iomap: support REQ_OP_ZONE_APPEND

A ZONE_APPEND bio must follow hardware restrictions (e.g. not exceeding
max_zone_append_sectors) not to be split. bio_iov_iter_get_pages builds
such restricted bio using __bio_iov_append_get_pages if bio_op(bio) ==
REQ_OP_ZONE_APPEND.

To utilize it, we need to set the bio_op before calling
bio_iov_iter_get_pages(). This commit introduces IOMAP_F_ZONE_APPEND, so
that iomap user can set the flag to indicate they want REQ_OP_ZONE_APPEND
and restricted bio.

Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>

2 files changed, 38 insertions, 6 deletions

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 933f234d5bec..2273120d8ed7 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -201,6 +201,34 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 	iomap_dio_submit_bio(dio, iomap, bio, pos);
 }
 
+/*
+ * Figure out the bio's operation flags from the dio request, the
+ * mapping, and whether or not we want FUA.  Note that we can end up
+ * clearing the WRITE_FUA flag in the dio request.
+ */
+static inline unsigned int
+iomap_dio_bio_opflags(struct iomap_dio *dio, struct iomap *iomap, bool use_fua)
+{
+	unsigned int opflags = REQ_SYNC | REQ_IDLE;
+
+	if (!(dio->flags & IOMAP_DIO_WRITE)) {
+		WARN_ON_ONCE(iomap->flags & IOMAP_F_ZONE_APPEND);
+		return REQ_OP_READ;
+	}
+
+	if (iomap->flags & IOMAP_F_ZONE_APPEND)
+		opflags |= REQ_OP_ZONE_APPEND;
+	else
+		opflags |= REQ_OP_WRITE;
+
+	if (use_fua)
+		opflags |= REQ_FUA;
+	else
+		dio->flags &= ~IOMAP_DIO_WRITE_FUA;
+
+	return opflags;
+}
+
 static loff_t
 iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 		struct iomap_dio *dio, struct iomap *iomap)
@@ -208,6 +236,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 	unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev));
 	unsigned int fs_block_size = i_blocksize(inode), pad;
 	unsigned int align = iov_iter_alignment(dio->submit.iter);
+	unsigned int bio_opf;
 	struct bio *bio;
 	bool need_zeroout = false;
 	bool use_fua = false;
@@ -263,6 +292,13 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 			iomap_dio_zero(dio, iomap, pos - pad, pad);
 	}
 
+	/*
+	 * Set the operation flags early so that bio_iov_iter_get_pages
+	 * can set up the page vector appropriately for a ZONE_APPEND
+	 * operation.
+	 */
+	bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua);
+
 	do {
 		size_t n;
 		if (dio->error) {
@@ -278,6 +314,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 		bio->bi_ioprio = dio->iocb->ki_ioprio;
 		bio->bi_private = dio;
 		bio->bi_end_io = iomap_dio_bio_end_io;
+		bio->bi_opf = bio_opf;
 
 		ret = bio_iov_iter_get_pages(bio, dio->submit.iter);
 		if (unlikely(ret)) {
@@ -293,14 +330,8 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 
 		n = bio->bi_iter.bi_size;
 		if (dio->flags & IOMAP_DIO_WRITE) {
-			bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
-			if (use_fua)
-				bio->bi_opf |= REQ_FUA;
-			else
-				dio->flags &= ~IOMAP_DIO_WRITE_FUA;
 			task_io_account_write(n);
 		} else {
-			bio->bi_opf = REQ_OP_READ;
 			if (dio->flags & IOMAP_DIO_DIRTY)
 				bio_set_pages_dirty(bio);
 		}
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 5bd3cac4df9c..8ebb1fa6f3b7 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -55,6 +55,7 @@ struct vm_fault;
 #define IOMAP_F_SHARED		0x04
 #define IOMAP_F_MERGED		0x08
 #define IOMAP_F_BUFFER_HEAD	0x10
+#define IOMAP_F_ZONE_APPEND	0x20
 
 /*
  * Flags set by the core iomap code during operations: