fs/buffer.c: support fsverity in block_read_full_folio()

After each filesystem block (as represented by a buffer_head) has been
read from disk by block_read_full_folio(), verify it if needed.  The
verification is done on the fsverity_read_workqueue.  Also allow reads
of verity metadata past i_size, as required by ext4.

This is needed to support fsverity on ext4 filesystems where the
filesystem block size is less than the page size.

The new code is compiled away when CONFIG_FS_VERITY=n.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Tested-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Link: https://lore.kernel.org/r/20221223203638.41293-11-ebiggers@kernel.org

1 files changed, 57 insertions, 10 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index d9c6d1fbb6dd..2e65ba2b3919 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -48,6 +48,7 @@
 #include <linux/sched/mm.h>
 #include <trace/events/block.h>
 #include <linux/fscrypt.h>
+#include <linux/fsverity.h>
 
 #include "internal.h"
 
@@ -295,20 +296,52 @@ still_busy:
 	return;
 }
 
-struct decrypt_bh_ctx {
+struct postprocess_bh_ctx {
 	struct work_struct work;
 	struct buffer_head *bh;
 };
 
+static void verify_bh(struct work_struct *work)
+{
+	struct postprocess_bh_ctx *ctx =
+		container_of(work, struct postprocess_bh_ctx, work);
+	struct buffer_head *bh = ctx->bh;
+	bool valid;
+
+	valid = fsverity_verify_blocks(bh->b_page, bh->b_size, bh_offset(bh));
+	end_buffer_async_read(bh, valid);
+	kfree(ctx);
+}
+
+static bool need_fsverity(struct buffer_head *bh)
+{
+	struct page *page = bh->b_page;
+	struct inode *inode = page->mapping->host;
+
+	return fsverity_active(inode) &&
+		/* needed by ext4 */
+		page->index < DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
+}
+
 static void decrypt_bh(struct work_struct *work)
 {
-	struct decrypt_bh_ctx *ctx =
-		container_of(work, struct decrypt_bh_ctx, work);
+	struct postprocess_bh_ctx *ctx =
+		container_of(work, struct postprocess_bh_ctx, work);
 	struct buffer_head *bh = ctx->bh;
 	int err;
 
 	err = fscrypt_decrypt_pagecache_blocks(bh->b_page, bh->b_size,
 					       bh_offset(bh));
+	if (err == 0 && need_fsverity(bh)) {
+		/*
+		 * 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.
+		 */
+		INIT_WORK(&ctx->work, verify_bh);
+		fsverity_enqueue_verify_work(&ctx->work);
+		return;
+	}
 	end_buffer_async_read(bh, err == 0);
 	kfree(ctx);
 }
@@ -319,15 +352,24 @@ static void decrypt_bh(struct work_struct *work)
  */
 static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate)
 {
-	/* Decrypt if needed */
-	if (uptodate &&
-	    fscrypt_inode_uses_fs_layer_crypto(bh->b_page->mapping->host)) {
-		struct decrypt_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC);
+	struct inode *inode = bh->b_page->mapping->host;
+	bool decrypt = fscrypt_inode_uses_fs_layer_crypto(inode);
+	bool verify = need_fsverity(bh);
+
+	/* Decrypt (with fscrypt) and/or verify (with fsverity) if needed. */
+	if (uptodate && (decrypt || verify)) {
+		struct postprocess_bh_ctx *ctx =
+			kmalloc(sizeof(*ctx), GFP_ATOMIC);
 
 		if (ctx) {
-			INIT_WORK(&ctx->work, decrypt_bh);
 			ctx->bh = bh;
-			fscrypt_enqueue_decrypt_work(&ctx->work);
+			if (decrypt) {
+				INIT_WORK(&ctx->work, decrypt_bh);
+				fscrypt_enqueue_decrypt_work(&ctx->work);
+			} else {
+				INIT_WORK(&ctx->work, verify_bh);
+				fsverity_enqueue_verify_work(&ctx->work);
+			}
 			return;
 		}
 		uptodate = 0;
@@ -2245,6 +2287,11 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 	int nr, i;
 	int fully_mapped = 1;
 	bool page_error = false;
+	loff_t limit = i_size_read(inode);
+
+	/* This is needed for ext4. */
+	if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode))
+		limit = inode->i_sb->s_maxbytes;
 
 	VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
 
@@ -2253,7 +2300,7 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 	bbits = block_size_bits(blocksize);
 
 	iblock = (sector_t)folio->index << (PAGE_SHIFT - bbits);
-	lblock = (i_size_read(inode)+blocksize-1) >> bbits;
+	lblock = (limit+blocksize-1) >> bbits;
 	bh = head;
 	nr = 0;
 	i = 0;