Merge branch 'for-4.8/drivers' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "This branch also contains core changes.  I've come to the conclusion
  that from 4.9 and forward, I'll be doing just a single branch.  We
  often have dependencies between core and drivers, and it's hard to
  always split them up appropriately without pulling core into drivers
  when that happens.

  That said, this contains:

   - separate secure erase type for the core block layer, from
     Christoph.

   - set of discard fixes, from Christoph.

   - bio shrinking fixes from Christoph, as a followup up to the
     op/flags change in the core branch.

   - map and append request fixes from Christoph.

   - NVMeF (NVMe over Fabrics) code from Christoph.  This is pretty
     exciting!

   - nvme-loop fixes from Arnd.

   - removal of ->driverfs_dev from Dan, after providing a
     device_add_disk() helper.

   - bcache fixes from Bhaktipriya and Yijing.

   - cdrom subchannel read fix from Vchannaiah.

   - set of lightnvm updates from Wenwei, Matias, Johannes, and Javier.

   - set of drbd updates and fixes from Fabian, Lars, and Philipp.

   - mg_disk error path fix from Bart.

   - user notification for failed device add for loop, from Minfei.

   - NVMe in general:
        + NVMe delay quirk from Guilherme.
        + SR-IOV support and command retry limits from Keith.
        + fix for memory-less NUMA node from Masayoshi.
        + use UINT_MAX for discard sectors, from Minfei.
        + cancel IO fixes from Ming.
        + don't allocate unused major, from Neil.
        + error code fixup from Dan.
        + use constants for PSDT/FUSE from James.
        + variable init fix from Jay.
        + fabrics fixes from Ming, Sagi, and Wei.
        + various fixes"

* 'for-4.8/drivers' of git://git.kernel.dk/linux-block: (115 commits)
  nvme/pci: Provide SR-IOV support
  nvme: initialize variable before logical OR'ing it
  block: unexport various bio mapping helpers
  scsi/osd: open code blk_make_request
  target: stop using blk_make_request
  block: simplify and export blk_rq_append_bio
  block: ensure bios return from blk_get_request are properly initialized
  virtio_blk: use blk_rq_map_kern
  memstick: don't allow REQ_TYPE_BLOCK_PC requests
  block: shrink bio size again
  block: simplify and cleanup bvec pool handling
  block: get rid of bio_rw and READA
  block: don't ignore -EOPNOTSUPP blkdev_issue_write_same
  block: introduce BLKDEV_DISCARD_ZERO to fix zeroout
  NVMe: don't allocate unused nvme_major
  nvme: avoid crashes when node 0 is memoryless node.
  nvme: Limit command retries
  loop: Make user notify for adding loop device failed
  nvme-loop: fix nvme-loop Kconfig dependencies
  nvmet: fix return value check in nvmet_subsys_alloc()
  ...

1 files changed, 62 insertions, 22 deletions

diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index e5d89f623b90..ab62b81c2ca7 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -96,6 +96,13 @@ struct drbd_bitmap {
 	struct page **bm_pages;
 	spinlock_t bm_lock;
 
+	/* exclusively to be used by __al_write_transaction(),
+	 * drbd_bm_mark_for_writeout() and
+	 * and drbd_bm_write_hinted() -> bm_rw() called from there.
+	 */
+	unsigned int n_bitmap_hints;
+	unsigned int al_bitmap_hints[AL_UPDATES_PER_TRANSACTION];
+
 	/* see LIMITATIONS: above */
 
 	unsigned long bm_set;       /* nr of set bits; THINK maybe atomic_t? */
@@ -242,6 +249,11 @@ static void bm_set_page_need_writeout(struct page *page)
 	set_bit(BM_PAGE_NEED_WRITEOUT, &page_private(page));
 }
 
+void drbd_bm_reset_al_hints(struct drbd_device *device)
+{
+	device->bitmap->n_bitmap_hints = 0;
+}
+
 /**
  * drbd_bm_mark_for_writeout() - mark a page with a "hint" to be considered for writeout
  * @device:	DRBD device.
@@ -253,6 +265,7 @@ static void bm_set_page_need_writeout(struct page *page)
  */
 void drbd_bm_mark_for_writeout(struct drbd_device *device, int page_nr)
 {
+	struct drbd_bitmap *b = device->bitmap;
 	struct page *page;
 	if (page_nr >= device->bitmap->bm_number_of_pages) {
 		drbd_warn(device, "BAD: page_nr: %u, number_of_pages: %u\n",
@@ -260,7 +273,9 @@ void drbd_bm_mark_for_writeout(struct drbd_device *device, int page_nr)
 		return;
 	}
 	page = device->bitmap->bm_pages[page_nr];
-	set_bit(BM_PAGE_HINT_WRITEOUT, &page_private(page));
+	BUG_ON(b->n_bitmap_hints >= ARRAY_SIZE(b->al_bitmap_hints));
+	if (!test_and_set_bit(BM_PAGE_HINT_WRITEOUT, &page_private(page)))
+		b->al_bitmap_hints[b->n_bitmap_hints++] = page_nr;
 }
 
 static int bm_test_page_unchanged(struct page *page)
@@ -427,8 +442,7 @@ static struct page **bm_realloc_pages(struct drbd_bitmap *b, unsigned long want)
 }
 
 /*
- * called on driver init only. TODO call when a device is created.
- * allocates the drbd_bitmap, and stores it in device->bitmap.
+ * allocates the drbd_bitmap and stores it in device->bitmap.
  */
 int drbd_bm_init(struct drbd_device *device)
 {
@@ -633,7 +647,8 @@ int drbd_bm_resize(struct drbd_device *device, sector_t capacity, int set_new_bi
 	unsigned long bits, words, owords, obits;
 	unsigned long want, have, onpages; /* number of pages */
 	struct page **npages, **opages = NULL;
-	int err = 0, growing;
+	int err = 0;
+	bool growing;
 
 	if (!expect(b))
 		return -ENOMEM;
@@ -1030,7 +1045,7 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned
 {
 	struct drbd_bm_aio_ctx *ctx;
 	struct drbd_bitmap *b = device->bitmap;
-	int num_pages, i, count = 0;
+	unsigned int num_pages, i, count = 0;
 	unsigned long now;
 	char ppb[10];
 	int err = 0;
@@ -1078,16 +1093,37 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned
 	now = jiffies;
 
 	/* let the layers below us try to merge these bios... */
-	for (i = 0; i < num_pages; i++) {
-		/* ignore completely unchanged pages */
-		if (lazy_writeout_upper_idx && i == lazy_writeout_upper_idx)
-			break;
-		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_AIO_READ) {
+		for (i = 0; i < num_pages; i++) {
+			atomic_inc(&ctx->in_flight);
+			bm_page_io_async(ctx, i);
+			++count;
+			cond_resched();
+		}
+	} else if (flags & BM_AIO_WRITE_HINTED) {
+		/* ASSERT: BM_AIO_WRITE_ALL_PAGES is not set. */
+		unsigned int hint;
+		for (hint = 0; hint < b->n_bitmap_hints; hint++) {
+			i = b->al_bitmap_hints[hint];
+			if (i >= num_pages) /* == -1U: no hint here. */
+				continue;
+			/* Several AL-extents may point to the same page. */
+			if (!test_and_clear_bit(BM_PAGE_HINT_WRITEOUT,
+			    &page_private(b->bm_pages[i])))
+				continue;
+			/* Has it even changed? */
+			if (bm_test_page_unchanged(b->bm_pages[i]))
+				continue;
+			atomic_inc(&ctx->in_flight);
+			bm_page_io_async(ctx, i);
+			++count;
+		}
+	} else {
+		for (i = 0; i < num_pages; i++) {
+			/* ignore completely unchanged pages */
+			if (lazy_writeout_upper_idx && i == lazy_writeout_upper_idx)
+				break;
 			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);
@@ -1100,11 +1136,11 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned
 				dynamic_drbd_dbg(device, "skipped bm lazy write for idx %u\n", i);
 				continue;
 			}
+			atomic_inc(&ctx->in_flight);
+			bm_page_io_async(ctx, i);
+			++count;
+			cond_resched();
 		}
-		atomic_inc(&ctx->in_flight);
-		bm_page_io_async(ctx, i);
-		++count;
-		cond_resched();
 	}
 
 	/*
@@ -1121,10 +1157,14 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned
 		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",
-			 (flags & BM_AIO_READ) ? "READ" : "WRITE",
-			 count, jiffies - now);
+	if (flags == 0) {
+		unsigned int ms = jiffies_to_msecs(jiffies - now);
+		if (ms > 5) {
+			drbd_info(device, "bitmap %s of %u pages took %u ms\n",
+				 (flags & BM_AIO_READ) ? "READ" : "WRITE",
+				 count, ms);
+		}
+	}
 
 	if (ctx->error) {
 		drbd_alert(device, "we had at least one MD IO ERROR during bitmap IO\n");