Commit b0ba2d0f authored by Tetsuo Handa's avatar Tetsuo Handa Committed by Linus Torvalds

mm/page_io.c: fix oops during block io poll in swapin path

When a thread is OOM-killed during swap_readpage() operation, an oops
occurs because end_swap_bio_read() is calling wake_up_process() based on
an assumption that the thread which called swap_readpage() is still
alive.

  Out of memory: Kill process 525 (polkitd) score 0 or sacrifice child
  Killed process 525 (polkitd) total-vm:528128kB, anon-rss:0kB, file-rss:4kB, shmem-rss:0kB
  oom_reaper: reaped process 525 (polkitd), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB
  general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC
  Modules linked in: nf_conntrack_netbios_ns nf_conntrack_broadcast ip6t_rpfilter ipt_REJECT nf_reject_ipv4 ip6t_REJECT nf_reject_ipv6 xt_conntrack ip_set nfnetlink ebtable_nat ebtable_broute bridge stp llc ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_raw iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_raw ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter coretemp ppdev pcspkr vmw_balloon sg shpchp vmw_vmci parport_pc parport i2c_piix4 ip_tables xfs libcrc32c sd_mod sr_mod cdrom ata_generic pata_acpi vmwgfx ahci libahci drm_kms_helper ata_piix syscopyarea sysfillrect sysimgblt fb_sys_fops mptspi scsi_transport_spi ttm e1000 mptscsih drm mptbase i2c_core libata serio_raw
  CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.13.0-rc2-next-20170725 #129
  Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/31/2013
  task: ffffffffb7c16500 task.stack: ffffffffb7c00000
  RIP: 0010:__lock_acquire+0x151/0x12f0
  Call Trace:
   <IRQ>
   lock_acquire+0x59/0x80
   _raw_spin_lock_irqsave+0x3b/0x4f
   try_to_wake_up+0x3b/0x410
   wake_up_process+0x10/0x20
   end_swap_bio_read+0x6f/0xf0
   bio_endio+0x92/0xb0
   blk_update_request+0x88/0x270
   scsi_end_request+0x32/0x1c0
   scsi_io_completion+0x209/0x680
   scsi_finish_command+0xd4/0x120
   scsi_softirq_done+0x120/0x140
   __blk_mq_complete_request_remote+0xe/0x10
   flush_smp_call_function_queue+0x51/0x120
   generic_smp_call_function_single_interrupt+0xe/0x20
   smp_trace_call_function_single_interrupt+0x22/0x30
   smp_call_function_single_interrupt+0x9/0x10
   call_function_single_interrupt+0xa7/0xb0
   </IRQ>
  RIP: 0010:native_safe_halt+0x6/0x10
   default_idle+0xe/0x20
   arch_cpu_idle+0xa/0x10
   default_idle_call+0x1e/0x30
   do_idle+0x187/0x200
   cpu_startup_entry+0x6e/0x70
   rest_init+0xd0/0xe0
   start_kernel+0x456/0x477
   x86_64_start_reservations+0x24/0x26
   x86_64_start_kernel+0xf7/0x11a
   secondary_startup_64+0xa5/0xa5
  Code: c3 49 81 3f 20 9e 0b b8 41 bc 00 00 00 00 44 0f 45 e2 83 fe 01 0f 87 62 ff ff ff 89 f0 49 8b 44 c7 08 48 85 c0 0f 84 52 ff ff ff <f0> ff 80 98 01 00 00 8b 3d 5a 49 c4 01 45 8b b3 18 0c 00 00 85
  RIP: __lock_acquire+0x151/0x12f0 RSP: ffffa01f39e03c50
  ---[ end trace 6c441db499169b1e ]---
  Kernel panic - not syncing: Fatal exception in interrupt
  Kernel Offset: 0x36000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
  ---[ end Kernel panic - not syncing: Fatal exception in interrupt

Fix it by holding a reference to the thread.

[akpm@linux-foundation.org: add comment]
Fixes: 23955622 ("swap: add block io poll in swapin path")
Signed-off-by: default avatarTetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reviewed-by: default avatarShaohua Li <shli@fb.com>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 3189c820
...@@ -22,6 +22,7 @@ ...@@ -22,6 +22,7 @@
#include <linux/frontswap.h> #include <linux/frontswap.h>
#include <linux/blkdev.h> #include <linux/blkdev.h>
#include <linux/uio.h> #include <linux/uio.h>
#include <linux/sched/task.h>
#include <asm/pgtable.h> #include <asm/pgtable.h>
static struct bio *get_swap_bio(gfp_t gfp_flags, static struct bio *get_swap_bio(gfp_t gfp_flags,
...@@ -136,6 +137,7 @@ static void end_swap_bio_read(struct bio *bio) ...@@ -136,6 +137,7 @@ static void end_swap_bio_read(struct bio *bio)
WRITE_ONCE(bio->bi_private, NULL); WRITE_ONCE(bio->bi_private, NULL);
bio_put(bio); bio_put(bio);
wake_up_process(waiter); wake_up_process(waiter);
put_task_struct(waiter);
} }
int generic_swapfile_activate(struct swap_info_struct *sis, int generic_swapfile_activate(struct swap_info_struct *sis,
...@@ -378,6 +380,11 @@ int swap_readpage(struct page *page, bool do_poll) ...@@ -378,6 +380,11 @@ int swap_readpage(struct page *page, bool do_poll)
goto out; goto out;
} }
bdev = bio->bi_bdev; bdev = bio->bi_bdev;
/*
* Keep this task valid during swap readpage because the oom killer may
* attempt to access it in the page fault retry time check.
*/
get_task_struct(current);
bio->bi_private = current; bio->bi_private = current;
bio_set_op_attrs(bio, REQ_OP_READ, 0); bio_set_op_attrs(bio, REQ_OP_READ, 0);
count_vm_event(PSWPIN); count_vm_event(PSWPIN);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment