* @bdev: device
*
* Locates the passed device's request queue and returns the address of its
- * backing_dev_info
- *
- * Will return NULL if the request queue cannot be located.
+ * backing_dev_info. This function can only be called if @bdev is opened
+ * and the return value is never NULL.
*/
struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
{
- struct backing_dev_info *ret = NULL;
struct request_queue *q = bdev_get_queue(bdev);
- if (q)
- ret = &q->backing_dev_info;
- return ret;
+ return &q->backing_dev_info;
}
EXPORT_SYMBOL(blk_get_backing_dev_info);
* Get a free request from @q. This function may fail under memory
* pressure or if @q is dead.
*
- * Must be callled with @q->queue_lock held and,
- * Returns %NULL on failure, with @q->queue_lock held.
- * Returns !%NULL on success, with @q->queue_lock *not held*.
+ * Must be called with @q->queue_lock held and,
+ * Returns ERR_PTR on failure, with @q->queue_lock held.
+ * Returns request pointer on success, with @q->queue_lock *not held*.
*/
static struct request *__get_request(struct request_list *rl, int rw_flags,
struct bio *bio, gfp_t gfp_mask)
int may_queue;
if (unlikely(blk_queue_dying(q)))
- return NULL;
+ return ERR_PTR(-ENODEV);
may_queue = elv_may_queue(q, rw_flags);
if (may_queue == ELV_MQUEUE_NO)
* process is not a "batcher", and not
* exempted by the IO scheduler
*/
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
}
}
* allocated with any setting of ->nr_requests
*/
if (rl->count[is_sync] >= (3 * q->nr_requests / 2))
- return NULL;
+ return ERR_PTR(-ENOMEM);
q->nr_rqs[is_sync]++;
rl->count[is_sync]++;
rq_starved:
if (unlikely(rl->count[is_sync] == 0))
rl->starved[is_sync] = 1;
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
/**
* Get a free request from @q. If %__GFP_WAIT is set in @gfp_mask, this
* function keeps retrying under memory pressure and fails iff @q is dead.
*
- * Must be callled with @q->queue_lock held and,
- * Returns %NULL on failure, with @q->queue_lock held.
- * Returns !%NULL on success, with @q->queue_lock *not held*.
+ * Must be called with @q->queue_lock held and,
+ * Returns ERR_PTR on failure, with @q->queue_lock held.
+ * Returns request pointer on success, with @q->queue_lock *not held*.
*/
static struct request *get_request(struct request_queue *q, int rw_flags,
struct bio *bio, gfp_t gfp_mask)
rl = blk_get_rl(q, bio); /* transferred to @rq on success */
retry:
rq = __get_request(rl, rw_flags, bio, gfp_mask);
- if (rq)
+ if (!IS_ERR(rq))
return rq;
if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dying(q))) {
blk_put_rl(rl);
- return NULL;
+ return rq;
}
/* wait on @rl and retry */
spin_lock_irq(q->queue_lock);
rq = get_request(q, rw, NULL, gfp_mask);
- if (!rq)
+ if (IS_ERR(rq))
spin_unlock_irq(q->queue_lock);
/* q->queue_lock is unlocked at this point */
{
struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask);
- if (unlikely(!rq))
- return ERR_PTR(-ENOMEM);
+ if (IS_ERR(rq))
+ return rq;
blk_rq_set_block_pc(rq);
rq->__sector = (sector_t) -1;
rq->bio = rq->biotail = NULL;
memset(rq->__cmd, 0, sizeof(rq->__cmd));
- rq->cmd = rq->__cmd;
}
EXPORT_SYMBOL(blk_rq_set_block_pc);
* Returns with the queue unlocked.
*/
req = get_request(q, rw_flags, bio, GFP_NOIO);
- if (unlikely(!req)) {
- bio_endio(bio, -ENODEV); /* @q is dead */
+ if (IS_ERR(req)) {
+ bio_endio(bio, PTR_ERR(req)); /* @q is dead */
goto out_unlock;
}
*/
void blk_mq_freeze_queue(struct request_queue *q)
{
+ bool freeze;
+
spin_lock_irq(q->queue_lock);
- q->mq_freeze_depth++;
+ freeze = !q->mq_freeze_depth++;
spin_unlock_irq(q->queue_lock);
- percpu_ref_kill(&q->mq_usage_counter);
- blk_mq_run_queues(q, false);
+ if (freeze) {
+ percpu_ref_kill(&q->mq_usage_counter);
+ blk_mq_run_queues(q, false);
+ }
wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter));
}
static void blk_mq_unfreeze_queue(struct request_queue *q)
{
- bool wake = false;
+ bool wake;
spin_lock_irq(q->queue_lock);
wake = !--q->mq_freeze_depth;
/* tag was already set */
rq->errors = 0;
+ rq->cmd = rq->__cmd;
+
rq->extra_len = 0;
rq->sense_len = 0;
rq->resid_len = 0;
struct blk_mq_hw_ctx *hctx;
struct request *rq;
struct blk_mq_alloc_data alloc_data;
+ int ret;
- if (blk_mq_queue_enter(q))
- return NULL;
+ ret = blk_mq_queue_enter(q);
+ if (ret)
+ return ERR_PTR(ret);
ctx = blk_mq_get_ctx(q);
hctx = q->mq_ops->map_queue(q, ctx->cpu);
ctx = alloc_data.ctx;
}
blk_mq_put_ctx(ctx);
+ if (!rq)
+ return ERR_PTR(-EWOULDBLOCK);
return rq;
}
EXPORT_SYMBOL(blk_mq_alloc_request);
blk_account_io_start(rq, 1);
}
+ static inline bool hctx_allow_merges(struct blk_mq_hw_ctx *hctx)
+ {
+ return (hctx->flags & BLK_MQ_F_SHOULD_MERGE) &&
+ !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)
{
- struct request_queue *q = hctx->queue;
-
- if (!(hctx->flags & BLK_MQ_F_SHOULD_MERGE)) {
+ if (!hctx_allow_merges(hctx)) {
blk_mq_bio_to_request(rq, bio);
spin_lock(&ctx->lock);
insert_rq:
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);
continue;
set->ops->exit_request(set->driver_data, tags->rqs[i],
hctx_idx, i);
+ tags->rqs[i] = NULL;
}
}
INIT_LIST_HEAD(&tags->page_list);
- tags->rqs = kmalloc_node(set->queue_depth * sizeof(struct request *),
- GFP_KERNEL, set->numa_node);
+ tags->rqs = kzalloc_node(set->queue_depth * sizeof(struct request *),
+ GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
+ set->numa_node);
if (!tags->rqs) {
blk_mq_free_tags(tags);
return NULL;
this_order--;
do {
- page = alloc_pages_node(set->numa_node, GFP_KERNEL,
- this_order);
+ page = alloc_pages_node(set->numa_node,
+ GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
+ this_order);
if (page)
break;
if (!this_order--)
if (set->ops->init_request) {
if (set->ops->init_request(set->driver_data,
tags->rqs[i], hctx_idx, i,
- set->numa_node))
+ set->numa_node)) {
+ tags->rqs[i] = NULL;
goto fail;
+ }
}
p += rq_size;
return tags;
fail:
- pr_warn("%s: failed to allocate requests\n", __func__);
blk_mq_free_rq_map(set, tags, hctx_idx);
return NULL;
}
hctx->tags = set->tags[i];
/*
- * Allocate space for all possible cpus to avoid allocation in
+ * Allocate space for all possible cpus to avoid allocation at
* runtime
*/
hctx->ctxs = kmalloc_node(nr_cpu_ids * sizeof(void *),
queue_for_each_hw_ctx(q, hctx, i) {
/*
- * If not software queues are mapped to this hardware queue,
- * disable it and free the request entries
+ * If no software queues are mapped to this hardware queue,
+ * disable it and free the request entries.
*/
if (!hctx->nr_ctx) {
struct blk_mq_tag_set *set = q->tag_set;
{
struct blk_mq_tag_set *set = q->tag_set;
- blk_mq_freeze_queue(q);
-
mutex_lock(&set->tag_list_lock);
list_del_init(&q->tag_set_list);
blk_mq_update_tag_set_depth(set);
mutex_unlock(&set->tag_list_lock);
-
- blk_mq_unfreeze_queue(q);
}
static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
return NOTIFY_OK;
}
+ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
+ {
+ int i;
+
+ for (i = 0; i < set->nr_hw_queues; i++) {
+ set->tags[i] = blk_mq_init_rq_map(set, i);
+ if (!set->tags[i])
+ goto out_unwind;
+ }
+
+ return 0;
+
+ out_unwind:
+ while (--i >= 0)
+ blk_mq_free_rq_map(set, set->tags[i], i);
+
+ set->tags = NULL;
+ return -ENOMEM;
+ }
+
+ /*
+ * Allocate the request maps associated with this tag_set. Note that this
+ * may reduce the depth asked for, if memory is tight. set->queue_depth
+ * will be updated to reflect the allocated depth.
+ */
+ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
+ {
+ unsigned int depth;
+ int err;
+
+ depth = set->queue_depth;
+ do {
+ err = __blk_mq_alloc_rq_maps(set);
+ if (!err)
+ break;
+
+ set->queue_depth >>= 1;
+ if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) {
+ err = -ENOMEM;
+ break;
+ }
+ } while (set->queue_depth);
+
+ if (!set->queue_depth || err) {
+ pr_err("blk-mq: failed to allocate request map\n");
+ return -ENOMEM;
+ }
+
+ if (depth != set->queue_depth)
+ pr_info("blk-mq: reduced tag depth (%u -> %u)\n",
+ depth, set->queue_depth);
+
+ return 0;
+ }
+
/*
* Alloc a tag set to be associated with one or more request queues.
* May fail with EINVAL for various error conditions. May adjust the
*/
int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
{
- int i;
-
if (!set->nr_hw_queues)
return -EINVAL;
if (!set->queue_depth)
sizeof(struct blk_mq_tags *),
GFP_KERNEL, set->numa_node);
if (!set->tags)
- goto out;
+ return -ENOMEM;
- for (i = 0; i < set->nr_hw_queues; i++) {
- set->tags[i] = blk_mq_init_rq_map(set, i);
- if (!set->tags[i])
- goto out_unwind;
- }
+ if (blk_mq_alloc_rq_maps(set))
+ goto enomem;
mutex_init(&set->tag_list_lock);
INIT_LIST_HEAD(&set->tag_list);
return 0;
-
- out_unwind:
- while (--i >= 0)
- blk_mq_free_rq_map(set, set->tags[i], i);
- out:
+ enomem:
+ kfree(set->tags);
+ set->tags = NULL;
return -ENOMEM;
}
EXPORT_SYMBOL(blk_mq_alloc_tag_set);
}
kfree(set->tags);
+ set->tags = NULL;
}
EXPORT_SYMBOL(blk_mq_free_tag_set);
struct cfq_ttime ttime;
int ioprio; /* the current ioprio */
#ifdef CONFIG_CFQ_GROUP_IOSCHED
- uint64_t blkcg_id; /* the current blkcg ID */
+ uint64_t blkcg_serial_nr; /* the current blkcg serial */
#endif
};
rb_insert_color(&cfqg->rb_node, &st->rb);
}
+ /*
+ * This has to be called only on activation of cfqg
+ */
static void
cfq_update_group_weight(struct cfq_group *cfqg)
{
- BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
-
if (cfqg->new_weight) {
cfqg->weight = cfqg->new_weight;
cfqg->new_weight = 0;
}
+ }
+
+ static void
+ cfq_update_group_leaf_weight(struct cfq_group *cfqg)
+ {
+ BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
if (cfqg->new_leaf_weight) {
cfqg->leaf_weight = cfqg->new_leaf_weight;
/* add to the service tree */
BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
- cfq_update_group_weight(cfqg);
+ /*
+ * Update leaf_weight. We cannot update weight at this point
+ * because cfqg might already have been activated and is
+ * contributing its current weight to the parent's child_weight.
+ */
+ cfq_update_group_leaf_weight(cfqg);
__cfq_group_service_tree_add(st, cfqg);
/*
*/
while ((parent = cfqg_parent(pos))) {
if (propagate) {
+ cfq_update_group_weight(pos);
propagate = !parent->nr_active++;
parent->children_weight += pos->weight;
}
{
struct cfq_data *cfqd = cic_to_cfqd(cic);
struct cfq_queue *sync_cfqq;
- uint64_t id;
+ uint64_t serial_nr;
rcu_read_lock();
- id = bio_blkcg(bio)->id;
+ serial_nr = bio_blkcg(bio)->css.serial_nr;
rcu_read_unlock();
/*
* Check whether blkcg has changed. The condition may trigger
* spuriously on a newly created cic but there's no harm.
*/
- if (unlikely(!cfqd) || likely(cic->blkcg_id == id))
+ if (unlikely(!cfqd) || likely(cic->blkcg_serial_nr == serial_nr))
return;
sync_cfqq = cic_to_cfqq(cic, 1);
cfq_put_queue(sync_cfqq);
}
- cic->blkcg_id = id;
+ cic->blkcg_serial_nr = serial_nr;
}
#else
static inline void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) { }
r = blk_rq_unmap_user(bio);
if (!ret)
ret = r;
- blk_put_request(rq);
return ret;
}
if (hdr->interface_id != 'S')
return -EINVAL;
- if (hdr->cmd_len > BLK_MAX_CDB)
- return -EINVAL;
if (hdr->dxfer_len > (queue_max_hw_sectors(q) << 9))
return -EIO;
if (hdr->flags & SG_FLAG_Q_AT_HEAD)
at_head = 1;
+ ret = -ENOMEM;
rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
- if (!rq)
- goto out;
+ if (IS_ERR(rq))
+ return PTR_ERR(rq);
blk_rq_set_block_pc(rq);
- if (blk_fill_sghdr_rq(q, rq, hdr, mode)) {
- blk_put_request(rq);
- return -EFAULT;
+ if (hdr->cmd_len > BLK_MAX_CDB) {
+ rq->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
+ if (!rq->cmd)
+ goto out_put_request;
}
+ ret = -EFAULT;
+ if (blk_fill_sghdr_rq(q, rq, hdr, mode))
+ goto out_free_cdb;
+
+ ret = 0;
if (hdr->iovec_count) {
size_t iov_data_len;
struct iovec *iov = NULL;
0, NULL, &iov);
if (ret < 0) {
kfree(iov);
- goto out;
+ goto out_free_cdb;
}
iov_data_len = ret;
GFP_KERNEL);
if (ret)
- goto out;
+ goto out_free_cdb;
bio = rq->bio;
memset(sense, 0, sizeof(sense));
hdr->duration = jiffies_to_msecs(jiffies - start_time);
- return blk_complete_sghdr_rq(rq, hdr, bio);
- out:
+ ret = blk_complete_sghdr_rq(rq, hdr, bio);
+
+ out_free_cdb:
+ if (rq->cmd != rq->__cmd)
+ kfree(rq->cmd);
+ out_put_request:
blk_put_request(rq);
-out:
return ret;
}
}
rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT);
- if (!rq) {
- err = -ENOMEM;
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
- goto error_free_buffer;
+ goto error;
}
+ blk_rq_set_block_pc(rq);
cmdlen = COMMAND_SIZE(opcode);
memset(sense, 0, sizeof(sense));
rq->sense = sense;
rq->sense_len = 0;
- blk_rq_set_block_pc(rq);
blk_execute_rq(q, disk, rq, 0);
}
error:
- blk_put_request(rq);
- error_free_buffer:
kfree(buffer);
+ if (rq)
+ blk_put_request(rq);
return err;
}
EXPORT_SYMBOL_GPL(sg_scsi_ioctl);
int err;
rq = blk_get_request(q, WRITE, __GFP_WAIT);
+ if (IS_ERR(rq))
+ return PTR_ERR(rq);
blk_rq_set_block_pc(rq);
rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
rq->cmd[0] = cmd;
int ret = DRIVER_ERROR << 24;
req = blk_get_request(sdev->request_queue, write, __GFP_WAIT);
- if (!req)
+ if (IS_ERR(req))
return ret;
blk_rq_set_block_pc(req);
cmd->tag = req->tag;
- req->cmd = req->__cmd;
cmd->cmnd = req->cmd;
cmd->prot_op = SCSI_PROT_NORMAL;
#include "btrfs_inode.h"
#include "volumes.h"
#include "print-tree.h"
- #include "async-thread.h"
#include "locking.h"
#include "tree-log.h"
#include "free-space-cache.h"
{
struct end_io_wq *end_io_wq = bio->bi_private;
struct btrfs_fs_info *fs_info;
+ struct btrfs_workqueue *wq;
+ btrfs_work_func_t func;
fs_info = end_io_wq->info;
end_io_wq->error = err;
- btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
if (bio->bi_rw & REQ_WRITE) {
- if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
- btrfs_queue_work(fs_info->endio_meta_write_workers,
- &end_io_wq->work);
- else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
- btrfs_queue_work(fs_info->endio_freespace_worker,
- &end_io_wq->work);
- else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
- btrfs_queue_work(fs_info->endio_raid56_workers,
- &end_io_wq->work);
- else
- btrfs_queue_work(fs_info->endio_write_workers,
- &end_io_wq->work);
+ if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
+ wq = fs_info->endio_meta_write_workers;
+ func = btrfs_endio_meta_write_helper;
+ } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) {
+ wq = fs_info->endio_freespace_worker;
+ func = btrfs_freespace_write_helper;
+ } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+ wq = fs_info->endio_raid56_workers;
+ func = btrfs_endio_raid56_helper;
+ } else {
+ wq = fs_info->endio_write_workers;
+ func = btrfs_endio_write_helper;
+ }
} else {
- if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
- btrfs_queue_work(fs_info->endio_raid56_workers,
- &end_io_wq->work);
- else if (end_io_wq->metadata)
- btrfs_queue_work(fs_info->endio_meta_workers,
- &end_io_wq->work);
- else
- btrfs_queue_work(fs_info->endio_workers,
- &end_io_wq->work);
+ if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+ wq = fs_info->endio_raid56_workers;
+ func = btrfs_endio_raid56_helper;
+ } else if (end_io_wq->metadata) {
+ wq = fs_info->endio_meta_workers;
+ func = btrfs_endio_meta_helper;
+ } else {
+ wq = fs_info->endio_workers;
+ func = btrfs_endio_helper;
+ }
}
+
+ btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL);
+ btrfs_queue_work(wq, &end_io_wq->work);
}
/*
async->submit_bio_start = submit_bio_start;
async->submit_bio_done = submit_bio_done;
- btrfs_init_work(&async->work, run_one_async_start,
+ btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
run_one_async_done, run_one_async_free);
async->bio_flags = bio_flags;
if (!device->bdev)
continue;
bdi = blk_get_backing_dev_info(device->bdev);
- if (bdi && bdi_congested(bdi, bdi_bits)) {
+ if (bdi_congested(bdi, bdi_bits)) {
ret = 1;
break;
}
btrfs_set_stack_device_generation(dev_item, 0);
btrfs_set_stack_device_type(dev_item, dev->type);
btrfs_set_stack_device_id(dev_item, dev->devid);
- btrfs_set_stack_device_total_bytes(dev_item, dev->total_bytes);
+ btrfs_set_stack_device_total_bytes(dev_item,
+ dev->disk_total_bytes);
btrfs_set_stack_device_bytes_used(dev_item, dev->bytes_used);
btrfs_set_stack_device_io_align(dev_item, dev->io_align);
btrfs_set_stack_device_io_width(dev_item, dev->io_width);