wrapper: properly handle MAX_IO_SIZE in writev(3p)

Some systems like NonStop set a comparatively small `MAX_IO_SIZE`, which
limits the maximum number of bytes we're allowed to write in a single
call. We already handle this limit properly in `xwrite()`, but we have
recently introduced wrappers for writev(3p) where we don't. This will
cause the syscall to return EINVAL in case somebody passes an iovec
entry to writev(3p) that is larger than `MAX_IO_SIZE`.

Introduce a new function `xwritev()` that is similar to `xwrite()` in
that it handles such platform-specific nuances:

  - We only pass the leading iovec entries to writev(3p) that fit into
    `MAX_IO_SIZE`, pretending that the underlying syscall performed a
    short write. This mirrors how `xwrite()` chomps overly large
    requests before handing them to write(3p). As a consequence, callers
    will never see writev(3p)'s EINVAL error for requests whose summed
    length would overflow an ssize_t, but observe a short write instead.

  - If already the first iovec entry exceeds the limit we instead punt
    to `xwrite()`, which knows to handle this case for us.

  - We restart the underlying syscall on EINTR and EAGAIN, just like
    `xwrite()` does for write(3p).

Adapt `writev_in_full()` to use this new wrapper. With the retry logic
now living in `xwritev()`, the calling loop becomes the exact mirror
image of `write_in_full()`, which also retains the responsibility of
translating a zero-length write into ENOSPC.

Reported-by: Randall Becker <randall.becker@nexbridge.ca>
Helped-by: Jeff King <peff@peff.net>
Helped-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/wrapper.c b/wrapper.c
index be8fa575e6f4255998b23699cb6ba743d8f4866e..561f9ee9c99fc1a88b083619f60f191321b53e25 100644 (file)
--- a/wrapper.c
+++ b/wrapper.c
@@ -323,17 +323,54 @@ ssize_t write_in_full(int fd, const void *buf, size_t count)
        return total;
 }
 
+ssize_t xwritev(int fd, struct iovec *iov, int iovcnt)
+{
+       size_t allowed = MAX_IO_SIZE;
+       int i;
+
+       /*
+        * Some platforms define a comparatively small `MAX_IO_SIZE` that
+        * limits how many bytes can be written with a single call to
+        * write(3p) or writev(3p); exceeding that limit causes the syscall to
+        * fail with EINVAL. Just like xwrite() chomps overly large requests
+        * for write(3p), pretend that the underlying writev(3p) performed a
+        * short write by only passing along the leading iovec entries that
+        * fit into that limit.
+        */
+       for (i = 0; i < iovcnt; i++) {
+               if (iov[i].iov_len > allowed) {
+                       /*
+                        * If the first buffer is larger than MAX_IO_SIZE,
+                        * let xwrite() deal with it.
+                        */
+                       if (!i)
+                               return xwrite(fd, iov->iov_base, iov->iov_len);
+                       break;
+               }
+               allowed -= iov[i].iov_len;
+       }
+
+       while (1) {
+               ssize_t bytes_written = writev(fd, iov, i);
+               if (bytes_written < 0) {
+                       if (errno == EINTR)
+                               continue;
+                       if (handle_nonblock(fd, POLLOUT, errno))
+                               continue;
+               }
+
+               return bytes_written;
+       }
+}
+
 ssize_t writev_in_full(int fd, struct iovec *iov, int iovcnt)
 {
        ssize_t total_written = 0;
 
        while (iovcnt) {
-               ssize_t bytes_written = writev(fd, iov, iovcnt);
-               if (bytes_written < 0) {
-                       if (errno == EINTR || errno == EAGAIN)
-                               continue;
+               ssize_t bytes_written = xwritev(fd, iov, iovcnt);
+               if (bytes_written < 0)
                        return -1;
-               }
                if (!bytes_written) {
                        errno = ENOSPC;
                        return -1;

diff --git a/wrapper.h b/wrapper.h
index 27519b32d1782db10411c62ead9d066b5ff2a325..a6287d7f4d11be9a82c0a118907fb9ee4866ec14 100644 (file)
--- a/wrapper.h
+++ b/wrapper.h
@@ -16,6 +16,7 @@ void *xmmap_gently(void *start, size_t length, int prot, int flags, int fd, off_
 int xopen(const char *path, int flags, ...);
 ssize_t xread(int fd, void *buf, size_t len);
 ssize_t xwrite(int fd, const void *buf, size_t len);
+ssize_t xwritev(int fd, struct iovec *iov, int iovcnt);
 ssize_t xpread(int fd, void *buf, size_t len, off_t offset);
 int xdup(int fd);
 FILE *xfopen(const char *path, const char *mode);