Commit 693ba15c authored by Matthew Wilcox's avatar Matthew Wilcox Committed by Martin K. Petersen

scsi: Remove percpu_ida

With its one user gone, remove the library code.
Signed-off-by: default avatarMatthew Wilcox <willy@infradead.org>
Reviewed-by: default avatarJens Axboe <axboe@kernel.dk>
Signed-off-by: default avatarMartin K. Petersen <martin.petersen@oracle.com>
parent 10e9cbb6
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __PERCPU_IDA_H__
#define __PERCPU_IDA_H__
#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/spinlock_types.h>
#include <linux/wait.h>
#include <linux/cpumask.h>
struct percpu_ida_cpu;
struct percpu_ida {
/*
* number of tags available to be allocated, as passed to
* percpu_ida_init()
*/
unsigned nr_tags;
unsigned percpu_max_size;
unsigned percpu_batch_size;
struct percpu_ida_cpu __percpu *tag_cpu;
/*
* Bitmap of cpus that (may) have tags on their percpu freelists:
* steal_tags() uses this to decide when to steal tags, and which cpus
* to try stealing from.
*
* It's ok for a freelist to be empty when its bit is set - steal_tags()
* will just keep looking - but the bitmap _must_ be set whenever a
* percpu freelist does have tags.
*/
cpumask_t cpus_have_tags;
struct {
spinlock_t lock;
/*
* When we go to steal tags from another cpu (see steal_tags()),
* we want to pick a cpu at random. Cycling through them every
* time we steal is a bit easier and more or less equivalent:
*/
unsigned cpu_last_stolen;
/* For sleeping on allocation failure */
wait_queue_head_t wait;
/*
* Global freelist - it's a stack where nr_free points to the
* top
*/
unsigned nr_free;
unsigned *freelist;
} ____cacheline_aligned_in_smp;
};
/*
* Number of tags we move between the percpu freelist and the global freelist at
* a time
*/
#define IDA_DEFAULT_PCPU_BATCH_MOVE 32U
/* Max size of percpu freelist, */
#define IDA_DEFAULT_PCPU_SIZE ((IDA_DEFAULT_PCPU_BATCH_MOVE * 3) / 2)
int percpu_ida_alloc(struct percpu_ida *pool, int state);
void percpu_ida_free(struct percpu_ida *pool, unsigned tag);
void percpu_ida_destroy(struct percpu_ida *pool);
int __percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags,
unsigned long max_size, unsigned long batch_size);
static inline int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags)
{
return __percpu_ida_init(pool, nr_tags, IDA_DEFAULT_PCPU_SIZE,
IDA_DEFAULT_PCPU_BATCH_MOVE);
}
typedef int (*percpu_ida_cb)(unsigned, void *);
int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
void *data);
unsigned percpu_ida_free_tags(struct percpu_ida *pool, int cpu);
#endif /* __PERCPU_IDA_H__ */
......@@ -40,7 +40,7 @@ obj-y += bcd.o div64.o sort.o parser.o debug_locks.o random32.o \
bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \
gcd.o lcm.o list_sort.o uuid.o flex_array.o iov_iter.o clz_ctz.o \
bsearch.o find_bit.o llist.o memweight.o kfifo.o \
percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o \
percpu-refcount.o rhashtable.o reciprocal_div.o \
once.o refcount.o usercopy.o errseq.o bucket_locks.o
obj-$(CONFIG_STRING_SELFTEST) += test_string.o
obj-y += string_helpers.o
......
/*
* Percpu IDA library
*
* Copyright (C) 2013 Datera, Inc. Kent Overstreet
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation; either version 2, or (at
* your option) any later version.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <linux/mm.h>
#include <linux/bitmap.h>
#include <linux/bitops.h>
#include <linux/bug.h>
#include <linux/err.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/sched/signal.h>
#include <linux/string.h>
#include <linux/spinlock.h>
#include <linux/percpu_ida.h>
struct percpu_ida_cpu {
/*
* Even though this is percpu, we need a lock for tag stealing by remote
* CPUs:
*/
spinlock_t lock;
/* nr_free/freelist form a stack of free IDs */
unsigned nr_free;
unsigned freelist[];
};
static inline void move_tags(unsigned *dst, unsigned *dst_nr,
unsigned *src, unsigned *src_nr,
unsigned nr)
{
*src_nr -= nr;
memcpy(dst + *dst_nr, src + *src_nr, sizeof(unsigned) * nr);
*dst_nr += nr;
}
/*
* Try to steal tags from a remote cpu's percpu freelist.
*
* We first check how many percpu freelists have tags
*
* Then we iterate through the cpus until we find some tags - we don't attempt
* to find the "best" cpu to steal from, to keep cacheline bouncing to a
* minimum.
*/
static inline void steal_tags(struct percpu_ida *pool,
struct percpu_ida_cpu *tags)
{
unsigned cpus_have_tags, cpu = pool->cpu_last_stolen;
struct percpu_ida_cpu *remote;
for (cpus_have_tags = cpumask_weight(&pool->cpus_have_tags);
cpus_have_tags; cpus_have_tags--) {
cpu = cpumask_next(cpu, &pool->cpus_have_tags);
if (cpu >= nr_cpu_ids) {
cpu = cpumask_first(&pool->cpus_have_tags);
if (cpu >= nr_cpu_ids)
BUG();
}
pool->cpu_last_stolen = cpu;
remote = per_cpu_ptr(pool->tag_cpu, cpu);
cpumask_clear_cpu(cpu, &pool->cpus_have_tags);
if (remote == tags)
continue;
spin_lock(&remote->lock);
if (remote->nr_free) {
memcpy(tags->freelist,
remote->freelist,
sizeof(unsigned) * remote->nr_free);
tags->nr_free = remote->nr_free;
remote->nr_free = 0;
}
spin_unlock(&remote->lock);
if (tags->nr_free)
break;
}
}
/*
* Pop up to IDA_PCPU_BATCH_MOVE IDs off the global freelist, and push them onto
* our percpu freelist:
*/
static inline void alloc_global_tags(struct percpu_ida *pool,
struct percpu_ida_cpu *tags)
{
move_tags(tags->freelist, &tags->nr_free,
pool->freelist, &pool->nr_free,
min(pool->nr_free, pool->percpu_batch_size));
}
/**
* percpu_ida_alloc - allocate a tag
* @pool: pool to allocate from
* @state: task state for prepare_to_wait
*
* Returns a tag - an integer in the range [0..nr_tags) (passed to
* tag_pool_init()), or otherwise -ENOSPC on allocation failure.
*
* Safe to be called from interrupt context (assuming it isn't passed
* TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, of course).
*
* @gfp indicates whether or not to wait until a free id is available (it's not
* used for internal memory allocations); thus if passed __GFP_RECLAIM we may sleep
* however long it takes until another thread frees an id (same semantics as a
* mempool).
*
* Will not fail if passed TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE.
*/
int percpu_ida_alloc(struct percpu_ida *pool, int state)
{
DEFINE_WAIT(wait);
struct percpu_ida_cpu *tags;
unsigned long flags;
int tag = -ENOSPC;
tags = raw_cpu_ptr(pool->tag_cpu);
spin_lock_irqsave(&tags->lock, flags);
/* Fastpath */
if (likely(tags->nr_free >= 0)) {
tag = tags->freelist[--tags->nr_free];
spin_unlock_irqrestore(&tags->lock, flags);
return tag;
}
spin_unlock_irqrestore(&tags->lock, flags);
while (1) {
spin_lock_irqsave(&pool->lock, flags);
tags = this_cpu_ptr(pool->tag_cpu);
/*
* prepare_to_wait() must come before steal_tags(), in case
* percpu_ida_free() on another cpu flips a bit in
* cpus_have_tags
*
* global lock held and irqs disabled, don't need percpu lock
*/
if (state != TASK_RUNNING)
prepare_to_wait(&pool->wait, &wait, state);
if (!tags->nr_free)
alloc_global_tags(pool, tags);
if (!tags->nr_free)
steal_tags(pool, tags);
if (tags->nr_free) {
tag = tags->freelist[--tags->nr_free];
if (tags->nr_free)
cpumask_set_cpu(smp_processor_id(),
&pool->cpus_have_tags);
}
spin_unlock_irqrestore(&pool->lock, flags);
if (tag >= 0 || state == TASK_RUNNING)
break;
if (signal_pending_state(state, current)) {
tag = -ERESTARTSYS;
break;
}
schedule();
}
if (state != TASK_RUNNING)
finish_wait(&pool->wait, &wait);
return tag;
}
EXPORT_SYMBOL_GPL(percpu_ida_alloc);
/**
* percpu_ida_free - free a tag
* @pool: pool @tag was allocated from
* @tag: a tag previously allocated with percpu_ida_alloc()
*
* Safe to be called from interrupt context.
*/
void percpu_ida_free(struct percpu_ida *pool, unsigned tag)
{
struct percpu_ida_cpu *tags;
unsigned long flags;
unsigned nr_free;
BUG_ON(tag >= pool->nr_tags);
tags = raw_cpu_ptr(pool->tag_cpu);
spin_lock_irqsave(&tags->lock, flags);
tags->freelist[tags->nr_free++] = tag;
nr_free = tags->nr_free;
if (nr_free == 1) {
cpumask_set_cpu(smp_processor_id(),
&pool->cpus_have_tags);
wake_up(&pool->wait);
}
spin_unlock_irqrestore(&tags->lock, flags);
if (nr_free == pool->percpu_max_size) {
spin_lock_irqsave(&pool->lock, flags);
spin_lock(&tags->lock);
if (tags->nr_free == pool->percpu_max_size) {
move_tags(pool->freelist, &pool->nr_free,
tags->freelist, &tags->nr_free,
pool->percpu_batch_size);
wake_up(&pool->wait);
}
spin_unlock(&tags->lock);
spin_unlock_irqrestore(&pool->lock, flags);
}
}
EXPORT_SYMBOL_GPL(percpu_ida_free);
/**
* percpu_ida_destroy - release a tag pool's resources
* @pool: pool to free
*
* Frees the resources allocated by percpu_ida_init().
*/
void percpu_ida_destroy(struct percpu_ida *pool)
{
free_percpu(pool->tag_cpu);
free_pages((unsigned long) pool->freelist,
get_order(pool->nr_tags * sizeof(unsigned)));
}
EXPORT_SYMBOL_GPL(percpu_ida_destroy);
/**
* percpu_ida_init - initialize a percpu tag pool
* @pool: pool to initialize
* @nr_tags: number of tags that will be available for allocation
*
* Initializes @pool so that it can be used to allocate tags - integers in the
* range [0, nr_tags). Typically, they'll be used by driver code to refer to a
* preallocated array of tag structures.
*
* Allocation is percpu, but sharding is limited by nr_tags - for best
* performance, the workload should not span more cpus than nr_tags / 128.
*/
int __percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags,
unsigned long max_size, unsigned long batch_size)
{
unsigned i, cpu, order;
memset(pool, 0, sizeof(*pool));
init_waitqueue_head(&pool->wait);
spin_lock_init(&pool->lock);
pool->nr_tags = nr_tags;
pool->percpu_max_size = max_size;
pool->percpu_batch_size = batch_size;
/* Guard against overflow */
if (nr_tags > (unsigned) INT_MAX + 1) {
pr_err("percpu_ida_init(): nr_tags too large\n");
return -EINVAL;
}
order = get_order(nr_tags * sizeof(unsigned));
pool->freelist = (void *) __get_free_pages(GFP_KERNEL, order);
if (!pool->freelist)
return -ENOMEM;
for (i = 0; i < nr_tags; i++)
pool->freelist[i] = i;
pool->nr_free = nr_tags;
pool->tag_cpu = __alloc_percpu(sizeof(struct percpu_ida_cpu) +
pool->percpu_max_size * sizeof(unsigned),
sizeof(unsigned));
if (!pool->tag_cpu)
goto err;
for_each_possible_cpu(cpu)
spin_lock_init(&per_cpu_ptr(pool->tag_cpu, cpu)->lock);
return 0;
err:
percpu_ida_destroy(pool);
return -ENOMEM;
}
EXPORT_SYMBOL_GPL(__percpu_ida_init);
/**
* percpu_ida_for_each_free - iterate free ids of a pool
* @pool: pool to iterate
* @fn: interate callback function
* @data: parameter for @fn
*
* Note, this doesn't guarantee to iterate all free ids restrictly. Some free
* ids might be missed, some might be iterated duplicated, and some might
* be iterated and not free soon.
*/
int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
void *data)
{
unsigned long flags;
struct percpu_ida_cpu *remote;
unsigned cpu, i, err = 0;
for_each_possible_cpu(cpu) {
remote = per_cpu_ptr(pool->tag_cpu, cpu);
spin_lock_irqsave(&remote->lock, flags);
for (i = 0; i < remote->nr_free; i++) {
err = fn(remote->freelist[i], data);
if (err)
break;
}
spin_unlock_irqrestore(&remote->lock, flags);
if (err)
goto out;
}
spin_lock_irqsave(&pool->lock, flags);
for (i = 0; i < pool->nr_free; i++) {
err = fn(pool->freelist[i], data);
if (err)
break;
}
spin_unlock_irqrestore(&pool->lock, flags);
out:
return err;
}
EXPORT_SYMBOL_GPL(percpu_ida_for_each_free);
/**
* percpu_ida_free_tags - return free tags number of a specific cpu or global pool
* @pool: pool related
* @cpu: specific cpu or global pool if @cpu == nr_cpu_ids
*
* Note: this just returns a snapshot of free tags number.
*/
unsigned percpu_ida_free_tags(struct percpu_ida *pool, int cpu)
{
struct percpu_ida_cpu *remote;
if (cpu == nr_cpu_ids)
return pool->nr_free;
remote = per_cpu_ptr(pool->tag_cpu, cpu);
return remote->nr_free;
}
EXPORT_SYMBOL_GPL(percpu_ida_free_tags);
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment