static void req_bio_endio(struct request *rq, struct bio *bio,
unsigned int nbytes, int error)
{
- if (error)
+ if (error && !(rq->cmd_flags & REQ_CLONE))
clear_bit(BIO_UPTODATE, &bio->bi_flags);
else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
error = -EIO;
bio_advance(bio, nbytes);
/* don't actually finish bio if it's part of flush sequence */
- if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+ if (bio->bi_iter.bi_size == 0 &&
+ !(rq->cmd_flags & (REQ_FLUSH_SEQ|REQ_CLONE)))
bio_endio(bio, error);
}
q->request_fn(q);
q->request_fn_active--;
}
+ EXPORT_SYMBOL_GPL(__blk_run_queue_uncond);
/**
* __blk_run_queue - run a single device queue
q->queue_lock = &q->__queue_lock;
spin_unlock_irq(lock);
+ bdi_destroy(&q->backing_dev_info);
+
/* @q is and will stay empty, shutdown and put */
blk_put_queue(q);
}
}
EXPORT_SYMBOL(blk_init_queue_node);
+static void blk_queue_bio(struct request_queue *q, struct bio *bio);
+
struct request_queue *
blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
spinlock_t *lock)
* Caller must ensure !blk_queue_nomerges(q) beforehand.
*/
bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
- unsigned int *request_count)
+ unsigned int *request_count,
+ struct request **same_queue_rq)
{
struct blk_plug *plug;
struct request *rq;
list_for_each_entry_reverse(rq, plug_list, queuelist) {
int el_ret;
- if (rq->q == q)
+ if (rq->q == q) {
(*request_count)++;
+ /*
+ * Only blk-mq multiple hardware queues case checks the
+ * rq in the same queue, there should be only one such
+ * rq in a queue
+ **/
+ if (same_queue_rq)
+ *same_queue_rq = rq;
+ }
if (rq->q != q || !blk_rq_merge_ok(rq, bio))
continue;
blk_rq_bio_prep(req->q, req, bio);
}
-void blk_queue_bio(struct request_queue *q, struct bio *bio)
+static void blk_queue_bio(struct request_queue *q, struct bio *bio)
{
const bool sync = !!(bio->bi_rw & REQ_SYNC);
struct blk_plug *plug;
* any locks.
*/
if (!blk_queue_nomerges(q) &&
- blk_attempt_plug_merge(q, bio, &request_count))
+ blk_attempt_plug_merge(q, bio, &request_count, NULL))
return;
spin_lock_irq(q->queue_lock);
spin_unlock_irq(q->queue_lock);
}
}
-EXPORT_SYMBOL_GPL(blk_queue_bio); /* for device mapper only */
/*
* If bio->bi_dev is a partition, remap the location
bio->bi_rw,
(unsigned long long)bio_end_sector(bio),
(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
-
- set_bit(BIO_EOF, &bio->bi_flags);
}
#ifdef CONFIG_FAIL_MAKE_REQUEST
}
EXPORT_SYMBOL_GPL(blk_lld_busy);
- /**
- * blk_rq_unprep_clone - Helper function to free all bios in a cloned request
- * @rq: the clone request to be cleaned up
- *
- * Description:
- * Free all bios in @rq for a cloned request.
- */
- void blk_rq_unprep_clone(struct request *rq)
- {
- struct bio *bio;
-
- while ((bio = rq->bio) != NULL) {
- rq->bio = bio->bi_next;
-
- bio_put(bio);
- }
- }
- EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
-
- /*
- * Copy attributes of the original request to the clone request.
- * The actual data parts (e.g. ->cmd, ->sense) are not copied.
- */
- static void __blk_rq_prep_clone(struct request *dst, struct request *src)
+ void blk_rq_prep_clone(struct request *dst, struct request *src)
{
dst->cpu = src->cpu;
- dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
+ dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK);
+ dst->cmd_flags |= REQ_NOMERGE | REQ_CLONE;
dst->cmd_type = src->cmd_type;
dst->__sector = blk_rq_pos(src);
dst->__data_len = blk_rq_bytes(src);
dst->nr_phys_segments = src->nr_phys_segments;
dst->ioprio = src->ioprio;
dst->extra_len = src->extra_len;
- }
-
- /**
- * blk_rq_prep_clone - Helper function to setup clone request
- * @rq: the request to be setup
- * @rq_src: original request to be cloned
- * @bs: bio_set that bios for clone are allocated from
- * @gfp_mask: memory allocation mask for bio
- * @bio_ctr: setup function to be called for each clone bio.
- * Returns %0 for success, non %0 for failure.
- * @data: private data to be passed to @bio_ctr
- *
- * Description:
- * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
- * The actual data parts of @rq_src (e.g. ->cmd, ->sense)
- * are not copied, and copying such parts is the caller's responsibility.
- * Also, pages which the original bios are pointing to are not copied
- * and the cloned bios just point same pages.
- * So cloned bios must be completed before original bios, which means
- * the caller must complete @rq before @rq_src.
- */
- int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
- struct bio_set *bs, gfp_t gfp_mask,
- int (*bio_ctr)(struct bio *, struct bio *, void *),
- void *data)
- {
- struct bio *bio, *bio_src;
-
- if (!bs)
- bs = fs_bio_set;
-
- __rq_for_each_bio(bio_src, rq_src) {
- bio = bio_clone_fast(bio_src, gfp_mask, bs);
- if (!bio)
- goto free_and_out;
-
- if (bio_ctr && bio_ctr(bio, bio_src, data))
- goto free_and_out;
-
- if (rq->bio) {
- rq->biotail->bi_next = bio;
- rq->biotail = bio;
- } else
- rq->bio = rq->biotail = bio;
- }
-
- __blk_rq_prep_clone(rq, rq_src);
-
- return 0;
-
- free_and_out:
- if (bio)
- bio_put(bio);
- blk_rq_unprep_clone(rq);
-
- return -ENOMEM;
+ dst->bio = src->bio;
+ dst->biotail = src->biotail;
+ dst->cmd = src->cmd;
+ dst->cmd_len = src->cmd_len;
+ dst->sense = src->sense;
}
EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
{
struct task_struct *tsk = current;
+ /*
+ * If this is a nested plug, don't actually assign it.
+ */
+ if (tsk->plug)
+ return;
+
INIT_LIST_HEAD(&plug->list);
INIT_LIST_HEAD(&plug->mq_list);
INIT_LIST_HEAD(&plug->cb_list);
-
/*
- * If this is a nested plug, don't actually assign it. It will be
- * flushed on its own.
+ * Store ordering should not be needed here, since a potential
+ * preempt will imply a full memory barrier
*/
- if (!tsk->plug) {
- /*
- * Store ordering should not be needed here, since a potential
- * preempt will imply a full memory barrier
- */
- tsk->plug = plug;
- }
+ tsk->plug = plug;
}
EXPORT_SYMBOL(blk_start_plug);
void blk_finish_plug(struct blk_plug *plug)
{
+ if (plug != current->plug)
+ return;
blk_flush_plug_list(plug, false);
- if (plug == current->plug)
- current->plug = NULL;
+ current->plug = NULL;
}
EXPORT_SYMBOL(blk_finish_plug);
return -EBUSY;
ret = wait_event_interruptible(q->mq_freeze_wq,
- !q->mq_freeze_depth || blk_queue_dying(q));
+ !atomic_read(&q->mq_freeze_depth) ||
+ blk_queue_dying(q));
if (blk_queue_dying(q))
return -ENODEV;
if (ret)
void blk_mq_freeze_queue_start(struct request_queue *q)
{
- bool freeze;
+ int freeze_depth;
- spin_lock_irq(q->queue_lock);
- freeze = !q->mq_freeze_depth++;
- spin_unlock_irq(q->queue_lock);
-
- if (freeze) {
+ freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
+ if (freeze_depth == 1) {
percpu_ref_kill(&q->mq_usage_counter);
blk_mq_run_hw_queues(q, false);
}
void blk_mq_unfreeze_queue(struct request_queue *q)
{
- bool wake;
+ int freeze_depth;
- spin_lock_irq(q->queue_lock);
- wake = !--q->mq_freeze_depth;
- WARN_ON_ONCE(q->mq_freeze_depth < 0);
- spin_unlock_irq(q->queue_lock);
- if (wake) {
+ freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
+ WARN_ON_ONCE(freeze_depth < 0);
+ if (!freeze_depth) {
percpu_ref_reinit(&q->mq_usage_counter);
wake_up_all(&q->mq_freeze_wq);
}
data.next = blk_rq_timeout(round_jiffies_up(data.next));
mod_timer(&q->timeout, data.next);
} else {
- queue_for_each_hw_ctx(q, hctx, i)
- blk_mq_tag_idle(hctx);
+ queue_for_each_hw_ctx(q, hctx, i) {
+ /* the hctx may be unmapped, so check it here */
+ if (blk_mq_hw_queue_mapped(hctx))
+ blk_mq_tag_idle(hctx);
+ }
}
}
spin_lock(&hctx->lock);
list_splice(&rq_list, &hctx->dispatch);
spin_unlock(&hctx->lock);
+ /*
+ * the queue is expected stopped with BLK_MQ_RQ_QUEUE_BUSY, but
+ * it's possible the queue is stopped and restarted again
+ * before this. Queue restart will dispatch requests. And since
+ * requests in rq_list aren't added into hctx->dispatch yet,
+ * the requests in rq_list might get lost.
+ *
+ * blk_mq_run_hw_queue() already checks the STOPPED bit
+ **/
+ blk_mq_run_hw_queue(hctx, true);
}
}
return rq;
}
+ static int blk_mq_direct_issue_request(struct request *rq)
+ {
+ int ret;
+ struct request_queue *q = rq->q;
+ struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q,
+ rq->mq_ctx->cpu);
+ struct blk_mq_queue_data bd = {
+ .rq = rq,
+ .list = NULL,
+ .last = 1
+ };
+
+ /*
+ * For OK queue, we are done. For error, kill it. Any other
+ * error (busy), just add it to our list as we previously
+ * would have done
+ */
+ ret = q->mq_ops->queue_rq(hctx, &bd);
+ if (ret == BLK_MQ_RQ_QUEUE_OK)
+ return 0;
+ else {
+ __blk_mq_requeue_request(rq);
+
+ if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
+ rq->errors = -EIO;
+ blk_mq_end_request(rq, rq->errors);
+ return 0;
+ }
+ return -1;
+ }
+ }
+
/*
* Multiple hardware queue variant. This will not use per-process plugs,
* but will attempt to bypass the hctx queueing if we can go straight to
const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
struct blk_map_ctx data;
struct request *rq;
+ unsigned int request_count = 0;
+ struct blk_plug *plug;
+ struct request *same_queue_rq = NULL;
blk_queue_bounce(q, &bio);
return;
}
+ if (!is_flush_fua && !blk_queue_nomerges(q) &&
+ blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
+ return;
+
rq = blk_mq_map_request(q, bio, &data);
if (unlikely(!rq))
return;
goto run_queue;
}
+ plug = current->plug;
/*
* If the driver supports defer issued based on 'last', then
* queue it up like normal since we can potentially save some
* CPU this way.
*/
- if (is_sync && !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
- struct blk_mq_queue_data bd = {
- .rq = rq,
- .list = NULL,
- .last = 1
- };
- int ret;
+ if (((plug && !blk_queue_nomerges(q)) || is_sync) &&
+ !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
+ struct request *old_rq = NULL;
blk_mq_bio_to_request(rq, bio);
/*
- * For OK queue, we are done. For error, kill it. Any other
- * error (busy), just add it to our list as we previously
- * would have done
+ * we do limited pluging. If bio can be merged, do merge.
+ * Otherwise the existing request in the plug list will be
+ * issued. So the plug list will have one request at most
*/
- ret = q->mq_ops->queue_rq(data.hctx, &bd);
- if (ret == BLK_MQ_RQ_QUEUE_OK)
- goto done;
- else {
- __blk_mq_requeue_request(rq);
-
- if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
- rq->errors = -EIO;
- blk_mq_end_request(rq, rq->errors);
- goto done;
+ if (plug) {
+ /*
+ * The plug list might get flushed before this. If that
+ * happens, same_queue_rq is invalid and plug list is empty
+ **/
+ if (same_queue_rq && !list_empty(&plug->mq_list)) {
+ old_rq = same_queue_rq;
+ list_del_init(&old_rq->queuelist);
}
- }
+ list_add_tail(&rq->queuelist, &plug->mq_list);
+ } else /* is_sync */
+ old_rq = rq;
+ blk_mq_put_ctx(data.ctx);
+ if (!old_rq)
+ return;
+ if (!blk_mq_direct_issue_request(old_rq))
+ return;
+ blk_mq_insert_request(old_rq, false, true, true);
+ return;
}
if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
run_queue:
blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
}
- done:
blk_mq_put_ctx(data.ctx);
}
{
const int is_sync = rw_is_sync(bio->bi_rw);
const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
- unsigned int use_plug, request_count = 0;
+ struct blk_plug *plug;
+ unsigned int request_count = 0;
struct blk_map_ctx data;
struct request *rq;
- /*
- * If we have multiple hardware queues, just go directly to
- * one of those for sync IO.
- */
- use_plug = !is_flush_fua && !is_sync;
-
blk_queue_bounce(q, &bio);
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
return;
}
- if (use_plug && !blk_queue_nomerges(q) &&
- blk_attempt_plug_merge(q, bio, &request_count))
+ if (!is_flush_fua && !blk_queue_nomerges(q) &&
+ blk_attempt_plug_merge(q, bio, &request_count, NULL))
return;
rq = blk_mq_map_request(q, bio, &data);
* utilize that to temporarily store requests until the task is
* either done or scheduled away.
*/
- if (use_plug) {
- struct blk_plug *plug = current->plug;
-
- if (plug) {
- blk_mq_bio_to_request(rq, bio);
- if (list_empty(&plug->mq_list))
- trace_block_plug(q);
- else if (request_count >= BLK_MAX_REQUEST_COUNT) {
- blk_flush_plug_list(plug, false);
- trace_block_plug(q);
- }
- list_add_tail(&rq->queuelist, &plug->mq_list);
- blk_mq_put_ctx(data.ctx);
- return;
+ plug = current->plug;
+ if (plug) {
+ blk_mq_bio_to_request(rq, bio);
+ if (list_empty(&plug->mq_list))
+ trace_block_plug(q);
+ else if (request_count >= BLK_MAX_REQUEST_COUNT) {
+ blk_flush_plug_list(plug, false);
+ trace_block_plug(q);
}
+ list_add_tail(&rq->queuelist, &plug->mq_list);
+ blk_mq_put_ctx(data.ctx);
+ return;
}
if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
return NOTIFY_OK;
}
-static int blk_mq_hctx_cpu_online(struct blk_mq_hw_ctx *hctx, int cpu)
-{
- struct request_queue *q = hctx->queue;
- struct blk_mq_tag_set *set = q->tag_set;
-
- if (set->tags[hctx->queue_num])
- return NOTIFY_OK;
-
- set->tags[hctx->queue_num] = blk_mq_init_rq_map(set, hctx->queue_num);
- if (!set->tags[hctx->queue_num])
- return NOTIFY_STOP;
-
- hctx->tags = set->tags[hctx->queue_num];
- return NOTIFY_OK;
-}
-
static int blk_mq_hctx_notify(void *data, unsigned long action,
unsigned int cpu)
{
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
return blk_mq_hctx_cpu_offline(hctx, cpu);
- else if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
- return blk_mq_hctx_cpu_online(hctx, cpu);
+
+ /*
+ * In case of CPU online, tags may be reallocated
+ * in blk_mq_map_swqueue() after mapping is updated.
+ */
return NOTIFY_OK;
}
unsigned int i;
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
+ struct blk_mq_tag_set *set = q->tag_set;
queue_for_each_hw_ctx(q, hctx, i) {
cpumask_clear(hctx->cpumask);
* disable it and free the request entries.
*/
if (!hctx->nr_ctx) {
- struct blk_mq_tag_set *set = q->tag_set;
-
if (set->tags[i]) {
blk_mq_free_rq_map(set, set->tags[i], i);
set->tags[i] = NULL;
- hctx->tags = NULL;
}
+ hctx->tags = NULL;
continue;
}
+ /* unmapped hw queue can be remapped after CPU topo changed */
+ if (!set->tags[i])
+ set->tags[i] = blk_mq_init_rq_map(set, i);
+ hctx->tags = set->tags[i];
+ WARN_ON(!hctx->tags);
+
/*
* Set the map size to the number of mapped software queues.
* This is more accurate and more efficient than looping
/* Basically redo blk_mq_init_queue with queue frozen */
static void blk_mq_queue_reinit(struct request_queue *q)
{
- WARN_ON_ONCE(!q->mq_freeze_depth);
+ WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
blk_mq_sysfs_unregister(q);
*/
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_freeze_queue_start(q);
- list_for_each_entry(q, &all_q_list, all_q_node)
+ list_for_each_entry(q, &all_q_list, all_q_node) {
blk_mq_freeze_queue_wait(q);
+ /*
+ * timeout handler can't touch hw queue during the
+ * reinitialization
+ */
+ del_timer_sync(&q->timeout);
+ }
+
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_queue_reinit(q);
struct bio_vec *bvec, *org_vec;
int i;
- if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
- set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);
-
/*
* free up bounce indirect pages used
*/
if (page_to_pfn(page) <= queue_bounce_pfn(q) && !force)
continue;
- inc_zone_page_state(to->bv_page, NR_BOUNCE);
to->bv_page = mempool_alloc(pool, q->bounce_gfp);
+ inc_zone_page_state(to->bv_page, NR_BOUNCE);
if (rw == WRITE) {
char *vto, *vfrom;
}
EXPORT_SYMBOL(dm_consume_args);
+static bool __table_type_request_based(unsigned table_type)
+{
+ return (table_type == DM_TYPE_REQUEST_BASED ||
+ table_type == DM_TYPE_MQ_REQUEST_BASED);
+}
+
static int dm_table_set_type(struct dm_table *t)
{
unsigned i;
* Determine the type from the live device.
* Default to bio-based if device is new.
*/
- if (live_md_type == DM_TYPE_REQUEST_BASED ||
- live_md_type == DM_TYPE_MQ_REQUEST_BASED)
+ if (__table_type_request_based(live_md_type))
request_based = 1;
else
bio_based = 1;
}
t->type = DM_TYPE_MQ_REQUEST_BASED;
- } else if (hybrid && list_empty(devices) && live_md_type != DM_TYPE_NONE) {
+ } else if (list_empty(devices) && __table_type_request_based(live_md_type)) {
/* inherit live MD type */
t->type = live_md_type;
bool dm_table_request_based(struct dm_table *t)
{
- unsigned table_type = dm_table_get_type(t);
-
- return (table_type == DM_TYPE_REQUEST_BASED ||
- table_type == DM_TYPE_MQ_REQUEST_BASED);
+ return __table_type_request_based(dm_table_get_type(t));
}
bool dm_table_mq_request_based(struct dm_table *t)
{
unsigned type = dm_table_get_type(t);
unsigned per_bio_data_size = 0;
- struct dm_target *tgt;
unsigned i;
- if (unlikely(type == DM_TYPE_NONE)) {
+ switch (type) {
+ case DM_TYPE_BIO_BASED:
+ for (i = 0; i < t->num_targets; i++) {
+ struct dm_target *tgt = t->targets + i;
+
+ per_bio_data_size = max(per_bio_data_size,
+ tgt->per_bio_data_size);
+ }
+ t->mempools = dm_alloc_bio_mempools(t->integrity_supported,
+ per_bio_data_size);
+ break;
+ case DM_TYPE_REQUEST_BASED:
+ case DM_TYPE_MQ_REQUEST_BASED:
+ t->mempools = dm_alloc_rq_mempools(md, type);
+ break;
+ default:
DMWARN("no table type is set, can't allocate mempools");
return -EINVAL;
}
- if (type == DM_TYPE_BIO_BASED)
- for (i = 0; i < t->num_targets; i++) {
- tgt = t->targets + i;
- per_bio_data_size = max(per_bio_data_size, tgt->per_bio_data_size);
- }
-
- t->mempools = dm_alloc_md_mempools(md, type, t->integrity_supported, per_bio_data_size);
if (!t->mempools)
return -ENOMEM;
dec_pending(io, error);
}
- /*
- * Partial completion handling for request-based dm
- */
- static void end_clone_bio(struct bio *clone, int error)
- {
- struct dm_rq_clone_bio_info *info =
- container_of(clone, struct dm_rq_clone_bio_info, clone);
- struct dm_rq_target_io *tio = info->tio;
- struct bio *bio = info->orig;
- unsigned int nr_bytes = info->orig->bi_iter.bi_size;
-
- bio_put(clone);
-
- if (tio->error)
- /*
- * An error has already been detected on the request.
- * Once error occurred, just let clone->end_io() handle
- * the remainder.
- */
- return;
- else if (error) {
- /*
- * Don't notice the error to the upper layer yet.
- * The error handling decision is made by the target driver,
- * when the request is completed.
- */
- tio->error = error;
- return;
- }
-
- /*
- * I/O for the bio successfully completed.
- * Notice the data completion to the upper layer.
- */
-
- /*
- * bios are processed from the head of the list.
- * So the completing bio should always be rq->bio.
- * If it's not, something wrong is happening.
- */
- if (tio->orig->bio != bio)
- DMERR("bio completion is going in the middle of the request");
-
- /*
- * Update the original request.
- * Do not use blk_end_request() here, because it may complete
- * the original request before the clone, and break the ordering.
- */
- blk_update_request(tio->orig, 0, nr_bytes);
- }
-
static struct dm_rq_target_io *tio_from_request(struct request *rq)
{
return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special);
dm_put(md);
}
-static void free_rq_clone(struct request *clone, bool must_be_mapped)
+static void free_rq_clone(struct request *clone)
{
struct dm_rq_target_io *tio = clone->end_io_data;
struct mapped_device *md = tio->md;
- blk_rq_unprep_clone(clone);
- WARN_ON_ONCE(must_be_mapped && !clone->q);
--
if (md->type == DM_TYPE_MQ_REQUEST_BASED)
/* stacked on blk-mq queue(s) */
tio->ti->type->release_clone_rq(clone);
rq->sense_len = clone->sense_len;
}
- free_rq_clone(clone, true);
+ free_rq_clone(clone);
if (!rq->q->mq_ops)
blk_end_request_all(rq, error);
else
}
if (clone)
- free_rq_clone(clone, false);
+ free_rq_clone(clone);
}
/*
spin_lock_irqsave(q->queue_lock, flags);
blk_requeue_request(q, rq);
+ blk_run_queue_async(q);
spin_unlock_irqrestore(q->queue_lock, flags);
}
struct mapped_device *md = q->queuedata;
struct dm_table *map = dm_get_live_table_fast(md);
struct dm_target *ti;
- sector_t max_sectors;
- int max_size = 0;
+ sector_t max_sectors, max_size = 0;
if (unlikely(!map))
goto out;
max_sectors = min(max_io_len(bvm->bi_sector, ti),
(sector_t) queue_max_sectors(q));
max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size;
- if (unlikely(max_size < 0)) /* this shouldn't _ever_ happen */
- max_size = 0;
+
+ /*
+ * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t
+ * to the targets' merge function since it holds sectors not bytes).
+ * Just doing this as an interim fix for stable@ because the more
+ * comprehensive cleanup of switching to sector_t will impact every
+ * DM target that implements a ->merge hook.
+ */
+ if (max_size > INT_MAX)
+ max_size = INT_MAX;
/*
* merge_bvec_fn() returns number of bytes
* max is precomputed maximal io size
*/
if (max_size && ti->type->merge)
- max_size = ti->type->merge(ti, bvm, biovec, max_size);
+ max_size = ti->type->merge(ti, bvm, biovec, (int) max_size);
/*
* If the target doesn't support merge method and some of the devices
* provided their merge_bvec method (we know this by looking for the
dm_complete_request(rq, r);
}
- static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
- void *data)
+ static void setup_clone(struct request *clone, struct request *rq,
+ struct dm_rq_target_io *tio)
{
- struct dm_rq_target_io *tio = data;
- struct dm_rq_clone_bio_info *info =
- container_of(bio, struct dm_rq_clone_bio_info, clone);
-
- info->orig = bio_orig;
- info->tio = tio;
- bio->bi_end_io = end_clone_bio;
-
- return 0;
- }
-
- static int setup_clone(struct request *clone, struct request *rq,
- struct dm_rq_target_io *tio, gfp_t gfp_mask)
- {
- int r;
-
- r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
- dm_rq_bio_constructor, tio);
- if (r)
- return r;
-
- clone->cmd = rq->cmd;
- clone->cmd_len = rq->cmd_len;
- clone->sense = rq->sense;
+ blk_rq_prep_clone(clone, rq);
clone->end_io = end_clone_request;
clone->end_io_data = tio;
-
tio->clone = clone;
-
- return 0;
}
static struct request *clone_rq(struct request *rq, struct mapped_device *md,
clone = tio->clone;
blk_rq_init(NULL, clone);
- if (setup_clone(clone, rq, tio, gfp_mask)) {
- /* -ENOMEM */
- if (alloc_clone)
- free_clone_request(md, clone);
- return NULL;
- }
+ setup_clone(clone, rq, tio);
return clone;
}
dm_kill_unmapped_request(rq, r);
return r;
}
- if (IS_ERR(clone))
- return DM_MAPIO_REQUEUE;
+ if (r != DM_MAPIO_REMAPPED)
+ return r;
- if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
- /* -ENOMEM */
- ti->type->release_clone_rq(clone);
- return DM_MAPIO_REQUEUE;
- }
+ setup_clone(clone, rq, tio);
}
switch (r) {
goto out;
}
- BUG_ON(!p || md->io_pool || md->rq_pool || md->bs);
-
md->io_pool = p->io_pool;
p->io_pool = NULL;
md->rq_pool = p->rq_pool;
if (dm_table_get_type(map) == DM_TYPE_REQUEST_BASED) {
/* clone request is allocated at the end of the pdu */
tio->clone = (void *)blk_mq_rq_to_pdu(rq) + sizeof(struct dm_rq_target_io);
- if (!clone_rq(rq, md, tio, GFP_ATOMIC))
- return BLK_MQ_RQ_QUEUE_BUSY;
+ (void) clone_rq(rq, md, tio, GFP_ATOMIC);
queue_kthread_work(&md->kworker, &tio->work);
} else {
/* Direct call is fine since .queue_rq allows allocations */
- if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
- dm_requeue_unmapped_original_request(md, rq);
+ if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
+ /* Undo dm_start_request() before requeuing */
+ rq_completed(md, rq_data_dir(rq), false);
+ return BLK_MQ_RQ_QUEUE_BUSY;
+ }
}
return BLK_MQ_RQ_QUEUE_OK;
}
EXPORT_SYMBOL_GPL(dm_noflush_suspending);
- struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned type,
- unsigned integrity, unsigned per_bio_data_size)
+ struct dm_md_mempools *dm_alloc_bio_mempools(unsigned integrity,
+ unsigned per_bio_data_size)
{
- struct dm_md_mempools *pools = kzalloc(sizeof(*pools), GFP_KERNEL);
- struct kmem_cache *cachep = NULL;
- unsigned int pool_size = 0;
+ struct dm_md_mempools *pools;
+ unsigned int pool_size = dm_get_reserved_bio_based_ios();
unsigned int front_pad;
+ pools = kzalloc(sizeof(*pools), GFP_KERNEL);
if (!pools)
return NULL;
- type = filter_md_type(type, md);
+ front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) +
+ offsetof(struct dm_target_io, clone);
- switch (type) {
- case DM_TYPE_BIO_BASED:
- cachep = _io_cache;
- pool_size = dm_get_reserved_bio_based_ios();
- front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
- break;
- case DM_TYPE_REQUEST_BASED:
- cachep = _rq_tio_cache;
- pool_size = dm_get_reserved_rq_based_ios();
- pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache);
- if (!pools->rq_pool)
- goto out;
- /* fall through to setup remaining rq-based pools */
- case DM_TYPE_MQ_REQUEST_BASED:
- if (!pool_size)
- pool_size = dm_get_reserved_rq_based_ios();
- front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
- /* per_bio_data_size is not used. See __bind_mempools(). */
- WARN_ON(per_bio_data_size != 0);
- break;
- default:
- BUG();
- }
-
- if (cachep) {
- pools->io_pool = mempool_create_slab_pool(pool_size, cachep);
- if (!pools->io_pool)
- goto out;
- }
+ pools->io_pool = mempool_create_slab_pool(pool_size, _io_cache);
+ if (!pools->io_pool)
+ goto out;
pools->bs = bioset_create_nobvec(pool_size, front_pad);
if (!pools->bs)
goto out;
return pools;
-
out:
dm_free_md_mempools(pools);
+ return NULL;
+ }
+
+ struct dm_md_mempools *dm_alloc_rq_mempools(struct mapped_device *md,
+ unsigned type)
+ {
+ unsigned int pool_size = dm_get_reserved_rq_based_ios();
+ struct dm_md_mempools *pools;
+
+ pools = kzalloc(sizeof(*pools), GFP_KERNEL);
+ if (!pools)
+ return NULL;
+
+ if (filter_md_type(type, md) == DM_TYPE_REQUEST_BASED) {
+ pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache);
+ if (!pools->rq_pool)
+ goto out;
+ }
+ pools->io_pool = mempool_create_slab_pool(pool_size, _rq_tio_cache);
+ if (!pools->io_pool)
+ goto out;
+
+ return pools;
+ out:
+ dm_free_md_mempools(pools);
return NULL;
}
else
btrfsic_submit_bio(rw, bio);
- if (bio_flagged(bio, BIO_EOPNOTSUPP))
- ret = -EOPNOTSUPP;
bio_put(bio);
return ret;
}
start >> PAGE_CACHE_SHIFT);
if (eb && atomic_inc_not_zero(&eb->refs)) {
rcu_read_unlock();
+ /*
+ * Lock our eb's refs_lock to avoid races with
+ * free_extent_buffer. When we get our eb it might be flagged
+ * with EXTENT_BUFFER_STALE and another task running
+ * free_extent_buffer might have seen that flag set,
+ * eb->refs == 2, that the buffer isn't under IO (dirty and
+ * writeback flags not set) and it's still in the tree (flag
+ * EXTENT_BUFFER_TREE_REF set), therefore being in the process
+ * of decrementing the extent buffer's reference count twice.
+ * So here we could race and increment the eb's reference count,
+ * clear its stale flag, mark it as dirty and drop our reference
+ * before the other task finishes executing free_extent_buffer,
+ * which would later result in an attempt to free an extent
+ * buffer that is dirty.
+ */
+ if (test_bit(EXTENT_BUFFER_STALE, &eb->bflags)) {
+ spin_lock(&eb->refs_lock);
+ spin_unlock(&eb->refs_lock);
+ }
mark_extent_buffer_accessed(eb, NULL);
return eb;
}
waitqueue_active(&fs_info->async_submit_wait))
wake_up(&fs_info->async_submit_wait);
- BUG_ON(atomic_read(&cur->bi_cnt) == 0);
+ BUG_ON(atomic_read(&cur->__bi_cnt) == 0);
/*
* if we're doing the sync list, record that our
{
u64 chunk_offset;
+ ASSERT(mutex_is_locked(&extent_root->fs_info->chunk_mutex));
chunk_offset = find_next_chunk(extent_root->fs_info);
return __btrfs_alloc_chunk(trans, extent_root, chunk_offset, type);
}
static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio, int err)
{
- if (likely(bbio->flags & BTRFS_BIO_ORIG_BIO_SUBMITTED))
- bio_endio_nodec(bio, err);
- else
- bio_endio(bio, err);
+ bio->bi_private = bbio->private;
+ bio->bi_end_io = bbio->end_io;
+ bio_endio(bio, err);
+
btrfs_put_bbio(bbio);
}
bio = bbio->orig_bio;
}
- bio->bi_private = bbio->private;
- bio->bi_end_io = bbio->end_io;
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
/* only send an error to the higher layers if it is
* beyond the tolerance of the btrfs bio
/* Shoud be the original bio. */
WARN_ON(bio != bbio->orig_bio);
- bio->bi_private = bbio->private;
- bio->bi_end_io = bbio->end_io;
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
bio->bi_iter.bi_sector = logical >> 9;
if (dev_nr < total_devs - 1) {
bio = btrfs_bio_clone(first_bio, GFP_NOFS);
BUG_ON(!bio); /* -ENOMEM */
- } else {
+ } else
bio = first_bio;
- bbio->flags |= BTRFS_BIO_ORIG_BIO_SUBMITTED;
- }
submit_stripe_bio(root, bbio, bio,
bbio->stripes[dev_nr].physical, dev_nr, rw,
unsigned int bi_seg_front_size;
unsigned int bi_seg_back_size;
- atomic_t bi_remaining;
+ atomic_t __bi_remaining;
bio_end_io_t *bi_end_io;
unsigned short bi_max_vecs; /* max bvl_vecs we can hold */
- atomic_t bi_cnt; /* pin count */
+ atomic_t __bi_cnt; /* pin count */
struct bio_vec *bi_io_vec; /* the actual vec list */
* bio flags
*/
#define BIO_UPTODATE 0 /* ok after I/O completion */
- #define BIO_RW_BLOCK 1 /* RW_AHEAD set, and read/write would block */
- #define BIO_EOF 2 /* out-out-bounds error */
- #define BIO_SEG_VALID 3 /* bi_phys_segments valid */
- #define BIO_CLONED 4 /* doesn't own data */
- #define BIO_BOUNCED 5 /* bio is a bounce bio */
- #define BIO_USER_MAPPED 6 /* contains user pages */
- #define BIO_EOPNOTSUPP 7 /* not supported */
- #define BIO_NULL_MAPPED 8 /* contains invalid user pages */
- #define BIO_QUIET 9 /* Make BIO Quiet */
- #define BIO_SNAP_STABLE 10 /* bio data must be snapshotted during write */
+ #define BIO_SEG_VALID 1 /* bi_phys_segments valid */
+ #define BIO_CLONED 2 /* doesn't own data */
+ #define BIO_BOUNCED 3 /* bio is a bounce bio */
+ #define BIO_USER_MAPPED 4 /* contains user pages */
+ #define BIO_NULL_MAPPED 5 /* contains invalid user pages */
+ #define BIO_QUIET 6 /* Make BIO Quiet */
+ #define BIO_SNAP_STABLE 7 /* bio data must be snapshotted during write */
+ #define BIO_CHAIN 8 /* chained bio, ->bi_remaining in effect */
+ #define BIO_REFFED 9 /* bio has elevated ->bi_cnt */
/*
* Flags starting here get preserved by bio_reset() - this includes
__REQ_HASHED, /* on IO scheduler merge hash */
__REQ_MQ_INFLIGHT, /* track inflight for MQ */
__REQ_NO_TIMEOUT, /* requests may never expire */
+ __REQ_CLONE, /* cloned bios */
__REQ_NR_BITS, /* stops here */
};
/* This mask is used for both bio and request merge checking */
#define REQ_NOMERGE_FLAGS \
- (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA)
+ (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA | REQ_FLUSH_SEQ)
#define REQ_RAHEAD (1ULL << __REQ_RAHEAD)
#define REQ_THROTTLED (1ULL << __REQ_THROTTLED)
#define REQ_HASHED (1ULL << __REQ_HASHED)
#define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT)
#define REQ_NO_TIMEOUT (1ULL << __REQ_NO_TIMEOUT)
+ #define REQ_CLONE (1ULL << __REQ_CLONE)
#endif /* __LINUX_BLK_TYPES_H */
struct request_queue;
struct elevator_queue;
- struct request_pm_state;
struct blk_trace;
struct request;
struct sg_io_hdr;
enum rq_cmd_type_bits {
REQ_TYPE_FS = 1, /* fs request */
REQ_TYPE_BLOCK_PC, /* scsi command */
- REQ_TYPE_SENSE, /* sense request */
- REQ_TYPE_PM_SUSPEND, /* suspend request */
- REQ_TYPE_PM_RESUME, /* resume request */
- REQ_TYPE_PM_SHUTDOWN, /* shutdown request */
- REQ_TYPE_SPECIAL, /* driver defined type */
- /*
- * for ATA/ATAPI devices. this really doesn't belong here, ide should
- * use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver
- * private REQ_LB opcodes to differentiate what type of request this is
- */
- REQ_TYPE_ATA_TASKFILE,
- REQ_TYPE_ATA_PC,
+ REQ_TYPE_DRV_PRIV, /* driver defined types from here */
};
#define BLK_MAX_CDB 16
struct blk_mq_ctx *mq_ctx;
u64 cmd_flags;
- enum rq_cmd_type_bits cmd_type;
+ unsigned cmd_type;
unsigned long atomic_flags;
int cpu;
return req->ioprio;
}
- /*
- * State information carried for REQ_TYPE_PM_SUSPEND and REQ_TYPE_PM_RESUME
- * requests. Some step values could eventually be made generic.
- */
- struct request_pm_state
- {
- /* PM state machine step value, currently driver specific */
- int pm_step;
- /* requested PM state value (S1, S2, S3, S4, ...) */
- u32 pm_state;
- void* data; /* for driver use */
- };
-
#include <linux/elevator.h>
struct blk_queue_ctx;
struct mutex sysfs_lock;
int bypass_depth;
- int mq_freeze_depth;
+ atomic_t mq_freeze_depth;
#if defined(CONFIG_BLK_DEV_BSG)
bsg_job_fn *bsg_job_fn;
(((rq)->cmd_flags & REQ_STARTED) && \
((rq)->cmd_type == REQ_TYPE_FS))
- #define blk_pm_request(rq) \
- ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \
- (rq)->cmd_type == REQ_TYPE_PM_RESUME)
-
#define blk_rq_cpu_valid(rq) ((rq)->cpu != -1)
#define blk_bidi_rq(rq) ((rq)->next_rq != NULL)
/* rq->queuelist of dequeued request must be list_empty() */
unsigned int len);
extern int blk_rq_check_limits(struct request_queue *q, struct request *rq);
extern int blk_lld_busy(struct request_queue *q);
- extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
- struct bio_set *bs, gfp_t gfp_mask,
- int (*bio_ctr)(struct bio *, struct bio *, void *),
- void *data);
- extern void blk_rq_unprep_clone(struct request *rq);
+ extern void blk_rq_prep_clone(struct request *rq, struct request *rq_src);
extern int blk_insert_cloned_request(struct request_queue *q,
struct request *rq);
extern void blk_delay_queue(struct request_queue *, unsigned long);
extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
struct scsi_ioctl_command __user *);
-extern void blk_queue_bio(struct request_queue *q, struct bio *bio);
-
/*
* A queue has just exitted congestion. Note this in the global counter of
* congested queues, and wake up anyone who was waiting for requests to be
extern void blk_sync_queue(struct request_queue *q);
extern void __blk_stop_queue(struct request_queue *q);
extern void __blk_run_queue(struct request_queue *q);
+ extern void __blk_run_queue_uncond(struct request_queue *q);
extern void blk_run_queue(struct request_queue *);
extern void blk_run_queue_async(struct request_queue *q);
extern int blk_rq_map_user(struct request_queue *, struct request *,
projects / karo-tx-linux.git / commitdiff