summaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/bfq-cgroup.c116
-rw-r--r--block/bfq-iosched.c2
-rw-r--r--block/bfq-iosched.h23
-rw-r--r--block/bio-integrity.c11
-rw-r--r--block/bio.c8
-rw-r--r--block/blk-core.c174
-rw-r--r--block/blk-exec.c4
-rw-r--r--block/blk-flush.c8
-rw-r--r--block/blk-integrity.c4
-rw-r--r--block/blk-mq-debugfs.c77
-rw-r--r--block/blk-mq-sched.c62
-rw-r--r--block/blk-mq-sched.h4
-rw-r--r--block/blk-mq.c148
-rw-r--r--block/blk-throttle.c22
-rw-r--r--block/bounce.c4
-rw-r--r--block/bsg-lib.c5
-rw-r--r--block/bsg.c12
-rw-r--r--block/cfq-iosched.c9
-rw-r--r--block/t10-pi.c30
19 files changed, 455 insertions, 268 deletions
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..ed93da2462ab 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -3665,7 +3665,7 @@ 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
}
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..7a5c8ed27f42 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -309,8 +309,8 @@ 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;
}
@@ -918,7 +918,7 @@ 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);
}
@@ -1818,7 +1818,7 @@ 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);
+ bio, bio->bi_status);
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
}
diff --git a/block/blk-core.c b/block/blk-core.c
index a7421b772d0e..8592409db272 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -129,11 +129,69 @@ 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" },
+
+ /* 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);
@@ -1668,7 +1726,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
blk_queue_split(q, &bio, q->bio_split);
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;
}
@@ -1726,7 +1784,10 @@ 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;
}
@@ -1881,7 +1942,7 @@ 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;
@@ -1924,7 +1985,7 @@ 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;
}
}
@@ -1976,9 +2037,9 @@ 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;
}
@@ -2183,29 +2244,29 @@ 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;
}
/*
@@ -2222,7 +2283,7 @@ 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);
@@ -2456,15 +2517,14 @@ 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;
@@ -2553,7 +2613,7 @@ 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:
@@ -2572,49 +2632,19 @@ 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);
@@ -2680,7 +2710,7 @@ 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)
{
@@ -2721,7 +2751,7 @@ 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;
@@ -2758,7 +2788,7 @@ 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
*
@@ -2772,7 +2802,7 @@ 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;
@@ -2791,7 +2821,7 @@ 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
*
@@ -2803,7 +2833,7 @@ 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)
{
if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
@@ -2817,7 +2847,7 @@ 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:
@@ -2828,7 +2858,8 @@ 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)
{
return blk_end_bidi_request(rq, error, nr_bytes, 0);
}
@@ -2837,12 +2868,12 @@ 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;
@@ -2858,7 +2889,7 @@ 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:
@@ -2868,7 +2899,8 @@ 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)
{
return __blk_end_bidi_request(rq, error, nr_bytes, 0);
}
@@ -2877,12 +2909,12 @@ 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. 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;
@@ -2898,7 +2930,7 @@ 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
@@ -2908,7 +2940,7 @@ 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));
}
@@ -3249,7 +3281,7 @@ 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..a572b47fa059 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;
@@ -341,7 +341,7 @@ 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);
@@ -382,7 +382,7 @@ 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;
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-mq-debugfs.c b/block/blk-mq-debugfs.c
index 803aed4d7221..9edebbdce0bd 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;
@@ -267,6 +269,14 @@ 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 +293,8 @@ 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 +310,37 @@ 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 +372,36 @@ 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;
@@ -655,6 +728,7 @@ 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},
{},
};
@@ -663,6 +737,7 @@ 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..c4e2afb9d12d 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -221,19 +221,71 @@ 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;
+
+ 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)
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index edafb5383b7b..b87e5be5db8c 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -38,9 +38,7 @@ 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);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1bcccedcc74f..359d2dc0d414 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -394,7 +394,7 @@ void blk_mq_free_request(struct 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 +409,7 @@ 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();
@@ -753,50 +753,6 @@ 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;
@@ -968,7 +924,7 @@ 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;
@@ -979,6 +935,7 @@ 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)) {
@@ -1019,25 +976,20 @@ 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)]++;
@@ -1075,7 +1027,7 @@ 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) &&
@@ -1427,30 +1379,13 @@ 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)
@@ -1461,22 +1396,28 @@ 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;
+
+ if (blk_mq_hctx_stopped(hctx)) {
+ 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);
@@ -1487,20 +1428,21 @@ 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,
@@ -1508,7 +1450,7 @@ 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;
@@ -1516,7 +1458,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
might_sleep();
srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
- __blk_mq_try_issue_directly(rq, cookie, true);
+ __blk_mq_try_issue_directly(hctx, rq, cookie, true);
srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
}
}
@@ -1619,9 +1561,12 @@ 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);
@@ -1630,11 +1575,12 @@ 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;
}
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index fc13dd0c6e39..a7285bf2831c 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -27,6 +27,13 @@ static int throtl_quantum = 32;
#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)
@@ -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;
};
@@ -698,7 +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
@@ -2281,7 +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;
@@ -2417,14 +2425,20 @@ void blk_throtl_exit(struct request_queue *q)
void blk_throtl_register_queue(struct request_queue *q)
{
struct throtl_data *td;
+ int i;
td = q->td;
BUG_ON(!td);
- if (blk_queue_nonrot(q))
+ if (blk_queue_nonrot(q)) {
td->throtl_slice = DFL_THROTL_SLICE_SSD;
- else
+ td->filtered_latency = LATENCY_FILTERED_SSD;
+ } else {
td->throtl_slice = DFL_THROTL_SLICE_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 */
td->throtl_slice = DFL_THROTL_SLICE_HD;
diff --git a/block/bounce.c b/block/bounce.c
index 1cb5dd3a5da1..e4703181d97f 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -143,7 +143,7 @@ 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 +163,7 @@ 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);
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..59d02dd31b0c 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -294,14 +294,14 @@ 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 +750,12 @@ 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 b7e9c7feeab2..3d5c28945719 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -982,15 +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;
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 680c6d636298..350b3cbcf9e5 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;
@@ -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);
}
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-03 04:44:04 +0300