Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/shli/md

Pull MD update from Shaohua Li:
 "This update mostly includes bug fixes:

   - md-cluster now supports raid10 from Guoqing

   - raid5 PPL fixes from Artur

   - badblock regression fix from Bo

   - suspend hang related fixes from Neil

   - raid5 reshape fixes from Neil

   - raid1 freeze deadlock fix from Nate

   - memleak fixes from Zdenek

   - bitmap related fixes from Me and Tao

   - other fixes and cleanups"

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md: (33 commits)
  md: free unused memory after bitmap resize
  md: release allocated bitset sync_set
  md/bitmap: clear BITMAP_WRITE_ERROR bit before writing it to sb
  md: be cautious about using ->curr_resync_completed for ->recovery_offset
  badblocks: fix wrong return value in badblocks_set if badblocks are disabled
  md: don't check MD_SB_CHANGE_CLEAN in md_allow_write
  md-cluster: update document for raid10
  md: remove redundant variable q
  raid1: remove obsolete code in raid1_write_request
  md-cluster: Use a small window for raid10 resync
  md-cluster: Suspend writes in RAID10 if within range
  md-cluster/raid10: set "do_balance = 0" if area is resyncing
  md: use lockdep_assert_held
  raid1: prevent freeze_array/wait_all_barriers deadlock
  md: use TASK_IDLE instead of blocking signals
  md: remove special meaning of ->quiesce(.., 2)
  md: allow metadata update while suspending.
  md: use mddev_suspend/resume instead of ->quiesce()
  md: move suspend_hi/lo handling into core md code
  md: don't call bitmap_create() while array is quiesced.
  ...

Documentation/md/md-cluster.txt

@@ -1,4 +1,5 @@
-The cluster MD is a shared-device RAID for a cluster.
+The cluster MD is a shared-device RAID for a cluster, it supports
+two levels: raid1 and raid10 (limited support).
 
 
 1. On-disk format

MAINTAINERS

@@ -4103,6 +4103,8 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm.git
 T:	quilt http://people.redhat.com/agk/patches/linux/editing/
 S:	Maintained
 F:	Documentation/device-mapper/
+F:	drivers/md/Makefile
+F:	drivers/md/Kconfig
 F:	drivers/md/dm*
 F:	drivers/md/persistent-data/
 F:	include/linux/device-mapper.h
@@ -12487,7 +12489,10 @@ M:	Shaohua Li <[email protected]>
 L:	[email protected]
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shli/md.git
 S:	Supported
-F:	drivers/md/
+F:	drivers/md/Makefile
+F:	drivers/md/Kconfig
+F:	drivers/md/md*
+F:	drivers/md/raid*
 F:	include/linux/raid/
 F:	include/uapi/linux/raid/
 

block/badblocks.c

@@ -178,7 +178,7 @@ int badblocks_set(struct badblocks *bb, sector_t s, int sectors,
 
 	if (bb->shift < 0)
 		/* badblocks are disabled */
-		return 0;
+		return 1;
 
 	if (bb->shift) {
 		/* round the start down, and the end up */

drivers/md/Kconfig

@@ -178,7 +178,7 @@ config MD_FAULTY
 
 
 config MD_CLUSTER
-	tristate "Cluster Support for MD (EXPERIMENTAL)"
+	tristate "Cluster Support for MD"
 	depends on BLK_DEV_MD
 	depends on DLM
 	default n
@@ -188,7 +188,8 @@ config MD_CLUSTER
 	nodes in the cluster can access the MD devices simultaneously.
 
 	This brings the redundancy (and uptime) of RAID levels across the
-	nodes of the cluster.
+	nodes of the cluster. Currently, it can work with raid1 and raid10
+	(limited support).
 
 	If unsure, say N.
 

drivers/md/Makefile

@@ -19,9 +19,12 @@ dm-cache-y	+= dm-cache-target.o dm-cache-metadata.o dm-cache-policy.o \
 dm-cache-smq-y   += dm-cache-policy-smq.o
 dm-era-y	+= dm-era-target.o
 dm-verity-y	+= dm-verity-target.o
-md-mod-y	+= md.o bitmap.o
+md-mod-y	+= md.o md-bitmap.o
 raid456-y	+= raid5.o raid5-cache.o raid5-ppl.o
 dm-zoned-y	+= dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
+linear-y	+= md-linear.o
+multipath-y	+= md-multipath.o
+faulty-y	+= md-faulty.o
 
 # Note: link order is important.  All raid personalities
 # and must come before md.o, as they each initialise 

drivers/md/dm-raid.c

@@ -12,7 +12,7 @@
 #include "raid1.h"
 #include "raid5.h"
 #include "raid10.h"
-#include "bitmap.h"
+#include "md-bitmap.h"
 
 #include <linux/device-mapper.h>
 
@@ -3630,8 +3630,11 @@ static void raid_postsuspend(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
 
-	if (!test_and_set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags))
+	if (!test_and_set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
+		mddev_lock_nointr(&rs->md);
 		mddev_suspend(&rs->md);
+		mddev_unlock(&rs->md);
+	}
 
 	rs->md.ro = 1;
 }
@@ -3888,8 +3891,11 @@ static void raid_resume(struct dm_target *ti)
 	if (!(rs->ctr_flags & RESUME_STAY_FROZEN_FLAGS))
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 
-	if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags))
+	if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
+		mddev_lock_nointr(mddev);
 		mddev_resume(mddev);
+		mddev_unlock(mddev);
+	}
 }
 
 static struct target_type raid_target = {

drivers/md/bitmap.c → drivers/md/md-bitmap.c

@@ -29,7 +29,7 @@
 #include <linux/seq_file.h>
 #include <trace/events/block.h>
 #include "md.h"
-#include "bitmap.h"
+#include "md-bitmap.h"
 
 static inline char *bmname(struct bitmap *bitmap)
 {
@@ -459,7 +459,11 @@ void bitmap_update_sb(struct bitmap *bitmap)
 		/* rocking back to read-only */
 		bitmap->events_cleared = bitmap->mddev->events;
 	sb->events_cleared = cpu_to_le64(bitmap->events_cleared);
-	sb->state = cpu_to_le32(bitmap->flags);
+	/*
+	 * clear BITMAP_WRITE_ERROR bit to protect against the case that
+	 * a bitmap write error occurred but the later writes succeeded.
+	 */
+	sb->state = cpu_to_le32(bitmap->flags & ~BIT(BITMAP_WRITE_ERROR));
 	/* Just in case these have been changed via sysfs: */
 	sb->daemon_sleep = cpu_to_le32(bitmap->mddev->bitmap_info.daemon_sleep/HZ);
 	sb->write_behind = cpu_to_le32(bitmap->mddev->bitmap_info.max_write_behind);
@@ -625,7 +629,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 		err = read_sb_page(bitmap->mddev,
 				   offset,
 				   sb_page,
-				   0, PAGE_SIZE);
+				   0, sizeof(bitmap_super_t));
 	}
 	if (err)
 		return err;
@@ -1816,6 +1820,12 @@ struct bitmap *bitmap_create(struct mddev *mddev, int slot)
 
 	BUG_ON(file && mddev->bitmap_info.offset);
 
+	if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
+		pr_notice("md/raid:%s: array with journal cannot have bitmap\n",
+			  mdname(mddev));
+		return ERR_PTR(-EBUSY);
+	}
+
 	bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL);
 	if (!bitmap)
 		return ERR_PTR(-ENOMEM);
@@ -2123,7 +2133,7 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	if (store.sb_page && bitmap->storage.sb_page)
 		memcpy(page_address(store.sb_page),
 		       page_address(bitmap->storage.sb_page),
-		       PAGE_SIZE);
+		       sizeof(bitmap_super_t));
 	bitmap_file_unmap(&bitmap->storage);
 	bitmap->storage = store;
 
@@ -2152,6 +2162,7 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 				for (k = 0; k < page; k++) {
 					kfree(new_bp[k].map);
 				}
+				kfree(new_bp);
 
 				/* restore some fields from old_counts */
 				bitmap->counts.bp = old_counts.bp;
@@ -2202,6 +2213,14 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 		block += old_blocks;
 	}
 
+	if (bitmap->counts.bp != old_counts.bp) {
+		unsigned long k;
+		for (k = 0; k < old_counts.pages; k++)
+			if (!old_counts.bp[k].hijacked)
+				kfree(old_counts.bp[k].map);
+		kfree(old_counts.bp);
+	}
+
 	if (!init) {
 		int i;
 		while (block < (chunks << chunkshift)) {

drivers/md/md-cluster.c

@@ -15,7 +15,7 @@
 #include <linux/sched.h>
 #include <linux/raid/md_p.h>
 #include "md.h"
-#include "bitmap.h"
+#include "md-bitmap.h"
 #include "md-cluster.h"
 
 #define LVB_SIZE	64
@@ -442,10 +442,11 @@ static void __remove_suspend_info(struct md_cluster_info *cinfo, int slot)
 static void remove_suspend_info(struct mddev *mddev, int slot)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
+	mddev->pers->quiesce(mddev, 1);
 	spin_lock_irq(&cinfo->suspend_lock);
 	__remove_suspend_info(cinfo, slot);
 	spin_unlock_irq(&cinfo->suspend_lock);
-	mddev->pers->quiesce(mddev, 2);
+	mddev->pers->quiesce(mddev, 0);
 }
 
 
@@ -492,13 +493,12 @@ static void process_suspend_info(struct mddev *mddev,
 	s->lo = lo;
 	s->hi = hi;
 	mddev->pers->quiesce(mddev, 1);
-	mddev->pers->quiesce(mddev, 0);
 	spin_lock_irq(&cinfo->suspend_lock);
 	/* Remove existing entry (if exists) before adding */
 	__remove_suspend_info(cinfo, slot);
 	list_add(&s->list, &cinfo->suspend_list);
 	spin_unlock_irq(&cinfo->suspend_lock);
-	mddev->pers->quiesce(mddev, 2);
+	mddev->pers->quiesce(mddev, 0);
 }
 
 static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
@@ -1094,7 +1094,7 @@ static void metadata_update_cancel(struct mddev *mddev)
 /*
  * return 0 if all the bitmaps have the same sync_size
  */
-int cluster_check_sync_size(struct mddev *mddev)
+static int cluster_check_sync_size(struct mddev *mddev)
 {
 	int i, rv;
 	bitmap_super_t *sb;
@@ -1478,7 +1478,7 @@ static struct md_cluster_operations cluster_ops = {
 
 static int __init cluster_init(void)
 {
-	pr_warn("md-cluster: EXPERIMENTAL. Use with caution\n");
+	pr_warn("md-cluster: support raid1 and raid10 (limited support)\n");
 	pr_info("Registering Cluster MD functions\n");
 	register_md_cluster_operations(&cluster_ops, THIS_MODULE);
 	return 0;

drivers/md/linear.c → drivers/md/md-linear.c

@@ -23,7 +23,7 @@
 #include <linux/slab.h>
 #include <trace/events/block.h>
 #include "md.h"
-#include "linear.h"
+#include "md-linear.h"
 
 /*
  * find which device holds a particular offset

drivers/md/multipath.c → drivers/md/md-multipath.c

@@ -25,7 +25,7 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include "md.h"
-#include "multipath.h"
+#include "md-multipath.h"
 
 #define MAX_WORK_PER_DISK 128
 
@@ -243,7 +243,6 @@ static void print_multipath_conf (struct mpconf *conf)
 static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct mpconf *conf = mddev->private;
-	struct request_queue *q;
 	int err = -EEXIST;
 	int path;
 	struct multipath_info *p;
@@ -257,7 +256,6 @@ static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 
 	for (path = first; path <= last; path++)
 		if ((p=conf->multipaths+path)->rdev == NULL) {
-			q = rdev->bdev->bd_disk->queue;
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);