1 files changed, 356 insertions, 181 deletions

diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 7ff14a1adba3..b20a1bf866ab 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -82,19 +82,24 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 				      struct buffer_head *bh)
 {
 	ext4_fsblk_t	blk;
-	struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
+	struct ext4_group_info *grp;
+
+	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
 
 	if (buffer_verified(bh))
 		return 0;
-	if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
+
+	grp = ext4_get_group_info(sb, block_group);
+	if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
 		return -EFSCORRUPTED;
 
 	ext4_lock_group(sb, block_group);
 	if (buffer_verified(bh))
 		goto verified;
 	blk = ext4_inode_bitmap(sb, desc);
-	if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh,
-					   EXT4_INODES_PER_GROUP(sb) / 8)) {
+	if (!ext4_inode_bitmap_csum_verify(sb, desc, bh) ||
+	    ext4_simulate_fail(sb, EXT4_SIM_IBITMAP_CRC)) {
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
 			   "inode_bitmap = %llu", block_group, blk);
@@ -112,7 +117,7 @@ verified:
  * Read the inode allocation bitmap for a given block_group, reading
  * into the specified slot in the superblock's bitmap cache.
  *
- * Return buffer_head of bitmap on success or NULL.
+ * Return buffer_head of bitmap on success, or an ERR_PTR on error.
  */
 static struct buffer_head *
 ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
@@ -188,15 +193,14 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	 * submit the buffer_head for reading
 	 */
 	trace_ext4_load_inode_bitmap(sb, block_group);
-	bh->b_end_io = ext4_end_bitmap_read;
-	get_bh(bh);
-	submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
-	wait_on_buffer(bh);
+	ext4_read_bh(bh, REQ_META | REQ_PRIO,
+		     ext4_end_bitmap_read,
+		     ext4_simulate_fail(sb, EXT4_SIM_IBITMAP_EIO));
 	if (!buffer_uptodate(bh)) {
 		put_bh(bh);
-		ext4_error(sb, "Cannot read inode bitmap - "
-			   "block_group = %u, inode_bitmap = %llu",
-			   block_group, bitmap_blk);
+		ext4_error_err(sb, EIO, "Cannot read inode bitmap - "
+			       "block_group = %u, inode_bitmap = %llu",
+			       block_group, bitmap_blk);
 		ext4_mark_group_bitmap_corrupted(sb, block_group,
 				EXT4_GROUP_INFO_IBITMAP_CORRUPT);
 		return ERR_PTR(-EIO);
@@ -248,10 +252,10 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 		       "nonexistent device\n", __func__, __LINE__);
 		return;
 	}
-	if (atomic_read(&inode->i_count) > 1) {
+	if (icount_read(inode) > 1) {
 		ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: count=%d",
 			 __func__, __LINE__, inode->i_ino,
-			 atomic_read(&inode->i_count));
+			 icount_read(inode));
 		return;
 	}
 	if (inode->i_nlink) {
@@ -265,13 +269,8 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	ext4_debug("freeing inode %lu\n", ino);
 	trace_ext4_free_inode(inode);
 
-	/*
-	 * Note: we must free any quota before locking the superblock,
-	 * as writing the quota to disk may need the lock as well.
-	 */
 	dquot_initialize(inode);
 	dquot_free_inode(inode);
-	dquot_drop(inode);
 
 	is_directory = S_ISDIR(inode->i_mode);
 
@@ -287,19 +286,22 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
 	bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
 	/* Don't bother if the inode bitmap is corrupt. */
-	grp = ext4_get_group_info(sb, block_group);
 	if (IS_ERR(bitmap_bh)) {
 		fatal = PTR_ERR(bitmap_bh);
 		bitmap_bh = NULL;
 		goto error_return;
 	}
-	if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) {
-		fatal = -EFSCORRUPTED;
-		goto error_return;
+	if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
+		grp = ext4_get_group_info(sb, block_group);
+		if (!grp || unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) {
+			fatal = -EFSCORRUPTED;
+			goto error_return;
+		}
 	}
 
 	BUFFER_TRACE(bitmap_bh, "get_write_access");
-	fatal = ext4_journal_get_write_access(handle, bitmap_bh);
+	fatal = ext4_journal_get_write_access(handle, sb, bitmap_bh,
+					      EXT4_JTR_NONE);
 	if (fatal)
 		goto error_return;
 
@@ -307,7 +309,8 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	gdp = ext4_get_group_desc(sb, block_group, &bh2);
 	if (gdp) {
 		BUFFER_TRACE(bh2, "get_write_access");
-		fatal = ext4_journal_get_write_access(handle, bh2);
+		fatal = ext4_journal_get_write_access(handle, sb, bh2,
+						      EXT4_JTR_NONE);
 	}
 	ext4_lock_group(sb, block_group);
 	cleared = ext4_test_and_clear_bit(bit, bitmap_bh->b_data);
@@ -321,20 +324,23 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	if (is_directory) {
 		count = ext4_used_dirs_count(sb, gdp) - 1;
 		ext4_used_dirs_set(sb, gdp, count);
-		percpu_counter_dec(&sbi->s_dirs_counter);
+		if (percpu_counter_initialized(&sbi->s_dirs_counter))
+			percpu_counter_dec(&sbi->s_dirs_counter);
 	}
-	ext4_inode_bitmap_csum_set(sb, block_group, gdp, bitmap_bh,
-				   EXT4_INODES_PER_GROUP(sb) / 8);
+	ext4_inode_bitmap_csum_set(sb, gdp, bitmap_bh);
 	ext4_group_desc_csum_set(sb, block_group, gdp);
 	ext4_unlock_group(sb, block_group);
 
-	percpu_counter_inc(&sbi->s_freeinodes_counter);
+	if (percpu_counter_initialized(&sbi->s_freeinodes_counter))
+		percpu_counter_inc(&sbi->s_freeinodes_counter);
 	if (sbi->s_log_groups_per_flex) {
-		ext4_group_t f = ext4_flex_group(sbi, block_group);
+		struct flex_groups *fg;
 
-		atomic_inc(&sbi->s_flex_groups[f].free_inodes);
+		fg = sbi_array_rcu_deref(sbi, s_flex_groups,
+					 ext4_flex_group(sbi, block_group));
+		atomic_inc(&fg->free_inodes);
 		if (is_directory)
-			atomic_dec(&sbi->s_flex_groups[f].used_dirs);
+			atomic_dec(&fg->used_dirs);
 	}
 	BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
 	fatal = ext4_handle_dirty_metadata(handle, NULL, bh2);
@@ -370,12 +376,13 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
 			    int flex_size, struct orlov_stats *stats)
 {
 	struct ext4_group_desc *desc;
-	struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups;
 
 	if (flex_size > 1) {
-		stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
-		stats->free_clusters = atomic64_read(&flex_group[g].free_clusters);
-		stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
+		struct flex_groups *fg = sbi_array_rcu_deref(EXT4_SB(sb),
+							     s_flex_groups, g);
+		stats->free_inodes = atomic_read(&fg->free_inodes);
+		stats->free_clusters = atomic64_read(&fg->free_clusters);
+		stats->used_dirs = atomic_read(&fg->used_dirs);
 		return;
 	}
 
@@ -396,7 +403,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
  *
  * We always try to spread first-level directories.
  *
- * If there are blockgroups with both free inodes and free blocks counts
+ * If there are blockgroups with both free inodes and free clusters counts
  * not worse than average we return one with smallest directory count.
  * Otherwise we simply return a random group.
  *
@@ -405,7 +412,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
  * It's OK to put directory into a group unless
  * it has too many directories already (max_dirs) or
  * it has too few free inodes left (min_inodes) or
- * it has too few free blocks left (min_blocks) or
+ * it has too few free clusters left (min_clusters) or
  * Parent's group is preferred, if it doesn't satisfy these
  * conditions we search cyclically through the rest. If none
  * of the groups look good we just look for a group with more
@@ -421,7 +428,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 	ext4_group_t real_ngroups = ext4_get_groups_count(sb);
 	int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
 	unsigned int freei, avefreei, grp_free;
-	ext4_fsblk_t freeb, avefreec;
+	ext4_fsblk_t freec, avefreec;
 	unsigned int ndirs;
 	int max_dirs, min_inodes;
 	ext4_grpblk_t min_clusters;
@@ -440,9 +447,8 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 
 	freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
 	avefreei = freei / ngroups;
-	freeb = EXT4_C2B(sbi,
-		percpu_counter_read_positive(&sbi->s_freeclusters_counter));
-	avefreec = freeb;
+	freec = percpu_counter_read_positive(&sbi->s_freeclusters_counter);
+	avefreec = freec;
 	do_div(avefreec, ngroups);
 	ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
 
@@ -455,11 +461,10 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 		if (qstr) {
 			hinfo.hash_version = DX_HASH_HALF_MD4;
 			hinfo.seed = sbi->s_hash_seed;
-			ext4fs_dirhash(qstr->name, qstr->len, &hinfo);
-			grp = hinfo.hash;
+			ext4fs_dirhash(parent, qstr->name, qstr->len, &hinfo);
+			parent_group = hinfo.hash % ngroups;
 		} else
-			grp = prandom_u32();
-		parent_group = (unsigned)grp % ngroups;
+			parent_group = get_random_u32_below(ngroups);
 		for (i = 0; i < ngroups; i++) {
 			g = (parent_group + i) % ngroups;
 			get_orlov_stats(sb, g, flex_size, &stats);
@@ -503,11 +508,13 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 		goto fallback;
 	}
 
-	max_dirs = ndirs / ngroups + inodes_per_group / 16;
+	max_dirs = ndirs / ngroups + inodes_per_group*flex_size / 16;
 	min_inodes = avefreei - inodes_per_group*flex_size / 4;
 	if (min_inodes < 1)
 		min_inodes = 1;
 	min_clusters = avefreec - EXT4_CLUSTERS_PER_GROUP(sb)*flex_size / 4;
+	if (min_clusters < 0)
+		min_clusters = 0;
 
 	/*
 	 * Start looking in the flex group where we last allocated an
@@ -662,7 +669,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
  * block has been written back to disk.  (Yes, these values are
  * somewhat arbitrary...)
  */
-#define RECENTCY_MIN	5
+#define RECENTCY_MIN	60
 #define RECENTCY_DIRTY	300
 
 static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)
@@ -684,7 +691,8 @@ static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)
 	if (!bh || !buffer_uptodate(bh))
 		/*
 		 * If the block is not in the buffer cache, then it
-		 * must have been written out.
+		 * must have been written out, or, most unlikely, is
+		 * being migrated - false failure should be OK here.
 		 */
 		goto out;
 
@@ -711,22 +719,197 @@ out:
 static int find_inode_bit(struct super_block *sb, ext4_group_t group,
 			  struct buffer_head *bitmap, unsigned long *ino)
 {
+	bool check_recently_deleted = EXT4_SB(sb)->s_journal == NULL;
+	unsigned long recently_deleted_ino = EXT4_INODES_PER_GROUP(sb);
+
 next:
 	*ino = ext4_find_next_zero_bit((unsigned long *)
 				       bitmap->b_data,
 				       EXT4_INODES_PER_GROUP(sb), *ino);
 	if (*ino >= EXT4_INODES_PER_GROUP(sb))
-		return 0;
+		goto not_found;
 
-	if ((EXT4_SB(sb)->s_journal == NULL) &&
-	    recently_deleted(sb, group, *ino)) {
+	if (check_recently_deleted && recently_deleted(sb, group, *ino)) {
+		recently_deleted_ino = *ino;
 		*ino = *ino + 1;
 		if (*ino < EXT4_INODES_PER_GROUP(sb))
 			goto next;
+		goto not_found;
+	}
+	return 1;
+not_found:
+	if (recently_deleted_ino >= EXT4_INODES_PER_GROUP(sb))
 		return 0;
+	/*
+	 * Not reusing recently deleted inodes is mostly a preference. We don't
+	 * want to report ENOSPC or skew allocation patterns because of that.
+	 * So return even recently deleted inode if we could find better in the
+	 * given range.
+	 */
+	*ino = recently_deleted_ino;
+	return 1;
+}
+
+int ext4_mark_inode_used(struct super_block *sb, int ino)
+{
+	unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
+	struct buffer_head *inode_bitmap_bh = NULL, *group_desc_bh = NULL;
+	struct ext4_group_desc *gdp;
+	ext4_group_t group;
+	int bit;
+	int err;
+
+	if (ino < EXT4_FIRST_INO(sb) || ino > max_ino)
+		return -EFSCORRUPTED;
+
+	group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
+	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
+	inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
+	if (IS_ERR(inode_bitmap_bh))
+		return PTR_ERR(inode_bitmap_bh);
+
+	if (ext4_test_bit(bit, inode_bitmap_bh->b_data)) {
+		err = 0;
+		goto out;
 	}
 
-	return 1;
+	gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
+	if (!gdp) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	ext4_set_bit(bit, inode_bitmap_bh->b_data);
+
+	BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
+	err = ext4_handle_dirty_metadata(NULL, NULL, inode_bitmap_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+	err = sync_dirty_buffer(inode_bitmap_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+
+	/* We may have to initialize the block bitmap if it isn't already */
+	if (ext4_has_group_desc_csum(sb) &&
+	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+		struct buffer_head *block_bitmap_bh;
+
+		block_bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (IS_ERR(block_bitmap_bh)) {
+			err = PTR_ERR(block_bitmap_bh);
+			goto out;
+		}
+
+		BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
+		err = ext4_handle_dirty_metadata(NULL, NULL, block_bitmap_bh);
+		sync_dirty_buffer(block_bitmap_bh);
+
+		/* recheck and clear flag under lock if we still need to */
+		ext4_lock_group(sb, group);
+		if (ext4_has_group_desc_csum(sb) &&
+		    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+			ext4_free_group_clusters_set(sb, gdp,
+				ext4_free_clusters_after_init(sb, group, gdp));
+			ext4_block_bitmap_csum_set(sb, gdp, block_bitmap_bh);
+			ext4_group_desc_csum_set(sb, group, gdp);
+		}
+		ext4_unlock_group(sb, group);
+		brelse(block_bitmap_bh);
+
+		if (err) {
+			ext4_std_error(sb, err);
+			goto out;
+		}
+	}
+
+	/* Update the relevant bg descriptor fields */
+	if (ext4_has_group_desc_csum(sb)) {
+		int free;
+
+		ext4_lock_group(sb, group); /* while we modify the bg desc */
+		free = EXT4_INODES_PER_GROUP(sb) -
+			ext4_itable_unused_count(sb, gdp);
+		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
+			free = 0;
+		}
+
+		/*
+		 * Check the relative inode number against the last used
+		 * relative inode number in this group. if it is greater
+		 * we need to update the bg_itable_unused count
+		 */
+		if (bit >= free)
+			ext4_itable_unused_set(sb, gdp,
+					(EXT4_INODES_PER_GROUP(sb) - bit - 1));
+	} else {
+		ext4_lock_group(sb, group);
+	}
+
+	ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1);
+	if (ext4_has_group_desc_csum(sb)) {
+		ext4_inode_bitmap_csum_set(sb, gdp, inode_bitmap_bh);
+		ext4_group_desc_csum_set(sb, group, gdp);
+	}
+
+	ext4_unlock_group(sb, group);
+	err = ext4_handle_dirty_metadata(NULL, NULL, group_desc_bh);
+	sync_dirty_buffer(group_desc_bh);
+out:
+	brelse(inode_bitmap_bh);
+	return err;
+}
+
+static int ext4_xattr_credits_for_new_inode(struct inode *dir, mode_t mode,
+					    bool encrypt)
+{
+	struct super_block *sb = dir->i_sb;
+	int nblocks = 0;
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+	struct posix_acl *p = get_inode_acl(dir, ACL_TYPE_DEFAULT);
+
+	if (IS_ERR(p))
+		return PTR_ERR(p);
+	if (p) {
+		int acl_size = p->a_count * sizeof(ext4_acl_entry);
+
+		nblocks += (S_ISDIR(mode) ? 2 : 1) *
+			__ext4_xattr_set_credits(sb, NULL /* inode */,
+						 NULL /* block_bh */, acl_size,
+						 true /* is_create */);
+		posix_acl_release(p);
+	}
+#endif
+
+#ifdef CONFIG_SECURITY
+	{
+		int num_security_xattrs = 1;
+
+#ifdef CONFIG_INTEGRITY
+		num_security_xattrs++;
+#endif
+		/*
+		 * We assume that security xattrs are never more than 1k.
+		 * In practice they are under 128 bytes.
+		 */
+		nblocks += num_security_xattrs *
+			__ext4_xattr_set_credits(sb, NULL /* inode */,
+						 NULL /* block_bh */, 1024,
+						 true /* is_create */);
+	}
+#endif
+	if (encrypt)
+		nblocks += __ext4_xattr_set_credits(sb,
+						    NULL /* inode */,
+						    NULL /* block_bh */,
+						    FSCRYPT_SET_CONTEXT_MAX_SIZE,
+						    true /* is_create */);
+	return nblocks;
 }
 
 /*
@@ -739,7 +922,8 @@ next:
  * For other inodes, search forward from the parent directory's block
  * group to find a free inode.
  */
-struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
+struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
+			       handle_t *handle, struct inode *dir,
 			       umode_t mode, const struct qstr *qstr,
 			       __u32 goal, uid_t *owner, __u32 i_flags,
 			       int handle_type, unsigned int line_no,
@@ -758,8 +942,8 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	struct inode *ret;
 	ext4_group_t i;
 	ext4_group_t flex_group;
-	struct ext4_group_info *grp;
-	int encrypt = 0;
+	struct ext4_group_info *grp = NULL;
+	bool encrypt = false;
 
 	/* Cannot create files in a deleted directory */
 	if (!dir || !dir->i_nlink)
@@ -768,61 +952,9 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	sb = dir->i_sb;
 	sbi = EXT4_SB(sb);
 
-	if (unlikely(ext4_forced_shutdown(sbi)))
-		return ERR_PTR(-EIO);
-
-	if ((ext4_encrypted_inode(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) &&
-	    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) &&
-	    !(i_flags & EXT4_EA_INODE_FL)) {
-		err = fscrypt_get_encryption_info(dir);
-		if (err)
-			return ERR_PTR(err);
-		if (!fscrypt_has_encryption_key(dir))
-			return ERR_PTR(-ENOKEY);
-		encrypt = 1;
-	}
-
-	if (!handle && sbi->s_journal && !(i_flags & EXT4_EA_INODE_FL)) {
-#ifdef CONFIG_EXT4_FS_POSIX_ACL
-		struct posix_acl *p = get_acl(dir, ACL_TYPE_DEFAULT);
-
-		if (IS_ERR(p))
-			return ERR_CAST(p);
-		if (p) {
-			int acl_size = p->a_count * sizeof(ext4_acl_entry);
-
-			nblocks += (S_ISDIR(mode) ? 2 : 1) *
-				__ext4_xattr_set_credits(sb, NULL /* inode */,
-					NULL /* block_bh */, acl_size,
-					true /* is_create */);
-			posix_acl_release(p);
-		}
-#endif
-
-#ifdef CONFIG_SECURITY
-		{
-			int num_security_xattrs = 1;
-
-#ifdef CONFIG_INTEGRITY
-			num_security_xattrs++;
-#endif
-			/*
-			 * We assume that security xattrs are never
-			 * more than 1k.  In practice they are under
-			 * 128 bytes.
-			 */
-			nblocks += num_security_xattrs *
-				__ext4_xattr_set_credits(sb, NULL /* inode */,
-					NULL /* block_bh */, 1024,
-					true /* is_create */);
-		}
-#endif
-		if (encrypt)
-			nblocks += __ext4_xattr_set_credits(sb,
-					NULL /* inode */, NULL /* block_bh */,
-					FSCRYPT_SET_CONTEXT_MAX_SIZE,
-					true /* is_create */);
-	}
+	ret2 = ext4_emergency_state(sb);
+	if (unlikely(ret2))
+		return ERR_PTR(ret2);
 
 	ngroups = ext4_get_groups_count(sb);
 	trace_ext4_request_inode(dir, mode);
@@ -842,10 +974,10 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 		i_gid_write(inode, owner[1]);
 	} else if (test_opt(sb, GRPID)) {
 		inode->i_mode = mode;
-		inode->i_uid = current_fsuid();
+		inode_fsuid_set(inode, idmap);
 		inode->i_gid = dir->i_gid;
 	} else
-		inode_init_owner(inode, dir, mode);
+		inode_init_owner(idmap, inode, dir, mode);
 
 	if (ext4_has_feature_project(sb) &&
 	    ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT))
@@ -853,10 +985,25 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	else
 		ei->i_projid = make_kprojid(&init_user_ns, EXT4_DEF_PROJID);
 
+	if (!(i_flags & EXT4_EA_INODE_FL)) {
+		err = fscrypt_prepare_new_inode(dir, inode, &encrypt);
+		if (err)
+			goto out;
+	}
+
 	err = dquot_initialize(inode);
 	if (err)
 		goto out;
 
+	if (!handle && sbi->s_journal && !(i_flags & EXT4_EA_INODE_FL)) {
+		ret2 = ext4_xattr_credits_for_new_inode(dir, mode, encrypt);
+		if (ret2 < 0) {
+			err = ret2;
+			goto out;
+		}
+		nblocks += ret2;
+	}
+
 	if (!goal)
 		goal = sbi->s_inode_goal;
 
@@ -896,21 +1043,27 @@ got_group:
 		if (ext4_free_inodes_count(sb, gdp) == 0)
 			goto next_group;
 
-		grp = ext4_get_group_info(sb, group);
-		/* Skip groups with already-known suspicious inode tables */
-		if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
-			goto next_group;
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
+			grp = ext4_get_group_info(sb, group);
+			/*
+			 * Skip groups with already-known suspicious inode
+			 * tables
+			 */
+			if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
+				goto next_group;
+		}
 
 		brelse(inode_bitmap_bh);
 		inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
 		/* Skip groups with suspicious inode tables */
-		if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp) ||
-		    IS_ERR(inode_bitmap_bh)) {
+		if (IS_ERR(inode_bitmap_bh)) {
 			inode_bitmap_bh = NULL;
 			goto next_group;
 		}
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY) &&
+		    EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
+			goto next_group;
 
-repeat_in_this_group:
 		ret2 = find_inode_bit(sb, group, inode_bitmap_bh, &ino);
 		if (!ret2)
 			goto next_group;
@@ -923,11 +1076,11 @@ repeat_in_this_group:
 			goto next_group;
 		}
 
-		if (!handle) {
+		if ((!(sbi->s_mount_state & EXT4_FC_REPLAY)) && !handle) {
 			BUG_ON(nblocks <= 0);
-			handle = __ext4_journal_start_sb(dir->i_sb, line_no,
-							 handle_type, nblocks,
-							 0);
+			handle = __ext4_journal_start_sb(NULL, dir->i_sb,
+				 line_no, handle_type, nblocks, 0,
+				 ext4_trans_default_revoke_credits(sb));
 			if (IS_ERR(handle)) {
 				err = PTR_ERR(handle);
 				ext4_std_error(sb, err);
@@ -935,7 +1088,8 @@ repeat_in_this_group:
 			}
 		}
 		BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
-		err = ext4_journal_get_write_access(handle, inode_bitmap_bh);
+		err = ext4_journal_get_write_access(handle, sb, inode_bitmap_bh,
+						    EXT4_JTR_NONE);
 		if (err) {
 			ext4_std_error(sb, err);
 			goto out;
@@ -959,8 +1113,6 @@ repeat_in_this_group:
 		if (!ret2)
 			goto got; /* we grabbed the inode! */
 
-		if (ino < EXT4_INODES_PER_GROUP(sb))
-			goto repeat_in_this_group;
 next_group:
 		if (++group == ngroups)
 			group = 0;
@@ -977,7 +1129,8 @@ got:
 	}
 
 	BUFFER_TRACE(group_desc_bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, group_desc_bh);
+	err = ext4_journal_get_write_access(handle, sb, group_desc_bh,
+					    EXT4_JTR_NONE);
 	if (err) {
 		ext4_std_error(sb, err);
 		goto out;
@@ -994,7 +1147,8 @@ got:
 			goto out;
 		}
 		BUFFER_TRACE(block_bitmap_bh, "get block bitmap access");
-		err = ext4_journal_get_write_access(handle, block_bitmap_bh);
+		err = ext4_journal_get_write_access(handle, sb, block_bitmap_bh,
+						    EXT4_JTR_NONE);
 		if (err) {
 			brelse(block_bitmap_bh);
 			ext4_std_error(sb, err);
@@ -1011,8 +1165,7 @@ got:
 			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
 			ext4_free_group_clusters_set(sb, gdp,
 				ext4_free_clusters_after_init(sb, group, gdp));
-			ext4_block_bitmap_csum_set(sb, group, gdp,
-						   block_bitmap_bh);
+			ext4_block_bitmap_csum_set(sb, gdp, block_bitmap_bh);
 			ext4_group_desc_csum_set(sb, group, gdp);
 		}
 		ext4_unlock_group(sb, group);
@@ -1027,9 +1180,19 @@ got:
 	/* Update the relevant bg descriptor fields */
 	if (ext4_has_group_desc_csum(sb)) {
 		int free;
-		struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+		struct ext4_group_info *grp = NULL;
 
-		down_read(&grp->alloc_sem); /* protect vs itable lazyinit */
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
+			grp = ext4_get_group_info(sb, group);
+			if (!grp) {
+				err = -EFSCORRUPTED;
+				goto out;
+			}
+			down_read(&grp->alloc_sem); /*
+						     * protect vs itable
+						     * lazyinit
+						     */
+		}
 		ext4_lock_group(sb, group); /* while we modify the bg desc */
 		free = EXT4_INODES_PER_GROUP(sb) -
 			ext4_itable_unused_count(sb, gdp);
@@ -1045,7 +1208,8 @@ got:
 		if (ino > free)
 			ext4_itable_unused_set(sb, gdp,
 					(EXT4_INODES_PER_GROUP(sb) - ino));
-		up_read(&grp->alloc_sem);
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY))
+			up_read(&grp->alloc_sem);
 	} else {
 		ext4_lock_group(sb, group);
 	}
@@ -1056,12 +1220,12 @@ got:
 		if (sbi->s_log_groups_per_flex) {
 			ext4_group_t f = ext4_flex_group(sbi, group);
 
-			atomic_inc(&sbi->s_flex_groups[f].used_dirs);
+			atomic_inc(&sbi_array_rcu_deref(sbi, s_flex_groups,
+							f)->used_dirs);
 		}
 	}
 	if (ext4_has_group_desc_csum(sb)) {
-		ext4_inode_bitmap_csum_set(sb, group, gdp, inode_bitmap_bh,
-					   EXT4_INODES_PER_GROUP(sb) / 8);
+		ext4_inode_bitmap_csum_set(sb, gdp, inode_bitmap_bh);
 		ext4_group_desc_csum_set(sb, group, gdp);
 	}
 	ext4_unlock_group(sb, group);
@@ -1079,14 +1243,15 @@ got:
 
 	if (sbi->s_log_groups_per_flex) {
 		flex_group = ext4_flex_group(sbi, group);
-		atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
+		atomic_dec(&sbi_array_rcu_deref(sbi, s_flex_groups,
+						flex_group)->free_inodes);
 	}
 
 	inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);
 	/* This is the optimal IO size (for stat), not the fs block size */
 	inode->i_blocks = 0;
-	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
-	ei->i_crtime = inode->i_mtime;
+	simple_inode_init_ts(inode);
+	ei->i_crtime = inode_get_mtime(inode);
 
 	memset(ei->i_data, 0, sizeof(ei->i_data));
 	ei->i_dir_start_lookup = 0;
@@ -1101,7 +1266,7 @@ got:
 	ei->i_block_group = group;
 	ei->i_last_alloc_group = ~0;
 
-	ext4_set_inode_flags(inode);
+	ext4_set_inode_flags(inode, true);
 	if (IS_DIRSYNC(inode))
 		ext4_handle_sync(handle);
 	if (insert_inode_locked(inode) < 0) {
@@ -1116,25 +1281,24 @@ got:
 					EXT4_GROUP_INFO_IBITMAP_CORRUPT);
 		goto out;
 	}
-	inode->i_generation = prandom_u32();
+	inode->i_generation = get_random_u32();
 
 	/* Precompute checksum seed for inode metadata */
-	if (ext4_has_metadata_csum(sb)) {
+	if (ext4_has_feature_metadata_csum(sb)) {
 		__u32 csum;
 		__le32 inum = cpu_to_le32(inode->i_ino);
 		__le32 gen = cpu_to_le32(inode->i_generation);
-		csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum,
+		csum = ext4_chksum(sbi->s_csum_seed, (__u8 *)&inum,
 				   sizeof(inum));
-		ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen,
-					      sizeof(gen));
+		ei->i_csum_seed = ext4_chksum(csum, (__u8 *)&gen, sizeof(gen));
 	}
 
-	ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
 	ext4_set_inode_state(inode, EXT4_STATE_NEW);
 
 	ei->i_extra_isize = sbi->s_want_extra_isize;
 	ei->i_inline_off = 0;
-	if (ext4_has_feature_inline_data(sb))
+	if (ext4_has_feature_inline_data(sb) &&
+	    (!(ei->i_flags & (EXT4_DAX_FL|EXT4_EA_INODE_FL)) || S_ISDIR(mode)))
 		ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
 	ret = inode;
 	err = dquot_alloc_inode(inode);
@@ -1147,7 +1311,7 @@ got:
 	 * prevent its deduplication.
 	 */
 	if (encrypt) {
-		err = fscrypt_inherit_context(dir, inode, handle, true);
+		err = fscrypt_set_context(inode, handle);
 		if (err)
 			goto fail_free_drop;
 	}
@@ -1170,10 +1334,9 @@ got:
 		}
 	}
 
-	if (ext4_handle_valid(handle)) {
-		ei->i_sync_tid = handle->h_transaction->t_tid;
-		ei->i_datasync_tid = handle->h_transaction->t_tid;
-	}
+	ext4_set_inode_mapping_order(inode);
+
+	ext4_update_inode_fsync_trans(handle, inode, 1);
 
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err) {
@@ -1228,8 +1391,10 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 	inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
-		ext4_error(sb, "couldn't read orphan inode %lu (err %d)",
-			   ino, err);
+		ext4_error_err(sb, -err,
+			       "couldn't read orphan inode %lu (err %d)",
+			       ino, err);
+		brelse(bitmap_bh);
 		return inode;
 	}
 
@@ -1353,15 +1518,10 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
 	handle_t *handle;
 	ext4_fsblk_t blk;
 	int num, ret = 0, used_blks = 0;
-
-	/* This should not happen, but just to be sure check this */
-	if (sb_rdonly(sb)) {
-		ret = 1;
-		goto out;
-	}
+	unsigned long used_inos = 0;
 
 	gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
-	if (!gdp)
+	if (!gdp || !grp)
 		goto out;
 
 	/*
@@ -1383,30 +1543,45 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
 	 * used inodes so we need to skip blocks with used inodes in
 	 * inode table.
 	 */
-	if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
-		used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) -
-			    ext4_itable_unused_count(sb, gdp)),
-			    sbi->s_inodes_per_block);
-
-	if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) ||
-	    ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) -
-			       ext4_itable_unused_count(sb, gdp)) <
-			      EXT4_FIRST_INO(sb)))) {
-		ext4_error(sb, "Something is wrong with group %u: "
-			   "used itable blocks: %d; "
-			   "itable unused count: %u",
-			   group, used_blks,
-			   ext4_itable_unused_count(sb, gdp));
-		ret = 1;
-		goto err_out;
+	if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) {
+		used_inos = EXT4_INODES_PER_GROUP(sb) -
+			    ext4_itable_unused_count(sb, gdp);
+		used_blks = DIV_ROUND_UP(used_inos, sbi->s_inodes_per_block);
+
+		/* Bogus inode unused count? */
+		if (used_blks < 0 || used_blks > sbi->s_itb_per_group) {
+			ext4_error(sb, "Something is wrong with group %u: "
+				   "used itable blocks: %d; "
+				   "itable unused count: %u",
+				   group, used_blks,
+				   ext4_itable_unused_count(sb, gdp));
+			ret = 1;
+			goto err_out;
+		}
+
+		used_inos += group * EXT4_INODES_PER_GROUP(sb);
+		/*
+		 * Are there some uninitialized inodes in the inode table
+		 * before the first normal inode?
+		 */
+		if ((used_blks != sbi->s_itb_per_group) &&
+		     (used_inos < EXT4_FIRST_INO(sb))) {
+			ext4_error(sb, "Something is wrong with group %u: "
+				   "itable unused count: %u; "
+				   "itables initialized count: %ld",
+				   group, ext4_itable_unused_count(sb, gdp),
+				   used_inos);
+			ret = 1;
+			goto err_out;
+		}
 	}
 
 	blk = ext4_inode_table(sb, gdp) + used_blks;
 	num = sbi->s_itb_per_group - used_blks;
 
 	BUFFER_TRACE(group_desc_bh, "get_write_access");
-	ret = ext4_journal_get_write_access(handle,
-					    group_desc_bh);
+	ret = ext4_journal_get_write_access(handle, sb, group_desc_bh,
+					    EXT4_JTR_NONE);
 	if (ret)
 		goto err_out;
 
@@ -1424,7 +1599,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
 	if (ret < 0)
 		goto err_out;
 	if (barrier)
-		blkdev_issue_flush(sb->s_bdev, GFP_NOFS, NULL);
+		blkdev_issue_flush(sb->s_bdev);
 
 skip_zeroout:
 	ext4_lock_group(sb, group);