#undef TRACE_SYSTEM #define TRACE_SYSTEM migrate #if !defined(_TRACE_MIGRATE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MIGRATE_H #include #define MIGRATE_MODE \ EM( MIGRATE_ASYNC, "MIGRATE_ASYNC") \ EM( MIGRATE_SYNC_LIGHT, "MIGRATE_SYNC_LIGHT") \ EMe(MIGRATE_SYNC, "MIGRATE_SYNC") #define MIGRATE_REASON \ EM( MR_COMPACTION, "compaction") \ EM( MR_MEMORY_FAILURE, "memory_failure") \ EM( MR_MEMORY_HOTPLUG, "memory_hotplug") \ EM( MR_SYSCALL, "syscall_or_cpuset") \ EM( MR_MEMPOLICY_MBIND, "mempolicy_mbind") \ EM( MR_NUMA_MISPLACED, "numa_misplaced") \ EMe(MR_CMA, "cma") /* * First define the enums in the above macros to be exported to userspace * via TRACE_DEFINE_ENUM(). */ #undef EM #undef EMe #define EM(a, b) TRACE_DEFINE_ENUM(a); #define EMe(a, b) TRACE_DEFINE_ENUM(a); MIGRATE_MODE MIGRATE_REASON /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a, b) {a, b}, #define EMe(a, b) {a, b} TRACE_EVENT(mm_migrate_pages, TP_PROTO(unsigned long succeeded, unsigned long failed, enum migrate_mode mode, int reason), TP_ARGS(succeeded, failed, mode, reason), TP_STRUCT__entry( __field( unsigned long, succeeded) __field( unsigned long, failed) __field( enum migrate_mode, mode) __field( int, reason) ), TP_fast_assign( __entry->succeeded = succeeded; __entry->failed = failed; __entry->mode = mode; __entry->reason = reason; ), TP_printk("nr_succeeded=%lu nr_failed=%lu mode=%s reason=%s", __entry->succeeded, __entry->failed, __print_symbolic(__entry->mode, MIGRATE_MODE), __print_symbolic(__entry->reason, MIGRATE_REASON)) ); TRACE_EVENT(mm_numa_migrate_ratelimit, TP_PROTO(struct task_struct *p, int dst_nid, unsigned long nr_pages), TP_ARGS(p, dst_nid, nr_pages), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN) __field( pid_t, pid) __field( int, dst_nid) __field( unsigned long, nr_pages) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->dst_nid = dst_nid; __entry->nr_pages = nr_pages; ), TP_printk("comm=%s pid=%d dst_nid=%d nr_pages=%lu", __entry->comm, __entry->pid, __entry->dst_nid, __entry->nr_pages) ); #endif /* _TRACE_MIGRATE_H */ /* This part must be outside protection */ #include e='range'>range
diff options
context:
space:
mode:
authorDouglas Miller <dougmill@linux.vnet.ibm.com>2017-01-28 06:42:20 -0600
committerTejun Heo <tj@kernel.org>2017-01-28 07:49:42 -0500
commit966d2b04e070bc040319aaebfec09e0144dc3341 (patch)
tree4b96156e3d1dd4dfd6039b7c219c9dc4616da52d /fs/nfsd/xdr.h
parent1b1bc42c1692e9b62756323c675a44cb1a1f9dbd (diff)
percpu-refcount: fix reference leak during percpu-atomic transition
percpu_ref_tryget() and percpu_ref_tryget_live() should return "true" IFF they acquire a reference. But the return value from atomic_long_inc_not_zero() is a long and may have high bits set, e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines is bool so the reference may actually be acquired but the routines return "false" which results in a reference leak since the caller assumes it does not need to do a corresponding percpu_ref_put(). This was seen when performing CPU hotplug during I/O, as hangs in blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start) raced with percpu_ref_tryget (blk_mq_timeout_work). Sample stack trace: __switch_to+0x2c0/0x450 __schedule+0x2f8/0x970 schedule+0x48/0xc0 blk_mq_freeze_queue_wait+0x94/0x120 blk_mq_queue_reinit_work+0xb8/0x180 blk_mq_queue_reinit_prepare+0x84/0xa0 cpuhp_invoke_callback+0x17c/0x600 cpuhp_up_callbacks+0x58/0x150 _cpu_up+0xf0/0x1c0 do_cpu_up+0x120/0x150 cpu_subsys_online+0x64/0xe0 device_online+0xb4/0x120 online_store+0xb4/0xc0 dev_attr_store+0x68/0xa0 sysfs_kf_write+0x80/0xb0 kernfs_fop_write+0x17c/0x250 __vfs_write+0x6c/0x1e0 vfs_write+0xd0/0x270 SyS_write+0x6c/0x110 system_call+0x38/0xe0 Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS, and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests. However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0 and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set. The fix is to make the tryget routines use an actual boolean internally instead of the atomic long result truncated to a int. Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751 Signed-off-by: Douglas Miller <dougmill@linux.vnet.ibm.com> Reviewed-by: Jens Axboe <axboe@fb.com> Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: e625305b3907 ("percpu-refcount: make percpu_ref based on longs instead of ints") Cc: stable@vger.kernel.org # v3.18+
Diffstat (limited to 'fs/nfsd/xdr.h')