#include <linux/task_io_accounting_ops.h>
#include <linux/fault-inject.h>
#include <linux/list_sort.h>
+#include <linux/delay.h>
#define CREATE_TRACE_POINTS
#include <trace/events/block.h>
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
-static int __make_request(struct request_queue *q, struct bio *bio);
+DEFINE_IDA(blk_queue_ida);
/*
* For the allocated request tables
}
EXPORT_SYMBOL(blk_dump_rq_flags);
-/*
- * Make sure that plugs that were pending when this function was entered,
- * are now complete and requests pushed to the queue.
-*/
-static inline void queue_sync_plugs(struct request_queue *q)
-{
- /*
- * If the current process is plugged and has barriers submitted,
- * we will livelock if we don't unplug first.
- */
- blk_flush_plug(current);
-}
-
static void blk_delay_work(struct work_struct *work)
{
struct request_queue *q;
q = container_of(work, struct request_queue, delay_work.work);
spin_lock_irq(q->queue_lock);
- __blk_run_queue(q, false);
+ __blk_run_queue(q);
spin_unlock_irq(q->queue_lock);
}
*/
void blk_delay_queue(struct request_queue *q, unsigned long msecs)
{
- schedule_delayed_work(&q->delay_work, msecs_to_jiffies(msecs));
+ queue_delayed_work(kblockd_workqueue, &q->delay_work,
+ msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_delay_queue);
WARN_ON(!irqs_disabled());
queue_flag_clear(QUEUE_FLAG_STOPPED, q);
- __blk_run_queue(q, false);
+ __blk_run_queue(q);
}
EXPORT_SYMBOL(blk_start_queue);
**/
void blk_stop_queue(struct request_queue *q)
{
- cancel_delayed_work(&q->delay_work);
+ __cancel_delayed_work(&q->delay_work);
queue_flag_set(QUEUE_FLAG_STOPPED, q);
}
EXPORT_SYMBOL(blk_stop_queue);
{
del_timer_sync(&q->timeout);
cancel_delayed_work_sync(&q->delay_work);
- queue_sync_plugs(q);
}
EXPORT_SYMBOL(blk_sync_queue);
/**
* __blk_run_queue - run a single device queue
* @q: The queue to run
- * @force_kblockd: Don't run @q->request_fn directly. Use kblockd.
*
* Description:
* See @blk_run_queue. This variant must be called with the queue lock
* held and interrupts disabled.
- *
*/
-void __blk_run_queue(struct request_queue *q, bool force_kblockd)
+void __blk_run_queue(struct request_queue *q)
{
if (unlikely(blk_queue_stopped(q)))
return;
- /*
- * Only recurse once to avoid overrunning the stack, let the unplug
- * handling reinvoke the handler shortly if we already got there.
- */
- if (!force_kblockd && !queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
- q->request_fn(q);
- queue_flag_clear(QUEUE_FLAG_REENTER, q);
- } else
- queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
+ q->request_fn(q);
}
EXPORT_SYMBOL(__blk_run_queue);
/**
+ * blk_run_queue_async - run a single device queue in workqueue context
+ * @q: The queue to run
+ *
+ * Description:
+ * Tells kblockd to perform the equivalent of @blk_run_queue on behalf
+ * of us.
+ */
+void blk_run_queue_async(struct request_queue *q)
+{
+ if (likely(!blk_queue_stopped(q))) {
+ __cancel_delayed_work(&q->delay_work);
+ queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
+ }
+}
+EXPORT_SYMBOL(blk_run_queue_async);
+
+/**
* blk_run_queue - run a single device queue
* @q: The queue to run
*
unsigned long flags;
spin_lock_irqsave(q->queue_lock, flags);
- __blk_run_queue(q, false);
+ __blk_run_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_run_queue);
{
kobject_put(&q->kobj);
}
+EXPORT_SYMBOL(blk_put_queue);
-/*
- * Note: If a driver supplied the queue lock, it should not zap that lock
- * unexpectedly as some queue cleanup components like elevator_exit() and
- * blk_throtl_exit() need queue lock.
+/**
+ * blk_drain_queue - drain requests from request_queue
+ * @q: queue to drain
+ * @drain_all: whether to drain all requests or only the ones w/ ELVPRIV
+ *
+ * Drain requests from @q. If @drain_all is set, all requests are drained.
+ * If not, only ELVPRIV requests are drained. The caller is responsible
+ * for ensuring that no new requests which need to be drained are queued.
+ */
+void blk_drain_queue(struct request_queue *q, bool drain_all)
+{
+ while (true) {
+ bool drain = false;
+ int i;
+
+ spin_lock_irq(q->queue_lock);
+
+ elv_drain_elevator(q);
+ if (drain_all)
+ blk_throtl_drain(q);
+
+ /*
+ * This function might be called on a queue which failed
+ * driver init after queue creation. Some drivers
+ * (e.g. fd) get unhappy in such cases. Kick queue iff
+ * dispatch queue has something on it.
+ */
+ if (!list_empty(&q->queue_head))
+ __blk_run_queue(q);
+
+ drain |= q->rq.elvpriv;
+
+ /*
+ * Unfortunately, requests are queued at and tracked from
+ * multiple places and there's no single counter which can
+ * be drained. Check all the queues and counters.
+ */
+ if (drain_all) {
+ drain |= !list_empty(&q->queue_head);
+ for (i = 0; i < 2; i++) {
+ drain |= q->rq.count[i];
+ drain |= q->in_flight[i];
+ drain |= !list_empty(&q->flush_queue[i]);
+ }
+ }
+
+ spin_unlock_irq(q->queue_lock);
+
+ if (!drain)
+ break;
+ msleep(10);
+ }
+}
+
+/**
+ * blk_cleanup_queue - shutdown a request queue
+ * @q: request queue to shutdown
+ *
+ * Mark @q DEAD, drain all pending requests, destroy and put it. All
+ * future requests will be failed immediately with -ENODEV.
*/
void blk_cleanup_queue(struct request_queue *q)
{
- /*
- * We know we have process context here, so we can be a little
- * cautious and ensure that pending block actions on this device
- * are done before moving on. Going into this function, we should
- * not have processes doing IO to this device.
- */
- blk_sync_queue(q);
+ spinlock_t *lock = q->queue_lock;
- del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
+ /* mark @q DEAD, no new request or merges will be allowed afterwards */
mutex_lock(&q->sysfs_lock);
queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
+
+ spin_lock_irq(lock);
+ queue_flag_set(QUEUE_FLAG_NOMERGES, q);
+ queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
+ queue_flag_set(QUEUE_FLAG_DEAD, q);
+
+ if (q->queue_lock != &q->__queue_lock)
+ q->queue_lock = &q->__queue_lock;
+
+ spin_unlock_irq(lock);
mutex_unlock(&q->sysfs_lock);
+ /*
+ * Drain all requests queued before DEAD marking. The caller might
+ * be trying to tear down @q before its elevator is initialized, in
+ * which case we don't want to call into draining.
+ */
if (q->elevator)
- elevator_exit(q->elevator);
+ blk_drain_queue(q, true);
- blk_throtl_exit(q);
+ /* @q won't process any more request, flush async actions */
+ del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
+ blk_sync_queue(q);
+ /* @q is and will stay empty, shutdown and put */
blk_put_queue(q);
}
EXPORT_SYMBOL(blk_cleanup_queue);
if (!q)
return NULL;
+ q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
+ if (q->id < 0)
+ goto fail_q;
+
q->backing_dev_info.ra_pages =
(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
q->backing_dev_info.state = 0;
q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
q->backing_dev_info.name = "block";
+ q->node = node_id;
err = bdi_init(&q->backing_dev_info);
- if (err) {
- kmem_cache_free(blk_requestq_cachep, q);
- return NULL;
- }
+ if (err)
+ goto fail_id;
- if (blk_throtl_init(q)) {
- kmem_cache_free(blk_requestq_cachep, q);
- return NULL;
- }
+ if (blk_throtl_init(q))
+ goto fail_id;
setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
laptop_mode_timer_fn, (unsigned long) q);
setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
INIT_LIST_HEAD(&q->timeout_list);
+ INIT_LIST_HEAD(&q->icq_list);
INIT_LIST_HEAD(&q->flush_queue[0]);
INIT_LIST_HEAD(&q->flush_queue[1]);
INIT_LIST_HEAD(&q->flush_data_in_flight);
q->queue_lock = &q->__queue_lock;
return q;
+
+fail_id:
+ ida_simple_remove(&blk_queue_ida, q->id);
+fail_q:
+ kmem_cache_free(blk_requestq_cachep, q);
+ return NULL;
}
EXPORT_SYMBOL(blk_alloc_queue_node);
if (!uninit_q)
return NULL;
- q = blk_init_allocated_queue_node(uninit_q, rfn, lock, node_id);
+ q = blk_init_allocated_queue(uninit_q, rfn, lock);
if (!q)
blk_cleanup_queue(uninit_q);
blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
spinlock_t *lock)
{
- return blk_init_allocated_queue_node(q, rfn, lock, -1);
-}
-EXPORT_SYMBOL(blk_init_allocated_queue);
-
-struct request_queue *
-blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn,
- spinlock_t *lock, int node_id)
-{
if (!q)
return NULL;
- q->node = node_id;
if (blk_init_free_list(q))
return NULL;
/*
* This also sets hw/phys segments, boundary and size
*/
- blk_queue_make_request(q, __make_request);
+ blk_queue_make_request(q, blk_queue_bio);
q->sg_reserved_size = INT_MAX;
return NULL;
}
-EXPORT_SYMBOL(blk_init_allocated_queue_node);
+EXPORT_SYMBOL(blk_init_allocated_queue);
-int blk_get_queue(struct request_queue *q)
+bool blk_get_queue(struct request_queue *q)
{
- if (likely(!test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
- kobject_get(&q->kobj);
- return 0;
+ if (likely(!blk_queue_dead(q))) {
+ __blk_get_queue(q);
+ return true;
}
- return 1;
+ return false;
}
+EXPORT_SYMBOL(blk_get_queue);
static inline void blk_free_request(struct request_queue *q, struct request *rq)
{
- BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
-
- if (rq->cmd_flags & REQ_ELVPRIV)
+ if (rq->cmd_flags & REQ_ELVPRIV) {
elv_put_request(q, rq);
+ if (rq->elv.icq)
+ put_io_context(rq->elv.icq->ioc);
+ }
+
mempool_free(rq, q->rq.rq_pool);
}
static struct request *
-blk_alloc_request(struct request_queue *q, int flags, int priv, gfp_t gfp_mask)
+blk_alloc_request(struct request_queue *q, struct io_cq *icq,
+ unsigned int flags, gfp_t gfp_mask)
{
struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask);
rq->cmd_flags = flags | REQ_ALLOCED;
- if (priv) {
+ if (flags & REQ_ELVPRIV) {
+ rq->elv.icq = icq;
if (unlikely(elv_set_request(q, rq, gfp_mask))) {
mempool_free(rq, q->rq.rq_pool);
return NULL;
}
- rq->cmd_flags |= REQ_ELVPRIV;
+ /* @rq->elv.icq holds on to io_context until @rq is freed */
+ if (icq)
+ get_io_context(icq->ioc);
}
return rq;
* A request has just been released. Account for it, update the full and
* congestion status, wake up any waiters. Called under q->queue_lock.
*/
-static void freed_request(struct request_queue *q, int sync, int priv)
+static void freed_request(struct request_queue *q, unsigned int flags)
{
struct request_list *rl = &q->rq;
+ int sync = rw_is_sync(flags);
rl->count[sync]--;
- if (priv)
+ if (flags & REQ_ELVPRIV)
rl->elvpriv--;
__freed_request(q, sync);
return true;
}
-/*
- * Get a free request, queue_lock must be held.
- * Returns NULL on failure, with queue_lock held.
- * Returns !NULL on success, with queue_lock *not held*.
+/**
+ * get_request - get a free request
+ * @q: request_queue to allocate request from
+ * @rw_flags: RW and SYNC flags
+ * @bio: bio to allocate request for (can be %NULL)
+ * @gfp_mask: allocation mask
+ *
+ * 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*.
*/
static struct request *get_request(struct request_queue *q, int rw_flags,
struct bio *bio, gfp_t gfp_mask)
{
struct request *rq = NULL;
struct request_list *rl = &q->rq;
- struct io_context *ioc = NULL;
+ struct elevator_type *et;
+ struct io_context *ioc;
+ struct io_cq *icq = NULL;
const bool is_sync = rw_is_sync(rw_flags) != 0;
- int may_queue, priv = 0;
+ bool retried = false;
+ int may_queue;
+retry:
+ et = q->elevator->type;
+ ioc = current->io_context;
+
+ if (unlikely(blk_queue_dead(q)))
+ return NULL;
may_queue = elv_may_queue(q, rw_flags);
if (may_queue == ELV_MQUEUE_NO)
if (rl->count[is_sync]+1 >= queue_congestion_on_threshold(q)) {
if (rl->count[is_sync]+1 >= q->nr_requests) {
- ioc = current_io_context(GFP_ATOMIC, q->node);
+ /*
+ * We want ioc to record batching state. If it's
+ * not already there, creating a new one requires
+ * dropping queue_lock, which in turn requires
+ * retesting conditions to avoid queue hang.
+ */
+ if (!ioc && !retried) {
+ spin_unlock_irq(q->queue_lock);
+ create_io_context(current, gfp_mask, q->node);
+ spin_lock_irq(q->queue_lock);
+ retried = true;
+ goto retry;
+ }
+
/*
* The queue will fill after this allocation, so set
* it as full, and mark this process as "batching".
rl->count[is_sync]++;
rl->starved[is_sync] = 0;
- if (blk_rq_should_init_elevator(bio)) {
- priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
- if (priv)
- rl->elvpriv++;
+ /*
+ * Decide whether the new request will be managed by elevator. If
+ * so, mark @rw_flags and increment elvpriv. Non-zero elvpriv will
+ * prevent the current elevator from being destroyed until the new
+ * request is freed. This guarantees icq's won't be destroyed and
+ * makes creating new ones safe.
+ *
+ * Also, lookup icq while holding queue_lock. If it doesn't exist,
+ * it will be created after releasing queue_lock.
+ */
+ if (blk_rq_should_init_elevator(bio) &&
+ !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags)) {
+ rw_flags |= REQ_ELVPRIV;
+ rl->elvpriv++;
+ if (et->icq_cache && ioc)
+ icq = ioc_lookup_icq(ioc, q);
}
if (blk_queue_io_stat(q))
rw_flags |= REQ_IO_STAT;
spin_unlock_irq(q->queue_lock);
- rq = blk_alloc_request(q, rw_flags, priv, gfp_mask);
+ /* create icq if missing */
+ if ((rw_flags & REQ_ELVPRIV) && unlikely(et->icq_cache && !icq)) {
+ icq = ioc_create_icq(q, gfp_mask);
+ if (!icq)
+ goto fail_icq;
+ }
+
+ rq = blk_alloc_request(q, icq, rw_flags, gfp_mask);
+
+fail_icq:
if (unlikely(!rq)) {
/*
* Allocation failed presumably due to memory. Undo anything
* wait queue, but this is pretty rare.
*/
spin_lock_irq(q->queue_lock);
- freed_request(q, is_sync, priv);
+ freed_request(q, rw_flags);
/*
* in the very unlikely event that allocation failed and no
return rq;
}
-/*
- * No available requests for this queue, wait for some requests to become
- * available.
+/**
+ * get_request_wait - get a free request with retry
+ * @q: request_queue to allocate request from
+ * @rw_flags: RW and SYNC flags
+ * @bio: bio to allocate request for (can be %NULL)
+ *
+ * Get a free request from @q. This function keeps retrying under memory
+ * pressure and fails iff @q is dead.
*
- * Called with q->queue_lock held, and returns with it unlocked.
+ * 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*.
*/
static struct request *get_request_wait(struct request_queue *q, int rw_flags,
struct bio *bio)
rq = get_request(q, rw_flags, bio, GFP_NOIO);
while (!rq) {
DEFINE_WAIT(wait);
- struct io_context *ioc;
struct request_list *rl = &q->rq;
+ if (unlikely(blk_queue_dead(q)))
+ return NULL;
+
prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
TASK_UNINTERRUPTIBLE);
* up to a big batch of them for a small period time.
* See ioc_batching, ioc_set_batching
*/
- ioc = current_io_context(GFP_NOIO, q->node);
- ioc_set_batching(q, ioc);
+ create_io_context(current, GFP_NOIO, q->node);
+ ioc_set_batching(q, current->io_context);
spin_lock_irq(q->queue_lock);
finish_wait(&rl->wait[is_sync], &wait);
BUG_ON(rw != READ && rw != WRITE);
spin_lock_irq(q->queue_lock);
- if (gfp_mask & __GFP_WAIT) {
+ if (gfp_mask & __GFP_WAIT)
rq = get_request_wait(q, rw, NULL);
- } else {
+ else
rq = get_request(q, rw, NULL, gfp_mask);
- if (!rq)
- spin_unlock_irq(q->queue_lock);
- }
+ if (!rq)
+ spin_unlock_irq(q->queue_lock);
/* q->queue_lock is unlocked at this point */
return rq;
__elv_add_request(q, rq, where);
}
-/**
- * blk_insert_request - insert a special request into a request queue
- * @q: request queue where request should be inserted
- * @rq: request to be inserted
- * @at_head: insert request at head or tail of queue
- * @data: private data
- *
- * Description:
- * Many block devices need to execute commands asynchronously, so they don't
- * block the whole kernel from preemption during request execution. This is
- * accomplished normally by inserting aritficial requests tagged as
- * REQ_TYPE_SPECIAL in to the corresponding request queue, and letting them
- * be scheduled for actual execution by the request queue.
- *
- * We have the option of inserting the head or the tail of the queue.
- * Typically we use the tail for new ioctls and so forth. We use the head
- * of the queue for things like a QUEUE_FULL message from a device, or a
- * host that is unable to accept a particular command.
- */
-void blk_insert_request(struct request_queue *q, struct request *rq,
- int at_head, void *data)
-{
- int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
- unsigned long flags;
-
- /*
- * tell I/O scheduler that this isn't a regular read/write (ie it
- * must not attempt merges on this) and that it acts as a soft
- * barrier
- */
- rq->cmd_type = REQ_TYPE_SPECIAL;
-
- rq->special = data;
-
- spin_lock_irqsave(q->queue_lock, flags);
-
- /*
- * If command is tagged, release the tag
- */
- if (blk_rq_tagged(rq))
- blk_queue_end_tag(q, rq);
-
- add_acct_request(q, rq, where);
- __blk_run_queue(q, false);
- spin_unlock_irqrestore(q->queue_lock, flags);
-}
-EXPORT_SYMBOL(blk_insert_request);
-
static void part_round_stats_single(int cpu, struct hd_struct *part,
unsigned long now)
{
* it didn't come out of our reserved rq pools
*/
if (req->cmd_flags & REQ_ALLOCED) {
- int is_sync = rq_is_sync(req) != 0;
- int priv = req->cmd_flags & REQ_ELVPRIV;
+ unsigned int flags = req->cmd_flags;
BUG_ON(!list_empty(&req->queuelist));
BUG_ON(!hlist_unhashed(&req->hash));
blk_free_request(q, req);
- freed_request(q, is_sync, priv);
+ freed_request(q, flags);
}
}
EXPORT_SYMBOL_GPL(__blk_put_request);
{
const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
- /*
- * Debug stuff, kill later
- */
- if (!rq_mergeable(req)) {
- blk_dump_rq_flags(req, "back");
- return false;
- }
-
if (!ll_back_merge_fn(q, req, bio))
return false;
struct request *req, struct bio *bio)
{
const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
- sector_t sector;
-
- /*
- * Debug stuff, kill later
- */
- if (!rq_mergeable(req)) {
- blk_dump_rq_flags(req, "front");
- return false;
- }
if (!ll_front_merge_fn(q, req, bio))
return false;
if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
blk_rq_set_mixed_merge(req);
- sector = bio->bi_sector;
-
bio->bi_next = req->bio;
req->bio = bio;
return true;
}
-/*
- * Attempts to merge with the plugged list in the current process. Returns
- * true if merge was succesful, otherwise false.
+/**
+ * attempt_plug_merge - try to merge with %current's plugged list
+ * @q: request_queue new bio is being queued at
+ * @bio: new bio being queued
+ * @request_count: out parameter for number of traversed plugged requests
+ *
+ * Determine whether @bio being queued on @q can be merged with a request
+ * on %current's plugged list. Returns %true if merge was successful,
+ * otherwise %false.
+ *
+ * Plugging coalesces IOs from the same issuer for the same purpose without
+ * going through @q->queue_lock. As such it's more of an issuing mechanism
+ * than scheduling, and the request, while may have elvpriv data, is not
+ * added on the elevator at this point. In addition, we don't have
+ * reliable access to the elevator outside queue lock. Only check basic
+ * merging parameters without querying the elevator.
*/
-static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q,
- struct bio *bio)
+static bool attempt_plug_merge(struct request_queue *q, struct bio *bio,
+ unsigned int *request_count)
{
struct blk_plug *plug;
struct request *rq;
bool ret = false;
- plug = tsk->plug;
+ plug = current->plug;
if (!plug)
goto out;
+ *request_count = 0;
list_for_each_entry_reverse(rq, &plug->list, queuelist) {
int el_ret;
- if (rq->q != q)
+ if (rq->q == q)
+ (*request_count)++;
+
+ if (rq->q != q || !blk_rq_merge_ok(rq, bio))
continue;
- el_ret = elv_try_merge(rq, bio);
+ el_ret = blk_try_merge(rq, bio);
if (el_ret == ELEVATOR_BACK_MERGE) {
ret = bio_attempt_back_merge(q, rq, bio);
if (ret)
void init_request_from_bio(struct request *req, struct bio *bio)
{
- req->cpu = bio->bi_comp_cpu;
req->cmd_type = REQ_TYPE_FS;
req->cmd_flags |= bio->bi_rw & REQ_COMMON_MASK;
blk_rq_bio_prep(req->q, req, bio);
}
-static int __make_request(struct request_queue *q, struct bio *bio)
+void blk_queue_bio(struct request_queue *q, struct bio *bio)
{
const bool sync = !!(bio->bi_rw & REQ_SYNC);
struct blk_plug *plug;
int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
struct request *req;
+ unsigned int request_count = 0;
/*
* low level driver can indicate that it wants pages above a
* Check if we can merge with the plugged list before grabbing
* any locks.
*/
- if (attempt_plug_merge(current, q, bio))
- goto out;
+ if (attempt_plug_merge(q, bio, &request_count))
+ return;
spin_lock_irq(q->queue_lock);
el_ret = elv_merge(q, &req, bio);
if (el_ret == ELEVATOR_BACK_MERGE) {
- BUG_ON(req->cmd_flags & REQ_ON_PLUG);
if (bio_attempt_back_merge(q, req, bio)) {
+ elv_bio_merged(q, req, bio);
if (!attempt_back_merge(q, req))
elv_merged_request(q, req, el_ret);
goto out_unlock;
}
} else if (el_ret == ELEVATOR_FRONT_MERGE) {
- BUG_ON(req->cmd_flags & REQ_ON_PLUG);
if (bio_attempt_front_merge(q, req, bio)) {
+ elv_bio_merged(q, req, bio);
if (!attempt_front_merge(q, req))
elv_merged_request(q, req, el_ret);
goto out_unlock;
* Returns with the queue unlocked.
*/
req = get_request_wait(q, rw_flags, bio);
+ if (unlikely(!req)) {
+ bio_endio(bio, -ENODEV); /* @q is dead */
+ goto out_unlock;
+ }
/*
* After dropping the lock and possibly sleeping here, our request
*/
init_request_from_bio(req, bio);
- if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) ||
- bio_flagged(bio, BIO_CPU_AFFINE)) {
- req->cpu = blk_cpu_to_group(get_cpu());
- put_cpu();
- }
+ if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags))
+ req->cpu = raw_smp_processor_id();
plug = current->plug;
if (plug) {
- if (!plug->should_sort && !list_empty(&plug->list)) {
- struct request *__rq;
-
- __rq = list_entry_rq(plug->list.prev);
- if (__rq->q != q)
- plug->should_sort = 1;
- }
/*
- * Debug flag, kill later
+ * If this is the first request added after a plug, fire
+ * of a plug trace. If others have been added before, check
+ * if we have multiple devices in this plug. If so, make a
+ * note to sort the list before dispatch.
*/
- req->cmd_flags |= REQ_ON_PLUG;
+ if (list_empty(&plug->list))
+ trace_block_plug(q);
+ else {
+ if (!plug->should_sort) {
+ struct request *__rq;
+
+ __rq = list_entry_rq(plug->list.prev);
+ if (__rq->q != q)
+ plug->should_sort = 1;
+ }
+ if (request_count >= BLK_MAX_REQUEST_COUNT) {
+ blk_flush_plug_list(plug, false);
+ trace_block_plug(q);
+ }
+ }
list_add_tail(&req->queuelist, &plug->list);
drive_stat_acct(req, 1);
} else {
spin_lock_irq(q->queue_lock);
add_acct_request(q, req, where);
- __blk_run_queue(q, false);
+ __blk_run_queue(q);
out_unlock:
spin_unlock_irq(q->queue_lock);
}
-out:
- return 0;
}
+EXPORT_SYMBOL_GPL(blk_queue_bio); /* for device mapper only */
/*
* If bio->bi_dev is a partition, remap the location
}
__setup("fail_make_request=", setup_fail_make_request);
-static int should_fail_request(struct bio *bio)
+static bool should_fail_request(struct hd_struct *part, unsigned int bytes)
{
- struct hd_struct *part = bio->bi_bdev->bd_part;
-
- if (part_to_disk(part)->part0.make_it_fail || part->make_it_fail)
- return should_fail(&fail_make_request, bio->bi_size);
-
- return 0;
+ return part->make_it_fail && should_fail(&fail_make_request, bytes);
}
static int __init fail_make_request_debugfs(void)
{
- return init_fault_attr_dentries(&fail_make_request,
- "fail_make_request");
+ struct dentry *dir = fault_create_debugfs_attr("fail_make_request",
+ NULL, &fail_make_request);
+
+ return IS_ERR(dir) ? PTR_ERR(dir) : 0;
}
late_initcall(fail_make_request_debugfs);
#else /* CONFIG_FAIL_MAKE_REQUEST */
-static inline int should_fail_request(struct bio *bio)
+static inline bool should_fail_request(struct hd_struct *part,
+ unsigned int bytes)
{
- return 0;
+ return false;
}
#endif /* CONFIG_FAIL_MAKE_REQUEST */
return 0;
}
-/**
- * generic_make_request - hand a buffer to its device driver for I/O
- * @bio: The bio describing the location in memory and on the device.
- *
- * generic_make_request() is used to make I/O requests of block
- * devices. It is passed a &struct bio, which describes the I/O that needs
- * to be done.
- *
- * generic_make_request() does not return any status. The
- * success/failure status of the request, along with notification of
- * completion, is delivered asynchronously through the bio->bi_end_io
- * function described (one day) else where.
- *
- * The caller of generic_make_request must make sure that bi_io_vec
- * are set to describe the memory buffer, and that bi_dev and bi_sector are
- * set to describe the device address, and the
- * bi_end_io and optionally bi_private are set to describe how
- * completion notification should be signaled.
- *
- * generic_make_request and the drivers it calls may use bi_next if this
- * bio happens to be merged with someone else, and may change bi_dev and
- * bi_sector for remaps as it sees fit. So the values of these fields
- * should NOT be depended on after the call to generic_make_request.
- */
-static inline void __generic_make_request(struct bio *bio)
+static noinline_for_stack bool
+generic_make_request_checks(struct bio *bio)
{
struct request_queue *q;
- sector_t old_sector;
- int ret, nr_sectors = bio_sectors(bio);
- dev_t old_dev;
+ int nr_sectors = bio_sectors(bio);
int err = -EIO;
+ char b[BDEVNAME_SIZE];
+ struct hd_struct *part;
might_sleep();
if (bio_check_eod(bio, nr_sectors))
goto end_io;
- /*
- * Resolve the mapping until finished. (drivers are
- * still free to implement/resolve their own stacking
- * by explicitly returning 0)
- *
- * NOTE: we don't repeat the blk_size check for each new device.
- * Stacking drivers are expected to know what they are doing.
- */
- old_sector = -1;
- old_dev = 0;
- do {
- char b[BDEVNAME_SIZE];
-
- q = bdev_get_queue(bio->bi_bdev);
- if (unlikely(!q)) {
- printk(KERN_ERR
- "generic_make_request: Trying to access "
- "nonexistent block-device %s (%Lu)\n",
- bdevname(bio->bi_bdev, b),
- (long long) bio->bi_sector);
- goto end_io;
- }
-
- if (unlikely(!(bio->bi_rw & REQ_DISCARD) &&
- nr_sectors > queue_max_hw_sectors(q))) {
- printk(KERN_ERR "bio too big device %s (%u > %u)\n",
- bdevname(bio->bi_bdev, b),
- bio_sectors(bio),
- queue_max_hw_sectors(q));
- goto end_io;
- }
-
- if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
- goto end_io;
-
- if (should_fail_request(bio))
- goto end_io;
-
- /*
- * If this device has partitions, remap block n
- * of partition p to block n+start(p) of the disk.
- */
- blk_partition_remap(bio);
+ q = bdev_get_queue(bio->bi_bdev);
+ if (unlikely(!q)) {
+ printk(KERN_ERR
+ "generic_make_request: Trying to access "
+ "nonexistent block-device %s (%Lu)\n",
+ bdevname(bio->bi_bdev, b),
+ (long long) bio->bi_sector);
+ goto end_io;
+ }
- if (bio_integrity_enabled(bio) && bio_integrity_prep(bio))
- goto end_io;
+ if (unlikely(!(bio->bi_rw & REQ_DISCARD) &&
+ nr_sectors > queue_max_hw_sectors(q))) {
+ printk(KERN_ERR "bio too big device %s (%u > %u)\n",
+ bdevname(bio->bi_bdev, b),
+ bio_sectors(bio),
+ queue_max_hw_sectors(q));
+ goto end_io;
+ }
- if (old_sector != -1)
- trace_block_bio_remap(q, bio, old_dev, old_sector);
+ part = bio->bi_bdev->bd_part;
+ if (should_fail_request(part, bio->bi_size) ||
+ should_fail_request(&part_to_disk(part)->part0,
+ bio->bi_size))
+ goto end_io;
- old_sector = bio->bi_sector;
- old_dev = bio->bi_bdev->bd_dev;
+ /*
+ * If this device has partitions, remap block n
+ * of partition p to block n+start(p) of the disk.
+ */
+ blk_partition_remap(bio);
- if (bio_check_eod(bio, nr_sectors))
- goto end_io;
+ if (bio_integrity_enabled(bio) && bio_integrity_prep(bio))
+ goto end_io;
- /*
- * Filter flush bio's early so that make_request based
- * drivers without flush support don't have to worry
- * about them.
- */
- if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) {
- bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA);
- if (!nr_sectors) {
- err = 0;
- goto end_io;
- }
- }
+ if (bio_check_eod(bio, nr_sectors))
+ goto end_io;
- if ((bio->bi_rw & REQ_DISCARD) &&
- (!blk_queue_discard(q) ||
- ((bio->bi_rw & REQ_SECURE) &&
- !blk_queue_secdiscard(q)))) {
- err = -EOPNOTSUPP;
+ /*
+ * Filter flush bio's early so that make_request based
+ * drivers without flush support don't have to worry
+ * about them.
+ */
+ if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) {
+ bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA);
+ if (!nr_sectors) {
+ err = 0;
goto end_io;
}
+ }
- blk_throtl_bio(q, &bio);
-
- /*
- * If bio = NULL, bio has been throttled and will be submitted
- * later.
- */
- if (!bio)
- break;
-
- trace_block_bio_queue(q, bio);
+ if ((bio->bi_rw & REQ_DISCARD) &&
+ (!blk_queue_discard(q) ||
+ ((bio->bi_rw & REQ_SECURE) &&
+ !blk_queue_secdiscard(q)))) {
+ err = -EOPNOTSUPP;
+ goto end_io;
+ }
- ret = q->make_request_fn(q, bio);
- } while (ret);
+ if (blk_throtl_bio(q, bio))
+ return false; /* throttled, will be resubmitted later */
- return;
+ trace_block_bio_queue(q, bio);
+ return true;
end_io:
bio_endio(bio, err);
+ return false;
}
-/*
- * We only want one ->make_request_fn to be active at a time,
- * else stack usage with stacked devices could be a problem.
- * So use current->bio_list to keep a list of requests
- * submited by a make_request_fn function.
- * current->bio_list is also used as a flag to say if
- * generic_make_request is currently active in this task or not.
- * If it is NULL, then no make_request is active. If it is non-NULL,
- * then a make_request is active, and new requests should be added
- * at the tail
+/**
+ * generic_make_request - hand a buffer to its device driver for I/O
+ * @bio: The bio describing the location in memory and on the device.
+ *
+ * generic_make_request() is used to make I/O requests of block
+ * devices. It is passed a &struct bio, which describes the I/O that needs
+ * to be done.
+ *
+ * generic_make_request() does not return any status. The
+ * success/failure status of the request, along with notification of
+ * completion, is delivered asynchronously through the bio->bi_end_io
+ * function described (one day) else where.
+ *
+ * The caller of generic_make_request must make sure that bi_io_vec
+ * are set to describe the memory buffer, and that bi_dev and bi_sector are
+ * set to describe the device address, and the
+ * bi_end_io and optionally bi_private are set to describe how
+ * completion notification should be signaled.
+ *
+ * generic_make_request and the drivers it calls may use bi_next if this
+ * bio happens to be merged with someone else, and may resubmit the bio to
+ * a lower device by calling into generic_make_request recursively, which
+ * means the bio should NOT be touched after the call to ->make_request_fn.
*/
void generic_make_request(struct bio *bio)
{
struct bio_list bio_list_on_stack;
+ if (!generic_make_request_checks(bio))
+ return;
+
+ /*
+ * We only want one ->make_request_fn to be active at a time, else
+ * stack usage with stacked devices could be a problem. So use
+ * current->bio_list to keep a list of requests submited by a
+ * make_request_fn function. current->bio_list is also used as a
+ * flag to say if generic_make_request is currently active in this
+ * task or not. If it is NULL, then no make_request is active. If
+ * it is non-NULL, then a make_request is active, and new requests
+ * should be added at the tail
+ */
if (current->bio_list) {
- /* make_request is active */
bio_list_add(current->bio_list, bio);
return;
}
+
/* following loop may be a bit non-obvious, and so deserves some
* explanation.
* Before entering the loop, bio->bi_next is NULL (as all callers
* We pretend that we have just taken it off a longer list, so
* we assign bio_list to a pointer to the bio_list_on_stack,
* thus initialising the bio_list of new bios to be
- * added. __generic_make_request may indeed add some more bios
+ * added. ->make_request() may indeed add some more bios
* through a recursive call to generic_make_request. If it
* did, we find a non-NULL value in bio_list and re-enter the loop
* from the top. In this case we really did just take the bio
* of the top of the list (no pretending) and so remove it from
- * bio_list, and call into __generic_make_request again.
- *
- * The loop was structured like this to make only one call to
- * __generic_make_request (which is important as it is large and
- * inlined) and to keep the structure simple.
+ * bio_list, and call into ->make_request() again.
*/
BUG_ON(bio->bi_next);
bio_list_init(&bio_list_on_stack);
current->bio_list = &bio_list_on_stack;
do {
- __generic_make_request(bio);
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+
+ q->make_request_fn(q, bio);
+
bio = bio_list_pop(current->bio_list);
} while (bio);
current->bio_list = NULL; /* deactivate */
int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
{
unsigned long flags;
+ int where = ELEVATOR_INSERT_BACK;
if (blk_rq_check_limits(q, rq))
return -EIO;
-#ifdef CONFIG_FAIL_MAKE_REQUEST
- if (rq->rq_disk && rq->rq_disk->part0.make_it_fail &&
- should_fail(&fail_make_request, blk_rq_bytes(rq)))
+ if (rq->rq_disk &&
+ should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
return -EIO;
-#endif
spin_lock_irqsave(q->queue_lock, flags);
+ if (unlikely(blk_queue_dead(q))) {
+ spin_unlock_irqrestore(q->queue_lock, flags);
+ return -ENODEV;
+ }
/*
* Submitting request must be dequeued before calling this function
*/
BUG_ON(blk_queued_rq(rq));
- add_acct_request(q, rq, ELEVATOR_INSERT_BACK);
+ if (rq->cmd_flags & (REQ_FLUSH|REQ_FUA))
+ where = ELEVATOR_INSERT_FLUSH;
+
+ add_acct_request(q, rq, where);
+ if (where == ELEVATOR_INSERT_FLUSH)
+ __blk_run_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
return 0;
if (error && req->cmd_type == REQ_TYPE_FS &&
!(req->cmd_flags & REQ_QUIET)) {
- printk(KERN_ERR "end_request: I/O error, dev %s, sector %llu\n",
- req->rq_disk ? req->rq_disk->disk_name : "?",
- (unsigned long long)blk_rq_pos(req));
+ char *error_type;
+
+ switch (error) {
+ case -ENOLINK:
+ error_type = "recoverable transport";
+ break;
+ case -EREMOTEIO:
+ error_type = "critical target";
+ break;
+ case -EBADE:
+ error_type = "critical nexus";
+ break;
+ case -EIO:
+ default:
+ error_type = "I/O";
+ break;
+ }
+ printk(KERN_ERR "end_request: %s error, dev %s, sector %llu\n",
+ error_type, req->rq_disk ? req->rq_disk->disk_name : "?",
+ (unsigned long long)blk_rq_pos(req));
}
blk_account_io_completion(req, nr_bytes);
* size, something has gone terribly wrong.
*/
if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
- printk(KERN_ERR "blk: request botched\n");
+ blk_dump_rq_flags(req, "request botched");
req->__data_len = blk_rq_cur_bytes(req);
}
* %false - we are done with this request
* %true - still buffers pending for this request
**/
-static bool __blk_end_bidi_request(struct request *rq, int error,
+bool __blk_end_bidi_request(struct request *rq, int error,
unsigned int nr_bytes, unsigned int bidi_bytes)
{
if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
#define PLUG_MAGIC 0x91827364
+/**
+ * blk_start_plug - initialize blk_plug and track it inside the task_struct
+ * @plug: The &struct blk_plug that needs to be initialized
+ *
+ * Description:
+ * Tracking blk_plug inside the task_struct will help with auto-flushing the
+ * pending I/O should the task end up blocking between blk_start_plug() and
+ * blk_finish_plug(). This is important from a performance perspective, but
+ * also ensures that we don't deadlock. For instance, if the task is blocking
+ * for a memory allocation, memory reclaim could end up wanting to free a
+ * page belonging to that request that is currently residing in our private
+ * plug. By flushing the pending I/O when the process goes to sleep, we avoid
+ * this kind of deadlock.
+ */
void blk_start_plug(struct blk_plug *plug)
{
struct task_struct *tsk = current;
plug->magic = PLUG_MAGIC;
INIT_LIST_HEAD(&plug->list);
+ INIT_LIST_HEAD(&plug->cb_list);
plug->should_sort = 0;
/*
struct request *rqa = container_of(a, struct request, queuelist);
struct request *rqb = container_of(b, struct request, queuelist);
- return !(rqa->q == rqb->q);
+ return !(rqa->q <= rqb->q);
+}
+
+/*
+ * If 'from_schedule' is true, then postpone the dispatch of requests
+ * until a safe kblockd context. We due this to avoid accidental big
+ * additional stack usage in driver dispatch, in places where the originally
+ * plugger did not intend it.
+ */
+static void queue_unplugged(struct request_queue *q, unsigned int depth,
+ bool from_schedule)
+ __releases(q->queue_lock)
+{
+ trace_block_unplug(q, depth, !from_schedule);
+
+ /*
+ * Don't mess with dead queue.
+ */
+ if (unlikely(blk_queue_dead(q))) {
+ spin_unlock(q->queue_lock);
+ return;
+ }
+
+ /*
+ * If we are punting this to kblockd, then we can safely drop
+ * the queue_lock before waking kblockd (which needs to take
+ * this lock).
+ */
+ if (from_schedule) {
+ spin_unlock(q->queue_lock);
+ blk_run_queue_async(q);
+ } else {
+ __blk_run_queue(q);
+ spin_unlock(q->queue_lock);
+ }
+
}
-static void flush_plug_list(struct blk_plug *plug)
+static void flush_plug_callbacks(struct blk_plug *plug)
+{
+ LIST_HEAD(callbacks);
+
+ if (list_empty(&plug->cb_list))
+ return;
+
+ list_splice_init(&plug->cb_list, &callbacks);
+
+ while (!list_empty(&callbacks)) {
+ struct blk_plug_cb *cb = list_first_entry(&callbacks,
+ struct blk_plug_cb,
+ list);
+ list_del(&cb->list);
+ cb->callback(cb);
+ }
+}
+
+void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
struct request_queue *q;
unsigned long flags;
struct request *rq;
+ LIST_HEAD(list);
+ unsigned int depth;
BUG_ON(plug->magic != PLUG_MAGIC);
+ flush_plug_callbacks(plug);
if (list_empty(&plug->list))
return;
- if (plug->should_sort)
- list_sort(NULL, &plug->list, plug_rq_cmp);
+ list_splice_init(&plug->list, &list);
+
+ if (plug->should_sort) {
+ list_sort(NULL, &list, plug_rq_cmp);
+ plug->should_sort = 0;
+ }
q = NULL;
+ depth = 0;
+
+ /*
+ * Save and disable interrupts here, to avoid doing it for every
+ * queue lock we have to take.
+ */
local_irq_save(flags);
- while (!list_empty(&plug->list)) {
- rq = list_entry_rq(plug->list.next);
+ while (!list_empty(&list)) {
+ rq = list_entry_rq(list.next);
list_del_init(&rq->queuelist);
- BUG_ON(!(rq->cmd_flags & REQ_ON_PLUG));
BUG_ON(!rq->q);
if (rq->q != q) {
- if (q) {
- __blk_run_queue(q, false);
- spin_unlock(q->queue_lock);
- }
+ /*
+ * This drops the queue lock
+ */
+ if (q)
+ queue_unplugged(q, depth, from_schedule);
q = rq->q;
+ depth = 0;
spin_lock(q->queue_lock);
}
- rq->cmd_flags &= ~REQ_ON_PLUG;
+
+ /*
+ * Short-circuit if @q is dead
+ */
+ if (unlikely(blk_queue_dead(q))) {
+ __blk_end_request_all(rq, -ENODEV);
+ continue;
+ }
/*
* rq is already accounted, so use raw insert
*/
- __elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);
- }
+ if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA))
+ __elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH);
+ else
+ __elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);
- if (q) {
- __blk_run_queue(q, false);
- spin_unlock(q->queue_lock);
+ depth++;
}
- BUG_ON(!list_empty(&plug->list));
- local_irq_restore(flags);
-}
-
-static void __blk_finish_plug(struct task_struct *tsk, struct blk_plug *plug)
-{
- flush_plug_list(plug);
+ /*
+ * This drops the queue lock
+ */
+ if (q)
+ queue_unplugged(q, depth, from_schedule);
- if (plug == tsk->plug)
- tsk->plug = NULL;
+ local_irq_restore(flags);
}
void blk_finish_plug(struct blk_plug *plug)
{
- if (plug)
- __blk_finish_plug(current, plug);
-}
-EXPORT_SYMBOL(blk_finish_plug);
+ blk_flush_plug_list(plug, false);
-void __blk_flush_plug(struct task_struct *tsk, struct blk_plug *plug)
-{
- __blk_finish_plug(tsk, plug);
- tsk->plug = plug;
+ if (plug == current->plug)
+ current->plug = NULL;
}
-EXPORT_SYMBOL(__blk_flush_plug);
+EXPORT_SYMBOL(blk_finish_plug);
int __init blk_dev_init(void)
{