Merge tag 'ext4-for-linus-5.8-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull more ext4 updates from Ted Ts'o:
 "This is the second round of ext4 commits for 5.8 merge window [1].

  It includes the per-inode DAX support, which was dependant on the DAX
  infrastructure which came in via the XFS tree, and a number of
  regression and bug fixes; most notably the "BUG: using
  smp_processor_id() in preemptible code in ext4_mb_new_blocks" reported
  by syzkaller"

[1] The pull request actually came in 15 minutes after I had tagged the
    rc1 release. Tssk, tssk, late..   - Linus

* tag 'ext4-for-linus-5.8-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4, jbd2: ensure panic by fix a race between jbd2 abort and ext4 error handlers
  ext4: support xattr gnu.* namespace for the Hurd
  ext4: mballoc: Use this_cpu_read instead of this_cpu_ptr
  ext4: avoid utf8_strncasecmp() with unstable name
  ext4: stop overwrite the errcode in ext4_setup_super
  ext4: fix partial cluster initialization when splitting extent
  ext4: avoid race conditions when remounting with options that change dax
  Documentation/dax: Update DAX enablement for ext4
  fs/ext4: Introduce DAX inode flag
  fs/ext4: Remove jflag variable
  fs/ext4: Make DAX mount option a tri-state
  fs/ext4: Only change S_DAX on inode load
  fs/ext4: Update ext4_should_use_dax()
  fs/ext4: Change EXT4_MOUNT_DAX to EXT4_MOUNT_DAX_ALWAYS
  fs/ext4: Disallow verity if inode is DAX
  fs/ext4: Narrow scope of DAX check in setflags

Author: torvalds

Documentation/filesystems/dax.txt

@@ -25,16 +25,16 @@ size when creating the filesystem.
 Currently 3 filesystems support DAX: ext2, ext4 and xfs.  Enabling DAX on them
 is different.
 
-Enabling DAX on ext4 and ext2
+Enabling DAX on ext2
 -----------------------------
 
 When mounting the filesystem, use the "-o dax" option on the command line or
 add 'dax' to the options in /etc/fstab.  This works to enable DAX on all files
 within the filesystem.  It is equivalent to the '-o dax=always' behavior below.
 
 
-Enabling DAX on xfs
--------------------
+Enabling DAX on xfs and ext4
+----------------------------
 
 Summary
 -------

Documentation/filesystems/ext4/verity.rst

@@ -39,3 +39,6 @@ is encrypted as well as the data itself.
 
 Verity files cannot have blocks allocated past the end of the verity
 metadata.
+
+Verity and DAX are not compatible and attempts to set both of these flags
+on a file will fail.

fs/ext4/Makefile

@@ -9,7 +9,8 @@ ext4-y	:= balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
 		extents_status.o file.o fsmap.o fsync.o hash.o ialloc.o \
 		indirect.o inline.o inode.o ioctl.o mballoc.o migrate.o \
 		mmp.o move_extent.o namei.o page-io.o readpage.o resize.o \
-		super.o symlink.o sysfs.o xattr.o xattr_trusted.o xattr_user.o
+		super.o symlink.o sysfs.o xattr.o xattr_hurd.o xattr_trusted.o \
+		xattr_user.o
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o

fs/ext4/dir.c

@@ -675,6 +675,7 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len,
 	struct qstr qstr = {.name = str, .len = len };
 	const struct dentry *parent = READ_ONCE(dentry->d_parent);
 	const struct inode *inode = READ_ONCE(parent->d_inode);
+	char strbuf[DNAME_INLINE_LEN];
 
 	if (!inode || !IS_CASEFOLDED(inode) ||
 	    !EXT4_SB(inode->i_sb)->s_encoding) {
@@ -683,6 +684,21 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len,
 		return memcmp(str, name->name, len);
 	}
 
+	/*
+	 * If the dentry name is stored in-line, then it may be concurrently
+	 * modified by a rename.  If this happens, the VFS will eventually retry
+	 * the lookup, so it doesn't matter what ->d_compare() returns.
+	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
+	 * string.  Therefore, we have to copy the name into a temporary buffer.
+	 */
+	if (len <= DNAME_INLINE_LEN - 1) {
+		memcpy(strbuf, str, len);
+		strbuf[len] = 0;
+		qstr.name = strbuf;
+		/* prevent compiler from optimizing out the temporary buffer */
+		barrier();
+	}
+
 	return ext4_ci_compare(inode, name, &qstr, false);
 }
 

fs/ext4/ext4.h

@@ -426,28 +426,33 @@ struct flex_groups {
 #define EXT4_VERITY_FL			0x00100000 /* Verity protected inode */
 #define EXT4_EA_INODE_FL	        0x00200000 /* Inode used for large EA */
 /* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */
+
+#define EXT4_DAX_FL			0x02000000 /* Inode is DAX */
+
 #define EXT4_INLINE_DATA_FL		0x10000000 /* Inode has inline data. */
 #define EXT4_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
 #define EXT4_CASEFOLD_FL		0x40000000 /* Casefolded directory */
 #define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
 
-#define EXT4_FL_USER_VISIBLE		0x705BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE		0x604BC0FF /* User modifiable flags */
+#define EXT4_FL_USER_VISIBLE		0x725BDFFF /* User visible flags */
+#define EXT4_FL_USER_MODIFIABLE		0x624BC0FF /* User modifiable flags */
 
 /* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */
 #define EXT4_FL_XFLAG_VISIBLE		(EXT4_SYNC_FL | \
 					 EXT4_IMMUTABLE_FL | \
 					 EXT4_APPEND_FL | \
 					 EXT4_NODUMP_FL | \
 					 EXT4_NOATIME_FL | \
-					 EXT4_PROJINHERIT_FL)
+					 EXT4_PROJINHERIT_FL | \
+					 EXT4_DAX_FL)
 
 /* Flags that should be inherited by new inodes from their parent. */
 #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
 			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
 			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
 			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\
-			   EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL)
+			   EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL |\
+			   EXT4_DAX_FL)
 
 /* Flags that are appropriate for regular files (all but dir-specific ones). */
 #define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\
@@ -459,6 +464,10 @@ struct flex_groups {
 /* The only flags that should be swapped */
 #define EXT4_FL_SHOULD_SWAP (EXT4_HUGE_FILE_FL | EXT4_EXTENTS_FL)
 
+/* Flags which are mutually exclusive to DAX */
+#define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\
+			   EXT4_JOURNAL_DATA_FL)
+
 /* Mask out flags that are inappropriate for the given type of inode. */
 static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
 {
@@ -499,6 +508,7 @@ enum {
 	EXT4_INODE_VERITY	= 20,	/* Verity protected inode */
 	EXT4_INODE_EA_INODE	= 21,	/* Inode used for large EA */
 /* 22 was formerly EXT4_INODE_EOFBLOCKS */
+	EXT4_INODE_DAX		= 25,	/* Inode is DAX */
 	EXT4_INODE_INLINE_DATA	= 28,	/* Data in inode. */
 	EXT4_INODE_PROJINHERIT	= 29,	/* Create with parents projid */
 	EXT4_INODE_CASEFOLD	= 30,	/* Casefolded directory */
@@ -1135,9 +1145,9 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
 #define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
 #ifdef CONFIG_FS_DAX
-#define EXT4_MOUNT_DAX			0x00200	/* Direct Access */
+#define EXT4_MOUNT_DAX_ALWAYS		0x00200	/* Direct Access */
 #else
-#define EXT4_MOUNT_DAX			0
+#define EXT4_MOUNT_DAX_ALWAYS		0
 #endif
 #define EXT4_MOUNT_DATA_FLAGS		0x00C00	/* Mode for data writes: */
 #define EXT4_MOUNT_JOURNAL_DATA		0x00400	/* Write data to journal */
@@ -1180,6 +1190,8 @@ struct ext4_inode_info {
 						      blocks */
 #define EXT4_MOUNT2_HURD_COMPAT		0x00000004 /* Support HURD-castrated
 						      file systems */
+#define EXT4_MOUNT2_DAX_NEVER		0x00000008 /* Do not allow Direct Access */
+#define EXT4_MOUNT2_DAX_INODE		0x00000010 /* For printing options only */
 
 #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
 						specified journal checksum */
@@ -1992,6 +2004,7 @@ static inline bool ext4_has_incompat_features(struct super_block *sb)
  */
 #define EXT4_FLAGS_RESIZING	0
 #define EXT4_FLAGS_SHUTDOWN	1
+#define EXT4_FLAGS_BDEV_IS_DAX	2
 
 static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
 {
@@ -2705,7 +2718,7 @@ extern int ext4_can_truncate(struct inode *inode);
 extern int ext4_truncate(struct inode *);
 extern int ext4_break_layouts(struct inode *);
 extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
-extern void ext4_set_inode_flags(struct inode *);
+extern void ext4_set_inode_flags(struct inode *, bool init);
 extern int ext4_alloc_da_blocks(struct inode *inode);
 extern void ext4_set_aops(struct inode *inode);
 extern int ext4_writepage_trans_blocks(struct inode *);

fs/ext4/extents.c

@@ -2844,7 +2844,7 @@ int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 			 * in use to avoid freeing it when removing blocks.
 			 */
 			if (sbi->s_cluster_ratio > 1) {
-				pblk = ext4_ext_pblock(ex) + end - ee_block + 2;
+				pblk = ext4_ext_pblock(ex) + end - ee_block + 1;
 				partial.pclu = EXT4_B2C(sbi, pblk);
 				partial.state = nofree;
 			}

fs/ext4/ialloc.c

@@ -1116,7 +1116,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	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) {

fs/ext4/inode.c

@@ -4403,9 +4403,11 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
 		!ext4_test_inode_state(inode, EXT4_STATE_XATTR));
 }
 
-static bool ext4_should_use_dax(struct inode *inode)
+static bool ext4_should_enable_dax(struct inode *inode)
 {
-	if (!test_opt(inode->i_sb, DAX))
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+	if (test_opt2(inode->i_sb, DAX_NEVER))
 		return false;
 	if (!S_ISREG(inode->i_mode))
 		return false;
@@ -4417,14 +4419,21 @@ static bool ext4_should_use_dax(struct inode *inode)
 		return false;
 	if (ext4_test_inode_flag(inode, EXT4_INODE_VERITY))
 		return false;
-	return true;
+	if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags))
+		return false;
+	if (test_opt(inode->i_sb, DAX_ALWAYS))
+		return true;
+
+	return ext4_test_inode_flag(inode, EXT4_INODE_DAX);
 }
 
-void ext4_set_inode_flags(struct inode *inode)
+void ext4_set_inode_flags(struct inode *inode, bool init)
 {
 	unsigned int flags = EXT4_I(inode)->i_flags;
 	unsigned int new_fl = 0;
 
+	WARN_ON_ONCE(IS_DAX(inode) && init);
+
 	if (flags & EXT4_SYNC_FL)
 		new_fl |= S_SYNC;
 	if (flags & EXT4_APPEND_FL)
@@ -4435,8 +4444,13 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
-	if (ext4_should_use_dax(inode))
+
+	/* Because of the way inode_set_flags() works we must preserve S_DAX
+	 * here if already set. */
+	new_fl |= (inode->i_flags & S_DAX);
+	if (init && ext4_should_enable_dax(inode))
 		new_fl |= S_DAX;
+
 	if (flags & EXT4_ENCRYPT_FL)
 		new_fl |= S_ENCRYPTED;
 	if (flags & EXT4_CASEFOLD_FL)
@@ -4650,7 +4664,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 		 * not initialized on a new filesystem. */
 	}
 	ei->i_flags = le32_to_cpu(raw_inode->i_flags);
-	ext4_set_inode_flags(inode);
+	ext4_set_inode_flags(inode, true);
 	inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
 	ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
 	if (ext4_has_feature_64bit(sb))

fs/ext4/ioctl.c

@@ -292,6 +292,38 @@ static int ext4_ioctl_check_immutable(struct inode *inode, __u32 new_projid,
 	return 0;
 }
 
+static void ext4_dax_dontcache(struct inode *inode, unsigned int flags)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (S_ISDIR(inode->i_mode))
+		return;
+
+	if (test_opt2(inode->i_sb, DAX_NEVER) ||
+	    test_opt(inode->i_sb, DAX_ALWAYS))
+		return;
+
+	if ((ei->i_flags ^ flags) & EXT4_DAX_FL)
+		d_mark_dontcache(inode);
+}
+
+static bool dax_compatible(struct inode *inode, unsigned int oldflags,
+			   unsigned int flags)
+{
+	if (flags & EXT4_DAX_FL) {
+		if ((oldflags & EXT4_DAX_MUT_EXCL) ||
+		     ext4_test_inode_state(inode,
+					  EXT4_STATE_VERITY_IN_PROGRESS)) {
+			return false;
+		}
+	}
+
+	if ((flags & EXT4_DAX_MUT_EXCL) && (oldflags & EXT4_DAX_FL))
+			return false;
+
+	return true;
+}
+
 static int ext4_ioctl_setflags(struct inode *inode,
 			       unsigned int flags)
 {
@@ -300,7 +332,6 @@ static int ext4_ioctl_setflags(struct inode *inode,
 	int err = -EPERM, migrate = 0;
 	struct ext4_iloc iloc;
 	unsigned int oldflags, mask, i;
-	unsigned int jflag;
 	struct super_block *sb = inode->i_sb;
 
 	/* Is it quota file? Do not allow user to mess with it */
@@ -309,9 +340,6 @@ static int ext4_ioctl_setflags(struct inode *inode,
 
 	oldflags = ei->i_flags;
 
-	/* The JOURNAL_DATA flag is modifiable only by root */
-	jflag = flags & EXT4_JOURNAL_DATA_FL;
-
 	err = vfs_ioc_setflags_prepare(inode, oldflags, flags);
 	if (err)
 		goto flags_out;
@@ -320,10 +348,16 @@ static int ext4_ioctl_setflags(struct inode *inode,
 	 * The JOURNAL_DATA flag can only be changed by
 	 * the relevant capability.
 	 */
-	if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
+	if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
 		if (!capable(CAP_SYS_RESOURCE))
 			goto flags_out;
 	}
+
+	if (!dax_compatible(inode, oldflags, flags)) {
+		err = -EOPNOTSUPP;
+		goto flags_out;
+	}
+
 	if ((flags ^ oldflags) & EXT4_EXTENTS_FL)
 		migrate = 1;
 
@@ -369,6 +403,8 @@ static int ext4_ioctl_setflags(struct inode *inode,
 	if (err)
 		goto flags_err;
 
+	ext4_dax_dontcache(inode, flags);
+
 	for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
 		if (!(mask & EXT4_FL_USER_MODIFIABLE))
 			continue;
@@ -381,7 +417,8 @@ static int ext4_ioctl_setflags(struct inode *inode,
 			ext4_clear_inode_flag(inode, i);
 	}
 
-	ext4_set_inode_flags(inode);
+	ext4_set_inode_flags(inode, false);
+
 	inode->i_ctime = current_time(inode);
 
 	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
@@ -390,17 +427,18 @@ static int ext4_ioctl_setflags(struct inode *inode,
 	if (err)
 		goto flags_out;
 
-	if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
+	if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
 		/*
 		 * Changes to the journaling mode can cause unsafe changes to
-		 * S_DAX if we are using the DAX mount option.
+		 * S_DAX if the inode is DAX
 		 */
-		if (test_opt(inode->i_sb, DAX)) {
+		if (IS_DAX(inode)) {
 			err = -EBUSY;
 			goto flags_out;
 		}
 
-		err = ext4_change_inode_journal_flag(inode, jflag);
+		err = ext4_change_inode_journal_flag(inode,
+						     flags & EXT4_JOURNAL_DATA_FL);
 		if (err)
 			goto flags_out;
 	}
@@ -527,12 +565,15 @@ static inline __u32 ext4_iflags_to_xflags(unsigned long iflags)
 		xflags |= FS_XFLAG_NOATIME;
 	if (iflags & EXT4_PROJINHERIT_FL)
 		xflags |= FS_XFLAG_PROJINHERIT;
+	if (iflags & EXT4_DAX_FL)
+		xflags |= FS_XFLAG_DAX;
 	return xflags;
 }
 
 #define EXT4_SUPPORTED_FS_XFLAGS (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | \
 				  FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \
-				  FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT)
+				  FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT | \
+				  FS_XFLAG_DAX)
 
 /* Transfer xflags flags to internal */
 static inline unsigned long ext4_xflags_to_iflags(__u32 xflags)
@@ -551,6 +592,8 @@ static inline unsigned long ext4_xflags_to_iflags(__u32 xflags)
 		iflags |= EXT4_NOATIME_FL;
 	if (xflags & FS_XFLAG_PROJINHERIT)
 		iflags |= EXT4_PROJINHERIT_FL;
+	if (xflags & FS_XFLAG_DAX)
+		iflags |= EXT4_DAX_FL;
 
 	return iflags;
 }

fs/ext4/mballoc.c

@@ -4708,7 +4708,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	}
 
 	ac->ac_op = EXT4_MB_HISTORY_PREALLOC;
-	seq = *this_cpu_ptr(&discard_pa_seq);
+	seq = this_cpu_read(discard_pa_seq);
 	if (!ext4_mb_use_preallocated(ac)) {
 		ac->ac_op = EXT4_MB_HISTORY_ALLOC;
 		ext4_mb_normalize_request(ac, ar);