Merge branch 'for-linus2' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Round 2 of this.  I cut back to the bare necessities, the patch is
  still larger than it usually would be at this time, due to the number
  of NVMe fixes in there.  This pull request contains:

   - The 4 core fixes from Ming, that fix both problems with exceeding
     the virtual boundary limit in case of merging, and the gap checking
     for cloned bio's.

   - NVMe fixes from Keith and Christoph:

        - Regression on larger user commands, causing problems with
          reading log pages (for instance). This touches both NVMe,
          and the block core since that is now generally utilized also
          for these types of commands.

        - Hot removal fixes.

        - User exploitable issue with passthrough IO commands, if !length
          is given, causing us to fault on writing to the zero
          page.

        - Fix for a hang under error conditions

   - And finally, the current series regression for umount with cgroup
     writeback, where the final flush would happen async and hence open
     up window after umount where the device wasn't consistent.  fsck
     right after umount would show this.  From Tejun"

* 'for-linus2' of git://git.kernel.dk/linux-block:
  block: support large requests in blk_rq_map_user_iov
  block: fix blk_rq_get_max_sectors for driver private requests
  nvme: fix max_segments integer truncation
  nvme: set queue limits for the admin queue
  writeback: flush inode cgroup wb switches instead of pinning super_block
  NVMe: Fix 0-length integrity payload
  NVMe: Don't allow unsupported flags
  NVMe: Move error handling to failed reset handler
  NVMe: Simplify device reset failure
  NVMe: Fix namespace removal deadlock
  NVMe: Use IDA for namespace disk naming
  NVMe: Don't unmap controller registers on reset
  block: merge: get the 1st and last bvec via helpers
  block: get the 1st and last bvec via helpers
  block: check virt boundary in bio_will_gap()
  block: bio: introduce helpers to get the 1st and last bvec

3 files changed, 60 insertions, 7 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 5349e6816cbb..cb6888824108 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -310,6 +310,43 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit)
 	bio->bi_flags &= ~(1U << bit);
 }
 
+static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv)
+{
+	*bv = bio_iovec(bio);
+}
+
+static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv)
+{
+	struct bvec_iter iter = bio->bi_iter;
+	int idx;
+
+	if (!bio_flagged(bio, BIO_CLONED)) {
+		*bv = bio->bi_io_vec[bio->bi_vcnt - 1];
+		return;
+	}
+
+	if (unlikely(!bio_multiple_segments(bio))) {
+		*bv = bio_iovec(bio);
+		return;
+	}
+
+	bio_advance_iter(bio, &iter, iter.bi_size);
+
+	if (!iter.bi_bvec_done)
+		idx = iter.bi_idx - 1;
+	else	/* in the middle of bvec */
+		idx = iter.bi_idx;
+
+	*bv = bio->bi_io_vec[idx];
+
+	/*
+	 * iter.bi_bvec_done records actual length of the last bvec
+	 * if this bio ends in the middle of one io vector
+	 */
+	if (iter.bi_bvec_done)
+		bv->bv_len = iter.bi_bvec_done;
+}
+
 enum bip_flags {
 	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
 	BIP_MAPPED_INTEGRITY	= 1 << 1, /* ref tag has been remapped */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4571ef1a12a9..413c84fbc4ed 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -895,7 +895,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
-	if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC))
+	if (unlikely(rq->cmd_type != REQ_TYPE_FS))
 		return q->limits.max_hw_sectors;
 
 	if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD))
@@ -1372,6 +1372,13 @@ static inline void put_dev_sector(Sector p)
 	page_cache_release(p.v);
 }
 
+static inline bool __bvec_gap_to_prev(struct request_queue *q,
+				struct bio_vec *bprv, unsigned int offset)
+{
+	return offset ||
+		((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
+}
+
 /*
  * Check if adding a bio_vec after bprv with offset would create a gap in
  * the SG list. Most drivers don't care about this, but some do.
@@ -1381,18 +1388,22 @@ static inline bool bvec_gap_to_prev(struct request_queue *q,
 {
 	if (!queue_virt_boundary(q))
 		return false;
-	return offset ||
-		((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
+	return __bvec_gap_to_prev(q, bprv, offset);
 }
 
 static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
 			 struct bio *next)
 {
-	if (!bio_has_data(prev))
-		return false;
+	if (bio_has_data(prev) && queue_virt_boundary(q)) {
+		struct bio_vec pb, nb;
+
+		bio_get_last_bvec(prev, &pb);
+		bio_get_first_bvec(next, &nb);
 
-	return bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1],
-				next->bi_io_vec[0].bv_offset);
+		return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
+	}
+
+	return false;
 }
 
 static inline bool req_gap_back_merge(struct request *req, struct bio *bio)
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index b333c945e571..d0b5ca5d4e08 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -198,6 +198,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
 void wbc_detach_inode(struct writeback_control *wbc);
 void wbc_account_io(struct writeback_control *wbc, struct page *page,
 		    size_t bytes);
+void cgroup_writeback_umount(void);
 
 /**
  * inode_attach_wb - associate an inode with its wb
@@ -301,6 +302,10 @@ static inline void wbc_account_io(struct writeback_control *wbc,
 {
 }
 
+static inline void cgroup_writeback_umount(void)
+{
+}
+
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
 /*