summaryrefslogtreecommitdiff
path: root/block/blk-core.c
diff options
context:
space:
mode:
authorArnd Bergmann <arnd@arndb.de>2012-09-04 17:01:37 +0400
committerArnd Bergmann <arnd@arndb.de>2012-09-04 17:01:37 +0400
commit863e99a8c1ea2b0391491904297f57a0f6a1fdd6 (patch)
tree0e7789f83c0ba3a1bc3c19d3ccf5ea6f84f19db6 /block/blk-core.c
parentdd9bf78040fa0da4cecc228e1682b9682b8cb180 (diff)
parenta849088aa1552b1a28eea3daff599ee22a734ae3 (diff)
downloadlinux-863e99a8c1ea2b0391491904297f57a0f6a1fdd6.tar.xz
Merge commit 'a849088aa1' from rmk/fixes into cleanup/io-pci
As Stephen Rothwell reports, a849088aa155 ("ARM: Fix ioremap() of address zero") from the arm-current tree and commit c2794437091a ("ARM: Add fixed PCI i/o mapping") from the arm-soc tree conflict in a nontrivial way in arch/arm/mm/mmu.c. Rob Herring explains: The PCI i/o reserved area has a dummy physical address of 0 and needs to be skipped by ioremap searches. So we don't set VM_ARM_STATIC_MAPPING to prevent matches by ioremap. The vm_struct settings don't really matter when we do the real mapping of the i/o space. Since commit a849088aa155 is at the start of the fixes branch in the arm tree, we can merge it into the branch that contains the other ioremap changes. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Rob Herring <rob.herring@calxeda.com> Cc: Russell King <rmk+kernel@arm.linux.org.uk>
Diffstat (limited to 'block/blk-core.c')
-rw-r--r--block/blk-core.c253
1 files changed, 145 insertions, 108 deletions
diff --git a/block/blk-core.c b/block/blk-core.c
index 93eb3e4f88ce..4b4dbdfbca89 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -387,7 +387,7 @@ void blk_drain_queue(struct request_queue *q, bool drain_all)
if (!list_empty(&q->queue_head) && q->request_fn)
__blk_run_queue(q);
- drain |= q->rq.elvpriv;
+ drain |= q->nr_rqs_elvpriv;
/*
* Unfortunately, requests are queued at and tracked from
@@ -397,7 +397,7 @@ void blk_drain_queue(struct request_queue *q, bool drain_all)
if (drain_all) {
drain |= !list_empty(&q->queue_head);
for (i = 0; i < 2; i++) {
- drain |= q->rq.count[i];
+ drain |= q->nr_rqs[i];
drain |= q->in_flight[i];
drain |= !list_empty(&q->flush_queue[i]);
}
@@ -416,9 +416,14 @@ void blk_drain_queue(struct request_queue *q, bool drain_all)
* left with hung waiters. We need to wake up those waiters.
*/
if (q->request_fn) {
+ struct request_list *rl;
+
spin_lock_irq(q->queue_lock);
- for (i = 0; i < ARRAY_SIZE(q->rq.wait); i++)
- wake_up_all(&q->rq.wait[i]);
+
+ blk_queue_for_each_rl(rl, q)
+ for (i = 0; i < ARRAY_SIZE(rl->wait); i++)
+ wake_up_all(&rl->wait[i]);
+
spin_unlock_irq(q->queue_lock);
}
}
@@ -517,28 +522,33 @@ void blk_cleanup_queue(struct request_queue *q)
}
EXPORT_SYMBOL(blk_cleanup_queue);
-static int blk_init_free_list(struct request_queue *q)
+int blk_init_rl(struct request_list *rl, struct request_queue *q,
+ gfp_t gfp_mask)
{
- struct request_list *rl = &q->rq;
-
if (unlikely(rl->rq_pool))
return 0;
+ rl->q = q;
rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;
- rl->elvpriv = 0;
init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);
rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
- mempool_free_slab, request_cachep, q->node);
-
+ mempool_free_slab, request_cachep,
+ gfp_mask, q->node);
if (!rl->rq_pool)
return -ENOMEM;
return 0;
}
+void blk_exit_rl(struct request_list *rl)
+{
+ if (rl->rq_pool)
+ mempool_destroy(rl->rq_pool);
+}
+
struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
{
return blk_alloc_queue_node(gfp_mask, -1);
@@ -680,7 +690,7 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
if (!q)
return NULL;
- if (blk_init_free_list(q))
+ if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
return NULL;
q->request_fn = rfn;
@@ -722,15 +732,15 @@ bool blk_get_queue(struct request_queue *q)
}
EXPORT_SYMBOL(blk_get_queue);
-static inline void blk_free_request(struct request_queue *q, struct request *rq)
+static inline void blk_free_request(struct request_list *rl, struct request *rq)
{
if (rq->cmd_flags & REQ_ELVPRIV) {
- elv_put_request(q, rq);
+ elv_put_request(rl->q, rq);
if (rq->elv.icq)
put_io_context(rq->elv.icq->ioc);
}
- mempool_free(rq, q->rq.rq_pool);
+ mempool_free(rq, rl->rq_pool);
}
/*
@@ -767,18 +777,23 @@ static void ioc_set_batching(struct request_queue *q, struct io_context *ioc)
ioc->last_waited = jiffies;
}
-static void __freed_request(struct request_queue *q, int sync)
+static void __freed_request(struct request_list *rl, int sync)
{
- struct request_list *rl = &q->rq;
+ struct request_queue *q = rl->q;
- if (rl->count[sync] < queue_congestion_off_threshold(q))
+ /*
+ * bdi isn't aware of blkcg yet. As all async IOs end up root
+ * blkcg anyway, just use root blkcg state.
+ */
+ if (rl == &q->root_rl &&
+ rl->count[sync] < queue_congestion_off_threshold(q))
blk_clear_queue_congested(q, sync);
if (rl->count[sync] + 1 <= q->nr_requests) {
if (waitqueue_active(&rl->wait[sync]))
wake_up(&rl->wait[sync]);
- blk_clear_queue_full(q, sync);
+ blk_clear_rl_full(rl, sync);
}
}
@@ -786,19 +801,20 @@ static void __freed_request(struct request_queue *q, int sync)
* 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, unsigned int flags)
+static void freed_request(struct request_list *rl, unsigned int flags)
{
- struct request_list *rl = &q->rq;
+ struct request_queue *q = rl->q;
int sync = rw_is_sync(flags);
+ q->nr_rqs[sync]--;
rl->count[sync]--;
if (flags & REQ_ELVPRIV)
- rl->elvpriv--;
+ q->nr_rqs_elvpriv--;
- __freed_request(q, sync);
+ __freed_request(rl, sync);
if (unlikely(rl->starved[sync ^ 1]))
- __freed_request(q, sync ^ 1);
+ __freed_request(rl, sync ^ 1);
}
/*
@@ -837,8 +853,8 @@ static struct io_context *rq_ioc(struct bio *bio)
}
/**
- * get_request - get a free request
- * @q: request_queue to allocate request from
+ * __get_request - get a free request
+ * @rl: request list to allocate from
* @rw_flags: RW and SYNC flags
* @bio: bio to allocate request for (can be %NULL)
* @gfp_mask: allocation mask
@@ -850,20 +866,16 @@ static struct io_context *rq_ioc(struct bio *bio)
* 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)
+static struct request *__get_request(struct request_list *rl, int rw_flags,
+ struct bio *bio, gfp_t gfp_mask)
{
+ struct request_queue *q = rl->q;
struct request *rq;
- struct request_list *rl = &q->rq;
- struct elevator_type *et;
- struct io_context *ioc;
+ struct elevator_type *et = q->elevator->type;
+ struct io_context *ioc = rq_ioc(bio);
struct io_cq *icq = NULL;
const bool is_sync = rw_is_sync(rw_flags) != 0;
- bool retried = false;
int may_queue;
-retry:
- et = q->elevator->type;
- ioc = rq_ioc(bio);
if (unlikely(blk_queue_dead(q)))
return NULL;
@@ -875,28 +887,14 @@ retry:
if (rl->count[is_sync]+1 >= queue_congestion_on_threshold(q)) {
if (rl->count[is_sync]+1 >= q->nr_requests) {
/*
- * 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(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".
* This process will be allowed to complete a batch of
* requests, others will be blocked.
*/
- if (!blk_queue_full(q, is_sync)) {
+ if (!blk_rl_full(rl, is_sync)) {
ioc_set_batching(q, ioc);
- blk_set_queue_full(q, is_sync);
+ blk_set_rl_full(rl, is_sync);
} else {
if (may_queue != ELV_MQUEUE_MUST
&& !ioc_batching(q, ioc)) {
@@ -909,7 +907,12 @@ retry:
}
}
}
- blk_set_queue_congested(q, is_sync);
+ /*
+ * bdi isn't aware of blkcg yet. As all async IOs end up
+ * root blkcg anyway, just use root blkcg state.
+ */
+ if (rl == &q->root_rl)
+ blk_set_queue_congested(q, is_sync);
}
/*
@@ -920,6 +923,7 @@ retry:
if (rl->count[is_sync] >= (3 * q->nr_requests / 2))
return NULL;
+ q->nr_rqs[is_sync]++;
rl->count[is_sync]++;
rl->starved[is_sync] = 0;
@@ -935,7 +939,7 @@ retry:
*/
if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) {
rw_flags |= REQ_ELVPRIV;
- rl->elvpriv++;
+ q->nr_rqs_elvpriv++;
if (et->icq_cache && ioc)
icq = ioc_lookup_icq(ioc, q);
}
@@ -945,22 +949,19 @@ retry:
spin_unlock_irq(q->queue_lock);
/* allocate and init request */
- rq = mempool_alloc(q->rq.rq_pool, gfp_mask);
+ rq = mempool_alloc(rl->rq_pool, gfp_mask);
if (!rq)
goto fail_alloc;
blk_rq_init(q, rq);
+ blk_rq_set_rl(rq, rl);
rq->cmd_flags = rw_flags | REQ_ALLOCED;
/* init elvpriv */
if (rw_flags & REQ_ELVPRIV) {
if (unlikely(et->icq_cache && !icq)) {
- create_io_context(gfp_mask, q->node);
- ioc = rq_ioc(bio);
- if (!ioc)
- goto fail_elvpriv;
-
- icq = ioc_create_icq(ioc, q, gfp_mask);
+ if (ioc)
+ icq = ioc_create_icq(ioc, q, gfp_mask);
if (!icq)
goto fail_elvpriv;
}
@@ -1000,7 +1001,7 @@ fail_elvpriv:
rq->elv.icq = NULL;
spin_lock_irq(q->queue_lock);
- rl->elvpriv--;
+ q->nr_rqs_elvpriv--;
spin_unlock_irq(q->queue_lock);
goto out;
@@ -1013,7 +1014,7 @@ fail_alloc:
* queue, but this is pretty rare.
*/
spin_lock_irq(q->queue_lock);
- freed_request(q, rw_flags);
+ freed_request(rl, rw_flags);
/*
* in the very unlikely event that allocation failed and no
@@ -1029,56 +1030,58 @@ rq_starved:
}
/**
- * get_request_wait - get a free request with retry
+ * 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 keeps retrying under memory
- * pressure and fails iff @q is dead.
+ * 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*.
*/
-static struct request *get_request_wait(struct request_queue *q, int rw_flags,
- struct bio *bio)
+static struct request *get_request(struct request_queue *q, int rw_flags,
+ struct bio *bio, gfp_t gfp_mask)
{
const bool is_sync = rw_is_sync(rw_flags) != 0;
+ DEFINE_WAIT(wait);
+ struct request_list *rl;
struct request *rq;
- rq = get_request(q, rw_flags, bio, GFP_NOIO);
- while (!rq) {
- DEFINE_WAIT(wait);
- struct request_list *rl = &q->rq;
-
- if (unlikely(blk_queue_dead(q)))
- return NULL;
+ rl = blk_get_rl(q, bio); /* transferred to @rq on success */
+retry:
+ rq = __get_request(rl, rw_flags, bio, gfp_mask);
+ if (rq)
+ return rq;
- prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
- TASK_UNINTERRUPTIBLE);
+ if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dead(q))) {
+ blk_put_rl(rl);
+ return NULL;
+ }
- trace_block_sleeprq(q, bio, rw_flags & 1);
+ /* wait on @rl and retry */
+ prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
+ TASK_UNINTERRUPTIBLE);
- spin_unlock_irq(q->queue_lock);
- io_schedule();
+ trace_block_sleeprq(q, bio, rw_flags & 1);
- /*
- * After sleeping, we become a "batching" process and
- * will be able to allocate at least one request, and
- * up to a big batch of them for a small period time.
- * See ioc_batching, ioc_set_batching
- */
- create_io_context(GFP_NOIO, q->node);
- ioc_set_batching(q, current->io_context);
+ spin_unlock_irq(q->queue_lock);
+ io_schedule();
- spin_lock_irq(q->queue_lock);
- finish_wait(&rl->wait[is_sync], &wait);
+ /*
+ * After sleeping, we become a "batching" process and will be able
+ * to allocate at least one request, and up to a big batch of them
+ * for a small period time. See ioc_batching, ioc_set_batching
+ */
+ ioc_set_batching(q, current->io_context);
- rq = get_request(q, rw_flags, bio, GFP_NOIO);
- };
+ spin_lock_irq(q->queue_lock);
+ finish_wait(&rl->wait[is_sync], &wait);
- return rq;
+ goto retry;
}
struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
@@ -1087,11 +1090,11 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
BUG_ON(rw != READ && rw != WRITE);
+ /* create ioc upfront */
+ create_io_context(gfp_mask, q->node);
+
spin_lock_irq(q->queue_lock);
- if (gfp_mask & __GFP_WAIT)
- rq = get_request_wait(q, rw, NULL);
- else
- rq = get_request(q, rw, NULL, gfp_mask);
+ rq = get_request(q, rw, NULL, gfp_mask);
if (!rq)
spin_unlock_irq(q->queue_lock);
/* q->queue_lock is unlocked at this point */
@@ -1248,12 +1251,14 @@ void __blk_put_request(struct request_queue *q, struct request *req)
*/
if (req->cmd_flags & REQ_ALLOCED) {
unsigned int flags = req->cmd_flags;
+ struct request_list *rl = blk_rq_rl(req);
BUG_ON(!list_empty(&req->queuelist));
BUG_ON(!hlist_unhashed(&req->hash));
- blk_free_request(q, req);
- freed_request(q, flags);
+ blk_free_request(rl, req);
+ freed_request(rl, flags);
+ blk_put_rl(rl);
}
}
EXPORT_SYMBOL_GPL(__blk_put_request);
@@ -1481,7 +1486,7 @@ get_rq:
* Grab a free request. This is might sleep but can not fail.
* Returns with the queue unlocked.
*/
- req = get_request_wait(q, rw_flags, bio);
+ req = get_request(q, rw_flags, bio, GFP_NOIO);
if (unlikely(!req)) {
bio_endio(bio, -ENODEV); /* @q is dead */
goto out_unlock;
@@ -1702,6 +1707,14 @@ generic_make_request_checks(struct bio *bio)
goto end_io;
}
+ /*
+ * Various block parts want %current->io_context and lazy ioc
+ * allocation ends up trading a lot of pain for a small amount of
+ * memory. Just allocate it upfront. This may fail and block
+ * layer knows how to live with it.
+ */
+ create_io_context(GFP_ATOMIC, q->node);
+
if (blk_throtl_bio(q, bio))
return false; /* throttled, will be resubmitted later */
@@ -2896,23 +2909,47 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth,
}
-static void flush_plug_callbacks(struct blk_plug *plug)
+static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule)
{
LIST_HEAD(callbacks);
- if (list_empty(&plug->cb_list))
- return;
+ while (!list_empty(&plug->cb_list)) {
+ list_splice_init(&plug->cb_list, &callbacks);
- list_splice_init(&plug->cb_list, &callbacks);
-
- while (!list_empty(&callbacks)) {
- struct blk_plug_cb *cb = list_first_entry(&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);
+ list_del(&cb->list);
+ cb->callback(cb, from_schedule);
+ }
+ }
+}
+
+struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data,
+ int size)
+{
+ struct blk_plug *plug = current->plug;
+ struct blk_plug_cb *cb;
+
+ if (!plug)
+ return NULL;
+
+ list_for_each_entry(cb, &plug->cb_list, list)
+ if (cb->callback == unplug && cb->data == data)
+ return cb;
+
+ /* Not currently on the callback list */
+ BUG_ON(size < sizeof(*cb));
+ cb = kzalloc(size, GFP_ATOMIC);
+ if (cb) {
+ cb->data = data;
+ cb->callback = unplug;
+ list_add(&cb->list, &plug->cb_list);
}
+ return cb;
}
+EXPORT_SYMBOL(blk_check_plugged);
void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
@@ -2924,7 +2961,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
BUG_ON(plug->magic != PLUG_MAGIC);
- flush_plug_callbacks(plug);
+ flush_plug_callbacks(plug, from_schedule);
if (list_empty(&plug->list))
return;