Revision 6f6acb00514c10be35529402f36ad7a288f08c2e authored by Michal Hocko on 22 May 2014, 18:54:19 UTC, committed by Linus Torvalds on 23 May 2014, 16:37:29 UTC
Commit 284f39afeaa4 ("mm: memcg: push !mm handling out to page cache
charge function") explicitly checks for page cache charges without any
mm context (from kernel thread context[1]).

This seemed to be the only possible case where memory could be charged
without mm context so commit 03583f1a631c ("memcg: remove unnecessary
!mm check from try_get_mem_cgroup_from_mm()") removed the mm check from
get_mem_cgroup_from_mm().  This however caused another NULL ptr
dereference during early boot when loopback kernel thread splices to
tmpfs as reported by Stephan Kulow:

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000360
  IP: get_mem_cgroup_from_mm.isra.42+0x2b/0x60
  Oops: 0000 [#1] SMP
  Modules linked in: btrfs dm_multipath dm_mod scsi_dh multipath raid10 raid456 async_raid6_recov async_memcpy async_pq raid6_pq async_xor xor async_tx raid1 raid0 md_mod parport_pc parport nls_utf8 isofs usb_storage iscsi_ibft iscsi_boot_sysfs arc4 ecb fan thermal nfs lockd fscache nls_iso8859_1 nls_cp437 sg st hid_generic usbhid af_packet sunrpc sr_mod cdrom ata_generic uhci_hcd virtio_net virtio_blk ehci_hcd usbcore ata_piix floppy processor button usb_common virtio_pci virtio_ring virtio edd squashfs loop ppa]
  CPU: 0 PID: 97 Comm: loop1 Not tainted 3.15.0-rc5-5-default #1
  Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  Call Trace:
    __mem_cgroup_try_charge_swapin+0x40/0xe0
    mem_cgroup_charge_file+0x8b/0xd0
    shmem_getpage_gfp+0x66b/0x7b0
    shmem_file_splice_read+0x18f/0x430
    splice_direct_to_actor+0xa2/0x1c0
    do_lo_receive+0x5a/0x60 [loop]
    loop_thread+0x298/0x720 [loop]
    kthread+0xc6/0xe0
    ret_from_fork+0x7c/0xb0

Also Branimir Maksimovic reported the following oops which is tiggered
for the swapcache charge path from the accounting code for kernel threads:

  CPU: 1 PID: 160 Comm: kworker/u8:5 Tainted: P           OE 3.15.0-rc5-core2-custom #159
  Hardware name: System manufacturer System Product Name/MAXIMUSV GENE, BIOS 1903 08/19/2013
  task: ffff880404e349b0 ti: ffff88040486a000 task.ti: ffff88040486a000
  RIP: get_mem_cgroup_from_mm.isra.42+0x2b/0x60
  Call Trace:
    __mem_cgroup_try_charge_swapin+0x45/0xf0
    mem_cgroup_charge_file+0x9c/0xe0
    shmem_getpage_gfp+0x62c/0x770
    shmem_write_begin+0x38/0x40
    generic_perform_write+0xc5/0x1c0
    __generic_file_aio_write+0x1d1/0x3f0
    generic_file_aio_write+0x4f/0xc0
    do_sync_write+0x5a/0x90
    do_acct_process+0x4b1/0x550
    acct_process+0x6d/0xa0
    do_exit+0x827/0xa70
    kthread+0xc3/0xf0

This patch fixes the issue by reintroducing mm check into
get_mem_cgroup_from_mm.  We could do the same trick in
__mem_cgroup_try_charge_swapin as we do for the regular page cache path
but it is not worth troubles.  The check is not that expensive and it is
better to have get_mem_cgroup_from_mm more robust.

[1] - http://marc.info/?l=linux-mm&m=139463617808941&w=2

Fixes: 03583f1a631c ("memcg: remove unnecessary !mm check from try_get_mem_cgroup_from_mm()")
Reported-and-tested-by: Stephan Kulow <coolo@suse.com>
Reported-by: Branimir Maksimovic <branimir.maksimovic@gmail.com>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 55231e5
Raw File
sys_ni.c

#include <linux/linkage.h>
#include <linux/errno.h>

#include <asm/unistd.h>

/*  we can't #include <linux/syscalls.h> here,
    but tell gcc to not warn with -Wmissing-prototypes  */
asmlinkage long sys_ni_syscall(void);

/*
 * Non-implemented system calls get redirected here.
 */
asmlinkage long sys_ni_syscall(void)
{
	return -ENOSYS;
}

cond_syscall(sys_quotactl);
cond_syscall(sys32_quotactl);
cond_syscall(sys_acct);
cond_syscall(sys_lookup_dcookie);
cond_syscall(compat_sys_lookup_dcookie);
cond_syscall(sys_swapon);
cond_syscall(sys_swapoff);
cond_syscall(sys_kexec_load);
cond_syscall(compat_sys_kexec_load);
cond_syscall(sys_init_module);
cond_syscall(sys_finit_module);
cond_syscall(sys_delete_module);
cond_syscall(sys_socketpair);
cond_syscall(sys_bind);
cond_syscall(sys_listen);
cond_syscall(sys_accept);
cond_syscall(sys_accept4);
cond_syscall(sys_connect);
cond_syscall(sys_getsockname);
cond_syscall(sys_getpeername);
cond_syscall(sys_sendto);
cond_syscall(sys_send);
cond_syscall(sys_recvfrom);
cond_syscall(sys_recv);
cond_syscall(sys_socket);
cond_syscall(sys_setsockopt);
cond_syscall(compat_sys_setsockopt);
cond_syscall(sys_getsockopt);
cond_syscall(compat_sys_getsockopt);
cond_syscall(sys_shutdown);
cond_syscall(sys_sendmsg);
cond_syscall(sys_sendmmsg);
cond_syscall(compat_sys_sendmsg);
cond_syscall(compat_sys_sendmmsg);
cond_syscall(sys_recvmsg);
cond_syscall(sys_recvmmsg);
cond_syscall(compat_sys_recvmsg);
cond_syscall(compat_sys_recv);
cond_syscall(compat_sys_recvfrom);
cond_syscall(compat_sys_recvmmsg);
cond_syscall(sys_socketcall);
cond_syscall(sys_futex);
cond_syscall(compat_sys_futex);
cond_syscall(sys_set_robust_list);
cond_syscall(compat_sys_set_robust_list);
cond_syscall(sys_get_robust_list);
cond_syscall(compat_sys_get_robust_list);
cond_syscall(sys_epoll_create);
cond_syscall(sys_epoll_create1);
cond_syscall(sys_epoll_ctl);
cond_syscall(sys_epoll_wait);
cond_syscall(sys_epoll_pwait);
cond_syscall(compat_sys_epoll_pwait);
cond_syscall(sys_semget);
cond_syscall(sys_semop);
cond_syscall(sys_semtimedop);
cond_syscall(compat_sys_semtimedop);
cond_syscall(sys_semctl);
cond_syscall(compat_sys_semctl);
cond_syscall(sys_msgget);
cond_syscall(sys_msgsnd);
cond_syscall(compat_sys_msgsnd);
cond_syscall(sys_msgrcv);
cond_syscall(compat_sys_msgrcv);
cond_syscall(sys_msgctl);
cond_syscall(compat_sys_msgctl);
cond_syscall(sys_shmget);
cond_syscall(sys_shmat);
cond_syscall(compat_sys_shmat);
cond_syscall(sys_shmdt);
cond_syscall(sys_shmctl);
cond_syscall(compat_sys_shmctl);
cond_syscall(sys_mq_open);
cond_syscall(sys_mq_unlink);
cond_syscall(sys_mq_timedsend);
cond_syscall(sys_mq_timedreceive);
cond_syscall(sys_mq_notify);
cond_syscall(sys_mq_getsetattr);
cond_syscall(compat_sys_mq_open);
cond_syscall(compat_sys_mq_timedsend);
cond_syscall(compat_sys_mq_timedreceive);
cond_syscall(compat_sys_mq_notify);
cond_syscall(compat_sys_mq_getsetattr);
cond_syscall(sys_mbind);
cond_syscall(sys_get_mempolicy);
cond_syscall(sys_set_mempolicy);
cond_syscall(compat_sys_mbind);
cond_syscall(compat_sys_get_mempolicy);
cond_syscall(compat_sys_set_mempolicy);
cond_syscall(sys_add_key);
cond_syscall(sys_request_key);
cond_syscall(sys_keyctl);
cond_syscall(compat_sys_keyctl);
cond_syscall(compat_sys_socketcall);
cond_syscall(sys_inotify_init);
cond_syscall(sys_inotify_init1);
cond_syscall(sys_inotify_add_watch);
cond_syscall(sys_inotify_rm_watch);
cond_syscall(sys_migrate_pages);
cond_syscall(sys_move_pages);
cond_syscall(sys_chown16);
cond_syscall(sys_fchown16);
cond_syscall(sys_getegid16);
cond_syscall(sys_geteuid16);
cond_syscall(sys_getgid16);
cond_syscall(sys_getgroups16);
cond_syscall(sys_getresgid16);
cond_syscall(sys_getresuid16);
cond_syscall(sys_getuid16);
cond_syscall(sys_lchown16);
cond_syscall(sys_setfsgid16);
cond_syscall(sys_setfsuid16);
cond_syscall(sys_setgid16);
cond_syscall(sys_setgroups16);
cond_syscall(sys_setregid16);
cond_syscall(sys_setresgid16);
cond_syscall(sys_setresuid16);
cond_syscall(sys_setreuid16);
cond_syscall(sys_setuid16);
cond_syscall(sys_vm86old);
cond_syscall(sys_vm86);
cond_syscall(sys_ipc);
cond_syscall(compat_sys_ipc);
cond_syscall(compat_sys_sysctl);
cond_syscall(sys_flock);
cond_syscall(sys_io_setup);
cond_syscall(sys_io_destroy);
cond_syscall(sys_io_submit);
cond_syscall(sys_io_cancel);
cond_syscall(sys_io_getevents);
cond_syscall(sys_sysfs);
cond_syscall(sys_syslog);
cond_syscall(sys_process_vm_readv);
cond_syscall(sys_process_vm_writev);
cond_syscall(compat_sys_process_vm_readv);
cond_syscall(compat_sys_process_vm_writev);
cond_syscall(sys_uselib);

/* arch-specific weak syscall entries */
cond_syscall(sys_pciconfig_read);
cond_syscall(sys_pciconfig_write);
cond_syscall(sys_pciconfig_iobase);
cond_syscall(compat_sys_s390_ipc);
cond_syscall(ppc_rtas);
cond_syscall(sys_spu_run);
cond_syscall(sys_spu_create);
cond_syscall(sys_subpage_prot);

/* mmu depending weak syscall entries */
cond_syscall(sys_mprotect);
cond_syscall(sys_msync);
cond_syscall(sys_mlock);
cond_syscall(sys_munlock);
cond_syscall(sys_mlockall);
cond_syscall(sys_munlockall);
cond_syscall(sys_mincore);
cond_syscall(sys_madvise);
cond_syscall(sys_mremap);
cond_syscall(sys_remap_file_pages);
cond_syscall(compat_sys_move_pages);
cond_syscall(compat_sys_migrate_pages);

/* block-layer dependent */
cond_syscall(sys_bdflush);
cond_syscall(sys_ioprio_set);
cond_syscall(sys_ioprio_get);

/* New file descriptors */
cond_syscall(sys_signalfd);
cond_syscall(sys_signalfd4);
cond_syscall(compat_sys_signalfd);
cond_syscall(compat_sys_signalfd4);
cond_syscall(sys_timerfd_create);
cond_syscall(sys_timerfd_settime);
cond_syscall(sys_timerfd_gettime);
cond_syscall(compat_sys_timerfd_settime);
cond_syscall(compat_sys_timerfd_gettime);
cond_syscall(sys_eventfd);
cond_syscall(sys_eventfd2);

/* performance counters: */
cond_syscall(sys_perf_event_open);

/* fanotify! */
cond_syscall(sys_fanotify_init);
cond_syscall(sys_fanotify_mark);
cond_syscall(compat_sys_fanotify_mark);

/* open by handle */
cond_syscall(sys_name_to_handle_at);
cond_syscall(sys_open_by_handle_at);
cond_syscall(compat_sys_open_by_handle_at);

/* compare kernel pointers */
cond_syscall(sys_kcmp);
back to top