linux.git/kernel/fork.c, branch v4.19.115

fork,memcg: alloc_thread_stack_node needs to set tsk->stack

2020-01-27T13:50:58+00:00

[ Upstream commit 1bf4580e00a248a2c86269125390eb3648e1877c ]

Commit 5eed6f1dff87 ("fork,memcg: fix crash in free_thread_stack on
memcg charge fail") corrected two instances, but there was a third
instance of this bug.

Without setting tsk->stack, if memcg_charge_kernel_stack fails, it'll
execute free_thread_stack() on a dangling pointer.

Enterprise kernels are compiled with VMAP_STACK=y so this isn't
critical, but custom VMAP_STACK=n builds should have some performance
advantage, with the drawback of risking to fail fork because compaction
didn't succeed.  So as long as VMAP_STACK=n is a supported option it's
worth fixing it upstream.

Link: http://lkml.kernel.org/r/20190619011450.28048-1-aarcange@redhat.com
Fixes: 9b6f7e163cd0 ("mm: rework memcg kernel stack accounting")
Signed-off-by: Andrea Arcangeli 
Reviewed-by: Rik van Riel 
Acked-by: Roman Gushchin 
Acked-by: Michal Hocko 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Sasha Levin

fork, memcg: fix cached_stacks case

2020-01-27T13:50:11+00:00

[ Upstream commit ba4a45746c362b665e245c50b870615f02f34781 ]

Commit 5eed6f1dff87 ("fork,memcg: fix crash in free_thread_stack on
memcg charge fail") fixes a crash caused due to failed memcg charge of
the kernel stack.  However the fix misses the cached_stacks case which
this patch fixes.  So, the same crash can happen if the memcg charge of
a cached stack is failed.

Link: http://lkml.kernel.org/r/20190102180145.57406-1-shakeelb@google.com
Fixes: 5eed6f1dff87 ("fork,memcg: fix crash in free_thread_stack on memcg charge fail")
Signed-off-by: Shakeel Butt 
Acked-by: Michal Hocko 
Acked-by: Rik van Riel 
Cc: Rik van Riel 
Cc: Roman Gushchin 
Cc: Johannes Weiner 
Cc: Tejun Heo 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Sasha Levin

fork,memcg: fix crash in free_thread_stack on memcg charge fail

2020-01-27T13:50:08+00:00

[ Upstream commit 5eed6f1dff87bfb5e545935def3843edf42800f2 ]

Commit 9b6f7e163cd0 ("mm: rework memcg kernel stack accounting") will
result in fork failing if allocating a kernel stack for a task in
dup_task_struct exceeds the kernel memory allowance for that cgroup.

Unfortunately, it also results in a crash.

This is due to the code jumping to free_stack and calling
free_thread_stack when the memcg kernel stack charge fails, but without
tsk->stack pointing at the freshly allocated stack.

This in turn results in the vfree_atomic in free_thread_stack oopsing
with a backtrace like this:

#5 [ffffc900244efc88] die at ffffffff8101f0ab
 #6 [ffffc900244efcb8] do_general_protection at ffffffff8101cb86
 #7 [ffffc900244efce0] general_protection at ffffffff818ff082
    [exception RIP: llist_add_batch+7]
    RIP: ffffffff8150d487  RSP: ffffc900244efd98  RFLAGS: 00010282
    RAX: 0000000000000000  RBX: ffff88085ef55980  RCX: 0000000000000000
    RDX: ffff88085ef55980  RSI: 343834343531203a  RDI: 343834343531203a
    RBP: ffffc900244efd98   R8: 0000000000000001   R9: ffff8808578c3600
    R10: 0000000000000000  R11: 0000000000000001  R12: ffff88029f6c21c0
    R13: 0000000000000286  R14: ffff880147759b00  R15: 0000000000000000
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
 #8 [ffffc900244efda0] vfree_atomic at ffffffff811df2c7
 #9 [ffffc900244efdb8] copy_process at ffffffff81086e37
#10 [ffffc900244efe98] _do_fork at ffffffff810884e0
#11 [ffffc900244eff10] sys_vfork at ffffffff810887ff
#12 [ffffc900244eff20] do_syscall_64 at ffffffff81002a43
    RIP: 000000000049b948  RSP: 00007ffcdb307830  RFLAGS: 00000246
    RAX: ffffffffffffffda  RBX: 0000000000896030  RCX: 000000000049b948
    RDX: 0000000000000000  RSI: 00007ffcdb307790  RDI: 00000000005d7421
    RBP: 000000000067370f   R8: 00007ffcdb3077b0   R9: 000000000001ed00
    R10: 0000000000000008  R11: 0000000000000246  R12: 0000000000000040
    R13: 000000000000000f  R14: 0000000000000000  R15: 000000000088d018
    ORIG_RAX: 000000000000003a  CS: 0033  SS: 002b

The simplest fix is to assign tsk->stack right where it is allocated.

Link: http://lkml.kernel.org/r/20181214231726.7ee4843c@imladris.surriel.com
Fixes: 9b6f7e163cd0 ("mm: rework memcg kernel stack accounting")
Signed-off-by: Rik van Riel 
Acked-by: Roman Gushchin 
Acked-by: Michal Hocko 
Cc: Shakeel Butt 
Cc: Johannes Weiner 
Cc: Tejun Heo 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Sasha Levin

fork: fix some -Wmissing-prototypes warnings

2019-12-05T08:21:04+00:00

[ Upstream commit fb5bf31722d0805a3f394f7d59f2e8cd07acccb7 ]

We get a warning when building kernel with W=1:

  kernel/fork.c:167:13: warning: no previous prototype for `arch_release_thread_stack' [-Wmissing-prototypes]
  kernel/fork.c:779:13: warning: no previous prototype for `fork_init' [-Wmissing-prototypes]

Add the missing declaration in head file to fix this.

Also, remove arch_release_thread_stack() completely because no arch
seems to implement it since bb9d81264 (arch: remove tile port).

Link: http://lkml.kernel.org/r/1542170087-23645-1-git-send-email-wang.yi59@zte.com.cn
Signed-off-by: Yi Wang 
Acked-by: Michal Hocko 
Acked-by: Mike Rapoport 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Sasha Levin

kernel/sysctl.c: do not override max_threads provided by userspace

2019-10-17T20:45:19+00:00

commit b0f53dbc4bc4c371f38b14c391095a3bb8a0bb40 upstream.

Partially revert 16db3d3f1170 ("kernel/sysctl.c: threads-max observe
limits") because the patch is causing a regression to any workload which
needs to override the auto-tuning of the limit provided by kernel.

set_max_threads is implementing a boot time guesstimate to provide a
sensible limit of the concurrently running threads so that runaways will
not deplete all the memory.  This is a good thing in general but there
are workloads which might need to increase this limit for an application
to run (reportedly WebSpher MQ is affected) and that is simply not
possible after the mentioned change.  It is also very dubious to
override an admin decision by an estimation that doesn't have any direct
relation to correctness of the kernel operation.

Fix this by dropping set_max_threads from sysctl_max_threads so any
value is accepted as long as it fits into MAX_THREADS which is important
to check because allowing more threads could break internal robust futex
restriction.  While at it, do not use MIN_THREADS as the lower boundary
because it is also only a heuristic for automatic estimation and admin
might have a good reason to stop new threads to be created even when
below this limit.

This became more severe when we switched x86 from 4k to 8k kernel
stacks.  Starting since 6538b8ea886e ("x86_64: expand kernel stack to
16K") (3.16) we use THREAD_SIZE_ORDER = 2 and that halved the auto-tuned
value.

In the particular case

  3.12
  kernel.threads-max = 515561

  4.4
  kernel.threads-max = 200000

Neither of the two values is really insane on 32GB machine.

I am not sure we want/need to tune the max_thread value further.  If
anything the tuning should be removed altogether if proven not useful in
general.  But we definitely need a way to override this auto-tuning.

Link: http://lkml.kernel.org/r/20190922065801.GB18814@dhcp22.suse.cz
Fixes: 16db3d3f1170 ("kernel/sysctl.c: threads-max observe limits")
Signed-off-by: Michal Hocko 
Reviewed-by: "Eric W. Biederman" 
Cc: Heinrich Schuchardt 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

sched/fair: Don't free p->numa_faults with concurrent readers

2019-08-04T07:30:56+00:00

commit 16d51a590a8ce3befb1308e0e7ab77f3b661af33 upstream.

When going through execve(), zero out the NUMA fault statistics instead of
freeing them.

During execve, the task is reachable through procfs and the scheduler. A
concurrent /proc/*/sched reader can read data from a freed ->numa_faults
allocation (confirmed by KASAN) and write it back to userspace.
I believe that it would also be possible for a use-after-free read to occur
through a race between a NUMA fault and execve(): task_numa_fault() can
lead to task_numa_compare(), which invokes task_weight() on the currently
running task of a different CPU.

Another way to fix this would be to make ->numa_faults RCU-managed or add
extra locking, but it seems easier to wipe the NUMA fault statistics on
execve.

Signed-off-by: Jann Horn 
Signed-off-by: Peter Zijlstra (Intel) 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Cc: Petr Mladek 
Cc: Sergey Senozhatsky 
Cc: Thomas Gleixner 
Cc: Will Deacon 
Fixes: 82727018b0d3 ("sched/numa: Call task_numa_free() from do_execve()")
Link: https://lkml.kernel.org/r/20190716152047.14424-1-jannh@google.com
Signed-off-by: Ingo Molnar 
Signed-off-by: Greg Kroah-Hartman

userfaultfd: use RCU to free the task struct when fork fails

2019-05-22T05:37:41+00:00

commit c3f3ce049f7d97cc7ec9c01cb51d9ec74e0f37c2 upstream.

The task structure is freed while get_mem_cgroup_from_mm() holds
rcu_read_lock() and dereferences mm->owner.

  get_mem_cgroup_from_mm()                failing fork()
  ----                                    ---
  task = mm->owner
                                          mm->owner = NULL;
                                          free(task)
  if (task) *task; /* use after free */

The fix consists in freeing the task with RCU also in the fork failure
case, exactly like it always happens for the regular exit(2) path.  That
is enough to make the rcu_read_lock hold in get_mem_cgroup_from_mm()
(left side above) effective to avoid a use after free when dereferencing
the task structure.

An alternate possible fix would be to defer the delivery of the
userfaultfd contexts to the monitor until after fork() is guaranteed to
succeed.  Such a change would require more changes because it would
create a strict ordering dependency where the uffd methods would need to
be called beyond the last potentially failing branch in order to be
safe.  This solution as opposed only adds the dependency to common code
to set mm->owner to NULL and to free the task struct that was pointed by
mm->owner with RCU, if fork ends up failing.  The userfaultfd methods
can still be called anywhere during the fork runtime and the monitor
will keep discarding orphaned "mm" coming from failed forks in userland.

This race condition couldn't trigger if CONFIG_MEMCG was set =n at build
time.

[aarcange@redhat.com: improve changelog, reduce #ifdefs per Michal]
  Link: http://lkml.kernel.org/r/20190429035752.4508-1-aarcange@redhat.com
Link: http://lkml.kernel.org/r/20190325225636.11635-2-aarcange@redhat.com
Fixes: 893e26e61d04 ("userfaultfd: non-cooperative: Add fork() event")
Signed-off-by: Andrea Arcangeli 
Tested-by: zhong jiang 
Reported-by: syzbot+cbb52e396df3e565ab02@syzkaller.appspotmail.com
Cc: Oleg Nesterov 
Cc: Jann Horn 
Cc: Hugh Dickins 
Cc: Mike Rapoport 
Cc: Mike Kravetz 
Cc: Peter Xu 
Cc: Jason Gunthorpe 
Cc: "Kirill A . Shutemov" 
Cc: Michal Hocko 
Cc: zhong jiang 
Cc: syzbot+cbb52e396df3e565ab02@syzkaller.appspotmail.com
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

fork: record start_time late

2019-01-13T08:51:04+00:00

commit 7b55851367136b1efd84d98fea81ba57a98304cf upstream.

This changes the fork(2) syscall to record the process start_time after
initializing the basic task structure but still before making the new
process visible to user-space.

Technically, we could record the start_time anytime during fork(2).  But
this might lead to scenarios where a start_time is recorded long before
a process becomes visible to user-space.  For instance, with
userfaultfd(2) and TLS, user-space can delay the execution of fork(2)
for an indefinite amount of time (and will, if this causes network
access, or similar).

By recording the start_time late, it much closer reflects the point in
time where the process becomes live and can be observed by other
processes.

Lastly, this makes it much harder for user-space to predict and control
the start_time they get assigned.  Previously, user-space could fork a
process and stall it in copy_thread_tls() before its pid is allocated,
but after its start_time is recorded.  This can be misused to later-on
cycle through PIDs and resume the stalled fork(2) yielding a process
that has the same pid and start_time as a process that existed before.
This can be used to circumvent security systems that identify processes
by their pid+start_time combination.

Even though user-space was always aware that start_time recording is
flaky (but several projects are known to still rely on start_time-based
identification), changing the start_time to be recorded late will help
mitigate existing attacks and make it much harder for user-space to
control the start_time a process gets assigned.

Reported-by: Jann Horn 
Signed-off-by: Tom Gundersen 
Signed-off-by: David Herrmann 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

mm: respect arch_dup_mmap() return value

2018-09-04T23:45:02+00:00

Commit d70f2a14b72a ("include/linux/sched/mm.h: uninline mmdrop_async(),
etc") ignored the return value of arch_dup_mmap(). As a result, on x86,
a failure to duplicate the LDT (e.g. due to memory allocation error)
would leave the duplicated memory mapping in an inconsistent state.

Fix by using the return value, as it was before the change.

Link: http://lkml.kernel.org/r/20180823051229.211856-1-namit@vmware.com
Fixes: d70f2a14b72a4 ("include/linux/sched/mm.h: uninline mmdrop_async(), etc")
Signed-off-by: Nadav Amit 
Acked-by: Michal Hocko 
Cc: 

Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

Merge branch 'akpm' (patches from Andrew)

2018-08-22T19:34:08+00:00

Merge more updates from Andrew Morton:

 - the rest of MM

 - procfs updates

 - various misc things

 - more y2038 fixes

 - get_maintainer updates

 - lib/ updates

 - checkpatch updates

 - various epoll updates

 - autofs updates

 - hfsplus

 - some reiserfs work

 - fatfs updates

 - signal.c cleanups

 - ipc/ updates

* emailed patches from Andrew Morton : (166 commits)
  ipc/util.c: update return value of ipc_getref from int to bool
  ipc/util.c: further variable name cleanups
  ipc: simplify ipc initialization
  ipc: get rid of ids->tables_initialized hack
  lib/rhashtable: guarantee initial hashtable allocation
  lib/rhashtable: simplify bucket_table_alloc()
  ipc: drop ipc_lock()
  ipc/util.c: correct comment in ipc_obtain_object_check
  ipc: rename ipcctl_pre_down_nolock()
  ipc/util.c: use ipc_rcu_putref() for failues in ipc_addid()
  ipc: reorganize initialization of kern_ipc_perm.seq
  ipc: compute kern_ipc_perm.id under the ipc lock
  init/Kconfig: remove EXPERT from CHECKPOINT_RESTORE
  fs/sysv/inode.c: use ktime_get_real_seconds() for superblock stamp
  adfs: use timespec64 for time conversion
  kernel/sysctl.c: fix typos in comments
  drivers/rapidio/devices/rio_mport_cdev.c: remove redundant pointer md
  fork: don't copy inconsistent signal handler state to child
  signal: make get_signal() return bool
  signal: make sigkill_pending() return bool
  ...