Merge tag 'md-3.11' of git://neil.brown.name/md

Pull md updates from NeilBrown:
 "Mostly fixes, with a few minor features (eg 'last_sync_action' sysfs
  file)

  A couple marked for -stable including one recent bug which causes a
  RAID10 reshape to complete without moving any data :-(

  A couple more bugfixes (at least) to come, but haven't confirmed the
  right solution yet."

* tag 'md-3.11' of git://neil.brown.name/md:
  md/raid10: fix bug which causes all RAID10 reshapes to move no data.
  md/raid5: allow 5-device RAID6 to be reshaped to 4-device.
  md/raid10: fix two bugs affecting RAID10 reshape.
  md: remove doubled description for sync_max, merging it within sync_min/sync_max
  MD: Remember the last sync operation that was performed
  md: fix buglet in RAID5 -> RAID0 conversion.
  md/raid10: check In_sync flag in 'enough()'.
  md/raid10: locking changes for 'enough()'.
  md: replace strict_strto*() with kstrto*()
  md: Wait for md_check_recovery before attempting device removal.
  dm-raid: silence compiler warning on rebuilds_per_group.
  DM RAID: Fix raid_resume not reviving failed devices in all cases
  DM RAID: Break-up untidy function
  DM RAID: Add ability to restore transiently failed devices on resume

10 files changed, 187 insertions, 70 deletions

diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt
index e9192283e5a5..ef8ba9fa58c4 100644
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@@ -222,3 +222,5 @@ Version History
 1.4.2   Add RAID10 "far" and "offset" algorithm support.
 1.5.0   Add message interface to allow manipulation of the sync_action.
         New status (STATUSTYPE_INFO) fields: sync_action and mismatch_cnt.
+1.5.1   Add ability to restore transiently failed devices on resume.
+1.5.2   'mismatch_cnt' is zero unless [last_]sync_action is "check".
diff --git a/Documentation/md.txt b/Documentation/md.txt
index e0ddd327632d..fbb2fcbf16b6 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -566,13 +566,6 @@ also have
      when it reaches the current sync_max (below) and possibly at
      other times.
 
-   sync_max
-     This is a number of sectors at which point a resync/recovery
-     process will pause.  When a resync is active, the value can
-     only ever be increased, never decreased.  The value of 'max'
-     effectively disables the limit.
-
-
    sync_speed
      This shows the current actual speed, in K/sec, of the current
      sync_action.  It is averaged over the last 30 seconds.
@@ -593,6 +586,12 @@ also have
      that number to reach sync_max.  Then you can either increase
      "sync_max", or can write 'idle' to "sync_action".
 
+     The value of 'max' for "sync_max" effectively disables the limit.
+     When a resync is active, the value can only ever be increased,
+     never decreased.
+     The value of '0' is the minimum for "sync_min".
+
+
 
 Each active md device may also have attributes specific to the
 personality module that manages it.
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 5a2c75499824..a7fd82133b12 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -2002,9 +2002,9 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
                 } else {
                         int rv;
                         if (buf[0] == '+')
-                                rv = strict_strtoll(buf+1, 10, &offset);
+                                rv = kstrtoll(buf+1, 10, &offset);
                         else
-                                rv = strict_strtoll(buf, 10, &offset);
+                                rv = kstrtoll(buf, 10, &offset);
                         if (rv)
                                 return rv;
                         if (offset == 0)
@@ -2139,7 +2139,7 @@ static ssize_t
 backlog_store(struct mddev *mddev, const char *buf, size_t len)
 {
         unsigned long backlog;
-        int rv = strict_strtoul(buf, 10, &backlog);
+        int rv = kstrtoul(buf, 10, &backlog);
         if (rv)
                 return rv;
         if (backlog > COUNTER_MAX)
@@ -2165,7 +2165,7 @@ chunksize_store(struct mddev *mddev, const char *buf, size_t len)
         unsigned long csize;
         if (mddev->bitmap)
                 return -EBUSY;
-        rv = strict_strtoul(buf, 10, &csize);
+        rv = kstrtoul(buf, 10, &csize);
         if (rv)
                 return rv;
         if (csize < 512 ||
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 1d3fe1a40a9b..4880b69e2e9e 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -380,7 +380,7 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
 static int validate_raid_redundancy(struct raid_set *rs)
 {
         unsigned i, rebuild_cnt = 0;
-        unsigned rebuilds_per_group, copies, d;
+        unsigned rebuilds_per_group = 0, copies, d;
         unsigned group_size, last_group_start;
 
         for (i = 0; i < rs->md.raid_disks; i++)
@@ -504,7 +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) {
@@ -585,7 +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;
                 }
@@ -1181,7 +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;
         }
@@ -1194,7 +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;
@@ -1388,6 +1388,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
                  *   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;
@@ -1572,6 +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);
+
+                        /*