Re: [Qemu-devel] [PATCH v2 2/3] filter-rewriter: fix memory leak for connection in connection_track_table

[Jason Wang <jasowang@redhat.com>]

On 2017年02月22日 11:46, zhanghailiang wrote:
> After a net connection is closed, we didn't clear its releated resources
> in connection_track_table, which will lead to memory leak.

Not a real leak but would lead reset of hash table if too many closed 
connections.

>
> Let't track the state of net connection, if it is closed, its related
> resources will be cleared up.

The issue is the state were tracked partially, do we need a full state 
machine here?

>
> Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
> ---
>   net/colo.h            |  4 +++
>   net/filter-rewriter.c | 70 +++++++++++++++++++++++++++++++++++++++++++++------
>   2 files changed, 67 insertions(+), 7 deletions(-)
>
> diff --git a/net/colo.h b/net/colo.h
> index 7c524f3..cd9027f 100644
> --- a/net/colo.h
> +++ b/net/colo.h
> @@ -18,6 +18,7 @@
>   #include "slirp/slirp.h"
>   #include "qemu/jhash.h"
>   #include "qemu/timer.h"
> +#include "slirp/tcp.h"
>   
>   #define HASHTABLE_MAX_SIZE 16384
>   
> @@ -69,6 +70,9 @@ typedef struct Connection {
>        * run once in independent tcp connection
>        */
>       int syn_flag;
> +
> +    int tcp_state; /* TCP FSM state */
> +    tcp_seq fin_ack_seq; /* the seq of 'fin=1,ack=1' */
>   } Connection;
>   
>   uint32_t connection_key_hash(const void *opaque);
> diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
> index c4ab91c..7e7ec35 100644
> --- a/net/filter-rewriter.c
> +++ b/net/filter-rewriter.c
> @@ -60,9 +60,9 @@ static int is_tcp_packet(Packet *pkt)
>   }
>   
>   /* handle tcp packet from primary guest */
> -static int handle_primary_tcp_pkt(NetFilterState *nf,
> +static int handle_primary_tcp_pkt(RewriterState *rf,
>                                     Connection *conn,
> -                                  Packet *pkt)
> +                                  Packet *pkt, ConnectionKey *key)
>   {
>       struct tcphdr *tcp_pkt;
>   
> @@ -97,15 +97,45 @@ static int handle_primary_tcp_pkt(NetFilterState *nf,
>           tcp_pkt->th_ack = htonl(ntohl(tcp_pkt->th_ack) + conn->offset);
>   
>           net_checksum_calculate((uint8_t *)pkt->data, pkt->size);
> +        /*
> +         * Case 1:
> +         * The *server* side of this connect is VM, *client* tries to close
> +         * the connection.
> +         *
> +         * We got 'ack=1' packets from client side, it acks 'fin=1, ack=1'
> +         * packet from server side. From this point, we can ensure that there
> +         * will be no packets in the connection, except that, some errors
> +         * happen between the path of 'filter object' and vNIC, if this rare
> +         * case really happen, we can still create a new connection,
> +         * So it is safe to remove the connection from connection_track_table.
> +         *
> +         */
> +        if ((conn->tcp_state == TCPS_LAST_ACK) &&
> +            (ntohl(tcp_pkt->th_ack) == (conn->fin_ack_seq + 1))) {
> +            fprintf(stderr, "Remove conn "

Can this even compile?

> +            g_hash_table_remove(rf->connection_track_table, key);
> +        }
> +    }
> +    /*
> +     * Case 2:
> +     * The *server* side of this connect is VM, *server* tries to close
> +     * the connection.
> +     *
> +     * We got 'fin=1, ack=1' packet from client side, we need to
> +     * record the seq of 'fin=1, ack=1' packet.
> +     */
> +    if ((tcp_pkt->th_flags & (TH_ACK | TH_FIN)) == (TH_ACK | TH_FIN)) {
> +        conn->fin_ack_seq = htonl(tcp_pkt->th_seq);
> +        conn->tcp_state = TCPS_LAST_ACK;
>       }
>   
>       return 0;
>   }
>   
>   /* handle tcp packet from secondary guest */
> -static int handle_secondary_tcp_pkt(NetFilterState *nf,
> +static int handle_secondary_tcp_pkt(RewriterState *rf,
>                                       Connection *conn,
> -                                    Packet *pkt)
> +                                    Packet *pkt, ConnectionKey *key)
>   {
>       struct tcphdr *tcp_pkt;
>   
> @@ -133,8 +163,34 @@ static int handle_secondary_tcp_pkt(NetFilterState *nf,
>           tcp_pkt->th_seq = htonl(ntohl(tcp_pkt->th_seq) - conn->offset);
>   
>           net_checksum_calculate((uint8_t *)pkt->data, pkt->size);
> +        /*
> +         * Case 2:
> +         * The *server* side of this connect is VM, *server* tries to close
> +         * the connection.
> +         *
> +         * We got 'ack=1' packets from server side, it acks 'fin=1, ack=1'
> +         * packet from client side. Like Case 1, there should be no packets
> +         * in the connection from now know, But the difference here is
> +         * if the packet is lost, We will get the resent 'fin=1,ack=1' packet.
> +         * TODO: Fix above case.
> +         */
> +        if ((conn->tcp_state == TCPS_LAST_ACK) &&
> +            (ntohl(tcp_pkt->th_ack) == (conn->fin_ack_seq + 1))) {
> +            g_hash_table_remove(rf->connection_track_table, key);
> +        }
> +    }
> +    /*
> +     * Case 1:
> +     * The *server* side of this connect is VM, *client* tries to close
> +     * the connection.
> +     *
> +     * We got 'fin=1, ack=1' packet from server side, we need to
> +     * record the seq of 'fin=1, ack=1' packet.
> +     */
> +    if ((tcp_pkt->th_flags & (TH_ACK | TH_FIN)) == (TH_ACK | TH_FIN)) {
> +        conn->fin_ack_seq = ntohl(tcp_pkt->th_seq);
> +        conn->tcp_state = TCPS_LAST_ACK;

I thought the tcp_state should store the state of TCP from the view of 
secondary VM? So TCPS_LAST_ACK is wrong and bring lots of confusion. And 
the handle of active close needs more states here. E.g if connection is 
in FIN_WAIT_2, the connection is only half closed, remote peer can still 
send packet to us unless we receive a FIN.

Thanks

>       }
> -
>       return 0;
>   }
>   
> @@ -178,7 +234,7 @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
>   
>           if (sender == nf->netdev) {
>               /* NET_FILTER_DIRECTION_TX */
> -            if (!handle_primary_tcp_pkt(nf, conn, pkt)) {
> +            if (!handle_primary_tcp_pkt(s, conn, pkt, &key)) {
>                   qemu_net_queue_send(s->incoming_queue, sender, 0,
>                   (const uint8_t *)pkt->data, pkt->size, NULL);
>                   packet_destroy(pkt, NULL);
> @@ -191,7 +247,7 @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
>               }
>           } else {
>               /* NET_FILTER_DIRECTION_RX */
> -            if (!handle_secondary_tcp_pkt(nf, conn, pkt)) {
> +            if (!handle_secondary_tcp_pkt(s, conn, pkt, &key)) {
>                   qemu_net_queue_send(s->incoming_queue, sender, 0,
>                   (const uint8_t *)pkt->data, pkt->size, NULL);
>                   packet_destroy(pkt, NULL);