Merge branch 'vfs-7.0.iomap' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull 'vfs-7.0.iomap' to allow iomap page cache users to set
`iomap_iter::private` for the upcoming page cache sharing support.

It also includes a patch to avoid triggering inline data reads for
the FIEMAP operation.

Signed-off-by: Gao Xiang <xiang@kernel.org>

fs/erofs/data.c

@@ -266,13 +266,20 @@ void erofs_onlinefolio_end(struct folio *folio, int err, bool dirty)
 	folio_end_read(folio, !(v & BIT(EROFS_ONLINEFOLIO_EIO)));
 }
 
+struct erofs_iomap_iter_ctx {
+	struct page *page;
+	void *base;
+};
+
 static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
 {
-	int ret;
+	struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap);
+	struct erofs_iomap_iter_ctx *ctx = iter->private;
 	struct super_block *sb = inode->i_sb;
 	struct erofs_map_blocks map;
 	struct erofs_map_dev mdev;
+	int ret;
 
 	map.m_la = offset;
 	map.m_llen = length;
@@ -283,7 +290,6 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	iomap->offset = map.m_la;
 	iomap->length = map.m_llen;
 	iomap->flags = 0;
-	iomap->private = NULL;
 	iomap->addr = IOMAP_NULL_ADDR;
 	if (!(map.m_flags & EROFS_MAP_MAPPED)) {
 		iomap->type = IOMAP_HOLE;
@@ -309,16 +315,20 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	}
 
 	if (map.m_flags & EROFS_MAP_META) {
-		void *ptr;
-		struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
-
 		iomap->type = IOMAP_INLINE;
-		ptr = erofs_read_metabuf(&buf, sb, map.m_pa,
-					 erofs_inode_in_metabox(inode));
-		if (IS_ERR(ptr))
-			return PTR_ERR(ptr);
-		iomap->inline_data = ptr;
-		iomap->private = buf.base;
+		/* read context should read the inlined data */
+		if (ctx) {
+			struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
+			void *ptr;
+
+			ptr = erofs_read_metabuf(&buf, sb, map.m_pa,
+						 erofs_inode_in_metabox(inode));
+			if (IS_ERR(ptr))
+				return PTR_ERR(ptr);
+			iomap->inline_data = ptr;
+			ctx->page = buf.page;
+			ctx->base = buf.base;
+		}
 	} else {
 		iomap->type = IOMAP_MAPPED;
 	}
@@ -328,18 +338,18 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 static int erofs_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 		ssize_t written, unsigned int flags, struct iomap *iomap)
 {
-	void *ptr = iomap->private;
+	struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap);
+	struct erofs_iomap_iter_ctx *ctx = iter->private;
 
-	if (ptr) {
+	if (ctx && ctx->base) {
 		struct erofs_buf buf = {
-			.page = kmap_to_page(ptr),
-			.base = ptr,
+			.page = ctx->page,
+			.base = ctx->base,
 		};
 
 		DBG_BUGON(iomap->type != IOMAP_INLINE);
 		erofs_put_metabuf(&buf);
-	} else {
-		DBG_BUGON(iomap->type == IOMAP_INLINE);
+		ctx->base = NULL;
 	}
 	return written;
 }
@@ -369,18 +379,30 @@ int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
  */
 static int erofs_read_folio(struct file *file, struct folio *folio)
 {
+	struct iomap_read_folio_ctx read_ctx = {
+		.ops		= &iomap_bio_read_ops,
+		.cur_folio	= folio,
+	};
+	struct erofs_iomap_iter_ctx iter_ctx = {};
+
 	trace_erofs_read_folio(folio, true);
 
-	iomap_bio_read_folio(folio, &erofs_iomap_ops);
+	iomap_read_folio(&erofs_iomap_ops, &read_ctx, &iter_ctx);
 	return 0;
 }
 
 static void erofs_readahead(struct readahead_control *rac)
 {
+	struct iomap_read_folio_ctx read_ctx = {
+		.ops		= &iomap_bio_read_ops,
+		.rac		= rac,
+	};
+	struct erofs_iomap_iter_ctx iter_ctx = {};
+
 	trace_erofs_readahead(rac->mapping->host, readahead_index(rac),
 					readahead_count(rac), true);
 
-	iomap_bio_readahead(rac, &erofs_iomap_ops);
+	iomap_readahead(&erofs_iomap_ops, &read_ctx, &iter_ctx);
 }
 
 static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
@@ -400,9 +422,12 @@ static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	if (IS_DAX(inode))
 		return dax_iomap_rw(iocb, to, &erofs_iomap_ops);
 #endif
-	if ((iocb->ki_flags & IOCB_DIRECT) && inode->i_sb->s_bdev)
+	if ((iocb->ki_flags & IOCB_DIRECT) && inode->i_sb->s_bdev) {
+		struct erofs_iomap_iter_ctx iter_ctx = {};
+
 		return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
-				    NULL, 0, NULL, 0);
+				    NULL, 0, &iter_ctx, 0);
+	}
 	return filemap_read(iocb, to, 0);
 }
 

fs/fuse/file.c

@@ -979,7 +979,7 @@ static int fuse_read_folio(struct file *file, struct folio *folio)
 		return -EIO;
 	}
 
-	iomap_read_folio(&fuse_iomap_ops, &ctx);
+	iomap_read_folio(&fuse_iomap_ops, &ctx, NULL);
 	fuse_invalidate_atime(inode);
 	return 0;
 }
@@ -1081,7 +1081,7 @@ static void fuse_readahead(struct readahead_control *rac)
 	if (fuse_is_bad(inode))
 		return;
 
-	iomap_readahead(&fuse_iomap_ops, &ctx);
+	iomap_readahead(&fuse_iomap_ops, &ctx, NULL);
 }
 
 static ssize_t fuse_cache_read_iter(struct kiocb *iocb, struct iov_iter *to)

fs/iomap/buffered-io.c

@@ -555,13 +555,14 @@ static int iomap_read_folio_iter(struct iomap_iter *iter,
 }
 
 void iomap_read_folio(const struct iomap_ops *ops,
-		struct iomap_read_folio_ctx *ctx)
+		struct iomap_read_folio_ctx *ctx, void *private)
 {
 	struct folio *folio = ctx->cur_folio;
 	struct iomap_iter iter = {
 		.inode		= folio->mapping->host,
 		.pos		= folio_pos(folio),
 		.len		= folio_size(folio),
+		.private	= private,
 	};
 	size_t bytes_submitted = 0;
 	int ret;
@@ -620,13 +621,14 @@ static int iomap_readahead_iter(struct iomap_iter *iter,
  * the filesystem to be reentered.
  */
 void iomap_readahead(const struct iomap_ops *ops,
-		struct iomap_read_folio_ctx *ctx)
+		struct iomap_read_folio_ctx *ctx, void *private)
 {
 	struct readahead_control *rac = ctx->rac;
 	struct iomap_iter iter = {
 		.inode	= rac->mapping->host,
 		.pos	= readahead_pos(rac),
 		.len	= readahead_length(rac),
+		.private = private,
 	};
 	size_t cur_bytes_submitted;
 

include/linux/iomap.h

@@ -345,9 +345,9 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops,
 		const struct iomap_write_ops *write_ops, void *private);
 void iomap_read_folio(const struct iomap_ops *ops,
-		struct iomap_read_folio_ctx *ctx);
+		struct iomap_read_folio_ctx *ctx, void *private);
 void iomap_readahead(const struct iomap_ops *ops,
-		struct iomap_read_folio_ctx *ctx);
+		struct iomap_read_folio_ctx *ctx, void *private);
 bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count);
 struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len);
 bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags);
@@ -599,7 +599,7 @@ static inline void iomap_bio_read_folio(struct folio *folio,
 		.cur_folio	= folio,
 	};
 
-	iomap_read_folio(ops, &ctx);
+	iomap_read_folio(ops, &ctx, NULL);
 }
 
 static inline void iomap_bio_readahead(struct readahead_control *rac,
@@ -610,7 +610,7 @@ static inline void iomap_bio_readahead(struct readahead_control *rac,
 		.rac		= rac,
 	};
 
-	iomap_readahead(ops, &ctx);
+	iomap_readahead(ops, &ctx, NULL);
 }
 #endif /* CONFIG_BLOCK */