Merge branch 'linus' into tracing/ftracetip-tracing-ftrace-2008-06-16_09.26_Montip-tracing-ftrace-2008-06-16_09.16_Mon

6 files changed, 145 insertions, 53 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index c14dacdacfac..b26927ce889c 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -203,17 +203,6 @@ static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page)
  * bitmap file handling - read and write the bitmap file and its superblock
  */
 
-/* copy the pathname of a file to a buffer */
-char *file_path(struct file *file, char *buf, int count)
-{
-	if (!buf)
-		return NULL;
-
-	buf = d_path(&file->f_path, buf, count);
-
-	return IS_ERR(buf) ? NULL : buf;
-}
-
 /*
  * basic page I/O operations
  */
@@ -721,11 +710,13 @@ static void bitmap_file_kick(struct bitmap *bitmap)
 		if (bitmap->file) {
 			path = kmalloc(PAGE_SIZE, GFP_KERNEL);
 			if (path)
-				ptr = file_path(bitmap->file, path, PAGE_SIZE);
+				ptr = d_path(&bitmap->file->f_path, path,
+					     PAGE_SIZE);
+
 
 			printk(KERN_ALERT
 			      "%s: kicking failed bitmap file %s from array!\n",
-			      bmname(bitmap), ptr ? ptr : "");
+			      bmname(bitmap), IS_ERR(ptr) ? "" : ptr);
 
 			kfree(path);
 		} else
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 83eb78b00137..7cf512a34ccf 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -74,6 +74,8 @@ static DEFINE_SPINLOCK(pers_lock);
 
 static void md_print_devices(void);
 
+static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
+
 #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
 
 /*
@@ -274,6 +276,7 @@ static mddev_t * mddev_find(dev_t unit)
 	atomic_set(&new->active, 1);
 	spin_lock_init(&new->write_lock);
 	init_waitqueue_head(&new->sb_wait);
+	init_waitqueue_head(&new->recovery_wait);
 	new->reshape_position = MaxSector;
 	new->resync_max = MaxSector;
 	new->level = LEVEL_NONE;
@@ -3013,6 +3016,36 @@ degraded_show(mddev_t *mddev, char *page)
 static struct md_sysfs_entry md_degraded = __ATTR_RO(degraded);
 
 static ssize_t
+sync_force_parallel_show(mddev_t *mddev, char *page)
+{
+	return sprintf(page, "%d\n", mddev->parallel_resync);
+}
+
+static ssize_t
+sync_force_parallel_store(mddev_t *mddev, const char *buf, size_t len)
+{
+	long n;
+
+	if (strict_strtol(buf, 10, &n))
+		return -EINVAL;
+
+	if (n != 0 && n != 1)
+		return -EINVAL;
+
+	mddev->parallel_resync = n;
+
+	if (mddev->sync_thread)
+		wake_up(&resync_wait);
+
+	return len;
+}
+
+/* force parallel resync, even with shared block devices */
+static struct md_sysfs_entry md_sync_force_parallel =
+__ATTR(sync_force_parallel, S_IRUGO|S_IWUSR,
+       sync_force_parallel_show, sync_force_parallel_store);
+
+static ssize_t
 sync_speed_show(mddev_t *mddev, char *page)
 {
 	unsigned long resync, dt, db;
@@ -3187,6 +3220,7 @@ static struct attribute *md_redundancy_attrs[] = {
 	&md_sync_min.attr,
 	&md_sync_max.attr,
 	&md_sync_speed.attr,
+	&md_sync_force_parallel.attr,
 	&md_sync_completed.attr,
 	&md_max_sync.attr,
 	&md_suspend_lo.attr,
@@ -3691,6 +3725,8 @@ static int do_md_stop(mddev_t * mddev, int mode)
 
 			module_put(mddev->pers->owner);
 			mddev->pers = NULL;
+			/* tell userspace to handle 'inactive' */
+			sysfs_notify(&mddev->kobj, NULL, "array_state");
 
 			set_capacity(disk, 0);
 			mddev->changed = 1;
@@ -3987,8 +4023,8 @@ static int get_bitmap_file(mddev_t * mddev, void __user * arg)
 	if (!buf)
 		goto out;
 
-	ptr = file_path(mddev->bitmap->file, buf, sizeof(file->pathname));
-	if (!ptr)
+	ptr = d_path(&mddev->bitmap->file->f_path, buf, sizeof(file->pathname));
+	if (IS_ERR(ptr))
 		goto out;
 
 	strcpy(file->pathname, ptr);
@@ -5399,7 +5435,7 @@ void md_done_sync(mddev_t *mddev, int blocks, int ok)
 	atomic_sub(blocks, &mddev->recovery_active);
 	wake_up(&mddev->recovery_wait);
 	if (!ok) {
-		set_bit(MD_RECOVERY_ERR, &mddev->recovery);
+		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 		// stop recovery, signal do_sync ....
 	}
@@ -5435,8 +5471,11 @@ void md_write_start(mddev_t *mddev, struct bio *bi)
 			md_wakeup_thread(mddev->thread);
 		}
 		spin_unlock_irq(&mddev->write_lock);
+		sysfs_notify(&mddev->kobj, NULL, "array_state");
 	}
-	wait_event(mddev->sb_wait, mddev->flags==0);
+	wait_event(mddev->sb_wait,
+		   !test_bit(MD_CHANGE_CLEAN, &mddev->flags) &&
+		   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
 }
 
 void md_write_end(mddev_t *mddev)
@@ -5471,13 +5510,17 @@ void md_allow_write(mddev_t *mddev)
 			mddev->safemode = 1;
 		spin_unlock_irq(&mddev->write_lock);
 		md_update_sb(mddev, 0);
+
+		sysfs_notify(&mddev->kobj, NULL, "array_state");
+		/* wait for the dirty state to be recorded in the metadata */
+		wait_event(mddev->sb_wait,
+			   !test_bit(MD_CHANGE_CLEAN, &mddev->flags) &&
+			   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
 	} else
 		spin_unlock_irq(&mddev->write_lock);
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
 
-static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
-
 #define SYNC_MARKS	10
 #define	SYNC_MARK_STEP	(3*HZ)
 void md_do_sync(mddev_t *mddev)
@@ -5541,8 +5584,9 @@ void md_do_sync(mddev_t *mddev)
 		for_each_mddev(mddev2, tmp) {
 			if (mddev2 == mddev)
 				continue;
-			if (mddev2->curr_resync && 
-			    match_mddev_units(mddev,mddev2)) {
+			if (!mddev->parallel_resync
+			&&  mddev2->curr_resync
+			&&  match_mddev_units(mddev, mddev2)) {
 				DEFINE_WAIT(wq);
 				if (mddev < mddev2 && mddev->curr_resync == 2) {
 					/* arbitrarily yield */
@@ -5622,7 +5666,6 @@ void md_do_sync(mddev_t *mddev)
 		window/2,(unsigned long long) max_sectors/2);
 
 	atomic_set(&mddev->recovery_active, 0);
-	init_waitqueue_head(&mddev->recovery_wait);
 	last_check = 0;
 
 	if (j>2) {
@@ -5647,7 +5690,7 @@ void md_do_sync(mddev_t *mddev)
 		sectors = mddev->pers->sync_request(mddev, j, &skipped,
 						  currspeed < speed_min(mddev));
 		if (sectors == 0) {
-			set_bit(MD_RECOVERY_ERR, &mddev->recovery);
+			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 			goto out;
 		}
 
@@ -5670,8 +5713,7 @@ void md_do_sync(mddev_t *mddev)
 
 		last_check = io_sectors;
 
-		if (test_bit(MD_RECOVERY_INTR, &mddev->recovery) ||
-		    test_bit(MD_RECOVERY_ERR, &mddev->recovery))
+		if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
 			break;
 
 	repeat:
@@ -5725,8 +5767,7 @@ void md_do_sync(mddev_t *mddev)
 	/* tell personality that we are finished */
 	mddev->pers->sync_request(mddev, max_sectors, &skipped, 1);
 
-	if (!test_bit(MD_RECOVERY_ERR, &mddev->recovery) &&
-	    !test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
+	if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
 	    mddev->curr_resync > 2) {
 		if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
 			if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
@@ -5795,7 +5836,10 @@ static int remove_and_add_spares(mddev_t *mddev)
 		}
 
 	if (mddev->degraded) {
-		rdev_for_each(rdev, rtmp, mddev)
+		rdev_for_each(rdev, rtmp, mddev) {
+			if (rdev->raid_disk >= 0 &&
+			    !test_bit(In_sync, &rdev->flags))
+				spares++;
 			if (rdev->raid_disk < 0
 			    && !test_bit(Faulty, &rdev->flags)) {
 				rdev->recovery_offset = 0;
@@ -5813,6 +5857,7 @@ static int remove_and_add_spares(mddev_t *mddev)
 				} else
 					break;
 			}
+		}
 	}
 	return spares;
 }
@@ -5826,7 +5871,7 @@ static int remove_and_add_spares(mddev_t *mddev)
  * to do that as needed.
  * When it is determined that resync is needed, we set MD_RECOVERY_RUNNING in
  * "->recovery" and create a thread at ->sync_thread.
- * When the thread finishes it sets MD_RECOVERY_DONE (and might set MD_RECOVERY_ERR)
+ * When the thread finishes it sets MD_RECOVERY_DONE
  * and wakeups up this thread which will reap the thread and finish up.
  * This thread also removes any faulty devices (with nr_pending == 0).
  *
@@ -5901,8 +5946,7 @@ void md_check_recovery(mddev_t *mddev)
 			/* resync has finished, collect result */
 			md_unregister_thread(mddev->sync_thread);
 			mddev->sync_thread = NULL;
-			if (!test_bit(MD_RECOVERY_ERR, &mddev->recovery) &&
-			    !test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+			if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
 				/* success...*/
 				/* activate any spares */
 				mddev->pers->spare_active(mddev);
@@ -5926,7 +5970,6 @@ void md_check_recovery(mddev_t *mddev)
 		 * might be left set
 		 */
 		clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-		clear_bit(MD_RECOVERY_ERR, &mddev->recovery);
 		clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 4f4d1f383842..e968116e0de9 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -327,7 +327,8 @@ static int multipath_remove_disk(mddev_t *mddev, int number)
 	if (rdev) {
 		if (test_bit(In_sync, &rdev->flags) ||
 		    atomic_read(&rdev->nr_pending)) {
-			printk(KERN_ERR "hot-remove-disk, slot %d is identified"				" but is still operational!\n", number);
+			printk(KERN_ERR "hot-remove-disk, slot %d is identified"
+			       " but is still operational!\n", number);
 			err = -EBUSY;
 			goto abort;
 		}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index ac409b7d83f5..c610b947218a 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -773,7 +773,7 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	r1bio_t *r1_bio;
 	struct bio *read_bio;
 	int i, targets = 0, disks;
-	struct bitmap *bitmap = mddev->bitmap;
+	struct bitmap *bitmap;
 	unsigned long flags;
 	struct bio_list bl;
 	struct page **behind_pages = NULL;
@@ -802,6 +802,8 @@ static int make_request(struct request_queue *q, struct bio * bio)
 
 	wait_barrier(conf);
 
+	bitmap = mddev->bitmap;
+
 	disk_stat_inc(mddev->gendisk, ios[rw]);
 	disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio));
 
@@ -1025,7 +1027,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 		/*
 		 * if recovery is running, make sure it aborts.
 		 */
-		set_bit(MD_RECOVERY_ERR, &mddev->recovery);
+		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	} else
 		set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
@@ -1146,6 +1148,14 @@ static int raid1_remove_disk(mddev_t *mddev, int number)
 			err = -EBUSY;
 			goto abort;
 		}
+		/* Only remove non-faulty devices is recovery
+		 * is not possible.
+		 */
+		if (!test_bit(Faulty, &rdev->flags) &&
+		    mddev->degraded < conf->raid_disks) {
+			err = -EBUSY;
+			goto abort;
+		}
 		p->rdev = NULL;
 		synchronize_rcu();
 		if (atomic_read(&rdev->nr_pending)) {
@@ -1282,6 +1292,7 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 					rdev_dec_pending(conf->mirrors[i].rdev, mddev);
 				} else {
 					/* fixup the bio for reuse */
+					int size;
 					sbio->bi_vcnt = vcnt;
 					sbio->bi_size = r1_bio->sectors << 9;
 					sbio->bi_idx = 0;
@@ -1295,10 +1306,20 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 					sbio->bi_sector = r1_bio->sector +
 						conf->mirrors[i].rdev->data_offset;
 					sbio->bi_bdev = conf->mirrors[i].rdev->bdev;
-					for (j = 0; j < vcnt ; j++)
-						memcpy(page_address(sbio->bi_io_vec[j].bv_page),
+					size = sbio->bi_size;
+					for (j = 0; j < vcnt ; j++) {
+						struct bio_vec *bi;
+						bi = &sbio->bi_io_vec[j];
+						bi->bv_offset = 0;
+						if (size > PAGE_SIZE)
+							bi->bv_len = PAGE_SIZE;
+						else
+							bi->bv_len = size;
+						size -= PAGE_SIZE;
+						memcpy(page_address(bi->bv_page),
 						       page_address(pbio->bi_io_vec[j].bv_page),
 						       PAGE_SIZE);
+					}
 
 				}
 			}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 8536ede1e712..1de17da34a95 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1020,7 +1020,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 		/*
 		 * if recovery is running, make sure it aborts.
 		 */
-		set_bit(MD_RECOVERY_ERR, &mddev->recovery);
+		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	}
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
@@ -1171,6 +1171,14 @@ static int raid10_remove_disk(mddev_t *mddev, int number)
 			err = -EBUSY;
 			goto abort;
 		}
+		/* Only remove faulty devices in recovery
+		 * is not possible.
+		 */
+		if (!test_bit(Faulty, &rdev->flags) &&
+		    enough(conf)) {
+			err = -EBUSY;
+			goto abort;
+		}
 		p->rdev = NULL;
 		synchronize_rcu();
 		if (atomic_read(&rdev->nr_pending)) {
@@ -1237,6 +1245,7 @@ static void end_sync_write(struct bio *bio, int error)
 
 	if (!uptodate)
 		md_error(mddev, conf->mirrors[d].rdev);
+
 	update_head_pos(i, r10_bio);
 
 	while (atomic_dec_and_test(&r10_bio->remaining)) {
@@ -1844,7 +1853,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 					if (rb2)
 						atomic_dec(&rb2->remaining);
 					r10_bio = rb2;
-					if (!test_and_set_bit(MD_RECOVERY_ERR, &mddev->recovery))
+					if (!test_and_set_bit(MD_RECOVERY_INTR,
+							      &mddev->recovery))
 						printk(KERN_INFO "raid10: %s: insufficient working devices for recovery.\n",
 						       mdname(mddev));
 					break;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 93fde48c0f42..c37e256b1176 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -94,6 +94,8 @@
 #define __inline__
 #endif
 
+#define printk_rl(args...) ((void) (printk_ratelimit() && printk(args)))
+
 #if !RAID6_USE_EMPTY_ZERO_PAGE
 /* In .bss so it's zeroed */
 const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256)));
@@ -1143,10 +1145,12 @@ static void raid5_end_read_request(struct bio * bi, int error)
 		set_bit(R5_UPTODATE, &sh->dev[i].flags);
 		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
 			rdev = conf->disks[i].rdev;
-			printk(KERN_INFO "raid5:%s: read error corrected (%lu sectors at %llu on %s)\n",
-			       mdname(conf->mddev), STRIPE_SECTORS,
-			       (unsigned long long)(sh->sector + rdev->data_offset),
-			       bdevname(rdev->bdev, b));
+			printk_rl(KERN_INFO "raid5:%s: read error corrected"
+				  " (%lu sectors at %llu on %s)\n",
+				  mdname(conf->mddev), STRIPE_SECTORS,
+				  (unsigned long long)(sh->sector
+						       + rdev->data_offset),
+				  bdevname(rdev->bdev, b));
 			clear_bit(R5_ReadError, &sh->dev[i].flags);
 			clear_bit(R5_ReWrite, &sh->dev[i].flags);
 		}
@@ -1160,16 +1164,22 @@ static void raid5_end_read_request(struct bio * bi, int error)
 		clear_bit(R5_UPTODATE, &sh->dev[i].flags);
 		atomic_inc(&rdev->read_errors);
 		if (conf->mddev->degraded)
-			printk(KERN_WARNING "raid5:%s: read error not correctable (sector %llu on %s).\n",
-			       mdname(conf->mddev),
-			       (unsigned long long)(sh->sector + rdev->data_offset),
-			       bdn);
+			printk_rl(KERN_WARNING
+				  "raid5:%s: read error not correctable "
+				  "(sector %llu on %s).\n",
+				  mdname(conf->mddev),
+				  (unsigned long long)(sh->sector
+						       + rdev->data_offset),
+				  bdn);
 		else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
 			/* Oh, no!!! */
-			printk(KERN_WARNING "raid5:%s: read error NOT corrected!! (sector %llu on %s).\n",
-			       mdname(conf->mddev),
-			       (unsigned long long)(sh->sector + rdev->data_offset),
-			       bdn);
+			printk_rl(KERN_WARNING
+				  "raid5:%s: read error NOT corrected!! "
+				  "(sector %llu on %s).\n",
+				  mdname(conf->mddev),
+				  (unsigned long long)(sh->sector
+						       + rdev->data_offset),
+				  bdn);
 		else if (atomic_read(&rdev->read_errors)
 			 > conf->max_nr_stripes)
 			printk(KERN_WARNING
@@ -1258,7 +1268,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 			/*
 			 * if recovery was running, make sure it aborts.
 			 */
-			set_bit(MD_RECOVERY_ERR, &mddev->recovery);
+			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		}
 		set_bit(Faulty, &rdev->flags);
 		printk (KERN_ALERT
@@ -1992,6 +2002,7 @@ static int __handle_issuing_new_read_requests5(struct stripe_head *sh,
 		 * have quiesced.
 		 */
 		if ((s->uptodate == disks - 1) &&
+		    (s->failed && disk_idx == s->failed_num) &&
 		    !test_bit(STRIPE_OP_CHECK, &sh->ops.pending)) {
 			set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
 			set_bit(R5_Wantcompute, &dev->flags);
@@ -2077,7 +2088,9 @@ static void handle_issuing_new_read_requests6(struct stripe_head *sh,
 			/* we would like to get this block, possibly
 			 * by computing it, but we might not be able to
 			 */
-			if (s->uptodate == disks-1) {
+			if ((s->uptodate == disks - 1) &&
+			    (s->failed && (i == r6s->failed_num[0] ||
+					   i == r6s->failed_num[1]))) {
 				pr_debug("Computing stripe %llu block %d\n",
 				       (unsigned long long)sh->sector, i);
 				compute_block_1(sh, i, 0);
@@ -2635,6 +2648,7 @@ static void handle_stripe5(struct stripe_head *sh)
 	struct r5dev *dev;
 	unsigned long pending = 0;
 	mdk_rdev_t *blocked_rdev = NULL;
+	int prexor;
 
 	memset(&s, 0, sizeof(s));
 	pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d "
@@ -2764,9 +2778,11 @@ static void handle_stripe5(struct stripe_head *sh)
 	/* leave prexor set until postxor is done, allows us to distinguish
 	 * a rmw from a rcw during biodrain
 	 */
+	prexor = 0;
 	if (test_bit(STRIPE_OP_PREXOR, &sh->ops.complete) &&
 		test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) {
 
+		prexor = 1;
 		clear_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
 		clear_bit(STRIPE_OP_PREXOR, &sh->ops.ack);
 		clear_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
@@ -2800,6 +2816,8 @@ static void handle_stripe5(struct stripe_head *sh)
 				if (!test_and_set_bit(
 				    STRIPE_OP_IO, &sh->ops.pending))
 					sh->ops.count++;
+				if (prexor)
+					continue;
 				if (!test_bit(R5_Insync, &dev->flags) ||
 				    (i == sh->pd_idx && s.failed == 0))
 					set_bit(STRIPE_INSYNC, &sh->state);
@@ -4564,6 +4582,14 @@ static int raid5_remove_disk(mddev_t *mddev, int number)
 			err = -EBUSY;
 			goto abort;
 		}
+		/* Only remove non-faulty devices if recovery
+		 * isn't possible.
+		 */
+		if (!test_bit(Faulty, &rdev->flags) &&
+		    mddev->degraded <= conf->max_degraded) {
+			err = -EBUSY;
+			goto abort;
+		}
 		p->rdev = NULL;
 		synchronize_rcu();
 		if (atomic_read(&rdev->nr_pending)) {