#include "blk-mq-sched.h"
#include "blk-rq-qos.h"
- static DEFINE_PER_CPU(struct list_head, blk_cpu_done);
+ static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
static void blk_mq_poll_stats_start(struct request_queue *q);
static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
}
EXPORT_SYMBOL(blk_mq_end_request);
- /*
- * Softirq action handler - move entries to local list and loop over them
- * while passing them to the queue registered handler.
- */
- static __latent_entropy void blk_done_softirq(struct softirq_action *h)
+ static void blk_complete_reqs(struct llist_head *list)
{
- struct list_head *cpu_list, local_list;
-
- local_irq_disable();
- cpu_list = this_cpu_ptr(&blk_cpu_done);
- list_replace_init(cpu_list, &local_list);
- local_irq_enable();
-
- while (!list_empty(&local_list)) {
- struct request *rq;
+ struct llist_node *entry = llist_reverse_order(llist_del_all(list));
+ struct request *rq, *next;
- rq = list_entry(local_list.next, struct request, ipi_list);
- list_del_init(&rq->ipi_list);
+ llist_for_each_entry_safe(rq, next, entry, ipi_list)
rq->q->mq_ops->complete(rq);
- }
}
- static void blk_mq_trigger_softirq(struct request *rq)
+ static __latent_entropy void blk_done_softirq(struct softirq_action *h)
{
- struct list_head *list;
- unsigned long flags;
-
- local_irq_save(flags);
- list = this_cpu_ptr(&blk_cpu_done);
- list_add_tail(&rq->ipi_list, list);
-
- /*
- * If the list only contains our just added request, signal a raise of
- * the softirq. If there are already entries there, someone already
- * raised the irq but it hasn't run yet.
- */
- if (list->next == &rq->ipi_list)
- raise_softirq_irqoff(BLOCK_SOFTIRQ);
- local_irq_restore(flags);
+ blk_complete_reqs(this_cpu_ptr(&blk_cpu_done));
}
static int blk_softirq_cpu_dead(unsigned int cpu)
{
- /*
- * If a CPU goes away, splice its entries to the current CPU
- * and trigger a run of the softirq
- */
- local_irq_disable();
- list_splice_init(&per_cpu(blk_cpu_done, cpu),
- this_cpu_ptr(&blk_cpu_done));
- raise_softirq_irqoff(BLOCK_SOFTIRQ);
- local_irq_enable();
-
+ blk_complete_reqs(&per_cpu(blk_cpu_done, cpu));
return 0;
}
-
static void __blk_mq_complete_request_remote(void *data)
{
- struct request *rq = data;
-
- /*
- * For most of single queue controllers, there is only one irq vector
- * for handling I/O completion, and the only irq's affinity is set
- * to all possible CPUs. On most of ARCHs, this affinity means the irq
- * is handled on one specific CPU.
- *
- * So complete I/O requests in softirq context in case of single queue
- * devices to avoid degrading I/O performance due to irqsoff latency.
- */
- if (rq->q->nr_hw_queues == 1)
- blk_mq_trigger_softirq(rq);
- else
- rq->q->mq_ops->complete(rq);
+ __raise_softirq_irqoff(BLOCK_SOFTIRQ);
}
static inline bool blk_mq_complete_need_ipi(struct request *rq)
return cpu_online(rq->mq_ctx->cpu);
}
+ static void blk_mq_complete_send_ipi(struct request *rq)
+ {
+ struct llist_head *list;
+ unsigned int cpu;
+
+ cpu = rq->mq_ctx->cpu;
+ list = &per_cpu(blk_cpu_done, cpu);
+ if (llist_add(&rq->ipi_list, list)) {
+ INIT_CSD(&rq->csd, __blk_mq_complete_request_remote, rq);
+ smp_call_function_single_async(cpu, &rq->csd);
+ }
+ }
+
+ static void blk_mq_raise_softirq(struct request *rq)
+ {
+ struct llist_head *list;
+
+ preempt_disable();
+ list = this_cpu_ptr(&blk_cpu_done);
+ if (llist_add(&rq->ipi_list, list))
+ raise_softirq(BLOCK_SOFTIRQ);
+ preempt_enable();
+ }
+
bool blk_mq_complete_request_remote(struct request *rq)
{
WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
return false;
if (blk_mq_complete_need_ipi(rq)) {
- INIT_CSD(&rq->csd, __blk_mq_complete_request_remote, rq);
- smp_call_function_single_async(rq->mq_ctx->cpu, &rq->csd);
- } else {
- if (rq->q->nr_hw_queues > 1)
- return false;
- blk_mq_trigger_softirq(rq);
+ blk_mq_complete_send_ipi(rq);
+ return true;
}
- return true;
+ if (rq->q->nr_hw_queues == 1) {
+ blk_mq_raise_softirq(rq);
+ return true;
+ }
+ return false;
}
EXPORT_SYMBOL_GPL(blk_mq_complete_request_remote);
}
EXPORT_SYMBOL(blk_mq_run_hw_queue);
+/*
+ * Is the request queue handled by an IO scheduler that does not respect
+ * hardware queues when dispatching?
+ */
+static bool blk_mq_has_sqsched(struct request_queue *q)
+{
+ struct elevator_queue *e = q->elevator;
+
+ if (e && e->type->ops.dispatch_request &&
+ !(e->type->elevator_features & ELEVATOR_F_MQ_AWARE))
+ return true;
+ return false;
+}
+
+/*
+ * Return prefered queue to dispatch from (if any) for non-mq aware IO
+ * scheduler.
+ */
+static struct blk_mq_hw_ctx *blk_mq_get_sq_hctx(struct request_queue *q)
+{
+ struct blk_mq_hw_ctx *hctx;
+
+ /*
+ * If the IO scheduler does not respect hardware queues when
+ * dispatching, we just don't bother with multiple HW queues and
+ * dispatch from hctx for the current CPU since running multiple queues
+ * just causes lock contention inside the scheduler and pointless cache
+ * bouncing.
+ */
+ hctx = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT,
+ raw_smp_processor_id());
+ if (!blk_mq_hctx_stopped(hctx))
+ return hctx;
+ return NULL;
+}
+
/**
* blk_mq_run_hw_queues - Run all hardware queues in a request queue.
* @q: Pointer to the request queue to run.
*/
void blk_mq_run_hw_queues(struct request_queue *q, bool async)
{
- struct blk_mq_hw_ctx *hctx;
+ struct blk_mq_hw_ctx *hctx, *sq_hctx;
int i;
+ sq_hctx = NULL;
+ if (blk_mq_has_sqsched(q))
+ sq_hctx = blk_mq_get_sq_hctx(q);
queue_for_each_hw_ctx(q, hctx, i) {
if (blk_mq_hctx_stopped(hctx))
continue;
-
- blk_mq_run_hw_queue(hctx, async);
+ /*
+ * Dispatch from this hctx either if there's no hctx preferred
+ * by IO scheduler or if it has requests that bypass the
+ * scheduler.
+ */
+ if (!sq_hctx || sq_hctx == hctx ||
+ !list_empty_careful(&hctx->dispatch))
+ blk_mq_run_hw_queue(hctx, async);
}
}
EXPORT_SYMBOL(blk_mq_run_hw_queues);
*/
void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
{
- struct blk_mq_hw_ctx *hctx;
+ struct blk_mq_hw_ctx *hctx, *sq_hctx;
int i;
+ sq_hctx = NULL;
+ if (blk_mq_has_sqsched(q))
+ sq_hctx = blk_mq_get_sq_hctx(q);
queue_for_each_hw_ctx(q, hctx, i) {
if (blk_mq_hctx_stopped(hctx))
continue;
-
- blk_mq_delay_run_hw_queue(hctx, msecs);
+ /*
+ * Dispatch from this hctx either if there's no hctx preferred
+ * by IO scheduler or if it has requests that bypass the
+ * scheduler.
+ */
+ if (!sq_hctx || sq_hctx == hctx ||
+ !list_empty_careful(&hctx->dispatch))
+ blk_mq_delay_run_hw_queue(hctx, msecs);
}
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queues);
*/
blk_qc_t blk_mq_submit_bio(struct bio *bio)
{
- struct request_queue *q = bio->bi_disk->queue;
+ struct request_queue *q = bio->bi_bdev->bd_disk->queue;
const int is_sync = op_is_sync(bio->bi_opf);
const int is_flush_fua = op_is_flush(bio->bi_opf);
struct blk_mq_alloc_data data = {
goto free_hctx;
atomic_set(&hctx->nr_active, 0);
- atomic_set(&hctx->elevator_queued, 0);
if (node == NUMA_NO_NODE)
node = set->numa_node;
hctx->numa_node = node;
int i;
for_each_possible_cpu(i)
- INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
+ init_llist_head(&per_cpu(blk_cpu_done, i));
open_softirq(BLOCK_SOFTIRQ, blk_done_softirq);
cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD,
*/
union {
struct hlist_node hash; /* merge hash */
- struct list_head ipi_list;
+ struct llist_node ipi_list;
};
/*
unsigned int max_zone_append_sectors;
unsigned int discard_granularity;
unsigned int discard_alignment;
+ unsigned int zone_write_granularity;
unsigned short max_segments;
unsigned short max_integrity_segments;
extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
struct rq_map_data *, const struct iov_iter *,
gfp_t);
-extern void blk_execute_rq(struct request_queue *, struct gendisk *,
- struct request *, int);
-extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
+extern void blk_execute_rq(struct gendisk *, struct request *, int);
+extern void blk_execute_rq_nowait(struct gendisk *,
struct request *, int, rq_end_io_fn *);
/* Helper to convert REQ_OP_XXX to its string format XXX */
extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
unsigned int max_zone_append_sectors);
extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
+void blk_queue_zone_write_granularity(struct request_queue *q,
+ unsigned int size);
extern void blk_queue_alignment_offset(struct request_queue *q,
unsigned int alignment);
void blk_queue_update_readahead(struct request_queue *q);
!list_empty(&plug->cb_list));
}
-int blkdev_issue_flush(struct block_device *, gfp_t);
+int blkdev_issue_flush(struct block_device *bdev);
long nr_blockdev_pages(void);
#else /* CONFIG_BLOCK */
struct blk_plug {
return false;
}
-static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask)
+static inline int blkdev_issue_flush(struct block_device *bdev)
{
return 0;
}
return queue_io_opt(bdev_get_queue(bdev));
}
+static inline unsigned int
+queue_zone_write_granularity(const struct request_queue *q)
+{
+ return q->limits.zone_write_granularity;
+}
+
+static inline unsigned int
+bdev_zone_write_granularity(struct block_device *bdev)
+{
+ return queue_zone_write_granularity(bdev_get_queue(bdev));
+}
+
static inline int queue_alignment_offset(const struct request_queue *q)
{
if (q->limits.misaligned)
void disk_end_io_acct(struct gendisk *disk, unsigned int op,
unsigned long start_time);
-unsigned long part_start_io_acct(struct gendisk *disk,
- struct block_device **part, struct bio *bio);
-void part_end_io_acct(struct block_device *part, struct bio *bio,
- unsigned long start_time);
-
-/**
- * bio_start_io_acct - start I/O accounting for bio based drivers
- * @bio: bio to start account for
- *
- * Returns the start time that should be passed back to bio_end_io_acct().
- */
-static inline unsigned long bio_start_io_acct(struct bio *bio)
-{
- return disk_start_io_acct(bio->bi_disk, bio_sectors(bio), bio_op(bio));
-}
+unsigned long bio_start_io_acct(struct bio *bio);
+void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,
+ struct block_device *orig_bdev);
/**
* bio_end_io_acct - end I/O accounting for bio based drivers
*/
static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
{
- return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time);
+ return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev);
}
int bdev_read_only(struct block_device *bdev);
struct block_device *I_BDEV(struct inode *inode);
struct block_device *bdgrab(struct block_device *bdev);
void bdput(struct block_device *);
+int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart,
+ loff_t lend);
#ifdef CONFIG_BLOCK
void invalidate_bdev(struct block_device *bdev);
-int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart,
- loff_t lend);
int sync_blockdev(struct block_device *bdev);
#else
static inline void invalidate_bdev(struct block_device *bdev)
{
}
-static inline int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
- loff_t lstart, loff_t lend)
-{
- return 0;
-}
static inline int sync_blockdev(struct block_device *bdev)
{
return 0;
projects / linux.git / commitdiff