[PATCH v3 04/15] fs: Add RWF_ATOMIC and IOCB_ATOMIC flags for atomic write support

[John Garry]

From: Prasad Singamsetty <prasad.singamsetty at oracle.com>

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.

Torn write prevention means that for a power or any other HW failure, all
or none of the data will be committed to storage, but never a mix of old
and new.

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:
- atomic_write_unit_min
- atomic_write_unit_max

Both values are 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.

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.

Signed-off-by: Prasad Singamsetty <prasad.singamsetty at oracle.com>
Signed-off-by: John Garry <john.g.garry at oracle.com>
---
 include/linux/fs.h      | 9 +++++++++
 include/uapi/linux/fs.h | 5 ++++-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index c316c0a92fff..95a7e2889d2c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -119,6 +119,10 @@ 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)0x40)
+
 /* 32bit hashes as llseek() offset (for directories) */
 #define FMODE_32BITHASH         ((__force fmode_t)0x200)
 /* 64bit hashes as llseek() offset (for directories) */
@@ -328,6 +332,7 @@ 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)
@@ -3344,6 +3349,10 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 			return -EOPNOTSUPP;
 		kiocb_flags |= IOCB_NOIO;
 	}
+	if (flags & RWF_ATOMIC) {
+		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;
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 48ad69f7722e..a0975ae81e64 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -301,9 +301,12 @@ 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)
 
 /* Pagemap ioctl */
 #define PAGEMAP_SCAN	_IOWR('f', 16, struct pm_scan_arg)
-- 
2.31.1