Merge patch series "vfs infrastructure for fs-verity support for XFS with post EOF merkle tree"

Christian Brauner <brauner@kernel.org> says:

This brings in the vfs infrastructure required to implement fs-verity
support for XFS.

* patches from https://patch.msgid.link/20260520123722.405752-1-aalbersh@kernel.org:
  iomap: introduce iomap_fsverity_write() for writing fsverity metadata
  iomap: teach iomap to read files with fsverity
  iomap: introduce IOMAP_F_FSVERITY and teach writeback to handle fsverity
  fsverity: generate and store zero-block hash

Link: https://patch.msgid.link/20260520123722.405752-1-aalbersh@kernel.org
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>

fs/iomap/buffered-io.c

@@ -9,6 +9,7 @@
 #include <linux/swap.h>
 #include <linux/migrate.h>
 #include <linux/fserror.h>
+#include <linux/fsverity.h>
 #include "internal.h"
 #include "trace.h"
 
@@ -353,9 +354,26 @@ static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter,
 {
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
 
-	return srcmap->type != IOMAP_MAPPED ||
-		(srcmap->flags & IOMAP_F_NEW) ||
-		pos >= i_size_read(iter->inode);
+	/*
+	 * If this block has not been written, there's nothing to read
+	 */
+	if (srcmap->type != IOMAP_MAPPED)
+		return true;
+
+	/*
+	 * Newly allocated blocks have not been written
+	 */
+	if (srcmap->flags & IOMAP_F_NEW)
+		return true;
+
+	/*
+	 * fsverity metadata is stored past i_size, we need to read it instead
+	 * of zeroing
+	 */
+	if (srcmap->flags & IOMAP_F_FSVERITY)
+		return false;
+
+	return pos >= i_size_read(iter->inode);
 }
 
 /**
@@ -544,9 +562,27 @@ static int iomap_read_folio_iter(struct iomap_iter *iter,
 		if (plen == 0)
 			return 0;
 
-		/* zero post-eof blocks as the page may be mapped */
-		if (iomap_block_needs_zeroing(iter, pos)) {
+		/*
+		 * Handling of fsverity "holes". We hit this for two case:
+		 *   1. No need to go further, the hole after fsverity
+		 *	descriptor is the end of the fsverity metadata.
+		 *
+		 *   2. This folio contains merkle tree blocks which need to be
+		 *	synthesized. If we already have fsverity info (ctx->vi)
+		 *	synthesize these blocks.
+		 */
+		if ((iomap->flags & IOMAP_F_FSVERITY) &&
+		    iomap->type == IOMAP_HOLE) {
+			if (ctx->vi)
+				fsverity_fill_zerohash(folio, poff, plen,
+						       ctx->vi);
+			iomap_set_range_uptodate(folio, poff, plen);
+		} else if (iomap_block_needs_zeroing(iter, pos)) {
+			/* zero post-eof blocks as the page may be mapped */
 			folio_zero_range(folio, poff, plen);
+			if (ctx->vi &&
+			    !fsverity_verify_blocks(ctx->vi, folio, plen, poff))
+				return -EIO;
 			iomap_set_range_uptodate(folio, poff, plen);
 		} else {
 			if (!*bytes_submitted)
@@ -597,6 +633,15 @@ void iomap_read_folio(const struct iomap_ops *ops,
 
 	trace_iomap_readpage(iter.inode, 1);
 
+	/*
+	 * Fetch fsverity_info for both data and fsverity metadata, as iomap
+	 * needs zeroed hash for merkle tree block synthesis
+	 */
+	ctx->vi = fsverity_get_info(iter.inode);
+	if (ctx->vi && iter.pos < i_size_read(iter.inode))
+		fsverity_readahead(ctx->vi, folio->index,
+				   folio_nr_pages(folio));
+
 	while ((ret = iomap_iter(&iter, ops)) > 0)
 		iter.status = iomap_read_folio_iter(&iter, ctx,
 				&bytes_submitted);
@@ -664,6 +709,15 @@ void iomap_readahead(const struct iomap_ops *ops,
 
 	trace_iomap_readahead(rac->mapping->host, readahead_count(rac));
 
+	/*
+	 * Fetch fsverity_info for both data and fsverity metadata, as iomap
+	 * needs zeroed hash for merkle tree block synthesis
+	 */
+	ctx->vi = fsverity_get_info(iter.inode);
+	if (ctx->vi && iter.pos < i_size_read(iter.inode))
+		fsverity_readahead(ctx->vi, readahead_index(rac),
+				readahead_count(rac));
+
 	while (iomap_iter(&iter, ops) > 0)
 		iter.status = iomap_readahead_iter(&iter, ctx,
 					&cur_bytes_submitted);
@@ -1170,13 +1224,14 @@ static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i,
 		 * unlock and release the folio.
 		 */
 		old_size = iter->inode->i_size;
-		if (pos + written > old_size) {
+		if (pos + written > old_size &&
+		    !(iter->iomap.flags & IOMAP_F_FSVERITY)) {
 			i_size_write(iter->inode, pos + written);
 			iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
 		}
 		__iomap_put_folio(iter, write_ops, written, folio);
 
-		if (old_size < pos)
+		if (old_size < pos && !(iter->iomap.flags & IOMAP_F_FSVERITY))
 			pagecache_isize_extended(iter->inode, old_size, pos);
 
 		cond_resched();
@@ -1235,6 +1290,31 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
 }
 EXPORT_SYMBOL_GPL(iomap_file_buffered_write);
 
+int iomap_fsverity_write(struct file *file, loff_t pos, size_t length,
+		const void *buf, const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops)
+{
+	int			ret;
+	struct iov_iter		iiter;
+	struct kvec		kvec = {
+		.iov_base	= (void *)buf,
+		.iov_len	= length,
+	};
+	struct kiocb		iocb = {
+		.ki_filp	= file,
+		.ki_ioprio	= get_current_ioprio(),
+		.ki_pos		= pos,
+	};
+
+	iov_iter_kvec(&iiter, WRITE, &kvec, 1, length);
+
+	ret = iomap_file_buffered_write(&iocb, &iiter, ops, write_ops, NULL);
+	if (ret < 0)
+		return ret;
+	return ret == length ? 0 : -EIO;
+}
+EXPORT_SYMBOL_GPL(iomap_fsverity_write);
+
 static void iomap_write_delalloc_ifs_punch(struct inode *inode,
 		struct folio *folio, loff_t start_byte, loff_t end_byte,
 		struct iomap *iomap, iomap_punch_t punch)
@@ -1802,13 +1882,20 @@ static int iomap_writeback_range(struct iomap_writepage_ctx *wpc,
  * Check interaction of the folio with the file end.
  *
  * If the folio is entirely beyond i_size, return false.  If it straddles
- * i_size, adjust end_pos and zero all data beyond i_size.
+ * i_size, adjust end_pos and zero all data beyond i_size. Don't skip fsverity
+ * folios as those are beyond i_size.
  */
-static bool iomap_writeback_handle_eof(struct folio *folio, struct inode *inode,
-		u64 *end_pos)
+static bool iomap_writeback_handle_eof(struct folio *folio,
+		struct iomap_writepage_ctx *wpc, u64 *end_pos)
 {
+	struct inode *inode = wpc->inode;
 	u64 isize = i_size_read(inode);
 
+	if (wpc->iomap.flags & IOMAP_F_FSVERITY) {
+		WARN_ON_ONCE(folio_pos(folio) < isize);
+		return true;
+	}
+
 	if (*end_pos > isize) {
 		size_t poff = offset_in_folio(folio, isize);
 		pgoff_t end_index = isize >> PAGE_SHIFT;
@@ -1874,7 +1961,7 @@ int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio)
 
 	trace_iomap_writeback_folio(inode, pos, folio_size(folio));
 
-	if (!iomap_writeback_handle_eof(folio, inode, &end_pos))
+	if (!iomap_writeback_handle_eof(folio, wpc, &end_pos))
 		return 0;
 	WARN_ON_ONCE(end_pos <= pos);
 

fs/iomap/ioend.c

@@ -28,6 +28,7 @@ struct iomap_ioend *iomap_init_ioend(struct inode *inode,
 	ioend->io_offset = file_offset;
 	ioend->io_size = bio->bi_iter.bi_size;
 	ioend->io_sector = bio->bi_iter.bi_sector;
+	ioend->io_vi = NULL;
 	ioend->io_private = NULL;
 	return ioend;
 }

fs/iomap/trace.h

@@ -118,7 +118,8 @@ DEFINE_RANGE_EVENT(iomap_zero_iter);
 	{ IOMAP_F_ATOMIC_BIO,	"ATOMIC_BIO" }, \
 	{ IOMAP_F_PRIVATE,	"PRIVATE" }, \
 	{ IOMAP_F_SIZE_CHANGED,	"SIZE_CHANGED" }, \
-	{ IOMAP_F_STALE,	"STALE" }
+	{ IOMAP_F_STALE,	"STALE" }, \
+	{ IOMAP_F_FSVERITY,	"FSVERITY" }
 
 
 #define IOMAP_DIO_STRINGS \

fs/verity/fsverity_private.h

@@ -53,6 +53,9 @@ struct merkle_tree_params {
 	u64 tree_size;			/* Merkle tree size in bytes */
 	unsigned long tree_pages;	/* Merkle tree size in pages */
 
+	/* the hash of an all-zeroes block */
+	u8 zero_digest[FS_VERITY_MAX_DIGEST_SIZE];
+
 	/*
 	 * Starting block index for each tree level, ordered from leaf level (0)
 	 * to root level ('num_levels - 1')

fs/verity/measure.c

@@ -68,8 +68,8 @@ EXPORT_SYMBOL_GPL(fsverity_ioctl_measure);
  * @alg: (out) the digest's algorithm, as a FS_VERITY_HASH_ALG_* value
  * @halg: (out) the digest's algorithm, as a HASH_ALGO_* value
  *
- * Retrieves the fsverity digest of the given file.  The file must have been
- * opened at least once since the inode was last loaded into the inode cache;
+ * Retrieves the fsverity digest of the given file. The
+ * fsverity_ensure_verity_info() must be called on the inode beforehand;
  * otherwise this function will not recognize when fsverity is enabled.
  *
  * The file's fsverity digest consists of @raw_digest in combination with either

fs/verity/open.c

@@ -153,6 +153,9 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params,
 		goto out_err;
 	}
 
+	fsverity_hash_block(params, page_address(ZERO_PAGE(0)),
+			    params->zero_digest);
+
 	params->tree_size = offset << log_blocksize;
 	params->tree_pages = PAGE_ALIGN(params->tree_size) >> PAGE_SHIFT;
 	return 0;

fs/verity/pagecache.c

@@ -2,6 +2,7 @@
 /*
  * Copyright 2019 Google LLC
  */
+#include "fsverity_private.h"
 
 #include <linux/export.h>
 #include <linux/fsverity.h>
@@ -56,3 +57,24 @@ void generic_readahead_merkle_tree(struct inode *inode, pgoff_t index,
 		folio_put(folio);
 }
 EXPORT_SYMBOL_GPL(generic_readahead_merkle_tree);
+
+/**
+ * fsverity_fill_zerohash() - fill folio with hashes of zero data block
+ * @folio:	folio to fill
+ * @offset:	offset in the folio to start
+ * @len:	length of the range to fill with hashes
+ * @vi:		fsverity info
+ */
+void fsverity_fill_zerohash(struct folio *folio, size_t offset, size_t len,
+			      struct fsverity_info *vi)
+{
+	size_t off = offset;
+
+	WARN_ON_ONCE(!IS_ALIGNED(offset, vi->tree_params.digest_size));
+	WARN_ON_ONCE(!IS_ALIGNED(len, vi->tree_params.digest_size));
+
+	for (; off < (offset + len); off += vi->tree_params.digest_size)
+		memcpy_to_folio(folio, off, vi->tree_params.zero_digest,
+				vi->tree_params.digest_size);
+}
+EXPORT_SYMBOL_GPL(fsverity_fill_zerohash);

include/linux/fsverity.h

@@ -201,6 +201,8 @@ bool fsverity_verify_blocks(struct fsverity_info *vi, struct folio *folio,
 			    size_t len, size_t offset);
 void fsverity_verify_bio(struct fsverity_info *vi, struct bio *bio);
 void fsverity_enqueue_verify_work(struct work_struct *work);
+void fsverity_fill_zerohash(struct folio *folio, size_t offset, size_t len,
+			    struct fsverity_info *vi);
 
 #else /* !CONFIG_FS_VERITY */
 
@@ -281,6 +283,12 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work)
 	WARN_ON_ONCE(1);
 }
 
+static inline void fsverity_fill_zerohash(struct folio *folio, size_t offset,
+		size_t len, struct fsverity_info *vi)
+{
+	WARN_ON_ONCE(1);
+}
+
 #endif	/* !CONFIG_FS_VERITY */
 
 static inline bool fsverity_verify_folio(struct fsverity_info *vi,

include/linux/iomap.h

@@ -91,6 +91,14 @@ struct vm_fault;
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 #define IOMAP_F_ZERO_TAIL	(1U << 10)
 
+/*
+ * Indicates reads and writes of fsverity metadata.
+ *
+ * Fsverity metadata is stored after the regular file data and thus beyond
+ * i_size.
+ */
+#define IOMAP_F_FSVERITY	(1U << 11)
+
 /*
  * Flag reserved for file system specific usage
  */
@@ -345,6 +353,9 @@ static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter)
 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);
+int iomap_fsverity_write(struct file *file, loff_t pos, size_t length,
+		const void *buf, const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops);
 void iomap_read_folio(const struct iomap_ops *ops,
 		struct iomap_read_folio_ctx *ctx, void *private);
 void iomap_readahead(const struct iomap_ops *ops,
@@ -421,6 +432,7 @@ struct iomap_ioend {
 	loff_t			io_offset;	/* offset in the file */
 	sector_t		io_sector;	/* start sector of ioend */
 	void			*io_private;	/* file system private data */
+	struct fsverity_info	*io_vi;		/* fsverity info */
 	struct bio		io_bio;		/* MUST BE LAST! */
 };
 
@@ -495,6 +507,7 @@ struct iomap_read_folio_ctx {
 	struct readahead_control *rac;
 	void			*read_ctx;
 	loff_t			read_ctx_file_offset;
+	struct fsverity_info	*vi;
 };
 
 struct iomap_read_ops {