From ab9177d83c040eba58387914077ebca56f14fae6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 26 Mar 2024 22:08:54 +0100 Subject: wifi: mac80211: don't use rate mask for scanning The rate mask is intended for use during operation, and can be set to only have masks for the currently active band. As such, it cannot be used for scanning which can be on other bands as well. Simply ignore the rate masks during scanning to avoid warnings from incorrect settings. Reported-by: syzbot+fdc5123366fb9c3fdc6d@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=fdc5123366fb9c3fdc6d Co-developed-by: Dmitry Antipov Signed-off-by: Dmitry Antipov Tested-by: Dmitry Antipov Link: https://msgid.link/20240326220854.9594cbb418ca.I7f86c0ba1f98cf7e27c2bacf6c2d417200ecea5c@changeid Signed-off-by: Johannes Berg --- include/net/mac80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 353488ab94a2..2d7f87bc5324 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -953,6 +953,8 @@ enum mac80211_tx_info_flags { * of their QoS TID or other priority field values. * @IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX: first MLO TX, used mostly internally * for sequence number assignment + * @IEEE80211_TX_CTRL_SCAN_TX: Indicates that this frame is transmitted + * due to scanning, not in normal operation on the interface. * @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this * frame should be transmitted on the specific link. This really is * only relevant for frames that do not have data present, and is @@ -973,6 +975,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX = BIT(9), + IEEE80211_TX_CTRL_SCAN_TX = BIT(10), IEEE80211_TX_CTRL_MLO_LINK = 0xf0000000, }; -- cgit v1.2.3 From 3584718cf2ec7e79b6814f2596dcf398c5fb2eca Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 21 Apr 2024 17:52:48 +0000 Subject: net: fix sk_memory_allocated_{add|sub} vs softirqs Jonathan Heathcote reported a regression caused by blamed commit on aarch64 architecture. x86 happens to have irq-safe __this_cpu_add_return() and __this_cpu_sub(), but this is not generic. I think my confusion came from "struct sock" argument, because these helpers are called with a locked socket. But the memory accounting is per-proto (and per-cpu after the blamed commit). We might cleanup these helpers later to directly accept a "struct proto *proto" argument. Switch to this_cpu_add_return() and this_cpu_xchg() operations, and get rid of preempt_disable()/preempt_enable() pairs. Fast path becomes a bit faster as a result :) Many thanks to Jonathan Heathcote for his awesome report and investigations. Fixes: 3cd3399dd7a8 ("net: implement per-cpu reserves for memory_allocated") Reported-by: Jonathan Heathcote Closes: https://lore.kernel.org/netdev/VI1PR01MB42407D7947B2EA448F1E04EFD10D2@VI1PR01MB4240.eurprd01.prod.exchangelabs.com/ Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Shakeel Butt Link: https://lore.kernel.org/r/20240421175248.1692552-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index f57bfd8a2ad2..b4b553df7870 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1410,32 +1410,34 @@ sk_memory_allocated(const struct sock *sk) #define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) extern int sysctl_mem_pcpu_rsv; +static inline void proto_memory_pcpu_drain(struct proto *proto) +{ + int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0); + + if (val) + atomic_long_add(val, proto->memory_allocated); +} + static inline void -sk_memory_allocated_add(struct sock *sk, int amt) +sk_memory_allocated_add(const struct sock *sk, int val) { - int local_reserve; + struct proto *proto = sk->sk_prot; - preempt_disable(); - local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt); - if (local_reserve >= READ_ONCE(sysctl_mem_pcpu_rsv)) { - __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); - atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); - } - preempt_enable(); + val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val >= READ_ONCE(sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); } static inline void -sk_memory_allocated_sub(struct sock *sk, int amt) +sk_memory_allocated_sub(const struct sock *sk, int val) { - int local_reserve; + struct proto *proto = sk->sk_prot; - preempt_disable(); - local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt); - if (local_reserve <= -READ_ONCE(sysctl_mem_pcpu_rsv)) { - __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); - atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); - } - preempt_enable(); + val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val <= -READ_ONCE(sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 -- cgit v1.2.3 From 2e7ed5f5e69b6fe93dd3c6b651d041e0a7a456d1 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 5 Apr 2024 16:40:33 -0400 Subject: Bluetooth: hci_sync: Use advertised PHYs on hci_le_ext_create_conn_sync The extended advertising reports do report the PHYs so this store then in hci_conn so it can be later used in hci_le_ext_create_conn_sync to narrow the PHYs to be scanned since the controller will also perform a scan having a smaller set of PHYs shall reduce the time it takes to find and connect peers. Fixes: 288c90224eec ("Bluetooth: Enable all supported LE PHY by default") Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 4 +++- net/bluetooth/hci_conn.c | 6 ++++-- net/bluetooth/hci_event.c | 20 ++++++++++++-------- net/bluetooth/hci_sync.c | 9 ++++++--- net/bluetooth/l2cap_core.c | 2 +- 5 files changed, 26 insertions(+), 15 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 56fb42df44a3..02af7d7013da 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -738,6 +738,8 @@ struct hci_conn { __u8 le_per_adv_data[HCI_MAX_PER_AD_TOT_LEN]; __u16 le_per_adv_data_len; __u16 le_per_adv_data_offset; + __u8 le_adv_phy; + __u8 le_adv_sec_phy; __u8 le_tx_phy; __u8 le_rx_phy; __s8 rssi; @@ -1512,7 +1514,7 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, enum conn_reasons conn_reason); struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, - u16 conn_timeout, u8 role); + u16 conn_timeout, u8 role, u8 phy, u8 sec_phy); void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status); struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 3ad74f76983b..05346250f719 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1263,7 +1263,7 @@ u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, - u16 conn_timeout, u8 role) + u16 conn_timeout, u8 role, u8 phy, u8 sec_phy) { struct hci_conn *conn; struct smp_irk *irk; @@ -1326,6 +1326,8 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, conn->dst_type = dst_type; conn->sec_level = BT_SECURITY_LOW; conn->conn_timeout = conn_timeout; + conn->le_adv_phy = phy; + conn->le_adv_sec_phy = sec_phy; err = hci_connect_le_sync(hdev, conn); if (err) { @@ -2273,7 +2275,7 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, le = hci_connect_le(hdev, dst, dst_type, false, BT_SECURITY_LOW, HCI_LE_CONN_TIMEOUT, - HCI_ROLE_SLAVE); + HCI_ROLE_SLAVE, 0, 0); else le = hci_connect_le_scan(hdev, dst, dst_type, BT_SECURITY_LOW, diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index a8b8cfebe018..4d70402e295f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -6038,7 +6038,7 @@ static void hci_le_conn_update_complete_evt(struct hci_dev *hdev, void *data, static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type, bool addr_resolved, - u8 adv_type) + u8 adv_type, u8 phy, u8 sec_phy) { struct hci_conn *conn; struct hci_conn_params *params; @@ -6093,7 +6093,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, conn = hci_connect_le(hdev, addr, addr_type, addr_resolved, BT_SECURITY_LOW, hdev->def_le_autoconnect_timeout, - HCI_ROLE_MASTER); + HCI_ROLE_MASTER, phy, sec_phy); if (!IS_ERR(conn)) { /* If HCI_AUTO_CONN_EXPLICIT is set, conn is already owned * by higher layer that tried to connect, if no then @@ -6128,8 +6128,9 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *direct_addr, - u8 direct_addr_type, s8 rssi, u8 *data, u8 len, - bool ext_adv, bool ctl_time, u64 instant) + u8 direct_addr_type, u8 phy, u8 sec_phy, s8 rssi, + u8 *data, u8 len, bool ext_adv, bool ctl_time, + u64 instant) { struct discovery_state *d = &hdev->discovery; struct smp_irk *irk; @@ -6217,7 +6218,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, * for advertising reports) and is already verified to be RPA above. */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, bdaddr_resolved, - type); + type, phy, sec_phy); if (!ext_adv && conn && type == LE_ADV_IND && len <= max_adv_len(hdev)) { /* Store report for later inclusion by @@ -6363,7 +6364,8 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, void *data, if (info->length <= max_adv_len(hdev)) { rssi = info->data[info->length]; process_adv_report(hdev, info->type, &info->bdaddr, - info->bdaddr_type, NULL, 0, rssi, + info->bdaddr_type, NULL, 0, + HCI_ADV_PHY_1M, 0, rssi, info->data, info->length, false, false, instant); } else { @@ -6448,6 +6450,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data, if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &info->bdaddr, info->bdaddr_type, NULL, 0, + info->primary_phy, + info->secondary_phy, info->rssi, info->data, info->length, !(evt_type & LE_EXT_ADV_LEGACY_PDU), false, instant); @@ -6730,8 +6734,8 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, void *data, process_adv_report(hdev, info->type, &info->bdaddr, info->bdaddr_type, &info->direct_addr, - info->direct_addr_type, info->rssi, NULL, 0, - false, false, instant); + info->direct_addr_type, HCI_ADV_PHY_1M, 0, + info->rssi, NULL, 0, false, false, instant); } hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index c5d8799046cc..4c707eb64e6f 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -6346,7 +6346,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, plen = sizeof(*cp); - if (scan_1m(hdev)) { + if (scan_1m(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_1M || + conn->le_adv_sec_phy == HCI_ADV_PHY_1M)) { cp->phys |= LE_SCAN_PHY_1M; set_ext_conn_params(conn, p); @@ -6354,7 +6355,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, plen += sizeof(*p); } - if (scan_2m(hdev)) { + if (scan_2m(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_2M || + conn->le_adv_sec_phy == HCI_ADV_PHY_2M)) { cp->phys |= LE_SCAN_PHY_2M; set_ext_conn_params(conn, p); @@ -6362,7 +6364,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, plen += sizeof(*p); } - if (scan_coded(hdev)) { + if (scan_coded(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_CODED || + conn->le_adv_sec_phy == HCI_ADV_PHY_CODED)) { cp->phys |= LE_SCAN_PHY_CODED; set_ext_conn_params(conn, p); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index dc0897408793..84fc70862d78 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7018,7 +7018,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) hcon = hci_connect_le(hdev, dst, dst_type, false, chan->sec_level, timeout, - HCI_ROLE_SLAVE); + HCI_ROLE_SLAVE, 0, 0); else hcon = hci_connect_le_scan(hdev, dst, dst_type, chan->sec_level, timeout, -- cgit v1.2.3 From a9a830a676a9a93c5020f5c61236166931fa4266 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 15 Apr 2024 13:41:01 -0400 Subject: Bluetooth: hci_event: Fix sending HCI_OP_READ_ENC_KEY_SIZE The code shall always check if HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE has been set before attempting to use HCI_OP_READ_ENC_KEY_SIZE. Fixes: c569242cd492 ("Bluetooth: hci_event: set the conn encrypted before conn establishes") Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 4 ++++ net/bluetooth/hci_event.c | 5 ++--- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 02af7d7013da..e8f581f3f3ce 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1907,6 +1907,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define privacy_mode_capable(dev) (use_ll_privacy(dev) && \ (hdev->commands[39] & 0x04)) +#define read_key_size_capable(dev) \ + ((dev)->commands[20] & 0x10 && \ + !test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) + /* Use enhanced synchronous connection if command is supported and its quirk * has not been set. */ diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 4d70402e295f..4a27e4a17a67 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3218,7 +3218,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, if (key) { set_bit(HCI_CONN_ENCRYPT, &conn->flags); - if (!(hdev->commands[20] & 0x10)) { + if (!read_key_size_capable(hdev)) { conn->enc_key_size = HCI_LINK_KEY_SIZE; } else { cp.handle = cpu_to_le16(conn->handle); @@ -3666,8 +3666,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data, * controller really supports it. If it doesn't, assume * the default size (16). */ - if (!(hdev->commands[20] & 0x10) || - test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) { + if (!read_key_size_capable(hdev)) { conn->enc_key_size = HCI_LINK_KEY_SIZE; goto notify; } -- cgit v1.2.3 From 475747a19316b08e856c666a20503e73d7ed67ed Mon Sep 17 00:00:00 2001 From: Rahul Rameshbabu Date: Tue, 23 Apr 2024 11:13:02 -0700 Subject: macsec: Enable devices to advertise whether they update sk_buff md_dst during offloads Cannot know whether a Rx skb missing md_dst is intended for MACsec or not without knowing whether the device is able to update this field during an offload. Assume that an offload to a MACsec device cannot support updating md_dst by default. Capable devices can advertise that they do indicate that an skb is related to a MACsec offloaded packet using the md_dst. Cc: Sabrina Dubroca Cc: stable@vger.kernel.org Fixes: 860ead89b851 ("net/macsec: Add MACsec skb_metadata_dst Rx Data path support") Signed-off-by: Rahul Rameshbabu Reviewed-by: Benjamin Poirier Reviewed-by: Cosmin Ratiu Reviewed-by: Sabrina Dubroca Link: https://lore.kernel.org/r/20240423181319.115860-2-rrameshbabu@nvidia.com Signed-off-by: Jakub Kicinski --- include/net/macsec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/macsec.h b/include/net/macsec.h index dbd22180cc5c..de216cbc6b05 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -321,6 +321,7 @@ struct macsec_context { * for the TX tag * @needed_tailroom: number of bytes reserved at the end of the sk_buff for the * TX tag + * @rx_uses_md_dst: whether MACsec device offload supports sk_buff md_dst */ struct macsec_ops { /* Device wide */ @@ -352,6 +353,7 @@ struct macsec_ops { struct sk_buff *skb); unsigned int needed_headroom; unsigned int needed_tailroom; + bool rx_uses_md_dst; }; void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa); -- cgit v1.2.3 From 0844370f8945086eb9335739d10205dcea8d707b Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Wed, 24 Apr 2024 12:25:47 +0200 Subject: tls: fix lockless read of strp->msg_ready in ->poll tls_sk_poll is called without locking the socket, and needs to read strp->msg_ready (via tls_strp_msg_ready). Convert msg_ready to a bool and use READ_ONCE/WRITE_ONCE where needed. The remaining reads are only performed when the socket is locked. Fixes: 121dca784fc0 ("tls: suppress wakeups unless we have a full record") Signed-off-by: Sabrina Dubroca Link: https://lore.kernel.org/r/0b7ee062319037cf86af6b317b3d72f7bfcd2e97.1713797701.git.sd@queasysnail.net Signed-off-by: Jakub Kicinski --- include/net/tls.h | 3 ++- net/tls/tls.h | 2 +- net/tls/tls_strp.c | 6 +++--- 3 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/tls.h b/include/net/tls.h index 340ad43971e4..33f657d3c051 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -111,7 +111,8 @@ struct tls_strparser { u32 stopped : 1; u32 copy_mode : 1; u32 mixed_decrypted : 1; - u32 msg_ready : 1; + + bool msg_ready; struct strp_msg stm; diff --git a/net/tls/tls.h b/net/tls/tls.h index 762f424ff2d5..e5e47452308a 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -215,7 +215,7 @@ static inline struct sk_buff *tls_strp_msg(struct tls_sw_context_rx *ctx) static inline bool tls_strp_msg_ready(struct tls_sw_context_rx *ctx) { - return ctx->strp.msg_ready; + return READ_ONCE(ctx->strp.msg_ready); } static inline bool tls_strp_msg_mixed_decrypted(struct tls_sw_context_rx *ctx) diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index ca1e0e198ceb..5df08d848b5c 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -360,7 +360,7 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, if (strp->stm.full_len && strp->stm.full_len == skb->len) { desc->count = 0; - strp->msg_ready = 1; + WRITE_ONCE(strp->msg_ready, 1); tls_rx_msg_ready(strp); } @@ -528,7 +528,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) if (!tls_strp_check_queue_ok(strp)) return tls_strp_read_copy(strp, false); - strp->msg_ready = 1; + WRITE_ONCE(strp->msg_ready, 1); tls_rx_msg_ready(strp); return 0; @@ -580,7 +580,7 @@ void tls_strp_msg_done(struct tls_strparser *strp) else tls_strp_flush_anchor_copy(strp); - strp->msg_ready = 0; + WRITE_ONCE(strp->msg_ready, 0); memset(&strp->stm, 0, sizeof(strp->stm)); tls_strp_check_rcv(strp); -- cgit v1.2.3 From 1971d13ffa84a551d29a81fdf5b5ec5be166ac83 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 24 Apr 2024 10:04:43 -0700 Subject: af_unix: Suppress false-positive lockdep splat for spin_lock() in __unix_gc(). syzbot reported a lockdep splat regarding unix_gc_lock and unix_state_lock(). One is called from recvmsg() for a connected socket, and another is called from GC for TCP_LISTEN socket. So, the splat is false-positive. Let's add a dedicated lock class for the latter to suppress the splat. Note that this change is not necessary for net-next.git as the issue is only applied to the old GC impl. [0]: WARNING: possible circular locking dependency detected 6.9.0-rc5-syzkaller-00007-g4d2008430ce8 #0 Not tainted ----------------------------------------------------- kworker/u8:1/11 is trying to acquire lock: ffff88807cea4e70 (&u->lock){+.+.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] ffff88807cea4e70 (&u->lock){+.+.}-{2:2}, at: __unix_gc+0x40e/0xf70 net/unix/garbage.c:302 but task is already holding lock: ffffffff8f6ab638 (unix_gc_lock){+.+.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] ffffffff8f6ab638 (unix_gc_lock){+.+.}-{2:2}, at: __unix_gc+0x117/0xf70 net/unix/garbage.c:261 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (unix_gc_lock){+.+.}-{2:2}: lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5754 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154 spin_lock include/linux/spinlock.h:351 [inline] unix_notinflight+0x13d/0x390 net/unix/garbage.c:140 unix_detach_fds net/unix/af_unix.c:1819 [inline] unix_destruct_scm+0x221/0x350 net/unix/af_unix.c:1876 skb_release_head_state+0x100/0x250 net/core/skbuff.c:1188 skb_release_all net/core/skbuff.c:1200 [inline] __kfree_skb net/core/skbuff.c:1216 [inline] kfree_skb_reason+0x16d/0x3b0 net/core/skbuff.c:1252 kfree_skb include/linux/skbuff.h:1262 [inline] manage_oob net/unix/af_unix.c:2672 [inline] unix_stream_read_generic+0x1125/0x2700 net/unix/af_unix.c:2749 unix_stream_splice_read+0x239/0x320 net/unix/af_unix.c:2981 do_splice_read fs/splice.c:985 [inline] splice_file_to_pipe+0x299/0x500 fs/splice.c:1295 do_splice+0xf2d/0x1880 fs/splice.c:1379 __do_splice fs/splice.c:1436 [inline] __do_sys_splice fs/splice.c:1652 [inline] __se_sys_splice+0x331/0x4a0 fs/splice.c:1634 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f -> #0 (&u->lock){+.+.}-{2:2}: check_prev_add kernel/locking/lockdep.c:3134 [inline] check_prevs_add kernel/locking/lockdep.c:3253 [inline] validate_chain+0x18cb/0x58e0 kernel/locking/lockdep.c:3869 __lock_acquire+0x1346/0x1fd0 kernel/locking/lockdep.c:5137 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5754 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154 spin_lock include/linux/spinlock.h:351 [inline] __unix_gc+0x40e/0xf70 net/unix/garbage.c:302 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0xa10/0x17c0 kernel/workqueue.c:3335 worker_thread+0x86d/0xd70 kernel/workqueue.c:3416 kthread+0x2f0/0x390 kernel/kthread.c:388 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(unix_gc_lock); lock(&u->lock); lock(unix_gc_lock); lock(&u->lock); *** DEADLOCK *** 3 locks held by kworker/u8:1/11: #0: ffff888015089148 ((wq_completion)events_unbound){+.+.}-{0:0}, at: process_one_work kernel/workqueue.c:3229 [inline] #0: ffff888015089148 ((wq_completion)events_unbound){+.+.}-{0:0}, at: process_scheduled_works+0x8e0/0x17c0 kernel/workqueue.c:3335 #1: ffffc90000107d00 (unix_gc_work){+.+.}-{0:0}, at: process_one_work kernel/workqueue.c:3230 [inline] #1: ffffc90000107d00 (unix_gc_work){+.+.}-{0:0}, at: process_scheduled_works+0x91b/0x17c0 kernel/workqueue.c:3335 #2: ffffffff8f6ab638 (unix_gc_lock){+.+.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] #2: ffffffff8f6ab638 (unix_gc_lock){+.+.}-{2:2}, at: __unix_gc+0x117/0xf70 net/unix/garbage.c:261 stack backtrace: CPU: 0 PID: 11 Comm: kworker/u8:1 Not tainted 6.9.0-rc5-syzkaller-00007-g4d2008430ce8 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 Workqueue: events_unbound __unix_gc Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114 check_noncircular+0x36a/0x4a0 kernel/locking/lockdep.c:2187 check_prev_add kernel/locking/lockdep.c:3134 [inline] check_prevs_add kernel/locking/lockdep.c:3253 [inline] validate_chain+0x18cb/0x58e0 kernel/locking/lockdep.c:3869 __lock_acquire+0x1346/0x1fd0 kernel/locking/lockdep.c:5137 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5754 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154 spin_lock include/linux/spinlock.h:351 [inline] __unix_gc+0x40e/0xf70 net/unix/garbage.c:302 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0xa10/0x17c0 kernel/workqueue.c:3335 worker_thread+0x86d/0xd70 kernel/workqueue.c:3416 kthread+0x2f0/0x390 kernel/kthread.c:388 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 Fixes: 47d8ac011fe1 ("af_unix: Fix garbage collector racing against connect()") Reported-and-tested-by: syzbot+fa379358c28cc87cc307@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=fa379358c28cc87cc307 Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20240424170443.9832-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/af_unix.h | 3 +++ net/unix/garbage.c | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 627ea8e2d915..3dee0b2721aa 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -85,6 +85,9 @@ enum unix_socket_lock_class { U_LOCK_NORMAL, U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ + U_LOCK_GC_LISTENER, /* used for listening socket while determining gc + * candidates to close a small race window. + */ }; static inline void unix_state_lock_nested(struct sock *sk, diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 6433a414acf8..0104be9d4704 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -299,7 +299,7 @@ static void __unix_gc(struct work_struct *work) __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); if (sk->sk_state == TCP_LISTEN) { - unix_state_lock(sk); + unix_state_lock_nested(sk, U_LOCK_GC_LISTENER); unix_state_unlock(sk); } } -- cgit v1.2.3 From 5ef31ea5d053a8f493a772ebad3f3ce82c35d845 Mon Sep 17 00:00:00 2001 From: Richard Gobert Date: Tue, 30 Apr 2024 16:35:54 +0200 Subject: net: gro: fix udp bad offset in socket lookup by adding {inner_}network_offset to napi_gro_cb Commits a602456 ("udp: Add GRO functions to UDP socket") and 57c67ff ("udp: additional GRO support") introduce incorrect usage of {ip,ipv6}_hdr in the complete phase of gro. The functions always return skb->network_header, which in the case of encapsulated packets at the gro complete phase, is always set to the innermost L3 of the packet. That means that calling {ip,ipv6}_hdr for skbs which completed the GRO receive phase (both in gro_list and *_gro_complete) when parsing an encapsulated packet's _outer_ L3/L4 may return an unexpected value. This incorrect usage leads to a bug in GRO's UDP socket lookup. udp{4,6}_lib_lookup_skb functions use ip_hdr/ipv6_hdr respectively. These *_hdr functions return network_header which will point to the innermost L3, resulting in the wrong offset being used in __udp{4,6}_lib_lookup with encapsulated packets. This patch adds network_offset and inner_network_offset to napi_gro_cb, and makes sure both are set correctly. To fix the issue, network_offsets union is used inside napi_gro_cb, in which both the outer and the inner network offsets are saved. Reproduction example: Endpoint configuration example (fou + local address bind) # ip fou add port 6666 ipproto 4 # ip link add name tun1 type ipip remote 2.2.2.1 local 2.2.2.2 encap fou encap-dport 5555 encap-sport 6666 mode ipip # ip link set tun1 up # ip a add 1.1.1.2/24 dev tun1 Netperf TCP_STREAM result on net-next before patch is applied: net-next main, GRO enabled: $ netperf -H 1.1.1.2 -t TCP_STREAM -l 5 Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 131072 16384 16384 5.28 2.37 net-next main, GRO disabled: $ netperf -H 1.1.1.2 -t TCP_STREAM -l 5 Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 131072 16384 16384 5.01 2745.06 patch applied, GRO enabled: $ netperf -H 1.1.1.2 -t TCP_STREAM -l 5 Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 131072 16384 16384 5.01 2877.38 Fixes: a6024562ffd7 ("udp: Add GRO functions to UDP socket") Signed-off-by: Richard Gobert Reviewed-by: Eric Dumazet Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- include/net/gro.h | 9 +++++++++ net/8021q/vlan_core.c | 2 ++ net/core/gro.c | 1 + net/ipv4/af_inet.c | 1 + net/ipv4/udp.c | 3 ++- net/ipv4/udp_offload.c | 3 ++- net/ipv6/ip6_offload.c | 1 + net/ipv6/udp.c | 3 ++- net/ipv6/udp_offload.c | 3 ++- 9 files changed, 22 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/gro.h b/include/net/gro.h index 50f1e403dbbb..c1d4ca0463a1 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -87,6 +87,15 @@ struct napi_gro_cb { /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; + + /* L3 offsets */ + union { + struct { + u16 network_offset; + u16 inner_network_offset; + }; + u16 network_offsets[2]; + }; }; #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index f00158234505..9404dd551dfd 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -478,6 +478,8 @@ static struct sk_buff *vlan_gro_receive(struct list_head *head, if (unlikely(!vhdr)) goto out; + NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = hlen; + type = vhdr->h_vlan_encapsulated_proto; ptype = gro_find_receive_by_type(type); diff --git a/net/core/gro.c b/net/core/gro.c index 83f35d99a682..c7901253a1a8 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -371,6 +371,7 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) const skb_frag_t *frag0; unsigned int headlen; + NAPI_GRO_CB(skb)->network_offset = 0; NAPI_GRO_CB(skb)->data_offset = 0; headlen = skb_headlen(skb); NAPI_GRO_CB(skb)->frag0 = skb->data; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 55bd72997b31..fafb123f798b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1572,6 +1572,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) /* The above will be needed by the transport layer if there is one * immediately following this IP hdr. */ + NAPI_GRO_CB(skb)->inner_network_offset = off; /* Note : No need to call skb_gro_postpull_rcsum() here, * as we already checked checksum over ipv4 header was 0 diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 420905be5f30..b32cf2eeeb41 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -532,7 +532,8 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { - const struct iphdr *iph = ip_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct net *net = dev_net(skb->dev); int iif, sdif; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 3498dd1d0694..fd29d21d579c 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -718,7 +718,8 @@ EXPORT_SYMBOL(udp_gro_complete); INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) { - const struct iphdr *iph = ip_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index b41e35af69ea..c8b909a9904f 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -237,6 +237,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, goto out; skb_set_network_header(skb, off); + NAPI_GRO_CB(skb)->inner_network_offset = off; flush += ntohs(iph->payload_len) != skb->len - hlen; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1a4cccdd40c9..8f7aa8bac1e7 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -272,7 +272,8 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { - const struct ipv6hdr *iph = ipv6_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset); struct net *net = dev_net(skb->dev); int iif, sdif; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index bbd347de00b4..b41152dd4246 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -164,7 +164,8 @@ flush: INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) { - const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ -- cgit v1.2.3