#include <linux/blkpg.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
-#include <linux/smp_lock.h>
#include <linux/mempool.h>
#include <linux/slab.h>
#include <linux/idr.h>
#define DM_COOKIE_ENV_VAR_NAME "DM_COOKIE"
#define DM_COOKIE_LENGTH 24
+static DEFINE_MUTEX(dm_mutex);
static const char *_name = DM_NAME;
static unsigned int major = 0;
#define DMF_FREEING 3
#define DMF_DELETING 4
#define DMF_NOFLUSH_SUSPENDING 5
-#define DMF_QUEUE_IO_TO_THREAD 6
/*
* Work processed by per-device workqueue.
spinlock_t deferred_lock;
/*
- * An error from the barrier request currently being processed.
- */
- int barrier_error;
-
- /*
- * Protect barrier_error from concurrent endio processing
- * in request-based dm.
- */
- spinlock_t barrier_error_lock;
-
- /*
- * Processing queue (flush/barriers)
+ * Processing queue (flush)
*/
struct workqueue_struct *wq;
- struct work_struct barrier_work;
-
- /* A pointer to the currently processing pre/post flush request */
- struct request *flush_request;
/*
* The current mapping.
/* sysfs handle */
struct kobject kobj;
- /* zero-length barrier that will be cloned and submitted to targets */
- struct bio barrier_bio;
+ /* zero-length flush that will be cloned and submitted to targets */
+ struct bio flush_bio;
};
/*
{
struct mapped_device *md;
- lock_kernel();
+ mutex_lock(&dm_mutex);
spin_lock(&_minor_lock);
md = bdev->bd_disk->private_data;
out:
spin_unlock(&_minor_lock);
- unlock_kernel();
+ mutex_unlock(&dm_mutex);
return md ? 0 : -ENXIO;
}
{
struct mapped_device *md = disk->private_data;
- lock_kernel();
+ mutex_lock(&dm_mutex);
atomic_dec(&md->open_count);
dm_put(md);
- unlock_kernel();
+ mutex_unlock(&dm_mutex);
return 0;
}
/*
* After this is decremented the bio must not be touched if it is
- * a barrier.
+ * a flush.
*/
dm_disk(md)->part0.in_flight[rw] = pending =
atomic_dec_return(&md->pending[rw]);
*/
static void queue_io(struct mapped_device *md, struct bio *bio)
{
- down_write(&md->io_lock);
+ unsigned long flags;
- spin_lock_irq(&md->deferred_lock);
+ spin_lock_irqsave(&md->deferred_lock, flags);
bio_list_add(&md->deferred, bio);
- spin_unlock_irq(&md->deferred_lock);
-
- if (!test_and_set_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags))
- queue_work(md->wq, &md->work);
-
- up_write(&md->io_lock);
+ spin_unlock_irqrestore(&md->deferred_lock, flags);
+ queue_work(md->wq, &md->work);
}
/*
* Target requested pushing back the I/O.
*/
spin_lock_irqsave(&md->deferred_lock, flags);
- if (__noflush_suspending(md)) {
- if (!(io->bio->bi_rw & REQ_HARDBARRIER))
- bio_list_add_head(&md->deferred,
- io->bio);
- } else
+ if (__noflush_suspending(md))
+ bio_list_add_head(&md->deferred, io->bio);
+ else
/* noflush suspend was interrupted. */
io->error = -EIO;
spin_unlock_irqrestore(&md->deferred_lock, flags);
io_error = io->error;
bio = io->bio;
+ end_io_acct(io);
+ free_io(md, io);
+
+ if (io_error == DM_ENDIO_REQUEUE)
+ return;
- if (bio->bi_rw & REQ_HARDBARRIER) {
+ if ((bio->bi_rw & REQ_FLUSH) && bio->bi_size) {
/*
- * There can be just one barrier request so we use
- * a per-device variable for error reporting.
- * Note that you can't touch the bio after end_io_acct
- *
- * We ignore -EOPNOTSUPP for empty flush reported by
- * underlying devices. We assume that if the device
- * doesn't support empty barriers, it doesn't need
- * cache flushing commands.
+ * Preflush done for flush with data, reissue
+ * without REQ_FLUSH.
*/
- if (!md->barrier_error &&
- !(bio_empty_barrier(bio) && io_error == -EOPNOTSUPP))
- md->barrier_error = io_error;
- end_io_acct(io);
- free_io(md, io);
+ bio->bi_rw &= ~REQ_FLUSH;
+ queue_io(md, bio);
} else {
- end_io_acct(io);
- free_io(md, io);
-
- if (io_error != DM_ENDIO_REQUEUE) {
- trace_block_bio_complete(md->queue, bio);
-
- bio_endio(bio, io_error);
- }
+ /* done with normal IO or empty flush */
+ trace_block_bio_complete(md->queue, bio);
+ bio_endio(bio, io_error);
}
}
}
blk_update_request(tio->orig, 0, nr_bytes);
}
-static void store_barrier_error(struct mapped_device *md, int error)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&md->barrier_error_lock, flags);
- /*
- * Basically, the first error is taken, but:
- * -EOPNOTSUPP supersedes any I/O error.
- * Requeue request supersedes any I/O error but -EOPNOTSUPP.
- */
- if (!md->barrier_error || error == -EOPNOTSUPP ||
- (md->barrier_error != -EOPNOTSUPP &&
- error == DM_ENDIO_REQUEUE))
- md->barrier_error = error;
- spin_unlock_irqrestore(&md->barrier_error_lock, flags);
-}
-
/*
* Don't touch any member of the md after calling this function because
* the md may be freed in dm_put() at the end of this function.
static void dm_end_request(struct request *clone, int error)
{
int rw = rq_data_dir(clone);
- int run_queue = 1;
- bool is_barrier = clone->cmd_flags & REQ_HARDBARRIER;
struct dm_rq_target_io *tio = clone->end_io_data;
struct mapped_device *md = tio->md;
struct request *rq = tio->orig;
- if (rq->cmd_type == REQ_TYPE_BLOCK_PC && !is_barrier) {
+ if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
rq->errors = clone->errors;
rq->resid_len = clone->resid_len;
}
free_rq_clone(clone);
-
- if (unlikely(is_barrier)) {
- if (unlikely(error))
- store_barrier_error(md, error);
- run_queue = 0;
- } else
- blk_end_request_all(rq, error);
-
- rq_completed(md, rw, run_queue);
+ blk_end_request_all(rq, error);
+ rq_completed(md, rw, true);
}
static void dm_unprep_request(struct request *rq)
struct request_queue *q = rq->q;
unsigned long flags;
- if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) {
- /*
- * Barrier clones share an original request.
- * Leave it to dm_end_request(), which handles this special
- * case.
- */
- dm_end_request(clone, DM_ENDIO_REQUEUE);
- return;
- }
-
dm_unprep_request(rq);
spin_lock_irqsave(q->queue_lock, flags);
struct dm_rq_target_io *tio = clone->end_io_data;
struct request *rq = tio->orig;
- if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) {
- /*
- * Barrier clones share an original request. So can't use
- * softirq_done with the original.
- * Pass the clone to dm_done() directly in this special case.
- * It is safe (even if clone->q->queue_lock is held here)
- * because there is no I/O dispatching during the completion
- * of barrier clone.
- */
- dm_done(clone, error, true);
- return;
- }
-
tio->error = error;
rq->completion_data = clone;
blk_complete_request(rq);
struct dm_rq_target_io *tio = clone->end_io_data;
struct request *rq = tio->orig;
- if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) {
- /*
- * Barrier clones share an original request.
- * Leave it to dm_end_request(), which handles this special
- * case.
- */
- BUG_ON(error > 0);
- dm_end_request(clone, error);
- return;
- }
-
rq->cmd_flags |= REQ_FAILED;
dm_complete_request(clone, error);
}
}
/*
- * Creates a little bio that is just does part of a bvec.
+ * Creates a little bio that just does part of a bvec.
*/
static struct bio *split_bvec(struct bio *bio, sector_t sector,
unsigned short idx, unsigned int offset,
clone->bi_sector = sector;
clone->bi_bdev = bio->bi_bdev;
- clone->bi_rw = bio->bi_rw & ~REQ_HARDBARRIER;
+ clone->bi_rw = bio->bi_rw;
clone->bi_vcnt = 1;
clone->bi_size = to_bytes(len);
clone->bi_io_vec->bv_offset = offset;
clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs);
__bio_clone(clone, bio);
- clone->bi_rw &= ~REQ_HARDBARRIER;
clone->bi_destructor = dm_bio_destructor;
clone->bi_sector = sector;
clone->bi_idx = idx;
__issue_target_request(ci, ti, request_nr, len);
}
-static int __clone_and_map_empty_barrier(struct clone_info *ci)
+static int __clone_and_map_empty_flush(struct clone_info *ci)
{
unsigned target_nr = 0;
struct dm_target *ti;
+ BUG_ON(bio_has_data(ci->bio));
while ((ti = dm_table_get_target(ci->map, target_nr++)))
__issue_target_requests(ci, ti, ti->num_flush_requests, 0);
- ci->sector_count = 0;
-
return 0;
}
sector_t len = 0, max;
struct dm_target_io *tio;
- if (unlikely(bio_empty_barrier(bio)))
- return __clone_and_map_empty_barrier(ci);
-
if (unlikely(bio->bi_rw & REQ_DISCARD))
return __clone_and_map_discard(ci);
ci.map = dm_get_live_table(md);
if (unlikely(!ci.map)) {
- if (!(bio->bi_rw & REQ_HARDBARRIER))
- bio_io_error(bio);
- else
- if (!md->barrier_error)
- md->barrier_error = -EIO;
+ bio_io_error(bio);
return;
}
ci.md = md;
- ci.bio = bio;
ci.io = alloc_io(md);
ci.io->error = 0;
atomic_set(&ci.io->io_count, 1);
ci.io->md = md;
spin_lock_init(&ci.io->endio_lock);
ci.sector = bio->bi_sector;
- ci.sector_count = bio_sectors(bio);
- if (unlikely(bio_empty_barrier(bio)))
- ci.sector_count = 1;
ci.idx = bio->bi_idx;
start_io_acct(ci.io);
- while (ci.sector_count && !error)
- error = __clone_and_map(&ci);
+ if (bio->bi_rw & REQ_FLUSH) {
+ ci.bio = &ci.md->flush_bio;
+ ci.sector_count = 0;
+ error = __clone_and_map_empty_flush(&ci);
+ /* dec_pending submits any data associated with flush */
+ } else {
+ ci.bio = bio;
+ ci.sector_count = bio_sectors(bio);
+ while (ci.sector_count && !error)
+ error = __clone_and_map(&ci);
+ }
/* drop the extra reference count */
dec_pending(ci.io, error);
part_stat_add(cpu, &dm_disk(md)->part0, sectors[rw], bio_sectors(bio));
part_stat_unlock();
- /*
- * If we're suspended or the thread is processing barriers
- * we have to queue this io for later.
- */
- if (unlikely(test_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags)) ||
- unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
+ /* if we're suspended, we have to queue this io for later */
+ if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
up_read(&md->io_lock);
- if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) &&
- bio_rw(bio) == READA) {
+ if (bio_rw(bio) != READA)
+ queue_io(md, bio);
+ else
bio_io_error(bio);
- return 0;
- }
-
- queue_io(md, bio);
-
return 0;
}
return _dm_request(q, bio);
}
-static bool dm_rq_is_flush_request(struct request *rq)
-{
- if (rq->cmd_flags & REQ_FLUSH)
- return true;
- else
- return false;
-}
-
void dm_dispatch_request(struct request *rq)
{
int r;
{
int r;
- if (dm_rq_is_flush_request(rq)) {
- blk_rq_init(NULL, clone);
- clone->cmd_type = REQ_TYPE_FS;
- clone->cmd_flags |= (REQ_HARDBARRIER | WRITE);
- } else {
- r = blk_rq_prep_clone(clone, rq, tio->md->bs, GFP_ATOMIC,
- dm_rq_bio_constructor, tio);
- if (r)
- return r;
-
- clone->cmd = rq->cmd;
- clone->cmd_len = rq->cmd_len;
- clone->sense = rq->sense;
- clone->buffer = rq->buffer;
- }
+ r = blk_rq_prep_clone(clone, rq, tio->md->bs, GFP_ATOMIC,
+ dm_rq_bio_constructor, tio);
+ if (r)
+ return r;
+ clone->cmd = rq->cmd;
+ clone->cmd_len = rq->cmd_len;
+ clone->sense = rq->sense;
+ clone->buffer = rq->buffer;
clone->end_io = end_clone_request;
clone->end_io_data = tio;
struct mapped_device *md = q->queuedata;
struct request *clone;
- if (unlikely(dm_rq_is_flush_request(rq)))
- return BLKPREP_OK;
-
if (unlikely(rq->special)) {
DMWARN("Already has something in rq->special.");
return BLKPREP_KILL;
struct dm_table *map = dm_get_live_table(md);
struct dm_target *ti;
struct request *rq, *clone;
+ sector_t pos;
/*
* For suspend, check blk_queue_stopped() and increment
if (!rq)
goto plug_and_out;
- if (unlikely(dm_rq_is_flush_request(rq))) {
- BUG_ON(md->flush_request);
- md->flush_request = rq;
- blk_start_request(rq);
- queue_work(md->wq, &md->barrier_work);
- goto out;
- }
+ /* always use block 0 to find the target for flushes for now */
+ pos = 0;
+ if (!(rq->cmd_flags & REQ_FLUSH))
+ pos = blk_rq_pos(rq);
+
+ ti = dm_table_find_target(map, pos);
+ BUG_ON(!dm_target_is_valid(ti));
- ti = dm_table_find_target(map, blk_rq_pos(rq));
if (ti->type->busy && ti->type->busy(ti))
goto plug_and_out;
static const struct block_device_operations dm_blk_dops;
static void dm_wq_work(struct work_struct *work);
-static void dm_rq_barrier_work(struct work_struct *work);
static void dm_init_md_queue(struct mapped_device *md)
{
blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY);
md->queue->unplug_fn = dm_unplug_all;
blk_queue_merge_bvec(md->queue, dm_merge_bvec);
+ blk_queue_flush(md->queue, REQ_FLUSH | REQ_FUA);
}
/*
mutex_init(&md->suspend_lock);
mutex_init(&md->type_lock);
spin_lock_init(&md->deferred_lock);
- spin_lock_init(&md->barrier_error_lock);
rwlock_init(&md->map_lock);
atomic_set(&md->holders, 1);
atomic_set(&md->open_count, 0);
atomic_set(&md->pending[1], 0);
init_waitqueue_head(&md->wait);
INIT_WORK(&md->work, dm_wq_work);
- INIT_WORK(&md->barrier_work, dm_rq_barrier_work);
init_waitqueue_head(&md->eventq);
md->disk->major = _major;
if (!md->bdev)
goto bad_bdev;
+ bio_init(&md->flush_bio);
+ md->flush_bio.bi_bdev = md->bdev;
+ md->flush_bio.bi_rw = WRITE_FLUSH;
+
/* Populate the mapping, nobody knows we exist yet */
spin_lock(&_minor_lock);
old_md = idr_replace(&_minor_idr, md, minor);
blk_queue_softirq_done(md->queue, dm_softirq_done);
blk_queue_prep_rq(md->queue, dm_prep_fn);
blk_queue_lld_busy(md->queue, dm_lld_busy);
- blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH);
elv_register_queue(md->queue);
return r;
}
-static void dm_flush(struct mapped_device *md)
-{
- dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
-
- bio_init(&md->barrier_bio);
- md->barrier_bio.bi_bdev = md->bdev;
- md->barrier_bio.bi_rw = WRITE_BARRIER;
- __split_and_process_bio(md, &md->barrier_bio);
-
- dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
-}
-
-static void process_barrier(struct mapped_device *md, struct bio *bio)
-{
- md->barrier_error = 0;
-
- dm_flush(md);
-
- if (!bio_empty_barrier(bio)) {
- __split_and_process_bio(md, bio);
- /*
- * If the request isn't supported, don't waste time with
- * the second flush.
- */
- if (md->barrier_error != -EOPNOTSUPP)
- dm_flush(md);
- }
-
- if (md->barrier_error != DM_ENDIO_REQUEUE)
- bio_endio(bio, md->barrier_error);
- else {
- spin_lock_irq(&md->deferred_lock);
- bio_list_add_head(&md->deferred, bio);
- spin_unlock_irq(&md->deferred_lock);
- }
-}
-
/*
* Process the deferred bios
*/
work);
struct bio *c;
- down_write(&md->io_lock);
+ down_read(&md->io_lock);
while (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) {
spin_lock_irq(&md->deferred_lock);
c = bio_list_pop(&md->deferred);
spin_unlock_irq(&md->deferred_lock);
- if (!c) {
- clear_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags);
+ if (!c)
break;
- }
- up_write(&md->io_lock);
+ up_read(&md->io_lock);
if (dm_request_based(md))
generic_make_request(c);
- else {
- if (c->bi_rw & REQ_HARDBARRIER)
- process_barrier(md, c);
- else
- __split_and_process_bio(md, c);
- }
+ else
+ __split_and_process_bio(md, c);
- down_write(&md->io_lock);
+ down_read(&md->io_lock);
}
- up_write(&md->io_lock);
+ up_read(&md->io_lock);
}
static void dm_queue_flush(struct mapped_device *md)
queue_work(md->wq, &md->work);
}
-static void dm_rq_set_target_request_nr(struct request *clone, unsigned request_nr)
-{
- struct dm_rq_target_io *tio = clone->end_io_data;
-
- tio->info.target_request_nr = request_nr;
-}
-
-/* Issue barrier requests to targets and wait for their completion. */
-static int dm_rq_barrier(struct mapped_device *md)
-{
- int i, j;
- struct dm_table *map = dm_get_live_table(md);
- unsigned num_targets = dm_table_get_num_targets(map);
- struct dm_target *ti;
- struct request *clone;
-
- md->barrier_error = 0;
-
- for (i = 0; i < num_targets; i++) {
- ti = dm_table_get_target(map, i);
- for (j = 0; j < ti->num_flush_requests; j++) {
- clone = clone_rq(md->flush_request, md, GFP_NOIO);
- dm_rq_set_target_request_nr(clone, j);
- atomic_inc(&md->pending[rq_data_dir(clone)]);
- map_request(ti, clone, md);
- }
- }
-
- dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
- dm_table_put(map);
-
- return md->barrier_error;
-}
-
-static void dm_rq_barrier_work(struct work_struct *work)
-{
- int error;
- struct mapped_device *md = container_of(work, struct mapped_device,
- barrier_work);
- struct request_queue *q = md->queue;
- struct request *rq;
- unsigned long flags;
-
- /*
- * Hold the md reference here and leave it at the last part so that
- * the md can't be deleted by device opener when the barrier request
- * completes.
- */
- dm_get(md);
-
- error = dm_rq_barrier(md);
-
- rq = md->flush_request;
- md->flush_request = NULL;
-
- if (error == DM_ENDIO_REQUEUE) {
- spin_lock_irqsave(q->queue_lock, flags);
- blk_requeue_request(q, rq);
- spin_unlock_irqrestore(q->queue_lock, flags);
- } else
- blk_end_request_all(rq, error);
-
- blk_run_queue(q);
-
- dm_put(md);
-}
-
/*
* Swap in a new table, returning the old one for the caller to destroy.
*/
*
* To get all processes out of __split_and_process_bio in dm_request,
* we take the write lock. To prevent any process from reentering
- * __split_and_process_bio from dm_request, we set
- * DMF_QUEUE_IO_TO_THREAD.
- *
- * To quiesce the thread (dm_wq_work), we set DMF_BLOCK_IO_FOR_SUSPEND
- * and call flush_workqueue(md->wq). flush_workqueue will wait until
- * dm_wq_work exits and DMF_BLOCK_IO_FOR_SUSPEND will prevent any
- * further calls to __split_and_process_bio from dm_wq_work.
+ * __split_and_process_bio from dm_request and quiesce the thread
+ * (dm_wq_work), we set BMF_BLOCK_IO_FOR_SUSPEND and call
+ * flush_workqueue(md->wq).
*/
down_write(&md->io_lock);
set_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags);
- set_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags);
up_write(&md->io_lock);
/*
- * Request-based dm uses md->wq for barrier (dm_rq_barrier_work) which
- * can be kicked until md->queue is stopped. So stop md->queue before
- * flushing md->wq.
+ * Stop md->queue before flushing md->wq in case request-based
+ * dm defers requests to md->wq from md->queue.
*/
if (dm_request_based(md))
stop_queue(md->queue);
projects / mv-sheeva.git / blobdiff