Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md: (52 commits)
  md: Protect access to mddev->disks list using RCU
  md: only count actual openers as access which prevent a 'stop'
  md: linear: Make array_size sector-based and rename it to array_sectors.
  md: Make mddev->array_size sector-based.
  md: Make super_type->rdev_size_change() take sector-based sizes.
  md: Fix check for overlapping devices.
  md: Tidy up rdev_size_store a bit:
  md: Remove some unused macros.
  md: Turn rdev->sb_offset into a sector-based quantity.
  md: Make calc_dev_sboffset() return a sector count.
  md: Replace calc_dev_size() by calc_num_sectors().
  md: Make update_size() take the number of sectors.
  md: Better control of when do_md_stop is allowed to stop the array.
  md: get_disk_info(): Don't convert between signed and unsigned and back.
  md: Simplify restart_array().
  md: alloc_disk_sb(): Return proper error value.
  md: Simplify sb_equal().
  md: Simplify uuid_equal().
  md: sb_equal(): Fix misleading printk.
  md: Fix a typo in the comment to cmd_match().
  ...

Documentation/md.txt

@@ -236,6 +236,11 @@ All md devices contain:
      writing the word for the desired state, however some states
      cannot be explicitly set, and some transitions are not allowed.
 
+     Select/poll works on this file.  All changes except between
+     	active_idle and active (which can be frequent and are not
+	very interesting) are notified.  active->active_idle is
+	reported if the metadata is externally managed.
+
      clear
          No devices, no size, no level
          Writing is equivalent to STOP_ARRAY ioctl
@@ -292,6 +297,10 @@ Each directory contains:
 	      writemostly - device will only be subject to read
 		         requests if there are no other options.
 			 This applies only to raid1 arrays.
+	      blocked  - device has failed, metadata is "external",
+	                 and the failure hasn't been acknowledged yet.
+			 Writes that would write to this device if
+			 it were not faulty are blocked.
 	      spare    - device is working, but not a full member.
 			 This includes spares that are in the process
 			 of being recovered to
@@ -301,6 +310,12 @@ Each directory contains:
 	Writing "remove" removes the device from the array.
 	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
+		to complete.
+
+	This file responds to select/poll. Any change to 'faulty'
+	or 'blocked' causes an event.
 
       errors
 	An approximate count of read errors that have been detected on
@@ -332,7 +347,7 @@ Each directory contains:
         for storage of data.  This will normally be the same as the
 	component_size.  This can be written while assembling an
         array.  If a value less than the current component_size is
-        written, component_size will be reduced to this value.
+        written, it will be rejected.
 
 
 An active md device will also contain and entry for each active device
@@ -381,6 +396,19 @@ also have
 	'check' and 'repair' will start the appropriate process
            providing the current state is 'idle'.
 
+      This file responds to select/poll.  Any important change in the value
+      triggers a poll event.  Sometimes the value will briefly be
+      "recover" if a recovery seems to be needed, but cannot be
+      achieved. In that case, the transition to "recover" isn't
+      notified, but the transition away is.
+
+   degraded
+      This contains a count of the number of devices by which the
+      arrays is degraded.  So an optimal array with show '0'.  A
+      single failed/missing drive will show '1', etc.
+      This file responds to select/poll, any increase or decrease
+      in the count of missing devices will trigger an event.
+
    mismatch_count
       When performing 'check' and 'repair', and possibly when
       performing 'resync', md will count the number of errors that are

drivers/md/bitmap.c

@@ -225,7 +225,7 @@ static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long inde
 		    || test_bit(Faulty, &rdev->flags))
 			continue;
 
-		target = (rdev->sb_offset << 1) + offset + index * (PAGE_SIZE/512);
+		target = rdev->sb_start + offset + index * (PAGE_SIZE/512);
 
 		if (sync_page_io(rdev->bdev, target, PAGE_SIZE, page, READ)) {
 			page->index = index;
@@ -241,10 +241,10 @@ static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long inde
 static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 {
 	mdk_rdev_t *rdev;
-	struct list_head *tmp;
 	mddev_t *mddev = bitmap->mddev;
 
-	rdev_for_each(rdev, tmp, mddev)
+	rcu_read_lock();
+	rdev_for_each_rcu(rdev, mddev)
 		if (test_bit(In_sync, &rdev->flags)
 		    && !test_bit(Faulty, &rdev->flags)) {
 			int size = PAGE_SIZE;
@@ -260,32 +260,37 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 				    + (long)(page->index * (PAGE_SIZE/512))
 				    + size/512 > 0)
 					/* bitmap runs in to metadata */
-					return -EINVAL;
+					goto bad_alignment;
 				if (rdev->data_offset + mddev->size*2
-				    > rdev->sb_offset*2 + bitmap->offset)
+				    > rdev->sb_start + bitmap->offset)
 					/* data runs in to bitmap */
-					return -EINVAL;
-			} else if (rdev->sb_offset*2 < rdev->data_offset) {
+					goto bad_alignment;
+			} else if (rdev->sb_start < rdev->data_offset) {
 				/* METADATA BITMAP DATA */
-				if (rdev->sb_offset*2
+				if (rdev->sb_start
 				    + bitmap->offset
 				    + page->index*(PAGE_SIZE/512) + size/512
 				    > rdev->data_offset)
 					/* bitmap runs in to data */
-					return -EINVAL;
+					goto bad_alignment;
 			} else {
 				/* DATA METADATA BITMAP - no problems */
 			}
 			md_super_write(mddev, rdev,
-				       (rdev->sb_offset<<1) + bitmap->offset
+				       rdev->sb_start + bitmap->offset
 				       + page->index * (PAGE_SIZE/512),
 				       size,
 				       page);
 		}
+	rcu_read_unlock();
 
 	if (wait)
 		md_super_wait(mddev);
 	return 0;
+
+ bad_alignment:
+	rcu_read_unlock();
+	return -EINVAL;
 }
 
 static void bitmap_file_kick(struct bitmap *bitmap);
@@ -454,8 +459,11 @@ void bitmap_update_sb(struct bitmap *bitmap)
 	spin_unlock_irqrestore(&bitmap->lock, flags);
 	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
 	sb->events = cpu_to_le64(bitmap->mddev->events);
-	if (!bitmap->mddev->degraded)
-		sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
+	if (bitmap->mddev->events < bitmap->events_cleared) {
+		/* rocking back to read-only */
+		bitmap->events_cleared = bitmap->mddev->events;
+		sb->events_cleared = cpu_to_le64(bitmap->events_cleared);
+	}
 	kunmap_atomic(sb, KM_USER0);
 	write_page(bitmap, bitmap->sb_page, 1);
 }
@@ -1085,9 +1093,19 @@ void bitmap_daemon_work(struct bitmap *bitmap)
 			} else
 				spin_unlock_irqrestore(&bitmap->lock, flags);
 			lastpage = page;
-/*
-			printk("bitmap clean at page %lu\n", j);
-*/
+
+			/* We are possibly going to clear some bits, so make
+			 * sure that events_cleared is up-to-date.
+			 */
+			if (bitmap->need_sync) {
+				bitmap_super_t *sb;
+				bitmap->need_sync = 0;
+				sb = kmap_atomic(bitmap->sb_page, KM_USER0);
+				sb->events_cleared =
+					cpu_to_le64(bitmap->events_cleared);
+				kunmap_atomic(sb, KM_USER0);
+				write_page(bitmap, bitmap->sb_page, 1);
+			}
 			spin_lock_irqsave(&bitmap->lock, flags);
 			clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
 		}
@@ -1257,6 +1275,12 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
 			return;
 		}
 
+		if (success &&
+		    bitmap->events_cleared < bitmap->mddev->events) {
+			bitmap->events_cleared = bitmap->mddev->events;
+			bitmap->need_sync = 1;
+		}
+
 		if (!success && ! (*bmc & NEEDED_MASK))
 			*bmc |= NEEDED_MASK;
 

drivers/md/faulty.c

@@ -297,7 +297,7 @@ static int run(mddev_t *mddev)
 	rdev_for_each(rdev, tmp, mddev)
 		conf->rdev = rdev;
 
-	mddev->array_size = mddev->size;
+	mddev->array_sectors = mddev->size * 2;
 	mddev->private = conf;
 
 	reconfig(mddev, mddev->layout, -1);

drivers/md/linear.c

@@ -122,13 +122,13 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 		return NULL;
 
 	cnt = 0;
-	conf->array_size = 0;
+	conf->array_sectors = 0;
 
 	rdev_for_each(rdev, tmp, mddev) {
 		int j = rdev->raid_disk;
 		dev_info_t *disk = conf->disks + j;
 
-		if (j < 0 || j > raid_disks || disk->rdev) {
+		if (j < 0 || j >= raid_disks || disk->rdev) {
 			printk("linear: disk numbering problem. Aborting!\n");
 			goto out;
 		}
@@ -146,7 +146,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->size = rdev->size;
-		conf->array_size += rdev->size;
+		conf->array_sectors += rdev->size * 2;
 
 		cnt++;
 	}
@@ -155,7 +155,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 		goto out;
 	}
 
-	min_spacing = conf->array_size;
+	min_spacing = conf->array_sectors / 2;
 	sector_div(min_spacing, PAGE_SIZE/sizeof(struct dev_info *));
 
 	/* min_spacing is the minimum spacing that will fit the hash
@@ -164,7 +164,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 	 * that is larger than min_spacing as use the size of that as
 	 * the actual spacing
 	 */
-	conf->hash_spacing = conf->array_size;
+	conf->hash_spacing = conf->array_sectors / 2;
 	for (i=0; i < cnt-1 ; i++) {
 		sector_t sz = 0;
 		int j;
@@ -194,7 +194,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 		unsigned round;
 		unsigned long base;
 
-		sz = conf->array_size >> conf->preshift;
+		sz = conf->array_sectors >> (conf->preshift + 1);
 		sz += 1; /* force round-up */
 		base = conf->hash_spacing >> conf->preshift;
 		round = sector_div(sz, base);
@@ -221,7 +221,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 	curr_offset = 0;
 	i = 0;
 	for (curr_offset = 0;
-	     curr_offset < conf->array_size;
+	     curr_offset < conf->array_sectors / 2;
 	     curr_offset += conf->hash_spacing) {
 
 		while (i < raid_disks-1 &&
@@ -258,7 +258,7 @@ static int linear_run (mddev_t *mddev)
 	if (!conf)
 		return 1;
 	mddev->private = conf;
-	mddev->array_size = conf->array_size;
+	mddev->array_sectors = conf->array_sectors;
 
 	blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
 	mddev->queue->unplug_fn = linear_unplug;
@@ -292,8 +292,8 @@ static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev)
 	newconf->prev = mddev_to_conf(mddev);
 	mddev->private = newconf;
 	mddev->raid_disks++;
-	mddev->array_size = newconf->array_size;
-	set_capacity(mddev->gendisk, mddev->array_size << 1);
+	mddev->array_sectors = newconf->array_sectors;
+	set_capacity(mddev->gendisk, mddev->array_sectors);
 	return 0;
 }