splice: sendfile() at once fails for big files

Using sendfile with below small program to get MD5 sums of some files,
it appear that big files (over 64kbytes with 4k pages system) get a
wrong MD5 sum while small files get the correct sum.
This program uses sendfile() to send a file to an AF_ALG socket
for hashing.

/* md5sum2.c */
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <string.h>
#include <fcntl.h>
#include <sys/socket.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <linux/if_alg.h>

int main(int argc, char **argv)
{
	int sk = socket(AF_ALG, SOCK_SEQPACKET, 0);
	struct stat st;
	struct sockaddr_alg sa = {
		.salg_family = AF_ALG,
		.salg_type = "hash",
		.salg_name = "md5",
	};
	int n;

	bind(sk, (struct sockaddr*)&sa, sizeof(sa));

	for (n = 1; n < argc; n++) {
		int size;
		int offset = 0;
		char buf[4096];
		int fd;
		int sko;
		int i;

		fd = open(argv[n], O_RDONLY);
		sko = accept(sk, NULL, 0);
		fstat(fd, &st);
		size = st.st_size;
		sendfile(sko, fd, &offset, size);
		size = read(sko, buf, sizeof(buf));
		for (i = 0; i < size; i++)
			printf("%2.2x", buf[i]);
		printf("  %s\n", argv[n]);
		close(fd);
		close(sko);
	}
	exit(0);
}

Test below is done using official linux patch files. First result is
with a software based md5sum. Second result is with the program above.

root@vgoip:~# ls -l patch-3.6.*
-rw-r--r--    1 root     root         64011 Aug 24 12:01 patch-3.6.2.gz
-rw-r--r--    1 root     root         94131 Aug 24 12:01 patch-3.6.3.gz

root@vgoip:~# md5sum patch-3.6.*
b3ffb9848196846f31b2ff133d2d6443  patch-3.6.2.gz
c5e8f687878457db77cb7158c38a7e43  patch-3.6.3.gz

root@vgoip:~# ./md5sum2 patch-3.6.*
b3ffb9848196846f31b2ff133d2d6443  patch-3.6.2.gz
5fd77b24e68bb24dcc72d6e57c64790e  patch-3.6.3.gz

After investivation, it appears that sendfile() sends the files by blocks
of 64kbytes (16 times PAGE_SIZE). The problem is that at the end of each
block, the SPLICE_F_MORE flag is missing, therefore the hashing operation
is reset as if it was the end of the file.

This patch adds SPLICE_F_MORE to the flags when more data is pending.

With the patch applied, we get the correct sums:

root@vgoip:~# md5sum patch-3.6.*
b3ffb9848196846f31b2ff133d2d6443  patch-3.6.2.gz
c5e8f687878457db77cb7158c38a7e43  patch-3.6.3.gz

root@vgoip:~# ./md5sum2 patch-3.6.*
b3ffb9848196846f31b2ff133d2d6443  patch-3.6.2.gz
c5e8f687878457db77cb7158c38a7e43  patch-3.6.3.gz

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Jens Axboe <axboe@fb.com>
This commit is contained in:
Christophe Leroy 2015-05-06 17:26:47 +02:00 committed by Jens Axboe
parent 9ba52e5812
commit 0ff28d9f46

View file

@ -1161,7 +1161,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
long ret, bytes; long ret, bytes;
umode_t i_mode; umode_t i_mode;
size_t len; size_t len;
int i, flags; int i, flags, more;
/* /*
* We require the input being a regular file, as we don't want to * We require the input being a regular file, as we don't want to
@ -1204,6 +1204,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
* Don't block on output, we have to drain the direct pipe. * Don't block on output, we have to drain the direct pipe.
*/ */
sd->flags &= ~SPLICE_F_NONBLOCK; sd->flags &= ~SPLICE_F_NONBLOCK;
more = sd->flags & SPLICE_F_MORE;
while (len) { while (len) {
size_t read_len; size_t read_len;
@ -1216,6 +1217,15 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
read_len = ret; read_len = ret;
sd->total_len = read_len; sd->total_len = read_len;
/*
* If more data is pending, set SPLICE_F_MORE
* If this is the last data and SPLICE_F_MORE was not set
* initially, clears it.
*/
if (read_len < len)
sd->flags |= SPLICE_F_MORE;
else if (!more)
sd->flags &= ~SPLICE_F_MORE;
/* /*
* NOTE: nonblocking mode only applies to the input. We * NOTE: nonblocking mode only applies to the input. We
* must not do the output in nonblocking mode as then we * must not do the output in nonblocking mode as then we