linux-stable/include/linux/rwsem.h
Thomas Gleixner 42254105df locking/rwsem: Add rtmutex based R/W semaphore implementation
The RT specific R/W semaphore implementation used to restrict the number of
readers to one, because a writer cannot block on multiple readers and
inherit its priority or budget.

The single reader restricting was painful in various ways:

 - Performance bottleneck for multi-threaded applications in the page fault
   path (mmap sem)

 - Progress blocker for drivers which are carefully crafted to avoid the
   potential reader/writer deadlock in mainline.

The analysis of the writer code paths shows that properly written RT tasks
should not take them. Syscalls like mmap(), file access which take mmap sem
write locked have unbound latencies, which are completely unrelated to mmap
sem. Other R/W sem users like graphics drivers are not suitable for RT tasks
either.

So there is little risk to hurt RT tasks when the RT rwsem implementation is
done in the following way:

 - Allow concurrent readers

 - Make writers block until the last reader left the critical section. This
   blocking is not subject to priority/budget inheritance.

 - Readers blocked on a writer inherit their priority/budget in the normal
   way.

There is a drawback with this scheme: R/W semaphores become writer unfair
though the applications which have triggered writer starvation (mostly on
mmap_sem) in the past are not really the typical workloads running on a RT
system. So while it's unlikely to hit writer starvation, it's possible. If
there are unexpected workloads on RT systems triggering it, the problem
has to be revisited.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211303.016885947@linutronix.de
2021-08-17 17:12:47 +02:00

262 lines
7.5 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/* rwsem.h: R/W semaphores, public interface
*
* Written by David Howells (dhowells@redhat.com).
* Derived from asm-i386/semaphore.h
*/
#ifndef _LINUX_RWSEM_H
#define _LINUX_RWSEM_H
#include <linux/linkage.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/atomic.h>
#include <linux/err.h>
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# define __RWSEM_DEP_MAP_INIT(lockname) \
.dep_map = { \
.name = #lockname, \
.wait_type_inner = LD_WAIT_SLEEP, \
},
#else
# define __RWSEM_DEP_MAP_INIT(lockname)
#endif
#ifndef CONFIG_PREEMPT_RT
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
#include <linux/osq_lock.h>
#endif
/*
* For an uncontended rwsem, count and owner are the only fields a task
* needs to touch when acquiring the rwsem. So they are put next to each
* other to increase the chance that they will share the same cacheline.
*
* In a contended rwsem, the owner is likely the most frequently accessed
* field in the structure as the optimistic waiter that holds the osq lock
* will spin on owner. For an embedded rwsem, other hot fields in the
* containing structure should be moved further away from the rwsem to
* reduce the chance that they will share the same cacheline causing
* cacheline bouncing problem.
*/
struct rw_semaphore {
atomic_long_t count;
/*
* Write owner or one of the read owners as well flags regarding
* the current state of the rwsem. Can be used as a speculative
* check to see if the write owner is running on the cpu.
*/
atomic_long_t owner;
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
struct optimistic_spin_queue osq; /* spinner MCS lock */
#endif
raw_spinlock_t wait_lock;
struct list_head wait_list;
#ifdef CONFIG_DEBUG_RWSEMS
void *magic;
#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif
};
/* In all implementations count != 0 means locked */
static inline int rwsem_is_locked(struct rw_semaphore *sem)
{
return atomic_long_read(&sem->count) != 0;
}
#define RWSEM_UNLOCKED_VALUE 0L
#define __RWSEM_COUNT_INIT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE)
/* Common initializer macros and functions */
#ifdef CONFIG_DEBUG_RWSEMS
# define __RWSEM_DEBUG_INIT(lockname) .magic = &lockname,
#else
# define __RWSEM_DEBUG_INIT(lockname)
#endif
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
#define __RWSEM_OPT_INIT(lockname) .osq = OSQ_LOCK_UNLOCKED,
#else
#define __RWSEM_OPT_INIT(lockname)
#endif
#define __RWSEM_INITIALIZER(name) \
{ __RWSEM_COUNT_INIT(name), \
.owner = ATOMIC_LONG_INIT(0), \
__RWSEM_OPT_INIT(name) \
.wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),\
.wait_list = LIST_HEAD_INIT((name).wait_list), \
__RWSEM_DEBUG_INIT(name) \
__RWSEM_DEP_MAP_INIT(name) }
#define DECLARE_RWSEM(name) \
struct rw_semaphore name = __RWSEM_INITIALIZER(name)
extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
struct lock_class_key *key);
#define init_rwsem(sem) \
do { \
static struct lock_class_key __key; \
\
__init_rwsem((sem), #sem, &__key); \
} while (0)
/*
* This is the same regardless of which rwsem implementation that is being used.
* It is just a heuristic meant to be called by somebody already holding the
* rwsem to see if somebody from an incompatible type is wanting access to the
* lock.
*/
static inline int rwsem_is_contended(struct rw_semaphore *sem)
{
return !list_empty(&sem->wait_list);
}
#else /* !CONFIG_PREEMPT_RT */
#include <linux/rwbase_rt.h>
struct rw_semaphore {
struct rwbase_rt rwbase;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif
};
#define __RWSEM_INITIALIZER(name) \
{ \
.rwbase = __RWBASE_INITIALIZER(name), \
__RWSEM_DEP_MAP_INIT(name) \
}
#define DECLARE_RWSEM(lockname) \
struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname)
#ifdef CONFIG_DEBUG_LOCK_ALLOC
extern void __rwsem_init(struct rw_semaphore *rwsem, const char *name,
struct lock_class_key *key);
#else
static inline void __rwsem_init(struct rw_semaphore *rwsem, const char *name,
struct lock_class_key *key)
{
}
#endif
#define init_rwsem(sem) \
do { \
static struct lock_class_key __key; \
\
init_rwbase_rt(&(sem)->rwbase); \
__rwsem_init((sem), #sem, &__key); \
} while (0)
static __always_inline int rwsem_is_locked(struct rw_semaphore *sem)
{
return rw_base_is_locked(&sem->rwbase);
}
static __always_inline int rwsem_is_contended(struct rw_semaphore *sem)
{
return rw_base_is_contended(&sem->rwbase);
}
#endif /* CONFIG_PREEMPT_RT */
/*
* The functions below are the same for all rwsem implementations including
* the RT specific variant.
*/
/*
* lock for reading
*/
extern void down_read(struct rw_semaphore *sem);
extern int __must_check down_read_interruptible(struct rw_semaphore *sem);
extern int __must_check down_read_killable(struct rw_semaphore *sem);
/*
* trylock for reading -- returns 1 if successful, 0 if contention
*/
extern int down_read_trylock(struct rw_semaphore *sem);
/*
* lock for writing
*/
extern void down_write(struct rw_semaphore *sem);
extern int __must_check down_write_killable(struct rw_semaphore *sem);
/*
* trylock for writing -- returns 1 if successful, 0 if contention
*/
extern int down_write_trylock(struct rw_semaphore *sem);
/*
* release a read lock
*/
extern void up_read(struct rw_semaphore *sem);
/*
* release a write lock
*/
extern void up_write(struct rw_semaphore *sem);
/*
* downgrade write lock to read lock
*/
extern void downgrade_write(struct rw_semaphore *sem);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
* nested locking. NOTE: rwsems are not allowed to recurse
* (which occurs if the same task tries to acquire the same
* lock instance multiple times), but multiple locks of the
* same lock class might be taken, if the order of the locks
* is always the same. This ordering rule can be expressed
* to lockdep via the _nested() APIs, but enumerating the
* subclasses that are used. (If the nesting relationship is
* static then another method for expressing nested locking is
* the explicit definition of lock class keys and the use of
* lockdep_set_class() at lock initialization time.
* See Documentation/locking/lockdep-design.rst for more details.)
*/
extern void down_read_nested(struct rw_semaphore *sem, int subclass);
extern int __must_check down_read_killable_nested(struct rw_semaphore *sem, int subclass);
extern void down_write_nested(struct rw_semaphore *sem, int subclass);
extern int down_write_killable_nested(struct rw_semaphore *sem, int subclass);
extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock);
# define down_write_nest_lock(sem, nest_lock) \
do { \
typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \
_down_write_nest_lock(sem, &(nest_lock)->dep_map); \
} while (0);
/*
* Take/release a lock when not the owner will release it.
*
* [ This API should be avoided as much as possible - the
* proper abstraction for this case is completions. ]
*/
extern void down_read_non_owner(struct rw_semaphore *sem);
extern void up_read_non_owner(struct rw_semaphore *sem);
#else
# define down_read_nested(sem, subclass) down_read(sem)
# define down_read_killable_nested(sem, subclass) down_read_killable(sem)
# define down_write_nest_lock(sem, nest_lock) down_write(sem)
# define down_write_nested(sem, subclass) down_write(sem)
# define down_write_killable_nested(sem, subclass) down_write_killable(sem)
# define down_read_non_owner(sem) down_read(sem)
# define up_read_non_owner(sem) up_read(sem)
#endif
#endif /* _LINUX_RWSEM_H */