[PATCH] iomap: support tail packing inline read

[Christoph Hellwig]

This tries to add tail packing inline read to iomap, which can support
several inline tail blocks. Similar to the previous approach, it cleans
post-EOF in one iteration.

The write path remains untouched since EROFS cannot be used for testing.
It'd be better to be implemented if upcoming real users care rather than
leave untested dead code around.

Signed-off-by: Gao Xiang <hsiangkao@xxxxxxxxxxxxxxxxx>
---
 fs/iomap/buffered-io.c | 59 ++++++++++++++++++++++++++++--------------
 fs/iomap/direct-io.c   |  6 +++--
 2 files changed, 43 insertions(+), 22 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 87ccb3438bec..95d4d0a76dbc 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -207,23 +207,25 @@ struct iomap_readpage_ctx {
 
 static void
 iomap_read_inline_data(struct inode *inode, struct page *page,
-		struct iomap *iomap)
+		struct iomap *iomap, loff_t pos)
 {
-	size_t size = i_size_read(inode);
+	unsigned int size = iomap->length + pos - iomap->offset;
+	unsigned int poff = offset_in_page(pos);
 	void *addr;
 
-	if (PageUptodate(page))
-		return;
-
-	BUG_ON(page_has_private(page));
-	BUG_ON(page->index);
-	BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data));
+	/* inline source data must be inside a single page */
+	BUG_ON(iomap->length > PAGE_SIZE - offset_in_page(iomap->inline_data));
+	/* handle tail-packing blocks cross the current page into the next */
+	if (size > PAGE_SIZE - poff)
+		size = PAGE_SIZE - poff;
 
 	addr = kmap_atomic(page);
-	memcpy(addr, iomap->inline_data, size);
-	memset(addr + size, 0, PAGE_SIZE - size);
+	memcpy(addr + poff, iomap->inline_data - iomap->offset + pos, size);
+	memset(addr + poff + size, 0, PAGE_SIZE - poff - size);
 	kunmap_atomic(addr);
-	SetPageUptodate(page);
+	flush_dcache_page(page);
+
+	iomap_set_range_uptodate(page, poff, PAGE_SIZE - poff);
 }
 
 static inline bool iomap_block_needs_zeroing(struct inode *inode,
@@ -240,24 +242,29 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 {
 	struct iomap_readpage_ctx *ctx = data;
 	struct page *page = ctx->cur_page;
-	struct iomap_page *iop;
+	struct iomap_page *iop = NULL;
 	bool same_page = false, is_contig = false;
 	loff_t orig_pos = pos;
 	unsigned poff, plen;
 	sector_t sector;
 
-	if (iomap->type == IOMAP_INLINE) {
-		WARN_ON_ONCE(pos);
-		iomap_read_inline_data(inode, page, iomap);
-		return PAGE_SIZE;
-	}
+	if (iomap->type == IOMAP_INLINE && !pos)
+		WARN_ON_ONCE(to_iomap_page(page) != NULL);
+	else
+		iop = iomap_page_create(inode, page);
 
-	/* zero post-eof blocks as the page may be mapped */
-	iop = iomap_page_create(inode, page);
+	/* needs to skip some leading uptodated blocks */
 	iomap_adjust_read_range(inode, iop, &pos, length, &poff, &plen);
 	if (plen == 0)
 		goto done;
 
+	if (iomap->type == IOMAP_INLINE) {
+		iomap_read_inline_data(inode, page, iomap, pos);
+		plen = PAGE_SIZE - poff;
+		goto done;
+	}
+
+	/* zero post-eof blocks as the page may be mapped */
 	if (iomap_block_needs_zeroing(inode, iomap, pos)) {
 		zero_user(page, poff, plen);
 		iomap_set_range_uptodate(page, poff, plen);
@@ -589,6 +596,18 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags,
 	return 0;
 }
 
+static int iomap_write_begin_inline(struct inode *inode, loff_t pos,
+		struct page *page, struct iomap *srcmap)
+{
+	/* needs more work for the tailpacking case, disable for now */
+	if (WARN_ON_ONCE(pos != 0))
+		return -EIO;
+	if (PageUptodate(page))
+		return 0;
+	iomap_read_inline_data(inode, page, srcmap, pos);
+	return 0;
+}
+
 static int
 iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 		struct page **pagep, struct iomap *iomap, struct iomap *srcmap)
@@ -618,7 +637,7 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 	}
 
 	if (srcmap->type == IOMAP_INLINE)
-		iomap_read_inline_data(inode, page, srcmap);
+		status = iomap_write_begin_inline(inode, pos, page, srcmap);
 	else if (iomap->flags & IOMAP_F_BUFFER_HEAD)
 		status = __block_write_begin_int(page, pos, len, NULL, srcmap);
 	else
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 9398b8c31323..a70a8632df22 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -380,7 +380,8 @@ iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct iov_iter *iter = dio->submit.iter;
 	size_t copied;
 
-	BUG_ON(pos + length > PAGE_SIZE - offset_in_page(iomap->inline_data));
+	/* inline data must be inside a single page */
+	BUG_ON(length > PAGE_SIZE - offset_in_page(iomap->inline_data));
 
 	if (dio->flags & IOMAP_DIO_WRITE) {
 		loff_t size = inode->i_size;
@@ -394,7 +395,8 @@ iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length,
 			mark_inode_dirty(inode);
 		}
 	} else {
-		copied = copy_to_iter(iomap->inline_data + pos, length, iter);
+		copied = copy_to_iter(iomap->inline_data + pos - iomap->offset,
+				length, iter);
 	}
 	dio->size += copied;
 	return copied;
-- 
2.24.4