summaryrefslogtreecommitdiffstats
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/.gitignore4
-rw-r--r--drivers/md/bitmap.c42
-rw-r--r--drivers/md/bitmap.h4
-rw-r--r--drivers/md/dm-crypt.c2
-rw-r--r--drivers/md/dm-io.c20
-rw-r--r--drivers/md/dm-ioctl.c1
-rw-r--r--drivers/md/dm-log.c2
-rw-r--r--drivers/md/dm-raid1.c8
-rw-r--r--drivers/md/dm-region-hash.c16
-rw-r--r--drivers/md/dm-snap-persistent.c4
-rw-r--r--drivers/md/dm-snap.c8
-rw-r--r--drivers/md/dm-stripe.c2
-rw-r--r--drivers/md/dm-table.c5
-rw-r--r--drivers/md/dm.c408
-rw-r--r--drivers/md/faulty.c2
-rw-r--r--drivers/md/linear.c4
-rw-r--r--drivers/md/md.c347
-rw-r--r--drivers/md/md.h33
-rw-r--r--drivers/md/multipath.c4
-rw-r--r--drivers/md/raid0.c4
-rw-r--r--drivers/md/raid1.c397
-rw-r--r--drivers/md/raid1.h4
-rw-r--r--drivers/md/raid10.c66
-rw-r--r--drivers/md/raid5.c62
-rw-r--r--drivers/md/raid5.h1
25 files changed, 563 insertions, 887 deletions
diff --git a/drivers/md/.gitignore b/drivers/md/.gitignore
deleted file mode 100644
index a7afec6b19c6..000000000000
--- a/drivers/md/.gitignore
+++ /dev/null
@@ -1,4 +0,0 @@
-mktables
-raid6altivec*.c
-raid6int*.c
-raid6tables.c
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 1ba1e122e948..5a1ffe3527aa 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -212,7 +212,7 @@ static struct page *read_sb_page(mddev_t *mddev, loff_t offset,
target = rdev->sb_start + offset + index * (PAGE_SIZE/512);
- if (sync_page_io(rdev->bdev, target,
+ if (sync_page_io(rdev, target,
roundup(size, bdev_logical_block_size(rdev->bdev)),
page, READ)) {
page->index = index;
@@ -343,7 +343,7 @@ static void write_page(struct bitmap *bitmap, struct page *page, int wait)
atomic_inc(&bitmap->pending_writes);
set_buffer_locked(bh);
set_buffer_mapped(bh);
- submit_bh(WRITE, bh);
+ submit_bh(WRITE | REQ_UNPLUG | REQ_SYNC, bh);
bh = bh->b_this_page;
}
@@ -1000,10 +1000,11 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
page = bitmap->sb_page;
offset = sizeof(bitmap_super_t);
if (!file)
- read_sb_page(bitmap->mddev,
- bitmap->mddev->bitmap_info.offset,
- page,
- index, count);
+ page = read_sb_page(
+ bitmap->mddev,
+ bitmap->mddev->bitmap_info.offset,
+ page,
+ index, count);
} else if (file) {
page = read_page(file, index, bitmap, count);
offset = 0;
@@ -1100,7 +1101,7 @@ static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc)
bitmap_checkfree(bitmap, page);
}
static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
- sector_t offset, int *blocks,
+ sector_t offset, sector_t *blocks,
int create);
/*
@@ -1114,7 +1115,7 @@ void bitmap_daemon_work(mddev_t *mddev)
unsigned long j;
unsigned long flags;
struct page *page = NULL, *lastpage = NULL;
- int blocks;
+ sector_t blocks;
void *paddr;
struct dm_dirty_log *log = mddev->bitmap_info.log;
@@ -1257,7 +1258,7 @@ void bitmap_daemon_work(mddev_t *mddev)
}
static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
- sector_t offset, int *blocks,
+ sector_t offset, sector_t *blocks,
int create)
__releases(bitmap->lock)
__acquires(bitmap->lock)
@@ -1315,7 +1316,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
}
while (sectors) {
- int blocks;
+ sector_t blocks;
bitmap_counter_t *bmc;
spin_lock_irq(&bitmap->lock);
@@ -1380,7 +1381,7 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
success = 0;
while (sectors) {
- int blocks;
+ sector_t blocks;
unsigned long flags;
bitmap_counter_t *bmc;
@@ -1422,7 +1423,7 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
}
EXPORT_SYMBOL(bitmap_endwrite);
-static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
+static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks,
int degraded)
{
bitmap_counter_t *bmc;
@@ -1451,7 +1452,7 @@ static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *bloc
return rv;
}
-int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
+int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks,
int degraded)
{
/* bitmap_start_sync must always report on multiples of whole
@@ -1462,7 +1463,7 @@ int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
* Return the 'or' of the result.
*/
int rv = 0;
- int blocks1;
+ sector_t blocks1;
*blocks = 0;
while (*blocks < (PAGE_SIZE>>9)) {
@@ -1475,7 +1476,7 @@ int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
}
EXPORT_SYMBOL(bitmap_start_sync);
-void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted)
+void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int aborted)
{
bitmap_counter_t *bmc;
unsigned long flags;
@@ -1514,7 +1515,7 @@ void bitmap_close_sync(struct bitmap *bitmap)
* RESYNC bit wherever it is still on
*/
sector_t sector = 0;
- int blocks;
+ sector_t blocks;
if (!bitmap)
return;
while (sector < bitmap->mddev->resync_max_sectors) {
@@ -1527,7 +1528,7 @@ EXPORT_SYMBOL(bitmap_close_sync);
void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
{
sector_t s = 0;
- int blocks;
+ sector_t blocks;
if (!bitmap)
return;
@@ -1542,8 +1543,7 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
atomic_read(&bitmap->mddev->recovery_active) == 0);
bitmap->mddev->curr_resync_completed = bitmap->mddev->curr_resync;
- if (bitmap->mddev->persistent)
- set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
+ set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
sector &= ~((1ULL << CHUNK_BLOCK_SHIFT(bitmap)) - 1);
s = 0;
while (s < sector && s < bitmap->mddev->resync_max_sectors) {
@@ -1562,7 +1562,7 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n
* be 0 at this point
*/
- int secs;
+ sector_t secs;
bitmap_counter_t *bmc;
spin_lock_irq(&bitmap->lock);
bmc = bitmap_get_counter(bitmap, offset, &secs, 1);
@@ -1790,7 +1790,7 @@ int bitmap_load(mddev_t *mddev)
* All chunks should be clean, but some might need_sync.
*/
while (sector < mddev->resync_max_sectors) {
- int blocks;
+ sector_t blocks;
bitmap_start_sync(bitmap, sector, &blocks, 0);
sector += blocks;
}
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
index e872a7bad6b8..931a7a7c3796 100644
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -271,8 +271,8 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset,
unsigned long sectors, int behind);
void bitmap_endwrite(struct bitmap *bitmap, sector_t offset,
unsigned long sectors, int success, int behind);
-int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int degraded);
-void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted);
+int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int degraded);
+void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int aborted);
void bitmap_close_sync(struct bitmap *bitmap);
void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector);
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 368e8e98f705..d5b0e4c0e702 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1278,7 +1278,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio,
struct dm_crypt_io *io;
struct crypt_config *cc;
- if (unlikely(bio_empty_barrier(bio))) {
+ if (bio->bi_rw & REQ_FLUSH) {
cc = ti->private;
bio->bi_bdev = cc->dev->bdev;
return DM_MAPIO_REMAPPED;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 0590c75b0ab6..136d4f71a116 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -31,7 +31,6 @@ struct dm_io_client {
*/
struct io {
unsigned long error_bits;
- unsigned long eopnotsupp_bits;
atomic_t count;
struct task_struct *sleeper;
struct dm_io_client *client;
@@ -130,11 +129,8 @@ static void retrieve_io_and_region_from_bio(struct bio *bio, struct io **io,
*---------------------------------------------------------------*/
static void dec_count(struct io *io, unsigned int region, int error)
{
- if (error) {
+ if (error)
set_bit(region, &io->error_bits);
- if (error == -EOPNOTSUPP)
- set_bit(region, &io->eopnotsupp_bits);
- }
if (atomic_dec_and_test(&io->count)) {
if (io->sleeper)
@@ -310,8 +306,8 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
sector_t remaining = where->count;
/*
- * where->count may be zero if rw holds a write barrier and we
- * need to send a zero-sized barrier.
+ * where->count may be zero if rw holds a flush and we need to
+ * send a zero-sized flush.
*/
do {
/*
@@ -364,7 +360,7 @@ static void dispatch_io(int rw, unsigned int num_regions,
*/
for (i = 0; i < num_regions; i++) {
*dp = old_pages;
- if (where[i].count || (rw & REQ_HARDBARRIER))
+ if (where[i].count || (rw & REQ_FLUSH))
do_region(rw, i, where + i, dp, io);
}
@@ -393,9 +389,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
return -EIO;
}
-retry:
io->error_bits = 0;
- io->eopnotsupp_bits = 0;
atomic_set(&io->count, 1); /* see dispatch_io() */
io->sleeper = current;
io->client = client;
@@ -412,11 +406,6 @@ retry:
}
set_current_state(TASK_RUNNING);
- if (io->eopnotsupp_bits && (rw & REQ_HARDBARRIER)) {
- rw &= ~REQ_HARDBARRIER;
- goto retry;
- }
-
if (error_bits)
*error_bits = io->error_bits;
@@ -437,7 +426,6 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
io = mempool_alloc(client->pool, GFP_NOIO);
io->error_bits = 0;
- io->eopnotsupp_bits = 0;
atomic_set(&io->count, 1); /* see dispatch_io() */
io->sleeper = NULL;
io->client = client;
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 3e39193e5036..4b54618b4159 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1596,6 +1596,7 @@ static const struct file_operations _ctl_fops = {
.unlocked_ioctl = dm_ctl_ioctl,
.compat_ioctl = dm_compat_ctl_ioctl,
.owner = THIS_MODULE,
+ .llseek = noop_llseek,
};
static struct miscdevice _dm_misc = {
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 5a08be0222db..33420e68d153 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -300,7 +300,7 @@ static int flush_header(struct log_c *lc)
.count = 0,
};
- lc->io_req.bi_rw = WRITE_BARRIER;
+ lc->io_req.bi_rw = WRITE_FLUSH;
return dm_io(&lc->io_req, 1, &null_location, NULL);
}
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 7c081bcbc3cf..19a59b041c27 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -259,7 +259,7 @@ static int mirror_flush(struct dm_target *ti)
struct dm_io_region io[ms->nr_mirrors];
struct mirror *m;
struct dm_io_request io_req = {
- .bi_rw = WRITE_BARRIER,
+ .bi_rw = WRITE_FLUSH,
.mem.type = DM_IO_KMEM,
.mem.ptr.bvec = NULL,
.client = ms->io_client,
@@ -629,7 +629,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
struct dm_io_region io[ms->nr_mirrors], *dest = io;
struct mirror *m;
struct dm_io_request io_req = {
- .bi_rw = WRITE | (bio->bi_rw & WRITE_BARRIER),
+ .bi_rw = WRITE | (bio->bi_rw & WRITE_FLUSH_FUA),
.mem.type = DM_IO_BVEC,
.mem.ptr.bvec = bio->bi_io_vec + bio->bi_idx,
.notify.fn = write_callback,
@@ -670,7 +670,7 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
bio_list_init(&requeue);
while ((bio = bio_list_pop(writes))) {
- if (unlikely(bio_empty_barrier(bio))) {
+ if (bio->bi_rw & REQ_FLUSH) {
bio_list_add(&sync, bio);
continue;
}
@@ -1203,7 +1203,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
* We need to dec pending if this was a write.
*/
if (rw == WRITE) {
- if (likely(!bio_empty_barrier(bio)))
+ if (!(bio->bi_rw & REQ_FLUSH))
dm_rh_dec(ms->rh, map_context->ll);
return error;
}
diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c
index bd5c58b28868..dad011aed0c9 100644
--- a/drivers/md/dm-region-hash.c
+++ b/drivers/md/dm-region-hash.c
@@ -81,9 +81,9 @@ struct dm_region_hash {
struct list_head failed_recovered_regions;
/*
- * If there was a barrier failure no regions can be marked clean.
+ * If there was a flush failure no regions can be marked clean.
*/
- int barrier_failure;
+ int flush_failure;
void *context;
sector_t target_begin;
@@ -217,7 +217,7 @@ struct dm_region_hash *dm_region_hash_create(
INIT_LIST_HEAD(&rh->quiesced_regions);
INIT_LIST_HEAD(&rh->recovered_regions);
INIT_LIST_HEAD(&rh->failed_recovered_regions);
- rh->barrier_failure = 0;
+ rh->flush_failure = 0;
rh->region_pool = mempool_create_kmalloc_pool(MIN_REGIONS,
sizeof(struct dm_region));
@@ -399,8 +399,8 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio)
region_t region = dm_rh_bio_to_region(rh, bio);
int recovering = 0;
- if (bio_empty_barrier(bio)) {
- rh->barrier_failure = 1;
+ if (bio->bi_rw & REQ_FLUSH) {
+ rh->flush_failure = 1;
return;
}
@@ -524,7 +524,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios)
struct bio *bio;
for (bio = bios->head; bio; bio = bio->bi_next) {
- if (bio_empty_barrier(bio))
+ if (bio->bi_rw & REQ_FLUSH)
continue;
rh_inc(rh, dm_rh_bio_to_region(rh, bio));
}
@@ -555,9 +555,9 @@ void dm_rh_dec(struct dm_region_hash *rh, region_t region)
*/
/* do nothing for DM_RH_NOSYNC */
- if (unlikely(rh->barrier_failure)) {
+ if (unlikely(rh->flush_failure)) {
/*
- * If a write barrier failed some time ago, we
+ * If a write flush failed some time ago, we
* don't know whether or not this write made it
* to the disk, so we must resync the device.
*/
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index cc2bdb83f9ad..2129cdb115dc 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -254,7 +254,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
* Issue the synchronous I/O from a different thread
* to avoid generic_make_request recursion.
*/
- INIT_WORK_ON_STACK(&req.work, do_metadata);
+ INIT_WORK_ONSTACK(&req.work, do_metadata);
queue_work(ps->metadata_wq, &req.work);
flush_workqueue(ps->metadata_wq);
@@ -687,7 +687,7 @@ static void persistent_commit_exception(struct dm_exception_store *store,
/*
* Commit exceptions to disk.
*/
- if (ps->valid && area_io(ps, WRITE_BARRIER))
+ if (ps->valid && area_io(ps, WRITE_FLUSH_FUA))
ps->valid = 0;
/*
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 5974d3094d97..53cf79d8bcbc 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -706,8 +706,6 @@ static int dm_add_exception(void *context, chunk_t old, chunk_t new)
return 0;
}
-#define min_not_zero(l, r) (((l) == 0) ? (r) : (((r) == 0) ? (l) : min(l, r)))
-
/*
* Return a minimum chunk size of all snapshots that have the specified origin.
* Return zero if the origin has no snapshots.
@@ -1587,7 +1585,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio,
chunk_t chunk;
struct dm_snap_pending_exception *pe = NULL;
- if (unlikely(bio_empty_barrier(bio))) {
+ if (bio->bi_rw & REQ_FLUSH) {
bio->bi_bdev = s->cow->bdev;
return DM_MAPIO_REMAPPED;
}
@@ -1691,7 +1689,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio,
int r = DM_MAPIO_REMAPPED;
chunk_t chunk;
- if (unlikely(bio_empty_barrier(bio))) {
+ if (bio->bi_rw & REQ_FLUSH) {
if (!map_context->target_request_nr)
bio->bi_bdev = s->origin->bdev;
else
@@ -2135,7 +2133,7 @@ static int origin_map(struct dm_target *ti, struct bio *bio,
struct dm_dev *dev = ti->private;
bio->bi_bdev = dev->bdev;
- if (unlikely(bio_empty_barrier(bio)))
+ if (bio->bi_rw & REQ_FLUSH)
return DM_MAPIO_REMAPPED;
/* Only tell snapshots if this is a write */
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index c297f6da91ea..f0371b4c4fbf 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -271,7 +271,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio,
uint32_t stripe;
unsigned target_request_nr;
- if (unlikely(bio_empty_barrier(bio))) {
+ if (bio->bi_rw & REQ_FLUSH) {
target_request_nr = map_context->target_request_nr;
BUG_ON(target_request_nr >= sc->stripes);
bio->bi_bdev = sc->stripe[target_request_nr].dev->bdev;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index f9fc07d7a4b9..90267f8d64ee 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -486,11 +486,6 @@ static int __table_get_device(struct dm_table *t, struct dm_target *ti,
return 0;
}
-/*
- * Returns the minimum that is _not_ zero, unless both are zero.
- */
-#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))
-
int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index ac384b2a6a33..7cb1352f7e7a 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -15,7 +15,6 @@
#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>
@@ -33,6 +32,7 @@
#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;
@@ -110,7 +110,6 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo);
#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.
@@ -144,24 +143,9 @@ struct mapped_device {
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.
@@ -200,8 +184,8 @@ struct mapped_device {
/* 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;
};
/*
@@ -344,7 +328,7 @@ static int dm_blk_open(struct block_device *bdev, fmode_t mode)
{
struct mapped_device *md;
- lock_kernel();
+ mutex_lock(&dm_mutex);
spin_lock(&_minor_lock);
md = bdev->bd_disk->private_data;
@@ -362,7 +346,7 @@ static int dm_blk_open(struct block_device *bdev, fmode_t mode)
out:
spin_unlock(&_minor_lock);
- unlock_kernel();
+ mutex_unlock(&dm_mutex);
return md ? 0 : -ENXIO;
}
@@ -371,10 +355,10 @@ static int dm_blk_close(struct gendisk *disk, fmode_t mode)
{
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;
}
@@ -512,7 +496,7 @@ static void end_io_acct(struct dm_io *io)
/*
* 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]);
@@ -528,16 +512,12 @@ static void end_io_acct(struct dm_io *io)
*/
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);
}
/*
@@ -625,11 +605,9 @@ static void dec_pending(struct dm_io *io, int error)
* 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);
@@ -637,32 +615,23 @@ static void dec_pending(struct dm_io *io, int error)
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);
}
}
}
@@ -755,23 +724,6 @@ static void end_clone_bio(struct bio *clone, int 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.
@@ -809,13 +761,11 @@ static void free_rq_clone(struct request *clone)
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;
@@ -829,15 +779,8 @@ static void dm_end_request(struct request *clone, int error)
}
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)
@@ -862,16 +805,6 @@ void dm_requeue_unmapped_request(struct request *clone)
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);
@@ -961,19 +894,6 @@ static void dm_complete_request(struct request *clone, int error)
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);
@@ -990,17 +910,6 @@ void dm_kill_unmapped_request(struct request *clone, int error)
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);
}
@@ -1119,7 +1028,7 @@ static void dm_bio_destructor(struct bio *bio)
}
/*
- * 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,
@@ -1134,7 +1043,7 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector,
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;
@@ -1161,7 +1070,6 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector,
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;
@@ -1225,16 +1133,15 @@ static void __issue_target_requests(struct clone_info *ci, struct dm_target *ti,
__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;
}
@@ -1289,9 +1196,6 @@ static int __clone_and_map(struct clone_info *ci)
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);
@@ -1383,16 +1287,11 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio)
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);
@@ -1400,14 +1299,20 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio)
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);
@@ -1491,22 +1396,14 @@ static int _dm_request(struct request_queue *q, struct bio *bio)
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;
}
@@ -1537,14 +1434,6 @@ static int dm_request(struct request_queue *q, struct bio *bio)
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;
@@ -1592,22 +1481,15 @@ static int setup_clone(struct request *clone, struct request *rq,
{
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;
@@ -1648,9 +1530,6 @@ static int dm_prep_fn(struct request_queue *q, struct request *rq)
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;
@@ -1727,6 +1606,7 @@ static void dm_request_fn(struct request_queue *q)
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
@@ -1739,15 +1619,14 @@ static void dm_request_fn(struct request_queue *q)
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;
@@ -1918,7 +1797,6 @@ 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)
{
@@ -1940,6 +1818,7 @@ 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);
}
/*
@@ -1972,7 +1851,6 @@ static struct mapped_device *alloc_dev(int minor)
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);
@@ -1995,7 +1873,6 @@ static struct mapped_device *alloc_dev(int minor)
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;
@@ -2015,6 +1892,10 @@ static struct mapped_device *alloc_dev(int minor)
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);
@@ -2245,7 +2126,6 @@ static int dm_init_request_based_queue(struct mapped_device *md)
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);
@@ -2406,43 +2286,6 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible)
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
*/
@@ -2452,33 +2295,27 @@ static void dm_wq_work(struct work_struct *work)
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)
@@ -2488,73 +2325,6 @@ 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.
*/
@@ -2677,23 +2447,17 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
*
* 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);
diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c
index 1a8987884614..339fdc670751 100644
--- a/drivers/md/faulty.c
+++ b/drivers/md/faulty.c
@@ -210,7 +210,7 @@ static int make_request(mddev_t *mddev, struct bio *bio)
}
}
if (failit) {
- struct bio *b = bio_clone(bio, GFP_NOIO);
+ struct bio *b = bio_clone_mddev(bio, GFP_NOIO, mddev);
b->bi_bdev = conf->rdev->bdev;
b->bi_private = bio;
b->bi_end_io = faulty_fail;
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index ba19060bcf3f..8a2f767f26d8 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -294,8 +294,8 @@ static int linear_make_request (mddev_t *mddev, struct bio *bio)
dev_info_t *tmp_dev;
sector_t start_sector;
- if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
- md_barrier_request(mddev, bio);
+ if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+ md_flush_request(mddev, bio);
return 0;
}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 11567c7999a2..4e957f3140a8 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -36,7 +36,7 @@
#include <linux/blkdev.h>
#include <linux/sysctl.h>
#include <linux/seq_file.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
#include <linux/buffer_head.h> /* for invalidate_bdev */
#include <linux/poll.h>
#include <linux/ctype.h>
@@ -57,7 +57,6 @@
#define DEBUG 0
#define dprintk(x...) ((void)(DEBUG && printk(x)))
-
#ifndef MODULE
static void autostart_arrays(int part);
#endif
@@ -68,6 +67,8 @@ static DEFINE_SPINLOCK(pers_lock);
static void md_print_devices(void);
static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
+static struct workqueue_struct *md_wq;
+static struct workqueue_struct *md_misc_wq;
#define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
@@ -148,6 +149,72 @@ static const struct block_device_operations md_fops;
static int start_readonly;
+/* bio_clone_mddev
+ * like bio_clone, but with a local bio set
+ */
+
+static void mddev_bio_destructor(struct bio *bio)
+{
+ mddev_t *mddev, **mddevp;
+
+ mddevp = (void*)bio;
+ mddev = mddevp[-1];
+
+ bio_free(bio, mddev->bio_set);
+}
+
+struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
+ mddev_t *mddev)
+{
+ struct bio *b;
+ mddev_t **mddevp;
+
+ if (!mddev || !mddev->bio_set)
+ return bio_alloc(gfp_mask, nr_iovecs);
+
+ b = bio_alloc_bioset(gfp_mask, nr_iovecs,
+ mddev->bio_set);
+ if (!b)
+ return NULL;
+ mddevp = (void*)b;
+ mddevp[-1] = mddev;
+ b->bi_destructor = mddev_bio_destructor;
+ return b;
+}
+EXPORT_SYMBOL_GPL(bio_alloc_mddev);
+
+struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask,
+ mddev_t *mddev)
+{
+ struct bio *b;
+ mddev_t **mddevp;
+
+ if (!mddev || !mddev->bio_set)
+ return bio_clone(bio, gfp_mask);
+
+ b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs,
+ mddev->bio_set);
+ if (!b)
+ return NULL;
+ mddevp = (void*)b;
+ mddevp[-1] = mddev;
+ b->bi_destructor = mddev_bio_destructor;
+ __bio_clone(b, bio);
+ if (bio_integrity(bio)) {
+ int ret;
+
+ ret = bio_integrity_clone(b, bio, gfp_mask, mddev->bio_set);
+
+ if (ret < 0) {
+ bio_put(b);
+ return NULL;
+ }
+ }
+
+ return b;
+}
+EXPORT_SYMBOL_GPL(bio_clone_mddev);
+
/*
* We have a system wide 'event count' that is incremented
* on any 'interesting' event, and readers of /proc/mdstat
@@ -226,12 +293,12 @@ static int md_make_request(struct request_queue *q, struct bio *bio)
return 0;
}
rcu_read_lock();
- if (mddev->suspended || mddev->barrier) {
+ if (mddev->suspended) {
DEFINE_WAIT(__wait);
for (;;) {
prepare_to_wait(&mddev->sb_wait, &__wait,
TASK_UNINTERRUPTIBLE);
- if (!mddev->suspended && !mddev->barrier)
+ if (!mddev->suspended)
break;
rcu_read_unlock();
schedule();
@@ -282,40 +349,29 @@ EXPORT_SYMBOL_GPL(mddev_resume);
int mddev_congested(mddev_t *mddev, int bits)
{
- if (mddev->barrier)
- return 1;
return mddev->suspended;
}
EXPORT_SYMBOL(mddev_congested);
/*
- * Generic barrier handling for md
+ * Generic flush handling for md
*/
-#define POST_REQUEST_BARRIER ((void*)1)
-
-static void md_end_barrier(struct bio *bio, int err)
+static void md_end_flush(struct bio *bio, int err)
{
mdk_rdev_t *rdev = bio->bi_private;
mddev_t *mddev = rdev->mddev;
- if (err == -EOPNOTSUPP && mddev->barrier != POST_REQUEST_BARRIER)
- set_bit(BIO_EOPNOTSUPP, &mddev->barrier->bi_flags);
rdev_dec_pending(rdev, mddev);
if (atomic_dec_and_test(&mddev->flush_pending)) {
- if (mddev->barrier == POST_REQUEST_BARRIER) {
- /* This was a post-request barrier */
- mddev->barrier = NULL;
- wake_up(&mddev->sb_wait);
- } else
- /* The pre-request barrier has finished */
- schedule_work(&mddev->barrier_work);
+ /* The pre-request flush has finished */
+ queue_work(md_wq, &mddev->flush_work);
}
bio_put(bio);
}
-static void submit_barriers(mddev_t *mddev)
+static void submit_flushes(mddev_t *mddev)
{
mdk_rdev_t *rdev;
@@ -331,61 +387,57 @@ static void submit_barriers(mddev_t *mddev)
atomic_inc(&rdev->nr_pending);
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
- bi = bio_alloc(GFP_KERNEL, 0);
- bi->bi_end_io = md_end_barrier;
+ bi = bio_alloc_mddev(GFP_KERNEL, 0, mddev);
+ bi->bi_end_io = md_end_flush;
bi->bi_private = rdev;
bi->bi_bdev = rdev->bdev;
atomic_inc(&mddev->flush_pending);
- submit_bio(WRITE_BARRIER, bi);
+ submit_bio(WRITE_FLUSH, bi);
rcu_read_lock();
rdev_dec_pending(rdev, mddev);
}
rcu_read_unlock();
}
-static void md_submit_barrier(struct work_struct *ws)
+static void md_submit_flush_data(struct work_struct *ws)
{
- mddev_t *mddev = container_of(ws, mddev_t, barrier_work);
- struct bio *bio = mddev->barrier;
+ mddev_t *mddev = container_of(ws, mddev_t, flush_work);
+ struct bio *bio = mddev->flush_bio;
atomic_set(&mddev->flush_pending, 1);
- if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
- bio_endio(bio, -EOPNOTSUPP);
- else if (bio->bi_size == 0)
+ if (bio->bi_size == 0)
/* an empty barrier - all done */
bio_endio(bio, 0);
else {
- bio->bi_rw &= ~REQ_HARDBARRIER;
+ bio->bi_rw &= ~REQ_FLUSH;
if (mddev->pers->make_request(mddev, bio))
generic_make_request(bio);
- mddev->barrier = POST_REQUEST_BARRIER;
- submit_barriers(mddev);
}
if (atomic_dec_and_test(&mddev->flush_pending)) {
- mddev->barrier = NULL;
+ mddev->flush_bio = NULL;
wake_up(&mddev->sb_wait);
}
}
-void md_barrier_request(mddev_t *mddev, struct bio *bio)
+void md_flush_request(mddev_t *mddev, struct bio *bio)
{
spin_lock_irq(&mddev->write_lock);
wait_event_lock_irq(mddev->sb_wait,
- !mddev->barrier,
+ !mddev->flush_bio,
mddev->write_lock, /*nothing*/);
- mddev->barrier = bio;
+ mddev->flush_bio = bio;
spin_unlock_irq(&mddev->write_lock);
atomic_set(&mddev->flush_pending, 1);
- INIT_WORK(&mddev->barrier_work, md_submit_barrier);
+ INIT_WORK(&mddev->flush_work, md_submit_flush_data);
- submit_barriers(mddev);
+ submit_flushes(mddev);
if (atomic_dec_and_test(&mddev->flush_pending))
- schedule_work(&mddev->barrier_work);
+ queue_work(md_wq, &mddev->flush_work);
}
-EXPORT_SYMBOL(md_barrier_request);
+EXPORT_SYMBOL(md_flush_request);
/* Support for plugging.
* This mirrors the plugging support in request_queue, but does not
@@ -442,6 +494,8 @@ static void mddev_delayed_delete(struct work_struct *ws);
static void mddev_put(mddev_t *mddev)
{
+ struct bio_set *bs = NULL;
+
if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
return;
if (!mddev->raid_disks && list_empty(&mddev->disks) &&
@@ -449,19 +503,22 @@ static void mddev_put(mddev_t *mddev)
/* Array is not configured at all, and not held active,
* so destroy it */
list_del(&mddev->all_mddevs);
+ bs = mddev->bio_set;
+ mddev->bio_set = NULL;
if (mddev->gendisk) {
- /* we did a probe so need to clean up.
- * Call schedule_work inside the spinlock
- * so that flush_scheduled_work() after
- * mddev_find will succeed in waiting for the
- * work to be done.
+ /* We did a probe so need to clean up. Call
+ * queue_work inside the spinlock so that
+ * flush_workqueue() after mddev_find will
+ * succeed in waiting for the work to be done.
*/
INIT_WORK(&mddev->del_work, mddev_delayed_delete);
- schedule_work(&mddev->del_work);
+ queue_work(md_misc_wq, &mddev->del_work);
} else
kfree(mddev);
}
spin_unlock(&all_mddevs_lock);
+ if (bs)
+ bioset_free(bs);
}
void mddev_init(mddev_t *mddev)
@@ -696,31 +753,6 @@ static void super_written(struct bio *bio, int error)
bio_put(bio);
}
-static void super_written_barrier(struct bio *bio, int error)
-{
- struct bio *bio2 = bio->bi_private;
- mdk_rdev_t *rdev = bio2->bi_private;
- mddev_t *mddev = rdev->mddev;
-
- if (!test_bit(BIO_UPTODATE, &bio->bi_flags) &&
- error == -EOPNOTSUPP) {
- unsigned long flags;
- /* barriers don't appear to be supported :-( */
- set_bit(BarriersNotsupp, &rdev->flags);
- mddev->barriers_work = 0;
- spin_lock_irqsave(&mddev->write_lock, flags);
- bio2->bi_next = mddev->biolist;
- mddev->biolist = bio2;
- spin_unlock_irqrestore(&mddev->write_lock, flags);
- wake_up(&mddev->sb_wait);
- bio_put(bio);
- } else {
- bio_put(bio2);
- bio->bi_private = rdev;
- super_written(bio, error);
- }
-}
-
void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
sector_t sector, int size, struct page *page)
{
@@ -729,51 +761,28 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
* and decrement it on completion, waking up sb_wait
* if zero is reached.
* If an error occurred, call md_error
- *
- * As we might need to resubmit the request if REQ_HARDBARRIER
- * causes ENOTSUPP, we allocate a spare bio...
*/
- struct bio *bio = bio_alloc(GFP_NOIO, 1);
- int rw = REQ_WRITE | REQ_SYNC | REQ_UNPLUG;
+ struct bio *bio = bio_alloc_mddev(GFP_NOIO, 1, mddev);
bio->bi_bdev = rdev->bdev;
bio->bi_sector = sector;
bio_add_page(bio, page, size, 0);
bio->bi_private = rdev;
bio->bi_end_io = super_written;
- bio->bi_rw = rw;
atomic_inc(&mddev->pending_writes);
- if (!test_bit(BarriersNotsupp, &rdev->flags)) {
- struct bio *rbio;
- rw |= REQ_HARDBARRIER;
- rbio = bio_clone(bio, GFP_NOIO);
- rbio->bi_private = bio;
- rbio->bi_end_io = super_written_barrier;
- submit_bio(rw, rbio);
- } else
- submit_bio(rw, bio);
+ submit_bio(REQ_WRITE | REQ_SYNC | REQ_UNPLUG | REQ_FLUSH | REQ_FUA,
+ bio);
}
void md_super_wait(mddev_t *mddev)
{
- /* wait for all superblock writes that were scheduled to complete.
- * if any had to be retried (due to BARRIER problems), retry them
- */
+ /* wait for all superblock writes that were scheduled to complete */
DEFINE_WAIT(wq);
for(;;) {
prepare_to_wait(&mddev->sb_wait, &wq, TASK_UNINTERRUPTIBLE);
if (atomic_read(&mddev->pending_writes)==0)
break;
- while (mddev->biolist) {
- struct bio *bio;
- spin_lock_irq(&mddev->write_lock);
- bio = mddev->biolist;
- mddev->biolist = bio->bi_next ;
- bio->bi_next = NULL;
- spin_unlock_irq(&mddev->write_lock);
- submit_bio(bio->bi_rw, bio);
- }
schedule();
}
finish_wait(&mddev->sb_wait, &wq);
@@ -784,16 +793,16 @@ static void bi_complete(struct bio *bio, int error)
complete((struct completion*)bio->bi_private);
}
-int sync_page_io(struct block_device *bdev, sector_t sector, int size,
- struct page *page, int rw)
+int sync_page_io(mdk_rdev_t *rdev, sector_t sector, int size,
+ struct page *page, int rw)
{
- struct bio *bio = bio_alloc(GFP_NOIO, 1);
+ struct bio *bio = bio_alloc_mddev(GFP_NOIO, 1, rdev->mddev);
struct completion event;
int ret;
rw |= REQ_SYNC | REQ_UNPLUG;
- bio->bi_bdev = bdev;
+ bio->bi_bdev = rdev->bdev;
bio->bi_sector = sector;
bio_add_page(bio, page, size, 0);
init_completion(&event);
@@ -819,7 +828,7 @@ static int read_disk_sb(mdk_rdev_t * rdev, int size)
return 0;
- if (!sync_page_io(rdev->bdev, rdev->sb_start, size, rdev->sb_page, READ))
+ if (!sync_page_io(rdev, rdev->sb_start, size, rdev->sb_page, READ))
goto fail;
rdev->sb_loaded = 1;
return 0;
@@ -1070,7 +1079,6 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
clear_bit(Faulty, &rdev->flags);
clear_bit(In_sync, &rdev->flags);
clear_bit(WriteMostly, &rdev->flags);
- clear_bit(BarriersNotsupp, &rdev->flags);
if (mddev->raid_disks == 0) {
mddev->major_version = 0;
@@ -1485,7 +1493,6 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
clear_bit(Faulty, &rdev->flags);
clear_bit(In_sync, &rdev->flags);
clear_bit(WriteMostly, &rdev->flags);
- clear_bit(BarriersNotsupp, &rdev->flags);
if (mddev->raid_disks == 0) {
mddev->major_version = 1;
@@ -1643,7 +1650,9 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1;
if (rdev->sb_size & bmask)
rdev->sb_size = (rdev->sb_size | bmask) + 1;
- }
+ } else
+ max_dev = le32_to_cpu(sb->max_dev);
+
for (i=0; i<max_dev;i++)
sb->dev_roles[i] = cpu_to_le16(0xfffe);
@@ -1912,7 +1921,7 @@ static void unbind_rdev_from_array(mdk_rdev_t * rdev)
synchronize_rcu();
INIT_WORK(&rdev->del_work, md_delayed_delete);
kobject_get(&rdev->kobj);
- schedule_work(&rdev->del_work);
+ queue_work(md_misc_wq, &rdev->del_work);
}
/*
@@ -2136,16 +2145,6 @@ static void sync_sbs(mddev_t * mddev, int nospares)
* with the rest of the array)
*/
mdk_rdev_t *rdev;
-
- /* First make sure individual recovery_offsets are correct */
- list_for_each_entry(rdev, &mddev->disks, same_set) {
- if (rdev->raid_disk >= 0 &&
- mddev->delta_disks >= 0 &&
- !test_bit(In_sync, &rdev->flags) &&
- mddev->curr_resync_completed > rdev->recovery_offset)
- rdev->recovery_offset = mddev->curr_resync_completed;
-
- }
list_for_each_entry(rdev, &mddev->disks, same_set) {
if (rdev->sb_events == mddev->events ||
(nospares &&
@@ -2167,13 +2166,29 @@ static void md_update_sb(mddev_t * mddev, int force_change)
int sync_req;
int nospares = 0;
- mddev->utime = get_seconds();
- if (mddev->external)
- return;
repeat:
+ /* First make sure individual recovery_offsets are correct */
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
+ if (rdev->raid_disk >= 0 &&
+ mddev->delta_disks >= 0 &&
+ !test_bit(In_sync, &rdev->flags) &&
+ mddev->curr_resync_completed > rdev->recovery_offset)
+ rdev->recovery_offset = mddev->curr_resync_completed;
+
+ }
+ if (!mddev->persistent) {
+ clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ clear_bit(MD_CHANGE_DEVS, &mddev->flags);
+ if (!mddev->external)
+ clear_bit(MD_CHANGE_PENDING, &mddev->flags);
+ wake_up(&mddev->sb_wait);
+ return;
+ }
+
spin_lock_irq(&mddev->write_lock);
- set_bit(MD_CHANGE_PENDING, &mddev->flags);
+ mddev->utime = get_seconds();
+
if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags))
force_change = 1;
if (test_and_clear_bit(MD_CHANGE_CLEAN, &mddev->flags))
@@ -2221,19 +2236,6 @@ repeat:
MD_BUG();
mddev->events --;
}
-
- /*
- * do not write anything to disk if using
- * nonpersistent superblocks
- */
- if (!mddev->persistent) {
- if (!mddev->external)
- clear_bit(MD_CHANGE_PENDING, &mddev->flags);
-
- spin_unlock_irq(&mddev->write_lock);
- wake_up(&mddev->sb_wait);
- return;
- }
sync_sbs(mddev, nospares);
spin_unlock_irq(&mddev->write_lock);
@@ -3379,7 +3381,7 @@ array_state_show(mddev_t *mddev, char *page)
case 0:
if (mddev->in_sync)
st = clean;
- else if (test_bit(MD_CHANGE_CLEAN, &mddev->flags))
+ else if (test_bit(MD_CHANGE_PENDING, &mddev->flags))
st = write_pending;
else if (mddev->safemode)
st = active_idle;
@@ -3460,9 +3462,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
mddev->in_sync = 1;
if (mddev->safemode == 1)
mddev->safemode = 0;
- if (mddev->persistent)
- set_bit(MD_CHANGE_CLEAN,
- &mddev->flags);
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
}
err = 0;
} else
@@ -3474,8 +3474,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
case active:
if (mddev->pers) {
restart_array(mddev);
- if (mddev->external)
- clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ clear_bit(MD_CHANGE_PENDING, &mddev->flags);
wake_up(&mddev->sb_wait);
err = 0;
} else {
@@ -4266,10 +4265,10 @@ static int md_alloc(dev_t dev, char *name)
shift = partitioned ? MdpMinorShift : 0;
unit = MINOR(mddev->unit) >> shift;
- /* wait for any previous instance if this device
- * to be completed removed (mddev_delayed_delete).
+ /* wait for any previous instance of this device to be
+ * completely removed (mddev_delayed_delete).
*/
- flush_scheduled_work();
+ flush_workqueue(md_misc_wq);
mutex_lock(&disks_mutex);
error = -EEXIST;
@@ -4452,6 +4451,9 @@ int md_run(mddev_t *mddev)
sysfs_notify_dirent_safe(rdev->sysfs_state);
}
+ if (mddev->bio_set == NULL)
+ mddev->bio_set = bioset_create(BIO_POOL_SIZE, sizeof(mddev));
+
spin_lock(&pers_lock);
pers = find_pers(mddev->level, mddev->clevel);
if (!pers || !try_module_get(pers->owner)) {
@@ -4514,7 +4516,6 @@ int md_run(mddev_t *mddev)
/* may be over-ridden by personality */
mddev->resync_max_sectors = mddev->dev_sectors;
- mddev->barriers_work = 1;
mddev->ok_start_degraded = start_dirty_degraded;
if (start_readonly && mddev->ro == 0)
@@ -4693,7 +4694,6 @@ static void md_clean(mddev_t *mddev)
mddev->recovery = 0;
mddev->in_sync = 0;
mddev->degraded = 0;
- mddev->barriers_work = 0;
mddev->safemode = 0;
mddev->bitmap_info.offset = 0;
mddev->bitmap_info.default_offset = 0;
@@ -5961,16 +5961,14 @@ static int md_open(struct block_device *bdev, fmode_t mode)
mddev_t *mddev = mddev_find(bdev->bd_dev);
int err;
- lock_kernel();
if (mddev->gendisk != bdev->bd_disk) {
/* we are racing with mddev_put which is discarding this
* bd_disk.
*/
mddev_put(mddev);
/* Wait until bdev->bd_disk is definitely gone */
- flush_scheduled_work();
+ flush_workqueue(md_misc_wq);
/* Then retry the open from the top */
- unlock_kernel();
return -ERESTARTSYS;
}
BUG_ON(mddev != bdev->bd_disk->private_data);
@@ -5984,7 +5982,6 @@ static int md_open(struct block_device *bdev, fmode_t mode)
check_disk_size_change(mddev->gendisk, bdev);
out:
- unlock_kernel();
return err;
}
@@ -5993,10 +5990,8 @@ static int md_release(struct gendisk *disk, fmode_t mode)
mddev_t *mddev = disk->private_data;
BUG_ON(!mddev);
- lock_kernel();
atomic_dec(&mddev->openers);
mddev_put(mddev);
- unlock_kernel();
return 0;
}
@@ -6128,7 +6123,7 @@ void md_error(mddev_t *mddev, mdk_rdev_t *rdev)
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
if (mddev->event_work.func)
- schedule_work(&mddev->event_work);
+ queue_work(md_misc_wq, &mddev->event_work);
md_new_event_inintr(mddev);
}
@@ -6580,6 +6575,7 @@ void md_write_start(mddev_t *mddev, struct bio *bi)
if (mddev->in_sync) {
mddev->in_sync = 0;
set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ set_bit(MD_CHANGE_PENDING, &mddev->flags);
md_wakeup_thread(mddev->thread);
did_change = 1;
}
@@ -6588,7 +6584,6 @@ void md_write_start(mddev_t *mddev, struct bio *bi)
if (did_change)
sysfs_notify_dirent_safe(mddev->sysfs_state);
wait_event(mddev->sb_wait,
- !test_bit(MD_CHANGE_CLEAN, &mddev->flags) &&
!test_bit(MD_CHANGE_PENDING, &mddev->flags));
}
@@ -6624,6 +6619,7 @@ int md_allow_write(mddev_t *mddev)
if (mddev->in_sync) {
mddev->in_sync = 0;
set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ set_bit(MD_CHANGE_PENDING, &mddev->flags);
if (mddev->safemode_delay &&
mddev->safemode == 0)
mddev->safemode = 1;
@@ -6633,7 +6629,7 @@ int md_allow_write(mddev_t *mddev)
} else
spin_unlock_irq(&mddev->write_lock);
- if (test_bit(MD_CHANGE_CLEAN, &mddev->flags))
+ if (test_bit(MD_CHANGE_PENDING, &mddev->flags))
return -EAGAIN;
else
return 0;
@@ -6831,8 +6827,7 @@ void md_do_sync(mddev_t *mddev)
atomic_read(&mddev->recovery_active) == 0);
mddev->curr_resync_completed =
mddev->curr_resync;
- if (mddev->persistent)
- set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
@@ -7081,7 +7076,7 @@ void md_check_recovery(mddev_t *mddev)
if (mddev->ro && !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
return;
if ( ! (
- (mddev->flags && !mddev->external) ||
+ (mddev->flags & ~ (1<<MD_CHANGE_PENDING)) ||
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
(mddev->external == 0 && mddev->safemode == 1) ||
@@ -7111,8 +7106,7 @@ void md_check_recovery(mddev_t *mddev)
mddev->recovery_cp == MaxSector) {
mddev->in_sync = 1;
did_change = 1;
- if (mddev->persistent)
- set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
}
if (mddev->safemode == 1)
mddev->safemode = 0;
@@ -7289,12 +7283,23 @@ static void md_geninit(void)
static int __init md_init(void)
{
- if (register_blkdev(MD_MAJOR, "md"))
- return -1;
- if ((mdp_major=register_blkdev(0, "mdp"))<=0) {
- unregister_blkdev(MD_MAJOR, "md");
- return -1;
- }
+ int ret = -ENOMEM;
+
+ md_wq = alloc_workqueue("md", WQ_RESCUER, 0);
+ if (!md_wq)
+ goto err_wq;
+
+ md_misc_wq = alloc_workqueue("md_misc", 0, 0);
+ if (!md_misc_wq)
+ goto err_misc_wq;
+
+ if ((ret = register_blkdev(MD_MAJOR, "md")) < 0)
+ goto err_md;
+
+ if ((ret = register_blkdev(0, "mdp")) < 0)
+ goto err_mdp;
+ mdp_major = ret;
+
blk_register_region(MKDEV(MD_MAJOR, 0), 1UL<<MINORBITS, THIS_MODULE,
md_probe, NULL, NULL);
blk_register_region(MKDEV(mdp_major, 0), 1UL<<MINORBITS, THIS_MODULE,
@@ -7305,8 +7310,16 @@ static int __init md_init(void)
md_geninit();
return 0;
-}
+err_mdp:
+ unregister_blkdev(MD_MAJOR, "md");
+err_md:
+ destroy_workqueue(md_misc_wq);
+err_misc_wq:
+ destroy_workqueue(md_wq);
+err_wq:
+ return ret;
+}
#ifndef MODULE
@@ -7393,6 +7406,8 @@ static __exit void md_exit(void)
export_array(mddev);
mddev->hold_active = 0;
}
+ destroy_workqueue(md_misc_wq);
+ destroy_workqueue(md_wq);
}
subsys_initcall(md_init);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index a953fe2808ae..d05bab55df4e 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -87,7 +87,6 @@ struct mdk_rdev_s
#define Faulty 1 /* device is known to have a fault */
#define In_sync 2 /* device is in_sync with rest of array */
#define WriteMostly 4 /* Avoid reading if at all possible */
-#define BarriersNotsupp 5 /* REQ_HARDBARRIER is not supported */
#define AllReserved 6 /* If whole device is reserved for
* one array */
#define AutoDetected 7 /* added by auto-detect */
@@ -140,7 +139,7 @@ struct mddev_s
unsigned long flags;
#define MD_CHANGE_DEVS 0 /* Some device status has changed */
#define MD_CHANGE_CLEAN 1 /* transition to or from 'clean' */
-#define MD_CHANGE_PENDING 2 /* superblock update in progress */
+#define MD_CHANGE_PENDING 2 /* switch from 'clean' to 'active' in progress */
int suspended;
atomic_t active_io;
@@ -273,13 +272,6 @@ struct mddev_s
int degraded; /* whether md should consider
* adding a spare
*/
- int barriers_work; /* initialised to true, cleared as soon
- * as a barrier request to slave
- * fails. Only supported
- */
- struct bio *biolist; /* bios that need to be retried
- * because REQ_HARDBARRIER is not supported
- */
atomic_t recovery_active; /* blocks scheduled, but not written */
wait_queue_head_t recovery_wait;
@@ -339,16 +331,15 @@ struct mddev_s
struct attribute_group *to_remove;
struct plug_handle *plug; /* if used by personality */
- /* Generic barrier handling.
- * If there is a pending barrier request, all other
- * writes are blocked while the devices are flushed.
- * The last to finish a flush schedules a worker to
- * submit the barrier request (without the barrier flag),
- * then submit more flush requests.
+ struct bio_set *bio_set;
+
+ /* Generic flush handling.
+ * The last to finish preflush schedules a worker to submit
+ * the rest of the request (without the REQ_FLUSH flag).
*/
- struct bio *barrier;
+ struct bio *flush_bio;
atomic_t flush_pending;
- struct work_struct barrier_work;
+ struct work_struct flush_work;
struct work_struct event_work; /* used by dm to report failure event */
};
@@ -502,11 +493,11 @@ extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev);
extern int mddev_congested(mddev_t *mddev, int bits);
-extern void md_barrier_request(mddev_t *mddev, struct bio *bio);
+extern void md_flush_request(mddev_t *mddev, struct bio *bio);
extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
sector_t sector, int size, struct page *page);
extern void md_super_wait(mddev_t *mddev);
-extern int sync_page_io(struct block_device *bdev, sector_t sector, int size,
+extern int sync_page_io(mdk_rdev_t *rdev, sector_t sector, int size,
struct page *page, int rw);
extern void md_do_sync(mddev_t *mddev);
extern void md_new_event(mddev_t *mddev);
@@ -528,4 +519,8 @@ extern void md_rdev_init(mdk_rdev_t *rdev);
extern void mddev_suspend(mddev_t *mddev);
extern void mddev_resume(mddev_t *mddev);
+extern struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask,
+ mddev_t *mddev);
+extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
+ mddev_t *mddev);
#endif /* _MD_MD_H */
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 0307d217e7a4..6d7ddf32ef2e 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -142,8 +142,8 @@ static int multipath_make_request(mddev_t *mddev, struct bio * bio)
struct multipath_bh * mp_bh;
struct multipath_info *multipath;
- if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
- md_barrier_request(mddev, bio);
+ if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+ md_flush_request(mddev, bio);
return 0;
}
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 6f7af46d623c..a39f4c355e55 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -483,8 +483,8 @@ static int raid0_make_request(mddev_t *mddev, struct bio *bio)
struct strip_zone *zone;
mdk_rdev_t *tmp_dev;
- if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
- md_barrier_request(mddev, bio);
+ if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+ md_flush_request(mddev, bio);
return 0;
}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 73cc74ffc26b..45f8324196ec 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -100,7 +100,7 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
* Allocate bios : 1 for reading, n-1 for writing
*/
for (j = pi->raid_disks ; j-- ; ) {
- bio = bio_alloc(gfp_flags, RESYNC_PAGES);
+ bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
if (!bio)
goto out_free_bio;
r1_bio->bios[j] = bio;
@@ -306,6 +306,28 @@ static void raid1_end_read_request(struct bio *bio, int error)
rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
}
+static void r1_bio_write_done(r1bio_t *r1_bio, int vcnt, struct bio_vec *bv,
+ int behind)
+{
+ if (atomic_dec_and_test(&r1_bio->remaining))
+ {
+ /* it really is the end of this request */
+ if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
+ /* free extra copy of the data pages */
+ int i = vcnt;
+ while (i--)
+ safe_put_page(bv[i].bv_page);
+ }
+ /* clear the bitmap if all writes complete successfully */
+ bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
+ r1_bio->sectors,
+ !test_bit(R1BIO_Degraded, &r1_bio->state),
+ behind);
+ md_write_end(r1_bio->mddev);
+ raid_end_bio_io(r1_bio);
+ }
+}
+
static void raid1_end_write_request(struct bio *bio, int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
@@ -319,84 +341,61 @@ static void raid1_end_write_request(struct bio *bio, int error)
if (r1_bio->bios[mirror] == bio)
break;
- if (error == -EOPNOTSUPP && test_bit(R1BIO_Barrier, &r1_bio->state)) {
- set_bit(BarriersNotsupp, &conf->mirrors[mirror].rdev->flags);
- set_bit(R1BIO_BarrierRetry, &r1_bio->state);
- r1_bio->mddev->barriers_work = 0;
- /* Don't rdev_dec_pending in this branch - keep it for the retry */
- } else {
+ /*
+ * 'one mirror IO has finished' event handler:
+ */
+ r1_bio->bios[mirror] = NULL;
+ to_put = bio;
+ if (!uptodate) {
+ md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
+ /* an I/O failed, we can't clear the bitmap */
+ set_bit(R1BIO_Degraded, &r1_bio->state);
+ } else
/*
- * this branch is our 'one mirror IO has finished' event handler:
+ * Set R1BIO_Uptodate in our master bio, so that we
+ * will return a good error code for to the higher
+ * levels even if IO on some other mirrored buffer
+ * fails.
+ *
+ * The 'master' represents the composite IO operation
+ * to user-side. So if something waits for IO, then it
+ * will wait for the 'master' bio.
*/
- r1_bio->bios[mirror] = NULL;
- to_put = bio;
- if (!uptodate) {
- md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
- /* an I/O failed, we can't clear the bitmap */
- set_bit(R1BIO_Degraded, &r1_bio->state);
- } else
- /*
- * Set R1BIO_Uptodate in our master bio, so that
- * we will return a good error code for to the higher
- * levels even if IO on some other mirrored buffer fails.
- *
- * The 'master' represents the composite IO operation to
- * user-side. So if something waits for IO, then it will
- * wait for the 'master' bio.
- */
- set_bit(R1BIO_Uptodate, &r1_bio->state);
-
- update_head_pos(mirror, r1_bio);
-
- if (behind) {
- if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags))
- atomic_dec(&r1_bio->behind_remaining);
-
- /* In behind mode, we ACK the master bio once the I/O has safely
- * reached all non-writemostly disks. Setting the Returned bit
- * ensures that this gets done only once -- we don't ever want to
- * return -EIO here, instead we'll wait */
-
- if (atomic_read(&r1_bio->behind_remaining) >= (atomic_read(&r1_bio->remaining)-1) &&
- test_bit(R1BIO_Uptodate, &r1_bio->state)) {
- /* Maybe we can return now */
- if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
- struct bio *mbio = r1_bio->master_bio;
- PRINTK(KERN_DEBUG "raid1: behind end write sectors %llu-%llu\n",
- (unsigned long long) mbio->bi_sector,
- (unsigned long long) mbio->bi_sector +
- (mbio->bi_size >> 9) - 1);
- bio_endio(mbio, 0);
- }
+ set_bit(R1BIO_Uptodate, &r1_bio->state);
+
+ update_head_pos(mirror, r1_bio);
+
+ if (behind) {
+ if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags))
+ atomic_dec(&r1_bio->behind_remaining);
+
+ /*
+ * In behind mode, we ACK the master bio once the I/O
+ * has safely reached all non-writemostly
+ * disks. Setting the Returned bit ensures that this
+ * gets done only once -- we don't ever want to return
+ * -EIO here, instead we'll wait
+ */
+ if (atomic_read(&r1_bio->behind_remaining) >= (atomic_read(&r1_bio->remaining)-1) &&
+ test_bit(R1BIO_Uptodate, &r1_bio->state)) {
+ /* Maybe we can return now */
+ if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
+ struct bio *mbio = r1_bio->master_bio;
+ PRINTK(KERN_DEBUG "raid1: behind end write sectors %llu-%llu\n",
+ (unsigned long long) mbio->bi_sector,
+ (unsigned long long) mbio->bi_sector +
+ (mbio->bi_size >> 9) - 1);
+ bio_endio(mbio, 0);
}
}
- rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
}
+ rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
+
/*
- *
* Let's see if all mirrored write operations have finished
* already.
*/
- if (atomic_dec_and_test(&r1_bio->remaining)) {
- if (test_bit(R1BIO_BarrierRetry, &r1_bio->state))
- reschedule_retry(r1_bio);
- else {
- /* it really is the end of this request */
- if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
- /* free extra copy of the data pages */
- int i = bio->bi_vcnt;
- while (i--)
- safe_put_page(bio->bi_io_vec[i].bv_page);
- }
- /* clear the bitmap if all writes complete successfully */
- bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
- r1_bio->sectors,
- !test_bit(R1BIO_Degraded, &r1_bio->state),
- behind);
- md_write_end(r1_bio->mddev);
- raid_end_bio_io(r1_bio);
- }
- }
+ r1_bio_write_done(r1_bio, bio->bi_vcnt, bio->bi_io_vec, behind);
if (to_put)
bio_put(to_put);
@@ -420,11 +419,13 @@ static void raid1_end_write_request(struct bio *bio, int error)
static int read_balance(conf_t *conf, r1bio_t *r1_bio)
{
const sector_t this_sector = r1_bio->sector;
- int new_disk = conf->last_used, disk = new_disk;
- int wonly_disk = -1;
const int sectors = r1_bio->sectors;
+ int new_disk = -1;
+ int start_disk;
+ int i;
sector_t new_distance, current_distance;
mdk_rdev_t *rdev;
+ int choose_first;
rcu_read_lock();
/*
@@ -435,54 +436,33 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
retry:
if (conf->mddev->recovery_cp < MaxSector &&
(this_sector + sectors >= conf->next_resync)) {
- /* Choose the first operational device, for consistancy */
- new_disk = 0;
-
- for (rdev = rcu_dereference(conf->mirrors[new_disk].rdev);
- r1_bio->bios[new_disk] == IO_BLOCKED ||
- !rdev || !test_bit(In_sync, &rdev->flags)
- || test_bit(WriteMostly, &rdev->flags);
- rdev = rcu_dereference(conf->mirrors[++new_disk].rdev)) {
-
- if (rdev && test_bit(In_sync, &rdev->flags) &&
- r1_bio->bios[new_disk] != IO_BLOCKED)
- wonly_disk = new_disk;
-
- if (new_disk == conf->raid_disks - 1) {
- new_disk = wonly_disk;
- break;
- }
- }
- goto rb_out;
+ choose_first = 1;
+ start_disk = 0;
+ } else {
+ choose_first = 0;
+ start_disk = conf->last_used;
}
-
/* make sure the disk is operational */
- for (rdev = rcu_dereference(conf->mirrors[new_disk].rdev);
- r1_bio->bios[new_disk] == IO_BLOCKED ||
- !rdev || !test_bit(In_sync, &rdev->flags) ||
- test_bit(WriteMostly, &rdev->flags);
- rdev = rcu_dereference(conf->mirrors[new_disk].rdev)) {
-
- if (rdev && test_bit(In_sync, &rdev->flags) &&
- r1_bio->bios[new_disk] != IO_BLOCKED)
- wonly_disk = new_disk;
-
- if (new_disk <= 0)
- new_disk = conf->raid_disks;
- new_disk--;
- if (new_disk == disk) {
- new_disk = wonly_disk;
+ for (i = 0 ; i < conf->raid_disks ; i++) {
+ int disk = start_disk + i;
+ if (disk >= conf->raid_disks)
+ disk -= conf->raid_disks;
+
+ rdev = rcu_dereference(conf->mirrors[disk].rdev);
+ if (r1_bio->bios[disk] == IO_BLOCKED
+ || rdev == NULL
+ || !test_bit(In_sync, &rdev->flags))
+ continue;
+
+ new_disk = disk;
+ if (!test_bit(WriteMostly, &rdev->flags))
break;
- }
}
- if (new_disk < 0)
+ if (new_disk < 0 || choose_first)
goto rb_out;
- disk = new_disk;
- /* now disk == new_disk == starting point for search */
-
/*
* Don't change to another disk for sequential reads:
*/
@@ -491,20 +471,21 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
if (this_sector == conf->mirrors[new_disk].head_position)
goto rb_out;
- current_distance = abs(this_sector - conf->mirrors[disk].head_position);
+ current_distance = abs(this_sector
+ - conf->mirrors[new_disk].head_position);
- /* Find the disk whose head is closest */
-
- do {
- if (disk <= 0)
- disk = conf->raid_disks;
- disk--;
+ /* look for a better disk - i.e. head is closer */
+ start_disk = new_disk;
+ for (i = 1; i < conf->raid_disks; i++) {
+ int disk = start_disk + 1;
+ if (disk >= conf->raid_disks)
+ disk -= conf->raid_disks;
rdev = rcu_dereference(conf->mirrors[disk].rdev);
-
- if (!rdev || r1_bio->bios[disk] == IO_BLOCKED ||
- !test_bit(In_sync, &rdev->flags) ||
- test_bit(WriteMostly, &rdev->flags))
+ if (r1_bio->bios[disk] == IO_BLOCKED
+ || rdev == NULL
+ || !test_bit(In_sync, &rdev->flags)
+ || test_bit(WriteMostly, &rdev->flags))
continue;
if (!atomic_read(&rdev->nr_pending)) {
@@ -516,11 +497,9 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
current_distance = new_distance;
new_disk = disk;
}
- } while (disk != conf->last_used);
+ }
rb_out:
-
-
if (new_disk >= 0) {
rdev = rcu_dereference(conf->mirrors[new_disk].rdev);
if (!rdev)
@@ -667,7 +646,7 @@ static void raise_barrier(conf_t *conf)
/* block any new IO from starting */
conf->barrier++;
- /* No wait for all pending IO to complete */
+ /* Now wait for all pending IO to complete */
wait_event_lock_irq(conf->wait_barrier,
!conf->nr_pending && conf->barrier < RESYNC_DEPTH,
conf->resync_lock,
@@ -744,23 +723,26 @@ static void unfreeze_array(conf_t *conf)
}
-/* duplicate the data pages for behind I/O */
-static struct page **alloc_behind_pages(struct bio *bio)
+/* duplicate the data pages for behind I/O
+ * We return a list of bio_vec rather than just page pointers
+ * as it makes freeing easier
+ */
+static struct bio_vec *alloc_behind_pages(struct bio *bio)
{
int i;
struct bio_vec *bvec;
- struct page **pages = kzalloc(bio->bi_vcnt * sizeof(struct page *),
+ struct bio_vec *pages = kzalloc(bio->bi_vcnt * sizeof(struct bio_vec),
GFP_NOIO);
if (unlikely(!pages))
goto do_sync_io;
bio_for_each_segment(bvec, bio, i) {
- pages[i] = alloc_page(GFP_NOIO);
- if (unlikely(!pages[i]))
+ pages[i].bv_page = alloc_page(GFP_NOIO);
+ if (unlikely(!pages[i].bv_page))
goto do_sync_io;
- memcpy(kmap(pages[i]) + bvec->bv_offset,
+ memcpy(kmap(pages[i].bv_page) + bvec->bv_offset,
kmap(bvec->bv_page) + bvec->bv_offset, bvec->bv_len);
- kunmap(pages[i]);
+ kunmap(pages[i].bv_page);
kunmap(bvec->bv_page);
}
@@ -768,8 +750,8 @@ static struct page **alloc_behind_pages(struct bio *bio)
do_sync_io:
if (pages)
- for (i = 0; i < bio->bi_vcnt && pages[i]; i++)
- put_page(pages[i]);
+ for (i = 0; i < bio->bi_vcnt && pages[i].bv_page; i++)
+ put_page(pages[i].bv_page);
kfree(pages);
PRINTK("%dB behind alloc failed, doing sync I/O\n", bio->bi_size);
return NULL;
@@ -784,20 +766,16 @@ static int make_request(mddev_t *mddev, struct bio * bio)
int i, targets = 0, disks;
struct bitmap *bitmap;
unsigned long flags;
- struct bio_list bl;
- struct page **behind_pages = NULL;
+ struct bio_vec *behind_pages = NULL;
const int rw = bio_data_dir(bio);
- const bool do_sync = (bio->bi_rw & REQ_SYNC);
- bool do_barriers;
+ const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
+ const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA));
mdk_rdev_t *blocked_rdev;
/*
* Register the new request and wait if the reconstruction
* thread has put up a bar for new requests.
* Continue immediately if no resync is active currently.
- * We test barriers_work *after* md_write_start as md_write_start
- * may cause the first superblock write, and that will check out
- * if barriers work.
*/
md_write_start(mddev, bio); /* wait on superblock update early */
@@ -821,13 +799,6 @@ static int make_request(mddev_t *mddev, struct bio * bio)
}
finish_wait(&conf->wait_barrier, &w);
}
- if (unlikely(!mddev->barriers_work &&
- (bio->bi_rw & REQ_HARDBARRIER))) {
- if (rw == WRITE)
- md_write_end(mddev);
- bio_endio(bio, -EOPNOTSUPP);
- return 0;
- }
wait_barrier(conf);
@@ -870,7 +841,7 @@ static int make_request(mddev_t *mddev, struct bio * bio)
}
r1_bio->read_disk = rdisk;
- read_bio = bio_clone(bio, GFP_NOIO);
+ read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
r1_bio->bios[rdisk] = read_bio;
@@ -892,13 +863,6 @@ static int make_request(mddev_t *mddev, struct bio * bio)
* bios[x] to bio
*/
disks = conf->raid_disks;
-#if 0
- { static int first=1;
- if (first) printk("First Write sector %llu disks %d\n",
- (unsigned long long)r1_bio->sector, disks);
- first = 0;
- }
-#endif
retry_write:
blocked_rdev = NULL;
rcu_read_lock();
@@ -956,26 +920,23 @@ static int make_request(mddev_t *mddev, struct bio * bio)
(behind_pages = alloc_behind_pages(bio)) != NULL)
set_bit(R1BIO_BehindIO, &r1_bio->state);
- atomic_set(&r1_bio->remaining, 0);
+ atomic_set(&r1_bio->remaining, 1);
atomic_set(&r1_bio->behind_remaining, 0);
- do_barriers = bio->bi_rw & REQ_HARDBARRIER;
- if (do_barriers)
- set_bit(R1BIO_Barrier, &r1_bio->state);
-
- bio_list_init(&bl);
+ bitmap_startwrite(bitmap, bio->bi_sector, r1_bio->sectors,
+ test_bit(R1BIO_BehindIO, &r1_bio->state));
for (i = 0; i < disks; i++) {
struct bio *mbio;
if (!r1_bio->bios[i])
continue;
- mbio = bio_clone(bio, GFP_NOIO);
+ mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
r1_bio->bios[i] = mbio;
mbio->bi_sector = r1_bio->sector + conf->mirrors[i].rdev->data_offset;
mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
mbio->bi_end_io = raid1_end_write_request;
- mbio->bi_rw = WRITE | do_barriers | do_sync;
+ mbio->bi_rw = WRITE | do_flush_fua | do_sync;
mbio->bi_private = r1_bio;
if (behind_pages) {
@@ -986,39 +947,29 @@ static int make_request(mddev_t *mddev, struct bio * bio)
* we clear any unused pointer in the io_vec, rather
* than leave them unchanged. This is important
* because when we come to free the pages, we won't
- * know the originial bi_idx, so we just free
+ * know the original bi_idx, so we just free
* them all
*/
__bio_for_each_segment(bvec, mbio, j, 0)
- bvec->bv_page = behind_pages[j];
+ bvec->bv_page = behind_pages[j].bv_page;
if (test_bit(WriteMostly, &conf->mirrors[i].rdev->flags))
atomic_inc(&r1_bio->behind_remaining);
}
atomic_inc(&r1_bio->remaining);
-
- bio_list_add(&bl, mbio);
+ spin_lock_irqsave(&conf->device_lock, flags);
+ bio_list_add(&conf->pending_bio_list, mbio);
+ blk_plug_device(mddev->queue);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
}
+ r1_bio_write_done(r1_bio, bio->bi_vcnt, behind_pages, behind_pages != NULL);
kfree(behind_pages); /* the behind pages are attached to the bios now */
- bitmap_startwrite(bitmap, bio->bi_sector, r1_bio->sectors,
- test_bit(R1BIO_BehindIO, &r1_bio->state));
- spin_lock_irqsave(&conf->device_lock, flags);
- bio_list_merge(&conf->pending_bio_list, &bl);
- bio_list_init(&bl);
-
- blk_plug_device(mddev->queue);
- spin_unlock_irqrestore(&conf->device_lock, flags);
-
- /* In case raid1d snuck into freeze_array */
+ /* In case raid1d snuck in to freeze_array */
wake_up(&conf->wait_barrier);
if (do_sync)
md_wakeup_thread(mddev->thread);
-#if 0
- while ((bio = bio_list_pop(&bl)) != NULL)
- generic_make_request(bio);
-#endif
return 0;
}
@@ -1120,6 +1071,8 @@ static int raid1_spare_active(mddev_t *mddev)
{
int i;
conf_t *conf = mddev->private;
+ int count = 0;
+ unsigned long flags;
/*
* Find all failed disks within the RAID1 configuration
@@ -1131,15 +1084,16 @@ static int raid1_spare_active(mddev_t *mddev)
if (rdev
&& !test_bit(Faulty, &rdev->flags)
&& !test_and_set_bit(In_sync, &rdev->flags)) {
- unsigned long flags;
- spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded--;
- spin_unlock_irqrestore(&conf->device_lock, flags);
+ count++;
+ sysfs_notify_dirent(rdev->sysfs_state);
}
}
+ spin_lock_irqsave(&conf->device_lock, flags);
+ mddev->degraded -= count;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
print_conf(conf);
- return 0;
+ return count;
}
@@ -1203,7 +1157,7 @@ static int raid1_remove_disk(mddev_t *mddev, int number)
err = -EBUSY;
goto abort;
}
- /* Only remove non-faulty devices is recovery
+ /* Only remove non-faulty devices if recovery
* is not possible.
*/
if (!test_bit(Faulty, &rdev->flags) &&
@@ -1265,7 +1219,7 @@ static void end_sync_write(struct bio *bio, int error)
break;
}
if (!uptodate) {
- int sync_blocks = 0;
+ sector_t sync_blocks = 0;
sector_t s = r1_bio->sector;
long sectors_to_go = r1_bio->sectors;
/* make sure these bits doesn't get cleared. */
@@ -1408,7 +1362,7 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
* active, and resync is currently active
*/
rdev = conf->mirrors[d].rdev;
- if (sync_page_io(rdev->bdev,
+ if (sync_page_io(rdev,
sect + rdev->data_offset,
s<<9,
bio->bi_io_vec[idx].bv_page,
@@ -1434,7 +1388,7 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
continue;
rdev = conf->mirrors[d].rdev;
atomic_add(s, &rdev->corrected_errors);
- if (sync_page_io(rdev->bdev,
+ if (sync_page_io(rdev,
sect + rdev->data_offset,
s<<9,
bio->bi_io_vec[idx].bv_page,
@@ -1449,7 +1403,7 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
if (r1_bio->bios[d]->bi_end_io != end_sync_read)
continue;
rdev = conf->mirrors[d].rdev;
- if (sync_page_io(rdev->bdev,
+ if (sync_page_io(rdev,
sect + rdev->data_offset,
s<<9,
bio->bi_io_vec[idx].bv_page,
@@ -1533,7 +1487,7 @@ static void fix_read_error(conf_t *conf, int read_disk,
rdev = conf->mirrors[d].rdev;
if (rdev &&
test_bit(In_sync, &rdev->flags) &&
- sync_page_io(rdev->bdev,
+ sync_page_io(rdev,
sect + rdev->data_offset,
s<<9,
conf->tmppage, READ))
@@ -1559,7 +1513,7 @@ static void fix_read_error(conf_t *conf, int read_disk,
rdev = conf->mirrors[d].rdev;
if (rdev &&
test_bit(In_sync, &rdev->flags)) {
- if (sync_page_io(rdev->bdev,
+ if (sync_page_io(rdev,
sect + rdev->data_offset,
s<<9, conf->tmppage, WRITE)
== 0)
@@ -1576,7 +1530,7 @@ static void fix_read_error(conf_t *conf, int read_disk,
rdev = conf->mirrors[d].rdev;
if (rdev &&
test_bit(In_sync, &rdev->flags)) {
- if (sync_page_io(rdev->bdev,
+ if (sync_page_io(rdev,
sect + rdev->data_offset,
s<<9, conf->tmppage, READ)
== 0)
@@ -1631,41 +1585,6 @@ static void raid1d(mddev_t *mddev)
if (test_bit(R1BIO_IsSync, &r1_bio->state)) {
sync_request_write(mddev, r1_bio);
unplug = 1;
- } else if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) {
- /* some requests in the r1bio were REQ_HARDBARRIER
- * requests which failed with -EOPNOTSUPP. Hohumm..
- * Better resubmit without the barrier.
- * We know which devices to resubmit for, because
- * all others have had their bios[] entry cleared.
- * We already have a nr_pending reference on these rdevs.
- */
- int i;
- const bool do_sync = (r1_bio->master_bio->bi_rw & REQ_SYNC);
- clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
- clear_bit(R1BIO_Barrier, &r1_bio->state);
- for (i=0; i < conf->raid_disks; i++)
- if (r1_bio->bios[i])
- atomic_inc(&r1_bio->remaining);
- for (i=0; i < conf->raid_disks; i++)
- if (r1_bio->bios[i]) {
- struct bio_vec *bvec;
- int j;
-
- bio = bio_clone(r1_bio->master_bio, GFP_NOIO);
- /* copy pages from the failed bio, as
- * this might be a write-behind device */
- __bio_for_each_segment(bvec, bio, j, 0)
- bvec->bv_page = bio_iovec_idx(r1_bio->bios[i], j)->bv_page;
- bio_put(r1_bio->bios[i]);
- bio->bi_sector = r1_bio->sector +
- conf->mirrors[i].rdev->data_offset;
- bio->bi_bdev = conf->mirrors[i].rdev->bdev;
- bio->bi_end_io = raid1_end_write_request;
- bio->bi_rw = WRITE | do_sync;
- bio->bi_private = r1_bio;
- r1_bio->bios[i] = bio;
- generic_make_request(bio);
- }
} else {
int disk;
@@ -1696,12 +1615,13 @@ static void raid1d(mddev_t *mddev)
(unsigned long long)r1_bio->sector);
raid_end_bio_io(r1_bio);
} else {
- const bool do_sync = r1_bio->master_bio->bi_rw & REQ_SYNC;
+ const unsigned long do_sync = r1_bio->master_bio->bi_rw & REQ_SYNC;
r1_bio->bios[r1_bio->read_disk] =
mddev->ro ? IO_BLOCKED : NULL;
r1_bio->read_disk = disk;
bio_put(bio);
- bio = bio_clone(r1_bio->master_bio, GFP_NOIO);
+ bio = bio_clone_mddev(r1_bio->master_bio,
+ GFP_NOIO, mddev);
r1_bio->bios[r1_bio->read_disk] = bio;
rdev = conf->mirrors[disk].rdev;
if (printk_ratelimit())
@@ -1760,7 +1680,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
int i;
int wonly = -1;
int write_targets = 0, read_targets = 0;
- int sync_blocks;
+ sector_t sync_blocks;
int still_degraded = 0;
if (!conf->r1buf_pool)
@@ -1810,11 +1730,11 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
msleep_interruptible(1000);
bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+ r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
raise_barrier(conf);
conf->next_resync = sector_nr;
- r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
rcu_read_lock();
/*
* If we get a correctably read error during resync or recovery,
@@ -1836,7 +1756,9 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
/* take from bio_init */
bio->bi_next = NULL;
+ bio->bi_flags &= ~(BIO_POOL_MASK-1);
bio->bi_flags |= 1 << BIO_UPTODATE;
+ bio->bi_comp_cpu = -1;
bio->bi_rw = READ;
bio->bi_vcnt = 0;
bio->bi_idx = 0;
@@ -1909,7 +1831,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
break;
BUG_ON(sync_blocks < (PAGE_SIZE>>9));
- if (len > (sync_blocks<<9))
+ if ((len >> 9) > sync_blocks)
len = sync_blocks<<9;
}
@@ -2024,7 +1946,6 @@ static conf_t *setup_conf(mddev_t *mddev)
init_waitqueue_head(&conf->wait_barrier);
bio_list_init(&conf->pending_bio_list);
- bio_list_init(&conf->flushing_bio_list);
conf->last_used = -1;
for (i = 0; i < conf->raid_disks; i++) {
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 5f2d443ae28a..cbfdf1a6acd9 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -35,8 +35,6 @@ struct r1_private_data_s {
struct list_head retry_list;
/* queue pending writes and submit them on unplug */
struct bio_list pending_bio_list;
- /* queue of writes that have been unplugged */
- struct bio_list flushing_bio_list;
/* for use when syncing mirrors: */
@@ -117,8 +115,6 @@ struct r1bio_s {
#define R1BIO_IsSync 1
#define R1BIO_Degraded 2
#define R1BIO_BehindIO 3
-#define R1BIO_Barrier 4
-#define R1BIO_BarrierRetry 5
/* For write-behind requests, we call bi_end_io when
* the last non-write-behind device completes, providing
* any write was successful. Otherwise we call when
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index a88aeb5198c7..c67aa54694ae 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -120,7 +120,7 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
* Allocate bios.
*/
for (j = nalloc ; j-- ; ) {
- bio = bio_alloc(gfp_flags, RESYNC_PAGES);
+ bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
if (!bio)
goto out_free_bio;
r10_bio->devs[j].bio = bio;
@@ -799,13 +799,13 @@ static int make_request(mddev_t *mddev, struct bio * bio)
int i;
int chunk_sects = conf->chunk_mask + 1;
const int rw = bio_data_dir(bio);
- const bool do_sync = (bio->bi_rw & REQ_SYNC);
- struct bio_list bl;
+ const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
+ const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
unsigned long flags;
mdk_rdev_t *blocked_rdev;
- if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
- md_barrier_request(mddev, bio);
+ if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+ md_flush_request(mddev, bio);
return 0;
}
@@ -889,7 +889,7 @@ static int make_request(mddev_t *mddev, struct bio * bio)
}
mirror = conf->mirrors + disk;
- read_bio = bio_clone(bio, GFP_NOIO);
+ read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
r10_bio->devs[slot].bio = read_bio;
@@ -949,42 +949,42 @@ static int make_request(mddev_t *mddev, struct bio * bio)
goto retry_write;
}
- atomic_set(&r10_bio->remaining, 0);
+ atomic_set(&r10_bio->remaining, 1);
+ bitmap_startwrite(mddev->bitmap, bio->bi_sector, r10_bio->sectors, 0);
- bio_list_init(&bl);
for (i = 0; i < conf->copies; i++) {
struct bio *mbio;
int d = r10_bio->devs[i].devnum;
if (!r10_bio->devs[i].bio)
continue;
- mbio = bio_clone(bio, GFP_NOIO);
+ mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
r10_bio->devs[i].bio = mbio;
mbio->bi_sector = r10_bio->devs[i].addr+
conf->mirrors[d].rdev->data_offset;
mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw = WRITE | do_sync;
+ mbio->bi_rw = WRITE | do_sync | do_fua;
mbio->bi_private = r10_bio;
atomic_inc(&r10_bio->remaining);
- bio_list_add(&bl, mbio);
+ spin_lock_irqsave(&conf->device_lock, flags);
+ bio_list_add(&conf->pending_bio_list, mbio);
+ blk_plug_device(mddev->queue);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
}
- if (unlikely(!atomic_read(&r10_bio->remaining))) {
- /* the array is dead */
+ if (atomic_dec_and_test(&r10_bio->remaining)) {
+ /* This matches the end of raid10_end_write_request() */
+ bitmap_endwrite(r10_bio->mddev->bitmap, r10_bio->sector,
+ r10_bio->sectors,
+ !test_bit(R10BIO_Degraded, &r10_bio->state),
+ 0);
md_write_end(mddev);
raid_end_bio_io(r10_bio);
- return 0;
}
- bitmap_startwrite(mddev->bitmap, bio->bi_sector, r10_bio->sectors, 0);
- spin_lock_irqsave(&conf->device_lock, flags);
- bio_list_merge(&conf->pending_bio_list, &bl);
- blk_plug_device(mddev->queue);
- spin_unlock_irqrestore(&conf->device_lock, flags);
-
/* In case raid10d snuck in to freeze_array */
wake_up(&conf->wait_barrier);
@@ -1116,6 +1116,8 @@ static int raid10_spare_active(mddev_t *mddev)
int i;
conf_t *conf = mddev->private;
mirror_info_t *tmp;
+ int count = 0;
+ unsigned long flags;
/*
* Find all non-in_sync disks within the RAID10 configuration
@@ -1126,15 +1128,16 @@ static int raid10_spare_active(mddev_t *mddev)
if (tmp->rdev
&& !test_bit(Faulty, &tmp->rdev->flags)
&& !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
- unsigned long flags;
- spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded--;
- spin_unlock_irqrestore(&conf->device_lock, flags);
+ count++;
+ sysfs_notify_dirent(tmp->rdev->sysfs_state);
}
}
+ spin_lock_irqsave(&conf->device_lock, flags);
+ mddev->degraded -= count;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
print_conf(conf);
- return 0;
+ return count;
}
@@ -1554,7 +1557,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
test_bit(In_sync, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
- success = sync_page_io(rdev->bdev,
+ success = sync_page_io(rdev,
r10_bio->devs[sl].addr +
sect + rdev->data_offset,
s<<9,
@@ -1593,7 +1596,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
atomic_add(s, &rdev->corrected_errors);
- if (sync_page_io(rdev->bdev,
+ if (sync_page_io(rdev,
r10_bio->devs[sl].addr +
sect + rdev->data_offset,
s<<9, conf->tmppage, WRITE)
@@ -1630,7 +1633,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
char b[BDEVNAME_SIZE];
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
- if (sync_page_io(rdev->bdev,
+ if (sync_page_io(rdev,
r10_bio->devs[sl].addr +
sect + rdev->data_offset,
s<<9, conf->tmppage,
@@ -1734,7 +1737,7 @@ static void raid10d(mddev_t *mddev)
raid_end_bio_io(r10_bio);
bio_put(bio);
} else {
- const bool do_sync = (r10_bio->master_bio->bi_rw & REQ_SYNC);
+ const unsigned long do_sync = (r10_bio->master_bio->bi_rw & REQ_SYNC);
bio_put(bio);
rdev = conf->mirrors[mirror].rdev;
if (printk_ratelimit())
@@ -1743,7 +1746,8 @@ static void raid10d(mddev_t *mddev)
mdname(mddev),
bdevname(rdev->bdev,b),
(unsigned long long)r10_bio->sector);
- bio = bio_clone(r10_bio->master_bio, GFP_NOIO);
+ bio = bio_clone_mddev(r10_bio->master_bio,
+ GFP_NOIO, mddev);
r10_bio->devs[r10_bio->read_slot].bio = bio;
bio->bi_sector = r10_bio->devs[r10_bio->read_slot].addr
+ rdev->data_offset;
@@ -1816,7 +1820,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
int disk;
int i;
int max_sync;
- int sync_blocks;
+ sector_t sync_blocks;
sector_t sectors_skipped = 0;
int chunks_skipped = 0;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 866d4b5a144c..dc574f303f8b 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -506,9 +506,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
int rw;
struct bio *bi;
mdk_rdev_t *rdev;
- if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
- rw = WRITE;
- else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
+ if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
+ if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags))
+ rw = WRITE_FUA;
+ else
+ rw = WRITE;
+ } else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
rw = READ;
else
continue;
@@ -1031,6 +1034,8 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
while (wbi && wbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
+ if (wbi->bi_rw & REQ_FUA)
+ set_bit(R5_WantFUA, &dev->flags);
tx = async_copy_data(1, wbi, dev->page,
dev->sector, tx);
wbi = r5_next_bio(wbi, dev->sector);
@@ -1048,15 +1053,22 @@ static void ops_complete_reconstruct(void *stripe_head_ref)
int pd_idx = sh->pd_idx;
int qd_idx = sh->qd_idx;
int i;
+ bool fua = false;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
+ for (i = disks; i--; )
+ fua |= test_bit(R5_WantFUA, &sh->dev[i].flags);
+
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- if (dev->written || i == pd_idx || i == qd_idx)
+ if (dev->written || i == pd_idx || i == qd_idx) {
set_bit(R5_UPTODATE, &dev->flags);
+ if (fua)
+ set_bit(R5_WantFUA, &dev->flags);
+ }
}
if (sh->reconstruct_state == reconstruct_state_drain_run)
@@ -3281,7 +3293,7 @@ static void handle_stripe5(struct stripe_head *sh)
if (dec_preread_active) {
/* We delay this until after ops_run_io so that if make_request
- * is waiting on a barrier, it won't continue until the writes
+ * is waiting on a flush, it won't continue until the writes
* have actually been submitted.
*/
atomic_dec(&conf->preread_active_stripes);
@@ -3583,7 +3595,7 @@ static void handle_stripe6(struct stripe_head *sh)
if (dec_preread_active) {
/* We delay this until after ops_run_io so that if make_request
- * is waiting on a barrier, it won't continue until the writes
+ * is waiting on a flush, it won't continue until the writes
* have actually been submitted.
*/
atomic_dec(&conf->preread_active_stripes);
@@ -3864,9 +3876,9 @@ static int chunk_aligned_read(mddev_t *mddev, struct bio * raid_bio)
return 0;
}
/*
- * use bio_clone to make a copy of the bio
+ * use bio_clone_mddev to make a copy of the bio
*/
- align_bi = bio_clone(raid_bio, GFP_NOIO);
+ align_bi = bio_clone_mddev(raid_bio, GFP_NOIO, mddev);
if (!align_bi)
return 0;
/*
@@ -3978,14 +3990,8 @@ static int make_request(mddev_t *mddev, struct bio * bi)
const int rw = bio_data_dir(bi);
int remaining;
- if (unlikely(bi->bi_rw & REQ_HARDBARRIER)) {
- /* Drain all pending writes. We only really need
- * to ensure they have been submitted, but this is
- * easier.
- */
- mddev->pers->quiesce(mddev, 1);
- mddev->pers->quiesce(mddev, 0);
- md_barrier_request(mddev, bi);
+ if (unlikely(bi->bi_rw & REQ_FLUSH)) {
+ md_flush_request(mddev, bi);
return 0;
}
@@ -4103,7 +4109,7 @@ static int make_request(mddev_t *mddev, struct bio * bi)
finish_wait(&conf->wait_for_overlap, &w);
set_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
- if (mddev->barrier &&
+ if ((bi->bi_rw & REQ_SYNC) &&
!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
atomic_inc(&conf->preread_active_stripes);
release_stripe(sh);
@@ -4126,13 +4132,6 @@ static int make_request(mddev_t *mddev, struct bio * bi)
bio_endio(bi, 0);
}
- if (mddev->barrier) {
- /* We need to wait for the stripes to all be handled.
- * So: wait for preread_active_stripes to drop to 0.
- */
- wait_event(mddev->thread->wqueue,
- atomic_read(&conf->preread_active_stripes) == 0);
- }
return 0;
}
@@ -4361,7 +4360,7 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
raid5_conf_t *conf = mddev->private;
struct stripe_head *sh;
sector_t max_sector = mddev->dev_sectors;
- int sync_blocks;
+ sector_t sync_blocks;
int still_degraded = 0;
int i;
@@ -5330,6 +5329,8 @@ static int raid5_spare_active(mddev_t *mddev)
int i;
raid5_conf_t *conf = mddev->private;
struct disk_info *tmp;
+ int count = 0;
+ unsigned long flags;
for (i = 0; i < conf->raid_disks; i++) {
tmp = conf->disks + i;
@@ -5337,14 +5338,15 @@ static int raid5_spare_active(mddev_t *mddev)
&& tmp->rdev->recovery_offset == MaxSector
&& !test_bit(Faulty, &tmp->rdev->flags)
&& !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
- unsigned long flags;
- spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded--;
- spin_unlock_irqrestore(&conf->device_lock, flags);
+ count++;
+ sysfs_notify_dirent(tmp->rdev->sysfs_state);
}
}
+ spin_lock_irqsave(&conf->device_lock, flags);
+ mddev->degraded -= count;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
print_raid5_conf(conf);
- return 0;
+ return count;
}
static int raid5_remove_disk(mddev_t *mddev, int number)
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 36eaed5dfd6e..2ace0582b409 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -275,6 +275,7 @@ struct r6_state {
* filling
*/
#define R5_Wantdrain 13 /* dev->towrite needs to be drained */
+#define R5_WantFUA 14 /* Write should be FUA */
/*
* Write method
*/
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-30 23:24:56 +0100