linux/block/blk-mq-tag.c
Linus Torvalds 5e57dc8110 Merge branch 'for-linus' of git://git.kernel.dk/linux-block
Pull block IO fixes from Jens Axboe:
 "Second round of updates and fixes for 3.14-rc2.  Most of this stuff
  has been queued up for a while.  The notable exception is the blk-mq
  changes, which are naturally a bit more in flux still.

  The pull request contains:

   - Two bug fixes for the new immutable vecs, causing crashes with raid
     or swap.  From Kent.

   - Various blk-mq tweaks and fixes from Christoph.  A fix for
     integrity bio's from Nic.

   - A few bcache fixes from Kent and Darrick Wong.

   - xen-blk{front,back} fixes from David Vrabel, Matt Rushton, Nicolas
     Swenson, and Roger Pau Monne.

   - Fix for a vec miscount with integrity vectors from Martin.

   - Minor annotations or fixes from Masanari Iida and Rashika Kheria.

   - Tweak to null_blk to do more normal FIFO processing of requests
     from Shlomo Pongratz.

   - Elevator switching bypass fix from Tejun.

   - Softlockup in blkdev_issue_discard() fix when !CONFIG_PREEMPT from
     me"

* 'for-linus' of git://git.kernel.dk/linux-block: (31 commits)
  block: add cond_resched() to potentially long running ioctl discard loop
  xen-blkback: init persistent_purge_work work_struct
  blk-mq: pair blk_mq_start_request / blk_mq_requeue_request
  blk-mq: dont assume rq->errors is set when returning an error from ->queue_rq
  block: Fix cloning of discard/write same bios
  block: Fix type mismatch in ssize_t_blk_mq_tag_sysfs_show
  blk-mq: rework flush sequencing logic
  null_blk: use blk_complete_request and blk_mq_complete_request
  virtio_blk: use blk_mq_complete_request
  blk-mq: rework I/O completions
  fs: Add prototype declaration to appropriate header file include/linux/bio.h
  fs: Mark function as static in fs/bio-integrity.c
  block/null_blk: Fix completion processing from LIFO to FIFO
  block: Explicitly handle discard/write same segments
  block: Fix nr_vecs for inline integrity vectors
  blk-mq: Add bio_integrity setup to blk_mq_make_request
  blk-mq: initialize sg_reserved_size
  blk-mq: handle dma_drain_size
  blk-mq: divert __blk_put_request for MQ ops
  blk-mq: support at_head inserations for blk_execute_rq
  ...
2014-02-14 10:45:18 -08:00

206 lines
4.7 KiB
C

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/percpu_ida.h>
#include <linux/blk-mq.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-tag.h"
/*
* Per tagged queue (tag address space) map
*/
struct blk_mq_tags {
unsigned int nr_tags;
unsigned int nr_reserved_tags;
unsigned int nr_batch_move;
unsigned int nr_max_cache;
struct percpu_ida free_tags;
struct percpu_ida reserved_tags;
};
void blk_mq_wait_for_tags(struct blk_mq_tags *tags)
{
int tag = blk_mq_get_tag(tags, __GFP_WAIT, false);
blk_mq_put_tag(tags, tag);
}
bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
{
return !tags ||
percpu_ida_free_tags(&tags->free_tags, nr_cpu_ids) != 0;
}
static unsigned int __blk_mq_get_tag(struct blk_mq_tags *tags, gfp_t gfp)
{
int tag;
tag = percpu_ida_alloc(&tags->free_tags, (gfp & __GFP_WAIT) ?
TASK_UNINTERRUPTIBLE : TASK_RUNNING);
if (tag < 0)
return BLK_MQ_TAG_FAIL;
return tag + tags->nr_reserved_tags;
}
static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_tags *tags,
gfp_t gfp)
{
int tag;
if (unlikely(!tags->nr_reserved_tags)) {
WARN_ON_ONCE(1);
return BLK_MQ_TAG_FAIL;
}
tag = percpu_ida_alloc(&tags->reserved_tags, (gfp & __GFP_WAIT) ?
TASK_UNINTERRUPTIBLE : TASK_RUNNING);
if (tag < 0)
return BLK_MQ_TAG_FAIL;
return tag;
}
unsigned int blk_mq_get_tag(struct blk_mq_tags *tags, gfp_t gfp, bool reserved)
{
if (!reserved)
return __blk_mq_get_tag(tags, gfp);
return __blk_mq_get_reserved_tag(tags, gfp);
}
static void __blk_mq_put_tag(struct blk_mq_tags *tags, unsigned int tag)
{
BUG_ON(tag >= tags->nr_tags);
percpu_ida_free(&tags->free_tags, tag - tags->nr_reserved_tags);
}
static void __blk_mq_put_reserved_tag(struct blk_mq_tags *tags,
unsigned int tag)
{
BUG_ON(tag >= tags->nr_reserved_tags);
percpu_ida_free(&tags->reserved_tags, tag);
}
void blk_mq_put_tag(struct blk_mq_tags *tags, unsigned int tag)
{
if (tag >= tags->nr_reserved_tags)
__blk_mq_put_tag(tags, tag);
else
__blk_mq_put_reserved_tag(tags, tag);
}
static int __blk_mq_tag_iter(unsigned id, void *data)
{
unsigned long *tag_map = data;
__set_bit(id, tag_map);
return 0;
}
void blk_mq_tag_busy_iter(struct blk_mq_tags *tags,
void (*fn)(void *, unsigned long *), void *data)
{
unsigned long *tag_map;
size_t map_size;
map_size = ALIGN(tags->nr_tags, BITS_PER_LONG) / BITS_PER_LONG;
tag_map = kzalloc(map_size * sizeof(unsigned long), GFP_ATOMIC);
if (!tag_map)
return;
percpu_ida_for_each_free(&tags->free_tags, __blk_mq_tag_iter, tag_map);
if (tags->nr_reserved_tags)
percpu_ida_for_each_free(&tags->reserved_tags, __blk_mq_tag_iter,
tag_map);
fn(data, tag_map);
kfree(tag_map);
}
struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
unsigned int reserved_tags, int node)
{
unsigned int nr_tags, nr_cache;
struct blk_mq_tags *tags;
int ret;
if (total_tags > BLK_MQ_TAG_MAX) {
pr_err("blk-mq: tag depth too large\n");
return NULL;
}
tags = kzalloc_node(sizeof(*tags), GFP_KERNEL, node);
if (!tags)
return NULL;
nr_tags = total_tags - reserved_tags;
nr_cache = nr_tags / num_possible_cpus();
if (nr_cache < BLK_MQ_TAG_CACHE_MIN)
nr_cache = BLK_MQ_TAG_CACHE_MIN;
else if (nr_cache > BLK_MQ_TAG_CACHE_MAX)
nr_cache = BLK_MQ_TAG_CACHE_MAX;
tags->nr_tags = total_tags;
tags->nr_reserved_tags = reserved_tags;
tags->nr_max_cache = nr_cache;
tags->nr_batch_move = max(1u, nr_cache / 2);
ret = __percpu_ida_init(&tags->free_tags, tags->nr_tags -
tags->nr_reserved_tags,
tags->nr_max_cache,
tags->nr_batch_move);
if (ret)
goto err_free_tags;
if (reserved_tags) {
/*
* With max_cahe and batch set to 1, the allocator fallbacks to
* no cached. It's fine reserved tags allocation is slow.
*/
ret = __percpu_ida_init(&tags->reserved_tags, reserved_tags,
1, 1);
if (ret)
goto err_reserved_tags;
}
return tags;
err_reserved_tags:
percpu_ida_destroy(&tags->free_tags);
err_free_tags:
kfree(tags);
return NULL;
}
void blk_mq_free_tags(struct blk_mq_tags *tags)
{
percpu_ida_destroy(&tags->free_tags);
percpu_ida_destroy(&tags->reserved_tags);
kfree(tags);
}
ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page)
{
char *orig_page = page;
unsigned int cpu;
if (!tags)
return 0;
page += sprintf(page, "nr_tags=%u, reserved_tags=%u, batch_move=%u,"
" max_cache=%u\n", tags->nr_tags, tags->nr_reserved_tags,
tags->nr_batch_move, tags->nr_max_cache);
page += sprintf(page, "nr_free=%u, nr_reserved=%u\n",
percpu_ida_free_tags(&tags->free_tags, nr_cpu_ids),
percpu_ida_free_tags(&tags->reserved_tags, nr_cpu_ids));
for_each_possible_cpu(cpu) {
page += sprintf(page, " cpu%02u: nr_free=%u\n", cpu,
percpu_ida_free_tags(&tags->free_tags, cpu));
}
return page - orig_page;
}