1 files changed, 122 insertions, 28 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index d2c0f94fa37d..96c690279fc6 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -277,12 +277,13 @@ out:
         return sh;
 }
 
-static void shrink_buffers(struct stripe_head *sh, int num)
+static void shrink_buffers(struct stripe_head *sh)
 {
         struct page *p;
         int i;
+        int num = sh->raid_conf->pool_size;
 
-        for (i=0; i<num ; i++) {
+        for (i = 0; i < num ; i++) {
                 p = sh->dev[i].page;
                 if (!p)
                         continue;
@@ -291,11 +292,12 @@ static void shrink_buffers(struct stripe_head *sh, int num)
         }
 }
 
-static int grow_buffers(struct stripe_head *sh, int num)
+static int grow_buffers(struct stripe_head *sh)
 {
         int i;
+        int num = sh->raid_conf->pool_size;
 
-        for (i=0; i<num; i++) {
+        for (i = 0; i < num; i++) {
                 struct page *page;
 
                 if (!(page = alloc_page(GFP_KERNEL))) {
@@ -364,6 +366,73 @@ static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector,
         return NULL;
 }
 
+/*
+ * Need to check if array has failed when deciding whether to:
+ *  - start an array
+ *  - remove non-faulty devices
+ *  - add a spare
+ *  - allow a reshape
+ * This determination is simple when no reshape is happening.
+ * However if there is a reshape, we need to carefully check
+ * both the before and after sections.
+ * This is because some failed devices may only affect one
+ * of the two sections, and some non-in_sync devices may
+ * be insync in the section most affected by failed devices.
+ */
+static int has_failed(raid5_conf_t *conf)
+{
+        int degraded;
+        int i;
+        if (conf->mddev->reshape_position == MaxSector)
+                return conf->mddev->degraded > conf->max_degraded;
+
+        rcu_read_lock();
+        degraded = 0;
+        for (i = 0; i < conf->previous_raid_disks; i++) {
+                mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
+                if (!rdev || test_bit(Faulty, &rdev->flags))
+                        degraded++;
+                else if (test_bit(In_sync, &rdev->flags))
+                        ;
+                else
+                        /* not in-sync or faulty.
+                         * If the reshape increases the number of devices,
+                         * this is being recovered by the reshape, so
+                         * this 'previous' section is not in_sync.
+                         * If the number of devices is being reduced however,
+                         * the device can only be part of the array if
+                         * we are reverting a reshape, so this section will
+                         * be in-sync.
+                         */
+                        if (conf->raid_disks >= conf->previous_raid_disks)
+                                degraded++;
+        }
+        rcu_read_unlock();
+        if (degraded > conf->max_degraded)
+                return 1;
+        rcu_read_lock();
+        degraded = 0;
+        for (i = 0; i < conf->raid_disks; i++) {
+                mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
+                if (!rdev || test_bit(Faulty, &rdev->flags))
+                        degraded++;
+                else if (test_bit(In_sync, &rdev->flags))
+                        ;
+                else
+                        /* not in-sync or faulty.
+                         * If reshape increases the number of devices, this
+                         * section has already been recovered, else it
+                         * almost certainly hasn't.
+                         */
+                        if (conf->raid_disks <= conf->previous_raid_disks)
+                                degraded++;
+        }
+        rcu_read_unlock();
+        if (degraded > conf->max_degraded)
+                return 1;
+        return 0;
+}
+
 static void unplug_slaves(mddev_t *mddev);
 static void raid5_unplug_device(struct request_queue *q);
 
@@ -1240,19 +1309,18 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 static int grow_one_stripe(raid5_conf_t *conf)
 {
         struct stripe_head *sh;
-        int disks = max(conf->raid_disks, conf->previous_raid_disks);
         sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL);
         if (!sh)
                 return 0;
-        memset(sh, 0, sizeof(*sh) + (disks-1)*sizeof(struct r5dev));
+        memset(sh, 0, sizeof(*sh) + (conf->pool_size-1)*sizeof(struct r5dev));
         sh->raid_conf = conf;
         spin_lock_init(&sh->lock);
         #ifdef CONFIG_MULTICORE_RAID456
         init_waitqueue_head(&sh->ops.wait_for_ops);
         #endif
 
-        if (grow_buffers(sh, disks)) {
-                shrink_buffers(sh, disks);
+        if (grow_buffers(sh)) {
+                shrink_buffers(sh);
                 kmem_cache_free(conf->slab_cache, sh);
                 return 0;
         }
@@ -1468,7 +1536,7 @@ static int drop_one_stripe(raid5_conf_t *conf)
         if (!sh)
                 return 0;
         BUG_ON(atomic_read(&sh->count));
-        shrink_buffers(sh, conf->pool_size);
+        shrink_buffers(sh);
         kmem_cache_free(conf->slab_cache, sh);
         atomic_dec(&conf->active_stripes);
         return 1;
@@ -2963,7 +3031,6 @@ static void handle_stripe5(struct stripe_head *sh)
                 mdk_rdev_t *rdev;
 
                 dev = &sh->dev[i];
-                clear_bit(R5_Insync, &dev->flags);
 
                 pr_debug("check %d: state 0x%lx toread %p read %p write %p "
                         "written %p\n", i, dev->flags, dev->toread, dev->read,
@@ -3000,17 +3067,27 @@ static void handle_stripe5(struct stripe_head *sh)
                         blocked_rdev = rdev;
                         atomic_inc(&rdev->nr_pending);
                 }
-                if (!rdev || !test_bit(In_sync, &rdev->flags)) {
+                clear_bit(R5_Insync, &dev->flags);
+                if (!rdev)
+                        /* Not in-sync */;
+                else if (test_bit(In_sync, &rdev->flags))
+                        set_bit(R5_Insync, &dev->flags);
+                else {
+                        /* could be in-sync depending on recovery/reshape status */
+                        if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
+                                set_bit(R5_Insync, &dev->flags);
+                }
+                if (!test_bit(R5_Insync, &dev->flags)) {
                         /* The ReadError flag will just be confusing now */
                         clear_bit(R5_ReadError, &dev->flags);
                         clear_bit(R5_ReWrite, &dev->flags);
                 }
-                if (!rdev || !test_bit(In_sync, &rdev->flags)
-                    || test_bit(R5_ReadError, &dev->flags)) {
+                if (test_bit(R5_ReadError, &dev->flags))
+                        clear_bit(R5_Insync, &dev->flags);
+                if (!test_bit(R5_Insync, &dev->flags)) {
                         s.failed++;
                         s.failed_num = i;
-                } else
-                        set_bit(R5_Insync, &dev->flags);
+                }
         }
         rcu_read_unlock();
 
@@ -3244,7 +3321,6 @@ static void handle_stripe6(struct stripe_head *sh)
         for (i=disks; i--; ) {
                 mdk_rdev_t *rdev;
                 dev = &sh->dev[i];
-                clear_bit(R5_Insync, &dev->flags);
 
                 pr_debug("check %d: state 0x%lx read %p write %p written %p\n",
                         i, dev->flags, dev->toread, dev->towrite, dev->written);
@@ -3282,18 +3358,28 @@ static void handle_stripe6(struct stripe_head *sh)
                         blocked_rdev = rdev;
                         atomic_inc(&rdev->nr_pending);
                 }
-                if (!rdev || !test_bit(In_sync, &rdev->flags)) {
+                clear_bit(R5_Insync, &dev->flags);
+                if (!rdev)
+                        /* Not in-sync */;
+                else if (test_bit(In_sync, &rdev->flags))
+                        set_bit(R5_Insync, &dev->flags);
+                else {
+                        /* in sync if before recovery_offset */
+                        if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
+                                set_bit(R5_Insync, &dev->flags);
+                }
+                if (!test_bit(R5_Insync, &dev->flags)) {
                         /* The ReadError flag will just be confusing now */
                         clear_bit(R5_ReadError, &dev->flags);
                         clear_bit(R5_ReWrite, &dev->flags);
                 }
-                if (!rdev || !test_bit(In_sync, &rdev->flags)
-                    || test_bit(R5_ReadError, &dev->flags)) {
+                if (test_bit(R5_ReadError, &dev->flags))
+                        clear_bit(R5_Insync, &dev->flags);
+                if (!test_bit(R5_Insync, &dev->flags)) {
                         if (s.failed < 2)
                                 r6s.failed_num[s.failed] = i;
                         s.failed++;
-                } else
-                        set_bit(R5_Insync, &dev->flags);
+                }
         }
         rcu_read_unlock();
 
@@ -4971,8 +5057,10 @@ static int run(mddev_t *mddev)
         list_for_each_entry(rdev, &mddev->disks, same_set) {
                 if (rdev->raid_disk < 0)
                         continue;
-                if (test_bit(In_sync, &rdev->flags))
+                if (test_bit(In_sync, &rdev->flags)) {
                         working_disks++;
+                        continue;
+                }
                 /* This disc is not fully in-sync.  However if it
                  * just stored parity (beyond the recovery_offset),
                  * when we don't need to be concerned about the
@@ -5005,7 +5093,7 @@ static int run(mddev_t *mddev)
         mddev->degraded = (max(conf->raid_disks, conf->previous_raid_disks)
                            - working_disks);
 
-        if (mddev->degraded > conf->max_degraded) {
+        if (has_failed(conf)) {
                 printk(KERN_ERR "md/raid:%s: not enough operational devices"
                         " (%d/%d failed)\n",
                         mdname(mddev), mddev->degraded, conf->raid_disks);
@@ -5207,6 +5295,7 @@ static int raid5_spare_active(mddev_t *mddev)
         for (i = 0; i < conf->raid_disks; i++) {
                 tmp = conf->disks + i;
                 if (tmp->rdev
+                    && tmp->rdev->recovery_offset == MaxSector
                     && !test_bit(Faulty, &tmp->rdev->flags)
                     && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
                         unsigned long flags;
@@ -5242,7 +5331,7 @@ static int raid5_remove_disk(mddev_t *mddev, int number)
                  * isn't possible.
                  */
                 if (!test_bit(Faulty, &rdev->flags) &&
-                    mddev->degraded <= conf->max_degraded &&
+                    !has_failed(conf) &&
                     number < conf->raid_disks) {
                         err = -EBUSY;
                         goto abort;
@@ -5270,7 +5359,7 @@ static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
         int first = 0;
         int last = conf->raid_disks - 1;
 
-        if (mddev->degraded > conf->max_degraded)
+        if (has_failed(conf))
                 /* no point adding a device */
                 return -EINVAL;
 
@@ -5362,7 +5451,7 @@ static int check_reshape(mddev_t *mddev)
         if (mddev->bitmap)
                 /* Cannot grow a bitmap yet */
                 return -EBUSY;
-        if (mddev->degraded > conf->max_degraded)
+        if (has_failed(conf))
                 return -EINVAL;
         if (mddev->delta_disks < 0) {
                 /* We might be able to shrink, but the devices must
@@ -5437,8 +5526,13 @@ static int raid5_start_reshape(mddev_t *mddev)
 
         /* Add some new drives, as many as will fit.
          * We know there are enough to make the newly sized array work.
+         * Don't add devices if we are reducing the number of
+         * devices in the array.  This is because it is not possible
+         * to correctly record the "partially reconstructed" state of
+         * such devices during the reshape and confusion could result.
          */
-        list_for_each_entry(rdev, &mddev->disks, same_set)
+        if (mddev->delta_disks >= 0)
+            list_for_each_entry(rdev, &mddev->disks, same_set)
                 if (rdev->raid_disk < 0 &&
                     !test_bit(Faulty, &rdev->flags)) {
                         if (raid5_add_disk(mddev, rdev) == 0) {
@@ -5460,7 +5554,7 @@ static int raid5_start_reshape(mddev_t *mddev)
                 }
 
         /* When a reshape changes the number of devices, ->degraded
-         * is measured against the large of the pre and post number of
+         * is measured against the larger of the pre and post number of
          * devices.*/
         if (mddev->delta_disks > 0) {
                 spin_lock_irqsave(&conf->device_lock, flags);