From e115f2d89253490fb2dbf304b627f8d908df26f1 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 15 Apr 2008 14:34:37 -0700 Subject: [PATCH] memcg: fix oops in oom handling When I used a test program to fork mass processes and immediately move them to a cgroup where the memory limit is low enough to trigger oom kill, I got oops: BUG: unable to handle kernel NULL pointer dereference at 0000000000000808 IP: [] _spin_lock_irqsave+0x8/0x18 PGD 4c95f067 PUD 4406c067 PMD 0 Oops: 0002 [1] SMP CPU 2 Modules linked in: Pid: 11973, comm: a.out Not tainted 2.6.25-rc7 #5 RIP: 0010:[] [] _spin_lock_irqsave+0x8/0x18 RSP: 0018:ffff8100448c7c30 EFLAGS: 00010002 RAX: 0000000000000202 RBX: 0000000000000009 RCX: 000000000001c9f3 RDX: 0000000000000100 RSI: 0000000000000001 RDI: 0000000000000808 RBP: ffff81007e444080 R08: 0000000000000000 R09: ffff8100448c7900 R10: ffff81000105f480 R11: 00000100ffffffff R12: ffff810067c84140 R13: 0000000000000001 R14: ffff8100441d0018 R15: ffff81007da56200 FS: 00007f70eb1856f0(0000) GS:ffff81007fbad3c0(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000808 CR3: 000000004498a000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process a.out (pid: 11973, threadinfo ffff8100448c6000, task ffff81007da533e0) Stack: ffffffff8023ef5a 00000000000000d0 ffffffff80548dc0 00000000000000d0 ffff810067c84140 ffff81007e444080 ffffffff8026cef9 00000000000000d0 ffff8100441d0000 00000000000000d0 ffff8100441d0000 ffff8100505445c0 Call Trace: [] ? force_sig_info+0x25/0xb9 [] ? oom_kill_task+0x77/0xe2 [] ? mem_cgroup_out_of_memory+0x55/0x67 [] ? mem_cgroup_charge_common+0xec/0x202 [] ? handle_mm_fault+0x24e/0x77f [] ? default_wake_function+0x0/0xe [] ? get_user_pages+0x2ce/0x3af [] ? mem_cgroup_charge_common+0x2d/0x202 [] ? make_pages_present+0x8e/0xa4 [] ? mmap_region+0x373/0x429 [] ? do_mmap_pgoff+0x2ff/0x364 [] ? sys_mmap+0xe5/0x111 [] ? tracesys+0xdc/0xe1 Code: 00 00 01 48 8b 3c 24 e9 46 d4 dd ff f0 ff 07 48 8b 3c 24 e9 3a d4 dd ff fe 07 48 8b 3c 24 e9 2f d4 dd ff 9c 58 fa ba 00 01 00 00 66 0f c1 17 38 f2 74 06 f3 90 8a 17 eb f6 c3 fa b8 00 01 00 RIP [] _spin_lock_irqsave+0x8/0x18 RSP CR2: 0000000000000808 ---[ end trace c3702fa668021ea4 ]--- It's reproducable in a x86_64 box, but doesn't happen in x86_32. This is because tsk->sighand is not guarded by RCU, so we have to hold tasklist_lock, just as what out_of_memory() does. Signed-off-by: Li Zefan Cc: KAMEZAWA Hiroyuki Acked-by: Balbir Singh Cc: Pavel Emelianov Cc: Paul Menage Cc: Oleg Nesterov Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/oom_kill.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f255eda693..beb592fe93 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -423,7 +423,7 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask) struct task_struct *p; cgroup_lock(); - rcu_read_lock(); + read_lock(&tasklist_lock); retry: p = select_bad_process(&points, mem); if (PTR_ERR(p) == -1UL) @@ -436,7 +436,7 @@ retry: "Memory cgroup out of memory")) goto retry; out: - rcu_read_unlock(); + read_unlock(&tasklist_lock); cgroup_unlock(); } #endif -- 2.39.5