Miscellaneous ext4 bug fixes for v4.5

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQEcBAABCAAGBQJWx2ZiAAoJEPL5WVaVDYGjrbcH/2EqCUDmW+FqVqR7PkpQsNiV
 WxBTNkxnVXf1Jin5beIUN/Ehq0GSuqcSujMwdbFUa0i7YJNVEe++hTw28JmFILYV
 5nZtTYmYIq7dZb/tnc3tj0SsDpgEE1h31VyWAu4W2q4wSQMDc8AqGM90VktgrerJ
 H9k/WDDL6KC8uXagBsQC0d5xaQglJNZC+S6pSBbMegBAFNJqAL5N78oWAoEFN3OH
 LN3B3eccxBx98rGWx8DBiugY8ZDRHB4Cre+fXu8wmAuMb/+Y7Mwj4RzI+fz5Vpiw
 vMS5RqZ7PvCaMhdyUWt9bI8j10bBXcaxOHL2UQND5A1zundJ1ZNOY/ZPvHVUS4s=
 =AXFu
 -----END PGP SIGNATURE-----

Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 bugfixes from Ted Ts'o:
 "Miscellaneous ext4 bug fixes for v4.5"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: fix crashes in dioread_nolock mode
  ext4: fix bh->b_state corruption
  ext4: fix memleak in ext4_readdir()
  ext4: remove unused parameter "newblock" in convert_initialized_extent()
  ext4: don't read blocks from disk after extents being swapped
  ext4: fix potential integer overflow
  ext4: add a line break for proc mb_groups display
  ext4: ioctl: fix erroneous return value
  ext4: fix scheduling in atomic on group checksum failure
  ext4 crypto: move context consistency check to ext4_file_open()
  ext4 crypto: revalidate dentry after adding or removing the key

fs/ext4/balloc.c

@@ -191,7 +191,6 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	/* If checksum is bad mark all blocks used to prevent allocation
 	 * essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
 		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
 			percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -442,14 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	}
 	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-
 		err = ext4_init_block_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
-		if (err)
+		if (err) {
+			ext4_error(sb, "Failed to init block bitmap for group "
+				   "%u: %d", block_group, err);
 			goto out;
+		}
 		goto verify;
 	}
 	ext4_unlock_group(sb, block_group);

fs/ext4/crypto.c

@@ -467,3 +467,59 @@ uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size)
 		return size;
 	return 0;
 }
+
+/*
+ * Validate dentries for encrypted directories to make sure we aren't
+ * potentially caching stale data after a key has been added or
+ * removed.
+ */
+static int ext4_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct inode *dir = d_inode(dentry->d_parent);
+	struct ext4_crypt_info *ci = EXT4_I(dir)->i_crypt_info;
+	int dir_has_key, cached_with_key;
+
+	if (!ext4_encrypted_inode(dir))
+		return 0;
+
+	if (ci && ci->ci_keyring_key &&
+	    (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					  (1 << KEY_FLAG_REVOKED) |
+					  (1 << KEY_FLAG_DEAD))))
+		ci = NULL;
+
+	/* this should eventually be an flag in d_flags */
+	cached_with_key = dentry->d_fsdata != NULL;
+	dir_has_key = (ci != NULL);
+
+	/*
+	 * If the dentry was cached without the key, and it is a
+	 * negative dentry, it might be a valid name.  We can't check
+	 * if the key has since been made available due to locking
+	 * reasons, so we fail the validation so ext4_lookup() can do
+	 * this check.
+	 *
+	 * We also fail the validation if the dentry was created with
+	 * the key present, but we no longer have the key, or vice versa.
+	 */
+	if ((!cached_with_key && d_is_negative(dentry)) ||
+	    (!cached_with_key && dir_has_key) ||
+	    (cached_with_key && !dir_has_key)) {
+#if 0				/* Revalidation debug */
+		char buf[80];
+		char *cp = simple_dname(dentry, buf, sizeof(buf));
+
+		if (IS_ERR(cp))
+			cp = (char *) "???";
+		pr_err("revalidate: %s %p %d %d %d\n", cp, dentry->d_fsdata,
+		       cached_with_key, d_is_negative(dentry),
+		       dir_has_key);
+#endif
+		return 0;
+	}
+	return 1;
+}
+
+const struct dentry_operations ext4_encrypted_d_ops = {
+	.d_revalidate = ext4_d_revalidate,
+};

fs/ext4/dir.c

@@ -111,6 +111,12 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	int dir_has_error = 0;
 	struct ext4_str fname_crypto_str = {.name = NULL, .len = 0};
 
+	if (ext4_encrypted_inode(inode)) {
+		err = ext4_get_encryption_info(inode);
+		if (err && err != -ENOKEY)
+			return err;
+	}
+
 	if (is_dx_dir(inode)) {
 		err = ext4_dx_readdir(file, ctx);
 		if (err != ERR_BAD_DX_DIR) {
@@ -157,8 +163,11 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 					index, 1);
 			file->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
 			bh = ext4_bread(NULL, inode, map.m_lblk, 0);
-			if (IS_ERR(bh))
+			if (IS_ERR(bh)) {
-				return PTR_ERR(bh);
+				err = PTR_ERR(bh);
+				bh = NULL;
+				goto errout;
+			}
 		}
 
 		if (!bh) {

fs/ext4/ext4.h

@@ -2302,6 +2302,7 @@ struct page *ext4_encrypt(struct inode *inode,
 int ext4_decrypt(struct page *page);
 int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk,
 			   ext4_fsblk_t pblk, ext4_lblk_t len);
+extern const struct dentry_operations ext4_encrypted_d_ops;
 
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 int ext4_init_crypto(void);

fs/ext4/extents.c

@@ -3928,7 +3928,7 @@ static int
 convert_initialized_extent(handle_t *handle, struct inode *inode,
 			   struct ext4_map_blocks *map,
 			   struct ext4_ext_path **ppath, int flags,
-			   unsigned int allocated, ext4_fsblk_t newblock)
+			   unsigned int allocated)
 {
 	struct ext4_ext_path *path = *ppath;
 	struct ext4_extent *ex;
@@ -4347,7 +4347,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			    (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
 				allocated = convert_initialized_extent(
 						handle, inode, map, &path,
-						flags, allocated, newblock);
+						flags, allocated);
 				goto out2;
 			} else if (!ext4_ext_is_unwritten(ex))
 				goto out;

fs/ext4/file.c

@@ -350,6 +350,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	struct super_block *sb = inode->i_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct vfsmount *mnt = filp->f_path.mnt;
+	struct inode *dir = filp->f_path.dentry->d_parent->d_inode;
 	struct path path;
 	char buf[64], *cp;
 	int ret;
@@ -393,6 +394,14 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 		if (ext4_encryption_info(inode) == NULL)
 			return -ENOKEY;
 	}
+	if (ext4_encrypted_inode(dir) &&
+	    !ext4_is_child_context_consistent_with_parent(dir, inode)) {
+		ext4_warning(inode->i_sb,
+			     "Inconsistent encryption contexts: %lu/%lu\n",
+			     (unsigned long) dir->i_ino,
+			     (unsigned long) inode->i_ino);
+		return -EPERM;
+	}
 	/*
 	 * Set up the jbd2_inode if we are opening the inode for
 	 * writing and the journal is present

fs/ext4/ialloc.c

@@ -76,7 +76,6 @@ static int ext4_init_inode_bitmap(struct super_block *sb,
 	/* If checksum is bad mark all blocks and inodes use to prevent
 	 * allocation, essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
 		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
 			percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -191,8 +190,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		set_buffer_verified(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
-		if (err)
+		if (err) {
+			ext4_error(sb, "Failed to init inode bitmap for group "
+				   "%u: %d", block_group, err);
 			goto out;
+		}
 		return bh;
 	}
 	ext4_unlock_group(sb, block_group);

fs/ext4/inode.c

@@ -686,6 +686,34 @@ out_sem:
 	return retval;
 }
 
+/*
+ * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
+ * we have to be careful as someone else may be manipulating b_state as well.
+ */
+static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
+{
+	unsigned long old_state;
+	unsigned long new_state;
+
+	flags &= EXT4_MAP_FLAGS;
+
+	/* Dummy buffer_head? Set non-atomically. */
+	if (!bh->b_page) {
+		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags;
+		return;
+	}
+	/*
+	 * Someone else may be modifying b_state. Be careful! This is ugly but
+	 * once we get rid of using bh as a container for mapping information
+	 * to pass to / from get_block functions, this can go away.
+	 */
+	do {
+		old_state = READ_ONCE(bh->b_state);
+		new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
+	} while (unlikely(
+		 cmpxchg(&bh->b_state, old_state, new_state) != old_state));
+}
+
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
@@ -722,7 +750,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 		ext4_io_end_t *io_end = ext4_inode_aio(inode);
 
 		map_bh(bh, inode->i_sb, map.m_pblk);
-		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		ext4_update_bh_state(bh, map.m_flags);
 		if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
 			set_buffer_defer_completion(bh);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
@@ -1685,7 +1713,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 		return ret;
 
 	map_bh(bh, inode->i_sb, map.m_pblk);
-	bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+	ext4_update_bh_state(bh, map.m_flags);
 
 	if (buffer_unwritten(bh)) {
 		/* A delayed write to unwritten bh should be marked
@@ -3253,29 +3281,29 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	 * case, we allocate an io_end structure to hook to the iocb.
 	 */
 	iocb->private = NULL;
-	ext4_inode_aio_set(inode, NULL);
-	if (!is_sync_kiocb(iocb)) {
-		io_end = ext4_init_io_end(inode, GFP_NOFS);
-		if (!io_end) {
-			ret = -ENOMEM;
-			goto retake_lock;
-		}
-		/*
-		 * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
-		 */
-		iocb->private = ext4_get_io_end(io_end);
-		/*
-		 * we save the io structure for current async direct
-		 * IO, so that later ext4_map_blocks() could flag the
-		 * io structure whether there is a unwritten extents
-		 * needs to be converted when IO is completed.
-		 */
-		ext4_inode_aio_set(inode, io_end);
-	}
-
 	if (overwrite) {
 		get_block_func = ext4_get_block_overwrite;
 	} else {
+		ext4_inode_aio_set(inode, NULL);
+		if (!is_sync_kiocb(iocb)) {
+			io_end = ext4_init_io_end(inode, GFP_NOFS);
+			if (!io_end) {
+				ret = -ENOMEM;
+				goto retake_lock;
+			}
+			/*
+			 * Grab reference for DIO. Will be dropped in
+			 * ext4_end_io_dio()
+			 */
+			iocb->private = ext4_get_io_end(io_end);
+			/*
+			 * we save the io structure for current async direct
+			 * IO, so that later ext4_map_blocks() could flag the
+			 * io structure whether there is a unwritten extents
+			 * needs to be converted when IO is completed.
+			 */
+			ext4_inode_aio_set(inode, io_end);
+		}
 		get_block_func = ext4_get_block_write;
 		dio_flags = DIO_LOCKING;
 	}

fs/ext4/ioctl.c

@@ -208,7 +208,7 @@ static int ext4_ioctl_setflags(struct inode *inode,
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	handle_t *handle = NULL;
-	int err = EPERM, migrate = 0;
+	int err = -EPERM, migrate = 0;
 	struct ext4_iloc iloc;
 	unsigned int oldflags, mask, i;
 	unsigned int jflag;

fs/ext4/mballoc.c

@@ -2285,7 +2285,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	if (group == 0)
 		seq_puts(seq, "#group: free  frags first ["
 			      " 2^0   2^1   2^2   2^3   2^4   2^5   2^6  "
-			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]");
+			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]\n");
 
 	i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) +
 		sizeof(struct ext4_group_info);

fs/ext4/move_extent.c

@@ -265,11 +265,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 	ext4_lblk_t orig_blk_offset, donor_blk_offset;
 	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
 	unsigned int tmp_data_size, data_size, replaced_size;
-	int err2, jblocks, retries = 0;
+	int i, err2, jblocks, retries = 0;
 	int replaced_count = 0;
 	int from = data_offset_in_page << orig_inode->i_blkbits;
 	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
 	struct super_block *sb = orig_inode->i_sb;
+	struct buffer_head *bh = NULL;
 
 	/*
 	 * It needs twice the amount of ordinary journal buffers because
@@ -380,8 +381,16 @@ data_copy:
 	}
 	/* Perform all necessary steps similar write_begin()/write_end()
 	 * but keeping in mind that i_size will not change */
-	*err = __block_write_begin(pagep[0], from, replaced_size,
+	if (!page_has_buffers(pagep[0]))
-				   ext4_get_block);
+		create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0);
+	bh = page_buffers(pagep[0]);
+	for (i = 0; i < data_offset_in_page; i++)
+		bh = bh->b_this_page;
+	for (i = 0; i < block_len_in_page; i++) {
+		*err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
+		if (*err < 0)
+			break;
+	}
 	if (!*err)
 		*err = block_commit_write(pagep[0], from, from + replaced_size);
 

fs/ext4/namei.c

@@ -1558,6 +1558,24 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 	struct ext4_dir_entry_2 *de;
 	struct buffer_head *bh;
 
+       if (ext4_encrypted_inode(dir)) {
+               int res = ext4_get_encryption_info(dir);
+
+		/*
+		 * This should be a properly defined flag for
+		 * dentry->d_flags when we uplift this to the VFS.
+		 * d_fsdata is set to (void *) 1 if if the dentry is
+		 * created while the directory was encrypted and we
+		 * don't have access to the key.
+		 */
+	       dentry->d_fsdata = NULL;
+	       if (ext4_encryption_info(dir))
+		       dentry->d_fsdata = (void *) 1;
+	       d_set_d_op(dentry, &ext4_encrypted_d_ops);
+	       if (res && res != -ENOKEY)
+		       return ERR_PTR(res);
+       }
+
 	if (dentry->d_name.len > EXT4_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
@@ -1585,11 +1603,15 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 			return ERR_PTR(-EFSCORRUPTED);
 		}
 		if (!IS_ERR(inode) && ext4_encrypted_inode(dir) &&
-		    (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
-		     S_ISLNK(inode->i_mode)) &&
 		    !ext4_is_child_context_consistent_with_parent(dir,
 								  inode)) {
+			int nokey = ext4_encrypted_inode(inode) &&
+				!ext4_encryption_info(inode);
+
 			iput(inode);
+			if (nokey)
+				return ERR_PTR(-ENOKEY);
 			ext4_warning(inode->i_sb,
 				     "Inconsistent encryption contexts: %lu/%lu\n",
 				     (unsigned long) dir->i_ino,

fs/ext4/resize.c

@@ -198,7 +198,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
 	if (flex_gd == NULL)
 		goto out3;
 
-	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data))
+	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data))
 		goto out2;
 	flex_gd->count = flexbg_size;