aboutsummaryrefslogtreecommitdiffstats
path: root/block/blk-mq.c
diff options
context:
space:
mode:
Diffstat (limited to 'block/blk-mq.c')
-rw-r--r--block/blk-mq.c939
1 files changed, 579 insertions, 360 deletions
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ce0f5f4ede70..4e0d173beaa3 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -26,10 +26,12 @@
#include <linux/delay.h>
#include <linux/crash_dump.h>
#include <linux/prefetch.h>
+#include <linux/blk-crypto.h>
#include <trace/events/block.h>
#include <linux/blk-mq.h>
+#include <linux/t10-pi.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
@@ -44,12 +46,12 @@ static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
static int blk_mq_poll_stats_bkt(const struct request *rq)
{
- int ddir, bytes, bucket;
+ int ddir, sectors, bucket;
ddir = rq_data_dir(rq);
- bytes = blk_rq_bytes(rq);
+ sectors = blk_rq_stats_sectors(rq);
- bucket = ddir + 2*(ilog2(bytes) - 9);
+ bucket = ddir + 2 * ilog2(sectors);
if (bucket < 0)
return -1;
@@ -92,7 +94,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
struct mq_inflight {
struct hd_struct *part;
- unsigned int *inflight;
+ unsigned int inflight[2];
};
static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
@@ -101,45 +103,29 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
{
struct mq_inflight *mi = priv;
- /*
- * index[0] counts the specific partition that was asked for.
- */
if (rq->part == mi->part)
- mi->inflight[0]++;
+ mi->inflight[rq_data_dir(rq)]++;
return true;
}
unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
{
- unsigned inflight[2];
- struct mq_inflight mi = { .part = part, .inflight = inflight, };
+ struct mq_inflight mi = { .part = part };
- inflight[0] = inflight[1] = 0;
blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
- return inflight[0];
-}
-
-static bool blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
- struct request *rq, void *priv,
- bool reserved)
-{
- struct mq_inflight *mi = priv;
-
- if (rq->part == mi->part)
- mi->inflight[rq_data_dir(rq)]++;
-
- return true;
+ return mi.inflight[0] + mi.inflight[1];
}
void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
unsigned int inflight[2])
{
- struct mq_inflight mi = { .part = part, .inflight = inflight, };
+ struct mq_inflight mi = { .part = part };
- inflight[0] = inflight[1] = 0;
- blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
+ blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
+ inflight[0] = mi.inflight[0];
+ inflight[1] = mi.inflight[1];
}
void blk_freeze_queue_start(struct request_queue *q)
@@ -275,30 +261,24 @@ void blk_mq_wake_waiters(struct request_queue *q)
blk_mq_tag_wakeup_all(hctx->tags, true);
}
-bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
-{
- return blk_mq_has_free_tags(hctx->tags);
-}
-EXPORT_SYMBOL(blk_mq_can_queue);
-
/*
- * Only need start/end time stamping if we have stats enabled, or using
- * an IO scheduler.
+ * Only need start/end time stamping if we have iostat or
+ * blk stats enabled, or using an IO scheduler.
*/
static inline bool blk_mq_need_time_stamp(struct request *rq)
{
- return (rq->rq_flags & RQF_IO_STAT) || rq->q->elevator;
+ return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS)) || rq->q->elevator;
}
static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
- unsigned int tag, unsigned int op)
+ unsigned int tag, u64 alloc_time_ns)
{
struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
struct request *rq = tags->static_rqs[tag];
req_flags_t rq_flags = 0;
if (data->flags & BLK_MQ_REQ_INTERNAL) {
- rq->tag = -1;
+ rq->tag = BLK_MQ_NO_TAG;
rq->internal_tag = tag;
} else {
if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
@@ -306,7 +286,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
atomic_inc(&data->hctx->nr_active);
}
rq->tag = tag;
- rq->internal_tag = -1;
+ rq->internal_tag = BLK_MQ_NO_TAG;
data->hctx->tags->rqs[rq->tag] = rq;
}
@@ -315,7 +295,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
rq->mq_ctx = data->ctx;
rq->mq_hctx = data->hctx;
rq->rq_flags = rq_flags;
- rq->cmd_flags = op;
+ rq->cmd_flags = data->cmd_flags;
if (data->flags & BLK_MQ_REQ_PREEMPT)
rq->rq_flags |= RQF_PREEMPT;
if (blk_queue_io_stat(data->q))
@@ -325,17 +305,21 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
RB_CLEAR_NODE(&rq->rb_node);
rq->rq_disk = NULL;
rq->part = NULL;
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+ rq->alloc_time_ns = alloc_time_ns;
+#endif
if (blk_mq_need_time_stamp(rq))
rq->start_time_ns = ktime_get_ns();
else
rq->start_time_ns = 0;
rq->io_start_time_ns = 0;
+ rq->stats_sectors = 0;
rq->nr_phys_segments = 0;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
rq->nr_integrity_segments = 0;
#endif
+ blk_crypto_rq_set_defaults(rq);
/* tag was already set */
- rq->extra_len = 0;
WRITE_ONCE(rq->deadline, 0);
rq->timeout = 0;
@@ -343,29 +327,37 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
rq->end_io = NULL;
rq->end_io_data = NULL;
- data->ctx->rq_dispatched[op_is_sync(op)]++;
+ data->ctx->rq_dispatched[op_is_sync(data->cmd_flags)]++;
refcount_set(&rq->ref, 1);
+
+ if (!op_is_flush(data->cmd_flags)) {
+ struct elevator_queue *e = data->q->elevator;
+
+ rq->elv.icq = NULL;
+ if (e && e->type->ops.prepare_request) {
+ if (e->type->icq_cache)
+ blk_mq_sched_assign_ioc(rq);
+
+ e->type->ops.prepare_request(rq);
+ rq->rq_flags |= RQF_ELVPRIV;
+ }
+ }
+
+ data->hctx->queued++;
return rq;
}
-static struct request *blk_mq_get_request(struct request_queue *q,
- struct bio *bio,
- struct blk_mq_alloc_data *data)
+static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data)
{
+ struct request_queue *q = data->q;
struct elevator_queue *e = q->elevator;
- struct request *rq;
+ u64 alloc_time_ns = 0;
unsigned int tag;
- bool put_ctx_on_error = false;
- blk_queue_enter_live(q);
- data->q = q;
- if (likely(!data->ctx)) {
- data->ctx = blk_mq_get_ctx(q);
- put_ctx_on_error = true;
- }
- if (likely(!data->hctx))
- data->hctx = blk_mq_map_queue(q, data->cmd_flags,
- data->ctx);
+ /* alloc_time includes depth and tag waits */
+ if (blk_queue_rq_alloc_time(q))
+ alloc_time_ns = ktime_get_ns();
+
if (data->cmd_flags & REQ_NOWAIT)
data->flags |= BLK_MQ_REQ_NOWAIT;
@@ -381,39 +373,43 @@ static struct request *blk_mq_get_request(struct request_queue *q,
e->type->ops.limit_depth &&
!(data->flags & BLK_MQ_REQ_RESERVED))
e->type->ops.limit_depth(data->cmd_flags, data);
- } else {
- blk_mq_tag_busy(data->hctx);
}
- tag = blk_mq_get_tag(data);
- if (tag == BLK_MQ_TAG_FAIL) {
- if (put_ctx_on_error) {
- blk_mq_put_ctx(data->ctx);
- data->ctx = NULL;
- }
- blk_queue_exit(q);
- return NULL;
- }
+retry:
+ data->ctx = blk_mq_get_ctx(q);
+ data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
+ if (!(data->flags & BLK_MQ_REQ_INTERNAL))
+ blk_mq_tag_busy(data->hctx);
- rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags);
- if (!op_is_flush(data->cmd_flags)) {
- rq->elv.icq = NULL;
- if (e && e->type->ops.prepare_request) {
- if (e->type->icq_cache)
- blk_mq_sched_assign_ioc(rq);
+ /*
+ * Waiting allocations only fail because of an inactive hctx. In that
+ * case just retry the hctx assignment and tag allocation as CPU hotplug
+ * should have migrated us to an online CPU by now.
+ */
+ tag = blk_mq_get_tag(data);
+ if (tag == BLK_MQ_NO_TAG) {
+ if (data->flags & BLK_MQ_REQ_NOWAIT)
+ return NULL;
- e->type->ops.prepare_request(rq, bio);
- rq->rq_flags |= RQF_ELVPRIV;
- }
+ /*
+ * Give up the CPU and sleep for a random short time to ensure
+ * that thread using a realtime scheduling class are migrated
+ * off the the CPU, and thus off the hctx that is going away.
+ */
+ msleep(3);
+ goto retry;
}
- data->hctx->queued++;
- return rq;
+ return blk_mq_rq_ctx_init(data, tag, alloc_time_ns);
}
struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
blk_mq_req_flags_t flags)
{
- struct blk_mq_alloc_data alloc_data = { .flags = flags, .cmd_flags = op };
+ struct blk_mq_alloc_data data = {
+ .q = q,
+ .flags = flags,
+ .cmd_flags = op,
+ };
struct request *rq;
int ret;
@@ -421,36 +417,43 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
if (ret)
return ERR_PTR(ret);
- rq = blk_mq_get_request(q, NULL, &alloc_data);
- blk_queue_exit(q);
-
+ rq = __blk_mq_alloc_request(&data);
if (!rq)
- return ERR_PTR(-EWOULDBLOCK);
-
- blk_mq_put_ctx(alloc_data.ctx);
-
+ goto out_queue_exit;
rq->__data_len = 0;
rq->__sector = (sector_t) -1;
rq->bio = rq->biotail = NULL;
return rq;
+out_queue_exit:
+ blk_queue_exit(q);
+ return ERR_PTR(-EWOULDBLOCK);
}
EXPORT_SYMBOL(blk_mq_alloc_request);
struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx)
{
- struct blk_mq_alloc_data alloc_data = { .flags = flags, .cmd_flags = op };
- struct request *rq;
+ struct blk_mq_alloc_data data = {
+ .q = q,
+ .flags = flags,
+ .cmd_flags = op,
+ };
+ u64 alloc_time_ns = 0;
unsigned int cpu;
+ unsigned int tag;
int ret;
+ /* alloc_time includes depth and tag waits */
+ if (blk_queue_rq_alloc_time(q))
+ alloc_time_ns = ktime_get_ns();
+
/*
* If the tag allocator sleeps we could get an allocation for a
* different hardware context. No need to complicate the low level
* allocator for this for the rare use case of a command tied to
* a specific queue.
*/
- if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)))
+ if (WARN_ON_ONCE(!(flags & (BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED))))
return ERR_PTR(-EINVAL);
if (hctx_idx >= q->nr_hw_queues)
@@ -464,21 +467,27 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
* Check if the hardware context is actually mapped to anything.
* If not tell the caller that it should skip this queue.
*/
- alloc_data.hctx = q->queue_hw_ctx[hctx_idx];
- if (!blk_mq_hw_queue_mapped(alloc_data.hctx)) {
- blk_queue_exit(q);
- return ERR_PTR(-EXDEV);
- }
- cpu = cpumask_first_and(alloc_data.hctx->cpumask, cpu_online_mask);
- alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
-
- rq = blk_mq_get_request(q, NULL, &alloc_data);
- blk_queue_exit(q);
+ ret = -EXDEV;
+ data.hctx = q->queue_hw_ctx[hctx_idx];
+ if (!blk_mq_hw_queue_mapped(data.hctx))
+ goto out_queue_exit;
+ cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
+ data.ctx = __blk_mq_get_ctx(q, cpu);
+
+ if (q->elevator)
+ data.flags |= BLK_MQ_REQ_INTERNAL;
+ else
+ blk_mq_tag_busy(data.hctx);
- if (!rq)
- return ERR_PTR(-EWOULDBLOCK);
+ ret = -EWOULDBLOCK;
+ tag = blk_mq_get_tag(&data);
+ if (tag == BLK_MQ_NO_TAG)
+ goto out_queue_exit;
+ return blk_mq_rq_ctx_init(&data, tag, alloc_time_ns);
- return rq;
+out_queue_exit:
+ blk_queue_exit(q);
+ return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
@@ -489,12 +498,13 @@ static void __blk_mq_free_request(struct request *rq)
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
const int sched_tag = rq->internal_tag;
+ blk_crypto_free_request(rq);
blk_pm_mark_last_busy(rq);
rq->mq_hctx = NULL;
- if (rq->tag != -1)
- blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
- if (sched_tag != -1)
- blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
+ if (rq->tag != BLK_MQ_NO_TAG)
+ blk_mq_put_tag(hctx->tags, ctx, rq->tag);
+ if (sched_tag != BLK_MQ_NO_TAG)
+ blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag);
blk_mq_sched_restart(hctx);
blk_queue_exit(q);
}
@@ -542,7 +552,7 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
blk_stat_add(rq, now);
}
- if (rq->internal_tag != -1)
+ if (rq->internal_tag != BLK_MQ_NO_TAG)
blk_mq_sched_completed_request(rq, now);
blk_account_io_done(rq, now);
@@ -572,7 +582,17 @@ static void __blk_mq_complete_request_remote(void *data)
q->mq_ops->complete(rq);
}
-static void __blk_mq_complete_request(struct request *rq)
+/**
+ * blk_mq_force_complete_rq() - Force complete the request, bypassing any error
+ * injection that could drop the completion.
+ * @rq: Request to be force completed
+ *
+ * Drivers should use blk_mq_complete_request() to complete requests in their
+ * normal IO path. For timeout error recovery, drivers may call this forced
+ * completion routine after they've reclaimed timed out requests to bypass
+ * potentially subsequent fake timeouts.
+ */
+void blk_mq_force_complete_rq(struct request *rq)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
struct request_queue *q = rq->q;
@@ -618,6 +638,7 @@ static void __blk_mq_complete_request(struct request *rq)
}
put_cpu();
}
+EXPORT_SYMBOL_GPL(blk_mq_force_complete_rq);
static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx)
__releases(hctx->srcu)
@@ -651,37 +672,28 @@ bool blk_mq_complete_request(struct request *rq)
{
if (unlikely(blk_should_fake_timeout(rq->q)))
return false;
- __blk_mq_complete_request(rq);
+ blk_mq_force_complete_rq(rq);
return true;
}
EXPORT_SYMBOL(blk_mq_complete_request);
-void blk_mq_complete_request_sync(struct request *rq)
-{
- WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
- rq->q->mq_ops->complete(rq);
-}
-EXPORT_SYMBOL_GPL(blk_mq_complete_request_sync);
-
-int blk_mq_request_started(struct request *rq)
-{
- return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
-}
-EXPORT_SYMBOL_GPL(blk_mq_request_started);
-
+/**
+ * blk_mq_start_request - Start processing a request
+ * @rq: Pointer to request to be started
+ *
+ * Function used by device drivers to notify the block layer that a request
+ * is going to be processed now, so blk layer can do proper initializations
+ * such as starting the timeout timer.
+ */
void blk_mq_start_request(struct request *rq)
{
struct request_queue *q = rq->q;
- blk_mq_sched_started_request(rq);
-
trace_block_rq_issue(q, rq);
if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
rq->io_start_time_ns = ktime_get_ns();
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
- rq->throtl_size = blk_rq_sectors(rq);
-#endif
+ rq->stats_sectors = blk_rq_sectors(rq);
rq->rq_flags |= RQF_STATS;
rq_qos_issue(q, rq);
}
@@ -691,14 +703,10 @@ void blk_mq_start_request(struct request *rq)
blk_add_timer(rq);
WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT);
- if (q->dma_drain_size && blk_rq_bytes(rq)) {
- /*
- * Make sure space for the drain appears. We know we can do
- * this because max_hw_segments has been adjusted to be one
- * fewer than the device can handle.
- */
- rq->nr_phys_segments++;
- }
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+ if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE)
+ q->integrity.profile->prepare_fn(rq);
+#endif
}
EXPORT_SYMBOL(blk_mq_start_request);
@@ -714,8 +722,6 @@ static void __blk_mq_requeue_request(struct request *rq)
if (blk_mq_request_started(rq)) {
WRITE_ONCE(rq->state, MQ_RQ_IDLE);
rq->rq_flags &= ~RQF_TIMED_OUT;
- if (q->dma_drain_size && blk_rq_bytes(rq))
- rq->nr_phys_segments--;
}
}
@@ -754,7 +760,7 @@ static void blk_mq_requeue_work(struct work_struct *work)
* merge.
*/
if (rq->rq_flags & RQF_DONTPREP)
- blk_mq_request_bypass_insert(rq, false);
+ blk_mq_request_bypass_insert(rq, false, false);
else
blk_mq_sched_insert_request(rq, true, false, false);
}
@@ -822,10 +828,10 @@ static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq,
void *priv, bool reserved)
{
/*
- * If we find a request that is inflight and the queue matches,
+ * If we find a request that isn't idle and the queue matches,
* we know the queue is busy. Return false to stop the iteration.
*/
- if (rq->state == MQ_RQ_IN_FLIGHT && rq->q == hctx->queue) {
+ if (blk_mq_request_started(rq) && rq->q == hctx->queue) {
bool *busy = priv;
*busy = true;
@@ -911,7 +917,10 @@ static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
*/
if (blk_mq_req_expired(rq, next))
blk_mq_rq_timed_out(rq, reserved);
- if (refcount_dec_and_test(&rq->ref))
+
+ if (is_flush_rq(rq, hctx))
+ rq->end_io(rq, 0);
+ else if (refcount_dec_and_test(&rq->ref))
__blk_mq_free_request(rq);
return true;
@@ -1043,36 +1052,6 @@ static inline unsigned int queued_to_index(unsigned int queued)
return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
}
-bool blk_mq_get_driver_tag(struct request *rq)
-{
- struct blk_mq_alloc_data data = {
- .q = rq->q,
- .hctx = rq->mq_hctx,
- .flags = BLK_MQ_REQ_NOWAIT,
- .cmd_flags = rq->cmd_flags,
- };
- bool shared;
-
- if (rq->tag != -1)
- goto done;
-
- if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
- data.flags |= BLK_MQ_REQ_RESERVED;
-
- shared = blk_mq_tag_busy(data.hctx);
- rq->tag = blk_mq_get_tag(&data);
- if (rq->tag >= 0) {
- if (shared) {
- rq->rq_flags |= RQF_MQ_INFLIGHT;
- atomic_inc(&data.hctx->nr_active);
- }
- data.hctx->tags->rqs[rq->tag] = rq;
- }
-
-done:
- return rq->tag != -1;
-}
-
static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
int flags, void *key)
{
@@ -1195,6 +1174,36 @@ static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy)
#define BLK_MQ_RESOURCE_DELAY 3 /* ms units */
+static void blk_mq_handle_dev_resource(struct request *rq,
+ struct list_head *list)
+{
+ struct request *next =
+ list_first_entry_or_null(list, struct request, queuelist);
+
+ /*
+ * If an I/O scheduler has been configured and we got a driver tag for
+ * the next request already, free it.
+ */
+ if (next)
+ blk_mq_put_driver_tag(next);
+
+ list_add(&rq->queuelist, list);
+ __blk_mq_requeue_request(rq);
+}
+
+static void blk_mq_handle_zone_resource(struct request *rq,
+ struct list_head *zone_list)
+{
+ /*
+ * If we end up here it is because we cannot dispatch a request to a
+ * specific zone due to LLD level zone-write locking or other zone
+ * related resource not being available. In this case, set the request
+ * aside in zone_list for retrying it later.
+ */
+ list_add(&rq->queuelist, zone_list);
+ __blk_mq_requeue_request(rq);
+}
+
/*
* Returns true if we did some work AND can potentially do more.
*/
@@ -1206,6 +1215,8 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
bool no_tag = false;
int errors, queued;
blk_status_t ret = BLK_STS_OK;
+ bool no_budget_avail = false;
+ LIST_HEAD(zone_list);
if (list_empty(list))
return false;
@@ -1222,8 +1233,11 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
rq = list_first_entry(list, struct request, queuelist);
hctx = rq->mq_hctx;
- if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
+ if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) {
+ blk_mq_put_driver_tag(rq);
+ no_budget_avail = true;
break;
+ }
if (!blk_mq_get_driver_tag(rq)) {
/*
@@ -1262,18 +1276,18 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
ret = q->mq_ops->queue_rq(hctx, &bd);
if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
+ blk_mq_handle_dev_resource(rq, list);
+ break;
+ } else if (ret == BLK_STS_ZONE_RESOURCE) {
/*
- * If an I/O scheduler has been configured and we got a
- * driver tag for the next request already, free it
- * again.
+ * Move the request to zone_list and keep going through
+ * the dispatch list to find more requests the drive can
+ * accept.
*/
- if (!list_empty(list)) {
- nxt = list_first_entry(list, struct request, queuelist);
- blk_mq_put_driver_tag(nxt);
- }
- list_add(&rq->queuelist, list);
- __blk_mq_requeue_request(rq);
- break;
+ blk_mq_handle_zone_resource(rq, &zone_list);
+ if (list_empty(list))
+ break;
+ continue;
}
if (unlikely(ret != BLK_STS_OK)) {
@@ -1285,6 +1299,9 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
queued++;
} while (!list_empty(list));
+ if (!list_empty(&zone_list))
+ list_splice_tail_init(&zone_list, list);
+
hctx->dispatched[queued_to_index(queued)]++;
/*
@@ -1299,11 +1316,11 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
* the driver there was more coming, but that turned out to
* be a lie.
*/
- if (q->mq_ops->commit_rqs)
+ if (q->mq_ops->commit_rqs && queued)
q->mq_ops->commit_rqs(hctx);
spin_lock(&hctx->lock);
- list_splice_init(list, &hctx->dispatch);
+ list_splice_tail_init(list, &hctx->dispatch);
spin_unlock(&hctx->lock);
/*
@@ -1328,13 +1345,15 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
*
* If driver returns BLK_STS_RESOURCE and SCHED_RESTART
* bit is set, run queue after a delay to avoid IO stalls
- * that could otherwise occur if the queue is idle.
+ * that could otherwise occur if the queue is idle. We'll do
+ * similar if we couldn't get budget and SCHED_RESTART is set.
*/
needs_restart = blk_mq_sched_needs_restart(hctx);
if (!needs_restart ||
(no_tag && list_empty_careful(&hctx->dispatch_wait.entry)))
blk_mq_run_hw_queue(hctx, true);
- else if (needs_restart && (ret == BLK_STS_RESOURCE))
+ else if (needs_restart && (ret == BLK_STS_RESOURCE ||
+ no_budget_avail))
blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
blk_mq_update_dispatch_busy(hctx, true);
@@ -1352,6 +1371,12 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
return (queued + errors) != 0;
}
+/**
+ * __blk_mq_run_hw_queue - Run a hardware queue.
+ * @hctx: Pointer to the hardware queue to run.
+ *
+ * Send pending requests to the hardware.
+ */
static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
{
int srcu_idx;
@@ -1449,6 +1474,15 @@ select_cpu:
return next_cpu;
}
+/**
+ * __blk_mq_delay_run_hw_queue - Run (or schedule to run) a hardware queue.
+ * @hctx: Pointer to the hardware queue to run.
+ * @async: If we want to run the queue asynchronously.
+ * @msecs: Microseconds of delay to wait before running the queue.
+ *
+ * If !@async, try to run the queue now. Else, run the queue asynchronously and
+ * with a delay of @msecs.
+ */
static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
unsigned long msecs)
{
@@ -1470,13 +1504,29 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
msecs_to_jiffies(msecs));
}
+/**
+ * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously.
+ * @hctx: Pointer to the hardware queue to run.
+ * @msecs: Microseconds of delay to wait before running the queue.
+ *
+ * Run a hardware queue asynchronously with a delay of @msecs.
+ */
void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
{
__blk_mq_delay_run_hw_queue(hctx, true, msecs);
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
-bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+/**
+ * blk_mq_run_hw_queue - Start to run a hardware queue.
+ * @hctx: Pointer to the hardware queue to run.
+ * @async: If we want to run the queue asynchronously.
+ *
+ * Check if the request queue is not in a quiesced state and if there are
+ * pending requests to be sent. If this is true, run the queue to send requests
+ * to hardware.
+ */
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
{
int srcu_idx;
bool need_run;
@@ -1494,15 +1544,16 @@ bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
blk_mq_hctx_has_pending(hctx);
hctx_unlock(hctx, srcu_idx);
- if (need_run) {
+ if (need_run)
__blk_mq_delay_run_hw_queue(hctx, async, 0);
- return true;
- }
-
- return false;
}
EXPORT_SYMBOL(blk_mq_run_hw_queue);
+/**
+ * blk_mq_run_hw_queue - Run all hardware queues in a request queue.
+ * @q: Pointer to the request queue to run.
+ * @async: If we want to run the queue asynchronously.
+ */
void blk_mq_run_hw_queues(struct request_queue *q, bool async)
{
struct blk_mq_hw_ctx *hctx;
@@ -1518,6 +1569,25 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async)
EXPORT_SYMBOL(blk_mq_run_hw_queues);
/**
+ * blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously.
+ * @q: Pointer to the request queue to run.
+ * @msecs: Microseconds of delay to wait before running the queues.
+ */
+void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
+{
+ struct blk_mq_hw_ctx *hctx;
+ int i;
+
+ queue_for_each_hw_ctx(q, hctx, i) {
+ if (blk_mq_hctx_stopped(hctx))
+ continue;
+
+ blk_mq_delay_run_hw_queue(hctx, msecs);
+ }
+}
+EXPORT_SYMBOL(blk_mq_delay_run_hw_queues);
+
+/**
* blk_mq_queue_stopped() - check whether one or more hctxs have been stopped
* @q: request queue.
*
@@ -1654,16 +1724,24 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
blk_mq_hctx_mark_pending(hctx, ctx);
}
-/*
+/**
+ * blk_mq_request_bypass_insert - Insert a request at dispatch list.
+ * @rq: Pointer to request to be inserted.
+ * @run_queue: If we should run the hardware queue after inserting the request.
+ *
* Should only be used carefully, when the caller knows we want to
* bypass a potential IO scheduler on the target device.
*/
-void blk_mq_request_bypass_insert(struct request *rq, bool run_queue)
+void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
+ bool run_queue)
{
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
spin_lock(&hctx->lock);
- list_add_tail(&rq->queuelist, &hctx->dispatch);
+ if (at_head)
+ list_add(&rq->queuelist, &hctx->dispatch);
+ else
+ list_add_tail(&rq->queuelist, &hctx->dispatch);
spin_unlock(&hctx->lock);
if (run_queue)
@@ -1697,28 +1775,20 @@ static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b)
struct request *rqa = container_of(a, struct request, queuelist);
struct request *rqb = container_of(b, struct request, queuelist);
- if (rqa->mq_ctx < rqb->mq_ctx)
- return -1;
- else if (rqa->mq_ctx > rqb->mq_ctx)
- return 1;
- else if (rqa->mq_hctx < rqb->mq_hctx)
- return -1;
- else if (rqa->mq_hctx > rqb->mq_hctx)
- return 1;
+ if (rqa->mq_ctx != rqb->mq_ctx)
+ return rqa->mq_ctx > rqb->mq_ctx;
+ if (rqa->mq_hctx != rqb->mq_hctx)
+ return rqa->mq_hctx > rqb->mq_hctx;
return blk_rq_pos(rqa) > blk_rq_pos(rqb);
}
void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
- struct blk_mq_hw_ctx *this_hctx;
- struct blk_mq_ctx *this_ctx;
- struct request_queue *this_q;
- struct request *rq;
LIST_HEAD(list);
- LIST_HEAD(rq_list);
- unsigned int depth;
+ if (list_empty(&plug->mq_list))
+ return;
list_splice_init(&plug->mq_list, &list);
if (plug->rq_count > 2 && plug->multiple_queues)
@@ -1726,49 +1796,41 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
plug->rq_count = 0;
- this_q = NULL;
- this_hctx = NULL;
- this_ctx = NULL;
- depth = 0;
-
- while (!list_empty(&list)) {
- rq = list_entry_rq(list.next);
- list_del_init(&rq->queuelist);
- BUG_ON(!rq->q);
- if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx) {
- if (this_hctx) {
- trace_block_unplug(this_q, depth, !from_schedule);
- blk_mq_sched_insert_requests(this_hctx, this_ctx,
- &rq_list,
- from_schedule);
- }
-
- this_q = rq->q;
- this_ctx = rq->mq_ctx;
- this_hctx = rq->mq_hctx;
- depth = 0;
+ do {
+ struct list_head rq_list;
+ struct request *rq, *head_rq = list_entry_rq(list.next);
+ struct list_head *pos = &head_rq->queuelist; /* skip first */
+ struct blk_mq_hw_ctx *this_hctx = head_rq->mq_hctx;
+ struct blk_mq_ctx *this_ctx = head_rq->mq_ctx;
+ unsigned int depth = 1;
+
+ list_for_each_continue(pos, &list) {
+ rq = list_entry_rq(pos);
+ BUG_ON(!rq->q);
+ if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx)
+ break;
+ depth++;
}
- depth++;
- list_add_tail(&rq->queuelist, &rq_list);
- }
-
- /*
- * If 'this_hctx' is set, we know we have entries to complete
- * on 'rq_list'. Do those.
- */
- if (this_hctx) {
- trace_block_unplug(this_q, depth, !from_schedule);
+ list_cut_before(&rq_list, &list, pos);
+ trace_block_unplug(head_rq->q, depth, !from_schedule);
blk_mq_sched_insert_requests(this_hctx, this_ctx, &rq_list,
from_schedule);
- }
+ } while(!list_empty(&list));
}
-static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
+static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
+ unsigned int nr_segs)
{
- blk_init_request_from_bio(rq, bio);
+ if (bio->bi_opf & REQ_RAHEAD)
+ rq->cmd_flags |= REQ_FAILFAST_MASK;
+
+ rq->__sector = bio->bi_iter.bi_sector;
+ rq->write_hint = bio->bi_write_hint;
+ blk_rq_bio_prep(rq, bio, nr_segs);
+ blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO);
- blk_account_io_start(rq, true);
+ blk_account_io_start(rq);
}
static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
@@ -1847,10 +1909,21 @@ insert:
if (bypass_insert)
return BLK_STS_RESOURCE;
- blk_mq_request_bypass_insert(rq, run_queue);
+ blk_mq_request_bypass_insert(rq, false, run_queue);
return BLK_STS_OK;
}
+/**
+ * blk_mq_try_issue_directly - Try to send a request directly to device driver.
+ * @hctx: Pointer of the associated hardware queue.
+ * @rq: Pointer to request to be sent.
+ * @cookie: Request queue cookie.
+ *
+ * If the device has enough resources to accept a new request now, send the
+ * request directly to device driver. Else, insert at hctx->dispatch queue, so
+ * we can try send it another time in the future. Requests inserted at this
+ * queue have higher priority.
+ */
static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
struct request *rq, blk_qc_t *cookie)
{
@@ -1863,7 +1936,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true);
if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
- blk_mq_request_bypass_insert(rq, true);
+ blk_mq_request_bypass_insert(rq, false, true);
else if (ret != BLK_STS_OK)
blk_mq_end_request(rq, ret);
@@ -1887,6 +1960,8 @@ blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
struct list_head *list)
{
+ int queued = 0;
+
while (!list_empty(list)) {
blk_status_t ret;
struct request *rq = list_first_entry(list, struct request,
@@ -1897,12 +1972,13 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
if (ret != BLK_STS_OK) {
if (ret == BLK_STS_RESOURCE ||
ret == BLK_STS_DEV_RESOURCE) {
- blk_mq_request_bypass_insert(rq,
+ blk_mq_request_bypass_insert(rq, false,
list_empty(list));
break;
}
blk_mq_end_request(rq, ret);
- }
+ } else
+ queued++;
}
/*
@@ -1910,7 +1986,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
* the driver there was more coming, but that turned out to
* be a lie.
*/
- if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs)
+ if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs && queued)
hctx->queue->mq_ops->commit_rqs(hctx);
}
@@ -1928,39 +2004,58 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
}
}
-static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
+/**
+ * blk_mq_make_request - Create and send a request to block device.
+ * @q: Request queue pointer.
+ * @bio: Bio pointer.
+ *
+ * Builds up a request structure from @q and @bio and send to the device. The
+ * request may not be queued directly to hardware if:
+ * * This request can be merged with another one
+ * * We want to place request at plug queue for possible future merging
+ * * There is an IO scheduler active at this queue
+ *
+ * It will not queue the request if there is an error with the bio, or at the
+ * request creation.
+ *
+ * Returns: Request queue cookie.
+ */
+blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
{
const int is_sync = op_is_sync(bio->bi_opf);
const int is_flush_fua = op_is_flush(bio->bi_opf);
- struct blk_mq_alloc_data data = { .flags = 0};
+ struct blk_mq_alloc_data data = {
+ .q = q,
+ };
struct request *rq;
struct blk_plug *plug;
struct request *same_queue_rq = NULL;
+ unsigned int nr_segs;
blk_qc_t cookie;
+ blk_status_t ret;
blk_queue_bounce(q, &bio);
-
- blk_queue_split(q, &bio);
+ __blk_queue_split(q, &bio, &nr_segs);
if (!bio_integrity_prep(bio))
- return BLK_QC_T_NONE;
+ goto queue_exit;
if (!is_flush_fua && !blk_queue_nomerges(q) &&
- blk_attempt_plug_merge(q, bio, &same_queue_rq))
- return BLK_QC_T_NONE;
+ blk_attempt_plug_merge(q, bio, nr_segs, &same_queue_rq))
+ goto queue_exit;
- if (blk_mq_sched_bio_merge(q, bio))
- return BLK_QC_T_NONE;
+ if (blk_mq_sched_bio_merge(q, bio, nr_segs))
+ goto queue_exit;
rq_qos_throttle(q, bio);
data.cmd_flags = bio->bi_opf;
- rq = blk_mq_get_request(q, bio, &data);
+ rq = __blk_mq_alloc_request(&data);
if (unlikely(!rq)) {
rq_qos_cleanup(q, bio);
if (bio->bi_opf & REQ_NOWAIT)
bio_wouldblock_error(bio);
- return BLK_QC_T_NONE;
+ goto queue_exit;
}
trace_block_getrq(q, bio, bio->bi_opf);
@@ -1969,25 +2064,33 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
cookie = request_to_qc_t(data.hctx, rq);
- plug = current->plug;
- if (unlikely(is_flush_fua)) {
- blk_mq_put_ctx(data.ctx);
- blk_mq_bio_to_request(rq, bio);
+ blk_mq_bio_to_request(rq, bio, nr_segs);
+
+ ret = blk_crypto_init_request(rq);
+ if (ret != BLK_STS_OK) {
+ bio->bi_status = ret;
+ bio_endio(bio);
+ blk_mq_free_request(rq);
+ return BLK_QC_T_NONE;
+ }
- /* bypass scheduler for flush rq */
+ plug = blk_mq_plug(q, bio);
+ if (unlikely(is_flush_fua)) {
+ /* Bypass scheduler for flush requests */
blk_insert_flush(rq);
blk_mq_run_hw_queue(data.hctx, true);
- } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs)) {
+ } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs ||
+ !blk_queue_nonrot(q))) {
/*
* Use plugging if we have a ->commit_rqs() hook as well, as
* we know the driver uses bd->last in a smart fashion.
+ *
+ * Use normal plugging if this disk is slow HDD, as sequential
+ * IO may benefit a lot from plug merging.
*/
unsigned int request_count = plug->rq_count;
struct request *last = NULL;
- blk_mq_put_ctx(data.ctx);
- blk_mq_bio_to_request(rq, bio);
-
if (!request_count)
trace_block_plug(q);
else
@@ -2000,9 +2103,10 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
}
blk_add_rq_to_plug(plug, rq);
+ } else if (q->elevator) {
+ /* Insert the request at the IO scheduler queue */
+ blk_mq_sched_insert_request(rq, false, true, true);
} else if (plug && !blk_queue_nomerges(q)) {
- blk_mq_bio_to_request(rq, bio);
-
/*
* We do limited plugging. If the bio can be merged, do that.
* Otherwise the existing request in the plug list will be
@@ -2019,27 +2123,30 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_add_rq_to_plug(plug, rq);
trace_block_plug(q);
- blk_mq_put_ctx(data.ctx);
-
if (same_queue_rq) {
data.hctx = same_queue_rq->mq_hctx;
trace_block_unplug(q, 1, true);
blk_mq_try_issue_directly(data.hctx, same_queue_rq,
&cookie);
}
- } else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
- !data.hctx->dispatch_busy)) {
- blk_mq_put_ctx(data.ctx);
- blk_mq_bio_to_request(rq, bio);
+ } else if ((q->nr_hw_queues > 1 && is_sync) ||
+ !data.hctx->dispatch_busy) {
+ /*
+ * There is no scheduler and we can try to send directly
+ * to the hardware.
+ */
blk_mq_try_issue_directly(data.hctx, rq, &cookie);
} else {
- blk_mq_put_ctx(data.ctx);
- blk_mq_bio_to_request(rq, bio);
+ /* Default case. */
blk_mq_sched_insert_request(rq, false, true, true);
}
return cookie;
+queue_exit:
+ blk_queue_exit(q);
+ return BLK_QC_T_NONE;
}
+EXPORT_SYMBOL_GPL(blk_mq_make_request); /* only for request based dm */
void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
unsigned int hctx_idx)
@@ -2215,6 +2322,86 @@ fail:
return -ENOMEM;
}
+struct rq_iter_data {
+ struct blk_mq_hw_ctx *hctx;
+ bool has_rq;
+};
+
+static bool blk_mq_has_request(struct request *rq, void *data, bool reserved)
+{
+ struct rq_iter_data *iter_data = data;
+
+ if (rq->mq_hctx != iter_data->hctx)
+ return true;
+ iter_data->has_rq = true;
+ return false;
+}
+
+static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
+{
+ struct blk_mq_tags *tags = hctx->sched_tags ?
+ hctx->sched_tags : hctx->tags;
+ struct rq_iter_data data = {
+ .hctx = hctx,
+ };
+
+ blk_mq_all_tag_iter(tags, blk_mq_has_request, &data);
+ return data.has_rq;
+}
+
+static inline bool blk_mq_last_cpu_in_hctx(unsigned int cpu,
+ struct blk_mq_hw_ctx *hctx)
+{
+ if (cpumask_next_and(-1, hctx->cpumask, cpu_online_mask) != cpu)
+ return false;
+ if (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) < nr_cpu_ids)
+ return false;
+ return true;
+}
+
+static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
+{
+ struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
+ struct blk_mq_hw_ctx, cpuhp_online);
+
+ if (!cpumask_test_cpu(cpu, hctx->cpumask) ||
+ !blk_mq_last_cpu_in_hctx(cpu, hctx))
+ return 0;
+
+ /*
+ * Prevent new request from being allocated on the current hctx.
+ *
+ * The smp_mb__after_atomic() Pairs with the implied barrier in
+ * test_and_set_bit_lock in sbitmap_get(). Ensures the inactive flag is
+ * seen once we return from the tag allocator.
+ */
+ set_bit(BLK_MQ_S_INACTIVE, &hctx->state);
+ smp_mb__after_atomic();
+
+ /*
+ * Try to grab a reference to the queue and wait for any outstanding
+ * requests. If we could not grab a reference the queue has been
+ * frozen and there are no requests.
+ */
+ if (percpu_ref_tryget(&hctx->queue->q_usage_counter)) {
+ while (blk_mq_hctx_has_requests(hctx))
+ msleep(5);
+ percpu_ref_put(&hctx->queue->q_usage_counter);
+ }
+
+ return 0;
+}
+
+static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node)
+{
+ struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
+ struct blk_mq_hw_ctx, cpuhp_online);
+
+ if (cpumask_test_cpu(cpu, hctx->cpumask))
+ clear_bit(BLK_MQ_S_INACTIVE, &hctx->state);
+ return 0;
+}
+
/*
* 'cpu' is going away. splice any existing rq_list entries from this
* software queue to the hw queue dispatch list, and ensure that it
@@ -2228,6 +2415,9 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
enum hctx_type type;
hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead);
+ if (!cpumask_test_cpu(cpu, hctx->cpumask))
+ return 0;
+
ctx = __blk_mq_get_ctx(hctx->queue, cpu);
type = hctx->type;
@@ -2251,6 +2441,9 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
{
+ if (!(hctx->flags & BLK_MQ_F_STACKING))
+ cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
+ &hctx->cpuhp_online);
cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD,
&hctx->cpuhp_dead);
}
@@ -2310,6 +2503,9 @@ static int blk_mq_init_hctx(struct request_queue *q,
{
hctx->queue_num = hctx_idx;
+ if (!(hctx->flags & BLK_MQ_F_STACKING))
+ cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
+ &hctx->cpuhp_online);
cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
hctx->tags = set->tags[hctx_idx];
@@ -2376,8 +2572,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
- hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size,
- gfp);
+ hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp);
if (!hctx->fq)
goto free_bitmap;
@@ -2429,7 +2624,8 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
}
}
-static bool __blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, int hctx_idx)
+static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set,
+ int hctx_idx)
{
int ret = 0;
@@ -2465,11 +2661,6 @@ static void blk_mq_map_swqueue(struct request_queue *q)
struct blk_mq_ctx *ctx;
struct blk_mq_tag_set *set = q->tag_set;
- /*
- * Avoid others reading imcomplete hctx->cpumask through sysfs
- */
- mutex_lock(&q->sysfs_lock);
-
queue_for_each_hw_ctx(q, hctx, i) {
cpumask_clear(hctx->cpumask);
hctx->nr_ctx = 0;
@@ -2482,18 +2673,6 @@ static void blk_mq_map_swqueue(struct request_queue *q)
* If the cpu isn't present, the cpu is mapped to first hctx.
*/
for_each_possible_cpu(i) {
- hctx_idx = set->map[HCTX_TYPE_DEFAULT].mq_map[i];
- /* unmapped hw queue can be remapped after CPU topo changed */
- if (!set->tags[hctx_idx] &&
- !__blk_mq_alloc_rq_map(set, hctx_idx)) {
- /*
- * If tags initialization fail for some hctx,
- * that hctx won't be brought online. In this
- * case, remap the current ctx to hctx[0] which
- * is guaranteed to always have tags allocated
- */
- set->map[HCTX_TYPE_DEFAULT].mq_map[i] = 0;
- }
ctx = per_cpu_ptr(q->queue_ctx, i);
for (j = 0; j < set->nr_maps; j++) {
@@ -2502,6 +2681,18 @@ static void blk_mq_map_swqueue(struct request_queue *q)
HCTX_TYPE_DEFAULT, i);
continue;
}
+ hctx_idx = set->map[j].mq_map[i];
+ /* unmapped hw queue can be remapped after CPU topo changed */
+ if (!set->tags[hctx_idx] &&
+ !__blk_mq_alloc_map_and_request(set, hctx_idx)) {
+ /*
+ * If tags initialization fail for some hctx,
+ * that hctx won't be brought online. In this
+ * case, remap the current ctx to hctx[0] which
+ * is guaranteed to always have tags allocated
+ */
+ set->map[j].mq_map[i] = 0;
+ }
hctx = blk_mq_map_queue_type(q, j, i);
ctx->hctxs[j] = hctx;
@@ -2530,8 +2721,6 @@ static void blk_mq_map_swqueue(struct request_queue *q)
HCTX_TYPE_DEFAULT, i);
}
- mutex_unlock(&q->sysfs_lock);
-
queue_for_each_hw_ctx(q, hctx, i) {
/*
* If no software queues are mapped to this hardware queue,
@@ -2674,8 +2863,6 @@ void blk_mq_release(struct request_queue *q)
struct blk_mq_hw_ctx *hctx, *next;
int i;
- cancel_delayed_work_sync(&q->requeue_work);
-
queue_for_each_hw_ctx(q, hctx, i)
WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list));
@@ -2694,20 +2881,32 @@ void blk_mq_release(struct request_queue *q)
blk_mq_sysfs_deinit(q);
}
-struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
+struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
+ void *queuedata)
{
struct request_queue *uninit_q, *q;
- uninit_q = blk_alloc_queue_node(GFP_KERNEL, set->numa_node);
+ uninit_q = __blk_alloc_queue(set->numa_node);
if (!uninit_q)
return ERR_PTR(-ENOMEM);
+ uninit_q->queuedata = queuedata;
- q = blk_mq_init_allocated_queue(set, uninit_q);
+ /*
+ * Initialize the queue without an elevator. device_add_disk() will do
+ * the initialization.
+ */
+ q = blk_mq_init_allocated_queue(set, uninit_q, false);
if (IS_ERR(q))
blk_cleanup_queue(uninit_q);
return q;
}
+EXPORT_SYMBOL_GPL(blk_mq_init_queue_data);
+
+struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
+{
+ return blk_mq_init_queue_data(set, NULL);
+}
EXPORT_SYMBOL(blk_mq_init_queue);
/*
@@ -2784,6 +2983,22 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
int i, j, end;
struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
+ if (q->nr_hw_queues < set->nr_hw_queues) {
+ struct blk_mq_hw_ctx **new_hctxs;
+
+ new_hctxs = kcalloc_node(set->nr_hw_queues,
+ sizeof(*new_hctxs), GFP_KERNEL,
+ set->numa_node);
+ if (!new_hctxs)
+ return;
+ if (hctxs)
+ memcpy(new_hctxs, hctxs, q->nr_hw_queues *
+ sizeof(*hctxs));
+ q->queue_hw_ctx = new_hctxs;
+ kfree(hctxs);
+ hctxs = new_hctxs;
+ }
+
/* protect against switching io scheduler */
mutex_lock(&q->sysfs_lock);
for (i = 0; i < set->nr_hw_queues; i++) {
@@ -2839,21 +3054,9 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
mutex_unlock(&q->sysfs_lock);
}
-/*
- * Maximum number of hardware queues we support. For single sets, we'll never
- * have more than the CPUs (software queues). For multiple sets, the tag_set
- * user may have set ->nr_hw_queues larger.
- */
-static unsigned int nr_hw_queues(struct blk_mq_tag_set *set)
-{
- if (set->nr_maps == 1)
- return nr_cpu_ids;
-
- return max(set->nr_hw_queues, nr_cpu_ids);
-}
-
struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
- struct request_queue *q)
+ struct request_queue *q,
+ bool elevator_init)
{
/* mark the queue as mq asap */
q->mq_ops = set->ops;
@@ -2870,12 +3073,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
/* init q->mq_kobj and sw queues' kobjects */
blk_mq_sysfs_init(q);
- q->nr_queues = nr_hw_queues(set);
- q->queue_hw_ctx = kcalloc_node(q->nr_queues, sizeof(*(q->queue_hw_ctx)),
- GFP_KERNEL, set->numa_node);
- if (!q->queue_hw_ctx)
- goto err_sys_init;
-
INIT_LIST_HEAD(&q->unused_hctx_list);
spin_lock_init(&q->unused_hctx_lock);
@@ -2899,11 +3096,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
INIT_LIST_HEAD(&q->requeue_list);
spin_lock_init(&q->requeue_lock);
- blk_queue_make_request(q, blk_mq_make_request);
-
- /*
- * Do this after blk_queue_make_request() overrides it...
- */
q->nr_requests = set->queue_depth;
/*
@@ -2915,19 +3107,14 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
blk_mq_add_queue_tag_set(set, q);
blk_mq_map_swqueue(q);
- if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
- int ret;
-
- ret = elevator_init_mq(q);
- if (ret)
- return ERR_PTR(ret);
- }
+ if (elevator_init)
+ elevator_init_mq(q);
return q;
err_hctxs:
kfree(q->queue_hw_ctx);
-err_sys_init:
+ q->nr_hw_queues = 0;
blk_mq_sysfs_deinit(q);
err_poll:
blk_stat_free_callback(q->poll_cb);
@@ -2952,14 +3139,14 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
int i;
for (i = 0; i < set->nr_hw_queues; i++)
- if (!__blk_mq_alloc_rq_map(set, i))
+ if (!__blk_mq_alloc_map_and_request(set, i))
goto out_unwind;
return 0;
out_unwind:
while (--i >= 0)
- blk_mq_free_rq_map(set->tags[i]);
+ blk_mq_free_map_and_requests(set, i);
return -ENOMEM;
}
@@ -2969,7 +3156,7 @@ out_unwind:
* may reduce the depth asked for, if memory is tight. set->queue_depth
* will be updated to reflect the allocated depth.
*/
-static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
+static int blk_mq_alloc_map_and_requests(struct blk_mq_tag_set *set)
{
unsigned int depth;
int err;
@@ -3001,6 +3188,14 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
{
+ /*
+ * blk_mq_map_queues() and multiple .map_queues() implementations
+ * expect that set->map[HCTX_TYPE_DEFAULT].nr_queues is set to the
+ * number of hardware queues.
+ */
+ if (set->nr_maps == 1)
+ set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues;
+
if (set->ops->map_queues && !is_kdump_kernel()) {
int i;
@@ -3028,6 +3223,29 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
}
}
+static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
+ int cur_nr_hw_queues, int new_nr_hw_queues)
+{
+ struct blk_mq_tags **new_tags;
+
+ if (cur_nr_hw_queues >= new_nr_hw_queues)
+ return 0;
+
+ new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *),
+ GFP_KERNEL, set->numa_node);
+ if (!new_tags)
+ return -ENOMEM;
+
+ if (set->tags)
+ memcpy(new_tags, set->tags, cur_nr_hw_queues *
+ sizeof(*set->tags));
+ kfree(set->tags);
+ set->tags = new_tags;
+ set->nr_hw_queues = new_nr_hw_queues;
+
+ return 0;
+}
+
/*
* Alloc a tag set to be associated with one or more request queues.
* May fail with EINVAL for various error conditions. May adjust the
@@ -3081,9 +3299,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids)
set->nr_hw_queues = nr_cpu_ids;
- set->tags = kcalloc_node(nr_hw_queues(set), sizeof(struct blk_mq_tags *),
- GFP_KERNEL, set->numa_node);
- if (!set->tags)
+ if (blk_mq_realloc_tag_set_tags(set, 0, set->nr_hw_queues) < 0)
return -ENOMEM;
ret = -ENOMEM;
@@ -3100,7 +3316,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
if (ret)
goto out_free_mq_map;
- ret = blk_mq_alloc_rq_maps(set);
+ ret = blk_mq_alloc_map_and_requests(set);
if (ret)
goto out_free_mq_map;
@@ -3124,7 +3340,7 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
{
int i, j;
- for (i = 0; i < nr_hw_queues(set); i++)
+ for (i = 0; i < set->nr_hw_queues; i++)
blk_mq_free_map_and_requests(set, i);
for (j = 0; j < set->nr_maps; j++) {
@@ -3263,16 +3479,14 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
if (set->nr_maps == 1 && nr_hw_queues > nr_cpu_ids)
nr_hw_queues = nr_cpu_ids;
- if (nr_hw_queues < 1 || nr_hw_queues == set->nr_hw_queues)
+ if (nr_hw_queues < 1)
+ return;
+ if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues)
return;
list_for_each_entry(q, &set->tag_list, tag_set_list)
blk_mq_freeze_queue(q);
/*
- * Sync with blk_mq_queue_tag_busy_iter.
- */
- synchronize_rcu();
- /*
* Switch IO scheduler to 'none', cleaning up the data associated
* with the previous scheduler. We will switch back once we are done
* updating the new sw to hw queue mappings.
@@ -3287,9 +3501,13 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
}
prev_nr_hw_queues = set->nr_hw_queues;
+ if (blk_mq_realloc_tag_set_tags(set, set->nr_hw_queues, nr_hw_queues) <
+ 0)
+ goto reregister;
+
set->nr_hw_queues = nr_hw_queues;
- blk_mq_update_queue_map(set);
fallback:
+ blk_mq_update_queue_map(set);
list_for_each_entry(q, &set->tag_list, tag_set_list) {
blk_mq_realloc_hw_ctxs(set, q);
if (q->nr_hw_queues != set->nr_hw_queues) {
@@ -3302,6 +3520,7 @@ fallback:
blk_mq_map_swqueue(q);
}
+reregister:
list_for_each_entry(q, &set->tag_list, tag_set_list) {
blk_mq_sysfs_register(q);
blk_mq_debugfs_register_hctxs(q);
@@ -3358,7 +3577,6 @@ static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb)
}
static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
- struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
unsigned long ret = 0;
@@ -3391,7 +3609,6 @@ static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
}
static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
- struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
struct hrtimer_sleeper hs;
@@ -3411,7 +3628,7 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
if (q->poll_nsec > 0)
nsecs = q->poll_nsec;
else
- nsecs = blk_mq_poll_nsecs(q, hctx, rq);
+ nsecs = blk_mq_poll_nsecs(q, rq);
if (!nsecs)
return false;
@@ -3425,15 +3642,14 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
kt = nsecs;
mode = HRTIMER_MODE_REL;
- hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode);
+ hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode);
hrtimer_set_expires(&hs.timer, kt);
- hrtimer_init_sleeper(&hs, current);
do {
if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE)
break;
set_current_state(TASK_UNINTERRUPTIBLE);
- hrtimer_start_expires(&hs.timer, mode);
+ hrtimer_sleeper_start_expires(&hs, mode);
if (hs.task)
io_schedule();
hrtimer_cancel(&hs.timer);
@@ -3467,7 +3683,7 @@ static bool blk_mq_poll_hybrid(struct request_queue *q,
return false;
}
- return blk_mq_poll_hybrid_sleep(q, hctx, rq);
+ return blk_mq_poll_hybrid_sleep(q, rq);
}
/**
@@ -3546,6 +3762,9 @@ static int __init blk_mq_init(void)
{
cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
blk_mq_hctx_notify_dead);
+ cpuhp_setup_state_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online",
+ blk_mq_hctx_notify_online,
+ blk_mq_hctx_notify_offline);
return 0;
}
subsys_initcall(blk_mq_init);