[Codel] [Bloat] better tc support for bittorrent/diffserv

[Eric Dumazet]

On Mon, 2012-05-14 at 20:31 +0200, Eric Dumazet wrote:
> On Mon, 2012-05-14 at 20:24 +0200, Juliusz Chroboczek wrote:
> > > There is an API to set ECN on UDP packets.
> > >
> > > setsockopt() IP_TOS, with val = 2
> > 
> > Interesting, I didn't realise that.  Is it also possible to read the ECN
> > bits?
> 
> 
> Yep
> 
> man 7 ip
> 
>      IP_RECVTOS (since Linux 2.2)
>        If enabled the IP_TOS ancillary message is passed with incoming packets.
>       It contains a byte which specifies the Type of Service/Precedence field
>       of the packet header.  Expects a boolean integer flag.
> 
> 


Here is a quick and dirty UDP echo server (reflecting the TOS and
correct src address on multi homed host )

#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <linux/udp.h>
#include <string.h>
#include <stdio.h>
#include <unistd.h>
#include <arpa/inet.h>

#define PORT 4040

int pktinfo_get(struct msghdr *my_hdr, struct in_pktinfo *pktinfo)
{
	int res = -1;

	if (my_hdr->msg_controllen > 0) {
		struct cmsghdr *get_cmsg;
		for (get_cmsg = CMSG_FIRSTHDR(my_hdr); get_cmsg;
			get_cmsg = CMSG_NXTHDR(my_hdr, get_cmsg)) {
			if (get_cmsg->cmsg_type == IP_PKTINFO) {
				struct in_pktinfo *get_pktinfo = (struct in_pktinfo *)CMSG_DATA(get_cmsg);
				memcpy(pktinfo, get_pktinfo, sizeof(*pktinfo));
				res = 0;
			}
		}
	}
	return res;
}

int tos_get(struct msghdr *my_hdr, unsigned char *tos)
{
	int res = -1;

	if (my_hdr->msg_controllen > 0) {
		struct cmsghdr *get_cmsg;
		for (get_cmsg = CMSG_FIRSTHDR(my_hdr); get_cmsg;
			get_cmsg = CMSG_NXTHDR(my_hdr, get_cmsg)) {
			if (get_cmsg->cmsg_type == IP_TOS) {
				unsigned char *pkttos = (unsigned char *)CMSG_DATA(get_cmsg);
				*tos = *pkttos;
				res = 0;
			}
		}
	}
	return res;
}

int main(int argc, char *argv[])
{
	int fd = socket(AF_INET, SOCK_DGRAM, 0);
	struct sockaddr_in addr, rem_addr;
	int res, on = 1;
	struct msghdr msghdr;
	struct iovec vec[1];
	char cbuf[512];
	char frame[4096];
	struct in_pktinfo pktinfo;
	int c, count = 1000000;
	unsigned char last_tos = 0;

	while ((c = getopt(argc, argv, "c:")) != -1) {
		if (c == 'c') count = atoi(optarg);
		}
	memset(&addr, 0, sizeof(addr));
	addr.sin_family = AF_INET;
	addr.sin_port = htons(PORT);
	if (bind(fd, (struct sockaddr *)&addr, sizeof(addr)) == -1) {
		perror("bind");
		return 1;
	}
	setsockopt(fd, SOL_IP, IP_PKTINFO, &on, sizeof(on));
	setsockopt(fd, SOL_IP, IP_RECVTOS, &on, sizeof(on));

	while (1) {
		unsigned char tos;

		memset(&msghdr, 0, sizeof(msghdr));
		msghdr.msg_control = cbuf;
		msghdr.msg_controllen = sizeof(cbuf);
		msghdr.msg_iov = vec;
		msghdr.msg_iovlen = 1;
		vec[0].iov_base = frame;
		vec[0].iov_len = sizeof(frame);
		msghdr.msg_name = &rem_addr;
		msghdr.msg_namelen = sizeof(rem_addr);
		res = recvmsg(fd, &msghdr, 0);
		if (res == -1)
			break;
		if (pktinfo_get(&msghdr, &pktinfo) == 0) {

//			printf("Got IP_PKTINFO dst addr=%s\n", inet_ntoa(pktinfo.ipi_spec_dst));
			}
		if (tos_get(&msghdr, &tos) == 0) {
			/* IP_TOS option wont be used in sendmsg(), we must use setsockopt() instead */
			if (tos != last_tos) {
				if (setsockopt(fd, SOL_IP, IP_TOS, &tos, sizeof(tos)) == 0)
					last_tos = tos;
			}
		}
		/* ok, just echo reply this frame.
		 * Using sendmsg() will provide IP_PKTINFO back to kernel
		 * to let it use the 'right' source address
		 * (destination address of the incoming packet)
		 */
		vec[0].iov_len = res;
		sendmsg(fd, &msghdr, 0);
		if (--count == 0)
			break;
	}
	return 0;
}