925b9cd1b8
Currently, when a reader acquires a lock, it only sets the RWSEM_READER_OWNED bit in the owner field. The other bits are simply not used. When debugging hanging cases involving rwsems and readers, the owner value does not provide much useful information at all. This patch modifies the current behavior to always store the task_struct pointer of the last rwsem-acquiring reader in a reader-owned rwsem. This may be useful in debugging rwsem hanging cases especially if only one reader is involved. However, the task in the owner field may not the real owner or one of the real owners at all when the owner value is examined, for example, in a crash dump. So it is just an additional hint about the past history. If CONFIG_DEBUG_RWSEMS=y is enabled, the owner field will be checked at unlock time too to make sure the task pointer value is valid. That does have a slight performance cost and so is only enabled as part of that debug option. From the performance point of view, it is expected that the changes shouldn't have any noticeable performance impact. A rwsem microbenchmark (with 48 worker threads and 1:1 reader/writer ratio) was ran on a 2-socket 24-core 48-thread Haswell system. The locking rates on a 4.19-rc1 based kernel were as follows: 1) Unpatched kernel: 543.3 kops/s 2) Patched kernel: 549.2 kops/s 3) Patched kernel (CONFIG_DEBUG_RWSEMS on): 546.6 kops/s There was actually a slight increase in performance (1.1%) in this particular case. Maybe it was caused by the elimination of a branch or just a testing noise. Turning on the CONFIG_DEBUG_RWSEMS option also had less than the expected impact on performance. The least significant 2 bits of the owner value are now used to designate the rwsem is readers owned and the owners are anonymous. Signed-off-by: Waiman Long <longman@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will.deacon@arm.com> Link: http://lkml.kernel.org/r/1536265114-10842-1-git-send-email-longman@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
135 lines
4.3 KiB
C
135 lines
4.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* The least significant 2 bits of the owner value has the following
|
|
* meanings when set.
|
|
* - RWSEM_READER_OWNED (bit 0): The rwsem is owned by readers
|
|
* - RWSEM_ANONYMOUSLY_OWNED (bit 1): The rwsem is anonymously owned,
|
|
* i.e. the owner(s) cannot be readily determined. It can be reader
|
|
* owned or the owning writer is indeterminate.
|
|
*
|
|
* When a writer acquires a rwsem, it puts its task_struct pointer
|
|
* into the owner field. It is cleared after an unlock.
|
|
*
|
|
* When a reader acquires a rwsem, it will also puts its task_struct
|
|
* pointer into the owner field with both the RWSEM_READER_OWNED and
|
|
* RWSEM_ANONYMOUSLY_OWNED bits set. On unlock, the owner field will
|
|
* largely be left untouched. So for a free or reader-owned rwsem,
|
|
* the owner value may contain information about the last reader that
|
|
* acquires the rwsem. The anonymous bit is set because that particular
|
|
* reader may or may not still own the lock.
|
|
*
|
|
* That information may be helpful in debugging cases where the system
|
|
* seems to hang on a reader owned rwsem especially if only one reader
|
|
* is involved. Ideally we would like to track all the readers that own
|
|
* a rwsem, but the overhead is simply too big.
|
|
*/
|
|
#define RWSEM_READER_OWNED (1UL << 0)
|
|
#define RWSEM_ANONYMOUSLY_OWNED (1UL << 1)
|
|
|
|
#ifdef CONFIG_DEBUG_RWSEMS
|
|
# define DEBUG_RWSEMS_WARN_ON(c) DEBUG_LOCKS_WARN_ON(c)
|
|
#else
|
|
# define DEBUG_RWSEMS_WARN_ON(c)
|
|
#endif
|
|
|
|
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
|
|
/*
|
|
* All writes to owner are protected by WRITE_ONCE() to make sure that
|
|
* store tearing can't happen as optimistic spinners may read and use
|
|
* the owner value concurrently without lock. Read from owner, however,
|
|
* may not need READ_ONCE() as long as the pointer value is only used
|
|
* for comparison and isn't being dereferenced.
|
|
*/
|
|
static inline void rwsem_set_owner(struct rw_semaphore *sem)
|
|
{
|
|
WRITE_ONCE(sem->owner, current);
|
|
}
|
|
|
|
static inline void rwsem_clear_owner(struct rw_semaphore *sem)
|
|
{
|
|
WRITE_ONCE(sem->owner, NULL);
|
|
}
|
|
|
|
/*
|
|
* The task_struct pointer of the last owning reader will be left in
|
|
* the owner field.
|
|
*
|
|
* Note that the owner value just indicates the task has owned the rwsem
|
|
* previously, it may not be the real owner or one of the real owners
|
|
* anymore when that field is examined, so take it with a grain of salt.
|
|
*/
|
|
static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem,
|
|
struct task_struct *owner)
|
|
{
|
|
unsigned long val = (unsigned long)owner | RWSEM_READER_OWNED
|
|
| RWSEM_ANONYMOUSLY_OWNED;
|
|
|
|
WRITE_ONCE(sem->owner, (struct task_struct *)val);
|
|
}
|
|
|
|
static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
|
|
{
|
|
__rwsem_set_reader_owned(sem, current);
|
|
}
|
|
|
|
/*
|
|
* Return true if the a rwsem waiter can spin on the rwsem's owner
|
|
* and steal the lock, i.e. the lock is not anonymously owned.
|
|
* N.B. !owner is considered spinnable.
|
|
*/
|
|
static inline bool is_rwsem_owner_spinnable(struct task_struct *owner)
|
|
{
|
|
return !((unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED);
|
|
}
|
|
|
|
/*
|
|
* Return true if rwsem is owned by an anonymous writer or readers.
|
|
*/
|
|
static inline bool rwsem_has_anonymous_owner(struct task_struct *owner)
|
|
{
|
|
return (unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED;
|
|
}
|
|
|
|
#ifdef CONFIG_DEBUG_RWSEMS
|
|
/*
|
|
* With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there
|
|
* is a task pointer in owner of a reader-owned rwsem, it will be the
|
|
* real owner or one of the real owners. The only exception is when the
|
|
* unlock is done by up_read_non_owner().
|
|
*/
|
|
#define rwsem_clear_reader_owned rwsem_clear_reader_owned
|
|
static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
|
|
{
|
|
unsigned long val = (unsigned long)current | RWSEM_READER_OWNED
|
|
| RWSEM_ANONYMOUSLY_OWNED;
|
|
if (READ_ONCE(sem->owner) == (struct task_struct *)val)
|
|
cmpxchg_relaxed((unsigned long *)&sem->owner, val,
|
|
RWSEM_READER_OWNED | RWSEM_ANONYMOUSLY_OWNED);
|
|
}
|
|
#endif
|
|
|
|
#else
|
|
static inline void rwsem_set_owner(struct rw_semaphore *sem)
|
|
{
|
|
}
|
|
|
|
static inline void rwsem_clear_owner(struct rw_semaphore *sem)
|
|
{
|
|
}
|
|
|
|
static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem,
|
|
struct task_struct *owner)
|
|
{
|
|
}
|
|
|
|
static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#ifndef rwsem_clear_reader_owned
|
|
static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
|
|
{
|
|
}
|
|
#endif
|