md: add 'recovery_start' per-device sysfs attribute

Enable external metadata arrays to manage rebuild checkpointing via a
md/dev-XXX/recovery_start attribute which reflects rdev->recovery_offset

Also update resync_start_store to allow 'none' to be written, for
consistency.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: NeilBrown <neilb@suse.de>

2 files changed, 63 insertions, 5 deletions

diff --git a/Documentation/md.txt b/Documentation/md.txt
index 21d26fb5d02b..188f4768f1d5 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -233,9 +233,9 @@ All md devices contain:
 
   resync_start
      The point at which resync should start.  If no resync is needed,
-     this will be a very large number.  At array creation it will
-     default to 0, though starting the array as 'clean' will
-     set it much larger.
+     this will be a very large number (or 'none' since 2.6.30-rc1).  At
+     array creation it will default to 0, though starting the array as
+     'clean' will set it much larger.
 
    new_dev
      This file can be written but not read.  The value written should
@@ -379,8 +379,9 @@ Each directory contains:
         Writing "writemostly" sets the writemostly flag.
         Writing "-writemostly" clears the writemostly flag.
         Writing "blocked" sets the "blocked" flag.
-        Writing "-blocked" clear the "blocked" flag and allows writes
+        Writing "-blocked" clears the "blocked" flag and allows writes
                 to complete.
+        Writing "in_sync" sets the in_sync flag.
 
         This file responds to select/poll. Any change to 'faulty'
         or 'blocked' causes an event.
@@ -417,6 +418,24 @@ Each directory contains:
         array.  If a value less than the current component_size is
         written, it will be rejected.
 
+      recovery_start
+
+        When the device is not 'in_sync', this records the number of
+        sectors from the start of the device which are known to be
+        correct.  This is normally zero, but during a recovery
+        operation is will steadily increase, and if the recovery is
+        interrupted, restoring this value can cause recovery to
+        avoid repeating the earlier blocks.  With v1.x metadata, this
+        value is saved and restored automatically.
+
+        This can be set whenever the device is not an active member of
+        the array, either before the array is activated, or before
+        the 'slot' is set.
+
+        Setting this to 'none' is equivalent to setting 'in_sync'.
+        Setting to any other value also clears the 'in_sync' flag.
+        
+
 
 An active md device will also contain and entry for each active device
 in the array.  These are named
diff --git a/drivers/md/md.c b/drivers/md/md.c
index ea64a68e9c75..e1f3c1715cca 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2551,12 +2551,49 @@ rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 static struct rdev_sysfs_entry rdev_size =
 __ATTR(size, S_IRUGO|S_IWUSR, rdev_size_show, rdev_size_store);
 
+
+static ssize_t recovery_start_show(mdk_rdev_t *rdev, char *page)
+{
+        unsigned long long recovery_start = rdev->recovery_offset;
+
+        if (test_bit(In_sync, &rdev->flags) ||
+            recovery_start == MaxSector)
+                return sprintf(page, "none\n");
+
+        return sprintf(page, "%llu\n", recovery_start);
+}
+
+static ssize_t recovery_start_store(mdk_rdev_t *rdev, const char *buf, size_t len)
+{
+        unsigned long long recovery_start;
+
+        if (cmd_match(buf, "none"))
+                recovery_start = MaxSector;
+        else if (strict_strtoull(buf, 10, &recovery_start))
+                return -EINVAL;
+
+        if (rdev->mddev->pers &&
+            rdev->raid_disk >= 0)
+                return -EBUSY;
+
+        rdev->recovery_offset = recovery_start;
+        if (recovery_start == MaxSector)
+                set_bit(In_sync, &rdev->flags);
+        else
+                clear_bit(In_sync, &rdev->flags);
+        return len;
+}
+
+static struct rdev_sysfs_entry rdev_recovery_start =
+__ATTR(recovery_start, S_IRUGO|S_IWUSR, recovery_start_show, recovery_start_store);
+
 static struct attribute *rdev_default_attrs[] = {
         &rdev_state.attr,
         &rdev_errors.attr,
         &rdev_slot.attr,
         &rdev_offset.attr,
         &rdev_size.attr,
+        &rdev_recovery_start.attr,
         NULL,
 };
 static ssize_t
@@ -3101,7 +3138,9 @@ resync_start_store(mddev_t *mddev, const char *buf, size_t len)
 
         if (mddev->pers)
                 return -EBUSY;
-        if (!*buf || (*e && *e != '\n'))
+        if (cmd_match(buf, "none"))
+                n = MaxSector;
+        else if (!*buf || (*e && *e != '\n'))
                 return -EINVAL;
 
         mddev->recovery_cp = n;