aboutsummaryrefslogtreecommitdiff
path: root/drivers/md/dm-raid.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/dm-raid.c')
-rw-r--r--drivers/md/dm-raid.c405
1 files changed, 315 insertions, 90 deletions
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 3d8984edeff..4880b69e2e9 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -91,15 +91,44 @@ static struct raid_type {
{"raid6_nc", "RAID6 (N continue)", 2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE}
};
+static char *raid10_md_layout_to_format(int layout)
+{
+ /*
+ * Bit 16 and 17 stand for "offset" and "use_far_sets"
+ * Refer to MD's raid10.c for details
+ */
+ if ((layout & 0x10000) && (layout & 0x20000))
+ return "offset";
+
+ if ((layout & 0xFF) > 1)
+ return "near";
+
+ return "far";
+}
+
static unsigned raid10_md_layout_to_copies(int layout)
{
- return layout & 0xFF;
+ if ((layout & 0xFF) > 1)
+ return layout & 0xFF;
+ return (layout >> 8) & 0xFF;
}
static int raid10_format_to_md_layout(char *format, unsigned copies)
{
- /* 1 "far" copy, and 'copies' "near" copies */
- return (1 << 8) | (copies & 0xFF);
+ unsigned n = 1, f = 1;
+
+ if (!strcmp("near", format))
+ n = copies;
+ else
+ f = copies;
+
+ if (!strcmp("offset", format))
+ return 0x30000 | (f << 8) | n;
+
+ if (!strcmp("far", format))
+ return 0x20000 | (f << 8) | n;
+
+ return (f << 8) | n;
}
static struct raid_type *get_raid_type(char *name)
@@ -340,24 +369,23 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
}
/*
- * validate_rebuild_devices
+ * validate_raid_redundancy
* @rs
*
- * Determine if the devices specified for rebuild can result in a valid
- * usable array that is capable of rebuilding the given devices.
+ * Determine if there are enough devices in the array that haven't
+ * failed (or are being rebuilt) to form a usable array.
*
* Returns: 0 on success, -EINVAL on failure.
*/
-static int validate_rebuild_devices(struct raid_set *rs)
+static int validate_raid_redundancy(struct raid_set *rs)
{
unsigned i, rebuild_cnt = 0;
- unsigned rebuilds_per_group, copies, d;
-
- if (!(rs->print_flags & DMPF_REBUILD))
- return 0;
+ unsigned rebuilds_per_group = 0, copies, d;
+ unsigned group_size, last_group_start;
for (i = 0; i < rs->md.raid_disks; i++)
- if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
+ if (!test_bit(In_sync, &rs->dev[i].rdev.flags) ||
+ !rs->dev[i].rdev.sb_page)
rebuild_cnt++;
switch (rs->raid_type->level) {
@@ -381,9 +409,6 @@ static int validate_rebuild_devices(struct raid_set *rs)
* as long as the failed devices occur in different mirror
* groups (i.e. different stripes).
*
- * Right now, we only allow for "near" copies. When other
- * formats are added, we will have to check those too.
- *
* When checking "near" format, make sure no adjacent devices
* have failed beyond what can be handled. In addition to the
* simple case where the number of devices is a multiple of the
@@ -393,27 +418,51 @@ static int validate_rebuild_devices(struct raid_set *rs)
* A A B B C
* C D D E E
*/
- rebuilds_per_group = 0;
- for (i = 0; i < rs->md.raid_disks * copies; i++) {
- d = i % rs->md.raid_disks;
- if (!test_bit(In_sync, &rs->dev[d].rdev.flags) &&
- (++rebuilds_per_group >= copies))
- goto too_many;
- if (!((i + 1) % copies))
+ if (!strcmp("near", raid10_md_layout_to_format(rs->md.layout))) {
+ for (i = 0; i < rs->md.raid_disks * copies; i++) {
+ if (!(i % copies))
+ rebuilds_per_group = 0;
+ d = i % rs->md.raid_disks;
+ if ((!rs->dev[d].rdev.sb_page ||
+ !test_bit(In_sync, &rs->dev[d].rdev.flags)) &&
+ (++rebuilds_per_group >= copies))
+ goto too_many;
+ }
+ break;
+ }
+
+ /*
+ * When checking "far" and "offset" formats, we need to ensure
+ * that the device that holds its copy is not also dead or
+ * being rebuilt. (Note that "far" and "offset" formats only
+ * support two copies right now. These formats also only ever
+ * use the 'use_far_sets' variant.)
+ *
+ * This check is somewhat complicated by the need to account
+ * for arrays that are not a multiple of (far) copies. This
+ * results in the need to treat the last (potentially larger)
+ * set differently.
+ */
+ group_size = (rs->md.raid_disks / copies);
+ last_group_start = (rs->md.raid_disks / group_size) - 1;
+ last_group_start *= group_size;
+ for (i = 0; i < rs->md.raid_disks; i++) {
+ if (!(i % copies) && !(i > last_group_start))
rebuilds_per_group = 0;
+ if ((!rs->dev[i].rdev.sb_page ||
+ !test_bit(In_sync, &rs->dev[i].rdev.flags)) &&
+ (++rebuilds_per_group >= copies))
+ goto too_many;
}
break;
default:
- DMERR("The rebuild parameter is not supported for %s",
- rs->raid_type->name);
- rs->ti->error = "Rebuild not supported for this RAID type";
- return -EINVAL;
+ if (rebuild_cnt)
+ return -EINVAL;
}
return 0;
too_many:
- rs->ti->error = "Too many rebuild devices specified";
return -EINVAL;
}
@@ -438,7 +487,7 @@ too_many:
*
* RAID10-only options:
* [raid10_copies <# copies>] Number of copies. (Default: 2)
- * [raid10_format <near>] Layout algorithm. (Default: near)
+ * [raid10_format <near|far|offset>] Layout algorithm. (Default: near)
*/
static int parse_raid_params(struct raid_set *rs, char **argv,
unsigned num_raid_params)
@@ -455,7 +504,7 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
* First, parse the in-order required arguments
* "chunk_size" is the only argument of this type.
*/
- if ((strict_strtoul(argv[0], 10, &value) < 0)) {
+ if ((kstrtoul(argv[0], 10, &value) < 0)) {
rs->ti->error = "Bad chunk size";
return -EINVAL;
} else if (rs->raid_type->level == 1) {
@@ -525,7 +574,9 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
rs->ti->error = "'raid10_format' is an invalid parameter for this RAID type";
return -EINVAL;
}
- if (strcmp("near", argv[i])) {
+ if (strcmp("near", argv[i]) &&
+ strcmp("far", argv[i]) &&
+ strcmp("offset", argv[i])) {
rs->ti->error = "Invalid 'raid10_format' value given";
return -EINVAL;
}
@@ -534,7 +585,7 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
continue;
}
- if (strict_strtoul(argv[i], 10, &value) < 0) {
+ if (kstrtoul(argv[i], 10, &value) < 0) {
rs->ti->error = "Bad numerical argument given in raid params";
return -EINVAL;
}
@@ -649,6 +700,15 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
return -EINVAL;
}
+ /*
+ * If the format is not "near", we only support
+ * two copies at the moment.
+ */
+ if (strcmp("near", raid10_format) && (raid10_copies > 2)) {
+ rs->ti->error = "Too many copies for given RAID10 format.";
+ return -EINVAL;
+ }
+
/* (Len * #mirrors) / #devices */
sectors_per_dev = rs->ti->len * raid10_copies;
sector_div(sectors_per_dev, rs->md.raid_disks);
@@ -664,9 +724,6 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
}
rs->md.dev_sectors = sectors_per_dev;
- if (validate_rebuild_devices(rs))
- return -EINVAL;
-
/* Assume there are no metadata devices until the drives are parsed */
rs->md.persistent = 0;
rs->md.external = 1;
@@ -862,17 +919,30 @@ static int super_init_validation(struct mddev *mddev, struct md_rdev *rdev)
/*
* Reshaping is not currently allowed
*/
- if ((le32_to_cpu(sb->level) != mddev->level) ||
- (le32_to_cpu(sb->layout) != mddev->layout) ||
- (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors)) {
- DMERR("Reshaping arrays not yet supported.");
+ if (le32_to_cpu(sb->level) != mddev->level) {
+ DMERR("Reshaping arrays not yet supported. (RAID level change)");
+ return -EINVAL;
+ }
+ if (le32_to_cpu(sb->layout) != mddev->layout) {
+ DMERR("Reshaping arrays not yet supported. (RAID layout change)");
+ DMERR(" 0x%X vs 0x%X", le32_to_cpu(sb->layout), mddev->layout);
+ DMERR(" Old layout: %s w/ %d copies",
+ raid10_md_layout_to_format(le32_to_cpu(sb->layout)),
+ raid10_md_layout_to_copies(le32_to_cpu(sb->layout)));
+ DMERR(" New layout: %s w/ %d copies",
+ raid10_md_layout_to_format(mddev->layout),
+ raid10_md_layout_to_copies(mddev->layout));
+ return -EINVAL;
+ }
+ if (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors) {
+ DMERR("Reshaping arrays not yet supported. (stripe sectors change)");
return -EINVAL;
}
/* We can only change the number of devices in RAID1 right now */
if ((rs->raid_type->level != 1) &&
(le32_to_cpu(sb->num_devices) != mddev->raid_disks)) {
- DMERR("Reshaping arrays not yet supported.");
+ DMERR("Reshaping arrays not yet supported. (device count change)");
return -EINVAL;
}
@@ -995,28 +1065,10 @@ static int super_validate(struct mddev *mddev, struct md_rdev *rdev)
static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
{
int ret;
- unsigned redundancy = 0;
struct raid_dev *dev;
struct md_rdev *rdev, *tmp, *freshest;
struct mddev *mddev = &rs->md;
- switch (rs->raid_type->level) {
- case 1:
- redundancy = rs->md.raid_disks - 1;
- break;
- case 4:
- case 5:
- 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;
- }
-
freshest = NULL;
rdev_for_each_safe(rdev, tmp, mddev) {
/*
@@ -1045,44 +1097,43 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
break;
default:
dev = container_of(rdev, struct raid_dev, rdev);
- if (redundancy--) {
- if (dev->meta_dev)
- dm_put_device(ti, dev->meta_dev);
-
- dev->meta_dev = NULL;
- rdev->meta_bdev = NULL;
+ if (dev->meta_dev)
+ dm_put_device(ti, dev->meta_dev);
- if (rdev->sb_page)
- put_page(rdev->sb_page);
+ dev->meta_dev = NULL;
+ rdev->meta_bdev = NULL;
- rdev->sb_page = NULL;
+ if (rdev->sb_page)
+ put_page(rdev->sb_page);
- rdev->sb_loaded = 0;
+ rdev->sb_page = NULL;
- /*
- * We might be able to salvage the data device
- * even though the meta device has failed. For
- * now, we behave as though '- -' had been
- * set for this device in the table.
- */
- if (dev->data_dev)
- dm_put_device(ti, dev->data_dev);
+ rdev->sb_loaded = 0;
- dev->data_dev = NULL;
- rdev->bdev = NULL;
+ /*
+ * We might be able to salvage the data device
+ * even though the meta device has failed. For
+ * now, we behave as though '- -' had been
+ * set for this device in the table.
+ */
+ if (dev->data_dev)
+ dm_put_device(ti, dev->data_dev);
- list_del(&rdev->same_set);
+ dev->data_dev = NULL;
+ rdev->bdev = NULL;
- continue;
- }
- ti->error = "Failed to load superblock";
- return ret;
+ list_del(&rdev->same_set);
}
}
if (!freshest)
return 0;
+ if (validate_raid_redundancy(rs)) {
+ rs->ti->error = "Insufficient redundancy to activate array";
+ return -EINVAL;
+ }
+
/*
* Validation of the freshest device provides the source of
* validation for the remaining devices.
@@ -1130,7 +1181,7 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
argv++;
/* number of RAID parameters */
- if (strict_strtoul(argv[0], 10, &num_raid_params) < 0) {
+ if (kstrtoul(argv[0], 10, &num_raid_params) < 0) {
ti->error = "Cannot understand number of RAID parameters";
return -EINVAL;
}
@@ -1143,7 +1194,7 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
return -EINVAL;
}
- if ((strict_strtoul(argv[num_raid_params], 10, &num_raid_devs) < 0) ||
+ if ((kstrtoul(argv[num_raid_params], 10, &num_raid_devs) < 0) ||
(num_raid_devs >= INT_MAX)) {
ti->error = "Cannot understand number of raid devices";
return -EINVAL;
@@ -1178,7 +1229,7 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
INIT_WORK(&rs->md.event_work, do_table_event);
ti->private = rs;
- ti->num_flush_requests = 1;
+ ti->num_flush_bios = 1;
mutex_lock(&rs->md.reconfig_mutex);
ret = md_run(&rs->md);
@@ -1228,8 +1279,33 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
return DM_MAPIO_SUBMITTED;
}
-static int raid_status(struct dm_target *ti, status_type_t type,
- unsigned status_flags, char *result, unsigned maxlen)
+static const char *decipher_sync_action(struct mddev *mddev)
+{
+ if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+ return "frozen";
+
+ if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+ (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))) {
+ if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+ return "reshape";
+
+ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+ return "resync";
+ else if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
+ return "check";
+ return "repair";
+ }
+
+ if (test_bit(MD_RECOVERY_RECOVER, &mddev->recovery))
+ return "recover";
+ }
+
+ return "idle";
+}
+
+static void raid_status(struct dm_target *ti, status_type_t type,
+ unsigned status_flags, char *result, unsigned maxlen)
{
struct raid_set *rs = ti->private;
unsigned raid_param_cnt = 1; /* at least 1 for chunksize */
@@ -1247,8 +1323,18 @@ static int raid_status(struct dm_target *ti, status_type_t type,
sync = rs->md.recovery_cp;
if (sync >= rs->md.resync_max_sectors) {
+ /*
+ * Sync complete.
+ */
array_in_sync = 1;
sync = rs->md.resync_max_sectors;
+ } else if (test_bit(MD_RECOVERY_REQUESTED, &rs->md.recovery)) {
+ /*
+ * If "check" or "repair" is occurring, the array has
+ * undergone and initial sync and the health characters
+ * should not be 'a' anymore.
+ */
+ array_in_sync = 1;
} else {
/*
* The array may be doing an initial sync, or it may
@@ -1260,6 +1346,7 @@ static int raid_status(struct dm_target *ti, status_type_t type,
if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
array_in_sync = 1;
}
+
/*
* Status characters:
* 'D' = Dead/Failed device
@@ -1288,6 +1375,22 @@ static int raid_status(struct dm_target *ti, status_type_t type,
(unsigned long long) sync,
(unsigned long long) rs->md.resync_max_sectors);
+ /*
+ * Sync action:
+ * See Documentation/device-mapper/dm-raid.c for
+ * information on each of these states.
+ */
+ DMEMIT(" %s", decipher_sync_action(&rs->md));
+
+ /*
+ * resync_mismatches/mismatch_cnt
+ * This field shows the number of discrepancies found when
+ * performing a "check" of the array.
+ */
+ DMEMIT(" %llu",
+ (strcmp(rs->md.last_sync_action, "check")) ? 0 :
+ (unsigned long long)
+ atomic64_read(&rs->md.resync_mismatches));
break;
case STATUSTYPE_TABLE:
/* The string you would use to construct this array */
@@ -1356,7 +1459,8 @@ static int raid_status(struct dm_target *ti, status_type_t type,
raid10_md_layout_to_copies(rs->md.layout));
if (rs->print_flags & DMPF_RAID10_FORMAT)
- DMEMIT(" raid10_format near");
+ DMEMIT(" raid10_format %s",
+ raid10_md_layout_to_format(rs->md.layout));
DMEMIT(" %d", rs->md.raid_disks);
for (i = 0; i < rs->md.raid_disks; i++) {
@@ -1371,11 +1475,64 @@ static int raid_status(struct dm_target *ti, status_type_t type,
DMEMIT(" -");
}
}
+}
+
+static int raid_message(struct dm_target *ti, unsigned argc, char **argv)
+{
+ struct raid_set *rs = ti->private;
+ struct mddev *mddev = &rs->md;
+
+ if (!strcasecmp(argv[0], "reshape")) {
+ DMERR("Reshape not supported.");
+ return -EINVAL;
+ }
+
+ if (!mddev->pers || !mddev->pers->sync_request)
+ return -EINVAL;
+
+ if (!strcasecmp(argv[0], "frozen"))
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ else
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+
+ if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
+ if (mddev->sync_thread) {
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ md_reap_sync_thread(mddev);
+ }
+ } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+ test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
+ return -EBUSY;
+ else if (!strcasecmp(argv[0], "resync"))
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ else if (!strcasecmp(argv[0], "recover")) {
+ set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ } else {
+ if (!strcasecmp(argv[0], "check"))
+ set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ else if (!!strcasecmp(argv[0], "repair"))
+ return -EINVAL;
+ set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+ set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ }
+ if (mddev->ro == 2) {
+ /* A write to sync_action is enough to justify
+ * canceling read-auto mode
+ */
+ mddev->ro = 0;
+ if (!mddev->suspended)
+ md_wakeup_thread(mddev->sync_thread);
+ }
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ if (!mddev->suspended)
+ md_wakeup_thread(mddev->thread);
return 0;
}
-static int raid_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data)
+static int raid_iterate_devices(struct dm_target *ti,
+ iterate_devices_callout_fn fn, void *data)
{
struct raid_set *rs = ti->private;
unsigned i;
@@ -1416,6 +1573,62 @@ static void raid_postsuspend(struct dm_target *ti)
mddev_suspend(&rs->md);
}
+static void attempt_restore_of_faulty_devices(struct raid_set *rs)
+{
+ int i;
+ uint64_t failed_devices, cleared_failed_devices = 0;
+ unsigned long flags;
+ struct dm_raid_superblock *sb;
+ struct md_rdev *r;
+
+ for (i = 0; i < rs->md.raid_disks; i++) {
+ r = &rs->dev[i].rdev;
+ if (test_bit(Faulty, &r->flags) && r->sb_page &&
+ sync_page_io(r, 0, r->sb_size, r->sb_page, READ, 1)) {
+ DMINFO("Faulty %s device #%d has readable super block."
+ " Attempting to revive it.",
+ rs->raid_type->name, i);
+
+ /*
+ * Faulty bit may be set, but sometimes the array can
+ * be suspended before the personalities can respond
+ * by removing the device from the array (i.e. calling
+ * 'hot_remove_disk'). If they haven't yet removed
+ * the failed device, its 'raid_disk' number will be
+ * '>= 0' - meaning we must call this function
+ * ourselves.
+ */
+ if ((r->raid_disk >= 0) &&
+ (r->mddev->pers->hot_remove_disk(r->mddev, r) != 0))
+ /* Failed to revive this device, try next */
+ continue;
+
+ r->raid_disk = i;
+ r->saved_raid_disk = i;
+ flags = r->flags;
+ clear_bit(Faulty, &r->flags);
+ clear_bit(WriteErrorSeen, &r->flags);
+ clear_bit(In_sync, &r->flags);
+ if (r->mddev->pers->hot_add_disk(r->mddev, r)) {
+ r->raid_disk = -1;
+ r->saved_raid_disk = -1;
+ r->flags = flags;
+ } else {
+ r->recovery_offset = 0;
+ cleared_failed_devices |= 1 << i;
+ }
+ }
+ }
+ if (cleared_failed_devices) {
+ rdev_for_each(r, &rs->md) {
+ sb = page_address(r->sb_page);
+ failed_devices = le64_to_cpu(sb->failed_devices);
+ failed_devices &= ~cleared_failed_devices;
+ sb->failed_devices = cpu_to_le64(failed_devices);
+ }
+ }
+}
+
static void raid_resume(struct dm_target *ti)
{
struct raid_set *rs = ti->private;
@@ -1424,6 +1637,13 @@ static void raid_resume(struct dm_target *ti)
if (!rs->bitmap_loaded) {
bitmap_load(&rs->md);
rs->bitmap_loaded = 1;
+ } else {
+ /*
+ * A secondary resume while the device is active.
+ * Take this opportunity to check whether any failed
+ * devices are reachable again.
+ */
+ attempt_restore_of_faulty_devices(rs);
}
clear_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
@@ -1432,12 +1652,13 @@ static void raid_resume(struct dm_target *ti)
static struct target_type raid_target = {
.name = "raid",
- .version = {1, 4, 0},
+ .version = {1, 5, 2},
.module = THIS_MODULE,
.ctr = raid_ctr,
.dtr = raid_dtr,
.map = raid_map,
.status = raid_status,
+ .message = raid_message,
.iterate_devices = raid_iterate_devices,
.io_hints = raid_io_hints,
.presuspend = raid_presuspend,
@@ -1447,6 +1668,10 @@ static struct target_type raid_target = {
static int __init dm_raid_init(void)
{
+ DMINFO("Loading target version %u.%u.%u",
+ raid_target.version[0],
+ raid_target.version[1],
+ raid_target.version[2]);
return dm_register_target(&raid_target);
}