From 2ea2f62c8bda242433809c7f4e9eae1c52c40bbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 24 Apr 2015 16:05:01 -0700 Subject: [PATCH] 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(-) 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 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, 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; } -- GitLab