qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Jason Wang <jasowang@redhat.com>
To: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>,
	qemu devel <qemu-devel@nongnu.org>
Cc: Li Zhijian <lizhijian@cn.fujitsu.com>,
	"eddie . dong" <eddie.dong@intel.com>,
	zhanghailiang <zhang.zhanghailiang@huawei.com>,
	"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
	Yang Hongyang <hongyang.yang@easystack.cn>
Subject: Re: [Qemu-devel] [RFC PATCH 3/3] filter-rewriter: rewrite tcp packet to keep secondary connection
Date: Mon, 20 Jun 2016 14:27:38 +0800	[thread overview]
Message-ID: <57678CDA.7020700@redhat.com> (raw)
In-Reply-To: <1465902912-27527-4-git-send-email-zhangchen.fnst@cn.fujitsu.com>



On 2016年06月14日 19:15, Zhang Chen wrote:
> We will rewrite tcp packet secondary received and sent.

More verbose please. E.g which fields were rewrote and why.

> Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
> Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
> ---
>   net/filter-rewriter.c | 94 +++++++++++++++++++++++++++++++++++++++++++++++++--
>   trace-events          |  3 ++
>   2 files changed, 95 insertions(+), 2 deletions(-)
>
> diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
> index 12f88c5..86a2f53 100644
> --- a/net/filter-rewriter.c
> +++ b/net/filter-rewriter.c
> @@ -21,6 +21,7 @@
>   #include "qemu/main-loop.h"
>   #include "qemu/iov.h"
>   #include "net/checksum.h"
> +#include "trace.h"
>   
>   #define FILTER_COLO_REWRITER(obj) \
>       OBJECT_CHECK(RewriterState, (obj), TYPE_FILTER_REWRITER)
> @@ -64,6 +65,75 @@ static int is_tcp_packet(Packet *pkt)
>       }
>   }
>   
> +static int handle_primary_tcp_pkt(NetFilterState *nf,
> +                                  Connection *conn,
> +                                  Packet *pkt)
> +{
> +    struct tcphdr *tcp_pkt;
> +
> +    tcp_pkt = (struct tcphdr *)pkt->transport_layer;
> +
> +    if (trace_event_get_state(TRACE_COLO_FILTER_REWRITER_DEBUG)) {

Why not use tracepoints directly?

> +        char *sdebug, *ddebug;
> +        sdebug = strdup(inet_ntoa(pkt->ip->ip_src));
> +        ddebug = strdup(inet_ntoa(pkt->ip->ip_dst));
> +        fprintf(stderr, "%s: src/dst: %s/%s p: seq/ack=%u/%u"
> +                "  flags=%x\n", __func__, sdebug, ddebug,
> +                ntohl(tcp_pkt->th_seq), ntohl(tcp_pkt->th_ack),
> +                tcp_pkt->th_flags);
> +        g_free(sdebug);
> +        g_free(ddebug);
> +    }
> +
> +    if (((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == TH_ACK)) {
> +        /* save primary colo tcp packet seq */
> +        conn->primary_seq = ntohl(tcp_pkt->th_ack) - 1;

Looks like primary_seq will only be updated during handshake, I wonder 
how this works.

> +
> +        /* adjust tcp seq to make secondary guest handle it */
> +        tcp_pkt->th_ack = htonl(conn->secondary_seq + 1);

I'm not sure this can work for all cases. I believe we should also 
rewrite seq here. And to me, a better approach is to track the offset of 
seq between pri and sec during handshake and rewrite both ack and seq 
based on this offset.

> +        net_checksum_calculate((uint8_t *)pkt->data, pkt->size);
> +    }
> +
> +    return 0;
> +}
> +
> +static int handle_secondary_tcp_pkt(NetFilterState *nf,
> +                                    Connection *conn,
> +                                    Packet *pkt)
> +{
> +    struct tcphdr *tcp_pkt;
> +
> +    tcp_pkt = (struct tcphdr *)pkt->transport_layer;
> +
> +    if (trace_event_get_state(TRACE_COLO_FILTER_REWRITER_DEBUG)) {
> +        char *sdebug, *ddebug;
> +        sdebug = strdup(inet_ntoa(pkt->ip->ip_src));
> +        ddebug = strdup(inet_ntoa(pkt->ip->ip_dst));
> +        printf("handle_secondary_tcp_pkt conn->secondary_seq = %u,\n",
> +               conn->secondary_seq);
> +        printf("handle_secondary_tcp_pkt conn->primary_seq = %u,\n",
> +               conn->primary_seq);
> +        fprintf(stderr, "%s: src/dst: %s/%s p: seq/ack=%u/%u"
> +                "  flags=%x\n", __func__, sdebug, ddebug,
> +                ntohl(tcp_pkt->th_seq), ntohl(tcp_pkt->th_ack),
> +                tcp_pkt->th_flags);
> +        g_free(sdebug);
> +        g_free(ddebug);
> +    }
> +
> +    if (((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == (TH_ACK | TH_SYN))) {
> +        /* save client's seq */
> +        conn->secondary_seq = ntohl(tcp_pkt->th_seq);
> +    }
> +
> +    if ((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == TH_ACK) {
> +        tcp_pkt->th_seq = htonl(conn->primary_seq + 1);
> +        net_checksum_calculate((uint8_t *)pkt->data, pkt->size);
> +    }
> +
> +    return 0;
> +}
> +
>   static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
>                                            NetClientState *sender,
>                                            unsigned flags,
> @@ -106,10 +176,30 @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
>           if (sender == nf->netdev) {
>               /* This packet is sent by netdev itself */
>               /* NET_FILTER_DIRECTION_TX */
> -            /* handle_primary_tcp_pkt */
> +            if (!handle_primary_tcp_pkt(nf, conn, pkt)) {
> +                qemu_net_queue_send(s->incoming_queue, sender, 0,
> +                (const uint8_t *)pkt->data, pkt->size, NULL);
> +                packet_destroy(pkt, NULL);
> +                pkt = NULL;
> +                /*
> +                 * We block the packet here,after rewrite pkt
> +                 * and will send it
> +                 */
> +                return 1;
> +            }
>           } else {
>               /* NET_FILTER_DIRECTION_RX */
> -            /* handle_secondary_tcp_pkt */
> +            if (!handle_secondary_tcp_pkt(nf, conn, pkt)) {
> +                qemu_net_queue_send(s->incoming_queue, sender, 0,
> +                (const uint8_t *)pkt->data, pkt->size, NULL);
> +                packet_destroy(pkt, NULL);
> +                pkt = NULL;
> +                /*
> +                 * We block the packet here,after rewrite pkt
> +                 * and will send it
> +                 */
> +                return 1;
> +            }
>           }
>       }
>   
> diff --git a/trace-events b/trace-events
> index 6686cdf..5d798c6 100644
> --- a/trace-events
> +++ b/trace-events
> @@ -1927,3 +1927,6 @@ colo_compare_icmp_miscompare_mtu(const char *sta, int size) ": %s  %d"
>   colo_compare_ip_info(int psize, const char *sta, const char *stb, int ssize, const char *stc, const char *std) "ppkt size = %d, ip_src = %s, ip_dst = %s, spkt size = %d, ip_src = %s, ip_dst = %s"
>   colo_old_packet_check_found(int64_t old_time) "%" PRId64
>   colo_compare_miscompare(void) ""
> +
> +# net/filter-rewriter.c
> +colo_filter_rewriter_debug(void) ""

  reply	other threads:[~2016-06-20  6:27 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-14 11:15 [Qemu-devel] [RFC PATCH 0/3] filter-rewriter: introduce filter-rewriter Zhang Chen
2016-06-14 11:15 ` [Qemu-devel] [RFC PATCH 1/3] filter-rewriter: introduce filter-rewriter initialization Zhang Chen
2016-06-14 11:15 ` [Qemu-devel] [RFC PATCH 2/3] filter-rewriter: track connection and parse packet Zhang Chen
2016-06-14 11:15 ` [Qemu-devel] [RFC PATCH 3/3] filter-rewriter: rewrite tcp packet to keep secondary connection Zhang Chen
2016-06-20  6:27   ` Jason Wang [this message]
2016-06-20 12:14     ` Dr. David Alan Gilbert
2016-06-22  3:12       ` Zhang Chen
2016-06-22  6:34         ` Jason Wang
2016-06-23 10:48           ` Zhang Chen
2016-06-24  6:08             ` Jason Wang
2016-06-28  6:33               ` Zhang Chen
2016-06-29  1:55                 ` Jason Wang
2016-06-29  6:13                   ` Zhang Chen
2016-06-30 12:17                     ` Jason Wang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=57678CDA.7020700@redhat.com \
    --to=jasowang@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=eddie.dong@intel.com \
    --cc=hongyang.yang@easystack.cn \
    --cc=lizhijian@cn.fujitsu.com \
    --cc=qemu-devel@nongnu.org \
    --cc=zhang.zhanghailiang@huawei.com \
    --cc=zhangchen.fnst@cn.fujitsu.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).