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
diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt
index 8e26707..8fdb78f 100644
--- a/Documentation/filesystems/dax.txt
+++ b/Documentation/filesystems/dax.txt
@@ -25,7 +25,7 @@
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
@@ -33,8 +33,8 @@
within the filesystem. It is equivalent to the '-o dax=always' behavior below.
-Enabling DAX on xfs
--------------------
+Enabling DAX on xfs and ext4
+----------------------------
Summary
-------
diff --git a/Documentation/filesystems/ext4/verity.rst b/Documentation/filesystems/ext4/verity.rst
index 3e4c0ee..e99ff3f 100644
--- a/Documentation/filesystems/ext4/verity.rst
+++ b/Documentation/filesystems/ext4/verity.rst
@@ -39,3 +39,6 @@
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.
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 4ccb3c9..2e42f47 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -9,7 +9,8 @@
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
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index c654205..1d82336 100644
--- a/fs/ext4/dir.c
+++ b/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);
}
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index b08841f..42f5060 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -426,13 +426,16 @@ 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 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 | \
@@ -440,14 +443,16 @@ 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 |\
@@ -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 *);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 7d088ff..221f240 100644
--- a/fs/ext4/extents.c
+++ b/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;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 54d324e8..df25d38 100644
--- a/fs/ext4/ialloc.c
+++ b/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) {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 40ec5c7..10dd47087 100644
--- a/fs/ext4/inode.c
+++ b/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))
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 2162db0..999cf6a 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)
{
@@ -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;
}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index a908311..c0a331e 100644
--- a/fs/ext4/mballoc.c
+++ b/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);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c668f6b..330957e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -522,9 +522,6 @@ static void ext4_handle_error(struct super_block *sb)
smp_wmb();
sb->s_flags |= SB_RDONLY;
} else if (test_opt(sb, ERRORS_PANIC)) {
- if (EXT4_SB(sb)->s_journal &&
- !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
- return;
panic("EXT4-fs (device %s): panic forced after error\n",
sb->s_id);
}
@@ -725,23 +722,20 @@ void __ext4_abort(struct super_block *sb, const char *function,
va_end(args);
if (sb_rdonly(sb) == 0) {
- ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+ if (EXT4_SB(sb)->s_journal)
+ jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
+
+ ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
/*
* Make sure updated value of ->s_mount_flags will be visible
* before ->s_flags update
*/
smp_wmb();
sb->s_flags |= SB_RDONLY;
- if (EXT4_SB(sb)->s_journal)
- jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
}
- if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) {
- if (EXT4_SB(sb)->s_journal &&
- !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
- return;
+ if (test_opt(sb, ERRORS_PANIC) && !system_going_down())
panic("EXT4-fs panic from previous error\n");
- }
}
void __ext4_msg(struct super_block *sb,
@@ -1324,6 +1318,9 @@ 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;
@@ -1349,7 +1346,7 @@ 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;
}
@@ -1376,7 +1373,7 @@ 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);
res = ext4_mark_inode_dirty(handle, inode);
if (res)
EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
@@ -1514,7 +1511,8 @@ 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,
@@ -1581,6 +1579,9 @@ 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"},
@@ -1729,6 +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;
@@ -1778,7 +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, 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},
@@ -2123,13 +2131,56 @@ 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:
+ if (is_remount &&
+ (!(sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) ||
+ (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER))) {
+ fail_dax_change_remount:
+ ext4_msg(sb, KERN_ERR, "can't change "
+ "dax mount option while remounting");
+ return -1;
+ }
+ if (is_remount &&
+ (test_opt(sb, DATA_FLAGS) ==
+ EXT4_MOUNT_JOURNAL_DATA)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and dax");
+ return -1;
+ }
+ 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:
+ if (is_remount &&
+ (!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) ||
+ (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS)))
+ goto fail_dax_change_remount;
+ sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER;
+ sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
+ break;
+ case Opt_dax_inode:
+ if (is_remount &&
+ ((sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) ||
+ (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) ||
+ !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE)))
+ goto fail_dax_change_remount;
+ 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) {
@@ -2293,7 +2344,7 @@ 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 */
@@ -2353,6 +2404,17 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
fscrypt_show_test_dummy_encryption(seq, sep, sb);
+ 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;
}
@@ -2383,6 +2445,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
ext4_msg(sb, KERN_ERR, "revision level too high, "
"forcing read-only mode");
err = -EROFS;
+ goto done;
}
if (read_only)
goto done;
@@ -4017,7 +4080,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
"both data=journal and delalloc");
goto failed_mount;
}
- if (test_opt(sb, DAX)) {
+ if (test_opt(sb, DAX_ALWAYS)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and dax");
goto failed_mount;
@@ -4127,13 +4190,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount;
}
- if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
+ 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;
@@ -5447,12 +5513,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
err = -EINVAL;
goto restore_opts;
}
- if (test_opt(sb, DAX)) {
- ext4_msg(sb, KERN_ERR, "can't mount with "
- "both data=journal and dax");
- err = -EINVAL;
- goto restore_opts;
- }
} else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) {
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
@@ -5468,12 +5528,6 @@ 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) {
- ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
- "dax flag with busy inodes while remounting");
- sbi->s_mount_opt ^= EXT4_MOUNT_DAX;
- }
-
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user");
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index dec1244..bbd5e7e 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -113,6 +113,9 @@ static int ext4_begin_enable_verity(struct file *filp)
handle_t *handle;
int err;
+ if (IS_DAX(inode) || ext4_test_inode_flag(inode, EXT4_INODE_DAX))
+ return -EINVAL;
+
if (ext4_verity_in_progress(inode))
return -EBUSY;
@@ -241,7 +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:
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 9b29a40..7d2f657 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -93,6 +93,7 @@ static const struct xattr_handler * const ext4_xattr_handler_map[] = {
#ifdef CONFIG_EXT4_FS_SECURITY
[EXT4_XATTR_INDEX_SECURITY] = &ext4_xattr_security_handler,
#endif
+ [EXT4_XATTR_INDEX_HURD] = &ext4_xattr_hurd_handler,
};
const struct xattr_handler *ext4_xattr_handlers[] = {
@@ -105,6 +106,7 @@ const struct xattr_handler *ext4_xattr_handlers[] = {
#ifdef CONFIG_EXT4_FS_SECURITY
&ext4_xattr_security_handler,
#endif
+ &ext4_xattr_hurd_handler,
NULL
};
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index ffe21ac..730b91f 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -124,6 +124,7 @@ struct ext4_xattr_inode_array {
extern const struct xattr_handler ext4_xattr_user_handler;
extern const struct xattr_handler ext4_xattr_trusted_handler;
extern const struct xattr_handler ext4_xattr_security_handler;
+extern const struct xattr_handler ext4_xattr_hurd_handler;
#define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c"
diff --git a/fs/ext4/xattr_hurd.c b/fs/ext4/xattr_hurd.c
new file mode 100644
index 0000000..8cfa74a
--- /dev/null
+++ b/fs/ext4/xattr_hurd.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/fs/ext4/xattr_hurd.c
+ * Handler for extended gnu attributes for the Hurd.
+ *
+ * Copyright (C) 2001 by Andreas Gruenbacher, <[email protected]>
+ * Copyright (C) 2020 by Jan (janneke) Nieuwenhuizen, <[email protected]>
+ */
+
+#include <linux/init.h>
+#include <linux/string.h>
+#include "ext4.h"
+#include "xattr.h"
+
+static bool
+ext4_xattr_hurd_list(struct dentry *dentry)
+{
+ return test_opt(dentry->d_sb, XATTR_USER);
+}
+
+static int
+ext4_xattr_hurd_get(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
+{
+ if (!test_opt(inode->i_sb, XATTR_USER))
+ return -EOPNOTSUPP;
+
+ return ext4_xattr_get(inode, EXT4_XATTR_INDEX_HURD,
+ name, buffer, size);
+}
+
+static int
+ext4_xattr_hurd_set(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ if (!test_opt(inode->i_sb, XATTR_USER))
+ return -EOPNOTSUPP;
+
+ return ext4_xattr_set(inode, EXT4_XATTR_INDEX_HURD,
+ name, value, size, flags);
+}
+
+const struct xattr_handler ext4_xattr_hurd_handler = {
+ .prefix = XATTR_HURD_PREFIX,
+ .list = ext4_xattr_hurd_list,
+ .get = ext4_xattr_hurd_get,
+ .set = ext4_xattr_hurd_set,
+};
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index a49d0e6..e494443 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1140,6 +1140,7 @@ static journal_t *journal_init_common(struct block_device *bdev,
init_waitqueue_head(&journal->j_wait_commit);
init_waitqueue_head(&journal->j_wait_updates);
init_waitqueue_head(&journal->j_wait_reserved);
+ mutex_init(&journal->j_abort_mutex);
mutex_init(&journal->j_barrier);
mutex_init(&journal->j_checkpoint_mutex);
spin_lock_init(&journal->j_revoke_lock);
@@ -1402,7 +1403,8 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
printk(KERN_ERR "JBD2: Error %d detected when updating "
"journal superblock for %s.\n", ret,
journal->j_devname);
- jbd2_journal_abort(journal, ret);
+ if (!is_journal_aborted(journal))
+ jbd2_journal_abort(journal, ret);
}
return ret;
@@ -2154,6 +2156,13 @@ void jbd2_journal_abort(journal_t *journal, int errno)
transaction_t *transaction;
/*
+ * Lock the aborting procedure until everything is done, this avoid
+ * races between filesystem's error handling flow (e.g. ext4_abort()),
+ * ensure panic after the error info is written into journal's
+ * superblock.
+ */
+ mutex_lock(&journal->j_abort_mutex);
+ /*
* ESHUTDOWN always takes precedence because a file system check
* caused by any other journal abort error is not required after
* a shutdown triggered.
@@ -2167,6 +2176,7 @@ void jbd2_journal_abort(journal_t *journal, int errno)
journal->j_errno = errno;
jbd2_journal_update_sb_errno(journal);
}
+ mutex_unlock(&journal->j_abort_mutex);
return;
}
@@ -2188,10 +2198,7 @@ void jbd2_journal_abort(journal_t *journal, int errno)
* layer could realise that a filesystem check is needed.
*/
jbd2_journal_update_sb_errno(journal);
-
- write_lock(&journal->j_state_lock);
- journal->j_flags |= JBD2_REC_ERR;
- write_unlock(&journal->j_state_lock);
+ mutex_unlock(&journal->j_abort_mutex);
}
/**
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index f613d85..d56128d 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -766,6 +766,11 @@ struct journal_s
int j_errno;
/**
+ * @j_abort_mutex: Lock the whole aborting procedure.
+ */
+ struct mutex j_abort_mutex;
+
+ /**
* @j_sb_buffer: The first part of the superblock buffer.
*/
struct buffer_head *j_sb_buffer;
@@ -1247,7 +1252,6 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3)
#define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file
* data write error in ordered
* mode */
-#define JBD2_REC_ERR 0x080 /* The errno in the sb has been recorded */
/*
* Function declarations for the journaling transaction and buffer
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 379a612..f44eb0a 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 */
diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h
index c1395b5..9463db2 100644
--- a/include/uapi/linux/xattr.h
+++ b/include/uapi/linux/xattr.h
@@ -7,6 +7,7 @@
Copyright (C) 2001 by Andreas Gruenbacher <[email protected]>
Copyright (c) 2001-2002 Silicon Graphics, Inc. All Rights Reserved.
Copyright (c) 2004 Red Hat, Inc., James Morris <[email protected]>
+ Copyright (c) 2020 Jan (janneke) Nieuwenhuizen <[email protected]>
*/
#include <linux/libc-compat.h>
@@ -31,6 +32,9 @@
#define XATTR_BTRFS_PREFIX "btrfs."
#define XATTR_BTRFS_PREFIX_LEN (sizeof(XATTR_BTRFS_PREFIX) - 1)
+#define XATTR_HURD_PREFIX "gnu."
+#define XATTR_HURD_PREFIX_LEN (sizeof(XATTR_HURD_PREFIX) - 1)
+
#define XATTR_SECURITY_PREFIX "security."
#define XATTR_SECURITY_PREFIX_LEN (sizeof(XATTR_SECURITY_PREFIX) - 1)
