fs-verity support for XFS with post EOF merkle tree

index 4004a1d42875..db8c350234bb 100644
@@ -9,6 +9,7 @@
 
 #include <linux/bio.h>
 #include <linux/export.h>
+#include <linux/fserror.h>
 
 #define FS_VERITY_MAX_PENDING_BLOCKS 2
 

@@ -205,6 +206,8 @@ static bool verify_data_block(struct fsverity_info *vi,
 		if (memchr_inv(dblock->data, 0, params->block_size)) {
 			fsverity_err(inode,
 				     "FILE CORRUPTED!  Data past EOF is not zeroed");
+			fserror_report_data_lost(inode, data_pos,
+						 params->block_size, GFP_NOFS);
 			return false;
 		}
 		return true;

@@ -312,6 +315,7 @@ static bool verify_data_block(struct fsverity_info *vi,
 		data_pos, level - 1, params->hash_alg->name, hsize, want_hash,
 		params->hash_alg->name, hsize,
 		level == 0 ? dblock->real_hash : real_hash);
+	fserror_report_data_lost(inode, data_pos, params->block_size, GFP_NOFS);
 error:
 	for (; level > 0; level--) {
 		kunmap_local(hblocks[level - 1].addr);

index dfa0d1afe0fe..d32d0899df25 100644
@@ -344,7 +344,24 @@ int fsverity_get_descriptor(struct inode *inode,
 	return 0;
 }
 
-static int ensure_verity_info(struct inode *inode)
+/**
+ * fsverity_ensure_verity_info() - cache verity info if it's not already cached
+ * @inode: the inode for which verity info should be cached
+ *
+ * Ensure this inode has verity info attached to it, it's assumed the inode
+ * already has fsverity enabled. Read fsverity descriptor and creates verity
+ * based on that.
+ *
+ * This needs to be called at least once before any of the inode's data
+ * can be verified (and thus read at all) or the inode's fsverity digest
+ * retrieved.  fsverity_file_open() calls this already, which handles
+ * normal file accesses.  If a filesystem does any internal (i.e. not
+ * associated with a file descriptor) reads of the file's data or
+ * fsverity digest, it must call this explicitly before doing so.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fsverity_ensure_verity_info(struct inode *inode)
 {
 	struct fsverity_info *vi = fsverity_get_info(inode), *found;
 	struct fsverity_descriptor *desc;

@@ -380,12 +397,13 @@ static int ensure_verity_info(struct inode *inode)
 	kfree(desc);
 	return err;
 }
+EXPORT_SYMBOL_GPL(fsverity_ensure_verity_info);
 
 int __fsverity_file_open(struct inode *inode, struct file *filp)
 {
 	if (filp->f_mode & FMODE_WRITE)
 		return -EPERM;
-	return ensure_verity_info(inode);
+	return fsverity_ensure_verity_info(inode);
 }
 EXPORT_SYMBOL_GPL(__fsverity_file_open);
 

index a8f9aa75b792..5562271bd628 100644
@@ -309,6 +309,8 @@ static inline int fsverity_file_open(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+int fsverity_ensure_verity_info(struct inode *inode);
+
 void fsverity_cleanup_inode(struct inode *inode);
 
 struct page *generic_read_merkle_tree_page(struct inode *inode, pgoff_t index);

index 2ea769f311c3..dd2e81022e4f 100644
@@ -16,6 +16,7 @@
 #include <linux/namei.h>
 #include <linux/ratelimit.h>
 #include <linux/overflow.h>
+#include <linux/fsverity.h>
 #include "overlayfs.h"
 
 /* Get write access to upper mnt - may fail if upper sb was remounted ro */

@@ -1377,18 +1378,9 @@ char *ovl_get_redirect_xattr(struct ovl_fs *ofs, const struct path *path, int pa
 int ovl_ensure_verity_loaded(const struct path *datapath)
 {
 	struct inode *inode = d_inode(datapath->dentry);
-	struct file *filp;
 
-	if (!fsverity_active(inode) && IS_VERITY(inode)) {
-		/*
-		 * If this inode was not yet opened, the verity info hasn't been
-		 * loaded yet, so we need to do that here to force it into memory.
-		 */
-		filp = kernel_file_open(datapath, O_RDONLY, current_cred());
-		if (IS_ERR(filp))
-			return PTR_ERR(filp);
-		fput(filp);
-	}
+	if (fsverity_active(inode))
+		return fsverity_ensure_verity_info(inode);
 
 	return 0;
 }

index 6e6854c19078..881d46f25e08 100644
@@ -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')

index 6a35623ebdf0..818083507885 100644
@@ -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

index d32d0899df25..875e8850ccba 100644
@@ -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;

index 1819314ecaa3..99f5f53eea98 100644
@@ -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);

index 5562271bd628..e4503312d114 100644
@@ -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 poff, size_t plen,
+			      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 poff,
+		size_t plen, struct fsverity_info *vi)
+{
+	WARN_ON_ONCE(1);
+}
+
 #endif	/* !CONFIG_FS_VERITY */
 
 static inline bool fsverity_verify_folio(struct fsverity_info *vi,

index 0062b3a55781..fd3696d3f4ce 100644
@@ -773,11 +773,15 @@ static struct page *btrfs_read_merkle_tree_page(struct inode *inode,
  * @buf:	Merkle tree block to write
  * @pos:	the position of the block in the Merkle tree (in bytes)
  * @size:	the Merkle tree block size (in bytes)
+ * @zero_digest:	the hash of the all-zeroes block
+ * @digest_size:	size of zero_digest, in bytes
  *
  * Returns 0 on success or negative error code on failure
  */
 static int btrfs_write_merkle_tree_block(struct file *file, const void *buf,
-					 u64 pos, unsigned int size)
+					 u64 pos, unsigned int size,
+					 const u8 *zero_digest,
+					 unsigned int digest_size)
 {
 	struct inode *inode = file_inode(file);
 	loff_t merkle_pos = merkle_file_pos(inode);

index ca61da53f313..347945ac23a4 100644
@@ -374,7 +374,9 @@ static void ext4_readahead_merkle_tree(struct inode *inode, pgoff_t index,
 }
 
 static int ext4_write_merkle_tree_block(struct file *file, const void *buf,
-					u64 pos, unsigned int size)
+					u64 pos, unsigned int size,
+					const u8 *zero_digest,
+					unsigned int digest_size)
 {
 	pos += ext4_verity_metadata_pos(file_inode(file));
 

index 92ebcc19cab0..b3b3e71604ac 100644
@@ -270,7 +270,9 @@ static void f2fs_readahead_merkle_tree(struct inode *inode, pgoff_t index,
 }
 
 static int f2fs_write_merkle_tree_block(struct file *file, const void *buf,
-					u64 pos, unsigned int size)
+					u64 pos, unsigned int size,
+					const u8 *zero_digest,
+					unsigned int digest_size)
 {
 	pos += f2fs_verity_metadata_pos(file_inode(file));
 

index 42dfed1ce0ce..ad4ff71d7dd9 100644
@@ -50,7 +50,9 @@ static int write_merkle_tree_block(struct file *file, const u8 *buf,
 	int err;
 
 	err = inode->i_sb->s_vop->write_merkle_tree_block(file, buf, pos,
-							  params->block_size);
+							  params->block_size,
+							  params->zero_digest,
+							  params->digest_size);
 	if (err)
 		fsverity_err(inode, "Error %d writing Merkle tree block %lu",
 			     err, index);

index e4503312d114..a5645ec07aa8 100644
@@ -124,6 +124,8 @@ struct fsverity_operations {
 	 * @buf: the Merkle tree block to write
 	 * @pos: the position of the block in the Merkle tree (in bytes)
 	 * @size: the Merkle tree block size (in bytes)
+	 * @zero_digest: the hash of the all-zeroes block
+	 * @digest_size: size of zero_digest, in bytes
 	 *
 	 * This is only called between ->begin_enable_verity() and
 	 * ->end_enable_verity().

@@ -131,7 +133,9 @@ struct fsverity_operations {
 	 * Return: 0 on success, -errno on failure
 	 */
 	int (*write_merkle_tree_block)(struct file *file, const void *buf,
-				       u64 pos, unsigned int size);
+				       u64 pos, unsigned int size,
+				       const u8 *zero_digest,
+				       unsigned int digest_size);
 };
 
 #ifdef CONFIG_FS_VERITY

index 347945ac23a4..ac5c133f5529 100644
@@ -34,32 +34,6 @@ static inline loff_t ext4_verity_metadata_pos(const struct inode *inode)
 	return round_up(inode->i_size, 65536);
 }
 
-/*
- * Read some verity metadata from the inode.  __vfs_read() can't be used because
- * we need to read beyond i_size.
- */
-static int pagecache_read(struct inode *inode, void *buf, size_t count,
-			  loff_t pos)
-{
-	while (count) {
-		struct folio *folio;
-		size_t n;
-
-		folio = read_mapping_folio(inode->i_mapping, pos >> PAGE_SHIFT,
-					 NULL);
-		if (IS_ERR(folio))
-			return PTR_ERR(folio);
-
-		n = memcpy_from_file_folio(buf, folio, pos, count);
-		folio_put(folio);
-
-		buf += n;
-		pos += n;
-		count -= n;
-	}
-	return 0;
-}
-
 /*
  * Write some verity metadata to the inode for FS_IOC_ENABLE_VERITY.
  * kernel_write() can't be used because the file descriptor is readonly.

@@ -311,8 +285,8 @@ static int ext4_get_verity_descriptor_location(struct inode *inode,
 		goto bad;
 	desc_size_pos -= sizeof(desc_size_disk);
 
-	err = pagecache_read(inode, &desc_size_disk, sizeof(desc_size_disk),
-			     desc_size_pos);
+	err = fsverity_pagecache_read(inode, &desc_size_disk,
+				      sizeof(desc_size_disk), desc_size_pos);
 	if (err)
 		return err;
 	desc_size = le32_to_cpu(desc_size_disk);

@@ -352,7 +326,7 @@ static int ext4_get_verity_descriptor(struct inode *inode, void *buf,
 	if (buf_size) {
 		if (desc_size > buf_size)
 			return -ERANGE;
-		err = pagecache_read(inode, buf, desc_size, desc_pos);
+		err = fsverity_pagecache_read(inode, buf, desc_size, desc_pos);
 		if (err)
 			return err;
 	}

index b3b3e71604ac..5ea0a9b40443 100644
@@ -36,34 +36,6 @@ static inline loff_t f2fs_verity_metadata_pos(const struct inode *inode)
 	return round_up(inode->i_size, 65536);
 }
 
-/*
- * Read some verity metadata from the inode.  __vfs_read() can't be used because
- * we need to read beyond i_size.
- */
-static int pagecache_read(struct inode *inode, void *buf, size_t count,
-			  loff_t pos)
-{
-	while (count) {
-		size_t n = min_t(size_t, count,
-				 PAGE_SIZE - offset_in_page(pos));
-		struct page *page;
-
-		page = read_mapping_page(inode->i_mapping, pos >> PAGE_SHIFT,
-					 NULL);
-		if (IS_ERR(page))
-			return PTR_ERR(page);
-
-		memcpy_from_page(buf, page, offset_in_page(pos), n);
-
-		put_page(page);
-
-		buf += n;
-		pos += n;
-		count -= n;
-	}
-	return 0;
-}
-
 /*
  * Write some verity metadata to the inode for FS_IOC_ENABLE_VERITY.
  * kernel_write() can't be used because the file descriptor is readonly.

@@ -248,7 +220,7 @@ static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
 	if (buf_size) {
 		if (size > buf_size)
 			return -ERANGE;
-		res = pagecache_read(inode, buf, size, pos);
+		res = fsverity_pagecache_read(inode, buf, size, pos);
 		if (res)
 			return res;
 	}

index 99f5f53eea98..9d82e6b74ba1 100644
@@ -78,3 +78,36 @@ void fsverity_fill_zerohash(struct folio *folio, size_t offset, size_t len,
 				vi->tree_params.digest_size);
 }
 EXPORT_SYMBOL_GPL(fsverity_fill_zerohash);
+
+/**
+ * fsverity_pagecache_read() - read page and copy data to buffer
+ * @inode:	copy from this inode's address space
+ * @buf:	buffer to copy to
+ * @count:	number of bytes to copy
+ * @pos:	position of the folio to copy from
+ *
+ * Read some verity metadata from the inode.  __vfs_read() can't be used because
+ * we need to read beyond i_size.
+ */
+int fsverity_pagecache_read(struct inode *inode, void *buf, size_t count,
+			  loff_t pos)
+{
+	while (count) {
+		struct folio *folio;
+		size_t n;
+
+		folio = read_mapping_folio(inode->i_mapping, pos >> PAGE_SHIFT,
+					 NULL);
+		if (IS_ERR(folio))
+			return PTR_ERR(folio);
+
+		n = memcpy_from_file_folio(buf, folio, pos, count);
+		folio_put(folio);
+
+		buf += n;
+		pos += n;
+		count -= n;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fsverity_pagecache_read);

index a5645ec07aa8..a2ae5cc649ad 100644
@@ -328,5 +328,7 @@ void fsverity_cleanup_inode(struct inode *inode);
 struct page *generic_read_merkle_tree_page(struct inode *inode, pgoff_t index);
 void generic_readahead_merkle_tree(struct inode *inode, pgoff_t index,
 				   unsigned long nr_pages);
+int fsverity_pagecache_read(struct inode *inode, void *buf, size_t count,
+			    loff_t pos);
 
 #endif	/* _LINUX_FSVERITY_H */

index e4b6886e5c3c..38c9592fba43 100644
@@ -353,9 +353,26 @@ 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);
 }
 
 /**

@@ -1167,13 +1184,14 @@ 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();

@@ -1801,13 +1819,20 @@ 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;

@@ -1873,7 +1898,7 @@ 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);
 

index 532787277b16..5252051cc137 100644
@@ -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 \

index 531f9ebdeeae..4506a99d5285 100644
@@ -87,6 +87,14 @@ struct vm_fault;
 #define IOMAP_F_INTEGRITY	0
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
+/*
+ * 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 << 10)
+
 /*
  * Flag reserved for file system specific usage
  */

index 38c9592fba43..843314852663 100644
@@ -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"
 

@@ -561,9 +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)

@@ -614,6 +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);

@@ -681,6 +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);

index 4506a99d5285..4d9202cae29f 100644
@@ -435,6 +435,7 @@ 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! */
 };
 

@@ -509,6 +510,7 @@ 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 {

index 843314852663..5c9fd925a62f 100644
@@ -1287,6 +1287,31 @@ 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)

index 4d9202cae29f..83586f09f365 100644
@@ -359,6 +359,9 @@ 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,

index 779dac59b1f3..4dff29659e40 100644
@@ -374,6 +374,7 @@ xfs_sb_has_compat_feature(
 #define XFS_SB_FEAT_RO_COMPAT_RMAPBT   (1 << 1)		/* reverse map btree */
 #define XFS_SB_FEAT_RO_COMPAT_REFLINK  (1 << 2)		/* reflinked files */
 #define XFS_SB_FEAT_RO_COMPAT_INOBTCNT (1 << 3)		/* inobt block counts */
+#define XFS_SB_FEAT_RO_COMPAT_VERITY   (1 << 4)		/* fs-verity */
 #define XFS_SB_FEAT_RO_COMPAT_ALL \
 		(XFS_SB_FEAT_RO_COMPAT_FINOBT | \
 		 XFS_SB_FEAT_RO_COMPAT_RMAPBT | \

@@ -1230,16 +1231,21 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
  */
 #define XFS_DIFLAG2_METADATA_BIT	5
 
+/* inodes sealed with fs-verity */
+#define XFS_DIFLAG2_VERITY_BIT		6
+
 #define XFS_DIFLAG2_DAX		(1ULL << XFS_DIFLAG2_DAX_BIT)
 #define XFS_DIFLAG2_REFLINK	(1ULL << XFS_DIFLAG2_REFLINK_BIT)
 #define XFS_DIFLAG2_COWEXTSIZE	(1ULL << XFS_DIFLAG2_COWEXTSIZE_BIT)
 #define XFS_DIFLAG2_BIGTIME	(1ULL << XFS_DIFLAG2_BIGTIME_BIT)
 #define XFS_DIFLAG2_NREXT64	(1ULL << XFS_DIFLAG2_NREXT64_BIT)
 #define XFS_DIFLAG2_METADATA	(1ULL << XFS_DIFLAG2_METADATA_BIT)
+#define XFS_DIFLAG2_VERITY	(1ULL << XFS_DIFLAG2_VERITY_BIT)
 
 #define XFS_DIFLAG2_ANY \
 	(XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE | \
-	 XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64 | XFS_DIFLAG2_METADATA)
+	 XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64 | XFS_DIFLAG2_METADATA | \
+	 XFS_DIFLAG2_VERITY)
 
 static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip)
 {

@@ -2021,4 +2027,26 @@ struct xfs_acl {
 #define SGI_ACL_FILE_SIZE	(sizeof(SGI_ACL_FILE)-1)
 #define SGI_ACL_DEFAULT_SIZE	(sizeof(SGI_ACL_DEFAULT)-1)
 
+/*
+ * At maximum of 8 levels with 128 hashes per block (32 bytes SHA-256) maximum
+ * tree size is ((128^8 − 1)/(128 − 1)) = 567*10^12 blocks. This should fit in
+ * 53 bits address space.
+ *
+ * At this Merkle tree size we can cover 295EB large file. This is much larger
+ * than the currently supported file size.
+ *
+ * For sha512 the largest file we can cover ends at 1 << 50 offset, this is also
+ * good.
+ */
+#define XFS_FSVERITY_LARGEST_FILE	((loff_t)1ULL << 53)
+
+/*
+ * Alignment of the fsverity metadata placement. This is largest supported PAGE
+ * SIZE for fsverity. This is used to space out data and metadata in page cache.
+ * The spacing is necessary for non-exposure of metadata to userspace and
+ * correct merkle tree synethesis in the iomap.
+ */
+#define XFS_FSVERITY_START_ALIGN	(65536)
+
+
 #endif /* __XFS_FORMAT_H__ */

index 3794e5412eba..f2181c1bed54 100644
@@ -760,6 +760,14 @@ xfs_dinode_verify(
 	    !xfs_has_rtreflink(mp))
 		return __this_address;
 
+	/* only regular files can have fsverity */
+	if (flags2 & XFS_DIFLAG2_VERITY) {
+		if (!xfs_has_verity(mp))
+			return __this_address;
+		if (!S_ISREG(mode))
+			return __this_address;
+	}
+
 	if (xfs_has_zoned(mp) &&
 	    dip->di_metatype == cpu_to_be16(XFS_METAFILE_RTRMAP)) {
 		if (be32_to_cpu(dip->di_used_blocks) > mp->m_sb.sb_rgextents)

index 551fa51befb6..6b1e20a4bb9b 100644
@@ -126,6 +126,8 @@ xfs_ip2xflags(
 			flags |= FS_XFLAG_DAX;
 		if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
 			flags |= FS_XFLAG_COWEXTSIZE;
+		if (ip->i_diflags2 & XFS_DIFLAG2_VERITY)
+			flags |= FS_XFLAG_VERITY;
 	}
 
 	if (xfs_inode_has_attr_fork(ip))

index 47322adb7690..a15510ebd2f1 100644
@@ -165,6 +165,8 @@ xfs_sb_version_to_features(
 		features |= XFS_FEAT_REFLINK;
 	if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_INOBTCNT)
 		features |= XFS_FEAT_INOBTCNT;
+	if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_VERITY)
+		features |= XFS_FEAT_VERITY;
 	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_FTYPE)
 		features |= XFS_FEAT_FTYPE;
 	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_SPINODES)

index 208543e57eda..ca369eb96561 100644
@@ -1415,6 +1415,8 @@ xfs_diflags_to_iflags(
 		flags |= S_NOATIME;
 	if (init && xfs_inode_should_enable_dax(ip))
 		flags |= S_DAX;
+	if (xflags & FS_XFLAG_VERITY)
+		flags |= S_VERITY;
 
 	/*
 	 * S_DAX can only be set during inode initialization and is never set by

index ddd4028be8d6..07f6aa3c3f26 100644
@@ -385,6 +385,7 @@ typedef struct xfs_mount {
 #define XFS_FEAT_EXCHANGE_RANGE	(1ULL << 27)	/* exchange range */
 #define XFS_FEAT_METADIR	(1ULL << 28)	/* metadata directory tree */
 #define XFS_FEAT_ZONED		(1ULL << 29)	/* zoned RT device */
+#define XFS_FEAT_VERITY		(1ULL << 30)	/* fs-verity */
 
 /* Mount features */
 #define XFS_FEAT_NOLIFETIME	(1ULL << 47)	/* disable lifetime hints */

@@ -442,6 +443,7 @@ __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE)
 __XFS_HAS_FEAT(metadir, METADIR)
 __XFS_HAS_FEAT(zoned, ZONED)
 __XFS_HAS_FEAT(nolifetime, NOLIFETIME)
+__XFS_HAS_FEAT(verity, VERITY)
 
 static inline bool xfs_has_rtgroups(const struct xfs_mount *mp)
 {

index 6246f34df9fd..a980ac5196a8 100644
@@ -37,6 +37,7 @@
 #include <linux/fadvise.h>
 #include <linux/mount.h>
 #include <linux/filelock.h>
+#include <linux/fsverity.h>
 
 static const struct vm_operations_struct xfs_file_vm_ops;
 

@@ -1640,11 +1641,18 @@ xfs_file_open(
 	struct inode	*inode,
 	struct file	*file)
 {
+	int		error;
+
 	if (xfs_is_shutdown(XFS_M(inode->i_sb)))
 		return -EIO;
 	file->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT;
 	if (xfs_get_atomic_write_min(XFS_I(inode)) > 0)
 		file->f_mode |= FMODE_CAN_ATOMIC_WRITE;
+
+	error = fsverity_file_open(inode, file);
+	if (error)
+		return error;
+
 	return generic_file_open(inode, file);
 }
 

index ca369eb96561..17efc83a86ed 100644
@@ -1387,6 +1387,8 @@ xfs_inode_should_enable_dax(
 		return false;
 	if (!xfs_inode_supports_dax(ip))
 		return false;
+	if (ip->i_diflags2 & XFS_DIFLAG2_VERITY)
+		return false;
 	if (xfs_has_dax_always(ip->i_mount))
 		return true;
 	if (ip->i_diflags2 & XFS_DIFLAG2_DAX)

index a980ac5196a8..6fa9835f9531 100644
@@ -282,7 +282,8 @@ xfs_file_dax_read(
 	struct kiocb		*iocb,
 	struct iov_iter		*to)
 {
-	struct xfs_inode	*ip = XFS_I(iocb->ki_filp->f_mapping->host);
+	struct inode		*inode = iocb->ki_filp->f_mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
 	ssize_t			ret = 0;
 
 	trace_xfs_file_dax_read(iocb, to);

@@ -333,6 +334,14 @@ xfs_file_read_iter(
 	if (xfs_is_shutdown(mp))
 		return -EIO;
 
+	/*
+	 * In case fs-verity is enabled, we also fallback to the buffered read
+	 * from the direct read path. Therefore, IOCB_DIRECT is set and need to
+	 * be cleared (see generic_file_read_iter())
+	 */
+	if (fsverity_active(inode))
+		iocb->ki_flags &= ~IOCB_DIRECT;
+
 	if (IS_DAX(inode))
 		ret = xfs_file_dax_read(iocb, to);
 	else if (iocb->ki_flags & IOCB_DIRECT)

index 7a4c8f1aa76c..931d02678d19 100644
@@ -41,6 +41,8 @@
 #include "xfs_inode_util.h"
 #include "xfs_rtgroup.h"
 #include "xfs_zone_alloc.h"
+#include "xfs_fsverity.h"
+#include <linux/fsverity.h>
 
 struct kmem_cache		*xfs_bmap_intent_cache;
 

@@ -4451,6 +4453,11 @@ xfs_bmapi_convert_one_delalloc(
 	XFS_STATS_ADD(mp, xs_xstrat_bytes, XFS_FSB_TO_B(mp, bma.length));
 	XFS_STATS_INC(mp, xs_xstrat_quick);
 
+	if (xfs_iflags_test(ip, XFS_VERITY_CONSTRUCTION) &&
+	    XFS_FSB_TO_B(mp, bma.got.br_startoff) >=
+		    xfs_fsverity_metadata_offset(ip))
+		flags |= IOMAP_F_FSVERITY;
+
 	ASSERT(!isnullstartblock(bma.got.br_startblock));
 	xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags,
 				xfs_iomap_inode_sequence(ip, flags));

index f279055fcea0..9503252a0fa4 100644
@@ -22,6 +22,7 @@
 #include "xfs_icache.h"
 #include "xfs_zone_alloc.h"
 #include "xfs_rtgroup.h"
+#include "xfs_fsverity.h"
 #include <linux/bio-integrity.h>
 
 struct xfs_writepage_ctx {

@@ -339,12 +340,16 @@ xfs_map_blocks(
 	int			retries = 0;
 	int			error = 0;
 	unsigned int		*seq;
+	unsigned int		iomap_flags = 0;
 
 	if (xfs_is_shutdown(mp))
 		return -EIO;
 
 	XFS_ERRORTAG_DELAY(mp, XFS_ERRTAG_WB_DELAY_MS);
 
+	if (xfs_iflags_test(ip, XFS_VERITY_CONSTRUCTION))
+		iomap_flags |= IOMAP_F_FSVERITY;
+
 	/*
 	 * COW fork blocks can overlap data fork blocks even if the blocks
 	 * aren't shared.  COW I/O always takes precedent, so we must always

@@ -432,7 +437,8 @@ xfs_map_blocks(
 	    isnullstartblock(imap.br_startblock))
 		goto allocate_blocks;
 
-	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0, XFS_WPC(wpc)->data_seq);
+	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, iomap_flags,
+			  XFS_WPC(wpc)->data_seq);
 	trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
 	return 0;
 allocate_blocks:

@@ -705,6 +711,14 @@ xfs_vm_writepages(
 			},
 		};
 
+		/*
+		 * Writeback does not work for folios past EOF, let it know that
+		 * I/O happens for fsverity metadata and this restriction need
+		 * to be skipped
+		 */
+		if (xfs_iflags_test(ip, XFS_VERITY_CONSTRUCTION))
+			wpc.ctx.iomap.flags |= IOMAP_F_FSVERITY;
+
 		return iomap_writepages(&wpc.ctx);
 	}
 }

new file mode 100644
index 000000000000..6e6a8636a577
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2026 Red Hat, Inc.
+ */
+#include "xfs_platform.h"
+#include "xfs_format.h"
+#include "xfs_inode.h"
+#include "xfs_shared.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_fsverity.h"
+#include "xfs_fsverity.h"
+#include <linux/fsverity.h>
+#include <linux/iomap.h>
+
+loff_t
+xfs_fsverity_metadata_offset(
+	const struct xfs_inode	*ip)
+{
+	return round_up(i_size_read(VFS_IC(ip)), XFS_FSVERITY_START_ALIGN);
+}

new file mode 100644
index 000000000000..5771db2cd797
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2026 Red Hat, Inc.
+ */
+#ifndef __XFS_FSVERITY_H__
+#define __XFS_FSVERITY_H__
+
+#include "xfs_platform.h"
+
+#ifdef CONFIG_FS_VERITY
+loff_t xfs_fsverity_metadata_offset(const struct xfs_inode *ip);
+#else
+static inline loff_t xfs_fsverity_metadata_offset(const struct xfs_inode *ip)
+{
+	WARN_ON_ONCE(1);
+	return ULLONG_MAX;
+}
+#endif	/* CONFIG_FS_VERITY */
+
+#endif	/* __XFS_FSVERITY_H__ */

index bd6d33557194..6df48d68a919 100644
@@ -415,6 +415,12 @@ static inline bool xfs_inode_can_sw_atomic_write(const struct xfs_inode *ip)
  */
 #define XFS_IREMAPPING		(1U << 15)
 
+/*
+ * fs-verity's Merkle tree is under construction. The file is read-only, the
+ * only writes happening are for the fsverity metadata.
+ */
+#define XFS_VERITY_CONSTRUCTION	(1U << 16)
+
 /* All inode state flags related to inode reclaim. */
 #define XFS_ALL_IRECLAIM_FLAGS	(XFS_IRECLAIMABLE | \
 				 XFS_IRECLAIM | \

index 9c2f12d5fec9..71ccd4ff5f48 100644
@@ -32,6 +32,8 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_icache.h"
 #include "xfs_zone_alloc.h"
+#include "xfs_fsverity.h"
+#include <linux/fsverity.h>
 
 #define XFS_ALLOC_ALIGN(mp, off) \
 	(((off) >> mp->m_allocsize_log) << mp->m_allocsize_log)

@@ -1789,6 +1791,9 @@ xfs_buffered_write_iomap_begin(
 		return xfs_direct_write_iomap_begin(inode, offset, count,
 				flags, iomap, srcmap);
 
+	if (xfs_iflags_test(ip, XFS_VERITY_CONSTRUCTION))
+		iomap_flags |= IOMAP_F_FSVERITY;
+
 	error = xfs_qm_dqattach(ip);
 	if (error)
 		return error;

@@ -2113,12 +2118,17 @@ xfs_read_iomap_begin(
 	bool			shared = false;
 	unsigned int		lockmode = XFS_ILOCK_SHARED;
 	u64			seq;
+	unsigned int		iomap_flags = 0;
 
 	ASSERT(!(flags & (IOMAP_WRITE | IOMAP_ZERO)));
 
 	if (xfs_is_shutdown(mp))
 		return -EIO;
 
+	if (fsverity_active(inode) &&
+	    (offset >= xfs_fsverity_metadata_offset(ip)))
+		iomap_flags |= IOMAP_F_FSVERITY;
+
 	error = xfs_ilock_for_iomap(ip, flags, &lockmode);
 	if (error)
 		return error;

@@ -2132,8 +2142,9 @@ xfs_read_iomap_begin(
 	if (error)
 		return error;
 	trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags,
-				 shared ? IOMAP_F_SHARED : 0, seq);
+	iomap_flags |= shared ? IOMAP_F_SHARED : 0;
+
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, iomap_flags, seq);
 }
 
 const struct iomap_ops xfs_read_iomap_ops = {

index 9503252a0fa4..ecb07f250956 100644
@@ -24,6 +24,7 @@
 #include "xfs_rtgroup.h"
 #include "xfs_fsverity.h"
 #include <linux/bio-integrity.h>
+#include <linux/fsverity.h>
 
 struct xfs_writepage_ctx {
 	struct iomap_writepage_ctx ctx;

@@ -171,6 +172,23 @@ xfs_end_ioend_write(
 	memalloc_nofs_restore(nofs_flag);
 }
 
+/*
+ * IO read completion.
+ */
+static void
+xfs_end_ioend_read(
+	struct iomap_ioend	*ioend)
+{
+	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+
+	if (!ioend->io_bio.bi_status &&
+			xfs_fsverity_is_file_data(ip, ioend->io_offset))
+		fsverity_verify_bio(ioend->io_vi,
+				    &ioend->io_bio);
+	iomap_finish_ioends(ioend,
+		blk_status_to_errno(ioend->io_bio.bi_status));
+}
+
 /*
  * Finish all pending IO completions that require transactional modifications.
  *

@@ -205,8 +223,7 @@ xfs_end_io(
 		list_del_init(&ioend->io_list);
 		iomap_ioend_try_merge(ioend, &tmp);
 		if (bio_op(&ioend->io_bio) == REQ_OP_READ)
-			iomap_finish_ioends(ioend,
-				blk_status_to_errno(ioend->io_bio.bi_status));
+			xfs_end_ioend_read(ioend);
 		else
 			xfs_end_ioend_write(ioend);
 		cond_resched();

@@ -232,9 +249,14 @@ xfs_end_bio(
 	}
 
 	spin_lock_irqsave(&ip->i_ioend_lock, flags);
-	if (list_empty(&ip->i_ioend_list))
-		WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue,
+	if (list_empty(&ip->i_ioend_list)) {
+		if (IS_ENABLED(CONFIG_FS_VERITY) && ioend->io_vi &&
+		    ioend->io_offset < xfs_fsverity_metadata_offset(ip))
+			fsverity_enqueue_verify_work(&ip->i_ioend_work);
+		else
+			WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue,
 					 &ip->i_ioend_work));
+	}
 	list_add_tail(&ioend->io_list, &ip->i_ioend_list);
 	spin_unlock_irqrestore(&ip->i_ioend_lock, flags);
 }

@@ -764,9 +786,13 @@ xfs_bio_submit_read(
 	struct iomap_read_folio_ctx	*ctx)
 {
 	struct bio			*bio = ctx->read_ctx;
+	struct iomap_ioend		*ioend;
 
 	/* defer read completions to the ioend workqueue */
-	iomap_init_ioend(iter->inode, bio, ctx->read_ctx_file_offset, 0);
+	ioend = iomap_init_ioend(iter->inode, bio, ctx->read_ctx_file_offset,
+			0);
+	ioend->io_vi = ctx->vi;
+
 	bio->bi_end_io = xfs_end_bio;
 	submit_bio(bio);
 }

@@ -779,11 +805,13 @@ static const struct iomap_read_ops xfs_iomap_read_ops = {
 
 static inline const struct iomap_read_ops *
 xfs_get_iomap_read_ops(
-	const struct address_space	*mapping)
+	const struct address_space	*mapping,
+	loff_t				position)
 {
 	struct xfs_inode		*ip = XFS_I(mapping->host);
 
-	if (bdev_has_integrity_csum(xfs_inode_buftarg(ip)->bt_bdev))
+	if (bdev_has_integrity_csum(xfs_inode_buftarg(ip)->bt_bdev) ||
+			xfs_fsverity_is_file_data(ip, position))
 		return &xfs_iomap_read_ops;
 	return &iomap_bio_read_ops;
 }

@@ -795,7 +823,7 @@ xfs_vm_read_folio(
 {
 	struct iomap_read_folio_ctx	ctx = { .cur_folio = folio };
 
-	ctx.ops = xfs_get_iomap_read_ops(folio->mapping);
+	ctx.ops = xfs_get_iomap_read_ops(folio->mapping, folio_pos(folio));
 	iomap_read_folio(&xfs_read_iomap_ops, &ctx, NULL);
 	return 0;
 }

@@ -806,7 +834,7 @@ xfs_vm_readahead(
 {
 	struct iomap_read_folio_ctx	ctx = { .rac = rac };
 
-	ctx.ops = xfs_get_iomap_read_ops(rac->mapping),
+	ctx.ops = xfs_get_iomap_read_ops(rac->mapping, readahead_pos(rac));
 	iomap_readahead(&xfs_read_iomap_ops, &ctx, NULL);
 }
 

index 6e6a8636a577..b983e20bb5e1 100644
@@ -19,3 +19,12 @@ xfs_fsverity_metadata_offset(
 {
 	return round_up(i_size_read(VFS_IC(ip)), XFS_FSVERITY_START_ALIGN);
 }
+
+bool
+xfs_fsverity_is_file_data(
+	const struct xfs_inode	*ip,
+	loff_t			offset)
+{
+	return fsverity_active(VFS_IC(ip)) &&
+			offset < xfs_fsverity_metadata_offset(ip);
+}

index 5771db2cd797..ec77ba571106 100644
@@ -9,12 +9,18 @@
 
 #ifdef CONFIG_FS_VERITY
 loff_t xfs_fsverity_metadata_offset(const struct xfs_inode *ip);
+bool xfs_fsverity_is_file_data(const struct xfs_inode *ip, loff_t offset);
 #else
 static inline loff_t xfs_fsverity_metadata_offset(const struct xfs_inode *ip)
 {
 	WARN_ON_ONCE(1);
 	return ULLONG_MAX;
 }
+static inline bool xfs_fsverity_is_file_data(const struct xfs_inode *ip,
+					    loff_t offset)
+{
+	return false;
+}
 #endif	/* CONFIG_FS_VERITY */
 
 #endif	/* __XFS_FSVERITY_H__ */

index 0ab00615f1ad..18348f4fd2aa 100644
@@ -31,6 +31,7 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_rtgroup.h"
 #include "xfs_zone_alloc.h"
+#include <linux/fsverity.h>
 
 /* Kernel only BMAP related definitions and functions */
 

@@ -553,6 +554,13 @@ xfs_can_free_eofblocks(
 	if (last_fsb <= end_fsb)
 		return false;
 
+	/*
+	 * Nothing to clean on fsverity inodes as they don't use prealloc and
+	 * there no delalloc as only written data is fsverity metadata
+	 */
+	if (IS_VERITY(VFS_I(ip)))
+		return false;
+
 	/*
 	 * Check if there is an post-EOF extent to free.  If there are any
 	 * delalloc blocks attached to the inode (data fork delalloc

369 lines not on this page · raw message

index ec77ba571106..6a981e20a75b 100644
@@ -6,8 +6,10 @@
 #define __XFS_FSVERITY_H__
 
 #include "xfs_platform.h"
+#include <linux/fsverity.h>
 
 #ifdef CONFIG_FS_VERITY
+extern const struct fsverity_operations xfs_fsverity_ops;
 loff_t xfs_fsverity_metadata_offset(const struct xfs_inode *ip);
 bool xfs_fsverity_is_file_data(const struct xfs_inode *ip, loff_t offset);
 #else

index fd297082aeb8..9818d8f8f239 100644
@@ -153,6 +153,10 @@ xfs_warn_experimental(
 			.opstate	= XFS_OPSTATE_WARNED_ZONED,
 			.name		= "zoned RT device",
 		},
+		[XFS_EXPERIMENTAL_FSVERITY] = {
+			.opstate	= XFS_OPSTATE_WARNED_FSVERITY,
+			.name		= "fsverity",
+		},
 	};
 	ASSERT(feat >= 0 && feat < XFS_EXPERIMENTAL_MAX);
 	BUILD_BUG_ON(ARRAY_SIZE(features) != XFS_EXPERIMENTAL_MAX);

index 49b0ef40d299..083403944f11 100644
@@ -94,6 +94,7 @@ enum xfs_experimental_feat {
 	XFS_EXPERIMENTAL_SHRINK,
 	XFS_EXPERIMENTAL_LARP,
 	XFS_EXPERIMENTAL_ZONED,
+	XFS_EXPERIMENTAL_FSVERITY,
 
 	XFS_EXPERIMENTAL_MAX,
 };

index 07f6aa3c3f26..84d7cfb5e2c7 100644
@@ -583,6 +583,8 @@ __XFS_HAS_FEAT(nouuid, NOUUID)
 #define XFS_OPSTATE_WARNED_ZONED	19
 /* (Zoned) GC is in progress */
 #define XFS_OPSTATE_ZONEGC_RUNNING	20
+/* Kernel has logged a warning about fsverity support */
+#define XFS_OPSTATE_WARNED_FSVERITY	21
 
 #define __XFS_IS_OPSTATE(name, NAME) \
 static inline bool xfs_is_ ## name (struct xfs_mount *mp) \

index f8de44443e81..d9d442009610 100644
@@ -30,6 +30,7 @@
 #include "xfs_filestream.h"
 #include "xfs_quota.h"
 #include "xfs_sysfs.h"
+#include "xfs_fsverity.h"
 #include "xfs_ondisk.h"
 #include "xfs_rmap_item.h"
 #include "xfs_refcount_item.h"

@@ -1686,6 +1687,9 @@ xfs_fs_fill_super(
 	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
 #endif
 	sb->s_op = &xfs_super_operations;
+#ifdef CONFIG_FS_VERITY
+	sb->s_vop = &xfs_fsverity_ops;
+#endif
 
 	/*
 	 * Delay mount work if the debug hook is set. This is debug

@@ -1939,6 +1943,9 @@ xfs_fs_fill_super(
 	if (error)
 		goto out_filestream_unmount;
 
+	if (xfs_has_verity(mp))
+		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_FSVERITY);
+
 	root = igrab(VFS_I(mp->m_rootip));
 	if (!root) {
 		error = -ENOENT;

index 68d9736d19d9..ef5cf97ad700 100644
@@ -21,6 +21,8 @@
 #include "xfs_iomap.h"
 #include "xfs_error.h"
 #include "xfs_health.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
 #include <linux/fsverity.h>
 #include <linux/iomap.h>
 #include <linux/pagemap.h>

@@ -173,6 +175,63 @@ xfs_fsverity_delete_metadata(
 	return error;
 }
 
+static int
+xfs_fsverity_cancel_unwritten(
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		start,
+	xfs_fileoff_t		end)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSB(mp, start);
+	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, end);
+	struct xfs_bmbt_irec	imap;
+	int			nimaps;
+	int			error = 0;
+	int			done;
+
+
+	while (offset_fsb < end_fsb) {
+		nimaps = 1;
+
+		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0,
+				0, &tp);
+		if (error)
+			return error;
+
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
+				&imap, &nimaps, 0);
+		if (error)
+			goto out_cancel;
+
+		if (nimaps == 0)
+			goto out_cancel;
+
+		if (imap.br_state == XFS_EXT_UNWRITTEN) {
+			xfs_trans_ijoin(tp, ip, 0);
+
+			error = xfs_bunmapi(tp, ip, imap.br_startoff,
+					imap.br_blockcount, 0, 1, &done);
+			if (error)
+				goto out_cancel;
+
+			error = xfs_trans_commit(tp);
+		} else {
+			xfs_trans_cancel(tp);
+		}
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+		offset_fsb = imap.br_startoff + imap.br_blockcount;
+	}
+
+	return error;
+out_cancel:
+	xfs_trans_cancel(tp);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return error;
+}
+
 
 /*
  * Prepare to enable fsverity by clearing old metadata.

@@ -248,6 +307,14 @@ xfs_fsverity_end_enable(
 	if (error)
 		goto out;
 
+	/*
+	 * Remove unwritten extents left by COW preallocations and write
+	 * preallocation in the merkle tree holes and past descriptor
+	 */
+	error = xfs_fsverity_cancel_unwritten(ip, range_start, LLONG_MAX);
+	if (error)
+		goto out;
+
 	/*
 	 * Proactively drop any delayed allocations in COW fork, the fsverity
 	 * files are read-only

index facffdc8dca8..e633d56cad00 100644
@@ -46,6 +46,7 @@
 
 #include <linux/mount.h>
 #include <linux/fileattr.h>
+#include <linux/fsverity.h>
 
 /* Return 0 on success or positive error */
 int

@@ -1426,6 +1427,19 @@ xfs_file_ioctl(
 	case XFS_IOC_VERIFY_MEDIA:
 		return xfs_ioc_verify_media(filp, arg);
 
+	case FS_IOC_ENABLE_VERITY:
+		if (!xfs_has_verity(mp))
+			return -EOPNOTSUPP;
+		return fsverity_ioctl_enable(filp, arg);
+	case FS_IOC_MEASURE_VERITY:
+		if (!xfs_has_verity(mp))
+			return -EOPNOTSUPP;
+		return fsverity_ioctl_measure(filp, arg);
+	case FS_IOC_READ_VERITY_METADATA:
+		if (!xfs_has_verity(mp))
+			return -EOPNOTSUPP;
+		return fsverity_ioctl_read_metadata(filp, arg);
+
 	default:
 		return -ENOTTY;
 	}

index d165de607d17..ebf17a0b0722 100644
@@ -250,6 +250,7 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_PARENT	(1 << 25) /* linux parent pointers */
 #define XFS_FSOP_GEOM_FLAGS_METADIR	(1 << 26) /* metadata directories */
 #define XFS_FSOP_GEOM_FLAGS_ZONED	(1 << 27) /* zoned rt device */
+#define XFS_FSOP_GEOM_FLAGS_VERITY	(1 << 28) /* fs-verity */
 
 /*
  * Minimum and maximum sizes need for growth checks.

index a15510ebd2f1..222bbe5559df 100644
@@ -1590,6 +1590,8 @@ xfs_fs_geometry(
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_METADIR;
 	if (xfs_has_zoned(mp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_ZONED;
+	if (xfs_has_verity(mp))
+		geo->flags |= XFS_FSOP_GEOM_FLAGS_VERITY;
 	geo->rtsectsize = sbp->sb_blocksize;
 	geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp);
 

index 390ac2e11ee0..daf7962c2374 100644
@@ -649,6 +649,13 @@ xchk_xattr(
 	if (!xfs_inode_hasattr(sc->ip))
 		return -ENOENT;
 
+	/*
+	 * If this is a verity file that won't activate, we cannot check the
+	 * merkle tree geometry.
+	 */
+	if (xchk_inode_verity_broken(sc->ip))
+		xchk_set_incomplete(sc);
+
 	/* Allocate memory for xattr checking. */
 	error = xchk_setup_xattr_buf(sc, 0);
 	if (error == -ENOMEM)

62 lines not on this page · raw message

index f2ecc68538f0..aa16d310bd6d 100644
@@ -264,6 +264,8 @@ int xchk_inode_is_allocated(struct xfs_scrub *sc, xfs_agino_t agino,
 		bool *inuse);
 int xchk_inode_count_blocks(struct xfs_scrub *sc, int whichfork,
 		xfs_extnum_t *nextents, xfs_filblks_t *count);
+int xchk_inode_setup_verity(struct xfs_scrub *sc);
+bool xchk_inode_verity_broken(struct xfs_inode *ip);
 
 bool xchk_inode_is_dirtree_root(const struct xfs_inode *ip);
 bool xchk_inode_is_sb_rooted(const struct xfs_inode *ip);

index 948d04dcba2a..8ce6917e22b4 100644
@@ -36,6 +36,10 @@ xchk_prepare_iscrub(
 
 	xchk_ilock(sc, XFS_IOLOCK_EXCL);
 
+	error = xchk_inode_setup_verity(sc);
+	if (error)
+		return error;
+
 	error = xchk_trans_alloc(sc, 0);
 	if (error)
 		return error;

@@ -833,6 +837,9 @@ xchk_inode(
 	if (S_ISREG(VFS_I(sc->ip)->i_mode))
 		xchk_inode_check_reflink_iflag(sc, sc->ip->i_ino);
 
+	if (xchk_inode_verity_broken(sc->ip))
+		xchk_ino_set_corrupt(sc, sc->sm->sm_ino);
+
 	xchk_inode_check_unlinked(sc);
 
 	xchk_inode_xref(sc, sc->ip->i_ino, &di);

index 9738b9ce3f2d..3761e3922466 100644
@@ -573,6 +573,8 @@ xrep_dinode_flags(
 		dip->di_nrext64_pad = 0;
 	else if (dip->di_version >= 3)
 		dip->di_v3_pad = 0;
+	if (!xfs_has_verity(mp) || !S_ISREG(mode))
+		flags2 &= ~XFS_DIFLAG2_VERITY;
 
 	if (flags2 & XFS_DIFLAG2_METADATA) {
 		xfs_failaddr_t	fa;

@@ -1613,6 +1615,10 @@ xrep_dinode_core(
 	if (iget_error)
 		return iget_error;
 
+	error = xchk_inode_setup_verity(sc);
+	if (error)
+		return error;
+
 	error = xchk_trans_alloc(sc, 0);
 	if (error)
 		return error;

@@ -2032,6 +2038,27 @@ xrep_inode_unlinked(
 	return 0;
 }
 
+/*
+ * If this file is a fsverity file, xchk_prepare_iscrub or xrep_dinode_core
+ * should have activated it.  If it's still not active, then there's something
+ * wrong with the verity descriptor and we should turn it off.
+ */
+STATIC int
+xrep_inode_verity(
+	struct xfs_scrub	*sc)
+{
+	struct inode		*inode = VFS_I(sc->ip);
+
+	if (xchk_inode_verity_broken(sc->ip)) {
+		sc->ip->i_diflags2 &= ~XFS_DIFLAG2_VERITY;
+		inode->i_flags &= ~S_VERITY;
+
+		xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+	}
+
+	return 0;
+}
+
 /* Repair an inode's fields. */
 int
 xrep_inode(

@@ -2081,6 +2108,15 @@ xrep_inode(
 			return error;
 	}
 
+	/*
+	 * Disable fsverity if it cannot be activated.  Activation failure
+	 * prohibits the file from being opened, so there cannot be another
+	 * program with an open fd to what it thinks is a verity file.
+	 */
+	error = xrep_inode_verity(sc);
+	if (error)
+		return error;
+
 	/* Reconnect incore unlinked list */
 	error = xrep_inode_unlinked(sc);
 	if (error)

index ebf17a0b0722..cece31ecee81 100644
@@ -422,6 +422,7 @@ struct xfs_bulkstat {
 #define XFS_BS_SICK_SYMLINK	(1 << 6)  /* symbolic link remote target */
 #define XFS_BS_SICK_PARENT	(1 << 7)  /* parent pointers */
 #define XFS_BS_SICK_DIRTREE	(1 << 8)  /* directory tree structure */
+#define XFS_BS_SICK_FSVERITY	(1 << 9)  /* fsverity metadata */
 
 /*
  * Project quota id helpers (previously projid was 16bit only

index 1d45cf5789e8..932b447190da 100644
@@ -104,6 +104,7 @@ struct xfs_rtgroup;
 /* Don't propagate sick status to ag health summary during inactivation */
 #define XFS_SICK_INO_FORGET	(1 << 12)
 #define XFS_SICK_INO_DIRTREE	(1 << 13)  /* directory tree structure */
+#define XFS_SICK_INO_FSVERITY	(1 << 14)  /* fsverity metadata */
 
 /* Primary evidence of health problems in a given group. */
 #define XFS_SICK_FS_PRIMARY	(XFS_SICK_FS_COUNTERS | \

@@ -140,7 +141,8 @@ struct xfs_rtgroup;
 				 XFS_SICK_INO_XATTR | \
 				 XFS_SICK_INO_SYMLINK | \
 				 XFS_SICK_INO_PARENT | \
-				 XFS_SICK_INO_DIRTREE)
+				 XFS_SICK_INO_DIRTREE | \
+				 XFS_SICK_INO_FSVERITY)
 
 #define XFS_SICK_INO_ZAPPED	(XFS_SICK_INO_BMBTD_ZAPPED | \
 				 XFS_SICK_INO_BMBTA_ZAPPED | \

index ef5cf97ad700..8ac810f0ffa1 100644
@@ -84,16 +84,23 @@ xfs_fsverity_get_descriptor(
 		return error;
 
 	desc_size = be32_to_cpu(d_desc_size);
-	if (XFS_IS_CORRUPT(mp, desc_size > FS_VERITY_MAX_DESCRIPTOR_SIZE))
+	if (XFS_IS_CORRUPT(mp, desc_size > FS_VERITY_MAX_DESCRIPTOR_SIZE)) {
+		xfs_inode_mark_sick(XFS_I(inode), XFS_SICK_INO_FSVERITY);
 		return -ERANGE;
-	if (XFS_IS_CORRUPT(mp, desc_size > desc_size_pos))
+	}
+
+	if (XFS_IS_CORRUPT(mp, desc_size > desc_size_pos)) {
+		xfs_inode_mark_sick(XFS_I(inode), XFS_SICK_INO_FSVERITY);
 		return -ERANGE;
+	}
 
 	if (!buf_size)
 		return desc_size;
 
-	if (XFS_IS_CORRUPT(mp, desc_size > buf_size))
+	if (XFS_IS_CORRUPT(mp, desc_size > buf_size)) {
+		xfs_inode_mark_sick(XFS_I(inode), XFS_SICK_INO_FSVERITY);
 		return -ERANGE;
+	}
 
 	desc_pos = round_down(desc_size_pos - desc_size, blocksize);
 	error = fsverity_pagecache_read(inode, buf, desc_size, desc_pos);

index 239b843e83d4..be66760fb120 100644
@@ -625,6 +625,7 @@ static const struct ioctl_sick_map ino_map[] = {
 	{ XFS_SICK_INO_DIR_ZAPPED,	XFS_BS_SICK_DIR },
 	{ XFS_SICK_INO_SYMLINK_ZAPPED,	XFS_BS_SICK_SYMLINK },
 	{ XFS_SICK_INO_DIRTREE,	XFS_BS_SICK_DIRTREE },
+	{ XFS_SICK_INO_FSVERITY,	XFS_BS_SICK_FSVERITY },
 };
 
 /* Fill out bulkstat health info. */

index 4dff29659e40..0ce46c234b9c 100644
@@ -378,8 +378,9 @@ xfs_sb_has_compat_feature(
 #define XFS_SB_FEAT_RO_COMPAT_ALL \
 		(XFS_SB_FEAT_RO_COMPAT_FINOBT | \
 		 XFS_SB_FEAT_RO_COMPAT_RMAPBT | \
-		 XFS_SB_FEAT_RO_COMPAT_REFLINK| \
-		 XFS_SB_FEAT_RO_COMPAT_INOBTCNT)
+		 XFS_SB_FEAT_RO_COMPAT_REFLINK | \
+		 XFS_SB_FEAT_RO_COMPAT_INOBTCNT | \
+		 XFS_SB_FEAT_RO_COMPAT_VERITY)
 #define XFS_SB_FEAT_RO_COMPAT_UNKNOWN	~XFS_SB_FEAT_RO_COMPAT_ALL
 static inline bool
 xfs_sb_has_ro_compat_feature(