Block device buffered reads and writes already pass through
filemap_read() and iomap_file_buffered_write() respectively, both of
which handle IOCB_DONTCACHE. Enable RWF_DONTCACHE for block device files
by setting FOP_DONTCACHE in def_blk_fops.

For CONFIG_BUFFER_HEAD=y paths, add block_write_begin_iocb() which
threads the kiocb through so that buffer_head-based I/O can use
DONTCACHE behavior. The existing block_write_begin() is preserved as a
wrapper that passes a NULL iocb. Set BIO_COMPLETE_IN_TASK in
submit_bh_wbc() when the folio has dropbehind so that buffer_head
writeback completions get deferred to task context.

CONFIG_BUFFER_HEAD=n paths are handled by the previously added iomap
BIO_COMPLETE_IN_TASK support.

This support is useful for databases that operate on raw block devices,
among other userspace applications.

Signed-off-by: Tal Zussman <tz2294@columbia.edu>
---
 block/fops.c                |  5 +++--
 fs/buffer.c                 | 22 +++++++++++++++++++---
 include/linux/buffer_head.h |  3 +++
 3 files changed, 25 insertions(+), 5 deletions(-)

diff --git a/block/fops.c b/block/fops.c
index 4d32785b31d9..d8165f6ba71c 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -505,7 +505,8 @@ static int blkdev_write_begin(const struct kiocb *iocb,
 			      unsigned len, struct folio **foliop,
 			      void **fsdata)
 {
-	return block_write_begin(mapping, pos, len, foliop, blkdev_get_block);
+	return block_write_begin_iocb(iocb, mapping, pos, len, foliop,
+				     blkdev_get_block);
 }
 
 static int blkdev_write_end(const struct kiocb *iocb,
@@ -967,7 +968,7 @@ const struct file_operations def_blk_fops = {
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= blkdev_fallocate,
 	.uring_cmd	= blkdev_uring_cmd,
-	.fop_flags	= FOP_BUFFER_RASYNC,
+	.fop_flags	= FOP_BUFFER_RASYNC | FOP_DONTCACHE,
 };
 
 static __init int blkdev_init(void)
diff --git a/fs/buffer.c b/fs/buffer.c
index ed724a902657..c60c0ad6cc35 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2239,14 +2239,19 @@ EXPORT_SYMBOL(block_commit_write);
  *
  * The filesystem needs to handle block truncation upon failure.
  */
-int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
+int block_write_begin_iocb(const struct kiocb *iocb,
+		struct address_space *mapping, loff_t pos, unsigned len,
 		struct folio **foliop, get_block_t *get_block)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
+	fgf_t fgp_flags = FGP_WRITEBEGIN;
 	struct folio *folio;
 	int status;
 
-	folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+	if (iocb && iocb->ki_flags & IOCB_DONTCACHE)
+		fgp_flags |= FGP_DONTCACHE;
+
+	folio = __filemap_get_folio(mapping, index, fgp_flags,
 			mapping_gfp_mask(mapping));
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
@@ -2261,6 +2266,13 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 	*foliop = folio;
 	return status;
 }
+
+int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
+		struct folio **foliop, get_block_t *get_block)
+{
+	return block_write_begin_iocb(NULL, mapping, pos, len, foliop,
+				      get_block);
+}
 EXPORT_SYMBOL(block_write_begin);
 
 int block_write_end(loff_t pos, unsigned len, unsigned copied,
@@ -2589,7 +2601,8 @@ int cont_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 		(*bytes)++;
 	}
 
-	return block_write_begin(mapping, pos, len, foliop, get_block);
+	return block_write_begin_iocb(iocb, mapping, pos, len, foliop,
+				     get_block);
 }
 EXPORT_SYMBOL(cont_write_begin);
 
@@ -2801,6 +2814,9 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
 
 	bio = bio_alloc(bh->b_bdev, 1, opf, GFP_NOIO);
 
+	if (folio_test_dropbehind(bh->b_folio))
+		bio_set_flag(bio, BIO_COMPLETE_IN_TASK);
+
 	fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
 
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index b16b88bfbc3e..ddf88ce290f2 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -260,6 +260,9 @@ int block_read_full_folio(struct folio *, get_block_t *);
 bool block_is_partially_uptodate(struct folio *, size_t from, size_t count);
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 		struct folio **foliop, get_block_t *get_block);
+int block_write_begin_iocb(const struct kiocb *iocb,
+		struct address_space *mapping, loff_t pos, unsigned len,
+		struct folio **foliop, get_block_t *get_block);
 int __block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 		get_block_t *get_block);
 int block_write_end(loff_t pos, unsigned len, unsigned copied, struct folio *);

-- 
2.39.5