Merge remote-tracking branch 'remotes/jasowang/tags/net-pull-request' into staging

# gpg: Signature made Fri 19 Oct 2018 04:16:03 BST
# gpg:                using RSA key EF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>"
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 215D 46F4 8246 689E C77F  3562 EF04 965B 398D 6211

* remotes/jasowang/tags/net-pull-request: (26 commits)
  qemu-options: Fix bad "macaddr" property in the documentation
  e1000: indicate dropped packets in HW counters
  net: ignore packet size greater than INT_MAX
  pcnet: fix possible buffer overflow
  rtl8139: fix possible out of bound access
  ne2000: fix possible out of bound access in ne2000_receive
  clean up callback when del virtqueue
  docs: Add COLO status diagram to COLO-FT.txt
  COLO: quick failover process by kick COLO thread
  COLO: notify net filters about checkpoint/failover event
  filter-rewriter: handle checkpoint and failover event
  filter: Add handle_event method for NetFilterClass
  COLO: flush host dirty ram from cache
  savevm: split the process of different stages for loadvm/savevm
  qapi: Add new command to query colo status
  qapi/migration.json: Rename COLO unknown mode to none mode.
  qmp event: Add COLO_EXIT event to notify users while exited COLO
  COLO: Flush memory data from ram cache
  ram/COLO: Record the dirty pages that SVM received
  COLO: Load dirty pages into SVM's RAM cache firstly
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 156 insertions, 10 deletions

diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
index f584e4eba4..bb8f4d93b1 100644
--- a/net/filter-rewriter.c
+++ b/net/filter-rewriter.c
@@ -20,11 +20,15 @@
 #include "qemu/main-loop.h"
 #include "qemu/iov.h"
 #include "net/checksum.h"
+#include "net/colo.h"
+#include "migration/colo.h"
 
 #define FILTER_COLO_REWRITER(obj) \
     OBJECT_CHECK(RewriterState, (obj), TYPE_FILTER_REWRITER)
 
 #define TYPE_FILTER_REWRITER "filter-rewriter"
+#define FAILOVER_MODE_ON  true
+#define FAILOVER_MODE_OFF false
 
 typedef struct RewriterState {
     NetFilterState parent_obj;
@@ -32,8 +36,14 @@ typedef struct RewriterState {
     /* hashtable to save connection */
     GHashTable *connection_track_table;
     bool vnet_hdr;
+    bool failover_mode;
 } RewriterState;
 
+static void filter_rewriter_failover_mode(RewriterState *s)
+{
+    s->failover_mode = FAILOVER_MODE_ON;
+}
+
 static void filter_rewriter_flush(NetFilterState *nf)
 {
     RewriterState *s = FILTER_COLO_REWRITER(nf);
@@ -59,9 +69,9 @@ 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;
 
@@ -74,23 +84,28 @@ static int handle_primary_tcp_pkt(NetFilterState *nf,
         trace_colo_filter_rewriter_conn_offset(conn->offset);
     }
 
+    if (((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == (TH_ACK | TH_SYN)) &&
+        conn->tcp_state == TCPS_SYN_SENT) {
+        conn->tcp_state = TCPS_ESTABLISHED;
+    }
+
     if (((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == TH_SYN)) {
         /*
          * we use this flag update offset func
          * run once in independent tcp connection
          */
-        conn->syn_flag = 1;
+        conn->tcp_state = TCPS_SYN_RECEIVED;
     }
 
     if (((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == TH_ACK)) {
-        if (conn->syn_flag) {
+        if (conn->tcp_state == TCPS_SYN_RECEIVED) {
             /*
              * offset = secondary_seq - primary seq
              * ack packet sent by guest from primary node,
              * so we use th_ack - 1 get primary_seq
              */
             conn->offset -= (ntohl(tcp_pkt->th_ack) - 1);
-            conn->syn_flag = 0;
+            conn->tcp_state = TCPS_ESTABLISHED;
         }
         if (conn->offset) {
             /* handle packets to the secondary from the primary */
@@ -99,15 +114,66 @@ static int handle_primary_tcp_pkt(NetFilterState *nf,
             net_checksum_calculate((uint8_t *)pkt->data + pkt->vnet_hdr_len,
                                    pkt->size - pkt->vnet_hdr_len);
         }
+
+        /*
+         * Passive close step 3
+         */
+        if ((conn->tcp_state == TCPS_LAST_ACK) &&
+            (ntohl(tcp_pkt->th_ack) == (conn->fin_ack_seq + 1))) {
+            conn->tcp_state = TCPS_CLOSED;
+            g_hash_table_remove(rf->connection_track_table, key);
+        }
+    }
+
+    if ((tcp_pkt->th_flags & TH_FIN) == TH_FIN) {
+        /*
+         * Passive close.
+         * Step 1:
+         * The *server* side of this connect is VM, *client* tries to close
+         * the connection. We will into CLOSE_WAIT status.
+         *
+         * Step 2:
+         * In this step we will into LAST_ACK status.
+         *
+         * We got 'fin=1, ack=1' packet from server side, we need to
+         * record the seq of 'fin=1, ack=1' packet.
+         *
+         * Step 3:
+         * 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_ESTABLISHED) {
+            conn->tcp_state = TCPS_CLOSE_WAIT;
+        }
+
+        /*
+         * Active close step 2.
+         */
+        if (conn->tcp_state == TCPS_FIN_WAIT_1) {
+            conn->tcp_state = TCPS_TIME_WAIT;
+            /*
+             * For simplify implementation, we needn't wait 2MSL time
+             * in filter rewriter. Because guest kernel will track the
+             * TCP status and wait 2MSL time, if client resend the FIN
+             * packet, guest will apply the last ACK too.
+             */
+            conn->tcp_state = TCPS_CLOSED;
+            g_hash_table_remove(rf->connection_track_table, key);
+        }
     }
 
     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;
 
@@ -121,7 +187,8 @@ static int handle_secondary_tcp_pkt(NetFilterState *nf,
         trace_colo_filter_rewriter_conn_offset(conn->offset);
     }
 
-    if (((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == (TH_ACK | TH_SYN))) {
+    if (conn->tcp_state == TCPS_SYN_RECEIVED &&
+        ((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == (TH_ACK | TH_SYN))) {
         /*
          * save offset = secondary_seq and then
          * in handle_primary_tcp_pkt make offset
@@ -130,6 +197,12 @@ static int handle_secondary_tcp_pkt(NetFilterState *nf,
         conn->offset = ntohl(tcp_pkt->th_seq);
     }
 
+    /* VM active connect */
+    if (conn->tcp_state == TCPS_CLOSED &&
+        ((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == TH_SYN)) {
+        conn->tcp_state = TCPS_SYN_SENT;
+    }
+
     if ((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == TH_ACK) {
         /* Only need to adjust seq while offset is Non-zero */
         if (conn->offset) {
@@ -141,6 +214,32 @@ static int handle_secondary_tcp_pkt(NetFilterState *nf,
         }
     }
 
+    /*
+     * Passive close step 2:
+     */
+    if (conn->tcp_state == TCPS_CLOSE_WAIT &&
+        (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;
+    }
+
+    /*
+     * Active close
+     *
+     * Step 1:
+     * The *server* side of this connect is VM, *server* tries to close
+     * the connection.
+     *
+     * Step 2:
+     * We will into CLOSE_WAIT status.
+     * We simplify the TCPS_FIN_WAIT_2, TCPS_TIME_WAIT and
+     * CLOSING status.
+     */
+    if (conn->tcp_state == TCPS_ESTABLISHED &&
+        (tcp_pkt->th_flags & (TH_ACK | TH_FIN)) == TH_FIN) {
+        conn->tcp_state = TCPS_FIN_WAIT_1;
+    }
+
     return 0;
 }
 
@@ -184,13 +283,20 @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
              */
             reverse_connection_key(&key);
         }
+
+        /* After failover we needn't change new TCP packet */
+        if (s->failover_mode &&
+            !connection_has_tracked(s->connection_track_table, &key)) {
+            goto out;
+        }
+
         conn = connection_get(s->connection_track_table,
                               &key,
                               NULL);
 
         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);
@@ -203,7 +309,7 @@ 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);
@@ -217,11 +323,49 @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
         }
     }
 
+out:
     packet_destroy(pkt, NULL);
     pkt = NULL;
     return 0;
 }
 
+static void reset_seq_offset(gpointer key, gpointer value, gpointer user_data)
+{
+    Connection *conn = (Connection *)value;
+
+    conn->offset = 0;
+}
+
+static gboolean offset_is_nonzero(gpointer key,
+                                  gpointer value,
+                                  gpointer user_data)
+{
+    Connection *conn = (Connection *)value;
+
+    return conn->offset ? true : false;
+}
+
+static void colo_rewriter_handle_event(NetFilterState *nf, int event,
+                                       Error **errp)
+{
+    RewriterState *rs = FILTER_COLO_REWRITER(nf);
+
+    switch (event) {
+    case COLO_EVENT_CHECKPOINT:
+        g_hash_table_foreach(rs->connection_track_table,
+                            reset_seq_offset, NULL);
+        break;
+    case COLO_EVENT_FAILOVER:
+        if (!g_hash_table_find(rs->connection_track_table,
+                              offset_is_nonzero, NULL)) {
+            filter_rewriter_failover_mode(rs);
+        }
+        break;
+    default:
+        break;
+    }
+}
+
 static void colo_rewriter_cleanup(NetFilterState *nf)
 {
     RewriterState *s = FILTER_COLO_REWRITER(nf);
@@ -265,6 +409,7 @@ static void filter_rewriter_init(Object *obj)
     RewriterState *s = FILTER_COLO_REWRITER(obj);
 
     s->vnet_hdr = false;
+    s->failover_mode = FAILOVER_MODE_OFF;
     object_property_add_bool(obj, "vnet_hdr_support",
                              filter_rewriter_get_vnet_hdr,
                              filter_rewriter_set_vnet_hdr, NULL);
@@ -277,6 +422,7 @@ static void colo_rewriter_class_init(ObjectClass *oc, void *data)
     nfc->setup = colo_rewriter_setup;
     nfc->cleanup = colo_rewriter_cleanup;
     nfc->receive_iov = colo_rewriter_receive_iov;
+    nfc->handle_event = colo_rewriter_handle_event;
 }
 
 static const TypeInfo colo_rewriter_info = {