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

Pull ext4 fixes from Ted Ts'o:
"Miscellaneous ext4 bug fixes for v5.12"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
ext4: initialize ret to suppress smatch warning
ext4: stop inode update before return
ext4: fix rename whiteout with fast commit
ext4: fix timer use-after-free on failed mount
ext4: fix potential error in ext4_do_update_inode
ext4: do not try to set xattr into ea_inode if value is empty
ext4: do not iput inode under running transaction in ext4_rename()
ext4: find old entry again if failed to rename whiteout
ext4: fix error handling in ext4_end_enable_verity()
ext4: fix bh ref count on error paths
fs/ext4: fix integer overflow in s_log_groups_per_flex
ext4: add reclaim checks to xattr code
ext4: shrink race window in ext4_should_retry_alloc()

fs/ext4/balloc.c

···
 
 /**
  * ext4_should_retry_alloc() - check if a block allocation should be retried
- * @sb:			super block
- * @retries:		number of attemps has been made
+ * @sb:			superblock
+ * @retries:		number of retry attempts made so far
  *
- * ext4_should_retry_alloc() is called when ENOSPC is returned, and if
- * it is profitable to retry the operation, this function will wait
- * for the current or committing transaction to complete, and then
- * return TRUE.  We will only retry once.
+ * ext4_should_retry_alloc() is called when ENOSPC is returned while
+ * attempting to allocate blocks.  If there's an indication that a pending
+ * journal transaction might free some space and allow another attempt to
+ * succeed, this function will wait for the current or committing transaction
+ * to complete and then return TRUE.
  */
 int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 {
-	if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) ||
-	    (*retries)++ > 1 ||
-	    !EXT4_SB(sb)->s_journal)
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (!sbi->s_journal)
 		return 0;
 
+	if (++(*retries) > 3) {
+		percpu_counter_inc(&sbi->s_sra_exceeded_retry_limit);
+		return 0;
+	}
+
+	/*
+	 * if there's no indication that blocks are about to be freed it's
+	 * possible we just missed a transaction commit that did so
+	 */
 	smp_mb();
-	if (EXT4_SB(sb)->s_mb_free_pending == 0)
-		return 0;
+	if (sbi->s_mb_free_pending == 0)
+		return ext4_has_free_clusters(sbi, 1, 0);
 
+	/*
+	 * it's possible we've just missed a transaction commit here,
+	 * so ignore the returned status
+	 */
 	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
-	jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+	(void) jbd2_journal_force_commit_nested(sbi->s_journal);
 	return 1;
 }
 

fs/ext4/ext4.h

···
 	struct percpu_counter s_freeinodes_counter;
 	struct percpu_counter s_dirs_counter;
 	struct percpu_counter s_dirtyclusters_counter;
+	struct percpu_counter s_sra_exceeded_retry_limit;
 	struct blockgroup_lock *s_blockgroup_lock;
 	struct proc_dir_entry *s_proc;
 	struct kobject s_kobj;
···
 	struct dentry *dentry);
 void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry);
 void ext4_fc_track_link(handle_t *handle, struct dentry *dentry);
+void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
+			    struct dentry *dentry);
 void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
 void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
 void ext4_fc_mark_ineligible(struct super_block *sb, int reason);

fs/ext4/extents.c

···
 {
 	struct inode *inode = file_inode(file);
 	handle_t *handle;
-	int ret, ret2 = 0, ret3 = 0;
+	int ret = 0, ret2 = 0, ret3 = 0;
 	int retries = 0;
 	int depth = 0;
 	struct ext4_map_blocks map;

fs/ext4/fast_commit.c

···
 	__ext4_fc_track_link(handle, d_inode(dentry), dentry);
 }
 
-void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
+void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
+			  struct dentry *dentry)
 {
 	struct __track_dentry_update_args args;
-	struct inode *inode = d_inode(dentry);
 	int ret;
 
 	args.dentry = dentry;
···
 	ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
 					(void *)&args, 0);
 	trace_ext4_fc_track_create(inode, dentry, ret);
+}
+
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
+{
+	__ext4_fc_track_create(handle, d_inode(dentry), dentry);
 }
 
 /* __track_fn for inode tracking */

fs/ext4/inode.c

···
 	if (!ret)
 		ret = err;
 
-	if (!ext4_has_inline_data(inode))
-		ext4_walk_page_buffers(NULL, page_bufs, 0, len,
-				       NULL, bput_one);
 	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 out:
 	unlock_page(page);
 out_no_pagelock:
+	if (!inline_data && page_bufs)
+		ext4_walk_page_buffers(NULL, page_bufs, 0, len,
+				       NULL, bput_one);
 	brelse(inode_bh);
 	return ret;
 }
···
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct buffer_head *bh = iloc->bh;
 	struct super_block *sb = inode->i_sb;
-	int err = 0, rc, block;
+	int err = 0, block;
 	int need_datasync = 0, set_large_file = 0;
 	uid_t i_uid;
 	gid_t i_gid;
···
 					      bh->b_data);
 
 	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-	rc = ext4_handle_dirty_metadata(handle, NULL, bh);
-	if (!err)
-		err = rc;
+	err = ext4_handle_dirty_metadata(handle, NULL, bh);
+	if (err)
+		goto out_brelse;
 	ext4_clear_inode_state(inode, EXT4_STATE_NEW);
 	if (set_large_file) {
 		BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");
···
 			inode->i_gid = attr->ia_gid;
 		error = ext4_mark_inode_dirty(handle, inode);
 		ext4_journal_stop(handle);
-		if (unlikely(error))
+		if (unlikely(error)) {
+			ext4_fc_stop_update(inode);
 			return error;
+		}
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {

fs/ext4/mballoc.c

···
 	}
 
 	if (ext4_has_feature_flex_bg(sb)) {
-		/* a single flex group is supposed to be read by a single IO */
-		sbi->s_mb_prefetch = min(1 << sbi->s_es->s_log_groups_per_flex,
+		/* a single flex group is supposed to be read by a single IO.
+		 * 2 ^ s_log_groups_per_flex != UINT_MAX as s_mb_prefetch is
+		 * unsigned integer, so the maximum shift is 32.
+		 */
+		if (sbi->s_es->s_log_groups_per_flex >= 32) {
+			ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group");
+			goto err_freesgi;
+		}
+		sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex,
 			BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9));
 		sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */
 	} else {

fs/ext4/namei.c

···
 	return retval;
 }
 
+static void ext4_resetent(handle_t *handle, struct ext4_renament *ent,
+			  unsigned ino, unsigned file_type)
+{
+	struct ext4_renament old = *ent;
+	int retval = 0;
+
+	/*
+	 * old->de could have moved from under us during make indexed dir,
+	 * so the old->de may no longer valid and need to find it again
+	 * before reset old inode info.
+	 */
+	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+	if (IS_ERR(old.bh))
+		retval = PTR_ERR(old.bh);
+	if (!old.bh)
+		retval = -ENOENT;
+	if (retval) {
+		ext4_std_error(old.dir->i_sb, retval);
+		return;
+	}
+
+	ext4_setent(handle, &old, ino, file_type);
+	brelse(old.bh);
+}
+
 static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
 				  const struct qstr *d_name)
 {
···
 	 */
 	retval = -ENOENT;
 	if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino)
-		goto end_rename;
+		goto release_bh;
 
 	new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
 				 &new.de, &new.inlined);
 	if (IS_ERR(new.bh)) {
 		retval = PTR_ERR(new.bh);
 		new.bh = NULL;
-		goto end_rename;
+		goto release_bh;
 	}
 	if (new.bh) {
 		if (!new.inode) {
···
 		handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits);
 		if (IS_ERR(handle)) {
 			retval = PTR_ERR(handle);
-			handle = NULL;
-			goto end_rename;
+			goto release_bh;
 		}
 	} else {
 		whiteout = ext4_whiteout_for_rename(mnt_userns, &old, credits, &handle);
 		if (IS_ERR(whiteout)) {
 			retval = PTR_ERR(whiteout);
-			whiteout = NULL;
-			goto end_rename;
+			goto release_bh;
 		}
 	}
 
···
 		retval = ext4_mark_inode_dirty(handle, whiteout);
 		if (unlikely(retval))
 			goto end_rename;
+
 	}
 	if (!new.bh) {
 		retval = ext4_add_entry(handle, new.dentry, old.inode);
···
 			ext4_fc_track_unlink(handle, new.dentry);
 		__ext4_fc_track_link(handle, old.inode, new.dentry);
 		__ext4_fc_track_unlink(handle, old.inode, old.dentry);
+		if (whiteout)
+			__ext4_fc_track_create(handle, whiteout, old.dentry);
 	}
 
 	if (new.inode) {
···
 end_rename:
 	if (whiteout) {
 		if (retval) {
-			ext4_setent(handle, &old,
-				old.inode->i_ino, old_file_type);
+			ext4_resetent(handle, &old,
+				      old.inode->i_ino, old_file_type);
 			drop_nlink(whiteout);
+			ext4_orphan_add(handle, whiteout);
 		}
 		unlock_new_inode(whiteout);
+		ext4_journal_stop(handle);
 		iput(whiteout);
-
+	} else {
+		ext4_journal_stop(handle);
 	}
+release_bh:
 	brelse(old.dir_bh);
 	brelse(old.bh);
 	brelse(new.bh);
-	if (handle)
-		ext4_journal_stop(handle);
 	return retval;
 }
 

fs/ext4/super.c

···
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+	percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
 	percpu_free_rwsem(&sbi->s_writepages_rwsem);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < EXT4_MAXQUOTAS; i++)
···
 		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
 					  GFP_KERNEL);
 	if (!err)
+		err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0,
+					  GFP_KERNEL);
+	if (!err)
 		err = percpu_init_rwsem(&sbi->s_writepages_rwsem);
 
 	if (err) {
···
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+	percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
 	percpu_free_rwsem(&sbi->s_writepages_rwsem);
 failed_mount5:
 	ext4_ext_release(sb);
···
 failed_mount3a:
 	ext4_es_unregister_shrinker(sbi);
 failed_mount3:
-	del_timer_sync(&sbi->s_err_report);
 	flush_work(&sbi->s_error_work);
+	del_timer_sync(&sbi->s_err_report);
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
 failed_mount2:

fs/ext4/sysfs.c

···
 	attr_session_write_kbytes,
 	attr_lifetime_write_kbytes,
 	attr_reserved_clusters,
+	attr_sra_exceeded_retry_limit,
 	attr_inode_readahead,
 	attr_trigger_test_error,
 	attr_first_error_time,
···
 EXT4_ATTR_FUNC(session_write_kbytes, 0444);
 EXT4_ATTR_FUNC(lifetime_write_kbytes, 0444);
 EXT4_ATTR_FUNC(reserved_clusters, 0644);
+EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444);
 
 EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead,
 		 ext4_sb_info, s_inode_readahead_blks);
···
 	ATTR_LIST(session_write_kbytes),
 	ATTR_LIST(lifetime_write_kbytes),
 	ATTR_LIST(reserved_clusters),
+	ATTR_LIST(sra_exceeded_retry_limit),
 	ATTR_LIST(inode_readahead_blks),
 	ATTR_LIST(inode_goal),
 	ATTR_LIST(mb_stats),
···
 		return snprintf(buf, PAGE_SIZE, "%llu\n",
 				(unsigned long long)
 				atomic64_read(&sbi->s_resv_clusters));
+	case attr_sra_exceeded_retry_limit:
+		return snprintf(buf, PAGE_SIZE, "%llu\n",
+				(unsigned long long)
+			percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit));
 	case attr_inode_readahead:
 	case attr_pointer_ui:
 		if (!ptr)

fs/ext4/verity.c

···
 	struct inode *inode = file_inode(filp);
 	const int credits = 2; /* superblock and inode for ext4_orphan_del() */
 	handle_t *handle;
+	struct ext4_iloc iloc;
 	int err = 0;
-	int err2;
-
-	if (desc != NULL) {
-		/* Succeeded; write the verity descriptor. */
-		err = ext4_write_verity_descriptor(inode, desc, desc_size,
-						   merkle_tree_size);
-
-		/* Write all pages before clearing VERITY_IN_PROGRESS. */
-		if (!err)
-			err = filemap_write_and_wait(inode->i_mapping);
-	}
-
-	/* If we failed, truncate anything we wrote past i_size. */
-	if (desc == NULL || err)
-		ext4_truncate(inode);
 
 	/*
-	 * We must always clean up by clearing EXT4_STATE_VERITY_IN_PROGRESS and
-	 * deleting the inode from the orphan list, even if something failed.
-	 * If everything succeeded, we'll also set the verity bit in the same
-	 * transaction.
+	 * If an error already occurred (which fs/verity/ signals by passing
+	 * desc == NULL), then only clean-up is needed.
 	 */
+	if (desc == NULL)
+		goto cleanup;
 
-	ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+	/* Append the verity descriptor. */
+	err = ext4_write_verity_descriptor(inode, desc, desc_size,
+					   merkle_tree_size);
+	if (err)
+		goto cleanup;
+
+	/*
+	 * Write all pages (both data and verity metadata).  Note that this must
+	 * happen before clearing EXT4_STATE_VERITY_IN_PROGRESS; otherwise pages
+	 * beyond i_size won't be written properly.  For crash consistency, this
+	 * also must happen before the verity inode flag gets persisted.
+	 */
+	err = filemap_write_and_wait(inode->i_mapping);
+	if (err)
+		goto cleanup;
+
+	/*
+	 * Finally, set the verity inode flag and remove the inode from the
+	 * orphan list (in a single transaction).
+	 */
 
 	handle = ext4_journal_start(inode, EXT4_HT_INODE, credits);
 	if (IS_ERR(handle)) {
-		ext4_orphan_del(NULL, inode);
-		return PTR_ERR(handle);
+		err = PTR_ERR(handle);
+		goto cleanup;
 	}
 
-	err2 = ext4_orphan_del(handle, inode);
-	if (err2)
-		goto out_stop;
+	err = ext4_orphan_del(handle, inode);
+	if (err)
+		goto stop_and_cleanup;
 
-	if (desc != NULL && !err) {
-		struct ext4_iloc iloc;
+	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		goto stop_and_cleanup;
 
-		err = ext4_reserve_inode_write(handle, inode, &iloc);
-		if (err)
-			goto out_stop;
-		ext4_set_inode_flag(inode, EXT4_INODE_VERITY);
-		ext4_set_inode_flags(inode, false);
-		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-	}
-out_stop:
+	ext4_set_inode_flag(inode, EXT4_INODE_VERITY);
+	ext4_set_inode_flags(inode, false);
+	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+	if (err)
+		goto stop_and_cleanup;
+
 	ext4_journal_stop(handle);
-	return err ?: err2;
+
+	ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+	return 0;
+
+stop_and_cleanup:
+	ext4_journal_stop(handle);
+cleanup:
+	/*
+	 * Verity failed to be enabled, so clean up by truncating any verity
+	 * metadata that was written beyond i_size (both from cache and from
+	 * disk), removing the inode from the orphan list (if it wasn't done
+	 * already), and clearing EXT4_STATE_VERITY_IN_PROGRESS.
+	 */
+	truncate_inode_pages(inode->i_mapping, inode->i_size);
+	ext4_truncate(inode);
+	ext4_orphan_del(NULL, inode);
+	ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+	return err;
 }
 
 static int ext4_get_verity_descriptor_location(struct inode *inode,

fs/ext4/xattr.c

···
 	if (!ce)
 		return NULL;
 
+	WARN_ON_ONCE(ext4_handle_valid(journal_current_handle()) &&
+		     !(current->flags & PF_MEMALLOC_NOFS));
+
 	ea_data = kvmalloc(value_len, GFP_KERNEL);
 	if (!ea_data) {
 		mb_cache_entry_put(ea_inode_cache, ce);
···
 			error = -ENOSPC;
 			goto cleanup;
 		}
+		WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS));
 	}
 
 	error = ext4_reserve_inode_write(handle, inode, &is.iloc);
···
 				 * external inode if possible.
 				 */
 				if (ext4_has_feature_ea_inode(inode->i_sb) &&
-				    !i.in_inode) {
+				    i.value_len && !i.in_inode) {
 					i.in_inode = 1;
 					goto retry_inode;
 				}