Merge branch 'iomap-for-next' into mb/dio

fs/dax.c

@@ -1090,7 +1090,7 @@ EXPORT_SYMBOL_GPL(__dax_zero_page_range);
 
 static loff_t
 dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
-		struct iomap *iomap)
+		struct iomap *iomap, struct iomap *srcmap)
 {
 	struct block_device *bdev = iomap->bdev;
 	struct dax_device *dax_dev = iomap->dax_dev;
@@ -1247,7 +1247,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	struct inode *inode = mapping->host;
 	unsigned long vaddr = vmf->address;
 	loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
-	struct iomap iomap = { 0 };
+	struct iomap iomap = { .type = IOMAP_HOLE };
+	struct iomap srcmap = { .type = IOMAP_HOLE };
 	unsigned flags = IOMAP_FAULT;
 	int error, major = 0;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -1292,7 +1293,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 * the file system block size to be equal the page size, which means
 	 * that we never have to deal with more than a single extent here.
 	 */
-	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
+	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap, &srcmap);
 	if (iomap_errp)
 		*iomap_errp = error;
 	if (error) {
@@ -1471,7 +1472,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
 	struct inode *inode = mapping->host;
 	vm_fault_t result = VM_FAULT_FALLBACK;
-	struct iomap iomap = { 0 };
+	struct iomap iomap = { .type = IOMAP_HOLE };
+	struct iomap srcmap = { .type = IOMAP_HOLE };
 	pgoff_t max_pgoff;
 	void *entry;
 	loff_t pos;
@@ -1546,7 +1548,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 * to look up our filesystem block.
 	 */
 	pos = (loff_t)xas.xa_index << PAGE_SHIFT;
-	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
+	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap,
+			&srcmap);
 	if (error)
 		goto unlock_entry;
 

fs/ext2/inode.c

@@ -801,7 +801,7 @@ int ext2_get_block(struct inode *inode, sector_t iblock,
 
 #ifdef CONFIG_FS_DAX
 static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
-		unsigned flags, struct iomap *iomap)
+		unsigned flags, struct iomap *iomap, struct iomap *srcmap)
 {
 	unsigned int blkbits = inode->i_blkbits;
 	unsigned long first_block = offset >> blkbits;

fs/ext4/inode.c

@@ -3449,7 +3449,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 }
 
 static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
-			    unsigned flags, struct iomap *iomap)
+		unsigned flags, struct iomap *iomap, struct iomap *srcmap)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	unsigned int blkbits = inode->i_blkbits;

fs/gfs2/bmap.c

@@ -1149,7 +1149,8 @@ static inline bool gfs2_iomap_need_write_lock(unsigned flags)
 }
 
 static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
-			    unsigned flags, struct iomap *iomap)
+			    unsigned flags, struct iomap *iomap,
+			    struct iomap *srcmap)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct metapath mp = { .mp_aheight = 1, };

fs/gfs2/file.c

@@ -732,7 +732,8 @@ static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to)
 	if (ret)
 		goto out_uninit;
 
-	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL);
+	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL,
+			   is_sync_kiocb(iocb));
 
 	gfs2_glock_dq(&gh);
 out_uninit:
@@ -767,7 +768,8 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	if (offset + len > i_size_read(&ip->i_inode))
 		goto out;
 
-	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL);
+	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL,
+			   is_sync_kiocb(iocb));
 
 out:
 	gfs2_glock_dq(&gh);

fs/iomap/Makefile

@@ -3,13 +3,15 @@
 # Copyright (c) 2019 Oracle.
 # All Rights Reserved.
 #
+
+ccflags-y += -I $(srctree)/$(src)		# needed for trace events
+
 obj-$(CONFIG_FS_IOMAP)		+= iomap.o
 
-iomap-y				+= \
+iomap-y				+= trace.o \
 				   apply.o \
 				   buffered-io.o \
 				   direct-io.o \
 				   fiemap.o \
 				   seek.o
-
 iomap-$(CONFIG_SWAP)		+= swapfile.o

fs/iomap/apply.c

@@ -23,8 +23,10 @@ loff_t
 iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
 		const struct iomap_ops *ops, void *data, iomap_actor_t actor)
 {
-	struct iomap iomap = { 0 };
+	struct iomap iomap = { .type = IOMAP_HOLE };
+	struct iomap srcmap = { .type = IOMAP_HOLE };
 	loff_t written = 0, ret;
+	u64 end;
 
 	/*
 	 * Need to map a range from start position for length bytes. This can
@@ -38,7 +40,7 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
 	 * expose transient stale data. If the reserve fails, we can safely
 	 * back out at this point as there is nothing to undo.
 	 */
-	ret = ops->iomap_begin(inode, pos, length, flags, &iomap);
+	ret = ops->iomap_begin(inode, pos, length, flags, &iomap, &srcmap);
 	if (ret)
 		return ret;
 	if (WARN_ON(iomap.offset > pos))
@@ -50,15 +52,26 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
 	 * Cut down the length to the one actually provided by the filesystem,
 	 * as it might not be able to give us the whole size that we requested.
 	 */
-	if (iomap.offset + iomap.length < pos + length)
-		length = iomap.offset + iomap.length - pos;
+	end = iomap.offset + iomap.length;
+	if (srcmap.type != IOMAP_HOLE)
+		end = min(end, srcmap.offset + srcmap.length);
+	if (pos + length > end)
+		length = end - pos;
 
 	/*
-	 * Now that we have guaranteed that the space allocation will succeed.
+	 * Now that we have guaranteed that the space allocation will succeed,
 	 * we can do the copy-in page by page without having to worry about
 	 * failures exposing transient data.
+	 *
+	 * To support COW operations, we read in data for partially blocks from
+	 * the srcmap if the file system filled it in.  In that case we the
+	 * length needs to be limited to the earlier of the ends of the iomaps.
+	 * If the file system did not provide a srcmap we pass in the normal
+	 * iomap into the actors so that they don't need to have special
+	 * handling for the two cases.
 	 */
-	written = actor(inode, pos, length, data, &iomap);
+	written = actor(inode, pos, length, data, &iomap,
+			srcmap.type != IOMAP_HOLE ? &srcmap : &iomap);
 
 	/*
 	 * Now the data has been copied, commit the range we've copied.  This

fs/iomap/direct-io.c

@@ -358,7 +358,7 @@ iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length,
 
 static loff_t
 iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
-		void *data, struct iomap *iomap)
+		void *data, struct iomap *iomap, struct iomap *srcmap)
 {
 	struct iomap_dio *dio = data;
 
@@ -392,7 +392,8 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
  */
 ssize_t
 iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
-		const struct iomap_ops *ops, const struct iomap_dio_ops *dops)
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
@@ -400,7 +401,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	loff_t pos = iocb->ki_pos, start = pos;
 	loff_t end = iocb->ki_pos + count - 1, ret = 0;
 	unsigned int flags = IOMAP_DIRECT;
-	bool wait_for_completion = is_sync_kiocb(iocb);
 	struct blk_plug plug;
 	struct iomap_dio *dio;
 
@@ -409,6 +409,9 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (!count)
 		return 0;
 
+	if (WARN_ON(is_sync_kiocb(iocb) && !wait_for_completion))
+		return -EIO;
+
 	dio = kmalloc(sizeof(*dio), GFP_KERNEL);
 	if (!dio)
 		return -ENOMEM;
@@ -430,7 +433,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		if (pos >= dio->i_size)
 			goto out_free_dio;
 
-		if (iter_is_iovec(iter) && iov_iter_rw(iter) == READ)
+		if (iter_is_iovec(iter))
 			dio->flags |= IOMAP_DIO_DIRTY;
 	} else {
 		flags |= IOMAP_WRITE;

fs/iomap/fiemap.c

@@ -44,7 +44,7 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi,
 
 static loff_t
 iomap_fiemap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
-		struct iomap *iomap)
+		struct iomap *iomap, struct iomap *srcmap)
 {
 	struct fiemap_ctx *ctx = data;
 	loff_t ret = length;
@@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(iomap_fiemap);
 
 static loff_t
 iomap_bmap_actor(struct inode *inode, loff_t pos, loff_t length,
-		void *data, struct iomap *iomap)
+		void *data, struct iomap *iomap, struct iomap *srcmap)
 {
 	sector_t *bno = data, addr;
 

fs/iomap/seek.c

@@ -119,7 +119,7 @@ page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
 
 static loff_t
 iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length,
-		      void *data, struct iomap *iomap)
+		      void *data, struct iomap *iomap, struct iomap *srcmap)
 {
 	switch (iomap->type) {
 	case IOMAP_UNWRITTEN:
@@ -165,7 +165,7 @@ EXPORT_SYMBOL_GPL(iomap_seek_hole);
 
 static loff_t
 iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length,
-		      void *data, struct iomap *iomap)
+		      void *data, struct iomap *iomap, struct iomap *srcmap)
 {
 	switch (iomap->type) {
 	case IOMAP_HOLE:

fs/iomap/swapfile.c

@@ -76,7 +76,8 @@ static int iomap_swapfile_add_extent(struct iomap_swapfile_info *isi)
  * distinction between written and unwritten extents.
  */
 static loff_t iomap_swapfile_activate_actor(struct inode *inode, loff_t pos,
-		loff_t count, void *data, struct iomap *iomap)
+		loff_t count, void *data, struct iomap *iomap,
+		struct iomap *srcmap)
 {
 	struct iomap_swapfile_info *isi = data;
 	int error;

fs/iomap/trace.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Christoph Hellwig
+ */
+#include <linux/iomap.h>
+
+/*
+ * We include this last to have the helpers above available for the trace
+ * event implementations.
+ */
+#define CREATE_TRACE_POINTS
+#include "trace.h"

fs/iomap/trace.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2009-2019 Christoph Hellwig
+ *
+ * NOTE: none of these tracepoints shall be consider a stable kernel ABI
+ * as they can change at any time.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM iomap
+
+#if !defined(_IOMAP_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _IOMAP_TRACE_H
+
+#include <linux/tracepoint.h>
+
+struct inode;
+
+DECLARE_EVENT_CLASS(iomap_readpage_class,
+	TP_PROTO(struct inode *inode, int nr_pages),
+	TP_ARGS(inode, nr_pages),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(u64, ino)
+		__field(int, nr_pages)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->nr_pages = nr_pages;
+	),
+	TP_printk("dev %d:%d ino 0x%llx nr_pages %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->nr_pages)
+)
+
+#define DEFINE_READPAGE_EVENT(name)		\
+DEFINE_EVENT(iomap_readpage_class, name,	\
+	TP_PROTO(struct inode *inode, int nr_pages), \
+	TP_ARGS(inode, nr_pages))
+DEFINE_READPAGE_EVENT(iomap_readpage);
+DEFINE_READPAGE_EVENT(iomap_readpages);
+
+DECLARE_EVENT_CLASS(iomap_page_class,
+	TP_PROTO(struct inode *inode, struct page *page, unsigned long off,
+		 unsigned int len),
+	TP_ARGS(inode, page, off, len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(u64, ino)
+		__field(pgoff_t, pgoff)
+		__field(loff_t, size)
+		__field(unsigned long, offset)
+		__field(unsigned int, length)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->pgoff = page_offset(page);
+		__entry->size = i_size_read(inode);
+		__entry->offset = off;
+		__entry->length = len;
+	),
+	TP_printk("dev %d:%d ino 0x%llx pgoff 0x%lx size 0x%llx offset %lx "
+		  "length %x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->pgoff,
+		  __entry->size,
+		  __entry->offset,
+		  __entry->length)
+)
+
+#define DEFINE_PAGE_EVENT(name)		\
+DEFINE_EVENT(iomap_page_class, name,	\
+	TP_PROTO(struct inode *inode, struct page *page, unsigned long off, \
+		 unsigned int len),	\
+	TP_ARGS(inode, page, off, len))
+DEFINE_PAGE_EVENT(iomap_writepage);
+DEFINE_PAGE_EVENT(iomap_releasepage);
+DEFINE_PAGE_EVENT(iomap_invalidatepage);
+
+#endif /* _IOMAP_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>

fs/xfs/libxfs/xfs_bmap.c

@@ -34,6 +34,7 @@
 #include "xfs_ag_resv.h"
 #include "xfs_refcount.h"
 #include "xfs_icache.h"
+#include "xfs_iomap.h"
 
 
 kmem_zone_t		*xfs_bmap_free_item_zone;
@@ -4456,16 +4457,21 @@ int
 xfs_bmapi_convert_delalloc(
 	struct xfs_inode	*ip,
 	int			whichfork,
-	xfs_fileoff_t		offset_fsb,
-	struct xfs_bmbt_irec	*imap,
+	xfs_off_t		offset,
+	struct iomap		*iomap,
 	unsigned int		*seq)
 {
 	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
 	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	struct xfs_bmalloca	bma = { NULL };
+	u16			flags = 0;
 	struct xfs_trans	*tp;
 	int			error;
 
+	if (whichfork == XFS_COW_FORK)
+		flags |= IOMAP_F_SHARED;
+
 	/*
 	 * Space for the extent and indirect blocks was reserved when the
 	 * delalloc extent was created so there's no need to do so here.
@@ -4495,7 +4501,7 @@ xfs_bmapi_convert_delalloc(
 	 * the extent.  Just return the real extent at this offset.
 	 */
 	if (!isnullstartblock(bma.got.br_startblock)) {
-		*imap = bma.got;
+		xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags);
 		*seq = READ_ONCE(ifp->if_seq);
 		goto out_trans_cancel;
 	}
@@ -4528,7 +4534,7 @@ xfs_bmapi_convert_delalloc(
 	XFS_STATS_INC(mp, xs_xstrat_quick);
 
 	ASSERT(!isnullstartblock(bma.got.br_startblock));
-	*imap = bma.got;
+	xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags);
 	*seq = READ_ONCE(ifp->if_seq);
 
 	if (whichfork == XFS_COW_FORK)

fs/xfs/libxfs/xfs_bmap.h

@@ -228,8 +228,7 @@ int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
 		struct xfs_bmbt_irec *got, struct xfs_iext_cursor *cur,
 		int eof);
 int	xfs_bmapi_convert_delalloc(struct xfs_inode *ip, int whichfork,
-		xfs_fileoff_t offset_fsb, struct xfs_bmbt_irec *imap,
-		unsigned int *seq);
+		xfs_off_t offset, struct iomap *iomap, unsigned int *seq);
 int	xfs_bmap_add_extent_unwritten_real(struct xfs_trans *tp,
 		struct xfs_inode *ip, int whichfork,
 		struct xfs_iext_cursor *icur, struct xfs_btree_cur **curp,

fs/xfs/xfs_aops.h

@@ -6,23 +6,6 @@
 #ifndef __XFS_AOPS_H__
 #define __XFS_AOPS_H__
 
-extern struct bio_set xfs_ioend_bioset;
-
-/*
- * Structure for buffered I/O completions.
- */
-struct xfs_ioend {
-	struct list_head	io_list;	/* next ioend in chain */
-	int			io_fork;	/* inode fork written back */
-	xfs_exntst_t		io_state;	/* extent state */
-	struct inode		*io_inode;	/* file being written to */
-	size_t			io_size;	/* size of the extent */
-	xfs_off_t		io_offset;	/* offset in the file */
-	struct xfs_trans	*io_append_trans;/* xact. for size update */
-	struct bio		*io_bio;	/* bio being built */
-	struct bio		io_inline_bio;	/* MUST BE LAST! */
-};
-
 extern const struct address_space_operations xfs_address_space_operations;
 extern const struct address_space_operations xfs_dax_aops;
 

fs/xfs/xfs_file.c

@@ -188,7 +188,7 @@ xfs_file_dio_aio_read(
 	file_accessed(iocb->ki_filp);
 
 	xfs_ilock(ip, XFS_IOLOCK_SHARED);
-	ret = iomap_dio_rw(iocb, to, &xfs_iomap_ops, NULL);
+	ret = iomap_dio_rw(iocb, to, &xfs_iomap_ops, NULL, is_sync_kiocb(iocb));
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	return ret;
@@ -547,15 +547,12 @@ xfs_file_dio_aio_write(
 	}
 
 	trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
-	ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, &xfs_dio_write_ops);
-
 	/*
-	 * If unaligned, this is the only IO in-flight. If it has not yet
-	 * completed, wait on it before we release the iolock to prevent
-	 * subsequent overlapping IO.
+	 * If unaligned, this is the only IO in-flight. Wait on it before we
+	 * release the iolock to prevent subsequent overlapping IO.
 	 */
-	if (ret == -EIOCBQUEUED && unaligned_io)
-		inode_dio_wait(inode);
+	ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, &xfs_dio_write_ops,
+			   is_sync_kiocb(iocb) || unaligned_io);
 out:
 	xfs_iunlock(ip, iolock);
 

fs/xfs/xfs_iomap.c

@@ -54,7 +54,7 @@ xfs_bmbt_to_iomap(
 	struct xfs_inode	*ip,
 	struct iomap		*iomap,
 	struct xfs_bmbt_irec	*imap,
-	bool			shared)
+	u16			flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 
@@ -79,12 +79,11 @@ xfs_bmbt_to_iomap(
 	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
 	iomap->bdev = xfs_find_bdev_for_inode(VFS_I(ip));
 	iomap->dax_dev = xfs_find_daxdev_for_inode(VFS_I(ip));
+	iomap->flags = flags;
 
 	if (xfs_ipincount(ip) &&
 	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
 		iomap->flags |= IOMAP_F_DIRTY;
-	if (shared)
-		iomap->flags |= IOMAP_F_SHARED;
 	return 0;
 }
 
@@ -540,6 +539,7 @@ xfs_file_iomap_begin_delay(
 	struct xfs_iext_cursor	icur, ccur;
 	xfs_fsblock_t		prealloc_blocks = 0;
 	bool			eof = false, cow_eof = false, shared = false;
+	u16			iomap_flags = 0;
 	int			whichfork = XFS_DATA_FORK;
 	int			error = 0;
 
@@ -707,22 +707,28 @@ xfs_file_iomap_begin_delay(
 	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
 	 * them out if the write happens to fail.
 	 */
-	iomap->flags |= IOMAP_F_NEW;
-	trace_xfs_iomap_alloc(ip, offset, count, whichfork,
-			whichfork == XFS_DATA_FORK ? &imap : &cmap);
+	if (whichfork == XFS_DATA_FORK) {
+		iomap_flags |= IOMAP_F_NEW;
+		trace_xfs_iomap_alloc(ip, offset, count, whichfork, &imap);
+	} else {
+		trace_xfs_iomap_alloc(ip, offset, count, whichfork, &cmap);
+	}
 done:
 	if (whichfork == XFS_COW_FORK) {
 		if (imap.br_startoff > offset_fsb) {
 			xfs_trim_extent(&cmap, offset_fsb,
 					imap.br_startoff - offset_fsb);
-			error = xfs_bmbt_to_iomap(ip, iomap, &cmap, true);
+			error = xfs_bmbt_to_iomap(ip, iomap, &cmap,
+					IOMAP_F_SHARED);
 			goto out_unlock;
 		}
 		/* ensure we only report blocks we have a reservation for */
 		xfs_trim_extent(&imap, cmap.br_startoff, cmap.br_blockcount);
 		shared = true;
 	}
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, shared);
+	if (shared)
+		iomap_flags |= IOMAP_F_SHARED;
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags);
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
@@ -922,7 +928,8 @@ xfs_file_iomap_begin(
 	loff_t			offset,
 	loff_t			length,
 	unsigned		flags,
-	struct iomap		*iomap)
+	struct iomap		*iomap,
+	struct iomap		*srcmap)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -930,6 +937,7 @@ xfs_file_iomap_begin(
 	xfs_fileoff_t		offset_fsb, end_fsb;
 	int			nimaps = 1, error = 0;
 	bool			shared = false;
+	u16			iomap_flags = 0;
 	unsigned		lockmode;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
@@ -1045,11 +1053,20 @@ xfs_file_iomap_begin(
 	if (error)
 		return error;
 
-	iomap->flags |= IOMAP_F_NEW;
+	iomap_flags |= IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap);
 
 out_finish:
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, shared);
+	/*
+	 * Writes that span EOF might trigger an IO size update on completion,
+	 * so consider them to be dirty for the purposes of O_DSYNC even if
+	 * there is no other metadata changes pending or have been made here.
+	 */
+	if ((flags & IOMAP_WRITE) && offset + length > i_size_read(inode))
+		iomap_flags |= IOMAP_F_DIRTY;
+	if (shared)
+		iomap_flags |= IOMAP_F_SHARED;
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags);
 
 out_found:
 	ASSERT(nimaps);
@@ -1145,7 +1162,8 @@ xfs_seek_iomap_begin(
 	loff_t			offset,
 	loff_t			length,
 	unsigned		flags,
-	struct iomap		*iomap)
+	struct iomap		*iomap,
+	struct iomap		*srcmap)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -1193,7 +1211,7 @@ xfs_seek_iomap_begin(
 		if (data_fsb < cow_fsb + cmap.br_blockcount)
 			end_fsb = min(end_fsb, data_fsb);
 		xfs_trim_extent(&cmap, offset_fsb, end_fsb);
-		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, true);
+		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
 		/*
 		 * This is a COW extent, so we must probe the page cache
 		 * because there could be dirty page cache being backed
@@ -1215,7 +1233,7 @@ xfs_seek_iomap_begin(
 	imap.br_state = XFS_EXT_NORM;
 done:
 	xfs_trim_extent(&imap, offset_fsb, end_fsb);
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, false);
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
 out_unlock:
 	xfs_iunlock(ip, lockmode);
 	return error;
@@ -1231,7 +1249,8 @@ xfs_xattr_iomap_begin(
 	loff_t			offset,
 	loff_t			length,
 	unsigned		flags,
-	struct iomap		*iomap)
+	struct iomap		*iomap,
+	struct iomap		*srcmap)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -1261,7 +1280,7 @@ xfs_xattr_iomap_begin(
 	if (error)
 		return error;
 	ASSERT(nimaps);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, false);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
 }
 
 const struct iomap_ops xfs_xattr_iomap_ops = {

fs/xfs/xfs_iomap.h

@@ -16,7 +16,7 @@ int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t,
 int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
 
 int xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
-		struct xfs_bmbt_irec *, bool shared);
+		struct xfs_bmbt_irec *, u16);
 xfs_extlen_t xfs_eof_alignment(struct xfs_inode *ip, xfs_extlen_t extsize);
 
 static inline xfs_filblks_t

fs/xfs/xfs_pnfs.c

@@ -178,7 +178,7 @@ xfs_fs_map_blocks(
 	}
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, false);
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
 	*device_generation = mp->m_generation;
 	return error;
 out_unlock:

fs/xfs/xfs_reflink.c

@@ -1442,7 +1442,7 @@ xfs_reflink_dirty_extents(
 			flen = XFS_FSB_TO_B(mp, rlen);
 			if (fpos + flen > isize)
 				flen = isize - fpos;
-			error = iomap_file_dirty(VFS_I(ip), fpos, flen,
+			error = iomap_file_unshare(VFS_I(ip), fpos, flen,
 					&xfs_iomap_ops);
 			xfs_ilock(ip, XFS_ILOCK_EXCL);
 			if (error)

fs/xfs/xfs_super.c

@@ -40,7 +40,6 @@
 #include <linux/parser.h>
 
 static const struct super_operations xfs_super_operations;
-struct bio_set xfs_ioend_bioset;
 
 static struct kset *xfs_kset;		/* top-level xfs sysfs dir */
 #ifdef DEBUG
@@ -1853,15 +1852,10 @@ MODULE_ALIAS_FS("xfs");
 STATIC int __init
 xfs_init_zones(void)
 {
-	if (bioset_init(&xfs_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
-			offsetof(struct xfs_ioend, io_inline_bio),
-			BIOSET_NEED_BVECS))
-		goto out;
-
 	xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t),
 						"xfs_log_ticket");
 	if (!xfs_log_ticket_zone)
-		goto out_free_ioend_bioset;
+		goto out;
 
 	xfs_bmap_free_item_zone = kmem_zone_init(
 			sizeof(struct xfs_extent_free_item),
@@ -1996,8 +1990,6 @@ xfs_init_zones(void)
 	kmem_zone_destroy(xfs_bmap_free_item_zone);
  out_destroy_log_ticket_zone:
 	kmem_zone_destroy(xfs_log_ticket_zone);
- out_free_ioend_bioset:
-	bioset_exit(&xfs_ioend_bioset);
  out:
 	return -ENOMEM;
 }
@@ -2028,7 +2020,6 @@ xfs_destroy_zones(void)
 	kmem_zone_destroy(xfs_btree_cur_zone);
 	kmem_zone_destroy(xfs_bmap_free_item_zone);
 	kmem_zone_destroy(xfs_log_ticket_zone);
-	bioset_exit(&xfs_ioend_bioset);
 }
 
 STATIC int __init

fs/xfs/xfs_trace.h

@@ -1158,71 +1158,6 @@ DEFINE_RW_EVENT(xfs_file_buffered_write);
 DEFINE_RW_EVENT(xfs_file_direct_write);
 DEFINE_RW_EVENT(xfs_file_dax_write);
 
-DECLARE_EVENT_CLASS(xfs_page_class,
-	TP_PROTO(struct inode *inode, struct page *page, unsigned long off,
-		 unsigned int len),
-	TP_ARGS(inode, page, off, len),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(xfs_ino_t, ino)
-		__field(pgoff_t, pgoff)
-		__field(loff_t, size)
-		__field(unsigned long, offset)
-		__field(unsigned int, length)
-	),
-	TP_fast_assign(
-		__entry->dev = inode->i_sb->s_dev;
-		__entry->ino = XFS_I(inode)->i_ino;
-		__entry->pgoff = page_offset(page);
-		__entry->size = i_size_read(inode);
-		__entry->offset = off;
-		__entry->length = len;
-	),
-	TP_printk("dev %d:%d ino 0x%llx pgoff 0x%lx size 0x%llx offset %lx "
-		  "length %x",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino,
-		  __entry->pgoff,
-		  __entry->size,
-		  __entry->offset,
-		  __entry->length)
-)
-
-#define DEFINE_PAGE_EVENT(name)		\
-DEFINE_EVENT(xfs_page_class, name,	\
-	TP_PROTO(struct inode *inode, struct page *page, unsigned long off, \
-		 unsigned int len),	\
-	TP_ARGS(inode, page, off, len))
-DEFINE_PAGE_EVENT(xfs_writepage);
-DEFINE_PAGE_EVENT(xfs_releasepage);
-DEFINE_PAGE_EVENT(xfs_invalidatepage);
-
-DECLARE_EVENT_CLASS(xfs_readpage_class,
-	TP_PROTO(struct inode *inode, int nr_pages),
-	TP_ARGS(inode, nr_pages),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(xfs_ino_t, ino)
-		__field(int, nr_pages)
-	),
-	TP_fast_assign(
-		__entry->dev = inode->i_sb->s_dev;
-		__entry->ino = inode->i_ino;
-		__entry->nr_pages = nr_pages;
-	),
-	TP_printk("dev %d:%d ino 0x%llx nr_pages %d",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino,
-		  __entry->nr_pages)
-)
-
-#define DEFINE_READPAGE_EVENT(name)		\
-DEFINE_EVENT(xfs_readpage_class, name,	\
-	TP_PROTO(struct inode *inode, int nr_pages), \
-	TP_ARGS(inode, nr_pages))
-DEFINE_READPAGE_EVENT(xfs_vm_readpage);
-DEFINE_READPAGE_EVENT(xfs_vm_readpages);
-
 DECLARE_EVENT_CLASS(xfs_imap_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count,
 		 int whichfork, struct xfs_bmbt_irec *irec),

include/linux/iomap.h

@@ -4,6 +4,7 @@
 
 #include <linux/atomic.h>
 #include <linux/bitmap.h>
+#include <linux/blk_types.h>
 #include <linux/mm.h>
 #include <linux/types.h>
 #include <linux/mm_types.h>
@@ -12,6 +13,7 @@
 struct address_space;
 struct fiemap_extent_info;
 struct inode;
+struct iomap_writepage_ctx;
 struct iov_iter;
 struct kiocb;
 struct page;
@@ -21,28 +23,45 @@ struct vm_fault;
 /*
  * Types of block ranges for iomap mappings:
  */
-#define IOMAP_HOLE	0x01	/* no blocks allocated, need allocation */
-#define IOMAP_DELALLOC	0x02	/* delayed allocation blocks */
-#define IOMAP_MAPPED	0x03	/* blocks allocated at @addr */
-#define IOMAP_UNWRITTEN	0x04	/* blocks allocated at @addr in unwritten state */
-#define IOMAP_INLINE	0x05	/* data inline in the inode */
+#define IOMAP_HOLE	0	/* no blocks allocated, need allocation */
+#define IOMAP_DELALLOC	1	/* delayed allocation blocks */
+#define IOMAP_MAPPED	2	/* blocks allocated at @addr */
+#define IOMAP_UNWRITTEN	3	/* blocks allocated at @addr in unwritten state */
+#define IOMAP_INLINE	4	/* data inline in the inode */
 
 /*
- * Flags for all iomap mappings:
+ * Flags reported by the file system from iomap_begin:
+ *
+ * IOMAP_F_NEW indicates that the blocks have been newly allocated and need
+ * zeroing for areas that no data is copied to.
  *
  * IOMAP_F_DIRTY indicates the inode has uncommitted metadata needed to access
  * written data and requires fdatasync to commit them to persistent storage.
+ * This needs to take into account metadata changes that *may* be made at IO
+ * completion, such as file size updates from direct IO.
+ *
+ * IOMAP_F_SHARED indicates that the blocks are shared, and will need to be
+ * unshared as part a write.
+ *
+ * IOMAP_F_MERGED indicates that the iomap contains the merge of multiple block
+ * mappings.
+ *
+ * IOMAP_F_BUFFER_HEAD indicates that the file system requires the use of
+ * buffer heads for this mapping.
  */
-#define IOMAP_F_NEW		0x01	/* blocks have been newly allocated */
-#define IOMAP_F_DIRTY		0x02	/* uncommitted metadata */
-#define IOMAP_F_BUFFER_HEAD	0x04	/* file system requires buffer heads */
-#define IOMAP_F_SIZE_CHANGED	0x08	/* file size has changed */
+#define IOMAP_F_NEW		0x01
+#define IOMAP_F_DIRTY		0x02
+#define IOMAP_F_SHARED		0x04
+#define IOMAP_F_MERGED		0x08
+#define IOMAP_F_BUFFER_HEAD	0x10
 
 /*
- * Flags that only need to be reported for IOMAP_REPORT requests:
+ * Flags set by the core iomap code during operations:
+ *
+ * IOMAP_F_SIZE_CHANGED indicates to the iomap_end method that the file size
+ * has changed as the result of this write operation.
  */
-#define IOMAP_F_MERGED		0x10	/* contains multiple blocks/extents */
-#define IOMAP_F_SHARED		0x20	/* block shared with another file */
+#define IOMAP_F_SIZE_CHANGED	0x100
 
 /*
  * Flags from 0x1000 up are for file system specific usage:
@@ -110,7 +129,8 @@ struct iomap_ops {
 	 * The actual length is returned in iomap->length.
 	 */
 	int (*iomap_begin)(struct inode *inode, loff_t pos, loff_t length,
-			unsigned flags, struct iomap *iomap);
+			unsigned flags, struct iomap *iomap,
+			struct iomap *srcmap);
 
 	/*
 	 * Commit and/or unreserve space previous allocated using iomap_begin.
@@ -126,29 +146,12 @@ struct iomap_ops {
  * Main iomap iterator function.
  */
 typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len,
-		void *data, struct iomap *iomap);
+		void *data, struct iomap *iomap, struct iomap *srcmap);
 
 loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length,
 		unsigned flags, const struct iomap_ops *ops, void *data,
 		iomap_actor_t actor);
 
-/*
- * Structure allocate for each page when block size < PAGE_SIZE to track
- * sub-page uptodate status and I/O completions.
- */
-struct iomap_page {
-	atomic_t		read_count;
-	atomic_t		write_count;
-	DECLARE_BITMAP(uptodate, PAGE_SIZE / 512);
-};
-
-static inline struct iomap_page *to_iomap_page(struct page *page)
-{
-	if (page_has_private(page))
-		return (struct iomap_page *)page_private(page);
-	return NULL;
-}
-
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops);
 int iomap_readpage(struct page *page, const struct iomap_ops *ops);
@@ -166,7 +169,7 @@ int iomap_migrate_page(struct address_space *mapping, struct page *newpage,
 #else
 #define iomap_migrate_page NULL
 #endif
-int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
+int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
 		bool *did_zero, const struct iomap_ops *ops);
@@ -183,6 +186,63 @@ loff_t iomap_seek_data(struct inode *inode, loff_t offset,
 sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
 		const struct iomap_ops *ops);
 
+/*
+ * Structure for writeback I/O completions.
+ */
+struct iomap_ioend {
+	struct list_head	io_list;	/* next ioend in chain */
+	u16			io_type;
+	u16			io_flags;	/* IOMAP_F_* */
+	struct inode		*io_inode;	/* file being written to */
+	size_t			io_size;	/* size of the extent */
+	loff_t			io_offset;	/* offset in the file */
+	void			*io_private;	/* file system private data */
+	struct bio		*io_bio;	/* bio being built */
+	struct bio		io_inline_bio;	/* MUST BE LAST! */
+};
+
+struct iomap_writeback_ops {
+	/*
+	 * Required, maps the blocks so that writeback can be performed on
+	 * the range starting at offset.
+	 */
+	int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode,
+				loff_t offset);
+
+	/*
+	 * Optional, allows the file systems to perform actions just before
+	 * submitting the bio and/or override the bio end_io handler for complex
+	 * operations like copy on write extent manipulation or unwritten extent
+	 * conversions.
+	 */
+	int (*prepare_ioend)(struct iomap_ioend *ioend, int status);
+
+	/*
+	 * Optional, allows the file system to discard state on a page where
+	 * we failed to submit any I/O.
+	 */
+	void (*discard_page)(struct page *page);
+};
+
+struct iomap_writepage_ctx {
+	struct iomap		iomap;
+	struct iomap_ioend	*ioend;
+	const struct iomap_writeback_ops *ops;
+};
+
+void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
+void iomap_ioend_try_merge(struct iomap_ioend *ioend,
+		struct list_head *more_ioends,
+		void (*merge_private)(struct iomap_ioend *ioend,
+				struct iomap_ioend *next));
+void iomap_sort_ioends(struct list_head *ioend_list);
+int iomap_writepage(struct page *page, struct writeback_control *wbc,
+		struct iomap_writepage_ctx *wpc,
+		const struct iomap_writeback_ops *ops);
+int iomap_writepages(struct address_space *mapping,
+		struct writeback_control *wbc, struct iomap_writepage_ctx *wpc,
+		const struct iomap_writeback_ops *ops);
+
 /*
  * Flags for direct I/O ->end_io:
  */
@@ -195,7 +255,8 @@ struct iomap_dio_ops {
 };
 
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
-		const struct iomap_ops *ops, const struct iomap_dio_ops *dops);
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion);
 int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
 
 #ifdef CONFIG_SWAP