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

* 'for-linus' of git://neil.brown.name/md:
  md: remove rd%d links immediately after stopping an array.
  md: remove ability to explicit set an inactive array to 'clean'.
  md: constify VFTs
  md: tidy up status_resync to handle large arrays.
  md: fix some (more) errors with bitmaps on devices larger than 2TB.
  md/raid10: don't clear bitmap during recovery if array will still be degraded.
  md: fix loading of out-of-date bitmap.

drivers/md/bitmap.c

@@ -986,6 +986,9 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 			oldindex = index;
 			oldpage = page;
 
+			bitmap->filemap[bitmap->file_pages++] = page;
+			bitmap->last_page_size = count;
+
 			if (outofdate) {
 				/*
 				 * if bitmap is out of date, dirty the
@@ -998,15 +1001,9 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 				write_page(bitmap, page, 1);
 
 				ret = -EIO;
-				if (bitmap->flags & BITMAP_WRITE_ERROR) {
-					/* release, page not in filemap yet */
-					put_page(page);
+				if (bitmap->flags & BITMAP_WRITE_ERROR)
 					goto err;
-				}
 			}
-
-			bitmap->filemap[bitmap->file_pages++] = page;
-			bitmap->last_page_size = count;
 		}
 		paddr = kmap_atomic(page, KM_USER0);
 		if (bitmap->flags & BITMAP_HOSTENDIAN)
@@ -1016,9 +1013,11 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 		kunmap_atomic(paddr, KM_USER0);
 		if (b) {
 			/* if the disk bit is set, set the memory bit */
-			bitmap_set_memory_bits(bitmap, i << CHUNK_BLOCK_SHIFT(bitmap),
-					       ((i+1) << (CHUNK_BLOCK_SHIFT(bitmap)) >= start)
-				);
+			int needed = ((sector_t)(i+1) << (CHUNK_BLOCK_SHIFT(bitmap))
+				      >= start);
+			bitmap_set_memory_bits(bitmap,
+					       (sector_t)i << CHUNK_BLOCK_SHIFT(bitmap),
+					       needed);
 			bit_cnt++;
 			set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
 		}
@@ -1154,8 +1153,9 @@ void bitmap_daemon_work(struct bitmap *bitmap)
 			spin_lock_irqsave(&bitmap->lock, flags);
 			clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
 		}
-		bmc = bitmap_get_counter(bitmap, j << CHUNK_BLOCK_SHIFT(bitmap),
-					&blocks, 0);
+		bmc = bitmap_get_counter(bitmap,
+					 (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap),
+					 &blocks, 0);
 		if (bmc) {
 /*
   if (j < 100) printk("bitmap: j=%lu, *bmc = 0x%x\n", j, *bmc);
@@ -1169,7 +1169,8 @@ void bitmap_daemon_work(struct bitmap *bitmap)
 			} else if (*bmc == 1) {
 				/* we can clear the bit */
 				*bmc = 0;
-				bitmap_count_page(bitmap, j << CHUNK_BLOCK_SHIFT(bitmap),
+				bitmap_count_page(bitmap,
+						  (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap),
 						  -1);
 
 				/* clear the bit */
@@ -1514,7 +1515,7 @@ void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e)
 	unsigned long chunk;
 
 	for (chunk = s; chunk <= e; chunk++) {
-		sector_t sec = chunk << CHUNK_BLOCK_SHIFT(bitmap);
+		sector_t sec = (sector_t)chunk << CHUNK_BLOCK_SHIFT(bitmap);
 		bitmap_set_memory_bits(bitmap, sec, 1);
 		bitmap_file_set_bit(bitmap, sec);
 	}

drivers/md/md.c

@@ -3066,11 +3066,8 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
 			} else
 				err = -EBUSY;
 			spin_unlock_irq(&mddev->write_lock);
-		} else {
-			mddev->ro = 0;
-			mddev->recovery_cp = MaxSector;
-			err = do_md_run(mddev);
-		}
+		} else
+			err = -EINVAL;
 		break;
 	case active:
 		if (mddev->pers) {
@@ -4297,6 +4294,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 {
 	int err = 0;
 	struct gendisk *disk = mddev->gendisk;
+	mdk_rdev_t *rdev;
 
 	if (atomic_read(&mddev->openers) > is_open) {
 		printk("md: %s still in use.\n",mdname(mddev));
@@ -4339,6 +4337,13 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 			/* tell userspace to handle 'inactive' */
 			sysfs_notify_dirent(mddev->sysfs_state);
 
+			list_for_each_entry(rdev, &mddev->disks, same_set)
+				if (rdev->raid_disk >= 0) {
+					char nm[20];
+					sprintf(nm, "rd%d", rdev->raid_disk);
+					sysfs_remove_link(&mddev->kobj, nm);
+				}
+
 			set_capacity(disk, 0);
 			mddev->changed = 1;
 
@@ -4359,7 +4364,6 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 	 * Free resources if final stop
 	 */
 	if (mode == 0) {
-		mdk_rdev_t *rdev;
 
 		printk(KERN_INFO "md: %s stopped.\n", mdname(mddev));
 
@@ -4371,13 +4375,6 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 		}
 		mddev->bitmap_offset = 0;
 
-		list_for_each_entry(rdev, &mddev->disks, same_set)
-			if (rdev->raid_disk >= 0) {
-				char nm[20];
-				sprintf(nm, "rd%d", rdev->raid_disk);
-				sysfs_remove_link(&mddev->kobj, nm);
-			}
-
 		/* make sure all md_delayed_delete calls have finished */
 		flush_scheduled_work();
 
@@ -5705,37 +5702,38 @@ static void status_unused(struct seq_file *seq)
 
 static void status_resync(struct seq_file *seq, mddev_t * mddev)
 {
-	sector_t max_blocks, resync, res;
-	unsigned long dt, db, rt;
+	sector_t max_sectors, resync, res;
+	unsigned long dt, db;
+	sector_t rt;
 	int scale;
 	unsigned int per_milli;
 
-	resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active))/2;
+	resync = mddev->curr_resync - atomic_read(&mddev->recovery_active);
 
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
-		max_blocks = mddev->resync_max_sectors >> 1;
+		max_sectors = mddev->resync_max_sectors;
 	else
-		max_blocks = mddev->dev_sectors / 2;
+		max_sectors = mddev->dev_sectors;
 
 	/*
 	 * Should not happen.
 	 */
-	if (!max_blocks) {
+	if (!max_sectors) {
 		MD_BUG();
 		return;
 	}
 	/* Pick 'scale' such that (resync>>scale)*1000 will fit
-	 * in a sector_t, and (max_blocks>>scale) will fit in a
+	 * in a sector_t, and (max_sectors>>scale) will fit in a
 	 * u32, as those are the requirements for sector_div.
 	 * Thus 'scale' must be at least 10
 	 */
 	scale = 10;
 	if (sizeof(sector_t) > sizeof(unsigned long)) {
-		while ( max_blocks/2 > (1ULL<<(scale+32)))
+		while ( max_sectors/2 > (1ULL<<(scale+32)))
 			scale++;
 	}
 	res = (resync>>scale)*1000;
-	sector_div(res, (u32)((max_blocks>>scale)+1));
+	sector_div(res, (u32)((max_sectors>>scale)+1));
 
 	per_milli = res;
 	{
@@ -5756,25 +5754,35 @@ static void status_resync(struct seq_file *seq, mddev_t * mddev)
 		     (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ?
 		      "resync" : "recovery"))),
 		   per_milli/10, per_milli % 10,
-		   (unsigned long long) resync,
-		   (unsigned long long) max_blocks);
+		   (unsigned long long) resync/2,
+		   (unsigned long long) max_sectors/2);
 
 	/*
-	 * We do not want to overflow, so the order of operands and
-	 * the * 100 / 100 trick are important. We do a +1 to be
-	 * safe against division by zero. We only estimate anyway.
-	 *
 	 * dt: time from mark until now
 	 * db: blocks written from mark until now
 	 * rt: remaining time
+	 *
+	 * rt is a sector_t, so could be 32bit or 64bit.
+	 * So we divide before multiply in case it is 32bit and close
+	 * to the limit.
+	 * We scale the divisor (db) by 32 to avoid loosing precision
+	 * near the end of resync when the number of remaining sectors
+	 * is close to 'db'.
+	 * We then divide rt by 32 after multiplying by db to compensate.
+	 * The '+1' avoids division by zero if db is very small.
 	 */
 	dt = ((jiffies - mddev->resync_mark) / HZ);
 	if (!dt) dt++;
 	db = (mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active))
 		- mddev->resync_mark_cnt;
-	rt = (dt * ((unsigned long)(max_blocks-resync) / (db/2/100+1)))/100;
 
-	seq_printf(seq, " finish=%lu.%lumin", rt / 60, (rt % 60)/6);
+	rt = max_sectors - resync;    /* number of remaining sectors */
+	sector_div(rt, db/32+1);
+	rt *= dt;
+	rt >>= 5;
+
+	seq_printf(seq, " finish=%lu.%lumin", (unsigned long)rt / 60,
+		   ((unsigned long)rt % 60)/6);
 
 	seq_printf(seq, " speed=%ldK/sec", db/2/dt);
 }
@@ -5965,7 +5973,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static struct seq_operations md_seq_ops = {
+static const struct seq_operations md_seq_ops = {
 	.start  = md_seq_start,
 	.next   = md_seq_next,
 	.stop   = md_seq_stop,

drivers/md/raid10.c

@@ -1809,17 +1809,17 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 				r10_bio->sector = sect;
 
 				raid10_find_phys(conf, r10_bio);
-				/* Need to check if this section will still be
+
+				/* Need to check if the array will still be
 				 * degraded
 				 */
-				for (j=0; j<conf->copies;j++) {
-					int d = r10_bio->devs[j].devnum;
-					if (conf->mirrors[d].rdev == NULL ||
-					    test_bit(Faulty, &conf->mirrors[d].rdev->flags)) {
+				for (j=0; j<conf->raid_disks; j++)
+					if (conf->mirrors[j].rdev == NULL ||
+					    test_bit(Faulty, &conf->mirrors[j].rdev->flags)) {
 						still_degraded = 1;
 						break;
 					}
-				}
+
 				must_sync = bitmap_start_sync(mddev->bitmap, sect,
 							      &sync_blocks, still_degraded);