@@ -65,7 +65,6 @@ Description of Contents:
3.2.3 I/O completion
3.2.4 Implications for drivers that do not interpret bios (don't handle
multiple segments)
- 3.2.5 Request command tagging
3.3 I/O submission
4. The I/O scheduler
5. Scalability related changes
@@ -708,93 +707,6 @@ is crossed on completion of a transfer. (The end*request* functions should
be used if only if the request has come down from block/bio path, not for
direct access requests which only specify rq->buffer without a valid rq->bio)
-3.2.5 Generic request command tagging
-
-3.2.5.1 Tag helpers
-
-Block now offers some simple generic functionality to help support command
-queueing (typically known as tagged command queueing), ie manage more than
-one outstanding command on a queue at any given time.
-
- blk_queue_init_tags(struct request_queue *q, int depth)
-
- Initialize internal command tagging structures for a maximum
- depth of 'depth'.
-
- blk_queue_free_tags((struct request_queue *q)
-
- Teardown tag info associated with the queue. This will be done
- automatically by block if blk_queue_cleanup() is called on a queue
- that is using tagging.
-
-The above are initialization and exit management, the main helpers during
-normal operations are:
-
- blk_queue_start_tag(struct request_queue *q, struct request *rq)
-
- Start tagged operation for this request. A free tag number between
- 0 and 'depth' is assigned to the request (rq->tag holds this number),
- and 'rq' is added to the internal tag management. If the maximum depth
- for this queue is already achieved (or if the tag wasn't started for
- some other reason), 1 is returned. Otherwise 0 is returned.
-
- blk_queue_end_tag(struct request_queue *q, struct request *rq)
-
- End tagged operation on this request. 'rq' is removed from the internal
- book keeping structures.
-
-To minimize struct request and queue overhead, the tag helpers utilize some
-of the same request members that are used for normal request queue management.
-This means that a request cannot both be an active tag and be on the queue
-list at the same time. blk_queue_start_tag() will remove the request, but
-the driver must remember to call blk_queue_end_tag() before signalling
-completion of the request to the block layer. This means ending tag
-operations before calling end_that_request_last()! For an example of a user
-of these helpers, see the IDE tagged command queueing support.
-
-3.2.5.2 Tag info
-
-Some block functions exist to query current tag status or to go from a
-tag number to the associated request. These are, in no particular order:
-
- blk_queue_tagged(q)
-
- Returns 1 if the queue 'q' is using tagging, 0 if not.
-
- blk_queue_tag_request(q, tag)
-
- Returns a pointer to the request associated with tag 'tag'.
-
- blk_queue_tag_depth(q)
-
- Return current queue depth.
-
- blk_queue_tag_queue(q)
-
- Returns 1 if the queue can accept a new queued command, 0 if we are
- at the maximum depth already.
-
- blk_queue_rq_tagged(rq)
-
- Returns 1 if the request 'rq' is tagged.
-
-3.2.5.2 Internal structure
-
-Internally, block manages tags in the blk_queue_tag structure:
-
- struct blk_queue_tag {
- struct request **tag_index; /* array or pointers to rq */
- unsigned long *tag_map; /* bitmap of free tags */
- struct list_head busy_list; /* fifo list of busy tags */
- int busy; /* queue depth */
- int max_depth; /* max queue depth */
- };
-
-Most of the above is simple and straight forward, however busy_list may need
-a bit of explaining. Normally we don't care too much about request ordering,
-but in the event of any barrier requests in the tag queue we need to ensure
-that requests are restarted in the order they were queue.
-
3.3 I/O Submission
The routine submit_bio() is used to submit a single io. Higher level i/o
@@ -3,7 +3,7 @@
# Makefile for the kernel block layer
#
-obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
+obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \
blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
@@ -1655,9 +1655,6 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
trace_block_rq_requeue(q, rq);
rq_qos_requeue(q, rq);
- if (rq->rq_flags & RQF_QUEUED)
- blk_queue_end_tag(q, rq);
-
BUG_ON(blk_queued_rq(rq));
elv_requeue_request(q, rq);
@@ -3172,9 +3169,6 @@ void blk_finish_request(struct request *req, blk_status_t error)
if (req->rq_flags & RQF_STATS)
blk_stat_add(req, now);
- if (req->rq_flags & RQF_QUEUED)
- blk_queue_end_tag(q, req);
-
BUG_ON(blk_queued_rq(req));
if (unlikely(laptop_mode) && !blk_rq_is_passthrough(req))
@@ -112,7 +112,6 @@ static int queue_pm_only_show(void *data, struct seq_file *m)
#define QUEUE_FLAG_NAME(name) [QUEUE_FLAG_##name] = #name
static const char *const blk_queue_flag_name[] = {
- QUEUE_FLAG_NAME(QUEUED),
QUEUE_FLAG_NAME(STOPPED),
QUEUE_FLAG_NAME(DYING),
QUEUE_FLAG_NAME(BYPASS),
@@ -318,7 +317,6 @@ static const char *const cmd_flag_name[] = {
static const char *const rqf_name[] = {
RQF_NAME(SORTED),
RQF_NAME(STARTED),
- RQF_NAME(QUEUED),
RQF_NAME(SOFTBARRIER),
RQF_NAME(FLUSH_SEQ),
RQF_NAME(MIXED_MERGE),
@@ -530,10 +530,8 @@ u32 blk_mq_unique_tag(struct request *rq)
struct blk_mq_hw_ctx *hctx;
int hwq = 0;
- if (q->mq_ops) {
- hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
- hwq = hctx->queue_num;
- }
+ hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
+ hwq = hctx->queue_num;
return (hwq << BLK_MQ_UNIQUE_TAG_BITS) |
(rq->tag & BLK_MQ_UNIQUE_TAG_MASK);
@@ -849,9 +849,6 @@ static void __blk_release_queue(struct work_struct *work)
blk_exit_rl(q, &q->root_rl);
- if (q->queue_tags)
- __blk_queue_free_tags(q);
-
blk_queue_free_zone_bitmaps(q);
if (!q->mq_ops) {
deleted file mode 100644
@@ -1,378 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Functions related to tagged command queuing
- */
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/bio.h>
-#include <linux/blkdev.h>
-#include <linux/slab.h>
-
-#include "blk.h"
-
-/**
- * blk_queue_find_tag - find a request by its tag and queue
- * @q: The request queue for the device
- * @tag: The tag of the request
- *
- * Notes:
- * Should be used when a device returns a tag and you want to match
- * it with a request.
- *
- * no locks need be held.
- **/
-struct request *blk_queue_find_tag(struct request_queue *q, int tag)
-{
- return blk_map_queue_find_tag(q->queue_tags, tag);
-}
-EXPORT_SYMBOL(blk_queue_find_tag);
-
-/**
- * blk_free_tags - release a given set of tag maintenance info
- * @bqt: the tag map to free
- *
- * Drop the reference count on @bqt and frees it when the last reference
- * is dropped.
- */
-void blk_free_tags(struct blk_queue_tag *bqt)
-{
- if (atomic_dec_and_test(&bqt->refcnt)) {
- BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) <
- bqt->max_depth);
-
- kfree(bqt->tag_index);
- bqt->tag_index = NULL;
-
- kfree(bqt->tag_map);
- bqt->tag_map = NULL;
-
- kfree(bqt);
- }
-}
-EXPORT_SYMBOL(blk_free_tags);
-
-/**
- * __blk_queue_free_tags - release tag maintenance info
- * @q: the request queue for the device
- *
- * Notes:
- * blk_cleanup_queue() will take care of calling this function, if tagging
- * has been used. So there's no need to call this directly.
- **/
-void __blk_queue_free_tags(struct request_queue *q)
-{
- struct blk_queue_tag *bqt = q->queue_tags;
-
- if (!bqt)
- return;
-
- blk_free_tags(bqt);
-
- q->queue_tags = NULL;
- queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
-}
-
-/**
- * blk_queue_free_tags - release tag maintenance info
- * @q: the request queue for the device
- *
- * Notes:
- * This is used to disable tagged queuing to a device, yet leave
- * queue in function.
- **/
-void blk_queue_free_tags(struct request_queue *q)
-{
- queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
-}
-EXPORT_SYMBOL(blk_queue_free_tags);
-
-static int
-init_tag_map(struct request_queue *q, struct blk_queue_tag *tags, int depth)
-{
- struct request **tag_index;
- unsigned long *tag_map;
- int nr_ulongs;
-
- if (q && depth > q->nr_requests * 2) {
- depth = q->nr_requests * 2;
- printk(KERN_ERR "%s: adjusted depth to %d\n",
- __func__, depth);
- }
-
- tag_index = kcalloc(depth, sizeof(struct request *), GFP_ATOMIC);
- if (!tag_index)
- goto fail;
-
- nr_ulongs = ALIGN(depth, BITS_PER_LONG) / BITS_PER_LONG;
- tag_map = kcalloc(nr_ulongs, sizeof(unsigned long), GFP_ATOMIC);
- if (!tag_map)
- goto fail;
-
- tags->real_max_depth = depth;
- tags->max_depth = depth;
- tags->tag_index = tag_index;
- tags->tag_map = tag_map;
-
- return 0;
-fail:
- kfree(tag_index);
- return -ENOMEM;
-}
-
-static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
- int depth, int alloc_policy)
-{
- struct blk_queue_tag *tags;
-
- tags = kmalloc(sizeof(struct blk_queue_tag), GFP_ATOMIC);
- if (!tags)
- goto fail;
-
- if (init_tag_map(q, tags, depth))
- goto fail;
-
- atomic_set(&tags->refcnt, 1);
- tags->alloc_policy = alloc_policy;
- tags->next_tag = 0;
- return tags;
-fail:
- kfree(tags);
- return NULL;
-}
-
-/**
- * blk_init_tags - initialize the tag info for an external tag map
- * @depth: the maximum queue depth supported
- * @alloc_policy: tag allocation policy
- **/
-struct blk_queue_tag *blk_init_tags(int depth, int alloc_policy)
-{
- return __blk_queue_init_tags(NULL, depth, alloc_policy);
-}
-EXPORT_SYMBOL(blk_init_tags);
-
-/**
- * blk_queue_init_tags - initialize the queue tag info
- * @q: the request queue for the device
- * @depth: the maximum queue depth supported
- * @tags: the tag to use
- * @alloc_policy: tag allocation policy
- *
- * Queue lock must be held here if the function is called to resize an
- * existing map.
- **/
-int blk_queue_init_tags(struct request_queue *q, int depth,
- struct blk_queue_tag *tags, int alloc_policy)
-{
- int rc;
-
- BUG_ON(tags && q->queue_tags && tags != q->queue_tags);
-
- if (!tags && !q->queue_tags) {
- tags = __blk_queue_init_tags(q, depth, alloc_policy);
-
- if (!tags)
- return -ENOMEM;
-
- } else if (q->queue_tags) {
- rc = blk_queue_resize_tags(q, depth);
- if (rc)
- return rc;
- queue_flag_set(QUEUE_FLAG_QUEUED, q);
- return 0;
- } else
- atomic_inc(&tags->refcnt);
-
- /*
- * assign it, all done
- */
- q->queue_tags = tags;
- queue_flag_set_unlocked(QUEUE_FLAG_QUEUED, q);
- return 0;
-}
-EXPORT_SYMBOL(blk_queue_init_tags);
-
-/**
- * blk_queue_resize_tags - change the queueing depth
- * @q: the request queue for the device
- * @new_depth: the new max command queueing depth
- *
- * Notes:
- * Must be called with the queue lock held.
- **/
-int blk_queue_resize_tags(struct request_queue *q, int new_depth)
-{
- struct blk_queue_tag *bqt = q->queue_tags;
- struct request **tag_index;
- unsigned long *tag_map;
- int max_depth, nr_ulongs;
-
- if (!bqt)
- return -ENXIO;
-
- /*
- * if we already have large enough real_max_depth. just
- * adjust max_depth. *NOTE* as requests with tag value
- * between new_depth and real_max_depth can be in-flight, tag
- * map can not be shrunk blindly here.
- */
- if (new_depth <= bqt->real_max_depth) {
- bqt->max_depth = new_depth;
- return 0;
- }
-
- /*
- * Currently cannot replace a shared tag map with a new
- * one, so error out if this is the case
- */
- if (atomic_read(&bqt->refcnt) != 1)
- return -EBUSY;
-
- /*
- * save the old state info, so we can copy it back
- */
- tag_index = bqt->tag_index;
- tag_map = bqt->tag_map;
- max_depth = bqt->real_max_depth;
-
- if (init_tag_map(q, bqt, new_depth))
- return -ENOMEM;
-
- memcpy(bqt->tag_index, tag_index, max_depth * sizeof(struct request *));
- nr_ulongs = ALIGN(max_depth, BITS_PER_LONG) / BITS_PER_LONG;
- memcpy(bqt->tag_map, tag_map, nr_ulongs * sizeof(unsigned long));
-
- kfree(tag_index);
- kfree(tag_map);
- return 0;
-}
-EXPORT_SYMBOL(blk_queue_resize_tags);
-
-/**
- * blk_queue_end_tag - end tag operations for a request
- * @q: the request queue for the device
- * @rq: the request that has completed
- *
- * Description:
- * Typically called when end_that_request_first() returns %0, meaning
- * all transfers have been done for a request. It's important to call
- * this function before end_that_request_last(), as that will put the
- * request back on the free list thus corrupting the internal tag list.
- **/
-void blk_queue_end_tag(struct request_queue *q, struct request *rq)
-{
- struct blk_queue_tag *bqt = q->queue_tags;
- unsigned tag = rq->tag; /* negative tags invalid */
-
- lockdep_assert_held(q->queue_lock);
-
- BUG_ON(tag >= bqt->real_max_depth);
-
- list_del_init(&rq->queuelist);
- rq->rq_flags &= ~RQF_QUEUED;
- rq->tag = -1;
- rq->internal_tag = -1;
-
- if (unlikely(bqt->tag_index[tag] == NULL))
- printk(KERN_ERR "%s: tag %d is missing\n",
- __func__, tag);
-
- bqt->tag_index[tag] = NULL;
-
- if (unlikely(!test_bit(tag, bqt->tag_map))) {
- printk(KERN_ERR "%s: attempt to clear non-busy tag (%d)\n",
- __func__, tag);
- return;
- }
- /*
- * The tag_map bit acts as a lock for tag_index[bit], so we need
- * unlock memory barrier semantics.
- */
- clear_bit_unlock(tag, bqt->tag_map);
-}
-
-/**
- * blk_queue_start_tag - find a free tag and assign it
- * @q: the request queue for the device
- * @rq: the block request that needs tagging
- *
- * Description:
- * This can either be used as a stand-alone helper, or possibly be
- * assigned as the queue &prep_rq_fn (in which case &struct request
- * automagically gets a tag assigned). Note that this function
- * assumes that any type of request can be queued! if this is not
- * true for your device, you must check the request type before
- * calling this function. The request will also be removed from
- * the request queue, so it's the drivers responsibility to readd
- * it if it should need to be restarted for some reason.
- **/
-int blk_queue_start_tag(struct request_queue *q, struct request *rq)
-{
- struct blk_queue_tag *bqt = q->queue_tags;
- unsigned max_depth;
- int tag;
-
- lockdep_assert_held(q->queue_lock);
-
- if (unlikely((rq->rq_flags & RQF_QUEUED))) {
- printk(KERN_ERR
- "%s: request %p for device [%s] already tagged %d",
- __func__, rq,
- rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->tag);
- BUG();
- }
-
- /*
- * Protect against shared tag maps, as we may not have exclusive
- * access to the tag map.
- *
- * We reserve a few tags just for sync IO, since we don't want
- * to starve sync IO on behalf of flooding async IO.
- */
- max_depth = bqt->max_depth;
- if (!rq_is_sync(rq) && max_depth > 1) {
- switch (max_depth) {
- case 2:
- max_depth = 1;
- break;
- case 3:
- max_depth = 2;
- break;
- default:
- max_depth -= 2;
- }
- if (q->in_flight[BLK_RW_ASYNC] > max_depth)
- return 1;
- }
-
- do {
- if (bqt->alloc_policy == BLK_TAG_ALLOC_FIFO) {
- tag = find_first_zero_bit(bqt->tag_map, max_depth);
- if (tag >= max_depth)
- return 1;
- } else {
- int start = bqt->next_tag;
- int size = min_t(int, bqt->max_depth, max_depth + start);
- tag = find_next_zero_bit(bqt->tag_map, size, start);
- if (tag >= size && start + size > bqt->max_depth) {
- size = start + size - bqt->max_depth;
- tag = find_first_zero_bit(bqt->tag_map, size);
- }
- if (tag >= size)
- return 1;
- }
-
- } while (test_and_set_bit_lock(tag, bqt->tag_map));
- /*
- * We need lock ordering semantics given by test_and_set_bit_lock.
- * See blk_queue_end_tag for details.
- */
-
- bqt->next_tag = (tag + 1) % bqt->max_depth;
- rq->rq_flags |= RQF_QUEUED;
- rq->tag = tag;
- bqt->tag_index[tag] = rq;
- blk_start_request(rq);
- return 0;
-}
-EXPORT_SYMBOL(blk_queue_start_tag);
@@ -85,8 +85,6 @@ typedef __u32 __bitwise req_flags_t;
#define RQF_SORTED ((__force req_flags_t)(1 << 0))
/* drive already may have started this one */
#define RQF_STARTED ((__force req_flags_t)(1 << 1))
-/* uses tagged queueing */
-#define RQF_QUEUED ((__force req_flags_t)(1 << 2))
/* may not be passed by ioscheduler */
#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3))
/* request for flush sequence */
@@ -336,15 +334,6 @@ enum blk_queue_state {
Queue_up,
};
-struct blk_queue_tag {
- struct request **tag_index; /* map of busy tags */
- unsigned long *tag_map; /* bit map of free/busy tags */
- int max_depth; /* what we will send to device */
- int real_max_depth; /* what the array can hold */
- atomic_t refcnt; /* map can be shared */
- int alloc_policy; /* tag allocation policy */
- int next_tag; /* next tag */
-};
#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
@@ -568,8 +557,6 @@ struct request_queue {
unsigned int dma_pad_mask;
unsigned int dma_alignment;
- struct blk_queue_tag *queue_tags;
-
unsigned int nr_sorted;
unsigned int in_flight[2];
@@ -680,7 +667,6 @@ struct request_queue {
u64 write_hints[BLK_MAX_WRITE_HINTS];
};
-#define QUEUE_FLAG_QUEUED 0 /* uses generic tag queueing */
#define QUEUE_FLAG_STOPPED 1 /* queue is stopped */
#define QUEUE_FLAG_DYING 2 /* queue being torn down */
#define QUEUE_FLAG_BYPASS 3 /* act as dumb FIFO queue */
@@ -724,7 +710,6 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q);
-#define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
#define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
#define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
#define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
@@ -1359,26 +1344,6 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk)
!list_empty(&plug->cb_list));
}
-/*
- * tag stuff
- */
-extern int blk_queue_start_tag(struct request_queue *, struct request *);
-extern struct request *blk_queue_find_tag(struct request_queue *, int);
-extern void blk_queue_end_tag(struct request_queue *, struct request *);
-extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *, int);
-extern void blk_queue_free_tags(struct request_queue *);
-extern int blk_queue_resize_tags(struct request_queue *, int);
-extern struct blk_queue_tag *blk_init_tags(int, int);
-extern void blk_free_tags(struct blk_queue_tag *);
-
-static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
- int tag)
-{
- if (unlikely(bqt == NULL || tag >= bqt->real_max_depth))
- return NULL;
- return bqt->tag_index[tag];
-}
-
extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, struct page *page);