summaryrefslogtreecommitdiffstats
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/blk-cgroup.c2
-rw-r--r--block/blk-cgroup.h8
-rw-r--r--block/blk-core.c23
-rw-r--r--block/blk-exec.c2
-rw-r--r--block/blk-flush.c108
-rw-r--r--block/blk-ioc.c2
-rw-r--r--block/blk-iopoll.c3
-rw-r--r--block/blk-lib.c8
-rw-r--r--block/blk-map.c2
-rw-r--r--block/blk-merge.c91
-rw-r--r--block/blk-mq-cpu.c14
-rw-r--r--block/blk-mq-cpumap.c10
-rw-r--r--block/blk-mq-sysfs.c31
-rw-r--r--block/blk-mq-tag.c2
-rw-r--r--block/blk-mq.c307
-rw-r--r--block/blk-mq.h7
-rw-r--r--block/blk-softirq.c19
-rw-r--r--block/blk-sysfs.c2
-rw-r--r--block/blk-timeout.c2
-rw-r--r--block/blk.h2
-rw-r--r--block/cfq-iosched.c8
-rw-r--r--block/deadline-iosched.c8
-rw-r--r--block/partitions/atari.h4
-rw-r--r--block/partitions/efi.h9
-rw-r--r--block/partitions/karma.c3
25 files changed, 376 insertions, 301 deletions
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4aefd46d7d9..e4a4145926f 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -336,7 +336,7 @@ static void blkg_destroy(struct blkcg_gq *blkg)
* under queue_lock. If it's not pointing to @blkg now, it never
* will. Hint assignment itself can race safely.
*/
- if (rcu_dereference_raw(blkcg->blkg_hint) == blkg)
+ if (rcu_access_pointer(blkcg->blkg_hint) == blkg)
rcu_assign_pointer(blkcg->blkg_hint, NULL);
/*
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 15a8d640de5..371fe8e92ab 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -439,9 +439,9 @@ static inline uint64_t blkg_stat_read(struct blkg_stat *stat)
uint64_t v;
do {
- start = u64_stats_fetch_begin_bh(&stat->syncp);
+ start = u64_stats_fetch_begin_irq(&stat->syncp);
v = stat->cnt;
- } while (u64_stats_fetch_retry_bh(&stat->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&stat->syncp, start));
return v;
}
@@ -512,9 +512,9 @@ static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat)
struct blkg_rwstat tmp;
do {
- start = u64_stats_fetch_begin_bh(&rwstat->syncp);
+ start = u64_stats_fetch_begin_irq(&rwstat->syncp);
tmp = *rwstat;
- } while (u64_stats_fetch_retry_bh(&rwstat->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&rwstat->syncp, start));
return tmp;
}
diff --git a/block/blk-core.c b/block/blk-core.c
index c00e0bdeab4..34d7c196338 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -708,9 +708,13 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
if (!q)
return NULL;
- if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+ q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
+ if (!q->flush_rq)
return NULL;
+ if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+ goto fail;
+
q->request_fn = rfn;
q->prep_rq_fn = NULL;
q->unprep_rq_fn = NULL;
@@ -733,12 +737,16 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
/* init elevator */
if (elevator_init(q, NULL)) {
mutex_unlock(&q->sysfs_lock);
- return NULL;
+ goto fail;
}
mutex_unlock(&q->sysfs_lock);
return q;
+
+fail:
+ kfree(q->flush_rq);
+ return NULL;
}
EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -1127,7 +1135,7 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
{
if (q->mq_ops)
- return blk_mq_alloc_request(q, rw, gfp_mask, false);
+ return blk_mq_alloc_request(q, rw, gfp_mask);
else
return blk_old_get_request(q, rw, gfp_mask);
}
@@ -1278,6 +1286,11 @@ void __blk_put_request(struct request_queue *q, struct request *req)
if (unlikely(!q))
return;
+ if (q->mq_ops) {
+ blk_mq_free_request(req);
+ return;
+ }
+
blk_pm_put_request(req);
elv_completed_request(q, req);
@@ -1915,7 +1928,7 @@ EXPORT_SYMBOL(submit_bio);
* in some cases below, so export this function.
* Request stacking drivers like request-based dm may change the queue
* limits while requests are in the queue (e.g. dm's table swapping).
- * Such request stacking drivers should check those requests agaist
+ * Such request stacking drivers should check those requests against
* the new queue limits again when they dispatch those requests,
* although such checkings are also done against the old queue limits
* when submitting requests.
@@ -2340,7 +2353,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
if (!req->bio)
return false;
- trace_block_rq_complete(req->q, req);
+ trace_block_rq_complete(req->q, req, nr_bytes);
/*
* For fs requests, rq is just carrier of independent bio's
diff --git a/block/blk-exec.c b/block/blk-exec.c
index bbfc072a79c..dbf4502b1d6 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -65,7 +65,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
* be resued after dying flag is set
*/
if (q->mq_ops) {
- blk_mq_insert_request(q, rq, true);
+ blk_mq_insert_request(rq, at_head, true, false);
return;
}
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 9288aaf35c2..43e6b4755e9 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -130,20 +130,29 @@ static void blk_flush_restore_request(struct request *rq)
blk_clear_rq_complete(rq);
}
-static void mq_flush_data_run(struct work_struct *work)
+static void mq_flush_run(struct work_struct *work)
{
struct request *rq;
- rq = container_of(work, struct request, mq_flush_data);
+ rq = container_of(work, struct request, mq_flush_work);
memset(&rq->csd, 0, sizeof(rq->csd));
- blk_mq_run_request(rq, true, false);
+ blk_mq_insert_request(rq, false, true, false);
}
-static void blk_mq_flush_data_insert(struct request *rq)
+static bool blk_flush_queue_rq(struct request *rq, bool add_front)
{
- INIT_WORK(&rq->mq_flush_data, mq_flush_data_run);
- kblockd_schedule_work(rq->q, &rq->mq_flush_data);
+ if (rq->q->mq_ops) {
+ INIT_WORK(&rq->mq_flush_work, mq_flush_run);
+ kblockd_schedule_work(rq->q, &rq->mq_flush_work);
+ return false;
+ } else {
+ if (add_front)
+ list_add(&rq->queuelist, &rq->q->queue_head);
+ else
+ list_add_tail(&rq->queuelist, &rq->q->queue_head);
+ return true;
+ }
}
/**
@@ -187,12 +196,7 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
case REQ_FSEQ_DATA:
list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
- if (q->mq_ops)
- blk_mq_flush_data_insert(rq);
- else {
- list_add(&rq->queuelist, &q->queue_head);
- queued = true;
- }
+ queued = blk_flush_queue_rq(rq, true);
break;
case REQ_FSEQ_DONE:
@@ -216,9 +220,6 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
}
kicked = blk_kick_flush(q);
- /* blk_mq_run_flush will run queue */
- if (q->mq_ops)
- return queued;
return kicked | queued;
}
@@ -230,10 +231,9 @@ static void flush_end_io(struct request *flush_rq, int error)
struct request *rq, *n;
unsigned long flags = 0;
- if (q->mq_ops) {
- blk_mq_free_request(flush_rq);
+ if (q->mq_ops)
spin_lock_irqsave(&q->mq_flush_lock, flags);
- }
+
running = &q->flush_queue[q->flush_running_idx];
BUG_ON(q->flush_pending_idx == q->flush_running_idx);
@@ -263,49 +263,14 @@ static void flush_end_io(struct request *flush_rq, int error)
* kblockd.
*/
if (queued || q->flush_queue_delayed) {
- if (!q->mq_ops)
- blk_run_queue_async(q);
- else
- /*
- * This can be optimized to only run queues with requests
- * queued if necessary.
- */
- blk_mq_run_queues(q, true);
+ WARN_ON(q->mq_ops);
+ blk_run_queue_async(q);
}
q->flush_queue_delayed = 0;
if (q->mq_ops)
spin_unlock_irqrestore(&q->mq_flush_lock, flags);
}
-static void mq_flush_work(struct work_struct *work)
-{
- struct request_queue *q;
- struct request *rq;
-
- q = container_of(work, struct request_queue, mq_flush_work);
-
- /* We don't need set REQ_FLUSH_SEQ, it's for consistency */
- rq = blk_mq_alloc_request(q, WRITE_FLUSH|REQ_FLUSH_SEQ,
- __GFP_WAIT|GFP_ATOMIC, true);
- rq->cmd_type = REQ_TYPE_FS;
- rq->end_io = flush_end_io;
-
- blk_mq_run_request(rq, true, false);
-}
-
-/*
- * We can't directly use q->flush_rq, because it doesn't have tag and is not in
- * hctx->rqs[]. so we must allocate a new request, since we can't sleep here,
- * so offload the work to workqueue.
- *
- * Note: we assume a flush request finished in any hardware queue will flush
- * the whole disk cache.
- */
-static void mq_run_flush(struct request_queue *q)
-{
- kblockd_schedule_work(q, &q->mq_flush_work);
-}
-
/**
* blk_kick_flush - consider issuing flush request
* @q: request_queue being kicked
@@ -340,19 +305,31 @@ static bool blk_kick_flush(struct request_queue *q)
* different from running_idx, which means flush is in flight.
*/
q->flush_pending_idx ^= 1;
+
if (q->mq_ops) {
- mq_run_flush(q);
- return true;
+ struct blk_mq_ctx *ctx = first_rq->mq_ctx;
+ struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+ blk_mq_rq_init(hctx, q->flush_rq);
+ q->flush_rq->mq_ctx = ctx;
+
+ /*
+ * Reuse the tag value from the fist waiting request,
+ * with blk-mq the tag is generated during request
+ * allocation and drivers can rely on it being inside
+ * the range they asked for.
+ */
+ q->flush_rq->tag = first_rq->tag;
+ } else {
+ blk_rq_init(q, q->flush_rq);
}
- blk_rq_init(q, &q->flush_rq);
- q->flush_rq.cmd_type = REQ_TYPE_FS;
- q->flush_rq.cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
- q->flush_rq.rq_disk = first_rq->rq_disk;
- q->flush_rq.end_io = flush_end_io;
+ q->flush_rq->cmd_type = REQ_TYPE_FS;
+ q->flush_rq->cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
+ q->flush_rq->rq_disk = first_rq->rq_disk;
+ q->flush_rq->end_io = flush_end_io;
- list_add_tail(&q->flush_rq.queuelist, &q->queue_head);
- return true;
+ return blk_flush_queue_rq(q->flush_rq, false);
}
static void flush_data_end_io(struct request *rq, int error)
@@ -437,7 +414,7 @@ void blk_insert_flush(struct request *rq)
if ((policy & REQ_FSEQ_DATA) &&
!(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
if (q->mq_ops) {
- blk_mq_run_request(rq, false, true);
+ blk_mq_insert_request(rq, false, false, true);
} else
list_add_tail(&rq->queuelist, &q->queue_head);
return;
@@ -558,5 +535,4 @@ EXPORT_SYMBOL(blkdev_issue_flush);
void blk_mq_init_flush(struct request_queue *q)
{
spin_lock_init(&q->mq_flush_lock);
- INIT_WORK(&q->mq_flush_work, mq_flush_work);
}
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 242df01413f..1a27f45ec77 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -68,7 +68,7 @@ static void ioc_destroy_icq(struct io_cq *icq)
* under queue_lock. If it's not pointing to @icq now, it never
* will. Hint assignment itself can race safely.
*/
- if (rcu_dereference_raw(ioc->icq_hint) == icq)
+ if (rcu_access_pointer(ioc->icq_hint) == icq)
rcu_assign_pointer(ioc->icq_hint, NULL);
ioc_exit_icq(icq);
diff --git a/block/blk-iopoll.c b/block/blk-iopoll.c
index 1855bf51edb..c11d24e379e 100644
--- a/block/blk-iopoll.c
+++ b/block/blk-iopoll.c
@@ -14,9 +14,6 @@
#include "blk.h"
-int blk_iopoll_enabled = 1;
-EXPORT_SYMBOL(blk_iopoll_enabled);
-
static unsigned int blk_iopoll_budget __read_mostly = 256;
static DEFINE_PER_CPU(struct list_head, blk_cpu_iopoll);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 2da76c999ef..97a733cf3d5 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -119,6 +119,14 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
atomic_inc(&bb.done);
submit_bio(type, bio);
+
+ /*
+ * We can loop for a long time in here, if someone does
+ * full device discards (like mkfs). Be nice and allow
+ * us to schedule out to avoid softlocking if preempt
+ * is disabled.
+ */
+ cond_resched();
}
blk_finish_plug(&plug);
diff --git a/block/blk-map.c b/block/blk-map.c
index ae4ae1047fd..cca6356d216 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -285,7 +285,7 @@ EXPORT_SYMBOL(blk_rq_unmap_user);
*
* Description:
* Data will be mapped directly if possible. Otherwise a bounce
- * buffer is used. Can be called multple times to append multple
+ * buffer is used. Can be called multiple times to append multiple
* buffers.
*/
int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 8f8adaa9546..6c583f9c5b6 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -21,6 +21,16 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
if (!bio)
return 0;
+ /*
+ * This should probably be returning 0, but blk_add_request_payload()
+ * (Christoph!!!!)
+ */
+ if (bio->bi_rw & REQ_DISCARD)
+ return 1;
+
+ if (bio->bi_rw & REQ_WRITE_SAME)
+ return 1;
+
fbio = bio;
cluster = blk_queue_cluster(q);
seg_size = 0;
@@ -161,30 +171,60 @@ new_segment:
*bvprv = *bvec;
}
-/*
- * map a request to scatterlist, return number of sg entries setup. Caller
- * must make sure sg can hold rq->nr_phys_segments entries
- */
-int blk_rq_map_sg(struct request_queue *q, struct request *rq,
- struct scatterlist *sglist)
+static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
+ struct scatterlist *sglist,
+ struct scatterlist **sg)
{
struct bio_vec bvec, bvprv = { NULL };
- struct req_iterator iter;
- struct scatterlist *sg;
+ struct bvec_iter iter;
int nsegs, cluster;
nsegs = 0;
cluster = blk_queue_cluster(q);
- /*
- * for each bio in rq
- */
- sg = NULL;
- rq_for_each_segment(bvec, rq, iter) {
- __blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg,
- &nsegs, &cluster);
- } /* segments in rq */
+ if (bio->bi_rw & REQ_DISCARD) {
+ /*
+ * This is a hack - drivers should be neither modifying the
+ * biovec, nor relying on bi_vcnt - but because of
+ * blk_add_request_payload(), a discard bio may or may not have
+ * a payload we need to set up here (thank you Christoph) and
+ * bi_vcnt is really the only way of telling if we need to.
+ */
+
+ if (bio->bi_vcnt)
+ goto single_segment;
+
+ return 0;
+ }
+
+ if (bio->bi_rw & REQ_WRITE_SAME) {
+single_segment:
+ *sg = sglist;
+ bvec = bio_iovec(bio);
+ sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
+ return 1;
+ }
+
+ for_each_bio(bio)
+ bio_for_each_segment(bvec, bio, iter)
+ __blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
+ &nsegs, &cluster);
+ return nsegs;
+}
+
+/*
+ * map a request to scatterlist, return number of sg entries setup. Caller
+ * must make sure sg can hold rq->nr_phys_segments entries
+ */
+int blk_rq_map_sg(struct request_queue *q, struct request *rq,
+ struct scatterlist *sglist)
+{
+ struct scatterlist *sg = NULL;
+ int nsegs = 0;
+
+ if (rq->bio)
+ nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg);
if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
(blk_rq_bytes(rq) & q->dma_pad_mask)) {
@@ -230,20 +270,13 @@ EXPORT_SYMBOL(blk_rq_map_sg);
int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
struct scatterlist *sglist)
{
- struct bio_vec bvec, bvprv = { NULL };
- struct scatterlist *sg;
- int nsegs, cluster;
- struct bvec_iter iter;
-
- nsegs = 0;
- cluster = blk_queue_cluster(q);
-
- sg = NULL;
- bio_for_each_segment(bvec, bio, iter) {
- __blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg,
- &nsegs, &cluster);
- } /* segments in bio */
+ struct scatterlist *sg = NULL;
+ int nsegs;
+ struct bio *next = bio->bi_next;
+ bio->bi_next = NULL;
+ nsegs = __blk_bios_map_sg(q, bio, sglist, &sg);
+ bio->bi_next = next;
if (sg)
sg_mark_end(sg);
diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c
index 3146befb56a..136ef8643bb 100644
--- a/block/blk-mq-cpu.c
+++ b/block/blk-mq-cpu.c
@@ -11,7 +11,7 @@
#include "blk-mq.h"
static LIST_HEAD(blk_mq_cpu_notify_list);
-static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock);
+static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock);
static int blk_mq_main_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
@@ -19,12 +19,12 @@ static int blk_mq_main_cpu_notify(struct notifier_block *self,
unsigned int cpu = (unsigned long) hcpu;
struct blk_mq_cpu_notifier *notify;
- spin_lock(&blk_mq_cpu_notify_lock);
+ raw_spin_lock(&blk_mq_cpu_notify_lock);
list_for_each_entry(notify, &blk_mq_cpu_notify_list, list)
notify->notify(notify->data, action, cpu);
- spin_unlock(&blk_mq_cpu_notify_lock);
+ raw_spin_unlock(&blk_mq_cpu_notify_lock);
return NOTIFY_OK;
}
@@ -32,16 +32,16 @@ void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
{
BUG_ON(!notifier->notify);
- spin_lock(&blk_mq_cpu_notify_lock);
+ raw_spin_lock(&blk_mq_cpu_notify_lock);
list_add_tail(&notifier->list, &blk_mq_cpu_notify_list);
- spin_unlock(&blk_mq_cpu_notify_lock);
+ raw_spin_unlock(&blk_mq_cpu_notify_lock);
}
void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
{
- spin_lock(&blk_mq_cpu_notify_lock);
+ raw_spin_lock(&blk_mq_cpu_notify_lock);
list_del(&notifier->list);
- spin_unlock(&blk_mq_cpu_notify_lock);
+ raw_spin_unlock(&blk_mq_cpu_notify_lock);
}
void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index f8721278601..09792132961 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -9,15 +9,6 @@
#include "blk.h"
#include "blk-mq.h"
-static void show_map(unsigned int *map, unsigned int nr)
-{
- int i;
-
- pr_info("blk-mq: CPU -> queue map\n");
- for_each_online_cpu(i)
- pr_info(" CPU%2u -> Queue %u\n", i, map[i]);
-}
-
static int cpu_to_queue_index(unsigned int nr_cpus, unsigned int nr_queues,
const int cpu)
{
@@ -85,7 +76,6 @@ int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues)
map[i] = map[first_sibling];
}
- show_map(map, nr_cpus);
free_cpumask_var(cpus);
return 0;
}
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index b91ce75bd35..b0ba264b052 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -244,6 +244,32 @@ static ssize_t blk_mq_hw_sysfs_tags_show(struct blk_mq_hw_ctx *hctx, char *page)
return blk_mq_tag_sysfs_show(hctx->tags, page);
}
+static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
+{
+ unsigned int i, queue_num, first = 1;
+ ssize_t ret = 0;
+
+ blk_mq_disable_hotplug();
+
+ for_each_online_cpu(i) {
+ queue_num = hctx->queue->mq_map[i];
+ if (queue_num != hctx->queue_num)
+ continue;
+
+ if (first)
+ ret += sprintf(ret + page, "%u", i);
+ else
+ ret += sprintf(ret + page, ", %u", i);
+
+ first = 0;
+ }
+
+ blk_mq_enable_hotplug();
+
+ ret += sprintf(ret + page, "\n");
+ return ret;
+}
+
static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_dispatched = {
.attr = {.name = "dispatched", .mode = S_IRUGO },
.show = blk_mq_sysfs_dispatched_show,
@@ -294,6 +320,10 @@ static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_tags = {
.attr = {.name = "tags", .mode = S_IRUGO },
.show = blk_mq_hw_sysfs_tags_show,
};
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_cpus = {
+ .attr = {.name = "cpu_list", .mode = S_IRUGO },
+ .show = blk_mq_hw_sysfs_cpus_show,
+};
static struct attribute *default_hw_ctx_attrs[] = {
&blk_mq_hw_sysfs_queued.attr,
@@ -302,6 +332,7 @@ static struct attribute *default_hw_ctx_attrs[] = {
&blk_mq_hw_sysfs_pending.attr,
&blk_mq_hw_sysfs_ipi.attr,
&blk_mq_hw_sysfs_tags.attr,
+ &blk_mq_hw_sysfs_cpus.attr,
NULL,
};
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 5d70edc9855..83ae96c51a2 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -184,7 +184,7 @@ void blk_mq_free_tags(struct blk_mq_tags *tags)
ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page)
{
char *orig_page = page;
- int cpu;
+ unsigned int cpu;
if (!tags)
return 0;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 57039fcd9c9..b1bcc619d0e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -73,8 +73,8 @@ static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx,
set_bit(ctx->index_hw, hctx->ctx_map);
}
-static struct request *blk_mq_alloc_rq(struct blk_mq_hw_ctx *hctx, gfp_t gfp,
- bool reserved)
+static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
+ gfp_t gfp, bool reserved)
{
struct request *rq;
unsigned int tag;
@@ -193,12 +193,6 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
}
-static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
- gfp_t gfp, bool reserved)
-{
- return blk_mq_alloc_rq(hctx, gfp, reserved);
-}
-
static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
int rw, gfp_t gfp,
bool reserved)
@@ -226,15 +220,14 @@ static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
return rq;
}
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
- gfp_t gfp, bool reserved)
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp)
{
struct request *rq;
if (blk_mq_queue_enter(q))
return NULL;
- rq = blk_mq_alloc_request_pinned(q, rw, gfp, reserved);
+ rq = blk_mq_alloc_request_pinned(q, rw, gfp, false);
if (rq)
blk_mq_put_ctx(rq->mq_ctx);
return rq;
@@ -258,7 +251,7 @@ EXPORT_SYMBOL(blk_mq_alloc_reserved_request);
/*
* Re-init and set pdu, if we have it
*/
-static void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq)
+void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq)
{
blk_rq_init(hctx->queue, rq);
@@ -290,38 +283,10 @@ void blk_mq_free_request(struct request *rq)
__blk_mq_free_request(hctx, ctx, rq);
}
-static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error)
-{
- if (error)
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
- else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
- error = -EIO;
-
- if (unlikely(rq->cmd_flags & REQ_QUIET))
- set_bit(BIO_QUIET, &bio->bi_flags);
-
- /* don't actually finish bio if it's part of flush sequence */
- if (!(rq->cmd_flags & REQ_FLUSH_SEQ))
- bio_endio(bio, error);
-}
-
-void blk_mq_complete_request(struct request *rq, int error)
+bool blk_mq_end_io_partial(struct request *rq, int error, unsigned int nr_bytes)
{
- struct bio *bio = rq->bio;
- unsigned int bytes = 0;
-
- trace_block_rq_complete(rq->q, rq);
-
- while (bio) {
- struct bio *next = bio->bi_next;
-
- bio->bi_next = NULL;
- bytes += bio->bi_iter.bi_size;
- blk_mq_bio_endio(rq, bio, error);
- bio = next;
- }
-
- blk_account_io_completion(rq, bytes);
+ if (blk_update_request(rq, error, blk_rq_bytes(rq)))
+ return true;
blk_account_io_done(rq);
@@ -329,49 +294,57 @@ void blk_mq_complete_request(struct request *rq, int error)
rq->end_io(rq, error);
else
blk_mq_free_request(rq);
+ return false;
}
+EXPORT_SYMBOL(blk_mq_end_io_partial);
-void __blk_mq_end_io(struct request *rq, int error)
-{
- if (!blk_mark_rq_complete(rq))
- blk_mq_complete_request(rq, error);
-}
-
-static void blk_mq_end_io_remote(void *data)
+static void __blk_mq_complete_request_remote(void *data)
{
struct request *rq = data;
- __blk_mq_end_io(rq, rq->errors);
+ rq->q->softirq_done_fn(rq);
}
-/*
- * End IO on this request on a multiqueue enabled driver. We'll either do
- * it directly inline, or punt to a local IPI handler on the matching
- * remote CPU.
- */
-void blk_mq_end_io(struct request *rq, int error)
+void __blk_mq_complete_request(struct request *rq)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
int cpu;
- if (!ctx->ipi_redirect)
- return __blk_mq_end_io(rq, error);
+ if (!ctx->ipi_redirect) {
+ rq->q->softirq_done_fn(rq);
+ return;
+ }
cpu = get_cpu();
if (cpu != ctx->cpu && cpu_online(ctx->cpu)) {
- rq->errors = error;
- rq->csd.func = blk_mq_end_io_remote;
+ rq->csd.func = __blk_mq_complete_request_remote;
rq->csd.info = rq;
rq->csd.flags = 0;
- __smp_call_function_single(ctx->cpu, &rq->csd, 0);
+ smp_call_function_single_async(ctx->cpu, &rq->csd);
} else {
- __blk_mq_end_io(rq, error);
+ rq->q->softirq_done_fn(rq);
}
put_cpu();
}
-EXPORT_SYMBOL(blk_mq_end_io);
-static void blk_mq_start_request(struct request *rq)
+/**
+ * blk_mq_complete_request - end I/O on a request
+ * @rq: the request being processed
+ *
+ * Description:
+ * Ends all I/O on a request. It does not handle partial completions.
+ * The actual completion happens out-of-order, through a IPI handler.
+ **/
+void blk_mq_complete_request(struct request *rq)
+{
+ if (unlikely(blk_should_fake_timeout(rq->q)))
+ return;
+ if (!blk_mark_rq_complete(rq))
+ __blk_mq_complete_request(rq);
+}
+EXPORT_SYMBOL(blk_mq_complete_request);
+
+static void blk_mq_start_request(struct request *rq, bool last)
{
struct request_queue *q = rq->q;
@@ -384,6 +357,25 @@ static void blk_mq_start_request(struct request *rq)
*/
rq->deadline = jiffies + q->rq_timeout;
set_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+
+ if (q->dma_drain_size && blk_rq_bytes(rq)) {
+ /*
+ * Make sure space for the drain appears. We know we can do
+ * this because max_hw_segments has been adjusted to be one
+ * fewer than the device can handle.
+ */
+ rq->nr_phys_segments++;
+ }
+
+ /*
+ * Flag the last request in the series so that drivers know when IO
+ * should be kicked off, if they don't do it on a per-request basis.
+ *
+ * Note: the flag isn't the only condition drivers should do kick off.
+ * If drive is busy, the last request might not have the bit set.
+ */
+ if (last)
+ rq->cmd_flags |= REQ_END;
}
static void blk_mq_requeue_request(struct request *rq)
@@ -392,6 +384,11 @@ static void blk_mq_requeue_request(struct request *rq)
trace_block_rq_requeue(q, rq);
clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+
+ rq->cmd_flags &= ~REQ_END;
+
+ if (q->dma_drain_size && blk_rq_bytes(rq))
+ rq->nr_phys_segments--;
}
struct blk_mq_timeout_data {
@@ -517,7 +514,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
LIST_HEAD(rq_list);
int bit, queued;
- if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->flags)))
+ if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
return;
hctx->run++;
@@ -559,19 +556,8 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
rq = list_first_entry(&rq_list, struct request, queuelist);
list_del_init(&rq->queuelist);
- blk_mq_start_request(rq);
- /*
- * Last request in the series. Flag it as such, this
- * enables drivers to know when IO should be kicked off,
- * if they don't do it on a per-request basis.
- *
- * Note: the flag isn't the only condition drivers
- * should do kick off. If drive is busy, the last
- * request might not have the bit set.
- */
- if (list_empty(&rq_list))
- rq->cmd_flags |= REQ_END;
+ blk_mq_start_request(rq, list_empty(&rq_list));
ret = q->mq_ops->queue_rq(hctx, rq);
switch (ret) {
@@ -589,8 +575,8 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
break;
default:
pr_err("blk-mq: bad return on queue: %d\n", ret);
- rq->errors = -EIO;
case BLK_MQ_RQ_QUEUE_ERROR:
+ rq->errors = -EIO;
blk_mq_end_io(rq, rq->errors);
break;
}
@@ -617,7 +603,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
{
- if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->flags)))
+ if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
return;
if (!async)
@@ -637,7 +623,7 @@ void blk_mq_run_queues(struct request_queue *q, bool async)
queue_for_each_hw_ctx(q, hctx, i) {
if ((!blk_mq_hctx_has_pending(hctx) &&
list_empty_careful(&hctx->dispatch)) ||
- test_bit(BLK_MQ_S_STOPPED, &hctx->flags))
+ test_bit(BLK_MQ_S_STOPPED, &hctx->state))
continue;
blk_mq_run_hw_queue(hctx, async);
@@ -693,13 +679,16 @@ static void blk_mq_work_fn(struct work_struct *work)
}
static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
- struct request *rq)
+ struct request *rq, bool at_head)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
trace_block_rq_insert(hctx->queue, rq);
- list_add_tail(&rq->queuelist, &ctx->rq_list);
+ if (at_head)
+ list_add(&rq->queuelist, &ctx->rq_list);
+ else
+ list_add_tail(&rq->queuelist, &ctx->rq_list);
blk_mq_hctx_mark_pending(hctx, ctx);
/*
@@ -708,60 +697,27 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
blk_mq_add_timer(rq);
}
-void blk_mq_insert_request(struct request_queue *q, struct request *rq,
- bool run_queue)
+void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
+ bool async)
{
+ struct request_queue *q = rq->q;
struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *ctx, *current_ctx;
+ struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx;
+
+ current_ctx = blk_mq_get_ctx(q);
+ if (!cpu_online(ctx->cpu))
+ rq->mq_ctx = ctx = current_ctx;
- ctx = rq->mq_ctx;
hctx = q->mq_ops->map_queue(q, ctx->cpu);
- if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
+ if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA) &&
+ !(rq->cmd_flags & (REQ_FLUSH_SEQ))) {
blk_insert_flush(rq);
} else {
- current_ctx = blk_mq_get_ctx(q);
-
- if (!cpu_online(ctx->cpu)) {
- ctx = current_ctx;
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
- rq->mq_ctx = ctx;
- }
spin_lock(&ctx->lock);
- __blk_mq_insert_request(hctx, rq);
+ __blk_mq_insert_request(hctx, rq, at_head);
spin_unlock(&ctx->lock);
-
- blk_mq_put_ctx(current_ctx);
- }
-
- if (run_queue)
- __blk_mq_run_hw_queue(hctx);
-}
-EXPORT_SYMBOL(blk_mq_insert_request);
-
-/*
- * This is a special version of blk_mq_insert_request to bypass FLUSH request
- * check. Should only be used internally.
- */
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async)
-{
- struct request_queue *q = rq->q;
- struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *ctx, *current_ctx;
-
- current_ctx = blk_mq_get_ctx(q);
-
- ctx = rq->mq_ctx;
- if (!cpu_online(ctx->cpu)) {
- ctx = current_ctx;
- rq->mq_ctx = ctx;
}
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
- /* ctx->cpu might be offline */
- spin_lock(&ctx->lock);
- __blk_mq_insert_request(hctx, rq);
- spin_unlock(&ctx->lock);
blk_mq_put_ctx(current_ctx);
@@ -798,7 +754,7 @@ static void blk_mq_insert_requests(struct request_queue *q,
rq = list_first_entry(list, struct request, queuelist);
list_del_init(&rq->queuelist);
rq->mq_ctx = ctx;
- __blk_mq_insert_request(hctx, rq);
+ __blk_mq_insert_request(hctx, rq, false);
}
spin_unlock(&ctx->lock);
@@ -888,6 +844,11 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_queue_bounce(q, &bio);
+ if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
+ bio_endio(bio, -EIO);
+ return;
+ }
+
if (use_plug && blk_attempt_plug_merge(q, bio, &request_count))
return;
@@ -899,6 +860,8 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
ctx = blk_mq_get_ctx(q);
hctx = q->mq_ops->map_queue(q, ctx->cpu);
+ if (is_sync)
+ rw |= REQ_SYNC;
trace_block_getrq(q, bio, rw);
rq = __blk_mq_alloc_request(hctx, GFP_ATOMIC, false);
if (likely(rq))
@@ -950,7 +913,7 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
__blk_mq_free_request(hctx, ctx, rq);
else {
blk_mq_bio_to_request(rq, bio);
- __blk_mq_insert_request(hctx, rq);
+ __blk_mq_insert_request(hctx, rq, false);
}
spin_unlock(&ctx->lock);
@@ -1031,8 +994,46 @@ static void blk_mq_hctx_notify(void *data, unsigned long action,
blk_mq_put_ctx(ctx);
}
-static void blk_mq_init_hw_commands(struct blk_mq_hw_ctx *hctx,
- void (*init)(void *, struct blk_mq_hw_ctx *,
+static int blk_mq_init_hw_commands(struct blk_mq_hw_ctx *hctx,
+ int (*init)(void *, struct blk_mq_hw_ctx *,
+ struct request *, unsigned int),
+ void *data)
+{
+ unsigned int i;
+ int ret = 0;
+
+ for (i = 0; i < hctx->queue_depth; i++) {
+ struct request *rq = hctx->rqs[i];
+
+ ret = init(data, hctx, rq, i);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+int blk_mq_init_commands(struct request_queue *q,
+ int (*init)(void *, struct blk_mq_hw_ctx *,
+ struct request *, unsigned int),
+ void *data)
+{
+ struct blk_mq_hw_ctx *hctx;
+ unsigned int i;
+ int ret = 0;
+
+ queue_for_each_hw_ctx(q, hctx, i) {
+ ret = blk_mq_init_hw_commands(hctx, init, data);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(blk_mq_init_commands);
+
+static void blk_mq_free_hw_commands(struct blk_mq_hw_ctx *hctx,
+ void (*free)(void *, struct blk_mq_hw_ctx *,
struct request *, unsigned int),
void *data)
{
@@ -1041,12 +1042,12 @@ static void blk_mq_init_hw_commands(struct blk_mq_hw_ctx *hctx,
for (i = 0; i < hctx->queue_depth; i++) {
struct request *rq = hctx->rqs[i];
- init(data, hctx, rq, i);
+ free(data, hctx, rq, i);
}
}
-void blk_mq_init_commands(struct request_queue *q,
- void (*init)(void *, struct blk_mq_hw_ctx *,
+void blk_mq_free_commands(struct request_queue *q,
+ void (*free)(void *, struct blk_mq_hw_ctx *,
struct request *, unsigned int),
void *data)
{
@@ -1054,9 +1055,9 @@ void blk_mq_init_commands(struct request_queue *q,
unsigned int i;
queue_for_each_hw_ctx(q, hctx, i)
- blk_mq_init_hw_commands(hctx, init, data);
+ blk_mq_free_hw_commands(hctx, free, data);
}
-EXPORT_SYMBOL(blk_mq_init_commands);
+EXPORT_SYMBOL(blk_mq_free_commands);
static void blk_mq_free_rq_map(struct blk_mq_hw_ctx *hctx)
{
@@ -1309,15 +1310,6 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
reg->queue_depth = BLK_MQ_MAX_DEPTH;
}
- /*
- * Set aside a tag for flush requests. It will only be used while
- * another flush request is in progress but outside the driver.
- *
- * TODO: only allocate if flushes are supported
- */
- reg->queue_depth++;
- reg->reserved_tags++;
-
if (reg->queue_depth < (reg->reserved_tags + BLK_MQ_TAG_MIN))
return ERR_PTR(-EINVAL);
@@ -1360,17 +1352,27 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
q->mq_ops = reg->ops;
q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
+ q->sg_reserved_size = INT_MAX;
+
blk_queue_make_request(q, blk_mq_make_request);
blk_queue_rq_timed_out(q, reg->ops->timeout);
if (reg->timeout)
blk_queue_rq_timeout(q, reg->timeout);
+ if (reg->ops->complete)
+ blk_queue_softirq_done(q, reg->ops->complete);
+
blk_mq_init_flush(q);
blk_mq_init_cpu_queues(q, reg->nr_hw_queues);
- if (blk_mq_init_hw_queues(q, reg, driver_data))
+ q->flush_rq = kzalloc(round_up(sizeof(struct request) + reg->cmd_size,
+ cache_line_size()), GFP_KERNEL);
+ if (!q->flush_rq)
goto err_hw;
+ if (blk_mq_init_hw_queues(q, reg, driver_data))
+ goto err_flush_rq;
+
blk_mq_map_swqueue(q);
mutex_lock(&all_q_mutex);
@@ -1378,6 +1380,9 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
mutex_unlock(&all_q_mutex);
return q;
+
+err_flush_rq:
+ kfree(q->flush_rq);
err_hw:
kfree(q->mq_map);
err_map:
@@ -1463,6 +1468,16 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
return NOTIFY_OK;
}
+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)
{
blk_mq_cpu_init();
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 5c3917984b0..ebbe6bac9d6 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -22,13 +22,12 @@ struct blk_mq_ctx {
struct kobject kobj;
};
-void __blk_mq_end_io(struct request *rq, int error);
-void blk_mq_complete_request(struct request *rq, int error);
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async);
+void __blk_mq_complete_request(struct request *rq);
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_init_flush(struct request_queue *q);
void blk_mq_drain_queue(struct request_queue *q);
void blk_mq_free_queue(struct request_queue *q);
+void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq);
/*
* CPU hotplug helpers
@@ -40,6 +39,8 @@ void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
void blk_mq_cpu_init(void);
+void blk_mq_enable_hotplug(void);
+void blk_mq_disable_hotplug(void);
/*
* CPU -> queue mappings
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 57790c1a97e..ebd6b6f1bde 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -30,8 +30,8 @@ static void blk_done_softirq(struct softirq_action *h)
while (!list_empty(&local_list)) {
struct request *rq;
- rq = list_entry(local_list.next, struct request, csd.list);
- list_del_init(&rq->csd.list);
+ rq = list_entry(local_list.next, struct request, queuelist);
+ list_del_init(&rq->queuelist);
rq->q->softirq_done_fn(rq);
}
}
@@ -45,9 +45,14 @@ static void trigger_softirq(void *data)
local_irq_save(flags);
list = this_cpu_ptr(&blk_cpu_done);
- list_add_tail(&rq->csd.list, list);
+ /*
+ * We reuse queuelist for a list of requests to process. Since the
+ * queuelist is used by the block layer only for requests waiting to be
+ * submitted to the device it is unused now.
+ */
+ list_add_tail(&rq->queuelist, list);
- if (list->next == &rq->csd.list)
+ if (list->next == &rq->queuelist)
raise_softirq_irqoff(BLOCK_SOFTIRQ);
local_irq_restore(flags);
@@ -65,7 +70,7 @@ static int raise_blk_irq(int cpu, struct request *rq)
data->info = rq;
data->flags = 0;
- __smp_call_function_single(cpu, data, 0);
+ smp_call_function_single_async(cpu, data);
return 0;
}
@@ -136,7 +141,7 @@ void __blk_complete_request(struct request *req)
struct list_head *list;
do_local:
list = this_cpu_ptr(&blk_cpu_done);
- list_add_tail(&req->csd.list, list);
+ list_add_tail(&req->queuelist, list);
/*
* if the list only contains our just added request,
@@ -144,7 +149,7 @@ do_local:
* entries there, someone already raised the irq but it
* hasn't run yet.
*/
- if (list->next == &req->csd.list)
+ if (list->next == &req->queuelist)
raise_softirq_irqoff(BLOCK_SOFTIRQ);
} else if (raise_blk_irq(ccpu, req))
goto do_local;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 8095c4a21fc..7500f876dae 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -549,6 +549,8 @@ static void blk_release_queue(struct kobject *kobj)
if (q->mq_ops)
blk_mq_free_queue(q);
+ kfree(q->flush_rq);
+
blk_trace_shutdown(q);
bdi_destroy(&q->backing_dev_info);
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index bba81c9348e..d96f7061c6f 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -91,7 +91,7 @@ static void blk_rq_timed_out(struct request *req)
case BLK_EH_HANDLED:
/* Can we use req->errors here? */
if (q->mq_ops)
- blk_mq_complete_request(req, req->errors);
+ __blk_mq_complete_request(req);
else
__blk_complete_request(req);
break;
diff --git a/block/blk.h b/block/blk.h
index c90e1d8f7a2..d23b415b8a2 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -113,7 +113,7 @@ static inline struct request *__elv_next_request(struct request_queue *q)
q->flush_queue_delayed = 1;
return NULL;
}
- if (unlikely(blk_queue_dying(q)) ||
+ if (unlikely(blk_queue_bypass(q)) ||
!q->elevator->type->ops.elevator_dispatch_fn(q, 0))
return NULL;
}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index f5de45b6af3..e0985f1955e 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -2364,10 +2364,10 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
* reposition in fifo if next is older than rq
*/
if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
- time_before(rq_fifo_time(next), rq_fifo_time(rq)) &&
+ time_before(next->fifo_time, rq->fifo_time) &&
cfqq == RQ_CFQQ(next)) {
list_move(&rq->queuelist, &next->queuelist);
- rq_set_fifo_time(rq, rq_fifo_time(next));
+ rq->fifo_time = next->fifo_time;
}
if (cfqq->next_rq == next)
@@ -2811,7 +2811,7 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
return NULL;
rq = rq_entry_fifo(cfqq->fifo.next);
- if (time_before(jiffies, rq_fifo_time(rq)))
+ if (time_before(jiffies, rq->fifo_time))
rq = NULL;
cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
@@ -3924,7 +3924,7 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
cfq_log_cfqq(cfqd, cfqq, "insert_request");
cfq_init_prio_data(cfqq, RQ_CIC(rq));
- rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]);
+ rq->fifo_time = jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)];
list_add_tail(&rq->queuelist, &cfqq->fifo);
cfq_add_rq_rb(rq);
cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group,
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index 9ef66406c62..a753df2b3fc 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -106,7 +106,7 @@ deadline_add_request(struct request_queue *q, struct request *rq)
/*
* set expire time and add to fifo list
*/
- rq_set_fifo_time(rq, jiffies + dd->fifo_expire[data_dir]);
+ rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
list_add_tail(&rq->queuelist, &dd->fifo_list[data_dir]);
}
@@ -174,9 +174,9 @@ deadline_merged_requests(struct request_queue *q, struct request *req,
* and move into next position (next will be deleted) in fifo
*/
if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
- if (time_before(rq_fifo_time(next), rq_fifo_time(req))) {
+ if (time_before(next->fifo_time, req->fifo_time)) {
list_move(&req->queuelist, &next->queuelist);
- rq_set_fifo_time(req, rq_fifo_time(next));
+ req->fifo_time = next->fifo_time;
}
}
@@ -230,7 +230,7 @@ static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
/*
* rq is expired!
*/
- if (time_after_eq(jiffies, rq_fifo_time(rq)))
+ if (time_after_eq(jiffies, rq->fifo_time))
return 1;
return 0;
diff --git a/block/partitions/atari.h b/block/partitions/atari.h
index fe2d32a89f3..f2ec43bfeec 100644
--- a/block/partitions/atari.h
+++ b/block/partitions/atari.h
@@ -11,6 +11,8 @@
* by Guenther Kelleter (guenther@pool.informatik.rwth-aachen.de)
*/
+#include <linux/compiler.h>
+
struct partition_info
{
u8 flg; /* bit 0: active; bit 7: bootable */
@@ -29,6 +31,6 @@ struct rootsector
u32 bsl_st; /* start of bad sector list */
u32 bsl_cnt; /* length of bad sector list */
u16 checksum; /* checksum for bootable disks */
-} __attribute__((__packed__));
+} __packed;
int atari_partition(struct parsed_partitions *state);
diff --git a/block/partitions/efi.h b/block/partitions/efi.h
index 4efcafba7e6..abd0b19288a 100644
--- a/block/partitions/efi.h
+++ b/block/partitions/efi.h
@@ -32,6 +32,7 @@
#include <linux/major.h>
#include <linux/string.h>
#include <linux/efi.h>
+#include <linux/compiler.h>
#define MSDOS_MBR_SIGNATURE 0xaa55
#define EFI_PMBR_OSTYPE_EFI 0xEF
@@ -87,13 +88,13 @@ typedef struct _gpt_header {
*
* uint8_t reserved2[ BlockSize - 92 ];
*/
-} __attribute__ ((packed)) gpt_header;
+} __packed gpt_header;
typedef struct _gpt_entry_attributes {
u64 required_to_function:1;
u64 reserved:47;
u64 type_guid_specific:16;
-} __attribute__ ((packed)) gpt_entry_attributes;
+} __packed gpt_entry_attributes;
typedef struct _gpt_entry {
efi_guid_t partition_type_guid;
@@ -102,7 +103,7 @@ typedef struct _gpt_entry {
__le64 ending_lba;
gpt_entry_attributes attributes;
efi_char16_t partition_name[72 / sizeof (efi_char16_t)];
-} __attribute__ ((packed)) gpt_entry;
+} __packed gpt_entry;
typedef struct _gpt_mbr_record {
u8 boot_indicator; /* unused by EFI, set to 0x80 for bootable */
@@ -124,7 +125,7 @@ typedef struct _legacy_mbr {
__le16 unknown;
gpt_mbr_record partition_record[4];
__le16 signature;
-} __attribute__ ((packed)) legacy_mbr;
+} __packed legacy_mbr;
/* Functions */
extern int efi_partition(struct parsed_partitions *state);
diff --git a/block/partitions/karma.c b/block/partitions/karma.c
index 0ea19312706..9721fa589bb 100644
--- a/block/partitions/karma.c
+++ b/block/partitions/karma.c
@@ -8,6 +8,7 @@
#include "check.h"
#include "karma.h"
+#include <linux/compiler.h>
int karma_partition(struct parsed_partitions *state)
{
@@ -26,7 +27,7 @@ int karma_partition(struct parsed_partitions *state)
} d_partitions[2];
u8 d_blank[208];
__le16 d_magic;
- } __attribute__((packed)) *label;
+ } __packed *label;
struct d_partition *p;
data = read_part_sector(state, 0, &sect);