summaryrefslogtreecommitdiffstats
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/badblocks.c1
-rw-r--r--block/bfq-cgroup.c116
-rw-r--r--block/bfq-iosched.c61
-rw-r--r--block/bfq-iosched.h23
-rw-r--r--block/bio-integrity.c11
-rw-r--r--block/bio.c97
-rw-r--r--block/blk-cgroup.c2
-rw-r--r--block/blk-core.c341
-rw-r--r--block/blk-exec.c4
-rw-r--r--block/blk-flush.c16
-rw-r--r--block/blk-integrity.c4
-rw-r--r--block/blk-map.c7
-rw-r--r--block/blk-merge.c48
-rw-r--r--block/blk-mq-cpumap.c68
-rw-r--r--block/blk-mq-debugfs.c101
-rw-r--r--block/blk-mq-sched.c192
-rw-r--r--block/blk-mq-sched.h37
-rw-r--r--block/blk-mq.c591
-rw-r--r--block/blk-mq.h16
-rw-r--r--block/blk-settings.c5
-rw-r--r--block/blk-sysfs.c42
-rw-r--r--block/blk-tag.c15
-rw-r--r--block/blk-throttle.c184
-rw-r--r--block/blk-timeout.c4
-rw-r--r--block/blk-wbt.c4
-rw-r--r--block/blk.h17
-rw-r--r--block/bounce.c47
-rw-r--r--block/bsg-lib.c5
-rw-r--r--block/bsg.c13
-rw-r--r--block/cfq-iosched.c26
-rw-r--r--block/elevator.c1
-rw-r--r--block/genhd.c4
-rw-r--r--block/ioprio.c3
-rw-r--r--block/kyber-iosched.c47
-rw-r--r--block/partition-generic.c4
-rw-r--r--block/partitions/ldm.c10
-rw-r--r--block/partitions/ldm.h6
-rw-r--r--block/partitions/msdos.c2
-rw-r--r--block/scsi_ioctl.c13
-rw-r--r--block/t10-pi.c32
40 files changed, 1250 insertions, 970 deletions
diff --git a/block/badblocks.c b/block/badblocks.c
index 6ebcef282314..43c71166e1e2 100644
--- a/block/badblocks.c
+++ b/block/badblocks.c
@@ -533,6 +533,7 @@ ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len,
case 3:
if (newline != '\n')
return -EINVAL;
+ /* fall through */
case 2:
if (length <= 0)
return -EINVAL;
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index c8a32fb345cf..78b2e0db4fb2 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -52,7 +52,7 @@ BFQG_FLAG_FNS(idling)
BFQG_FLAG_FNS(empty)
#undef BFQG_FLAG_FNS
-/* This should be called with the queue_lock held. */
+/* This should be called with the scheduler lock held. */
static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
{
unsigned long long now;
@@ -67,7 +67,7 @@ static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
bfqg_stats_clear_waiting(stats);
}
-/* This should be called with the queue_lock held. */
+/* This should be called with the scheduler lock held. */
static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
struct bfq_group *curr_bfqg)
{
@@ -81,7 +81,7 @@ static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
bfqg_stats_mark_waiting(stats);
}
-/* This should be called with the queue_lock held. */
+/* This should be called with the scheduler lock held. */
static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
{
unsigned long long now;
@@ -203,12 +203,30 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
static void bfqg_get(struct bfq_group *bfqg)
{
- return blkg_get(bfqg_to_blkg(bfqg));
+ bfqg->ref++;
}
void bfqg_put(struct bfq_group *bfqg)
{
- return blkg_put(bfqg_to_blkg(bfqg));
+ bfqg->ref--;
+
+ if (bfqg->ref == 0)
+ kfree(bfqg);
+}
+
+static void bfqg_and_blkg_get(struct bfq_group *bfqg)
+{
+ /* see comments in bfq_bic_update_cgroup for why refcounting bfqg */
+ bfqg_get(bfqg);
+
+ blkg_get(bfqg_to_blkg(bfqg));
+}
+
+void bfqg_and_blkg_put(struct bfq_group *bfqg)
+{
+ bfqg_put(bfqg);
+
+ blkg_put(bfqg_to_blkg(bfqg));
}
void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
@@ -312,7 +330,11 @@ void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
if (bfqq) {
bfqq->ioprio = bfqq->new_ioprio;
bfqq->ioprio_class = bfqq->new_ioprio_class;
- bfqg_get(bfqg);
+ /*
+ * Make sure that bfqg and its associated blkg do not
+ * disappear before entity.
+ */
+ bfqg_and_blkg_get(bfqg);
}
entity->parent = bfqg->my_entity; /* NULL for root group */
entity->sched_data = &bfqg->sched_data;
@@ -399,6 +421,8 @@ struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
return NULL;
}
+ /* see comments in bfq_bic_update_cgroup for why refcounting */
+ bfqg_get(bfqg);
return &bfqg->pd;
}
@@ -426,7 +450,7 @@ void bfq_pd_free(struct blkg_policy_data *pd)
struct bfq_group *bfqg = pd_to_bfqg(pd);
bfqg_stats_exit(&bfqg->stats);
- return kfree(bfqg);
+ bfqg_put(bfqg);
}
void bfq_pd_reset_stats(struct blkg_policy_data *pd)
@@ -496,9 +520,10 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
* Move @bfqq to @bfqg, deactivating it from its old group and reactivating
* it on the new one. Avoid putting the entity on the old group idle tree.
*
- * Must be called under the queue lock; the cgroup owning @bfqg must
- * not disappear (by now this just means that we are called under
- * rcu_read_lock()).
+ * Must be called under the scheduler lock, to make sure that the blkg
+ * owning @bfqg does not disappear (see comments in
+ * bfq_bic_update_cgroup on guaranteeing the consistency of blkg
+ * objects).
*/
void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
struct bfq_group *bfqg)
@@ -519,16 +544,12 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bfq_deactivate_bfqq(bfqd, bfqq, false, false);
else if (entity->on_st)
bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
- bfqg_put(bfqq_group(bfqq));
+ bfqg_and_blkg_put(bfqq_group(bfqq));
- /*
- * Here we use a reference to bfqg. We don't need a refcounter
- * as the cgroup reference will not be dropped, so that its
- * destroy() callback will not be invoked.
- */
entity->parent = bfqg->my_entity;
entity->sched_data = &bfqg->sched_data;
- bfqg_get(bfqg);
+ /* pin down bfqg and its associated blkg */
+ bfqg_and_blkg_get(bfqg);
if (bfq_bfqq_busy(bfqq)) {
bfq_pos_tree_add_move(bfqd, bfqq);
@@ -545,8 +566,9 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
* @bic: the bic to move.
* @blkcg: the blk-cgroup to move to.
*
- * Move bic to blkcg, assuming that bfqd->queue is locked; the caller
- * has to make sure that the reference to cgroup is valid across the call.
+ * Move bic to blkcg, assuming that bfqd->lock is held; which makes
+ * sure that the reference to cgroup is valid across the call (see
+ * comments in bfq_bic_update_cgroup on this issue)
*
* NOTE: an alternative approach might have been to store the current
* cgroup in bfqq and getting a reference to it, reducing the lookup
@@ -604,6 +626,57 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
goto out;
bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
+ /*
+ * Update blkg_path for bfq_log_* functions. We cache this
+ * path, and update it here, for the following
+ * reasons. Operations on blkg objects in blk-cgroup are
+ * protected with the request_queue lock, and not with the
+ * lock that protects the instances of this scheduler
+ * (bfqd->lock). This exposes BFQ to the following sort of
+ * race.
+ *
+ * The blkg_lookup performed in bfq_get_queue, protected
+ * through rcu, may happen to return the address of a copy of
+ * the original blkg. If this is the case, then the
+ * bfqg_and_blkg_get performed in bfq_get_queue, to pin down
+ * the blkg, is useless: it does not prevent blk-cgroup code
+ * from destroying both the original blkg and all objects
+ * directly or indirectly referred by the copy of the
+ * blkg.
+ *
+ * On the bright side, destroy operations on a blkg invoke, as
+ * a first step, hooks of the scheduler associated with the
+ * blkg. And these hooks are executed with bfqd->lock held for
+ * BFQ. As a consequence, for any blkg associated with the
+ * request queue this instance of the scheduler is attached
+ * to, we are guaranteed that such a blkg is not destroyed, and
+ * that all the pointers it contains are consistent, while we
+ * are holding bfqd->lock. A blkg_lookup performed with
+ * bfqd->lock held then returns a fully consistent blkg, which
+ * remains consistent until this lock is held.
+ *
+ * Thanks to the last fact, and to the fact that: (1) bfqg has
+ * been obtained through a blkg_lookup in the above
+ * assignment, and (2) bfqd->lock is being held, here we can
+ * safely use the policy data for the involved blkg (i.e., the
+ * field bfqg->pd) to get to the blkg associated with bfqg,
+ * and then we can safely use any field of blkg. After we
+ * release bfqd->lock, even just getting blkg through this
+ * bfqg may cause dangling references to be traversed, as
+ * bfqg->pd may not exist any more.
+ *
+ * In view of the above facts, here we cache, in the bfqg, any
+ * blkg data we may need for this bic, and for its associated
+ * bfq_queue. As of now, we need to cache only the path of the
+ * blkg, which is used in the bfq_log_* functions.
+ *
+ * Finally, note that bfqg itself needs to be protected from
+ * destruction on the blkg_free of the original blkg (which
+ * invokes bfq_pd_free). We use an additional private
+ * refcounter for bfqg, to let it disappear only after no
+ * bfq_queue refers to it any longer.
+ */
+ blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path));
bic->blkcg_serial_nr = serial_nr;
out:
rcu_read_unlock();
@@ -640,8 +713,6 @@ static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
* @bfqd: the device data structure with the root group.
* @bfqg: the group to move from.
* @st: the service tree with the entities.
- *
- * Needs queue_lock to be taken and reference to be valid over the call.
*/
static void bfq_reparent_active_entities(struct bfq_data *bfqd,
struct bfq_group *bfqg,
@@ -692,8 +763,7 @@ void bfq_pd_offline(struct blkg_policy_data *pd)
/*
* The idle tree may still contain bfq_queues belonging
* to exited task because they never migrated to a different
- * cgroup from the one being destroyed now. No one else
- * can access them so it's safe to act without any lock.
+ * cgroup from the one being destroyed now.
*/
bfq_flush_idle_tree(st);
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 08ce45096350..12bbc6b8657d 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -725,8 +725,12 @@ static void bfq_updated_next_req(struct bfq_data *bfqd,
}
static void
-bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
+bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
+ struct bfq_io_cq *bic, bool bfq_already_existing)
{
+ unsigned int old_wr_coeff = bfqq->wr_coeff;
+ bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);
+
if (bic->saved_idle_window)
bfq_mark_bfqq_idle_window(bfqq);
else
@@ -754,6 +758,14 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
/* make sure weight will be updated, however we got here */
bfqq->entity.prio_changed = 1;
+
+ if (likely(!busy))
+ return;
+
+ if (old_wr_coeff == 1 && bfqq->wr_coeff > 1)
+ bfqd->wr_busy_queues++;
+ else if (old_wr_coeff > 1 && bfqq->wr_coeff == 1)
+ bfqd->wr_busy_queues--;
}
static int bfqq_process_refs(struct bfq_queue *bfqq)
@@ -3665,7 +3677,7 @@ void bfq_put_queue(struct bfq_queue *bfqq)
kmem_cache_free(bfq_pool, bfqq);
#ifdef CONFIG_BFQ_GROUP_IOSCHED
- bfqg_put(bfqg);
+ bfqg_and_blkg_put(bfqg);
#endif
}
@@ -4290,10 +4302,16 @@ static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
bfq_put_queue(bfqq);
}
-static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
+static void bfq_finish_request(struct request *rq)
{
- struct bfq_queue *bfqq = RQ_BFQQ(rq);
- struct bfq_data *bfqd = bfqq->bfqd;
+ struct bfq_queue *bfqq;
+ struct bfq_data *bfqd;
+
+ if (!rq->elv.icq)
+ return;
+
+ bfqq = RQ_BFQQ(rq);
+ bfqd = bfqq->bfqd;
if (rq->rq_flags & RQF_STARTED)
bfqg_stats_update_completion(bfqq_group(bfqq),
@@ -4324,7 +4342,7 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
*/
if (!RB_EMPTY_NODE(&rq->rb_node))
- bfq_remove_request(q, rq);
+ bfq_remove_request(rq->q, rq);
bfq_put_rq_priv_body(bfqq);
}
@@ -4394,20 +4412,21 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
/*
* Allocate bfq data structures associated with this request.
*/
-static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
- struct bio *bio)
+static void bfq_prepare_request(struct request *rq, struct bio *bio)
{
+ struct request_queue *q = rq->q;
struct bfq_data *bfqd = q->elevator->elevator_data;
- struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
+ struct bfq_io_cq *bic;
const int is_sync = rq_is_sync(rq);
struct bfq_queue *bfqq;
bool new_queue = false;
- bool split = false;
+ bool bfqq_already_existing = false, split = false;
- spin_lock_irq(&bfqd->lock);
+ if (!rq->elv.icq)
+ return;
+ bic = icq_to_bic(rq->elv.icq);
- if (!bic)
- goto queue_fail;
+ spin_lock_irq(&bfqd->lock);
bfq_check_ioprio_change(bic, bio);
@@ -4432,6 +4451,8 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
true, is_sync,
NULL);
+ else
+ bfqq_already_existing = true;
}
}
@@ -4457,7 +4478,8 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
* queue: restore the idle window and the
* possible weight raising period.
*/
- bfq_bfqq_resume_state(bfqq, bic);
+ bfq_bfqq_resume_state(bfqq, bfqd, bic,
+ bfqq_already_existing);
}
}
@@ -4465,13 +4487,6 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
bfq_handle_burst(bfqd, bfqq);
spin_unlock_irq(&bfqd->lock);
-
- return 0;
-
-queue_fail:
- spin_unlock_irq(&bfqd->lock);
-
- return 1;
}
static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
@@ -4950,8 +4965,8 @@ static struct elv_fs_entry bfq_attrs[] = {
static struct elevator_type iosched_bfq_mq = {
.ops.mq = {
- .get_rq_priv = bfq_get_rq_private,
- .put_rq_priv = bfq_put_rq_private,
+ .prepare_request = bfq_prepare_request,
+ .finish_request = bfq_finish_request,
.exit_icq = bfq_exit_icq,
.insert_requests = bfq_insert_requests,
.dispatch_request = bfq_dispatch_request,
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index ae783c06dfd9..5c3bf9861492 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -759,6 +759,12 @@ struct bfq_group {
/* must be the first member */
struct blkg_policy_data pd;
+ /* cached path for this blkg (see comments in bfq_bic_update_cgroup) */
+ char blkg_path[128];
+
+ /* reference counter (see comments in bfq_bic_update_cgroup) */
+ int ref;
+
struct bfq_entity entity;
struct bfq_sched_data sched_data;
@@ -838,7 +844,7 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
-void bfqg_put(struct bfq_group *bfqg);
+void bfqg_and_blkg_put(struct bfq_group *bfqg);
#ifdef CONFIG_BFQ_GROUP_IOSCHED
extern struct cftype bfq_blkcg_legacy_files[];
@@ -910,20 +916,13 @@ void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \
- char __pbuf[128]; \
- \
- blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
- blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid, \
+ blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid,\
bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \
- __pbuf, ##args); \
+ bfqq_group(bfqq)->blkg_path, ##args); \
} while (0)
-#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \
- char __pbuf[128]; \
- \
- blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf)); \
- blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args); \
-} while (0)
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) \
+ blk_add_trace_msg((bfqd)->queue, "%s " fmt, (bfqg)->blkg_path, ##args)
#else /* CONFIG_BFQ_GROUP_IOSCHED */
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 5384713d48bc..b8a3a65f7364 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -175,6 +175,9 @@ bool bio_integrity_enabled(struct bio *bio)
if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE)
return false;
+ if (!bio_sectors(bio))
+ return false;
+
/* Already protected? */
if (bio_integrity(bio))
return false;
@@ -221,7 +224,7 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
* @bio: bio to generate/verify integrity metadata for
* @proc_fn: Pointer to the relevant processing function
*/
-static int bio_integrity_process(struct bio *bio,
+static blk_status_t bio_integrity_process(struct bio *bio,
integrity_processing_fn *proc_fn)
{
struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
@@ -229,7 +232,7 @@ static int bio_integrity_process(struct bio *bio,
struct bvec_iter bviter;
struct bio_vec bv;
struct bio_integrity_payload *bip = bio_integrity(bio);
- unsigned int ret = 0;
+ blk_status_t ret = BLK_STS_OK;
void *prot_buf = page_address(bip->bip_vec->bv_page) +
bip->bip_vec->bv_offset;
@@ -366,7 +369,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
struct bio *bio = bip->bip_bio;
struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
- bio->bi_error = bio_integrity_process(bio, bi->profile->verify_fn);
+ bio->bi_status = bio_integrity_process(bio, bi->profile->verify_fn);
/* Restore original bio completion handler */
bio->bi_end_io = bip->bip_end_io;
@@ -395,7 +398,7 @@ void bio_integrity_endio(struct bio *bio)
* integrity metadata. Restore original bio end_io handler
* and run it.
*/
- if (bio->bi_error) {
+ if (bio->bi_status) {
bio->bi_end_io = bip->bip_end_io;
bio_endio(bio);
diff --git a/block/bio.c b/block/bio.c
index 888e7801c638..1cfcd0df3f30 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -240,20 +240,21 @@ fallback:
return bvl;
}
-static void __bio_free(struct bio *bio)
+void bio_uninit(struct bio *bio)
{
bio_disassociate_task(bio);
if (bio_integrity(bio))
bio_integrity_free(bio);
}
+EXPORT_SYMBOL(bio_uninit);
static void bio_free(struct bio *bio)
{
struct bio_set *bs = bio->bi_pool;
void *p;
- __bio_free(bio);
+ bio_uninit(bio);
if (bs) {
bvec_free(bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio));
@@ -271,6 +272,11 @@ static void bio_free(struct bio *bio)
}
}
+/*
+ * Users of this function have their own bio allocation. Subsequently,
+ * they must remember to pair any call to bio_init() with bio_uninit()
+ * when IO has completed, or when the bio is released.
+ */
void bio_init(struct bio *bio, struct bio_vec *table,
unsigned short max_vecs)
{
@@ -297,7 +303,7 @@ void bio_reset(struct bio *bio)
{
unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS);
- __bio_free(bio);
+ bio_uninit(bio);
memset(bio, 0, BIO_RESET_BYTES);
bio->bi_flags = flags;
@@ -309,8 +315,8 @@ static struct bio *__bio_chain_endio(struct bio *bio)
{
struct bio *parent = bio->bi_private;
- if (!parent->bi_error)
- parent->bi_error = bio->bi_error;
+ if (!parent->bi_status)
+ parent->bi_status = bio->bi_status;
bio_put(bio);
return parent;
}
@@ -363,6 +369,8 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
struct bio_list punt, nopunt;
struct bio *bio;
+ if (WARN_ON_ONCE(!bs->rescue_workqueue))
+ return;
/*
* In order to guarantee forward progress we must punt only bios that
* were allocated from this bio_set; otherwise, if there was a bio on
@@ -474,7 +482,8 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
if (current->bio_list &&
(!bio_list_empty(&current->bio_list[0]) ||
- !bio_list_empty(&current->bio_list[1])))
+ !bio_list_empty(&current->bio_list[1])) &&
+ bs->rescue_workqueue)
gfp_mask &= ~__GFP_DIRECT_RECLAIM;
p = mempool_alloc(bs->bio_pool, gfp_mask);
@@ -544,7 +553,7 @@ EXPORT_SYMBOL(zero_fill_bio);
*
* Description:
* Put a reference to a &struct bio, either one you have gotten with
- * bio_alloc, bio_get or bio_clone. The last put of a bio will free it.
+ * bio_alloc, bio_get or bio_clone_*. The last put of a bio will free it.
**/
void bio_put(struct bio *bio)
{
@@ -593,6 +602,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
bio->bi_bdev = bio_src->bi_bdev;
bio_set_flag(bio, BIO_CLONED);
bio->bi_opf = bio_src->bi_opf;
+ bio->bi_write_hint = bio_src->bi_write_hint;
bio->bi_iter = bio_src->bi_iter;
bio->bi_io_vec = bio_src->bi_io_vec;
@@ -676,6 +686,7 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
return NULL;
bio->bi_bdev = bio_src->bi_bdev;
bio->bi_opf = bio_src->bi_opf;
+ bio->bi_write_hint = bio_src->bi_write_hint;
bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector;
bio->bi_iter.bi_size = bio_src->bi_iter.bi_size;
@@ -918,7 +929,7 @@ static void submit_bio_wait_endio(struct bio *bio)
{
struct submit_bio_ret *ret = bio->bi_private;
- ret->error = bio->bi_error;
+ ret->error = blk_status_to_errno(bio->bi_status);
complete(&ret->event);
}
@@ -1817,8 +1828,8 @@ again:
}
if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
- trace_block_bio_complete(bdev_get_queue(bio->bi_bdev),
- bio, bio->bi_error);
+ trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio,
+ blk_status_to_errno(bio->bi_status));
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
}
@@ -1921,9 +1932,29 @@ void bioset_free(struct bio_set *bs)
}
EXPORT_SYMBOL(bioset_free);
-static struct bio_set *__bioset_create(unsigned int pool_size,
- unsigned int front_pad,
- bool create_bvec_pool)
+/**
+ * bioset_create - Create a bio_set
+ * @pool_size: Number of bio and bio_vecs to cache in the mempool
+ * @front_pad: Number of bytes to allocate in front of the returned bio
+ * @flags: Flags to modify behavior, currently %BIOSET_NEED_BVECS
+ * and %BIOSET_NEED_RESCUER
+ *
+ * Description:
+ * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
+ * to ask for a number of bytes to be allocated in front of the bio.
+ * Front pad allocation is useful for embedding the bio inside
+ * another structure, to avoid allocating extra data to go with the bio.
+ * Note that the bio must be embedded at the END of that structure always,
+ * or things will break badly.
+ * If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated
+ * for allocating iovecs. This pool is not needed e.g. for bio_clone_fast().
+ * If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used to
+ * dispatch queued requests when the mempool runs out of space.
+ *
+ */
+struct bio_set *bioset_create(unsigned int pool_size,
+ unsigned int front_pad,
+ int flags)
{
unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
struct bio_set *bs;
@@ -1948,12 +1979,15 @@ static struct bio_set *__bioset_create(unsigned int pool_size,
if (!bs->bio_pool)
goto bad;
- if (create_bvec_pool) {
+ if (flags & BIOSET_NEED_BVECS) {
bs->bvec_pool = biovec_create_pool(pool_size);
if (!bs->bvec_pool)
goto bad;
}
+ if (!(flags & BIOSET_NEED_RESCUER))
+ return bs;
+
bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
if (!bs->rescue_workqueue)
goto bad;
@@ -1963,41 +1997,8 @@ bad:
bioset_free(bs);
return NULL;
}
-
-/**
- * bioset_create - Create a bio_set
- * @pool_size: Number of bio and bio_vecs to cache in the mempool
- * @front_pad: Number of bytes to allocate in front of the returned bio
- *
- * Description:
- * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
- * to ask for a number of bytes to be allocated in front of the bio.
- * Front pad allocation is useful for embedding the bio inside
- * another structure, to avoid allocating extra data to go with the bio.
- * Note that the bio must be embedded at the END of that structure always,
- * or things will break badly.
- */
-struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
-{
- return __bioset_create(pool_size, front_pad, true);
-}
EXPORT_SYMBOL(bioset_create);
-/**
- * bioset_create_nobvec - Create a bio_set without bio_vec mempool
- * @pool_size: Number of bio to cache in the mempool
- * @front_pad: Number of bytes to allocate in front of the returned bio
- *
- * Description:
- * Same functionality as bioset_create() except that mempool is not
- * created for bio_vecs. Saving some memory for bio_clone_fast() users.
- */
-struct bio_set *bioset_create_nobvec(unsigned int pool_size, unsigned int front_pad)
-{
- return __bioset_create(pool_size, front_pad, false);
-}
-EXPORT_SYMBOL(bioset_create_nobvec);
-
#ifdef CONFIG_BLK_CGROUP
/**
@@ -2112,7 +2113,7 @@ static int __init init_bio(void)
bio_integrity_init();
biovec_init_slabs();
- fs_bio_set = bioset_create(BIO_POOL_SIZE, 0);
+ fs_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
if (!fs_bio_set)
panic("bio: can't allocate bios\n");
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 7c2947128f58..0480892e97e5 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -74,7 +74,7 @@ static void blkg_free(struct blkcg_gq *blkg)
blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
if (blkg->blkcg != &blkcg_root)
- blk_exit_rl(&blkg->rl);
+ blk_exit_rl(blkg->q, &blkg->rl);
blkg_rwstat_exit(&blkg->stat_ios);
blkg_rwstat_exit(&blkg->stat_bytes);
diff --git a/block/blk-core.c b/block/blk-core.c
index c7068520794b..af393d5a9680 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -129,11 +129,70 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
}
EXPORT_SYMBOL(blk_rq_init);
+static const struct {
+ int errno;
+ const char *name;
+} blk_errors[] = {
+ [BLK_STS_OK] = { 0, "" },
+ [BLK_STS_NOTSUPP] = { -EOPNOTSUPP, "operation not supported" },
+ [BLK_STS_TIMEOUT] = { -ETIMEDOUT, "timeout" },
+ [BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" },
+ [BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" },
+ [BLK_STS_TARGET] = { -EREMOTEIO, "critical target" },
+ [BLK_STS_NEXUS] = { -EBADE, "critical nexus" },
+ [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" },
+ [BLK_STS_PROTECTION] = { -EILSEQ, "protection" },
+ [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" },
+ [BLK_STS_AGAIN] = { -EAGAIN, "nonblocking retry" },
+
+ /* device mapper special case, should not leak out: */
+ [BLK_STS_DM_REQUEUE] = { -EREMCHG, "dm internal retry" },
+
+ /* everything else not covered above: */
+ [BLK_STS_IOERR] = { -EIO, "I/O" },
+};
+
+blk_status_t errno_to_blk_status(int errno)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(blk_errors); i++) {
+ if (blk_errors[i].errno == errno)
+ return (__force blk_status_t)i;
+ }
+
+ return BLK_STS_IOERR;
+}
+EXPORT_SYMBOL_GPL(errno_to_blk_status);
+
+int blk_status_to_errno(blk_status_t status)
+{
+ int idx = (__force int)status;
+
+ if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
+ return -EIO;
+ return blk_errors[idx].errno;
+}
+EXPORT_SYMBOL_GPL(blk_status_to_errno);
+
+static void print_req_error(struct request *req, blk_status_t status)
+{
+ int idx = (__force int)status;
+
+ if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
+ return;
+
+ printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu\n",
+ __func__, blk_errors[idx].name, req->rq_disk ?
+ req->rq_disk->disk_name : "?",
+ (unsigned long long)blk_rq_pos(req));
+}
+
static void req_bio_endio(struct request *rq, struct bio *bio,
- unsigned int nbytes, int error)
+ unsigned int nbytes, blk_status_t error)
{
if (error)
- bio->bi_error = error;
+ bio->bi_status = error;
if (unlikely(rq->rq_flags & RQF_QUIET))
bio_set_flag(bio, BIO_QUIET);
@@ -177,10 +236,13 @@ static void blk_delay_work(struct work_struct *work)
* Description:
* Sometimes queueing needs to be postponed for a little while, to allow
* resources to come back. This function will make sure that queueing is
- * restarted around the specified time. Queue lock must be held.
+ * restarted around the specified time.
*/
void blk_delay_queue(struct request_queue *q, unsigned long msecs)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
if (likely(!blk_queue_dead(q)))
queue_delayed_work(kblockd_workqueue, &q->delay_work,
msecs_to_jiffies(msecs));
@@ -198,6 +260,9 @@ EXPORT_SYMBOL(blk_delay_queue);
**/
void blk_start_queue_async(struct request_queue *q)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
queue_flag_clear(QUEUE_FLAG_STOPPED, q);
blk_run_queue_async(q);
}
@@ -210,11 +275,13 @@ EXPORT_SYMBOL(blk_start_queue_async);
* Description:
* blk_start_queue() will clear the stop flag on the queue, and call
* the request_fn for the queue if it was in a stopped state when
- * entered. Also see blk_stop_queue(). Queue lock must be held.
+ * entered. Also see blk_stop_queue().
**/
void blk_start_queue(struct request_queue *q)
{
+ lockdep_assert_held(q->queue_lock);
WARN_ON(!irqs_disabled());
+ WARN_ON_ONCE(q->mq_ops);
queue_flag_clear(QUEUE_FLAG_STOPPED, q);
__blk_run_queue(q);
@@ -233,10 +300,13 @@ EXPORT_SYMBOL(blk_start_queue);
* or if it simply chooses not to queue more I/O at one point, it can
* call this function to prevent the request_fn from being called until
* the driver has signalled it's ready to go again. This happens by calling
- * blk_start_queue() to restart queue operations. Queue lock must be held.
+ * blk_start_queue() to restart queue operations.
**/
void blk_stop_queue(struct request_queue *q)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
cancel_delayed_work(&q->delay_work);
queue_flag_set(QUEUE_FLAG_STOPPED, q);
}
@@ -289,6 +359,9 @@ EXPORT_SYMBOL(blk_sync_queue);
*/
inline void __blk_run_queue_uncond(struct request_queue *q)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
if (unlikely(blk_queue_dead(q)))
return;
@@ -310,11 +383,13 @@ EXPORT_SYMBOL_GPL(__blk_run_queue_uncond);
* @q: The queue to run
*
* Description:
- * See @blk_run_queue. This variant must be called with the queue lock
- * held and interrupts disabled.
+ * See @blk_run_queue.
*/
void __blk_run_queue(struct request_queue *q)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
if (unlikely(blk_queue_stopped(q)))
return;
@@ -328,10 +403,18 @@ EXPORT_SYMBOL(__blk_run_queue);
*
* Description:
* Tells kblockd to perform the equivalent of @blk_run_queue on behalf
- * of us. The caller must hold the queue lock.
+ * of us.
+ *
+ * Note:
+ * Since it is not allowed to run q->delay_work after blk_cleanup_queue()
+ * has canceled q->delay_work, callers must hold the queue lock to avoid
+ * race conditions between blk_cleanup_queue() and blk_run_queue_async().
*/
void blk_run_queue_async(struct request_queue *q)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
if (likely(!blk_queue_stopped(q) && !blk_queue_dead(q)))
mod_delayed_work(kblockd_workqueue, &q->delay_work, 0);
}
@@ -349,6 +432,8 @@ void blk_run_queue(struct request_queue *q)
{
unsigned long flags;
+ WARN_ON_ONCE(q->mq_ops);
+
spin_lock_irqsave(q->queue_lock, flags);
__blk_run_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
@@ -377,6 +462,7 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all)
int i;
lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
while (true) {
bool drain = false;
@@ -455,6 +541,8 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all)
*/
void blk_queue_bypass_start(struct request_queue *q)
{
+ WARN_ON_ONCE(q->mq_ops);
+
spin_lock_irq(q->queue_lock);
q->bypass_depth++;
queue_flag_set(QUEUE_FLAG_BYPASS, q);
@@ -481,6 +569,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_start);
* @q: queue of interest
*
* Leave bypass mode and restore the normal queueing behavior.
+ *
+ * Note: although blk_queue_bypass_start() is only called for blk-sq queues,
+ * this function is called for both blk-sq and blk-mq queues.
*/
void blk_queue_bypass_end(struct request_queue *q)
{
@@ -648,13 +739,19 @@ int blk_init_rl(struct request_list *rl, struct request_queue *q,
if (!rl->rq_pool)
return -ENOMEM;
+ if (rl != &q->root_rl)
+ WARN_ON_ONCE(!blk_get_queue(q));
+
return 0;
}
-void blk_exit_rl(struct request_list *rl)
+void blk_exit_rl(struct request_queue *q, struct request_list *rl)
{
- if (rl->rq_pool)
+ if (rl->rq_pool) {
mempool_destroy(rl->rq_pool);
+ if (rl != &q->root_rl)
+ blk_put_queue(q);
+ }
}
struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
@@ -726,7 +823,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
if (q->id < 0)
goto fail_q;
- q->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+ q->bio_split = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
if (!q->bio_split)
goto fail_id;
@@ -872,6 +969,8 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio);
int blk_init_allocated_queue(struct request_queue *q)
{
+ WARN_ON_ONCE(q->mq_ops);
+
q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, q->cmd_size);
if (!q->fq)
return -ENOMEM;
@@ -1009,6 +1108,8 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
struct request_list *rl;
int on_thresh, off_thresh;
+ WARN_ON_ONCE(q->mq_ops);
+
spin_lock_irq(q->queue_lock);
q->nr_requests = nr;
blk_queue_congestion_threshold(q);
@@ -1071,6 +1172,8 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
int may_queue;
req_flags_t rq_flags = RQF_ALLOCED;
+ lockdep_assert_held(q->queue_lock);
+
if (unlikely(blk_queue_dying(q)))
return ERR_PTR(-ENODEV);
@@ -1244,12 +1347,20 @@ static struct request *get_request(struct request_queue *q, unsigned int op,
struct request_list *rl;
struct request *rq;
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
rl = blk_get_rl(q, bio); /* transferred to @rq on success */
retry:
rq = __get_request(rl, op, bio, gfp_mask);
if (!IS_ERR(rq))
return rq;
+ if (op & REQ_NOWAIT) {
+ blk_put_rl(rl);
+ return ERR_PTR(-EAGAIN);
+ }
+
if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) {
blk_put_rl(rl);
return rq;
@@ -1277,16 +1388,18 @@ retry:
goto retry;
}
-static struct request *blk_old_get_request(struct request_queue *q, int rw,
- gfp_t gfp_mask)
+static struct request *blk_old_get_request(struct request_queue *q,
+ unsigned int op, gfp_t gfp_mask)
{
struct request *rq;
+ WARN_ON_ONCE(q->mq_ops);
+
/* create ioc upfront */
create_io_context(gfp_mask, q->node);
spin_lock_irq(q->queue_lock);
- rq = get_request(q, rw, NULL, gfp_mask);
+ rq = get_request(q, op, NULL, gfp_mask);
if (IS_ERR(rq)) {
spin_unlock_irq(q->queue_lock);
return rq;
@@ -1299,14 +1412,24 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
return rq;
}
-struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
+struct request *blk_get_request(struct request_queue *q, unsigned int op,
+ gfp_t gfp_mask)
{
- if (q->mq_ops)
- return blk_mq_alloc_request(q, rw,
+ struct request *req;
+
+ if (q->mq_ops) {
+ req = blk_mq_alloc_request(q, op,
(gfp_mask & __GFP_DIRECT_RECLAIM) ?
0 : BLK_MQ_REQ_NOWAIT);
- else
- return blk_old_get_request(q, rw, gfp_mask);
+ if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn)
+ q->mq_ops->initialize_rq_fn(req);
+ } else {
+ req = blk_old_get_request(q, op, gfp_mask);
+ if (!IS_ERR(req) && q->initialize_rq_fn)
+ q->initialize_rq_fn(req);
+ }
+
+ return req;
}
EXPORT_SYMBOL(blk_get_request);
@@ -1322,6 +1445,9 @@ EXPORT_SYMBOL(blk_get_request);
*/
void blk_requeue_request(struct request_queue *q, struct request *rq)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
blk_delete_timer(rq);
blk_clear_rq_complete(rq);
trace_block_rq_requeue(q, rq);
@@ -1396,9 +1522,6 @@ static void blk_pm_put_request(struct request *rq)
static inline void blk_pm_put_request(struct request *rq) {}
#endif
-/*
- * queue lock must be held
- */
void __blk_put_request(struct request_queue *q, struct request *req)
{
req_flags_t rq_flags = req->rq_flags;
@@ -1411,6 +1534,8 @@ void __blk_put_request(struct request_queue *q, struct request *req)
return;
}
+ lockdep_assert_held(q->queue_lock);
+
blk_pm_put_request(req);
elv_completed_request(q, req);
@@ -1640,6 +1765,7 @@ void blk_init_request_from_bio(struct request *req, struct bio *bio)
req->ioprio = ioc->ioprio;
else
req->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
+ req->write_hint = bio->bi_write_hint;
blk_rq_bio_prep(req->q, req, bio);
}
EXPORT_SYMBOL_GPL(blk_init_request_from_bio);
@@ -1659,10 +1785,10 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
*/
blk_queue_bounce(q, &bio);
- blk_queue_split(q, &bio, q->bio_split);
+ blk_queue_split(q, &bio);
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
- bio->bi_error = -EIO;
+ bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
return BLK_QC_T_NONE;
}
@@ -1720,7 +1846,10 @@ get_rq:
req = get_request(q, bio->bi_opf, bio, GFP_NOIO);
if (IS_ERR(req)) {
__wbt_done(q->rq_wb, wb_acct);
- bio->bi_error = PTR_ERR(req);
+ if (PTR_ERR(req) == -ENOMEM)
+ bio->bi_status = BLK_STS_RESOURCE;
+ else
+ bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
goto out_unlock;
}
@@ -1875,7 +2004,7 @@ generic_make_request_checks(struct bio *bio)
{
struct request_queue *q;
int nr_sectors = bio_sectors(bio);
- int err = -EIO;
+ blk_status_t status = BLK_STS_IOERR;
char b[BDEVNAME_SIZE];
struct hd_struct *part;
@@ -1894,6 +2023,14 @@ generic_make_request_checks(struct bio *bio)
goto end_io;
}
+ /*
+ * For a REQ_NOWAIT based request, return -EOPNOTSUPP
+ * if queue is not a request based queue.
+ */
+
+ if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q))
+ goto not_supported;
+
part = bio->bi_bdev->bd_part;
if (should_fail_request(part, bio->bi_iter.bi_size) ||
should_fail_request(&part_to_disk(part)->part0,
@@ -1918,7 +2055,7 @@ generic_make_request_checks(struct bio *bio)
!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
if (!nr_sectors) {
- err = 0;
+ status = BLK_STS_OK;
goto end_io;
}
}
@@ -1970,9 +2107,9 @@ generic_make_request_checks(struct bio *bio)
return true;
not_supported:
- err = -EOPNOTSUPP;
+ status = BLK_STS_NOTSUPP;
end_io:
- bio->bi_error = err;
+ bio->bi_status = status;
bio_endio(bio);
return false;
}
@@ -2051,7 +2188,7 @@ blk_qc_t generic_make_request(struct bio *bio)
do {
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
- if (likely(blk_queue_enter(q, false) == 0)) {
+ if (likely(blk_queue_enter(q, bio->bi_opf & REQ_NOWAIT) == 0)) {
struct bio_list lower, same;
/* Create a fresh bio_list for all subordinate requests */
@@ -2076,7 +2213,11 @@ blk_qc_t generic_make_request(struct bio *bio)
bio_list_merge(&bio_list_on_stack[0], &same);
bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
} else {
- bio_io_error(bio);
+ if (unlikely(!blk_queue_dying(q) &&
+ (bio->bi_opf & REQ_NOWAIT)))
+ bio_wouldblock_error(bio);
+ else
+ bio_io_error(bio);
}
bio = bio_list_pop(&bio_list_on_stack[0]);
} while (bio);
@@ -2177,29 +2318,29 @@ static int blk_cloned_rq_check_limits(struct request_queue *q,
* @q: the queue to submit the request
* @rq: the request being queued
*/
-int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
+blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq)
{
unsigned long flags;
int where = ELEVATOR_INSERT_BACK;
if (blk_cloned_rq_check_limits(q, rq))
- return -EIO;
+ return BLK_STS_IOERR;
if (rq->rq_disk &&
should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
- return -EIO;
+ return BLK_STS_IOERR;
if (q->mq_ops) {
if (blk_queue_io_stat(q))
blk_account_io_start(rq, true);
blk_mq_sched_insert_request(rq, false, true, false, false);
- return 0;
+ return BLK_STS_OK;
}
spin_lock_irqsave(q->queue_lock, flags);
if (unlikely(blk_queue_dying(q))) {
spin_unlock_irqrestore(q->queue_lock, flags);
- return -ENODEV;
+ return BLK_STS_IOERR;
}
/*
@@ -2216,7 +2357,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
__blk_run_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
- return 0;
+ return BLK_STS_OK;
}
EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
@@ -2232,9 +2373,6 @@ EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
*
* Return:
* The number of bytes to fail.
- *
- * Context:
- * queue_lock must be held.
*/
unsigned int blk_rq_err_bytes(const struct request *rq)
{
@@ -2374,15 +2512,15 @@ void blk_account_io_start(struct request *rq, bool new_io)
* Return:
* Pointer to the request at the top of @q if available. Null
* otherwise.
- *
- * Context:
- * queue_lock must be held.
*/
struct request *blk_peek_request(struct request_queue *q)
{
struct request *rq;
int ret;
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
while ((rq = __elv_next_request(q)) != NULL) {
rq = blk_pm_peek_request(q, rq);
@@ -2450,15 +2588,14 @@ struct request *blk_peek_request(struct request_queue *q)
rq = NULL;
break;
} else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) {
- int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO;
-
rq->rq_flags |= RQF_QUIET;
/*
* Mark this request as started so we don't trigger
* any debug logic in the end I/O path.
*/
blk_start_request(rq);
- __blk_end_request_all(rq, err);
+ __blk_end_request_all(rq, ret == BLKPREP_INVALID ?
+ BLK_STS_TARGET : BLK_STS_IOERR);
} else {
printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
break;
@@ -2499,12 +2636,12 @@ void blk_dequeue_request(struct request *rq)
*
* Block internal functions which don't want to start timer should
* call blk_dequeue_request().
- *
- * Context:
- * queue_lock must be held.
*/
void blk_start_request(struct request *req)
{
+ lockdep_assert_held(req->q->queue_lock);
+ WARN_ON_ONCE(req->q->mq_ops);
+
blk_dequeue_request(req);
if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) {
@@ -2529,14 +2666,14 @@ EXPORT_SYMBOL(blk_start_request);
* Return:
* Pointer to the request at the top of @q if available. Null
* otherwise.
- *
- * Context:
- * queue_lock must be held.
*/
struct request *blk_fetch_request(struct request_queue *q)
{
struct request *rq;
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
rq = blk_peek_request(q);
if (rq)
blk_start_request(rq);
@@ -2547,7 +2684,7 @@ EXPORT_SYMBOL(blk_fetch_request);
/**
* blk_update_request - Special helper function for request stacking drivers
* @req: the request being processed
- * @error: %0 for success, < %0 for error
+ * @error: block status code
* @nr_bytes: number of bytes to complete @req
*
* Description:
@@ -2566,49 +2703,19 @@ EXPORT_SYMBOL(blk_fetch_request);
* %false - this request doesn't have any more data
* %true - this request has more data
**/
-bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
+bool blk_update_request(struct request *req, blk_status_t error,
+ unsigned int nr_bytes)
{
int total_bytes;
- trace_block_rq_complete(req, error, nr_bytes);
+ trace_block_rq_complete(req, blk_status_to_errno(error), nr_bytes);
if (!req->bio)
return false;
- if (error && !blk_rq_is_passthrough(req) &&
- !(req->rq_flags & RQF_QUIET)) {
- char *error_type;
-
- switch (error) {
- case -ENOLINK:
- error_type = "recoverable transport";
- break;
- case -EREMOTEIO:
- error_type = "critical target";
- break;
- case -EBADE:
- error_type = "critical nexus";
- break;
- case -ETIMEDOUT:
- error_type = "timeout";
- break;
- case -ENOSPC:
- error_type = "critical space allocation";
- break;
- case -ENODATA:
- error_type = "critical medium";
- break;
- case -EIO:
- default:
- error_type = "I/O";
- break;
- }
- printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu\n",
- __func__, error_type, req->rq_disk ?
- req->rq_disk->disk_name : "?",
- (unsigned long long)blk_rq_pos(req));
-
- }
+ if (unlikely(error && !blk_rq_is_passthrough(req) &&
+ !(req->rq_flags & RQF_QUIET)))
+ print_req_error(req, error);
blk_account_io_completion(req, nr_bytes);
@@ -2674,7 +2781,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
}
EXPORT_SYMBOL_GPL(blk_update_request);
-static bool blk_update_bidi_request(struct request *rq, int error,
+static bool blk_update_bidi_request(struct request *rq, blk_status_t error,
unsigned int nr_bytes,
unsigned int bidi_bytes)
{
@@ -2712,13 +2819,13 @@ void blk_unprep_request(struct request *req)
}
EXPORT_SYMBOL_GPL(blk_unprep_request);
-/*
- * queue lock must be held
- */
-void blk_finish_request(struct request *req, int error)
+void blk_finish_request(struct request *req, blk_status_t error)
{
struct request_queue *q = req->q;
+ lockdep_assert_held(req->q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
if (req->rq_flags & RQF_STATS)
blk_stat_add(req);
@@ -2752,7 +2859,7 @@ EXPORT_SYMBOL(blk_finish_request);
/**
* blk_end_bidi_request - Complete a bidi request
* @rq: the request to complete
- * @error: %0 for success, < %0 for error
+ * @error: block status code
* @nr_bytes: number of bytes to complete @rq
* @bidi_bytes: number of bytes to complete @rq->next_rq
*
@@ -2766,12 +2873,14 @@ EXPORT_SYMBOL(blk_finish_request);
* %false - we are done with this request
* %true - still buffers pending for this request
**/
-static bool blk_end_bidi_request(struct request *rq, int error,
+static bool blk_end_bidi_request(struct request *rq, blk_status_t error,
unsigned int nr_bytes, unsigned int bidi_bytes)
{
struct request_queue *q = rq->q;
unsigned long flags;
+ WARN_ON_ONCE(q->mq_ops);
+
if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
return true;
@@ -2785,7 +2894,7 @@ static bool blk_end_bidi_request(struct request *rq, int error,
/**
* __blk_end_bidi_request - Complete a bidi request with queue lock held
* @rq: the request to complete
- * @error: %0 for success, < %0 for error
+ * @error: block status code
* @nr_bytes: number of bytes to complete @rq
* @bidi_bytes: number of bytes to complete @rq->next_rq
*
@@ -2797,9 +2906,12 @@ static bool blk_end_bidi_request(struct request *rq, int error,
* %false - we are done with this request
* %true - still buffers pending for this request
**/
-static bool __blk_end_bidi_request(struct request *rq, int error,
+static bool __blk_end_bidi_request(struct request *rq, blk_status_t error,
unsigned int nr_bytes, unsigned int bidi_bytes)
{
+ lockdep_assert_held(rq->q->queue_lock);
+ WARN_ON_ONCE(rq->q->mq_ops);
+
if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
return true;
@@ -2811,7 +2923,7 @@ static bool __blk_end_bidi_request(struct request *rq, int error,
/**
* blk_end_request - Helper function for drivers to complete the request.
* @rq: the request being processed
- * @error: %0 for success, < %0 for error
+ * @error: block status code
* @nr_bytes: number of bytes to complete
*
* Description:
@@ -2822,8 +2934,10 @@ static bool __blk_end_bidi_request(struct request *rq, int error,
* %false - we are done with this request
* %true - still buffers pending for this request
**/
-bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
+bool blk_end_request(struct request *rq, blk_status_t error,
+ unsigned int nr_bytes)
{
+ WARN_ON_ONCE(rq->q->mq_ops);
return blk_end_bidi_request(rq, error, nr_bytes, 0);
}
EXPORT_SYMBOL(blk_end_request);
@@ -2831,12 +2945,12 @@ EXPORT_SYMBOL(blk_end_request);
/**
* blk_end_request_all - Helper function for drives to finish the request.
* @rq: the request to finish
- * @error: %0 for success, < %0 for error
+ * @error: block status code
*
* Description:
* Completely finish @rq.
*/
-void blk_end_request_all(struct request *rq, int error)
+void blk_end_request_all(struct request *rq, blk_status_t error)
{
bool pending;
unsigned int bidi_bytes = 0;
@@ -2852,7 +2966,7 @@ EXPORT_SYMBOL(blk_end_request_all);
/**
* __blk_end_request - Helper function for drivers to complete the request.
* @rq: the request being processed
- * @error: %0 for success, < %0 for error
+ * @error: block status code
* @nr_bytes: number of bytes to complete
*
* Description:
@@ -2862,8 +2976,12 @@ EXPORT_SYMBOL(blk_end_request_all);
* %false - we are done with this request
* %true - still buffers pending for this request
**/
-bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
+bool __blk_end_request(struct request *rq, blk_status_t error,
+ unsigned int nr_bytes)
{
+ lockdep_assert_held(rq->q->queue_lock);
+ WARN_ON_ONCE(rq->q->mq_ops);
+
return __blk_end_bidi_request(rq, error, nr_bytes, 0);
}
EXPORT_SYMBOL(__blk_end_request);
@@ -2871,16 +2989,19 @@ EXPORT_SYMBOL(__blk_end_request);
/**
* __blk_end_request_all - Helper function for drives to finish the request.
* @rq: the request to finish
- * @error: %0 for success, < %0 for error
+ * @error: block status code
*
* Description:
* Completely finish @rq. Must be called with queue lock held.
*/
-void __blk_end_request_all(struct request *rq, int error)
+void __blk_end_request_all(struct request *rq, blk_status_t error)
{
bool pending;
unsigned int bidi_bytes = 0;
+ lockdep_assert_held(rq->q->queue_lock);
+ WARN_ON_ONCE(rq->q->mq_ops);
+
if (unlikely(blk_bidi_rq(rq)))
bidi_bytes = blk_rq_bytes(rq->next_rq);
@@ -2892,7 +3013,7 @@ EXPORT_SYMBOL(__blk_end_request_all);
/**
* __blk_end_request_cur - Helper function to finish the current request chunk.
* @rq: the request to finish the current chunk for
- * @error: %0 for success, < %0 for error
+ * @error: block status code
*
* Description:
* Complete the current consecutively mapped chunk from @rq. Must
@@ -2902,7 +3023,7 @@ EXPORT_SYMBOL(__blk_end_request_all);
* %false - we are done with this request
* %true - still buffers pending for this request
*/
-bool __blk_end_request_cur(struct request *rq, int error)
+bool __blk_end_request_cur(struct request *rq, blk_status_t error)
{
return __blk_end_request(rq, error, blk_rq_cur_bytes(rq));
}
@@ -3145,6 +3266,8 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth,
bool from_schedule)
__releases(q->queue_lock)
{
+ lockdep_assert_held(q->queue_lock);
+
trace_block_unplug(q, depth, !from_schedule);
if (from_schedule)
@@ -3243,7 +3366,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
* Short-circuit if @q is dead
*/
if (unlikely(blk_queue_dying(q))) {
- __blk_end_request_all(rq, -ENODEV);
+ __blk_end_request_all(rq, BLK_STS_IOERR);
continue;
}
diff --git a/block/blk-exec.c b/block/blk-exec.c
index a9451e3b8587..5c0f3dc446dc 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -16,7 +16,7 @@
* @rq: request to complete
* @error: end I/O status of the request
*/
-static void blk_end_sync_rq(struct request *rq, int error)
+static void blk_end_sync_rq(struct request *rq, blk_status_t error)
{
struct completion *waiting = rq->end_io_data;
@@ -69,7 +69,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
if (unlikely(blk_queue_dying(q))) {
rq->rq_flags |= RQF_QUIET;
- __blk_end_request_all(rq, -ENXIO);
+ __blk_end_request_all(rq, BLK_STS_IOERR);
spin_unlock_irq(q->queue_lock);
return;
}
diff --git a/block/blk-flush.c b/block/blk-flush.c
index c4e0880b54bb..ed5fe322abba 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -164,7 +164,7 @@ static bool blk_flush_queue_rq(struct request *rq, bool add_front)
*/
static bool blk_flush_complete_seq(struct request *rq,
struct blk_flush_queue *fq,
- unsigned int seq, int error)
+ unsigned int seq, blk_status_t error)
{
struct request_queue *q = rq->q;
struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
@@ -216,7 +216,7 @@ static bool blk_flush_complete_seq(struct request *rq,
return kicked | queued;
}
-static void flush_end_io(struct request *flush_rq, int error)
+static void flush_end_io(struct request *flush_rq, blk_status_t error)
{
struct request_queue *q = flush_rq->q;
struct list_head *running;
@@ -341,11 +341,13 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
return blk_flush_queue_rq(flush_rq, false);
}
-static void flush_data_end_io(struct request *rq, int error)
+static void flush_data_end_io(struct request *rq, blk_status_t error)
{
struct request_queue *q = rq->q;
struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
+ lockdep_assert_held(q->queue_lock);
+
/*
* Updating q->in_flight[] here for making this tag usable
* early. Because in blk_queue_start_tag(),
@@ -382,7 +384,7 @@ static void flush_data_end_io(struct request *rq, int error)
blk_run_queue_async(q);
}
-static void mq_flush_data_end_io(struct request *rq, int error)
+static void mq_flush_data_end_io(struct request *rq, blk_status_t error)
{
struct request_queue *q = rq->q;
struct blk_mq_hw_ctx *hctx;
@@ -411,9 +413,6 @@ static void mq_flush_data_end_io(struct request *rq, int error)
* or __blk_mq_run_hw_queue() to dispatch request.
* @rq is being submitted. Analyze what needs to be done and put it on the
* right queue.
- *
- * CONTEXT:
- * spin_lock_irq(q->queue_lock) in !mq case
*/
void blk_insert_flush(struct request *rq)
{
@@ -422,6 +421,9 @@ void blk_insert_flush(struct request *rq)
unsigned int policy = blk_flush_policy(fflags, rq);
struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx);
+ if (!q->mq_ops)
+ lockdep_assert_held(q->queue_lock);
+
/*
* @policy now records what operations need to be done. Adjust
* REQ_PREFLUSH and FUA for the driver.
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 0f891a9aff4d..feb30570eaf5 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -384,9 +384,9 @@ static struct kobj_type integrity_ktype = {
.sysfs_ops = &integrity_ops,
};
-static int blk_integrity_nop_fn(struct blk_integrity_iter *iter)
+static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter)
{
- return 0;
+ return BLK_STS_OK;
}
static const struct blk_integrity_profile nop_profile = {
diff --git a/block/blk-map.c b/block/blk-map.c
index 3b5cb863318f..2547016aa7aa 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -16,6 +16,8 @@
*/
int blk_rq_append_bio(struct request *rq, struct bio *bio)
{
+ blk_queue_bounce(rq->q, &bio);
+
if (!rq->bio) {
blk_rq_bio_prep(rq->q, rq, bio);
} else {
@@ -72,15 +74,13 @@ static int __blk_rq_map_user_iov(struct request *rq,
map_data->offset += bio->bi_iter.bi_size;
orig_bio = bio;
- blk_queue_bounce(q, &bio);
/*
* We link the bounce buffer in and could have to traverse it
* later so we have to get a ref to prevent it from being freed
*/
- bio_get(bio);
-
ret = blk_rq_append_bio(rq, bio);
+ bio_get(bio);
if (ret) {
bio_endio(bio);
__blk_rq_unmap_user(orig_bio);
@@ -249,7 +249,6 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
return ret;
}
- blk_queue_bounce(q, &rq->bio);
return 0;
}
EXPORT_SYMBOL(blk_rq_map_kern);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 3990ae406341..99038830fb42 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -108,31 +108,9 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
bool do_split = true;
struct bio *new = NULL;
const unsigned max_sectors = get_max_io_size(q, bio);
- unsigned bvecs = 0;
bio_for_each_segment(bv, bio, iter) {
/*
- * With arbitrary bio size, the incoming bio may be very
- * big. We have to split the bio into small bios so that
- * each holds at most BIO_MAX_PAGES bvecs because
- * bio_clone() can fail to allocate big bvecs.
- *
- * It should have been better to apply the limit per
- * request queue in which bio_clone() is involved,
- * instead of globally. The biggest blocker is the
- * bio_clone() in bio bounce.
- *
- * If bio is splitted by this reason, we should have
- * allowed to continue bios merging, but don't do
- * that now for making the change simple.
- *
- * TODO: deal with bio bounce's bio_clone() gracefully
- * and convert the global limit into per-queue limit.
- */
- if (bvecs++ >= BIO_MAX_PAGES)
- goto split;
-
- /*
* If the queue doesn't support SG gaps and adding this
* offset would create a gap, disallow it.
*/
@@ -202,8 +180,7 @@ split:
return do_split ? new : NULL;
}
-void blk_queue_split(struct request_queue *q, struct bio **bio,
- struct bio_set *bs)
+void blk_queue_split(struct request_queue *q, struct bio **bio)
{
struct bio *split, *res;
unsigned nsegs;
@@ -211,13 +188,13 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
switch (bio_op(*bio)) {
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
- split = blk_bio_discard_split(q, *bio, bs, &nsegs);
+ split = blk_bio_discard_split(q, *bio, q->bio_split, &nsegs);
break;
case REQ_OP_WRITE_ZEROES:
- split = blk_bio_write_zeroes_split(q, *bio, bs, &nsegs);
+ split = blk_bio_write_zeroes_split(q, *bio, q->bio_split, &nsegs);
break;
case REQ_OP_WRITE_SAME:
- split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
+ split = blk_bio_write_same_split(q, *bio, q->bio_split, &nsegs);
break;
default:
split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
@@ -671,6 +648,9 @@ static void blk_account_io_merge(struct request *req)
static struct request *attempt_merge(struct request_queue *q,
struct request *req, struct request *next)
{
+ if (!q->mq_ops)
+ lockdep_assert_held(q->queue_lock);
+
if (!rq_mergeable(req) || !rq_mergeable(next))
return NULL;
@@ -693,6 +673,13 @@ static struct request *attempt_merge(struct request_queue *q,
return NULL;
/*
+ * Don't allow merge of different write hints, or for a hint with
+ * non-hint IO.
+ */
+ if (req->write_hint != next->write_hint)
+ return NULL;
+
+ /*
* If we are allowed to merge, then append bio list
* from next to rq and release next. merge_requests_fn
* will have updated segment counts, update sector
@@ -811,6 +798,13 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
!blk_write_same_mergeable(rq->bio, bio))
return false;
+ /*
+ * Don't allow merge of different write hints, or for a hint with
+ * non-hint IO.
+ */
+ if (rq->write_hint != bio->bi_write_hint)
+ return false;
+
return true;
}
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 8e61e8640e17..4891f042a22f 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -14,10 +14,14 @@
#include "blk.h"
#include "blk-mq.h"
-static int cpu_to_queue_index(unsigned int nr_cpus, unsigned int nr_queues,
- const int cpu)
+static int cpu_to_queue_index(unsigned int nr_queues, const int cpu)
{
- return cpu * nr_queues / nr_cpus;
+ /*
+ * Non online CPU will be mapped to queue index 0.
+ */
+ if (!cpu_online(cpu))
+ return 0;
+ return cpu % nr_queues;
}
static int get_first_sibling(unsigned int cpu)
@@ -35,56 +39,26 @@ int blk_mq_map_queues(struct blk_mq_tag_set *set)
{
unsigned int *map = set->mq_map;
unsigned int nr_queues = set->nr_hw_queues;
- const struct cpumask *online_mask = cpu_online_mask;
- unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
- cpumask_var_t cpus;
-
- if (!alloc_cpumask_var(&cpus, GFP_ATOMIC))
- return -ENOMEM;
-
- cpumask_clear(cpus);
- nr_cpus = nr_uniq_cpus = 0;
- for_each_cpu(i, online_mask) {
- nr_cpus++;
- first_sibling = get_first_sibling(i);
- if (!cpumask_test_cpu(first_sibling, cpus))
- nr_uniq_cpus++;
- cpumask_set_cpu(i, cpus);
- }
-
- queue = 0;
- for_each_possible_cpu(i) {
- if (!cpumask_test_cpu(i, online_mask)) {
- map[i] = 0;
- continue;
- }
+ unsigned int cpu, first_sibling;
+ for_each_possible_cpu(cpu) {
/*
- * Easy case - we have equal or more hardware queues. Or
- * there are no thread siblings to take into account. Do
- * 1:1 if enough, or sequential mapping if less.
+ * First do sequential mapping between CPUs and queues.
+ * In case we still have CPUs to map, and we have some number of
+ * threads per cores then map sibling threads to the same queue for
+ * performace optimizations.
*/
- if (nr_queues >= nr_cpus || nr_cpus == nr_uniq_cpus) {
- map[i] = cpu_to_queue_index(nr_cpus, nr_queues, queue);
- queue++;
- continue;
+ if (cpu < nr_queues) {
+ map[cpu] = cpu_to_queue_index(nr_queues, cpu);
+ } else {
+ first_sibling = get_first_sibling(cpu);
+ if (first_sibling == cpu)
+ map[cpu] = cpu_to_queue_index(nr_queues, cpu);
+ else
+ map[cpu] = map[first_sibling];
}
-
- /*
- * Less then nr_cpus queues, and we have some number of
- * threads per cores. Map sibling threads to the same
- * queue.
- */
- first_sibling = get_first_sibling(i);
- if (first_sibling == i) {
- map[i] = cpu_to_queue_index(nr_uniq_cpus, nr_queues,
- queue);
- queue++;
- } else
- map[i] = map[first_sibling];
}
- free_cpumask_var(cpus);
return 0;
}
EXPORT_SYMBOL_GPL(blk_mq_map_queues);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 803aed4d7221..9ebc2945f991 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -114,10 +114,12 @@ static ssize_t queue_state_write(void *data, const char __user *buf,
blk_mq_run_hw_queues(q, true);
} else if (strcmp(op, "start") == 0) {
blk_mq_start_stopped_hw_queues(q, true);
+ } else if (strcmp(op, "kick") == 0) {
+ blk_mq_kick_requeue_list(q);
} else {
pr_err("%s: unsupported operation '%s'\n", __func__, op);
inval:
- pr_err("%s: use either 'run' or 'start'\n", __func__);
+ pr_err("%s: use 'run', 'start' or 'kick'\n", __func__);
return -EINVAL;
}
return count;
@@ -133,6 +135,29 @@ static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
}
}
+static int queue_write_hint_show(void *data, struct seq_file *m)
+{
+ struct request_queue *q = data;
+ int i;
+
+ for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
+ seq_printf(m, "hint%d: %llu\n", i, q->write_hints[i]);
+
+ return 0;
+}
+
+static ssize_t queue_write_hint_store(void *data, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct request_queue *q = data;
+ int i;
+
+ for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
+ q->write_hints[i] = 0;
+
+ return count;
+}
+
static int queue_poll_stat_show(void *data, struct seq_file *m)
{
struct request_queue *q = data;
@@ -267,6 +292,14 @@ static const char *const rqf_name[] = {
};
#undef RQF_NAME
+#define RQAF_NAME(name) [REQ_ATOM_##name] = #name
+static const char *const rqaf_name[] = {
+ RQAF_NAME(COMPLETE),
+ RQAF_NAME(STARTED),
+ RQAF_NAME(POLL_SLEPT),
+};
+#undef RQAF_NAME
+
int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
{
const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
@@ -283,6 +316,8 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
seq_puts(m, ", .rq_flags=");
blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name,
ARRAY_SIZE(rqf_name));
+ seq_puts(m, ", .atomic_flags=");
+ blk_flags_show(m, rq->atomic_flags, rqaf_name, ARRAY_SIZE(rqaf_name));
seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag,
rq->internal_tag);
if (mq_ops->show_rq)
@@ -298,6 +333,37 @@ int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
}
EXPORT_SYMBOL_GPL(blk_mq_debugfs_rq_show);
+static void *queue_requeue_list_start(struct seq_file *m, loff_t *pos)
+ __acquires(&q->requeue_lock)
+{
+ struct request_queue *q = m->private;
+
+ spin_lock_irq(&q->requeue_lock);
+ return seq_list_start(&q->requeue_list, *pos);
+}
+
+static void *queue_requeue_list_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct request_queue *q = m->private;
+
+ return seq_list_next(v, &q->requeue_list, pos);
+}
+
+static void queue_requeue_list_stop(struct seq_file *m, void *v)
+ __releases(&q->requeue_lock)
+{
+ struct request_queue *q = m->private;
+
+ spin_unlock_irq(&q->requeue_lock);
+}
+
+static const struct seq_operations queue_requeue_list_seq_ops = {
+ .start = queue_requeue_list_start,
+ .next = queue_requeue_list_next,
+ .stop = queue_requeue_list_stop,
+ .show = blk_mq_debugfs_rq_show,
+};
+
static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos)
__acquires(&hctx->lock)
{
@@ -329,6 +395,36 @@ static const struct seq_operations hctx_dispatch_seq_ops = {
.show = blk_mq_debugfs_rq_show,
};
+struct show_busy_params {
+ struct seq_file *m;
+ struct blk_mq_hw_ctx *hctx;
+};
+
+/*
+ * Note: the state of a request may change while this function is in progress,
+ * e.g. due to a concurrent blk_mq_finish_request() call.
+ */
+static void hctx_show_busy_rq(struct request *rq, void *data, bool reserved)
+{
+ const struct show_busy_params *params = data;
+
+ if (blk_mq_map_queue(rq->q, rq->mq_ctx->cpu) == params->hctx &&
+ test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
+ __blk_mq_debugfs_rq_show(params->m,
+ list_entry_rq(&rq->queuelist));
+}
+
+static int hctx_busy_show(void *data, struct seq_file *m)
+{
+ struct blk_mq_hw_ctx *hctx = data;
+ struct show_busy_params params = { .m = m, .hctx = hctx };
+
+ blk_mq_tagset_busy_iter(hctx->queue->tag_set, hctx_show_busy_rq,
+ &params);
+
+ return 0;
+}
+
static int hctx_ctx_map_show(void *data, struct seq_file *m)
{
struct blk_mq_hw_ctx *hctx = data;
@@ -655,7 +751,9 @@ const struct file_operations blk_mq_debugfs_fops = {
static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
{"poll_stat", 0400, queue_poll_stat_show},
+ {"requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops},
{"state", 0600, queue_state_show, queue_state_write},
+ {"write_hints", 0600, queue_write_hint_show, queue_write_hint_store},
{},
};
@@ -663,6 +761,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
{"state", 0400, hctx_state_show},
{"flags", 0400, hctx_flags_show},
{"dispatch", 0400, .seq_ops = &hctx_dispatch_seq_ops},
+ {"busy", 0400, hctx_busy_show},
{"ctx_map", 0400, hctx_ctx_map_show},
{"tags", 0400, hctx_tags_show},
{"tags_bitmap", 0400, hctx_tags_bitmap_show},
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 1f5b692526ae..7f0dc48ffb40 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -31,11 +31,10 @@ void blk_mq_sched_free_hctx_data(struct request_queue *q,
}
EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);
-static void __blk_mq_sched_assign_ioc(struct request_queue *q,
- struct request *rq,
- struct bio *bio,
- struct io_context *ioc)
+void blk_mq_sched_assign_ioc(struct request *rq, struct bio *bio)
{
+ struct request_queue *q = rq->q;
+ struct io_context *ioc = rq_ioc(bio);
struct io_cq *icq;
spin_lock_irq(q->queue_lock);
@@ -47,90 +46,47 @@ static void __blk_mq_sched_assign_ioc(struct request_queue *q,
if (!icq)
return;
}
-
+ get_io_context(icq->ioc);
rq->elv.icq = icq;
- if (!blk_mq_sched_get_rq_priv(q, rq, bio)) {
- rq->rq_flags |= RQF_ELVPRIV;
- get_io_context(icq->ioc);
- return;
- }
-
- rq->elv.icq = NULL;
}
-static void blk_mq_sched_assign_ioc(struct request_queue *q,
- struct request *rq, struct bio *bio)
+/*
+ * Mark a hardware queue as needing a restart. For shared queues, maintain
+ * a count of how many hardware queues are marked for restart.
+ */
+static void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx)
{
- struct io_context *ioc;
+ if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+ return;
+
+ if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
+ struct request_queue *q = hctx->queue;
- ioc = rq_ioc(bio);
- if (ioc)
- __blk_mq_sched_assign_ioc(q, rq, bio, ioc);
+ if (!test_and_set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+ atomic_inc(&q->shared_hctx_restart);
+ } else
+ set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
}
-struct request *blk_mq_sched_get_request(struct request_queue *q,
- struct bio *bio,
- unsigned int op,
- struct blk_mq_alloc_data *data)
+static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
{
- struct elevator_queue *e = q->elevator;
- struct request *rq;
-
- blk_queue_enter_live(q);
- data->q = q;
- if (likely(!data->ctx))
- data->ctx = blk_mq_get_ctx(q);
- if (likely(!data->hctx))
- data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
-
- if (e) {
- data->flags |= BLK_MQ_REQ_INTERNAL;
-
- /*
- * Flush requests are special and go directly to the
- * dispatch list.
- */
- if (!op_is_flush(op) && e->type->ops.mq.get_request) {
- rq = e->type->ops.mq.get_request(q, op, data);
- if (rq)
- rq->rq_flags |= RQF_QUEUED;
- } else
- rq = __blk_mq_alloc_request(data, op);
- } else {
- rq = __blk_mq_alloc_request(data, op);
- }
-
- if (rq) {
- if (!op_is_flush(op)) {
- rq->elv.icq = NULL;
- if (e && e->type->icq_cache)
- blk_mq_sched_assign_ioc(q, rq, bio);
- }
- data->hctx->queued++;
- return rq;
- }
+ if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+ return false;
- blk_queue_exit(q);
- return NULL;
-}
+ if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
+ struct request_queue *q = hctx->queue;
-void blk_mq_sched_put_request(struct request *rq)
-{
- struct request_queue *q = rq->q;
- struct elevator_queue *e = q->elevator;
+ if (test_and_clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+ atomic_dec(&q->shared_hctx_restart);
+ } else
+ clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
- if (rq->rq_flags & RQF_ELVPRIV) {
- blk_mq_sched_put_rq_priv(rq->q, rq);
- if (rq->elv.icq) {
- put_io_context(rq->elv.icq->ioc);
- rq->elv.icq = NULL;
- }
+ if (blk_mq_hctx_has_pending(hctx)) {
+ blk_mq_run_hw_queue(hctx, true);
+ return true;
}
- if ((rq->rq_flags & RQF_QUEUED) && e && e->type->ops.mq.put_request)
- e->type->ops.mq.put_request(rq);
- else
- blk_mq_finish_request(rq);
+ return false;
}
void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
@@ -141,7 +97,8 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
bool did_work = false;
LIST_HEAD(rq_list);
- if (unlikely(blk_mq_hctx_stopped(hctx)))
+ /* RCU or SRCU read lock is needed before checking quiesced flag */
+ if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
return;
hctx->run++;
@@ -221,19 +178,73 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
}
EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
+/*
+ * Reverse check our software queue for entries that we could potentially
+ * merge with. Currently includes a hand-wavy stop count of 8, to not spend
+ * too much time checking for merges.
+ */
+static bool blk_mq_attempt_merge(struct request_queue *q,
+ struct blk_mq_ctx *ctx, struct bio *bio)
+{
+ struct request *rq;
+ int checked = 8;
+
+ lockdep_assert_held(&ctx->lock);
+
+ list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
+ bool merged = false;
+
+ if (!checked--)
+ break;
+
+ if (!blk_rq_merge_ok(rq, bio))
+ continue;
+
+ switch (blk_try_merge(rq, bio)) {
+ case ELEVATOR_BACK_MERGE:
+ if (blk_mq_sched_allow_merge(q, rq, bio))
+ merged = bio_attempt_back_merge(q, rq, bio);
+ break;
+ case ELEVATOR_FRONT_MERGE:
+ if (blk_mq_sched_allow_merge(q, rq, bio))
+ merged = bio_attempt_front_merge(q, rq, bio);
+ break;
+ case ELEVATOR_DISCARD_MERGE:
+ merged = bio_attempt_discard_merge(q, rq, bio);
+ break;
+ default:
+ continue;
+ }
+
+ if (merged)
+ ctx->rq_merged++;
+ return merged;
+ }
+
+ return false;
+}
+
bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
{
struct elevator_queue *e = q->elevator;
+ struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
+ struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+ bool ret = false;
- if (e->type->ops.mq.bio_merge) {
- struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
- struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
-
+ if (e && e->type->ops.mq.bio_merge) {
blk_mq_put_ctx(ctx);
return e->type->ops.mq.bio_merge(hctx, bio);
}
- return false;
+ if (hctx->flags & BLK_MQ_F_SHOULD_MERGE) {
+ /* default per sw-queue merge */
+ spin_lock(&ctx->lock);
+ ret = blk_mq_attempt_merge(q, ctx, bio);
+ spin_unlock(&ctx->lock);
+ }
+
+ blk_mq_put_ctx(ctx);
+ return ret;
}
bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq)
@@ -266,18 +277,6 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
return true;
}
-static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
-{
- if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
- clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
- if (blk_mq_hctx_has_pending(hctx)) {
- blk_mq_run_hw_queue(hctx, true);
- return true;
- }
- }
- return false;
-}
-
/**
* list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list
* @pos: loop cursor.
@@ -309,6 +308,13 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
unsigned int i, j;
if (set->flags & BLK_MQ_F_TAG_SHARED) {
+ /*
+ * If this is 0, then we know that no hardware queues
+ * have RESTART marked. We're done.
+ */
+ if (!atomic_read(&queue->shared_hctx_restart))
+ return;
+
rcu_read_lock();
list_for_each_entry_rcu_rr(q, queue, &set->tag_list,
tag_set_list) {
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index edafb5383b7b..9267d0b7c197 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -7,8 +7,7 @@
void blk_mq_sched_free_hctx_data(struct request_queue *q,
void (*exit)(struct blk_mq_hw_ctx *));
-struct request *blk_mq_sched_get_request(struct request_queue *q, struct bio *bio, unsigned int op, struct blk_mq_alloc_data *data);
-void blk_mq_sched_put_request(struct request *rq);
+void blk_mq_sched_assign_ioc(struct request *rq, struct bio *bio);
void blk_mq_sched_request_inserted(struct request *rq);
bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
@@ -38,35 +37,12 @@ int blk_mq_sched_init(struct request_queue *q);
static inline bool
blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
{
- struct elevator_queue *e = q->elevator;
-
- if (!e || blk_queue_nomerges(q) || !bio_mergeable(bio))
+ if (blk_queue_nomerges(q) || !bio_mergeable(bio))
return false;
return __blk_mq_sched_bio_merge(q, bio);
}
-static inline int blk_mq_sched_get_rq_priv(struct request_queue *q,
- struct request *rq,
- struct bio *bio)
-{
- struct elevator_queue *e = q->elevator;
-
- if (e && e->type->ops.mq.get_rq_priv)
- return e->type->ops.mq.get_rq_priv(q, rq, bio);
-
- return 0;
-}
-
-static inline void blk_mq_sched_put_rq_priv(struct request_queue *q,
- struct request *rq)
-{
- struct elevator_queue *e = q->elevator;
-
- if (e && e->type->ops.mq.put_rq_priv)
- e->type->ops.mq.put_rq_priv(q, rq);
-}
-
static inline bool
blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
struct bio *bio)
@@ -115,15 +91,6 @@ static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx)
return false;
}
-/*
- * Mark a hardware queue as needing a restart.
- */
-static inline void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx)
-{
- if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
- set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
-}
-
static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
{
return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a69ad122ed66..6cef42f419a5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -37,12 +37,8 @@
#include "blk-wbt.h"
#include "blk-mq-sched.h"
-static DEFINE_MUTEX(all_q_mutex);
-static LIST_HEAD(all_q_list);
-
static void blk_mq_poll_stats_start(struct request_queue *q);
static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
-static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync);
static int blk_mq_poll_stats_bkt(const struct request *rq)
{
@@ -154,13 +150,28 @@ void blk_mq_unfreeze_queue(struct request_queue *q)
}
EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
+/*
+ * FIXME: replace the scsi_internal_device_*block_nowait() calls in the
+ * mpt3sas driver such that this function can be removed.
+ */
+void blk_mq_quiesce_queue_nowait(struct request_queue *q)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ queue_flag_set(QUEUE_FLAG_QUIESCED, q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
+
/**
- * blk_mq_quiesce_queue() - wait until all ongoing queue_rq calls have finished
+ * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished
* @q: request queue.
*
* Note: this function does not prevent that the struct request end_io()
- * callback function is invoked. Additionally, it is not prevented that
- * new queue_rq() calls occur unless the queue has been stopped first.
+ * callback function is invoked. Once this function is returned, we make
+ * sure no dispatch can happen until the queue is unquiesced via
+ * blk_mq_unquiesce_queue().
*/
void blk_mq_quiesce_queue(struct request_queue *q)
{
@@ -168,11 +179,11 @@ void blk_mq_quiesce_queue(struct request_queue *q)
unsigned int i;
bool rcu = false;
- __blk_mq_stop_hw_queues(q, true);
+ blk_mq_quiesce_queue_nowait(q);
queue_for_each_hw_ctx(q, hctx, i) {
if (hctx->flags & BLK_MQ_F_BLOCKING)
- synchronize_srcu(&hctx->queue_rq_srcu);
+ synchronize_srcu(hctx->queue_rq_srcu);
else
rcu = true;
}
@@ -181,6 +192,26 @@ void blk_mq_quiesce_queue(struct request_queue *q)
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
+/*
+ * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue()
+ * @q: request queue.
+ *
+ * This function recovers queue into the state before quiescing
+ * which is done by blk_mq_quiesce_queue.
+ */
+void blk_mq_unquiesce_queue(struct request_queue *q)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+
+ /* dispatch requests which are inserted during quiescing */
+ blk_mq_run_hw_queues(q, true);
+}
+EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
+
void blk_mq_wake_waiters(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
@@ -204,15 +235,33 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
}
EXPORT_SYMBOL(blk_mq_can_queue);
-void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
- struct request *rq, unsigned int op)
+static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
+ unsigned int tag, unsigned int op)
{
+ struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+ struct request *rq = tags->static_rqs[tag];
+
+ rq->rq_flags = 0;
+
+ if (data->flags & BLK_MQ_REQ_INTERNAL) {
+ rq->tag = -1;
+ rq->internal_tag = tag;
+ } else {
+ if (blk_mq_tag_busy(data->hctx)) {
+ rq->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;
+ }
+
INIT_LIST_HEAD(&rq->queuelist);
/* csd/requeue_work/fifo_time is initialized before use */
- rq->q = q;
- rq->mq_ctx = ctx;
+ rq->q = data->q;
+ rq->mq_ctx = data->ctx;
rq->cmd_flags = op;
- if (blk_queue_io_stat(q))
+ if (blk_queue_io_stat(data->q))
rq->rq_flags |= RQF_IO_STAT;
/* do not touch atomic flags, it needs atomic ops against the timer */
rq->cpu = -1;
@@ -241,44 +290,60 @@ void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
rq->end_io_data = NULL;
rq->next_rq = NULL;
- ctx->rq_dispatched[op_is_sync(op)]++;
+ data->ctx->rq_dispatched[op_is_sync(op)]++;
+ return rq;
}
-EXPORT_SYMBOL_GPL(blk_mq_rq_ctx_init);
-struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
- unsigned int op)
+static struct request *blk_mq_get_request(struct request_queue *q,
+ struct bio *bio, unsigned int op,
+ struct blk_mq_alloc_data *data)
{
+ struct elevator_queue *e = q->elevator;
struct request *rq;
unsigned int tag;
- tag = blk_mq_get_tag(data);
- if (tag != BLK_MQ_TAG_FAIL) {
- struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+ blk_queue_enter_live(q);
+ data->q = q;
+ if (likely(!data->ctx))
+ data->ctx = blk_mq_get_ctx(q);
+ if (likely(!data->hctx))
+ data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
+ if (op & REQ_NOWAIT)
+ data->flags |= BLK_MQ_REQ_NOWAIT;
- rq = tags->static_rqs[tag];
+ if (e) {
+ data->flags |= BLK_MQ_REQ_INTERNAL;
- if (data->flags & BLK_MQ_REQ_INTERNAL) {
- rq->tag = -1;
- rq->internal_tag = tag;
- } else {
- if (blk_mq_tag_busy(data->hctx)) {
- rq->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;
- }
+ /*
+ * Flush requests are special and go directly to the
+ * dispatch list.
+ */
+ if (!op_is_flush(op) && e->type->ops.mq.limit_depth)
+ e->type->ops.mq.limit_depth(op, data);
+ }
- blk_mq_rq_ctx_init(data->q, data->ctx, rq, op);
- return rq;
+ tag = blk_mq_get_tag(data);
+ if (tag == BLK_MQ_TAG_FAIL) {
+ blk_queue_exit(q);
+ return NULL;
}
- 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;
+ }
+ }
+ data->hctx->queued++;
+ return rq;
}
-EXPORT_SYMBOL_GPL(__blk_mq_alloc_request);
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
+struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
unsigned int flags)
{
struct blk_mq_alloc_data alloc_data = { .flags = flags };
@@ -289,7 +354,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
if (ret)
return ERR_PTR(ret);
- rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
+ rq = blk_mq_get_request(q, NULL, op, &alloc_data);
blk_mq_put_ctx(alloc_data.ctx);
blk_queue_exit(q);
@@ -304,8 +369,8 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
}
EXPORT_SYMBOL(blk_mq_alloc_request);
-struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
- unsigned int flags, unsigned int hctx_idx)
+struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
+ unsigned int op, unsigned int flags, unsigned int hctx_idx)
{
struct blk_mq_alloc_data alloc_data = { .flags = flags };
struct request *rq;
@@ -340,7 +405,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
cpu = cpumask_first(alloc_data.hctx->cpumask);
alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
- rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
+ rq = blk_mq_get_request(q, NULL, op, &alloc_data);
blk_queue_exit(q);
@@ -351,17 +416,28 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
-void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
- struct request *rq)
+void blk_mq_free_request(struct request *rq)
{
- const int sched_tag = rq->internal_tag;
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);
+ const int sched_tag = rq->internal_tag;
+
+ if (rq->rq_flags & RQF_ELVPRIV) {
+ if (e && e->type->ops.mq.finish_request)
+ e->type->ops.mq.finish_request(rq);
+ if (rq->elv.icq) {
+ put_io_context(rq->elv.icq->ioc);
+ rq->elv.icq = NULL;
+ }
+ }
+ ctx->rq_completed[rq_is_sync(rq)]++;
if (rq->rq_flags & RQF_MQ_INFLIGHT)
atomic_dec(&hctx->nr_active);
wbt_done(q->rq_wb, &rq->issue_stat);
- rq->rq_flags = 0;
clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
@@ -372,29 +448,9 @@ void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
blk_mq_sched_restart(hctx);
blk_queue_exit(q);
}
-
-static void blk_mq_finish_hctx_request(struct blk_mq_hw_ctx *hctx,
- struct request *rq)
-{
- struct blk_mq_ctx *ctx = rq->mq_ctx;
-
- ctx->rq_completed[rq_is_sync(rq)]++;
- __blk_mq_finish_request(hctx, ctx, rq);
-}
-
-void blk_mq_finish_request(struct request *rq)
-{
- blk_mq_finish_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
-}
-EXPORT_SYMBOL_GPL(blk_mq_finish_request);
-
-void blk_mq_free_request(struct request *rq)
-{
- blk_mq_sched_put_request(rq);
-}
EXPORT_SYMBOL_GPL(blk_mq_free_request);
-inline void __blk_mq_end_request(struct request *rq, int error)
+inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
{
blk_account_io_done(rq);
@@ -409,7 +465,7 @@ inline void __blk_mq_end_request(struct request *rq, int error)
}
EXPORT_SYMBOL(__blk_mq_end_request);
-void blk_mq_end_request(struct request *rq, int error)
+void blk_mq_end_request(struct request *rq, blk_status_t error)
{
if (blk_update_request(rq, error, blk_rq_bytes(rq)))
BUG();
@@ -628,25 +684,6 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q,
}
EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
-void blk_mq_abort_requeue_list(struct request_queue *q)
-{
- unsigned long flags;
- LIST_HEAD(rq_list);
-
- spin_lock_irqsave(&q->requeue_lock, flags);
- list_splice_init(&q->requeue_list, &rq_list);
- spin_unlock_irqrestore(&q->requeue_lock, flags);
-
- while (!list_empty(&rq_list)) {
- struct request *rq;
-
- rq = list_first_entry(&rq_list, struct request, queuelist);
- list_del_init(&rq->queuelist);
- blk_mq_end_request(rq, -EIO);
- }
-}
-EXPORT_SYMBOL(blk_mq_abort_requeue_list);
-
struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
{
if (tag < tags->nr_tags) {
@@ -772,50 +809,6 @@ static void blk_mq_timeout_work(struct work_struct *work)
blk_queue_exit(q);
}
-/*
- * Reverse check our software queue for entries that we could potentially
- * merge with. Currently includes a hand-wavy stop count of 8, to not spend
- * too much time checking for merges.
- */
-static bool blk_mq_attempt_merge(struct request_queue *q,
- struct blk_mq_ctx *ctx, struct bio *bio)
-{
- struct request *rq;
- int checked = 8;
-
- list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
- bool merged = false;
-
- if (!checked--)
- break;
-
- if (!blk_rq_merge_ok(rq, bio))
- continue;
-
- switch (blk_try_merge(rq, bio)) {
- case ELEVATOR_BACK_MERGE:
- if (blk_mq_sched_allow_merge(q, rq, bio))
- merged = bio_attempt_back_merge(q, rq, bio);
- break;
- case ELEVATOR_FRONT_MERGE:
- if (blk_mq_sched_allow_merge(q, rq, bio))
- merged = bio_attempt_front_merge(q, rq, bio);
- break;
- case ELEVATOR_DISCARD_MERGE:
- merged = bio_attempt_discard_merge(q, rq, bio);
- break;
- default:
- continue;
- }
-
- if (merged)
- ctx->rq_merged++;
- return merged;
- }
-
- return false;
-}
-
struct flush_busy_ctx_data {
struct blk_mq_hw_ctx *hctx;
struct list_head *list;
@@ -945,14 +938,14 @@ static bool reorder_tags_to_front(struct list_head *list)
return first != NULL;
}
-static int blk_mq_dispatch_wake(wait_queue_t *wait, unsigned mode, int flags,
+static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
void *key)
{
struct blk_mq_hw_ctx *hctx;
hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
- list_del(&wait->task_list);
+ list_del(&wait->entry);
clear_bit_unlock(BLK_MQ_S_TAG_WAITING, &hctx->state);
blk_mq_run_hw_queue(hctx, true);
return 1;
@@ -987,7 +980,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
{
struct blk_mq_hw_ctx *hctx;
struct request *rq;
- int errors, queued, ret = BLK_MQ_RQ_QUEUE_OK;
+ int errors, queued;
if (list_empty(list))
return false;
@@ -998,6 +991,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
errors = queued = 0;
do {
struct blk_mq_queue_data bd;
+ blk_status_t ret;
rq = list_first_entry(list, struct request, queuelist);
if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
@@ -1038,25 +1032,20 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
}
ret = q->mq_ops->queue_rq(hctx, &bd);
- switch (ret) {
- case BLK_MQ_RQ_QUEUE_OK:
- queued++;
- break;
- case BLK_MQ_RQ_QUEUE_BUSY:
+ if (ret == BLK_STS_RESOURCE) {
blk_mq_put_driver_tag_hctx(hctx, rq);
list_add(&rq->queuelist, list);
__blk_mq_requeue_request(rq);
break;
- default:
- pr_err("blk-mq: bad return on queue: %d\n", ret);
- case BLK_MQ_RQ_QUEUE_ERROR:
+ }
+
+ if (unlikely(ret != BLK_STS_OK)) {
errors++;
- blk_mq_end_request(rq, -EIO);
- break;
+ blk_mq_end_request(rq, BLK_STS_IOERR);
+ continue;
}
- if (ret == BLK_MQ_RQ_QUEUE_BUSY)
- break;
+ queued++;
} while (!list_empty(list));
hctx->dispatched[queued_to_index(queued)]++;
@@ -1094,7 +1083,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
* - blk_mq_run_hw_queue() checks whether or not a queue has
* been stopped before rerunning a queue.
* - Some but not all block drivers stop a queue before
- * returning BLK_MQ_RQ_QUEUE_BUSY. Two exceptions are scsi-mq
+ * returning BLK_STS_RESOURCE. Two exceptions are scsi-mq
* and dm-rq.
*/
if (!blk_mq_sched_needs_restart(hctx) &&
@@ -1119,9 +1108,9 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
} else {
might_sleep();
- srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
+ srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);
blk_mq_sched_dispatch_requests(hctx);
- srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
+ srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);
}
}
@@ -1153,8 +1142,10 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
unsigned long msecs)
{
- if (unlikely(blk_mq_hctx_stopped(hctx) ||
- !blk_mq_hw_queue_mapped(hctx)))
+ if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))
+ return;
+
+ if (unlikely(blk_mq_hctx_stopped(hctx)))
return;
if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
@@ -1220,34 +1211,39 @@ bool blk_mq_queue_stopped(struct request_queue *q)
}
EXPORT_SYMBOL(blk_mq_queue_stopped);
-static void __blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx, bool sync)
+/*
+ * This function is often used for pausing .queue_rq() by driver when
+ * there isn't enough resource or some conditions aren't satisfied, and
+ * BLK_MQ_RQ_QUEUE_BUSY is usually returned.
+ *
+ * We do not guarantee that dispatch can be drained or blocked
+ * after blk_mq_stop_hw_queue() returns. Please use
+ * blk_mq_quiesce_queue() for that requirement.
+ */
+void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
{
- if (sync)
- cancel_delayed_work_sync(&hctx->run_work);
- else
- cancel_delayed_work(&hctx->run_work);
+ cancel_delayed_work(&hctx->run_work);
set_bit(BLK_MQ_S_STOPPED, &hctx->state);
}
-
-void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
-{
- __blk_mq_stop_hw_queue(hctx, false);
-}
EXPORT_SYMBOL(blk_mq_stop_hw_queue);
-static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync)
+/*
+ * This function is often used for pausing .queue_rq() by driver when
+ * there isn't enough resource or some conditions aren't satisfied, and
+ * BLK_MQ_RQ_QUEUE_BUSY is usually returned.
+ *
+ * We do not guarantee that dispatch can be drained or blocked
+ * after blk_mq_stop_hw_queues() returns. Please use
+ * blk_mq_quiesce_queue() for that requirement.
+ */
+void blk_mq_stop_hw_queues(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
int i;
queue_for_each_hw_ctx(q, hctx, i)
- __blk_mq_stop_hw_queue(hctx, sync);
-}
-
-void blk_mq_stop_hw_queues(struct request_queue *q)
-{
- __blk_mq_stop_hw_queues(q, false);
+ blk_mq_stop_hw_queue(hctx);
}
EXPORT_SYMBOL(blk_mq_stop_hw_queues);
@@ -1314,7 +1310,7 @@ static void blk_mq_run_work_fn(struct work_struct *work)
void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
{
- if (unlikely(!blk_mq_hw_queue_mapped(hctx)))
+ if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))
return;
/*
@@ -1336,6 +1332,8 @@ static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
+ lockdep_assert_held(&ctx->lock);
+
trace_block_rq_insert(hctx->queue, rq);
if (at_head)
@@ -1349,6 +1347,8 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
+ lockdep_assert_held(&ctx->lock);
+
__blk_mq_insert_req_list(hctx, rq, at_head);
blk_mq_hctx_mark_pending(hctx, ctx);
}
@@ -1446,30 +1446,13 @@ static inline bool hctx_allow_merges(struct blk_mq_hw_ctx *hctx)
!blk_queue_nomerges(hctx->queue);
}
-static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx,
- struct blk_mq_ctx *ctx,
- struct request *rq, struct bio *bio)
+static inline void blk_mq_queue_io(struct blk_mq_hw_ctx *hctx,
+ struct blk_mq_ctx *ctx,
+ struct request *rq)
{
- if (!hctx_allow_merges(hctx) || !bio_mergeable(bio)) {
- blk_mq_bio_to_request(rq, bio);
- spin_lock(&ctx->lock);
-insert_rq:
- __blk_mq_insert_request(hctx, rq, false);
- spin_unlock(&ctx->lock);
- return false;
- } else {
- struct request_queue *q = hctx->queue;
-
- spin_lock(&ctx->lock);
- if (!blk_mq_attempt_merge(q, ctx, bio)) {
- blk_mq_bio_to_request(rq, bio);
- goto insert_rq;
- }
-
- spin_unlock(&ctx->lock);
- __blk_mq_finish_request(hctx, ctx, rq);
- return true;
- }
+ spin_lock(&ctx->lock);
+ __blk_mq_insert_request(hctx, rq, false);
+ spin_unlock(&ctx->lock);
}
static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
@@ -1480,22 +1463,29 @@ static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
}
-static void __blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
- bool may_sleep)
+static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+ struct request *rq,
+ blk_qc_t *cookie, bool may_sleep)
{
struct request_queue *q = rq->q;
struct blk_mq_queue_data bd = {
.rq = rq,
.last = true,
};
- struct blk_mq_hw_ctx *hctx;
blk_qc_t new_cookie;
- int ret;
+ blk_status_t ret;
+ bool run_queue = true;
+
+ /* RCU or SRCU read lock is needed before checking quiesced flag */
+ if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) {
+ run_queue = false;
+ goto insert;
+ }
if (q->elevator)
goto insert;
- if (!blk_mq_get_driver_tag(rq, &hctx, false))
+ if (!blk_mq_get_driver_tag(rq, NULL, false))
goto insert;
new_cookie = request_to_qc_t(hctx, rq);
@@ -1506,20 +1496,21 @@ static void __blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
* would have done
*/
ret = q->mq_ops->queue_rq(hctx, &bd);
- if (ret == BLK_MQ_RQ_QUEUE_OK) {
+ switch (ret) {
+ case BLK_STS_OK:
*cookie = new_cookie;
return;
- }
-
- if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
+ case BLK_STS_RESOURCE:
+ __blk_mq_requeue_request(rq);
+ goto insert;
+ default:
*cookie = BLK_QC_T_NONE;
- blk_mq_end_request(rq, -EIO);
+ blk_mq_end_request(rq, ret);
return;
}
- __blk_mq_requeue_request(rq);
insert:
- blk_mq_sched_insert_request(rq, false, true, false, may_sleep);
+ blk_mq_sched_insert_request(rq, false, run_queue, false, may_sleep);
}
static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
@@ -1527,16 +1518,16 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
{
if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
rcu_read_lock();
- __blk_mq_try_issue_directly(rq, cookie, false);
+ __blk_mq_try_issue_directly(hctx, rq, cookie, false);
rcu_read_unlock();
} else {
unsigned int srcu_idx;
might_sleep();
- srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
- __blk_mq_try_issue_directly(rq, cookie, true);
- srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
+ srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);
+ __blk_mq_try_issue_directly(hctx, rq, cookie, true);
+ srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);
}
}
@@ -1554,7 +1545,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_queue_bounce(q, &bio);
- blk_queue_split(q, &bio, q->bio_split);
+ blk_queue_split(q, &bio);
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
bio_io_error(bio);
@@ -1572,9 +1563,11 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
trace_block_getrq(q, bio, bio->bi_opf);
- rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
+ rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
if (unlikely(!rq)) {
__wbt_done(q->rq_wb, wb_acct);
+ if (bio->bi_opf & REQ_NOWAIT)
+ bio_wouldblock_error(bio);
return BLK_QC_T_NONE;
}
@@ -1638,9 +1631,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_mq_put_ctx(data.ctx);
- if (same_queue_rq)
+ if (same_queue_rq) {
+ data.hctx = blk_mq_map_queue(q,
+ same_queue_rq->mq_ctx->cpu);
blk_mq_try_issue_directly(data.hctx, same_queue_rq,
&cookie);
+ }
} else if (q->nr_hw_queues > 1 && is_sync) {
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
@@ -1649,11 +1645,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
blk_mq_sched_insert_request(rq, false, true, true, true);
- } else if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
+ } else {
blk_mq_put_ctx(data.ctx);
+ blk_mq_bio_to_request(rq, bio);
+ blk_mq_queue_io(data.hctx, data.ctx, rq);
blk_mq_run_hw_queue(data.hctx, true);
- } else
- blk_mq_put_ctx(data.ctx);
+ }
return cookie;
}
@@ -1876,7 +1873,7 @@ static void blk_mq_exit_hctx(struct request_queue *q,
set->ops->exit_hctx(hctx, hctx_idx);
if (hctx->flags & BLK_MQ_F_BLOCKING)
- cleanup_srcu_struct(&hctx->queue_rq_srcu);
+ cleanup_srcu_struct(hctx->queue_rq_srcu);
blk_mq_remove_cpuhp(hctx);
blk_free_flush_queue(hctx->fq);
@@ -1910,7 +1907,6 @@ static int blk_mq_init_hctx(struct request_queue *q,
spin_lock_init(&hctx->lock);
INIT_LIST_HEAD(&hctx->dispatch);
hctx->queue = q;
- hctx->queue_num = hctx_idx;
hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
@@ -1949,7 +1945,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
goto free_fq;
if (hctx->flags & BLK_MQ_F_BLOCKING)
- init_srcu_struct(&hctx->queue_rq_srcu);
+ init_srcu_struct(hctx->queue_rq_srcu);
blk_mq_debugfs_register_hctx(q, hctx);
@@ -1985,8 +1981,8 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
INIT_LIST_HEAD(&__ctx->rq_list);
__ctx->queue = q;
- /* If the cpu isn't online, the cpu is mapped to first hctx */
- if (!cpu_online(i))
+ /* If the cpu isn't present, the cpu is mapped to first hctx */
+ if (!cpu_present(i))
continue;
hctx = blk_mq_map_queue(q, i);
@@ -2029,8 +2025,7 @@ static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
}
}
-static void blk_mq_map_swqueue(struct request_queue *q,
- const struct cpumask *online_mask)
+static void blk_mq_map_swqueue(struct request_queue *q)
{
unsigned int i, hctx_idx;
struct blk_mq_hw_ctx *hctx;
@@ -2048,13 +2043,11 @@ static void blk_mq_map_swqueue(struct request_queue *q,
}
/*
- * Map software to hardware queues
+ * Map software to hardware queues.
+ *
+ * If the cpu isn't present, the cpu is mapped to first hctx.
*/
- for_each_possible_cpu(i) {
- /* If the cpu isn't online, the cpu is mapped to first hctx */
- if (!cpumask_test_cpu(i, online_mask))
- continue;
-
+ for_each_present_cpu(i) {
hctx_idx = q->mq_map[i];
/* unmapped hw queue can be remapped after CPU topo changed */
if (!set->tags[hctx_idx] &&
@@ -2113,20 +2106,30 @@ static void blk_mq_map_swqueue(struct request_queue *q,
}
}
+/*
+ * Caller needs to ensure that we're either frozen/quiesced, or that
+ * the queue isn't live yet.
+ */
static void queue_set_hctx_shared(struct request_queue *q, bool shared)
{
struct blk_mq_hw_ctx *hctx;
int i;
queue_for_each_hw_ctx(q, hctx, i) {
- if (shared)
+ if (shared) {
+ if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+ atomic_inc(&q->shared_hctx_restart);
hctx->flags |= BLK_MQ_F_TAG_SHARED;
- else
+ } else {
+ if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+ atomic_dec(&q->shared_hctx_restart);
hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
+ }
}
}
-static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set, bool shared)
+static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set,
+ bool shared)
{
struct request_queue *q;
@@ -2224,6 +2227,20 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
}
EXPORT_SYMBOL(blk_mq_init_queue);
+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, queue_rq_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 void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
struct request_queue *q)
{
@@ -2238,7 +2255,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
continue;
node = blk_mq_hw_queue_to_node(q->mq_map, i);
- hctxs[i] = kzalloc_node(sizeof(struct blk_mq_hw_ctx),
+ hctxs[i] = kzalloc_node(blk_mq_hw_ctx_size(set),
GFP_KERNEL, node);
if (!hctxs[i])
break;
@@ -2340,16 +2357,8 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
blk_queue_softirq_done(q, set->ops->complete);
blk_mq_init_cpu_queues(q, set->nr_hw_queues);
-
- get_online_cpus();
- mutex_lock(&all_q_mutex);
-
- list_add_tail(&q->all_q_node, &all_q_list);
blk_mq_add_queue_tag_set(set, q);
- blk_mq_map_swqueue(q, cpu_online_mask);
-
- mutex_unlock(&all_q_mutex);
- put_online_cpus();
+ blk_mq_map_swqueue(q);
if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
int ret;
@@ -2375,18 +2384,12 @@ void blk_mq_free_queue(struct request_queue *q)
{
struct blk_mq_tag_set *set = q->tag_set;
- mutex_lock(&all_q_mutex);
- list_del_init(&q->all_q_node);
- mutex_unlock(&all_q_mutex);
-
blk_mq_del_queue_tag_set(q);
-
blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
}
/* Basically redo blk_mq_init_queue with queue frozen */
-static void blk_mq_queue_reinit(struct request_queue *q,
- const struct cpumask *online_mask)
+static void blk_mq_queue_reinit(struct request_queue *q)
{
WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
@@ -2399,76 +2402,12 @@ static void blk_mq_queue_reinit(struct request_queue *q,
* involves free and re-allocate memory, worthy doing?)
*/
- blk_mq_map_swqueue(q, online_mask);
+ blk_mq_map_swqueue(q);
blk_mq_sysfs_register(q);
blk_mq_debugfs_register_hctxs(q);
}
-/*
- * New online cpumask which is going to be set in this hotplug event.
- * Declare this cpumasks as global as cpu-hotplug operation is invoked
- * one-by-one and dynamically allocating this could result in a failure.
- */
-static struct cpumask cpuhp_online_new;
-
-static void blk_mq_queue_reinit_work(void)
-{
- struct request_queue *q;
-
- mutex_lock(&all_q_mutex);
- /*
- * We need to freeze and reinit all existing queues. Freezing
- * involves synchronous wait for an RCU grace period and doing it
- * one by one may take a long time. Start freezing all queues in
- * one swoop and then wait for the completions so that freezing can
- * take place in parallel.
- */
- list_for_each_entry(q, &all_q_list, all_q_node)
- blk_freeze_queue_start(q);
- list_for_each_entry(q, &all_q_list, all_q_node)
- blk_mq_freeze_queue_wait(q);
-
- list_for_each_entry(q, &all_q_list, all_q_node)
- blk_mq_queue_reinit(q, &cpuhp_online_new);
-
- list_for_each_entry(q, &all_q_list, all_q_node)
- blk_mq_unfreeze_queue(q);
-
- mutex_unlock(&all_q_mutex);
-}
-
-static int blk_mq_queue_reinit_dead(unsigned int cpu)
-{
- cpumask_copy(&cpuhp_online_new, cpu_online_mask);
- blk_mq_queue_reinit_work();
- return 0;
-}
-
-/*
- * Before hotadded cpu starts handling requests, new mappings must be
- * established. Otherwise, these requests in hw queue might never be
- * dispatched.
- *
- * For example, there is a single hw queue (hctx) and two CPU queues (ctx0
- * for CPU0, and ctx1 for CPU1).
- *
- * Now CPU1 is just onlined and a request is inserted into ctx1->rq_list
- * and set bit0 in pending bitmap as ctx1->index_hw is still zero.
- *
- * And then while running hw queue, blk_mq_flush_busy_ctxs() finds bit0 is set
- * in pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
- * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list is
- * ignored.
- */
-static int blk_mq_queue_reinit_prepare(unsigned int cpu)
-{
- cpumask_copy(&cpuhp_online_new, cpu_online_mask);
- cpumask_set_cpu(cpu, &cpuhp_online_new);
- blk_mq_queue_reinit_work();
- return 0;
-}
-
static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
{
int i;
@@ -2660,7 +2599,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
return ret;
}
-void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
+static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
+ int nr_hw_queues)
{
struct request_queue *q;
@@ -2678,12 +2618,19 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
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, cpu_online_mask);
+ blk_mq_queue_reinit(q);
}
list_for_each_entry(q, &set->tag_list, tag_set_list)
blk_mq_unfreeze_queue(q);
}
+
+void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
+{
+ mutex_lock(&set->tag_list_lock);
+ __blk_mq_update_nr_hw_queues(set, nr_hw_queues);
+ mutex_unlock(&set->tag_list_lock);
+}
EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
/* Enable polling stats and return whether they were already enabled. */
@@ -2887,24 +2834,10 @@ bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
}
EXPORT_SYMBOL_GPL(blk_mq_poll);
-void blk_mq_disable_hotplug(void)
-{
- mutex_lock(&all_q_mutex);
-}
-
-void blk_mq_enable_hotplug(void)
-{
- mutex_unlock(&all_q_mutex);
-}
-
static int __init blk_mq_init(void)
{
cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
blk_mq_hctx_notify_dead);
-
- cpuhp_setup_state_nocalls(CPUHP_BLK_MQ_PREPARE, "block/mq:prepare",
- blk_mq_queue_reinit_prepare,
- blk_mq_queue_reinit_dead);
return 0;
}
subsys_initcall(blk_mq_init);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index cc67b48e3551..60b01c0309bc 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -56,11 +56,6 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
bool at_head);
void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
struct list_head *list);
-/*
- * CPU hotplug helpers
- */
-void blk_mq_enable_hotplug(void);
-void blk_mq_disable_hotplug(void);
/*
* CPU -> queue mappings
@@ -128,17 +123,6 @@ static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data
return data->hctx->tags;
}
-/*
- * Internal helpers for request allocation/init/free
- */
-void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
- struct request *rq, unsigned int op);
-void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
- struct request *rq);
-void blk_mq_finish_request(struct request *rq);
-struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
- unsigned int op);
-
static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
{
return test_bit(BLK_MQ_S_STOPPED, &hctx->state);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 4fa81ed383ca..be1f115b538b 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -172,11 +172,6 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
q->nr_batching = BLK_BATCH_REQ;
blk_set_default_limits(&q->limits);
-
- /*
- * by default assume old behaviour and bounce for any highmem page
- */
- blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
}
EXPORT_SYMBOL(blk_queue_make_request);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 504fee940052..27aceab1cc31 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -777,24 +777,25 @@ static void blk_free_queue_rcu(struct rcu_head *rcu_head)
}
/**
- * blk_release_queue: - release a &struct request_queue when it is no longer needed
- * @kobj: the kobj belonging to the request queue to be released
+ * __blk_release_queue - release a request queue when it is no longer needed
+ * @work: pointer to the release_work member of the request queue to be released
*
* Description:
- * blk_release_queue is the pair to blk_init_queue() or
- * blk_queue_make_request(). It should be called when a request queue is
- * being released; typically when a block device is being de-registered.
- * Currently, its primary task it to free all the &struct request
- * structures that were allocated to the queue and the queue itself.
+ * blk_release_queue is the counterpart of blk_init_queue(). It should be
+ * called when a request queue is being released; typically when a block
+ * device is being de-registered. Its primary task it to free the queue
+ * itself.
*
- * Note:
+ * Notes:
* The low level driver must have finished any outstanding requests first
* via blk_cleanup_queue().
- **/
-static void blk_release_queue(struct kobject *kobj)
+ *
+ * Although blk_release_queue() may be called with preemption disabled,
+ * __blk_release_queue() may sleep.
+ */
+static void __blk_release_queue(struct work_struct *work)
{
- struct request_queue *q =
- container_of(kobj, struct request_queue, kobj);
+ struct request_queue *q = container_of(work, typeof(*q), release_work);
if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
blk_stat_remove_callback(q, q->poll_cb);
@@ -809,7 +810,7 @@ static void blk_release_queue(struct kobject *kobj)
blk_free_queue_stats(q->stats);
- blk_exit_rl(&q->root_rl);
+ blk_exit_rl(q, &q->root_rl);
if (q->queue_tags)
__blk_queue_free_tags(q);
@@ -834,6 +835,15 @@ static void blk_release_queue(struct kobject *kobj)
call_rcu(&q->rcu_head, blk_free_queue_rcu);
}
+static void blk_release_queue(struct kobject *kobj)
+{
+ struct request_queue *q =
+ container_of(kobj, struct request_queue, kobj);
+
+ INIT_WORK(&q->release_work, __blk_release_queue);
+ schedule_work(&q->release_work);
+}
+
static const struct sysfs_ops queue_sysfs_ops = {
.show = queue_attr_show,
.store = queue_attr_store,
@@ -887,10 +897,10 @@ int blk_register_queue(struct gendisk *disk)
goto unlock;
}
- if (q->mq_ops)
+ if (q->mq_ops) {
__blk_mq_register_dev(dev, q);
-
- blk_mq_debugfs_register(q);
+ blk_mq_debugfs_register(q);
+ }
kobject_uevent(&q->kobj, KOBJ_ADD);
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 07cc329fa4b0..2290f65b9d73 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -258,15 +258,14 @@ EXPORT_SYMBOL(blk_queue_resize_tags);
* all transfers have been done for a request. It's important to call
* this function before end_that_request_last(), as that will put the
* request back on the free list thus corrupting the internal tag list.
- *
- * Notes:
- * queue lock must be held.
**/
void blk_queue_end_tag(struct request_queue *q, struct request *rq)
{
struct blk_queue_tag *bqt = q->queue_tags;
unsigned tag = rq->tag; /* negative tags invalid */
+ lockdep_assert_held(q->queue_lock);
+
BUG_ON(tag >= bqt->real_max_depth);
list_del_init(&rq->queuelist);
@@ -307,9 +306,6 @@ EXPORT_SYMBOL(blk_queue_end_tag);
* calling this function. The request will also be removed from
* the request queue, so it's the drivers responsibility to readd
* it if it should need to be restarted for some reason.
- *
- * Notes:
- * queue lock must be held.
**/
int blk_queue_start_tag(struct request_queue *q, struct request *rq)
{
@@ -317,6 +313,8 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
unsigned max_depth;
int tag;
+ lockdep_assert_held(q->queue_lock);
+
if (unlikely((rq->rq_flags & RQF_QUEUED))) {
printk(KERN_ERR
"%s: request %p for device [%s] already tagged %d",
@@ -389,14 +387,13 @@ EXPORT_SYMBOL(blk_queue_start_tag);
* Hardware conditions may dictate a need to stop all pending requests.
* In this case, we will safely clear the block side of the tag queue and
* readd all requests to the request queue in the right order.
- *
- * Notes:
- * queue lock must be held.
**/
void blk_queue_invalidate_tags(struct request_queue *q)
{
struct list_head *tmp, *n;
+ lockdep_assert_held(q->queue_lock);
+
list_for_each_safe(tmp, n, &q->tag_busy_list)
blk_requeue_request(q, list_entry_rq(tmp));
}
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index b78db2e5fdff..a7285bf2831c 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -22,11 +22,18 @@ static int throtl_quantum = 32;
#define DFL_THROTL_SLICE_HD (HZ / 10)
#define DFL_THROTL_SLICE_SSD (HZ / 50)
#define MAX_THROTL_SLICE (HZ)
-#define DFL_IDLE_THRESHOLD_SSD (1000L) /* 1 ms */
-#define DFL_IDLE_THRESHOLD_HD (100L * 1000) /* 100 ms */
#define MAX_IDLE_TIME (5L * 1000 * 1000) /* 5 s */
-/* default latency target is 0, eg, guarantee IO latency by default */
-#define DFL_LATENCY_TARGET (0)
+#define MIN_THROTL_BPS (320 * 1024)
+#define MIN_THROTL_IOPS (10)
+#define DFL_LATENCY_TARGET (-1L)
+#define DFL_IDLE_THRESHOLD (0)
+#define DFL_HD_BASELINE_LATENCY (4000L) /* 4ms */
+#define LATENCY_FILTERED_SSD (0)
+/*
+ * For HD, very small latency comes from sequential IO. Such IO is helpless to
+ * help determine if its IO is impacted by others, hence we ignore the IO
+ */
+#define LATENCY_FILTERED_HD (1000L) /* 1ms */
#define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT)
@@ -157,6 +164,7 @@ struct throtl_grp {
unsigned long last_check_time;
unsigned long latency_target; /* us */
+ unsigned long latency_target_conf; /* us */
/* When did we start a new slice */
unsigned long slice_start[2];
unsigned long slice_end[2];
@@ -165,6 +173,7 @@ struct throtl_grp {
unsigned long checked_last_finish_time; /* ns / 1024 */
unsigned long avg_idletime; /* ns / 1024 */
unsigned long idletime_threshold; /* us */
+ unsigned long idletime_threshold_conf; /* us */
unsigned int bio_cnt; /* total bios */
unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
@@ -201,8 +210,6 @@ struct throtl_data
unsigned int limit_index;
bool limit_valid[LIMIT_CNT];
- unsigned long dft_idletime_threshold; /* us */
-
unsigned long low_upgrade_time;
unsigned long low_downgrade_time;
@@ -212,6 +219,7 @@ struct throtl_data
struct avg_latency_bucket avg_buckets[LATENCY_BUCKET_SIZE];
struct latency_bucket __percpu *latency_buckets;
unsigned long last_calculate_time;
+ unsigned long filtered_latency;
bool track_bio_latency;
};
@@ -294,8 +302,14 @@ static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw)
td = tg->td;
ret = tg->bps[rw][td->limit_index];
- if (ret == 0 && td->limit_index == LIMIT_LOW)
- return tg->bps[rw][LIMIT_MAX];
+ if (ret == 0 && td->limit_index == LIMIT_LOW) {
+ /* intermediate node or iops isn't 0 */
+ if (!list_empty(&blkg->blkcg->css.children) ||
+ tg->iops[rw][td->limit_index])
+ return U64_MAX;
+ else
+ return MIN_THROTL_BPS;
+ }
if (td->limit_index == LIMIT_MAX && tg->bps[rw][LIMIT_LOW] &&
tg->bps[rw][LIMIT_LOW] != tg->bps[rw][LIMIT_MAX]) {
@@ -315,10 +329,17 @@ static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw)
if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
return UINT_MAX;
+
td = tg->td;
ret = tg->iops[rw][td->limit_index];
- if (ret == 0 && tg->td->limit_index == LIMIT_LOW)
- return tg->iops[rw][LIMIT_MAX];
+ if (ret == 0 && tg->td->limit_index == LIMIT_LOW) {
+ /* intermediate node or bps isn't 0 */
+ if (!list_empty(&blkg->blkcg->css.children) ||
+ tg->bps[rw][td->limit_index])
+ return UINT_MAX;
+ else
+ return MIN_THROTL_IOPS;
+ }
if (td->limit_index == LIMIT_MAX && tg->iops[rw][LIMIT_LOW] &&
tg->iops[rw][LIMIT_LOW] != tg->iops[rw][LIMIT_MAX]) {
@@ -482,6 +503,9 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, int node)
/* LIMIT_LOW will have default value 0 */
tg->latency_target = DFL_LATENCY_TARGET;
+ tg->latency_target_conf = DFL_LATENCY_TARGET;
+ tg->idletime_threshold = DFL_IDLE_THRESHOLD;
+ tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD;
return &tg->pd;
}
@@ -510,8 +534,6 @@ static void throtl_pd_init(struct blkg_policy_data *pd)
if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent)
sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue;
tg->td = td;
-
- tg->idletime_threshold = td->dft_idletime_threshold;
}
/*
@@ -684,7 +706,7 @@ static void throtl_dequeue_tg(struct throtl_grp *tg)
static void throtl_schedule_pending_timer(struct throtl_service_queue *sq,
unsigned long expires)
{
- unsigned long max_expire = jiffies + 8 * sq_to_tg(sq)->td->throtl_slice;
+ unsigned long max_expire = jiffies + 8 * sq_to_td(sq)->throtl_slice;
/*
* Since we are adjusting the throttle limit dynamically, the sleep
@@ -1349,7 +1371,7 @@ static int tg_print_conf_uint(struct seq_file *sf, void *v)
return 0;
}
-static void tg_conf_updated(struct throtl_grp *tg)
+static void tg_conf_updated(struct throtl_grp *tg, bool global)
{
struct throtl_service_queue *sq = &tg->service_queue;
struct cgroup_subsys_state *pos_css;
@@ -1367,8 +1389,26 @@ static void tg_conf_updated(struct throtl_grp *tg)
* restrictions in the whole hierarchy and allows them to bypass
* blk-throttle.
*/
- blkg_for_each_descendant_pre(blkg, pos_css, tg_to_blkg(tg))
- tg_update_has_rules(blkg_to_tg(blkg));
+ blkg_for_each_descendant_pre(blkg, pos_css,
+ global ? tg->td->queue->root_blkg : tg_to_blkg(tg)) {
+ struct throtl_grp *this_tg = blkg_to_tg(blkg);
+ struct throtl_grp *parent_tg;
+
+ tg_update_has_rules(this_tg);
+ /* ignore root/second level */
+ if (!cgroup_subsys_on_dfl(io_cgrp_subsys) || !blkg->parent ||
+ !blkg->parent->parent)
+ continue;
+ parent_tg = blkg_to_tg(blkg->parent);
+ /*
+ * make sure all children has lower idle time threshold and
+ * higher latency target
+ */
+ this_tg->idletime_threshold = min(this_tg->idletime_threshold,
+ parent_tg->idletime_threshold);
+ this_tg->latency_target = max(this_tg->latency_target,
+ parent_tg->latency_target);
+ }
/*
* We're already holding queue_lock and know @tg is valid. Let's
@@ -1413,7 +1453,7 @@ static ssize_t tg_set_conf(struct kernfs_open_file *of,
else
*(unsigned int *)((void *)tg + of_cft(of)->private) = v;
- tg_conf_updated(tg);
+ tg_conf_updated(tg, false);
ret = 0;
out_finish:
blkg_conf_finish(&ctx);
@@ -1497,34 +1537,34 @@ static u64 tg_prfill_limit(struct seq_file *sf, struct blkg_policy_data *pd,
tg->iops_conf[READ][off] == iops_dft &&
tg->iops_conf[WRITE][off] == iops_dft &&
(off != LIMIT_LOW ||
- (tg->idletime_threshold == tg->td->dft_idletime_threshold &&
- tg->latency_target == DFL_LATENCY_TARGET)))
+ (tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD &&
+ tg->latency_target_conf == DFL_LATENCY_TARGET)))
return 0;
- if (tg->bps_conf[READ][off] != bps_dft)
+ if (tg->bps_conf[READ][off] != U64_MAX)
snprintf(bufs[0], sizeof(bufs[0]), "%llu",
tg->bps_conf[READ][off]);
- if (tg->bps_conf[WRITE][off] != bps_dft)
+ if (tg->bps_conf[WRITE][off] != U64_MAX)
snprintf(bufs[1], sizeof(bufs[1]), "%llu",
tg->bps_conf[WRITE][off]);
- if (tg->iops_conf[READ][off] != iops_dft)
+ if (tg->iops_conf[READ][off] != UINT_MAX)
snprintf(bufs[2], sizeof(bufs[2]), "%u",
tg->iops_conf[READ][off]);
- if (tg->iops_conf[WRITE][off] != iops_dft)
+ if (tg->iops_conf[WRITE][off] != UINT_MAX)
snprintf(bufs[3], sizeof(bufs[3]), "%u",
tg->iops_conf[WRITE][off]);
if (off == LIMIT_LOW) {
- if (tg->idletime_threshold == ULONG_MAX)
+ if (tg->idletime_threshold_conf == ULONG_MAX)
strcpy(idle_time, " idle=max");
else
snprintf(idle_time, sizeof(idle_time), " idle=%lu",
- tg->idletime_threshold);
+ tg->idletime_threshold_conf);
- if (tg->latency_target == ULONG_MAX)
+ if (tg->latency_target_conf == ULONG_MAX)
strcpy(latency_time, " latency=max");
else
snprintf(latency_time, sizeof(latency_time),
- " latency=%lu", tg->latency_target);
+ " latency=%lu", tg->latency_target_conf);
}
seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s%s%s\n",
@@ -1563,8 +1603,8 @@ static ssize_t tg_set_limit(struct kernfs_open_file *of,
v[2] = tg->iops_conf[READ][index];
v[3] = tg->iops_conf[WRITE][index];
- idle_time = tg->idletime_threshold;
- latency_time = tg->latency_target;
+ idle_time = tg->idletime_threshold_conf;
+ latency_time = tg->latency_target_conf;
while (true) {
char tok[27]; /* wiops=18446744073709551616 */
char *p;
@@ -1623,17 +1663,33 @@ static ssize_t tg_set_limit(struct kernfs_open_file *of,
tg->iops_conf[READ][LIMIT_MAX]);
tg->iops[WRITE][LIMIT_LOW] = min(tg->iops_conf[WRITE][LIMIT_LOW],
tg->iops_conf[WRITE][LIMIT_MAX]);
+ tg->idletime_threshold_conf = idle_time;
+ tg->latency_target_conf = latency_time;
+
+ /* force user to configure all settings for low limit */
+ if (!(tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW] ||
+ tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) ||
+ tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD ||
+ tg->latency_target_conf == DFL_LATENCY_TARGET) {
+ tg->bps[READ][LIMIT_LOW] = 0;
+ tg->bps[WRITE][LIMIT_LOW] = 0;
+ tg->iops[READ][LIMIT_LOW] = 0;
+ tg->iops[WRITE][LIMIT_LOW] = 0;
+ tg->idletime_threshold = DFL_IDLE_THRESHOLD;
+ tg->latency_target = DFL_LATENCY_TARGET;
+ } else if (index == LIMIT_LOW) {
+ tg->idletime_threshold = tg->idletime_threshold_conf;
+ tg->latency_target = tg->latency_target_conf;
+ }
- if (index == LIMIT_LOW) {
- blk_throtl_update_limit_valid(tg->td);
- if (tg->td->limit_valid[LIMIT_LOW])
+ blk_throtl_update_limit_valid(tg->td);
+ if (tg->td->limit_valid[LIMIT_LOW]) {
+ if (index == LIMIT_LOW)
tg->td->limit_index = LIMIT_LOW;
- tg->idletime_threshold = (idle_time == ULONG_MAX) ?
- ULONG_MAX : idle_time;
- tg->latency_target = (latency_time == ULONG_MAX) ?
- ULONG_MAX : latency_time;
- }
- tg_conf_updated(tg);
+ } else
+ tg->td->limit_index = LIMIT_MAX;
+ tg_conf_updated(tg, index == LIMIT_LOW &&
+ tg->td->limit_valid[LIMIT_LOW]);
ret = 0;
out_finish:
blkg_conf_finish(&ctx);
@@ -1722,17 +1778,25 @@ static bool throtl_tg_is_idle(struct throtl_grp *tg)
/*
* cgroup is idle if:
* - single idle is too long, longer than a fixed value (in case user
- * configure a too big threshold) or 4 times of slice
+ * configure a too big threshold) or 4 times of idletime threshold
* - average think time is more than threshold
* - IO latency is largely below threshold
*/
- unsigned long time = jiffies_to_usecs(4 * tg->td->throtl_slice);
-
- time = min_t(unsigned long, MAX_IDLE_TIME, time);
- return (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
- tg->avg_idletime > tg->idletime_threshold ||
- (tg->latency_target && tg->bio_cnt &&
+ unsigned long time;
+ bool ret;
+
+ time = min_t(unsigned long, MAX_IDLE_TIME, 4 * tg->idletime_threshold);
+ ret = tg->latency_target == DFL_LATENCY_TARGET ||
+ tg->idletime_threshold == DFL_IDLE_THRESHOLD ||
+ (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
+ tg->avg_idletime > tg->idletime_threshold ||
+ (tg->latency_target && tg->bio_cnt &&
tg->bad_bio_cnt * 5 < tg->bio_cnt);
+ throtl_log(&tg->service_queue,
+ "avg_idle=%ld, idle_threshold=%ld, bad_bio=%d, total_bio=%d, is_idle=%d, scale=%d",
+ tg->avg_idletime, tg->idletime_threshold, tg->bad_bio_cnt,
+ tg->bio_cnt, ret, tg->td->scale);
+ return ret;
}
static bool throtl_tg_can_upgrade(struct throtl_grp *tg)
@@ -1828,6 +1892,7 @@ static void throtl_upgrade_state(struct throtl_data *td)
struct cgroup_subsys_state *pos_css;
struct blkcg_gq *blkg;
+ throtl_log(&td->service_queue, "upgrade to max");
td->limit_index = LIMIT_MAX;
td->low_upgrade_time = jiffies;
td->scale = 0;
@@ -1850,6 +1915,7 @@ static void throtl_downgrade_state(struct throtl_data *td, int new)
{
td->scale /= 2;
+ throtl_log(&td->service_queue, "downgrade, scale %d", td->scale);
if (td->scale) {
td->low_upgrade_time = jiffies - td->scale * td->throtl_slice;
return;
@@ -2023,6 +2089,11 @@ static void throtl_update_latency_buckets(struct throtl_data *td)
td->avg_buckets[i].valid = true;
last_latency = td->avg_buckets[i].latency;
}
+
+ for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
+ throtl_log(&td->service_queue,
+ "Latency bucket %d: latency=%ld, valid=%d", i,
+ td->avg_buckets[i].latency, td->avg_buckets[i].valid);
}
#else
static inline void throtl_update_latency_buckets(struct throtl_data *td)
@@ -2218,7 +2289,7 @@ void blk_throtl_bio_endio(struct bio *bio)
throtl_track_latency(tg->td, blk_stat_size(&bio->bi_issue_stat),
bio_op(bio), lat);
- if (tg->latency_target) {
+ if (tg->latency_target && lat >= tg->td->filtered_latency) {
int bucket;
unsigned int threshold;
@@ -2354,18 +2425,19 @@ void blk_throtl_exit(struct request_queue *q)
void blk_throtl_register_queue(struct request_queue *q)
{
struct throtl_data *td;
- struct cgroup_subsys_state *pos_css;
- struct blkcg_gq *blkg;
+ int i;
td = q->td;
BUG_ON(!td);
if (blk_queue_nonrot(q)) {
td->throtl_slice = DFL_THROTL_SLICE_SSD;
- td->dft_idletime_threshold = DFL_IDLE_THRESHOLD_SSD;
+ td->filtered_latency = LATENCY_FILTERED_SSD;
} else {
td->throtl_slice = DFL_THROTL_SLICE_HD;
- td->dft_idletime_threshold = DFL_IDLE_THRESHOLD_HD;
+ td->filtered_latency = LATENCY_FILTERED_HD;
+ for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
+ td->avg_buckets[i].latency = DFL_HD_BASELINE_LATENCY;
}
#ifndef CONFIG_BLK_DEV_THROTTLING_LOW
/* if no low limit, use previous default */
@@ -2375,18 +2447,6 @@ void blk_throtl_register_queue(struct request_queue *q)
td->track_bio_latency = !q->mq_ops && !q->request_fn;
if (!td->track_bio_latency)
blk_stat_enable_accounting(q);
-
- /*
- * some tg are created before queue is fully initialized, eg, nonrot
- * isn't initialized yet
- */
- rcu_read_lock();
- blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) {
- struct throtl_grp *tg = blkg_to_tg(blkg);
-
- tg->idletime_threshold = td->dft_idletime_threshold;
- }
- rcu_read_unlock();
}
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index cbff183f3d9f..17ec83bb0900 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -189,13 +189,15 @@ unsigned long blk_rq_timeout(unsigned long timeout)
* Notes:
* Each request has its own timer, and as it is added to the queue, we
* set up the timer. When the request completes, we cancel the timer.
- * Queue lock must be held for the non-mq case, mq case doesn't care.
*/
void blk_add_timer(struct request *req)
{
struct request_queue *q = req->q;
unsigned long expiry;
+ if (!q->mq_ops)
+ lockdep_assert_held(q->queue_lock);
+
/* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */
if (!q->mq_ops && !q->rq_timed_out_fn)
return;
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 17676f4d7fd1..6a9a0f03a67b 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -503,7 +503,7 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
}
static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw,
- wait_queue_t *wait, unsigned long rw)
+ wait_queue_entry_t *wait, unsigned long rw)
{
/*
* inc it here even if disabled, since we'll dec it at completion.
@@ -520,7 +520,7 @@ static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw,
* in line to be woken up, wait for our turn.
*/
if (waitqueue_active(&rqw->wait) &&
- rqw->wait.task_list.next != &wait->task_list)
+ rqw->wait.head.next != &wait->entry)
return false;
return atomic_inc_below(&rqw->inflight, get_limit(rwb, rw));
diff --git a/block/blk.h b/block/blk.h
index 2ed70228e44f..01ebb8185f6b 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -59,7 +59,7 @@ void blk_free_flush_queue(struct blk_flush_queue *q);
int blk_init_rl(struct request_list *rl, struct request_queue *q,
gfp_t gfp_mask);
-void blk_exit_rl(struct request_list *rl);
+void blk_exit_rl(struct request_queue *q, struct request_list *rl);
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio);
void blk_queue_bypass_start(struct request_queue *q);
@@ -143,6 +143,8 @@ static inline struct request *__elv_next_request(struct request_queue *q)
struct request *rq;
struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
+ WARN_ON_ONCE(q->mq_ops);
+
while (1) {
if (!list_empty(&q->queue_head)) {
rq = list_entry_rq(q->queue_head.next);
@@ -334,4 +336,17 @@ static inline void blk_throtl_bio_endio(struct bio *bio) { }
static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
#endif
+#ifdef CONFIG_BOUNCE
+extern int init_emergency_isa_pool(void);
+extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
+#else
+static inline int init_emergency_isa_pool(void)
+{
+ return 0;
+}
+static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
+{
+}
+#endif /* CONFIG_BOUNCE */
+
#endif /* BLK_INTERNAL_H */
diff --git a/block/bounce.c b/block/bounce.c
index 1cb5dd3a5da1..5793c2dc1a15 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -22,10 +22,12 @@
#include <asm/tlbflush.h>
#include <trace/events/block.h>
+#include "blk.h"
#define POOL_SIZE 64
#define ISA_POOL_SIZE 16
+static struct bio_set *bounce_bio_set, *bounce_bio_split;
static mempool_t *page_pool, *isa_page_pool;
#if defined(CONFIG_HIGHMEM) || defined(CONFIG_NEED_BOUNCE_POOL)
@@ -40,6 +42,14 @@ static __init int init_emergency_pool(void)
BUG_ON(!page_pool);
pr_info("pool size: %d pages\n", POOL_SIZE);
+ bounce_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ BUG_ON(!bounce_bio_set);
+ if (bioset_integrity_create(bounce_bio_set, BIO_POOL_SIZE))
+ BUG_ON(1);
+
+ bounce_bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
+ BUG_ON(!bounce_bio_split);
+
return 0;
}
@@ -143,7 +153,7 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool)
mempool_free(bvec->bv_page, pool);
}
- bio_orig->bi_error = bio->bi_error;
+ bio_orig->bi_status = bio->bi_status;
bio_endio(bio_orig);
bio_put(bio);
}
@@ -163,7 +173,7 @@ static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
{
struct bio *bio_orig = bio->bi_private;
- if (!bio->bi_error)
+ if (!bio->bi_status)
copy_to_high_bio_irq(bio_orig, bio);
bounce_end_io(bio, pool);
@@ -186,20 +196,31 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
int rw = bio_data_dir(*bio_orig);
struct bio_vec *to, from;
struct bvec_iter iter;
- unsigned i;
-
- bio_for_each_segment(from, *bio_orig, iter)
- if (page_to_pfn(from.bv_page) > queue_bounce_pfn(q))
- goto bounce;
+ unsigned i = 0;
+ bool bounce = false;
+ int sectors = 0;
+
+ bio_for_each_segment(from, *bio_orig, iter) {
+ if (i++ < BIO_MAX_PAGES)
+ sectors += from.bv_len >> 9;
+ if (page_to_pfn(from.bv_page) > q->limits.bounce_pfn)
+ bounce = true;
+ }
+ if (!bounce)
+ return;
- return;
-bounce:
- bio = bio_clone_bioset(*bio_orig, GFP_NOIO, fs_bio_set);
+ if (sectors < bio_sectors(*bio_orig)) {
+ bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split);
+ bio_chain(bio, *bio_orig);
+ generic_make_request(*bio_orig);
+ *bio_orig = bio;
+ }
+ bio = bio_clone_bioset(*bio_orig, GFP_NOIO, bounce_bio_set);
bio_for_each_segment_all(to, bio, i) {
struct page *page = to->bv_page;
- if (page_to_pfn(page) <= queue_bounce_pfn(q))
+ if (page_to_pfn(page) <= q->limits.bounce_pfn)
continue;
to->bv_page = mempool_alloc(pool, q->bounce_gfp);
@@ -251,7 +272,7 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
* don't waste time iterating over bio segments
*/
if (!(q->bounce_gfp & GFP_DMA)) {
- if (queue_bounce_pfn(q) >= blk_max_pfn)
+ if (q->limits.bounce_pfn >= blk_max_pfn)
return;
pool = page_pool;
} else {
@@ -264,5 +285,3 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
*/
__blk_queue_bounce(q, bio_orig, pool);
}
-
-EXPORT_SYMBOL(blk_queue_bounce);
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 0a23dbba2d30..c4513b23f57a 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -37,7 +37,7 @@ static void bsg_destroy_job(struct kref *kref)
struct bsg_job *job = container_of(kref, struct bsg_job, kref);
struct request *rq = job->req;
- blk_end_request_all(rq, scsi_req(rq)->result);
+ blk_end_request_all(rq, BLK_STS_OK);
put_device(job->dev); /* release reference for the request */
@@ -202,7 +202,7 @@ static void bsg_request_fn(struct request_queue *q)
ret = bsg_create_job(dev, req);
if (ret) {
scsi_req(req)->result = ret;
- blk_end_request_all(req, ret);
+ blk_end_request_all(req, BLK_STS_OK);
spin_lock_irq(q->queue_lock);
continue;
}
@@ -246,6 +246,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name,
q->bsg_job_size = dd_job_size;
q->bsg_job_fn = job_fn;
queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q);
+ queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q);
blk_queue_softirq_done(q, bsg_softirq_done);
blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
diff --git a/block/bsg.c b/block/bsg.c
index 6fd08544d77e..37663b664666 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -236,7 +236,6 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
rq = blk_get_request(q, op, GFP_KERNEL);
if (IS_ERR(rq))
return rq;
- scsi_req_init(rq);
ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm);
if (ret)
@@ -294,14 +293,14 @@ out:
* async completion call-back from the block layer, when scsi/ide/whatever
* calls end_that_request_last() on a request
*/
-static void bsg_rq_end_io(struct request *rq, int uptodate)
+static void bsg_rq_end_io(struct request *rq, blk_status_t status)
{
struct bsg_command *bc = rq->end_io_data;
struct bsg_device *bd = bc->bd;
unsigned long flags;
- dprintk("%s: finished rq %p bc %p, bio %p stat %d\n",
- bd->name, rq, bc, bc->bio, uptodate);
+ dprintk("%s: finished rq %p bc %p, bio %p\n",
+ bd->name, rq, bc, bc->bio);
bc->hdr.duration = jiffies_to_msecs(jiffies - bc->hdr.duration);
@@ -750,6 +749,12 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
#ifdef BSG_DEBUG
unsigned char buf[32];
#endif
+
+ if (!blk_queue_scsi_passthrough(rq)) {
+ WARN_ONCE(true, "Attempt to register a non-SCSI queue\n");
+ return ERR_PTR(-EINVAL);
+ }
+
if (!blk_get_queue(rq))
return ERR_PTR(-ENXIO);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index da69b079725f..3d5c28945719 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -38,9 +38,13 @@ static const u64 cfq_target_latency = (u64)NSEC_PER_SEC * 3/10; /* 300 ms */
static const int cfq_hist_divisor = 4;
/*
- * offset from end of service tree
+ * offset from end of queue service tree for idle class
*/
#define CFQ_IDLE_DELAY (NSEC_PER_SEC / 5)
+/* offset from end of group service tree under time slice mode */
+#define CFQ_SLICE_MODE_GROUP_DELAY (NSEC_PER_SEC / 5)
+/* offset from end of group service under IOPS mode */
+#define CFQ_IOPS_MODE_GROUP_DELAY (HZ / 5)
/*
* below this threshold, we consider thinktime immediate
@@ -978,15 +982,6 @@ static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime)
return min_vdisktime;
}
-static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime)
-{
- s64 delta = (s64)(vdisktime - min_vdisktime);
- if (delta < 0)
- min_vdisktime = vdisktime;
-
- return min_vdisktime;
-}
-
static void update_min_vdisktime(struct cfq_rb_root *st)
{
struct cfq_group *cfqg;
@@ -1362,6 +1357,14 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
cfqg->vfraction = max_t(unsigned, vfr, 1);
}
+static inline u64 cfq_get_cfqg_vdisktime_delay(struct cfq_data *cfqd)
+{
+ if (!iops_mode(cfqd))
+ return CFQ_SLICE_MODE_GROUP_DELAY;
+ else
+ return CFQ_IOPS_MODE_GROUP_DELAY;
+}
+
static void
cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
@@ -1381,7 +1384,8 @@ cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
n = rb_last(&st->rb);
if (n) {
__cfqg = rb_entry_cfqg(n);
- cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
+ cfqg->vdisktime = __cfqg->vdisktime +
+ cfq_get_cfqg_vdisktime_delay(cfqd);
} else
cfqg->vdisktime = st->min_vdisktime;
cfq_group_service_tree_add(st, cfqg);
diff --git a/block/elevator.c b/block/elevator.c
index dac99fbfc273..4bb2f0c93fa6 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -681,6 +681,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
*/
if (elv_attempt_insert_merge(q, rq))
break;
+ /* fall through */
case ELEVATOR_INSERT_SORT:
BUG_ON(blk_rq_is_passthrough(rq));
rq->rq_flags |= RQF_SORTED;
diff --git a/block/genhd.c b/block/genhd.c
index d252d29fe837..7f520fa25d16 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -36,7 +36,7 @@ struct kobject *block_depr;
static DEFINE_SPINLOCK(ext_devt_lock);
static DEFINE_IDR(ext_devt_idr);
-static struct device_type disk_type;
+static const struct device_type disk_type;
static void disk_check_events(struct disk_events *ev,
unsigned int *clearing_ptr);
@@ -1183,7 +1183,7 @@ static char *block_devnode(struct device *dev, umode_t *mode,
return NULL;
}
-static struct device_type disk_type = {
+static const struct device_type disk_type = {
.name = "disk",
.groups = disk_attr_groups,
.release = disk_release,
diff --git a/block/ioprio.c b/block/ioprio.c
index 4b120c9cf7e8..6f5d0b6625e3 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -75,7 +75,8 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
case IOPRIO_CLASS_RT:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- /* fall through, rt has prio field too */
+ /* fall through */
+ /* rt has prio field too */
case IOPRIO_CLASS_BE:
if (data >= IOPRIO_BE_NR || data < 0)
return -EINVAL;
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index b9faabc75fdb..f58cab82105b 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -99,7 +99,7 @@ struct kyber_hctx_data {
struct list_head rqs[KYBER_NUM_DOMAINS];
unsigned int cur_domain;
unsigned int batching;
- wait_queue_t domain_wait[KYBER_NUM_DOMAINS];
+ wait_queue_entry_t domain_wait[KYBER_NUM_DOMAINS];
atomic_t wait_index[KYBER_NUM_DOMAINS];
};
@@ -385,7 +385,7 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
INIT_LIST_HEAD(&khd->rqs[i]);
- INIT_LIST_HEAD(&khd->domain_wait[i].task_list);
+ INIT_LIST_HEAD(&khd->domain_wait[i].entry);
atomic_set(&khd->wait_index[i], 0);
}
@@ -426,33 +426,29 @@ static void rq_clear_domain_token(struct kyber_queue_data *kqd,
}
}
-static struct request *kyber_get_request(struct request_queue *q,
- unsigned int op,
- struct blk_mq_alloc_data *data)
+static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
{
- struct kyber_queue_data *kqd = q->elevator->elevator_data;
- struct request *rq;
-
/*
* We use the scheduler tags as per-hardware queue queueing tokens.
* Async requests can be limited at this stage.
*/
- if (!op_is_sync(op))
+ if (!op_is_sync(op)) {
+ struct kyber_queue_data *kqd = data->q->elevator->elevator_data;
+
data->shallow_depth = kqd->async_depth;
+ }
+}
- rq = __blk_mq_alloc_request(data, op);
- if (rq)
- rq_set_domain_token(rq, -1);
- return rq;
+static void kyber_prepare_request(struct request *rq, struct bio *bio)
+{
+ rq_set_domain_token(rq, -1);
}
-static void kyber_put_request(struct request *rq)
+static void kyber_finish_request(struct request *rq)
{
- struct request_queue *q = rq->q;
- struct kyber_queue_data *kqd = q->elevator->elevator_data;
+ struct kyber_queue_data *kqd = rq->q->elevator->elevator_data;
rq_clear_domain_token(kqd, rq);
- blk_mq_finish_request(rq);
}
static void kyber_completed_request(struct request *rq)
@@ -507,12 +503,12 @@ static void kyber_flush_busy_ctxs(struct kyber_hctx_data *khd,
}
}
-static int kyber_domain_wake(wait_queue_t *wait, unsigned mode, int flags,
+static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
void *key)
{
struct blk_mq_hw_ctx *hctx = READ_ONCE(wait->private);
- list_del_init(&wait->task_list);
+ list_del_init(&wait->entry);
blk_mq_run_hw_queue(hctx, true);
return 1;
}
@@ -523,7 +519,7 @@ static int kyber_get_domain_token(struct kyber_queue_data *kqd,
{
unsigned int sched_domain = khd->cur_domain;
struct sbitmap_queue *domain_tokens = &kqd->domain_tokens[sched_domain];
- wait_queue_t *wait = &khd->domain_wait[sched_domain];
+ wait_queue_entry_t *wait = &khd->domain_wait[sched_domain];
struct sbq_wait_state *ws;
int nr;
@@ -536,7 +532,7 @@ static int kyber_get_domain_token(struct kyber_queue_data *kqd,
* run when one becomes available. Note that this is serialized on
* khd->lock, but we still need to be careful about the waker.
*/
- if (list_empty_careful(&wait->task_list)) {
+ if (list_empty_careful(&wait->entry)) {
init_waitqueue_func_entry(wait, kyber_domain_wake);
wait->private = hctx;
ws = sbq_wait_ptr(domain_tokens,
@@ -734,9 +730,9 @@ static int kyber_##name##_waiting_show(void *data, struct seq_file *m) \
{ \
struct blk_mq_hw_ctx *hctx = data; \
struct kyber_hctx_data *khd = hctx->sched_data; \
- wait_queue_t *wait = &khd->domain_wait[domain]; \
+ wait_queue_entry_t *wait = &khd->domain_wait[domain]; \
\
- seq_printf(m, "%d\n", !list_empty_careful(&wait->task_list)); \
+ seq_printf(m, "%d\n", !list_empty_careful(&wait->entry)); \
return 0; \
}
KYBER_DEBUGFS_DOMAIN_ATTRS(KYBER_READ, read)
@@ -815,8 +811,9 @@ static struct elevator_type kyber_sched = {
.exit_sched = kyber_exit_sched,
.init_hctx = kyber_init_hctx,
.exit_hctx = kyber_exit_hctx,
- .get_request = kyber_get_request,
- .put_request = kyber_put_request,
+ .limit_depth = kyber_limit_depth,
+ .prepare_request = kyber_prepare_request,
+ .finish_request = kyber_finish_request,
.completed_request = kyber_completed_request,
.dispatch_request = kyber_dispatch_request,
.has_work = kyber_has_work,
diff --git a/block/partition-generic.c b/block/partition-generic.c
index ff07b9143ca4..c5ec8246e25e 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -320,8 +320,10 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
if (info) {
struct partition_meta_info *pinfo = alloc_part_info(disk);
- if (!pinfo)
+ if (!pinfo) {
+ err = -ENOMEM;
goto out_free_stats;
+ }
memcpy(pinfo, info, sizeof(*info));
p->info = pinfo;
}
diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c
index edcea70674c9..2a365c756648 100644
--- a/block/partitions/ldm.c
+++ b/block/partitions/ldm.c
@@ -115,7 +115,7 @@ static bool ldm_parse_privhead(const u8 *data, struct privhead *ph)
ldm_error("PRIVHEAD disk size doesn't match real disk size");
return false;
}
- if (uuid_be_to_bin(data + 0x0030, (uuid_be *)ph->disk_id)) {
+ if (uuid_parse(data + 0x0030, &ph->disk_id)) {
ldm_error("PRIVHEAD contains an invalid GUID.");
return false;
}
@@ -234,7 +234,7 @@ static bool ldm_compare_privheads (const struct privhead *ph1,
(ph1->logical_disk_size == ph2->logical_disk_size) &&
(ph1->config_start == ph2->config_start) &&
(ph1->config_size == ph2->config_size) &&
- !memcmp (ph1->disk_id, ph2->disk_id, GUID_SIZE));
+ uuid_equal(&ph1->disk_id, &ph2->disk_id));
}
/**
@@ -557,7 +557,7 @@ static struct vblk * ldm_get_disk_objid (const struct ldmdb *ldb)
list_for_each (item, &ldb->v_disk) {
struct vblk *v = list_entry (item, struct vblk, list);
- if (!memcmp (v->vblk.disk.disk_id, ldb->ph.disk_id, GUID_SIZE))
+ if (uuid_equal(&v->vblk.disk.disk_id, &ldb->ph.disk_id))
return v;
}
@@ -892,7 +892,7 @@ static bool ldm_parse_dsk3 (const u8 *buffer, int buflen, struct vblk *vb)
disk = &vb->vblk.disk;
ldm_get_vstr (buffer + 0x18 + r_diskid, disk->alt_name,
sizeof (disk->alt_name));
- if (uuid_be_to_bin(buffer + 0x19 + r_name, (uuid_be *)disk->disk_id))
+ if (uuid_parse(buffer + 0x19 + r_name, &disk->disk_id))
return false;
return true;
@@ -927,7 +927,7 @@ static bool ldm_parse_dsk4 (const u8 *buffer, int buflen, struct vblk *vb)
return false;
disk = &vb->vblk.disk;
- memcpy (disk->disk_id, buffer + 0x18 + r_name, GUID_SIZE);
+ uuid_copy(&disk->disk_id, (uuid_t *)(buffer + 0x18 + r_name));
return true;
}
diff --git a/block/partitions/ldm.h b/block/partitions/ldm.h
index 374242c0971a..f4c6055df956 100644
--- a/block/partitions/ldm.h
+++ b/block/partitions/ldm.h
@@ -112,8 +112,6 @@ struct frag { /* VBLK Fragment handling */
/* In memory LDM database structures. */
-#define GUID_SIZE 16
-
struct privhead { /* Offsets and sizes are in sectors. */
u16 ver_major;
u16 ver_minor;
@@ -121,7 +119,7 @@ struct privhead { /* Offsets and sizes are in sectors. */
u64 logical_disk_size;
u64 config_start;
u64 config_size;
- u8 disk_id[GUID_SIZE];
+ uuid_t disk_id;
};
struct tocblock { /* We have exactly two bitmaps. */
@@ -154,7 +152,7 @@ struct vblk_dgrp { /* VBLK Disk Group */
};
struct vblk_disk { /* VBLK Disk */
- u8 disk_id[GUID_SIZE];
+ uuid_t disk_id;
u8 alt_name[128];
};
diff --git a/block/partitions/msdos.c b/block/partitions/msdos.c
index 93e7c1b32edd..5610cd537da7 100644
--- a/block/partitions/msdos.c
+++ b/block/partitions/msdos.c
@@ -300,6 +300,8 @@ static void parse_bsd(struct parsed_partitions *state,
continue;
bsd_start = le32_to_cpu(p->p_offset);
bsd_size = le32_to_cpu(p->p_size);
+ if (memcmp(flavour, "bsd\0", 4) == 0)
+ bsd_start += offset;
if (offset == bsd_start && size == bsd_size)
/* full parent partition, we have it already */
continue;
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 4a294a5f7fab..7440de44dd85 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -326,7 +326,6 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
if (IS_ERR(rq))
return PTR_ERR(rq);
req = scsi_req(rq);
- scsi_req_init(rq);
if (hdr->cmd_len > BLK_MAX_CDB) {
req->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
@@ -456,7 +455,6 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
goto error_free_buffer;
}
req = scsi_req(rq);
- scsi_req_init(rq);
cmdlen = COMMAND_SIZE(opcode);
@@ -542,7 +540,6 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
rq = blk_get_request(q, REQ_OP_SCSI_OUT, __GFP_RECLAIM);
if (IS_ERR(rq))
return PTR_ERR(rq);
- scsi_req_init(rq);
rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
scsi_req(rq)->cmd[0] = cmd;
scsi_req(rq)->cmd[4] = data;
@@ -744,10 +741,14 @@ int scsi_cmd_blk_ioctl(struct block_device *bd, fmode_t mode,
}
EXPORT_SYMBOL(scsi_cmd_blk_ioctl);
-void scsi_req_init(struct request *rq)
+/**
+ * scsi_req_init - initialize certain fields of a scsi_request structure
+ * @req: Pointer to a scsi_request structure.
+ * Initializes .__cmd[], .cmd, .cmd_len and .sense_len but no other members
+ * of struct scsi_request.
+ */
+void scsi_req_init(struct scsi_request *req)
{
- struct scsi_request *req = scsi_req(rq);
-
memset(req->__cmd, 0, sizeof(req->__cmd));
req->cmd = req->__cmd;
req->cmd_len = BLK_MAX_CDB;
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 680c6d636298..3416dadf7b15 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -46,8 +46,8 @@ static __be16 t10_pi_ip_fn(void *data, unsigned int len)
* 16 bit app tag, 32 bit reference tag. Type 3 does not define the ref
* tag.
*/
-static int t10_pi_generate(struct blk_integrity_iter *iter, csum_fn *fn,
- unsigned int type)
+static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
+ csum_fn *fn, unsigned int type)
{
unsigned int i;
@@ -67,11 +67,11 @@ static int t10_pi_generate(struct blk_integrity_iter *iter, csum_fn *fn,
iter->seed++;
}
- return 0;
+ return BLK_STS_OK;
}
-static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn,
- unsigned int type)
+static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
+ csum_fn *fn, unsigned int type)
{
unsigned int i;
@@ -91,7 +91,7 @@ static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn,
"(rcvd %u)\n", iter->disk_name,
(unsigned long long)
iter->seed, be32_to_cpu(pi->ref_tag));
- return -EILSEQ;
+ return BLK_STS_PROTECTION;
}
break;
case 3:
@@ -108,7 +108,7 @@ static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn,
"(rcvd %04x, want %04x)\n", iter->disk_name,
(unsigned long long)iter->seed,
be16_to_cpu(pi->guard_tag), be16_to_cpu(csum));
- return -EILSEQ;
+ return BLK_STS_PROTECTION;
}
next:
@@ -117,45 +117,45 @@ next:
iter->seed++;
}
- return 0;
+ return BLK_STS_OK;
}
-static int t10_pi_type1_generate_crc(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type1_generate_crc(struct blk_integrity_iter *iter)
{
return t10_pi_generate(iter, t10_pi_crc_fn, 1);
}
-static int t10_pi_type1_generate_ip(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type1_generate_ip(struct blk_integrity_iter *iter)
{
return t10_pi_generate(iter, t10_pi_ip_fn, 1);
}
-static int t10_pi_type1_verify_crc(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type1_verify_crc(struct blk_integrity_iter *iter)
{
return t10_pi_verify(iter, t10_pi_crc_fn, 1);
}
-static int t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
{
return t10_pi_verify(iter, t10_pi_ip_fn, 1);
}
-static int t10_pi_type3_generate_crc(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type3_generate_crc(struct blk_integrity_iter *iter)
{
return t10_pi_generate(iter, t10_pi_crc_fn, 3);
}
-static int t10_pi_type3_generate_ip(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type3_generate_ip(struct blk_integrity_iter *iter)
{
return t10_pi_generate(iter, t10_pi_ip_fn, 3);
}
-static int t10_pi_type3_verify_crc(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type3_verify_crc(struct blk_integrity_iter *iter)
{
return t10_pi_verify(iter, t10_pi_crc_fn, 3);
}
-static int t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
{
return t10_pi_verify(iter, t10_pi_ip_fn, 3);
}