Merge branch 'v3.1-rc10' into for-3.2/core

Conflicts:
	block/blk-core.c
	include/linux/blkdev.h

Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 42 insertions, 8 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 5c2178562c96..8f52d4eb78a0 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -61,6 +61,11 @@
 static void autostart_arrays(int part);
 #endif
 
+/* pers_list is a list of registered personalities protected
+ * by pers_lock.
+ * pers_lock does extra service to protect accesses to
+ * mddev->thread when the mutex cannot be held.
+ */
 static LIST_HEAD(pers_list);
 static DEFINE_SPINLOCK(pers_lock);
 
@@ -735,7 +740,12 @@ static void mddev_unlock(mddev_t * mddev)
         } else
                 mutex_unlock(&mddev->reconfig_mutex);
 
+        /* was we've dropped the mutex we need a spinlock to
+         * make sur the thread doesn't disappear
+         */
+        spin_lock(&pers_lock);
         md_wakeup_thread(mddev->thread);
+        spin_unlock(&pers_lock);
 }
 
 static mdk_rdev_t * find_rdev_nr(mddev_t *mddev, int nr)
@@ -844,7 +854,7 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
         bio->bi_end_io = super_written;
 
         atomic_inc(&mddev->pending_writes);
-        submit_bio(REQ_WRITE | REQ_SYNC | REQ_FLUSH | REQ_FUA, bio);
+        submit_bio(WRITE_FLUSH_FUA, bio);
 }
 
 void md_super_wait(mddev_t *mddev)
@@ -1134,8 +1144,11 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
                         ret = 0;
         }
         rdev->sectors = rdev->sb_start;
+        /* Limit to 4TB as metadata cannot record more than that */
+        if (rdev->sectors >= (2ULL << 32))
+                rdev->sectors = (2ULL << 32) - 2;
 
-        if (rdev->sectors < sb->size * 2 && sb->level > 1)
+        if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
                 /* "this cannot possibly happen" ... */
                 ret = -EINVAL;
 
@@ -1169,7 +1182,7 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
                 mddev->clevel[0] = 0;
                 mddev->layout = sb->layout;
                 mddev->raid_disks = sb->raid_disks;
-                mddev->dev_sectors = sb->size * 2;
+                mddev->dev_sectors = ((sector_t)sb->size) * 2;
                 mddev->events = ev1;
                 mddev->bitmap_info.offset = 0;
                 mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9;
@@ -1411,6 +1424,11 @@ super_90_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
         rdev->sb_start = calc_dev_sboffset(rdev);
         if (!num_sectors || num_sectors > rdev->sb_start)
                 num_sectors = rdev->sb_start;
+        /* Limit to 4TB as metadata cannot record more than that.
+         * 4TB == 2^32 KB, or 2*2^32 sectors.
+         */
+        if (num_sectors >= (2ULL << 32))
+                num_sectors = (2ULL << 32) - 2;
         md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
                        rdev->sb_page);
         md_super_wait(rdev->mddev);
@@ -1734,6 +1752,11 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
         sb->level = cpu_to_le32(mddev->level);
         sb->layout = cpu_to_le32(mddev->layout);
 
+        if (test_bit(WriteMostly, &rdev->flags))
+                sb->devflags |= WriteMostly1;
+        else
+                sb->devflags &= ~WriteMostly1;
+
         if (mddev->bitmap && mddev->bitmap_info.file == NULL) {
                 sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_info.offset);
                 sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
@@ -2557,7 +2580,10 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
         int err = -EINVAL;
         if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
                 md_error(rdev->mddev, rdev);
-                err = 0;
+                if (test_bit(Faulty, &rdev->flags))
+                        err = 0;
+                else
+                        err = -EBUSY;
         } else if (cmd_match(buf, "remove")) {
                 if (rdev->raid_disk >= 0)
                         err = -EBUSY;
@@ -2580,7 +2606,7 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
                 err = 0;
         } else if (cmd_match(buf, "-blocked")) {
                 if (!test_bit(Faulty, &rdev->flags) &&
-                    test_bit(BlockedBadBlocks, &rdev->flags)) {
+                    rdev->badblocks.unacked_exist) {
                         /* metadata handler doesn't understand badblocks,
                          * so we need to fail the device
                          */
@@ -5979,6 +6005,8 @@ static int set_disk_faulty(mddev_t *mddev, dev_t dev)
                 return -ENODEV;
 
         md_error(mddev, rdev);
+        if (!test_bit(Faulty, &rdev->flags))
+                return -EBUSY;
         return 0;
 }
 
@@ -6407,11 +6435,18 @@ mdk_thread_t *md_register_thread(void (*run) (mddev_t *), mddev_t *mddev,
         return thread;
 }
 
-void md_unregister_thread(mdk_thread_t *thread)
+void md_unregister_thread(mdk_thread_t **threadp)
 {
+        mdk_thread_t *thread = *threadp;
         if (!thread)
                 return;
         dprintk("interrupting MD-thread pid %d\n", task_pid_nr(thread->tsk));
+        /* Locking ensures that mddev_unlock does not wake_up a
+         * non-existent thread
+         */
+        spin_lock(&pers_lock);
+        *threadp = NULL;
+        spin_unlock(&pers_lock);
 
         kthread_stop(thread->tsk);
         kfree(thread);
@@ -7318,8 +7353,7 @@ static void reap_sync_thread(mddev_t *mddev)
         mdk_rdev_t *rdev;
 
         /* resync has finished, collect result */
-        md_unregister_thread(mddev->sync_thread);
-        mddev->sync_thread = NULL;
+        md_unregister_thread(&mddev->sync_thread);
         if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
             !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
                 /* success...*/