Merge branch 'for-3.17/drivers' of git://git.kernel.dk/linux-block

Pull block driver changes from Jens Axboe:
 "Nothing out of the ordinary here, this pull request contains:

   - A big round of fixes for bcache from Kent Overstreet, Slava Pestov,
     and Surbhi Palande.  No new features, just a lot of fixes.

   - The usual round of drbd updates from Andreas Gruenbacher, Lars
     Ellenberg, and Philipp Reisner.

   - virtio_blk was converted to blk-mq back in 3.13, but now Ming Lei
     has taken it one step further and added support for actually using
     more than one queue.

   - Addition of an explicit SG_FLAG_Q_AT_HEAD for block/bsg, to
     compliment the the default behavior of adding to the tail of the
     queue.  From Douglas Gilbert"

* 'for-3.17/drivers' of git://git.kernel.dk/linux-block: (86 commits)
  bcache: Drop unneeded blk_sync_queue() calls
  bcache: add mutex lock for bch_is_open
  bcache: Correct printing of btree_gc_max_duration_ms
  bcache: try to set b->parent properly
  bcache: fix memory corruption in init error path
  bcache: fix crash with incomplete cache set
  bcache: Fix more early shutdown bugs
  bcache: fix use-after-free in btree_gc_coalesce()
  bcache: Fix an infinite loop in journal replay
  bcache: fix crash in bcache_btree_node_alloc_fail tracepoint
  bcache: bcache_write tracepoint was crashing
  bcache: fix typo in bch_bkey_equal_header
  bcache: Allocate bounce buffers with GFP_NOWAIT
  bcache: Make sure to pass GFP_WAIT to mempool_alloc()
  bcache: fix uninterruptible sleep in writeback thread
  bcache: wait for buckets when allocating new btree root
  bcache: fix crash on shutdown in passthrough mode
  bcache: fix lockdep warnings on shutdown
  bcache allocator: send discards with correct size
  bcache: Fix to remove the rcu_sched stalls.
  ...

block/scsi_ioctl.c

@@ -290,6 +290,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	unsigned long start_time;
 	ssize_t ret = 0;
 	int writing = 0;
+	int at_head = 0;
 	struct request *rq;
 	char sense[SCSI_SENSE_BUFFERSIZE];
 	struct bio *bio;
@@ -313,6 +314,8 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		case SG_DXFER_FROM_DEV:
 			break;
 		}
+	if (hdr->flags & SG_FLAG_Q_AT_HEAD)
+		at_head = 1;
 
 	rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
 	if (!rq)
@@ -369,7 +372,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	 * (if he doesn't check that is his problem).
 	 * N.B. a non-zero SCSI status is _not_ necessarily an error.
 	 */
-	blk_execute_rq(q, bd_disk, rq, 0);
+	blk_execute_rq(q, bd_disk, rq, at_head);
 
 	hdr->duration = jiffies_to_msecs(jiffies - start_time);
 

drivers/block/drbd/Makefile

@@ -3,5 +3,6 @@ drbd-y += drbd_worker.o drbd_receiver.o drbd_req.o drbd_actlog.o
 drbd-y += drbd_main.o drbd_strings.o drbd_nl.o
 drbd-y += drbd_interval.o drbd_state.o
 drbd-y += drbd_nla.o
+drbd-$(CONFIG_DEBUG_FS) += drbd_debugfs.o
 
 obj-$(CONFIG_BLK_DEV_DRBD)     += drbd.o

drivers/block/drbd/drbd_bitmap.c

@@ -22,6 +22,8 @@
    the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
 #include <linux/bitops.h>
 #include <linux/vmalloc.h>
 #include <linux/string.h>
@@ -353,9 +355,8 @@ static void bm_free_pages(struct page **pages, unsigned long number)
 
 	for (i = 0; i < number; i++) {
 		if (!pages[i]) {
-			printk(KERN_ALERT "drbd: bm_free_pages tried to free "
-					  "a NULL pointer; i=%lu n=%lu\n",
-					  i, number);
+			pr_alert("bm_free_pages tried to free a NULL pointer; i=%lu n=%lu\n",
+				 i, number);
 			continue;
 		}
 		__free_page(pages[i]);
@@ -592,7 +593,7 @@ static void bm_memset(struct drbd_bitmap *b, size_t offset, int c, size_t len)
 	end = offset + len;
 
 	if (end > b->bm_words) {
-		printk(KERN_ALERT "drbd: bm_memset end > bm_words\n");
+		pr_alert("bm_memset end > bm_words\n");
 		return;
 	}
 
@@ -602,7 +603,7 @@ static void bm_memset(struct drbd_bitmap *b, size_t offset, int c, size_t len)
 		p_addr = bm_map_pidx(b, idx);
 		bm = p_addr + MLPP(offset);
 		if (bm+do_now > p_addr + LWPP) {
-			printk(KERN_ALERT "drbd: BUG BUG BUG! p_addr:%p bm:%p do_now:%d\n",
+			pr_alert("BUG BUG BUG! p_addr:%p bm:%p do_now:%d\n",
 			       p_addr, bm, (int)do_now);
 		} else
 			memset(bm, c, do_now * sizeof(long));
@@ -927,22 +928,14 @@ void drbd_bm_clear_all(struct drbd_device *device)
 	spin_unlock_irq(&b->bm_lock);
 }
 
-struct bm_aio_ctx {
-	struct drbd_device *device;
-	atomic_t in_flight;
-	unsigned int done;
-	unsigned flags;
-#define BM_AIO_COPY_PAGES	1
-#define BM_AIO_WRITE_HINTED	2
-#define BM_WRITE_ALL_PAGES	4
-	int error;
-	struct kref kref;
-};
-
-static void bm_aio_ctx_destroy(struct kref *kref)
+static void drbd_bm_aio_ctx_destroy(struct kref *kref)
 {
-	struct bm_aio_ctx *ctx = container_of(kref, struct bm_aio_ctx, kref);
+	struct drbd_bm_aio_ctx *ctx = container_of(kref, struct drbd_bm_aio_ctx, kref);
+	unsigned long flags;
 
+	spin_lock_irqsave(&ctx->device->resource->req_lock, flags);
+	list_del(&ctx->list);
+	spin_unlock_irqrestore(&ctx->device->resource->req_lock, flags);
 	put_ldev(ctx->device);
 	kfree(ctx);
 }
@@ -950,7 +943,7 @@ static void bm_aio_ctx_destroy(struct kref *kref)
 /* bv_page may be a copy, or may be the original */
 static void bm_async_io_complete(struct bio *bio, int error)
 {
-	struct bm_aio_ctx *ctx = bio->bi_private;
+	struct drbd_bm_aio_ctx *ctx = bio->bi_private;
 	struct drbd_device *device = ctx->device;
 	struct drbd_bitmap *b = device->bitmap;
 	unsigned int idx = bm_page_to_idx(bio->bi_io_vec[0].bv_page);
@@ -993,17 +986,18 @@ static void bm_async_io_complete(struct bio *bio, int error)
 	if (atomic_dec_and_test(&ctx->in_flight)) {
 		ctx->done = 1;
 		wake_up(&device->misc_wait);
-		kref_put(&ctx->kref, &bm_aio_ctx_destroy);
+		kref_put(&ctx->kref, &drbd_bm_aio_ctx_destroy);
 	}
 }
 
-static void bm_page_io_async(struct bm_aio_ctx *ctx, int page_nr, int rw) __must_hold(local)
+static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_hold(local)
 {
 	struct bio *bio = bio_alloc_drbd(GFP_NOIO);
 	struct drbd_device *device = ctx->device;
 	struct drbd_bitmap *b = device->bitmap;
 	struct page *page;
 	unsigned int len;
+	unsigned int rw = (ctx->flags & BM_AIO_READ) ? READ : WRITE;
 
 	sector_t on_disk_sector =
 		device->ldev->md.md_offset + device->ldev->md.bm_offset;
@@ -1049,9 +1043,9 @@ static void bm_page_io_async(struct bm_aio_ctx *ctx, int page_nr, int rw) __must
 /*
  * bm_rw: read/write the whole bitmap from/to its on disk location.
  */
-static int bm_rw(struct drbd_device *device, int rw, unsigned flags, unsigned lazy_writeout_upper_idx) __must_hold(local)
+static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned lazy_writeout_upper_idx) __must_hold(local)
 {
-	struct bm_aio_ctx *ctx;
+	struct drbd_bm_aio_ctx *ctx;
 	struct drbd_bitmap *b = device->bitmap;
 	int num_pages, i, count = 0;
 	unsigned long now;
@@ -1067,12 +1061,13 @@ static int bm_rw(struct drbd_device *device, int rw, unsigned flags, unsigned la
 	 * as we submit copies of pages anyways.
 	 */
 
-	ctx = kmalloc(sizeof(struct bm_aio_ctx), GFP_NOIO);
+	ctx = kmalloc(sizeof(struct drbd_bm_aio_ctx), GFP_NOIO);
 	if (!ctx)
 		return -ENOMEM;
 
-	*ctx = (struct bm_aio_ctx) {
+	*ctx = (struct drbd_bm_aio_ctx) {
 		.device = device,
+		.start_jif = jiffies,
 		.in_flight = ATOMIC_INIT(1),
 		.done = 0,
 		.flags = flags,
@@ -1080,15 +1075,21 @@ static int bm_rw(struct drbd_device *device, int rw, unsigned flags, unsigned la
 		.kref = { ATOMIC_INIT(2) },
 	};
 
-	if (!get_ldev_if_state(device, D_ATTACHING)) {  /* put is in bm_aio_ctx_destroy() */
+	if (!get_ldev_if_state(device, D_ATTACHING)) {  /* put is in drbd_bm_aio_ctx_destroy() */
 		drbd_err(device, "ASSERT FAILED: get_ldev_if_state() == 1 in bm_rw()\n");
 		kfree(ctx);
 		return -ENODEV;
 	}
+	/* Here D_ATTACHING is sufficient since drbd_bm_read() is called only from
+	   drbd_adm_attach(), after device->ldev was assigned. */
 
-	if (!ctx->flags)
+	if (0 == (ctx->flags & ~BM_AIO_READ))
 		WARN_ON(!(BM_LOCKED_MASK & b->bm_flags));
 
+	spin_lock_irq(&device->resource->req_lock);
+	list_add_tail(&ctx->list, &device->pending_bitmap_io);
+	spin_unlock_irq(&device->resource->req_lock);
+
 	num_pages = b->bm_number_of_pages;
 
 	now = jiffies;
@@ -1098,13 +1099,13 @@ static int bm_rw(struct drbd_device *device, int rw, unsigned flags, unsigned la
 		/* ignore completely unchanged pages */
 		if (lazy_writeout_upper_idx && i == lazy_writeout_upper_idx)
 			break;
-		if (rw & WRITE) {
+		if (!(flags & BM_AIO_READ)) {
 			if ((flags & BM_AIO_WRITE_HINTED) &&
 			    !test_and_clear_bit(BM_PAGE_HINT_WRITEOUT,
 				    &page_private(b->bm_pages[i])))
 				continue;
 
-			if (!(flags & BM_WRITE_ALL_PAGES) &&
+			if (!(flags & BM_AIO_WRITE_ALL_PAGES) &&
 			    bm_test_page_unchanged(b->bm_pages[i])) {
 				dynamic_drbd_dbg(device, "skipped bm write for idx %u\n", i);
 				continue;
@@ -1118,7 +1119,7 @@ static int bm_rw(struct drbd_device *device, int rw, unsigned flags, unsigned la
 			}
 		}
 		atomic_inc(&ctx->in_flight);
-		bm_page_io_async(ctx, i, rw);
+		bm_page_io_async(ctx, i);
 		++count;
 		cond_resched();
 	}
@@ -1134,12 +1135,12 @@ static int bm_rw(struct drbd_device *device, int rw, unsigned flags, unsigned la
 	if (!atomic_dec_and_test(&ctx->in_flight))
 		wait_until_done_or_force_detached(device, device->ldev, &ctx->done);
 	else
-		kref_put(&ctx->kref, &bm_aio_ctx_destroy);
+		kref_put(&ctx->kref, &drbd_bm_aio_ctx_destroy);
 
 	/* summary for global bitmap IO */
 	if (flags == 0)
 		drbd_info(device, "bitmap %s of %u pages took %lu jiffies\n",
-			 rw == WRITE ? "WRITE" : "READ",
+			 (flags & BM_AIO_READ) ? "READ" : "WRITE",
 			 count, jiffies - now);
 
 	if (ctx->error) {
@@ -1152,20 +1153,18 @@ static int bm_rw(struct drbd_device *device, int rw, unsigned flags, unsigned la
 		err = -EIO; /* Disk timeout/force-detach during IO... */
 
 	now = jiffies;
-	if (rw == WRITE) {
-		drbd_md_flush(device);
-	} else /* rw == READ */ {
+	if (flags & BM_AIO_READ) {
 		b->bm_set = bm_count_bits(b);
 		drbd_info(device, "recounting of set bits took additional %lu jiffies\n",
 		     jiffies - now);
 	}
 	now = b->bm_set;
 
-	if (flags == 0)
+	if ((flags & ~BM_AIO_READ) == 0)
 		drbd_info(device, "%s (%lu bits) marked out-of-sync by on disk bit-map.\n",
 		     ppsize(ppb, now << (BM_BLOCK_SHIFT-10)), now);
 
-	kref_put(&ctx->kref, &bm_aio_ctx_destroy);
+	kref_put(&ctx->kref, &drbd_bm_aio_ctx_destroy);
 	return err;
 }
 
@@ -1175,7 +1174,7 @@ static int bm_rw(struct drbd_device *device, int rw, unsigned flags, unsigned la
  */
 int drbd_bm_read(struct drbd_device *device) __must_hold(local)
 {
-	return bm_rw(device, READ, 0, 0);
+	return bm_rw(device, BM_AIO_READ, 0);
 }
 
 /**
@@ -1186,7 +1185,7 @@ int drbd_bm_read(struct drbd_device *device) __must_hold(local)
  */
 int drbd_bm_write(struct drbd_device *device) __must_hold(local)
 {
-	return bm_rw(device, WRITE, 0, 0);
+	return bm_rw(device, 0, 0);
 }
 
 /**
@@ -1197,7 +1196,17 @@ int drbd_bm_write(struct drbd_device *device) __must_hold(local)
  */
 int drbd_bm_write_all(struct drbd_device *device) __must_hold(local)
 {
-	return bm_rw(device, WRITE, BM_WRITE_ALL_PAGES, 0);
+	return bm_rw(device, BM_AIO_WRITE_ALL_PAGES, 0);
+}
+
+/**
+ * drbd_bm_write_lazy() - Write bitmap pages 0 to @upper_idx-1, if they have changed.
+ * @device:	DRBD device.
+ * @upper_idx:	0: write all changed pages; +ve: page index to stop scanning for changed pages
+ */
+int drbd_bm_write_lazy(struct drbd_device *device, unsigned upper_idx) __must_hold(local)
+{
+	return bm_rw(device, BM_AIO_COPY_PAGES, upper_idx);
 }
 
 /**
@@ -1213,7 +1222,7 @@ int drbd_bm_write_all(struct drbd_device *device) __must_hold(local)
  */
 int drbd_bm_write_copy_pages(struct drbd_device *device) __must_hold(local)
 {
-	return bm_rw(device, WRITE, BM_AIO_COPY_PAGES, 0);
+	return bm_rw(device, BM_AIO_COPY_PAGES, 0);
 }
 
 /**
@@ -1222,62 +1231,7 @@ int drbd_bm_write_copy_pages(struct drbd_device *device) __must_hold(local)
  */
 int drbd_bm_write_hinted(struct drbd_device *device) __must_hold(local)
 {
-	return bm_rw(device, WRITE, BM_AIO_WRITE_HINTED | BM_AIO_COPY_PAGES, 0);
-}
-
-/**
- * drbd_bm_write_page() - Writes a PAGE_SIZE aligned piece of bitmap
- * @device:	DRBD device.
- * @idx:	bitmap page index
- *
- * We don't want to special case on logical_block_size of the backend device,
- * so we submit PAGE_SIZE aligned pieces.
- * Note that on "most" systems, PAGE_SIZE is 4k.
- *
- * In case this becomes an issue on systems with larger PAGE_SIZE,
- * we may want to change this again to write 4k aligned 4k pieces.
- */
-int drbd_bm_write_page(struct drbd_device *device, unsigned int idx) __must_hold(local)
-{
-	struct bm_aio_ctx *ctx;
-	int err;
-
-	if (bm_test_page_unchanged(device->bitmap->bm_pages[idx])) {
-		dynamic_drbd_dbg(device, "skipped bm page write for idx %u\n", idx);
-		return 0;
-	}
-
-	ctx = kmalloc(sizeof(struct bm_aio_ctx), GFP_NOIO);
-	if (!ctx)
-		return -ENOMEM;
-
-	*ctx = (struct bm_aio_ctx) {
-		.device = device,
-		.in_flight = ATOMIC_INIT(1),
-		.done = 0,
-		.flags = BM_AIO_COPY_PAGES,
-		.error = 0,
-		.kref = { ATOMIC_INIT(2) },
-	};
-
-	if (!get_ldev_if_state(device, D_ATTACHING)) {  /* put is in bm_aio_ctx_destroy() */
-		drbd_err(device, "ASSERT FAILED: get_ldev_if_state() == 1 in drbd_bm_write_page()\n");
-		kfree(ctx);
-		return -ENODEV;
-	}
-
-	bm_page_io_async(ctx, idx, WRITE_SYNC);
-	wait_until_done_or_force_detached(device, device->ldev, &ctx->done);
-
-	if (ctx->error)
-		drbd_chk_io_error(device, 1, DRBD_META_IO_ERROR);
-		/* that causes us to detach, so the in memory bitmap will be
-		 * gone in a moment as well. */
-
-	device->bm_writ_cnt++;
-	err = atomic_read(&ctx->in_flight) ? -EIO : ctx->error;
-	kref_put(&ctx->kref, &bm_aio_ctx_destroy);
-	return err;
+	return bm_rw(device, BM_AIO_WRITE_HINTED | BM_AIO_COPY_PAGES, 0);
 }
 
 /* NOTE

drivers/block/drbd/drbd_debugfs.h

+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/debugfs.h>
+
+#include "drbd_int.h"
+
+#ifdef CONFIG_DEBUG_FS
+int __init drbd_debugfs_init(void);
+void drbd_debugfs_cleanup(void);
+
+void drbd_debugfs_resource_add(struct drbd_resource *resource);
+void drbd_debugfs_resource_cleanup(struct drbd_resource *resource);
+
+void drbd_debugfs_connection_add(struct drbd_connection *connection);
+void drbd_debugfs_connection_cleanup(struct drbd_connection *connection);
+
+void drbd_debugfs_device_add(struct drbd_device *device);
+void drbd_debugfs_device_cleanup(struct drbd_device *device);
+
+void drbd_debugfs_peer_device_add(struct drbd_peer_device *peer_device);
+void drbd_debugfs_peer_device_cleanup(struct drbd_peer_device *peer_device);
+#else
+
+static inline int __init drbd_debugfs_init(void) { return -ENODEV; }
+static inline void drbd_debugfs_cleanup(void) { }
+
+static inline void drbd_debugfs_resource_add(struct drbd_resource *resource) { }
+static inline void drbd_debugfs_resource_cleanup(struct drbd_resource *resource) { }
+
+static inline void drbd_debugfs_connection_add(struct drbd_connection *connection) { }
+static inline void drbd_debugfs_connection_cleanup(struct drbd_connection *connection) { }
+
+static inline void drbd_debugfs_device_add(struct drbd_device *device) { }
+static inline void drbd_debugfs_device_cleanup(struct drbd_device *device) { }
+
+static inline void drbd_debugfs_peer_device_add(struct drbd_peer_device *peer_device) { }
+static inline void drbd_debugfs_peer_device_cleanup(struct drbd_peer_device *peer_device) { }
+
+#endif

drivers/block/drbd/drbd_interval.h

@@ -10,7 +10,9 @@ struct drbd_interval {
 	unsigned int size;	/* size in bytes */
 	sector_t end;		/* highest interval end in subtree */
 	int local:1		/* local or remote request? */;
-	int waiting:1;
+	int waiting:1;		/* someone is waiting for this to complete */
+	int completed:1;	/* this has been completed already;
+				 * ignore for conflict detection */
 };
 
 static inline void drbd_clear_interval(struct drbd_interval *i)

drivers/block/drbd/drbd_nl.c

@@ -23,6 +23,8 @@
 
  */
 
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/drbd.h>
 #include <linux/in.h>
@@ -85,7 +87,7 @@ static void drbd_adm_send_reply(struct sk_buff *skb, struct genl_info *info)
 {
 	genlmsg_end(skb, genlmsg_data(nlmsg_data(nlmsg_hdr(skb))));
 	if (genlmsg_reply(skb, info))
-		printk(KERN_ERR "drbd: error sending genl reply\n");
+		pr_err("error sending genl reply\n");
 }
 
 /* Used on a fresh "drbd_adm_prepare"d reply_skb, this cannot fail: The only
@@ -558,8 +560,10 @@ void conn_try_outdate_peer_async(struct drbd_connection *connection)
 }
 
 enum drbd_state_rv
-drbd_set_role(struct drbd_device *device, enum drbd_role new_role, int force)
+drbd_set_role(struct drbd_device *const device, enum drbd_role new_role, int force)
 {
+	struct drbd_peer_device *const peer_device = first_peer_device(device);
+	struct drbd_connection *const connection = peer_device ? peer_device->connection : NULL;
 	const int max_tries = 4;
 	enum drbd_state_rv rv = SS_UNKNOWN_ERROR;
 	struct net_conf *nc;
@@ -607,7 +611,7 @@ drbd_set_role(struct drbd_device *device, enum drbd_role new_role, int force)
 		    device->state.disk == D_CONSISTENT && mask.pdsk == 0) {
 			D_ASSERT(device, device->state.pdsk == D_UNKNOWN);
 
-			if (conn_try_outdate_peer(first_peer_device(device)->connection)) {
+			if (conn_try_outdate_peer(connection)) {
 				val.disk = D_UP_TO_DATE;
 				mask.disk = D_MASK;
 			}
@@ -617,7 +621,7 @@ drbd_set_role(struct drbd_device *device, enum drbd_role new_role, int force)
 		if (rv == SS_NOTHING_TO_DO)
 			goto out;
 		if (rv == SS_PRIMARY_NOP && mask.pdsk == 0) {
-			if (!conn_try_outdate_peer(first_peer_device(device)->connection) && force) {
+			if (!conn_try_outdate_peer(connection) && force) {
 				drbd_warn(device, "Forced into split brain situation!\n");
 				mask.pdsk = D_MASK;
 				val.pdsk  = D_OUTDATED;
@@ -630,7 +634,7 @@ drbd_set_role(struct drbd_device *device, enum drbd_role new_role, int force)
 			   retry at most once more in this case. */
 			int timeo;
 			rcu_read_lock();
-			nc = rcu_dereference(first_peer_device(device)->connection->net_conf);
+			nc = rcu_dereference(connection->net_conf);
 			timeo = nc ? (nc->ping_timeo + 1) * HZ / 10 : 1;
 			rcu_read_unlock();
 			schedule_timeout_interruptible(timeo);
@@ -659,19 +663,17 @@ drbd_set_role(struct drbd_device *device, enum drbd_role new_role, int force)
 	/* FIXME also wait for all pending P_BARRIER_ACK? */
 
 	if (new_role == R_SECONDARY) {
-		set_disk_ro(device->vdisk, true);
 		if (get_ldev(device)) {
 			device->ldev->md.uuid[UI_CURRENT] &= ~(u64)1;
 			put_ldev(device);
 		}
 	} else {
-		/* Called from drbd_adm_set_role only.
-		 * We are still holding the conf_update mutex. */
-		nc = first_peer_device(device)->connection->net_conf;
+		mutex_lock(&device->resource->conf_update);
+		nc = connection->net_conf;
 		if (nc)
 			nc->discard_my_data = 0; /* without copy; single bit op is atomic */
+		mutex_unlock(&device->resource->conf_update);
 
-		set_disk_ro(device->vdisk, false);
 		if (get_ldev(device)) {
 			if (((device->state.conn < C_CONNECTED ||
 			       device->state.pdsk <= D_FAILED)
@@ -689,12 +691,12 @@ drbd_set_role(struct drbd_device *device, enum drbd_role new_role, int force)
 	if (device->state.conn >= C_WF_REPORT_PARAMS) {
 		/* if this was forced, we should consider sync */
 		if (forced)
-			drbd_send_uuids(first_peer_device(device));
-		drbd_send_current_state(first_peer_device(device));
+			drbd_send_uuids(peer_device);
+		drbd_send_current_state(peer_device);
 	}
 
 	drbd_md_sync(device);
-
+	set_disk_ro(device->vdisk, new_role == R_SECONDARY);
 	kobject_uevent(&disk_to_dev(device->vdisk)->kobj, KOBJ_CHANGE);
 out:
 	mutex_unlock(device->state_mutex);
@@ -891,7 +893,7 @@ drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct
 	 * still lock the act_log to not trigger ASSERTs there.
 	 */
 	drbd_suspend_io(device);
-	buffer = drbd_md_get_buffer(device); /* Lock meta-data IO */
+	buffer = drbd_md_get_buffer(device, __func__); /* Lock meta-data IO */
 	if (!buffer) {
 		drbd_resume_io(device);
 		return DS_ERROR;
@@ -971,6 +973,10 @@ drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct
 	if (la_size_changed || md_moved || rs) {
 		u32 prev_flags;
 
+		/* We do some synchronous IO below, which may take some time.
+		 * Clear the timer, to avoid scary "timer expired!" messages,
+		 * "Superblock" is written out at least twice below, anyways. */
+		del_timer(&device->md_sync_timer);
 		drbd_al_shrink(device); /* All extents inactive. */
 
 		prev_flags = md->flags;
@@ -1116,15 +1122,16 @@ static int drbd_check_al_size(struct drbd_device *device, struct disk_conf *dc)
 	return 0;
 }
 
-static void drbd_setup_queue_param(struct drbd_device *device, unsigned int max_bio_size)
+static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backing_dev *bdev,
+				   unsigned int max_bio_size)
 {
 	struct request_queue * const q = device->rq_queue;
 	unsigned int max_hw_sectors = max_bio_size >> 9;
 	unsigned int max_segments = 0;
 	struct request_queue *b = NULL;
 
-	if (get_ldev_if_state(device, D_ATTACHING)) {
-		b = device->ldev->backing_bdev->bd_disk->queue;
+	if (bdev) {
+		b = bdev->backing_bdev->bd_disk->queue;
 
 		max_hw_sectors = min(queue_max_hw_sectors(b), max_bio_size >> 9);
 		rcu_read_lock();
@@ -1169,11 +1176,10 @@ static void drbd_setup_queue_param(struct drbd_device *device, unsigned int max_
 				 b->backing_dev_info.ra_pages);
 			q->backing_dev_info.ra_pages = b->backing_dev_info.ra_pages;
 		}
-		put_ldev(device);
 	}
 }
 
-void drbd_reconsider_max_bio_size(struct drbd_device *device)
+void drbd_reconsider_max_bio_size(struct drbd_device *device, struct drbd_backing_dev *bdev)
 {
 	unsigned int now, new, local, peer;
 
@@ -1181,10 +1187,9 @@ void drbd_reconsider_max_bio_size(struct drbd_device *device)
 	local = device->local_max_bio_size; /* Eventually last known value, from volatile memory */
 	peer = device->peer_max_bio_size; /* Eventually last known value, from meta data */
 
-	if (get_ldev_if_state(device, D_ATTACHING)) {
-		local = queue_max_hw_sectors(device->ldev->backing_bdev->bd_disk->queue) << 9;
+	if (bdev) {
+		local = queue_max_hw_sectors(bdev->backing_bdev->bd_disk->queue) << 9;
 		device->local_max_bio_size = local;
-		put_ldev(device);
 	}
 	local = min(local, DRBD_MAX_BIO_SIZE);
 
@@ -1217,7 +1222,7 @@ void drbd_reconsider_max_bio_size(struct drbd_device *device)
 	if (new != now)
 		drbd_info(device, "max BIO size = %u\n", new);
 
-	drbd_setup_queue_param(device, new);
+	drbd_setup_queue_param(device, bdev, new);
 }
 
 /* Starts the worker thread */
@@ -1299,6 +1304,13 @@ static unsigned int drbd_al_extents_max(struct drbd_backing_dev *bdev)
 	return (al_size_4k - 1) * AL_CONTEXT_PER_TRANSACTION;
 }
 
+static bool write_ordering_changed(struct disk_conf *a, struct disk_conf *b)
+{
+	return	a->disk_barrier != b->disk_barrier ||
+		a->disk_flushes != b->disk_flushes ||
+		a->disk_drain != b->disk_drain;
+}
+
 int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
@@ -1405,7 +1417,8 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 	else
 		set_bit(MD_NO_FUA, &device->flags);
 
-	drbd_bump_write_ordering(first_peer_device(device)->connection, WO_bdev_flush);
+	if (write_ordering_changed(old_disk_conf, new_disk_conf))
+		drbd_bump_write_ordering(device->resource, NULL, WO_bdev_flush);
 
 	drbd_md_sync(device);
 
@@ -1440,6 +1453,8 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
 	struct drbd_device *device;
+	struct drbd_peer_device *peer_device;
+	struct drbd_connection *connection;
 	int err;
 	enum drbd_ret_code retcode;
 	enum determine_dev_size dd;
@@ -1462,7 +1477,9 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 
 	device = adm_ctx.device;
 	mutex_lock(&adm_ctx.resource->adm_mutex);
-	conn_reconfig_start(first_peer_device(device)->connection);
+	peer_device = first_peer_device(device);
+	connection = peer_device ? peer_device->connection : NULL;
+	conn_reconfig_start(connection);
 
 	/* if you want to reconfigure, please tear down first */
 	if (device->state.disk > D_DISKLESS) {
@@ -1473,7 +1490,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	 * drbd_ldev_destroy is done already, we may end up here very fast,
 	 * e.g. if someone calls attach from the on-io-error handler,
 	 * to realize a "hot spare" feature (not that I'd recommend that) */
-	wait_event(device->misc_wait, !atomic_read(&device->local_cnt));
+	wait_event(device->misc_wait, !test_bit(GOING_DISKLESS, &device->flags));
 
 	/* make sure there is no leftover from previous force-detach attempts */
 	clear_bit(FORCE_DETACH, &device->flags);
@@ -1529,7 +1546,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		goto fail;
 
 	rcu_read_lock();
-	nc = rcu_dereference(first_peer_device(device)->connection->net_conf);
+	nc = rcu_dereference(connection->net_conf);
 	if (nc) {
 		if (new_disk_conf->fencing == FP_STONITH && nc->wire_protocol == DRBD_PROT_A) {
 			rcu_read_unlock();
@@ -1649,7 +1666,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	 */
 	wait_event(device->misc_wait, !atomic_read(&device->ap_pending_cnt) || drbd_suspended(device));
 	/* and for any other previously queued work */
-	drbd_flush_workqueue(&first_peer_device(device)->connection->sender_work);
+	drbd_flush_workqueue(&connection->sender_work);
 
 	rv = _drbd_request_state(device, NS(disk, D_ATTACHING), CS_VERBOSE);
 	retcode = rv;  /* FIXME: Type mismatch. */
@@ -1710,7 +1727,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	new_disk_conf = NULL;
 	new_plan = NULL;
 
-	drbd_bump_write_ordering(first_peer_device(device)->connection, WO_bdev_flush);
+	drbd_bump_write_ordering(device->resource, device->ldev, WO_bdev_flush);
 
 	if (drbd_md_test_flag(device->ldev, MDF_CRASHED_PRIMARY))
 		set_bit(CRASHED_PRIMARY, &device->flags);
@@ -1726,7 +1743,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	device->read_cnt = 0;
 	device->writ_cnt = 0;
 
-	drbd_reconsider_max_bio_size(device);
+	drbd_reconsider_max_bio_size(device, device->ldev);
 
 	/* If I am currently not R_PRIMARY,
 	 * but meta data primary indicator is set,
@@ -1845,7 +1862,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 
 	kobject_uevent(&disk_to_dev(device->vdisk)->kobj, KOBJ_CHANGE);
 	put_ldev(device);
-	conn_reconfig_done(first_peer_device(device)->connection);
+	conn_reconfig_done(connection);
 	mutex_unlock(&adm_ctx.resource->adm_mutex);
 	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
@@ -1856,7 +1873,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	drbd_force_state(device, NS(disk, D_DISKLESS));
 	drbd_md_sync(device);
  fail:
-	conn_reconfig_done(first_peer_device(device)->connection);
+	conn_reconfig_done(connection);
 	if (nbc) {
 		if (nbc->backing_bdev)
 			blkdev_put(nbc->backing_bdev,
@@ -1888,7 +1905,7 @@ static int adm_detach(struct drbd_device *device, int force)
 	}
 
 	drbd_suspend_io(device); /* so no-one is stuck in drbd_al_begin_io */
-	drbd_md_get_buffer(device); /* make sure there is no in-flight meta-data IO */
+	drbd_md_get_buffer(device, __func__); /* make sure there is no in-flight meta-data IO */
 	retcode = drbd_request_state(device, NS(disk, D_FAILED));
 	drbd_md_put_buffer(device);
 	/* D_FAILED will transition to DISKLESS. */
@@ -2654,8 +2671,13 @@ int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info)
 	if (retcode != NO_ERROR)
 		goto out;
 
-	mutex_lock(&adm_ctx.resource->adm_mutex);
 	device = adm_ctx.device;
+	if (!get_ldev(device)) {
+		retcode = ERR_NO_DISK;
+		goto out;
+	}
+
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 
 	/* If there is still bitmap IO pending, probably because of a previous
 	 * resync just being finished, wait for it before requesting a new resync.
@@ -2679,6 +2701,7 @@ int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info)
 		retcode = drbd_request_state(device, NS(conn, C_STARTING_SYNC_T));
 	drbd_resume_io(device);
 	mutex_unlock(&adm_ctx.resource->adm_mutex);
+	put_ldev(device);
 out:
 	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
@@ -2704,7 +2727,7 @@ static int drbd_adm_simple_request_state(struct sk_buff *skb, struct genl_info *
 	return 0;
 }
 
-static int drbd_bmio_set_susp_al(struct drbd_device *device)
+static int drbd_bmio_set_susp_al(struct drbd_device *device) __must_hold(local)
 {
 	int rv;
 
@@ -2725,8 +2748,13 @@ int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info)
 	if (retcode != NO_ERROR)
 		goto out;
 
-	mutex_lock(&adm_ctx.resource->adm_mutex);
 	device = adm_ctx.device;
+	if (!get_ldev(device)) {
+		retcode = ERR_NO_DISK;
+		goto out;
+	}
+
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 
 	/* If there is still bitmap IO pending, probably because of a previous
 	 * resync just being finished, wait for it before requesting a new resync.
@@ -2753,6 +2781,7 @@ int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info)
 		retcode = drbd_request_state(device, NS(conn, C_STARTING_SYNC_S));
 	drbd_resume_io(device);
 	mutex_unlock(&adm_ctx.resource->adm_mutex);
+	put_ldev(device);
 out:
 	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
@@ -2892,7 +2921,7 @@ static struct drbd_connection *the_only_connection(struct drbd_resource *resourc
 	return list_first_entry(&resource->connections, struct drbd_connection, connections);
 }
 
-int nla_put_status_info(struct sk_buff *skb, struct drbd_device *device,
+static int nla_put_status_info(struct sk_buff *skb, struct drbd_device *device,
 		const struct sib_info *sib)
 {
 	struct drbd_resource *resource = device->resource;
@@ -3622,13 +3651,6 @@ void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib)
 	unsigned seq;
 	int err = -ENOMEM;
 
-	if (sib->sib_reason == SIB_SYNC_PROGRESS) {
-		if (time_after(jiffies, device->rs_last_bcast + HZ))
-			device->rs_last_bcast = jiffies;
-		else
-			return;
-	}
-
 	seq = atomic_inc_return(&drbd_genl_seq);
 	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_NOIO);
 	if (!msg)

drivers/block/drbd/drbd_proc.c

@@ -60,20 +60,65 @@ static void seq_printf_with_thousands_grouping(struct seq_file *seq, long v)
 		seq_printf(seq, "%ld", v);
 }
 
+static void drbd_get_syncer_progress(struct drbd_device *device,
+		union drbd_dev_state state, unsigned long *rs_total,
+		unsigned long *bits_left, unsigned int *per_mil_done)
+{
+	/* this is to break it at compile time when we change that, in case we
+	 * want to support more than (1<<32) bits on a 32bit arch. */
+	typecheck(unsigned long, device->rs_total);
+	*rs_total = device->rs_total;
+
+	/* note: both rs_total and rs_left are in bits, i.e. in
+	 * units of BM_BLOCK_SIZE.
+	 * for the percentage, we don't care. */
+
+	if (state.conn == C_VERIFY_S || state.conn == C_VERIFY_T)
+		*bits_left = device->ov_left;
+	else
+		*bits_left = drbd_bm_total_weight(device) - device->rs_failed;
+	/* >> 10 to prevent overflow,
+	 * +1 to prevent division by zero */
+	if (*bits_left > *rs_total) {
+		/* D'oh. Maybe a logic bug somewhere.  More likely just a race
+		 * between state change and reset of rs_total.
+		 */
+		*bits_left = *rs_total;
+		*per_mil_done = *rs_total ? 0 : 1000;
+	} else {
+		/* Make sure the division happens in long context.
+		 * We allow up to one petabyte storage right now,
+		 * at a granularity of 4k per bit that is 2**38 bits.
+		 * After shift right and multiplication by 1000,
+		 * this should still fit easily into a 32bit long,
+		 * so we don't need a 64bit division on 32bit arch.
+		 * Note: currently we don't support such large bitmaps on 32bit
+		 * arch anyways, but no harm done to be prepared for it here.
+		 */
+		unsigned int shift = *rs_total > UINT_MAX ? 16 : 10;
+		unsigned long left = *bits_left >> shift;
+		unsigned long total = 1UL + (*rs_total >> shift);
+		unsigned long tmp = 1000UL - left * 1000UL/total;
+		*per_mil_done = tmp;
+	}
+}
+
+
 /*lge
  * progress bars shamelessly adapted from driver/md/md.c
  * output looks like
  *	[=====>..............] 33.5% (23456/123456)
  *	finish: 2:20:20 speed: 6,345 (6,456) K/sec
  */
-static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *seq)
+static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *seq,
+		union drbd_dev_state state)
 {
-	unsigned long db, dt, dbdt, rt, rs_left;
+	unsigned long db, dt, dbdt, rt, rs_total, rs_left;
 	unsigned int res;
 	int i, x, y;
 	int stalled = 0;
 
-	drbd_get_syncer_progress(device, &rs_left, &res);
+	drbd_get_syncer_progress(device, state, &rs_total, &rs_left, &res);
 
 	x = res/50;
 	y = 20-x;
@@ -85,21 +130,21 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 		seq_printf(seq, ".");
 	seq_printf(seq, "] ");
 
-	if (device->state.conn == C_VERIFY_S || device->state.conn == C_VERIFY_T)
+	if (state.conn == C_VERIFY_S || state.conn == C_VERIFY_T)
 		seq_printf(seq, "verified:");
 	else
 		seq_printf(seq, "sync'ed:");
 	seq_printf(seq, "%3u.%u%% ", res / 10, res % 10);
 
 	/* if more than a few GB, display in MB */
-	if (device->rs_total > (4UL << (30 - BM_BLOCK_SHIFT)))
+	if (rs_total > (4UL << (30 - BM_BLOCK_SHIFT)))
 		seq_printf(seq, "(%lu/%lu)M",
 			    (unsigned long) Bit2KB(rs_left >> 10),
-			    (unsigned long) Bit2KB(device->rs_total >> 10));
+			    (unsigned long) Bit2KB(rs_total >> 10));
 	else
 		seq_printf(seq, "(%lu/%lu)K\n\t",
 			    (unsigned long) Bit2KB(rs_left),
-			    (unsigned long) Bit2KB(device->rs_total));
+			    (unsigned long) Bit2KB(rs_total));
 
 	/* see drivers/md/md.c
 	 * We do not want to overflow, so the order of operands and
@@ -150,13 +195,13 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 	dt = (jiffies - device->rs_start - device->rs_paused) / HZ;
 	if (dt == 0)
 		dt = 1;
-	db = device->rs_total - rs_left;
+	db = rs_total - rs_left;
 	dbdt = Bit2KB(db/dt);
 	seq_printf_with_thousands_grouping(seq, dbdt);
 	seq_printf(seq, ")");
 
-	if (device->state.conn == C_SYNC_TARGET ||
-	    device->state.conn == C_VERIFY_S) {
+	if (state.conn == C_SYNC_TARGET ||
+	    state.conn == C_VERIFY_S) {
 		seq_printf(seq, " want: ");
 		seq_printf_with_thousands_grouping(seq, device->c_sync_rate);
 	}
@@ -168,8 +213,8 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 		unsigned long bm_bits = drbd_bm_bits(device);
 		unsigned long bit_pos;
 		unsigned long long stop_sector = 0;
-		if (device->state.conn == C_VERIFY_S ||
-		    device->state.conn == C_VERIFY_T) {
+		if (state.conn == C_VERIFY_S ||
+		    state.conn == C_VERIFY_T) {
 			bit_pos = bm_bits - device->ov_left;
 			if (verify_can_do_stop_sector(device))
 				stop_sector = device->ov_stop_sector;
@@ -188,22 +233,13 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 	}
 }
 
-static void resync_dump_detail(struct seq_file *seq, struct lc_element *e)
-{
-	struct bm_extent *bme = lc_entry(e, struct bm_extent, lce);
-
-	seq_printf(seq, "%5d %s %s\n", bme->rs_left,
-		   bme->flags & BME_NO_WRITES ? "NO_WRITES" : "---------",
-		   bme->flags & BME_LOCKED ? "LOCKED" : "------"
-		   );
-}
-
 static int drbd_seq_show(struct seq_file *seq, void *v)
 {
 	int i, prev_i = -1;
 	const char *sn;
 	struct drbd_device *device;
 	struct net_conf *nc;
+	union drbd_dev_state state;
 	char wp;
 
 	static char write_ordering_chars[] = {
@@ -241,11 +277,12 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 			seq_printf(seq, "\n");
 		prev_i = i;
 
-		sn = drbd_conn_str(device->state.conn);
+		state = device->state;
+		sn = drbd_conn_str(state.conn);
 
-		if (device->state.conn == C_STANDALONE &&
-		    device->state.disk == D_DISKLESS &&
-		    device->state.role == R_SECONDARY) {
+		if (state.conn == C_STANDALONE &&
+		    state.disk == D_DISKLESS &&
+		    state.role == R_SECONDARY) {
 			seq_printf(seq, "%2d: cs:Unconfigured\n", i);
 		} else {
 			/* reset device->congestion_reason */
@@ -258,15 +295,15 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 			   "    ns:%u nr:%u dw:%u dr:%u al:%u bm:%u "
 			   "lo:%d pe:%d ua:%d ap:%d ep:%d wo:%c",
 			   i, sn,
-			   drbd_role_str(device->state.role),
-			   drbd_role_str(device->state.peer),
-			   drbd_disk_str(device->state.disk),
-			   drbd_disk_str(device->state.pdsk),
+			   drbd_role_str(state.role),
+			   drbd_role_str(state.peer),
+			   drbd_disk_str(state.disk),
+			   drbd_disk_str(state.pdsk),
 			   wp,
 			   drbd_suspended(device) ? 's' : 'r',
-			   device->state.aftr_isp ? 'a' : '-',
-			   device->state.peer_isp ? 'p' : '-',
-			   device->state.user_isp ? 'u' : '-',
+			   state.aftr_isp ? 'a' : '-',
+			   state.peer_isp ? 'p' : '-',
+			   state.user_isp ? 'u' : '-',
 			   device->congestion_reason ?: '-',
 			   test_bit(AL_SUSPENDED, &device->flags) ? 's' : '-',
 			   device->send_cnt/2,
@@ -281,17 +318,17 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 			   atomic_read(&device->unacked_cnt),
 			   atomic_read(&device->ap_bio_cnt),
 			   first_peer_device(device)->connection->epochs,
-			   write_ordering_chars[first_peer_device(device)->connection->write_ordering]
+			   write_ordering_chars[device->resource->write_ordering]
 			);
 			seq_printf(seq, " oos:%llu\n",
 				   Bit2KB((unsigned long long)
 					   drbd_bm_total_weight(device)));
 		}
-		if (device->state.conn == C_SYNC_SOURCE ||
-		    device->state.conn == C_SYNC_TARGET ||
-		    device->state.conn == C_VERIFY_S ||
-		    device->state.conn == C_VERIFY_T)
-			drbd_syncer_progress(device, seq);
+		if (state.conn == C_SYNC_SOURCE ||
+		    state.conn == C_SYNC_TARGET ||
+		    state.conn == C_VERIFY_S ||
+		    state.conn == C_VERIFY_T)
+			drbd_syncer_progress(device, seq, state);
 
 		if (proc_details >= 1 && get_ldev_if_state(device, D_FAILED)) {
 			lc_seq_printf_stats(seq, device->resync);
@@ -299,12 +336,8 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 			put_ldev(device);
 		}
 
-		if (proc_details >= 2) {
-			if (device->resync) {
-				lc_seq_dump_details(seq, device->resync, "rs_left",
-					resync_dump_detail);
-			}
-		}
+		if (proc_details >= 2)
+			seq_printf(seq, "\tblocked on activity log: %d\n", atomic_read(&device->ap_actlog_cnt));
 	}
 	rcu_read_unlock();
 
@@ -316,7 +349,7 @@ static int drbd_proc_open(struct inode *inode, struct file *file)
 	int err;
 
 	if (try_module_get(THIS_MODULE)) {
-		err = single_open(file, drbd_seq_show, PDE_DATA(inode));
+		err = single_open(file, drbd_seq_show, NULL);
 		if (err)
 			module_put(THIS_MODULE);
 		return err;

drivers/block/drbd/drbd_req.h

@@ -288,6 +288,7 @@ extern void complete_master_bio(struct drbd_device *device,
 extern void request_timer_fn(unsigned long data);
 extern void tl_restart(struct drbd_connection *connection, enum drbd_req_event what);
 extern void _tl_restart(struct drbd_connection *connection, enum drbd_req_event what);
+extern void tl_abort_disk_io(struct drbd_device *device);
 
 /* this is in drbd_main.c */
 extern void drbd_restart_request(struct drbd_request *req);

drivers/block/drbd/drbd_state.c

@@ -410,7 +410,7 @@ _drbd_request_state(struct drbd_device *device, union drbd_state mask,
 	return rv;
 }
 
-static void print_st(struct drbd_device *device, char *name, union drbd_state ns)
+static void print_st(struct drbd_device *device, const char *name, union drbd_state ns)
 {
 	drbd_err(device, " %s = { cs:%s ro:%s/%s ds:%s/%s %c%c%c%c%c%c }\n",
 	    name,
@@ -952,11 +952,12 @@ enum drbd_state_rv
 __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 	         enum chg_state_flags flags, struct completion *done)
 {
+	struct drbd_peer_device *peer_device = first_peer_device(device);
+	struct drbd_connection *connection = peer_device ? peer_device->connection : NULL;
 	union drbd_state os;
 	enum drbd_state_rv rv = SS_SUCCESS;
 	enum sanitize_state_warnings ssw;
 	struct after_state_chg_work *ascw;
-	bool did_remote, should_do_remote;
 
 	os = drbd_read_state(device);
 
@@ -978,9 +979,9 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 			   this happen...*/
 
 			if (is_valid_state(device, os) == rv)
-				rv = is_valid_soft_transition(os, ns, first_peer_device(device)->connection);
+				rv = is_valid_soft_transition(os, ns, connection);
 		} else
-			rv = is_valid_soft_transition(os, ns, first_peer_device(device)->connection);
+			rv = is_valid_soft_transition(os, ns, connection);
 	}
 
 	if (rv < SS_SUCCESS) {
@@ -997,7 +998,7 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 	   sanitize_state(). Only display it here if we where not called from
 	   _conn_request_state() */
 	if (!(flags & CS_DC_SUSP))
-		conn_pr_state_change(first_peer_device(device)->connection, os, ns,
+		conn_pr_state_change(connection, os, ns,
 				     (flags & ~CS_DC_MASK) | CS_DC_SUSP);
 
 	/* if we are going -> D_FAILED or D_DISKLESS, grab one extra reference
@@ -1008,28 +1009,35 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 	    (os.disk != D_DISKLESS && ns.disk == D_DISKLESS))
 		atomic_inc(&device->local_cnt);
 
-	did_remote = drbd_should_do_remote(device->state);
+	if (!is_sync_state(os.conn) && is_sync_state(ns.conn))
+		clear_bit(RS_DONE, &device->flags);
+
+	/* changes to local_cnt and device flags should be visible before
+	 * changes to state, which again should be visible before anything else
+	 * depending on that change happens. */
+	smp_wmb();
 	device->state.i = ns.i;
-	should_do_remote = drbd_should_do_remote(device->state);
 	device->resource->susp = ns.susp;
 	device->resource->susp_nod = ns.susp_nod;
 	device->resource->susp_fen = ns.susp_fen;
+	smp_wmb();
 
 	/* put replicated vs not-replicated requests in seperate epochs */
-	if (did_remote != should_do_remote)
-		start_new_tl_epoch(first_peer_device(device)->connection);
+	if (drbd_should_do_remote((union drbd_dev_state)os.i) !=
+	    drbd_should_do_remote((union drbd_dev_state)ns.i))
+		start_new_tl_epoch(connection);
 
 	if (os.disk == D_ATTACHING && ns.disk >= D_NEGOTIATING)
 		drbd_print_uuids(device, "attached to UUIDs");
 
 	/* Wake up role changes, that were delayed because of connection establishing */
 	if (os.conn == C_WF_REPORT_PARAMS && ns.conn != C_WF_REPORT_PARAMS &&
-	    no_peer_wf_report_params(first_peer_device(device)->connection))
-		clear_bit(STATE_SENT, &first_peer_device(device)->connection->flags);
+	    no_peer_wf_report_params(connection))
+		clear_bit(STATE_SENT, &connection->flags);
 
 	wake_up(&device->misc_wait);
 	wake_up(&device->state_wait);
-	wake_up(&first_peer_device(device)->connection->ping_wait);
+	wake_up(&connection->ping_wait);
 
 	/* Aborted verify run, or we reached the stop sector.
 	 * Log the last position, unless end-of-device. */
@@ -1118,21 +1126,21 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 
 	/* Receiver should clean up itself */
 	if (os.conn != C_DISCONNECTING && ns.conn == C_DISCONNECTING)
-		drbd_thread_stop_nowait(&first_peer_device(device)->connection->receiver);
+		drbd_thread_stop_nowait(&connection->receiver);
 
 	/* Now the receiver finished cleaning up itself, it should die */
 	if (os.conn != C_STANDALONE && ns.conn == C_STANDALONE)
-		drbd_thread_stop_nowait(&first_peer_device(device)->connection->receiver);
+		drbd_thread_stop_nowait(&connection->receiver);
 
 	/* Upon network failure, we need to restart the receiver. */
 	if (os.conn > C_WF_CONNECTION &&
 	    ns.conn <= C_TEAR_DOWN && ns.conn >= C_TIMEOUT)
-		drbd_thread_restart_nowait(&first_peer_device(device)->connection->receiver);
+		drbd_thread_restart_nowait(&connection->receiver);
 
 	/* Resume AL writing if we get a connection */
 	if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED) {
 		drbd_resume_al(device);
-		first_peer_device(device)->connection->connect_cnt++;
+		connection->connect_cnt++;
 	}
 
 	/* remember last attach time so request_timer_fn() won't
@@ -1150,7 +1158,7 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 		ascw->w.cb = w_after_state_ch;
 		ascw->device = device;
 		ascw->done = done;
-		drbd_queue_work(&first_peer_device(device)->connection->sender_work,
+		drbd_queue_work(&connection->sender_work,
 				&ascw->w);
 	} else {
 		drbd_err(device, "Could not kmalloc an ascw\n");
@@ -1222,13 +1230,16 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 			   union drbd_state ns, enum chg_state_flags flags)
 {
 	struct drbd_resource *resource = device->resource;
+	struct drbd_peer_device *peer_device = first_peer_device(device);
+	struct drbd_connection *connection = peer_device ? peer_device->connection : NULL;
 	struct sib_info sib;
 
 	sib.sib_reason = SIB_STATE_CHANGE;
 	sib.os = os;
 	sib.ns = ns;
 
-	if (os.conn != C_CONNECTED && ns.conn == C_CONNECTED) {
+	if ((os.disk != D_UP_TO_DATE || os.pdsk != D_UP_TO_DATE)
+	&&  (ns.disk == D_UP_TO_DATE && ns.pdsk == D_UP_TO_DATE)) {
 		clear_bit(CRASHED_PRIMARY, &device->flags);
 		if (device->p_uuid)
 			device->p_uuid[UI_FLAGS] &= ~((u64)2);
@@ -1245,7 +1256,6 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 	   state change. This function might sleep */
 
 	if (ns.susp_nod) {
-		struct drbd_connection *connection = first_peer_device(device)->connection;
 		enum drbd_req_event what = NOTHING;
 
 		spin_lock_irq(&device->resource->req_lock);
@@ -1267,8 +1277,6 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 	}
 
 	if (ns.susp_fen) {
-		struct drbd_connection *connection = first_peer_device(device)->connection;
-
 		spin_lock_irq(&device->resource->req_lock);
 		if (resource->susp_fen && conn_lowest_conn(connection) >= C_CONNECTED) {
 			/* case2: The connection was established again: */
@@ -1294,8 +1302,8 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 	 * which is unexpected. */
 	if ((os.conn != C_SYNC_SOURCE && os.conn != C_PAUSED_SYNC_S) &&
 	    (ns.conn == C_SYNC_SOURCE || ns.conn == C_PAUSED_SYNC_S) &&
-	    first_peer_device(device)->connection->agreed_pro_version >= 96 && get_ldev(device)) {
-		drbd_gen_and_send_sync_uuid(first_peer_device(device));
+	    connection->agreed_pro_version >= 96 && get_ldev(device)) {
+		drbd_gen_and_send_sync_uuid(peer_device);
 		put_ldev(device);
 	}
 
@@ -1309,8 +1317,8 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 		atomic_set(&device->rs_pending_cnt, 0);
 		drbd_rs_cancel_all(device);
 
-		drbd_send_uuids(first_peer_device(device));
-		drbd_send_state(first_peer_device(device), ns);
+		drbd_send_uuids(peer_device);
+		drbd_send_state(peer_device, ns);
 	}
 	/* No point in queuing send_bitmap if we don't have a connection
 	 * anymore, so check also the _current_ state, not only the new state
@@ -1335,7 +1343,7 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 					set_bit(NEW_CUR_UUID, &device->flags);
 				} else {
 					drbd_uuid_new_current(device);
-					drbd_send_uuids(first_peer_device(device));
+					drbd_send_uuids(peer_device);
 				}
 			}
 			put_ldev(device);
@@ -1346,7 +1354,7 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 		if (os.peer == R_SECONDARY && ns.peer == R_PRIMARY &&
 		    device->ldev->md.uuid[UI_BITMAP] == 0 && ns.disk >= D_UP_TO_DATE) {
 			drbd_uuid_new_current(device);
-			drbd_send_uuids(first_peer_device(device));
+			drbd_send_uuids(peer_device);
 		}
 		/* D_DISKLESS Peer becomes secondary */
 		if (os.peer == R_PRIMARY && ns.peer == R_SECONDARY)
@@ -1373,16 +1381,16 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 	/* Last part of the attaching process ... */
 	if (ns.conn >= C_CONNECTED &&
 	    os.disk == D_ATTACHING && ns.disk == D_NEGOTIATING) {
-		drbd_send_sizes(first_peer_device(device), 0, 0);  /* to start sync... */
-		drbd_send_uuids(first_peer_device(device));
-		drbd_send_state(first_peer_device(device), ns);
+		drbd_send_sizes(peer_device, 0, 0);  /* to start sync... */
+		drbd_send_uuids(peer_device);
+		drbd_send_state(peer_device, ns);
 	}
 
 	/* We want to pause/continue resync, tell peer. */
 	if (ns.conn >= C_CONNECTED &&
 	     ((os.aftr_isp != ns.aftr_isp) ||
 	      (os.user_isp != ns.user_isp)))
-		drbd_send_state(first_peer_device(device), ns);
+		drbd_send_state(peer_device, ns);
 
 	/* In case one of the isp bits got set, suspend other devices. */
 	if ((!os.aftr_isp && !os.peer_isp && !os.user_isp) &&
@@ -1392,10 +1400,10 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 	/* Make sure the peer gets informed about eventual state
 	   changes (ISP bits) while we were in WFReportParams. */
 	if (os.conn == C_WF_REPORT_PARAMS && ns.conn >= C_CONNECTED)
-		drbd_send_state(first_peer_device(device), ns);
+		drbd_send_state(peer_device, ns);
 
 	if (os.conn != C_AHEAD && ns.conn == C_AHEAD)
-		drbd_send_state(first_peer_device(device), ns);
+		drbd_send_state(peer_device, ns);
 
 	/* We are in the progress to start a full sync... */
 	if ((os.conn != C_STARTING_SYNC_T && ns.conn == C_STARTING_SYNC_T) ||
@@ -1449,7 +1457,7 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 					drbd_disk_str(device->state.disk));
 
 			if (ns.conn >= C_CONNECTED)
-				drbd_send_state(first_peer_device(device), ns);
+				drbd_send_state(peer_device, ns);
 
 			drbd_rs_cancel_all(device);
 
@@ -1473,7 +1481,7 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 				 drbd_disk_str(device->state.disk));
 
 		if (ns.conn >= C_CONNECTED)
-			drbd_send_state(first_peer_device(device), ns);
+			drbd_send_state(peer_device, ns);
 		/* corresponding get_ldev in __drbd_set_state
 		 * this may finally trigger drbd_ldev_destroy. */
 		put_ldev(device);
@@ -1481,7 +1489,7 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 
 	/* Notify peer that I had a local IO error, and did not detached.. */
 	if (os.disk == D_UP_TO_DATE && ns.disk == D_INCONSISTENT && ns.conn >= C_CONNECTED)
-		drbd_send_state(first_peer_device(device), ns);
+		drbd_send_state(peer_device, ns);
 
 	/* Disks got bigger while they were detached */
 	if (ns.disk > D_NEGOTIATING && ns.pdsk > D_NEGOTIATING &&
@@ -1499,14 +1507,14 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 	/* sync target done with resync.  Explicitly notify peer, even though
 	 * it should (at least for non-empty resyncs) already know itself. */
 	if (os.disk < D_UP_TO_DATE && os.conn >= C_SYNC_SOURCE && ns.conn == C_CONNECTED)
-		drbd_send_state(first_peer_device(device), ns);
+		drbd_send_state(peer_device, ns);
 
 	/* Verify finished, or reached stop sector.  Peer did not know about
 	 * the stop sector, and we may even have changed the stop sector during
 	 * verify to interrupt/stop early.  Send the new state. */
 	if (os.conn == C_VERIFY_S && ns.conn == C_CONNECTED
 	&& verify_can_do_stop_sector(device))
-		drbd_send_state(first_peer_device(device), ns);
+		drbd_send_state(peer_device, ns);
 
 	/* This triggers bitmap writeout of potentially still unwritten pages
 	 * if the resync finished cleanly, or aborted because of peer disk
@@ -1563,7 +1571,7 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused)
 		old_conf = connection->net_conf;
 		connection->my_addr_len = 0;
 		connection->peer_addr_len = 0;
-		rcu_assign_pointer(connection->net_conf, NULL);
+		RCU_INIT_POINTER(connection->net_conf, NULL);
 		conn_free_crypto(connection);
 		mutex_unlock(&connection->resource->conf_update);
 
@@ -1599,7 +1607,7 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused)
 	return 0;
 }
 
-void conn_old_common_state(struct drbd_connection *connection, union drbd_state *pcs, enum chg_state_flags *pf)
+static void conn_old_common_state(struct drbd_connection *connection, union drbd_state *pcs, enum chg_state_flags *pf)
 {
 	enum chg_state_flags flags = ~0;
 	struct drbd_peer_device *peer_device;
@@ -1688,7 +1696,7 @@ conn_is_valid_transition(struct drbd_connection *connection, union drbd_state ma
 	return rv;
 }
 
-void
+static void
 conn_set_state(struct drbd_connection *connection, union drbd_state mask, union drbd_state val,
 	       union drbd_state *pns_min, union drbd_state *pns_max, enum chg_state_flags flags)
 {

drivers/md/bcache/alloc.c

@@ -331,7 +331,7 @@ static int bch_allocator_thread(void *arg)
 				mutex_unlock(&ca->set->bucket_lock);
 				blkdev_issue_discard(ca->bdev,
 					bucket_to_sector(ca->set, bucket),
-					ca->sb.block_size, GFP_KERNEL, 0);
+					ca->sb.bucket_size, GFP_KERNEL, 0);
 				mutex_lock(&ca->set->bucket_lock);
 			}
 

drivers/md/bcache/bcache.h

@@ -477,9 +477,13 @@ struct gc_stat {
  * CACHE_SET_STOPPING always gets set first when we're closing down a cache set;
  * we'll continue to run normally for awhile with CACHE_SET_STOPPING set (i.e.
  * flushing dirty data).
+ *
+ * CACHE_SET_RUNNING means all cache devices have been registered and journal
+ * replay is complete.
  */
 #define CACHE_SET_UNREGISTERING		0
 #define	CACHE_SET_STOPPING		1
+#define	CACHE_SET_RUNNING		2
 
 struct cache_set {
 	struct closure		cl;

drivers/md/bcache/bset.c

@@ -1182,7 +1182,7 @@ static void __btree_sort(struct btree_keys *b, struct btree_iter *iter,
 {
 	uint64_t start_time;
 	bool used_mempool = false;
-	struct bset *out = (void *) __get_free_pages(__GFP_NOWARN|GFP_NOIO,
+	struct bset *out = (void *) __get_free_pages(__GFP_NOWARN|GFP_NOWAIT,
 						     order);
 	if (!out) {
 		struct page *outp;

drivers/md/bcache/bset.h

@@ -453,7 +453,7 @@ static inline bool bch_bkey_equal_header(const struct bkey *l,
 {
 	return (KEY_DIRTY(l) == KEY_DIRTY(r) &&
 		KEY_PTRS(l) == KEY_PTRS(r) &&
-		KEY_CSUM(l) == KEY_CSUM(l));
+		KEY_CSUM(l) == KEY_CSUM(r));
 }
 
 /* Keylists */

drivers/md/bcache/btree.h

@@ -242,9 +242,10 @@ void __bch_btree_node_write(struct btree *, struct closure *);
 void bch_btree_node_write(struct btree *, struct closure *);
 
 void bch_btree_set_root(struct btree *);
-struct btree *bch_btree_node_alloc(struct cache_set *, struct btree_op *, int);
+struct btree *__bch_btree_node_alloc(struct cache_set *, struct btree_op *,
+				     int, bool, struct btree *);
 struct btree *bch_btree_node_get(struct cache_set *, struct btree_op *,
-				 struct bkey *, int, bool);
+				 struct bkey *, int, bool, struct btree *);
 
 int bch_btree_insert_check_key(struct btree *, struct btree_op *,
 			       struct bkey *);

drivers/md/bcache/extents.h

@@ -9,5 +9,6 @@ struct cache_set;
 
 void bch_extent_to_text(char *, size_t, const struct bkey *);
 bool __bch_btree_ptr_invalid(struct cache_set *, const struct bkey *);
+bool __bch_extent_invalid(struct cache_set *, const struct bkey *);
 
 #endif /* _BCACHE_EXTENTS_H */

drivers/md/bcache/request.c

@@ -311,7 +311,8 @@ void bch_data_insert(struct closure *cl)
 {
 	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 
-	trace_bcache_write(op->bio, op->writeback, op->bypass);
+	trace_bcache_write(op->c, op->inode, op->bio,
+			   op->writeback, op->bypass);
 
 	bch_keylist_init(&op->insert_keys);
 	bio_get(op->bio);