mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 02:39:48 +00:00
![Michael S. Tsirkin](/assets/img/avatar_default.png)
In 2.6.34-rc1, removing vhost_net module causes an oops in sync_mm_rss (called from do_exit) when workqueue is destroyed. This does not happen on net-next, or with vhost on top of to 2.6.33. The issue seems to be introduced by34e55232e5
("mm: avoid false sharing of mm_counter) which added sync_mm_rss() that is passed task->mm, and dereferences it without checking. If task is a kernel thread, mm might be NULL. I think this might also happen e.g. with aio. This patch fixes the oops by calling sync_mm_rss when task->mm is set to NULL. I also added BUG_ON to detect any other cases where counters get incremented while mm is NULL. The oops I observed looks like this: BUG: unable to handle kernel NULL pointer dereference at 00000000000002a8 IP: [<ffffffff810b436d>] sync_mm_rss+0x33/0x6f PGD 0 Oops: 0002 [#1] SMP last sysfs file: /sys/devices/system/cpu/cpu7/cache/index2/shared_cpu_map CPU 2 Modules linked in: vhost_net(-) tun bridge stp sunrpc ipv6 cpufreq_ondemand acpi_cpufreq freq_table kvm_intel kvm i5000_edac edac_core rtc_cmos bnx2 button i2c_i801 i2c_core rtc_core e1000e sg joydev ide_cd_mod serio_raw pcspkr rtc_lib cdrom virtio_net virtio_blk virtio_pci virtio_ring virtio af_packet e1000 shpchp aacraid uhci_hcd ohci_hcd ehci_hcd [last unloaded: microcode] Pid: 2046, comm: vhost Not tainted 2.6.34-rc1-vhost #25 System Planar/IBM System x3550 -[7978B3G]- RIP: 0010:[<ffffffff810b436d>] [<ffffffff810b436d>] sync_mm_rss+0x33/0x6f RSP: 0018:ffff8802379b7e60 EFLAGS: 00010202 RAX: 0000000000000008 RBX: ffff88023f2390c0 RCX: 0000000000000000 RDX: ffff88023f2396b0 RSI: 0000000000000000 RDI: ffff88023f2390c0 RBP: ffff8802379b7e60 R08: 0000000000000000 R09: 0000000000000000 R10: ffff88023aecfbc0 R11: 0000000000013240 R12: 0000000000000000 R13: ffffffff81051a6c R14: ffffe8ffffc0f540 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff880001e80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00000000000002a8 CR3: 000000023af23000 CR4: 00000000000406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process vhost (pid: 2046, threadinfo ffff8802379b6000, task ffff88023f2390c0) Stack: ffff8802379b7ee0 ffffffff81040687 ffffe8ffffc0f558 ffffffffa00a3e2d <0> 0000000000000000 ffff88023f2390c0 ffffffff81055817 ffff8802379b7e98 <0> ffff8802379b7e98 0000000100000286 ffff8802379b7ee0 ffff88023ad47d78 Call Trace: [<ffffffff81040687>] do_exit+0x147/0x6c4 [<ffffffffa00a3e2d>] ? handle_rx_net+0x0/0x17 [vhost_net] [<ffffffff81055817>] ? autoremove_wake_function+0x0/0x39 [<ffffffff81051a6c>] ? worker_thread+0x0/0x229 [<ffffffff810553c9>] kthreadd+0x0/0xf2 [<ffffffff810038d4>] kernel_thread_helper+0x4/0x10 [<ffffffff81055342>] ? kthread+0x0/0x87 [<ffffffff810038d0>] ? kernel_thread_helper+0x0/0x10 Code: 00 8b 87 6c 02 00 00 85 c0 74 14 48 98 f0 48 01 86 a0 02 00 00 c7 87 6c 02 00 00 00 00 00 00 8b 87 70 02 00 00 85 c0 74 14 48 98 <f0> 48 01 86 a8 02 00 00 c7 87 70 02 00 00 00 00 00 00 8b 87 74 RIP [<ffffffff810b436d>] sync_mm_rss+0x33/0x6f RSP <ffff8802379b7e60> CR2: 00000000000002a8 ---[ end trace 41603ba922beddd2 ]--- Fixing recursive fault but reboot is needed! (note: handle_rx_net is a work item using workqueue in question). sync_mm_rss+0x33/0x6f gave me a hint. I also tried reverting34e55232e5
and the oops goes away. The module in question calls use_mm and later unuse_mm from a kernel thread. It is when this kernel thread is destroyed that the crash happens. Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Andrea Arcangeli <aarcange@redhat.com> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
62 lines
1.4 KiB
C
62 lines
1.4 KiB
C
/* Copyright (C) 2009 Red Hat, Inc.
|
|
*
|
|
* See ../COPYING for licensing terms.
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/mmu_context.h>
|
|
#include <linux/module.h>
|
|
#include <linux/sched.h>
|
|
|
|
#include <asm/mmu_context.h>
|
|
|
|
/*
|
|
* use_mm
|
|
* Makes the calling kernel thread take on the specified
|
|
* mm context.
|
|
* Called by the retry thread execute retries within the
|
|
* iocb issuer's mm context, so that copy_from/to_user
|
|
* operations work seamlessly for aio.
|
|
* (Note: this routine is intended to be called only
|
|
* from a kernel thread context)
|
|
*/
|
|
void use_mm(struct mm_struct *mm)
|
|
{
|
|
struct mm_struct *active_mm;
|
|
struct task_struct *tsk = current;
|
|
|
|
task_lock(tsk);
|
|
active_mm = tsk->active_mm;
|
|
if (active_mm != mm) {
|
|
atomic_inc(&mm->mm_count);
|
|
tsk->active_mm = mm;
|
|
}
|
|
tsk->mm = mm;
|
|
switch_mm(active_mm, mm, tsk);
|
|
task_unlock(tsk);
|
|
|
|
if (active_mm != mm)
|
|
mmdrop(active_mm);
|
|
}
|
|
EXPORT_SYMBOL_GPL(use_mm);
|
|
|
|
/*
|
|
* unuse_mm
|
|
* Reverses the effect of use_mm, i.e. releases the
|
|
* specified mm context which was earlier taken on
|
|
* by the calling kernel thread
|
|
* (Note: this routine is intended to be called only
|
|
* from a kernel thread context)
|
|
*/
|
|
void unuse_mm(struct mm_struct *mm)
|
|
{
|
|
struct task_struct *tsk = current;
|
|
|
|
task_lock(tsk);
|
|
sync_mm_rss(tsk, mm);
|
|
tsk->mm = NULL;
|
|
/* active_mm is still 'mm' */
|
|
enter_lazy_tlb(mm, tsk);
|
|
task_unlock(tsk);
|
|
}
|
|
EXPORT_SYMBOL_GPL(unuse_mm);
|