summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/Kconfig5
-rw-r--r--drivers/md/bitmap.c2
-rw-r--r--drivers/md/dm-mpath.c11
-rw-r--r--drivers/md/dm-raid.c95
-rw-r--r--drivers/md/dm-table.c61
-rw-r--r--drivers/md/dm-thin.c135
-rw-r--r--drivers/md/dm-verity.c8
-rw-r--r--drivers/md/dm.c71
-rw-r--r--drivers/md/dm.h1
-rw-r--r--drivers/md/md.c82
-rw-r--r--drivers/md/md.h11
-rw-r--r--drivers/md/raid1.c224
-rw-r--r--drivers/md/raid1.h30
-rw-r--r--drivers/md/raid10.c133
-rw-r--r--drivers/md/raid10.h25
-rw-r--r--drivers/md/raid5.c320
-rw-r--r--drivers/md/raid5.h3
17 files changed, 815 insertions, 402 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 1eee45b69b71..d949b781f6f8 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -268,13 +268,14 @@ config DM_MIRROR
needed for live data migration tools such as 'pvmove'.
config DM_RAID
- tristate "RAID 1/4/5/6 target"
+ tristate "RAID 1/4/5/6/10 target"
depends on BLK_DEV_DM
select MD_RAID1
+ select MD_RAID10
select MD_RAID456
select BLK_DEV_MD
---help---
- A dm target that supports RAID1, RAID4, RAID5 and RAID6 mappings
+ A dm target that supports RAID1, RAID10, RAID4, RAID5 and RAID6 mappings
A RAID-5 set of N drives with a capacity of C MB per drive provides
the capacity of C * (N - 1) MB, and protects against a failure
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 15dbe03117e4..94e7f6ba2e11 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1305,7 +1305,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
prepare_to_wait(&bitmap->overflow_wait, &__wait,
TASK_UNINTERRUPTIBLE);
spin_unlock_irq(&bitmap->counts.lock);
- io_schedule();
+ schedule();
finish_wait(&bitmap->overflow_wait, &__wait);
continue;
}
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index d8abb90a6c2f..034233eefc82 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1555,6 +1555,7 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
unsigned long arg)
{
struct multipath *m = ti->private;
+ struct pgpath *pgpath;
struct block_device *bdev;
fmode_t mode;
unsigned long flags;
@@ -1570,12 +1571,14 @@ again:
if (!m->current_pgpath)
__choose_pgpath(m, 0);
- if (m->current_pgpath) {
- bdev = m->current_pgpath->path.dev->bdev;
- mode = m->current_pgpath->path.dev->mode;
+ pgpath = m->current_pgpath;
+
+ if (pgpath) {
+ bdev = pgpath->path.dev->bdev;
+ mode = pgpath->path.dev->mode;
}
- if (m->queue_io)
+ if ((pgpath && m->queue_io) || (!pgpath && m->queue_if_no_path))
r = -EAGAIN;
else if (!bdev)
r = -EIO;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index f2f29c526544..982e3e390c45 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -11,6 +11,7 @@
#include "md.h"
#include "raid1.h"
#include "raid5.h"
+#include "raid10.h"
#include "bitmap.h"
#include <linux/device-mapper.h>
@@ -52,7 +53,10 @@ struct raid_dev {
#define DMPF_MAX_RECOVERY_RATE 0x20
#define DMPF_MAX_WRITE_BEHIND 0x40
#define DMPF_STRIPE_CACHE 0x80
-#define DMPF_REGION_SIZE 0X100
+#define DMPF_REGION_SIZE 0x100
+#define DMPF_RAID10_COPIES 0x200
+#define DMPF_RAID10_FORMAT 0x400
+
struct raid_set {
struct dm_target *ti;
@@ -76,6 +80,7 @@ static struct raid_type {
const unsigned algorithm; /* RAID algorithm. */
} raid_types[] = {
{"raid1", "RAID1 (mirroring)", 0, 2, 1, 0 /* NONE */},
+ {"raid10", "RAID10 (striped mirrors)", 0, 2, 10, UINT_MAX /* Varies */},
{"raid4", "RAID4 (dedicated parity disk)", 1, 2, 5, ALGORITHM_PARITY_0},
{"raid5_la", "RAID5 (left asymmetric)", 1, 2, 5, ALGORITHM_LEFT_ASYMMETRIC},
{"raid5_ra", "RAID5 (right asymmetric)", 1, 2, 5, ALGORITHM_RIGHT_ASYMMETRIC},
@@ -86,6 +91,17 @@ static struct raid_type {
{"raid6_nc", "RAID6 (N continue)", 2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE}
};
+static unsigned raid10_md_layout_to_copies(int layout)
+{
+ return layout & 0xFF;
+}
+
+static int raid10_format_to_md_layout(char *format, unsigned copies)
+{
+ /* 1 "far" copy, and 'copies' "near" copies */
+ return (1 << 8) | (copies & 0xFF);
+}
+
static struct raid_type *get_raid_type(char *name)
{
int i;
@@ -339,10 +355,16 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
* [max_write_behind <sectors>] See '-write-behind=' (man mdadm)
* [stripe_cache <sectors>] Stripe cache size for higher RAIDs
* [region_size <sectors>] Defines granularity of bitmap
+ *
+ * RAID10-only options:
+ * [raid10_copies <# copies>] Number of copies. (Default: 2)
+ * [raid10_format <near>] Layout algorithm. (Default: near)
*/
static int parse_raid_params(struct raid_set *rs, char **argv,
unsigned num_raid_params)
{
+ char *raid10_format = "near";
+ unsigned raid10_copies = 2;
unsigned i, rebuild_cnt = 0;
unsigned long value, region_size = 0;
sector_t sectors_per_dev = rs->ti->len;
@@ -416,11 +438,28 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
}
key = argv[i++];
+
+ /* Parameters that take a string value are checked here. */
+ if (!strcasecmp(key, "raid10_format")) {
+ if (rs->raid_type->level != 10) {
+ rs->ti->error = "'raid10_format' is an invalid parameter for this RAID type";
+ return -EINVAL;
+ }
+ if (strcmp("near", argv[i])) {
+ rs->ti->error = "Invalid 'raid10_format' value given";
+ return -EINVAL;
+ }
+ raid10_format = argv[i];
+ rs->print_flags |= DMPF_RAID10_FORMAT;
+ continue;
+ }
+
if (strict_strtoul(argv[i], 10, &value) < 0) {
rs->ti->error = "Bad numerical argument given in raid params";
return -EINVAL;
}
+ /* Parameters that take a numeric value are checked here */
if (!strcasecmp(key, "rebuild")) {
rebuild_cnt++;
@@ -439,6 +478,7 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
return -EINVAL;
}
break;
+ case 10:
default:
DMERR("The rebuild parameter is not supported for %s", rs->raid_type->name);
rs->ti->error = "Rebuild not supported for this RAID type";
@@ -495,7 +535,8 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
*/
value /= 2;
- if (rs->raid_type->level < 5) {
+ if ((rs->raid_type->level != 5) &&
+ (rs->raid_type->level != 6)) {
rs->ti->error = "Inappropriate argument: stripe_cache";
return -EINVAL;
}
@@ -520,6 +561,14 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
} else if (!strcasecmp(key, "region_size")) {
rs->print_flags |= DMPF_REGION_SIZE;
region_size = value;
+ } else if (!strcasecmp(key, "raid10_copies") &&
+ (rs->raid_type->level == 10)) {
+ if ((value < 2) || (value > 0xFF)) {
+ rs->ti->error = "Bad value for 'raid10_copies'";
+ return -EINVAL;
+ }
+ rs->print_flags |= DMPF_RAID10_COPIES;
+ raid10_copies = value;
} else {
DMERR("Unable to parse RAID parameter: %s", key);
rs->ti->error = "Unable to parse RAID parameters";
@@ -538,8 +587,22 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
if (dm_set_target_max_io_len(rs->ti, max_io_len))
return -EINVAL;
- if ((rs->raid_type->level > 1) &&
- sector_div(sectors_per_dev, (rs->md.raid_disks - rs->raid_type->parity_devs))) {
+ if (rs->raid_type->level == 10) {
+ if (raid10_copies > rs->md.raid_disks) {
+ rs->ti->error = "Not enough devices to satisfy specification";
+ return -EINVAL;
+ }
+
+ /* (Len * #mirrors) / #devices */
+ sectors_per_dev = rs->ti->len * raid10_copies;
+ sector_div(sectors_per_dev, rs->md.raid_disks);
+
+ rs->md.layout = raid10_format_to_md_layout(raid10_format,
+ raid10_copies);
+ rs->md.new_layout = rs->md.layout;
+ } else if ((rs->raid_type->level > 1) &&
+ sector_div(sectors_per_dev,
+ (rs->md.raid_disks - rs->raid_type->parity_devs))) {
rs->ti->error = "Target length not divisible by number of data devices";
return -EINVAL;
}
@@ -566,6 +629,9 @@ static int raid_is_congested(struct dm_target_callbacks *cb, int bits)
if (rs->raid_type->level == 1)
return md_raid1_congested(&rs->md, bits);
+ if (rs->raid_type->level == 10)
+ return md_raid10_congested(&rs->md, bits);
+
return md_raid5_congested(&rs->md, bits);
}
@@ -884,6 +950,9 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
case 6:
redundancy = rs->raid_type->parity_devs;
break;
+ case 10:
+ redundancy = raid10_md_layout_to_copies(mddev->layout) - 1;
+ break;
default:
ti->error = "Unknown RAID type";
return -EINVAL;
@@ -1049,12 +1118,19 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
goto bad;
}
+ if (ti->len != rs->md.array_sectors) {
+ ti->error = "Array size does not match requested target length";
+ ret = -EINVAL;
+ goto size_mismatch;
+ }
rs->callbacks.congested_fn = raid_is_congested;
dm_table_add_target_callbacks(ti->table, &rs->callbacks);
mddev_suspend(&rs->md);
return 0;
+size_mismatch:
+ md_stop(&rs->md);
bad:
context_free(rs);
@@ -1203,6 +1279,13 @@ static int raid_status(struct dm_target *ti, status_type_t type,
DMEMIT(" region_size %lu",
rs->md.bitmap_info.chunksize >> 9);
+ if (rs->print_flags & DMPF_RAID10_COPIES)
+ DMEMIT(" raid10_copies %u",
+ raid10_md_layout_to_copies(rs->md.layout));
+
+ if (rs->print_flags & DMPF_RAID10_FORMAT)
+ DMEMIT(" raid10_format near");
+
DMEMIT(" %d", rs->md.raid_disks);
for (i = 0; i < rs->md.raid_disks; i++) {
if (rs->dev[i].meta_dev)
@@ -1277,7 +1360,7 @@ static void raid_resume(struct dm_target *ti)
static struct target_type raid_target = {
.name = "raid",
- .version = {1, 2, 0},
+ .version = {1, 3, 0},
.module = THIS_MODULE,
.ctr = raid_ctr,
.dtr = raid_dtr,
@@ -1304,6 +1387,8 @@ module_init(dm_raid_init);
module_exit(dm_raid_exit);
MODULE_DESCRIPTION(DM_NAME " raid4/5/6 target");
+MODULE_ALIAS("dm-raid1");
+MODULE_ALIAS("dm-raid10");
MODULE_ALIAS("dm-raid4");
MODULE_ALIAS("dm-raid5");
MODULE_ALIAS("dm-raid6");
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index f90069029aae..100368eb7991 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1212,6 +1212,41 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector)
return &t->targets[(KEYS_PER_NODE * n) + k];
}
+static int count_device(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ unsigned *num_devices = data;
+
+ (*num_devices)++;
+
+ return 0;
+}
+
+/*
+ * Check whether a table has no data devices attached using each
+ * target's iterate_devices method.
+ * Returns false if the result is unknown because a target doesn't
+ * support iterate_devices.
+ */
+bool dm_table_has_no_data_devices(struct dm_table *table)
+{
+ struct dm_target *uninitialized_var(ti);
+ unsigned i = 0, num_devices = 0;
+
+ while (i < dm_table_get_num_targets(table)) {
+ ti = dm_table_get_target(table, i++);
+
+ if (!ti->type->iterate_devices)
+ return false;
+
+ ti->type->iterate_devices(ti, count_device, &num_devices);
+ if (num_devices)
+ return false;
+ }
+
+ return true;
+}
+
/*
* Establish the new table's queue_limits and validate them.
*/
@@ -1354,17 +1389,25 @@ static int device_is_nonrot(struct dm_target *ti, struct dm_dev *dev,
return q && blk_queue_nonrot(q);
}
-static bool dm_table_is_nonrot(struct dm_table *t)
+static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ struct request_queue *q = bdev_get_queue(dev->bdev);
+
+ return q && !blk_queue_add_random(q);
+}
+
+static bool dm_table_all_devices_attribute(struct dm_table *t,
+ iterate_devices_callout_fn func)
{
struct dm_target *ti;
unsigned i = 0;
- /* Ensure that all underlying device are non-rotational. */
while (i < dm_table_get_num_targets(t)) {
ti = dm_table_get_target(t, i++);
if (!ti->type->iterate_devices ||
- !ti->type->iterate_devices(ti, device_is_nonrot, NULL))
+ !ti->type->iterate_devices(ti, func, NULL))
return 0;
}
@@ -1396,7 +1439,8 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
if (!dm_table_discard_zeroes_data(t))
q->limits.discard_zeroes_data = 0;
- if (dm_table_is_nonrot(t))
+ /* Ensure that all underlying devices are non-rotational. */
+ if (dm_table_all_devices_attribute(t, device_is_nonrot))
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
else
queue_flag_clear_unlocked(QUEUE_FLAG_NONROT, q);
@@ -1404,6 +1448,15 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
dm_table_set_integrity(t);
/*
+ * Determine whether or not this queue's I/O timings contribute
+ * to the entropy pool, Only request-based targets use this.
+ * Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not
+ * have it set.
+ */
+ if (blk_queue_add_random(q) && dm_table_all_devices_attribute(t, device_is_not_random))
+ queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q);
+
+ /*
* QUEUE_FLAG_STACKABLE must be set after all queue settings are
* visible to other CPUs because, once the flag is set, incoming bios
* are processed by request-based dm, which refers to the queue
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index af1fc3b2c2ad..c29410af1e22 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -509,9 +509,9 @@ enum pool_mode {
struct pool_features {
enum pool_mode mode;
- unsigned zero_new_blocks:1;
- unsigned discard_enabled:1;
- unsigned discard_passdown:1;
+ bool zero_new_blocks:1;
+ bool discard_enabled:1;
+ bool discard_passdown:1;
};
struct thin_c;
@@ -580,7 +580,8 @@ struct pool_c {
struct dm_target_callbacks callbacks;
dm_block_t low_water_blocks;
- struct pool_features pf;
+ struct pool_features requested_pf; /* Features requested during table load */
+ struct pool_features adjusted_pf; /* Features used after adjusting for constituent devices */
};
/*
@@ -1839,6 +1840,47 @@ static void __requeue_bios(struct pool *pool)
/*----------------------------------------------------------------
* Binding of control targets to a pool object
*--------------------------------------------------------------*/
+static bool data_dev_supports_discard(struct pool_c *pt)
+{
+ struct request_queue *q = bdev_get_queue(pt->data_dev->bdev);
+
+ return q && blk_queue_discard(q);
+}
+
+/*
+ * If discard_passdown was enabled verify that the data device
+ * supports discards. Disable discard_passdown if not.
+ */
+static void disable_passdown_if_not_supported(struct pool_c *pt)
+{
+ struct pool *pool = pt->pool;
+ struct block_device *data_bdev = pt->data_dev->bdev;
+ struct queue_limits *data_limits = &bdev_get_queue(data_bdev)->limits;
+ sector_t block_size = pool->sectors_per_block << SECTOR_SHIFT;
+ const char *reason = NULL;
+ char buf[BDEVNAME_SIZE];
+
+ if (!pt->adjusted_pf.discard_passdown)
+ return;
+
+ if (!data_dev_supports_discard(pt))
+ reason = "discard unsupported";
+
+ else if (data_limits->max_discard_sectors < pool->sectors_per_block)
+ reason = "max discard sectors smaller than a block";
+
+ else if (data_limits->discard_granularity > block_size)
+ reason = "discard granularity larger than a block";
+
+ else if (block_size & (data_limits->discard_granularity - 1))
+ reason = "discard granularity not a factor of block size";
+
+ if (reason) {
+ DMWARN("Data device (%s) %s: Disabling discard passdown.", bdevname(data_bdev, buf), reason);
+ pt->adjusted_pf.discard_passdown = false;
+ }
+}
+
static int bind_control_target(struct pool *pool, struct dm_target *ti)
{
struct pool_c *pt = ti->private;
@@ -1847,31 +1889,16 @@ static int bind_control_target(struct pool *pool, struct dm_target *ti)
* We want to make sure that degraded pools are never upgraded.
*/
enum pool_mode old_mode = pool->pf.mode;
- enum pool_mode new_mode = pt->pf.mode;
+ enum pool_mode new_mode = pt->adjusted_pf.mode;
if (old_mode > new_mode)
new_mode = old_mode;
pool->ti = ti;
pool->low_water_blocks = pt->low_water_blocks;
- pool->pf = pt->pf;
- set_pool_mode(pool, new_mode);
+ pool->pf = pt->adjusted_pf;
- /*
- * If discard_passdown was enabled verify that the data device
- * supports discards. Disable discard_passdown if not; otherwise
- * -EOPNOTSUPP will be returned.
- */
- /* FIXME: pull this out into a sep fn. */
- if (pt->pf.discard_passdown) {
- struct request_queue *q = bdev_get_queue(pt->data_dev->bdev);
- if (!q || !blk_queue_discard(q)) {
- char buf[BDEVNAME_SIZE];
- DMWARN("Discard unsupported by data device (%s): Disabling discard passdown.",
- bdevname(pt->data_dev->bdev, buf));
- pool->pf.discard_passdown = 0;
- }
- }
+ set_pool_mode(pool, new_mode);
return 0;
}
@@ -1889,9 +1916,9 @@ static void unbind_control_target(struct pool *pool, struct dm_target *ti)
static void pool_features_init(struct pool_features *pf)
{
pf->mode = PM_WRITE;
- pf->zero_new_blocks = 1;
- pf->discard_enabled = 1;
- pf->discard_passdown = 1;
+ pf->zero_new_blocks = true;
+ pf->discard_enabled = true;
+ pf->discard_passdown = true;
}
static void __pool_destroy(struct pool *pool)
@@ -2119,13 +2146,13 @@ static int parse_pool_features(struct dm_arg_set *as, struct pool_features *pf,
argc--;
if (!strcasecmp(arg_name, "skip_block_zeroing"))
- pf->zero_new_blocks = 0;
+ pf->zero_new_blocks = false;
else if (!strcasecmp(arg_name, "ignore_discard"))
- pf->discard_enabled = 0;
+ pf->discard_enabled = false;
else if (!strcasecmp(arg_name, "no_discard_passdown"))
- pf->discard_passdown = 0;
+ pf->discard_passdown = false;
else if (!strcasecmp(arg_name, "read_only"))
pf->mode = PM_READ_ONLY;
@@ -2259,8 +2286,9 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
pt->metadata_dev = metadata_dev;
pt->data_dev = data_dev;
pt->low_water_blocks = low_water_blocks;
- pt->pf = pf;
+ pt->adjusted_pf = pt->requested_pf = pf;
ti->num_flush_requests = 1;
+
/*
* Only need to enable discards if the pool should pass
* them down to the data device. The thin device's discard
@@ -2268,12 +2296,14 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
*/
if (pf.discard_enabled && pf.discard_passdown) {
ti->num_discard_requests = 1;
+
/*
* Setting 'discards_supported' circumvents the normal
* stacking of discard limits (this keeps the pool and
* thin devices' discard limits consistent).
*/
ti->discards_supported = true;
+ ti->discard_zeroes_data_unsupported = true;
}
ti->private = pt;
@@ -2703,7 +2733,7 @@ static int pool_status(struct dm_target *ti, status_type_t type,
format_dev_t(buf2, pt->data_dev->bdev->bd_dev),
(unsigned long)pool->sectors_per_block,
(unsigned long long)pt->low_water_blocks);
- emit_flags(&pt->pf, result, sz, maxlen);
+ emit_flags(&pt->requested_pf, result, sz, maxlen);
break;
}
@@ -2732,20 +2762,21 @@ static int pool_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
}
-static void set_discard_limits(struct pool *pool, struct queue_limits *limits)
+static void set_discard_limits(struct pool_c *pt, struct queue_limits *limits)
{
- /*
- * FIXME: these limits may be incompatible with the pool's data device
- */
+ struct pool *pool = pt->pool;
+ struct queue_limits *data_limits;
+
limits->max_discard_sectors = pool->sectors_per_block;
/*
- * This is just a hint, and not enforced. We have to cope with
- * bios that cover a block partially. A discard that spans a block
- * boundary is not sent to this target.
+ * discard_granularity is just a hint, and not enforced.
*/
- limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
- limits->discard_zeroes_data = pool->pf.zero_new_blocks;
+ if (pt->adjusted_pf.discard_passdown) {
+ data_limits = &bdev_get_queue(pt->data_dev->bdev)->limits;
+ limits->discard_granularity = data_limits->discard_granularity;
+ } else
+ limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
}
static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
@@ -2755,15 +2786,25 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
blk_limits_io_min(limits, 0);
blk_limits_io_opt(limits, pool->sectors_per_block << SECTOR_SHIFT);
- if (pool->pf.discard_enabled)
- set_discard_limits(pool, limits);
+
+ /*
+ * pt->adjusted_pf is a staging area for the actual features to use.
+ * They get transferred to the live pool in bind_control_target()
+ * called from pool_preresume().
+ */
+ if (!pt->adjusted_pf.discard_enabled)
+ return;
+
+ disable_passdown_if_not_supported(pt);
+
+ set_discard_limits(pt, limits);
}
static struct target_type pool_target = {
.name = "thin-pool",
.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
DM_TARGET_IMMUTABLE,
- .version = {1, 3, 0},
+ .version = {1, 4, 0},
.module = THIS_MODULE,
.ctr = pool_ctr,
.dtr = pool_dtr,
@@ -3042,19 +3083,19 @@ static int thin_iterate_devices(struct dm_target *ti,
return 0;
}
+/*
+ * A thin device always inherits its queue limits from its pool.
+ */
static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
{
struct thin_c *tc = ti->private;
- struct pool *pool = tc->pool;
- blk_limits_io_min(limits, 0);
- blk_limits_io_opt(limits, pool->sectors_per_block << SECTOR_SHIFT);
- set_discard_limits(pool, limits);
+ *limits = bdev_get_queue(tc->pool_dev->bdev)->limits;
}
static struct target_type thin_target = {
.name = "thin",
- .version = {1, 3, 0},
+ .version = {1, 4, 0},
.module = THIS_MODULE,
.ctr = thin_ctr,
.dtr = thin_dtr,
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
index 254d19268ad2..892ae2766aa6 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity.c
@@ -718,8 +718,8 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
v->hash_dev_block_bits = ffs(num) - 1;
if (sscanf(argv[5], "%llu%c", &num_ll, &dummy) != 1 ||
- num_ll << (v->data_dev_block_bits - SECTOR_SHIFT) !=
- (sector_t)num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) {
+ (sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT))
+ >> (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll) {
ti->error = "Invalid data blocks";
r = -EINVAL;
goto bad;
@@ -733,8 +733,8 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
}
if (sscanf(argv[6], "%llu%c", &num_ll, &dummy) != 1 ||
- num_ll << (v->hash_dev_block_bits - SECTOR_SHIFT) !=
- (sector_t)num_ll << (v->hash_dev_block_bits - SECTOR_SHIFT)) {
+ (sector_t)(num_ll << (v->hash_dev_block_bits - SECTOR_SHIFT))
+ >> (v->hash_dev_block_bits - SECTOR_SHIFT) != num_ll) {
ti->error = "Invalid hash start";
r = -EINVAL;
goto bad;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 4e09b6ff5b49..67ffa391edcf 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -865,10 +865,14 @@ static void dm_done(struct request *clone, int error, bool mapped)
{
int r = error;
struct dm_rq_target_io *tio = clone->end_io_data;
- dm_request_endio_fn rq_end_io = tio->ti->type->rq_end_io;
+ dm_request_endio_fn rq_end_io = NULL;
- if (mapped && rq_end_io)
- r = rq_end_io(tio->ti, clone, error, &tio->info);
+ if (tio->ti) {
+ rq_end_io = tio->ti->type->rq_end_io;
+
+ if (mapped && rq_end_io)
+ r = rq_end_io(tio->ti, clone, error, &tio->info);
+ }
if (r <= 0)
/* The target wants to complete the I/O */
@@ -1588,15 +1592,6 @@ static int map_request(struct dm_target *ti, struct request *clone,
int r, requeued = 0;
struct dm_rq_target_io *tio = clone->end_io_data;
- /*
- * Hold the md reference here for the in-flight I/O.
- * We can't rely on the reference count by device opener,
- * because the device may be closed during the request completion
- * when all bios are completed.
- * See the comment in rq_completed() too.
- */
- dm_get(md);
-
tio->ti = ti;
r = ti->type->map_rq(ti, clone, &tio->info);
switch (r) {
@@ -1628,6 +1623,26 @@ static int map_request(struct dm_target *ti, struct request *clone,
return requeued;
}
+static struct request *dm_start_request(struct mapped_device *md, struct request *orig)
+{
+ struct request *clone;
+
+ blk_start_request(orig);
+ clone = orig->special;
+ atomic_inc(&md->pending[rq_data_dir(clone)]);
+
+ /*
+ * Hold the md reference here for the in-flight I/O.
+ * We can't rely on the reference count by device opener,
+ * because the device may be closed during the request completion
+ * when all bios are completed.
+ * See the comment in rq_completed() too.
+ */
+ dm_get(md);
+
+ return clone;
+}
+
/*
* q->request_fn for request-based dm.
* Called with the queue lock held.
@@ -1657,14 +1672,21 @@ static void dm_request_fn(struct request_queue *q)
pos = blk_rq_pos(rq);
ti = dm_table_find_target(map, pos);
- BUG_ON(!dm_target_is_valid(ti));
+ if (!dm_target_is_valid(ti)) {
+ /*
+ * Must perform setup, that dm_done() requires,
+ * before calling dm_kill_unmapped_request
+ */
+ DMERR_LIMIT("request attempted access beyond the end of device");
+ clone = dm_start_request(md, rq);
+ dm_kill_unmapped_request(clone, -EIO);
+ continue;
+ }
if (ti->type->busy && ti->type->busy(ti))
goto delay_and_out;
- blk_start_request(rq);
- clone = rq->special;
- atomic_inc(&md->pending[rq_data_dir(clone)]);
+ clone = dm_start_request(md, rq);
spin_unlock(q->queue_lock);
if (map_request(ti, clone, md))
@@ -1684,8 +1706,6 @@ delay_and_out:
blk_delay_queue(q, HZ / 10);
out:
dm_table_put(map);
-
- return;
}
int dm_underlying_device_busy(struct request_queue *q)
@@ -2409,7 +2429,7 @@ static void dm_queue_flush(struct mapped_device *md)
*/
struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table)
{
- struct dm_table *map = ERR_PTR(-EINVAL);
+ struct dm_table *live_map, *map = ERR_PTR(-EINVAL);
struct queue_limits limits;
int r;
@@ -2419,6 +2439,19 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table)
if (!dm_suspended_md(md))
goto out;
+ /*
+ * If the new table has no data devices, retain the existing limits.
+ * This helps multipath with queue_if_no_path if all paths disappear,
+ * then new I/O is queued based on these limits, and then some paths
+ * reappear.
+ */
+ if (dm_table_has_no_data_devices(table)) {
+ live_map = dm_get_live_table(md);
+ if (live_map)
+ limits = md->queue->limits;
+ dm_table_put(live_map);
+ }
+
r = dm_calculate_queue_limits(table, &limits);
if (r) {
map = ERR_PTR(r);
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 52eef493d266..6a99fefaa743 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -54,6 +54,7 @@ void dm_table_event_callback(struct dm_table *t,
void (*fn)(void *), void *context);
struct dm_target *dm_table_get_target(struct dm_table *t, unsigned int index);
struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector);
+bool dm_table_has_no_data_devices(struct dm_table *table);
int dm_calculate_queue_limits(struct dm_table *table,
struct queue_limits *limits);
void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d5ab4493c8be..308e87b417e0 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -498,61 +498,13 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
}
EXPORT_SYMBOL(md_flush_request);
-/* Support for plugging.
- * This mirrors the plugging support in request_queue, but does not
- * require having a whole queue or request structures.
- * We allocate an md_plug_cb for each md device and each thread it gets
- * plugged on. This links tot the private plug_handle structure in the
- * personality data where we keep a count of the number of outstanding
- * plugs so other code can see if a plug is active.
- */
-struct md_plug_cb {
- struct blk_plug_cb cb;
- struct mddev *mddev;
-};
-
-static void plugger_unplug(struct blk_plug_cb *cb)
-{
- struct md_plug_cb *mdcb = container_of(cb, struct md_plug_cb, cb);
- if (atomic_dec_and_test(&mdcb->mddev->plug_cnt))
- md_wakeup_thread(mdcb->mddev->thread);
- kfree(mdcb);
-}
-
-/* Check that an unplug wakeup will come shortly.
- * If not, wakeup the md thread immediately
- */
-int mddev_check_plugged(struct mddev *mddev)
+void md_unplug(struct blk_plug_cb *cb, bool from_schedule)
{
- struct blk_plug *plug = current->plug;
- struct md_plug_cb *mdcb;
-
- if (!plug)
- return 0;
-
- list_for_each_entry(mdcb, &plug->cb_list, cb.list) {
- if (mdcb->cb.callback == plugger_unplug &&
- mdcb->mddev == mddev) {
- /* Already on the list, move to top */
- if (mdcb != list_first_entry(&plug->cb_list,
- struct md_plug_cb,
- cb.list))
- list_move(&mdcb->cb.list, &plug->cb_list);
- return 1;
- }
- }
- /* Not currently on the callback list */
- mdcb = kmalloc(sizeof(*mdcb), GFP_ATOMIC);
- if (!mdcb)
- return 0;
-
- mdcb->mddev = mddev;
- mdcb->cb.callback = plugger_unplug;
- atomic_inc(&mddev->plug_cnt);
- list_add(&mdcb->cb.list, &plug->cb_list);
- return 1;
+ struct mddev *mddev = cb->data;
+ md_wakeup_thread(mddev->thread);
+ kfree(cb);
}
-EXPORT_SYMBOL_GPL(mddev_check_plugged);
+EXPORT_SYMBOL(md_unplug);
static inline struct mddev *mddev_get(struct mddev *mddev)
{
@@ -602,7 +554,6 @@ void mddev_init(struct mddev *mddev)
atomic_set(&mddev->active, 1);
atomic_set(&mddev->openers, 0);
atomic_set(&mddev->active_io, 0);
- atomic_set(&mddev->plug_cnt, 0);
spin_lock_init(&mddev->write_lock);
atomic_set(&mddev->flush_pending, 0);
init_waitqueue_head(&mddev->sb_wait);
@@ -1157,8 +1108,11 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
ret = 0;
}
rdev->sectors = rdev->sb_start;
- /* Limit to 4TB as metadata cannot record more than that */
- if (rdev->sectors >= (2ULL << 32))
+ /* Limit to 4TB as metadata cannot record more than that.
+ * (not needed for Linear and RAID0 as metadata doesn't
+ * record this size)
+ */
+ if (rdev->sectors >= (2ULL << 32) && sb->level >= 1)
rdev->sectors = (2ULL << 32) - 2;
if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
@@ -1449,7 +1403,7 @@ super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
/* Limit to 4TB as metadata cannot record more than that.
* 4TB == 2^32 KB, or 2*2^32 sectors.
*/
- if (num_sectors >= (2ULL << 32))
+ if (num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1)
num_sectors = (2ULL << 32) - 2;
md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
rdev->sb_page);
@@ -3942,17 +3896,13 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
break;
case clear:
/* stopping an active array */
- if (atomic_read(&mddev->openers) > 0)
- return -EBUSY;
err = do_md_stop(mddev, 0, NULL);
break;
case inactive:
/* stopping an active array */
- if (mddev->pers) {
- if (atomic_read(&mddev->openers) > 0)
- return -EBUSY;
+ if (mddev->pers)
err = do_md_stop(mddev, 2, NULL);
- } else
+ else
err = 0; /* already inactive */
break;
case suspended:
@@ -7669,6 +7619,8 @@ static int remove_and_add_spares(struct mddev *mddev)
}
}
}
+ if (removed)
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
return spares;
}
@@ -7682,9 +7634,11 @@ static void reap_sync_thread(struct mddev *mddev)
!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
/* success...*/
/* activate any spares */
- if (mddev->pers->spare_active(mddev))
+ if (mddev->pers->spare_active(mddev)) {
sysfs_notify(&mddev->kobj, NULL,
"degraded");
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ }
}
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
mddev->pers->finish_reshape)
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 7b4a3c318cae..f385b038589d 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -266,9 +266,6 @@ struct mddev {
int new_chunk_sectors;
int reshape_backwards;
- atomic_t plug_cnt; /* If device is expecting
- * more bios soon.
- */
struct md_thread *thread; /* management thread */
struct md_thread *sync_thread; /* doing resync or reconstruct */
sector_t curr_resync; /* last block scheduled */
@@ -630,6 +627,12 @@ extern struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask,
struct mddev *mddev);
extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
struct mddev *mddev);
-extern int mddev_check_plugged(struct mddev *mddev);
extern void md_trim_bio(struct bio *bio, int offset, int size);
+
+extern void md_unplug(struct blk_plug_cb *cb, bool from_schedule);
+static inline int mddev_check_plugged(struct mddev *mddev)
+{
+ return !!blk_check_plugged(md_unplug, mddev,
+ sizeof(struct blk_plug_cb));
+}
#endif /* _MD_MD_H */
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index cacd008d6864..611b5f797618 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -46,6 +46,20 @@
*/
#define NR_RAID1_BIOS 256
+/* when we get a read error on a read-only array, we redirect to another
+ * device without failing the first device, or trying to over-write to
+ * correct the read error. To keep track of bad blocks on a per-bio
+ * level, we store IO_BLOCKED in the appropriate 'bios' pointer
+ */
+#define IO_BLOCKED ((struct bio *)1)
+/* When we successfully write to a known bad-block, we need to remove the
+ * bad-block marking which must be done from process context. So we record
+ * the success by setting devs[n].bio to IO_MADE_GOOD
+ */
+#define IO_MADE_GOOD ((struct bio *)2)
+
+#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
+
/* When there are this many requests queue to be written by
* the raid1 thread, we become 'congested' to provide back-pressure
* for writeback.
@@ -483,12 +497,14 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
const sector_t this_sector = r1_bio->sector;
int sectors;
int best_good_sectors;
- int start_disk;
- int best_disk;
- int i;
+ int best_disk, best_dist_disk, best_pending_disk;
+ int has_nonrot_disk;
+ int disk;
sector_t best_dist;
+ unsigned int min_pending;
struct md_rdev *rdev;
int choose_first;
+ int choose_next_idle;
rcu_read_lock();
/*
@@ -499,26 +515,26 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
retry:
sectors = r1_bio->sectors;
best_disk = -1;
+ best_dist_disk = -1;
best_dist = MaxSector;
+ best_pending_disk = -1;
+ min_pending = UINT_MAX;
best_good_sectors = 0;
+ has_nonrot_disk = 0;
+ choose_next_idle = 0;
if (conf->mddev->recovery_cp < MaxSector &&
- (this_sector + sectors >= conf->next_resync)) {
+ (this_sector + sectors >= conf->next_resync))
choose_first = 1;
- start_disk = 0;
- } else {
+ else
choose_first = 0;
- start_disk = conf->last_used;
- }
- for (i = 0 ; i < conf->raid_disks * 2 ; i++) {
+ for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
sector_t dist;
sector_t first_bad;
int bad_sectors;
-
- int disk = start_disk + i;
- if (disk >= conf->raid_disks * 2)
- disk -= conf->raid_disks * 2;
+ unsigned int pending;
+ bool nonrot;
rdev = rcu_dereference(conf->mirrors[disk].rdev);
if (r1_bio->bios[disk] == IO_BLOCKED
@@ -577,22 +593,77 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
} else
best_good_sectors = sectors;
+ nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev));
+ has_nonrot_disk |= nonrot;
+ pending = atomic_read(&rdev->nr_pending);
dist = abs(this_sector - conf->mirrors[disk].head_position);
- if (choose_first
- /* Don't change to another disk for sequential reads */
- || conf->next_seq_sect == this_sector
- || dist == 0
- /* If device is idle, use it */
- || atomic_read(&rdev->nr_pending) == 0) {
+ if (choose_first) {
+ best_disk = disk;
+ break;
+ }
+ /* Don't change to another disk for sequential reads */
+ if (conf->mirrors[disk].next_seq_sect == this_sector
+ || dist == 0) {
+ int opt_iosize = bdev_io_opt(rdev->bdev) >> 9;
+ struct raid1_info *mirror = &conf->mirrors[disk];
+
+ best_disk = disk;
+ /*
+ * If buffered sequential IO size exceeds optimal
+ * iosize, check if there is idle disk. If yes, choose
+ * the idle disk. read_balance could already choose an
+ * idle disk before noticing it's a sequential IO in
+ * this disk. This doesn't matter because this disk
+ * will idle, next time it will be utilized after the
+ * first disk has IO size exceeds optimal iosize. In
+ * this way, iosize of the first disk will be optimal
+ * iosize at least. iosize of the second disk might be
+ * small, but not a big deal since when the second disk
+ * starts IO, the first disk is likely still busy.
+ */
+ if (nonrot && opt_iosize > 0 &&
+ mirror->seq_start != MaxSector &&
+ mirror->next_seq_sect > opt_iosize &&
+ mirror->next_seq_sect - opt_iosize >=
+ mirror->seq_start) {
+ choose_next_idle = 1;
+ continue;
+ }
+ break;
+ }
+ /* If device is idle, use it */
+ if (pending == 0) {
best_disk = disk;
break;
}
+
+ if (choose_next_idle)
+ continue;
+
+ if (min_pending > pending) {
+ min_pending = pending;
+ best_pending_disk = disk;
+ }
+
if (dist < best_dist) {
best_dist = dist;
- best_disk = disk;
+ best_dist_disk = disk;
}
}
+ /*
+ * If all disks are rotational, choose the closest disk. If any disk is
+ * non-rotational, choose the disk with less pending request even the
+ * disk is rotational, which might/might not be optimal for raids with
+ * mixed ratation/non-rotational disks depending on workload.
+ */
+ if (best_disk == -1) {
+ if (has_nonrot_disk)
+ best_disk = best_pending_disk;
+ else
+ best_disk = best_dist_disk;
+ }
+
if (best_disk >= 0) {
rdev = rcu_dereference(conf->mirrors[best_disk].rdev);
if (!rdev)
@@ -606,8 +677,11 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
goto retry;
}
sectors = best_good_sectors;
- conf->next_seq_sect = this_sector + sectors;
- conf->last_used = best_disk;
+
+ if (conf->mirrors[best_disk].next_seq_sect != this_sector)
+ conf->mirrors[best_disk].seq_start = this_sector;
+
+ conf->mirrors[best_disk].next_seq_sect = this_sector + sectors;
}
rcu_read_unlock();
*max_sectors = sectors;
@@ -870,10 +944,48 @@ do_sync_io:
pr_debug("%dB behind alloc failed, doing sync I/O\n", bio->bi_size);
}
+struct raid1_plug_cb {
+ struct blk_plug_cb cb;
+ struct bio_list pending;
+ int pending_cnt;
+};
+
+static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
+{
+ struct raid1_plug_cb *plug = container_of(cb, struct raid1_plug_cb,
+ cb);
+ struct mddev *mddev = plug->cb.data;
+ struct r1conf *conf = mddev->private;
+ struct bio *bio;
+
+ if (from_schedule) {
+ spin_lock_irq(&conf->device_lock);
+ bio_list_merge(&conf->pending_bio_list, &plug->pending);
+ conf->pending_count += plug->pending_cnt;
+ spin_unlock_irq(&conf->device_lock);
+ md_wakeup_thread(mddev->thread);
+ kfree(plug);
+ return;
+ }
+
+ /* we aren't scheduling, so we can do the write-out directly. */
+ bio = bio_list_get(&plug->pending);
+ bitmap_unplug(mddev->bitmap);
+ wake_up(&conf->wait_barrier);
+
+ while (bio) { /* submit pending writes */
+ struct bio *next = bio->bi_next;
+ bio->bi_next = NULL;
+ generic_make_request(bio);
+ bio = next;
+ }
+ kfree(plug);
+}
+
static void make_request(struct mddev *mddev, struct bio * bio)
{
struct r1conf *conf = mddev->private;
- struct mirror_info *mirror;
+ struct raid1_info *mirror;
struct r1bio *r1_bio;
struct bio *read_bio;
int i, disks;
@@ -883,6 +995,8 @@ static void make_request(struct mddev *mddev, struct bio * bio)
const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA));
struct md_rdev *blocked_rdev;
+ struct blk_plug_cb *cb;
+ struct raid1_plug_cb *plug = NULL;
int first_clone;
int sectors_handled;
int max_sectors;
@@ -1185,11 +1299,22 @@ read_again:
mbio->bi_private = r1_bio;
atomic_inc(&r1_bio->remaining);
+
+ cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug));
+ if (cb)
+ plug = container_of(cb, struct raid1_plug_cb, cb);
+ else
+ plug = NULL;
spin_lock_irqsave(&conf->device_lock, flags);
- bio_list_add(&conf->pending_bio_list, mbio);
- conf->pending_count++;
+ if (plug) {
+ bio_list_add(&plug->pending, mbio);
+ plug->pending_cnt++;
+ } else {
+ bio_list_add(&conf->pending_bio_list, mbio);
+ conf->pending_count++;
+ }
spin_unlock_irqrestore(&conf->device_lock, flags);
- if (!mddev_check_plugged(mddev))
+ if (!plug)
md_wakeup_thread(mddev->thread);
}
/* Mustn't call r1_bio_write_done before this next test,
@@ -1364,7 +1489,7 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
struct r1conf *conf = mddev->private;
int err = -EEXIST;
int mirror = 0;
- struct mirror_info *p;
+ struct raid1_info *p;
int first = 0;
int last = conf->raid_disks - 1;
struct request_queue *q = bdev_get_queue(rdev->bdev);
@@ -1433,7 +1558,7 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
struct r1conf *conf = mddev->private;
int err = 0;
int number = rdev->raid_disk;
- struct mirror_info *p = conf->mirrors+ number;
+ struct raid1_info *p = conf->mirrors + number;
if (rdev != p->rdev)
p = conf->mirrors + conf->raid_disks + number;
@@ -2173,8 +2298,7 @@ static void raid1d(struct mddev *mddev)
blk_start_plug(&plug);
for (;;) {
- if (atomic_read(&mddev->plug_cnt) == 0)
- flush_pending_writes(conf);
+ flush_pending_writes(conf);
spin_lock_irqsave(&conf->device_lock, flags);
if (list_empty(head)) {
@@ -2371,6 +2495,18 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
bio->bi_rw = READ;
bio->bi_end_io = end_sync_read;
read_targets++;
+ } else if (!test_bit(WriteErrorSeen, &rdev->flags) &&
+ test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
+ !test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) {
+ /*
+ * The device is suitable for reading (InSync),
+ * but has bad block(s) here. Let's try to correct them,
+ * if we are doing resync or repair. Otherwise, leave
+ * this device alone for this sync request.
+ */
+ bio->bi_rw = WRITE;
+ bio->bi_end_io = end_sync_write;
+ write_targets++;
}
}
if (bio->bi_end_io) {
@@ -2428,7 +2564,10 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
/* There is nowhere to write, so all non-sync
* drives must be failed - so we are finished
*/
- sector_t rv = max_sector - sector_nr;
+ sector_t rv;
+ if (min_bad > 0)
+ max_sector = sector_nr + min_bad;
+ rv = max_sector - sector_nr;
*skipped = 1;
put_buf(r1_bio);
return rv;
@@ -2521,7 +2660,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
{
struct r1conf *conf;
int i;
- struct mirror_info *disk;
+ struct raid1_info *disk;
struct md_rdev *rdev;
int err = -ENOMEM;
@@ -2529,7 +2668,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
if (!conf)
goto abort;
- conf->mirrors = kzalloc(sizeof(struct mirror_info)
+ conf->mirrors = kzalloc(sizeof(struct raid1_info)
* mddev->raid_disks * 2,
GFP_KERNEL);
if (!conf->mirrors)
@@ -2572,6 +2711,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
mddev->merge_check_needed = 1;
disk->head_position = 0;
+ disk->seq_start = MaxSector;
}
conf->raid_disks = mddev->raid_disks;
conf->mddev = mddev;
@@ -2585,7 +2725,6 @@ static struct r1conf *setup_conf(struct mddev *mddev)
conf->recovery_disabled = mddev->recovery_disabled - 1;
err = -EIO;
- conf->last_used = -1;
for (i = 0; i < conf->raid_disks * 2; i++) {
disk = conf->mirrors + i;
@@ -2611,19 +2750,9 @@ static struct r1conf *setup_conf(struct mddev *mddev)
if (disk->rdev &&
(disk->rdev->saved_raid_disk < 0))
conf->fullsync = 1;
- } else if (conf->last_used < 0)
- /*
- * The first working device is used as a
- * starting point to read balancing.
- */
- conf->last_used = i;
+ }
}
- if (conf->last_used < 0) {
- printk(KERN_ERR "md/raid1:%s: no operational mirrors\n",
- mdname(mddev));
- goto abort;
- }
err = -ENOMEM;
conf->thread = md_register_thread(raid1d, mddev, "raid1");
if (!conf->thread) {
@@ -2798,7 +2927,7 @@ static int raid1_reshape(struct mddev *mddev)
*/
mempool_t *newpool, *oldpool;
struct pool_info *newpoolinfo;
- struct mirror_info *newmirrors;
+ struct raid1_info *newmirrors;
struct r1conf *conf = mddev->private;
int cnt, raid_disks;
unsigned long flags;
@@ -2841,7 +2970,7 @@ static int raid1_reshape(struct mddev *mddev)
kfree(newpoolinfo);
return -ENOMEM;
}
- newmirrors = kzalloc(sizeof(struct mirror_info) * raid_disks * 2,
+ newmirrors = kzalloc(sizeof(struct raid1_info) * raid_disks * 2,
GFP_KERNEL);
if (!newmirrors) {
kfree(newpoolinfo);
@@ -2880,7 +3009,6 @@ static int raid1_reshape(struct mddev *mddev)
conf->raid_disks = mddev->raid_disks = raid_disks;
mddev->delta_disks = 0;
- conf->last_used = 0; /* just make sure it is in-range */
lower_barrier(conf);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 80ded139314c..0ff3715fb7eb 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -1,9 +1,15 @@
#ifndef _RAID1_H
#define _RAID1_H
-struct mirror_info {
+struct raid1_info {
struct md_rdev *rdev;
sector_t head_position;
+
+ /* When choose the best device for a read (read_balance())
+ * we try to keep sequential reads one the same device
+ */
+ sector_t next_seq_sect;
+ sector_t seq_start;
};
/*
@@ -24,17 +30,11 @@ struct pool_info {
struct r1conf {
struct mddev *mddev;
- struct mirror_info *mirrors; /* twice 'raid_disks' to
+ struct raid1_info *mirrors; /* twice 'raid_disks' to
* allow for replacements.
*/
int raid_disks;
- /* When choose the best device for a read (read_balance())
- * we try to keep sequential reads one the same device
- * using 'last_used' and 'next_seq_sect'
- */
- int last_used;
- sector_t next_seq_sect;
/* During resync, read_balancing is only allowed on the part
* of the array that has been resynced. 'next_resync' tells us
* where that is.
@@ -135,20 +135,6 @@ struct r1bio {
/* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/
};
-/* when we get a read error on a read-only array, we redirect to another
- * device without failing the first device, or trying to over-write to
- * correct the read error. To keep track of bad blocks on a per-bio
- * level, we store IO_BLOCKED in the appropriate 'bios' pointer
- */
-#define IO_BLOCKED ((struct bio *)1)
-/* When we successfully write to a known bad-block, we need to remove the
- * bad-block marking which must be done from process context. So we record
- * the success by setting bios[n] to IO_MADE_GOOD
- */
-#define IO_MADE_GOOD ((struct bio *)2)
-
-#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
-
/* bits for r1bio.state */
#define R1BIO_Uptodate 0
#define R1BIO_IsSync 1
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 8da6282254c3..0138a727c1f3 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -60,7 +60,21 @@
*/
#define NR_RAID10_BIOS 256
-/* When there are this many requests queue to be written by
+/* when we get a read error on a read-only array, we redirect to another
+ * device without failing the first device, or trying to over-write to
+ * correct the read error. To keep track of bad blocks on a per-bio
+ * level, we store IO_BLOCKED in the appropriate 'bios' pointer
+ */
+#define IO_BLOCKED ((struct bio *)1)
+/* When we successfully write to a known bad-block, we need to remove the
+ * bad-block marking which must be done from process context. So we record
+ * the success by setting devs[n].bio to IO_MADE_GOOD
+ */
+#define IO_MADE_GOOD ((struct bio *)2)
+
+#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
+
+/* When there are this many requests queued to be written by
* the raid10 thread, we become 'congested' to provide back-pressure
* for writeback.
*/
@@ -645,7 +659,11 @@ static int raid10_mergeable_bvec(struct request_queue *q,
max = biovec->bv_len;
if (mddev->merge_check_needed) {
- struct r10bio r10_bio;
+ struct {
+ struct r10bio r10_bio;
+ struct r10dev devs[conf->copies];
+ } on_stack;
+ struct r10bio *r10_bio = &on_stack.r10_bio;
int s;
if (conf->reshape_progress != MaxSector) {
/* Cannot give any guidance during reshape */
@@ -653,18 +671,18 @@ static int raid10_mergeable_bvec(struct request_queue *q,
return biovec->bv_len;
return 0;
}
- r10_bio.sector = sector;
- raid10_find_phys(conf, &r10_bio);
+ r10_bio->sector = sector;
+ raid10_find_phys(conf, r10_bio);
rcu_read_lock();
for (s = 0; s < conf->copies; s++) {
- int disk = r10_bio.devs[s].devnum;
+ int disk = r10_bio->devs[s].devnum;
struct md_rdev *rdev = rcu_dereference(
conf->mirrors[disk].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags)) {
struct request_queue *q =
bdev_get_queue(rdev->bdev);
if (q->merge_bvec_fn) {
- bvm->bi_sector = r10_bio.devs[s].addr
+ bvm->bi_sector = r10_bio->devs[s].addr
+ rdev->data_offset;
bvm->bi_bdev = rdev->bdev;
max = min(max, q->merge_bvec_fn(
@@ -676,7 +694,7 @@ static int raid10_mergeable_bvec(struct request_queue *q,
struct request_queue *q =
bdev_get_queue(rdev->bdev);
if (q->merge_bvec_fn) {
- bvm->bi_sector = r10_bio.devs[s].addr
+ bvm->bi_sector = r10_bio->devs[s].addr
+ rdev->data_offset;
bvm->bi_bdev = rdev->bdev;
max = min(max, q->merge_bvec_fn(
@@ -717,7 +735,7 @@ static struct md_rdev *read_balance(struct r10conf *conf,
int sectors = r10_bio->sectors;
int best_good_sectors;
sector_t new_distance, best_dist;
- struct md_rdev *rdev, *best_rdev;
+ struct md_rdev *best_rdev, *rdev = NULL;
int do_balance;
int best_slot;
struct geom *geo = &conf->geo;
@@ -839,9 +857,8 @@ retry:
return rdev;
}
-static int raid10_congested(void *data, int bits)
+int md_raid10_congested(struct mddev *mddev, int bits)
{
- struct mddev *mddev = data;
struct r10conf *conf = mddev->private;
int i, ret = 0;
@@ -849,8 +866,6 @@ static int raid10_congested(void *data, int bits)
conf->pending_count >= max_queued_requests)
return 1;
- if (mddev_congested(mddev, bits))
- return 1;
rcu_read_lock();
for (i = 0;
(i < conf->geo.raid_disks || i < conf->prev.raid_disks)
@@ -866,6 +881,15 @@ static int raid10_congested(void *data, int bits)
rcu_read_unlock();
return ret;
}
+EXPORT_SYMBOL_GPL(md_raid10_congested);
+
+static int raid10_congested(void *data, int bits)
+{
+ struct mddev *mddev = data;
+
+ return mddev_congested(mddev, bits) ||
+ md_raid10_congested(mddev, bits);
+}
static void flush_pending_writes(struct r10conf *conf)
{
@@ -1488,14 +1512,16 @@ static int _enough(struct r10conf *conf, struct geom *geo, int ignore)
do {
int n = conf->copies;
int cnt = 0;
+ int this = first;
while (n--) {
- if (conf->mirrors[first].rdev &&
- first != ignore)
+ if (conf->mirrors[this].rdev &&
+ this != ignore)
cnt++;
- first = (first+1) % geo->raid_disks;
+ this = (this+1) % geo->raid_disks;
}
if (cnt == 0)
return 0;
+ first = (first + geo->near_copies) % geo->raid_disks;
} while (first != 0);
return 1;
}
@@ -1546,7 +1572,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
static void print_conf(struct r10conf *conf)
{
int i;
- struct mirror_info *tmp;
+ struct raid10_info *tmp;
printk(KERN_DEBUG "RAID10 conf printout:\n");
if (!conf) {
@@ -1580,7 +1606,7 @@ static int raid10_spare_active(struct mddev *mddev)
{
int i;
struct r10conf *conf = mddev->private;
- struct mirror_info *tmp;
+ struct raid10_info *tmp;
int count = 0;
unsigned long flags;
@@ -1655,7 +1681,7 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
else
mirror = first;
for ( ; mirror <= last ; mirror++) {
- struct mirror_info *p = &conf->mirrors[mirror];
+ struct raid10_info *p = &conf->mirrors[mirror];
if (p->recovery_disabled == mddev->recovery_disabled)
continue;
if (p->rdev) {
@@ -1709,7 +1735,7 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
int err = 0;
int number = rdev->raid_disk;
struct md_rdev **rdevp;
- struct mirror_info *p = conf->mirrors + number;
+ struct raid10_info *p = conf->mirrors + number;
print_conf(conf);
if (rdev == p->rdev)
@@ -2660,8 +2686,7 @@ static void raid10d(struct mddev *mddev)
blk_start_plug(&plug);
for (;;) {
- if (atomic_read(&mddev->plug_cnt) == 0)
- flush_pending_writes(conf);
+ flush_pending_writes(conf);
spin_lock_irqsave(&conf->device_lock, flags);
if (list_empty(head)) {
@@ -2876,7 +2901,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
sector_t sect;
int must_sync;
int any_working;
- struct mirror_info *mirror = &conf->mirrors[i];
+ struct raid10_info *mirror = &conf->mirrors[i];
if ((mirror->rdev == NULL ||
test_bit(In_sync, &mirror->rdev->flags))
@@ -3388,7 +3413,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
goto out;
/* FIXME calc properly */
- conf->mirrors = kzalloc(sizeof(struct mirror_info)*(mddev->raid_disks +
+ conf->mirrors = kzalloc(sizeof(struct raid10_info)*(mddev->raid_disks +
max(0,mddev->delta_disks)),
GFP_KERNEL);
if (!conf->mirrors)
@@ -3452,7 +3477,7 @@ static int run(struct mddev *mddev)
{
struct r10conf *conf;
int i, disk_idx, chunk_size;
- struct mirror_info *disk;
+ struct raid10_info *disk;
struct md_rdev *rdev;
sector_t size;
sector_t min_offset_diff = 0;
@@ -3472,12 +3497,14 @@ static int run(struct mddev *mddev)
conf->thread = NULL;
chunk_size = mddev->chunk_sectors << 9;
- blk_queue_io_min(mddev->queue, chunk_size);
- if (conf->geo.raid_disks % conf->geo.near_copies)
- blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);
- else
- blk_queue_io_opt(mddev->queue, chunk_size *
- (conf->geo.raid_disks / conf->geo.near_copies));
+ if (mddev->queue) {
+ blk_queue_io_min(mddev->queue, chunk_size);
+ if (conf->geo.raid_disks % conf->geo.near_copies)
+ blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);
+ else
+ blk_queue_io_opt(mddev->queue, chunk_size *
+ (conf->geo.raid_disks / conf->geo.near_copies));
+ }
rdev_for_each(rdev, mddev) {
long long diff;
@@ -3511,8 +3538,9 @@ static int run(struct mddev *mddev)
if (first || diff < min_offset_diff)
min_offset_diff = diff;
- disk_stack_limits(mddev->gendisk, rdev->bdev,
- rdev->data_offset << 9);
+ if (mddev->gendisk)
+ disk_stack_limits(mddev->gendisk, rdev->bdev,
+ rdev->data_offset << 9);
disk->head_position = 0;
}
@@ -3575,22 +3603,22 @@ static int run(struct mddev *mddev)
md_set_array_sectors(mddev, size);
mddev->resync_max_sectors = size;
- mddev->queue->backing_dev_info.congested_fn = raid10_congested;
- mddev->queue->backing_dev_info.congested_data = mddev;
-
- /* Calculate max read-ahead size.
- * We need to readahead at least twice a whole stripe....
- * maybe...
- */
- {
+ if (mddev->queue) {
int stripe = conf->geo.raid_disks *
((mddev->chunk_sectors << 9) / PAGE_SIZE);
+ mddev->queue->backing_dev_info.congested_fn = raid10_congested;
+ mddev->queue->backing_dev_info.congested_data = mddev;
+
+ /* Calculate max read-ahead size.
+ * We need to readahead at least twice a whole stripe....
+ * maybe...
+ */
stripe /= conf->geo.near_copies;
if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+ blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
}
- blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
if (md_integrity_register(mddev))
goto out_free_conf;
@@ -3641,7 +3669,10 @@ static int stop(struct mddev *mddev)
lower_barrier(conf);
md_unregister_thread(&mddev->thread);
- blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
+ if (mddev->queue)
+ /* the unplug fn references 'conf'*/
+ blk_sync_queue(mddev->queue);
+
if (conf->r10bio_pool)
mempool_destroy(conf->r10bio_pool);
kfree(conf->mirrors);
@@ -3805,7 +3836,7 @@ static int raid10_check_reshape(struct mddev *mddev)
if (mddev->delta_disks > 0) {
/* allocate new 'mirrors' list */
conf->mirrors_new = kzalloc(
- sizeof(struct mirror_info)
+ sizeof(struct raid10_info)
*(mddev->raid_disks +
mddev->delta_disks),
GFP_KERNEL);
@@ -3930,7 +3961,7 @@ static int raid10_start_reshape(struct mddev *mddev)
spin_lock_irq(&conf->device_lock);
if (conf->mirrors_new) {
memcpy(conf->mirrors_new, conf->mirrors,
- sizeof(struct mirror_info)*conf->prev.raid_disks);
+ sizeof(struct raid10_info)*conf->prev.raid_disks);
smp_mb();
kfree(conf->mirrors_old); /* FIXME and elsewhere */
conf->mirrors_old = conf->mirrors;
@@ -4389,14 +4420,18 @@ static int handle_reshape_read_error(struct mddev *mddev,
{
/* Use sync reads to get the blocks from somewhere else */
int sectors = r10_bio->sectors;
- struct r10bio r10b;
struct r10conf *conf = mddev->private;
+ struct {
+ struct r10bio r10_bio;
+ struct r10dev devs[conf->copies];
+ } on_stack;
+ struct r10bio *r10b = &on_stack.r10_bio;
int slot = 0;
int idx = 0;
struct bio_vec *bvec = r10_bio->master_bio->bi_io_vec;
- r10b.sector = r10_bio->sector;
- __raid10_find_phys(&conf->prev, &r10b);
+ r10b->sector = r10_bio->sector;
+ __raid10_find_phys(&conf->prev, r10b);
while (sectors) {
int s = sectors;
@@ -4407,7 +4442,7 @@ static int handle_reshape_read_error(struct mddev *mddev,
s = PAGE_SIZE >> 9;
while (!success) {
- int d = r10b.devs[slot].devnum;
+ int d = r10b->devs[slot].devnum;
struct md_rdev *rdev = conf->mirrors[d].rdev;
sector_t addr;
if (rdev == NULL ||
@@ -4415,7 +4450,7 @@ static int handle_reshape_read_error(struct mddev *mddev,
!test_bit(In_sync, &rdev->flags))
goto failed;
- addr = r10b.devs[slot].addr + idx * PAGE_SIZE;
+ addr = r10b->devs[slot].addr + idx * PAGE_SIZE;
success = sync_page_io(rdev,
addr,
s << 9,
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index 135b1b0a1554..1054cf602345 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -1,7 +1,7 @@
#ifndef _RAID10_H
#define _RAID10_H
-struct mirror_info {
+struct raid10_info {
struct md_rdev *rdev, *replacement;
sector_t head_position;
int recovery_disabled; /* matches
@@ -13,8 +13,8 @@ struct mirror_info {
struct r10conf {
struct mddev *mddev;
- struct mirror_info *mirrors;
- struct mirror_info *mirrors_new, *mirrors_old;
+ struct raid10_info *mirrors;
+ struct raid10_info *mirrors_new, *mirrors_old;
spinlock_t device_lock;
/* geometry */
@@ -110,7 +110,7 @@ struct r10bio {
* We choose the number when they are allocated.
* We sometimes need an extra bio to write to the replacement.
*/
- struct {
+ struct r10dev {
struct bio *bio;
union {
struct bio *repl_bio; /* used for resync and
@@ -123,20 +123,6 @@ struct r10bio {
} devs[0];
};
-/* when we get a read error on a read-only array, we redirect to another
- * device without failing the first device, or trying to over-write to
- * correct the read error. To keep track of bad blocks on a per-bio
- * level, we store IO_BLOCKED in the appropriate 'bios' pointer
- */
-#define IO_BLOCKED ((struct bio*)1)
-/* When we successfully write to a known bad-block, we need to remove the
- * bad-block marking which must be done from process context. So we record
- * the success by setting devs[n].bio to IO_MADE_GOOD
- */
-#define IO_MADE_GOOD ((struct bio *)2)
-
-#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
-
/* bits for r10bio.state */
enum r10bio_state {
R10BIO_Uptodate,
@@ -159,4 +145,7 @@ enum r10bio_state {
*/
R10BIO_Previous,
};
+
+extern int md_raid10_congested(struct mddev *mddev, int bits);
+
#endif
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 04348d76bb30..0689173fd9f5 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -99,34 +99,40 @@ static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
* We maintain a biased count of active stripes in the bottom 16 bits of
* bi_phys_segments, and a count of processed stripes in the upper 16 bits
*/
-static inline int raid5_bi_phys_segments(struct bio *bio)
+static inline int raid5_bi_processed_stripes(struct bio *bio)
{
- return bio->bi_phys_segments & 0xffff;
+ atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
+ return (atomic_read(segments) >> 16) & 0xffff;
}
-static inline int raid5_bi_hw_segments(struct bio *bio)
+static inline int raid5_dec_bi_active_stripes(struct bio *bio)
{
- return (bio->bi_phys_segments >> 16) & 0xffff;
+ atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
+ return atomic_sub_return(1, segments) & 0xffff;
}
-static inline int raid5_dec_bi_phys_segments(struct bio *bio)
+static inline void raid5_inc_bi_active_stripes(struct bio *bio)
{
- --bio->bi_phys_segments;
- return raid5_bi_phys_segments(bio);
+ atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
+ atomic_inc(segments);
}
-static inline int raid5_dec_bi_hw_segments(struct bio *bio)
+static inline void raid5_set_bi_processed_stripes(struct bio *bio,
+ unsigned int cnt)
{
- unsigned short val = raid5_bi_hw_segments(bio);
+ atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
+ int old, new;
- --val;
- bio->bi_phys_segments = (val << 16) | raid5_bi_phys_segments(bio);
- return val;
+ do {
+ old = atomic_read(segments);
+ new = (old & 0xffff) | (cnt << 16);
+ } while (atomic_cmpxchg(segments, old, new) != old);
}
-static inline void raid5_set_bi_hw_segments(struct bio *bio, unsigned int cnt)
+static inline void raid5_set_bi_stripes(struct bio *bio, unsigned int cnt)
{
- bio->bi_phys_segments = raid5_bi_phys_segments(bio) | (cnt << 16);
+ atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
+ atomic_set(segments, cnt);
}
/* Find first data disk in a raid6 stripe */
@@ -190,49 +196,56 @@ static int stripe_operations_active(struct stripe_head *sh)
test_bit(STRIPE_COMPUTE_RUN, &sh->state);
}
-static void __release_stripe(struct r5conf *conf, struct stripe_head *sh)
+static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh)
{
- if (atomic_dec_and_test(&sh->count)) {
- BUG_ON(!list_empty(&sh->lru));
- BUG_ON(atomic_read(&conf->active_stripes)==0);
- if (test_bit(STRIPE_HANDLE, &sh->state)) {
- if (test_bit(STRIPE_DELAYED, &sh->state) &&
- !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
- list_add_tail(&sh->lru, &conf->delayed_list);
- else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
- sh->bm_seq - conf->seq_write > 0)
- list_add_tail(&sh->lru, &conf->bitmap_list);
- else {
- clear_bit(STRIPE_DELAYED, &sh->state);
- clear_bit(STRIPE_BIT_DELAY, &sh->state);
- list_add_tail(&sh->lru, &conf->handle_list);
- }
- md_wakeup_thread(conf->mddev->thread);
- } else {
- BUG_ON(stripe_operations_active(sh));
- if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
- if (atomic_dec_return(&conf->preread_active_stripes)
- < IO_THRESHOLD)
- md_wakeup_thread(conf->mddev->thread);
- atomic_dec(&conf->active_stripes);
- if (!test_bit(STRIPE_EXPANDING, &sh->state)) {
- list_add_tail(&sh->lru, &conf->inactive_list);
- wake_up(&conf->wait_for_stripe);
- if (conf->retry_read_aligned)
- md_wakeup_thread(conf->mddev->thread);
- }
+ BUG_ON(!list_empty(&sh->lru));
+ BUG_ON(atomic_read(&conf->active_stripes)==0);
+ if (test_bit(STRIPE_HANDLE, &sh->state)) {
+ if (test_bit(STRIPE_DELAYED, &sh->state) &&
+ !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+ list_add_tail(&sh->lru, &conf->delayed_list);
+ else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
+ sh->bm_seq - conf->seq_write > 0)
+ list_add_tail(&sh->lru, &conf->bitmap_list);
+ else {
+ clear_bit(STRIPE_DELAYED, &sh->state);
+ clear_bit(STRIPE_BIT_DELAY, &sh->state);
+ list_add_tail(&sh->lru, &conf->handle_list);
+ }
+ md_wakeup_thread(conf->mddev->thread);
+ } else {
+ BUG_ON(stripe_operations_active(sh));
+ if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+ if (atomic_dec_return(&conf->preread_active_stripes)
+ < IO_THRESHOLD)
+ md_wakeup_thread(conf->mddev->thread);
+ atomic_dec(&conf->active_stripes);
+ if (!test_bit(STRIPE_EXPANDING, &sh->state)) {
+ list_add_tail(&sh->lru, &conf->inactive_list);
+ wake_up(&conf->wait_for_stripe);
+ if (conf->retry_read_aligned)
+ md_wakeup_thread(conf->mddev->thread);
}
}
}
+static void __release_stripe(struct r5conf *conf, struct stripe_head *sh)
+{
+ if (atomic_dec_and_test(&sh->count))
+ do_release_stripe(conf, sh);
+}
+
static void release_stripe(struct stripe_head *sh)
{
struct r5conf *conf = sh->raid_conf;
unsigned long flags;
- spin_lock_irqsave(&conf->device_lock, flags);
- __release_stripe(conf, sh);
- spin_unlock_irqrestore(&conf->device_lock, flags);
+ local_irq_save(flags);
+ if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
+ do_release_stripe(conf, sh);
+ spin_unlock(&conf->device_lock);
+ }
+ local_irq_restore(flags);
}
static inline void remove_hash(struct stripe_head *sh)
@@ -380,6 +393,8 @@ static int calc_degraded(struct r5conf *conf)
degraded = 0;
for (i = 0; i < conf->previous_raid_disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && test_bit(Faulty, &rdev->flags))
+ rdev = rcu_dereference(conf->disks[i].replacement);
if (!rdev || test_bit(Faulty, &rdev->flags))
degraded++;
else if (test_bit(In_sync, &rdev->flags))
@@ -404,6 +419,8 @@ static int calc_degraded(struct r5conf *conf)
degraded2 = 0;
for (i = 0; i < conf->raid_disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && test_bit(Faulty, &rdev->flags))
+ rdev = rcu_dereference(conf->disks[i].replacement);
if (!rdev || test_bit(Faulty, &rdev->flags))
degraded2++;
else if (test_bit(In_sync, &rdev->flags))
@@ -471,7 +488,8 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
} else {
if (atomic_read(&sh->count)) {
BUG_ON(!list_empty(&sh->lru)
- && !test_bit(STRIPE_EXPANDING, &sh->state));
+ && !test_bit(STRIPE_EXPANDING, &sh->state)
+ && !test_bit(STRIPE_ON_UNPLUG_LIST, &sh->state));
} else {
if (!test_bit(STRIPE_HANDLE, &sh->state))
atomic_inc(&conf->active_stripes);
@@ -640,6 +658,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
else
bi->bi_sector = (sh->sector
+ rdev->data_offset);
+ if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
+ bi->bi_rw |= REQ_FLUSH;
+
bi->bi_flags = 1 << BIO_UPTODATE;
bi->bi_idx = 0;
bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
@@ -749,14 +770,12 @@ static void ops_complete_biofill(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
struct bio *return_bi = NULL;
- struct r5conf *conf = sh->raid_conf;
int i;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
/* clear completed biofills */
- spin_lock_irq(&conf->device_lock);
for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
@@ -774,7 +793,7 @@ static void ops_complete_biofill(void *stripe_head_ref)
while (rbi && rbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
rbi2 = r5_next_bio(rbi, dev->sector);
- if (!raid5_dec_bi_phys_segments(rbi)) {
+ if (!raid5_dec_bi_active_stripes(rbi)) {
rbi->bi_next = return_bi;
return_bi = rbi;
}
@@ -782,7 +801,6 @@ static void ops_complete_biofill(void *stripe_head_ref)
}
}
}
- spin_unlock_irq(&conf->device_lock);
clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
return_io(return_bi);
@@ -794,7 +812,6 @@ static void ops_complete_biofill(void *stripe_head_ref)
static void ops_run_biofill(struct stripe_head *sh)
{
struct dma_async_tx_descriptor *tx = NULL;
- struct r5conf *conf = sh->raid_conf;
struct async_submit_ctl submit;
int i;
@@ -805,10 +822,10 @@ static void ops_run_biofill(struct stripe_head *sh)
struct r5dev *dev = &sh->dev[i];
if (test_bit(R5_Wantfill, &dev->flags)) {
struct bio *rbi;
- spin_lock_irq(&conf->device_lock);
+ spin_lock_irq(&sh->stripe_lock);
dev->read = rbi = dev->toread;
dev->toread = NULL;
- spin_unlock_irq(&conf->device_lock);
+ spin_unlock_irq(&sh->stripe_lock);
while (rbi && rbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
tx = async_copy_data(0, rbi, dev->page,
@@ -1144,12 +1161,12 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) {
struct bio *wbi;
- spin_lock_irq(&sh->raid_conf->device_lock);
+ spin_lock_irq(&sh->stripe_lock);
chosen = dev->towrite;
dev->towrite = NULL;
BUG_ON(dev->written);
wbi = dev->written = chosen;
- spin_unlock_irq(&sh->raid_conf->device_lock);
+ spin_unlock_irq(&sh->stripe_lock);
while (wbi && wbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
@@ -1454,6 +1471,8 @@ static int grow_one_stripe(struct r5conf *conf)
init_waitqueue_head(&sh->ops.wait_for_ops);
#endif
+ spin_lock_init(&sh->stripe_lock);
+
if (grow_buffers(sh)) {
shrink_buffers(sh);
kmem_cache_free(conf->slab_cache, sh);
@@ -1572,6 +1591,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
#ifdef CONFIG_MULTICORE_RAID456
init_waitqueue_head(&nsh->ops.wait_for_ops);
#endif
+ spin_lock_init(&nsh->stripe_lock);
list_add(&nsh->lru, &newstripes);
}
@@ -1739,7 +1759,9 @@ static void raid5_end_read_request(struct bio * bi, int error)
atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
clear_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReWrite, &sh->dev[i].flags);
- }
+ } else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
+ clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
+
if (atomic_read(&rdev->read_errors))
atomic_set(&rdev->read_errors, 0);
} else {
@@ -1784,7 +1806,11 @@ static void raid5_end_read_request(struct bio * bi, int error)
else
retry = 1;
if (retry)
- set_bit(R5_ReadError, &sh->dev[i].flags);
+ if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) {
+ set_bit(R5_ReadError, &sh->dev[i].flags);
+ clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
+ } else
+ set_bit(R5_ReadNoMerge, &sh->dev[i].flags);
else {
clear_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReWrite, &sh->dev[i].flags);
@@ -2340,11 +2366,18 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
(unsigned long long)bi->bi_sector,
(unsigned long long)sh->sector);
-
- spin_lock_irq(&conf->device_lock);
+ /*
+ * If several bio share a stripe. The bio bi_phys_segments acts as a
+ * reference count to avoid race. The reference count should already be
+ * increased before this function is called (for example, in
+ * make_request()), so other bio sharing this stripe will not free the
+ * stripe. If a stripe is owned by one stripe, the stripe lock will
+ * protect it.
+ */
+ spin_lock_irq(&sh->stripe_lock);
if (forwrite) {
bip = &sh->dev[dd_idx].towrite;
- if (*bip == NULL && sh->dev[dd_idx].written == NULL)
+ if (*bip == NULL)
firstwrite = 1;
} else
bip = &sh->dev[dd_idx].toread;
@@ -2360,7 +2393,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
if (*bip)
bi->bi_next = *bip;
*bip = bi;
- bi->bi_phys_segments++;
+ raid5_inc_bi_active_stripes(bi);
if (forwrite) {
/* check if page is covered */
@@ -2375,7 +2408,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
}
- spin_unlock_irq(&conf->device_lock);
+ spin_unlock_irq(&sh->stripe_lock);
pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
(unsigned long long)(*bip)->bi_sector,
@@ -2391,7 +2424,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
overlap:
set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
- spin_unlock_irq(&conf->device_lock);
+ spin_unlock_irq(&sh->stripe_lock);
return 0;
}
@@ -2441,10 +2474,11 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
rdev_dec_pending(rdev, conf->mddev);
}
}
- spin_lock_irq(&conf->device_lock);
+ spin_lock_irq(&sh->stripe_lock);
/* fail all writes first */
bi = sh->dev[i].towrite;
sh->dev[i].towrite = NULL;
+ spin_unlock_irq(&sh->stripe_lock);
if (bi) {
s->to_write--;
bitmap_end = 1;
@@ -2457,13 +2491,17 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
- if (!raid5_dec_bi_phys_segments(bi)) {
+ if (!raid5_dec_bi_active_stripes(bi)) {
md_write_end(conf->mddev);
bi->bi_next = *return_bi;
*return_bi = bi;
}
bi = nextbi;
}
+ if (bitmap_end)
+ bitmap_endwrite(conf->mddev->bitmap, sh->sector,
+ STRIPE_SECTORS, 0, 0);
+ bitmap_end = 0;
/* and fail all 'written' */
bi = sh->dev[i].written;
sh->dev[i].written = NULL;
@@ -2472,7 +2510,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
- if (!raid5_dec_bi_phys_segments(bi)) {
+ if (!raid5_dec_bi_active_stripes(bi)) {
md_write_end(conf->mddev);
bi->bi_next = *return_bi;
*return_bi = bi;
@@ -2496,14 +2534,13 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
struct bio *nextbi =
r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
- if (!raid5_dec_bi_phys_segments(bi)) {
+ if (!raid5_dec_bi_active_stripes(bi)) {
bi->bi_next = *return_bi;
*return_bi = bi;
}
bi = nextbi;
}
}
- spin_unlock_irq(&conf->device_lock);
if (bitmap_end)
bitmap_endwrite(conf->mddev->bitmap, sh->sector,
STRIPE_SECTORS, 0, 0);
@@ -2707,30 +2744,23 @@ static void handle_stripe_clean_event(struct r5conf *conf,
test_bit(R5_UPTODATE, &dev->flags)) {
/* We can return any write requests */
struct bio *wbi, *wbi2;
- int bitmap_end = 0;
pr_debug("Return write for disc %d\n", i);
- spin_lock_irq(&conf->device_lock);
wbi = dev->written;
dev->written = NULL;
while (wbi && wbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
wbi2 = r5_next_bio(wbi, dev->sector);
- if (!raid5_dec_bi_phys_segments(wbi)) {
+ if (!raid5_dec_bi_active_stripes(wbi)) {
md_write_end(conf->mddev);
wbi->bi_next = *return_bi;
*return_bi = wbi;
}
wbi = wbi2;
}
- if (dev->towrite == NULL)
- bitmap_end = 1;
- spin_unlock_irq(&conf->device_lock);
- if (bitmap_end)
- bitmap_endwrite(conf->mddev->bitmap,
- sh->sector,
- STRIPE_SECTORS,
+ bitmap_endwrite(conf->mddev->bitmap, sh->sector,
+ STRIPE_SECTORS,
!test_bit(STRIPE_DEGRADED, &sh->state),
- 0);
+ 0);
}
}
@@ -3182,7 +3212,6 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
/* Now to look around and see what can be done */
rcu_read_lock();
- spin_lock_irq(&conf->device_lock);
for (i=disks; i--; ) {
struct md_rdev *rdev;
sector_t first_bad;
@@ -3328,7 +3357,6 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
do_recovery = 1;
}
}
- spin_unlock_irq(&conf->device_lock);
if (test_bit(STRIPE_SYNCING, &sh->state)) {
/* If there is a failed device being replaced,
* we must be recovering.
@@ -3791,7 +3819,7 @@ static struct bio *remove_bio_from_retry(struct r5conf *conf)
* this sets the active strip count to 1 and the processed
* strip count to zero (upper 8 bits)
*/
- bi->bi_phys_segments = 1; /* biased count of active stripes */
+ raid5_set_bi_stripes(bi, 1); /* biased count of active stripes */
}
return bi;
@@ -3988,6 +4016,62 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf)
return sh;
}
+struct raid5_plug_cb {
+ struct blk_plug_cb cb;
+ struct list_head list;
+};
+
+static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
+{
+ struct raid5_plug_cb *cb = container_of(
+ blk_cb, struct raid5_plug_cb, cb);
+ struct stripe_head *sh;
+ struct mddev *mddev = cb->cb.data;
+ struct r5conf *conf = mddev->private;
+
+ if (cb->list.next && !list_empty(&cb->list)) {
+ spin_lock_irq(&conf->device_lock);
+ while (!list_empty(&cb->list)) {
+ sh = list_first_entry(&cb->list, struct stripe_head, lru);
+ list_del_init(&sh->lru);
+ /*
+ * avoid race release_stripe_plug() sees
+ * STRIPE_ON_UNPLUG_LIST clear but the stripe
+ * is still in our list
+ */
+ smp_mb__before_clear_bit();
+ clear_bit(STRIPE_ON_UNPLUG_LIST, &sh->state);
+ __release_stripe(conf, sh);
+ }
+ spin_unlock_irq(&conf->device_lock);
+ }
+ kfree(cb);
+}
+
+static void release_stripe_plug(struct mddev *mddev,
+ struct stripe_head *sh)
+{
+ struct blk_plug_cb *blk_cb = blk_check_plugged(
+ raid5_unplug, mddev,
+ sizeof(struct raid5_plug_cb));
+ struct raid5_plug_cb *cb;
+
+ if (!blk_cb) {
+ release_stripe(sh);
+ return;
+ }
+
+ cb = container_of(blk_cb, struct raid5_plug_cb, cb);
+
+ if (cb->list.next == NULL)
+ INIT_LIST_HEAD(&cb->list);
+
+ if (!test_and_set_bit(STRIPE_ON_UNPLUG_LIST, &sh->state))
+ list_add_tail(&sh->lru, &cb->list);
+ else
+ release_stripe(sh);
+}
+
static void make_request(struct mddev *mddev, struct bio * bi)
{
struct r5conf *conf = mddev->private;
@@ -4116,8 +4200,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
if ((bi->bi_rw & REQ_SYNC) &&
!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
atomic_inc(&conf->preread_active_stripes);
- mddev_check_plugged(mddev);
- release_stripe(sh);
+ release_stripe_plug(mddev, sh);
} else {
/* cannot get stripe for read-ahead, just give-up */
clear_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -4126,9 +4209,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
}
}
- spin_lock_irq(&conf->device_lock);
- remaining = raid5_dec_bi_phys_segments(bi);
- spin_unlock_irq(&conf->device_lock);
+ remaining = raid5_dec_bi_active_stripes(bi);
if (remaining == 0) {
if ( rw == WRITE )
@@ -4484,7 +4565,7 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
sector += STRIPE_SECTORS,
scnt++) {
- if (scnt < raid5_bi_hw_segments(raid_bio))
+ if (scnt < raid5_bi_processed_stripes(raid_bio))
/* already done this stripe */
continue;
@@ -4492,25 +4573,24 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
if (!sh) {
/* failed to get a stripe - must wait */
- raid5_set_bi_hw_segments(raid_bio, scnt);
+ raid5_set_bi_processed_stripes(raid_bio, scnt);
conf->retry_read_aligned = raid_bio;
return handled;
}
if (!add_stripe_bio(sh, raid_bio, dd_idx, 0)) {
release_stripe(sh);
- raid5_set_bi_hw_segments(raid_bio, scnt);
+ raid5_set_bi_processed_stripes(raid_bio, scnt);
conf->retry_read_aligned = raid_bio;
return handled;
}
+ set_bit(R5_ReadNoMerge, &sh->dev[dd_idx].flags);
handle_stripe(sh);
release_stripe(sh);
handled++;
}
- spin_lock_irq(&conf->device_lock);
- remaining = raid5_dec_bi_phys_segments(raid_bio);
- spin_unlock_irq(&conf->device_lock);
+ remaining = raid5_dec_bi_active_stripes(raid_bio);
if (remaining == 0)
bio_endio(raid_bio, 0);
if (atomic_dec_and_test(&conf->active_aligned_reads))
@@ -4518,6 +4598,30 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
return handled;
}
+#define MAX_STRIPE_BATCH 8
+static int handle_active_stripes(struct r5conf *conf)
+{
+ struct stripe_head *batch[MAX_STRIPE_BATCH], *sh;
+ int i, batch_size = 0;
+
+ while (batch_size < MAX_STRIPE_BATCH &&
+ (sh = __get_priority_stripe(conf)) != NULL)
+ batch[batch_size++] = sh;
+
+ if (batch_size == 0)
+ return batch_size;
+ spin_unlock_irq(&conf->device_lock);
+
+ for (i = 0; i < batch_size; i++)
+ handle_stripe(batch[i]);
+
+ cond_resched();
+
+ spin_lock_irq(&conf->device_lock);
+ for (i = 0; i < batch_size; i++)
+ __release_stripe(conf, batch[i]);
+ return batch_size;
+}
/*
* This is our raid5 kernel thread.
@@ -4528,7 +4632,6 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
*/
static void raid5d(struct mddev *mddev)
{
- struct stripe_head *sh;
struct r5conf *conf = mddev->private;
int handled;
struct blk_plug plug;
@@ -4542,8 +4645,9 @@ static void raid5d(struct mddev *mddev)
spin_lock_irq(&conf->device_lock);
while (1) {
struct bio *bio;
+ int batch_size;
- if (atomic_read(&mddev->plug_cnt) == 0 &&
+ if (
!list_empty(&conf->bitmap_list)) {
/* Now is a good time to flush some bitmap updates */
conf->seq_flush++;
@@ -4553,8 +4657,7 @@ static void raid5d(struct mddev *mddev)
conf->seq_write = conf->seq_flush;
activate_bit_delay(conf);
}
- if (atomic_read(&mddev->plug_cnt) == 0)
- raid5_activate_delayed(conf);
+ raid5_activate_delayed(conf);
while ((bio = remove_bio_from_retry(conf))) {
int ok;
@@ -4566,21 +4669,16 @@ static void raid5d(struct mddev *mddev)
handled++;
}
- sh = __get_priority_stripe(conf);
-
- if (!sh)
+ batch_size = handle_active_stripes(conf);
+ if (!batch_size)
break;
- spin_unlock_irq(&conf->device_lock);
-
- handled++;
- handle_stripe(sh);
- release_stripe(sh);
- cond_resched();
+ handled += batch_size;
- if (mddev->flags & ~(1<<MD_CHANGE_PENDING))
+ if (mddev->flags & ~(1<<MD_CHANGE_PENDING)) {
+ spin_unlock_irq(&conf->device_lock);
md_check_recovery(mddev);
-
- spin_lock_irq(&conf->device_lock);
+ spin_lock_irq(&conf->device_lock);
+ }
}
pr_debug("%d stripes handled\n", handled);
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 2164021f3b5f..a9fc24901eda 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -210,6 +210,7 @@ struct stripe_head {
int disks; /* disks in stripe */
enum check_states check_state;
enum reconstruct_states reconstruct_state;
+ spinlock_t stripe_lock;
/**
* struct stripe_operations
* @target - STRIPE_OP_COMPUTE_BLK target
@@ -273,6 +274,7 @@ enum r5dev_flags {
R5_Wantwrite,
R5_Overlap, /* There is a pending overlapping request
* on this block */
+ R5_ReadNoMerge, /* prevent bio from merging in block-layer */
R5_ReadError, /* seen a read error here recently */
R5_ReWrite, /* have tried to over-write the readerror */
@@ -319,6 +321,7 @@ enum {
STRIPE_BIOFILL_RUN,
STRIPE_COMPUTE_RUN,
STRIPE_OPS_REQ_PENDING,
+ STRIPE_ON_UNPLUG_LIST,
};
/*
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-02 04:41:48 +0300