cpuset: fix a deadlock due to incomplete patching of cpusets_enabled()

commit 89affbf5d9ebb15c6460596822e8857ea2f9e735 upstream.

In codepaths that use the begin/retry interface for reading
mems_allowed_seq with irqs disabled, there exists a race condition that
stalls the patch process after only modifying a subset of the
static_branch call sites.

This problem manifested itself as a deadlock in the slub allocator,
inside get_any_partial.  The loop reads mems_allowed_seq value (via
read_mems_allowed_begin), performs the defrag operation, and then
verifies the consistency of mem_allowed via the read_mems_allowed_retry
and the cookie returned by xxx_begin.

The issue here is that both begin and retry first check if cpusets are
enabled via cpusets_enabled() static branch.  This branch can be
rewritted dynamically (via cpuset_inc) if a new cpuset is created.  The
x86 jump label code fully synchronizes across all CPUs for every entry
it rewrites.  If it rewrites only one of the callsites (specifically the
one in read_mems_allowed_retry) and then waits for the
smp_call_function(do_sync_core) to complete while a CPU is inside the
begin/retry section with IRQs off and the mems_allowed value is changed,
we can hang.

This is because begin() will always return 0 (since it wasn't patched
yet) while retry() will test the 0 against the actual value of the seq
counter.

The fix is to use two different static keys: one for begin
(pre_enable_key) and one for retry (enable_key).  In cpuset_inc(), we
first bump the pre_enable key to ensure that cpuset_mems_allowed_begin()
always return a valid seqcount if are enabling cpusets.  Similarly, when
disabling cpusets via cpuset_dec(), we first ensure that callers of
cpuset_mems_allowed_retry() will start ignoring the seqcount value
before we let cpuset_mems_allowed_begin() return 0.

The relevant stack traces of the two stuck threads:

  CPU: 1 PID: 1415 Comm: mkdir Tainted: G L  4.9.36-00104-g540c51286237 #4
  Hardware name: Default string Default string/Hardware, BIOS 4.29.1-20170526215256 05/26/2017
  task: ffff8817f9c28000 task.stack: ffffc9000ffa4000
  RIP: smp_call_function_many+0x1f9/0x260
  Call Trace:
    smp_call_function+0x3b/0x70
    on_each_cpu+0x2f/0x90
    text_poke_bp+0x87/0xd0
    arch_jump_label_transform+0x93/0x100
    __jump_label_update+0x77/0x90
    jump_label_update+0xaa/0xc0
    static_key_slow_inc+0x9e/0xb0
    cpuset_css_online+0x70/0x2e0
    online_css+0x2c/0xa0
    cgroup_apply_control_enable+0x27f/0x3d0
    cgroup_mkdir+0x2b7/0x420
    kernfs_iop_mkdir+0x5a/0x80
    vfs_mkdir+0xf6/0x1a0
    SyS_mkdir+0xb7/0xe0
    entry_SYSCALL_64_fastpath+0x18/0xad

  ...

  CPU: 2 PID: 1 Comm: init Tainted: G L  4.9.36-00104-g540c51286237 #4
  Hardware name: Default string Default string/Hardware, BIOS 4.29.1-20170526215256 05/26/2017
  task: ffff8818087c0000 task.stack: ffffc90000030000
  RIP: int3+0x39/0x70
  Call Trace:
    <#DB> ? ___slab_alloc+0x28b/0x5a0
    <EOE> ? copy_process.part.40+0xf7/0x1de0
    __slab_alloc.isra.80+0x54/0x90
    copy_process.part.40+0xf7/0x1de0
    copy_process.part.40+0xf7/0x1de0
    kmem_cache_alloc_node+0x8a/0x280
    copy_process.part.40+0xf7/0x1de0
    _do_fork+0xe7/0x6c0
    _raw_spin_unlock_irq+0x2d/0x60
    trace_hardirqs_on_caller+0x136/0x1d0
    entry_SYSCALL_64_fastpath+0x5/0xad
    do_syscall_64+0x27/0x350
    SyS_clone+0x19/0x20
    do_syscall_64+0x60/0x350
    entry_SYSCALL64_slow_path+0x25/0x25

Link: http://lkml.kernel.org/r/20170731040113.14197-1-dmitriyz@waymo.com
Fixes: 46e700abc44c ("mm, page_alloc: remove unnecessary taking of a seqlock when cpusets are disabled")
Signed-off-by: Dima Zavin <dmitriyz@waymo.com>
Reported-by: Cliff Spradlin <cspradlin@waymo.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christopher Lameter <cl@linux.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 85a868ccb4931d374a1ee9fb4e4036bb84399561..8397dc235e844ea3e0cdaf8490b617e4e46a9bf6 100644 (file)
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -16,6 +16,7 @@
 
 #ifdef CONFIG_CPUSETS
 
+extern struct static_key cpusets_pre_enable_key;
 extern struct static_key cpusets_enabled_key;
 static inline bool cpusets_enabled(void)
 {
@@ -30,12 +31,14 @@ static inline int nr_cpusets(void)
 
 static inline void cpuset_inc(void)
 {
+       static_key_slow_inc(&cpusets_pre_enable_key);
        static_key_slow_inc(&cpusets_enabled_key);
 }
 
 static inline void cpuset_dec(void)
 {
        static_key_slow_dec(&cpusets_enabled_key);
+       static_key_slow_dec(&cpusets_pre_enable_key);
 }
 
 extern int cpuset_init(void);
@@ -104,7 +107,7 @@ extern void cpuset_print_current_mems_allowed(void);
  */
 static inline unsigned int read_mems_allowed_begin(void)
 {
-       if (!cpusets_enabled())
+       if (!static_key_false(&cpusets_pre_enable_key))
                return 0;
 
        return read_seqcount_begin(&current->mems_allowed_seq);
@@ -118,7 +121,7 @@ static inline unsigned int read_mems_allowed_begin(void)
  */
 static inline bool read_mems_allowed_retry(unsigned int seq)
 {
-       if (!cpusets_enabled())
+       if (!static_key_false(&cpusets_enabled_key))
                return false;
 
        return read_seqcount_retry(&current->mems_allowed_seq, seq);

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 3b5e5430f5d094a1f766640240a52638d680a875..8ccd66a97c8be89c21bd4b22f5577f452ac5c185 100644 (file)
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -60,6 +60,7 @@
 #include <linux/cgroup.h>
 #include <linux/wait.h>
 
+struct static_key cpusets_pre_enable_key __read_mostly = STATIC_KEY_INIT_FALSE;
 struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE;
 
 /* See "Frequency meter" comments, below. */