From 03c57747a7020a28a200e7e920fb48ecdc9b0fb8 Mon Sep 17 00:00:00 2001 From: Robert Shearman Date: Wed, 22 Apr 2015 11:14:37 +0100 Subject: mpls: Per-device MPLS state Add per-device MPLS state to supported interfaces. Use the presence of this state in mpls_route_add to determine that this is a supported interface. Use the presence of mpls_dev to drop packets that arrived on an unsupported interface - previously they were allowed through. Cc: "Eric W. Biederman" Signed-off-by: Robert Shearman Reviewed-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bcbde799ec69..dae106a3a998 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -60,6 +60,7 @@ struct phy_device; struct wireless_dev; /* 802.15.4 specific */ struct wpan_dev; +struct mpls_dev; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -1627,6 +1628,9 @@ struct net_device { void *ax25_ptr; struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; +#if IS_ENABLED(CONFIG_MPLS_ROUTING) + struct mpls_dev __rcu *mpls_ptr; +#endif /* * Cache lines mostly used on receive path (including eth_type_trans()) -- cgit v1.2.3 From ec65aafb9e3f316ff9167289e288856a7d528773 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 23 Apr 2015 12:06:30 +0200 Subject: netdev_alloc_pcpu_stats: use less common iterator variable With the CPU iteration variable called 'i', it's relatively easy to have variable shadowing which sparse will warn about. Avoid that by renaming the variable to __cpu which is less likely to be used in the surrounding context. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dae106a3a998..dbad4d728b4b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2025,10 +2025,10 @@ struct pcpu_sw_netstats { ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \ if (pcpu_stats) { \ - int i; \ - for_each_possible_cpu(i) { \ + int __cpu; \ + for_each_possible_cpu(__cpu) { \ typeof(type) *stat; \ - stat = per_cpu_ptr(pcpu_stats, i); \ + stat = per_cpu_ptr(pcpu_stats, __cpu); \ u64_stats_init(&stat->syncp); \ } \ } \ -- cgit v1.2.3 From 1d8dc3d3c8f1d8ee1da9d54c5d7c8694419ade42 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 23 Apr 2015 16:38:43 +0200 Subject: rhashtable: don't attempt to grow when at max_size The conversion of mac80211's station table to rhashtable had a bug that I found by accident in code review, that hadn't been found as rhashtable apparently managed to have a maximum hash chain length of one (!) in all our testing. In order to test the bug and verify the fix I set my rhashtable's max_size very low (4) in order to force getting hash collisions. At that point, rhashtable WARNed in rhashtable_insert_rehash() but didn't actually reject the hash table insertion. This caused it to lose insertions - my master list of stations would have 9 entries, but the rhashtable only had 5. This may warrant a deeper look, but that WARN_ON() just shouldn't happen. Fix this by not returning true from rht_grow_above_100() when the rhashtable's max_size has been reached - in this case the user is explicitly configuring it to be at most that big, so even if it's now above 100% it shouldn't attempt to resize. This fixes the "lost insertion" issue and consequently allows my code to display its error (and verify my fix for it.) Signed-off-by: Johannes Berg Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index e23d242d1230..dbcbcc59aa92 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -282,7 +282,8 @@ static inline bool rht_shrink_below_30(const struct rhashtable *ht, static inline bool rht_grow_above_100(const struct rhashtable *ht, const struct bucket_table *tbl) { - return atomic_read(&ht->nelems) > tbl->size; + return atomic_read(&ht->nelems) > tbl->size && + (!ht->p.max_size || tbl->size < ht->p.max_size); } /* The bucket lock is selected based on the hash and protects mutations -- cgit v1.2.3 From 2ea2f62c8bda242433809c7f4e9eae1c52c40bbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 24 Apr 2015 16:05:01 -0700 Subject: net: fix crash in build_skb() When I added pfmemalloc support in build_skb(), I forgot netlink was using build_skb() with a vmalloc() area. In this patch I introduce __build_skb() for netlink use, and build_skb() is a wrapper handling both skb->head_frag and skb->pfmemalloc This means netlink no longer has to hack skb->head_frag [ 1567.700067] kernel BUG at arch/x86/mm/physaddr.c:26! [ 1567.700067] invalid opcode: 0000 [#1] PREEMPT SMP KASAN [ 1567.700067] Dumping ftrace buffer: [ 1567.700067] (ftrace buffer empty) [ 1567.700067] Modules linked in: [ 1567.700067] CPU: 9 PID: 16186 Comm: trinity-c182 Not tainted 4.0.0-next-20150424-sasha-00037-g4796e21 #2167 [ 1567.700067] task: ffff880127efb000 ti: ffff880246770000 task.ti: ffff880246770000 [ 1567.700067] RIP: __phys_addr (arch/x86/mm/physaddr.c:26 (discriminator 3)) [ 1567.700067] RSP: 0018:ffff8802467779d8 EFLAGS: 00010202 [ 1567.700067] RAX: 000041000ed8e000 RBX: ffffc9008ed8e000 RCX: 000000000000002c [ 1567.700067] RDX: 0000000000000004 RSI: 0000000000000000 RDI: ffffffffb3fd6049 [ 1567.700067] RBP: ffff8802467779f8 R08: 0000000000000019 R09: ffff8801d0168000 [ 1567.700067] R10: ffff8801d01680c7 R11: ffffed003a02d019 R12: ffffc9000ed8e000 [ 1567.700067] R13: 0000000000000f40 R14: 0000000000001180 R15: ffffc9000ed8e000 [ 1567.700067] FS: 00007f2a7da3f700(0000) GS:ffff8801d1000000(0000) knlGS:0000000000000000 [ 1567.700067] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1567.700067] CR2: 0000000000738308 CR3: 000000022e329000 CR4: 00000000000007e0 [ 1567.700067] Stack: [ 1567.700067] ffffc9000ed8e000 ffff8801d0168000 ffffc9000ed8e000 ffff8801d0168000 [ 1567.700067] ffff880246777a28 ffffffffad7c0a21 0000000000001080 ffff880246777c08 [ 1567.700067] ffff88060d302e68 ffff880246777b58 ffff880246777b88 ffffffffad9a6821 [ 1567.700067] Call Trace: [ 1567.700067] build_skb (include/linux/mm.h:508 net/core/skbuff.c:316) [ 1567.700067] netlink_sendmsg (net/netlink/af_netlink.c:1633 net/netlink/af_netlink.c:2329) [ 1567.774369] ? sched_clock_cpu (kernel/sched/clock.c:311) [ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273) [ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273) [ 1567.774369] sock_sendmsg (net/socket.c:614 net/socket.c:623) [ 1567.774369] sock_write_iter (net/socket.c:823) [ 1567.774369] ? sock_sendmsg (net/socket.c:806) [ 1567.774369] __vfs_write (fs/read_write.c:479 fs/read_write.c:491) [ 1567.774369] ? get_lock_stats (kernel/locking/lockdep.c:249) [ 1567.774369] ? default_llseek (fs/read_write.c:487) [ 1567.774369] ? vtime_account_user (kernel/sched/cputime.c:701) [ 1567.774369] ? rw_verify_area (fs/read_write.c:406 (discriminator 4)) [ 1567.774369] vfs_write (fs/read_write.c:539) [ 1567.774369] SyS_write (fs/read_write.c:586 fs/read_write.c:577) [ 1567.774369] ? SyS_read (fs/read_write.c:577) [ 1567.774369] ? __this_cpu_preempt_check (lib/smp_processor_id.c:63) [ 1567.774369] ? trace_hardirqs_on_caller (kernel/locking/lockdep.c:2594 kernel/locking/lockdep.c:2636) [ 1567.774369] ? trace_hardirqs_on_thunk (arch/x86/lib/thunk_64.S:42) [ 1567.774369] system_call_fastpath (arch/x86/kernel/entry_64.S:261) Fixes: 79930f5892e ("net: do not deplete pfmemalloc reserve") Signed-off-by: Eric Dumazet Reported-by: Sasha Levin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + net/core/skbuff.c | 31 ++++++++++++++++++++++--------- net/netlink/af_netlink.c | 6 ++---- 3 files changed, 25 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 06793b598f44..66e374d62f64 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -773,6 +773,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); +struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 456ead534e10..3cfff2a3d651 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -280,13 +280,14 @@ nodata: EXPORT_SYMBOL(__alloc_skb); /** - * build_skb - build a network buffer + * __build_skb - build a network buffer * @data: data buffer provided by caller - * @frag_size: size of fragment, or 0 if head was kmalloced + * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if - * @frag_size is 0, otherwise data should come from the page allocator. + * @frag_size is 0, otherwise data should come from the page allocator + * or vmalloc() * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : @@ -297,7 +298,7 @@ EXPORT_SYMBOL(__alloc_skb); * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ -struct sk_buff *build_skb(void *data, unsigned int frag_size) +struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; struct sk_buff *skb; @@ -311,11 +312,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) memset(skb, 0, offsetof(struct sk_buff, tail)); skb->truesize = SKB_TRUESIZE(size); - if (frag_size) { - skb->head_frag = 1; - if (virt_to_head_page(data)->pfmemalloc) - skb->pfmemalloc = 1; - } atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -332,6 +328,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) return skb; } + +/* build_skb() is wrapper over __build_skb(), that specifically + * takes care of skb->head and skb->pfmemalloc + * This means that if @frag_size is not zero, then @data must be backed + * by a page fragment, not kmalloc() or vmalloc() + */ +struct sk_buff *build_skb(void *data, unsigned int frag_size) +{ + struct sk_buff *skb = __build_skb(data, frag_size); + + if (skb && frag_size) { + skb->head_frag = 1; + if (virt_to_head_page(data)->pfmemalloc) + skb->pfmemalloc = 1; + } + return skb; +} EXPORT_SYMBOL(build_skb); struct netdev_alloc_cache { diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 19909d0786a2..ec4adbdcb9b4 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1629,13 +1629,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size, if (data == NULL) return NULL; - skb = build_skb(data, size); + skb = __build_skb(data, size); if (skb == NULL) vfree(data); - else { - skb->head_frag = 0; + else skb->destructor = netlink_skb_destructor; - } return skb; } -- cgit v1.2.3