From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:54760) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cgRxP-0004uC-4H for qemu-devel@nongnu.org; Wed, 22 Feb 2017 03:07:28 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1cgRxL-0000G3-4b for qemu-devel@nongnu.org; Wed, 22 Feb 2017 03:07:27 -0500 Received: from mx1.redhat.com ([209.132.183.28]:33854) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1cgRxK-0000Fy-Rw for qemu-devel@nongnu.org; Wed, 22 Feb 2017 03:07:23 -0500 References: <1487735198-127300-1-git-send-email-zhang.zhanghailiang@huawei.com> <1487735198-127300-3-git-send-email-zhang.zhanghailiang@huawei.com> From: Jason Wang Message-ID: Date: Wed, 22 Feb 2017 16:07:14 +0800 MIME-Version: 1.0 In-Reply-To: <1487735198-127300-3-git-send-email-zhang.zhanghailiang@huawei.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] [PATCH v2 2/3] filter-rewriter: fix memory leak for connection in connection_track_table List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: zhanghailiang , zhangchen.fnst@cn.fujitsu.com, lizhijian@cn.fujitsu.com Cc: qemu-devel@nongnu.org, xuquan8@huawei.com, pss.wulizhen@huawei.com On 2017=E5=B9=B402=E6=9C=8822=E6=97=A5 11:46, zhanghailiang wrote: > After a net connection is closed, we didn't clear its releated resource= s > 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=20 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=20 machine here? > > Signed-off-by: zhanghailiang > --- > 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" > =20 > #define HASHTABLE_MAX_SIZE 16384 > =20 > @@ -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=3D1,ack=3D1' */ > } Connection; > =20 > 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) > } > =20 > /* 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; > =20 > @@ -97,15 +97,45 @@ static int handle_primary_tcp_pkt(NetFilterState *n= f, > tcp_pkt->th_ack =3D htonl(ntohl(tcp_pkt->th_ack) + conn->offs= et); > =20 > 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=3D1' packets from client side, it acks 'fin=3D1= , ack=3D1' > + * packet from server side. From this point, we can ensure tha= t there > + * will be no packets in the connection, except that, some err= ors > + * happen between the path of 'filter object' and vNIC, if thi= s rare > + * case really happen, we can still create a new connection, > + * So it is safe to remove the connection from connection_trac= k_table. > + * > + */ > + if ((conn->tcp_state =3D=3D TCPS_LAST_ACK) && > + (ntohl(tcp_pkt->th_ack) =3D=3D (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 clos= e > + * the connection. > + * > + * We got 'fin=3D1, ack=3D1' packet from client side, we need to > + * record the seq of 'fin=3D1, ack=3D1' packet. > + */ > + if ((tcp_pkt->th_flags & (TH_ACK | TH_FIN)) =3D=3D (TH_ACK | TH_FI= N)) { > + conn->fin_ack_seq =3D htonl(tcp_pkt->th_seq); > + conn->tcp_state =3D TCPS_LAST_ACK; > } > =20 > return 0; > } > =20 > /* 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; > =20 > @@ -133,8 +163,34 @@ static int handle_secondary_tcp_pkt(NetFilterState= *nf, > tcp_pkt->th_seq =3D htonl(ntohl(tcp_pkt->th_seq) - conn->offs= et); > =20 > 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=3D1' packets from server side, it acks 'fin=3D1= , ack=3D1' > + * packet from client side. Like Case 1, there should be no pa= ckets > + * in the connection from now know, But the difference here is > + * if the packet is lost, We will get the resent 'fin=3D1,ack=3D= 1' packet. > + * TODO: Fix above case. > + */ > + if ((conn->tcp_state =3D=3D TCPS_LAST_ACK) && > + (ntohl(tcp_pkt->th_ack) =3D=3D (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 clos= e > + * the connection. > + * > + * We got 'fin=3D1, ack=3D1' packet from server side, we need to > + * record the seq of 'fin=3D1, ack=3D1' packet. > + */ > + if ((tcp_pkt->th_flags & (TH_ACK | TH_FIN)) =3D=3D (TH_ACK | TH_FI= N)) { > + conn->fin_ack_seq =3D ntohl(tcp_pkt->th_seq); > + conn->tcp_state =3D TCPS_LAST_ACK; I thought the tcp_state should store the state of TCP from the view of=20 secondary VM? So TCPS_LAST_ACK is wrong and bring lots of confusion. And=20 the handle of active close needs more states here. E.g if connection is=20 in FIN_WAIT_2, the connection is only half closed, remote peer can still=20 send packet to us unless we receive a FIN. Thanks > } > - > return 0; > } > =20 > @@ -178,7 +234,7 @@ static ssize_t colo_rewriter_receive_iov(NetFilterS= tate *nf, > =20 > if (sender =3D=3D 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(NetFilterS= tate *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);