#include <linux/delay.h>
#include <linux/ratelimit.h>
#include <linux/pm_runtime.h>
+#include <linux/blk-cgroup.h>
#define CREATE_TRACE_POINTS
#include <trace/events/block.h>
#include "blk.h"
-#include "blk-cgroup.h"
#include "blk-mq.h"
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
*/
static struct workqueue_struct *kblockd_workqueue;
+static void blk_clear_congested(struct request_list *rl, int sync)
+{
+#ifdef CONFIG_CGROUP_WRITEBACK
+ clear_wb_congested(rl->blkg->wb_congested, sync);
+#else
+ /*
+ * If !CGROUP_WRITEBACK, all blkg's map to bdi->wb and we shouldn't
+ * flip its congestion state for events on other blkcgs.
+ */
+ if (rl == &rl->q->root_rl)
+ clear_wb_congested(rl->q->backing_dev_info.wb.congested, sync);
+#endif
+}
+
+static void blk_set_congested(struct request_list *rl, int sync)
+{
+#ifdef CONFIG_CGROUP_WRITEBACK
+ set_wb_congested(rl->blkg->wb_congested, sync);
+#else
+ /* see blk_clear_congested() */
+ if (rl == &rl->q->root_rl)
+ set_wb_congested(rl->q->backing_dev_info.wb.congested, sync);
+#endif
+}
+
void blk_queue_congestion_threshold(struct request_queue *q)
{
int nr;
unsigned int nbytes, int error)
{
if (error)
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
- else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
- error = -EIO;
+ bio->bi_error = error;
if (unlikely(rq->cmd_flags & REQ_QUIET))
- set_bit(BIO_QUIET, &bio->bi_flags);
+ bio_set_flag(bio, BIO_QUIET);
bio_advance(bio, nbytes);
/* don't actually finish bio if it's part of flush sequence */
if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
- bio_endio(bio, error);
+ bio_endio(bio);
}
void blk_dump_rq_flags(struct request *rq, char *msg)
}
EXPORT_SYMBOL(blk_delay_queue);
+/**
+ * blk_start_queue_async - asynchronously restart a previously stopped queue
+ * @q: The &struct request_queue in question
+ *
+ * Description:
+ * blk_start_queue_async() will clear the stop flag on the queue, and
+ * ensure that the request_fn for the queue is run from an async
+ * context.
+ **/
+void blk_start_queue_async(struct request_queue *q)
+{
+ queue_flag_clear(QUEUE_FLAG_STOPPED, q);
+ blk_run_queue_async(q);
+}
+EXPORT_SYMBOL(blk_start_queue_async);
+
/**
* blk_start_queue - restart a previously stopped queue
* @q: The &struct request_queue in question
q->request_fn(q);
q->request_fn_active--;
}
+EXPORT_SYMBOL_GPL(__blk_run_queue_uncond);
/**
* __blk_run_queue - run a single device queue
* Drain all requests queued before DYING marking. Set DEAD flag to
* prevent that q->request_fn() gets invoked after draining finished.
*/
- if (q->mq_ops) {
- blk_mq_freeze_queue(q);
- spin_lock_irq(lock);
- } else {
- spin_lock_irq(lock);
+ blk_freeze_queue(q);
+ spin_lock_irq(lock);
+ if (!q->mq_ops)
__blk_drain_queue(q, true);
- }
queue_flag_set(QUEUE_FLAG_DEAD, q);
spin_unlock_irq(lock);
+ /* for synchronous bio-based driver finish in-flight integrity i/o */
+ blk_flush_integrity();
+
/* @q won't process any more request, flush async actions */
del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
blk_sync_queue(q);
if (q->mq_ops)
blk_mq_free_queue(q);
+ percpu_ref_exit(&q->q_usage_counter);
spin_lock_irq(lock);
if (q->queue_lock != &q->__queue_lock)
q->queue_lock = &q->__queue_lock;
spin_unlock_irq(lock);
- bdi_destroy(&q->backing_dev_info);
+ bdi_unregister(&q->backing_dev_info);
/* @q is and will stay empty, shutdown and put */
blk_put_queue(q);
}
EXPORT_SYMBOL(blk_alloc_queue);
+int blk_queue_enter(struct request_queue *q, gfp_t gfp)
+{
+ while (true) {
+ int ret;
+
+ if (percpu_ref_tryget_live(&q->q_usage_counter))
+ return 0;
+
+ if (!gfpflags_allow_blocking(gfp))
+ return -EBUSY;
+
+ ret = swait_event_interruptible(q->mq_freeze_wq,
+ !atomic_read(&q->mq_freeze_depth) ||
+ blk_queue_dying(q));
+ if (blk_queue_dying(q))
+ return -ENODEV;
+ if (ret)
+ return ret;
+ }
+}
+
+void blk_queue_exit(struct request_queue *q)
+{
+ percpu_ref_put(&q->q_usage_counter);
+}
+
+static void blk_queue_usage_counter_release(struct percpu_ref *ref)
+{
+ struct request_queue *q =
+ container_of(ref, struct request_queue, q_usage_counter);
+
+ swake_up_all(&q->mq_freeze_wq);
+}
+
struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
{
struct request_queue *q;
if (q->id < 0)
goto fail_q;
+ q->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+ if (!q->bio_split)
+ goto fail_id;
+
q->backing_dev_info.ra_pages =
(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
- q->backing_dev_info.state = 0;
- q->backing_dev_info.capabilities = 0;
+ q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK;
q->backing_dev_info.name = "block";
q->node = node_id;
err = bdi_init(&q->backing_dev_info);
if (err)
- goto fail_id;
+ goto fail_split;
setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
laptop_mode_timer_fn, (unsigned long) q);
q->bypass_depth = 1;
__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
- init_swait_head(&q->mq_freeze_wq);
+ init_swait_queue_head(&q->mq_freeze_wq);
- if (blkcg_init_queue(q))
+ /*
+ * Init percpu_ref in atomic mode so that it's faster to shutdown.
+ * See blk_register_queue() for details.
+ */
+ if (percpu_ref_init(&q->q_usage_counter,
+ blk_queue_usage_counter_release,
+ PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
goto fail_bdi;
+ if (blkcg_init_queue(q))
+ goto fail_ref;
+
return q;
+fail_ref:
+ percpu_ref_exit(&q->q_usage_counter);
fail_bdi:
bdi_destroy(&q->backing_dev_info);
+fail_split:
+ bioset_free(q->bio_split);
fail_id:
ida_simple_remove(&blk_queue_ida, q->id);
fail_q:
}
EXPORT_SYMBOL(blk_init_queue_node);
-static void blk_queue_bio(struct request_queue *q, struct bio *bio);
+static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio);
struct request_queue *
blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
{
struct request_queue *q = rl->q;
- /*
- * bdi isn't aware of blkcg yet. As all async IOs end up root
- * blkcg anyway, just use root blkcg state.
- */
- if (rl == &q->root_rl &&
- rl->count[sync] < queue_congestion_off_threshold(q))
- blk_clear_queue_congested(q, sync);
+ if (rl->count[sync] < queue_congestion_off_threshold(q))
+ blk_clear_congested(rl, sync);
if (rl->count[sync] + 1 <= q->nr_requests) {
if (waitqueue_active(&rl->wait[sync]))
int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
{
struct request_list *rl;
+ int on_thresh, off_thresh;
spin_lock_irq(q->queue_lock);
q->nr_requests = nr;
blk_queue_congestion_threshold(q);
+ on_thresh = queue_congestion_on_threshold(q);
+ off_thresh = queue_congestion_off_threshold(q);
- /* congestion isn't cgroup aware and follows root blkcg for now */
- rl = &q->root_rl;
-
- if (rl->count[BLK_RW_SYNC] >= queue_congestion_on_threshold(q))
- blk_set_queue_congested(q, BLK_RW_SYNC);
- else if (rl->count[BLK_RW_SYNC] < queue_congestion_off_threshold(q))
- blk_clear_queue_congested(q, BLK_RW_SYNC);
+ blk_queue_for_each_rl(rl, q) {
+ if (rl->count[BLK_RW_SYNC] >= on_thresh)
+ blk_set_congested(rl, BLK_RW_SYNC);
+ else if (rl->count[BLK_RW_SYNC] < off_thresh)
+ blk_clear_congested(rl, BLK_RW_SYNC);
- if (rl->count[BLK_RW_ASYNC] >= queue_congestion_on_threshold(q))
- blk_set_queue_congested(q, BLK_RW_ASYNC);
- else if (rl->count[BLK_RW_ASYNC] < queue_congestion_off_threshold(q))
- blk_clear_queue_congested(q, BLK_RW_ASYNC);
+ if (rl->count[BLK_RW_ASYNC] >= on_thresh)
+ blk_set_congested(rl, BLK_RW_ASYNC);
+ else if (rl->count[BLK_RW_ASYNC] < off_thresh)
+ blk_clear_congested(rl, BLK_RW_ASYNC);
- blk_queue_for_each_rl(rl, q) {
if (rl->count[BLK_RW_SYNC] >= q->nr_requests) {
blk_set_rl_full(rl, BLK_RW_SYNC);
} else {
}
}
}
- /*
- * bdi isn't aware of blkcg yet. As all async IOs end up
- * root blkcg anyway, just use root blkcg state.
- */
- if (rl == &q->root_rl)
- blk_set_queue_congested(q, is_sync);
+ blk_set_congested(rl, is_sync);
}
/*
* @bio: bio to allocate request for (can be %NULL)
* @gfp_mask: allocation mask
*
- * Get a free request from @q. If %__GFP_WAIT is set in @gfp_mask, this
- * function keeps retrying under memory pressure and fails iff @q is dead.
+ * Get a free request from @q. If %__GFP_DIRECT_RECLAIM is set in @gfp_mask,
+ * this function keeps retrying under memory pressure and fails iff @q is dead.
*
* Must be called with @q->queue_lock held and,
* Returns ERR_PTR on failure, with @q->queue_lock held.
if (!IS_ERR(rq))
return rq;
- if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dying(q))) {
+ if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) {
blk_put_rl(rl);
return rq;
}
* BUG.
*
* WARNING: When allocating/cloning a bio-chain, careful consideration should be
- * given to how you allocate bios. In particular, you cannot use __GFP_WAIT for
- * anything but the first bio in the chain. Otherwise you risk waiting for IO
- * completion of a bio that hasn't been submitted yet, thus resulting in a
- * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead
- * of bio_alloc(), as that avoids the mempool deadlock.
+ * given to how you allocate bios. In particular, you cannot use
+ * __GFP_DIRECT_RECLAIM for anything but the first bio in the chain. Otherwise
+ * you risk waiting for IO completion of a bio that hasn't been submitted yet,
+ * thus resulting in a deadlock. Alternatively bios should be allocated using
+ * bio_kmalloc() instead of bio_alloc(), as that avoids the mempool deadlock.
* If possible a big IO should be split into smaller parts when allocation
* fails. Partial allocation should not be an error, or you risk a live-lock.
*/
* @q: request_queue new bio is being queued at
* @bio: new bio being queued
* @request_count: out parameter for number of traversed plugged requests
+ * @same_queue_rq: pointer to &struct request that gets filled in when
+ * another request associated with @q is found on the plug list
+ * (optional, may be %NULL)
*
* Determine whether @bio being queued on @q can be merged with a request
* on %current's plugged list. Returns %true if merge was successful,
* Caller must ensure !blk_queue_nomerges(q) beforehand.
*/
bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
- unsigned int *request_count)
+ unsigned int *request_count,
+ struct request **same_queue_rq)
{
struct blk_plug *plug;
struct request *rq;
list_for_each_entry_reverse(rq, plug_list, queuelist) {
int el_ret;
- if (rq->q == q)
+ if (rq->q == q) {
(*request_count)++;
+ /*
+ * Only blk-mq multiple hardware queues case checks the
+ * rq in the same queue, there should be only one such
+ * rq in a queue
+ **/
+ if (same_queue_rq)
+ *same_queue_rq = rq;
+ }
if (rq->q != q || !blk_rq_merge_ok(rq, bio))
continue;
return ret;
}
+unsigned int blk_plug_queued_count(struct request_queue *q)
+{
+ struct blk_plug *plug;
+ struct request *rq;
+ struct list_head *plug_list;
+ unsigned int ret = 0;
+
+ plug = current->plug;
+ if (!plug)
+ goto out;
+
+ if (q->mq_ops)
+ plug_list = &plug->mq_list;
+ else
+ plug_list = &plug->list;
+
+ list_for_each_entry(rq, plug_list, queuelist) {
+ if (rq->q == q)
+ ret++;
+ }
+out:
+ return ret;
+}
+
void init_request_from_bio(struct request *req, struct bio *bio)
{
req->cmd_type = REQ_TYPE_FS;
blk_rq_bio_prep(req->q, req, bio);
}
-static void blk_queue_bio(struct request_queue *q, struct bio *bio)
+static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
{
const bool sync = !!(bio->bi_rw & REQ_SYNC);
struct blk_plug *plug;
*/
blk_queue_bounce(q, &bio);
+ blk_queue_split(q, &bio, q->bio_split);
+
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
- bio_endio(bio, -EIO);
- return;
+ bio->bi_error = -EIO;
+ bio_endio(bio);
+ return BLK_QC_T_NONE;
}
if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
* Check if we can merge with the plugged list before grabbing
* any locks.
*/
- if (!blk_queue_nomerges(q) &&
- blk_attempt_plug_merge(q, bio, &request_count))
- return;
+ if (!blk_queue_nomerges(q)) {
+ if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
+ return BLK_QC_T_NONE;
+ } else
+ request_count = blk_plug_queued_count(q);
spin_lock_irq(q->queue_lock);
*/
req = get_request(q, rw_flags, bio, GFP_NOIO);
if (IS_ERR(req)) {
- bio_endio(bio, PTR_ERR(req)); /* @q is dead */
+ bio->bi_error = PTR_ERR(req);
+ bio_endio(bio);
goto out_unlock;
}
out_unlock:
spin_unlock_irq(q->queue_lock);
}
+
+ return BLK_QC_T_NONE;
}
/*
bio->bi_rw,
(unsigned long long)bio_end_sector(bio),
(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
-
- set_bit(BIO_EOF, &bio->bi_flags);
}
#ifdef CONFIG_FAIL_MAKE_REQUEST
goto end_io;
}
- if (likely(bio_is_rw(bio) &&
- nr_sectors > queue_max_hw_sectors(q))) {
- printk(KERN_ERR "bio too big device %s (%u > %u)\n",
- bdevname(bio->bi_bdev, b),
- bio_sectors(bio),
- queue_max_hw_sectors(q));
- goto end_io;
- }
-
part = bio->bi_bdev->bd_part;
if (should_fail_request(part, bio->bi_iter.bi_size) ||
should_fail_request(&part_to_disk(part)->part0,
*/
create_io_context(GFP_ATOMIC, q->node);
- if (blk_throtl_bio(q, bio))
- return false; /* throttled, will be resubmitted later */
+ if (!blkcg_bio_issue_check(q, bio))
+ return false;
trace_block_bio_queue(q, bio);
return true;
end_io:
- bio_endio(bio, err);
+ bio->bi_error = err;
+ bio_endio(bio);
return false;
}
* a lower device by calling into generic_make_request recursively, which
* means the bio should NOT be touched after the call to ->make_request_fn.
*/
-void generic_make_request(struct bio *bio)
+blk_qc_t generic_make_request(struct bio *bio)
{
struct bio_list bio_list_on_stack;
+ blk_qc_t ret = BLK_QC_T_NONE;
if (!generic_make_request_checks(bio))
- return;
+ goto out;
/*
* We only want one ->make_request_fn to be active at a time, else
*/
if (current->bio_list) {
bio_list_add(current->bio_list, bio);
- return;
+ goto out;
}
/* following loop may be a bit non-obvious, and so deserves some
do {
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
- q->make_request_fn(q, bio);
+ if (likely(blk_queue_enter(q, __GFP_DIRECT_RECLAIM) == 0)) {
+
+ ret = q->make_request_fn(q, bio);
- bio = bio_list_pop(current->bio_list);
+ blk_queue_exit(q);
+
+ bio = bio_list_pop(current->bio_list);
+ } else {
+ struct bio *bio_next = bio_list_pop(current->bio_list);
+
+ bio_io_error(bio);
+ bio = bio_next;
+ }
} while (bio);
current->bio_list = NULL; /* deactivate */
+
+out:
+ return ret;
}
EXPORT_SYMBOL(generic_make_request);
* interfaces; @bio must be presetup and ready for I/O.
*
*/
-void submit_bio(int rw, struct bio *bio)
+blk_qc_t submit_bio(int rw, struct bio *bio)
{
bio->bi_rw |= rw;
}
}
- generic_make_request(bio);
+ return generic_make_request(bio);
}
EXPORT_SYMBOL(submit_bio);
/**
- * blk_rq_check_limits - Helper function to check a request for the queue limit
+ * blk_cloned_rq_check_limits - Helper function to check a cloned request
+ * for new the queue limits
* @q: the queue
* @rq: the request being checked
*
* after it is inserted to @q, it should be checked against @q before
* the insertion using this generic function.
*
- * This function should also be useful for request stacking drivers
- * in some cases below, so export this function.
* Request stacking drivers like request-based dm may change the queue
- * limits while requests are in the queue (e.g. dm's table swapping).
- * Such request stacking drivers should check those requests against
- * the new queue limits again when they dispatch those requests,
- * although such checkings are also done against the old queue limits
- * when submitting requests.
+ * limits when retrying requests on other queues. Those requests need
+ * to be checked against the new queue limits again during dispatch.
*/
-int blk_rq_check_limits(struct request_queue *q, struct request *rq)
+static int blk_cloned_rq_check_limits(struct request_queue *q,
+ struct request *rq)
{
- if (!rq_mergeable(rq))
- return 0;
-
if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, rq->cmd_flags)) {
printk(KERN_ERR "%s: over max size limit.\n", __func__);
return -EIO;
return 0;
}
-EXPORT_SYMBOL_GPL(blk_rq_check_limits);
/**
* blk_insert_cloned_request - Helper for stacking drivers to submit a request
unsigned long flags;
int where = ELEVATOR_INSERT_BACK;
- if (blk_rq_check_limits(q, rq))
+ if (blk_cloned_rq_check_limits(q, rq))
return -EIO;
if (rq->rq_disk &&
{
struct task_struct *tsk = current;
+ /*
+ * If this is a nested plug, don't actually assign it.
+ */
+ if (tsk->plug)
+ return;
+
INIT_LIST_HEAD(&plug->list);
INIT_LIST_HEAD(&plug->mq_list);
INIT_LIST_HEAD(&plug->cb_list);
-
/*
- * If this is a nested plug, don't actually assign it. It will be
- * flushed on its own.
+ * Store ordering should not be needed here, since a potential
+ * preempt will imply a full memory barrier
*/
- if (!tsk->plug) {
- /*
- * Store ordering should not be needed here, since a potential
- * preempt will imply a full memory barrier
- */
- tsk->plug = plug;
- }
+ tsk->plug = plug;
}
EXPORT_SYMBOL(blk_start_plug);
void blk_finish_plug(struct blk_plug *plug)
{
+ if (plug != current->plug)
+ return;
blk_flush_plug_list(plug, false);
- if (plug == current->plug)
- current->plug = NULL;
+ current->plug = NULL;
}
EXPORT_SYMBOL(blk_finish_plug);
+bool blk_poll(struct request_queue *q, blk_qc_t cookie)
+{
+ struct blk_plug *plug;
+ long state;
+
+ if (!q->mq_ops || !q->mq_ops->poll || !blk_qc_t_valid(cookie) ||
+ !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+ return false;
+
+ plug = current->plug;
+ if (plug)
+ blk_flush_plug_list(plug, false);
+
+ state = current->state;
+ while (!need_resched()) {
+ unsigned int queue_num = blk_qc_t_to_queue_num(cookie);
+ struct blk_mq_hw_ctx *hctx = q->queue_hw_ctx[queue_num];
+ int ret;
+
+ hctx->poll_invoked++;
+
+ ret = q->mq_ops->poll(hctx, blk_qc_t_to_tag(cookie));
+ if (ret > 0) {
+ hctx->poll_success++;
+ set_current_state(TASK_RUNNING);
+ return true;
+ }
+
+ if (signal_pending_state(state, current))
+ set_current_state(TASK_RUNNING);
+
+ if (current->state == TASK_RUNNING)
+ return true;
+ if (ret < 0)
+ break;
+ cpu_relax();
+ }
+
+ return false;
+}
+
#ifdef CONFIG_PM
/**
* blk_pm_runtime_init - Block layer runtime PM initialization routine
{
int ret = 0;
+ if (!q->dev)
+ return ret;
+
spin_lock_irq(q->queue_lock);
if (q->nr_pending) {
ret = -EBUSY;
*/
void blk_post_runtime_suspend(struct request_queue *q, int err)
{
+ if (!q->dev)
+ return;
+
spin_lock_irq(q->queue_lock);
if (!err) {
q->rpm_status = RPM_SUSPENDED;
*/
void blk_pre_runtime_resume(struct request_queue *q)
{
+ if (!q->dev)
+ return;
+
spin_lock_irq(q->queue_lock);
q->rpm_status = RPM_RESUMING;
spin_unlock_irq(q->queue_lock);
*/
void blk_post_runtime_resume(struct request_queue *q, int err)
{
+ if (!q->dev)
+ return;
+
spin_lock_irq(q->queue_lock);
if (!err) {
q->rpm_status = RPM_ACTIVE;
int __init blk_dev_init(void)
{
BUILD_BUG_ON(__REQ_NR_BITS > 8 *
- sizeof(((struct request *)0)->cmd_flags));
+ FIELD_SIZEOF(struct request, cmd_flags));
/* used for unplugging and affects IO latency/throughput - HIGHPRI */
kblockd_workqueue = alloc_workqueue("kblockd",
Code Review / kvmfornfv.git / blobdiff