vfs: add RWF_NOAPPEND flag for pwritev2

The pwrite function, originally defined by POSIX (thus the "p"), is
defined to ignore O_APPEND and write at the offset passed as its
argument. However, historically Linux honored O_APPEND if set and
ignored the offset. This cannot be changed due to stability policy,
but is documented in the man page as a bug.

Now that there's a pwritev2 syscall providing a superset of the pwrite
functionality that has a flags argument, the conforming behavior can
be offered to userspace via a new flag. Since pwritev2 checks flag
validity (in kiocb_set_rw_flags) and reports unknown ones with
EOPNOTSUPP, callers will not get wrong behavior on old kernels that
don't support the new flag; the error is reported and the caller can
decide how to handle it.

Signed-off-by: Rich Felker <dalias@libc.org>
Link: https://lore.kernel.org/r/20200831153207.GO3265@brightrain.aerifal.cx
Reviewed-by: Jann Horn <jannh@google.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>

diff --git a/include/linux/fs.h b/include/linux/fs.h
index ed5966a70495129be1d6729eed2918240db62df1..4f7cfda29143e2b0f4c47bfac14141acccc85fec 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3335,6 +3335,8 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
                return 0;
        if (unlikely(flags & ~RWF_SUPPORTED))
                return -EOPNOTSUPP;
+       if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND)))
+               return -EINVAL;
 
        if (flags & RWF_NOWAIT) {
                if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
@@ -3345,6 +3347,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
        if (flags & RWF_SYNC)
                kiocb_flags |= IOCB_DSYNC;
 
+       if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) {
+               if (IS_APPEND(file_inode(ki->ki_filp)))
+                       return -EPERM;
+               ki->ki_flags &= ~IOCB_APPEND;
+       }
+
        ki->ki_flags |= kiocb_flags;
        return 0;
 }

diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 48ad69f7722e1ae51ae5871a06482b6aa45dfc18..2203d3194b91a798b21131bd5886b0d071c5cc0b 100644 (file)
--- 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)
 
+/* per-IO negation of O_APPEND */
+#define RWF_NOAPPEND   ((__force __kernel_rwf_t)0x00000020)
+
 /* mask of flags supported by the kernel */
 #define RWF_SUPPORTED  (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
-                        RWF_APPEND)
+                        RWF_APPEND | RWF_NOAPPEND)
 
 /* Pagemap ioctl */
 #define PAGEMAP_SCAN   _IOWR('f', 16, struct pm_scan_arg)