linux-sg2042/include/linux/percpu-refcount.h

328 lines
9.9 KiB
C
Raw Normal View History

/*
* Percpu refcounts:
* (C) 2012 Google, Inc.
* Author: Kent Overstreet <koverstreet@google.com>
*
* This implements a refcount with similar semantics to atomic_t - atomic_inc(),
* atomic_dec_and_test() - but percpu.
*
* There's one important difference between percpu refs and normal atomic_t
* refcounts; you have to keep track of your initial refcount, and then when you
* start shutting down you call percpu_ref_kill() _before_ dropping the initial
* refcount.
*
* The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less
* than an atomic_t - this is because of the way shutdown works, see
* percpu_ref_kill()/PERCPU_COUNT_BIAS.
*
* Before you call percpu_ref_kill(), percpu_ref_put() does not check for the
* refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill()
* puts the ref back in single atomic_t mode, collecting the per cpu refs and
* issuing the appropriate barriers, and then marks the ref as shutting down so
* that percpu_ref_put() will check for the ref hitting 0. After it returns,
* it's safe to drop the initial ref.
*
* USAGE:
*
* See fs/aio.c for some example usage; it's used there for struct kioctx, which
* is created when userspaces calls io_setup(), and destroyed when userspace
* calls io_destroy() or the process exits.
*
* In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it
* calls percpu_ref_kill(), then hlist_del_rcu() and synchronize_rcu() to remove
* the kioctx from the proccess's list of kioctxs - after that, there can't be
* any new users of the kioctx (from lookup_ioctx()) and it's then safe to drop
* the initial ref with percpu_ref_put().
*
* Code that does a two stage shutdown like this often needs some kind of
* explicit synchronization to ensure the initial refcount can only be dropped
* once - percpu_ref_kill() does this for you, it returns true once and false if
* someone else already called it. The aio code uses it this way, but it's not
* necessary if the code has some other mechanism to synchronize teardown.
* around.
*/
#ifndef _LINUX_PERCPU_REFCOUNT_H
#define _LINUX_PERCPU_REFCOUNT_H
#include <linux/atomic.h>
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/rcupdate.h>
#include <linux/gfp.h>
struct percpu_ref;
typedef void (percpu_ref_func_t)(struct percpu_ref *);
/* flags set in the lower bits of percpu_ref->percpu_count_ptr */
enum {
__PERCPU_REF_ATOMIC = 1LU << 0, /* operating in atomic mode */
__PERCPU_REF_DEAD = 1LU << 1, /* (being) killed */
__PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD,
__PERCPU_REF_FLAG_BITS = 2,
};
/* @flags for percpu_ref_init() */
enum {
/*
* Start w/ ref == 1 in atomic mode. Can be switched to percpu
* operation using percpu_ref_switch_to_percpu(). If initialized
* with this flag, the ref will stay in atomic mode until
* percpu_ref_switch_to_percpu() is invoked on it.
*/
PERCPU_REF_INIT_ATOMIC = 1 << 0,
/*
* Start dead w/ ref == 0 in atomic mode. Must be revived with
* percpu_ref_reinit() before used. Implies INIT_ATOMIC.
*/
PERCPU_REF_INIT_DEAD = 1 << 1,
};
struct percpu_ref {
atomic_long_t count;
/*
* The low bit of the pointer indicates whether the ref is in percpu
* mode; if set, then get/put will manipulate the atomic_t.
*/
unsigned long percpu_count_ptr;
percpu_ref_func_t *release;
percpu_ref_func_t *confirm_switch;
bool force_atomic:1;
struct rcu_head rcu;
};
int __must_check percpu_ref_init(struct percpu_ref *ref,
percpu_ref_func_t *release, unsigned int flags,
gfp_t gfp);
void percpu_ref_exit(struct percpu_ref *ref);
percpu_ref: decouple switching to atomic mode and killing percpu_ref has treated the dropping of the base reference and switching to atomic mode as an integral operation; however, there's nothing inherent tying the two together. The use cases for percpu_ref have been expanding continuously. While the current init/kill/reinit/exit model can cover a lot, the coupling of kill/reinit with atomic/percpu mode switching is turning out to be too restrictive for use cases where many percpu_refs are created and destroyed back-to-back with only some of them reaching extended operation. The coupling also makes implementing always-atomic debug mode difficult. This patch separates out atomic mode switching into percpu_ref_switch_to_atomic() and reimplements percpu_ref_kill_and_confirm() on top of it. * The handling of __PERCPU_REF_ATOMIC and __PERCPU_REF_DEAD is now differentiated. Among get/put operations, percpu_ref_tryget_live() is the only one which cares about DEAD. * percpu_ref_switch_to_atomic() can be called multiple times on the same ref. This means that multiple @confirm_switch may get queued up which we can't do reliably without extra memory area. This is handled by making the later invocation synchronously wait for the completion of the previous one. This isn't particularly desirable but such synchronous waits shouldn't happen in most cases. Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org>
2014-09-25 01:31:49 +08:00
void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
percpu_ref_func_t *confirm_switch);
void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref);
void percpu_ref_switch_to_percpu(struct percpu_ref *ref);
void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
percpu_ref_func_t *confirm_kill);
void percpu_ref_reinit(struct percpu_ref *ref);
/**
* percpu_ref_kill - drop the initial ref
* @ref: percpu_ref to kill
*
* Must be used to drop the initial ref on a percpu refcount; must be called
* precisely once before shutdown.
*
* Puts @ref in non percpu mode, then does a call_rcu() before gathering up the
* percpu counters and dropping the initial ref.
*/
static inline void percpu_ref_kill(struct percpu_ref *ref)
{
percpu_ref_kill_and_confirm(ref, NULL);
}
/*
* Internal helper. Don't use outside percpu-refcount proper. The
* function doesn't return the pointer and let the caller test it for NULL
* because doing so forces the compiler to generate two conditional
* branches as it can't assume that @ref->percpu_count is not NULL.
*/
static inline bool __ref_is_percpu(struct percpu_ref *ref,
unsigned long __percpu **percpu_countp)
{
unsigned long percpu_ptr;
/*
* The value of @ref->percpu_count_ptr is tested for
* !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then
* used as a pointer. If the compiler generates a separate fetch
* when using it as a pointer, __PERCPU_REF_ATOMIC may be set in
* between contaminating the pointer value, meaning that
* READ_ONCE() is required when fetching it.
*/
percpu_ptr = READ_ONCE(ref->percpu_count_ptr);
/* paired with smp_store_release() in __percpu_ref_switch_to_percpu() */
smp_read_barrier_depends();
/*
* Theoretically, the following could test just ATOMIC; however,
* then we'd have to mask off DEAD separately as DEAD may be
* visible without ATOMIC if we race with percpu_ref_kill(). DEAD
* implies ATOMIC anyway. Test them together.
*/
if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD))
return false;
*percpu_countp = (unsigned long __percpu *)percpu_ptr;
return true;
}
/**
* percpu_ref_get_many - increment a percpu refcount
* @ref: percpu_ref to get
* @nr: number of references to get
*
* Analogous to atomic_long_add().
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr)
{
unsigned long __percpu *percpu_count;
rcu_read_lock_sched();
if (__ref_is_percpu(ref, &percpu_count))
this_cpu_add(*percpu_count, nr);
else
atomic_long_add(nr, &ref->count);
rcu_read_unlock_sched();
}
/**
* percpu_ref_get - increment a percpu refcount
* @ref: percpu_ref to get
*
* Analagous to atomic_long_inc().
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline void percpu_ref_get(struct percpu_ref *ref)
{
percpu_ref_get_many(ref, 1);
}
/**
* percpu_ref_tryget - try to increment a percpu refcount
* @ref: percpu_ref to try-get
*
* Increment a percpu refcount unless its count already reached zero.
* Returns %true on success; %false on failure.
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline bool percpu_ref_tryget(struct percpu_ref *ref)
{
unsigned long __percpu *percpu_count;
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+
2017-01-28 20:42:20 +08:00
bool ret;
rcu_read_lock_sched();
if (__ref_is_percpu(ref, &percpu_count)) {
this_cpu_inc(*percpu_count);
ret = true;
} else {
ret = atomic_long_inc_not_zero(&ref->count);
}
rcu_read_unlock_sched();
return ret;
}
/**
* percpu_ref_tryget_live - try to increment a live percpu refcount
* @ref: percpu_ref to try-get
*
* Increment a percpu refcount unless it has already been killed. Returns
* %true on success; %false on failure.
*
* Completion of percpu_ref_kill() in itself doesn't guarantee that this
* function will fail. For such guarantee, percpu_ref_kill_and_confirm()
* should be used. After the confirm_kill callback is invoked, it's
* guaranteed that no new reference will be given out by
* percpu_ref_tryget_live().
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
{
unsigned long __percpu *percpu_count;
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+
2017-01-28 20:42:20 +08:00
bool ret = false;
rcu_read_lock_sched();
if (__ref_is_percpu(ref, &percpu_count)) {
this_cpu_inc(*percpu_count);
ret = true;
} else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) {
percpu_ref: decouple switching to atomic mode and killing percpu_ref has treated the dropping of the base reference and switching to atomic mode as an integral operation; however, there's nothing inherent tying the two together. The use cases for percpu_ref have been expanding continuously. While the current init/kill/reinit/exit model can cover a lot, the coupling of kill/reinit with atomic/percpu mode switching is turning out to be too restrictive for use cases where many percpu_refs are created and destroyed back-to-back with only some of them reaching extended operation. The coupling also makes implementing always-atomic debug mode difficult. This patch separates out atomic mode switching into percpu_ref_switch_to_atomic() and reimplements percpu_ref_kill_and_confirm() on top of it. * The handling of __PERCPU_REF_ATOMIC and __PERCPU_REF_DEAD is now differentiated. Among get/put operations, percpu_ref_tryget_live() is the only one which cares about DEAD. * percpu_ref_switch_to_atomic() can be called multiple times on the same ref. This means that multiple @confirm_switch may get queued up which we can't do reliably without extra memory area. This is handled by making the later invocation synchronously wait for the completion of the previous one. This isn't particularly desirable but such synchronous waits shouldn't happen in most cases. Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org>
2014-09-25 01:31:49 +08:00
ret = atomic_long_inc_not_zero(&ref->count);
}
rcu_read_unlock_sched();
return ret;
}
/**
* percpu_ref_put_many - decrement a percpu refcount
* @ref: percpu_ref to put
* @nr: number of references to put
*
* Decrement the refcount, and if 0, call the release function (which was passed
* to percpu_ref_init())
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr)
{
unsigned long __percpu *percpu_count;
rcu_read_lock_sched();
if (__ref_is_percpu(ref, &percpu_count))
this_cpu_sub(*percpu_count, nr);
else if (unlikely(atomic_long_sub_and_test(nr, &ref->count)))
ref->release(ref);
rcu_read_unlock_sched();
}
/**
* percpu_ref_put - decrement a percpu refcount
* @ref: percpu_ref to put
*
* Decrement the refcount, and if 0, call the release function (which was passed
* to percpu_ref_init())
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline void percpu_ref_put(struct percpu_ref *ref)
{
percpu_ref_put_many(ref, 1);
}
/**
* percpu_ref_is_dying - test whether a percpu refcount is dying or dead
* @ref: percpu_ref to test
*
* Returns %true if @ref is dying or dead.
*
* This function is safe to call as long as @ref is between init and exit
* and the caller is responsible for synchronizing against state changes.
*/
static inline bool percpu_ref_is_dying(struct percpu_ref *ref)
{
return ref->percpu_count_ptr & __PERCPU_REF_DEAD;
}
/**
* percpu_ref_is_zero - test whether a percpu refcount reached zero
* @ref: percpu_ref to test
*
* Returns %true if @ref reached zero.
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline bool percpu_ref_is_zero(struct percpu_ref *ref)
{
unsigned long __percpu *percpu_count;
if (__ref_is_percpu(ref, &percpu_count))
return false;
return !atomic_long_read(&ref->count);
}
#endif