From fc626fe322f13ecdfac58cbfa6cfea797ed22623 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Thu, 28 May 2020 07:59:57 -0700
Subject: fs/ext4: Change EXT4_MOUNT_DAX to EXT4_MOUNT_DAX_ALWAYS

In prep for the new tri-state mount option which then introduces
EXT4_MOUNT_DAX_NEVER.

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>

Link: https://lore.kernel.org/r/20200528150003.828793-4-ira.weiny@intel.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2a4aae6acdcb..a10ff12194db 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4400,7 +4400,7 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
 
 static bool ext4_should_use_dax(struct inode *inode)
 {
-	if (!test_opt(inode->i_sb, DAX))
+	if (!test_opt(inode->i_sb, DAX_ALWAYS))
 		return false;
 	if (!S_ISREG(inode->i_mode))
 		return false;
-- 
cgit v1.2.3


From a8ab6d3885ef5e2300d683b79a9e1999403eefd9 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Thu, 28 May 2020 07:59:58 -0700
Subject: fs/ext4: Update ext4_should_use_dax()

S_DAX should only be enabled when the underlying block device supports
dax.

Cache the underlying support for DAX in the super block and modify
ext4_should_use_dax() to check for device support prior to the over
riding mount option.

While we are at it change the function to ext4_should_enable_dax() as
this better reflects the ask as well as matches xfs.

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>

Link: https://lore.kernel.org/r/20200528150003.828793-5-ira.weiny@intel.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h  |  1 +
 fs/ext4/inode.c | 15 ++++++++++-----
 fs/ext4/super.c |  5 ++++-
 3 files changed, 15 insertions(+), 6 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1a3daf2d18ef..0b4db9ce7756 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1979,6 +1979,7 @@ 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)
 {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index a10ff12194db..6532870f6a0b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4398,10 +4398,10 @@ 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_ALWAYS))
-		return false;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
 	if (!S_ISREG(inode->i_mode))
 		return false;
 	if (ext4_should_journal_data(inode))
@@ -4412,7 +4412,12 @@ 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 false;
 }
 
 void ext4_set_inode_flags(struct inode *inode)
@@ -4430,7 +4435,7 @@ 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))
+	if (ext4_should_enable_dax(inode))
 		new_fl |= S_DAX;
 	if (flags & EXT4_ENCRYPT_FL)
 		new_fl |= S_ENCRYPTED;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7b99c44d0a91..f7d76dcaedfe 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4092,13 +4092,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
+	if (bdev_dax_supported(sb->s_bdev, blocksize))
+		set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
+
 	if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) {
 		if (ext4_has_feature_inline_data(sb)) {
 			ext4_msg(sb, KERN_ERR, "Cannot use DAX on a filesystem"
 					" that may contain inline data");
 			goto failed_mount;
 		}
-		if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
+		if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) {
 			ext4_msg(sb, KERN_ERR,
 				"DAX unsupported by block device.");
 			goto failed_mount;
-- 
cgit v1.2.3


From 043546e46dc70c25ff7e2cf6d09cbb0424fc9978 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Thu, 28 May 2020 07:59:59 -0700
Subject: fs/ext4: Only change S_DAX on inode load

To prevent complications with in memory inodes we only set S_DAX on
inode load.  FS_XFLAG_DAX can be changed at any time and S_DAX will
change after inode eviction and reload.

Add init bool to ext4_set_inode_flags() to indicate if the inode is
being newly initialized.

Assert that S_DAX is not set on an inode which is just being loaded.

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>

Link: https://lore.kernel.org/r/20200528150003.828793-6-ira.weiny@intel.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h   |  2 +-
 fs/ext4/ialloc.c |  2 +-
 fs/ext4/inode.c  | 13 ++++++++++---
 fs/ext4/ioctl.c  |  3 ++-
 fs/ext4/super.c  |  4 ++--
 fs/ext4/verity.c |  2 +-
 6 files changed, 17 insertions(+), 9 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0b4db9ce7756..f5291693ce6e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2693,7 +2693,7 @@ 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 *);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 4b8c9a9bdf0c..7941c140723f 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1116,7 +1116,7 @@ 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) {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 6532870f6a0b..01636cf5f322 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4420,11 +4420,13 @@ static bool ext4_should_enable_dax(struct inode *inode)
 	return false;
 }
 
-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 +4437,13 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
-	if (ext4_should_enable_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 +4657,7 @@ 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))
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 5813e5e73eab..145083e8cd1e 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -381,7 +381,8 @@ 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);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index f7d76dcaedfe..80eb814c47eb 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1348,7 +1348,7 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 			 * Update inode->i_flags - S_ENCRYPTED will be enabled,
 			 * S_DAX may be disabled
 			 */
-			ext4_set_inode_flags(inode);
+			ext4_set_inode_flags(inode, false);
 		}
 		return res;
 	}
@@ -1375,7 +1375,7 @@ retry:
 		 * Update inode->i_flags - S_ENCRYPTED will be enabled,
 		 * S_DAX may be disabled
 		 */
-		ext4_set_inode_flags(inode);
+		ext4_set_inode_flags(inode, false);
 		res = ext4_mark_inode_dirty(handle, inode);
 		if (res)
 			EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index f05a09fb2ae4..89a155ece323 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -244,7 +244,7 @@ static int ext4_end_enable_verity(struct file *filp, const void *desc,
 		if (err)
 			goto out_stop;
 		ext4_set_inode_flag(inode, EXT4_INODE_VERITY);
-		ext4_set_inode_flags(inode);
+		ext4_set_inode_flags(inode, false);
 		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 	}
 out_stop:
-- 
cgit v1.2.3


From 9cb20f94afcd2964944f9468e38da736ee855b19 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Thu, 28 May 2020 08:00:00 -0700
Subject: fs/ext4: Make DAX mount option a tri-state

We add 'always', 'never', and 'inode' (default).  '-o dax' continues to
operate the same which is equivalent to 'always'.  This new
functionality is limited to ext4 only.

Specifically we introduce a 2nd DAX mount flag EXT4_MOUNT2_DAX_NEVER and set
it and EXT4_MOUNT_DAX_ALWAYS appropriately for the mode.

We also force EXT4_MOUNT2_DAX_NEVER if !CONFIG_FS_DAX.

Finally, EXT4_MOUNT2_DAX_INODE is used solely to detect if the user
specified that option for printing.

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>

Link: https://lore.kernel.org/r/20200528150003.828793-7-ira.weiny@intel.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h  |  2 ++
 fs/ext4/inode.c |  2 ++
 fs/ext4/super.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++++---------
 3 files changed, 61 insertions(+), 10 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index f5291693ce6e..65ffb831b2b9 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1168,6 +1168,8 @@ 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 */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 01636cf5f322..68fac9289109 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4402,6 +4402,8 @@ static bool ext4_should_enable_dax(struct inode *inode)
 {
 	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;
 	if (ext4_should_journal_data(inode))
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 80eb814c47eb..5e056aa20ce9 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1512,7 +1512,8 @@ enum {
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
-	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
+	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version,
+	Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
 	Opt_nowarn_on_error, Opt_mblk_io_submit,
 	Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
@@ -1579,6 +1580,9 @@ static const match_table_t tokens = {
 	{Opt_nobarrier, "nobarrier"},
 	{Opt_i_version, "i_version"},
 	{Opt_dax, "dax"},
+	{Opt_dax_always, "dax=always"},
+	{Opt_dax_inode, "dax=inode"},
+	{Opt_dax_never, "dax=never"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_delalloc, "delalloc"},
 	{Opt_warn_on_error, "warn_on_error"},
@@ -1726,6 +1730,7 @@ static int clear_qf_name(struct super_block *sb, int qtype)
 #define MOPT_NO_EXT3	0x0200
 #define MOPT_EXT4_ONLY	(MOPT_NO_EXT2 | MOPT_NO_EXT3)
 #define MOPT_STRING	0x0400
+#define MOPT_SKIP	0x0800
 
 static const struct mount_opts {
 	int	token;
@@ -1775,7 +1780,13 @@ static const struct mount_opts {
 	{Opt_min_batch_time, 0, MOPT_GTE0},
 	{Opt_inode_readahead_blks, 0, MOPT_GTE0},
 	{Opt_init_itable, 0, MOPT_GTE0},
-	{Opt_dax, EXT4_MOUNT_DAX_ALWAYS, MOPT_SET},
+	{Opt_dax, EXT4_MOUNT_DAX_ALWAYS, MOPT_SET | MOPT_SKIP},
+	{Opt_dax_always, EXT4_MOUNT_DAX_ALWAYS,
+		MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
+	{Opt_dax_inode, EXT4_MOUNT2_DAX_INODE,
+		MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
+	{Opt_dax_never, EXT4_MOUNT2_DAX_NEVER,
+		MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
 	{Opt_stripe, 0, MOPT_GTE0},
 	{Opt_resuid, 0, MOPT_GTE0},
 	{Opt_resgid, 0, MOPT_GTE0},
@@ -2084,13 +2095,32 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		}
 		sbi->s_jquota_fmt = m->mount_opt;
 #endif
-	} else if (token == Opt_dax) {
+	} else if (token == Opt_dax || token == Opt_dax_always ||
+		   token == Opt_dax_inode || token == Opt_dax_never) {
 #ifdef CONFIG_FS_DAX
-		ext4_msg(sb, KERN_WARNING,
-		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
-		sbi->s_mount_opt |= m->mount_opt;
+		switch (token) {
+		case Opt_dax:
+		case Opt_dax_always:
+			ext4_msg(sb, KERN_WARNING,
+				"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+			sbi->s_mount_opt |= EXT4_MOUNT_DAX_ALWAYS;
+			sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER;
+			break;
+		case Opt_dax_never:
+			sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER;
+			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
+			break;
+		case Opt_dax_inode:
+			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
+			sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER;
+			/* Strictly for printing options */
+			sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_INODE;
+			break;
+		}
 #else
 		ext4_msg(sb, KERN_INFO, "dax option not supported");
+		sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER;
+		sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
 		return -1;
 #endif
 	} else if (token == Opt_data_err_abort) {
@@ -2254,7 +2284,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 	for (m = ext4_mount_opts; m->token != Opt_err; m++) {
 		int want_set = m->flags & MOPT_SET;
 		if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) ||
-		    (m->flags & MOPT_CLEAR_ERR))
+		    (m->flags & MOPT_CLEAR_ERR) || m->flags & MOPT_SKIP)
 			continue;
 		if (!nodefs && !(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt)))
 			continue; /* skip if same as the default */
@@ -2314,6 +2344,17 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 	if (DUMMY_ENCRYPTION_ENABLED(sbi))
 		SEQ_OPTS_PUTS("test_dummy_encryption");
 
+	if (test_opt(sb, DAX_ALWAYS)) {
+		if (IS_EXT2_SB(sb))
+			SEQ_OPTS_PUTS("dax");
+		else
+			SEQ_OPTS_PUTS("dax=always");
+	} else if (test_opt2(sb, DAX_NEVER)) {
+		SEQ_OPTS_PUTS("dax=never");
+	} else if (test_opt2(sb, DAX_INODE)) {
+		SEQ_OPTS_PUTS("dax=inode");
+	}
+
 	ext4_show_quota_options(seq, sb);
 	return 0;
 }
@@ -5436,10 +5477,16 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		goto restore_opts;
 	}
 
-	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX_ALWAYS) {
+	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX_ALWAYS ||
+	    (sbi->s_mount_opt2 ^ old_opts.s_mount_opt2) & EXT4_MOUNT2_DAX_NEVER ||
+	    (sbi->s_mount_opt2 ^ old_opts.s_mount_opt2) & EXT4_MOUNT2_DAX_INODE) {
 		ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
-			"dax flag with busy inodes while remounting");
-		sbi->s_mount_opt ^= EXT4_MOUNT_DAX_ALWAYS;
+			"dax mount option with busy inodes while remounting");
+		sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
+		sbi->s_mount_opt |= old_opts.s_mount_opt & EXT4_MOUNT_DAX_ALWAYS;
+		sbi->s_mount_opt2 &= ~(EXT4_MOUNT2_DAX_NEVER | EXT4_MOUNT2_DAX_INODE);
+		sbi->s_mount_opt2 |= old_opts.s_mount_opt2 &
+				     (EXT4_MOUNT2_DAX_NEVER | EXT4_MOUNT2_DAX_INODE);
 	}
 
 	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
-- 
cgit v1.2.3


From b383a73f2b832491a2f9e6e8ada26aad53b5763d Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Thu, 28 May 2020 08:00:02 -0700
Subject: fs/ext4: Introduce DAX inode flag

Add a flag ([EXT4|FS]_DAX_FL) to preserve FS_XFLAG_DAX in the ext4
inode.

Set the flag to be user visible and changeable.  Set the flag to be
inherited.  Allow applications to change the flag at any time except if
it conflicts with the set of mutually exclusive flags (Currently VERITY,
ENCRYPT, JOURNAL_DATA).

Furthermore, restrict setting any of the exclusive flags if DAX is set.

While conceptually possible, we do not allow setting EXT4_DAX_FL while
at the same time clearing exclusion flags (or vice versa) for 2 reasons:

	1) The DAX flag does not take effect immediately which
	   introduces quite a bit of complexity
	2) There is no clear use case for being this flexible

Finally, on regular files, flag the inode to not be cached to facilitate
changing S_DAX on the next creation of the inode.

Signed-off-by: Ira Weiny <ira.weiny@intel.com>

Link: https://lore.kernel.org/r/20200528150003.828793-9-ira.weiny@intel.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h          | 18 ++++++++++++++----
 fs/ext4/inode.c         |  2 +-
 fs/ext4/ioctl.c         | 47 ++++++++++++++++++++++++++++++++++++++++++++++-
 fs/ext4/super.c         |  3 +++
 fs/ext4/verity.c        |  2 +-
 include/uapi/linux/fs.h |  1 +
 6 files changed, 66 insertions(+), 7 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 65ffb831b2b9..598e00a9453f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -415,13 +415,16 @@ 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 file */
 #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 | \
@@ -429,14 +432,16 @@ struct flex_groups {
 					 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 |\
@@ -448,6 +453,10 @@ 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)
 {
@@ -488,6 +497,7 @@ 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_RESERVED	= 31,	/* reserved for ext4 lib */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 68fac9289109..778b0dbe3da6 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4419,7 +4419,7 @@ static bool ext4_should_enable_dax(struct inode *inode)
 	if (test_opt(inode->i_sb, DAX_ALWAYS))
 		return true;
 
-	return false;
+	return ext4_test_inode_flag(inode, EXT4_INODE_DAX);
 }
 
 void ext4_set_inode_flags(struct inode *inode, bool init)
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 779631e8e849..1b520d07d371 100644
--- a/fs/ext4/ioctl.c
+++ b/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)
 {
@@ -320,6 +352,12 @@ static int ext4_ioctl_setflags(struct inode *inode,
 		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;
 
@@ -365,6 +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;
@@ -525,12 +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)
@@ -549,6 +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;
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 5e056aa20ce9..3658e3016999 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1323,6 +1323,9 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 	if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode)))
 		return -EINVAL;
 
+	if (ext4_test_inode_flag(inode, EXT4_INODE_DAX))
+		return -EOPNOTSUPP;
+
 	res = ext4_convert_inline_data(inode);
 	if (res)
 		return res;
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index 89a155ece323..4fecb3e4e338 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -113,7 +113,7 @@ static int ext4_begin_enable_verity(struct file *filp)
 	handle_t *handle;
 	int err;
 
-	if (IS_DAX(inode))
+	if (IS_DAX(inode) || ext4_test_inode_flag(inode, EXT4_INODE_DAX))
 		return -EINVAL;
 
 	if (ext4_verity_in_progress(inode))
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 379a612f8f1d..f44eb0a04afd 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -262,6 +262,7 @@ struct fsxattr {
 #define FS_EA_INODE_FL			0x00200000 /* Inode used for large EA */
 #define FS_EOFBLOCKS_FL			0x00400000 /* Reserved for ext4 */
 #define FS_NOCOW_FL			0x00800000 /* Do not cow file */
+#define FS_DAX_FL			0x02000000 /* Inode is DAX */
 #define FS_INLINE_DATA_FL		0x10000000 /* Reserved for ext4 */
 #define FS_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
 #define FS_CASEFOLD_FL			0x40000000 /* Folder is case insensitive */
-- 
cgit v1.2.3