f2fs: add fs-verity support

Add fs-verity support to f2fs.  fs-verity is a filesystem feature that
enables transparent integrity protection and authentication of read-only
files.  It uses a dm-verity like mechanism at the file level: a Merkle
tree is used to verify any block in the file in log(filesize) time.  It
is implemented mainly by helper functions in fs/verity/.  See
Documentation/filesystems/fsverity.rst for the full documentation.

The f2fs support for fs-verity consists of:

- Adding a filesystem feature flag and an inode flag for fs-verity.

- Implementing the fsverity_operations to support enabling verity on an
  inode and reading/writing the verity metadata.

- Updating ->readpages() to verify data as it's read from verity files
  and to support reading verity metadata pages.

- Updating ->write_begin(), ->write_end(), and ->writepages() to support
  writing verity metadata pages.

- Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl().

Like ext4, f2fs stores the verity metadata (Merkle tree and
fsverity_descriptor) past the end of the file, starting at the first 64K
boundary beyond i_size.  This approach works because (a) verity files
are readonly, and (b) pages fully beyond i_size aren't visible to
userspace but can be read/written internally by f2fs with only some
relatively small changes to f2fs.  Extended attributes cannot be used
because (a) f2fs limits the total size of an inode's xattr entries to
4096 bytes, which wouldn't be enough for even a single Merkle tree
block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity
metadata *must* be encrypted when the file is because it contains hashes
of the plaintext data.

Acked-by: Jaegeuk Kim <jaegeuk@kernel.org>
Acked-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Eric Biggers <ebiggers@google.com>

1 files changed, 65 insertions, 10 deletions

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index abbf14e9bd72..54cad80acb7d 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -74,6 +74,7 @@ static enum count_type __read_io_type(struct page *page)
 enum bio_post_read_step {
 	STEP_INITIAL = 0,
 	STEP_DECRYPT,
+	STEP_VERITY,
 };
 
 struct bio_post_read_ctx {
@@ -120,8 +121,23 @@ static void decrypt_work(struct work_struct *work)
 	bio_post_read_processing(ctx);
 }
 
+static void verity_work(struct work_struct *work)
+{
+	struct bio_post_read_ctx *ctx =
+		container_of(work, struct bio_post_read_ctx, work);
+
+	fsverity_verify_bio(ctx->bio);
+
+	bio_post_read_processing(ctx);
+}
+
 static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
 {
+	/*
+	 * We use different work queues for decryption and for verity because
+	 * verity may require reading metadata pages that need decryption, and
+	 * we shouldn't recurse to the same workqueue.
+	 */
 	switch (++ctx->cur_step) {
 	case STEP_DECRYPT:
 		if (ctx->enabled_steps & (1 << STEP_DECRYPT)) {
@@ -131,6 +147,14 @@ static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
 		}
 		ctx->cur_step++;
 		/* fall-through */
+	case STEP_VERITY:
+		if (ctx->enabled_steps & (1 << STEP_VERITY)) {
+			INIT_WORK(&ctx->work, verity_work);
+			fsverity_enqueue_verify_work(&ctx->work);
+			return;
+		}
+		ctx->cur_step++;
+		/* fall-through */
 	default:
 		__read_end_io(ctx->bio);
 	}
@@ -608,8 +632,15 @@ out:
 	up_write(&io->io_rwsem);
 }
 
+static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx)
+{
+	return fsverity_active(inode) &&
+	       idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
+}
+
 static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
-					unsigned nr_pages, unsigned op_flag)
+				      unsigned nr_pages, unsigned op_flag,
+				      pgoff_t first_idx)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct bio *bio;
@@ -625,6 +656,10 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 
 	if (f2fs_encrypted_file(inode))
 		post_read_steps |= 1 << STEP_DECRYPT;
+
+	if (f2fs_need_verity(inode, first_idx))
+		post_read_steps |= 1 << STEP_VERITY;
+
 	if (post_read_steps) {
 		ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
 		if (!ctx) {
@@ -646,7 +681,7 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct bio *bio;
 
-	bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0);
+	bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0, page->index);
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
@@ -1569,6 +1604,15 @@ out:
 	return ret;
 }
 
+static inline loff_t f2fs_readpage_limit(struct inode *inode)
+{
+	if (IS_ENABLED(CONFIG_FS_VERITY) &&
+	    (IS_VERITY(inode) || f2fs_verity_in_progress(inode)))
+		return inode->i_sb->s_maxbytes;
+
+	return i_size_read(inode);
+}
+
 static int f2fs_read_single_page(struct inode *inode, struct page *page,
 					unsigned nr_pages,
 					struct f2fs_map_blocks *map,
@@ -1587,7 +1631,7 @@ static int f2fs_read_single_page(struct inode *inode, struct page *page,
 
 	block_in_file = (sector_t)page_index(page);
 	last_block = block_in_file + nr_pages;
-	last_block_in_file = (i_size_read(inode) + blocksize - 1) >>
+	last_block_in_file = (f2fs_readpage_limit(inode) + blocksize - 1) >>
 							blkbits;
 	if (last_block > last_block_in_file)
 		last_block = last_block_in_file;
@@ -1632,6 +1676,11 @@ got_it:
 	} else {
 zero_out:
 		zero_user_segment(page, 0, PAGE_SIZE);
+		if (f2fs_need_verity(inode, page->index) &&
+		    !fsverity_verify_page(page)) {
+			ret = -EIO;
+			goto out;
+		}
 		if (!PageUptodate(page))
 			SetPageUptodate(page);
 		unlock_page(page);
@@ -1650,7 +1699,7 @@ submit_and_realloc:
 	}
 	if (bio == NULL) {
 		bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
-				is_readahead ? REQ_RAHEAD : 0);
+				is_readahead ? REQ_RAHEAD : 0, page->index);
 		if (IS_ERR(bio)) {
 			ret = PTR_ERR(bio);
 			bio = NULL;
@@ -2052,7 +2101,7 @@ static int __write_data_page(struct page *page, bool *submitted,
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 
-	if (page->index < end_index)
+	if (page->index < end_index || f2fs_verity_in_progress(inode))
 		goto write;
 
 	/*
@@ -2427,7 +2476,8 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to)
 	struct inode *inode = mapping->host;
 	loff_t i_size = i_size_read(inode);
 
-	if (to > i_size) {
+	/* In the fs-verity case, f2fs_end_enable_verity() does the truncate */
+	if (to > i_size && !f2fs_verity_in_progress(inode)) {
 		down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 		down_write(&F2FS_I(inode)->i_mmap_sem);
 
@@ -2458,7 +2508,8 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
 	 * the block addresses when there is no need to fill the page.
 	 */
 	if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE &&
-			!is_inode_flag_set(inode, FI_NO_PREALLOC))
+	    !is_inode_flag_set(inode, FI_NO_PREALLOC) &&
+	    !f2fs_verity_in_progress(inode))
 		return 0;
 
 	/* f2fs_lock_op avoids race between write CP and convert_inline_page */
@@ -2597,7 +2648,8 @@ repeat:
 	if (len == PAGE_SIZE || PageUptodate(page))
 		return 0;
 
-	if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode)) {
+	if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode) &&
+	    !f2fs_verity_in_progress(inode)) {
 		zero_user_segment(page, len, PAGE_SIZE);
 		return 0;
 	}
@@ -2660,7 +2712,8 @@ static int f2fs_write_end(struct file *file,
 
 	set_page_dirty(page);
 
-	if (pos + copied > i_size_read(inode))
+	if (pos + copied > i_size_read(inode) &&
+	    !f2fs_verity_in_progress(inode))
 		f2fs_i_size_write(inode, pos + copied);
 unlock_out:
 	f2fs_put_page(page, 1);
@@ -3104,7 +3157,9 @@ void f2fs_clear_page_cache_dirty_tag(struct page *page)
 
 int __init f2fs_init_post_read_processing(void)
 {
-	bio_post_read_ctx_cache = KMEM_CACHE(bio_post_read_ctx, 0);
+	bio_post_read_ctx_cache =
+		kmem_cache_create("f2fs_bio_post_read_ctx",
+				  sizeof(struct bio_post_read_ctx), 0, 0, NULL);
 	if (!bio_post_read_ctx_cache)
 		goto fail;
 	bio_post_read_ctx_pool =