Merge branch 'for-3.18/core' of git://git.kernel.dk/linux-block

Pull core block layer changes from Jens Axboe:
 "This is the core block IO pull request for 3.18.  Apart from the new
  and improved flush machinery for blk-mq, this is all mostly bug fixes
  and cleanups.

   - blk-mq timeout updates and fixes from Christoph.

   - Removal of REQ_END, also from Christoph.  We pass it through the
     ->queue_rq() hook for blk-mq instead, freeing up one of the request
     bits.  The space was overly tight on 32-bit, so Martin also killed
     REQ_KERNEL since it's no longer used.

   - blk integrity updates and fixes from Martin and Gu Zheng.

   - Update to the flush machinery for blk-mq from Ming Lei.  Now we
     have a per hardware context flush request, which both cleans up the
     code should scale better for flush intensive workloads on blk-mq.

   - Improve the error printing, from Rob Elliott.

   - Backing device improvements and cleanups from Tejun.

   - Fixup of a misplaced rq_complete() tracepoint from Hannes.

   - Make blk_get_request() return error pointers, fixing up issues
     where we NULL deref when a device goes bad or missing.  From Joe
     Lawrence.

   - Prep work for drastically reducing the memory consumption of dm
     devices from Junichi Nomura.  This allows creating clone bio sets
     without preallocating a lot of memory.

   - Fix a blk-mq hang on certain combinations of queue depths and
     hardware queues from me.

   - Limit memory consumption for blk-mq devices for crash dump
     scenarios and drivers that use crazy high depths (certain SCSI
     shared tag setups).  We now just use a single queue and limited
     depth for that"

* 'for-3.18/core' of git://git.kernel.dk/linux-block: (58 commits)
  block: Remove REQ_KERNEL
  blk-mq: allocate cpumask on the home node
  bio-integrity: remove the needless fail handle of bip_slab creating
  block: include func name in __get_request prints
  block: make blk_update_request print prefix match ratelimited prefix
  blk-merge: don't compute bi_phys_segments from bi_vcnt for cloned bio
  block: fix alignment_offset math that assumes io_min is a power-of-2
  blk-mq: Make bt_clear_tag() easier to read
  blk-mq: fix potential hang if rolling wakeup depth is too high
  block: add bioset_create_nobvec()
  block: use bio_clone_fast() in blk_rq_prep_clone()
  block: misplaced rq_complete tracepoint
  sd: Honor block layer integrity handling flags
  block: Replace strnicmp with strncasecmp
  block: Add T10 Protection Information functions
  block: Don't merge requests if integrity flags differ
  block: Integrity checksum flag
  block: Relocate bio integrity flags
  block: Add a disk flag to block integrity profile
  block: Add prefix to block integrity profile flags
  ...

5 files changed, 19 insertions, 35 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index e2f3ad08..cc9d411 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -50,32 +50,22 @@ inline struct block_device *I_BDEV(struct inode *inode)
 EXPORT_SYMBOL(I_BDEV);
 
 /*
- * Move the inode from its current bdi to a new bdi. If the inode is dirty we
- * need to move it onto the dirty list of @dst so that the inode is always on
- * the right list.
+ * Move the inode from its current bdi to a new bdi.  Make sure the inode
+ * is clean before moving so that it doesn't linger on the old bdi.
  */
 static void bdev_inode_switch_bdi(struct inode *inode,
 			struct backing_dev_info *dst)
 {
-	struct backing_dev_info *old = inode->i_data.backing_dev_info;
-	bool wakeup_bdi = false;
-
-	if (unlikely(dst == old))		/* deadlock avoidance */
-		return;
-	bdi_lock_two(&old->wb, &dst->wb);
-	spin_lock(&inode->i_lock);
-	inode->i_data.backing_dev_info = dst;
-	if (inode->i_state & I_DIRTY) {
-		if (bdi_cap_writeback_dirty(dst) && !wb_has_dirty_io(&dst->wb))
-			wakeup_bdi = true;
-		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
+	while (true) {
+		spin_lock(&inode->i_lock);
+		if (!(inode->i_state & I_DIRTY)) {
+			inode->i_data.backing_dev_info = dst;
+			spin_unlock(&inode->i_lock);
+			return;
+		}
+		spin_unlock(&inode->i_lock);
+		WARN_ON_ONCE(write_inode_now(inode, true));
 	}
-	spin_unlock(&inode->i_lock);
-	spin_unlock(&old->wb.list_lock);
-	spin_unlock(&dst->wb.list_lock);
-
-	if (wakeup_bdi)
-		bdi_wakeup_thread_delayed(dst);
 }
 
 /* Kill _all_ buffers and pagecache , dirty or not.. */
@@ -1179,8 +1169,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (!ret) {
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
 				bdi = blk_get_backing_dev_info(bdev);
-				if (bdi == NULL)
-					bdi = &default_backing_dev_info;
 				bdev_inode_switch_bdi(bdev->bd_inode, bdi);
 			}
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index fa45e3c..1ad0f47 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1702,7 +1702,7 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 		if (!device->bdev)
 			continue;
 		bdi = blk_get_backing_dev_info(device->bdev);
-		if (bdi && bdi_congested(bdi, bdi_bits)) {
+		if (bdi_congested(bdi, bdi_bits)) {
 			ret = 1;
 			break;
 		}
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index dda4b86..20cffc8 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -220,11 +220,9 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t
 #else
 	VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
 
-	if (rw == READ || rw == KERNEL_READ)
-		return nfs_file_direct_read(iocb, iter, pos,
-				rw == READ ? true : false);
-	return nfs_file_direct_write(iocb, iter, pos,
-				rw == WRITE ? true : false);
+	if (rw == READ)
+		return nfs_file_direct_read(iocb, iter, pos);
+	return nfs_file_direct_write(iocb, iter, pos);
 #endif /* CONFIG_NFS_SWAP */
 }
 
@@ -510,7 +508,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
  * cache.
  */
 ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
-				loff_t pos, bool uio)
+				loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
@@ -879,7 +877,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
  * is no atomic O_APPEND write facility in the NFS protocol.
  */
 ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
-				loff_t pos, bool uio)
+				loff_t pos)
 {
 	ssize_t result = -EINVAL;
 	struct file *file = iocb->ki_filp;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 4ea92ce..2ab6f00 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -172,7 +172,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 	ssize_t result;
 
 	if (iocb->ki_filp->f_flags & O_DIRECT)
-		return nfs_file_direct_read(iocb, to, iocb->ki_pos, true);
+		return nfs_file_direct_read(iocb, to, iocb->ki_pos);
 
 	dprintk("NFS: read(%pD2, %zu@%lu)\n",
 		iocb->ki_filp,
@@ -676,7 +676,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 		return result;
 
 	if (file->f_flags & O_DIRECT)
-		return nfs_file_direct_write(iocb, from, pos, true);
+		return nfs_file_direct_write(iocb, from, pos);
 
 	dprintk("NFS: write(%pD2, %zu@%Ld)\n",
 		file, count, (long long) pos);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 017b6af..24b4ebe 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1670,8 +1670,6 @@ xfs_alloc_buftarg(
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
 	btp->bt_bdi = blk_get_backing_dev_info(bdev);
-	if (!btp->bt_bdi)
-		goto error;
 
 	if (xfs_setsize_buftarg_early(btp, bdev))
 		goto error;