From 510c321b557121861601f9d259aadd65aa274f35 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 14 Feb 2018 19:06:02 +0800 Subject: xfrm: reuse uncached_list to track xdsts In early time, when freeing a xdst, it would be inserted into dst_garbage.list first. Then if it's refcnt was still held somewhere, later it would be put into dst_busy_list in dst_gc_task(). When one dev was being unregistered, the dev of these dsts in dst_busy_list would be set with loopback_dev and put this dev. So that this dev's removal wouldn't get blocked, and avoid the kmsg warning: kernel:unregister_netdevice: waiting for veth0 to become \ free. Usage count = 2 However after Commit 52df157f17e5 ("xfrm: take refcnt of dst when creating struct xfrm_dst bundle"), the xdst will not be freed with dst gc, and this warning happens. To fix it, we need to find these xdsts that are still held by others when removing the dev, and free xdst's dev and set it with loopback_dev. But unfortunately after flow_cache for xfrm was deleted, no list tracks them anymore. So we need to save these xdsts somewhere to release the xdst's dev later. To make this easier, this patch is to reuse uncached_list to track xdsts, so that the dev refcnt can be released in the event NETDEV_UNREGISTER process of fib_netdev_notifier. Thanks to Florian, we could move forward this fix quickly. Fixes: 52df157f17e5 ("xfrm: take refcnt of dst when creating struct xfrm_dst bundle") Reported-by: Jianlin Shi Reported-by: Hangbin Liu Tested-by: Eyal Birger Signed-off-by: Xin Long Signed-off-by: Steffen Klassert --- include/net/ip6_route.h | 3 +++ include/net/route.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/net') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 27d23a65f3cd..ac0866bb9e93 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -179,6 +179,9 @@ void rt6_disable_ip(struct net_device *dev, unsigned long event); void rt6_sync_down_dev(struct net_device *dev, unsigned long event); void rt6_multipath_rebalance(struct rt6_info *rt); +void rt6_uncached_list_add(struct rt6_info *rt); +void rt6_uncached_list_del(struct rt6_info *rt); + static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { const struct dst_entry *dst = skb_dst(skb); diff --git a/include/net/route.h b/include/net/route.h index 1eb9ce470e25..40b870d58f38 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -227,6 +227,9 @@ struct in_ifaddr; void fib_add_ifaddr(struct in_ifaddr *); void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *); +void rt_add_uncached_list(struct rtable *rt); +void rt_del_uncached_list(struct rtable *rt); + static inline void ip_rt_put(struct rtable *rt) { /* dst_release() accepts a NULL parameter. -- cgit v1.2.3 From 15f35d49c93f4fa9875235e7bf3e3783d2dd7a1b Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Thu, 15 Feb 2018 20:18:43 +0300 Subject: udplite: fix partial checksum initialization Since UDP-Lite is always using checksum, the following path is triggered when calculating pseudo header for it: udp4_csum_init() or udp6_csum_init() skb_checksum_init_zero_check() __skb_checksum_validate_complete() The problem can appear if skb->len is less than CHECKSUM_BREAK. In this particular case __skb_checksum_validate_complete() also invokes __skb_checksum_complete(skb). If UDP-Lite is using partial checksum that covers only part of a packet, the function will return bad checksum and the packet will be dropped. It can be fixed if we skip skb_checksum_init_zero_check() and only set the required pseudo header checksum for UDP-Lite with partial checksum before udp4_csum_init()/udp6_csum_init() functions return. Fixes: ed70fcfcee95 ("net: Call skb_checksum_init in IPv4") Fixes: e4f45b7f40bd ("net: Call skb_checksum_init in IPv6") Signed-off-by: Alexey Kodanev Signed-off-by: David S. Miller --- include/net/udplite.h | 1 + net/ipv4/udp.c | 5 +++++ net/ipv6/ip6_checksum.c | 5 +++++ 3 files changed, 11 insertions(+) (limited to 'include/net') diff --git a/include/net/udplite.h b/include/net/udplite.h index 81bdbf97319b..9185e45b997f 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -64,6 +64,7 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) UDP_SKB_CB(skb)->cscov = cscov; if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; + skb->csum_valid = 0; } return 0; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index bfaefe560b5c..e5ef7c38c934 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2024,6 +2024,11 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, err = udplite_checksum_init(skb, uh); if (err) return err; + + if (UDP_SKB_CB(skb)->partial_cov) { + skb->csum = inet_compute_pseudo(skb, proto); + return 0; + } } /* Note, we are only interested in != 0 or == 0, thus the diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c index ec43d18b5ff9..547515e8450a 100644 --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -73,6 +73,11 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) err = udplite_checksum_init(skb, uh); if (err) return err; + + if (UDP_SKB_CB(skb)->partial_cov) { + skb->csum = ip6_compute_pseudo(skb, proto); + return 0; + } } /* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels) -- cgit v1.2.3 From 651b9920d7a694ffb1f885aef2bbb068a25d9d66 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Sat, 10 Feb 2018 13:20:34 +0100 Subject: mac80211: round IEEE80211_TX_STATUS_HEADROOM up to multiple of 4 This ensures that mac80211 allocated management frames are properly aligned, which makes copying them more efficient. For instance, mt76 uses iowrite32_copy to copy beacon frames to beacon template memory on the chip. Misaligned 32-bit accesses cause CPU exceptions on MIPS and should be avoided. Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index eec143cca1c0..c9077a832977 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -4141,7 +4141,7 @@ void ieee80211_sta_uapsd_trigger(struct ieee80211_sta *sta, u8 tid); * The TX headroom reserved by mac80211 for its own tx_status functions. * This is enough for the radiotap header. */ -#define IEEE80211_TX_STATUS_HEADROOM 14 +#define IEEE80211_TX_STATUS_HEADROOM ALIGN(14, 4) /** * ieee80211_sta_set_buffered - inform mac80211 about driver-buffered frames -- cgit v1.2.3 From 657308f73e674e86b60509a430a46e569bf02846 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 22 Feb 2018 20:55:28 +0100 Subject: regulatory: add NUL to request alpha2 Similar to the ancient commit a5fe8e7695dc ("regulatory: add NUL to alpha2"), add another byte to alpha2 in the request struct so that when we use nla_put_string(), we don't overrun anything. Fixes: 73d54c9e74c4 ("cfg80211: add regulatory netlink multicast group") Reported-by: Kees Cook Signed-off-by: Johannes Berg --- include/net/regulatory.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/regulatory.h b/include/net/regulatory.h index ebc5a2ed8631..f83cacce3308 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -78,7 +78,7 @@ struct regulatory_request { int wiphy_idx; enum nl80211_reg_initiator initiator; enum nl80211_user_reg_hint_type user_reg_hint_type; - char alpha2[2]; + char alpha2[3]; enum nl80211_dfs_regions dfs_region; bool intersect; bool processed; -- cgit v1.2.3 From 77d270967c5f723e5910dd073962b6372d7ef466 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 28 Feb 2018 13:12:09 +0100 Subject: mlxsw: spectrum: Fix handling of resource_size_param Current code uses global variables, adjusts them and passes pointer down to devlink. With every other mlxsw_core instance, the previously passed pointer values are rewritten. Fix this by de-globalize the variables and also memcpy size_params during devlink resource registration. Also, introduce a convenient size_param_init helper. Fixes: ef3116e5403e ("mlxsw: spectrum: Register KVD resources with devlink") Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 75 +++++++++++++------------- include/net/devlink.h | 18 +++++-- net/core/devlink.c | 7 +-- 3 files changed, 57 insertions(+), 43 deletions(-) (limited to 'include/net') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3dcc58d61506..c364a1ace75d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4207,13 +4207,12 @@ static struct devlink_resource_ops mlxsw_sp_resource_kvd_hash_double_ops = { .size_validate = mlxsw_sp_resource_kvd_hash_double_size_validate, }; -static struct devlink_resource_size_params mlxsw_sp_kvd_size_params; -static struct devlink_resource_size_params mlxsw_sp_linear_size_params; -static struct devlink_resource_size_params mlxsw_sp_hash_single_size_params; -static struct devlink_resource_size_params mlxsw_sp_hash_double_size_params; - static void -mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core) +mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core, + struct devlink_resource_size_params *kvd_size_params, + struct devlink_resource_size_params *linear_size_params, + struct devlink_resource_size_params *hash_double_size_params, + struct devlink_resource_size_params *hash_single_size_params) { u32 single_size_min = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE); @@ -4222,37 +4221,35 @@ mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core) u32 kvd_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE); u32 linear_size_min = 0; - /* KVD top resource */ - mlxsw_sp_kvd_size_params.size_min = kvd_size; - mlxsw_sp_kvd_size_params.size_max = kvd_size; - mlxsw_sp_kvd_size_params.size_granularity = MLXSW_SP_KVD_GRANULARITY; - mlxsw_sp_kvd_size_params.unit = DEVLINK_RESOURCE_UNIT_ENTRY; - - /* Linear part init */ - mlxsw_sp_linear_size_params.size_min = linear_size_min; - mlxsw_sp_linear_size_params.size_max = kvd_size - single_size_min - - double_size_min; - mlxsw_sp_linear_size_params.size_granularity = MLXSW_SP_KVD_GRANULARITY; - mlxsw_sp_linear_size_params.unit = DEVLINK_RESOURCE_UNIT_ENTRY; - - /* Hash double part init */ - mlxsw_sp_hash_double_size_params.size_min = double_size_min; - mlxsw_sp_hash_double_size_params.size_max = kvd_size - single_size_min - - linear_size_min; - mlxsw_sp_hash_double_size_params.size_granularity = MLXSW_SP_KVD_GRANULARITY; - mlxsw_sp_hash_double_size_params.unit = DEVLINK_RESOURCE_UNIT_ENTRY; - - /* Hash single part init */ - mlxsw_sp_hash_single_size_params.size_min = single_size_min; - mlxsw_sp_hash_single_size_params.size_max = kvd_size - double_size_min - - linear_size_min; - mlxsw_sp_hash_single_size_params.size_granularity = MLXSW_SP_KVD_GRANULARITY; - mlxsw_sp_hash_single_size_params.unit = DEVLINK_RESOURCE_UNIT_ENTRY; + devlink_resource_size_params_init(kvd_size_params, kvd_size, kvd_size, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); + devlink_resource_size_params_init(linear_size_params, linear_size_min, + kvd_size - single_size_min - + double_size_min, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); + devlink_resource_size_params_init(hash_double_size_params, + double_size_min, + kvd_size - single_size_min - + linear_size_min, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); + devlink_resource_size_params_init(hash_single_size_params, + single_size_min, + kvd_size - double_size_min - + linear_size_min, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); } static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) { struct devlink *devlink = priv_to_devlink(mlxsw_core); + struct devlink_resource_size_params hash_single_size_params; + struct devlink_resource_size_params hash_double_size_params; + struct devlink_resource_size_params linear_size_params; + struct devlink_resource_size_params kvd_size_params; u32 kvd_size, single_size, double_size, linear_size; const struct mlxsw_config_profile *profile; int err; @@ -4261,13 +4258,17 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) if (!MLXSW_CORE_RES_VALID(mlxsw_core, KVD_SIZE)) return -EIO; - mlxsw_sp_resource_size_params_prepare(mlxsw_core); + mlxsw_sp_resource_size_params_prepare(mlxsw_core, &kvd_size_params, + &linear_size_params, + &hash_double_size_params, + &hash_single_size_params); + kvd_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE); err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD, true, kvd_size, MLXSW_SP_RESOURCE_KVD, DEVLINK_RESOURCE_ID_PARENT_TOP, - &mlxsw_sp_kvd_size_params, + &kvd_size_params, &mlxsw_sp_resource_kvd_ops); if (err) return err; @@ -4277,7 +4278,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) false, linear_size, MLXSW_SP_RESOURCE_KVD_LINEAR, MLXSW_SP_RESOURCE_KVD, - &mlxsw_sp_linear_size_params, + &linear_size_params, &mlxsw_sp_resource_kvd_linear_ops); if (err) return err; @@ -4291,7 +4292,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) false, double_size, MLXSW_SP_RESOURCE_KVD_HASH_DOUBLE, MLXSW_SP_RESOURCE_KVD, - &mlxsw_sp_hash_double_size_params, + &hash_double_size_params, &mlxsw_sp_resource_kvd_hash_double_ops); if (err) return err; @@ -4301,7 +4302,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) false, single_size, MLXSW_SP_RESOURCE_KVD_HASH_SINGLE, MLXSW_SP_RESOURCE_KVD, - &mlxsw_sp_hash_single_size_params, + &hash_single_size_params, &mlxsw_sp_resource_kvd_hash_single_ops); if (err) return err; diff --git a/include/net/devlink.h b/include/net/devlink.h index 6545b03e97f7..4de35ed12bcc 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -257,6 +257,18 @@ struct devlink_resource_size_params { enum devlink_resource_unit unit; }; +static inline void +devlink_resource_size_params_init(struct devlink_resource_size_params *size_params, + u64 size_min, u64 size_max, + u64 size_granularity, + enum devlink_resource_unit unit) +{ + size_params->size_min = size_min; + size_params->size_max = size_max; + size_params->size_granularity = size_granularity; + size_params->unit = unit; +} + /** * struct devlink_resource - devlink resource * @name: name of the resource @@ -278,7 +290,7 @@ struct devlink_resource { u64 size_new; bool size_valid; struct devlink_resource *parent; - struct devlink_resource_size_params *size_params; + struct devlink_resource_size_params size_params; struct list_head list; struct list_head resource_list; const struct devlink_resource_ops *resource_ops; @@ -402,7 +414,7 @@ int devlink_resource_register(struct devlink *devlink, u64 resource_size, u64 resource_id, u64 parent_resource_id, - struct devlink_resource_size_params *size_params, + const struct devlink_resource_size_params *size_params, const struct devlink_resource_ops *resource_ops); void devlink_resources_unregister(struct devlink *devlink, struct devlink_resource *resource); @@ -556,7 +568,7 @@ devlink_resource_register(struct devlink *devlink, u64 resource_size, u64 resource_id, u64 parent_resource_id, - struct devlink_resource_size_params *size_params, + const struct devlink_resource_size_params *size_params, const struct devlink_resource_ops *resource_ops) { return 0; diff --git a/net/core/devlink.c b/net/core/devlink.c index 7b1076dc1292..2f2307d94787 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2379,7 +2379,7 @@ devlink_resource_size_params_put(struct devlink_resource *resource, { struct devlink_resource_size_params *size_params; - size_params = resource->size_params; + size_params = &resource->size_params; if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN, size_params->size_granularity, DEVLINK_ATTR_PAD) || nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX, @@ -3156,7 +3156,7 @@ int devlink_resource_register(struct devlink *devlink, u64 resource_size, u64 resource_id, u64 parent_resource_id, - struct devlink_resource_size_params *size_params, + const struct devlink_resource_size_params *size_params, const struct devlink_resource_ops *resource_ops) { struct devlink_resource *resource; @@ -3199,7 +3199,8 @@ int devlink_resource_register(struct devlink *devlink, resource->id = resource_id; resource->resource_ops = resource_ops; resource->size_valid = true; - resource->size_params = size_params; + memcpy(&resource->size_params, size_params, + sizeof(resource->size_params)); INIT_LIST_HEAD(&resource->resource_list); list_add_tail(&resource->list, resource_list); out: -- cgit v1.2.3 From 35d889d10b649fda66121891ec05eca88150059d Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Mon, 5 Mar 2018 20:52:54 +0300 Subject: sch_netem: fix skb leak in netem_enqueue() When we exceed current packets limit and we have more than one segment in the list returned by skb_gso_segment(), netem drops only the first one, skipping the rest, hence kmemleak reports: unreferenced object 0xffff880b5d23b600 (size 1024): comm "softirq", pid 0, jiffies 4384527763 (age 2770.629s) hex dump (first 32 bytes): 00 80 23 5d 0b 88 ff ff 00 00 00 00 00 00 00 00 ..#]............ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000d8a19b9d>] __alloc_skb+0xc9/0x520 [<000000001709b32f>] skb_segment+0x8c8/0x3710 [<00000000c7b9bb88>] tcp_gso_segment+0x331/0x1830 [<00000000c921cba1>] inet_gso_segment+0x476/0x1370 [<000000008b762dd4>] skb_mac_gso_segment+0x1f9/0x510 [<000000002182660a>] __skb_gso_segment+0x1dd/0x620 [<00000000412651b9>] netem_enqueue+0x1536/0x2590 [sch_netem] [<0000000005d3b2a9>] __dev_queue_xmit+0x1167/0x2120 [<00000000fc5f7327>] ip_finish_output2+0x998/0xf00 [<00000000d309e9d3>] ip_output+0x1aa/0x2c0 [<000000007ecbd3a4>] tcp_transmit_skb+0x18db/0x3670 [<0000000042d2a45f>] tcp_write_xmit+0x4d4/0x58c0 [<0000000056a44199>] tcp_tasklet_func+0x3d9/0x540 [<0000000013d06d02>] tasklet_action+0x1ca/0x250 [<00000000fcde0b8b>] __do_softirq+0x1b4/0x5a3 [<00000000e7ed027c>] irq_exit+0x1e2/0x210 Fix it by adding the rest of the segments, if any, to skb 'to_free' list. Add new __qdisc_drop_all() and qdisc_drop_all() functions because they can be useful in the future if we need to drop segmented GSO packets in other places. Fixes: 6071bd1aa13e ("netem: Segment GSO packets on enqueue") Signed-off-by: Alexey Kodanev Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/net/sch_generic.h | 19 +++++++++++++++++++ net/sched/sch_netem.c | 2 +- 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index e2ab13687fb9..2092d33194dd 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -824,6 +824,16 @@ static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free) *to_free = skb; } +static inline void __qdisc_drop_all(struct sk_buff *skb, + struct sk_buff **to_free) +{ + if (skb->prev) + skb->prev->next = *to_free; + else + skb->next = *to_free; + *to_free = skb; +} + static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, struct qdisc_skb_head *qh, struct sk_buff **to_free) @@ -956,6 +966,15 @@ static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch, return NET_XMIT_DROP; } +static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + __qdisc_drop_all(skb, to_free); + qdisc_qstats_drop(sch); + + return NET_XMIT_DROP; +} + /* Length to Time (L2T) lookup in a qdisc_rate_table, to determine how long it will take to send a packet given its size. */ diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 7c179addebcd..7d6801fc5340 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -509,7 +509,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, } if (unlikely(sch->q.qlen >= sch->limit)) - return qdisc_drop(skb, sch, to_free); + return qdisc_drop_all(skb, sch, to_free); qdisc_qstats_backlog_inc(sch, skb); -- cgit v1.2.3 From bf2ae2e4bf9360e07c0cdfa166bcdc0afd92f4ce Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 10 Mar 2018 18:57:50 +0800 Subject: sock_diag: request _diag module only when the family or proto has been registered Now when using 'ss' in iproute, kernel would try to load all _diag modules, which also causes corresponding family and proto modules to be loaded as well due to module dependencies. Like after running 'ss', sctp, dccp, af_packet (if it works as a module) would be loaded. For example: $ lsmod|grep sctp $ ss $ lsmod|grep sctp sctp_diag 16384 0 sctp 323584 5 sctp_diag inet_diag 24576 4 raw_diag,tcp_diag,sctp_diag,udp_diag libcrc32c 16384 3 nf_conntrack,nf_nat,sctp As these family and proto modules are loaded unintentionally, it could cause some problems, like: - Some debug tools use 'ss' to collect the socket info, which loads all those diag and family and protocol modules. It's noisy for identifying issues. - Users usually expect to drop sctp init packet silently when they have no sense of sctp protocol instead of sending abort back. - It wastes resources (especially with multiple netns), and SCTP module can't be unloaded once it's loaded. ... In short, it's really inappropriate to have these family and proto modules loaded unexpectedly when just doing debugging with inet_diag. This patch is to introduce sock_load_diag_module() where it loads the _diag module only when it's corresponding family or proto has been already registered. Note that we can't just load _diag module without the family or proto loaded, as some symbols used in _diag module are from the family or proto module. v1->v2: - move inet proto check to inet_diag to avoid a compiling err. v2->v3: - define sock_load_diag_module in sock.c and export one symbol only. - improve the changelog. Reported-by: Sabrina Dubroca Acked-by: Marcelo Ricardo Leitner Acked-by: Phil Sutter Acked-by: Sabrina Dubroca Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/net.h | 1 + include/net/sock.h | 1 + net/core/sock.c | 21 +++++++++++++++++++++ net/core/sock_diag.c | 12 ++++-------- net/ipv4/inet_diag.c | 3 +-- net/socket.c | 5 +++++ 6 files changed, 33 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/include/linux/net.h b/include/linux/net.h index 91216b16feb7..2a0391eea05c 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -222,6 +222,7 @@ enum { int sock_wake_async(struct socket_wq *sk_wq, int how, int band); int sock_register(const struct net_proto_family *fam); void sock_unregister(int family); +bool sock_is_registered(int family); int __sock_create(struct net *net, int family, int type, int proto, struct socket **res, int kern); int sock_create(int family, int type, int proto, struct socket **res); diff --git a/include/net/sock.h b/include/net/sock.h index 169c92afcafa..ae23f3b389ca 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1137,6 +1137,7 @@ struct proto { int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); +int sock_load_diag_module(int family, int protocol); #ifdef SOCK_REFCNT_DEBUG static inline void sk_refcnt_debug_inc(struct sock *sk) diff --git a/net/core/sock.c b/net/core/sock.c index c501499a04fe..85b0b64e7f9d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3261,6 +3261,27 @@ void proto_unregister(struct proto *prot) } EXPORT_SYMBOL(proto_unregister); +int sock_load_diag_module(int family, int protocol) +{ + if (!protocol) { + if (!sock_is_registered(family)) + return -ENOENT; + + return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, family); + } + +#ifdef CONFIG_INET + if (family == AF_INET && + !rcu_access_pointer(inet_protos[protocol])) + return -ENOENT; +#endif + + return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, family, protocol); +} +EXPORT_SYMBOL(sock_load_diag_module); + #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) __acquires(proto_list_mutex) diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 146b50e30659..c37b5be7c5e4 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -220,8 +220,7 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; if (sock_diag_handlers[req->sdiag_family] == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, req->sdiag_family); + sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[req->sdiag_family]; @@ -247,8 +246,7 @@ static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, case TCPDIAG_GETSOCK: case DCCPDIAG_GETSOCK: if (inet_rcv_compat == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + sock_load_diag_module(AF_INET, 0); mutex_lock(&sock_diag_table_mutex); if (inet_rcv_compat != NULL) @@ -281,14 +279,12 @@ static int sock_diag_bind(struct net *net, int group) case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: if (!sock_diag_handlers[AF_INET]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: if (!sock_diag_handlers[AF_INET6]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET6); + sock_load_diag_module(AF_INET6, 0); break; } return 0; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index a383f299ce24..4e5bc4b2f14e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -53,8 +53,7 @@ static DEFINE_MUTEX(inet_diag_table_mutex); static const struct inet_diag_handler *inet_diag_lock_handler(int proto) { if (!inet_diag_table[proto]) - request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET, proto); + sock_load_diag_module(AF_INET, proto); mutex_lock(&inet_diag_table_mutex); if (!inet_diag_table[proto]) diff --git a/net/socket.c b/net/socket.c index a93c99b518ca..08847c3b8c39 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2587,6 +2587,11 @@ void sock_unregister(int family) } EXPORT_SYMBOL(sock_unregister); +bool sock_is_registered(int family) +{ + return family < NPROTO && rcu_access_pointer(net_families[family]); +} + static int __init sock_init(void) { int err; -- cgit v1.2.3 From d52e5a7e7ca49457dd31fc8b42fb7c0d58a31221 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Wed, 14 Mar 2018 10:21:14 +0100 Subject: ipv4: lock mtu in fnhe when received PMTU < net.ipv4.route.min_pmtu Prior to the rework of PMTU information storage in commit 2c8cec5c10bc ("ipv4: Cache learned PMTU information in inetpeer."), when a PMTU event advertising a PMTU smaller than net.ipv4.route.min_pmtu was received, we would disable setting the DF flag on packets by locking the MTU metric, and set the PMTU to net.ipv4.route.min_pmtu. Since then, we don't disable DF, and set PMTU to net.ipv4.route.min_pmtu, so the intermediate router that has this link with a small MTU will have to drop the packets. This patch reestablishes pre-2.6.39 behavior by splitting rtable->rt_pmtu into a bitfield with rt_mtu_locked and rt_pmtu. rt_mtu_locked indicates that we shouldn't set the DF bit on that path, and is checked in ip_dont_fragment(). One possible workaround is to set net.ipv4.route.min_pmtu to a value low enough to accommodate the lowest MTU encountered. Fixes: 2c8cec5c10bc ("ipv4: Cache learned PMTU information in inetpeer.") Signed-off-by: Sabrina Dubroca Reviewed-by: Stefano Brivio Signed-off-by: David S. Miller --- include/net/ip.h | 11 +++++++++-- include/net/ip_fib.h | 1 + include/net/route.h | 3 ++- net/ipv4/route.c | 26 +++++++++++++++++++------- net/ipv4/xfrm4_policy.c | 1 + 5 files changed, 32 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/include/net/ip.h b/include/net/ip.h index 746abff9ce51..f49b3a576bec 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -328,6 +328,13 @@ int ip_decrease_ttl(struct iphdr *iph) return --iph->ttl; } +static inline int ip_mtu_locked(const struct dst_entry *dst) +{ + const struct rtable *rt = (const struct rtable *)dst; + + return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU); +} + static inline int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) { @@ -335,7 +342,7 @@ int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) return pmtudisc == IP_PMTUDISC_DO || (pmtudisc == IP_PMTUDISC_WANT && - !(dst_metric_locked(dst, RTAX_MTU))); + !ip_mtu_locked(dst)); } static inline bool ip_sk_accept_pmtu(const struct sock *sk) @@ -361,7 +368,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, struct net *net = dev_net(dst->dev); if (net->ipv4.sysctl_ip_fwd_use_pmtu || - dst_metric_locked(dst, RTAX_MTU) || + ip_mtu_locked(dst) || !forwarding) return dst_mtu(dst); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index f80524396c06..77d0a78cf7d2 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -59,6 +59,7 @@ struct fib_nh_exception { int fnhe_genid; __be32 fnhe_daddr; u32 fnhe_pmtu; + bool fnhe_mtu_locked; __be32 fnhe_gw; unsigned long fnhe_expires; struct rtable __rcu *fnhe_rth_input; diff --git a/include/net/route.h b/include/net/route.h index 40b870d58f38..20a92ca9e115 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -63,7 +63,8 @@ struct rtable { __be32 rt_gateway; /* Miscellaneous cached information */ - u32 rt_pmtu; + u32 rt_mtu_locked:1, + rt_pmtu:31; u32 rt_table_id; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f9dbb8cb66bf..299e247b2032 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -634,6 +634,7 @@ static inline u32 fnhe_hashfun(__be32 daddr) static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) { rt->rt_pmtu = fnhe->fnhe_pmtu; + rt->rt_mtu_locked = fnhe->fnhe_mtu_locked; rt->dst.expires = fnhe->fnhe_expires; if (fnhe->fnhe_gw) { @@ -644,7 +645,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh } static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, - u32 pmtu, unsigned long expires) + u32 pmtu, bool lock, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; @@ -681,8 +682,10 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; - if (pmtu) + if (pmtu) { fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; + } fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); @@ -706,6 +709,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = expires; /* Exception created; mark the cached routes for the nexthop @@ -787,7 +791,8 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, jiffies + ip_rt_gc_timeout); + 0, false, + jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -1009,15 +1014,18 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; struct fib_result res; + bool lock = false; - if (dst_metric_locked(dst, RTAX_MTU)) + if (ip_mtu_locked(dst)) return; if (ipv4_mtu(dst) < mtu) return; - if (mtu < ip_rt_min_pmtu) + if (mtu < ip_rt_min_pmtu) { + lock = true; mtu = ip_rt_min_pmtu; + } if (rt->rt_pmtu == mtu && time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) @@ -1027,7 +1035,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { struct fib_nh *nh = &FIB_RES_NH(res); - update_or_create_fnhe(nh, fl4->daddr, 0, mtu, + update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } rcu_read_unlock(); @@ -1280,7 +1288,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = READ_ONCE(dst->dev->mtu); - if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { + if (unlikely(ip_mtu_locked(dst))) { if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } @@ -1521,6 +1529,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_is_input = 0; rt->rt_iif = 0; rt->rt_pmtu = 0; + rt->rt_mtu_locked = 0; rt->rt_gateway = 0; rt->rt_uses_gateway = 0; rt->rt_table_id = 0; @@ -2546,6 +2555,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; + rt->rt_mtu_locked = ort->rt_mtu_locked; rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; @@ -2648,6 +2658,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; + if (rt->rt_mtu_locked && expires) + metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU); if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 8d33f7b311f4..fbebda67ac1b 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,6 +100,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_gateway = rt->rt_gateway; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; + xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; xdst->u.rt.rt_table_id = rt->rt_table_id; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); rt_add_uncached_list(&xdst->u.rt); -- cgit v1.2.3 From 7c181f4fcdc62e5dc7a87fd33387d322262c3b52 Mon Sep 17 00:00:00 2001 From: Ben Caradoc-Davies Date: Mon, 19 Mar 2018 12:57:44 +1300 Subject: mac80211: add ieee80211_hw flag for QoS NDP support Commit 7b6ddeaf27ec ("mac80211: use QoS NDP for AP probing") added an argument qos_ok to ieee80211_nullfunc_get to support QoS NDP. Despite the claim in the commit log "Change all the drivers to *not* allow QoS NDP for now, even though it looks like most of them should be OK with that", this commit enables QoS NDP in response to beacons (see change to mlme.c:ieee80211_send_nullfunc), causing ath9k_htc to lose IP connectivity. See: https://patchwork.kernel.org/patch/10241109/ https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=891060 Introduce a hardware flag to allow such buggy drivers to override the correct default behaviour of mac80211 of sending QoS NDP packets. Signed-off-by: Ben Caradoc-Davies Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++++ net/mac80211/debugfs.c | 1 + net/mac80211/mlme.c | 3 ++- 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c96511fa9198..2b581bd93812 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2063,6 +2063,9 @@ struct ieee80211_txq { * @IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA: Hardware supports buffer STA on * TDLS links. * + * @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't + * support QoS NDP for AP probing - that's most likely a driver bug. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2106,6 +2109,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_REPORTS_LOW_ACK, IEEE80211_HW_SUPPORTS_TX_FRAG, IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA, + IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 1f466d12a6bc..94c7ee9df33b 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -212,6 +212,7 @@ static const char *hw_flag_names[] = { FLAG(REPORTS_LOW_ACK), FLAG(SUPPORTS_TX_FRAG), FLAG(SUPPORTS_TDLS_BUFFER_STA), + FLAG(DOESNT_SUPPORT_QOS_NDP), #undef FLAG }; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 39b660b9a908..5f303abac5ad 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -896,7 +896,8 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, struct ieee80211_hdr_3addr *nullfunc; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, true); + skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, + !ieee80211_hw_check(&local->hw, DOESNT_SUPPORT_QOS_NDP)); if (!skb) return; -- cgit v1.2.3