From efbe3c2493d2f7a1e1a753780fe727b34709ebd2 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 30 Apr 2020 07:41:33 -0700 Subject: [PATCH 1/3] fs: Remove unneeded IS_DAX() check in io_is_direct() Remove the check because DAX now has it's own read/write methods and file systems which support DAX check IS_DAX() prior to IOCB_DIRECT on their own. Therefore, it does not matter if the file state is DAX when the iocb flags are created. Also remove io_is_direct() as it is just a simple flag check. Reviewed-by: Dave Chinner Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Ira Weiny Signed-off-by: Darrick J. Wong --- drivers/block/loop.c | 6 +++--- include/linux/fs.h | 7 +------ 2 files changed, 4 insertions(+), 9 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index da693e6a834e..14372df0f354 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -634,8 +634,8 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) static inline void loop_update_dio(struct loop_device *lo) { - __loop_update_dio(lo, io_is_direct(lo->lo_backing_file) | - lo->use_dio); + __loop_update_dio(lo, (lo->lo_backing_file->f_flags & O_DIRECT) | + lo->use_dio); } static void loop_reread_partitions(struct loop_device *lo, @@ -1028,7 +1028,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) blk_queue_write_cache(lo->lo_queue, true, false); - if (io_is_direct(lo->lo_backing_file) && inode->i_sb->s_bdev) { + if ((lo->lo_backing_file->f_flags & O_DIRECT) && inode->i_sb->s_bdev) { /* In case of direct I/O, match underlying block size */ unsigned short bsize = bdev_logical_block_size( inode->i_sb->s_bdev); diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..a87cc5845a02 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3394,11 +3394,6 @@ extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); -static inline bool io_is_direct(struct file *filp) -{ - return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); -} - static inline bool vma_is_dax(const struct vm_area_struct *vma) { return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); @@ -3423,7 +3418,7 @@ static inline int iocb_flags(struct file *file) int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; - if (io_is_direct(file)) + if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host)) res |= IOCB_DSYNC; From 712b2698e4c024b561694cbcc1abba13eb0fd9ce Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 30 Apr 2020 07:41:34 -0700 Subject: [PATCH 2/3] fs/stat: Define DAX statx attribute In order for users to determine if a file is currently operating in DAX state (effective DAX). Define a statx attribute value and set that attribute if the effective DAX flag is set. To go along with this we propose the following addition to the statx man page: STATX_ATTR_DAX The file is in the DAX (cpu direct access) state. DAX state attempts to minimize software cache effects for both I/O and memory mappings of this file. It requires a file system which has been configured to support DAX. DAX generally assumes all accesses are via cpu load / store instructions which can minimize overhead for small accesses, but may adversely affect cpu utilization for large transfers. File I/O is done directly to/from user-space buffers and memory mapped I/O may be performed with direct memory mappings that bypass kernel page cache. While the DAX property tends to result in data being transferred synchronously, it does not give the same guarantees of O_SYNC where data and the necessary metadata are transferred together. A DAX file may support being mapped with the MAP_SYNC flag, which enables a program to use CPU cache flush instructions to persist CPU store operations without an explicit fsync(2). See mmap(2) for more information. Reviewed-by: Dave Chinner Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Signed-off-by: Ira Weiny Signed-off-by: Darrick J. Wong --- fs/stat.c | 3 +++ include/uapi/linux/stat.h | 1 + 2 files changed, 4 insertions(+) diff --git a/fs/stat.c b/fs/stat.c index 030008796479..894699c74dde 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -79,6 +79,9 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, if (IS_AUTOMOUNT(inode)) stat->attributes |= STATX_ATTR_AUTOMOUNT; + if (IS_DAX(inode)) + stat->attributes |= STATX_ATTR_DAX; + if (inode->i_op->getattr) return inode->i_op->getattr(path, stat, request_mask, query_flags); diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index ad80a5c885d5..e5f9d5517f6b 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -169,6 +169,7 @@ struct statx { #define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ +#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */ #endif /* _UAPI_LINUX_STAT_H */ From 83d9088659e8f113741bb197324bd9554d159657 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 30 Apr 2020 07:41:34 -0700 Subject: [PATCH 3/3] Documentation/dax: Update Usage section Update the Usage section to reflect the new individual dax selection functionality. Signed-off-by: Ira Weiny Acked-by: Randy Dunlap Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- Documentation/filesystems/dax.txt | 142 +++++++++++++++++++++++++++++- 1 file changed, 139 insertions(+), 3 deletions(-) diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt index 679729442fd2..735fb4b54117 100644 --- a/Documentation/filesystems/dax.txt +++ b/Documentation/filesystems/dax.txt @@ -20,8 +20,144 @@ Usage If you have a block device which supports DAX, you can make a filesystem on it as usual. The DAX code currently only supports files with a block size equal to your kernel's PAGE_SIZE, so you may need to specify a block -size when creating the filesystem. When mounting it, use the "-o dax" -option on the command line or add 'dax' to the options in /etc/fstab. +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 +----------------------------- + +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 +------------------- + +Summary +------- + + 1. There exists an in-kernel file access mode flag S_DAX that corresponds to + the statx flag STATX_ATTR_DAX. See the manpage for statx(2) for details + about this access mode. + + 2. There exists a persistent flag FS_XFLAG_DAX that can be applied to regular + files and directories. This advisory flag can be set or cleared at any + time, but doing so does not immediately affect the S_DAX state. + + 3. If the persistent FS_XFLAG_DAX flag is set on a directory, this flag will + be inherited by all regular files and subdirectories that are subsequently + created in this directory. Files and subdirectories that exist at the time + this flag is set or cleared on the parent directory are not modified by + this modification of the parent directory. + + 4. There exist dax mount options which can override FS_XFLAG_DAX in the + setting of the S_DAX flag. Given underlying storage which supports DAX the + following hold: + + "-o dax=inode" means "follow FS_XFLAG_DAX" and is the default. + + "-o dax=never" means "never set S_DAX, ignore FS_XFLAG_DAX." + + "-o dax=always" means "always set S_DAX ignore FS_XFLAG_DAX." + + "-o dax" is a legacy option which is an alias for "dax=always". + This may be removed in the future so "-o dax=always" is + the preferred method for specifying this behavior. + + NOTE: Modifications to and the inheritance behavior of FS_XFLAG_DAX remain + the same even when the filesystem is mounted with a dax option. However, + in-core inode state (S_DAX) will be overridden until the filesystem is + remounted with dax=inode and the inode is evicted from kernel memory. + + 5. The S_DAX policy can be changed via: + + a) Setting the parent directory FS_XFLAG_DAX as needed before files are + created + + b) Setting the appropriate dax="foo" mount option + + c) Changing the FS_XFLAG_DAX flag on existing regular files and + directories. This has runtime constraints and limitations that are + described in 6) below. + + 6. When changing the S_DAX policy via toggling the persistent FS_XFLAG_DAX flag, + the change in behaviour for existing regular files may not occur + immediately. If the change must take effect immediately, the administrator + needs to: + + a) stop the application so there are no active references to the data set + the policy change will affect + + b) evict the data set from kernel caches so it will be re-instantiated when + the application is restarted. This can be achieved by: + + i. drop-caches + ii. a filesystem unmount and mount cycle + iii. a system reboot + + +Details +------- + +There are 2 per-file dax flags. One is a persistent inode setting (FS_XFLAG_DAX) +and the other is a volatile flag indicating the active state of the feature +(S_DAX). + +FS_XFLAG_DAX is preserved within the filesystem. This persistent config +setting can be set, cleared and/or queried using the FS_IOC_FS[GS]ETXATTR ioctl +(see ioctl_xfs_fsgetxattr(2)) or an utility such as 'xfs_io'. + +New files and directories automatically inherit FS_XFLAG_DAX from +their parent directory _when_ _created_. Therefore, setting FS_XFLAG_DAX at +directory creation time can be used to set a default behavior for an entire +sub-tree. + +To clarify inheritance, here are 3 examples: + +Example A: + +mkdir -p a/b/c +xfs_io -c 'chattr +x' a +mkdir a/b/c/d +mkdir a/e + + dax: a,e + no dax: b,c,d + +Example B: + +mkdir a +xfs_io -c 'chattr +x' a +mkdir -p a/b/c/d + + dax: a,b,c,d + no dax: + +Example C: + +mkdir -p a/b/c +xfs_io -c 'chattr +x' c +mkdir a/b/c/d + + dax: c,d + no dax: a,b + + +The current enabled state (S_DAX) is set when a file inode is instantiated in +memory by the kernel. It is set based on the underlying media support, the +value of FS_XFLAG_DAX and the filesystem's dax mount option. + +statx can be used to query S_DAX. NOTE that only regular files will ever have +S_DAX set and therefore statx will never indicate that S_DAX is set on +directories. + +Setting the FS_XFLAG_DAX flag (specifically or through inheritance) occurs even +if the underlying media does not support dax and/or the filesystem is +overridden with a mount option. + Implementation Tips for Block Driver Writers @@ -94,7 +230,7 @@ sysadmins have an option to restore the lost data from a prior backup/inbuilt redundancy in the following ways: 1. Delete the affected file, and restore from a backup (sysadmin route): - This will free the file system blocks that were being used by the file, + This will free the filesystem blocks that were being used by the file, and the next time they're allocated, they will be zeroed first, which happens through the driver, and will clear bad sectors.