From: Prasad Singamsetty <prasad.singamsetty@oracle.com> mainline inclusion from mainline-v6.10-rc3 commit c34fc6f26ab86d03a2d47446f42b6cd492dfdc56 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ID2HML CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- An atomic write is a write issued with torn-write protection, meaning that for a power failure or any other hardware failure, all or none of the data from the write will be stored, but never a mix of old and new data. Userspace may add flag RWF_ATOMIC to pwritev2() to indicate that the write is to be issued with torn-write prevention, according to special alignment and length rules. For any syscall interface utilizing struct iocb, add IOCB_ATOMIC for iocb->ki_flags field to indicate the same. A call to statx will give the relevant atomic write info for a file: - atomic_write_unit_min - atomic_write_unit_max - atomic_write_segments_max Both min and max values must be a power-of-2. Applications can avail of atomic write feature by ensuring that the total length of a write is a power-of-2 in size and also sized between atomic_write_unit_min and atomic_write_unit_max, inclusive. Applications must ensure that the write is at a naturally-aligned offset in the file wrt the total write length. The value in atomic_write_segments_max indicates the upper limit for IOV_ITER iovcnt. Add file mode flag FMODE_CAN_ATOMIC_WRITE, so files which do not have the flag set will have RWF_ATOMIC rejected and not just ignored. Add a type argument to kiocb_set_rw_flags() to allows reads which have RWF_ATOMIC set to be rejected. Helper function generic_atomic_write_valid() can be used by FSes to verify compliant writes. There we check for iov_iter type is for ubuf, which implies iovcnt==1 for pwritev2(), which is an initial restriction for atomic_write_segments_max. Initially the only user will be bdev file operations write handler. We will rely on the block BIO submission path to ensure write sizes are compliant for the bdev, so we don't need to check atomic writes sizes yet. Signed-off-by: Prasad Singamsetty <prasad.singamsetty@oracle.com> jpg: merge into single patch and much rewrite Acked-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-4-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk> Conflicts: fs/read_write.c include/linux/fs.h include/uapi/linux/fs.h io_uring/rw.c Signed-off-by: Long Li <leo.lilong@huawei.com> --- fs/aio.c | 8 ++++---- fs/btrfs/ioctl.c | 2 +- fs/read_write.c | 18 +++++++++++++++++- include/linux/fs.h | 15 ++++++++++++++- include/uapi/linux/fs.h | 5 ++++- io_uring/rw.c | 8 ++++---- 6 files changed, 44 insertions(+), 12 deletions(-) diff --git a/fs/aio.c b/fs/aio.c index c3614193d749..3b5d6f65a758 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1467,7 +1467,7 @@ static void aio_complete_rw(struct kiocb *kiocb, long res) iocb_put(iocb); } -static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) +static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb, int rw_type) { int ret; @@ -1493,7 +1493,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) } else req->ki_ioprio = get_current_ioprio(); - ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags); + ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags, rw_type); if (unlikely(ret)) return ret; @@ -1545,7 +1545,7 @@ static int aio_read(struct kiocb *req, const struct iocb *iocb, struct file *file; int ret; - ret = aio_prep_rw(req, iocb); + ret = aio_prep_rw(req, iocb, READ); if (ret) return ret; file = req->ki_filp; @@ -1572,7 +1572,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb, struct file *file; int ret; - ret = aio_prep_rw(req, iocb); + ret = aio_prep_rw(req, iocb, WRITE); if (ret) return ret; file = req->ki_filp; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3d1cb018f3c4..5487b35bc78e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4569,7 +4569,7 @@ static int btrfs_ioctl_encoded_write(struct file *file, void __user *argp, bool goto out_iov; init_sync_kiocb(&kiocb, file); - ret = kiocb_set_rw_flags(&kiocb, 0); + ret = kiocb_set_rw_flags(&kiocb, 0, WRITE); if (ret) goto out_iov; kiocb.ki_pos = pos; diff --git a/fs/read_write.c b/fs/read_write.c index 27a7729b82f3..c3d0c8d7dd24 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -726,7 +726,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, ssize_t ret; init_sync_kiocb(&kiocb, filp); - ret = kiocb_set_rw_flags(&kiocb, flags); + ret = kiocb_set_rw_flags(&kiocb, flags, type); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); @@ -1766,6 +1766,22 @@ int generic_file_rw_checks(struct file *file_in, struct file *file_out) return 0; } +bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos) +{ + size_t len = iov_iter_count(iter); + + if (!iter_is_ubuf(iter)) + return false; + + if (!is_power_of_2(len)) + return false; + + if (!IS_ALIGNED(pos, len)) + return false; + + return true; +} + #ifdef CONFIG_BPF_READAHEAD static void fs_file_read_ctx_init(struct fs_file_read_ctx *ctx, struct file *filp, loff_t pos) diff --git a/include/linux/fs.h b/include/linux/fs.h index 8dd49c400ec0..facd1aa99f97 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -127,6 +127,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_PWRITE ((__force fmode_t)0x10) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)0x20) +/* File supports atomic writes */ +#define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(0x80)) /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)0x200) /* 64bit hashes as llseek() offset (for directories) */ @@ -347,6 +349,7 @@ enum rw_hint { #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND +#define IOCB_ATOMIC (__force int) RWF_ATOMIC /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) @@ -381,6 +384,7 @@ enum rw_hint { { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ + { IOCB_ATOMIC, "ATOMIC"}, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ @@ -3409,7 +3413,8 @@ static inline int iocb_flags(struct file *file) return res; } -static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, + int rw_type) { int kiocb_flags = 0; @@ -3426,6 +3431,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) return -EOPNOTSUPP; kiocb_flags |= IOCB_NOIO; } + if (flags & RWF_ATOMIC) { + if (rw_type != WRITE) + return -EOPNOTSUPP; + if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) + return -EOPNOTSUPP; + } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; @@ -3658,4 +3669,6 @@ static inline bool cachefiles_ondemand_is_enabled(void) } #endif +bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos); + #endif /* _LINUX_FS_H */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index b7b56871029c..d88bb0c3a048 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -301,8 +301,11 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO O_APPEND */ #define RWF_APPEND ((__force __kernel_rwf_t)0x00000010) +/* Atomic Write */ +#define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND) + RWF_APPEND | RWF_ATOMIC) #endif /* _UAPI_LINUX_FS_H */ diff --git a/io_uring/rw.c b/io_uring/rw.c index 75b001febb4d..d6190532f64b 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -660,7 +660,7 @@ static bool need_complete_io(struct io_kiocb *req) S_ISBLK(file_inode(req->file)->i_mode); } -static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) +static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type) { struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); struct kiocb *kiocb = &rw->kiocb; @@ -675,7 +675,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) req->flags |= io_file_get_flags(file); kiocb->ki_flags = file->f_iocb_flags; - ret = kiocb_set_rw_flags(kiocb, rw->flags); + ret = kiocb_set_rw_flags(kiocb, rw->flags, rw_type); if (unlikely(ret)) return ret; kiocb->ki_flags |= IOCB_ALLOC_CACHE; @@ -743,7 +743,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } - ret = io_rw_init_file(req, FMODE_READ); + ret = io_rw_init_file(req, FMODE_READ, READ); if (unlikely(ret)) { kfree(iovec); return ret; @@ -918,7 +918,7 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } - ret = io_rw_init_file(req, FMODE_WRITE); + ret = io_rw_init_file(req, FMODE_WRITE, WRITE); if (unlikely(ret)) { kfree(iovec); return ret; -- 2.39.2