + if (rc < 0) + return rc; + + /* AFE_VDAC_ICTRL_0 bit 7:4 Iq=1100 for 1g 10bt, normal modes */ + rc = bcm_phy_write_misc(phydev, 0x39, 0x01, 0xA7C8); + if (rc < 0) + return rc; + + /* AFE_HPF_TRIM_OTHERS bit11=1, short cascode enable for all modes*/ + rc = bcm_phy_write_misc(phydev, 0x3A, 0x00, 0x0803); + if (rc < 0) + return rc; + + /* AFE_TX_CONFIG_1 bit 7:4 Iq=1100 for test modes */ + rc = bcm_phy_write_misc(phydev, 0x3A, 0x01, 0xA740); + if (rc < 0) + return rc; + + /* AFE TEMPSEN_OTHERS rcal_HT, rcal_LT 10000 */ + rc = bcm_phy_write_misc(phydev, 0x3A, 0x03, 0x8400); + if (rc < 0) + return rc; + + /* AFE_FUTURE_RSV bit 2:0 rccal <2:0>=100 */ + rc = bcm_phy_write_misc(phydev, 0x3B, 0x00, 0x0004); + if (rc < 0) + return rc; + + /* Adjust bias current trim to overcome digital offSet */ + rc = phy_write(phydev, MII_BRCM_CORE_BASE1E, 0x02); + if (rc < 0) + return rc; + + /* make rcal=100, since rdb default is 000 */ + rc = bcm_phy_write_exp(phydev, MII_BRCM_CORE_EXPB1, 0x10); + if (rc < 0) + return rc; + + /* CORE_EXPB0, Reset R_CAL/RC_CAL Engine */ + rc = bcm_phy_write_exp(phydev, MII_BRCM_CORE_EXPB0, 0x10); + if (rc < 0) + return rc; + + /* CORE_EXPB0, Disable Reset R_CAL/RC_CAL Engine */ + rc = bcm_phy_write_exp(phydev, MII_BRCM_CORE_EXPB0, 0x00); + + return 0; +} + +static int bcm_cygnus_config_init(struct phy_device *phydev) +{ + int reg, rc; + + reg = phy_read(phydev, MII_BCM54XX_ECR); + if (reg < 0) + return reg; + + /* Mask interrupts globally. */ + reg |= MII_BCM54XX_ECR_IM; + rc = phy_write(phydev, MII_BCM54XX_ECR, reg); + if (rc) + return rc; + + /* Unmask events of interest */ + reg = ~(MII_BCM54XX_INT_DUPLEX | + MII_BCM54XX_INT_SPEED | + MII_BCM54XX_INT_LINK); + rc = phy_write(phydev, MII_BCM54XX_IMR, reg); + if (rc) + return rc; + + /* Apply AFE settings for the PHY */ + rc = bcm_cygnus_afe_config(phydev); + if (rc) + return rc; + + /* Advertise EEE */ + rc = bcm_phy_enable_eee(phydev); + if (rc) + return rc; + + /* Enable APD */ + return bcm_phy_enable_apd(phydev, false); +} + +static int bcm_cygnus_resume(struct phy_device *phydev) +{ + int rc; + + genphy_resume(phydev); + + /* Re-initialize the PHY to apply AFE work-arounds and + * configurations when coming out of suspend. + */ + rc = bcm_cygnus_config_init(phydev); + if (rc) + return rc; + + /* restart auto negotiation with the new settings */ + return genphy_config_aneg(phydev); +} + +static struct phy_driver bcm_cygnus_phy_driver[] = { +{ + .phy_id = PHY_ID_BCM_CYGNUS, + .phy_id_mask = 0xfffffff0, + .name = "Broadcom Cygnus PHY", + .features = PHY_GBIT_FEATURES | + SUPPORTED_Pause | SUPPORTED_Asym_Pause, + .config_init = bcm_cygnus_config_init, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, + .suspend = genphy_suspend, + .resume = bcm_cygnus_resume, +} }; + +static struct mdio_device_id __maybe_unused bcm_cygnus_phy_tbl[] = { + { PHY_ID_BCM_CYGNUS, 0xfffffff0, }, + { } +}; +MODULE_DEVICE_TABLE(mdio, bcm_cygnus_phy_tbl); + +module_phy_driver(bcm_cygnus_phy_driver); + +MODULE_DESCRIPTION("Broadcom Cygnus internal PHY driver"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Broadcom Corporation"); diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6a53ab91407c..59f4a7304419 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -30,6 +30,8 @@ #define PHY_ID_BCM7439_2 0xae025080 #define PHY_ID_BCM7445 0x600d8510 +#define PHY_ID_BCM_CYGNUS 0xae025200 + #define PHY_BCM_OUI_MASK 0xfffffc00 #define PHY_BCM_OUI_1 0x00206000 #define PHY_BCM_OUI_2 0x0143bc00 @@ -216,4 +218,9 @@ #define LPI_FEATURE_EN 0x8000 #define LPI_FEATURE_EN_DIG1000X 0x4000 +/* Core register definitions*/ +#define MII_BRCM_CORE_BASE1E 0x1E +#define MII_BRCM_CORE_EXPB0 0xB0 +#define MII_BRCM_CORE_EXPB1 0xB1 + #endif /* _LINUX_BRCMPHY_H */ -- cgit v1.2.3 From 4d6a6aed22f91b35c14a6717d42953f260090175 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 2 Oct 2015 20:28:04 +0200 Subject: 6lowpan: move shared settings to lowpan_netdev_setup This patch moves values for all lowpan interface to the shared implementation of 6lowpan. This patch also quietly fixes the forgotten IFF_NO_QUEUE flag for the bluetooth 6LoWPAN interface. An identically commit is 4afbc0d ("net: 6lowpan: convert to using IFF_NO_QUEUE") which wasn't changed for bluetooth 6lowpan. All 6lowpan interfaces should be virtual with IFF_NO_QUEUE, using EUI64 address length, the mtu size is 1280 (IPV6_MIN_MTU) and the netdev type is ARPHRD_6LOWPAN. Signed-off-by: Alexander Aring Acked-by: Jukka Rissanen Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 2 ++ net/6lowpan/core.c | 5 +++++ net/bluetooth/6lowpan.c | 6 ------ net/ieee802154/6lowpan/core.c | 4 ---- 4 files changed, 7 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index c17f556644fc..07db532696df 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -61,6 +61,8 @@ #define UIP_PROTO_UDP 17 /* ipv6 next header value for UDP */ #define UIP_FRAGH_LEN 8 /* ipv6 fragment header size */ +#define EUI64_ADDR_LEN 8 + #define LOWPAN_NHC_MAX_ID_LEN 1 /* Max IPHC Header len without IPv6 hdr specific inline data. * Useful for getting the "extra" bytes we need at worst case compression. diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c index ae1896fa45e2..83b19e072224 100644 --- a/net/6lowpan/core.c +++ b/net/6lowpan/core.c @@ -17,6 +17,11 @@ void lowpan_netdev_setup(struct net_device *dev, enum lowpan_lltypes lltype) { + dev->addr_len = EUI64_ADDR_LEN; + dev->type = ARPHRD_6LOWPAN; + dev->mtu = IPV6_MIN_MTU; + dev->priv_flags |= IFF_NO_QUEUE; + lowpan_priv(dev)->lltype = lltype; } EXPORT_SYMBOL(lowpan_netdev_setup); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 9363f05275f4..db73b8a1433f 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -35,7 +35,6 @@ static struct dentry *lowpan_enable_debugfs; static struct dentry *lowpan_control_debugfs; #define IFACE_NAME_TEMPLATE "bt%d" -#define EUI64_ADDR_LEN 8 struct skb_cb { struct in6_addr addr; @@ -674,13 +673,8 @@ static struct header_ops header_ops = { static void netdev_setup(struct net_device *dev) { - dev->addr_len = EUI64_ADDR_LEN; - dev->type = ARPHRD_6LOWPAN; - dev->hard_header_len = 0; dev->needed_tailroom = 0; - dev->mtu = IPV6_MIN_MTU; - dev->tx_queue_len = 0; dev->flags = IFF_RUNNING | IFF_POINTOPOINT | IFF_MULTICAST; dev->watchdog_timeo = 0; diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 44420ed95574..20c49c724ba0 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -101,13 +101,9 @@ static const struct net_device_ops lowpan_netdev_ops = { static void lowpan_setup(struct net_device *ldev) { - ldev->addr_len = IEEE802154_ADDR_LEN; memset(ldev->broadcast, 0xff, IEEE802154_ADDR_LEN); - ldev->type = ARPHRD_6LOWPAN; /* We need an ipv6hdr as minimum len when calling xmit */ ldev->hard_header_len = sizeof(struct ipv6hdr); - ldev->mtu = IPV6_MIN_MTU; - ldev->priv_flags |= IFF_NO_QUEUE; ldev->flags = IFF_BROADCAST | IFF_MULTICAST; ldev->netdev_ops = &lowpan_netdev_ops; -- cgit v1.2.3 From 46234253b9363894a254844a6550b4cc5f3edfe8 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Thu, 8 Oct 2015 01:20:35 +0200 Subject: net: move net_get_random_once to lib There's no good reason why users outside of networking should not be using this facility, f.e. for initializing their seeds. Therefore, make it accessible from there as get_random_once(). Signed-off-by: Hannes Frederic Sowa Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/net.h | 21 ++++---------------- include/linux/once.h | 24 +++++++++++++++++++++++ lib/Makefile | 3 ++- lib/once.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++++ net/core/utils.c | 49 ----------------------------------------------- 5 files changed, 84 insertions(+), 67 deletions(-) create mode 100644 include/linux/once.h create mode 100644 lib/once.c (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index 049d4b03c4c4..70ac5e28e6b7 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -24,7 +24,8 @@ #include /* For O_CLOEXEC and O_NONBLOCK */ #include #include -#include +#include + #include struct poll_table_struct; @@ -250,22 +251,8 @@ do { \ } while (0) #endif -bool __net_get_random_once(void *buf, int nbytes, bool *done, - struct static_key *done_key); - -#define net_get_random_once(buf, nbytes) \ - ({ \ - bool ___ret = false; \ - static bool ___done = false; \ - static struct static_key ___once_key = \ - STATIC_KEY_INIT_TRUE; \ - if (static_key_true(&___once_key)) \ - ___ret = __net_get_random_once(buf, \ - nbytes, \ - &___done, \ - &___once_key); \ - ___ret; \ - }) +#define net_get_random_once(buf, nbytes) \ + get_random_once((buf), (nbytes)) int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); diff --git a/include/linux/once.h b/include/linux/once.h new file mode 100644 index 000000000000..2a83b538dd6a --- /dev/null +++ b/include/linux/once.h @@ -0,0 +1,24 @@ +#ifndef _LINUX_ONCE_H +#define _LINUX_ONCE_H + +#include +#include + +bool __get_random_once(void *buf, int nbytes, bool *done, + struct static_key *once_key); + +#define get_random_once(buf, nbytes) \ + ({ \ + bool ___ret = false; \ + static bool ___done = false; \ + static struct static_key ___once_key = \ + STATIC_KEY_INIT_TRUE; \ + if (static_key_true(&___once_key)) \ + ___ret = __get_random_once((buf), \ + (nbytes), \ + &___done, \ + &___once_key); \ + ___ret; \ + }) + +#endif /* _LINUX_ONCE_H */ diff --git a/lib/Makefile b/lib/Makefile index 13a7c6ae3fec..8de3b012eac7 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -26,7 +26,8 @@ obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \ gcd.o lcm.o list_sort.o uuid.o flex_array.o iov_iter.o clz_ctz.o \ bsearch.o find_bit.o llist.o memweight.o kfifo.o \ - percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o + percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o \ + once.o obj-y += string_helpers.o obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o obj-y += hexdump.o diff --git a/lib/once.c b/lib/once.c new file mode 100644 index 000000000000..2d5a7de17aba --- /dev/null +++ b/lib/once.c @@ -0,0 +1,54 @@ +#include +#include +#include +#include + +struct __random_once_work { + struct work_struct work; + struct static_key *key; +}; + +static void __random_once_deferred(struct work_struct *w) +{ + struct __random_once_work *work; + + work = container_of(w, struct __random_once_work, work); + BUG_ON(!static_key_enabled(work->key)); + static_key_slow_dec(work->key); + kfree(work); +} + +static void __random_once_disable_jump(struct static_key *key) +{ + struct __random_once_work *w; + + w = kmalloc(sizeof(*w), GFP_ATOMIC); + if (!w) + return; + + INIT_WORK(&w->work, __random_once_deferred); + w->key = key; + schedule_work(&w->work); +} + +bool __get_random_once(void *buf, int nbytes, bool *done, + struct static_key *once_key) +{ + static DEFINE_SPINLOCK(lock); + unsigned long flags; + + spin_lock_irqsave(&lock, flags); + if (*done) { + spin_unlock_irqrestore(&lock, flags); + return false; + } + + get_random_bytes(buf, nbytes); + *done = true; + spin_unlock_irqrestore(&lock, flags); + + __random_once_disable_jump(once_key); + + return true; +} +EXPORT_SYMBOL(__get_random_once); diff --git a/net/core/utils.c b/net/core/utils.c index 3dffce953c39..3d17ca8b4744 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -348,52 +348,3 @@ void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, } } EXPORT_SYMBOL(inet_proto_csum_replace_by_diff); - -struct __net_random_once_work { - struct work_struct work; - struct static_key *key; -}; - -static void __net_random_once_deferred(struct work_struct *w) -{ - struct __net_random_once_work *work = - container_of(w, struct __net_random_once_work, work); - BUG_ON(!static_key_enabled(work->key)); - static_key_slow_dec(work->key); - kfree(work); -} - -static void __net_random_once_disable_jump(struct static_key *key) -{ - struct __net_random_once_work *w; - - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (!w) - return; - - INIT_WORK(&w->work, __net_random_once_deferred); - w->key = key; - schedule_work(&w->work); -} - -bool __net_get_random_once(void *buf, int nbytes, bool *done, - struct static_key *once_key) -{ - static DEFINE_SPINLOCK(lock); - unsigned long flags; - - spin_lock_irqsave(&lock, flags); - if (*done) { - spin_unlock_irqrestore(&lock, flags); - return false; - } - - get_random_bytes(buf, nbytes); - *done = true; - spin_unlock_irqrestore(&lock, flags); - - __net_random_once_disable_jump(once_key); - - return true; -} -EXPORT_SYMBOL(__net_get_random_once); -- cgit v1.2.3 From c90aeb948222a7b3d3391d232ec4f50fd8322ad3 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Thu, 8 Oct 2015 01:20:36 +0200 Subject: once: make helper generic for calling functions once Make the get_random_once() helper generic enough, so that functions in general would only be called once, where one user of this is then net_get_random_once(). The only implementation specific call is to get_random_bytes(), all the rest of this *_once() facility would be duplicated among different subsystems otherwise. The new DO_ONCE() helper will be used by prandom() later on, but might also be useful for other scenarios/subsystems as well where a one-time initialization in often-called, possibly fast path code could occur. Signed-off-by: Hannes Frederic Sowa Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/once.h | 61 ++++++++++++++++++++++++++++++++++++++++------------ lib/once.c | 50 ++++++++++++++++++++++++------------------ 2 files changed, 76 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/linux/once.h b/include/linux/once.h index 2a83b538dd6a..285f12cb40e6 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -4,21 +4,54 @@ #include #include -bool __get_random_once(void *buf, int nbytes, bool *done, - struct static_key *once_key); +bool __do_once_start(bool *done, unsigned long *flags); +void __do_once_done(bool *done, struct static_key *once_key, + unsigned long *flags); -#define get_random_once(buf, nbytes) \ - ({ \ - bool ___ret = false; \ - static bool ___done = false; \ - static struct static_key ___once_key = \ - STATIC_KEY_INIT_TRUE; \ - if (static_key_true(&___once_key)) \ - ___ret = __get_random_once((buf), \ - (nbytes), \ - &___done, \ - &___once_key); \ - ___ret; \ +/* Call a function exactly once. The idea of DO_ONCE() is to perform + * a function call such as initialization of random seeds, etc, only + * once, where DO_ONCE() can live in the fast-path. After @func has + * been called with the passed arguments, the static key will patch + * out the condition into a nop. DO_ONCE() guarantees type safety of + * arguments! + * + * Not that the following is not equivalent ... + * + * DO_ONCE(func, arg); + * DO_ONCE(func, arg); + * + * ... to this version: + * + * void foo(void) + * { + * DO_ONCE(func, arg); + * } + * + * foo(); + * foo(); + * + * In case the one-time invocation could be triggered from multiple + * places, then a common helper function must be defined, so that only + * a single static key will be placed there! + */ +#define DO_ONCE(func, ...) \ + ({ \ + bool ___ret = false; \ + static bool ___done = false; \ + static struct static_key ___once_key = STATIC_KEY_INIT_TRUE; \ + if (static_key_true(&___once_key)) { \ + unsigned long ___flags; \ + ___ret = __do_once_start(&___done, &___flags); \ + if (unlikely(___ret)) { \ + func(__VA_ARGS__); \ + __do_once_done(&___done, &___once_key, \ + &___flags); \ + } \ + } \ + ___ret; \ }) +#define get_random_once(buf, nbytes) \ + DO_ONCE(get_random_bytes, (buf), (nbytes)) + #endif /* _LINUX_ONCE_H */ diff --git a/lib/once.c b/lib/once.c index 2d5a7de17aba..05c8604627eb 100644 --- a/lib/once.c +++ b/lib/once.c @@ -3,52 +3,60 @@ #include #include -struct __random_once_work { +struct once_work { struct work_struct work; struct static_key *key; }; -static void __random_once_deferred(struct work_struct *w) +static void once_deferred(struct work_struct *w) { - struct __random_once_work *work; + struct once_work *work; - work = container_of(w, struct __random_once_work, work); + work = container_of(w, struct once_work, work); BUG_ON(!static_key_enabled(work->key)); static_key_slow_dec(work->key); kfree(work); } -static void __random_once_disable_jump(struct static_key *key) +static void once_disable_jump(struct static_key *key) { - struct __random_once_work *w; + struct once_work *w; w = kmalloc(sizeof(*w), GFP_ATOMIC); if (!w) return; - INIT_WORK(&w->work, __random_once_deferred); + INIT_WORK(&w->work, once_deferred); w->key = key; schedule_work(&w->work); } -bool __get_random_once(void *buf, int nbytes, bool *done, - struct static_key *once_key) -{ - static DEFINE_SPINLOCK(lock); - unsigned long flags; +static DEFINE_SPINLOCK(once_lock); - spin_lock_irqsave(&lock, flags); +bool __do_once_start(bool *done, unsigned long *flags) + __acquires(once_lock) +{ + spin_lock_irqsave(&once_lock, *flags); if (*done) { - spin_unlock_irqrestore(&lock, flags); + spin_unlock_irqrestore(&once_lock, *flags); + /* Keep sparse happy by restoring an even lock count on + * this lock. In case we return here, we don't call into + * __do_once_done but return early in the DO_ONCE() macro. + */ + __acquire(once_lock); return false; } - get_random_bytes(buf, nbytes); - *done = true; - spin_unlock_irqrestore(&lock, flags); - - __random_once_disable_jump(once_key); - return true; } -EXPORT_SYMBOL(__get_random_once); +EXPORT_SYMBOL(__do_once_start); + +void __do_once_done(bool *done, struct static_key *once_key, + unsigned long *flags) + __releases(once_lock) +{ + *done = true; + spin_unlock_irqrestore(&once_lock, *flags); + once_disable_jump(once_key); +} +EXPORT_SYMBOL(__do_once_done); -- cgit v1.2.3 From 897ece56e714a2cc64e6914cb89a362d7021b36e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 8 Oct 2015 01:20:38 +0200 Subject: random32: add prandom_init_once helper for own rngs Add a prandom_init_once() facility that works on the rnd_state, so that users that are keeping their own state independent from prandom_u32() can initialize their taus113 per cpu states. The motivation here is similar to net_get_random_once(): initialize the state as late as possible in the hope that enough entropy has been collected for the seeding. prandom_init_once() makes use of the recently introduced prandom_seed_full_state() helper and is generic enough so that it could also be used on fast-paths due to the DO_ONCE(). Signed-off-by: Daniel Borkmann Acked-by: Hannes Frederic Sowa Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/random.h | 6 ++++++ lib/random32.c | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index e651874df2c9..a75840c1aa71 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -7,6 +7,8 @@ #define _LINUX_RANDOM_H #include +#include + #include struct random_ready_callback { @@ -45,6 +47,10 @@ struct rnd_state { u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); +void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); + +#define prandom_init_once(pcpu_state) \ + DO_ONCE(prandom_seed_full_state, (pcpu_state)) /** * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) diff --git a/lib/random32.c b/lib/random32.c index 36c09fb3fec9..12111910ccd0 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -238,7 +238,7 @@ static void __init __prandom_start_seed_timer(void) add_timer(&seed_timer); } -static void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state) +void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state) { int i; -- cgit v1.2.3 From 3ad0040573b0c00f88488bc31958acd07a55ee2e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 8 Oct 2015 01:20:39 +0200 Subject: bpf: split state from prandom_u32() and consolidate {c, e}BPF prngs While recently arguing on a seccomp discussion that raw prandom_u32() access shouldn't be exposed to unpriviledged user space, I forgot the fact that SKF_AD_RANDOM extension actually already does it for some time in cBPF via commit 4cd3675ebf74 ("filter: added BPF random opcode"). Since prandom_u32() is being used in a lot of critical networking code, lets be more conservative and split their states. Furthermore, consolidate eBPF and cBPF prandom handlers to use the new internal PRNG. For eBPF, bpf_get_prandom_u32() was only accessible for priviledged users, but should that change one day, we also don't want to leak raw sequences through things like eBPF maps. One thought was also to have own per bpf_prog states, but due to ABI reasons this is not easily possible, i.e. the program code currently cannot access bpf_prog itself, and copying the rnd_state to/from the stack scratch space whenever a program uses the prng seems not really worth the trouble and seems too hacky. If needed, taus113 could in such cases be implemented within eBPF using a map entry to keep the state space, or get_random_bytes() could become a second helper in cases where performance would not be critical. Both sides can trigger a one-time late init via prandom_init_once() on the shared state. Performance-wise, there should even be a tiny gain as bpf_user_rnd_u32() saves one function call. The PRNG needs to live inside the BPF core since kernels could have a NET-less config as well. Signed-off-by: Daniel Borkmann Acked-by: Hannes Frederic Sowa Acked-by: Alexei Starovoitov Cc: Chema Gonzalez Signed-off-by: David S. Miller --- include/linux/bpf.h | 4 ++++ kernel/bpf/core.c | 26 ++++++++++++++++++++++++++ kernel/bpf/helpers.c | 7 +------ kernel/bpf/syscall.c | 2 ++ net/core/filter.c | 9 ++------- 5 files changed, 35 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c915a6b54570..3697ad563899 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -200,4 +200,8 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_skb_vlan_push_proto; extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; +/* Shared helpers among cBPF and eBPF. */ +void bpf_user_rnd_init_once(void); +u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); + #endif /* _LINUX_BPF_H */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index c8855c2a7a48..80864712d2c4 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -731,6 +731,32 @@ void bpf_prog_free(struct bpf_prog *fp) } EXPORT_SYMBOL_GPL(bpf_prog_free); +/* RNG for unpriviledged user space with separated state from prandom_u32(). */ +static DEFINE_PER_CPU(struct rnd_state, bpf_user_rnd_state); + +void bpf_user_rnd_init_once(void) +{ + prandom_init_once(&bpf_user_rnd_state); +} + +u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + /* Should someone ever have the rather unwise idea to use some + * of the registers passed into this function, then note that + * this function is called from native eBPF and classic-to-eBPF + * transformations. Register assignments from both sides are + * different, f.e. classic always sets fn(ctx, A, X) here. + */ + struct rnd_state *state; + u32 res; + + state = &get_cpu_var(bpf_user_rnd_state); + res = prandom_u32_state(state); + put_cpu_var(state); + + return res; +} + /* Weak definitions of helper functions in case we don't have bpf syscall. */ const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1447ec09421e..4504ca66118d 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -93,13 +93,8 @@ const struct bpf_func_proto bpf_map_delete_elem_proto = { .arg2_type = ARG_PTR_TO_MAP_KEY, }; -static u64 bpf_get_prandom_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) -{ - return prandom_u32(); -} - const struct bpf_func_proto bpf_get_prandom_u32_proto = { - .func = bpf_get_prandom_u32, + .func = bpf_user_rnd_u32, .gpl_only = false, .ret_type = RET_INTEGER, }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5f35f420c12f..c868cafbc00c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -404,6 +404,8 @@ static void fixup_bpf_calls(struct bpf_prog *prog) if (insn->imm == BPF_FUNC_get_route_realm) prog->dst_needed = 1; + if (insn->imm == BPF_FUNC_get_prandom_u32) + bpf_user_rnd_init_once(); if (insn->imm == BPF_FUNC_tail_call) { /* mark bpf_tail_call as different opcode * to avoid conditional branch in diff --git a/net/core/filter.c b/net/core/filter.c index 8f4603c712cd..342e6c8fc415 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -149,12 +149,6 @@ static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) return raw_smp_processor_id(); } -/* note that this only generates 32-bit random numbers */ -static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) -{ - return prandom_u32(); -} - static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, struct bpf_insn *insn_buf) { @@ -313,7 +307,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, *insn = BPF_EMIT_CALL(__get_raw_cpu_id); break; case SKF_AD_OFF + SKF_AD_RANDOM: - *insn = BPF_EMIT_CALL(__get_random_u32); + *insn = BPF_EMIT_CALL(bpf_user_rnd_u32); + bpf_user_rnd_init_once(); break; } break; -- cgit v1.2.3 From 020446e01eebc9dbe7eda038e570ab9c7ab13586 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 8 Oct 2015 17:13:58 +0300 Subject: net/mlx5_core: Prepare cmd interface to system errors handling In preparation to handling system errors at the mlx5_core level, change the interface of cmd_work_handler to accept a 64 bit argument for the vector. This allows to encode a flag that signifies when the handler is called as a result of a driver logic that wishes to terminate commands that the hardware may not be able to terminate. Such command completions are detected at the handler and proper return status is encoded. To be able to terminate page handler commands, we make sure to set the corresponding bit in the bitmask. Signed-off-by: Eli Cohen Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 20 ++++++++++++++++++-- include/linux/mlx5/driver.h | 6 +++++- 2 files changed, 23 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 84838c2f528f..c3e54b7e8780 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -254,6 +254,10 @@ static void dump_buf(void *buf, int size, int data_only, int offset) pr_debug("\n"); } +enum { + MLX5_DRIVER_STATUS_ABORTED = 0xfe, +}; + const char *mlx5_command_str(int command) { switch (command) { @@ -473,6 +477,7 @@ static void cmd_work_handler(struct work_struct *work) struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd); struct mlx5_cmd_layout *lay; struct semaphore *sem; + unsigned long flags; sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); @@ -485,6 +490,9 @@ static void cmd_work_handler(struct work_struct *work) } } else { ent->idx = cmd->max_reg_cmds; + spin_lock_irqsave(&cmd->alloc_lock, flags); + clear_bit(ent->idx, &cmd->bitmask); + spin_unlock_irqrestore(&cmd->alloc_lock, flags); } ent->token = alloc_token(cmd); @@ -1081,7 +1089,7 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg) } } -void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector) +void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec) { struct mlx5_cmd *cmd = &dev->cmd; struct mlx5_cmd_work_ent *ent; @@ -1092,7 +1100,10 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector) s64 ds; struct mlx5_cmd_stats *stats; unsigned long flags; + unsigned long vector; + /* there can be at most 32 command queues */ + vector = vec & 0xffffffff; for (i = 0; i < (1 << cmd->log_sz); i++) { if (test_bit(i, &vector)) { struct semaphore *sem; @@ -1110,11 +1121,16 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector) ent->ret = verify_signature(ent); else ent->ret = 0; - ent->status = ent->lay->status_own >> 1; + if (vec & MLX5_TRIGGERED_CMD_COMP) + ent->status = MLX5_DRIVER_STATUS_ABORTED; + else + ent->status = ent->lay->status_own >> 1; + mlx5_core_dbg(dev, "command completed. ret 0x%x, delivery status %s(0x%x)\n", ent->ret, deliv_status_to_str(ent->status), ent->status); } free_ent(cmd, ent->idx); + if (ent->callback) { ds = ent->ts2 - ent->ts1; if (ent->op < ARRAY_SIZE(cmd->stats)) { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8b6d6f2154a4..aa899559eec0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -731,7 +731,7 @@ void mlx5_eq_pagefault(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe); #endif void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type); struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn); -void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector); +void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec); void mlx5_cq_event(struct mlx5_core_dev *dev, u32 cqn, int event_type); int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, int nent, u64 mask, const char *name, struct mlx5_uar *uar); @@ -865,4 +865,8 @@ static inline int mlx5_get_gid_table_len(u16 param) return 8 * (1 << param); } +enum { + MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, +}; + #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3 From ac6ea6e81a80172612e0c9ef93720f371b198918 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 8 Oct 2015 17:14:00 +0300 Subject: net/mlx5_core: Use private health thread for each device Use a single threaded work queue for each device in the system instead of using one thread for any device. This is required so we can concurrently process system error handling for all the devices that need that. Signed-off-by: Eli Cohen Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 63 +++++++++++------------- drivers/net/ethernet/mellanox/mlx5/core/main.c | 37 +++++++------- include/linux/mlx5/driver.h | 7 +-- 3 files changed, 52 insertions(+), 55 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 8770968fff35..9b81e1ceb8de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -57,31 +57,16 @@ enum { MLX5_HEALTH_SYNDR_HIGH_TEMP = 0x10 }; -static DEFINE_SPINLOCK(health_lock); -static LIST_HEAD(health_list); -static struct work_struct health_work; - static void health_care(struct work_struct *work) { - struct mlx5_core_health *health, *n; + struct mlx5_core_health *health; struct mlx5_core_dev *dev; struct mlx5_priv *priv; - LIST_HEAD(tlist); - - spin_lock_irq(&health_lock); - list_splice_init(&health_list, &tlist); - - spin_unlock_irq(&health_lock); - list_for_each_entry_safe(health, n, &tlist, list) { - priv = container_of(health, struct mlx5_priv, health); - dev = container_of(priv, struct mlx5_core_dev, priv); - mlx5_core_warn(dev, "handling bad device here\n"); - /* nothing yet */ - spin_lock_irq(&health_lock); - list_del_init(&health->list); - spin_unlock_irq(&health_lock); - } + health = container_of(work, struct mlx5_core_health, work); + priv = container_of(health, struct mlx5_priv, health); + dev = container_of(priv, struct mlx5_core_dev, priv); + mlx5_core_warn(dev, "handling bad device here\n"); } static const char *hsynd_str(u8 synd) @@ -168,11 +153,7 @@ static void poll_health(unsigned long data) if (health->miss_counter == MAX_MISSES) { mlx5_core_err(dev, "device's health compromised\n"); print_health_info(dev); - spin_lock_irq(&health_lock); - list_add_tail(&health->list, &health_list); - spin_unlock_irq(&health_lock); - - queue_work(mlx5_core_wq, &health_work); + queue_work(health->wq, &health->work); } else { get_random_bytes(&next, sizeof(next)); next %= HZ; @@ -185,7 +166,6 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; - INIT_LIST_HEAD(&health->list); init_timer(&health->timer); health->health = &dev->iseg->health; health->health_counter = &dev->iseg->health_counter; @@ -201,18 +181,33 @@ void mlx5_stop_health_poll(struct mlx5_core_dev *dev) struct mlx5_core_health *health = &dev->priv.health; del_timer_sync(&health->timer); - - spin_lock_irq(&health_lock); - if (!list_empty(&health->list)) - list_del_init(&health->list); - spin_unlock_irq(&health_lock); } -void mlx5_health_cleanup(void) +void mlx5_health_cleanup(struct mlx5_core_dev *dev) { + struct mlx5_core_health *health = &dev->priv.health; + + destroy_workqueue(health->wq); } -void __init mlx5_health_init(void) +int mlx5_health_init(struct mlx5_core_dev *dev) { - INIT_WORK(&health_work, health_care); + struct mlx5_core_health *health; + char *name; + + health = &dev->priv.health; + name = kmalloc(64, GFP_KERNEL); + if (!name) + return -ENOMEM; + + strcpy(name, "mlx5_health"); + strcat(name, dev_name(&dev->pdev->dev)); + health->wq = create_singlethread_workqueue(name); + kfree(name); + if (!health->wq) + return -ENOMEM; + + INIT_WORK(&health->work, health_care); + + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 7718f6ac6214..b6edc58766ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -62,7 +62,6 @@ static int prof_sel = MLX5_DEFAULT_PROF; module_param_named(prof_sel, prof_sel, int, 0444); MODULE_PARM_DESC(prof_sel, "profile selector. Valid range 0 - 2"); -struct workqueue_struct *mlx5_core_wq; static LIST_HEAD(intf_list); static LIST_HEAD(dev_list); static DEFINE_MUTEX(intf_mutex); @@ -1046,6 +1045,7 @@ err_pagealloc_cleanup: static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) { + int err; mlx5_unregister_device(dev); mlx5_cleanup_mr_table(dev); @@ -1060,9 +1060,10 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_eq_cleanup(dev); mlx5_disable_msix(dev); mlx5_stop_health_poll(dev); - if (mlx5_cmd_teardown_hca(dev)) { + err = mlx5_cmd_teardown_hca(dev); + if (err) { dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); - return 1; + goto out; } mlx5_pagealloc_stop(dev); mlx5_reclaim_startup_pages(dev); @@ -1070,11 +1071,12 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_pagealloc_cleanup(dev); mlx5_cmd_cleanup(dev); - return 0; +out: + return err; } static void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, - unsigned long param) + unsigned long param) { struct mlx5_priv *priv = &dev->priv; struct mlx5_device_context *dev_ctx; @@ -1129,14 +1131,22 @@ static int init_one(struct pci_dev *pdev, goto clean_dev; } + err = mlx5_health_init(dev); + if (err) { + dev_err(&pdev->dev, "mlx5_health_init failed with error code %d\n", err); + goto close_pci; + } + err = mlx5_load_one(dev, priv); if (err) { dev_err(&pdev->dev, "mlx5_load_one failed with error code %d\n", err); - goto close_pci; + goto clean_health; } return 0; +clean_health: + mlx5_health_cleanup(dev); close_pci: mlx5_pci_close(dev, priv); clean_dev: @@ -1153,8 +1163,10 @@ static void remove_one(struct pci_dev *pdev) if (mlx5_unload_one(dev, priv)) { dev_err(&dev->pdev->dev, "mlx5_unload_one failed\n"); + mlx5_health_cleanup(dev); return; } + mlx5_health_cleanup(dev); mlx5_pci_close(dev, priv); pci_set_drvdata(pdev, NULL); kfree(dev); @@ -1184,16 +1196,10 @@ static int __init init(void) int err; mlx5_register_debugfs(); - mlx5_core_wq = create_singlethread_workqueue("mlx5_core_wq"); - if (!mlx5_core_wq) { - err = -ENOMEM; - goto err_debug; - } - mlx5_health_init(); err = pci_register_driver(&mlx5_core_driver); if (err) - goto err_health; + goto err_debug; #ifdef CONFIG_MLX5_CORE_EN mlx5e_init(); @@ -1201,9 +1207,6 @@ static int __init init(void) return 0; -err_health: - mlx5_health_cleanup(); - destroy_workqueue(mlx5_core_wq); err_debug: mlx5_unregister_debugfs(); return err; @@ -1215,8 +1218,6 @@ static void __exit cleanup(void) mlx5e_cleanup(); #endif pci_unregister_driver(&mlx5_core_driver); - mlx5_health_cleanup(); - destroy_workqueue(mlx5_core_wq); mlx5_unregister_debugfs(); } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index aa899559eec0..41a32873f608 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -391,9 +391,10 @@ struct mlx5_core_health { struct health_buffer __iomem *health; __be32 __iomem *health_counter; struct timer_list timer; - struct list_head list; u32 prev; int miss_counter; + struct workqueue_struct *wq; + struct work_struct work; }; struct mlx5_cq_table { @@ -676,8 +677,8 @@ int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); -void mlx5_health_cleanup(void); -void __init mlx5_health_init(void); +void mlx5_health_cleanup(struct mlx5_core_dev *dev); +int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev); int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, -- cgit v1.2.3 From 61d03535e4be3a46c1e171a25458237e343195e3 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:28:54 +0800 Subject: net/netlink: lockdep_genl_is_held can be boolean This patch makes lockdep_genl_is_held return bool to improve readability due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/genetlink.h | 2 +- net/netlink/genetlink.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h index 09460d6d6682..a4c61cbce777 100644 --- a/include/linux/genetlink.h +++ b/include/linux/genetlink.h @@ -8,7 +8,7 @@ extern void genl_lock(void); extern void genl_unlock(void); #ifdef CONFIG_LOCKDEP -extern int lockdep_genl_is_held(void); +extern bool lockdep_genl_is_held(void); #endif /* for synchronisation between af_netlink and genetlink */ diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 75724a96aef2..bc0e504f33a6 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -39,7 +39,7 @@ void genl_unlock(void) EXPORT_SYMBOL(genl_unlock); #ifdef CONFIG_LOCKDEP -int lockdep_genl_is_held(void) +bool lockdep_genl_is_held(void) { return lockdep_is_held(&genl_mutex); } -- cgit v1.2.3 From 35498edc6481d588feadee7e76220884d5bbca48 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:28:55 +0800 Subject: net/ieee80211: ieee80211_is_* can be boolean This patch makes ieee80211_is_* return bool to improve readability due to these particular functions only using either one or zero as their return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/ieee80211.h | 76 +++++++++++++++++++++++------------------------ 1 file changed, 38 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f79a02a69d26..dcfb2f43d316 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -121,7 +121,7 @@ #define IEEE80211_MAX_SN IEEE80211_SN_MASK #define IEEE80211_SN_MODULO (IEEE80211_MAX_SN + 1) -static inline int ieee80211_sn_less(u16 sn1, u16 sn2) +static inline bool ieee80211_sn_less(u16 sn1, u16 sn2) { return ((sn1 - sn2) & IEEE80211_SN_MASK) > (IEEE80211_SN_MODULO >> 1); } @@ -250,7 +250,7 @@ struct ieee80211_qos_hdr { * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_tods(__le16 fc) +static inline bool ieee80211_has_tods(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_TODS)) != 0; } @@ -259,7 +259,7 @@ static inline int ieee80211_has_tods(__le16 fc) * ieee80211_has_fromds - check if IEEE80211_FCTL_FROMDS is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_fromds(__le16 fc) +static inline bool ieee80211_has_fromds(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FROMDS)) != 0; } @@ -268,7 +268,7 @@ static inline int ieee80211_has_fromds(__le16 fc) * ieee80211_has_a4 - check if IEEE80211_FCTL_TODS and IEEE80211_FCTL_FROMDS are set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_a4(__le16 fc) +static inline bool ieee80211_has_a4(__le16 fc) { __le16 tmp = cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS); return (fc & tmp) == tmp; @@ -278,7 +278,7 @@ static inline int ieee80211_has_a4(__le16 fc) * ieee80211_has_morefrags - check if IEEE80211_FCTL_MOREFRAGS is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_morefrags(__le16 fc) +static inline bool ieee80211_has_morefrags(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_MOREFRAGS)) != 0; } @@ -287,7 +287,7 @@ static inline int ieee80211_has_morefrags(__le16 fc) * ieee80211_has_retry - check if IEEE80211_FCTL_RETRY is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_retry(__le16 fc) +static inline bool ieee80211_has_retry(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_RETRY)) != 0; } @@ -296,7 +296,7 @@ static inline int ieee80211_has_retry(__le16 fc) * ieee80211_has_pm - check if IEEE80211_FCTL_PM is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_pm(__le16 fc) +static inline bool ieee80211_has_pm(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_PM)) != 0; } @@ -305,7 +305,7 @@ static inline int ieee80211_has_pm(__le16 fc) * ieee80211_has_moredata - check if IEEE80211_FCTL_MOREDATA is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_moredata(__le16 fc) +static inline bool ieee80211_has_moredata(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_MOREDATA)) != 0; } @@ -314,7 +314,7 @@ static inline int ieee80211_has_moredata(__le16 fc) * ieee80211_has_protected - check if IEEE80211_FCTL_PROTECTED is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_protected(__le16 fc) +static inline bool ieee80211_has_protected(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_PROTECTED)) != 0; } @@ -323,7 +323,7 @@ static inline int ieee80211_has_protected(__le16 fc) * ieee80211_has_order - check if IEEE80211_FCTL_ORDER is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_order(__le16 fc) +static inline bool ieee80211_has_order(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_ORDER)) != 0; } @@ -332,7 +332,7 @@ static inline int ieee80211_has_order(__le16 fc) * ieee80211_is_mgmt - check if type is IEEE80211_FTYPE_MGMT * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_mgmt(__le16 fc) +static inline bool ieee80211_is_mgmt(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT); @@ -342,7 +342,7 @@ static inline int ieee80211_is_mgmt(__le16 fc) * ieee80211_is_ctl - check if type is IEEE80211_FTYPE_CTL * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_ctl(__le16 fc) +static inline bool ieee80211_is_ctl(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL); @@ -352,7 +352,7 @@ static inline int ieee80211_is_ctl(__le16 fc) * ieee80211_is_data - check if type is IEEE80211_FTYPE_DATA * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_data(__le16 fc) +static inline bool ieee80211_is_data(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA); @@ -362,7 +362,7 @@ static inline int ieee80211_is_data(__le16 fc) * ieee80211_is_data_qos - check if type is IEEE80211_FTYPE_DATA and IEEE80211_STYPE_QOS_DATA is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_data_qos(__le16 fc) +static inline bool ieee80211_is_data_qos(__le16 fc) { /* * mask with QOS_DATA rather than IEEE80211_FCTL_STYPE as we just need @@ -376,7 +376,7 @@ static inline int ieee80211_is_data_qos(__le16 fc) * ieee80211_is_data_present - check if type is IEEE80211_FTYPE_DATA and has data * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_data_present(__le16 fc) +static inline bool ieee80211_is_data_present(__le16 fc) { /* * mask with 0x40 and test that that bit is clear to only return true @@ -390,7 +390,7 @@ static inline int ieee80211_is_data_present(__le16 fc) * ieee80211_is_assoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_REQ * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_assoc_req(__le16 fc) +static inline bool ieee80211_is_assoc_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_REQ); @@ -400,7 +400,7 @@ static inline int ieee80211_is_assoc_req(__le16 fc) * ieee80211_is_assoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_RESP * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_assoc_resp(__le16 fc) +static inline bool ieee80211_is_assoc_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_RESP); @@ -410,7 +410,7 @@ static inline int ieee80211_is_assoc_resp(__le16 fc) * ieee80211_is_reassoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_REQ * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_reassoc_req(__le16 fc) +static inline bool ieee80211_is_reassoc_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_REQ); @@ -420,7 +420,7 @@ static inline int ieee80211_is_reassoc_req(__le16 fc) * ieee80211_is_reassoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_RESP * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_reassoc_resp(__le16 fc) +static inline bool ieee80211_is_reassoc_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_RESP); @@ -430,7 +430,7 @@ static inline int ieee80211_is_reassoc_resp(__le16 fc) * ieee80211_is_probe_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_REQ * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_probe_req(__le16 fc) +static inline bool ieee80211_is_probe_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ); @@ -440,7 +440,7 @@ static inline int ieee80211_is_probe_req(__le16 fc) * ieee80211_is_probe_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_RESP * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_probe_resp(__le16 fc) +static inline bool ieee80211_is_probe_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP); @@ -450,7 +450,7 @@ static inline int ieee80211_is_probe_resp(__le16 fc) * ieee80211_is_beacon - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_BEACON * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_beacon(__le16 fc) +static inline bool ieee80211_is_beacon(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON); @@ -460,7 +460,7 @@ static inline int ieee80211_is_beacon(__le16 fc) * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_atim(__le16 fc) +static inline bool ieee80211_is_atim(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ATIM); @@ -470,7 +470,7 @@ static inline int ieee80211_is_atim(__le16 fc) * ieee80211_is_disassoc - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DISASSOC * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_disassoc(__le16 fc) +static inline bool ieee80211_is_disassoc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_DISASSOC); @@ -480,7 +480,7 @@ static inline int ieee80211_is_disassoc(__le16 fc) * ieee80211_is_auth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_AUTH * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_auth(__le16 fc) +static inline bool ieee80211_is_auth(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH); @@ -490,7 +490,7 @@ static inline int ieee80211_is_auth(__le16 fc) * ieee80211_is_deauth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DEAUTH * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_deauth(__le16 fc) +static inline bool ieee80211_is_deauth(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_DEAUTH); @@ -500,7 +500,7 @@ static inline int ieee80211_is_deauth(__le16 fc) * ieee80211_is_action - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ACTION * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_action(__le16 fc) +static inline bool ieee80211_is_action(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); @@ -510,7 +510,7 @@ static inline int ieee80211_is_action(__le16 fc) * ieee80211_is_back_req - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK_REQ * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_back_req(__le16 fc) +static inline bool ieee80211_is_back_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK_REQ); @@ -520,7 +520,7 @@ static inline int ieee80211_is_back_req(__le16 fc) * ieee80211_is_back - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_back(__le16 fc) +static inline bool ieee80211_is_back(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK); @@ -530,7 +530,7 @@ static inline int ieee80211_is_back(__le16 fc) * ieee80211_is_pspoll - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_PSPOLL * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_pspoll(__le16 fc) +static inline bool ieee80211_is_pspoll(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_PSPOLL); @@ -540,7 +540,7 @@ static inline int ieee80211_is_pspoll(__le16 fc) * ieee80211_is_rts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_RTS * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_rts(__le16 fc) +static inline bool ieee80211_is_rts(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_RTS); @@ -550,7 +550,7 @@ static inline int ieee80211_is_rts(__le16 fc) * ieee80211_is_cts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CTS * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_cts(__le16 fc) +static inline bool ieee80211_is_cts(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTS); @@ -560,7 +560,7 @@ static inline int ieee80211_is_cts(__le16 fc) * ieee80211_is_ack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_ACK * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_ack(__le16 fc) +static inline bool ieee80211_is_ack(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_ACK); @@ -570,7 +570,7 @@ static inline int ieee80211_is_ack(__le16 fc) * ieee80211_is_cfend - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFEND * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_cfend(__le16 fc) +static inline bool ieee80211_is_cfend(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CFEND); @@ -580,7 +580,7 @@ static inline int ieee80211_is_cfend(__le16 fc) * ieee80211_is_cfendack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFENDACK * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_cfendack(__le16 fc) +static inline bool ieee80211_is_cfendack(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CFENDACK); @@ -590,7 +590,7 @@ static inline int ieee80211_is_cfendack(__le16 fc) * ieee80211_is_nullfunc - check if frame is a regular (non-QoS) nullfunc frame * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_nullfunc(__le16 fc) +static inline bool ieee80211_is_nullfunc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC); @@ -600,7 +600,7 @@ static inline int ieee80211_is_nullfunc(__le16 fc) * ieee80211_is_qos_nullfunc - check if frame is a QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_qos_nullfunc(__le16 fc) +static inline bool ieee80211_is_qos_nullfunc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC); @@ -624,7 +624,7 @@ static inline bool ieee80211_is_bufferable_mmpdu(__le16 fc) * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set * @seq_ctrl: frame sequence control bytes in little-endian byteorder */ -static inline int ieee80211_is_first_frag(__le16 seq_ctrl) +static inline bool ieee80211_is_first_frag(__le16 seq_ctrl) { return (seq_ctrl & cpu_to_le16(IEEE80211_SCTL_FRAG)) == 0; } -- cgit v1.2.3 From 875e08294911b3cb8c60416d64d990809421de29 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:28:56 +0800 Subject: net/nfnetlink: lockdep_nfnl_is_held can be boolean This patch makes lockdep_nfnl_is_held return bool to improve readability due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 6 +++--- net/netfilter/nfnetlink.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index e955d4730625..249d1bb01e03 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -45,11 +45,11 @@ int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, void nfnl_lock(__u8 subsys_id); void nfnl_unlock(__u8 subsys_id); #ifdef CONFIG_PROVE_LOCKING -int lockdep_nfnl_is_held(__u8 subsys_id); +bool lockdep_nfnl_is_held(__u8 subsys_id); #else -static inline int lockdep_nfnl_is_held(__u8 subsys_id) +static inline bool lockdep_nfnl_is_held(__u8 subsys_id) { - return 1; + return true; } #endif /* CONFIG_PROVE_LOCKING */ diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 70277b11f742..f1d9e887f5b1 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -64,7 +64,7 @@ void nfnl_unlock(__u8 subsys_id) EXPORT_SYMBOL_GPL(nfnl_unlock); #ifdef CONFIG_PROVE_LOCKING -int lockdep_nfnl_is_held(u8 subsys_id) +bool lockdep_nfnl_is_held(u8 subsys_id) { return lockdep_is_held(&table[subsys_id].mutex); } -- cgit v1.2.3 From d6fbaea5f635216c9861587c4e658086cf3b1b6b Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:28:57 +0800 Subject: net/can: can_dropped_invalid_skb can be boolean This patch makes can_dropped_invalid_skb return bool due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Acked-by: Marc Kleine-Budde Signed-off-by: David S. Miller --- include/linux/can/dev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 56dcadd83716..735f9f8c4e43 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -78,7 +78,7 @@ struct can_priv { #define get_canfd_dlc(i) (min_t(__u8, (i), CANFD_MAX_DLC)) /* Drop a given socketbuffer if it does not contain a valid CAN frame. */ -static inline int can_dropped_invalid_skb(struct net_device *dev, +static inline bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb) { const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; @@ -94,12 +94,12 @@ static inline int can_dropped_invalid_skb(struct net_device *dev, } else goto inval_skb; - return 0; + return false; inval_skb: kfree_skb(skb); dev->stats.tx_dropped++; - return 1; + return true; } static inline bool can_is_canfd_skb(const struct sk_buff *skb) -- cgit v1.2.3 From 0c6119d99bf5df9403a688d267537284e9cc8bcb Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:28:58 +0800 Subject: net/dccp: dccp_list_has_service can be boolean This patch makes dccp_list_has_service return bool due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/dccp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 221025423e6c..61d042bbbf60 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -202,16 +202,16 @@ struct dccp_service_list { #define DCCP_SERVICE_INVALID_VALUE htonl((__u32)-1) #define DCCP_SERVICE_CODE_IS_ABSENT 0 -static inline int dccp_list_has_service(const struct dccp_service_list *sl, +static inline bool dccp_list_has_service(const struct dccp_service_list *sl, const __be32 service) { if (likely(sl != NULL)) { u32 i = sl->dccpsl_nr; while (i--) if (sl->dccpsl_list[i] == service) - return 1; + return true; } - return 0; + return false; } struct dccp_ackvec; -- cgit v1.2.3 From c3225164cf60ccecce2459dcb5813dd798233f2d Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:29:00 +0800 Subject: net/inetdevice: inet_ifa_match can be boolean This patch makes inet_ifa_match return bool due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index a4328cea376a..3b0999e0260f 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -171,7 +171,7 @@ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); -static __inline__ int inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) +static __inline__ bool inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } -- cgit v1.2.3 From f06cc7b284f3dfb2c5decbf9fde711b50a530050 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:29:01 +0800 Subject: net/inetdevice: bad_mask can be boolean This patch makes bad_mask return bool due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 3b0999e0260f..ee971f335a8b 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -180,15 +180,15 @@ static __inline__ bool inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) * Check if a mask is acceptable. */ -static __inline__ int bad_mask(__be32 mask, __be32 addr) +static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) - return 1; + return true; hmask = ntohl(mask); if (hmask & (hmask+1)) - return 1; - return 0; + return true; + return false; } #define for_primary_ifa(in_dev) { struct in_ifaddr *ifa; \ -- cgit v1.2.3 From 0cbf334376d5e82d7a2f5cd234ca4f5d0843f3ea Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:29:02 +0800 Subject: net/core: lockdep_rtnl_is_held can be boolean This patch makes lockdep_rtnl_is_held return bool due to this particular function only using either one or zero as its return value. In another patch lockdep_is_held is also made return bool. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 6 +++--- net/core/rtnetlink.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 39adaa9529eb..4be5048b1fbe 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -33,11 +33,11 @@ extern wait_queue_head_t netdev_unregistering_wq; extern struct mutex net_mutex; #ifdef CONFIG_PROVE_LOCKING -extern int lockdep_rtnl_is_held(void); +extern bool lockdep_rtnl_is_held(void); #else -static inline int lockdep_rtnl_is_held(void) +static inline bool lockdep_rtnl_is_held(void) { - return 1; + return true; } #endif /* #ifdef CONFIG_PROVE_LOCKING */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b2258a36d894..24775953fa68 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -96,7 +96,7 @@ int rtnl_is_locked(void) EXPORT_SYMBOL(rtnl_is_locked); #ifdef CONFIG_PROVE_LOCKING -int lockdep_rtnl_is_held(void) +bool lockdep_rtnl_is_held(void) { return lockdep_is_held(&rtnl_mutex); } -- cgit v1.2.3 From ff936a04e5f28b7e0455be0e7fa91334f89e4b44 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 7 Oct 2015 10:55:41 -0700 Subject: bpf: fix cb access in socket filter programs eBPF socket filter programs may see junk in 'u32 cb[5]' area, since it could have been used by protocol layers earlier. For socket filter programs used in af_packet we need to clean 20 bytes of skb->cb area if it could be used by the program. For programs attached to TCP/UDP sockets we need to save/restore these 20 bytes, since it's used by protocol layers. Remove SK_RUN_FILTER macro, since it's no longer used. Long term we may move this bpf cb area to per-cpu scratch, but that requires addition of new 'per-cpu load/store' instructions, so not suitable as a short term fix. Fixes: d691f9e8d440 ("bpf: allow programs to write to certain skb fields") Reported-by: Eric Dumazet Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 6 +++--- include/linux/filter.h | 39 +++++++++++++++++++++++++++++++++++---- kernel/bpf/verifier.c | 2 +- net/core/filter.c | 12 +++++++----- net/packet/af_packet.c | 10 +++++----- 5 files changed, 51 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3697ad563899..b4fdee6cb686 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -100,6 +100,8 @@ enum bpf_access_type { BPF_WRITE = 2 }; +struct bpf_prog; + struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); @@ -111,7 +113,7 @@ struct bpf_verifier_ops { u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, - struct bpf_insn *insn); + struct bpf_insn *insn, struct bpf_prog *prog); }; struct bpf_prog_type_list { @@ -120,8 +122,6 @@ struct bpf_prog_type_list { enum bpf_prog_type type; }; -struct bpf_prog; - struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; diff --git a/include/linux/filter.h b/include/linux/filter.h index 1bbce14bcf17..4165e9ac9e36 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -13,6 +13,7 @@ #include #include #include +#include #include @@ -302,10 +303,6 @@ struct bpf_prog_aux; bpf_size; \ }) -/* Macro to invoke filter function. */ -#define SK_RUN_FILTER(filter, ctx) \ - (*filter->prog->bpf_func)(ctx, filter->prog->insnsi) - #ifdef CONFIG_COMPAT /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { @@ -329,6 +326,7 @@ struct bpf_prog { kmemcheck_bitfield_begin(meta); u16 jited:1, /* Is our filter JIT'ed? */ gpl_compatible:1, /* Is filter GPL compatible? */ + cb_access:1, /* Is control block accessed? */ dst_needed:1; /* Do we need dst entry? */ kmemcheck_bitfield_end(meta); u32 len; /* Number of filter blocks */ @@ -352,6 +350,39 @@ struct sk_filter { #define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi) +static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u8 *cb_data = qdisc_skb_cb(skb)->data; + u8 saved_cb[QDISC_CB_PRIV_LEN]; + u32 res; + + BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != + QDISC_CB_PRIV_LEN); + + if (unlikely(prog->cb_access)) { + memcpy(saved_cb, cb_data, sizeof(saved_cb)); + memset(cb_data, 0, sizeof(saved_cb)); + } + + res = BPF_PROG_RUN(prog, skb); + + if (unlikely(prog->cb_access)) + memcpy(cb_data, saved_cb, sizeof(saved_cb)); + + return res; +} + +static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u8 *cb_data = qdisc_skb_cb(skb)->data; + + if (unlikely(prog->cb_access)) + memset(cb_data, 0, QDISC_CB_PRIV_LEN); + return BPF_PROG_RUN(prog, skb); +} + static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b074b23000d6..f8da034c2258 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2024,7 +2024,7 @@ static int convert_ctx_accesses(struct verifier_env *env) cnt = env->prog->aux->ops-> convert_ctx_access(type, insn->dst_reg, insn->src_reg, - insn->off, insn_buf); + insn->off, insn_buf, env->prog); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { verbose("bpf verifier is misconfigured\n"); return -EINVAL; diff --git a/net/core/filter.c b/net/core/filter.c index 342e6c8fc415..5f4cf1cffed3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -56,10 +56,10 @@ * @sk: sock associated with &sk_buff * @skb: buffer to filter * - * Run the filter code and then cut skb->data to correct size returned by - * SK_RUN_FILTER. If pkt_len is 0 we toss packet. If skb->len is smaller + * Run the eBPF program and then cut skb->data to correct size returned by + * the program. If pkt_len is 0 we toss packet. If skb->len is smaller * than pkt_len we keep whole skb->data. This is the socket level - * wrapper to SK_RUN_FILTER. It returns 0 if the packet should + * wrapper to BPF_PROG_RUN. It returns 0 if the packet should * be accepted or -EPERM if the packet should be tossed. * */ @@ -83,7 +83,7 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter) { - unsigned int pkt_len = SK_RUN_FILTER(filter, skb); + unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb); err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; } @@ -1736,7 +1736,8 @@ static bool tc_cls_act_is_valid_access(int off, int size, static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, - struct bpf_insn *insn_buf) + struct bpf_insn *insn_buf, + struct bpf_prog *prog) { struct bpf_insn *insn = insn_buf; @@ -1827,6 +1828,7 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, offsetof(struct __sk_buff, cb[4]): BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); + prog->cb_access = 1; ctx_off -= offsetof(struct __sk_buff, cb[0]); ctx_off += offsetof(struct sk_buff, cb); ctx_off += offsetof(struct qdisc_skb_cb, data); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 81c900fbc4a4..104910f7d1fb 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1423,7 +1423,7 @@ static unsigned int fanout_demux_bpf(struct packet_fanout *f, rcu_read_lock(); prog = rcu_dereference(f->bpf_prog); if (prog) - ret = BPF_PROG_RUN(prog, skb) % num; + ret = bpf_prog_run_clear_cb(prog, skb) % num; rcu_read_unlock(); return ret; @@ -1939,16 +1939,16 @@ out_free: return err; } -static unsigned int run_filter(const struct sk_buff *skb, - const struct sock *sk, - unsigned int res) +static unsigned int run_filter(struct sk_buff *skb, + const struct sock *sk, + unsigned int res) { struct sk_filter *filter; rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) - res = SK_RUN_FILTER(filter, skb); + res = bpf_prog_run_clear_cb(filter->prog, skb); rcu_read_unlock(); return res; -- cgit v1.2.3 From e446f9dfe17bbaa76a1fe22912636f38be1e1af8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Oct 2015 05:01:55 -0700 Subject: net: synack packets can be attached to request sockets selinux needs few changes to accommodate fact that SYNACK messages can be attached to a request socket, lacking sk_security pointer (Only syncookies are still attached to a TCP_LISTEN socket) Adds a new sk_listener() helper, and use it in selinux and sch_fq Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet Reported by: kernel test robot Cc: Paul Moore Cc: Stephen Smalley Cc: Eric Paris Acked-by: Paul Moore Signed-off-by: David S. Miller --- include/net/sock.h | 8 ++++++++ net/sched/sch_fq.c | 3 ++- security/selinux/hooks.c | 12 ++++++++---- 3 files changed, 18 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index dfe2eb8e1132..771ca1996442 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2201,6 +2201,14 @@ static inline bool sk_fullsock(const struct sock *sk) return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); } +/* This helper checks if a socket is a LISTEN or NEW_SYN_RECV + * SYNACK messages can be attached to either ones (depending on SYNCOOKIE) + */ +static inline bool sk_listener(const struct sock *sk) +{ + return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); +} + void sock_enable_timestamp(struct sock *sk, int flag); int sock_get_timestamp(struct sock *, struct timeval __user *); int sock_get_timestampns(struct sock *, struct timespec __user *); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 3386cce4751e..109b2322778f 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -225,6 +225,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) return &q->internal; /* SYNACK messages are attached to a TCP_NEW_SYN_RECV request socket + * or a listener (SYNCOOKIE mode) * 1) request sockets are not full blown, * they do not contain sk_pacing_rate * 2) They are not part of a 'flow' yet @@ -232,7 +233,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) * especially if the listener set SO_MAX_PACING_RATE * 4) We pretend they are orphaned */ - if (!sk || sk->sk_state == TCP_NEW_SYN_RECV) { + if (!sk || sk_listener(sk)) { unsigned long hash = skb_get_hash(skb) & q->orphan_mask; /* By forcing low order bit to 1, we make sure to not diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 64340160f4ac..6e50841ef1f6 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4898,7 +4898,7 @@ static unsigned int selinux_ip_output(struct sk_buff *skb, if (sk) { struct sk_security_struct *sksec; - if (sk->sk_state == TCP_LISTEN) + if (sk_listener(sk)) /* if the socket is the listening state then this * packet is a SYN-ACK packet which means it needs to * be labeled based on the connection/request_sock and @@ -5005,7 +5005,7 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, * unfortunately, this means more work, but it is only once per * connection. */ if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL && - !(sk != NULL && sk->sk_state == TCP_LISTEN)) + !(sk && sk_listener(sk))) return NF_ACCEPT; #endif @@ -5022,7 +5022,7 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, secmark_perm = PACKET__SEND; peer_sid = SECINITSID_KERNEL; } - } else if (sk->sk_state == TCP_LISTEN) { + } else if (sk_listener(sk)) { /* Locally generated packet but the associated socket is in the * listening state which means this is a SYN-ACK packet. In * this particular case the correct security label is assigned @@ -5033,7 +5033,11 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, * selinux_inet_conn_request(). See also selinux_ip_output() * for similar problems. */ u32 skb_sid; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec; + + if (sk->sk_state == TCP_NEW_SYN_RECV) + sk = inet_reqsk(sk)->rsk_listener; + sksec = sk->sk_security; if (selinux_skb_peerlbl_sid(skb, family, &skb_sid)) return NF_DROP; /* At this point, if the returned skb peerlbl is SECSID_NULL -- cgit v1.2.3 From 146a32067b3fde1424d737d7fb333eb0951e6419 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 8 Oct 2015 11:35:12 -0400 Subject: net: dsa: add port_fdb_prepare Push the prepare phase for FDB operations down to the DSA drivers, with a new port_fdb_prepare function. Currently only mv88e6xxx is affected. Signed-off-by: Vivien Didelot Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6171.c | 1 + drivers/net/dsa/mv88e6352.c | 1 + drivers/net/dsa/mv88e6xxx.c | 10 ++++++++++ drivers/net/dsa/mv88e6xxx.h | 3 +++ include/net/dsa.h | 6 ++++++ net/dsa/slave.c | 7 +++++-- 6 files changed, 26 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/dsa/mv88e6171.c b/drivers/net/dsa/mv88e6171.c index c95cfab56a4f..ca3330aec740 100644 --- a/drivers/net/dsa/mv88e6171.c +++ b/drivers/net/dsa/mv88e6171.c @@ -121,6 +121,7 @@ struct dsa_switch_driver mv88e6171_switch_driver = { .port_vlan_add = mv88e6xxx_port_vlan_add, .port_vlan_del = mv88e6xxx_port_vlan_del, .vlan_getnext = mv88e6xxx_vlan_getnext, + .port_fdb_prepare = mv88e6xxx_port_fdb_prepare, .port_fdb_add = mv88e6xxx_port_fdb_add, .port_fdb_del = mv88e6xxx_port_fdb_del, .port_fdb_getnext = mv88e6xxx_port_fdb_getnext, diff --git a/drivers/net/dsa/mv88e6352.c b/drivers/net/dsa/mv88e6352.c index 37367060676f..078a358c1b83 100644 --- a/drivers/net/dsa/mv88e6352.c +++ b/drivers/net/dsa/mv88e6352.c @@ -348,6 +348,7 @@ struct dsa_switch_driver mv88e6352_switch_driver = { .port_vlan_add = mv88e6xxx_port_vlan_add, .port_vlan_del = mv88e6xxx_port_vlan_del, .vlan_getnext = mv88e6xxx_vlan_getnext, + .port_fdb_prepare = mv88e6xxx_port_fdb_prepare, .port_fdb_add = mv88e6xxx_port_fdb_add, .port_fdb_del = mv88e6xxx_port_fdb_del, .port_fdb_getnext = mv88e6xxx_port_fdb_getnext, diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index 8e088e355834..0da865171798 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -1841,6 +1841,16 @@ static int _mv88e6xxx_port_fdb_load(struct dsa_switch *ds, int port, return _mv88e6xxx_atu_load(ds, &entry); } +int mv88e6xxx_port_fdb_prepare(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_fdb *fdb, + struct switchdev_trans *trans) +{ + /* We don't need any dynamic resource from the kernel (yet), + * so skip the prepare phase. + */ + return 0; +} + int mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid) { diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h index d8ec48710b80..304286924642 100644 --- a/drivers/net/dsa/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx.h @@ -474,6 +474,9 @@ int mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, u16 vid, int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, u16 vid); int mv88e6xxx_vlan_getnext(struct dsa_switch *ds, u16 *vid, unsigned long *ports, unsigned long *untagged); +int mv88e6xxx_port_fdb_prepare(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_fdb *fdb, + struct switchdev_trans *trans); int mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid); int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port, diff --git a/include/net/dsa.h b/include/net/dsa.h index b34d812bc5d0..4f66f8411583 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -197,6 +197,9 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) return ds->pd->rtable[dst->cpu_switch]; } +struct switchdev_trans; +struct switchdev_obj_port_fdb; + struct dsa_switch_driver { struct list_head list; @@ -316,6 +319,9 @@ struct dsa_switch_driver { /* * Forwarding database */ + int (*port_fdb_prepare)(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_fdb *fdb, + struct switchdev_trans *trans); int (*port_fdb_add)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid); int (*port_fdb_del)(struct dsa_switch *ds, int port, diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 4f607bc2a845..48e8c15a2611 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -346,10 +346,13 @@ static int dsa_slave_port_fdb_add(struct net_device *dev, { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - int ret = -EOPNOTSUPP; + int ret; + + if (!ds->drv->port_fdb_prepare || !ds->drv->port_fdb_add) + return -EOPNOTSUPP; if (switchdev_trans_ph_prepare(trans)) - ret = ds->drv->port_fdb_add ? 0 : -EOPNOTSUPP; + ret = ds->drv->port_fdb_prepare(ds, p->port, fdb, trans); else ret = ds->drv->port_fdb_add(ds, p->port, fdb->addr, fdb->vid); -- cgit v1.2.3 From 1f36faf26943f5f5fc1d1a7be6ce252d2ff25e1a Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 8 Oct 2015 11:35:13 -0400 Subject: net: dsa: push prepare phase in port_fdb_add Now that the prepare phase is pushed down to the DSA drivers, propagate it to the port_fdb_add function. Signed-off-by: Vivien Didelot Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx.c | 8 +++++--- drivers/net/dsa/mv88e6xxx.h | 3 ++- include/net/dsa.h | 3 ++- net/dsa/slave.c | 2 +- 4 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index 0da865171798..644fffc6b98b 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "mv88e6xxx.h" /* MDIO bus access can be nested in the case of PHYs connected to the @@ -1852,16 +1853,17 @@ int mv88e6xxx_port_fdb_prepare(struct dsa_switch *ds, int port, } int mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid) + const struct switchdev_obj_port_fdb *fdb, + struct switchdev_trans *trans) { - int state = is_multicast_ether_addr(addr) ? + int state = is_multicast_ether_addr(fdb->addr) ? GLOBAL_ATU_DATA_STATE_MC_STATIC : GLOBAL_ATU_DATA_STATE_UC_STATIC; struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); int ret; mutex_lock(&ps->smi_mutex); - ret = _mv88e6xxx_port_fdb_load(ds, port, addr, vid, state); + ret = _mv88e6xxx_port_fdb_load(ds, port, fdb->addr, fdb->vid, state); mutex_unlock(&ps->smi_mutex); return ret; diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h index 304286924642..86a94dc0d86e 100644 --- a/drivers/net/dsa/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx.h @@ -478,7 +478,8 @@ int mv88e6xxx_port_fdb_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans); int mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid); + const struct switchdev_obj_port_fdb *fdb, + struct switchdev_trans *trans); int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid); int mv88e6xxx_port_fdb_getnext(struct dsa_switch *ds, int port, diff --git a/include/net/dsa.h b/include/net/dsa.h index 4f66f8411583..ce8f9b748a77 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -323,7 +323,8 @@ struct dsa_switch_driver { const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans); int (*port_fdb_add)(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid); + const struct switchdev_obj_port_fdb *fdb, + struct switchdev_trans *trans); int (*port_fdb_del)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid); int (*port_fdb_getnext)(struct dsa_switch *ds, int port, diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 48e8c15a2611..6f7f27e9410c 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -354,7 +354,7 @@ static int dsa_slave_port_fdb_add(struct net_device *dev, if (switchdev_trans_ph_prepare(trans)) ret = ds->drv->port_fdb_prepare(ds, p->port, fdb, trans); else - ret = ds->drv->port_fdb_add(ds, p->port, fdb->addr, fdb->vid); + ret = ds->drv->port_fdb_add(ds, p->port, fdb, trans); return ret; } -- cgit v1.2.3 From 8057b3e7a1cfb4da61717ba609e1ea642bb82f9b Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 8 Oct 2015 11:35:14 -0400 Subject: net: dsa: use switchdev obj in port_fdb_del For consistency with the FDB add operation, propagate the switchdev_obj_port_fdb structure in the DSA drivers. Signed-off-by: Vivien Didelot Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx.c | 4 ++-- drivers/net/dsa/mv88e6xxx.h | 2 +- include/net/dsa.h | 2 +- net/dsa/slave.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index 644fffc6b98b..87b405e4f9f6 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -1870,13 +1870,13 @@ int mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port, } int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid) + const struct switchdev_obj_port_fdb *fdb) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); int ret; mutex_lock(&ps->smi_mutex); - ret = _mv88e6xxx_port_fdb_load(ds, port, addr, vid, + ret = _mv88e6xxx_port_fdb_load(ds, port, fdb->addr, fdb->vid, GLOBAL_ATU_DATA_STATE_UNUSED); mutex_unlock(&ps->smi_mutex); diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h index 86a94dc0d86e..8325c11b9be2 100644 --- a/drivers/net/dsa/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx.h @@ -481,7 +481,7 @@ int mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port, const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans); int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid); + const struct switchdev_obj_port_fdb *fdb); int mv88e6xxx_port_fdb_getnext(struct dsa_switch *ds, int port, unsigned char *addr, u16 *vid, bool *is_static); int mv88e6xxx_phy_page_read(struct dsa_switch *ds, int port, int page, int reg); diff --git a/include/net/dsa.h b/include/net/dsa.h index ce8f9b748a77..e00588625bc2 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -326,7 +326,7 @@ struct dsa_switch_driver { const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans); int (*port_fdb_del)(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid); + const struct switchdev_obj_port_fdb *fdb); int (*port_fdb_getnext)(struct dsa_switch *ds, int port, unsigned char *addr, u16 *vid, bool *is_static); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 6f7f27e9410c..bb2bd3b56b16 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -367,7 +367,7 @@ static int dsa_slave_port_fdb_del(struct net_device *dev, int ret = -EOPNOTSUPP; if (ds->drv->port_fdb_del) - ret = ds->drv->port_fdb_del(ds, p->port, fdb->addr, fdb->vid); + ret = ds->drv->port_fdb_del(ds, p->port, fdb); return ret; } -- cgit v1.2.3 From f55ac58ae64cbb0315382e738681fe31837dcac0 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 8 Oct 2015 19:23:17 -0700 Subject: switchdev: add bridge ageing_time attribute Setting the stage to push bridge-level attributes down to port driver so hardware can be programmed accordingly. Bridge-level attribute example is ageing_time. This is a per-bridge attribute, not a per-bridge-port attr. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 89266a3e473d..61f129bd74b2 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -43,6 +43,7 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_PORT_PARENT_ID, SWITCHDEV_ATTR_ID_PORT_STP_STATE, SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, + SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, }; struct switchdev_attr { @@ -52,6 +53,7 @@ struct switchdev_attr { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */ + u32 ageing_time; /* BRIDGE_AGEING_TIME */ } u; }; -- cgit v1.2.3 From 464314ea6c119ebc22ee78453e63814453c31611 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 8 Oct 2015 19:23:18 -0700 Subject: switchdev: skip over ports returning -EOPNOTSUPP when recursing ports This allows us to recurse over all the ports, skipping over unsupporting ports. Without the change, the recursion would stop at first unsupported port. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 + net/switchdev/switchdev.c | 9 ++++++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 61f129bd74b2..1ce70830357d 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -16,6 +16,7 @@ #include #define SWITCHDEV_F_NO_RECURSE BIT(0) +#define SWITCHDEV_F_SKIP_EOPNOTSUPP BIT(1) struct switchdev_trans_item { struct list_head list; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 6e4a4f9ad927..7a9ab90363be 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -147,7 +147,7 @@ static int __switchdev_port_attr_set(struct net_device *dev, return ops->switchdev_port_attr_set(dev, attr, trans); if (attr->flags & SWITCHDEV_F_NO_RECURSE) - return err; + goto done; /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to set attr on @@ -156,10 +156,17 @@ static int __switchdev_port_attr_set(struct net_device *dev, netdev_for_each_lower_dev(dev, lower_dev, iter) { err = __switchdev_port_attr_set(lower_dev, attr, trans); + if (err == -EOPNOTSUPP && + attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP) + continue; if (err) break; } +done: + if (err == -EOPNOTSUPP && attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP) + err = 0; + return err; } -- cgit v1.2.3 From 1be7f75d1668d6296b80bf35dcf6762393530afc Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 7 Oct 2015 22:23:21 -0700 Subject: bpf: enable non-root eBPF programs In order to let unprivileged users load and execute eBPF programs teach verifier to prevent pointer leaks. Verifier will prevent - any arithmetic on pointers (except R10+Imm which is used to compute stack addresses) - comparison of pointers (except if (map_value_ptr == 0) ... ) - passing pointers to helper functions - indirectly passing pointers in stack to helper functions - returning pointer from bpf program - storing pointers into ctx or maps Spill/fill of pointers into stack is allowed, but mangling of pointers stored in the stack or reading them byte by byte is not. Within bpf programs the pointers do exist, since programs need to be able to access maps, pass skb pointer to LD_ABS insns, etc but programs cannot pass such pointer values to the outside or obfuscate them. Only allow BPF_PROG_TYPE_SOCKET_FILTER unprivileged programs, so that socket filters (tcpdump), af_packet (quic acceleration) and future kcm can use it. tracing and tc cls/act program types still require root permissions, since tracing actually needs to be able to see all kernel pointers and tc is for root only. For example, the following unprivileged socket filter program is allowed: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += skb->len; return 0; } but the following program is not: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += (u64) skb; return 0; } since it would leak the kernel address into the map. Unprivileged socket filter bpf programs have access to the following helper functions: - map lookup/update/delete (but they cannot store kernel pointers into them) - get_random (it's already exposed to unprivileged user space) - get_smp_processor_id - tail_call into another socket filter program - ktime_get_ns The feature is controlled by sysctl kernel.unprivileged_bpf_disabled. This toggle defaults to off (0), but can be set true (1). Once true, bpf programs and maps cannot be accessed from unprivileged process, and the toggle cannot be set back to false. Signed-off-by: Alexei Starovoitov Reviewed-by: Kees Cook Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 + kernel/bpf/syscall.c | 11 +++--- kernel/bpf/verifier.c | 106 +++++++++++++++++++++++++++++++++++++++++++++----- kernel/sysctl.c | 13 +++++++ net/core/filter.c | 3 +- 5 files changed, 120 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b4fdee6cb686..02fa3db3c1ec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -167,6 +167,8 @@ void bpf_prog_put_rcu(struct bpf_prog *prog); struct bpf_map *bpf_map_get(struct fd f); void bpf_map_put(struct bpf_map *map); +extern int sysctl_unprivileged_bpf_disabled; + /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); #else diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c868cafbc00c..83697bc8e574 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -18,6 +18,8 @@ #include #include +int sysctl_unprivileged_bpf_disabled __read_mostly; + static LIST_HEAD(bpf_map_types); static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) @@ -544,6 +546,9 @@ static int bpf_prog_load(union bpf_attr *attr) attr->kern_version != LINUX_VERSION_CODE) return -EINVAL; + if (type != BPF_PROG_TYPE_SOCKET_FILTER && !capable(CAP_SYS_ADMIN)) + return -EPERM; + /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); if (!prog) @@ -599,11 +604,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz union bpf_attr attr = {}; int err; - /* the syscall is limited to root temporarily. This restriction will be - * lifted when security audit is clean. Note that eBPF+tracing must have - * this restriction, since it may pass kernel data to user space - */ - if (!capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled) return -EPERM; if (!access_ok(VERIFY_READ, uattr, 1)) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f8da034c2258..1d6b97be79e1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -199,6 +199,7 @@ struct verifier_env { struct verifier_state_list **explored_states; /* search pruning optimization */ struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ u32 used_map_cnt; /* number of used maps */ + bool allow_ptr_leaks; }; /* verbose verifier prints what it's seeing @@ -538,6 +539,21 @@ static int bpf_size_to_bytes(int bpf_size) return -EINVAL; } +static bool is_spillable_regtype(enum bpf_reg_type type) +{ + switch (type) { + case PTR_TO_MAP_VALUE: + case PTR_TO_MAP_VALUE_OR_NULL: + case PTR_TO_STACK: + case PTR_TO_CTX: + case FRAME_PTR: + case CONST_PTR_TO_MAP: + return true; + default: + return false; + } +} + /* check_stack_read/write functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ @@ -550,9 +566,7 @@ static int check_stack_write(struct verifier_state *state, int off, int size, */ if (value_regno >= 0 && - (state->regs[value_regno].type == PTR_TO_MAP_VALUE || - state->regs[value_regno].type == PTR_TO_STACK || - state->regs[value_regno].type == PTR_TO_CTX)) { + is_spillable_regtype(state->regs[value_regno].type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -643,6 +657,20 @@ static int check_ctx_access(struct verifier_env *env, int off, int size, return -EACCES; } +static bool is_pointer_value(struct verifier_env *env, int regno) +{ + if (env->allow_ptr_leaks) + return false; + + switch (env->cur_state.regs[regno].type) { + case UNKNOWN_VALUE: + case CONST_IMM: + return false; + default: + return true; + } +} + /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory @@ -669,11 +697,21 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, } if (state->regs[regno].type == PTR_TO_MAP_VALUE) { + if (t == BPF_WRITE && value_regno >= 0 && + is_pointer_value(env, value_regno)) { + verbose("R%d leaks addr into map\n", value_regno); + return -EACCES; + } err = check_map_access(env, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown_value(state->regs, value_regno); } else if (state->regs[regno].type == PTR_TO_CTX) { + if (t == BPF_WRITE && value_regno >= 0 && + is_pointer_value(env, value_regno)) { + verbose("R%d leaks addr into ctx\n", value_regno); + return -EACCES; + } err = check_ctx_access(env, off, size, t); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown_value(state->regs, value_regno); @@ -684,10 +722,17 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, verbose("invalid stack off=%d size=%d\n", off, size); return -EACCES; } - if (t == BPF_WRITE) + if (t == BPF_WRITE) { + if (!env->allow_ptr_leaks && + state->stack_slot_type[MAX_BPF_STACK + off] == STACK_SPILL && + size != BPF_REG_SIZE) { + verbose("attempt to corrupt spilled pointer on stack\n"); + return -EACCES; + } err = check_stack_write(state, off, size, value_regno); - else + } else { err = check_stack_read(state, off, size, value_regno); + } } else { verbose("R%d invalid mem access '%s'\n", regno, reg_type_str[state->regs[regno].type]); @@ -775,8 +820,13 @@ static int check_func_arg(struct verifier_env *env, u32 regno, return -EACCES; } - if (arg_type == ARG_ANYTHING) + if (arg_type == ARG_ANYTHING) { + if (is_pointer_value(env, regno)) { + verbose("R%d leaks addr into helper function\n", regno); + return -EACCES; + } return 0; + } if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { @@ -950,8 +1000,9 @@ static int check_call(struct verifier_env *env, int func_id) } /* check validity of 32-bit and 64-bit arithmetic operations */ -static int check_alu_op(struct reg_state *regs, struct bpf_insn *insn) +static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn) { + struct reg_state *regs = env->cur_state.regs; u8 opcode = BPF_OP(insn->code); int err; @@ -976,6 +1027,12 @@ static int check_alu_op(struct reg_state *regs, struct bpf_insn *insn) if (err) return err; + if (is_pointer_value(env, insn->dst_reg)) { + verbose("R%d pointer arithmetic prohibited\n", + insn->dst_reg); + return -EACCES; + } + /* check dest operand */ err = check_reg_arg(regs, insn->dst_reg, DST_OP); if (err) @@ -1012,6 +1069,11 @@ static int check_alu_op(struct reg_state *regs, struct bpf_insn *insn) */ regs[insn->dst_reg] = regs[insn->src_reg]; } else { + if (is_pointer_value(env, insn->src_reg)) { + verbose("R%d partial copy of pointer\n", + insn->src_reg); + return -EACCES; + } regs[insn->dst_reg].type = UNKNOWN_VALUE; regs[insn->dst_reg].map_ptr = NULL; } @@ -1061,8 +1123,18 @@ static int check_alu_op(struct reg_state *regs, struct bpf_insn *insn) /* pattern match 'bpf_add Rx, imm' instruction */ if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 && regs[insn->dst_reg].type == FRAME_PTR && - BPF_SRC(insn->code) == BPF_K) + BPF_SRC(insn->code) == BPF_K) { stack_relative = true; + } else if (is_pointer_value(env, insn->dst_reg)) { + verbose("R%d pointer arithmetic prohibited\n", + insn->dst_reg); + return -EACCES; + } else if (BPF_SRC(insn->code) == BPF_X && + is_pointer_value(env, insn->src_reg)) { + verbose("R%d pointer arithmetic prohibited\n", + insn->src_reg); + return -EACCES; + } /* check dest operand */ err = check_reg_arg(regs, insn->dst_reg, DST_OP); @@ -1101,6 +1173,12 @@ static int check_cond_jmp_op(struct verifier_env *env, err = check_reg_arg(regs, insn->src_reg, SRC_OP); if (err) return err; + + if (is_pointer_value(env, insn->src_reg)) { + verbose("R%d pointer comparison prohibited\n", + insn->src_reg); + return -EACCES; + } } else { if (insn->src_reg != BPF_REG_0) { verbose("BPF_JMP uses reserved fields\n"); @@ -1155,6 +1233,9 @@ static int check_cond_jmp_op(struct verifier_env *env, regs[insn->dst_reg].type = CONST_IMM; regs[insn->dst_reg].imm = 0; } + } else if (is_pointer_value(env, insn->dst_reg)) { + verbose("R%d pointer comparison prohibited\n", insn->dst_reg); + return -EACCES; } else if (BPF_SRC(insn->code) == BPF_K && (opcode == BPF_JEQ || opcode == BPF_JNE)) { @@ -1658,7 +1739,7 @@ static int do_check(struct verifier_env *env) } if (class == BPF_ALU || class == BPF_ALU64) { - err = check_alu_op(regs, insn); + err = check_alu_op(env, insn); if (err) return err; @@ -1816,6 +1897,11 @@ static int do_check(struct verifier_env *env) if (err) return err; + if (is_pointer_value(env, BPF_REG_0)) { + verbose("R0 leaks addr as return value\n"); + return -EACCES; + } + process_bpf_exit: insn_idx = pop_stack(env, &prev_insn_idx); if (insn_idx < 0) { @@ -2144,6 +2230,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (ret < 0) goto skip_full_check; + env->allow_ptr_leaks = capable(CAP_SYS_ADMIN); + ret = do_check(env); skip_full_check: diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e69201d8094e..96c856b04081 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -64,6 +64,7 @@ #include #include #include +#include #include #include @@ -1138,6 +1139,18 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = timer_migration_handler, }, +#endif +#ifdef CONFIG_BPF_SYSCALL + { + .procname = "unprivileged_bpf_disabled", + .data = &sysctl_unprivileged_bpf_disabled, + .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), + .mode = 0644, + /* only handle a transition from default "0" to "1" */ + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &one, + }, #endif { } }; diff --git a/net/core/filter.c b/net/core/filter.c index 5f4cf1cffed3..0b00094932ab 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1640,7 +1640,8 @@ sk_filter_func_proto(enum bpf_func_id func_id) case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; case BPF_FUNC_trace_printk: - return bpf_get_trace_printk_proto(); + if (capable(CAP_SYS_ADMIN)) + return bpf_get_trace_printk_proto(); default: return NULL; } -- cgit v1.2.3 From aaac3ba95e4c8b496d22f68bd1bc01cfbf525eca Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 7 Oct 2015 22:23:22 -0700 Subject: bpf: charge user for creation of BPF maps and programs since eBPF programs and maps use kernel memory consider it 'locked' memory from user accounting point of view and charge it against RLIMIT_MEMLOCK limit. This limit is typically set to 64Kbytes by distros, so almost all bpf+tracing programs would need to increase it, since they use maps, but kernel charges maximum map size upfront. For example the hash map of 1024 elements will be charged as 64Kbyte. It's inconvenient for current users and changes current behavior for root, but probably worth doing to be consistent root vs non-root. Similar accounting logic is done by mmap of perf_event. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 3 +++ include/linux/sched.h | 2 +- kernel/bpf/arraymap.c | 2 +- kernel/bpf/hashtab.c | 4 ++++ kernel/bpf/syscall.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 72 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 02fa3db3c1ec..e3a51b74e275 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -36,6 +36,8 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; + u32 pages; + struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; }; @@ -128,6 +130,7 @@ struct bpf_prog_aux { const struct bpf_verifier_ops *ops; struct bpf_map **used_maps; struct bpf_prog *prog; + struct user_struct *user; union { struct work_struct work; struct rcu_head rcu; diff --git a/include/linux/sched.h b/include/linux/sched.h index b7b9501b41af..4817df5fffae 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -840,7 +840,7 @@ struct user_struct { struct hlist_node uidhash_node; kuid_t uid; -#ifdef CONFIG_PERF_EVENTS +#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) atomic_long_t locked_vm; #endif }; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 2fecc4aed119..f2d9e698c753 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -49,7 +49,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array->map.key_size = attr->key_size; array->map.value_size = attr->value_size; array->map.max_entries = attr->max_entries; - + array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT; array->elem_size = elem_size; return &array->map; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 83c209d9b17a..28592d79502b 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -88,6 +88,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->elem_size = sizeof(struct htab_elem) + round_up(htab->map.key_size, 8) + htab->map.value_size; + + htab->map.pages = round_up(htab->n_buckets * sizeof(struct hlist_head) + + htab->elem_size * htab->map.max_entries, + PAGE_SIZE) >> PAGE_SHIFT; return &htab->map; free_htab: diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 83697bc8e574..f640e5f7afbd 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -46,11 +46,38 @@ void bpf_register_map_type(struct bpf_map_type_list *tl) list_add(&tl->list_node, &bpf_map_types); } +static int bpf_map_charge_memlock(struct bpf_map *map) +{ + struct user_struct *user = get_current_user(); + unsigned long memlock_limit; + + memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + + atomic_long_add(map->pages, &user->locked_vm); + + if (atomic_long_read(&user->locked_vm) > memlock_limit) { + atomic_long_sub(map->pages, &user->locked_vm); + free_uid(user); + return -EPERM; + } + map->user = user; + return 0; +} + +static void bpf_map_uncharge_memlock(struct bpf_map *map) +{ + struct user_struct *user = map->user; + + atomic_long_sub(map->pages, &user->locked_vm); + free_uid(user); +} + /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); + bpf_map_uncharge_memlock(map); /* implementation dependent freeing */ map->ops->map_free(map); } @@ -110,6 +137,10 @@ static int map_create(union bpf_attr *attr) atomic_set(&map->refcnt, 1); + err = bpf_map_charge_memlock(map); + if (err) + goto free_map; + err = anon_inode_getfd("bpf-map", &bpf_map_fops, map, O_RDWR | O_CLOEXEC); if (err < 0) @@ -442,11 +473,37 @@ static void free_used_maps(struct bpf_prog_aux *aux) kfree(aux->used_maps); } +static int bpf_prog_charge_memlock(struct bpf_prog *prog) +{ + struct user_struct *user = get_current_user(); + unsigned long memlock_limit; + + memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + + atomic_long_add(prog->pages, &user->locked_vm); + if (atomic_long_read(&user->locked_vm) > memlock_limit) { + atomic_long_sub(prog->pages, &user->locked_vm); + free_uid(user); + return -EPERM; + } + prog->aux->user = user; + return 0; +} + +static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) +{ + struct user_struct *user = prog->aux->user; + + atomic_long_sub(prog->pages, &user->locked_vm); + free_uid(user); +} + static void __prog_put_rcu(struct rcu_head *rcu) { struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); free_used_maps(aux); + bpf_prog_uncharge_memlock(aux->prog); bpf_prog_free(aux->prog); } @@ -554,6 +611,10 @@ static int bpf_prog_load(union bpf_attr *attr) if (!prog) return -ENOMEM; + err = bpf_prog_charge_memlock(prog); + if (err) + goto free_prog_nouncharge; + prog->len = attr->insn_cnt; err = -EFAULT; @@ -595,6 +656,8 @@ static int bpf_prog_load(union bpf_attr *attr) free_used_maps: free_used_maps(prog->aux); free_prog: + bpf_prog_uncharge_memlock(prog); +free_prog_nouncharge: bpf_prog_free(prog); return err; } -- cgit v1.2.3 From f28ea365cdefc3b4fd0373e70b0106a0cd9b4c23 Mon Sep 17 00:00:00 2001 From: Edward Jee Date: Thu, 8 Oct 2015 14:56:48 -0700 Subject: sock: support per-packet fwmark It's useful to allow users to set fwmark for an individual packet, without changing the socket state. The function this patch adds in sock layer can be used by the protocols that need such a feature. Signed-off-by: Edward Hyunkoo Jee Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/sock.h | 7 +++++++ net/core/sock.c | 26 ++++++++++++++++++++++++++ 2 files changed, 33 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 771ca1996442..9322cafd191b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1514,6 +1514,13 @@ void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); +struct sockcm_cookie { + u32 mark; +}; + +int sock_cmsg_send(struct sock *sk, struct msghdr *msg, + struct sockcm_cookie *sockc); + /* * Functions to fill in entries in struct proto_ops when a protocol * does not implement a particular function. diff --git a/net/core/sock.c b/net/core/sock.c index 7dd1263e4c24..33957776cc1a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1852,6 +1852,32 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, } EXPORT_SYMBOL(sock_alloc_send_skb); +int sock_cmsg_send(struct sock *sk, struct msghdr *msg, + struct sockcm_cookie *sockc) +{ + struct cmsghdr *cmsg; + + for_each_cmsghdr(cmsg, msg) { + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + if (cmsg->cmsg_level != SOL_SOCKET) + continue; + switch (cmsg->cmsg_type) { + case SO_MARK: + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; + if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) + return -EINVAL; + sockc->mark = *(u32 *)CMSG_DATA(cmsg); + break; + default: + return -EINVAL; + } + } + return 0; +} +EXPORT_SYMBOL(sock_cmsg_send); + /* On 32bit arches, an skb frag is limited to 2^15 */ #define SKB_FRAG_PAGE_ORDER get_order(32768) -- cgit v1.2.3 From 70da268b569d32a9fddeea85dc18043de9d89f89 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Oct 2015 19:33:21 -0700 Subject: net: SO_INCOMING_CPU setsockopt() support SO_INCOMING_CPU as added in commit 2c8c56e15df3 was a getsockopt() command to fetch incoming cpu handling a particular TCP flow after accept() This commits adds setsockopt() support and extends SO_REUSEPORT selection logic : If a TCP listener or UDP socket has this option set, a packet is delivered to this socket only if CPU handling the packet matches the specified one. This allows to build very efficient TCP servers, using one listener per RX queue, as the associated TCP listener should only accept flows handled in softirq by the same cpu. This provides optimal NUMA behavior and keep cpu caches hot. Note that __inet_lookup_listener() still has to iterate over the list of all listeners. Following patch puts sk_refcnt in a different cache line to let this iteration hit only shared and read mostly cache lines. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 10 ++++------ net/core/sock.c | 5 +++++ net/ipv4/inet_hashtables.c | 2 ++ net/ipv4/udp.c | 6 +++++- net/ipv6/inet6_hashtables.c | 2 ++ net/ipv6/udp.c | 11 +++++++---- 6 files changed, 25 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 9322cafd191b..cf54739f30d5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -150,6 +150,7 @@ typedef __u64 __bitwise __addrpair; * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_incoming_cpu: record/match cpu processing incoming packets * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header @@ -212,6 +213,8 @@ struct sock_common { struct hlist_nulls_node skc_nulls_node; }; int skc_tx_queue_mapping; + int skc_incoming_cpu; + atomic_t skc_refcnt; /* private: */ int skc_dontcopy_end[0]; @@ -274,7 +277,6 @@ struct cg_proto; * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_rxhash: flow hash received from netif layer - * @sk_incoming_cpu: record cpu processing incoming packets * @sk_txhash: computed flow hash for use on transmit * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer @@ -331,6 +333,7 @@ struct sock { #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_cookie __sk_common.skc_cookie +#define sk_incoming_cpu __sk_common.skc_incoming_cpu socket_lock_t sk_lock; struct sk_buff_head sk_receive_queue; @@ -353,11 +356,6 @@ struct sock { #ifdef CONFIG_RPS __u32 sk_rxhash; #endif - u16 sk_incoming_cpu; - /* 16bit hole - * Warned : sk_incoming_cpu can be set from softirq, - * Do not use this hole without fully understanding possible issues. - */ __u32 sk_txhash; #ifdef CONFIG_NET_RX_BUSY_POLL diff --git a/net/core/sock.c b/net/core/sock.c index 33957776cc1a..dcc7d62654d5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -988,6 +988,10 @@ set_rcvbuf: sk->sk_max_pacing_rate); break; + case SO_INCOMING_CPU: + sk->sk_incoming_cpu = val; + break; + default: ret = -ENOPROTOOPT; break; @@ -2379,6 +2383,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_max_pacing_rate = ~0U; sk->sk_pacing_rate = ~0U; + sk->sk_incoming_cpu = -1; /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index bed8886a4b6c..08643a3616af 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -185,6 +185,8 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score += 4; } + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; } return score; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e1fc129099ea..24ec14f9825c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -375,7 +375,8 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score += 4; } - + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; return score; } @@ -419,6 +420,9 @@ static inline int compute_score2(struct sock *sk, struct net *net, score += 4; } + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; + return score; } diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 6ac8dad0138a..21ace5a2bf7c 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -114,6 +114,8 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score++; } + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; } return score; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 0aba654f5b91..01bcb49619ee 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -182,10 +182,12 @@ static inline int compute_score(struct sock *sk, struct net *net, score++; } + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; + return score; } -#define SCORE2_MAX (1 + 1 + 1) static inline int compute_score2(struct sock *sk, struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, @@ -223,6 +225,9 @@ static inline int compute_score2(struct sock *sk, struct net *net, score++; } + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; + return score; } @@ -251,8 +256,7 @@ begin: hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); matches = 1; - } else if (score == SCORE2_MAX) - goto exact_match; + } } else if (score == badness && reuseport) { matches++; if (reciprocal_scale(hash, matches) == 0) @@ -269,7 +273,6 @@ begin: goto begin; if (result) { -exact_match: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score2(result, net, saddr, sport, -- cgit v1.2.3 From 8e5eb54d303b7cb1174977ca79030e135728c95e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Oct 2015 19:33:22 -0700 Subject: net: align sk_refcnt on 128 bytes boundary sk->sk_refcnt is dirtied for every TCP/UDP incoming packet. This is a performance issue if multiple cpus hit a common socket, or multiple sockets are chained due to SO_REUSEPORT. By moving sk_refcnt 8 bytes further, first 128 bytes of sockets are mostly read. As they contain the lookup keys, this has a considerable performance impact, as cpus can cache them. These 8 bytes are not wasted, we use them as a place holder for various fields, depending on the socket type. Tested: SYN flood hitting a 16 RX queues NIC. TCP listener using 16 sockets and SO_REUSEPORT and SO_INCOMING_CPU for proper siloing. Could process 6.0 Mpps SYN instead of 4.2 Mpps Kernel profile looked like : 11.68% [kernel] [k] sha_transform 6.51% [kernel] [k] __inet_lookup_listener 5.07% [kernel] [k] __inet_lookup_established 4.15% [kernel] [k] memcpy_erms 3.46% [kernel] [k] ipt_do_table 2.74% [kernel] [k] fib_table_lookup 2.54% [kernel] [k] tcp_make_synack 2.34% [kernel] [k] tcp_conn_request 2.05% [kernel] [k] __netif_receive_skb_core 2.03% [kernel] [k] kmem_cache_alloc Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 2 +- include/net/request_sock.h | 2 +- include/net/sock.h | 17 ++++++++++++++--- 3 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 186f3a1e1b1f..e581fc69129d 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -70,6 +70,7 @@ struct inet_timewait_sock { #define tw_dport __tw_common.skc_dport #define tw_num __tw_common.skc_num #define tw_cookie __tw_common.skc_cookie +#define tw_dr __tw_common.skc_tw_dr int tw_timeout; volatile unsigned char tw_substate; @@ -88,7 +89,6 @@ struct inet_timewait_sock { kmemcheck_bitfield_end(flags); struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; - struct inet_timewait_death_row *tw_dr; }; #define tw_tclass tw_tos diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 95ab5d7aab96..6b818b77d5e5 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -50,9 +50,9 @@ struct request_sock { struct sock_common __req_common; #define rsk_refcnt __req_common.skc_refcnt #define rsk_hash __req_common.skc_hash +#define rsk_listener __req_common.skc_listener struct request_sock *dl_next; - struct sock *rsk_listener; u16 mss; u8 num_retrans; /* number of retransmits */ u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */ diff --git a/include/net/sock.h b/include/net/sock.h index cf54739f30d5..65712409464b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -150,6 +150,9 @@ typedef __u64 __bitwise __addrpair; * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_flags: place holder for sk_flags + * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, + * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @skc_incoming_cpu: record/match cpu processing incoming packets * @skc_refcnt: reference count * @@ -201,6 +204,16 @@ struct sock_common { atomic64_t skc_cookie; + /* following fields are padding to force + * offset(struct sock, sk_refcnt) == 128 on 64bit arches + * assuming IPV6 is enabled. We use this padding differently + * for different kind of 'sockets' + */ + union { + unsigned long skc_flags; + struct sock *skc_listener; /* request_sock */ + struct inet_timewait_death_row *skc_tw_dr; /* inet_timewait_sock */ + }; /* * fields between dontcopy_begin/dontcopy_end * are not copied in sock_copy() @@ -246,8 +259,6 @@ struct cg_proto; * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes - * @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, - * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) @@ -334,6 +345,7 @@ struct sock { #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_cookie __sk_common.skc_cookie #define sk_incoming_cpu __sk_common.skc_incoming_cpu +#define sk_flags __sk_common.skc_flags socket_lock_t sk_lock; struct sk_buff_head sk_receive_queue; @@ -371,7 +383,6 @@ struct sock { #ifdef CONFIG_XFRM struct xfrm_policy *sk_policy[2]; #endif - unsigned long sk_flags; struct dst_entry *sk_rx_dst; struct dst_entry __rcu *sk_dst_cache; spinlock_t sk_dst_lock; -- cgit v1.2.3 From ed53d0ab761f5c71d77c8dc05fd19c0a851200db Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Oct 2015 19:33:23 -0700 Subject: net: shrink struct sock and request_sock by 8 bytes One 32bit hole is following skc_refcnt, use it. skc_incoming_cpu can also be an union for request_sock rcv_wnd. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 5 ++--- include/net/sock.h | 14 +++++++++----- net/ipv4/syncookies.c | 4 ++-- net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_minisocks.c | 18 +++++++++--------- net/ipv4/tcp_output.c | 2 +- net/ipv6/syncookies.c | 4 ++-- net/ipv6/tcp_ipv6.c | 2 +- 9 files changed, 28 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 6b818b77d5e5..2e73748956d5 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -51,15 +51,14 @@ struct request_sock { #define rsk_refcnt __req_common.skc_refcnt #define rsk_hash __req_common.skc_hash #define rsk_listener __req_common.skc_listener +#define rsk_window_clamp __req_common.skc_window_clamp +#define rsk_rcv_wnd __req_common.skc_rcv_wnd struct request_sock *dl_next; u16 mss; u8 num_retrans; /* number of retransmits */ u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */ u8 num_timeout:7; /* number of timeouts */ - /* The following two fields can be easily recomputed I think -AK */ - u32 window_clamp; /* window clamp at creation time */ - u32 rcv_wnd; /* rcv_wnd offered first time */ u32 ts_recent; struct timer_list rsk_timer; const struct request_sock_ops *rsk_ops; diff --git a/include/net/sock.h b/include/net/sock.h index 65712409464b..19cfe1fc911c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -226,11 +226,18 @@ struct sock_common { struct hlist_nulls_node skc_nulls_node; }; int skc_tx_queue_mapping; - int skc_incoming_cpu; + union { + int skc_incoming_cpu; + u32 skc_rcv_wnd; + }; atomic_t skc_refcnt; /* private: */ int skc_dontcopy_end[0]; + union { + u32 skc_rxhash; + u32 skc_window_clamp; + }; /* public: */ }; @@ -287,7 +294,6 @@ struct cg_proto; * @sk_rcvlowat: %SO_RCVLOWAT setting * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting - * @sk_rxhash: flow hash received from netif layer * @sk_txhash: computed flow hash for use on transmit * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer @@ -346,6 +352,7 @@ struct sock { #define sk_cookie __sk_common.skc_cookie #define sk_incoming_cpu __sk_common.skc_incoming_cpu #define sk_flags __sk_common.skc_flags +#define sk_rxhash __sk_common.skc_rxhash socket_lock_t sk_lock; struct sk_buff_head sk_receive_queue; @@ -365,9 +372,6 @@ struct sock { } sk_backlog; #define sk_rmem_alloc sk_backlog.rmem_alloc int sk_forward_alloc; -#ifdef CONFIG_RPS - __u32 sk_rxhash; -#endif __u32 sk_txhash; #ifdef CONFIG_NET_RX_BUSY_POLL diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 2dbb11331f6c..4c0892badb8b 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -382,10 +382,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) } /* Try to redo what tcp_v4_send_synack did. */ - req->window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); + req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); tcp_select_initial_window(tcp_full_space(sk), req->mss, - &req->rcv_wnd, &req->window_clamp, + &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ddadb318e850..3b35c3f4d268 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6022,7 +6022,7 @@ static void tcp_openreq_init(struct request_sock *req, { struct inet_request_sock *ireq = inet_rsk(req); - req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ + req->rsk_rcv_wnd = 0; /* So that tcp_send_synack() knows! */ req->cookie_ts = 0; tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 34310748a365..ddb198392c7f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -803,7 +803,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, */ tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, - tcp_rsk(req)->rcv_nxt, req->rcv_wnd, + tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, tcp_time_stamp, req->ts_recent, 0, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 1079e6ad77fe..41828bdc5d32 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -381,18 +381,18 @@ void tcp_openreq_init_rwin(struct request_sock *req, window_clamp = READ_ONCE(tp->window_clamp); /* Set this up on the first call only */ - req->window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW); + req->rsk_window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW); /* limit the window selection if the user enforce a smaller rx buffer */ if (sk_listener->sk_userlocks & SOCK_RCVBUF_LOCK && - (req->window_clamp > full_space || req->window_clamp == 0)) - req->window_clamp = full_space; + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; /* tcp_full_space because it is guaranteed to be the first packet */ tcp_select_initial_window(full_space, mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), - &req->rcv_wnd, - &req->window_clamp, + &req->rsk_rcv_wnd, + &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); @@ -512,9 +512,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, if (sysctl_tcp_fack) tcp_enable_fack(newtp); } - newtp->window_clamp = req->window_clamp; - newtp->rcv_ssthresh = req->rcv_wnd; - newtp->rcv_wnd = req->rcv_wnd; + newtp->window_clamp = req->rsk_window_clamp; + newtp->rcv_ssthresh = req->rsk_rcv_wnd; + newtp->rcv_wnd = req->rsk_rcv_wnd; newtp->rx_opt.wscale_ok = ireq->wscale_ok; if (newtp->rx_opt.wscale_ok) { newtp->rx_opt.snd_wscale = ireq->snd_wscale; @@ -707,7 +707,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* RFC793: "first check sequence number". */ if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rcv_wnd)) { + tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rsk_rcv_wnd)) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST)) req->rsk_ops->send_ack(sk, skb, req); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 55ed3266b05f..6e79fcb0addb 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3023,7 +3023,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ - th->window = htons(min(req->rcv_wnd, 65535U)); + th->window = htons(min(req->rsk_rcv_wnd, 65535U)); tcp_options_write((__be32 *)(th + 1), NULL, &opts); th->doff = (tcp_header_size >> 2); TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index f610b5310b17..bb8f2fa1c7fb 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -235,9 +235,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out_free; } - req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); + req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); tcp_select_initial_window(tcp_full_space(sk), req->mss, - &req->rcv_wnd, &req->window_clamp, + &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 33334f0c217d..2887c8474b65 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -931,7 +931,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, - tcp_rsk(req)->rcv_nxt, req->rcv_wnd, + tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); -- cgit v1.2.3 From d475f090bf1c0dc2999e98bbf2e7cb2243358849 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Oct 2015 19:33:24 -0700 Subject: tcp: shrink tcp_timewait_sock by 8 bytes Reducing tcp_timewait_sock from 280 bytes to 272 bytes allows SLAB to pack 15 objects per page instead of 14 (on x86) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ++-- include/net/sock.h | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e442e6e9a365..86a7edaa6797 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -356,8 +356,8 @@ static inline struct tcp_sock *tcp_sk(const struct sock *sk) struct tcp_timewait_sock { struct inet_timewait_sock tw_sk; - u32 tw_rcv_nxt; - u32 tw_snd_nxt; +#define tw_rcv_nxt tw_sk.__tw_common.skc_tw_rcv_nxt +#define tw_snd_nxt tw_sk.__tw_common.skc_tw_snd_nxt u32 tw_rcv_wnd; u32 tw_ts_offset; u32 tw_ts_recent; diff --git a/include/net/sock.h b/include/net/sock.h index 19cfe1fc911c..64a75458d22c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -229,6 +229,7 @@ struct sock_common { union { int skc_incoming_cpu; u32 skc_rcv_wnd; + u32 skc_tw_rcv_nxt; /* struct tcp_timewait_sock */ }; atomic_t skc_refcnt; @@ -237,6 +238,7 @@ struct sock_common { union { u32 skc_rxhash; u32 skc_window_clamp; + u32 skc_tw_snd_nxt; /* struct tcp_timewait_sock */ }; /* public: */ }; -- cgit v1.2.3 From e2ca690b657f4ca5c204fcc6470d462b776d73b3 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 9 Oct 2015 14:34:31 +0200 Subject: ipv4/icmp: redirect messages can use the ingress daddr as source This patch allows configuring how the source address of ICMP redirect messages is selected; by default the old behaviour is retained, while setting icmp_redirects_use_orig_daddr force the usage of the destination address of the packet that caused the redirect. The new behaviour fits closely the RFC 5798 section 8.1.1, and fix the following scenario: Two machines are set up with VRRP to act as routers out of a subnet, they have IPs x.x.x.1/24 and x.x.x.2/24, with VRRP holding on to x.x.x.254/24. If a host in said subnet needs to get an ICMP redirect from the VRRP router, i.e. to reach a destination behind a different gateway, the source IP in the ICMP redirect is chosen as the primary IP on the interface that the packet arrived at, i.e. x.x.x.1 or x.x.x.2. The host will then ignore said redirect, due to RFC 1122 section 3.2.2.2, and will continue to use the wrong next-op. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 19 +++++++++++++++++-- include/net/netns/ipv4.h | 1 + net/ipv4/icmp.c | 9 ++++++++- net/ipv4/sysctl_net_ipv4.c | 7 +++++++ 4 files changed, 33 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index ebe94f2cab98..99838259e2e6 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -884,8 +884,8 @@ icmp_ignore_bogus_error_responses - BOOLEAN icmp_errors_use_inbound_ifaddr - BOOLEAN - If zero, icmp error messages are sent with the primary address of - the exiting interface. + If zero, icmp error messages except redirects are sent with the primary + address of the exiting interface. If non-zero, the message will be sent with the primary address of the interface that received the packet that caused the icmp error. @@ -897,8 +897,23 @@ icmp_errors_use_inbound_ifaddr - BOOLEAN then the primary address of the first non-loopback interface that has one will be used regardless of this setting. + The source address selection of icmp redirect messages is controlled by + icmp_errors_use_inbound_ifaddr. Default: 0 +icmp_redirects_use_orig_daddr - BOOLEAN + + If zero, icmp redirect messages are sent using the address specified for + other icmp errors by icmp_errors_use_inbound_ifaddr. + + If non-zero, the message will be sent with the destination address of + the packet that caused the icmp redirect. + This behaviour is the preferred one on VRRP routers (see RFC 5798 + section 8.1.1). + + Default: 0 + + igmp_max_memberships - INTEGER Change the maximum number of multicast groups we can subscribe to. Default: 20 diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index c68926b4899c..46d336abca92 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -74,6 +74,7 @@ struct netns_ipv4 { int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; int sysctl_icmp_errors_use_inbound_ifaddr; + int sysctl_icmp_redirects_use_orig_daddr; struct local_ports ip_local_ports; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 36e26977c908..f3c356b7c1f0 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -659,7 +659,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) */ saddr = iph->daddr; - if (!(rt->rt_flags & RTCF_LOCAL)) { + if (!((type == ICMP_REDIRECT) && + net->ipv4.sysctl_icmp_redirects_use_orig_daddr) && + !(rt->rt_flags & RTCF_LOCAL)) { struct net_device *dev = NULL; rcu_read_lock(); @@ -1222,6 +1224,11 @@ static int __net_init icmp_sk_init(struct net *net) net->ipv4.sysctl_icmp_ratemask = 0x1818; net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0; + /* Control paramerer - use the daddr of originating packets as saddr + * in redirect messages? + */ + net->ipv4.sysctl_icmp_redirects_use_orig_daddr = 0; + return 0; fail: diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 894da3a70aff..30a531ccbf77 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -817,6 +817,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "icmp_redirects_use_orig_daddr", + .data = &init_net.ipv4.sysctl_icmp_redirects_use_orig_daddr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "icmp_ratelimit", .data = &init_net.ipv4.sysctl_icmp_ratelimit, -- cgit v1.2.3 From 19bcf9f203c82c2028f5a0881b1f0690e3207190 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 9 Oct 2015 13:44:54 -0500 Subject: ipv4: Pass struct net into ip_defrag and ip_check_defrag The function ip_defrag is called on both the input and the output paths of the networking stack. In particular conntrack when it is tracking outbound packets from the local machine calls ip_defrag. So add a struct net parameter and stop making ip_defrag guess which network namespace it needs to defragment packets in. Signed-off-by: "Eric W. Biederman" Acked-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 2 +- include/net/ip.h | 6 +++--- net/ipv4/ip_fragment.c | 7 +++---- net/ipv4/ip_input.c | 7 ++++--- net/ipv4/netfilter/nf_defrag_ipv4.c | 7 ++++--- net/netfilter/ipvs/ip_vs_core.c | 2 +- net/openvswitch/conntrack.c | 2 +- net/packet/af_packet.c | 6 +++--- 8 files changed, 20 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 47da43595ac2..86f6c6292c27 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -412,7 +412,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) port = macvlan_port_get_rcu(skb->dev); if (is_multicast_ether_addr(eth->h_dest)) { - skb = ip_check_defrag(skb, IP_DEFRAG_MACVLAN); + skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN); if (!skb) return RX_HANDLER_CONSUMED; eth = eth_hdr(skb); diff --git a/include/net/ip.h b/include/net/ip.h index 3c904a28d5e5..1a98f1ca1638 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -506,11 +506,11 @@ static inline bool ip_defrag_user_in_between(u32 user, return user >= lower_bond && user <= upper_bond; } -int ip_defrag(struct sk_buff *skb, u32 user); +int ip_defrag(struct net *net, struct sk_buff *skb, u32 user); #ifdef CONFIG_INET -struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user); +struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user); #else -static inline struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) +static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) { return skb; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 9772b789adf3..5482745d5d68 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -654,11 +654,10 @@ out_fail: } /* Process an incoming IP datagram fragment. */ -int ip_defrag(struct sk_buff *skb, u32 user) +int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) { struct net_device *dev = skb->dev ? : skb_dst(skb)->dev; int vif = l3mdev_master_ifindex_rcu(dev); - struct net *net = dev_net(dev); struct ipq *qp; IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); @@ -683,7 +682,7 @@ int ip_defrag(struct sk_buff *skb, u32 user) } EXPORT_SYMBOL(ip_defrag); -struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) +struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) { struct iphdr iph; int netoff; @@ -712,7 +711,7 @@ struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) if (pskb_trim_rcsum(skb, netoff + len)) return skb; memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - if (ip_defrag(skb, user)) + if (ip_defrag(net, skb, user)) return NULL; skb_clear_hash(skb); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 804b86fd615f..b1209b63381f 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -170,7 +170,7 @@ bool ip_call_ra_chain(struct sk_buff *skb) sk->sk_bound_dev_if == dev->ifindex) && net_eq(sock_net(sk), net)) { if (ip_is_fragment(ip_hdr(skb))) { - if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) + if (ip_defrag(net, skb, IP_DEFRAG_CALL_RA_CHAIN)) return true; } if (last) { @@ -247,14 +247,15 @@ int ip_local_deliver(struct sk_buff *skb) /* * Reassemble IP fragments. */ + struct net *net = dev_net(skb->dev); if (ip_is_fragment(ip_hdr(skb))) { - if (ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER)) + if (ip_defrag(net, skb, IP_DEFRAG_LOCAL_DELIVER)) return 0; } return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, - dev_net(skb->dev), NULL, skb, skb->dev, NULL, + net, NULL, skb, skb->dev, NULL, ip_local_deliver_finish); } diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index b246346ee849..bf25f45b23d2 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -22,14 +22,15 @@ #endif #include -static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) +static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb, + u_int32_t user) { int err; skb_orphan(skb); local_bh_disable(); - err = ip_defrag(skb, user); + err = ip_defrag(net, skb, user); local_bh_enable(); if (!err) { @@ -85,7 +86,7 @@ static unsigned int ipv4_conntrack_defrag(void *priv, enum ip_defrag_users user = nf_ct_defrag_user(state->hook, skb); - if (nf_ct_ipv4_gather_frags(skb, user)) + if (nf_ct_ipv4_gather_frags(state->net, skb, user)) return NF_STOLEN; } return NF_ACCEPT; diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 37dd77a3d0fb..07a791ecdfba 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -694,7 +694,7 @@ static inline int ip_vs_gather_frags(struct netns_ipvs *ipvs, int err; local_bh_disable(); - err = ip_defrag(skb, user); + err = ip_defrag(ipvs->net, skb, user); local_bh_enable(); if (!err) ip_send_check(ip_hdr(skb)); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index eb759e3a88ca..cb76076a7a42 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -304,7 +304,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, int err; memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - err = ip_defrag(skb, user); + err = ip_defrag(net, skb, user); if (err) return err; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 396b3f1e7cc0..691660b9b7ef 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1439,17 +1439,17 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, { struct packet_fanout *f = pt->af_packet_priv; unsigned int num = READ_ONCE(f->num_members); + struct net *net = read_pnet(&f->net); struct packet_sock *po; unsigned int idx; - if (!net_eq(dev_net(dev), read_pnet(&f->net)) || - !num) { + if (!net_eq(dev_net(dev), net) || !num) { kfree_skb(skb); return 0; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) { - skb = ip_check_defrag(skb, IP_DEFRAG_AF_PACKET); + skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET); if (!skb) return 0; } -- cgit v1.2.3 From b72775977c39dcd380777ff5ea8041fdf67ee382 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 9 Oct 2015 13:44:55 -0500 Subject: ipv6: Pass struct net into nf_ct_frag6_gather The function nf_ct_frag6_gather is called on both the input and the output paths of the networking stack. In particular ipv6_defrag which calls nf_ct_frag6_gather is called from both the the PRE_ROUTING chain on input and the LOCAL_OUT chain on output. The addition of a net parameter makes it explicit which network namespace the packets are being reassembled in, and removes the need for nf_ct_frag6_gather to guess. Signed-off-by: "Eric W. Biederman" Acked-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/netfilter/ipv6/nf_defrag_ipv6.h | 2 +- net/ipv6/netfilter/nf_conntrack_reasm.c | 4 +--- net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 3 ++- net/openvswitch/conntrack.c | 2 +- 4 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h index 27666d8a0bd0..fb7da5bb76cc 100644 --- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -5,7 +5,7 @@ void nf_defrag_ipv6_enable(void); int nf_ct_frag6_init(void); void nf_ct_frag6_cleanup(void); -struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user); +struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user); void nf_ct_frag6_consume_orig(struct sk_buff *skb); struct inet_frags_ctl; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 701cd2bae0a9..2fb86a99bf5f 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -563,12 +563,10 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) return 0; } -struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) +struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { struct sk_buff *clone; struct net_device *dev = skb->dev; - struct net *net = skb_dst(skb) ? dev_net(skb_dst(skb)->dev) - : dev_net(skb->dev); struct frag_hdr *fhdr; struct frag_queue *fq; struct ipv6hdr *hdr; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index a99baf63eccf..5173a89a238e 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -63,7 +63,8 @@ static unsigned int ipv6_defrag(void *priv, return NF_ACCEPT; #endif - reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(state->hook, skb)); + reasm = nf_ct_frag6_gather(state->net, skb, + nf_ct6_defrag_user(state->hook, skb)); /* queued */ if (reasm == NULL) return NF_STOLEN; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index cb76076a7a42..ad614267cc2a 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -315,7 +315,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, struct sk_buff *reasm; memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); - reasm = nf_ct_frag6_gather(skb, user); + reasm = nf_ct_frag6_gather(net, skb, user); if (!reasm) return -EINPROGRESS; -- cgit v1.2.3 From 93f0490e5deb9445737cabf0e436f3288a4042b7 Mon Sep 17 00:00:00 2001 From: Tamizh chelvam Date: Wed, 7 Oct 2015 10:40:04 +0530 Subject: Revert "mac80211: remove exposing 'mfp' to drivers" This reverts commit 5c48f1201744233d4f235c7dd916d5196ed20716. Some device drivers (ath10k) offload part of aggregation including AddBA/DelBA negotiations to firmware. In such scenario, the PMF configuration of the station needs to be provided to driver to enable encryption of AddBA/DelBA action frames. Signed-off-by: Tamizh chelvam Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 ++ net/mac80211/cfg.c | 1 + net/mac80211/mlme.c | 6 +++++- 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 4ec6fedeb220..1bb2a2b4e187 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1683,6 +1683,7 @@ struct ieee80211_sta_rates { * @tdls: indicates whether the STA is a TDLS peer * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only * valid if the STA is a TDLS peer in the first place. + * @mfp: indicates whether the STA uses management frame protection or not. * @txq: per-TID data TX queues (if driver uses the TXQ abstraction) */ struct ieee80211_sta { @@ -1700,6 +1701,7 @@ struct ieee80211_sta { struct ieee80211_sta_rates __rcu *rates; bool tdls; bool tdls_initiator; + bool mfp; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS]; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 68e551e263c6..63d03dad654c 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1138,6 +1138,7 @@ static int sta_apply_parameters(struct ieee80211_local *local, } if (mask & BIT(NL80211_STA_FLAG_MFP)) { + sta->sta.mfp = !!(set & BIT(NL80211_STA_FLAG_MFP)); if (set & BIT(NL80211_STA_FLAG_MFP)) set_sta_flag(sta, WLAN_STA_MFP); else diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 56ef9a8e151c..9c450ffdabe8 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3044,8 +3044,12 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, rate_control_rate_init(sta); - if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED) + if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED) { set_sta_flag(sta, WLAN_STA_MFP); + sta->sta.mfp = true; + } else { + sta->sta.mfp = false; + } sta->sta.wme = elems.wmm_param && local->hw.queues >= IEEE80211_NUM_ACS; -- cgit v1.2.3 From 6e19bc4b7091ffd26586100eee78232b44427ec7 Mon Sep 17 00:00:00 2001 From: Dmitry Shmidt Date: Wed, 7 Oct 2015 11:32:53 +0200 Subject: nl80211: allow BSS data to include CLOCK_BOOTTIME timestamp For location and connectivity services, userspace would often like to know the time when the BSS was last seen. The current "last seen" value is calculated in a way that makes it less useful, especially if the system suspended in the meantime. Add the ability for the driver to report a real CLOCK_BOOTTIME stamp that can then be reported to userspace (if present). Drivers wishing to use this must be converted to the new API to call cfg80211_inform_bss_data() or cfg80211_inform_bss_frame_data(). They need to ensure the reported value is accurate enough even when the frame might have been buffered in the device (e.g. firmware.) Signed-off-by: Dmitry Shmidt [modified to use struct, inlines] Signed-off-by: Johannes Berg --- Documentation/DocBook/80211.tmpl | 5 ++- include/net/cfg80211.h | 95 ++++++++++++++++++++++++++++++++-------- include/uapi/linux/nl80211.h | 4 ++ net/wireless/core.h | 1 + net/wireless/nl80211.c | 5 +++ net/wireless/scan.c | 58 ++++++++++++------------ net/wireless/trace.h | 22 +++++----- 7 files changed, 130 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl index aac9357d4866..f9b9ad7894f5 100644 --- a/Documentation/DocBook/80211.tmpl +++ b/Documentation/DocBook/80211.tmpl @@ -154,8 +154,9 @@ !Finclude/net/cfg80211.h cfg80211_scan_request !Finclude/net/cfg80211.h cfg80211_scan_done !Finclude/net/cfg80211.h cfg80211_bss -!Finclude/net/cfg80211.h cfg80211_inform_bss_width_frame -!Finclude/net/cfg80211.h cfg80211_inform_bss_width +!Finclude/net/cfg80211.h cfg80211_inform_bss +!Finclude/net/cfg80211.h cfg80211_inform_bss_frame_data +!Finclude/net/cfg80211.h cfg80211_inform_bss_data !Finclude/net/cfg80211.h cfg80211_unlink_bss !Finclude/net/cfg80211.h cfg80211_find_ie !Finclude/net/cfg80211.h ieee80211_bss_get_ie diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 90332a1838cc..7f1e9ee844e2 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1575,6 +1575,26 @@ enum cfg80211_signal_type { CFG80211_SIGNAL_TYPE_UNSPEC, }; +/** + * struct cfg80211_inform_bss - BSS inform data + * @chan: channel the frame was received on + * @scan_width: scan width that was used + * @signal: signal strength value, according to the wiphy's + * signal type + * @boottime_ns: timestamp (CLOCK_BOOTTIME) when the information was + * received; should match the time when the frame was actually + * received by the device (not just by the host, in case it was + * buffered on the device) and be accurate to about 10ms. + * If the frame isn't buffered, just passing the return value of + * ktime_get_boot_ns() is likely appropriate. + */ +struct cfg80211_inform_bss { + struct ieee80211_channel *chan; + enum nl80211_bss_scan_width scan_width; + s32 signal; + u64 boottime_ns; +}; + /** * struct cfg80211_bss_ie_data - BSS entry IE data * @tsf: TSF contained in the frame that carried these IEs @@ -3958,14 +3978,11 @@ void cfg80211_sched_scan_stopped(struct wiphy *wiphy); void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy); /** - * cfg80211_inform_bss_width_frame - inform cfg80211 of a received BSS frame - * + * cfg80211_inform_bss_frame_data - inform cfg80211 of a received BSS frame * @wiphy: the wiphy reporting the BSS - * @rx_channel: The channel the frame was received on - * @scan_width: width of the control channel + * @data: the BSS metadata * @mgmt: the management frame (probe response or beacon) * @len: length of the management frame - * @signal: the signal strength, type depends on the wiphy's signal_type * @gfp: context flags * * This informs cfg80211 that BSS information was found and @@ -3975,11 +3992,26 @@ void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy); * Or %NULL on error. */ struct cfg80211_bss * __must_check +cfg80211_inform_bss_frame_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + struct ieee80211_mgmt *mgmt, size_t len, + gfp_t gfp); + +static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_width_frame(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, enum nl80211_bss_scan_width scan_width, struct ieee80211_mgmt *mgmt, size_t len, - s32 signal, gfp_t gfp); + s32 signal, gfp_t gfp) +{ + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = scan_width, + .signal = signal, + }; + + return cfg80211_inform_bss_frame_data(wiphy, &data, mgmt, len, gfp); +} static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_frame(struct wiphy *wiphy, @@ -3987,9 +4019,13 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy, struct ieee80211_mgmt *mgmt, size_t len, s32 signal, gfp_t gfp) { - return cfg80211_inform_bss_width_frame(wiphy, rx_channel, - NL80211_BSS_CHAN_WIDTH_20, - mgmt, len, signal, gfp); + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = NL80211_BSS_CHAN_WIDTH_20, + .signal = signal, + }; + + return cfg80211_inform_bss_frame_data(wiphy, &data, mgmt, len, gfp); } /** @@ -4006,11 +4042,10 @@ enum cfg80211_bss_frame_type { }; /** - * cfg80211_inform_bss_width - inform cfg80211 of a new BSS + * cfg80211_inform_bss_data - inform cfg80211 of a new BSS * * @wiphy: the wiphy reporting the BSS - * @rx_channel: The channel the frame was received on - * @scan_width: width of the control channel + * @data: the BSS metadata * @ftype: frame type (if known) * @bssid: the BSSID of the BSS * @tsf: the TSF sent by the peer in the beacon/probe response (or 0) @@ -4018,7 +4053,6 @@ enum cfg80211_bss_frame_type { * @beacon_interval: the beacon interval announced by the peer * @ie: additional IEs sent by the peer * @ielen: length of the additional IEs - * @signal: the signal strength, type depends on the wiphy's signal_type * @gfp: context flags * * This informs cfg80211 that BSS information was found and @@ -4028,13 +4062,32 @@ enum cfg80211_bss_frame_type { * Or %NULL on error. */ struct cfg80211_bss * __must_check +cfg80211_inform_bss_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + enum cfg80211_bss_frame_type ftype, + const u8 *bssid, u64 tsf, u16 capability, + u16 beacon_interval, const u8 *ie, size_t ielen, + gfp_t gfp); + +static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_width(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, enum nl80211_bss_scan_width scan_width, enum cfg80211_bss_frame_type ftype, const u8 *bssid, u64 tsf, u16 capability, u16 beacon_interval, const u8 *ie, size_t ielen, - s32 signal, gfp_t gfp); + s32 signal, gfp_t gfp) +{ + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = scan_width, + .signal = signal, + }; + + return cfg80211_inform_bss_data(wiphy, &data, ftype, bssid, tsf, + capability, beacon_interval, ie, ielen, + gfp); +} static inline struct cfg80211_bss * __must_check cfg80211_inform_bss(struct wiphy *wiphy, @@ -4044,11 +4097,15 @@ cfg80211_inform_bss(struct wiphy *wiphy, u16 beacon_interval, const u8 *ie, size_t ielen, s32 signal, gfp_t gfp) { - return cfg80211_inform_bss_width(wiphy, rx_channel, - NL80211_BSS_CHAN_WIDTH_20, ftype, - bssid, tsf, capability, - beacon_interval, ie, ielen, signal, - gfp); + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = NL80211_BSS_CHAN_WIDTH_20, + .signal = signal, + }; + + return cfg80211_inform_bss_data(wiphy, &data, ftype, bssid, tsf, + capability, beacon_interval, ie, ielen, + gfp); } struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c0ab6b0a3919..5dadb844fe18 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3364,6 +3364,9 @@ enum nl80211_bss_scan_width { * (not present if no beacon frame has been received yet) * @NL80211_BSS_PRESP_DATA: the data in @NL80211_BSS_INFORMATION_ELEMENTS and * @NL80211_BSS_TSF is known to be from a probe response (flag attribute) + * @NL80211_BSS_LAST_SEEN_BOOTTIME: CLOCK_BOOTTIME timestamp when this entry + * was last updated by a received frame. The value is expected to be + * accurate to about 10ms. (u64, nanoseconds) * @__NL80211_BSS_AFTER_LAST: internal * @NL80211_BSS_MAX: highest BSS attribute */ @@ -3383,6 +3386,7 @@ enum nl80211_bss { NL80211_BSS_CHAN_WIDTH, NL80211_BSS_BEACON_TSF, NL80211_BSS_PRESP_DATA, + NL80211_BSS_LAST_SEEN_BOOTTIME, /* keep last */ __NL80211_BSS_AFTER_LAST, diff --git a/net/wireless/core.h b/net/wireless/core.h index b9d5bc8c148d..a618b4b86fa4 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -137,6 +137,7 @@ struct cfg80211_internal_bss { struct list_head list; struct list_head hidden_list; struct rb_node rbn; + u64 ts_boottime; unsigned long ts; unsigned long refcount; atomic_t hold; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f05ba8b7af61..fb0712b3d9cb 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6605,6 +6605,11 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, jiffies_to_msecs(jiffies - intbss->ts))) goto nla_put_failure; + if (intbss->ts_boottime && + nla_put_u64(msg, NL80211_BSS_LAST_SEEN_BOOTTIME, + intbss->ts_boottime)) + goto nla_put_failure; + switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: if (nla_put_u32(msg, NL80211_BSS_SIGNAL_MBM, res->signal)) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 3a50aa2553bf..3feaa03aa046 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -839,6 +839,7 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, found->pub.signal = tmp->pub.signal; found->pub.capability = tmp->pub.capability; found->ts = tmp->ts; + found->ts_boottime = tmp->ts_boottime; } else { struct cfg80211_internal_bss *new; struct cfg80211_internal_bss *hidden; @@ -938,14 +939,13 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, } /* Returned bss is reference counted and must be cleaned up appropriately. */ -struct cfg80211_bss* -cfg80211_inform_bss_width(struct wiphy *wiphy, - struct ieee80211_channel *rx_channel, - enum nl80211_bss_scan_width scan_width, - enum cfg80211_bss_frame_type ftype, - const u8 *bssid, u64 tsf, u16 capability, - u16 beacon_interval, const u8 *ie, size_t ielen, - s32 signal, gfp_t gfp) +struct cfg80211_bss * +cfg80211_inform_bss_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + enum cfg80211_bss_frame_type ftype, + const u8 *bssid, u64 tsf, u16 capability, + u16 beacon_interval, const u8 *ie, size_t ielen, + gfp_t gfp) { struct cfg80211_bss_ies *ies; struct ieee80211_channel *channel; @@ -957,19 +957,21 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, return NULL; if (WARN_ON(wiphy->signal_type == CFG80211_SIGNAL_TYPE_UNSPEC && - (signal < 0 || signal > 100))) + (data->signal < 0 || data->signal > 100))) return NULL; - channel = cfg80211_get_bss_channel(wiphy, ie, ielen, rx_channel); + channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan); if (!channel) return NULL; memcpy(tmp.pub.bssid, bssid, ETH_ALEN); tmp.pub.channel = channel; - tmp.pub.scan_width = scan_width; - tmp.pub.signal = signal; + tmp.pub.scan_width = data->scan_width; + tmp.pub.signal = data->signal; tmp.pub.beacon_interval = beacon_interval; tmp.pub.capability = capability; + tmp.ts_boottime = data->boottime_ns; + /* * If we do not know here whether the IEs are from a Beacon or Probe * Response frame, we need to pick one of the options and only use it @@ -999,7 +1001,7 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, } rcu_assign_pointer(tmp.pub.ies, ies); - signal_valid = abs(rx_channel->center_freq - channel->center_freq) <= + signal_valid = abs(data->chan->center_freq - channel->center_freq) <= wiphy->max_adj_channel_rssi_comp; res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid); if (!res) @@ -1019,15 +1021,15 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, /* cfg80211_bss_update gives us a referenced result */ return &res->pub; } -EXPORT_SYMBOL(cfg80211_inform_bss_width); +EXPORT_SYMBOL(cfg80211_inform_bss_data); -/* Returned bss is reference counted and must be cleaned up appropriately. */ +/* cfg80211_inform_bss_width_frame helper */ struct cfg80211_bss * -cfg80211_inform_bss_width_frame(struct wiphy *wiphy, - struct ieee80211_channel *rx_channel, - enum nl80211_bss_scan_width scan_width, - struct ieee80211_mgmt *mgmt, size_t len, - s32 signal, gfp_t gfp) +cfg80211_inform_bss_frame_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + struct ieee80211_mgmt *mgmt, size_t len, + gfp_t gfp) + { struct cfg80211_internal_bss tmp = {}, *res; struct cfg80211_bss_ies *ies; @@ -1040,8 +1042,7 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) != offsetof(struct ieee80211_mgmt, u.beacon.variable)); - trace_cfg80211_inform_bss_width_frame(wiphy, rx_channel, scan_width, mgmt, - len, signal); + trace_cfg80211_inform_bss_frame(wiphy, data, mgmt, len); if (WARN_ON(!mgmt)) return NULL; @@ -1050,14 +1051,14 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, return NULL; if (WARN_ON(wiphy->signal_type == CFG80211_SIGNAL_TYPE_UNSPEC && - (signal < 0 || signal > 100))) + (data->signal < 0 || data->signal > 100))) return NULL; if (WARN_ON(len < offsetof(struct ieee80211_mgmt, u.probe_resp.variable))) return NULL; channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable, - ielen, rx_channel); + ielen, data->chan); if (!channel) return NULL; @@ -1077,12 +1078,13 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, memcpy(tmp.pub.bssid, mgmt->bssid, ETH_ALEN); tmp.pub.channel = channel; - tmp.pub.scan_width = scan_width; - tmp.pub.signal = signal; + tmp.pub.scan_width = data->scan_width; + tmp.pub.signal = data->signal; tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int); tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info); + tmp.ts_boottime = data->boottime_ns; - signal_valid = abs(rx_channel->center_freq - channel->center_freq) <= + signal_valid = abs(data->chan->center_freq - channel->center_freq) <= wiphy->max_adj_channel_rssi_comp; res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid); if (!res) @@ -1102,7 +1104,7 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, /* cfg80211_bss_update gives us a referenced result */ return &res->pub; } -EXPORT_SYMBOL(cfg80211_inform_bss_width_frame); +EXPORT_SYMBOL(cfg80211_inform_bss_frame_data); void cfg80211_ref_bss(struct wiphy *wiphy, struct cfg80211_bss *pub) { diff --git a/net/wireless/trace.h b/net/wireless/trace.h index a808279a432a..0c392d36781b 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2670,30 +2670,30 @@ TRACE_EVENT(cfg80211_get_bss, __entry->privacy) ); -TRACE_EVENT(cfg80211_inform_bss_width_frame, - TP_PROTO(struct wiphy *wiphy, struct ieee80211_channel *channel, - enum nl80211_bss_scan_width scan_width, - struct ieee80211_mgmt *mgmt, size_t len, - s32 signal), - TP_ARGS(wiphy, channel, scan_width, mgmt, len, signal), +TRACE_EVENT(cfg80211_inform_bss_frame, + TP_PROTO(struct wiphy *wiphy, struct cfg80211_inform_bss *data, + struct ieee80211_mgmt *mgmt, size_t len), + TP_ARGS(wiphy, data, mgmt, len), TP_STRUCT__entry( WIPHY_ENTRY CHAN_ENTRY __field(enum nl80211_bss_scan_width, scan_width) __dynamic_array(u8, mgmt, len) __field(s32, signal) + __field(u64, ts_boottime) ), TP_fast_assign( WIPHY_ASSIGN; - CHAN_ASSIGN(channel); - __entry->scan_width = scan_width; + CHAN_ASSIGN(data->chan); + __entry->scan_width = data->scan_width; if (mgmt) memcpy(__get_dynamic_array(mgmt), mgmt, len); - __entry->signal = signal; + __entry->signal = data->signal; + __entry->ts_boottime = data->boottime_ns; ), - TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT "(scan_width: %d) signal: %d", + TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT "(scan_width: %d) signal: %d, tsb:%llu", WIPHY_PR_ARG, CHAN_PR_ARG, __entry->scan_width, - __entry->signal) + __entry->signal, (unsigned long long)__entry->ts_boottime) ); DECLARE_EVENT_CLASS(cfg80211_bss_evt, -- cgit v1.2.3 From a4288289f585d42a19145f266e214acb165fe9b3 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 7 Oct 2015 15:48:25 +0200 Subject: wireless: update robust action frame list Unprotected DMG and VHT action frames are not protected, reflect that in the list. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index dcfb2f43d316..0109f3847e9a 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2397,6 +2397,8 @@ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) return *category != WLAN_CATEGORY_PUBLIC && *category != WLAN_CATEGORY_HT && *category != WLAN_CATEGORY_SELF_PROTECTED && + *category != WLAN_CATEGORY_UNPROT_DMG && + *category != WLAN_CATEGORY_VHT && *category != WLAN_CATEGORY_VENDOR_SPECIFIC; } -- cgit v1.2.3 From af61426187cd854bffe013ca8547bd8fa3c4dfbf Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 7 Oct 2015 15:48:26 +0200 Subject: wireless: add WNM action frame categories Add the WNM and unprotected WNM categories and mark the latter as not robust. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 0109f3847e9a..452c0b0d2f32 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1932,6 +1932,8 @@ enum ieee80211_category { WLAN_CATEGORY_HT = 7, WLAN_CATEGORY_SA_QUERY = 8, WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION = 9, + WLAN_CATEGORY_WNM = 10, + WLAN_CATEGORY_WNM_UNPROTECTED = 11, WLAN_CATEGORY_TDLS = 12, WLAN_CATEGORY_MESH_ACTION = 13, WLAN_CATEGORY_MULTIHOP_ACTION = 14, @@ -2396,6 +2398,7 @@ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) category = ((u8 *) hdr) + 24; return *category != WLAN_CATEGORY_PUBLIC && *category != WLAN_CATEGORY_HT && + *category != WLAN_CATEGORY_WNM_UNPROTECTED && *category != WLAN_CATEGORY_SELF_PROTECTED && *category != WLAN_CATEGORY_UNPROT_DMG && *category != WLAN_CATEGORY_VHT && -- cgit v1.2.3 From 3b06d277957c7af705a9c0cdda4b371759efb717 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Mon, 12 Oct 2015 09:51:34 +0300 Subject: cfg80211: Add multiple scan plans for scheduled scan Add the option to configure multiple 'scan plans' for scheduled scan. Each 'scan plan' defines the number of scan cycles and the interval between scans. The scan plans are executed in the order they were configured. The last scan plan will always run infinitely and thus defines only the interval between scans. The maximum number of scan plans supported by the device and the maximum number of iterations in a single scan plan are advertised to userspace so it can configure the scan plans appropriately. When scheduled scan results are received there is no way to know which scan plan is being currently executed, so there is no way to know when the next scan iteration will start. This is not a problem, however. The scan start timestamp is only used for flushing old scan results, and there is no difference between flushing all results received until the end of the previous iteration or the start of the current one, since no results will be received in between. Signed-off-by: Avraham Stern Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/ath/ath6kl/cfg80211.c | 2 +- drivers/net/wireless/iwlwifi/mvm/ops.c | 1 + drivers/net/wireless/iwlwifi/mvm/scan.c | 4 +- drivers/net/wireless/ti/wl12xx/scan.c | 3 +- drivers/net/wireless/ti/wl18xx/scan.c | 8 +- include/net/cfg80211.h | 31 ++++- include/uapi/linux/nl80211.h | 53 ++++++++- net/wireless/core.c | 3 + net/wireless/nl80211.c | 179 ++++++++++++++++++++++++++--- net/wireless/scan.c | 3 +- 10 files changed, 262 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c index a511ef3614b9..3fda750db2a9 100644 --- a/drivers/net/wireless/ath/ath6kl/cfg80211.c +++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c @@ -3312,7 +3312,7 @@ static int ath6kl_cfg80211_sscan_start(struct wiphy *wiphy, } /* fw uses seconds, also make sure that it's >0 */ - interval = max_t(u16, 1, request->interval / 1000); + interval = max_t(u16, 1, request->scan_plans[0].interval); ath6kl_wmi_scanparams_cmd(ar->wmi, vif->fw_vif_idx, interval, interval, diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c index 064c100e45fe..f0728b784edb 100644 --- a/drivers/net/wireless/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/iwlwifi/mvm/ops.c @@ -629,6 +629,7 @@ static void iwl_op_mode_mvm_stop(struct iwl_op_mode *op_mode) kfree(mvm->d3_resume_sram); if (mvm->nd_config) { kfree(mvm->nd_config->match_sets); + kfree(mvm->nd_config->scan_plans); kfree(mvm->nd_config); mvm->nd_config = NULL; } diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c index 4a1f9af63bf0..cee4f267ca66 100644 --- a/drivers/net/wireless/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/iwlwifi/mvm/scan.c @@ -1271,12 +1271,12 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm, params.type = iwl_mvm_get_scan_type(mvm, vif, ¶ms); - if (req->interval > U16_MAX) { + if (req->scan_plans[0].interval > U16_MAX) { IWL_DEBUG_SCAN(mvm, "interval value is > 16-bits, set to max possible\n"); params.interval = U16_MAX; } else { - params.interval = req->interval / MSEC_PER_SEC; + params.interval = req->scan_plans[0].interval; } /* In theory, LMAC scans can handle a 32-bit delay, but since diff --git a/drivers/net/wireless/ti/wl12xx/scan.c b/drivers/net/wireless/ti/wl12xx/scan.c index 7c355fff2c5e..ebed13af9852 100644 --- a/drivers/net/wireless/ti/wl12xx/scan.c +++ b/drivers/net/wireless/ti/wl12xx/scan.c @@ -350,7 +350,8 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl, cfg->bss_type = SCAN_BSS_TYPE_ANY; /* currently NL80211 supports only a single interval */ for (i = 0; i < SCAN_MAX_CYCLE_INTERVALS; i++) - cfg->intervals[i] = cpu_to_le32(req->interval); + cfg->intervals[i] = cpu_to_le32(req->scan_plans[0].interval * + MSEC_PER_SEC); cfg->ssid_len = 0; ret = wlcore_scan_sched_scan_ssid_list(wl, wlvif, req); diff --git a/drivers/net/wireless/ti/wl18xx/scan.c b/drivers/net/wireless/ti/wl18xx/scan.c index c938c494c785..bc15aa2c3efa 100644 --- a/drivers/net/wireless/ti/wl18xx/scan.c +++ b/drivers/net/wireless/ti/wl18xx/scan.c @@ -228,13 +228,15 @@ int wl18xx_scan_sched_scan_config(struct wl1271 *wl, wl18xx_adjust_channels(cmd, cmd_channels); if (c->num_short_intervals && c->long_interval && - c->long_interval > req->interval) { - cmd->short_cycles_msec = cpu_to_le16(req->interval); + c->long_interval > req->scan_plans[0].interval * MSEC_PER_SEC) { + cmd->short_cycles_msec = + cpu_to_le16(req->scan_plans[0].interval * MSEC_PER_SEC); cmd->long_cycles_msec = cpu_to_le16(c->long_interval); cmd->short_cycles_count = c->num_short_intervals; } else { cmd->short_cycles_msec = 0; - cmd->long_cycles_msec = cpu_to_le16(req->interval); + cmd->long_cycles_msec = + cpu_to_le16(req->scan_plans[0].interval * MSEC_PER_SEC); cmd->short_cycles_count = 0; } wl1271_debug(DEBUG_SCAN, "short_interval: %d, long_interval: %d, num_short: %d", diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7f1e9ee844e2..48155be5db7f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5,6 +5,7 @@ * * Copyright 2006-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright 2015 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1500,6 +1501,20 @@ struct cfg80211_match_set { s32 rssi_thold; }; +/** + * struct cfg80211_sched_scan_plan - scan plan for scheduled scan + * + * @interval: interval between scheduled scan iterations. In seconds. + * @iterations: number of scan iterations in this scan plan. Zero means + * infinite loop. + * The last scan plan will always have this parameter set to zero, + * all other scan plans will have a finite number of iterations. + */ +struct cfg80211_sched_scan_plan { + u32 interval; + u32 iterations; +}; + /** * struct cfg80211_sched_scan_request - scheduled scan request description * @@ -1507,7 +1522,6 @@ struct cfg80211_match_set { * @n_ssids: number of SSIDs * @n_channels: total number of channels to scan * @scan_width: channel width for scanning - * @interval: interval between each scheduled scan cycle * @ie: optional information element(s) to add into Probe Request or %NULL * @ie_len: length of ie in octets * @flags: bit field of flags controlling operation @@ -1526,6 +1540,9 @@ struct cfg80211_match_set { * @mac_addr_mask: MAC address mask used with randomisation, bits that * are 0 in the mask should be randomised, bits that are 1 should * be taken from the @mac_addr + * @scan_plans: scan plans to be executed in this scheduled scan. Lowest + * index must be executed first. + * @n_scan_plans: number of scan plans, at least 1. * @rcu_head: RCU callback used to free the struct * @owner_nlportid: netlink portid of owner (if this should is a request * owned by a particular socket) @@ -1539,7 +1556,6 @@ struct cfg80211_sched_scan_request { int n_ssids; u32 n_channels; enum nl80211_bss_scan_width scan_width; - u32 interval; const u8 *ie; size_t ie_len; u32 flags; @@ -1547,6 +1563,8 @@ struct cfg80211_sched_scan_request { int n_match_sets; s32 min_rssi_thold; u32 delay; + struct cfg80211_sched_scan_plan *scan_plans; + int n_scan_plans; u8 mac_addr[ETH_ALEN] __aligned(2); u8 mac_addr_mask[ETH_ALEN] __aligned(2); @@ -3076,6 +3094,12 @@ struct wiphy_vendor_command { * include fixed IEs like supported rates * @max_sched_scan_ie_len: same as max_scan_ie_len, but for scheduled * scans + * @max_sched_scan_plans: maximum number of scan plans (scan interval and number + * of iterations) for scheduled scan supported by the device. + * @max_sched_scan_plan_interval: maximum interval (in seconds) for a + * single scan plan supported by the device. + * @max_sched_scan_plan_iterations: maximum number of iterations for a single + * scan plan supported by the device. * @coverage_class: current coverage class * @fw_version: firmware version for ethtool reporting * @hw_version: hardware version for ethtool reporting @@ -3183,6 +3207,9 @@ struct wiphy { u8 max_match_sets; u16 max_scan_ie_len; u16 max_sched_scan_ie_len; + u32 max_sched_scan_plans; + u32 max_sched_scan_plan_interval; + u32 max_sched_scan_plan_iterations; int n_cipher_suites; const u32 *cipher_suites; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5dadb844fe18..1f0b4cf5dd03 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -10,6 +10,7 @@ * Copyright 2008, 2009 Luis R. Rodriguez * Copyright 2008 Jouni Malinen * Copyright 2008 Colin McCabe + * Copyright 2015 Intel Deutschland GmbH * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -328,7 +329,15 @@ * partial scan results may be available * * @NL80211_CMD_START_SCHED_SCAN: start a scheduled scan at certain - * intervals, as specified by %NL80211_ATTR_SCHED_SCAN_INTERVAL. + * intervals and certain number of cycles, as specified by + * %NL80211_ATTR_SCHED_SCAN_PLANS. If %NL80211_ATTR_SCHED_SCAN_PLANS is + * not specified and only %NL80211_ATTR_SCHED_SCAN_INTERVAL is specified, + * scheduled scan will run in an infinite loop with the specified interval. + * These attributes are mutually exculsive, + * i.e. NL80211_ATTR_SCHED_SCAN_INTERVAL must not be passed if + * NL80211_ATTR_SCHED_SCAN_PLANS is defined. + * If for some reason scheduled scan is aborted by the driver, all scan + * plans are canceled (including scan plans that did not start yet). * Like with normal scans, if SSIDs (%NL80211_ATTR_SCAN_SSIDS) * are passed, they are used in the probe requests. For * broadcast, a broadcast SSID must be passed (ie. an empty @@ -1761,6 +1770,19 @@ enum nl80211_commands { * @NL80211_ATTR_REG_INDOOR: flag attribute, if set indicates that the device * is operating in an indoor environment. * + * @NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS: maximum number of scan plans for + * scheduled scan supported by the device (u32), a wiphy attribute. + * @NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL: maximum interval (in seconds) for + * a scan plan (u32), a wiphy attribute. + * @NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS: maximum number of iterations in + * a scan plan (u32), a wiphy attribute. + * @NL80211_ATTR_SCHED_SCAN_PLANS: a list of scan plans for scheduled scan. + * Each scan plan defines the number of scan iterations and the interval + * between scans. The last scan plan will always run infinitely, + * thus it must not specify the number of iterations, only the interval + * between scans. The scan plans are executed sequentially. + * Each scan plan is a nested attribute of &enum nl80211_sched_scan_plan. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2130,6 +2152,11 @@ enum nl80211_attrs { NL80211_ATTR_REG_INDOOR, + NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS, + NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL, + NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS, + NL80211_ATTR_SCHED_SCAN_PLANS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -4593,4 +4620,28 @@ enum nl80211_tdls_peer_capability { NL80211_TDLS_PEER_WMM = 1<<2, }; +/** + * enum nl80211_sched_scan_plan - scanning plan for scheduled scan + * @__NL80211_SCHED_SCAN_PLAN_INVALID: attribute number 0 is reserved + * @NL80211_SCHED_SCAN_PLAN_INTERVAL: interval between scan iterations. In + * seconds (u32). + * @NL80211_SCHED_SCAN_PLAN_ITERATIONS: number of scan iterations in this + * scan plan (u32). The last scan plan must not specify this attribute + * because it will run infinitely. A value of zero is invalid as it will + * make the scan plan meaningless. + * @NL80211_SCHED_SCAN_PLAN_MAX: highest scheduled scan plan attribute number + * currently defined + * @__NL80211_SCHED_SCAN_PLAN_AFTER_LAST: internal use + */ +enum nl80211_sched_scan_plan { + __NL80211_SCHED_SCAN_PLAN_INVALID, + NL80211_SCHED_SCAN_PLAN_INTERVAL, + NL80211_SCHED_SCAN_PLAN_ITERATIONS, + + /* keep last */ + __NL80211_SCHED_SCAN_PLAN_AFTER_LAST, + NL80211_SCHED_SCAN_PLAN_MAX = + __NL80211_SCHED_SCAN_PLAN_AFTER_LAST - 1 +}; + #endif /* __LINUX_NL80211_H */ diff --git a/net/wireless/core.c b/net/wireless/core.c index f223026ddb03..a83037da21b6 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -461,6 +461,9 @@ use_default_name: rdev->wiphy.max_num_csa_counters = 1; + rdev->wiphy.max_sched_scan_plans = 1; + rdev->wiphy.max_sched_scan_plan_interval = U32_MAX; + return &rdev->wiphy; } EXPORT_SYMBOL(wiphy_new_nm); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fb0712b3d9cb..28c29e7da749 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -479,6 +479,12 @@ nl80211_match_policy[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1] = { [NL80211_SCHED_SCAN_MATCH_ATTR_RSSI] = { .type = NLA_U32 }, }; +static const struct nla_policy +nl80211_plan_policy[NL80211_SCHED_SCAN_PLAN_MAX + 1] = { + [NL80211_SCHED_SCAN_PLAN_INTERVAL] = { .type = NLA_U32 }, + [NL80211_SCHED_SCAN_PLAN_ITERATIONS] = { .type = NLA_U32 }, +}; + static int nl80211_prepare_wdev_dump(struct sk_buff *skb, struct netlink_callback *cb, struct cfg80211_registered_device **rdev, @@ -1304,7 +1310,13 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, nla_put_u16(msg, NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN, rdev->wiphy.max_sched_scan_ie_len) || nla_put_u8(msg, NL80211_ATTR_MAX_MATCH_SETS, - rdev->wiphy.max_match_sets)) + rdev->wiphy.max_match_sets) || + nla_put_u32(msg, NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS, + rdev->wiphy.max_sched_scan_plans) || + nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL, + rdev->wiphy.max_sched_scan_plan_interval) || + nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS, + rdev->wiphy.max_sched_scan_plan_iterations)) goto nla_put_failure; if ((rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) && @@ -5974,14 +5986,100 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) return err; } +static int +nl80211_parse_sched_scan_plans(struct wiphy *wiphy, int n_plans, + struct cfg80211_sched_scan_request *request, + struct nlattr **attrs) +{ + int tmp, err, i = 0; + struct nlattr *attr; + + if (!attrs[NL80211_ATTR_SCHED_SCAN_PLANS]) { + u32 interval; + + /* + * If scan plans are not specified, + * %NL80211_ATTR_SCHED_SCAN_INTERVAL must be specified. In this + * case one scan plan will be set with the specified scan + * interval and infinite number of iterations. + */ + if (!attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]) + return -EINVAL; + + interval = nla_get_u32(attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]); + if (!interval) + return -EINVAL; + + request->scan_plans[0].interval = + DIV_ROUND_UP(interval, MSEC_PER_SEC); + if (!request->scan_plans[0].interval) + return -EINVAL; + + if (request->scan_plans[0].interval > + wiphy->max_sched_scan_plan_interval) + request->scan_plans[0].interval = + wiphy->max_sched_scan_plan_interval; + + return 0; + } + + nla_for_each_nested(attr, attrs[NL80211_ATTR_SCHED_SCAN_PLANS], tmp) { + struct nlattr *plan[NL80211_SCHED_SCAN_PLAN_MAX + 1]; + + if (WARN_ON(i >= n_plans)) + return -EINVAL; + + err = nla_parse(plan, NL80211_SCHED_SCAN_PLAN_MAX, + nla_data(attr), nla_len(attr), + nl80211_plan_policy); + if (err) + return err; + + if (!plan[NL80211_SCHED_SCAN_PLAN_INTERVAL]) + return -EINVAL; + + request->scan_plans[i].interval = + nla_get_u32(plan[NL80211_SCHED_SCAN_PLAN_INTERVAL]); + if (!request->scan_plans[i].interval || + request->scan_plans[i].interval > + wiphy->max_sched_scan_plan_interval) + return -EINVAL; + + if (plan[NL80211_SCHED_SCAN_PLAN_ITERATIONS]) { + request->scan_plans[i].iterations = + nla_get_u32(plan[NL80211_SCHED_SCAN_PLAN_ITERATIONS]); + if (!request->scan_plans[i].iterations || + (request->scan_plans[i].iterations > + wiphy->max_sched_scan_plan_iterations)) + return -EINVAL; + } else if (i < n_plans - 1) { + /* + * All scan plans but the last one must specify + * a finite number of iterations + */ + return -EINVAL; + } + + i++; + } + + /* + * The last scan plan must not specify the number of + * iterations, it is supposed to run infinitely + */ + if (request->scan_plans[n_plans - 1].iterations) + return -EINVAL; + + return 0; +} + static struct cfg80211_sched_scan_request * nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, struct nlattr **attrs) { struct cfg80211_sched_scan_request *request; struct nlattr *attr; - int err, tmp, n_ssids = 0, n_match_sets = 0, n_channels, i; - u32 interval; + int err, tmp, n_ssids = 0, n_match_sets = 0, n_channels, i, n_plans = 0; enum ieee80211_band band; size_t ie_len; struct nlattr *tb[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1]; @@ -5990,13 +6088,6 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, if (!is_valid_ie_attr(attrs[NL80211_ATTR_IE])) return ERR_PTR(-EINVAL); - if (!attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]) - return ERR_PTR(-EINVAL); - - interval = nla_get_u32(attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]); - if (interval == 0) - return ERR_PTR(-EINVAL); - if (attrs[NL80211_ATTR_SCAN_FREQUENCIES]) { n_channels = validate_scan_freqs( attrs[NL80211_ATTR_SCAN_FREQUENCIES]); @@ -6060,9 +6151,37 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, if (ie_len > wiphy->max_sched_scan_ie_len) return ERR_PTR(-EINVAL); + if (attrs[NL80211_ATTR_SCHED_SCAN_PLANS]) { + /* + * NL80211_ATTR_SCHED_SCAN_INTERVAL must not be specified since + * each scan plan already specifies its own interval + */ + if (attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]) + return ERR_PTR(-EINVAL); + + nla_for_each_nested(attr, + attrs[NL80211_ATTR_SCHED_SCAN_PLANS], tmp) + n_plans++; + } else { + /* + * The scan interval attribute is kept for backward + * compatibility. If no scan plans are specified and sched scan + * interval is specified, one scan plan will be set with this + * scan interval and infinite number of iterations. + */ + if (!attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]) + return ERR_PTR(-EINVAL); + + n_plans = 1; + } + + if (!n_plans || n_plans > wiphy->max_sched_scan_plans) + return ERR_PTR(-EINVAL); + request = kzalloc(sizeof(*request) + sizeof(*request->ssids) * n_ssids + sizeof(*request->match_sets) * n_match_sets + + sizeof(*request->scan_plans) * n_plans + sizeof(*request->channels) * n_channels + ie_len, GFP_KERNEL); if (!request) @@ -6090,6 +6209,18 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, } request->n_match_sets = n_match_sets; + if (n_match_sets) + request->scan_plans = (void *)(request->match_sets + + n_match_sets); + else if (request->ie) + request->scan_plans = (void *)(request->ie + ie_len); + else if (n_ssids) + request->scan_plans = (void *)(request->ssids + n_ssids); + else + request->scan_plans = (void *)(request->channels + n_channels); + + request->n_scan_plans = n_plans; + i = 0; if (attrs[NL80211_ATTR_SCAN_FREQUENCIES]) { /* user specified, bail out if channel not found */ @@ -6252,7 +6383,10 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, request->delay = nla_get_u32(attrs[NL80211_ATTR_SCHED_SCAN_DELAY]); - request->interval = interval; + err = nl80211_parse_sched_scan_plans(wiphy, n_plans, request, attrs); + if (err) + goto out_free; + request->scan_start = jiffies; return request; @@ -8850,7 +8984,7 @@ static int nl80211_send_wowlan_tcp(struct sk_buff *msg, static int nl80211_send_wowlan_nd(struct sk_buff *msg, struct cfg80211_sched_scan_request *req) { - struct nlattr *nd, *freqs, *matches, *match; + struct nlattr *nd, *freqs, *matches, *match, *scan_plans, *scan_plan; int i; if (!req) @@ -8860,7 +8994,9 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg, if (!nd) return -ENOBUFS; - if (nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_INTERVAL, req->interval)) + if (req->n_scan_plans == 1 && + nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_INTERVAL, + req->scan_plans[0].interval * 1000)) return -ENOBUFS; if (nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_DELAY, req->delay)) @@ -8887,6 +9023,23 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg, nla_nest_end(msg, matches); } + scan_plans = nla_nest_start(msg, NL80211_ATTR_SCHED_SCAN_PLANS); + if (!scan_plans) + return -ENOBUFS; + + for (i = 0; i < req->n_scan_plans; i++) { + scan_plan = nla_nest_start(msg, i + 1); + if (!scan_plan || + nla_put_u32(msg, NL80211_SCHED_SCAN_PLAN_INTERVAL, + req->scan_plans[i].interval) || + (req->scan_plans[i].iterations && + nla_put_u32(msg, NL80211_SCHED_SCAN_PLAN_ITERATIONS, + req->scan_plans[i].iterations))) + return -ENOBUFS; + nla_nest_end(msg, scan_plan); + } + nla_nest_end(msg, scan_plans); + nla_nest_end(msg, nd); return 0; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 3feaa03aa046..14d5369eb778 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -266,8 +266,7 @@ void __cfg80211_sched_scan_results(struct work_struct *wk) spin_lock_bh(&rdev->bss_lock); __cfg80211_bss_expire(rdev, request->scan_start); spin_unlock_bh(&rdev->bss_lock); - request->scan_start = - jiffies + msecs_to_jiffies(request->interval); + request->scan_start = jiffies; } nl80211_send_sched_scan_results(rdev, request->dev); } -- cgit v1.2.3 From 4a733ef1bea705cdc69d936b95fedab4b47fbd40 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 14 Oct 2015 18:02:43 +0200 Subject: mac80211: remove PM-QoS listener As this API has never really seen any use and most drivers don't ever use the value derived from it, remove it. Change the only driver using it (rt2x00) to simply use the DTIM period instead of the "max sleep" time. Signed-off-by: Johannes Berg --- drivers/net/wireless/rt2x00/rt2x00config.c | 2 +- include/net/mac80211.h | 6 --- net/mac80211/cfg.c | 4 +- net/mac80211/ieee80211_i.h | 5 +-- net/mac80211/iface.c | 4 +- net/mac80211/main.c | 13 ------ net/mac80211/mlme.c | 69 ++++++------------------------ net/mac80211/scan.c | 1 - net/mac80211/trace.h | 2 - net/mac80211/util.c | 2 +- 10 files changed, 21 insertions(+), 87 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/rt2x00/rt2x00config.c b/drivers/net/wireless/rt2x00/rt2x00config.c index 48a2cad29477..7e8bb1198ae9 100644 --- a/drivers/net/wireless/rt2x00/rt2x00config.c +++ b/drivers/net/wireless/rt2x00/rt2x00config.c @@ -266,7 +266,7 @@ void rt2x00lib_config(struct rt2x00_dev *rt2x00dev, if (beacon_diff > beacon_int) beacon_diff = 0; - autowake_timeout = (conf->max_sleep_period * beacon_int) - beacon_diff; + autowake_timeout = (conf->ps_dtim_period * beacon_int) - beacon_diff; queue_delayed_work(rt2x00dev->workqueue, &rt2x00dev->autowakeup_work, autowake_timeout - 15); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 1bb2a2b4e187..4b9dd070aeb9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1241,11 +1241,6 @@ enum ieee80211_smps_mode { * @flags: configuration flags defined above * * @listen_interval: listen interval in units of beacon interval - * @max_sleep_period: the maximum number of beacon intervals to sleep for - * before checking the beacon for a TIM bit (managed mode only); this - * value will be only achievable between DTIM frames, the hardware - * needs to check for the multicast traffic bit in DTIM beacons. - * This variable is valid only when the CONF_PS flag is set. * @ps_dtim_period: The DTIM period of the AP we're connected to, for use * in power saving. Power saving will not be enabled until a beacon * has been received and the DTIM period is known. @@ -1275,7 +1270,6 @@ enum ieee80211_smps_mode { struct ieee80211_conf { u32 flags; int power_level, dynamic_ps_timeout; - int max_sleep_period; u16 listen_interval; u8 ps_dtim_period; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 63d03dad654c..276b57243298 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1428,7 +1428,7 @@ static int ieee80211_change_station(struct wiphy *wiphy, if (sdata->vif.type == NL80211_IFTYPE_STATION && params->sta_flags_mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { - ieee80211_recalc_ps(local, -1); + ieee80211_recalc_ps(local); ieee80211_recalc_ps_vif(sdata); } @@ -2463,7 +2463,7 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, if (ieee80211_hw_check(&local->hw, SUPPORTS_DYNAMIC_PS)) ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); - ieee80211_recalc_ps(local, -1); + ieee80211_recalc_ps(local); ieee80211_recalc_ps_vif(sdata); return 0; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index f9605f13def9..99735408e99d 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1305,7 +1305,6 @@ struct ieee80211_local { struct work_struct dynamic_ps_enable_work; struct work_struct dynamic_ps_disable_work; struct timer_list dynamic_ps_timer; - struct notifier_block network_latency_notifier; struct notifier_block ifa_notifier; struct notifier_block ifa6_notifier; @@ -1491,10 +1490,8 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, struct cfg80211_disassoc_request *req); void ieee80211_send_pspoll(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); -void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency); +void ieee80211_recalc_ps(struct ieee80211_local *local); void ieee80211_recalc_ps_vif(struct ieee80211_sub_if_data *sdata); -int ieee80211_max_network_latency(struct notifier_block *nb, - unsigned long data, void *dummy); int ieee80211_set_arp_filter(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 42d7f0f65bd6..f848c75518a2 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -709,7 +709,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) if (hw_reconf_flags) ieee80211_hw_config(local, hw_reconf_flags); - ieee80211_recalc_ps(local, -1); + ieee80211_recalc_ps(local); if (sdata->vif.type == NL80211_IFTYPE_MONITOR || sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { @@ -1016,7 +1016,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, drv_remove_interface(local, sdata); } - ieee80211_recalc_ps(local, -1); + ieee80211_recalc_ps(local); if (cancel_scan) flush_delayed_work(&local->scan_work); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 9b813a2f3a75..e2514fadc3d7 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include @@ -1083,13 +1082,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) rtnl_unlock(); - local->network_latency_notifier.notifier_call = - ieee80211_max_network_latency; - result = pm_qos_add_notifier(PM_QOS_NETWORK_LATENCY, - &local->network_latency_notifier); - if (result) - goto fail_pm_qos; - #ifdef CONFIG_INET local->ifa_notifier.notifier_call = ieee80211_ifa_changed; result = register_inetaddr_notifier(&local->ifa_notifier); @@ -1114,10 +1106,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) #endif #if defined(CONFIG_INET) || defined(CONFIG_IPV6) fail_ifa: - pm_qos_remove_notifier(PM_QOS_NETWORK_LATENCY, - &local->network_latency_notifier); #endif - fail_pm_qos: rtnl_lock(); rate_control_deinitialize(local); ieee80211_remove_interfaces(local); @@ -1143,8 +1132,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) tasklet_kill(&local->tx_pending_tasklet); tasklet_kill(&local->tasklet); - pm_qos_remove_notifier(PM_QOS_NETWORK_LATENCY, - &local->network_latency_notifier); #ifdef CONFIG_INET unregister_inetaddr_notifier(&local->ifa_notifier); #endif diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 9c450ffdabe8..6158db06a5b5 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include @@ -1476,7 +1475,7 @@ static bool ieee80211_powersave_allowed(struct ieee80211_sub_if_data *sdata) } /* need to hold RTNL or interface lock */ -void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency) +void ieee80211_recalc_ps(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata, *found = NULL; int count = 0; @@ -1505,48 +1504,23 @@ void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency) } if (count == 1 && ieee80211_powersave_allowed(found)) { + u8 dtimper = found->u.mgd.dtim_period; s32 beaconint_us; - if (latency < 0) - latency = pm_qos_request(PM_QOS_NETWORK_LATENCY); - beaconint_us = ieee80211_tu_to_usec( found->vif.bss_conf.beacon_int); timeout = local->dynamic_ps_forced_timeout; - if (timeout < 0) { - /* - * Go to full PSM if the user configures a very low - * latency requirement. - * The 2000 second value is there for compatibility - * until the PM_QOS_NETWORK_LATENCY is configured - * with real values. - */ - if (latency > (1900 * USEC_PER_MSEC) && - latency != (2000 * USEC_PER_SEC)) - timeout = 0; - else - timeout = 100; - } + if (timeout < 0) + timeout = 100; local->hw.conf.dynamic_ps_timeout = timeout; - if (beaconint_us > latency) { - local->ps_sdata = NULL; - } else { - int maxslp = 1; - u8 dtimper = found->u.mgd.dtim_period; - - /* If the TIM IE is invalid, pretend the value is 1 */ - if (!dtimper) - dtimper = 1; - else if (dtimper > 1) - maxslp = min_t(int, dtimper, - latency / beaconint_us); - - local->hw.conf.max_sleep_period = maxslp; - local->hw.conf.ps_dtim_period = dtimper; - local->ps_sdata = found; - } + /* If the TIM IE is invalid, pretend the value is 1 */ + if (!dtimper) + dtimper = 1; + + local->hw.conf.ps_dtim_period = dtimper; + local->ps_sdata = found; } else { local->ps_sdata = NULL; } @@ -1997,7 +1971,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, ieee80211_bss_info_change_notify(sdata, bss_info_changed); mutex_lock(&local->iflist_mtx); - ieee80211_recalc_ps(local, -1); + ieee80211_recalc_ps(local); mutex_unlock(&local->iflist_mtx); ieee80211_recalc_smps(sdata); @@ -2165,7 +2139,7 @@ static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) __ieee80211_stop_poll(sdata); mutex_lock(&local->iflist_mtx); - ieee80211_recalc_ps(local, -1); + ieee80211_recalc_ps(local); mutex_unlock(&local->iflist_mtx); if (ieee80211_hw_check(&sdata->local->hw, CONNECTION_MONITOR)) @@ -2341,7 +2315,7 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata, goto out; mutex_lock(&sdata->local->iflist_mtx); - ieee80211_recalc_ps(sdata->local, -1); + ieee80211_recalc_ps(sdata->local); mutex_unlock(&sdata->local->iflist_mtx); ifmgd->probe_send_count = 0; @@ -3548,7 +3522,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ifmgd->have_beacon = true; mutex_lock(&local->iflist_mtx); - ieee80211_recalc_ps(local, -1); + ieee80211_recalc_ps(local); mutex_unlock(&local->iflist_mtx); ieee80211_recalc_ps_vif(sdata); @@ -4152,21 +4126,6 @@ void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local) rcu_read_unlock(); } -int ieee80211_max_network_latency(struct notifier_block *nb, - unsigned long data, void *dummy) -{ - s32 latency_usec = (s32) data; - struct ieee80211_local *local = - container_of(nb, struct ieee80211_local, - network_latency_notifier); - - mutex_lock(&local->iflist_mtx); - ieee80211_recalc_ps(local, latency_usec); - mutex_unlock(&local->iflist_mtx); - - return NOTIFY_OK; -} - static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata, struct cfg80211_bss *cbss) { diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index a368a1d6caff..b64fd2b2d95a 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 314e3bd7fbdb..5cf8f4ea077f 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -325,7 +325,6 @@ TRACE_EVENT(drv_config, __field(u32, flags) __field(int, power_level) __field(int, dynamic_ps_timeout) - __field(int, max_sleep_period) __field(u16, listen_interval) __field(u8, long_frame_max_tx_count) __field(u8, short_frame_max_tx_count) @@ -339,7 +338,6 @@ TRACE_EVENT(drv_config, __entry->flags = local->hw.conf.flags; __entry->power_level = local->hw.conf.power_level; __entry->dynamic_ps_timeout = local->hw.conf.dynamic_ps_timeout; - __entry->max_sleep_period = local->hw.conf.max_sleep_period; __entry->listen_interval = local->hw.conf.listen_interval; __entry->long_frame_max_tx_count = local->hw.conf.long_frame_max_tx_count; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 8f0fa357a5a7..8274c86296f9 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1951,7 +1951,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) } } - ieee80211_recalc_ps(local, -1); + ieee80211_recalc_ps(local); /* * The sta might be in psm against the ap (e.g. because -- cgit v1.2.3