From: Darrick J. Wong <[email protected]>
Refactor __bdev_dax_supported into a sb_dax_supported helper for
single-bdev filesystems and a regular bdev_dax_supported that takes a
bdev parameter. This enables multi-device filesystems like xfs to check
that a dax device can work for the particular filesystem. Once that's
in place, actually fix all the parts of XFS where we need to be able to
distinguish between datadev and rtdev.
This patch fixes the problem where we screw up the dax support checking
in xfs if the datadev and rtdev have different dax capabilities.
Signed-off-by: Darrick J. Wong <[email protected]>
---
drivers/dax/super.c | 9 +++++----
fs/ext2/super.c | 2 +-
fs/ext4/super.c | 2 +-
fs/xfs/xfs_ioctl.c | 3 ++-
fs/xfs/xfs_iops.c | 30 +++++++++++++++++++++++++-----
fs/xfs/xfs_super.c | 11 +++++++++--
include/linux/dax.h | 16 ++++++++++++----
7 files changed, 55 insertions(+), 18 deletions(-)
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 473af694ad1c..8a3a168a267f 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -73,8 +73,9 @@ EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
#endif
/**
- * __bdev_dax_supported() - Check if the device supports dax for filesystem
+ * bdev_dax_supported() - Check if the device supports dax for filesystem
* @sb: The superblock of the device
+ * @bdev: block device to check
* @blocksize: The block size of the device
*
* This is a library function for filesystems to check if the block device
@@ -82,9 +83,9 @@ EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
*
* Return: negative errno if unsupported, 0 if supported.
*/
-int __bdev_dax_supported(struct super_block *sb, int blocksize)
+int bdev_dax_supported(struct super_block *sb, struct block_device *bdev,
+ int blocksize)
{
- struct block_device *bdev = sb->s_bdev;
struct dax_device *dax_dev;
pgoff_t pgoff;
int err, id;
@@ -135,7 +136,7 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
return 0;
}
-EXPORT_SYMBOL_GPL(__bdev_dax_supported);
+EXPORT_SYMBOL_GPL(bdev_dax_supported);
#endif
enum dax_device_flags {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 7666c065b96f..28ca694e9e92 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -961,7 +961,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
if (sbi->s_mount_opt & EXT2_MOUNT_DAX) {
- err = bdev_dax_supported(sb, blocksize);
+ err = sb_dax_supported(sb, blocksize);
if (err) {
ext2_msg(sb, KERN_ERR,
"DAX unsupported by block device. Turning off DAX.");
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 39bf464c35f1..a09f832aad35 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3714,7 +3714,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
" that may contain inline data");
sbi->s_mount_opt &= ~EXT4_MOUNT_DAX;
}
- err = bdev_dax_supported(sb, blocksize);
+ err = sb_dax_supported(sb, blocksize);
if (err) {
ext4_msg(sb, KERN_ERR,
"DAX unsupported by block device. Turning off DAX.");
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 89fb1eb80aae..277355f5c084 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1103,7 +1103,8 @@ xfs_ioctl_setattr_dax_invalidate(
if (fa->fsx_xflags & FS_XFLAG_DAX) {
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
return -EINVAL;
- if (bdev_dax_supported(sb, sb->s_blocksize) < 0)
+ if (bdev_dax_supported(sb, xfs_find_bdev_for_inode(VFS_I(ip)),
+ sb->s_blocksize) < 0)
return -EINVAL;
}
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 56475fcd76f2..66cd61c172af 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -1182,6 +1182,30 @@ static const struct inode_operations xfs_inline_symlink_inode_operations = {
.update_time = xfs_vn_update_time,
};
+/* Figure out if this file actually supports DAX. */
+static bool
+xfs_inode_supports_dax(
+ struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = ip->i_mount;
+
+ /* Only supported on non-reflinked files. */
+ if (!S_ISREG(VFS_I(ip)->i_mode) || xfs_is_reflink_inode(ip))
+ return false;
+
+ /* DAX mount option or DAX iflag must be set. */
+ if (!(mp->m_flags & XFS_MOUNT_DAX) &&
+ !(ip->i_d.di_flags2 & XFS_DIFLAG2_DAX))
+ return false;
+
+ /* Block size must match page size */
+ if (mp->m_sb.sb_blocksize != PAGE_SIZE)
+ return false;
+
+ /* Device has to support DAX too. */
+ return xfs_find_daxdev_for_inode(VFS_I(ip)) != NULL;
+}
+
STATIC void
xfs_diflags_to_iflags(
struct inode *inode,
@@ -1200,11 +1224,7 @@ xfs_diflags_to_iflags(
inode->i_flags |= S_SYNC;
if (flags & XFS_DIFLAG_NOATIME)
inode->i_flags |= S_NOATIME;
- if (S_ISREG(inode->i_mode) &&
- ip->i_mount->m_sb.sb_blocksize == PAGE_SIZE &&
- !xfs_is_reflink_inode(ip) &&
- (ip->i_mount->m_flags & XFS_MOUNT_DAX ||
- ip->i_d.di_flags2 & XFS_DIFLAG2_DAX))
+ if (xfs_inode_supports_dax(ip))
inode->i_flags |= S_DAX;
}
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 7aba628dc527..f6c74ef9722c 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1657,11 +1657,18 @@ xfs_fs_fill_super(
sb->s_flags |= SB_I_VERSION;
if (mp->m_flags & XFS_MOUNT_DAX) {
+ int error2 = 0;
+
xfs_warn(mp,
"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
- error = bdev_dax_supported(sb, sb->s_blocksize);
- if (error) {
+ error = bdev_dax_supported(sb, mp->m_ddev_targp->bt_bdev,
+ sb->s_blocksize);
+ if (mp->m_rtdev_targp)
+ error2 = bdev_dax_supported(sb,
+ mp->m_rtdev_targp->bt_bdev,
+ sb->s_blocksize);
+ if (error && error2) {
xfs_alert(mp,
"DAX unsupported by block device. Turning off DAX.");
mp->m_flags &= ~XFS_MOUNT_DAX;
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 0185ecdae135..e640c8a19ec0 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -40,10 +40,11 @@ static inline void put_dax(struct dax_device *dax_dev)
int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
#if IS_ENABLED(CONFIG_FS_DAX)
-int __bdev_dax_supported(struct super_block *sb, int blocksize);
-static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
+int bdev_dax_supported(struct super_block *sb, struct block_device *bdev,
+ int blocksize);
+static inline int sb_dax_supported(struct super_block *sb, int blocksize)
{
- return __bdev_dax_supported(sb, blocksize);
+ return bdev_dax_supported(sb, sb->s_bdev, blocksize);
}
static inline struct dax_device *fs_dax_get_by_host(const char *host)
@@ -58,7 +59,14 @@ static inline void fs_put_dax(struct dax_device *dax_dev)
struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
#else
-static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
+static inline int bdev_dax_supported(struct super_block *sb,
+ struct block_device *bdev,
+ int blocksize)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int sb_dax_supported(struct super_block *sb, int blocksize)
{
return -EOPNOTSUPP;
}
> /**
> - * __bdev_dax_supported() - Check if the device supports dax for filesystem
> + * bdev_dax_supported() - Check if the device supports dax for filesystem
> * @sb: The superblock of the device
> + * @bdev: block device to check
> * @blocksize: The block size of the device
> *
> * This is a library function for filesystems to check if the block device
> @@ -82,9 +83,9 @@ EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
> *
> * Return: negative errno if unsupported, 0 if supported.
> */
> -int __bdev_dax_supported(struct super_block *sb, int blocksize)
> +int bdev_dax_supported(struct super_block *sb, struct block_device *bdev,
> + int blocksize)
> {
> - struct block_device *bdev = sb->s_bdev;
> struct dax_device *dax_dev;
> pgoff_t pgoff;
> int err, id;
This now only uses sb for sb->s_id. It might be better to use bdevname
to print the device name and don't bother passing a sb at all.
On 02/15/2018 10:52 AM, Christoph Hellwig wrote:
>> /**
>> - * __bdev_dax_supported() - Check if the device supports dax for filesystem
>> + * bdev_dax_supported() - Check if the device supports dax for filesystem
>> * @sb: The superblock of the device
>> + * @bdev: block device to check
>> * @blocksize: The block size of the device
>> *
>> * This is a library function for filesystems to check if the block device
>> @@ -82,9 +83,9 @@ EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
>> *
>> * Return: negative errno if unsupported, 0 if supported.
>> */
>> -int __bdev_dax_supported(struct super_block *sb, int blocksize)
>> +int bdev_dax_supported(struct super_block *sb, struct block_device *bdev,
>> + int blocksize)
>> {
>> - struct block_device *bdev = sb->s_bdev;
>> struct dax_device *dax_dev;
>> pgoff_t pgoff;
>> int err, id;
>
> This now only uses sb for sb->s_id. It might be better to use bdevname
> to print the device name and don't bother passing a sb at all.
>
I think Darrick wanted to keep the API the same for non-XFS users. I'm
ok with dropping the passed in sb if Darrick has no objections.
On Thu, Feb 15, 2018 at 10:58:54AM -0700, Dave Jiang wrote:
> I think Darrick wanted to keep the API the same for non-XFS users. I'm
> ok with dropping the passed in sb if Darrick has no objections.
But the old API is gone - everyone either uses the new
sb_dax_supported, or the updated bdev_dax_supported.
On Thu, Feb 15, 2018 at 10:58:54AM -0700, Dave Jiang wrote:
> On 02/15/2018 10:52 AM, Christoph Hellwig wrote:
> >> /**
> >> - * __bdev_dax_supported() - Check if the device supports dax for filesystem
> >> + * bdev_dax_supported() - Check if the device supports dax for filesystem
> >> * @sb: The superblock of the device
> >> + * @bdev: block device to check
> >> * @blocksize: The block size of the device
> >> *
> >> * This is a library function for filesystems to check if the block device
> >> @@ -82,9 +83,9 @@ EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
> >> *
> >> * Return: negative errno if unsupported, 0 if supported.
> >> */
> >> -int __bdev_dax_supported(struct super_block *sb, int blocksize)
> >> +int bdev_dax_supported(struct super_block *sb, struct block_device *bdev,
> >> + int blocksize)
> >> {
> >> - struct block_device *bdev = sb->s_bdev;
> >> struct dax_device *dax_dev;
> >> pgoff_t pgoff;
> >> int err, id;
> >
> > This now only uses sb for sb->s_id. It might be better to use bdevname
> > to print the device name and don't bother passing a sb at all.
> >
>
> I think Darrick wanted to keep the API the same for non-XFS users. I'm
> ok with dropping the passed in sb if Darrick has no objections.
Fine with me to use bdevname.
--D
> --
> To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
Hi Darrick,
I love your patch! Yet something to improve:
[auto build test ERROR on linus/master]
[also build test ERROR on v4.16-rc3 next-20180228]
[cannot apply to dgc-xfs/for-next]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Dave-Jiang/minimal-DAX-support-for-XFS-realtime-device/20180218-154220
config: i386-randconfig-c0-03010621 (attached as .config)
compiler: gcc-7 (Debian 7.3.0-1) 7.3.0
reproduce:
# save the attached .config to linux build tree
make ARCH=i386
All errors (new ones prefixed by >>):
>> drivers/dax/super.c:86:5: error: redefinition of 'bdev_dax_supported'
int bdev_dax_supported(struct super_block *sb, struct block_device *bdev,
^~~~~~~~~~~~~~~~~~
In file included from drivers/dax/super.c:23:0:
include/linux/dax.h:62:19: note: previous definition of 'bdev_dax_supported' was here
static inline int bdev_dax_supported(struct super_block *sb,
^~~~~~~~~~~~~~~~~~
vim +/bdev_dax_supported +86 drivers/dax/super.c
74
75 /**
76 * bdev_dax_supported() - Check if the device supports dax for filesystem
77 * @sb: The superblock of the device
78 * @bdev: block device to check
79 * @blocksize: The block size of the device
80 *
81 * This is a library function for filesystems to check if the block device
82 * can be mounted with dax option.
83 *
84 * Return: negative errno if unsupported, 0 if supported.
85 */
> 86 int bdev_dax_supported(struct super_block *sb, struct block_device *bdev,
87 int blocksize)
88 {
89 struct dax_device *dax_dev;
90 pgoff_t pgoff;
91 int err, id;
92 void *kaddr;
93 pfn_t pfn;
94 long len;
95
96 if (blocksize != PAGE_SIZE) {
97 pr_debug("VFS (%s): error: unsupported blocksize for dax\n",
98 sb->s_id);
99 return -EINVAL;
100 }
101
102 err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
103 if (err) {
104 pr_debug("VFS (%s): error: unaligned partition for dax\n",
105 sb->s_id);
106 return err;
107 }
108
109 dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
110 if (!dax_dev) {
111 pr_debug("VFS (%s): error: device does not support dax\n",
112 sb->s_id);
113 return -EOPNOTSUPP;
114 }
115
116 id = dax_read_lock();
117 len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
118 dax_read_unlock(id);
119
120 put_dax(dax_dev);
121
122 if (len < 1) {
123 pr_debug("VFS (%s): error: dax access failed (%ld)\n",
124 sb->s_id, len);
125 return len < 0 ? len : -EIO;
126 }
127
128 if ((IS_ENABLED(CONFIG_FS_DAX_LIMITED) && pfn_t_special(pfn))
129 || pfn_t_devmap(pfn))
130 /* pass */;
131 else {
132 pr_debug("VFS (%s): error: dax support not enabled\n",
133 sb->s_id);
134 return -EOPNOTSUPP;
135 }
136
137 return 0;
138 }
139 EXPORT_SYMBOL_GPL(bdev_dax_supported);
140 #endif
141
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation