From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/block/blk-mq.c | 2347 +++++++++++++++++++++++++++++++++++++++-------------------
1 files changed, 1,571 insertions(+), 776 deletions(-)
diff --git a/kernel/block/blk-mq.c b/kernel/block/blk-mq.c
index 0f8dcb6..21544b1 100644
--- a/kernel/block/blk-mq.c
+++ b/kernel/block/blk-mq.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Block multiqueue core code
*
@@ -25,30 +26,36 @@
#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"
#include "blk-mq-tag.h"
+#include "blk-pm.h"
#include "blk-stat.h"
#include "blk-mq-sched.h"
#include "blk-rq-qos.h"
-static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie);
+#include <trace/hooks/block.h>
+
+static DEFINE_PER_CPU(struct list_head, blk_cpu_done);
+
static void blk_mq_poll_stats_start(struct request_queue *q);
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;
@@ -59,7 +66,8 @@
}
/*
- * Check if any of the ctx's have pending work in this hardware queue
+ * Check if any of the ctx, dispatch list or elevator
+ * have pending work in this hardware queue.
*/
static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
{
@@ -74,75 +82,67 @@
static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *ctx)
{
- if (!sbitmap_test_bit(&hctx->ctx_map, ctx->index_hw))
- sbitmap_set_bit(&hctx->ctx_map, ctx->index_hw);
+ const int bit = ctx->index_hw[hctx->type];
+
+ if (!sbitmap_test_bit(&hctx->ctx_map, bit))
+ sbitmap_set_bit(&hctx->ctx_map, bit);
}
static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *ctx)
{
- sbitmap_clear_bit(&hctx->ctx_map, ctx->index_hw);
+ const int bit = ctx->index_hw[hctx->type];
+
+ sbitmap_clear_bit(&hctx->ctx_map, bit);
}
struct mq_inflight {
struct hd_struct *part;
- unsigned int *inflight;
+ unsigned int inflight[2];
};
-static void blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
+static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
struct request *rq, void *priv,
bool reserved)
{
struct mq_inflight *mi = priv;
- /*
- * index[0] counts the specific partition that was asked for. index[1]
- * counts the ones that are active on the whole device, so increment
- * that if mi->part is indeed a partition, and not a whole device.
- */
- if (rq->part == mi->part)
- mi->inflight[0]++;
- if (mi->part->partno)
- mi->inflight[1]++;
-}
-
-void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
- unsigned int inflight[2])
-{
- struct mq_inflight mi = { .part = part, .inflight = inflight, };
-
- inflight[0] = inflight[1] = 0;
- blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
-}
-
-static void 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)
+ if ((!mi->part->partno || rq->part == mi->part) &&
+ blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
mi->inflight[rq_data_dir(rq)]++;
+
+ return true;
+}
+
+unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
+{
+ struct mq_inflight mi = { .part = part };
+
+ blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
+
+ 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)
{
- int freeze_depth;
-
- freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
- if (freeze_depth == 1) {
+ mutex_lock(&q->mq_freeze_lock);
+ if (++q->mq_freeze_depth == 1) {
percpu_ref_kill(&q->q_usage_counter);
- if (q->mq_ops)
+ mutex_unlock(&q->mq_freeze_lock);
+ if (queue_is_mq(q))
blk_mq_run_hw_queues(q, false);
+ } else {
+ mutex_unlock(&q->mq_freeze_lock);
}
}
EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
@@ -176,8 +176,6 @@
* exported to drivers as the only user for unfreeze is blk_mq.
*/
blk_freeze_queue_start(q);
- if (!q->mq_ops)
- blk_drain_queue(q);
blk_mq_freeze_queue_wait(q);
}
@@ -193,14 +191,14 @@
void blk_mq_unfreeze_queue(struct request_queue *q)
{
- int freeze_depth;
-
- freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
- WARN_ON_ONCE(freeze_depth < 0);
- if (!freeze_depth) {
- percpu_ref_reinit(&q->q_usage_counter);
+ mutex_lock(&q->mq_freeze_lock);
+ q->mq_freeze_depth--;
+ WARN_ON_ONCE(q->mq_freeze_depth < 0);
+ if (!q->mq_freeze_depth) {
+ percpu_ref_resurrect(&q->q_usage_counter);
wake_up_all(&q->mq_freeze_wq);
}
+ mutex_unlock(&q->mq_freeze_lock);
}
EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
@@ -268,40 +266,37 @@
blk_mq_tag_wakeup_all(hctx->tags, true);
}
-bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
+/*
+ * 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 blk_mq_has_free_tags(hctx->tags);
+ return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS)) || rq->q->elevator;
}
-EXPORT_SYMBOL(blk_mq_can_queue);
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;
+ if (data->q->elevator) {
+ rq->tag = BLK_MQ_NO_TAG;
rq->internal_tag = tag;
} else {
- if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
- rq_flags = RQF_MQ_INFLIGHT;
- atomic_inc(&data->hctx->nr_active);
- }
rq->tag = tag;
- rq->internal_tag = -1;
- data->hctx->tags->rqs[rq->tag] = rq;
+ rq->internal_tag = BLK_MQ_NO_TAG;
}
/* csd/requeue_work/fifo_time is initialized before use */
rq->q = data->q;
rq->mq_ctx = data->ctx;
- rq->rq_flags = rq_flags;
- rq->cpu = -1;
- rq->cmd_flags = op;
- if (data->flags & BLK_MQ_REQ_PREEMPT)
- rq->rq_flags |= RQF_PREEMPT;
+ rq->mq_hctx = data->hctx;
+ rq->rq_flags = 0;
+ rq->cmd_flags = data->cmd_flags;
+ if (data->flags & BLK_MQ_REQ_PM)
+ rq->rq_flags |= RQF_PM;
if (blk_queue_io_stat(data->q))
rq->rq_flags |= RQF_IO_STAT;
INIT_LIST_HEAD(&rq->queuelist);
@@ -309,100 +304,110 @@
RB_CLEAR_NODE(&rq->rb_node);
rq->rq_disk = NULL;
rq->part = NULL;
- rq->start_time_ns = ktime_get_ns();
+#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
- rq->special = NULL;
+ blk_crypto_rq_set_defaults(rq);
/* tag was already set */
- rq->extra_len = 0;
- rq->__deadline = 0;
+ WRITE_ONCE(rq->deadline, 0);
-#ifdef CONFIG_PREEMPT_RT_FULL
- INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work);
-#endif
- INIT_LIST_HEAD(&rq->timeout_list);
rq->timeout = 0;
rq->end_io = NULL;
rq->end_io_data = NULL;
- rq->next_rq = NULL;
-#ifdef CONFIG_BLK_CGROUP
- rq->rl = NULL;
-#endif
-
- 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++;
+ trace_android_vh_blk_rq_ctx_init(rq, tags, data, alloc_time_ns);
return rq;
}
-static struct request *blk_mq_get_request(struct request_queue *q,
- struct bio *bio, unsigned int op,
- 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->ctx->cpu);
- if (op & REQ_NOWAIT)
+ /* 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;
if (e) {
- data->flags |= BLK_MQ_REQ_INTERNAL;
-
/*
* Flush requests are special and go directly to the
* dispatch list. Don't include reserved tags in the
* limiting, as it isn't useful.
*/
- if (!op_is_flush(op) && e->type->ops.mq.limit_depth &&
+ if (!op_is_flush(data->cmd_flags) &&
+ e->type->ops.limit_depth &&
!(data->flags & BLK_MQ_REQ_RESERVED))
- e->type->ops.mq.limit_depth(op, data);
- } else {
+ e->type->ops.limit_depth(data->cmd_flags, data);
+ }
+
+retry:
+ data->ctx = blk_mq_get_ctx(q);
+ data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
+ if (!e)
blk_mq_tag_busy(data->hctx);
- }
+ /*
+ * 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_TAG_FAIL) {
- if (put_ctx_on_error) {
- blk_mq_put_ctx(data->ctx);
- data->ctx = NULL;
- }
- blk_queue_exit(q);
- return NULL;
- }
+ if (tag == BLK_MQ_NO_TAG) {
+ if (data->flags & BLK_MQ_REQ_NOWAIT)
+ return NULL;
- rq = blk_mq_rq_ctx_init(data, tag, op);
- if (!op_is_flush(op)) {
- rq->elv.icq = NULL;
- if (e && e->type->ops.mq.prepare_request) {
- if (e->type->icq_cache && rq_ioc(bio))
- blk_mq_sched_assign_ioc(rq, bio);
-
- e->type->ops.mq.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 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 };
+ struct blk_mq_alloc_data data = {
+ .q = q,
+ .flags = flags,
+ .cmd_flags = op,
+ };
struct request *rq;
int ret;
@@ -410,28 +415,35 @@
if (ret)
return ERR_PTR(ret);
- rq = blk_mq_get_request(q, NULL, op, &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 };
- 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
@@ -439,7 +451,8 @@
* 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)) ||
+ WARN_ON_ONCE(!(flags & BLK_MQ_REQ_RESERVED)))
return ERR_PTR(-EINVAL);
if (hctx_idx >= q->nr_hw_queues)
@@ -453,21 +466,27 @@
* 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);
+ 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);
+ if (cpu >= nr_cpu_ids)
+ goto out_queue_exit;
+ data.ctx = __blk_mq_get_ctx(q, cpu);
- rq = blk_mq_get_request(q, NULL, op, &alloc_data);
+ if (!q->elevator)
+ blk_mq_tag_busy(data.hctx);
+
+ 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);
+
+out_queue_exit:
blk_queue_exit(q);
-
- if (!rq)
- return ERR_PTR(-EWOULDBLOCK);
-
- return rq;
+ return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
@@ -475,13 +494,16 @@
{
struct request_queue *q = rq->q;
struct blk_mq_ctx *ctx = rq->mq_ctx;
- struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+ struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
const int sched_tag = rq->internal_tag;
- 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);
+ blk_crypto_free_request(rq);
+ blk_pm_mark_last_busy(rq);
+ rq->mq_hctx = NULL;
+ 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);
}
@@ -491,11 +513,11 @@
struct request_queue *q = rq->q;
struct elevator_queue *e = q->elevator;
struct blk_mq_ctx *ctx = rq->mq_ctx;
- struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+ struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
if (rq->rq_flags & RQF_ELVPRIV) {
- if (e && e->type->ops.mq.finish_request)
- e->type->ops.mq.finish_request(rq);
+ if (e && e->type->ops.finish_request)
+ e->type->ops.finish_request(rq);
if (rq->elv.icq) {
put_io_context(rq->elv.icq->ioc);
rq->elv.icq = NULL;
@@ -504,15 +526,12 @@
ctx->rq_completed[rq_is_sync(rq)]++;
if (rq->rq_flags & RQF_MQ_INFLIGHT)
- atomic_dec(&hctx->nr_active);
+ __blk_mq_dec_active_requests(hctx);
if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
laptop_io_completion(q->backing_dev_info);
rq_qos_done(q, rq);
-
- if (blk_rq_rl(rq))
- blk_put_rl(blk_rq_rl(rq));
WRITE_ONCE(rq->state, MQ_RQ_IDLE);
if (refcount_dec_and_test(&rq->ref))
@@ -522,12 +541,17 @@
inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
{
- u64 now = ktime_get_ns();
+ u64 now = 0;
+
+ if (blk_mq_need_time_stamp(rq))
+ now = ktime_get_ns();
if (rq->rq_flags & RQF_STATS) {
blk_mq_poll_stats_start(rq->q);
blk_stat_add(rq, now);
}
+
+ blk_mq_sched_completed_request(rq, now);
blk_account_io_done(rq, now);
@@ -535,8 +559,6 @@
rq_qos_done(rq->q, rq);
rq->end_io(rq, error);
} else {
- if (unlikely(blk_bidi_rq(rq)))
- blk_mq_free_request(rq->next_rq);
blk_mq_free_request(rq);
}
}
@@ -550,63 +572,139 @@
}
EXPORT_SYMBOL(blk_mq_end_request);
-#ifdef CONFIG_PREEMPT_RT_FULL
-
-void __blk_mq_complete_request_remote_work(struct work_struct *work)
+/*
+ * Softirq action handler - move entries to local list and loop over them
+ * while passing them to the queue registered handler.
+ */
+static __latent_entropy void blk_done_softirq(struct softirq_action *h)
{
- struct request *rq = container_of(work, struct request, work);
+ struct list_head *cpu_list, local_list;
- rq->q->softirq_done_fn(rq);
+ local_irq_disable();
+ cpu_list = this_cpu_ptr(&blk_cpu_done);
+ list_replace_init(cpu_list, &local_list);
+ local_irq_enable();
+
+ while (!list_empty(&local_list)) {
+ struct request *rq;
+
+ rq = list_entry(local_list.next, struct request, ipi_list);
+ list_del_init(&rq->ipi_list);
+ rq->q->mq_ops->complete(rq);
+ }
}
-#else
+static void blk_mq_trigger_softirq(struct request *rq)
+{
+ struct list_head *list;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ list = this_cpu_ptr(&blk_cpu_done);
+ list_add_tail(&rq->ipi_list, list);
+
+ /*
+ * If the list only contains our just added request, signal a raise of
+ * the softirq. If there are already entries there, someone already
+ * raised the irq but it hasn't run yet.
+ */
+ if (list->next == &rq->ipi_list)
+ raise_softirq_irqoff(BLOCK_SOFTIRQ);
+ local_irq_restore(flags);
+}
+
+static int blk_softirq_cpu_dead(unsigned int cpu)
+{
+ /*
+ * If a CPU goes away, splice its entries to the current CPU
+ * and trigger a run of the softirq
+ */
+ local_irq_disable();
+ list_splice_init(&per_cpu(blk_cpu_done, cpu),
+ this_cpu_ptr(&blk_cpu_done));
+ raise_softirq_irqoff(BLOCK_SOFTIRQ);
+ local_irq_enable();
+
+ return 0;
+}
+
static void __blk_mq_complete_request_remote(void *data)
{
struct request *rq = data;
- rq->q->softirq_done_fn(rq);
+ /*
+ * For most of single queue controllers, there is only one irq vector
+ * for handling I/O completion, and the only irq's affinity is set
+ * to all possible CPUs. On most of ARCHs, this affinity means the irq
+ * is handled on one specific CPU.
+ *
+ * So complete I/O requests in softirq context in case of single queue
+ * devices to avoid degrading I/O performance due to irqsoff latency.
+ */
+ if (rq->q->nr_hw_queues == 1)
+ blk_mq_trigger_softirq(rq);
+ else
+ rq->q->mq_ops->complete(rq);
}
-#endif
-static void __blk_mq_complete_request(struct request *rq)
+static inline bool blk_mq_complete_need_ipi(struct request *rq)
{
- struct blk_mq_ctx *ctx = rq->mq_ctx;
- bool shared = false;
- int cpu;
+ int cpu = raw_smp_processor_id();
- if (!blk_mq_mark_complete(rq))
- return;
- if (rq->internal_tag != -1)
- blk_mq_sched_completed_request(rq);
+ if (!IS_ENABLED(CONFIG_SMP) ||
+ !test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags))
+ return false;
- if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) {
- rq->q->softirq_done_fn(rq);
- return;
- }
+ /* same CPU or cache domain? Complete locally */
+ if (cpu == rq->mq_ctx->cpu ||
+ (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags) &&
+ cpus_share_cache(cpu, rq->mq_ctx->cpu)))
+ return false;
- cpu = get_cpu_light();
- if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags))
- shared = cpus_share_cache(cpu, ctx->cpu);
+ /* don't try to IPI to an offline CPU */
+ return cpu_online(rq->mq_ctx->cpu);
+}
- if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) {
-#ifdef CONFIG_PREEMPT_RT_FULL
- /*
- * We could force QUEUE_FLAG_SAME_FORCE then we would not get in
- * here. But we could try to invoke it one the CPU like this.
- */
- schedule_work_on(ctx->cpu, &rq->work);
-#else
+bool blk_mq_complete_request_remote(struct request *rq)
+{
+ WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
+
+ /*
+ * For a polled request, always complete locallly, it's pointless
+ * to redirect the completion.
+ */
+ if (rq->cmd_flags & REQ_HIPRI)
+ return false;
+
+ if (blk_mq_complete_need_ipi(rq)) {
rq->csd.func = __blk_mq_complete_request_remote;
rq->csd.info = rq;
rq->csd.flags = 0;
- smp_call_function_single_async(ctx->cpu, &rq->csd);
-#endif
+ smp_call_function_single_async(rq->mq_ctx->cpu, &rq->csd);
} else {
- rq->q->softirq_done_fn(rq);
+ if (rq->q->nr_hw_queues > 1)
+ return false;
+ blk_mq_trigger_softirq(rq);
}
- put_cpu_light();
+
+ return true;
}
+EXPORT_SYMBOL_GPL(blk_mq_complete_request_remote);
+
+/**
+ * blk_mq_complete_request - end I/O on a request
+ * @rq: the request being processed
+ *
+ * Description:
+ * Complete a request by scheduling the ->complete_rq operation.
+ **/
+void blk_mq_complete_request(struct request *rq)
+{
+ if (!blk_mq_complete_request_remote(rq))
+ rq->q->mq_ops->complete(rq);
+}
+EXPORT_SYMBOL(blk_mq_complete_request);
static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx)
__releases(hctx->srcu)
@@ -629,40 +727,22 @@
}
/**
- * blk_mq_complete_request - end I/O on a request
- * @rq: the request being processed
+ * blk_mq_start_request - Start processing a request
+ * @rq: Pointer to request to be started
*
- * Description:
- * Ends all I/O on a request. It does not handle partial completions.
- * The actual completion happens out-of-order, through a IPI handler.
- **/
-void blk_mq_complete_request(struct request *rq)
-{
- if (unlikely(blk_should_fake_timeout(rq->q)))
- return;
- __blk_mq_complete_request(rq);
-}
-EXPORT_SYMBOL(blk_mq_complete_request);
-
-int blk_mq_request_started(struct request *rq)
-{
- return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
-}
-EXPORT_SYMBOL_GPL(blk_mq_request_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);
}
@@ -672,14 +752,10 @@
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);
@@ -695,8 +771,6 @@
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--;
}
}
@@ -707,7 +781,6 @@
/* this request will be re-inserted to io scheduler queue */
blk_mq_sched_requeue_request(rq);
- BUG_ON(blk_queued_rq(rq));
blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
}
EXPORT_SYMBOL(blk_mq_requeue_request);
@@ -735,7 +808,7 @@
* 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);
}
@@ -773,7 +846,6 @@
if (kick_requeue_list)
blk_mq_kick_requeue_list(q);
}
-EXPORT_SYMBOL(blk_mq_add_to_requeue_list);
void blk_mq_kick_requeue_list(struct request_queue *q)
{
@@ -800,6 +872,32 @@
}
EXPORT_SYMBOL(blk_mq_tag_to_rq);
+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 isn't idle and the queue matches,
+ * we know the queue is busy. Return false to stop the iteration.
+ */
+ if (blk_mq_request_started(rq) && rq->q == hctx->queue) {
+ bool *busy = priv;
+
+ *busy = true;
+ return false;
+ }
+
+ return true;
+}
+
+bool blk_mq_queue_inflight(struct request_queue *q)
+{
+ bool busy = false;
+
+ blk_mq_queue_tag_busy_iter(q, blk_mq_rq_inflight, &busy);
+ return busy;
+}
+EXPORT_SYMBOL_GPL(blk_mq_queue_inflight);
+
static void blk_mq_rq_timed_out(struct request *req, bool reserved)
{
req->rq_flags |= RQF_TIMED_OUT;
@@ -824,7 +922,7 @@
if (rq->rq_flags & RQF_TIMED_OUT)
return false;
- deadline = blk_rq_deadline(rq);
+ deadline = READ_ONCE(rq->deadline);
if (time_after_eq(jiffies, deadline))
return true;
@@ -835,43 +933,29 @@
return false;
}
-static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
+void blk_mq_put_rq_ref(struct request *rq)
+{
+ if (is_flush_rq(rq))
+ rq->end_io(rq, 0);
+ else if (refcount_dec_and_test(&rq->ref))
+ __blk_mq_free_request(rq);
+}
+
+static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
struct request *rq, void *priv, bool reserved)
{
unsigned long *next = priv;
/*
- * Just do a quick check if it is expired before locking the request in
- * so we're not unnecessarilly synchronizing across CPUs.
- */
- if (!blk_mq_req_expired(rq, next))
- return;
-
- /*
- * We have reason to believe the request may be expired. Take a
- * reference on the request to lock this request lifetime into its
- * currently allocated context to prevent it from being reallocated in
- * the event the completion by-passes this timeout handler.
- *
- * If the reference was already released, then the driver beat the
- * timeout handler to posting a natural completion.
- */
- if (!refcount_inc_not_zero(&rq->ref))
- return;
-
- /*
- * The request is now locked and cannot be reallocated underneath the
- * timeout handler's processing. Re-verify this exact request is truly
- * expired; if it is not expired, then the request was completed and
- * reallocated as a new request.
+ * blk_mq_queue_tag_busy_iter() has locked the request, so it cannot
+ * be reallocated underneath the timeout handler's processing, then
+ * the expire check is reliable. If the request is not expired, then
+ * it was completed and reallocated as a new request after returning
+ * from blk_mq_check_expired().
*/
if (blk_mq_req_expired(rq, next))
blk_mq_rq_timed_out(rq, reserved);
-
- 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;
}
static void blk_mq_timeout_work(struct work_struct *work)
@@ -928,9 +1012,10 @@
struct flush_busy_ctx_data *flush_data = data;
struct blk_mq_hw_ctx *hctx = flush_data->hctx;
struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
+ enum hctx_type type = hctx->type;
spin_lock(&ctx->lock);
- list_splice_tail_init(&ctx->rq_list, flush_data->list);
+ list_splice_tail_init(&ctx->rq_lists[type], flush_data->list);
sbitmap_clear_bit(sb, bitnr);
spin_unlock(&ctx->lock);
return true;
@@ -962,12 +1047,13 @@
struct dispatch_rq_data *dispatch_data = data;
struct blk_mq_hw_ctx *hctx = dispatch_data->hctx;
struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
+ enum hctx_type type = hctx->type;
spin_lock(&ctx->lock);
- if (!list_empty(&ctx->rq_list)) {
- dispatch_data->rq = list_entry_rq(ctx->rq_list.next);
+ if (!list_empty(&ctx->rq_lists[type])) {
+ dispatch_data->rq = list_entry_rq(ctx->rq_lists[type].next);
list_del_init(&dispatch_data->rq->queuelist);
- if (list_empty(&ctx->rq_list))
+ if (list_empty(&ctx->rq_lists[type]))
sbitmap_clear_bit(sb, bitnr);
}
spin_unlock(&ctx->lock);
@@ -978,7 +1064,7 @@
struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *start)
{
- unsigned off = start ? start->index_hw : 0;
+ unsigned off = start ? start->index_hw[hctx->type] : 0;
struct dispatch_rq_data data = {
.hctx = hctx,
.rq = NULL,
@@ -998,33 +1084,44 @@
return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
}
-bool blk_mq_get_driver_tag(struct request *rq)
+static bool __blk_mq_get_driver_tag(struct request *rq)
{
- struct blk_mq_alloc_data data = {
- .q = rq->q,
- .hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
- .flags = BLK_MQ_REQ_NOWAIT,
- };
- bool shared;
+ struct sbitmap_queue *bt = rq->mq_hctx->tags->bitmap_tags;
+ unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
+ int tag;
- if (rq->tag != -1)
- goto done;
+ blk_mq_tag_busy(rq->mq_hctx);
- 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;
+ if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) {
+ bt = rq->mq_hctx->tags->breserved_tags;
+ tag_offset = 0;
+ } else {
+ if (!hctx_may_queue(rq->mq_hctx, bt))
+ return false;
}
-done:
- return rq->tag != -1;
+ tag = __sbitmap_queue_get(bt);
+ if (tag == BLK_MQ_NO_TAG)
+ return false;
+
+ rq->tag = tag + tag_offset;
+ return true;
+}
+
+static bool blk_mq_get_driver_tag(struct request *rq)
+{
+ struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+ if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq))
+ return false;
+
+ if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
+ !(rq->rq_flags & RQF_MQ_INFLIGHT)) {
+ rq->rq_flags |= RQF_MQ_INFLIGHT;
+ __blk_mq_inc_active_requests(hctx);
+ }
+ hctx->tags->rqs[rq->tag] = rq;
+ return true;
}
static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
@@ -1035,7 +1132,13 @@
hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
spin_lock(&hctx->dispatch_wait_lock);
- list_del_init(&wait->entry);
+ if (!list_empty(&wait->entry)) {
+ struct sbitmap_queue *sbq;
+
+ list_del_init(&wait->entry);
+ sbq = hctx->tags->bitmap_tags;
+ atomic_dec(&sbq->ws_active);
+ }
spin_unlock(&hctx->dispatch_wait_lock);
blk_mq_run_hw_queue(hctx, true);
@@ -1051,13 +1154,13 @@
static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
+ struct sbitmap_queue *sbq = hctx->tags->bitmap_tags;
struct wait_queue_head *wq;
wait_queue_entry_t *wait;
bool ret;
- if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) {
- if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
- set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+ if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+ blk_mq_sched_mark_restart_hctx(hctx);
/*
* It's possible that a tag was freed in the window between the
@@ -1074,7 +1177,7 @@
if (!list_empty_careful(&wait->entry))
return false;
- wq = &bt_wait_ptr(&hctx->tags->bitmap_tags, hctx)->wait;
+ wq = &bt_wait_ptr(sbq, hctx)->wait;
spin_lock_irq(&wq->lock);
spin_lock(&hctx->dispatch_wait_lock);
@@ -1084,6 +1187,7 @@
return false;
}
+ atomic_inc(&sbq->ws_active);
wait->flags &= ~WQ_FLAG_EXCLUSIVE;
__add_wait_queue(wq, wait);
@@ -1104,6 +1208,7 @@
* someone else gets the wakeup.
*/
list_del_init(&wait->entry);
+ atomic_dec(&sbq->ws_active);
spin_unlock(&hctx->dispatch_wait_lock);
spin_unlock_irq(&wq->lock);
@@ -1122,9 +1227,6 @@
static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy)
{
unsigned int ewma;
-
- if (hctx->queue->elevator)
- return;
ewma = hctx->dispatch_busy;
@@ -1158,22 +1260,83 @@
__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);
+}
+
+enum prep_dispatch {
+ PREP_DISPATCH_OK,
+ PREP_DISPATCH_NO_TAG,
+ PREP_DISPATCH_NO_BUDGET,
+};
+
+static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq,
+ bool need_budget)
+{
+ struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+ if (need_budget && !blk_mq_get_dispatch_budget(rq->q)) {
+ blk_mq_put_driver_tag(rq);
+ return PREP_DISPATCH_NO_BUDGET;
+ }
+
+ if (!blk_mq_get_driver_tag(rq)) {
+ /*
+ * The initial allocation attempt failed, so we need to
+ * rerun the hardware queue when a tag is freed. The
+ * waitqueue takes care of that. If the queue is run
+ * before we add this entry back on the dispatch list,
+ * we'll re-run it below.
+ */
+ if (!blk_mq_mark_tag_wait(hctx, rq)) {
+ /*
+ * All budgets not got from this function will be put
+ * together during handling partial dispatch
+ */
+ if (need_budget)
+ blk_mq_put_dispatch_budget(rq->q);
+ return PREP_DISPATCH_NO_TAG;
+ }
+ }
+
+ return PREP_DISPATCH_OK;
+}
+
+/* release all allocated budgets before calling to blk_mq_dispatch_rq_list */
+static void blk_mq_release_budgets(struct request_queue *q,
+ unsigned int nr_budgets)
+{
+ int i;
+
+ for (i = 0; i < nr_budgets; i++)
+ blk_mq_put_dispatch_budget(q);
+}
+
/*
* Returns true if we did some work AND can potentially do more.
*/
-bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
- bool got_budget)
+bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
+ unsigned int nr_budgets)
{
- struct blk_mq_hw_ctx *hctx;
+ enum prep_dispatch prep;
+ struct request_queue *q = hctx->queue;
struct request *rq, *nxt;
- bool no_tag = false;
int errors, queued;
blk_status_t ret = BLK_STS_OK;
+ LIST_HEAD(zone_list);
+ bool needs_resource = false;
if (list_empty(list))
return false;
-
- WARN_ON(!list_is_singular(list) && got_budget);
/*
* Now process all the entries, sending them to the driver.
@@ -1184,29 +1347,10 @@
rq = list_first_entry(list, struct request, queuelist);
- hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
- if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
+ WARN_ON_ONCE(hctx != rq->mq_hctx);
+ prep = blk_mq_prep_dispatch_rq(rq, !nr_budgets);
+ if (prep != PREP_DISPATCH_OK)
break;
-
- if (!blk_mq_get_driver_tag(rq)) {
- /*
- * The initial allocation attempt failed, so we need to
- * rerun the hardware queue when a tag is freed. The
- * waitqueue takes care of that. If the queue is run
- * before we add this entry back on the dispatch list,
- * we'll re-run it below.
- */
- if (!blk_mq_mark_tag_wait(hctx, rq)) {
- blk_mq_put_dispatch_budget(hctx);
- /*
- * For non-shared tags, the RESTART check
- * will suffice.
- */
- if (hctx->flags & BLK_MQ_F_TAG_SHARED)
- no_tag = true;
- break;
- }
- }
list_del_init(&rq->queuelist);
@@ -1223,32 +1367,63 @@
bd.last = !blk_mq_get_driver_tag(nxt);
}
+ /*
+ * once the request is queued to lld, no need to cover the
+ * budget any more
+ */
+ if (nr_budgets)
+ nr_budgets--;
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);
+ switch (ret) {
+ case BLK_STS_OK:
+ queued++;
break;
- }
-
- if (unlikely(ret != BLK_STS_OK)) {
+ case BLK_STS_RESOURCE:
+ needs_resource = true;
+ fallthrough;
+ case BLK_STS_DEV_RESOURCE:
+ blk_mq_handle_dev_resource(rq, list);
+ goto out;
+ case BLK_STS_ZONE_RESOURCE:
+ /*
+ * Move the request to zone_list and keep going through
+ * the dispatch list to find more requests the drive can
+ * accept.
+ */
+ blk_mq_handle_zone_resource(rq, &zone_list);
+ needs_resource = true;
+ break;
+ default:
errors++;
blk_mq_end_request(rq, BLK_STS_IOERR);
- continue;
}
-
- queued++;
} while (!list_empty(list));
+out:
+ if (!list_empty(&zone_list))
+ list_splice_tail_init(&zone_list, list);
hctx->dispatched[queued_to_index(queued)]++;
+ /* If we didn't flush the entire list, we could have told the driver
+ * there was more coming, but that turned out to be a lie.
+ */
+ if ((!list_empty(list) || errors || needs_resource ||
+ ret == BLK_STS_DEV_RESOURCE) && q->mq_ops->commit_rqs && queued)
+ q->mq_ops->commit_rqs(hctx);
/*
* Any items that need requeuing? Stuff them into hctx->dispatch,
* that is where we will continue on next queue run.
*/
if (!list_empty(list)) {
bool needs_restart;
+ /* For non-shared tags, the RESTART check will suffice */
+ bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
+ (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
+
+ blk_mq_release_budgets(q, nr_budgets);
spin_lock(&hctx->lock);
- list_splice_init(list, &hctx->dispatch);
+ list_splice_tail_init(list, &hctx->dispatch);
spin_unlock(&hctx->lock);
/*
@@ -1282,13 +1457,17 @@
*
* 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 or couldn't lock a zone
+ * and SCHED_RESTART is set.
*/
needs_restart = blk_mq_sched_needs_restart(hctx);
+ if (prep == PREP_DISPATCH_NO_BUDGET)
+ needs_resource = true;
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 && needs_resource)
blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
blk_mq_update_dispatch_busy(hctx, true);
@@ -1296,16 +1475,15 @@
} else
blk_mq_update_dispatch_busy(hctx, false);
- /*
- * If the host/device is unable to accept more work, inform the
- * caller of that.
- */
- if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
- return false;
-
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;
@@ -1403,6 +1581,15 @@
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)
{
@@ -1410,27 +1597,43 @@
return;
if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
- int cpu = get_cpu_light();
+ int cpu = get_cpu();
if (cpumask_test_cpu(cpu, hctx->cpumask)) {
__blk_mq_run_hw_queue(hctx);
- put_cpu_light();
+ put_cpu();
return;
}
- put_cpu_light();
+ put_cpu();
}
kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
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;
@@ -1448,28 +1651,101 @@
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);
+/*
+ * Is the request queue handled by an IO scheduler that does not respect
+ * hardware queues when dispatching?
+ */
+static bool blk_mq_has_sqsched(struct request_queue *q)
+{
+ struct elevator_queue *e = q->elevator;
+
+ if (e && e->type->ops.dispatch_request &&
+ !(e->type->elevator_features & ELEVATOR_F_MQ_AWARE))
+ return true;
+ return false;
+}
+
+/*
+ * Return prefered queue to dispatch from (if any) for non-mq aware IO
+ * scheduler.
+ */
+static struct blk_mq_hw_ctx *blk_mq_get_sq_hctx(struct request_queue *q)
+{
+ struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
+ /*
+ * If the IO scheduler does not respect hardware queues when
+ * dispatching, we just don't bother with multiple HW queues and
+ * dispatch from hctx for the current CPU since running multiple queues
+ * just causes lock contention inside the scheduler and pointless cache
+ * bouncing.
+ */
+ struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, 0, ctx);
+
+ if (!blk_mq_hctx_stopped(hctx))
+ return hctx;
+ return NULL;
+}
+
+/**
+ * blk_mq_run_hw_queues - 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;
+ struct blk_mq_hw_ctx *hctx, *sq_hctx;
int i;
+ sq_hctx = NULL;
+ if (blk_mq_has_sqsched(q))
+ sq_hctx = blk_mq_get_sq_hctx(q);
queue_for_each_hw_ctx(q, hctx, i) {
if (blk_mq_hctx_stopped(hctx))
continue;
-
- blk_mq_run_hw_queue(hctx, async);
+ /*
+ * Dispatch from this hctx either if there's no hctx preferred
+ * by IO scheduler or if it has requests that bypass the
+ * scheduler.
+ */
+ if (!sq_hctx || sq_hctx == hctx ||
+ !list_empty_careful(&hctx->dispatch))
+ blk_mq_run_hw_queue(hctx, 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, *sq_hctx;
+ int i;
+
+ sq_hctx = NULL;
+ if (blk_mq_has_sqsched(q))
+ sq_hctx = blk_mq_get_sq_hctx(q);
+ queue_for_each_hw_ctx(q, hctx, i) {
+ if (blk_mq_hctx_stopped(hctx))
+ continue;
+ /*
+ * Dispatch from this hctx either if there's no hctx preferred
+ * by IO scheduler or if it has requests that bypass the
+ * scheduler.
+ */
+ if (!sq_hctx || sq_hctx == hctx ||
+ !list_empty_careful(&hctx->dispatch))
+ 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
@@ -1574,7 +1850,7 @@
/*
* If we are stopped, don't run the queue.
*/
- if (test_bit(BLK_MQ_S_STOPPED, &hctx->state))
+ if (blk_mq_hctx_stopped(hctx))
return;
__blk_mq_run_hw_queue(hctx);
@@ -1585,15 +1861,16 @@
bool at_head)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
+ enum hctx_type type = hctx->type;
lockdep_assert_held(&ctx->lock);
trace_block_rq_insert(hctx->queue, rq);
if (at_head)
- list_add(&rq->queuelist, &ctx->rq_list);
+ list_add(&rq->queuelist, &ctx->rq_lists[type]);
else
- list_add_tail(&rq->queuelist, &ctx->rq_list);
+ list_add_tail(&rq->queuelist, &ctx->rq_lists[type]);
}
void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
@@ -1607,17 +1884,25 @@
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.
+ * @at_head: true if the request should be inserted at the head of the list.
+ * @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_ctx *ctx = rq->mq_ctx;
- struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, ctx->cpu);
+ 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)
@@ -1629,6 +1914,7 @@
{
struct request *rq;
+ enum hctx_type type = hctx->type;
/*
* preemption doesn't flush plug list, so it's possible ctx->cpu is
@@ -1640,95 +1926,87 @@
}
spin_lock(&ctx->lock);
- list_splice_tail_init(list, &ctx->rq_list);
+ list_splice_tail_init(list, &ctx->rq_lists[type]);
blk_mq_hctx_mark_pending(hctx, ctx);
spin_unlock(&ctx->lock);
}
-static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
+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);
- return !(rqa->mq_ctx < rqb->mq_ctx ||
- (rqa->mq_ctx == rqb->mq_ctx &&
- blk_rq_pos(rqa) < blk_rq_pos(rqb)));
+ 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_ctx *this_ctx;
- struct request_queue *this_q;
- struct request *rq;
LIST_HEAD(list);
- LIST_HEAD(ctx_list);
- unsigned int depth;
+ if (list_empty(&plug->mq_list))
+ return;
list_splice_init(&plug->mq_list, &list);
- list_sort(NULL, &list, plug_ctx_cmp);
+ if (plug->rq_count > 2 && plug->multiple_queues)
+ list_sort(NULL, &list, plug_rq_cmp);
- this_q = NULL;
- this_ctx = NULL;
- depth = 0;
+ plug->rq_count = 0;
- while (!list_empty(&list)) {
- rq = list_entry_rq(list.next);
- list_del_init(&rq->queuelist);
- BUG_ON(!rq->q);
- if (rq->mq_ctx != this_ctx) {
- if (this_ctx) {
- trace_block_unplug(this_q, depth, !from_schedule);
- blk_mq_sched_insert_requests(this_q, this_ctx,
- &ctx_list,
- from_schedule);
- }
+ 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;
- this_ctx = rq->mq_ctx;
- this_q = rq->q;
- depth = 0;
+ 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, &ctx_list);
- }
-
- /*
- * If 'this_ctx' is set, we know we have entries to complete
- * on 'ctx_list'. Do those.
- */
- if (this_ctx) {
- trace_block_unplug(this_q, depth, !from_schedule);
- blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list,
+ 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);
+ int err;
- blk_rq_set_rl(rq, blk_get_rl(rq->q, bio));
+ if (bio->bi_opf & REQ_RAHEAD)
+ rq->cmd_flags |= REQ_FAILFAST_MASK;
- blk_account_io_start(rq, true);
-}
+ rq->__sector = bio->bi_iter.bi_sector;
+ rq->write_hint = bio->bi_write_hint;
+ blk_rq_bio_prep(rq, bio, nr_segs);
-static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
-{
- if (rq->tag != -1)
- return blk_tag_to_qc_t(rq->tag, hctx->queue_num, false);
+ /* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */
+ err = blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO);
+ WARN_ON_ONCE(err);
- return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
+ blk_account_io_start(rq);
}
static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
struct request *rq,
- blk_qc_t *cookie)
+ blk_qc_t *cookie, bool last)
{
struct request_queue *q = rq->q;
struct blk_mq_queue_data bd = {
.rq = rq,
- .last = true,
+ .last = last,
};
blk_qc_t new_cookie;
blk_status_t ret;
@@ -1763,7 +2041,7 @@
static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
struct request *rq,
blk_qc_t *cookie,
- bool bypass_insert)
+ bool bypass_insert, bool last)
{
struct request_queue *q = rq->q;
bool run_queue = true;
@@ -1784,23 +2062,35 @@
if (q->elevator && !bypass_insert)
goto insert;
- if (!blk_mq_get_dispatch_budget(hctx))
+ if (!blk_mq_get_dispatch_budget(q))
goto insert;
if (!blk_mq_get_driver_tag(rq)) {
- blk_mq_put_dispatch_budget(hctx);
+ blk_mq_put_dispatch_budget(q);
goto insert;
}
- return __blk_mq_issue_directly(hctx, rq, cookie);
+ return __blk_mq_issue_directly(hctx, rq, cookie, last);
insert:
if (bypass_insert)
return BLK_STS_RESOURCE;
- blk_mq_request_bypass_insert(rq, run_queue);
+ blk_mq_sched_insert_request(rq, false, run_queue, false);
+
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)
{
@@ -1811,25 +2101,24 @@
hctx_lock(hctx, &srcu_idx);
- ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false);
+ 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);
hctx_unlock(hctx, srcu_idx);
}
-blk_status_t blk_mq_request_issue_directly(struct request *rq)
+blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
{
blk_status_t ret;
int srcu_idx;
blk_qc_t unused_cookie;
- struct blk_mq_ctx *ctx = rq->mq_ctx;
- struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, ctx->cpu);
+ struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
hctx_lock(hctx, &srcu_idx);
- ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true);
+ ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true, last);
hctx_unlock(hctx, srcu_idx);
return ret;
@@ -1838,104 +2127,169 @@
void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
struct list_head *list)
{
+ int queued = 0;
+ int errors = 0;
+
while (!list_empty(list)) {
blk_status_t ret;
struct request *rq = list_first_entry(list, struct request,
queuelist);
list_del_init(&rq->queuelist);
- ret = blk_mq_request_issue_directly(rq);
+ ret = blk_mq_request_issue_directly(rq, list_empty(list));
if (ret != BLK_STS_OK) {
+ errors++;
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++;
+ }
+
+ /*
+ * If we didn't flush the entire list, we could have told
+ * the driver there was more coming, but that turned out to
+ * be a lie.
+ */
+ if ((!list_empty(list) || errors) &&
+ hctx->queue->mq_ops->commit_rqs && queued)
+ hctx->queue->mq_ops->commit_rqs(hctx);
+}
+
+static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
+{
+ list_add_tail(&rq->queuelist, &plug->mq_list);
+ plug->rq_count++;
+ if (!plug->multiple_queues && !list_is_singular(&plug->mq_list)) {
+ struct request *tmp;
+
+ tmp = list_first_entry(&plug->mq_list, struct request,
+ queuelist);
+ if (tmp->q != rq->q)
+ plug->multiple_queues = true;
}
}
-static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
+/*
+ * Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple
+ * queues. This is important for md arrays to benefit from merging
+ * requests.
+ */
+static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug)
{
+ if (plug->multiple_queues)
+ return BLK_MAX_REQUEST_COUNT * 2;
+ return BLK_MAX_REQUEST_COUNT;
+}
+
+/**
+ * blk_mq_submit_bio - Create and send a request to block device.
+ * @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_submit_bio(struct bio *bio)
+{
+ struct request_queue *q = bio->bi_disk->queue;
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;
- unsigned int request_count = 0;
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(&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, &request_count, &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, NULL);
+ rq_qos_throttle(q, bio);
- trace_block_getrq(q, bio, bio->bi_opf);
-
- rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
+ data.cmd_flags = bio->bi_opf;
+ 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);
rq_qos_track(q, rq, 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);
- /* bypass scheduler for flush rq */
+ ret = blk_crypto_rq_get_keyslot(rq);
+ if (ret != BLK_STS_OK) {
+ bio->bi_status = ret;
+ bio_endio(bio);
+ blk_mq_free_request(rq);
+ return BLK_QC_T_NONE;
+ }
+
+ 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) {
- struct request *last = NULL;
-
- blk_mq_put_ctx(data.ctx);
- blk_mq_bio_to_request(rq, bio);
-
+ } else if (plug && (q->nr_hw_queues == 1 ||
+ blk_mq_is_sbitmap_shared(rq->mq_hctx->flags) ||
+ q->mq_ops->commit_rqs || !blk_queue_nonrot(q))) {
/*
- * @request_count may become stale because of schedule
- * out, so check the list again.
+ * 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.
*/
- if (list_empty(&plug->mq_list))
- request_count = 0;
- else if (blk_queue_nomerges(q))
- request_count = blk_plug_queued_count(q);
+ unsigned int request_count = plug->rq_count;
+ struct request *last = NULL;
if (!request_count)
trace_block_plug(q);
else
last = list_entry_rq(plug->mq_list.prev);
- if (request_count >= BLK_MAX_REQUEST_COUNT || (last &&
+ if (request_count >= blk_plug_max_rq_count(plug) || (last &&
blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
blk_flush_plug_list(plug, false);
trace_block_plug(q);
}
- list_add_tail(&rq->queuelist, &plug->mq_list);
+ 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
@@ -1945,30 +2299,74 @@
*/
if (list_empty(&plug->mq_list))
same_queue_rq = NULL;
- if (same_queue_rq)
+ if (same_queue_rq) {
list_del_init(&same_queue_rq->queuelist);
- list_add_tail(&rq->queuelist, &plug->mq_list);
-
- blk_mq_put_ctx(data.ctx);
+ plug->rq_count--;
+ }
+ blk_add_rq_to_plug(plug, rq);
+ trace_block_plug(q);
if (same_queue_rq) {
- data.hctx = blk_mq_map_queue(q,
- same_queue_rq->mq_ctx->cpu);
+ 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;
+}
+
+static size_t order_to_size(unsigned int order)
+{
+ return (size_t)PAGE_SIZE << order;
+}
+
+/* called before freeing request pool in @tags */
+static void blk_mq_clear_rq_mapping(struct blk_mq_tag_set *set,
+ struct blk_mq_tags *tags, unsigned int hctx_idx)
+{
+ struct blk_mq_tags *drv_tags = set->tags[hctx_idx];
+ struct page *page;
+ unsigned long flags;
+
+ list_for_each_entry(page, &tags->page_list, lru) {
+ unsigned long start = (unsigned long)page_address(page);
+ unsigned long end = start + order_to_size(page->private);
+ int i;
+
+ for (i = 0; i < set->queue_depth; i++) {
+ struct request *rq = drv_tags->rqs[i];
+ unsigned long rq_addr = (unsigned long)rq;
+
+ if (rq_addr >= start && rq_addr < end) {
+ WARN_ON_ONCE(refcount_read(&rq->ref) != 0);
+ cmpxchg(&drv_tags->rqs[i], rq, NULL);
+ }
+ }
+ }
+
+ /*
+ * Wait until all pending iteration is done.
+ *
+ * Request reference is cleared and it is guaranteed to be observed
+ * after the ->lock is released.
+ */
+ spin_lock_irqsave(&drv_tags->lock, flags);
+ spin_unlock_irqrestore(&drv_tags->lock, flags);
}
void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
@@ -1989,42 +2387,44 @@
}
}
+ blk_mq_clear_rq_mapping(set, tags, hctx_idx);
+
while (!list_empty(&tags->page_list)) {
page = list_first_entry(&tags->page_list, struct page, lru);
list_del_init(&page->lru);
/*
* Remove kmemleak object previously allocated in
- * blk_mq_init_rq_map().
+ * blk_mq_alloc_rqs().
*/
kmemleak_free(page_address(page));
__free_pages(page, page->private);
}
}
-void blk_mq_free_rq_map(struct blk_mq_tags *tags)
+void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags)
{
kfree(tags->rqs);
tags->rqs = NULL;
kfree(tags->static_rqs);
tags->static_rqs = NULL;
- blk_mq_free_tags(tags);
+ blk_mq_free_tags(tags, flags);
}
struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
unsigned int hctx_idx,
unsigned int nr_tags,
- unsigned int reserved_tags)
+ unsigned int reserved_tags,
+ unsigned int flags)
{
struct blk_mq_tags *tags;
int node;
- node = blk_mq_hw_queue_to_node(set->mq_map, hctx_idx);
+ node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], hctx_idx);
if (node == NUMA_NO_NODE)
node = set->numa_node;
- tags = blk_mq_init_tags(nr_tags, reserved_tags, node,
- BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
+ tags = blk_mq_init_tags(nr_tags, reserved_tags, node, flags);
if (!tags)
return NULL;
@@ -2032,7 +2432,7 @@
GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
node);
if (!tags->rqs) {
- blk_mq_free_tags(tags);
+ blk_mq_free_tags(tags, flags);
return NULL;
}
@@ -2041,16 +2441,11 @@
node);
if (!tags->static_rqs) {
kfree(tags->rqs);
- blk_mq_free_tags(tags);
+ blk_mq_free_tags(tags, flags);
return NULL;
}
return tags;
-}
-
-static size_t order_to_size(unsigned int order)
-{
- return (size_t)PAGE_SIZE << order;
}
static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
@@ -2075,7 +2470,7 @@
size_t rq_size, left;
int node;
- node = blk_mq_hw_queue_to_node(set->mq_map, hctx_idx);
+ node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], hctx_idx);
if (node == NUMA_NO_NODE)
node = set->numa_node;
@@ -2087,6 +2482,7 @@
*/
rq_size = round_up(sizeof(struct request) + set->cmd_size,
cache_line_size());
+ trace_android_vh_blk_alloc_rqs(&rq_size, set, tags);
left = rq_size * depth;
for (i = 0; i < depth; ) {
@@ -2145,6 +2541,86 @@
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
@@ -2155,13 +2631,18 @@
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
LIST_HEAD(tmp);
+ 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;
spin_lock(&ctx->lock);
- if (!list_empty(&ctx->rq_list)) {
- list_splice_init(&ctx->rq_list, &tmp);
+ if (!list_empty(&ctx->rq_lists[type])) {
+ list_splice_init(&ctx->rq_lists[type], &tmp);
blk_mq_hctx_clear_pending(hctx, ctx);
}
spin_unlock(&ctx->lock);
@@ -2179,8 +2660,40 @@
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);
+}
+
+/*
+ * Before freeing hw queue, clearing the flush request reference in
+ * tags->rqs[] for avoiding potential UAF.
+ */
+static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags,
+ unsigned int queue_depth, struct request *flush_rq)
+{
+ int i;
+ unsigned long flags;
+
+ /* The hw queue may not be mapped yet */
+ if (!tags)
+ return;
+
+ WARN_ON_ONCE(refcount_read(&flush_rq->ref) != 0);
+
+ for (i = 0; i < queue_depth; i++)
+ cmpxchg(&tags->rqs[i], flush_rq, NULL);
+
+ /*
+ * Wait until all pending iteration is done.
+ *
+ * Request reference is cleared and it is guaranteed to be observed
+ * after the ->lock is released.
+ */
+ spin_lock_irqsave(&tags->lock, flags);
+ spin_unlock_irqrestore(&tags->lock, flags);
}
/* hctx->ctxs will be freed in queue's release handler */
@@ -2188,18 +2701,24 @@
struct blk_mq_tag_set *set,
struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
{
- blk_mq_debugfs_unregister_hctx(hctx);
+ struct request *flush_rq = hctx->fq->flush_rq;
if (blk_mq_hw_queue_mapped(hctx))
blk_mq_tag_idle(hctx);
+ blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx],
+ set->queue_depth, flush_rq);
if (set->ops->exit_request)
- set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);
+ set->ops->exit_request(set, flush_rq, hctx_idx);
if (set->ops->exit_hctx)
set->ops->exit_hctx(hctx, hctx_idx);
blk_mq_remove_cpuhp(hctx);
+
+ spin_lock(&q->unused_hctx_lock);
+ list_add(&hctx->hctx_list, &q->unused_hctx_list);
+ spin_unlock(&q->unused_hctx_lock);
}
static void blk_mq_exit_hw_queues(struct request_queue *q,
@@ -2211,112 +2730,160 @@
queue_for_each_hw_ctx(q, hctx, i) {
if (i == nr_queue)
break;
+ blk_mq_debugfs_unregister_hctx(hctx);
blk_mq_exit_hctx(q, set, hctx, i);
}
+}
+
+static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
+{
+ int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
+
+ BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
+ __alignof__(struct blk_mq_hw_ctx)) !=
+ sizeof(struct blk_mq_hw_ctx));
+
+ if (tag_set->flags & BLK_MQ_F_BLOCKING)
+ hw_ctx_size += sizeof(struct srcu_struct);
+
+ return hw_ctx_size;
}
static int blk_mq_init_hctx(struct request_queue *q,
struct blk_mq_tag_set *set,
struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
{
- int node;
+ hctx->queue_num = hctx_idx;
- node = hctx->numa_node;
+ 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];
+
+ if (set->ops->init_hctx &&
+ set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
+ goto unregister_cpu_notifier;
+
+ if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx,
+ hctx->numa_node))
+ goto exit_hctx;
+ return 0;
+
+ exit_hctx:
+ if (set->ops->exit_hctx)
+ set->ops->exit_hctx(hctx, hctx_idx);
+ unregister_cpu_notifier:
+ blk_mq_remove_cpuhp(hctx);
+ return -1;
+}
+
+static struct blk_mq_hw_ctx *
+blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
+ int node)
+{
+ struct blk_mq_hw_ctx *hctx;
+ gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY;
+
+ hctx = kzalloc_node(blk_mq_hw_ctx_size(set), gfp, node);
+ if (!hctx)
+ goto fail_alloc_hctx;
+
+ if (!zalloc_cpumask_var_node(&hctx->cpumask, gfp, node))
+ goto free_hctx;
+
+ atomic_set(&hctx->nr_active, 0);
if (node == NUMA_NO_NODE)
- node = hctx->numa_node = set->numa_node;
+ node = set->numa_node;
+ hctx->numa_node = node;
INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
spin_lock_init(&hctx->lock);
INIT_LIST_HEAD(&hctx->dispatch);
hctx->queue = q;
- hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
+ hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED;
- cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
-
- hctx->tags = set->tags[hctx_idx];
+ INIT_LIST_HEAD(&hctx->hctx_list);
/*
* Allocate space for all possible cpus to avoid allocation at
* runtime
*/
hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *),
- GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node);
+ gfp, node);
if (!hctx->ctxs)
- goto unregister_cpu_notifier;
+ goto free_cpumask;
if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8),
- GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node))
+ gfp, node))
goto free_ctxs;
-
hctx->nr_ctx = 0;
spin_lock_init(&hctx->dispatch_wait_lock);
init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
- if (set->ops->init_hctx &&
- set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
- goto free_bitmap;
-
- hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size,
- GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY);
+ hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp);
if (!hctx->fq)
- goto exit_hctx;
-
- if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, node))
- goto free_fq;
+ goto free_bitmap;
if (hctx->flags & BLK_MQ_F_BLOCKING)
init_srcu_struct(hctx->srcu);
+ blk_mq_hctx_kobj_init(hctx);
- blk_mq_debugfs_register_hctx(q, hctx);
+ return hctx;
- return 0;
-
- free_fq:
- blk_free_flush_queue(hctx->fq);
- exit_hctx:
- if (set->ops->exit_hctx)
- set->ops->exit_hctx(hctx, hctx_idx);
free_bitmap:
sbitmap_free(&hctx->ctx_map);
free_ctxs:
kfree(hctx->ctxs);
- unregister_cpu_notifier:
- blk_mq_remove_cpuhp(hctx);
- return -1;
+ free_cpumask:
+ free_cpumask_var(hctx->cpumask);
+ free_hctx:
+ kfree(hctx);
+ fail_alloc_hctx:
+ return NULL;
}
static void blk_mq_init_cpu_queues(struct request_queue *q,
unsigned int nr_hw_queues)
{
- unsigned int i;
+ struct blk_mq_tag_set *set = q->tag_set;
+ unsigned int i, j;
for_each_possible_cpu(i) {
struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i);
struct blk_mq_hw_ctx *hctx;
+ int k;
__ctx->cpu = i;
spin_lock_init(&__ctx->lock);
- INIT_LIST_HEAD(&__ctx->rq_list);
+ for (k = HCTX_TYPE_DEFAULT; k < HCTX_MAX_TYPES; k++)
+ INIT_LIST_HEAD(&__ctx->rq_lists[k]);
+
__ctx->queue = q;
/*
* Set local node, IFF we have more than one hw queue. If
* not, we remain on the home node of the device
*/
- hctx = blk_mq_map_queue(q, i);
- if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE)
- hctx->numa_node = local_memory_node(cpu_to_node(i));
+ for (j = 0; j < set->nr_maps; j++) {
+ hctx = blk_mq_map_queue_type(q, j, i);
+ if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE)
+ hctx->numa_node = cpu_to_node(i);
+ }
}
}
-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)
{
+ unsigned int flags = set->flags;
int ret = 0;
set->tags[hctx_idx] = blk_mq_alloc_rq_map(set, hctx_idx,
- set->queue_depth, set->reserved_tags);
+ set->queue_depth, set->reserved_tags, flags);
if (!set->tags[hctx_idx])
return false;
@@ -2325,7 +2892,7 @@
if (!ret)
return true;
- blk_mq_free_rq_map(set->tags[hctx_idx]);
+ blk_mq_free_rq_map(set->tags[hctx_idx], flags);
set->tags[hctx_idx] = NULL;
return false;
}
@@ -2333,16 +2900,18 @@
static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
unsigned int hctx_idx)
{
- if (set->tags[hctx_idx]) {
+ unsigned int flags = set->flags;
+
+ if (set->tags && set->tags[hctx_idx]) {
blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx);
- blk_mq_free_rq_map(set->tags[hctx_idx]);
+ blk_mq_free_rq_map(set->tags[hctx_idx], flags);
set->tags[hctx_idx] = NULL;
}
}
static void blk_mq_map_swqueue(struct request_queue *q)
{
- unsigned int i, hctx_idx;
+ unsigned int i, j, hctx_idx;
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
struct blk_mq_tag_set *set = q->tag_set;
@@ -2359,25 +2928,52 @@
* If the cpu isn't present, the cpu is mapped to first hctx.
*/
for_each_possible_cpu(i) {
- hctx_idx = q->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
- */
- q->mq_map[i] = 0;
- }
ctx = per_cpu_ptr(q->queue_ctx, i);
- hctx = blk_mq_map_queue(q, i);
+ for (j = 0; j < set->nr_maps; j++) {
+ if (!set->map[j].nr_queues) {
+ ctx->hctxs[j] = blk_mq_map_queue_type(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;
+ }
- cpumask_set_cpu(i, hctx->cpumask);
- ctx->index_hw = hctx->nr_ctx;
- hctx->ctxs[hctx->nr_ctx++] = ctx;
+ hctx = blk_mq_map_queue_type(q, j, i);
+ ctx->hctxs[j] = hctx;
+ /*
+ * If the CPU is already set in the mask, then we've
+ * mapped this one already. This can happen if
+ * devices share queues across queue maps.
+ */
+ if (cpumask_test_cpu(i, hctx->cpumask))
+ continue;
+
+ cpumask_set_cpu(i, hctx->cpumask);
+ hctx->type = j;
+ ctx->index_hw[hctx->type] = hctx->nr_ctx;
+ hctx->ctxs[hctx->nr_ctx++] = ctx;
+
+ /*
+ * If the nr_ctx type overflows, we have exceeded the
+ * amount of sw queues we can support.
+ */
+ BUG_ON(!hctx->nr_ctx);
+ }
+
+ for (; j < HCTX_MAX_TYPES; j++)
+ ctx->hctxs[j] = blk_mq_map_queue_type(q,
+ HCTX_TYPE_DEFAULT, i);
}
queue_for_each_hw_ctx(q, hctx, i) {
@@ -2426,14 +3022,14 @@
queue_for_each_hw_ctx(q, hctx, i) {
if (shared)
- hctx->flags |= BLK_MQ_F_TAG_SHARED;
+ hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED;
else
- hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
+ hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
}
}
-static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set,
- bool shared)
+static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set,
+ bool shared)
{
struct request_queue *q;
@@ -2451,12 +3047,12 @@
struct blk_mq_tag_set *set = q->tag_set;
mutex_lock(&set->tag_list_lock);
- list_del_rcu(&q->tag_set_list);
+ list_del(&q->tag_set_list);
if (list_is_singular(&set->tag_list)) {
/* just transitioned to unshared */
- set->flags &= ~BLK_MQ_F_TAG_SHARED;
+ set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
/* update existing queue */
- blk_mq_update_tag_set_depth(set, false);
+ blk_mq_update_tag_set_shared(set, false);
}
mutex_unlock(&set->tag_list_lock);
INIT_LIST_HEAD(&q->tag_set_list);
@@ -2465,24 +3061,50 @@
static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
struct request_queue *q)
{
- q->tag_set = set;
-
mutex_lock(&set->tag_list_lock);
/*
* Check to see if we're transitioning to shared (from 1 to 2 queues).
*/
if (!list_empty(&set->tag_list) &&
- !(set->flags & BLK_MQ_F_TAG_SHARED)) {
- set->flags |= BLK_MQ_F_TAG_SHARED;
+ !(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+ set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED;
/* update existing queue */
- blk_mq_update_tag_set_depth(set, true);
+ blk_mq_update_tag_set_shared(set, true);
}
- if (set->flags & BLK_MQ_F_TAG_SHARED)
+ if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
queue_set_hctx_shared(q, true);
- list_add_tail_rcu(&q->tag_set_list, &set->tag_list);
+ list_add_tail(&q->tag_set_list, &set->tag_list);
mutex_unlock(&set->tag_list_lock);
+}
+
+/* All allocations will be freed in release handler of q->mq_kobj */
+static int blk_mq_alloc_ctxs(struct request_queue *q)
+{
+ struct blk_mq_ctxs *ctxs;
+ int cpu;
+
+ ctxs = kzalloc(sizeof(*ctxs), GFP_KERNEL);
+ if (!ctxs)
+ return -ENOMEM;
+
+ ctxs->queue_ctx = alloc_percpu(struct blk_mq_ctx);
+ if (!ctxs->queue_ctx)
+ goto fail;
+
+ for_each_possible_cpu(cpu) {
+ struct blk_mq_ctx *ctx = per_cpu_ptr(ctxs->queue_ctx, cpu);
+ ctx->ctxs = ctxs;
+ }
+
+ q->mq_kobj = &ctxs->kobj;
+ q->queue_ctx = ctxs->queue_ctx;
+
+ return 0;
+ fail:
+ kfree(ctxs);
+ return -ENOMEM;
}
/*
@@ -2493,17 +3115,17 @@
*/
void blk_mq_release(struct request_queue *q)
{
- struct blk_mq_hw_ctx *hctx;
- unsigned int i;
+ struct blk_mq_hw_ctx *hctx, *next;
+ int i;
- /* hctx kobj stays in hctx */
- queue_for_each_hw_ctx(q, hctx, i) {
- if (!hctx)
- continue;
+ queue_for_each_hw_ctx(q, hctx, i)
+ WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list));
+
+ /* all hctx are in .unused_hctx_list now */
+ list_for_each_entry_safe(hctx, next, &q->unused_hctx_list, hctx_list) {
+ list_del_init(&hctx->hctx_list);
kobject_put(&hctx->kobj);
}
-
- q->mq_map = NULL;
kfree(q->queue_hw_ctx);
@@ -2512,102 +3134,184 @@
* both share lifetime with request queue.
*/
blk_mq_sysfs_deinit(q);
-
- free_percpu(q->queue_ctx);
}
-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, NULL);
+ 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);
-static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
+/*
+ * Helper for setting up a queue with mq ops, given queue depth, and
+ * the passed in mq ops flags.
+ */
+struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set,
+ const struct blk_mq_ops *ops,
+ unsigned int queue_depth,
+ unsigned int set_flags)
{
- int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
+ struct request_queue *q;
+ int ret;
- BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
- __alignof__(struct blk_mq_hw_ctx)) !=
- sizeof(struct blk_mq_hw_ctx));
+ memset(set, 0, sizeof(*set));
+ set->ops = ops;
+ set->nr_hw_queues = 1;
+ set->nr_maps = 1;
+ set->queue_depth = queue_depth;
+ set->numa_node = NUMA_NO_NODE;
+ set->flags = set_flags;
- if (tag_set->flags & BLK_MQ_F_BLOCKING)
- hw_ctx_size += sizeof(struct srcu_struct);
+ ret = blk_mq_alloc_tag_set(set);
+ if (ret)
+ return ERR_PTR(ret);
- return hw_ctx_size;
+ q = blk_mq_init_queue(set);
+ if (IS_ERR(q)) {
+ blk_mq_free_tag_set(set);
+ return q;
+ }
+
+ return q;
+}
+EXPORT_SYMBOL(blk_mq_init_sq_queue);
+
+static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx(
+ struct blk_mq_tag_set *set, struct request_queue *q,
+ int hctx_idx, int node)
+{
+ struct blk_mq_hw_ctx *hctx = NULL, *tmp;
+
+ /* reuse dead hctx first */
+ spin_lock(&q->unused_hctx_lock);
+ list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) {
+ if (tmp->numa_node == node) {
+ hctx = tmp;
+ break;
+ }
+ }
+ if (hctx)
+ list_del_init(&hctx->hctx_list);
+ spin_unlock(&q->unused_hctx_lock);
+
+ if (!hctx)
+ hctx = blk_mq_alloc_hctx(q, set, node);
+ if (!hctx)
+ goto fail;
+
+ if (blk_mq_init_hctx(q, set, hctx, hctx_idx))
+ goto free_hctx;
+
+ return hctx;
+
+ free_hctx:
+ kobject_put(&hctx->kobj);
+ fail:
+ return NULL;
}
static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
struct request_queue *q)
{
- int i, j;
+ int i, j, end;
struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
- blk_mq_sysfs_unregister(q);
+ 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++) {
int node;
+ struct blk_mq_hw_ctx *hctx;
- if (hctxs[i])
+ node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], i);
+ /*
+ * If the hw queue has been mapped to another numa node,
+ * we need to realloc the hctx. If allocation fails, fallback
+ * to use the previous one.
+ */
+ if (hctxs[i] && (hctxs[i]->numa_node == node))
continue;
- node = blk_mq_hw_queue_to_node(q->mq_map, i);
- hctxs[i] = kzalloc_node(blk_mq_hw_ctx_size(set),
- GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
- node);
- if (!hctxs[i])
- break;
-
- if (!zalloc_cpumask_var_node(&hctxs[i]->cpumask,
- GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
- node)) {
- kfree(hctxs[i]);
- hctxs[i] = NULL;
- break;
+ hctx = blk_mq_alloc_and_init_hctx(set, q, i, node);
+ if (hctx) {
+ if (hctxs[i])
+ blk_mq_exit_hctx(q, set, hctxs[i], i);
+ hctxs[i] = hctx;
+ } else {
+ if (hctxs[i])
+ pr_warn("Allocate new hctx on node %d fails,\
+ fallback to previous one on node %d\n",
+ node, hctxs[i]->numa_node);
+ else
+ break;
}
-
- atomic_set(&hctxs[i]->nr_active, 0);
- hctxs[i]->numa_node = node;
- hctxs[i]->queue_num = i;
-
- if (blk_mq_init_hctx(q, set, hctxs[i], i)) {
- free_cpumask_var(hctxs[i]->cpumask);
- kfree(hctxs[i]);
- hctxs[i] = NULL;
- break;
- }
- blk_mq_hctx_kobj_init(hctxs[i]);
}
- for (j = i; j < q->nr_hw_queues; j++) {
+ /*
+ * Increasing nr_hw_queues fails. Free the newly allocated
+ * hctxs and keep the previous q->nr_hw_queues.
+ */
+ if (i != set->nr_hw_queues) {
+ j = q->nr_hw_queues;
+ end = i;
+ } else {
+ j = i;
+ end = q->nr_hw_queues;
+ q->nr_hw_queues = set->nr_hw_queues;
+ }
+
+ for (; j < end; j++) {
struct blk_mq_hw_ctx *hctx = hctxs[j];
if (hctx) {
if (hctx->tags)
blk_mq_free_map_and_requests(set, j);
blk_mq_exit_hctx(q, set, hctx, j);
- kobject_put(&hctx->kobj);
hctxs[j] = NULL;
-
}
}
- q->nr_hw_queues = i;
mutex_unlock(&q->sysfs_lock);
- blk_mq_sysfs_register(q);
}
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;
@@ -2618,19 +3322,14 @@
if (!q->poll_cb)
goto err_exit;
- q->queue_ctx = alloc_percpu(struct blk_mq_ctx);
- if (!q->queue_ctx)
- goto err_exit;
+ if (blk_mq_alloc_ctxs(q))
+ goto err_poll;
/* init q->mq_kobj and sw queues' kobjects */
blk_mq_sysfs_init(q);
- q->queue_hw_ctx = kcalloc_node(nr_cpu_ids, sizeof(*(q->queue_hw_ctx)),
- GFP_KERNEL, set->numa_node);
- if (!q->queue_hw_ctx)
- goto err_percpu;
-
- q->mq_map = set->mq_map;
+ INIT_LIST_HEAD(&q->unused_hctx_list);
+ spin_lock_init(&q->unused_hctx_lock);
blk_mq_realloc_hw_ctxs(set, q);
if (!q->nr_hw_queues)
@@ -2639,12 +3338,12 @@
INIT_WORK(&q->timeout_work, blk_mq_timeout_work);
blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
- q->nr_queues = nr_cpu_ids;
+ q->tag_set = set;
q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
-
- if (!(set->flags & BLK_MQ_F_SG_MERGE))
- queue_flag_set_unlocked(QUEUE_FLAG_NO_SG_MERGE, q);
+ if (set->nr_maps > HCTX_TYPE_POLL &&
+ set->map[HCTX_TYPE_POLL].nr_queues)
+ blk_queue_flag_set(QUEUE_FLAG_POLL, q);
q->sg_reserved_size = INT_MAX;
@@ -2652,41 +3351,29 @@
INIT_LIST_HEAD(&q->requeue_list);
spin_lock_init(&q->requeue_lock);
- blk_queue_make_request(q, blk_mq_make_request);
- if (q->mq_ops->poll)
- q->poll_fn = blk_mq_poll;
-
- /*
- * Do this after blk_queue_make_request() overrides it...
- */
q->nr_requests = set->queue_depth;
/*
* Default to classic polling
*/
- q->poll_nsec = -1;
-
- if (set->ops->complete)
- blk_queue_softirq_done(q, set->ops->complete);
+ q->poll_nsec = BLK_MQ_POLL_CLASSIC;
blk_mq_init_cpu_queues(q, set->nr_hw_queues);
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_percpu:
- free_percpu(q->queue_ctx);
+ q->nr_hw_queues = 0;
+ blk_mq_sysfs_deinit(q);
+err_poll:
+ blk_stat_free_callback(q->poll_cb);
+ q->poll_cb = NULL;
err_exit:
q->mq_ops = NULL;
return ERR_PTR(-ENOMEM);
@@ -2704,38 +3391,21 @@
blk_mq_del_queue_tag_set(q);
}
-/* Basically redo blk_mq_init_queue with queue frozen */
-static void blk_mq_queue_reinit(struct request_queue *q)
-{
- WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
-
- blk_mq_debugfs_unregister_hctxs(q);
- blk_mq_sysfs_unregister(q);
-
- /*
- * redo blk_mq_init_cpu_queues and blk_mq_init_hw_queues. FIXME: maybe
- * we should change hctx numa_node according to the new topology (this
- * involves freeing and re-allocating memory, worth doing?)
- */
- blk_mq_map_swqueue(q);
-
- blk_mq_sysfs_register(q);
- blk_mq_debugfs_register_hctxs(q);
-}
-
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))
+ for (i = 0; i < set->nr_hw_queues; i++) {
+ if (!__blk_mq_alloc_map_and_request(set, i))
goto out_unwind;
+ cond_resched();
+ }
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;
}
@@ -2745,7 +3415,7 @@
* 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;
@@ -2777,7 +3447,17 @@
static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
{
- if (set->ops->map_queues) {
+ /*
+ * 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;
+
/*
* transport .map_queues is usually done in the following
* way:
@@ -2785,18 +3465,44 @@
* for (queue = 0; queue < set->nr_hw_queues; queue++) {
* mask = get_cpu_mask(queue)
* for_each_cpu(cpu, mask)
- * set->mq_map[cpu] = queue;
+ * set->map[x].mq_map[cpu] = queue;
* }
*
* When we need to remap, the table has to be cleared for
* killing stale mapping since one CPU may not be mapped
* to any hw queue.
*/
- blk_mq_clear_mq_map(set);
+ for (i = 0; i < set->nr_maps; i++)
+ blk_mq_clear_mq_map(&set->map[i]);
return set->ops->map_queues(set);
- } else
- return blk_mq_map_queues(set);
+ } else {
+ BUG_ON(set->nr_maps > 1);
+ return blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
+ }
+}
+
+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;
}
/*
@@ -2807,7 +3513,7 @@
*/
int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
{
- int ret;
+ int i, ret;
BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS);
@@ -2830,6 +3536,11 @@
set->queue_depth = BLK_MQ_MAX_DEPTH;
}
+ if (!set->nr_maps)
+ set->nr_maps = 1;
+ else if (set->nr_maps > HCTX_MAX_TYPES)
+ return -EINVAL;
+
/*
* If a crashdump is active, then we are potentially in a very
* memory constrained environment. Limit us to 1 queue and
@@ -2837,42 +3548,59 @@
*/
if (is_kdump_kernel()) {
set->nr_hw_queues = 1;
+ set->nr_maps = 1;
set->queue_depth = min(64U, set->queue_depth);
}
/*
- * There is no use for more h/w queues than cpus.
+ * There is no use for more h/w queues than cpus if we just have
+ * a single map
*/
- if (set->nr_hw_queues > nr_cpu_ids)
+ if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids)
set->nr_hw_queues = nr_cpu_ids;
- set->tags = kcalloc_node(nr_cpu_ids, 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;
- set->mq_map = kcalloc_node(nr_cpu_ids, sizeof(*set->mq_map),
- GFP_KERNEL, set->numa_node);
- if (!set->mq_map)
- goto out_free_tags;
+ for (i = 0; i < set->nr_maps; i++) {
+ set->map[i].mq_map = kcalloc_node(nr_cpu_ids,
+ sizeof(set->map[i].mq_map[0]),
+ GFP_KERNEL, set->numa_node);
+ if (!set->map[i].mq_map)
+ goto out_free_mq_map;
+ set->map[i].nr_queues = is_kdump_kernel() ? 1 : set->nr_hw_queues;
+ }
ret = blk_mq_update_queue_map(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;
+
+ if (blk_mq_is_sbitmap_shared(set->flags)) {
+ atomic_set(&set->active_queues_shared_sbitmap, 0);
+
+ if (blk_mq_init_shared_sbitmap(set, set->flags)) {
+ ret = -ENOMEM;
+ goto out_free_mq_rq_maps;
+ }
+ }
mutex_init(&set->tag_list_lock);
INIT_LIST_HEAD(&set->tag_list);
return 0;
+out_free_mq_rq_maps:
+ for (i = 0; i < set->nr_hw_queues; i++)
+ blk_mq_free_map_and_requests(set, i);
out_free_mq_map:
- kfree(set->mq_map);
- set->mq_map = NULL;
-out_free_tags:
+ for (i = 0; i < set->nr_maps; i++) {
+ kfree(set->map[i].mq_map);
+ set->map[i].mq_map = NULL;
+ }
kfree(set->tags);
set->tags = NULL;
return ret;
@@ -2881,13 +3609,18 @@
void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
{
- int i;
+ int i, j;
- for (i = 0; i < nr_cpu_ids; i++)
+ for (i = 0; i < set->nr_hw_queues; i++)
blk_mq_free_map_and_requests(set, i);
- kfree(set->mq_map);
- set->mq_map = NULL;
+ if (blk_mq_is_sbitmap_shared(set->flags))
+ blk_mq_exit_shared_sbitmap(set);
+
+ for (j = 0; j < set->nr_maps; j++) {
+ kfree(set->map[j].mq_map);
+ set->map[j].mq_map = NULL;
+ }
kfree(set->tags);
set->tags = NULL;
@@ -2903,6 +3636,9 @@
if (!set)
return -EINVAL;
+ if (q->nr_requests == nr)
+ return 0;
+
blk_mq_freeze_queue(q);
blk_mq_quiesce_queue(q);
@@ -2917,14 +3653,16 @@
if (!hctx->sched_tags) {
ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr,
false);
+ if (!ret && blk_mq_is_sbitmap_shared(set->flags))
+ blk_mq_tag_resize_shared_sbitmap(set, nr);
} else {
ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags,
nr, true);
}
if (ret)
break;
- if (q->elevator && q->elevator->type->ops.mq.depth_updated)
- q->elevator->type->ops.mq.depth_updated(hctx);
+ if (q->elevator && q->elevator->type->ops.depth_updated)
+ q->elevator->type->ops.depth_updated(hctx);
}
if (!ret)
@@ -3011,20 +3749,19 @@
{
struct request_queue *q;
LIST_HEAD(head);
+ int prev_nr_hw_queues;
lockdep_assert_held(&set->tag_list_lock);
- if (nr_hw_queues > nr_cpu_ids)
+ 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
@@ -3034,11 +3771,35 @@
if (!blk_mq_elv_switch_none(&head, q))
goto switch_back;
+ list_for_each_entry(q, &set->tag_list, tag_set_list) {
+ blk_mq_debugfs_unregister_hctxs(q);
+ blk_mq_sysfs_unregister(q);
+ }
+
+ 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;
+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);
- blk_mq_queue_reinit(q);
+ if (q->nr_hw_queues != set->nr_hw_queues) {
+ pr_warn("Increasing nr_hw_queues to %d fails, fallback to %d\n",
+ nr_hw_queues, prev_nr_hw_queues);
+ set->nr_hw_queues = prev_nr_hw_queues;
+ blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
+ goto 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);
}
switch_back:
@@ -3092,7 +3853,6 @@
}
static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
- struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
unsigned long ret = 0;
@@ -3125,7 +3885,6 @@
}
static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
- struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
struct hrtimer_sleeper hs;
@@ -3137,18 +3896,15 @@
return false;
/*
- * poll_nsec can be:
+ * If we get here, hybrid polling is enabled. Hence poll_nsec can be:
*
- * -1: don't ever hybrid sleep
* 0: use half of prev avg
* >0: use this specific value
*/
- if (q->poll_nsec == -1)
- return false;
- else if (q->poll_nsec > 0)
+ 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;
@@ -3162,14 +3918,14 @@
kt = nsecs;
mode = HRTIMER_MODE_REL;
- hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode, current);
+ hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode);
hrtimer_set_expires(&hs.timer, kt);
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);
@@ -3181,59 +3937,14 @@
return true;
}
-static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq)
+static bool blk_mq_poll_hybrid(struct request_queue *q,
+ struct blk_mq_hw_ctx *hctx, blk_qc_t cookie)
{
- struct request_queue *q = hctx->queue;
- long state;
-
- /*
- * If we sleep, have the caller restart the poll loop to reset
- * the state. Like for the other success return cases, the
- * caller is responsible for checking if the IO completed. If
- * the IO isn't complete, we'll get called again and will go
- * straight to the busy poll loop.
- */
- if (blk_mq_poll_hybrid_sleep(q, hctx, rq))
- return true;
-
- hctx->poll_considered++;
-
- state = current->state;
- while (!need_resched()) {
- int ret;
-
- hctx->poll_invoked++;
-
- ret = q->mq_ops->poll(hctx, rq->tag);
- 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();
- }
-
- __set_current_state(TASK_RUNNING);
- return false;
-}
-
-static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
-{
- struct blk_mq_hw_ctx *hctx;
struct request *rq;
- if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+ if (q->poll_nsec == BLK_MQ_POLL_CLASSIC)
return false;
- hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
if (!blk_qc_t_is_internal(cookie))
rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
else {
@@ -3248,13 +3959,97 @@
return false;
}
- return __blk_mq_poll(hctx, rq);
+ return blk_mq_poll_hybrid_sleep(q, rq);
}
+
+/**
+ * blk_poll - poll for IO completions
+ * @q: the queue
+ * @cookie: cookie passed back at IO submission time
+ * @spin: whether to spin for completions
+ *
+ * Description:
+ * Poll for completions on the passed in queue. Returns number of
+ * completed entries found. If @spin is true, then blk_poll will continue
+ * looping until at least one completion is found, unless the task is
+ * otherwise marked running (or we need to reschedule).
+ */
+int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
+{
+ struct blk_mq_hw_ctx *hctx;
+ long state;
+
+ if (!blk_qc_t_valid(cookie) ||
+ !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+ return 0;
+
+ if (current->plug)
+ blk_flush_plug_list(current->plug, false);
+
+ hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
+
+ /*
+ * If we sleep, have the caller restart the poll loop to reset
+ * the state. Like for the other success return cases, the
+ * caller is responsible for checking if the IO completed. If
+ * the IO isn't complete, we'll get called again and will go
+ * straight to the busy poll loop.
+ */
+ if (blk_mq_poll_hybrid(q, hctx, cookie))
+ return 1;
+
+ hctx->poll_considered++;
+
+ state = current->state;
+ do {
+ int ret;
+
+ hctx->poll_invoked++;
+
+ ret = q->mq_ops->poll(hctx);
+ if (ret > 0) {
+ hctx->poll_success++;
+ __set_current_state(TASK_RUNNING);
+ return ret;
+ }
+
+ if (signal_pending_state(state, current))
+ __set_current_state(TASK_RUNNING);
+
+ if (current->state == TASK_RUNNING)
+ return 1;
+ if (ret < 0 || !spin)
+ break;
+ cpu_relax();
+ } while (!need_resched());
+
+ __set_current_state(TASK_RUNNING);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(blk_poll);
+
+unsigned int blk_mq_rq_cpu(struct request *rq)
+{
+ return rq->mq_ctx->cpu;
+}
+EXPORT_SYMBOL(blk_mq_rq_cpu);
static int __init blk_mq_init(void)
{
+ int i;
+
+ for_each_possible_cpu(i)
+ INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
+ open_softirq(BLOCK_SOFTIRQ, blk_done_softirq);
+
+ cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD,
+ "block/softirq:dead", NULL,
+ blk_softirq_cpu_dead);
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);
--
Gitblit v1.6.2