fix pwrite/pwritev handling of O_APPEND files

POSIX requires pwrite to honor the explicit file offset where the
write should take place even if the file was opened as O_APPEND.
however, linux historically defined the pwrite syscall family as
honoring O_APPEND. this cannot be changed on the kernel side due to
stability policy, but the addition of the pwritev2 syscall with a
flags argument opened the door to fixing it, and linux commit
73fa7547c70b32cc69685f79be31135797734eb6 adds the RWF_NOAPPEND flag
that lets us request a write honoring the file offset argument.

this patch changes the pwrite function to first attempt using the
pwritev2 syscall with RWF_NOAPPEND, falling back to using the old
pwrite syscall only after checking that O_APPEND is not set for the
open file. if O_APPEND is set, the operation fails with EOPNOTSUPP,
reflecting that the kernel does not support the correct behavior. this
is an extended error case needed to avoid the wrong behavior that
happened before (writing the data at the wrong location), and is
aligned with the spirit of the POSIX requirement that "An attempt to
perform a pwrite() on a file that is incapable of seeking shall result
in an error."

since the pwritev2 syscall interprets the offset of -1 as a request to
write at the current file offset, it is mapped to a different negative
value that will produce the expected error.

pwritev, though not governed by POSIX at this time, is adjusted to
match pwrite in honoring the offset.

2 files changed, 20 insertions, 1 deletions

diff --git a/src/unistd/pwrite.c b/src/unistd/pwrite.c
index 869b69f0..a008b3ec 100644
--- a/src/unistd/pwrite.c
+++ b/src/unistd/pwrite.c
@@ -1,7 +1,18 @@
+#define _GNU_SOURCE
 #include <unistd.h>
+#include <sys/uio.h>
+#include <fcntl.h>
 #include "syscall.h"
 
 ssize_t pwrite(int fd, const void *buf, size_t size, off_t ofs)
 {
+	if (ofs == -1) ofs--;
+	int r = __syscall_cp(SYS_pwritev2, fd,
+		(&(struct iovec){ .iov_base = (void *)buf, .iov_len = size }),
+		1, (long)(ofs), (long)(ofs>>32), RWF_NOAPPEND);
+	if (r != -EOPNOTSUPP && r != -ENOSYS)
+		return __syscall_ret(r);
+	if (fcntl(fd, F_GETFL) & O_APPEND)
+		return __syscall_ret(-EOPNOTSUPP);
 	return syscall_cp(SYS_pwrite, fd, buf, size, __SYSCALL_LL_PRW(ofs));
 }
diff --git a/src/unistd/pwritev.c b/src/unistd/pwritev.c
index becf9deb..44a53d85 100644
--- a/src/unistd/pwritev.c
+++ b/src/unistd/pwritev.c
@@ -1,10 +1,18 @@
-#define _BSD_SOURCE
+#define _GNU_SOURCE
 #include <sys/uio.h>
 #include <unistd.h>
+#include <fcntl.h>
 #include "syscall.h"
 
 ssize_t pwritev(int fd, const struct iovec *iov, int count, off_t ofs)
 {
+	if (ofs == -1) ofs--;
+	int r = __syscall_cp(SYS_pwritev2, fd, iov, count,
+		(long)(ofs), (long)(ofs>>32), RWF_NOAPPEND);
+	if (r != -EOPNOTSUPP && r != -ENOSYS)
+		return __syscall_ret(r);
+	if (fcntl(fd, F_GETFL) & O_APPEND)
+		return __syscall_ret(-EOPNOTSUPP);
 	return syscall_cp(SYS_pwritev, fd, iov, count,
 		(long)(ofs), (long)(ofs>>32));
 }