1 files changed, 665 insertions, 91 deletions

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index e25901ae3ff4..d33c7bc5ee92 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2010 Red Hat, Inc.
- * Copyright (c) 2016-2018 Christoph Hellwig.
+ * Copyright (C) 2016-2019 Christoph Hellwig.
  */
 #include <linux/module.h>
 #include <linux/compiler.h>
@@ -12,13 +12,34 @@
 #include <linux/buffer_head.h>
 #include <linux/dax.h>
 #include <linux/writeback.h>
+#include <linux/list_sort.h>
 #include <linux/swap.h>
 #include <linux/bio.h>
 #include <linux/sched/signal.h>
 #include <linux/migrate.h>
+#include "trace.h"
 
 #include "../internal.h"
 
+/*
+ * Structure allocated 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;
+}
+
+static struct bio_set iomap_ioend_bioset;
+
 static struct iomap_page *
 iomap_page_create(struct inode *inode, struct page *page)
 {
@@ -203,9 +224,17 @@ iomap_read_inline_data(struct inode *inode, struct page *page,
 	SetPageUptodate(page);
 }
 
+static inline bool iomap_block_needs_zeroing(struct inode *inode,
+		struct iomap *iomap, loff_t pos)
+{
+	return iomap->type != IOMAP_MAPPED ||
+		(iomap->flags & IOMAP_F_NEW) ||
+		pos >= i_size_read(inode);
+}
+
 static loff_t
 iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
-		struct iomap *iomap)
+		struct iomap *iomap, struct iomap *srcmap)
 {
 	struct iomap_readpage_ctx *ctx = data;
 	struct page *page = ctx->cur_page;
@@ -226,7 +255,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	if (plen == 0)
 		goto done;
 
-	if (iomap->type != IOMAP_MAPPED || pos >= i_size_read(inode)) {
+	if (iomap_block_needs_zeroing(inode, iomap, pos)) {
 		zero_user(page, poff, plen);
 		iomap_set_range_uptodate(page, poff, plen);
 		goto done;
@@ -293,6 +322,8 @@ iomap_readpage(struct page *page, const struct iomap_ops *ops)
 	unsigned poff;
 	loff_t ret;
 
+	trace_iomap_readpage(page->mapping->host, 1);
+
 	for (poff = 0; poff < PAGE_SIZE; poff += ret) {
 		ret = iomap_apply(inode, page_offset(page) + poff,
 				PAGE_SIZE - poff, 0, ops, &ctx,
@@ -351,7 +382,7 @@ iomap_next_page(struct inode *inode, struct list_head *pages, loff_t pos,
 
 static loff_t
 iomap_readpages_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_readpage_ctx *ctx = data;
 	loff_t done, ret;
@@ -371,7 +402,7 @@ iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
 			ctx->cur_page_in_bio = false;
 		}
 		ret = iomap_readpage_actor(inode, pos + done, length - done,
-				ctx, iomap);
+				ctx, iomap, srcmap);
 	}
 
 	return done;
@@ -389,6 +420,8 @@ iomap_readpages(struct address_space *mapping, struct list_head *pages,
 	loff_t last = page_offset(list_entry(pages->next, struct page, lru));
 	loff_t length = last - pos + PAGE_SIZE, ret = 0;
 
+	trace_iomap_readpages(mapping->host, nr_pages);
+
 	while (length > 0) {
 		ret = iomap_apply(mapping->host, pos, length, 0, ops,
 				&ctx, iomap_readpages_actor);
@@ -455,6 +488,8 @@ EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);
 int
 iomap_releasepage(struct page *page, gfp_t gfp_mask)
 {
+	trace_iomap_releasepage(page->mapping->host, page, 0, 0);
+
 	/*
 	 * mm accommodates an old ext3 case where clean pages might not have had
 	 * the dirty bit cleared. Thus, it can send actual dirty pages to
@@ -470,6 +505,8 @@ EXPORT_SYMBOL_GPL(iomap_releasepage);
 void
 iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len)
 {
+	trace_iomap_invalidatepage(page->mapping->host, page, offset, len);
+
 	/*
 	 * If we are invalidating the entire page, clear the dirty state from it
 	 * and release it to avoid unnecessary buildup of the LRU.
@@ -511,6 +548,10 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage,
 EXPORT_SYMBOL_GPL(iomap_migrate_page);
 #endif /* CONFIG_MIGRATION */
 
+enum {
+	IOMAP_WRITE_F_UNSHARE		= (1 << 0),
+};
+
 static void
 iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 {
@@ -525,19 +566,12 @@ iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 }
 
 static int
-iomap_read_page_sync(struct inode *inode, loff_t block_start, struct page *page,
-		unsigned poff, unsigned plen, unsigned from, unsigned to,
-		struct iomap *iomap)
+iomap_read_page_sync(loff_t block_start, struct page *page, unsigned poff,
+		unsigned plen, struct iomap *iomap)
 {
 	struct bio_vec bvec;
 	struct bio bio;
 
-	if (iomap->type != IOMAP_MAPPED || block_start >= i_size_read(inode)) {
-		zero_user_segments(page, poff, from, to, poff + plen);
-		iomap_set_range_uptodate(page, poff, plen);
-		return 0;
-	}
-
 	bio_init(&bio, &bvec, 1);
 	bio.bi_opf = REQ_OP_READ;
 	bio.bi_iter.bi_sector = iomap_sector(iomap, block_start);
@@ -547,15 +581,15 @@ iomap_read_page_sync(struct inode *inode, loff_t block_start, struct page *page,
 }
 
 static int
-__iomap_write_begin(struct inode *inode, loff_t pos, unsigned len,
-		struct page *page, struct iomap *iomap)
+__iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags,
+		struct page *page, struct iomap *srcmap)
 {
 	struct iomap_page *iop = iomap_page_create(inode, page);
 	loff_t block_size = i_blocksize(inode);
 	loff_t block_start = pos & ~(block_size - 1);
 	loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1);
 	unsigned from = offset_in_page(pos), to = from + len, poff, plen;
-	int status = 0;
+	int status;
 
 	if (PageUptodate(page))
 		return 0;
@@ -566,29 +600,39 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len,
 		if (plen == 0)
 			break;
 
-		if ((from > poff && from < poff + plen) ||
-		    (to > poff && to < poff + plen)) {
-			status = iomap_read_page_sync(inode, block_start, page,
-					poff, plen, from, to, iomap);
-			if (status)
-				break;
+		if (!(flags & IOMAP_WRITE_F_UNSHARE) &&
+		    (from <= poff || from >= poff + plen) &&
+		    (to <= poff || to >= poff + plen))
+			continue;
+
+		if (iomap_block_needs_zeroing(inode, srcmap, block_start)) {
+			if (WARN_ON_ONCE(flags & IOMAP_WRITE_F_UNSHARE))
+				return -EIO;
+			zero_user_segments(page, poff, from, to, poff + plen);
+			iomap_set_range_uptodate(page, poff, plen);
+			continue;
 		}
 
+		status = iomap_read_page_sync(block_start, page, poff, plen,
+				srcmap);
+		if (status)
+			return status;
 	} while ((block_start += plen) < block_end);
 
-	return status;
+	return 0;
 }
 
 static int
 iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
-		struct page **pagep, struct iomap *iomap)
+		struct page **pagep, struct iomap *iomap, struct iomap *srcmap)
 {
 	const struct iomap_page_ops *page_ops = iomap->page_ops;
-	pgoff_t index = pos >> PAGE_SHIFT;
 	struct page *page;
 	int status = 0;
 
 	BUG_ON(pos + len > iomap->offset + iomap->length);
+	if (srcmap != iomap)
+		BUG_ON(pos + len > srcmap->offset + srcmap->length);
 
 	if (fatal_signal_pending(current))
 		return -EINTR;
@@ -599,18 +643,20 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 			return status;
 	}
 
-	page = grab_cache_page_write_begin(inode->i_mapping, index, flags);
+	page = grab_cache_page_write_begin(inode->i_mapping, pos >> PAGE_SHIFT,
+			AOP_FLAG_NOFS);
 	if (!page) {
 		status = -ENOMEM;
 		goto out_no_page;
 	}
 
-	if (iomap->type == IOMAP_INLINE)
-		iomap_read_inline_data(inode, page, iomap);
+	if (srcmap->type == IOMAP_INLINE)
+		iomap_read_inline_data(inode, page, srcmap);
 	else if (iomap->flags & IOMAP_F_BUFFER_HEAD)
-		status = __block_write_begin_int(page, pos, len, NULL, iomap);
+		status = __block_write_begin_int(page, pos, len, NULL, srcmap);
 	else
-		status = __iomap_write_begin(inode, pos, len, page, iomap);
+		status = __iomap_write_begin(inode, pos, len, flags, page,
+				srcmap);
 
 	if (unlikely(status))
 		goto out_unlock;
@@ -656,7 +702,7 @@ EXPORT_SYMBOL_GPL(iomap_set_page_dirty);
 
 static int
 __iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
-		unsigned copied, struct page *page, struct iomap *iomap)
+		unsigned copied, struct page *page)
 {
 	flush_dcache_page(page);
 
@@ -696,20 +742,20 @@ iomap_write_end_inline(struct inode *inode, struct page *page,
 }
 
 static int
-iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
-		unsigned copied, struct page *page, struct iomap *iomap)
+iomap_write_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied,
+		struct page *page, struct iomap *iomap, struct iomap *srcmap)
 {
 	const struct iomap_page_ops *page_ops = iomap->page_ops;
 	loff_t old_size = inode->i_size;
 	int ret;
 
-	if (iomap->type == IOMAP_INLINE) {
+	if (srcmap->type == IOMAP_INLINE) {
 		ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
-	} else if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
+	} else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
 		ret = block_write_end(NULL, inode->i_mapping, pos, len, copied,
 				page, NULL);
 	} else {
-		ret = __iomap_write_end(inode, pos, len, copied, page, iomap);
+		ret = __iomap_write_end(inode, pos, len, copied, page);
 	}
 
 	/*
@@ -736,12 +782,11 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 
 static loff_t
 iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
-		struct iomap *iomap)
+		struct iomap *iomap, struct iomap *srcmap)
 {
 	struct iov_iter *i = data;
 	long status = 0;
 	ssize_t written = 0;
-	unsigned int flags = AOP_FLAG_NOFS;
 
 	do {
 		struct page *page;
@@ -771,8 +816,8 @@ again:
 			break;
 		}
 
-		status = iomap_write_begin(inode, pos, bytes, flags, &page,
-				iomap);
+		status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap,
+				srcmap);
 		if (unlikely(status))
 			break;
 
@@ -783,8 +828,8 @@ again:
 
 		flush_dcache_page(page);
 
-		status = iomap_write_end(inode, pos, bytes, copied, page,
-				iomap);
+		status = iomap_write_end(inode, pos, bytes, copied, page, iomap,
+				srcmap);
 		if (unlikely(status < 0))
 			break;
 		copied = status;
@@ -835,50 +880,32 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *iter,
 }
 EXPORT_SYMBOL_GPL(iomap_file_buffered_write);
 
-static struct page *
-__iomap_read_page(struct inode *inode, loff_t offset)
-{
-	struct address_space *mapping = inode->i_mapping;
-	struct page *page;
-
-	page = read_mapping_page(mapping, offset >> PAGE_SHIFT, NULL);
-	if (IS_ERR(page))
-		return page;
-	if (!PageUptodate(page)) {
-		put_page(page);
-		return ERR_PTR(-EIO);
-	}
-	return page;
-}
-
 static loff_t
-iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
-		struct iomap *iomap)
+iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
+		struct iomap *iomap, struct iomap *srcmap)
 {
 	long status = 0;
 	ssize_t written = 0;
 
-	do {
-		struct page *page, *rpage;
-		unsigned long offset;	/* Offset into pagecache page */
-		unsigned long bytes;	/* Bytes to write to page */
-
-		offset = offset_in_page(pos);
-		bytes = min_t(loff_t, PAGE_SIZE - offset, length);
+	/* don't bother with blocks that are not shared to start with */
+	if (!(iomap->flags & IOMAP_F_SHARED))
+		return length;
+	/* don't bother with holes or unwritten extents */
+	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
+		return length;
 
-		rpage = __iomap_read_page(inode, pos);
-		if (IS_ERR(rpage))
-			return PTR_ERR(rpage);
+	do {
+		unsigned long offset = offset_in_page(pos);
+		unsigned long bytes = min_t(loff_t, PAGE_SIZE - offset, length);
+		struct page *page;
 
 		status = iomap_write_begin(inode, pos, bytes,
-					   AOP_FLAG_NOFS, &page, iomap);
-		put_page(rpage);
+				IOMAP_WRITE_F_UNSHARE, &page, iomap, srcmap);
 		if (unlikely(status))
 			return status;
 
-		WARN_ON_ONCE(!PageUptodate(page));
-
-		status = iomap_write_end(inode, pos, bytes, bytes, page, iomap);
+		status = iomap_write_end(inode, pos, bytes, bytes, page, iomap,
+				srcmap);
 		if (unlikely(status <= 0)) {
 			if (WARN_ON_ONCE(status == 0))
 				return -EIO;
@@ -898,14 +925,14 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 }
 
 int
-iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
+iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops)
 {
 	loff_t ret;
 
 	while (len) {
 		ret = iomap_apply(inode, pos, len, IOMAP_WRITE, ops, NULL,
-				iomap_dirty_actor);
+				iomap_unshare_actor);
 		if (ret <= 0)
 			return ret;
 		pos += ret;
@@ -914,23 +941,22 @@ iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(iomap_file_dirty);
+EXPORT_SYMBOL_GPL(iomap_file_unshare);
 
 static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
-		unsigned bytes, struct iomap *iomap)
+		unsigned bytes, struct iomap *iomap, struct iomap *srcmap)
 {
 	struct page *page;
 	int status;
 
-	status = iomap_write_begin(inode, pos, bytes, AOP_FLAG_NOFS, &page,
-				   iomap);
+	status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, srcmap);
 	if (status)
 		return status;
 
 	zero_user(page, offset, bytes);
 	mark_page_accessed(page);
 
-	return iomap_write_end(inode, pos, bytes, bytes, page, iomap);
+	return iomap_write_end(inode, pos, bytes, bytes, page, iomap, srcmap);
 }
 
 static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
@@ -942,14 +968,14 @@ static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
 
 static loff_t
 iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
-		void *data, struct iomap *iomap)
+		void *data, struct iomap *iomap, struct iomap *srcmap)
 {
 	bool *did_zero = data;
 	loff_t written = 0;
 	int status;
 
 	/* already zeroed?  we're done. */
-	if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN)
+	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
 		return count;
 
 	do {
@@ -961,7 +987,8 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
 		if (IS_DAX(inode))
 			status = iomap_dax_zero(pos, offset, bytes, iomap);
 		else
-			status = iomap_zero(inode, pos, offset, bytes, iomap);
+			status = iomap_zero(inode, pos, offset, bytes, iomap,
+					srcmap);
 		if (status < 0)
 			return status;
 
@@ -1011,7 +1038,7 @@ EXPORT_SYMBOL_GPL(iomap_truncate_page);
 
 static loff_t
 iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
-		void *data, struct iomap *iomap)
+		void *data, struct iomap *iomap, struct iomap *srcmap)
 {
 	struct page *page = data;
 	int ret;
@@ -1040,20 +1067,19 @@ vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
 
 	lock_page(page);
 	size = i_size_read(inode);
-	if ((page->mapping != inode->i_mapping) ||
-	    (page_offset(page) > size)) {
+	offset = page_offset(page);
+	if (page->mapping != inode->i_mapping || offset > size) {
 		/* We overload EFAULT to mean page got truncated */
 		ret = -EFAULT;
 		goto out_unlock;
 	}
 
 	/* page is wholly or partially inside EOF */
-	if (((page->index + 1) << PAGE_SHIFT) > size)
+	if (offset > size - PAGE_SIZE)
 		length = offset_in_page(size);
 	else
 		length = PAGE_SIZE;
 
-	offset = page_offset(page);
 	while (length > 0) {
 		ret = iomap_apply(inode, offset, length,
 				IOMAP_WRITE | IOMAP_FAULT, ops, page,
@@ -1071,3 +1097,551 @@ out_unlock:
 	return block_page_mkwrite_return(ret);
 }
 EXPORT_SYMBOL_GPL(iomap_page_mkwrite);
+
+static void
+iomap_finish_page_writeback(struct inode *inode, struct page *page,
+		int error)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+
+	if (error) {
+		SetPageError(page);
+		mapping_set_error(inode->i_mapping, -EIO);
+	}
+
+	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop);
+	WARN_ON_ONCE(iop && atomic_read(&iop->write_count) <= 0);
+
+	if (!iop || atomic_dec_and_test(&iop->write_count))
+		end_page_writeback(page);
+}
+
+/*
+ * We're now finished for good with this ioend structure.  Update the page
+ * state, release holds on bios, and finally free up memory.  Do not use the
+ * ioend after this.
+ */
+static void
+iomap_finish_ioend(struct iomap_ioend *ioend, int error)
+{
+	struct inode *inode = ioend->io_inode;
+	struct bio *bio = &ioend->io_inline_bio;
+	struct bio *last = ioend->io_bio, *next;
+	u64 start = bio->bi_iter.bi_sector;
+	bool quiet = bio_flagged(bio, BIO_QUIET);
+
+	for (bio = &ioend->io_inline_bio; bio; bio = next) {
+		struct bio_vec *bv;
+		struct bvec_iter_all iter_all;
+
+		/*
+		 * For the last bio, bi_private points to the ioend, so we
+		 * need to explicitly end the iteration here.
+		 */
+		if (bio == last)
+			next = NULL;
+		else
+			next = bio->bi_private;
+
+		/* walk each page on bio, ending page IO on them */
+		bio_for_each_segment_all(bv, bio, iter_all)
+			iomap_finish_page_writeback(inode, bv->bv_page, error);
+		bio_put(bio);
+	}
+
+	if (unlikely(error && !quiet)) {
+		printk_ratelimited(KERN_ERR
+"%s: writeback error on inode %lu, offset %lld, sector %llu",
+			inode->i_sb->s_id, inode->i_ino, ioend->io_offset,
+			start);
+	}
+}
+
+void
+iomap_finish_ioends(struct iomap_ioend *ioend, int error)
+{
+	struct list_head tmp;
+
+	list_replace_init(&ioend->io_list, &tmp);
+	iomap_finish_ioend(ioend, error);
+
+	while (!list_empty(&tmp)) {
+		ioend = list_first_entry(&tmp, struct iomap_ioend, io_list);
+		list_del_init(&ioend->io_list);
+		iomap_finish_ioend(ioend, error);
+	}
+}
+EXPORT_SYMBOL_GPL(iomap_finish_ioends);
+
+/*
+ * We can merge two adjacent ioends if they have the same set of work to do.
+ */
+static bool
+iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next)
+{
+	if (ioend->io_bio->bi_status != next->io_bio->bi_status)
+		return false;
+	if ((ioend->io_flags & IOMAP_F_SHARED) ^
+	    (next->io_flags & IOMAP_F_SHARED))
+		return false;
+	if ((ioend->io_type == IOMAP_UNWRITTEN) ^
+	    (next->io_type == IOMAP_UNWRITTEN))
+		return false;
+	if (ioend->io_offset + ioend->io_size != next->io_offset)
+		return false;
+	return true;
+}
+
+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))
+{
+	struct iomap_ioend *next;
+
+	INIT_LIST_HEAD(&ioend->io_list);
+
+	while ((next = list_first_entry_or_null(more_ioends, struct iomap_ioend,
+			io_list))) {
+		if (!iomap_ioend_can_merge(ioend, next))
+			break;
+		list_move_tail(&next->io_list, &ioend->io_list);
+		ioend->io_size += next->io_size;
+		if (next->io_private && merge_private)
+			merge_private(ioend, next);
+	}
+}
+EXPORT_SYMBOL_GPL(iomap_ioend_try_merge);
+
+static int
+iomap_ioend_compare(void *priv, struct list_head *a, struct list_head *b)
+{
+	struct iomap_ioend *ia = container_of(a, struct iomap_ioend, io_list);
+	struct iomap_ioend *ib = container_of(b, struct iomap_ioend, io_list);
+
+	if (ia->io_offset < ib->io_offset)
+		return -1;
+	if (ia->io_offset > ib->io_offset)
+		return 1;
+	return 0;
+}
+
+void
+iomap_sort_ioends(struct list_head *ioend_list)
+{
+	list_sort(NULL, ioend_list, iomap_ioend_compare);
+}
+EXPORT_SYMBOL_GPL(iomap_sort_ioends);
+
+static void iomap_writepage_end_bio(struct bio *bio)
+{
+	struct iomap_ioend *ioend = bio->bi_private;
+
+	iomap_finish_ioend(ioend, blk_status_to_errno(bio->bi_status));
+}
+
+/*
+ * Submit the final bio for an ioend.
+ *
+ * If @error is non-zero, it means that we have a situation where some part of
+ * the submission process has failed after we have marked paged for writeback
+ * and unlocked them.  In this situation, we need to fail the bio instead of
+ * submitting it.  This typically only happens on a filesystem shutdown.
+ */
+static int
+iomap_submit_ioend(struct iomap_writepage_ctx *wpc, struct iomap_ioend *ioend,
+		int error)
+{
+	ioend->io_bio->bi_private = ioend;
+	ioend->io_bio->bi_end_io = iomap_writepage_end_bio;
+
+	if (wpc->ops->prepare_ioend)
+		error = wpc->ops->prepare_ioend(ioend, error);
+	if (error) {
+		/*
+		 * If we are failing the IO now, just mark the ioend with an
+		 * error and finish it.  This will run IO completion immediately
+		 * as there is only one reference to the ioend at this point in
+		 * time.
+		 */
+		ioend->io_bio->bi_status = errno_to_blk_status(error);
+		bio_endio(ioend->io_bio);
+		return error;
+	}
+
+	submit_bio(ioend->io_bio);
+	return 0;
+}
+
+static struct iomap_ioend *
+iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc,
+		loff_t offset, sector_t sector, struct writeback_control *wbc)
+{
+	struct iomap_ioend *ioend;
+	struct bio *bio;
+
+	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &iomap_ioend_bioset);
+	bio_set_dev(bio, wpc->iomap.bdev);
+	bio->bi_iter.bi_sector = sector;
+	bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
+	bio->bi_write_hint = inode->i_write_hint;
+	wbc_init_bio(wbc, bio);
+
+	ioend = container_of(bio, struct iomap_ioend, io_inline_bio);
+	INIT_LIST_HEAD(&ioend->io_list);
+	ioend->io_type = wpc->iomap.type;
+	ioend->io_flags = wpc->iomap.flags;
+	ioend->io_inode = inode;
+	ioend->io_size = 0;
+	ioend->io_offset = offset;
+	ioend->io_private = NULL;
+	ioend->io_bio = bio;
+	return ioend;
+}
+
+/*
+ * Allocate a new bio, and chain the old bio to the new one.
+ *
+ * Note that we have to do perform the chaining in this unintuitive order
+ * so that the bi_private linkage is set up in the right direction for the
+ * traversal in iomap_finish_ioend().
+ */
+static struct bio *
+iomap_chain_bio(struct bio *prev)
+{
+	struct bio *new;
+
+	new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
+	bio_copy_dev(new, prev);/* also copies over blkcg information */
+	new->bi_iter.bi_sector = bio_end_sector(prev);
+	new->bi_opf = prev->bi_opf;
+	new->bi_write_hint = prev->bi_write_hint;
+
+	bio_chain(prev, new);
+	bio_get(prev);		/* for iomap_finish_ioend */
+	submit_bio(prev);
+	return new;
+}
+
+static bool
+iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset,
+		sector_t sector)
+{
+	if ((wpc->iomap.flags & IOMAP_F_SHARED) !=
+	    (wpc->ioend->io_flags & IOMAP_F_SHARED))
+		return false;
+	if (wpc->iomap.type != wpc->ioend->io_type)
+		return false;
+	if (offset != wpc->ioend->io_offset + wpc->ioend->io_size)
+		return false;
+	if (sector != bio_end_sector(wpc->ioend->io_bio))
+		return false;
+	return true;
+}
+
+/*
+ * Test to see if we have an existing ioend structure that we could append to
+ * first, otherwise finish off the current ioend and start another.
+ */
+static void
+iomap_add_to_ioend(struct inode *inode, loff_t offset, struct page *page,
+		struct iomap_page *iop, struct iomap_writepage_ctx *wpc,
+		struct writeback_control *wbc, struct list_head *iolist)
+{
+	sector_t sector = iomap_sector(&wpc->iomap, offset);
+	unsigned len = i_blocksize(inode);
+	unsigned poff = offset & (PAGE_SIZE - 1);
+	bool merged, same_page = false;
+
+	if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, offset, sector)) {
+		if (wpc->ioend)
+			list_add(&wpc->ioend->io_list, iolist);
+		wpc->ioend = iomap_alloc_ioend(inode, wpc, offset, sector, wbc);
+	}
+
+	merged = __bio_try_merge_page(wpc->ioend->io_bio, page, len, poff,
+			&same_page);
+	if (iop && !same_page)
+		atomic_inc(&iop->write_count);
+
+	if (!merged) {
+		if (bio_full(wpc->ioend->io_bio, len)) {
+			wpc->ioend->io_bio =
+				iomap_chain_bio(wpc->ioend->io_bio);
+		}
+		bio_add_page(wpc->ioend->io_bio, page, len, poff);
+	}
+
+	wpc->ioend->io_size += len;
+	wbc_account_cgroup_owner(wbc, page, len);
+}
+
+/*
+ * We implement an immediate ioend submission policy here to avoid needing to
+ * chain multiple ioends and hence nest mempool allocations which can violate
+ * forward progress guarantees we need to provide. The current ioend we are
+ * adding blocks to is cached on the writepage context, and if the new block
+ * does not append to the cached ioend it will create a new ioend and cache that
+ * instead.
+ *
+ * If a new ioend is created and cached, the old ioend is returned and queued
+ * locally for submission once the entire page is processed or an error has been
+ * detected.  While ioends are submitted immediately after they are completed,
+ * batching optimisations are provided by higher level block plugging.
+ *
+ * At the end of a writeback pass, there will be a cached ioend remaining on the
+ * writepage context that the caller will need to submit.
+ */
+static int
+iomap_writepage_map(struct iomap_writepage_ctx *wpc,
+		struct writeback_control *wbc, struct inode *inode,
+		struct page *page, u64 end_offset)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+	struct iomap_ioend *ioend, *next;
+	unsigned len = i_blocksize(inode);
+	u64 file_offset; /* file offset of page */
+	int error = 0, count = 0, i;
+	LIST_HEAD(submit_list);
+
+	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop);
+	WARN_ON_ONCE(iop && atomic_read(&iop->write_count) != 0);
+
+	/*
+	 * Walk through the page to find areas to write back. If we run off the
+	 * end of the current map or find the current map invalid, grab a new
+	 * one.
+	 */
+	for (i = 0, file_offset = page_offset(page);
+	     i < (PAGE_SIZE >> inode->i_blkbits) && file_offset < end_offset;
+	     i++, file_offset += len) {
+		if (iop && !test_bit(i, iop->uptodate))
+			continue;
+
+		error = wpc->ops->map_blocks(wpc, inode, file_offset);
+		if (error)
+			break;
+		if (WARN_ON_ONCE(wpc->iomap.type == IOMAP_INLINE))
+			continue;
+		if (wpc->iomap.type == IOMAP_HOLE)
+			continue;
+		iomap_add_to_ioend(inode, file_offset, page, iop, wpc, wbc,
+				 &submit_list);
+		count++;
+	}
+
+	WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list));
+	WARN_ON_ONCE(!PageLocked(page));
+	WARN_ON_ONCE(PageWriteback(page));
+
+	/*
+	 * We cannot cancel the ioend directly here on error.  We may have
+	 * already set other pages under writeback and hence we have to run I/O
+	 * completion to mark the error state of the pages under writeback
+	 * appropriately.
+	 */
+	if (unlikely(error)) {
+		if (!count) {
+			/*
+			 * If the current page hasn't been added to ioend, it
+			 * won't be affected by I/O completions and we must
+			 * discard and unlock it right here.
+			 */
+			if (wpc->ops->discard_page)
+				wpc->ops->discard_page(page);
+			ClearPageUptodate(page);
+			unlock_page(page);
+			goto done;
+		}
+
+		/*
+		 * If the page was not fully cleaned, we need to ensure that the
+		 * higher layers come back to it correctly.  That means we need
+		 * to keep the page dirty, and for WB_SYNC_ALL writeback we need
+		 * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed
+		 * so another attempt to write this page in this writeback sweep
+		 * will be made.
+		 */
+		set_page_writeback_keepwrite(page);
+	} else {
+		clear_page_dirty_for_io(page);
+		set_page_writeback(page);
+	}
+
+	unlock_page(page);
+
+	/*
+	 * Preserve the original error if there was one, otherwise catch
+	 * submission errors here and propagate into subsequent ioend
+	 * submissions.
+	 */
+	list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
+		int error2;
+
+		list_del_init(&ioend->io_list);
+		error2 = iomap_submit_ioend(wpc, ioend, error);
+		if (error2 && !error)
+			error = error2;
+	}
+
+	/*
+	 * We can end up here with no error and nothing to write only if we race
+	 * with a partial page truncate on a sub-page block sized filesystem.
+	 */
+	if (!count)
+		end_page_writeback(page);
+done:
+	mapping_set_error(page->mapping, error);
+	return error;
+}
+
+/*
+ * Write out a dirty page.
+ *
+ * For delalloc space on the page we need to allocate space and flush it.
+ * For unwritten space on the page we need to start the conversion to
+ * regular allocated space.
+ */
+static int
+iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data)
+{
+	struct iomap_writepage_ctx *wpc = data;
+	struct inode *inode = page->mapping->host;
+	pgoff_t end_index;
+	u64 end_offset;
+	loff_t offset;
+
+	trace_iomap_writepage(inode, page, 0, 0);
+
+	/*
+	 * Refuse to write the page out if we are called from reclaim context.
+	 *
+	 * This avoids stack overflows when called from deeply used stacks in
+	 * random callers for direct reclaim or memcg reclaim.  We explicitly
+	 * allow reclaim from kswapd as the stack usage there is relatively low.
+	 *
+	 * This should never happen except in the case of a VM regression so
+	 * warn about it.
+	 */
+	if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
+			PF_MEMALLOC))
+		goto redirty;
+
+	/*
+	 * Given that we do not allow direct reclaim to call us, we should
+	 * never be called in a recursive filesystem reclaim context.
+	 */
+	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS))
+		goto redirty;
+
+	/*
+	 * Is this page beyond the end of the file?
+	 *
+	 * The page index is less than the end_index, adjust the end_offset
+	 * to the highest offset that this page should represent.
+	 * -----------------------------------------------------
+	 * |			file mapping	       | <EOF> |
+	 * -----------------------------------------------------
+	 * | Page ... | Page N-2 | Page N-1 |  Page N  |       |
+	 * ^--------------------------------^----------|--------
+	 * |     desired writeback range    |      see else    |
+	 * ---------------------------------^------------------|
+	 */
+	offset = i_size_read(inode);
+	end_index = offset >> PAGE_SHIFT;
+	if (page->index < end_index)
+		end_offset = (loff_t)(page->index + 1) << PAGE_SHIFT;
+	else {
+		/*
+		 * Check whether the page to write out is beyond or straddles
+		 * i_size or not.
+		 * -------------------------------------------------------
+		 * |		file mapping		        | <EOF>  |
+		 * -------------------------------------------------------
+		 * | Page ... | Page N-2 | Page N-1 |  Page N   | Beyond |
+		 * ^--------------------------------^-----------|---------
+		 * |				    |      Straddles     |
+		 * ---------------------------------^-----------|--------|
+		 */
+		unsigned offset_into_page = offset & (PAGE_SIZE - 1);
+
+		/*
+		 * Skip the page if it is fully outside i_size, e.g. due to a
+		 * truncate operation that is in progress. We must redirty the
+		 * page so that reclaim stops reclaiming it. Otherwise
+		 * iomap_vm_releasepage() is called on it and gets confused.
+		 *
+		 * Note that the end_index is unsigned long, it would overflow
+		 * if the given offset is greater than 16TB on 32-bit system
+		 * and if we do check the page is fully outside i_size or not
+		 * via "if (page->index >= end_index + 1)" as "end_index + 1"
+		 * will be evaluated to 0.  Hence this page will be redirtied
+		 * and be written out repeatedly which would result in an
+		 * infinite loop, the user program that perform this operation
+		 * will hang.  Instead, we can verify this situation by checking
+		 * if the page to write is totally beyond the i_size or if it's
+		 * offset is just equal to the EOF.
+		 */
+		if (page->index > end_index ||
+		    (page->index == end_index && offset_into_page == 0))
+			goto redirty;
+
+		/*
+		 * The page straddles i_size.  It must be zeroed out on each
+		 * and every writepage invocation because it may be mmapped.
+		 * "A file is mapped in multiples of the page size.  For a file
+		 * that is not a multiple of the page size, the remaining
+		 * memory is zeroed when mapped, and writes to that region are
+		 * not written out to the file."
+		 */
+		zero_user_segment(page, offset_into_page, PAGE_SIZE);
+
+		/* Adjust the end_offset to the end of file */
+		end_offset = offset;
+	}
+
+	return iomap_writepage_map(wpc, wbc, inode, page, end_offset);
+
+redirty:
+	redirty_page_for_writepage(wbc, page);
+	unlock_page(page);
+	return 0;
+}
+
+int
+iomap_writepage(struct page *page, struct writeback_control *wbc,
+		struct iomap_writepage_ctx *wpc,
+		const struct iomap_writeback_ops *ops)
+{
+	int ret;
+
+	wpc->ops = ops;
+	ret = iomap_do_writepage(page, wbc, wpc);
+	if (!wpc->ioend)
+		return ret;
+	return iomap_submit_ioend(wpc, wpc->ioend, ret);
+}
+EXPORT_SYMBOL_GPL(iomap_writepage);
+
+int
+iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
+		struct iomap_writepage_ctx *wpc,
+		const struct iomap_writeback_ops *ops)
+{
+	int			ret;
+
+	wpc->ops = ops;
+	ret = write_cache_pages(mapping, wbc, iomap_do_writepage, wpc);
+	if (!wpc->ioend)
+		return ret;
+	return iomap_submit_ioend(wpc, wpc->ioend, ret);
+}
+EXPORT_SYMBOL_GPL(iomap_writepages);
+
+static int __init iomap_init(void)
+{
+	return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
+			   offsetof(struct iomap_ioend, io_inline_bio),
+			   BIOSET_NEED_BVECS);
+}
+fs_initcall(iomap_init);