mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-05 18:39:59 +00:00
![Gabriel Krisman Bertazi](/assets/img/avatar_default.png)
sbitmap suffers from code complexity, as demonstrated by recent fixes, and eventual lost wake ups on nested I/O completion. The later happens, from what I understand, due to the non-atomic nature of the updates to wait_cnt, which needs to be subtracted and eventually reset when equal to zero. This two step process can eventually miss an update when a nested completion happens to interrupt the CPU in between the wait_cnt updates. This is very hard to fix, as shown by the recent changes to this code. The code complexity arises mostly from the corner cases to avoid missed wakes in this scenario. In addition, the handling of wake_batch recalculation plus the synchronization with sbq_queue_wake_up is non-trivial. This patchset implements the idea originally proposed by Jan [1], which removes the need for the two-step updates of wait_cnt. This is done by tracking the number of completions and wakeups in always increasing, per-bitmap counters. Instead of having to reset the wait_cnt when it reaches zero, we simply keep counting, and attempt to wake up N threads in a single wait queue whenever there is enough space for a batch. Waking up less than batch_wake shouldn't be a problem, because we haven't changed the conditions for wake up, and the existing batch calculation guarantees at least enough remaining completions to wake up a batch for each queue at any time. Performance-wise, one should expect very similar performance to the original algorithm for the case where there is no queueing. In both the old algorithm and this implementation, the first thing is to check ws_active, which bails out if there is no queueing to be managed. In the new code, we took care to avoid accounting completions and wakeups when there is no queueing, to not pay the cost of atomic operations unnecessarily, since it doesn't skew the numbers. For more interesting cases, where there is queueing, we need to take into account the cross-communication of the atomic operations. I've been benchmarking by running parallel fio jobs against a single hctx nullb in different hardware queue depth scenarios, and verifying both IOPS and queueing. Each experiment was repeated 5 times on a 20-CPU box, with 20 parallel jobs. fio was issuing fixed-size randwrites with qd=64 against nullb, varying only the hardware queue length per test. queue size 2 4 8 16 32 64 6.1-rc2 1681.1K (1.6K) 2633.0K (12.7K) 6940.8K (16.3K) 8172.3K (617.5K) 8391.7K (367.1K) 8606.1K (351.2K) patched 1721.8K (15.1K) 3016.7K (3.8K) 7543.0K (89.4K) 8132.5K (303.4K) 8324.2K (230.6K) 8401.8K (284.7K) The following is a similar experiment, ran against a nullb with a single bitmap shared by 20 hctx spread across 2 NUMA nodes. This has 40 parallel fio jobs operating on the same device queue size 2 4 8 16 32 64 6.1-rc2 1081.0K (2.3K) 957.2K (1.5K) 1699.1K (5.7K) 6178.2K (124.6K) 12227.9K (37.7K) 13286.6K (92.9K) patched 1081.8K (2.8K) 1316.5K (5.4K) 2364.4K (1.8K) 6151.4K (20.0K) 11893.6K (17.5K) 12385.6K (18.4K) It has also survived blktests and a 12h-stress run against nullb. I also ran the code against nvme and a scsi SSD, and I didn't observe performance regression in those. If there are other tests you think I should run, please let me know and I will follow up with results. [1] https://lore.kernel.org/all/aef9de29-e9f5-259a-f8be-12d1b734e72@google.com/ Cc: Hugh Dickins <hughd@google.com> Cc: Keith Busch <kbusch@kernel.org> Cc: Liu Song <liusong@linux.alibaba.com> Suggested-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de> Link: https://lore.kernel.org/r/20221105231055.25953-1-krisman@suse.de Signed-off-by: Jens Axboe <axboe@kernel.dk>
639 lines
18 KiB
C
639 lines
18 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Fast and scalable bitmaps.
|
|
*
|
|
* Copyright (C) 2016 Facebook
|
|
* Copyright (C) 2013-2014 Jens Axboe
|
|
*/
|
|
|
|
#ifndef __LINUX_SCALE_BITMAP_H
|
|
#define __LINUX_SCALE_BITMAP_H
|
|
|
|
#include <linux/atomic.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/cache.h>
|
|
#include <linux/list.h>
|
|
#include <linux/log2.h>
|
|
#include <linux/minmax.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/types.h>
|
|
#include <linux/wait.h>
|
|
|
|
struct seq_file;
|
|
|
|
/**
|
|
* struct sbitmap_word - Word in a &struct sbitmap.
|
|
*/
|
|
struct sbitmap_word {
|
|
/**
|
|
* @word: word holding free bits
|
|
*/
|
|
unsigned long word;
|
|
|
|
/**
|
|
* @cleared: word holding cleared bits
|
|
*/
|
|
unsigned long cleared ____cacheline_aligned_in_smp;
|
|
} ____cacheline_aligned_in_smp;
|
|
|
|
/**
|
|
* struct sbitmap - Scalable bitmap.
|
|
*
|
|
* A &struct sbitmap is spread over multiple cachelines to avoid ping-pong. This
|
|
* trades off higher memory usage for better scalability.
|
|
*/
|
|
struct sbitmap {
|
|
/**
|
|
* @depth: Number of bits used in the whole bitmap.
|
|
*/
|
|
unsigned int depth;
|
|
|
|
/**
|
|
* @shift: log2(number of bits used per word)
|
|
*/
|
|
unsigned int shift;
|
|
|
|
/**
|
|
* @map_nr: Number of words (cachelines) being used for the bitmap.
|
|
*/
|
|
unsigned int map_nr;
|
|
|
|
/**
|
|
* @round_robin: Allocate bits in strict round-robin order.
|
|
*/
|
|
bool round_robin;
|
|
|
|
/**
|
|
* @map: Allocated bitmap.
|
|
*/
|
|
struct sbitmap_word *map;
|
|
|
|
/*
|
|
* @alloc_hint: Cache of last successfully allocated or freed bit.
|
|
*
|
|
* This is per-cpu, which allows multiple users to stick to different
|
|
* cachelines until the map is exhausted.
|
|
*/
|
|
unsigned int __percpu *alloc_hint;
|
|
};
|
|
|
|
#define SBQ_WAIT_QUEUES 8
|
|
#define SBQ_WAKE_BATCH 8
|
|
|
|
/**
|
|
* struct sbq_wait_state - Wait queue in a &struct sbitmap_queue.
|
|
*/
|
|
struct sbq_wait_state {
|
|
/**
|
|
* @wait: Wait queue.
|
|
*/
|
|
wait_queue_head_t wait;
|
|
} ____cacheline_aligned_in_smp;
|
|
|
|
/**
|
|
* struct sbitmap_queue - Scalable bitmap with the added ability to wait on free
|
|
* bits.
|
|
*
|
|
* A &struct sbitmap_queue uses multiple wait queues and rolling wakeups to
|
|
* avoid contention on the wait queue spinlock. This ensures that we don't hit a
|
|
* scalability wall when we run out of free bits and have to start putting tasks
|
|
* to sleep.
|
|
*/
|
|
struct sbitmap_queue {
|
|
/**
|
|
* @sb: Scalable bitmap.
|
|
*/
|
|
struct sbitmap sb;
|
|
|
|
/**
|
|
* @wake_batch: Number of bits which must be freed before we wake up any
|
|
* waiters.
|
|
*/
|
|
unsigned int wake_batch;
|
|
|
|
/**
|
|
* @wake_index: Next wait queue in @ws to wake up.
|
|
*/
|
|
atomic_t wake_index;
|
|
|
|
/**
|
|
* @ws: Wait queues.
|
|
*/
|
|
struct sbq_wait_state *ws;
|
|
|
|
/*
|
|
* @ws_active: count of currently active ws waitqueues
|
|
*/
|
|
atomic_t ws_active;
|
|
|
|
/**
|
|
* @min_shallow_depth: The minimum shallow depth which may be passed to
|
|
* sbitmap_queue_get_shallow()
|
|
*/
|
|
unsigned int min_shallow_depth;
|
|
|
|
/**
|
|
* @completion_cnt: Number of bits cleared passed to the
|
|
* wakeup function.
|
|
*/
|
|
atomic_t completion_cnt;
|
|
|
|
/**
|
|
* @wakeup_cnt: Number of thread wake ups issued.
|
|
*/
|
|
atomic_t wakeup_cnt;
|
|
};
|
|
|
|
/**
|
|
* sbitmap_init_node() - Initialize a &struct sbitmap on a specific memory node.
|
|
* @sb: Bitmap to initialize.
|
|
* @depth: Number of bits to allocate.
|
|
* @shift: Use 2^@shift bits per word in the bitmap; if a negative number if
|
|
* given, a good default is chosen.
|
|
* @flags: Allocation flags.
|
|
* @node: Memory node to allocate on.
|
|
* @round_robin: If true, be stricter about allocation order; always allocate
|
|
* starting from the last allocated bit. This is less efficient
|
|
* than the default behavior (false).
|
|
* @alloc_hint: If true, apply percpu hint for where to start searching for
|
|
* a free bit.
|
|
*
|
|
* Return: Zero on success or negative errno on failure.
|
|
*/
|
|
int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
|
|
gfp_t flags, int node, bool round_robin, bool alloc_hint);
|
|
|
|
/* sbitmap internal helper */
|
|
static inline unsigned int __map_depth(const struct sbitmap *sb, int index)
|
|
{
|
|
if (index == sb->map_nr - 1)
|
|
return sb->depth - (index << sb->shift);
|
|
return 1U << sb->shift;
|
|
}
|
|
|
|
/**
|
|
* sbitmap_free() - Free memory used by a &struct sbitmap.
|
|
* @sb: Bitmap to free.
|
|
*/
|
|
static inline void sbitmap_free(struct sbitmap *sb)
|
|
{
|
|
free_percpu(sb->alloc_hint);
|
|
kvfree(sb->map);
|
|
sb->map = NULL;
|
|
}
|
|
|
|
/**
|
|
* sbitmap_resize() - Resize a &struct sbitmap.
|
|
* @sb: Bitmap to resize.
|
|
* @depth: New number of bits to resize to.
|
|
*
|
|
* Doesn't reallocate anything. It's up to the caller to ensure that the new
|
|
* depth doesn't exceed the depth that the sb was initialized with.
|
|
*/
|
|
void sbitmap_resize(struct sbitmap *sb, unsigned int depth);
|
|
|
|
/**
|
|
* sbitmap_get() - Try to allocate a free bit from a &struct sbitmap.
|
|
* @sb: Bitmap to allocate from.
|
|
*
|
|
* This operation provides acquire barrier semantics if it succeeds.
|
|
*
|
|
* Return: Non-negative allocated bit number if successful, -1 otherwise.
|
|
*/
|
|
int sbitmap_get(struct sbitmap *sb);
|
|
|
|
/**
|
|
* sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap,
|
|
* limiting the depth used from each word.
|
|
* @sb: Bitmap to allocate from.
|
|
* @shallow_depth: The maximum number of bits to allocate from a single word.
|
|
*
|
|
* This rather specific operation allows for having multiple users with
|
|
* different allocation limits. E.g., there can be a high-priority class that
|
|
* uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow()
|
|
* with a @shallow_depth of (1 << (@sb->shift - 1)). Then, the low-priority
|
|
* class can only allocate half of the total bits in the bitmap, preventing it
|
|
* from starving out the high-priority class.
|
|
*
|
|
* Return: Non-negative allocated bit number if successful, -1 otherwise.
|
|
*/
|
|
int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth);
|
|
|
|
/**
|
|
* sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap.
|
|
* @sb: Bitmap to check.
|
|
*
|
|
* Return: true if any bit in the bitmap is set, false otherwise.
|
|
*/
|
|
bool sbitmap_any_bit_set(const struct sbitmap *sb);
|
|
|
|
#define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift)
|
|
#define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U))
|
|
|
|
typedef bool (*sb_for_each_fn)(struct sbitmap *, unsigned int, void *);
|
|
|
|
/**
|
|
* __sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap.
|
|
* @start: Where to start the iteration.
|
|
* @sb: Bitmap to iterate over.
|
|
* @fn: Callback. Should return true to continue or false to break early.
|
|
* @data: Pointer to pass to callback.
|
|
*
|
|
* This is inline even though it's non-trivial so that the function calls to the
|
|
* callback will hopefully get optimized away.
|
|
*/
|
|
static inline void __sbitmap_for_each_set(struct sbitmap *sb,
|
|
unsigned int start,
|
|
sb_for_each_fn fn, void *data)
|
|
{
|
|
unsigned int index;
|
|
unsigned int nr;
|
|
unsigned int scanned = 0;
|
|
|
|
if (start >= sb->depth)
|
|
start = 0;
|
|
index = SB_NR_TO_INDEX(sb, start);
|
|
nr = SB_NR_TO_BIT(sb, start);
|
|
|
|
while (scanned < sb->depth) {
|
|
unsigned long word;
|
|
unsigned int depth = min_t(unsigned int,
|
|
__map_depth(sb, index) - nr,
|
|
sb->depth - scanned);
|
|
|
|
scanned += depth;
|
|
word = sb->map[index].word & ~sb->map[index].cleared;
|
|
if (!word)
|
|
goto next;
|
|
|
|
/*
|
|
* On the first iteration of the outer loop, we need to add the
|
|
* bit offset back to the size of the word for find_next_bit().
|
|
* On all other iterations, nr is zero, so this is a noop.
|
|
*/
|
|
depth += nr;
|
|
while (1) {
|
|
nr = find_next_bit(&word, depth, nr);
|
|
if (nr >= depth)
|
|
break;
|
|
if (!fn(sb, (index << sb->shift) + nr, data))
|
|
return;
|
|
|
|
nr++;
|
|
}
|
|
next:
|
|
nr = 0;
|
|
if (++index >= sb->map_nr)
|
|
index = 0;
|
|
}
|
|
}
|
|
|
|
/**
|
|
* sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap.
|
|
* @sb: Bitmap to iterate over.
|
|
* @fn: Callback. Should return true to continue or false to break early.
|
|
* @data: Pointer to pass to callback.
|
|
*/
|
|
static inline void sbitmap_for_each_set(struct sbitmap *sb, sb_for_each_fn fn,
|
|
void *data)
|
|
{
|
|
__sbitmap_for_each_set(sb, 0, fn, data);
|
|
}
|
|
|
|
static inline unsigned long *__sbitmap_word(struct sbitmap *sb,
|
|
unsigned int bitnr)
|
|
{
|
|
return &sb->map[SB_NR_TO_INDEX(sb, bitnr)].word;
|
|
}
|
|
|
|
/* Helpers equivalent to the operations in asm/bitops.h and linux/bitmap.h */
|
|
|
|
static inline void sbitmap_set_bit(struct sbitmap *sb, unsigned int bitnr)
|
|
{
|
|
set_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
|
|
}
|
|
|
|
static inline void sbitmap_clear_bit(struct sbitmap *sb, unsigned int bitnr)
|
|
{
|
|
clear_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
|
|
}
|
|
|
|
/*
|
|
* This one is special, since it doesn't actually clear the bit, rather it
|
|
* sets the corresponding bit in the ->cleared mask instead. Paired with
|
|
* the caller doing sbitmap_deferred_clear() if a given index is full, which
|
|
* will clear the previously freed entries in the corresponding ->word.
|
|
*/
|
|
static inline void sbitmap_deferred_clear_bit(struct sbitmap *sb, unsigned int bitnr)
|
|
{
|
|
unsigned long *addr = &sb->map[SB_NR_TO_INDEX(sb, bitnr)].cleared;
|
|
|
|
set_bit(SB_NR_TO_BIT(sb, bitnr), addr);
|
|
}
|
|
|
|
/*
|
|
* Pair of sbitmap_get, and this one applies both cleared bit and
|
|
* allocation hint.
|
|
*/
|
|
static inline void sbitmap_put(struct sbitmap *sb, unsigned int bitnr)
|
|
{
|
|
sbitmap_deferred_clear_bit(sb, bitnr);
|
|
|
|
if (likely(sb->alloc_hint && !sb->round_robin && bitnr < sb->depth))
|
|
*raw_cpu_ptr(sb->alloc_hint) = bitnr;
|
|
}
|
|
|
|
static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)
|
|
{
|
|
return test_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
|
|
}
|
|
|
|
static inline int sbitmap_calculate_shift(unsigned int depth)
|
|
{
|
|
int shift = ilog2(BITS_PER_LONG);
|
|
|
|
/*
|
|
* If the bitmap is small, shrink the number of bits per word so
|
|
* we spread over a few cachelines, at least. If less than 4
|
|
* bits, just forget about it, it's not going to work optimally
|
|
* anyway.
|
|
*/
|
|
if (depth >= 4) {
|
|
while ((4U << shift) > depth)
|
|
shift--;
|
|
}
|
|
|
|
return shift;
|
|
}
|
|
|
|
/**
|
|
* sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file.
|
|
* @sb: Bitmap to show.
|
|
* @m: struct seq_file to write to.
|
|
*
|
|
* This is intended for debugging. The format may change at any time.
|
|
*/
|
|
void sbitmap_show(struct sbitmap *sb, struct seq_file *m);
|
|
|
|
|
|
/**
|
|
* sbitmap_weight() - Return how many set and not cleared bits in a &struct
|
|
* sbitmap.
|
|
* @sb: Bitmap to check.
|
|
*
|
|
* Return: How many set and not cleared bits set
|
|
*/
|
|
unsigned int sbitmap_weight(const struct sbitmap *sb);
|
|
|
|
/**
|
|
* sbitmap_bitmap_show() - Write a hex dump of a &struct sbitmap to a &struct
|
|
* seq_file.
|
|
* @sb: Bitmap to show.
|
|
* @m: struct seq_file to write to.
|
|
*
|
|
* This is intended for debugging. The output isn't guaranteed to be internally
|
|
* consistent.
|
|
*/
|
|
void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m);
|
|
|
|
/**
|
|
* sbitmap_queue_init_node() - Initialize a &struct sbitmap_queue on a specific
|
|
* memory node.
|
|
* @sbq: Bitmap queue to initialize.
|
|
* @depth: See sbitmap_init_node().
|
|
* @shift: See sbitmap_init_node().
|
|
* @round_robin: See sbitmap_get().
|
|
* @flags: Allocation flags.
|
|
* @node: Memory node to allocate on.
|
|
*
|
|
* Return: Zero on success or negative errno on failure.
|
|
*/
|
|
int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
|
|
int shift, bool round_robin, gfp_t flags, int node);
|
|
|
|
/**
|
|
* sbitmap_queue_free() - Free memory used by a &struct sbitmap_queue.
|
|
*
|
|
* @sbq: Bitmap queue to free.
|
|
*/
|
|
static inline void sbitmap_queue_free(struct sbitmap_queue *sbq)
|
|
{
|
|
kfree(sbq->ws);
|
|
sbitmap_free(&sbq->sb);
|
|
}
|
|
|
|
/**
|
|
* sbitmap_queue_recalculate_wake_batch() - Recalculate wake batch
|
|
* @sbq: Bitmap queue to recalculate wake batch.
|
|
* @users: Number of shares.
|
|
*
|
|
* Like sbitmap_queue_update_wake_batch(), this will calculate wake batch
|
|
* by depth. This interface is for HCTX shared tags or queue shared tags.
|
|
*/
|
|
void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq,
|
|
unsigned int users);
|
|
|
|
/**
|
|
* sbitmap_queue_resize() - Resize a &struct sbitmap_queue.
|
|
* @sbq: Bitmap queue to resize.
|
|
* @depth: New number of bits to resize to.
|
|
*
|
|
* Like sbitmap_resize(), this doesn't reallocate anything. It has to do
|
|
* some extra work on the &struct sbitmap_queue, so it's not safe to just
|
|
* resize the underlying &struct sbitmap.
|
|
*/
|
|
void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth);
|
|
|
|
/**
|
|
* __sbitmap_queue_get() - Try to allocate a free bit from a &struct
|
|
* sbitmap_queue with preemption already disabled.
|
|
* @sbq: Bitmap queue to allocate from.
|
|
*
|
|
* Return: Non-negative allocated bit number if successful, -1 otherwise.
|
|
*/
|
|
int __sbitmap_queue_get(struct sbitmap_queue *sbq);
|
|
|
|
/**
|
|
* __sbitmap_queue_get_batch() - Try to allocate a batch of free bits
|
|
* @sbq: Bitmap queue to allocate from.
|
|
* @nr_tags: number of tags requested
|
|
* @offset: offset to add to returned bits
|
|
*
|
|
* Return: Mask of allocated tags, 0 if none are found. Each tag allocated is
|
|
* a bit in the mask returned, and the caller must add @offset to the value to
|
|
* get the absolute tag value.
|
|
*/
|
|
unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
|
|
unsigned int *offset);
|
|
|
|
/**
|
|
* sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
|
|
* sbitmap_queue, limiting the depth used from each word, with preemption
|
|
* already disabled.
|
|
* @sbq: Bitmap queue to allocate from.
|
|
* @shallow_depth: The maximum number of bits to allocate from a single word.
|
|
* See sbitmap_get_shallow().
|
|
*
|
|
* If you call this, make sure to call sbitmap_queue_min_shallow_depth() after
|
|
* initializing @sbq.
|
|
*
|
|
* Return: Non-negative allocated bit number if successful, -1 otherwise.
|
|
*/
|
|
int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
|
|
unsigned int shallow_depth);
|
|
|
|
/**
|
|
* sbitmap_queue_get() - Try to allocate a free bit from a &struct
|
|
* sbitmap_queue.
|
|
* @sbq: Bitmap queue to allocate from.
|
|
* @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to
|
|
* sbitmap_queue_clear()).
|
|
*
|
|
* Return: Non-negative allocated bit number if successful, -1 otherwise.
|
|
*/
|
|
static inline int sbitmap_queue_get(struct sbitmap_queue *sbq,
|
|
unsigned int *cpu)
|
|
{
|
|
int nr;
|
|
|
|
*cpu = get_cpu();
|
|
nr = __sbitmap_queue_get(sbq);
|
|
put_cpu();
|
|
return nr;
|
|
}
|
|
|
|
/**
|
|
* sbitmap_queue_min_shallow_depth() - Inform a &struct sbitmap_queue of the
|
|
* minimum shallow depth that will be used.
|
|
* @sbq: Bitmap queue in question.
|
|
* @min_shallow_depth: The minimum shallow depth that will be passed to
|
|
* sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow().
|
|
*
|
|
* sbitmap_queue_clear() batches wakeups as an optimization. The batch size
|
|
* depends on the depth of the bitmap. Since the shallow allocation functions
|
|
* effectively operate with a different depth, the shallow depth must be taken
|
|
* into account when calculating the batch size. This function must be called
|
|
* with the minimum shallow depth that will be used. Failure to do so can result
|
|
* in missed wakeups.
|
|
*/
|
|
void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq,
|
|
unsigned int min_shallow_depth);
|
|
|
|
/**
|
|
* sbitmap_queue_clear() - Free an allocated bit and wake up waiters on a
|
|
* &struct sbitmap_queue.
|
|
* @sbq: Bitmap to free from.
|
|
* @nr: Bit number to free.
|
|
* @cpu: CPU the bit was allocated on.
|
|
*/
|
|
void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
|
|
unsigned int cpu);
|
|
|
|
/**
|
|
* sbitmap_queue_clear_batch() - Free a batch of allocated bits
|
|
* &struct sbitmap_queue.
|
|
* @sbq: Bitmap to free from.
|
|
* @offset: offset for each tag in array
|
|
* @tags: array of tags
|
|
* @nr_tags: number of tags in array
|
|
*/
|
|
void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset,
|
|
int *tags, int nr_tags);
|
|
|
|
static inline int sbq_index_inc(int index)
|
|
{
|
|
return (index + 1) & (SBQ_WAIT_QUEUES - 1);
|
|
}
|
|
|
|
static inline void sbq_index_atomic_inc(atomic_t *index)
|
|
{
|
|
int old = atomic_read(index);
|
|
int new = sbq_index_inc(old);
|
|
atomic_cmpxchg(index, old, new);
|
|
}
|
|
|
|
/**
|
|
* sbq_wait_ptr() - Get the next wait queue to use for a &struct
|
|
* sbitmap_queue.
|
|
* @sbq: Bitmap queue to wait on.
|
|
* @wait_index: A counter per "user" of @sbq.
|
|
*/
|
|
static inline struct sbq_wait_state *sbq_wait_ptr(struct sbitmap_queue *sbq,
|
|
atomic_t *wait_index)
|
|
{
|
|
struct sbq_wait_state *ws;
|
|
|
|
ws = &sbq->ws[atomic_read(wait_index)];
|
|
sbq_index_atomic_inc(wait_index);
|
|
return ws;
|
|
}
|
|
|
|
/**
|
|
* sbitmap_queue_wake_all() - Wake up everything waiting on a &struct
|
|
* sbitmap_queue.
|
|
* @sbq: Bitmap queue to wake up.
|
|
*/
|
|
void sbitmap_queue_wake_all(struct sbitmap_queue *sbq);
|
|
|
|
/**
|
|
* sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue
|
|
* on a &struct sbitmap_queue.
|
|
* @sbq: Bitmap queue to wake up.
|
|
* @nr: Number of bits cleared.
|
|
*/
|
|
void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr);
|
|
|
|
/**
|
|
* sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct
|
|
* seq_file.
|
|
* @sbq: Bitmap queue to show.
|
|
* @m: struct seq_file to write to.
|
|
*
|
|
* This is intended for debugging. The format may change at any time.
|
|
*/
|
|
void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m);
|
|
|
|
struct sbq_wait {
|
|
struct sbitmap_queue *sbq; /* if set, sbq_wait is accounted */
|
|
struct wait_queue_entry wait;
|
|
};
|
|
|
|
#define DEFINE_SBQ_WAIT(name) \
|
|
struct sbq_wait name = { \
|
|
.sbq = NULL, \
|
|
.wait = { \
|
|
.private = current, \
|
|
.func = autoremove_wake_function, \
|
|
.entry = LIST_HEAD_INIT((name).wait.entry), \
|
|
} \
|
|
}
|
|
|
|
/*
|
|
* Wrapper around prepare_to_wait_exclusive(), which maintains some extra
|
|
* internal state.
|
|
*/
|
|
void sbitmap_prepare_to_wait(struct sbitmap_queue *sbq,
|
|
struct sbq_wait_state *ws,
|
|
struct sbq_wait *sbq_wait, int state);
|
|
|
|
/*
|
|
* Must be paired with sbitmap_prepare_to_wait().
|
|
*/
|
|
void sbitmap_finish_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws,
|
|
struct sbq_wait *sbq_wait);
|
|
|
|
/*
|
|
* Wrapper around add_wait_queue(), which maintains some extra internal state
|
|
*/
|
|
void sbitmap_add_wait_queue(struct sbitmap_queue *sbq,
|
|
struct sbq_wait_state *ws,
|
|
struct sbq_wait *sbq_wait);
|
|
|
|
/*
|
|
* Must be paired with sbitmap_add_wait_queue()
|
|
*/
|
|
void sbitmap_del_wait_queue(struct sbq_wait *sbq_wait);
|
|
|
|
#endif /* __LINUX_SCALE_BITMAP_H */
|