Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "New features for ext4 this cycle include support for encrypted
  casefold, ensure that deleted file names are cleared in directory
  blocks by zeroing directory entries when they are unlinked or moved as
  part of a hash tree node split. We also improve the block allocator's
  performance on a freshly mounted file system by prefetching block
  bitmaps.

  There are also the usual cleanups and bug fixes, including fixing a
  page cache invalidation race when there is mixed buffered and direct
  I/O and the block size is less than page size, and allow the dax flag
  to be set and cleared on inline directories"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (32 commits)
  ext4: wipe ext4_dir_entry2 upon file deletion
  ext4: Fix occasional generic/418 failure
  fs: fix reporting supported extra file attributes for statx()
  ext4: allow the dax flag to be set and cleared on inline directories
  ext4: fix debug format string warning
  ext4: fix trailing whitespace
  ext4: fix various seppling typos
  ext4: fix error return code in ext4_fc_perform_commit()
  ext4: annotate data race in jbd2_journal_dirty_metadata()
  ext4: annotate data race in start_this_handle()
  ext4: fix ext4_error_err save negative errno into superblock
  ext4: fix error code in ext4_commit_super
  ext4: always panic when errors=panic is specified
  ext4: delete redundant uptodate check for buffer
  ext4: do not set SB_ACTIVE in ext4_orphan_cleanup()
  ext4: make prefetch_block_bitmaps default
  ext4: add proc files to monitor new structures
  ext4: improve cr 0 / cr 1 group scanning
  ext4: add MB_NUM_ORDERS macro
  ext4: add mballoc stats proc file
  ...

1 files changed, 73 insertions, 43 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3868377dec2d..7dc94f3e18e6 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -667,9 +667,6 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
 			ext4_commit_super(sb);
 	}
 
-	if (sb_rdonly(sb) || continue_fs)
-		return;
-
 	/*
 	 * We force ERRORS_RO behavior when system is rebooting. Otherwise we
 	 * could panic during 'reboot -f' as the underlying device got already
@@ -679,6 +676,10 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
 		panic("EXT4-fs (device %s): panic forced after error\n",
 			sb->s_id);
 	}
+
+	if (sb_rdonly(sb) || continue_fs)
+		return;
+
 	ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 	/*
 	 * Make sure updated value of ->s_mount_flags will be visible before
@@ -1688,7 +1689,7 @@ enum {
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
 	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
-	Opt_prefetch_block_bitmaps,
+	Opt_no_prefetch_block_bitmaps, Opt_mb_optimize_scan,
 #ifdef CONFIG_EXT4_DEBUG
 	Opt_fc_debug_max_replay, Opt_fc_debug_force
 #endif
@@ -1788,7 +1789,9 @@ static const match_table_t tokens = {
 	{Opt_inlinecrypt, "inlinecrypt"},
 	{Opt_nombcache, "nombcache"},
 	{Opt_nombcache, "no_mbcache"},	/* for backward compatibility */
-	{Opt_prefetch_block_bitmaps, "prefetch_block_bitmaps"},
+	{Opt_removed, "prefetch_block_bitmaps"},
+	{Opt_no_prefetch_block_bitmaps, "no_prefetch_block_bitmaps"},
+	{Opt_mb_optimize_scan, "mb_optimize_scan=%d"},
 	{Opt_removed, "check=none"},	/* mount option from ext2/3 */
 	{Opt_removed, "nocheck"},	/* mount option from ext2/3 */
 	{Opt_removed, "reservation"},	/* mount option from ext2/3 */
@@ -1821,6 +1824,8 @@ static ext4_fsblk_t get_sb_block(void **data)
 }
 
 #define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
+#define DEFAULT_MB_OPTIMIZE_SCAN	(-1)
+
 static const char deprecated_msg[] =
 	"Mount option \"%s\" will be removed by %s\n"
 	"Contact linux-ext4@vger.kernel.org if you think we should keep it.\n";
@@ -2007,8 +2012,9 @@ static const struct mount_opts {
 	{Opt_max_dir_size_kb, 0, MOPT_GTE0},
 	{Opt_test_dummy_encryption, 0, MOPT_STRING},
 	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
-	{Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
+	{Opt_no_prefetch_block_bitmaps, EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS,
 	 MOPT_SET},
+	{Opt_mb_optimize_scan, EXT4_MOUNT2_MB_OPTIMIZE_SCAN, MOPT_GTE0},
 #ifdef CONFIG_EXT4_DEBUG
 	{Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
 	 MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY},
@@ -2090,9 +2096,15 @@ static int ext4_set_test_dummy_encryption(struct super_block *sb,
 	return 1;
 }
 
+struct ext4_parsed_options {
+	unsigned long journal_devnum;
+	unsigned int journal_ioprio;
+	int mb_optimize_scan;
+};
+
 static int handle_mount_opt(struct super_block *sb, char *opt, int token,
-			    substring_t *args, unsigned long *journal_devnum,
-			    unsigned int *journal_ioprio, int is_remount)
+			    substring_t *args, struct ext4_parsed_options *parsed_opts,
+			    int is_remount)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	const struct mount_opts *m;
@@ -2249,7 +2261,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 				 "Cannot specify journal on remount");
 			return -1;
 		}
-		*journal_devnum = arg;
+		parsed_opts->journal_devnum = arg;
 	} else if (token == Opt_journal_path) {
 		char *journal_path;
 		struct inode *journal_inode;
@@ -2285,7 +2297,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			return -1;
 		}
 
-		*journal_devnum = new_encode_dev(journal_inode->i_rdev);
+		parsed_opts->journal_devnum = new_encode_dev(journal_inode->i_rdev);
 		path_put(&path);
 		kfree(journal_path);
 	} else if (token == Opt_journal_ioprio) {
@@ -2294,7 +2306,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 				 " (must be 0-7)");
 			return -1;
 		}
-		*journal_ioprio =
+		parsed_opts->journal_ioprio =
 			IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg);
 	} else if (token == Opt_test_dummy_encryption) {
 		return ext4_set_test_dummy_encryption(sb, opt, &args[0],
@@ -2384,6 +2396,13 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		sbi->s_mount_opt |= m->mount_opt;
 	} else if (token == Opt_data_err_ignore) {
 		sbi->s_mount_opt &= ~m->mount_opt;
+	} else if (token == Opt_mb_optimize_scan) {
+		if (arg != 0 && arg != 1) {
+			ext4_msg(sb, KERN_WARNING,
+				 "mb_optimize_scan should be set to 0 or 1.");
+			return -1;
+		}
+		parsed_opts->mb_optimize_scan = arg;
 	} else {
 		if (!args->from)
 			arg = 1;
@@ -2411,8 +2430,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 }
 
 static int parse_options(char *options, struct super_block *sb,
-			 unsigned long *journal_devnum,
-			 unsigned int *journal_ioprio,
+			 struct ext4_parsed_options *ret_opts,
 			 int is_remount)
 {
 	struct ext4_sb_info __maybe_unused *sbi = EXT4_SB(sb);
@@ -2432,8 +2450,8 @@ static int parse_options(char *options, struct super_block *sb,
 		 */
 		args[0].to = args[0].from = NULL;
 		token = match_token(p, tokens, args);
-		if (handle_mount_opt(sb, p, token, args, journal_devnum,
-				     journal_ioprio, is_remount) < 0)
+		if (handle_mount_opt(sb, p, token, args, ret_opts,
+				     is_remount) < 0)
 			return 0;
 	}
 #ifdef CONFIG_QUOTA
@@ -3023,9 +3041,6 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 		sb->s_flags &= ~SB_RDONLY;
 	}
 #ifdef CONFIG_QUOTA
-	/* Needed for iput() to work correctly and not trash data */
-	sb->s_flags |= SB_ACTIVE;
-
 	/*
 	 * Turn on quotas which were not enabled for read-only mounts if
 	 * filesystem has quota feature, so that they are updated correctly.
@@ -3691,11 +3706,11 @@ static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
 
 	elr->lr_super = sb;
 	elr->lr_first_not_zeroed = start;
-	if (test_opt(sb, PREFETCH_BLOCK_BITMAPS))
-		elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP;
-	else {
+	if (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS)) {
 		elr->lr_mode = EXT4_LI_MODE_ITABLE;
 		elr->lr_next_group = start;
+	} else {
+		elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP;
 	}
 
 	/*
@@ -3726,7 +3741,7 @@ int ext4_register_li_request(struct super_block *sb,
 		goto out;
 	}
 
-	if (!test_opt(sb, PREFETCH_BLOCK_BITMAPS) &&
+	if (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS) &&
 	    (first_not_zeroed == ngroups || sb_rdonly(sb) ||
 	     !test_opt(sb, INIT_INODE_TABLE)))
 		goto out;
@@ -4015,7 +4030,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	ext4_fsblk_t sb_block = get_sb_block(&data);
 	ext4_fsblk_t logical_sb_block;
 	unsigned long offset = 0;
-	unsigned long journal_devnum = 0;
 	unsigned long def_mount_opts;
 	struct inode *root;
 	const char *descr;
@@ -4026,8 +4040,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	int needs_recovery, has_huge_files;
 	__u64 blocks_count;
 	int err = 0;
-	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
 	ext4_group_t first_not_zeroed;
+	struct ext4_parsed_options parsed_opts;
+
+	/* Set defaults for the variables that will be set during parsing */
+	parsed_opts.journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+	parsed_opts.journal_devnum = 0;
+	parsed_opts.mb_optimize_scan = DEFAULT_MB_OPTIMIZE_SCAN;
 
 	if ((data && !orig_data) || !sbi)
 		goto out_free_base;
@@ -4273,8 +4292,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 					      GFP_KERNEL);
 		if (!s_mount_opts)
 			goto failed_mount;
-		if (!parse_options(s_mount_opts, sb, &journal_devnum,
-				   &journal_ioprio, 0)) {
+		if (!parse_options(s_mount_opts, sb, &parsed_opts, 0)) {
 			ext4_msg(sb, KERN_WARNING,
 				 "failed to parse options in superblock: %s",
 				 s_mount_opts);
@@ -4282,8 +4300,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		kfree(s_mount_opts);
 	}
 	sbi->s_def_mount_opt = sbi->s_mount_opt;
-	if (!parse_options((char *) data, sb, &journal_devnum,
-			   &journal_ioprio, 0))
+	if (!parse_options((char *) data, sb, &parsed_opts, 0))
 		goto failed_mount;
 
 #ifdef CONFIG_UNICODE
@@ -4292,12 +4309,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		struct unicode_map *encoding;
 		__u16 encoding_flags;
 
-		if (ext4_has_feature_encrypt(sb)) {
-			ext4_msg(sb, KERN_ERR,
-				 "Can't mount with encoding and encryption");
-			goto failed_mount;
-		}
-
 		if (ext4_sb_read_encoding(es, &encoding_info,
 					  &encoding_flags)) {
 			ext4_msg(sb, KERN_ERR,
@@ -4774,7 +4785,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 * root first: it may be modified in the journal!
 	 */
 	if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) {
-		err = ext4_load_journal(sb, es, journal_devnum);
+		err = ext4_load_journal(sb, es, parsed_opts.journal_devnum);
 		if (err)
 			goto failed_mount3a;
 	} else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) &&
@@ -4874,7 +4885,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount_wq;
 	}
 
-	set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+	set_task_ioprio(sbi->s_journal->j_task, parsed_opts.journal_ioprio);
 
 	sbi->s_journal->j_submit_inode_data_buffers =
 		ext4_journal_submit_inode_data_buffers;
@@ -4980,6 +4991,19 @@ no_journal:
 	ext4_fc_replay_cleanup(sb);
 
 	ext4_ext_init(sb);
+
+	/*
+	 * Enable optimize_scan if number of groups is > threshold. This can be
+	 * turned off by passing "mb_optimize_scan=0". This can also be
+	 * turned on forcefully by passing "mb_optimize_scan=1".
+	 */
+	if (parsed_opts.mb_optimize_scan == 1)
+		set_opt2(sb, MB_OPTIMIZE_SCAN);
+	else if (parsed_opts.mb_optimize_scan == 0)
+		clear_opt2(sb, MB_OPTIMIZE_SCAN);
+	else if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD)
+		set_opt2(sb, MB_OPTIMIZE_SCAN);
+
 	err = ext4_mb_init(sb);
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
@@ -4996,7 +5020,7 @@ no_journal:
 			ext4_journal_commit_callback;
 
 	block = ext4_count_free_clusters(sb);
-	ext4_free_blocks_count_set(sbi->s_es, 
+	ext4_free_blocks_count_set(sbi->s_es,
 				   EXT4_C2B(sbi, block));
 	err = percpu_counter_init(&sbi->s_freeclusters_counter, block,
 				  GFP_KERNEL);
@@ -5561,8 +5585,10 @@ static int ext4_commit_super(struct super_block *sb)
 	struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
 	int error = 0;
 
-	if (!sbh || block_device_ejected(sb))
-		return error;
+	if (!sbh)
+		return -EINVAL;
+	if (block_device_ejected(sb))
+		return -ENODEV;
 
 	ext4_update_super(sb);
 
@@ -5813,13 +5839,16 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	struct ext4_mount_options old_opts;
 	int enable_quota = 0;
 	ext4_group_t g;
-	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
 	int err = 0;
 #ifdef CONFIG_QUOTA
 	int i, j;
 	char *to_free[EXT4_MAXQUOTAS];
 #endif
 	char *orig_data = kstrdup(data, GFP_KERNEL);
+	struct ext4_parsed_options parsed_opts;
+
+	parsed_opts.journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+	parsed_opts.journal_devnum = 0;
 
 	if (data && !orig_data)
 		return -ENOMEM;
@@ -5850,7 +5879,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			old_opts.s_qf_names[i] = NULL;
 #endif
 	if (sbi->s_journal && sbi->s_journal->j_task->io_context)
-		journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
+		parsed_opts.journal_ioprio =
+			sbi->s_journal->j_task->io_context->ioprio;
 
 	/*
 	 * Some options can be enabled by ext4 and/or by VFS mount flag
@@ -5860,7 +5890,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	vfs_flags = SB_LAZYTIME | SB_I_VERSION;
 	sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags);
 
-	if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) {
+	if (!parse_options(data, sb, &parsed_opts, 1)) {
 		err = -EINVAL;
 		goto restore_opts;
 	}
@@ -5910,7 +5940,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 
 	if (sbi->s_journal) {
 		ext4_init_journal_params(sb, sbi->s_journal);
-		set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+		set_task_ioprio(sbi->s_journal->j_task, parsed_opts.journal_ioprio);
 	}
 
 	/* Flush outstanding errors before changing fs state */