Series comparison

-[Qemu-devel] [PULL 0/9] Net patches
+[Qemu-devel] [PULL 0/6] Net patches
-The following changes since commit 56821559f0ba682fe6b367815572e6f974d329ab:
+The following changes since commit e607bbee553cfe73072870cef458cfa4e78133e2:
-  Merge remote-tracking branch 'dgilbert/tags/pull-hmp-20170517' into staging (2017-05-18 13:36:15 +0100)
+  Merge remote-tracking branch 'remotes/edgar/tags/edgar/xilinx-next-2018-01-26.for-upstream' into staging (2018-01-26 14:24:25 +0000)
 are available in the git repository at:
   https://github.com/jasowang/qemu.git tags/net-pull-request
-for you to fetch changes up to 82342e91b60a4a078811df4e1a545e57abffa11d:
+for you to fetch changes up to bf4835a4d5338bb7424827715df22570a8adc67c:
-  e1000e: Fix ICR "Other" causes clear logic (2017-05-23 10:10:38 +0800)
+  MAINTAINERS: update Dmitry Fleytman email (2018-01-29 16:05:38 +0800)
 ----------------------------------------------------------------
 ----------------------------------------------------------------
-Sameeh Jubran (1):
+Mao Zhongyi (2):
-      e1000e: Fix ICR "Other" causes clear logic
+      colo: modified the payload compare function
       colo: compare the packet based on the tcp sequence number
 Philippe Mathieu-Daudé (1):
       MAINTAINERS: update Dmitry Fleytman email
 Thomas Huth (3):
-      net/tap: Replace tap-haiku.c and tap-aix.c by a generic tap-stub.c
+      net: Allow hubports to connect to other netdevs
-      net/dump: Issue a warning for the deprecated "-net dump"
+      net: Allow netdevs to be used with 'hostfwd_add' and 'hostfwd_remove'
-      hmp / net: Mark host_net_add/remove as deprecated
+      qemu-doc: Get rid of "vlan=X" example in the documentation
-Yunjian Wang (1):
+ MAINTAINERS        |   8 +-
-      virtio-net: fix wild pointer when remove virtio-net queues
+ hmp-commands.hx    |   4 +-
+ net/colo-compare.c | 411 +++++++++++++++++++++++++++++++++--------------------
-Zhang Chen (4):
+ net/colo.c         |   9 ++
-      COLO-compare: Improve tcp compare trace event readability
+ net/colo.h         |  15 ++
-      net/filter-mirror.c: Remove duplicate check code.
+ net/hub.c          |  27 +++-
-      net/filter-mirror.c: Rename filter_mirror_send() and fix codestyle
+ net/hub.h          |   3 +-
-      net/filter-rewriter: Remove unused option in filter-rewriter
+ net/net.c          |   2 +-
+ net/slirp.c        |  33 +++--
- hmp-commands.hx               |  8 ++--
+ net/trace-events   |   2 +-
- hw/net/e1000e_core.c          | 10 ++++-
+ qapi/net.json      |   4 +-
- hw/net/virtio-net.c           |  3 ++
+ qemu-options.hx    |  12 +-
- net/Makefile.objs             | 15 ++++----
+files changed, 347 insertions(+), 183 deletions(-)
  net/colo-compare.c            | 33 ++++++++++------
  net/dump.c                    |  3 ++
  net/filter-mirror.c           | 35 ++++++++---------
  net/net.c                     | 13 +++++++
  net/tap-haiku.c               | 87 -------------------------------------------
  net/{tap-aix.c => tap-stub.c} |  3 +-
  net/trace-events              |  3 +-
  qemu-options.hx               |  2 +-
 files changed, 80 insertions(+), 135 deletions(-)
  delete mode 100644 net/tap-haiku.c
  rename net/{tap-aix.c => tap-stub.c} (97%)

-[Qemu-devel] [PULL 1/9] net/tap: Replace tap-haiku.c and tap-aix.c by a generic tap-stub.c
+Deleted patch
-From: Thomas Huth <thuth@redhat.com>
-The files tap-haiku.c and tap-aix.c are identical (except one line
-of error message). We should avoid such code duplication, so replace
-these by a generic tap-stub.c file instead.
-Signed-off-by: Thomas Huth <thuth@redhat.com>
-Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
----
- net/Makefile.objs | 15 +++++-----
- net/tap-aix.c     | 88 -------------------------------------------------------
- net/tap-haiku.c   | 87 ------------------------------------------------------
- net/tap-stub.c    | 87 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
-files changed, 95 insertions(+), 182 deletions(-)
- delete mode 100644 net/tap-aix.c
- delete mode 100644 net/tap-haiku.c
- create mode 100644 net/tap-stub.c
-diff --git a/net/Makefile.objs b/net/Makefile.objs
-index XXXXXXX..XXXXXXX 100644
---- a/net/Makefile.objs
-+++ b/net/Makefile.objs
-@@ -XXX,XX +XXX,XX @@ common-obj-y += socket.o
- common-obj-y += dump.o
- common-obj-y += eth.o
- common-obj-$(CONFIG_L2TPV3) += l2tpv3.o
--common-obj-$(CONFIG_POSIX) += tap.o vhost-user.o
--common-obj-$(CONFIG_LINUX) += tap-linux.o
--common-obj-$(CONFIG_WIN32) += tap-win32.o
--common-obj-$(CONFIG_BSD) += tap-bsd.o
--common-obj-$(CONFIG_SOLARIS) += tap-solaris.o
--common-obj-$(CONFIG_AIX) += tap-aix.o
--common-obj-$(CONFIG_HAIKU) += tap-haiku.o
-+common-obj-$(CONFIG_POSIX) += vhost-user.o
- common-obj-$(CONFIG_SLIRP) += slirp.o
- common-obj-$(CONFIG_VDE) += vde.o
- common-obj-$(CONFIG_NETMAP) += netmap.o
-@@ -XXX,XX +XXX,XX @@ common-obj-y += colo-compare.o
- common-obj-y += colo.o
- common-obj-y += filter-rewriter.o
- common-obj-y += filter-replay.o
-+
-+tap-obj-$(CONFIG_LINUX) = tap-linux.o
-+tap-obj-$(CONFIG_BSD) = tap-bsd.o
-+tap-obj-$(CONFIG_SOLARIS) = tap-solaris.o
-+tap-obj-y ?= tap-stub.o
-+common-obj-$(CONFIG_POSIX) += tap.o $(tap-obj-y)
-+common-obj-$(CONFIG_WIN32) += tap-win32.o
-diff --git a/net/tap-aix.c b/net/tap-aix.c
-deleted file mode 100644
-index XXXXXXX..XXXXXXX
---- a/net/tap-aix.c
-+++ /dev/null
-@@ -XXX,XX +XXX,XX @@
--/*
-- * QEMU System Emulator
-- *
-- * Copyright (c) 2003-2008 Fabrice Bellard
-- *
-- * Permission is hereby granted, free of charge, to any person obtaining a copy
-- * of this software and associated documentation files (the "Software"), to deal
-- * in the Software without restriction, including without limitation the rights
-- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-- * copies of the Software, and to permit persons to whom the Software is
-- * furnished to do so, subject to the following conditions:
-- *
-- * The above copyright notice and this permission notice shall be included in
-- * all copies or substantial portions of the Software.
-- *
-- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
-- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-- * THE SOFTWARE.
-- */
--
--#include "qemu/osdep.h"
--#include "qapi/error.h"
--#include "tap_int.h"
--
--int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
--             int vnet_hdr_required, int mq_required, Error **errp)
--{
--    error_setg(errp, "no tap on AIX");
--    return -1;
--}
--
--void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
--{
--}
--
--int tap_probe_vnet_hdr(int fd)
--{
--    return 0;
--}
--
--int tap_probe_has_ufo(int fd)
--{
--    return 0;
--}
--
--int tap_probe_vnet_hdr_len(int fd, int len)
--{
--    return 0;
--}
--
--void tap_fd_set_vnet_hdr_len(int fd, int len)
--{
--}
--
--int tap_fd_set_vnet_le(int fd, int is_le)
--{
--    return -EINVAL;
--}
--
--int tap_fd_set_vnet_be(int fd, int is_be)
--{
--    return -EINVAL;
--}
--
--void tap_fd_set_offload(int fd, int csum, int tso4,
--                        int tso6, int ecn, int ufo)
--{
--}
--
--int tap_fd_enable(int fd)
--{
--    return -1;
--}
--
--int tap_fd_disable(int fd)
--{
--    return -1;
--}
--
--int tap_fd_get_ifname(int fd, char *ifname)
--{
--    return -1;
--}
--
-diff --git a/net/tap-haiku.c b/net/tap-haiku.c
-deleted file mode 100644
-index XXXXXXX..XXXXXXX
---- a/net/tap-haiku.c
-+++ /dev/null
-@@ -XXX,XX +XXX,XX @@
--/*
-- * QEMU System Emulator
-- *
-- * Copyright (c) 2003-2008 Fabrice Bellard
-- *
-- * Permission is hereby granted, free of charge, to any person obtaining a copy
-- * of this software and associated documentation files (the "Software"), to deal
-- * in the Software without restriction, including without limitation the rights
-- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-- * copies of the Software, and to permit persons to whom the Software is
-- * furnished to do so, subject to the following conditions:
-- *
-- * The above copyright notice and this permission notice shall be included in
-- * all copies or substantial portions of the Software.
-- *
-- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
-- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-- * THE SOFTWARE.
-- */
--
--#include "qemu/osdep.h"
--#include "qapi/error.h"
--#include "tap_int.h"
--
--int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
--             int vnet_hdr_required, int mq_required, Error **errp)
--{
--    error_setg(errp, "no tap on Haiku");
--    return -1;
--}
--
--void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
--{
--}
--
--int tap_probe_vnet_hdr(int fd)
--{
--    return 0;
--}
--
--int tap_probe_has_ufo(int fd)
--{
--    return 0;
--}
--
--int tap_probe_vnet_hdr_len(int fd, int len)
--{
--    return 0;
--}
--
--void tap_fd_set_vnet_hdr_len(int fd, int len)
--{
--}
--
--int tap_fd_set_vnet_le(int fd, int is_le)
--{
--    return -EINVAL;
--}
--
--int tap_fd_set_vnet_be(int fd, int is_be)
--{
--    return -EINVAL;
--}
--
--void tap_fd_set_offload(int fd, int csum, int tso4,
--                        int tso6, int ecn, int ufo)
--{
--}
--
--int tap_fd_enable(int fd)
--{
--    return -1;
--}
--
--int tap_fd_disable(int fd)
--{
--    return -1;
--}
--
--int tap_fd_get_ifname(int fd, char *ifname)
--{
--    return -1;
--}
-diff --git a/net/tap-stub.c b/net/tap-stub.c
-new file mode 100644
-index XXXXXXX..XXXXXXX
---- /dev/null
-+++ b/net/tap-stub.c
-@@ -XXX,XX +XXX,XX @@
-+/*
-+ * QEMU System Emulator
-+ *
-+ * Copyright (c) 2003-2008 Fabrice Bellard
-+ *
-+ * Permission is hereby granted, free of charge, to any person obtaining a copy
-+ * of this software and associated documentation files (the "Software"), to deal
-+ * in the Software without restriction, including without limitation the rights
-+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-+ * copies of the Software, and to permit persons to whom the Software is
-+ * furnished to do so, subject to the following conditions:
-+ *
-+ * The above copyright notice and this permission notice shall be included in
-+ * all copies or substantial portions of the Software.
-+ *
-+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
-+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-+ * THE SOFTWARE.
-+ */
-+
-+#include "qemu/osdep.h"
-+#include "qapi/error.h"
-+#include "tap_int.h"
-+
-+int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
-+             int vnet_hdr_required, int mq_required, Error **errp)
-+{
-+    error_setg(errp, "tap is not supported in this build");
-+    return -1;
-+}
-+
-+void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
-+{
-+}
-+
-+int tap_probe_vnet_hdr(int fd)
-+{
-+    return 0;
-+}
-+
-+int tap_probe_has_ufo(int fd)
-+{
-+    return 0;
-+}
-+
-+int tap_probe_vnet_hdr_len(int fd, int len)
-+{
-+    return 0;
-+}
-+
-+void tap_fd_set_vnet_hdr_len(int fd, int len)
-+{
-+}
-+
-+int tap_fd_set_vnet_le(int fd, int is_le)
-+{
-+    return -EINVAL;
-+}
-+
-+int tap_fd_set_vnet_be(int fd, int is_be)
-+{
-+    return -EINVAL;
-+}
-+
-+void tap_fd_set_offload(int fd, int csum, int tso4,
-+                        int tso6, int ecn, int ufo)
-+{
-+}
-+
-+int tap_fd_enable(int fd)
-+{
-+    return -1;
-+}
-+
-+int tap_fd_disable(int fd)
-+{
-+    return -1;
-+}
-+
-+int tap_fd_get_ifname(int fd, char *ifname)
-+{
-+    return -1;
-+}
---
-.7.4

-[Qemu-devel] [PULL 2/9] net/dump: Issue a warning for the deprecated "-net dump"
+Deleted patch
-From: Thomas Huth <thuth@redhat.com>
-Network dumping should be done with "-object filter-dump" nowadays.
-Using "-net dump" via the VLAN mechanism is considered as deprecated
-and might be removed in a future release. So warn the users now
-to inform them to user the filter-dump method instead.
-Signed-off-by: Thomas Huth <thuth@redhat.com>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
----
- net/dump.c | 3 +++
-file changed, 3 insertions(+)
-diff --git a/net/dump.c b/net/dump.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/dump.c
-+++ b/net/dump.c
-@@ -XXX,XX +XXX,XX @@ int net_init_dump(const Netdev *netdev, const char *name,
-     assert(peer);
-+    error_report("'-net dump' is deprecated. "
-+                 "Please use '-object filter-dump' instead.");
-+
-     if (dump->has_file) {
-         file = dump->file;
-     } else {
---
-.7.4

-[Qemu-devel] [PULL 9/9] e1000e: Fix ICR "Other" causes clear logic
+[Qemu-devel] [PULL 1/6] colo: modified the payload compare function
-From: Sameeh Jubran <sameeh@daynix.com>
+From: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>
-This commit fixes a bug which causes the guest to hang. The bug was
+Modified the function colo_packet_compare_common to prepare for the
-observed upon a "receive overrun" (bit #6 of the ICR register)
+tcp packet comparison in the next patch.
 interrupt which could be triggered post migration in a heavy traffic
 environment. Even though the "receive overrun" bit (#6) is masked out
 by the IMS register (refer to the log below) the driver still receives
 an interrupt as the "receive overrun" bit (#6) causes the "Other" -
 bit #24 of the ICR register - bit to be set as documented below. The
 driver handles the interrupt and clears the "Other" bit (#24) but
 doesn't clear the "receive overrun" bit (#6) which leads to an
 infinite loop. Apparently the Windows driver expects that the "receive
 overrun" bit and other ones - documented below - to be cleared when
 the "Other" bit (#24) is cleared.
-So to sum that up:
+Cc: Zhang Chen <zhangckid@gmail.com>
-. Bit #6 of the ICR register is set by heavy traffic
+Cc: Li Zhijian <lizhijian@cn.fujitsu.com>
-. As a results of setting bit #6, bit #24 is set
+Cc: Jason Wang <jasowang@redhat.com>
 . The driver receives an interrupt for bit 24 (it doesn't receieve an
    interrupt for bit #6 as it is masked out by IMS)
 . The driver handles and clears the interrupt of bit #24
 . Bit #6 is still set.
 . 2 happens all over again
-The Interrupt Cause Read - ICR register:
+Signed-off-by: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>
+Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
-The ICR has the "Other" bit - bit #24 - that is set when one or more
+Signed-off-by: Zhang Chen <zhangckid@gmail.com>
-of the following ICR register's bits are set:
+Reviewed-by: Zhang Chen <zhangckid@gmail.com>
 LSC - bit #2, RXO - bit #6, MDAC - bit #9, SRPD - bit #16, ACK - bit
 #17, MNG - bit #18
 This bug can occur with any of these bits depending on the driver's
 behaviour and the way it configures the device. However, trying to
 reproduce it with any bit other than RX0 is challenging and came to
 failure as the drivers don't implement most of these bits, trying to
 reproduce it with LSC (Link Status Change - bit #2) bit didn't succeed
 too as it seems that Windows handles this bit differently.
 Log sample of the storm:
 @1494850819.411877:e1000e_irq_pending_interrupts ICR PENDING: 0x1000000 (ICR: 0x815000c2, IMS: 0x1a00004)
 @1494850819.411900:e1000e_irq_pending_interrupts ICR PENDING: 0x0 (ICR: 0x815000c2, IMS: 0xa00004)
 @1494850819.411915:e1000e_irq_pending_interrupts ICR PENDING: 0x0 (ICR: 0x815000c2, IMS: 0xa00004)
 @1494850819.412380:e1000e_irq_pending_interrupts ICR PENDING: 0x0 (ICR: 0x815000c2, IMS: 0xa00004)
 @1494850819.412395:e1000e_irq_pending_interrupts ICR PENDING: 0x0 (ICR: 0x815000c2, IMS: 0xa00004)
 @1494850819.412436:e1000e_irq_pending_interrupts ICR PENDING: 0x0 (ICR: 0x815000c2, IMS: 0xa00004)
 @1494850819.412441:e1000e_irq_pending_interrupts ICR PENDING: 0x0 (ICR: 0x815000c2, IMS: 0xa00004)
 @1494850819.412998:e1000e_irq_pending_interrupts ICR PENDING: 0x1000000 (ICR: 0x815000c2, IMS: 0x1a00004)
 * This bug behaviour wasn't observed with the Linux driver.
 This commit solves:
 https://bugzilla.redhat.com/show_bug.cgi?id=1447935
 https://bugzilla.redhat.com/show_bug.cgi?id=1449490
 Cc: qemu-stable@nongnu.org
 Signed-off-by: Sameeh Jubran <sjubran@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- hw/net/e1000e_core.c | 10 ++++++++--
+ net/colo-compare.c | 88 +++++++++++++++++++++++++++---------------------------
-file changed, 8 insertions(+), 2 deletions(-)
+file changed, 44 insertions(+), 44 deletions(-)
-diff --git a/hw/net/e1000e_core.c b/hw/net/e1000e_core.c
+diff --git a/net/colo-compare.c b/net/colo-compare.c
 index XXXXXXX..XXXXXXX 100644
---- a/hw/net/e1000e_core.c
+--- a/net/colo-compare.c
-+++ b/hw/net/e1000e_core.c
++++ b/net/colo-compare.c
-@@ -XXX,XX +XXX,XX @@ e1000e_set_ics(E1000ECore *core, int index, uint32_t val)
+@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode, Connection **con)
- static void
+  * return:    0  means packet same
- e1000e_set_icr(E1000ECore *core, int index, uint32_t val)
+  *            > 0 || < 0 means packet different
   */
 -static int colo_packet_compare_common(Packet *ppkt,
 -                                      Packet *spkt,
 -                                      int poffset,
 -                                      int soffset)
 +static int colo_compare_packet_payload(Packet *ppkt,
 +                                       Packet *spkt,
 +                                       uint16_t poffset,
 +                                       uint16_t soffset,
 +                                       uint16_t len)
 +
  {
-+    uint32_t icr = 0;
+     if (trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
-     if ((core->mac[ICR] & E1000_ICR_ASSERTED) &&
+         char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
-         (core->mac[CTRL_EXT] & E1000_CTRL_EXT_IAME)) {
+@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_common(Packet *ppkt,
-         trace_e1000e_irq_icr_process_iame();
+                                    sec_ip_src, sec_ip_dst);
          e1000e_clear_ims_bits(core, core->mac[IAM]);
      }
--    trace_e1000e_irq_icr_write(val, core->mac[ICR], core->mac[ICR] & ~val);
+-    poffset = ppkt->vnet_hdr_len + poffset;
--    core->mac[ICR] &= ~val;
+-    soffset = ppkt->vnet_hdr_len + soffset;
-+    icr = core->mac[ICR] & ~val;
+-
-+    /* Windows driver expects that the "receive overrun" bit and other
+-    if (ppkt->size - poffset == spkt->size - soffset) {
-+     * ones to be cleared when the "Other" bit (#24) is cleared.
+-        return memcmp(ppkt->data + poffset,
-+     */
+-                      spkt->data + soffset,
-+    icr = (val & E1000_ICR_OTHER) ? (icr & ~E1000_ICR_OTHER_CAUSES) : icr;
+-                      spkt->size - soffset);
-+    trace_e1000e_irq_icr_write(val, core->mac[ICR], icr);
+-    } else {
-+    core->mac[ICR] = icr;
+-        trace_colo_compare_main("Net packet size are not the same");
-     e1000e_update_interrupt_state(core);
+-        return -1;
 -    }
 +    return memcmp(ppkt->data + poffset, spkt->data + soffset, len);
  }
+ /*
+@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
+      * the secondary guest's timestamp. COLO just focus on payload,
+      * so we just need skip this field.
+      */
+-    if (ptcp->th_off > 5) {
+-        ptrdiff_t ptcp_offset, stcp_offset;
+-        ptcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
+-                      + (ptcp->th_off * 4) - ppkt->vnet_hdr_len;
+-        stcp_offset = spkt->transport_header - (uint8_t *)spkt->data
+-                      + (stcp->th_off * 4) - spkt->vnet_hdr_len;
++    ptrdiff_t ptcp_offset, stcp_offset;
+-        /*
+-         * When network is busy, some tcp options(like sack) will unpredictable
+-         * occur in primary side or secondary side. it will make packet size
+-         * not same, but the two packet's payload is identical. colo just
+-         * care about packet payload, so we skip the option field.
+-         */
+-        res = colo_packet_compare_common(ppkt, spkt, ptcp_offset, stcp_offset);
+-    } else if (ptcp->th_sum == stcp->th_sum) {
+-        res = colo_packet_compare_common(ppkt, spkt, ETH_HLEN, ETH_HLEN);
++    ptcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
++                  + (ptcp->th_off << 2) - ppkt->vnet_hdr_len;
++    stcp_offset = spkt->transport_header - (uint8_t *)spkt->data
++                  + (stcp->th_off << 2) - spkt->vnet_hdr_len;
++    if (ppkt->size - ptcp_offset == spkt->size - stcp_offset) {
++        res = colo_compare_packet_payload(ppkt, spkt,
++                                          ptcp_offset, stcp_offset,
++                                          ppkt->size - ptcp_offset);
+     } else {
++        trace_colo_compare_main("TCP: payload size of packets are different");
+         res = -1;
+     }
+@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
+  */
+ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
+ {
+-    int ret;
+-    int network_header_length = ppkt->ip->ip_hl * 4;
++    uint16_t network_header_length = ppkt->ip->ip_hl << 2;
++    uint16_t offset = network_header_length + ETH_HLEN + ppkt->vnet_hdr_len;
+     trace_colo_compare_main("compare udp");
+@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
+      * other field like TOS,TTL,IP Checksum. we only need to compare
+      * the ip payload here.
+      */
+-    ret = colo_packet_compare_common(ppkt, spkt,
+-                                     network_header_length + ETH_HLEN,
+-                                     network_header_length + ETH_HLEN);
+-
+-    if (ret) {
++    if (ppkt->size != spkt->size) {
++        trace_colo_compare_main("UDP: payload size of packets are different");
++        return -1;
++    }
++    if (colo_compare_packet_payload(ppkt, spkt, offset, offset,
++                                    ppkt->size - offset)) {
+         trace_colo_compare_udp_miscompare("primary pkt size", ppkt->size);
+         trace_colo_compare_udp_miscompare("Secondary pkt size", spkt->size);
+         if (trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
+@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
+             qemu_hexdump((char *)spkt->data, stderr, "colo-compare sec pkt",
+                          spkt->size);
+         }
++        return -1;
++    } else {
++        return 0;
+     }
+-
+-    return ret;
+ }
+ /*
+@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
+  */
+ static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
+ {
+-    int network_header_length = ppkt->ip->ip_hl * 4;
++    uint16_t network_header_length = ppkt->ip->ip_hl << 2;
++    uint16_t offset = network_header_length + ETH_HLEN + ppkt->vnet_hdr_len;
+     trace_colo_compare_main("compare icmp");
+@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
+      * other field like TOS,TTL,IP Checksum. we only need to compare
+      * the ip payload here.
+      */
+-    if (colo_packet_compare_common(ppkt, spkt,
+-                                   network_header_length + ETH_HLEN,
+-                                   network_header_length + ETH_HLEN)) {
++    if (ppkt->size != spkt->size) {
++        trace_colo_compare_main("ICMP: payload size of packets are different");
++        return -1;
++    }
++    if (colo_compare_packet_payload(ppkt, spkt, offset, offset,
++                                    ppkt->size - offset)) {
+         trace_colo_compare_icmp_miscompare("primary pkt size",
+                                            ppkt->size);
+         trace_colo_compare_icmp_miscompare("Secondary pkt size",
+@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
+  */
+ static int colo_packet_compare_other(Packet *spkt, Packet *ppkt)
+ {
++    uint16_t offset = ppkt->vnet_hdr_len;
++
+     trace_colo_compare_main("compare other");
+     if (trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
+         char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
+@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_other(Packet *spkt, Packet *ppkt)
+                                    sec_ip_src, sec_ip_dst);
+     }
+-    return colo_packet_compare_common(ppkt, spkt, 0, 0);
++    if (ppkt->size != spkt->size) {
++        trace_colo_compare_main("Other: payload size of packets are different");
++        return -1;
++    }
++    return colo_compare_packet_payload(ppkt, spkt, offset, offset,
++                                       ppkt->size - offset);
+ }
+ static int colo_old_packet_check_one(Packet *pkt, int64_t *check_time)
 --
 .7.4

-[Qemu-devel] [PULL 4/9] COLO-compare: Improve tcp compare trace event readability
+[Qemu-devel] [PULL 2/6] colo: compare the packet based on the tcp sequence number
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>
-Because of previous patch's trace arguments over the limit
+Packet size some time different or when network is busy.
-of UST backend, so I rewrite the patch.
+Based on same payload size, but TCP protocol can not
+guarantee send the same one packet in the same way,
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
 like that:
 We send this payload:
 ------------------------------
 | header |1|2|3|4|5|6|7|8|9|0|
 ------------------------------
 primary:
 ppkt1:
 ----------------
 | header |1|2|3|
 ----------------
 ppkt2:
 ------------------------
 | header |4|5|6|7|8|9|0|
 ------------------------
 secondary:
 spkt1:
 ------------------------------
 | header |1|2|3|4|5|6|7|8|9|0|
 ------------------------------
 In the original method, ppkt1 and ppkt2 are different in size and
 spkt1, so they can't compare and trigger the checkpoint.
 I have tested FTP get 200M and 1G file many times, I found that
 the performance was less than 1% of the native.
 Now I reconstructed the comparison of TCP packets based on the
 TCP sequence number. first of all, ppkt1 and spkt1 have the same
 starting sequence number, so they can compare, even though their
 length is different. And then ppkt1 with a smaller payload length
 is used as the comparison length, if the payload is same, send
 out the ppkt1 and record the offset(the length of ppkt1 payload)
 in spkt1. The next comparison, ppkt2 and spkt1 can be compared
 from the recorded position of spkt1.
 like that:
 ----------------
 | header |1|2|3| ppkt1
 ---------|-----|
          |     |
 ---------v-----v--------------
 | header |1|2|3|4|5|6|7|8|9|0| spkt1
 ---------------|\------------|
                | \offset     |
       ---------v-------------v
       | header |4|5|6|7|8|9|0| ppkt2
       ------------------------
 In this way, the performance can reach native 20% in my multiple
 tests.
 Cc: Zhang Chen <zhangckid@gmail.com>
 Cc: Li Zhijian <lizhijian@cn.fujitsu.com>
 Cc: Jason Wang <jasowang@redhat.com>
 Signed-off-by: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>
 Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
 Signed-off-by: Zhang Chen <zhangckid@gmail.com>
 Reviewed-by: Zhang Chen <zhangckid@gmail.com>
 Tested-by: Zhang Chen <zhangckid@gmail.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/colo-compare.c | 33 ++++++++++++++++++++++-----------
+ net/colo-compare.c | 343 +++++++++++++++++++++++++++++++++++------------------
- net/trace-events   |  3 +--
+ net/colo.c         |   9 ++
-files changed, 23 insertions(+), 13 deletions(-)
+ net/colo.h         |  15 +++
  net/trace-events   |   2 +-
 files changed, 250 insertions(+), 119 deletions(-)
 diff --git a/net/colo-compare.c b/net/colo-compare.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/colo-compare.c
 +++ b/net/colo-compare.c
-@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
+@@ -XXX,XX +XXX,XX @@
  #define COMPARE_READ_LEN_MAX NET_BUFSIZE
  #define MAX_QUEUE_SIZE 1024
 +#define COLO_COMPARE_FREE_PRIMARY     0x01
 +#define COLO_COMPARE_FREE_SECONDARY   0x02
 +
  /* TODO: Should be configurable */
  #define REGULAR_PACKET_CHECK_MS 3000
@@ -XXX,XX +XXX,XX @@ static gint seq_sorter(Packet *a, Packet *b, gpointer data)
      return ntohl(atcp->th_seq) - ntohl(btcp->th_seq);
  }
 +static void fill_pkt_tcp_info(void *data, uint32_t *max_ack)
 +{
 +    Packet *pkt = data;
 +    struct tcphdr *tcphd;
 +
 +    tcphd = (struct tcphdr *)pkt->transport_header;
 +
 +    pkt->tcp_seq = ntohl(tcphd->th_seq);
 +    pkt->tcp_ack = ntohl(tcphd->th_ack);
 +    *max_ack = *max_ack > pkt->tcp_ack ? *max_ack : pkt->tcp_ack;
 +    pkt->header_size = pkt->transport_header - (uint8_t *)pkt->data
 +                       + (tcphd->th_off << 2) - pkt->vnet_hdr_len;
 +    pkt->payload_size = pkt->size - pkt->header_size;
 +    pkt->seq_end = pkt->tcp_seq + pkt->payload_size;
 +    pkt->flags = tcphd->th_flags;
 +}
 +
  /*
   * Return 1 on success, if return 0 means the
   * packet will be dropped
   */
 -static int colo_insert_packet(GQueue *queue, Packet *pkt)
 +static int colo_insert_packet(GQueue *queue, Packet *pkt, uint32_t *max_ack)
  {
      if (g_queue_get_length(queue) <= MAX_QUEUE_SIZE) {
          if (pkt->ip->ip_p == IPPROTO_TCP) {
 +            fill_pkt_tcp_info(pkt, max_ack);
              g_queue_insert_sorted(queue,
                                    pkt,
                                    (GCompareDataFunc)seq_sorter,
@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode, Connection **con)
      }
-     if (res != 0 && trace_event_get_state(TRACE_COLO_COMPARE_MISCOMPARE)) {
+     if (mode == PRIMARY_IN) {
--        trace_colo_compare_pkt_info_src(inet_ntoa(ppkt->ip->ip_src),
+-        if (!colo_insert_packet(&conn->primary_list, pkt)) {
--                                        ntohl(stcp->th_seq),
++        if (!colo_insert_packet(&conn->primary_list, pkt, &conn->pack)) {
--                                        ntohl(stcp->th_ack),
+             error_report("colo compare primary queue size too big,"
--                                        res, stcp->th_flags,
+                          "drop packet");
--                                        spkt->size);
+         }
      } else {
 -        if (!colo_insert_packet(&conn->secondary_list, pkt)) {
 +        if (!colo_insert_packet(&conn->secondary_list, pkt, &conn->sack)) {
              error_report("colo compare secondary queue size too big,"
                           "drop packet");
          }
@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode, Connection **con)
      return 0;
  }
 +static inline bool after(uint32_t seq1, uint32_t seq2)
 +{
 +        return (int32_t)(seq1 - seq2) > 0;
 +}
 +
 +static void colo_release_primary_pkt(CompareState *s, Packet *pkt)
 +{
 +    int ret;
 +    ret = compare_chr_send(s,
 +                           pkt->data,
 +                           pkt->size,
 +                           pkt->vnet_hdr_len);
 +    if (ret < 0) {
 +        error_report("colo send primary packet failed");
 +    }
 +    trace_colo_compare_main("packet same and release packet");
 +    packet_destroy(pkt, NULL);
 +}
 +
  /*
   * The IP packets sent by primary and secondary
   * will be compared in here
@@ -XXX,XX +XXX,XX @@ static int colo_compare_packet_payload(Packet *ppkt,
  }
  /*
 - * Called from the compare thread on the primary
 - * for compare tcp packet
 - * compare_tcp copied from Dr. David Alan Gilbert's branch
 - */
 -static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
 + * return true means that the payload is consist and
 + * need to make the next comparison, false means do
 + * the checkpoint
 +*/
 +static bool colo_mark_tcp_pkt(Packet *ppkt, Packet *spkt,
 +                              int8_t *mark, uint32_t max_ack)
  {
 -    struct tcphdr *ptcp, *stcp;
 -    int res;
 +    *mark = 0;
 +
 +    if (ppkt->tcp_seq == spkt->tcp_seq && ppkt->seq_end == spkt->seq_end) {
 +        if (colo_compare_packet_payload(ppkt, spkt,
 +                                        ppkt->header_size, spkt->header_size,
 +                                        ppkt->payload_size)) {
 +            *mark = COLO_COMPARE_FREE_SECONDARY | COLO_COMPARE_FREE_PRIMARY;
 +            return true;
 +        }
 +    }
 +    if (ppkt->tcp_seq == spkt->tcp_seq && ppkt->seq_end == spkt->seq_end) {
 +        if (colo_compare_packet_payload(ppkt, spkt,
 +                                        ppkt->header_size, spkt->header_size,
 +                                        ppkt->payload_size)) {
 +            *mark = COLO_COMPARE_FREE_SECONDARY | COLO_COMPARE_FREE_PRIMARY;
 +            return true;
 +        }
 +    }
 +
 +    /* one part of secondary packet payload still need to be compared */
 +    if (!after(ppkt->seq_end, spkt->seq_end)) {
 +        if (colo_compare_packet_payload(ppkt, spkt,
 +                                        ppkt->header_size + ppkt->offset,
 +                                        spkt->header_size + spkt->offset,
 +                                        ppkt->payload_size - ppkt->offset)) {
 +            if (!after(ppkt->tcp_ack, max_ack)) {
 +                *mark = COLO_COMPARE_FREE_PRIMARY;
 +                spkt->offset += ppkt->payload_size - ppkt->offset;
 +                return true;
 +            } else {
 +                /* secondary guest hasn't ack the data, don't send
 +                 * out this packet
 +                 */
 +                return false;
 +            }
 +        }
 +    } else {
 +        /* primary packet is longer than secondary packet, compare
 +         * the same part and mark the primary packet offset
 +         */
 +        if (colo_compare_packet_payload(ppkt, spkt,
 +                                        ppkt->header_size + ppkt->offset,
 +                                        spkt->header_size + spkt->offset,
 +                                        spkt->payload_size - spkt->offset)) {
 +            *mark = COLO_COMPARE_FREE_SECONDARY;
 +            ppkt->offset += spkt->payload_size - spkt->offset;
 +            return true;
 +        }
 +    }
 -    trace_colo_compare_main("compare tcp");
 +    return false;
 +}
 -    ptcp = (struct tcphdr *)ppkt->transport_header;
 -    stcp = (struct tcphdr *)spkt->transport_header;
 +static void colo_compare_tcp(CompareState *s, Connection *conn)
 +{
 +    Packet *ppkt = NULL, *spkt = NULL;
 +    int8_t mark;
      /*
 -     * The 'identification' field in the IP header is *very* random
 -     * it almost never matches.  Fudge this by ignoring differences in
 -     * unfragmented packets; they'll normally sort themselves out if different
 -     * anyway, and it should recover at the TCP level.
 -     * An alternative would be to get both the primary and secondary to rewrite
 -     * somehow; but that would need some sync traffic to sync the state
 -     */
 -    if (ntohs(ppkt->ip->ip_off) & IP_DF) {
 -        spkt->ip->ip_id = ppkt->ip->ip_id;
 -        /* and the sum will be different if the IDs were different */
 -        spkt->ip->ip_sum = ppkt->ip->ip_sum;
 +     * If ppkt and spkt have the same payload, but ppkt's ACK
 +     * is greater than spkt's ACK, in this case we can not
 +     * send the ppkt because it will cause the secondary guest
 +     * to miss sending some data in the next. Therefore, we
 +     * record the maximum ACK in the current queue at both
 +     * primary side and secondary side. Only when the ack is
 +     * less than the smaller of the two maximum ack, then we
 +     * can ensure that the packet's payload is acknowledged by
 +     * primary and secondary.
 +    */
 +    uint32_t min_ack = conn->pack > conn->sack ? conn->sack : conn->pack;
 +
 +pri:
 +    if (g_queue_is_empty(&conn->primary_list)) {
 +        return;
      }
 +    ppkt = g_queue_pop_head(&conn->primary_list);
 +sec:
 +    if (g_queue_is_empty(&conn->secondary_list)) {
 +        g_queue_push_head(&conn->primary_list, ppkt);
 +        return;
 +    }
 +    spkt = g_queue_pop_head(&conn->secondary_list);
 -    /*
 -     * Check tcp header length for tcp option field.
 -     * th_off > 5 means this tcp packet have options field.
 -     * The tcp options maybe always different.
 -     * for example:
 -     * From RFC 7323.
 -     * TCP Timestamps option (TSopt):
 -     * Kind: 8
 -     *
 -     * Length: 10 bytes
 -     *
 -     *    +-------+-------+---------------------+---------------------+
 -     *    |Kind=8 |  10   |   TS Value (TSval)  |TS Echo Reply (TSecr)|
 -     *    +-------+-------+---------------------+---------------------+
 -     *       1       1              4                     4
 -     *
 -     * In this case the primary guest's timestamp always different with
 -     * the secondary guest's timestamp. COLO just focus on payload,
 -     * so we just need skip this field.
 -     */
 +    if (ppkt->tcp_seq == ppkt->seq_end) {
 +        colo_release_primary_pkt(s, ppkt);
 +        ppkt = NULL;
 +    }
 -    ptrdiff_t ptcp_offset, stcp_offset;
 +    if (ppkt && conn->compare_seq && !after(ppkt->seq_end, conn->compare_seq)) {
 +        trace_colo_compare_main("pri: this packet has compared");
 +        colo_release_primary_pkt(s, ppkt);
 +        ppkt = NULL;
 +    }
 -    ptcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
 -                  + (ptcp->th_off << 2) - ppkt->vnet_hdr_len;
 -    stcp_offset = spkt->transport_header - (uint8_t *)spkt->data
 -                  + (stcp->th_off << 2) - spkt->vnet_hdr_len;
 -    if (ppkt->size - ptcp_offset == spkt->size - stcp_offset) {
 -        res = colo_compare_packet_payload(ppkt, spkt,
 -                                          ptcp_offset, stcp_offset,
 -                                          ppkt->size - ptcp_offset);
 +    if (spkt->tcp_seq == spkt->seq_end) {
 +        packet_destroy(spkt, NULL);
 +        if (!ppkt) {
 +            goto pri;
 +        } else {
 +            goto sec;
 +        }
      } else {
 -        trace_colo_compare_main("TCP: payload size of packets are different");
 -        res = -1;
 +        if (conn->compare_seq && !after(spkt->seq_end, conn->compare_seq)) {
 +            trace_colo_compare_main("sec: this packet has compared");
 +            packet_destroy(spkt, NULL);
 +            if (!ppkt) {
 +                goto pri;
 +            } else {
 +                goto sec;
 +            }
 +        }
 +        if (!ppkt) {
 +            g_queue_push_head(&conn->secondary_list, spkt);
 +            goto pri;
 +        }
      }
 -    if (res != 0 &&
 -        trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
 -        char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
 -
--        trace_colo_compare_pkt_info_dst(inet_ntoa(ppkt->ip->ip_dst),
+-        strcpy(pri_ip_src, inet_ntoa(ppkt->ip->ip_src));
--                                        ntohl(ptcp->th_seq),
+-        strcpy(pri_ip_dst, inet_ntoa(ppkt->ip->ip_dst));
--                                        ntohl(ptcp->th_ack),
+-        strcpy(sec_ip_src, inet_ntoa(spkt->ip->ip_src));
--                                        res, ptcp->th_flags,
+-        strcpy(sec_ip_dst, inet_ntoa(spkt->ip->ip_dst));
--                                        ppkt->size);
+-
-+        char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
+-        trace_colo_compare_ip_info(ppkt->size, pri_ip_src,
-+
+-                                   pri_ip_dst, spkt->size,
-+        strcpy(pri_ip_src, inet_ntoa(ppkt->ip->ip_src));
+-                                   sec_ip_src, sec_ip_dst);
-+        strcpy(pri_ip_dst, inet_ntoa(ppkt->ip->ip_dst));
+-
-+        strcpy(sec_ip_src, inet_ntoa(spkt->ip->ip_src));
+-        trace_colo_compare_tcp_info("pri tcp packet",
-+        strcpy(sec_ip_dst, inet_ntoa(spkt->ip->ip_dst));
+-                                    ntohl(ptcp->th_seq),
-+
+-                                    ntohl(ptcp->th_ack),
-+        trace_colo_compare_ip_info(ppkt->size, pri_ip_src,
+-                                    res, ptcp->th_flags,
-+                                   pri_ip_dst, spkt->size,
+-                                    ppkt->size);
-+                                   sec_ip_src, sec_ip_dst);
+-
-+
+-        trace_colo_compare_tcp_info("sec tcp packet",
-+        trace_colo_compare_tcp_info("pri tcp packet",
+-                                    ntohl(stcp->th_seq),
-+                                    ntohl(ptcp->th_seq),
+-                                    ntohl(stcp->th_ack),
-+                                    ntohl(ptcp->th_ack),
+-                                    res, stcp->th_flags,
-+                                    res, ptcp->th_flags,
+-                                    spkt->size);
-+                                    ppkt->size);
++    if (colo_mark_tcp_pkt(ppkt, spkt, &mark, min_ack)) {
-+
++        trace_colo_compare_tcp_info("pri",
-+        trace_colo_compare_tcp_info("sec tcp packet",
++                                    ppkt->tcp_seq, ppkt->tcp_ack,
-+                                    ntohl(stcp->th_seq),
++                                    ppkt->header_size, ppkt->payload_size,
-+                                    ntohl(stcp->th_ack),
++                                    ppkt->offset, ppkt->flags);
-+                                    res, stcp->th_flags,
++
-+                                    spkt->size);
++        trace_colo_compare_tcp_info("sec",
 +                                    spkt->tcp_seq, spkt->tcp_ack,
 +                                    spkt->header_size, spkt->payload_size,
 +                                    spkt->offset, spkt->flags);
 +
 +        if (mark == COLO_COMPARE_FREE_PRIMARY) {
 +            conn->compare_seq = ppkt->seq_end;
 +            colo_release_primary_pkt(s, ppkt);
 +            g_queue_push_head(&conn->secondary_list, spkt);
 +            goto pri;
 +        }
 +        if (mark == COLO_COMPARE_FREE_SECONDARY) {
 +            conn->compare_seq = spkt->seq_end;
 +            packet_destroy(spkt, NULL);
 +            goto sec;
 +        }
 +        if (mark == (COLO_COMPARE_FREE_PRIMARY | COLO_COMPARE_FREE_SECONDARY)) {
 +            conn->compare_seq = ppkt->seq_end;
 +            colo_release_primary_pkt(s, ppkt);
 +            packet_destroy(spkt, NULL);
 +            goto pri;
 +        }
 +    } else {
 +        g_queue_push_head(&conn->primary_list, ppkt);
 +        g_queue_push_head(&conn->secondary_list, spkt);
          qemu_hexdump((char *)ppkt->data, stderr,
                       "colo-compare ppkt", ppkt->size);
+         qemu_hexdump((char *)spkt->data, stderr,
+                      "colo-compare spkt", spkt->size);
+-    }
+-    return res;
++        /*
++         * colo_compare_inconsistent_notify();
++         * TODO: notice to checkpoint();
++         */
++    }
+ }
++
+ /*
+  * Called from the compare thread on the primary
+  * for compare udp packet
+@@ -XXX,XX +XXX,XX @@ static void colo_old_packet_check(void *opaque)
+                         (GCompareFunc)colo_old_packet_check_one_conn);
+ }
+-/*
+- * Called from the compare thread on the primary
+- * for compare packet with secondary list of the
+- * specified connection when a new packet was
+- * queued to it.
+- */
+-static void colo_compare_connection(void *opaque, void *user_data)
++static void colo_compare_packet(CompareState *s, Connection *conn,
++                                int (*HandlePacket)(Packet *spkt,
++                                Packet *ppkt))
+ {
+-    CompareState *s = user_data;
+-    Connection *conn = opaque;
+     Packet *pkt = NULL;
+     GList *result = NULL;
+-    int ret;
+     while (!g_queue_is_empty(&conn->primary_list) &&
+            !g_queue_is_empty(&conn->secondary_list)) {
+         pkt = g_queue_pop_head(&conn->primary_list);
+-        switch (conn->ip_proto) {
+-        case IPPROTO_TCP:
+-            result = g_queue_find_custom(&conn->secondary_list,
+-                     pkt, (GCompareFunc)colo_packet_compare_tcp);
+-            break;
+-        case IPPROTO_UDP:
+-            result = g_queue_find_custom(&conn->secondary_list,
+-                     pkt, (GCompareFunc)colo_packet_compare_udp);
+-            break;
+-        case IPPROTO_ICMP:
+-            result = g_queue_find_custom(&conn->secondary_list,
+-                     pkt, (GCompareFunc)colo_packet_compare_icmp);
+-            break;
+-        default:
+-            result = g_queue_find_custom(&conn->secondary_list,
+-                     pkt, (GCompareFunc)colo_packet_compare_other);
+-            break;
+-        }
++        result = g_queue_find_custom(&conn->secondary_list,
++                 pkt, (GCompareFunc)HandlePacket);
+         if (result) {
+-            ret = compare_chr_send(s,
+-                                   pkt->data,
+-                                   pkt->size,
+-                                   pkt->vnet_hdr_len);
+-            if (ret < 0) {
+-                error_report("colo_send_primary_packet failed");
+-            }
+-            trace_colo_compare_main("packet same and release packet");
++            colo_release_primary_pkt(s, pkt);
+             g_queue_remove(&conn->secondary_list, result->data);
+-            packet_destroy(pkt, NULL);
+         } else {
+             /*
+              * If one packet arrive late, the secondary_list or
+@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
+     }
+ }
++/*
++ * Called from the compare thread on the primary
++ * for compare packet with secondary list of the
++ * specified connection when a new packet was
++ * queued to it.
++ */
++static void colo_compare_connection(void *opaque, void *user_data)
++{
++    CompareState *s = user_data;
++    Connection *conn = opaque;
++
++    switch (conn->ip_proto) {
++    case IPPROTO_TCP:
++        colo_compare_tcp(s, conn);
++        break;
++    case IPPROTO_UDP:
++        colo_compare_packet(s, conn, colo_packet_compare_udp);
++        break;
++    case IPPROTO_ICMP:
++        colo_compare_packet(s, conn, colo_packet_compare_icmp);
++        break;
++    default:
++        colo_compare_packet(s, conn, colo_packet_compare_other);
++        break;
++    }
++}
++
+ static int compare_chr_send(CompareState *s,
+                             const uint8_t *buf,
+                             uint32_t size,
+diff --git a/net/colo.c b/net/colo.c
+index XXXXXXX..XXXXXXX 100644
+--- a/net/colo.c
++++ b/net/colo.c
+@@ -XXX,XX +XXX,XX @@ Connection *connection_new(ConnectionKey *key)
+     conn->processing = false;
+     conn->offset = 0;
+     conn->syn_flag = 0;
++    conn->pack = 0;
++    conn->sack = 0;
+     g_queue_init(&conn->primary_list);
+     g_queue_init(&conn->secondary_list);
+@@ -XXX,XX +XXX,XX @@ Packet *packet_new(const void *data, int size, int vnet_hdr_len)
+     pkt->size = size;
+     pkt->creation_ms = qemu_clock_get_ms(QEMU_CLOCK_HOST);
+     pkt->vnet_hdr_len = vnet_hdr_len;
++    pkt->tcp_seq = 0;
++    pkt->tcp_ack = 0;
++    pkt->seq_end = 0;
++    pkt->header_size = 0;
++    pkt->payload_size = 0;
++    pkt->offset = 0;
++    pkt->flags = 0;
+     return pkt;
+ }
+diff --git a/net/colo.h b/net/colo.h
+index XXXXXXX..XXXXXXX 100644
+--- a/net/colo.h
++++ b/net/colo.h
+@@ -XXX,XX +XXX,XX @@ typedef struct Packet {
+     int64_t creation_ms;
+     /* Get vnet_hdr_len from filter */
+     uint32_t vnet_hdr_len;
++    uint32_t tcp_seq; /* sequence number */
++    uint32_t tcp_ack; /* acknowledgement number */
++    /* the sequence number of the last byte of the packet */
++    uint32_t seq_end;
++    uint8_t header_size;  /* the header length */
++    uint16_t payload_size; /* the payload length */
++    /* record the payload offset(the length that has been compared) */
++    uint16_t offset;
++    uint8_t flags; /* Flags(aka Control bits) */
+ } Packet;
+ typedef struct ConnectionKey {
+@@ -XXX,XX +XXX,XX @@ typedef struct Connection {
+     /* flag to enqueue unprocessed_connections */
+     bool processing;
+     uint8_t ip_proto;
++    /* record the sequence number that has been compared */
++    uint32_t compare_seq;
++    /* the maximum of acknowledgement number in primary_list queue */
++    uint32_t pack;
++    /* the maximum of acknowledgement number in secondary_list queue */
++    uint32_t sack;
+     /* offset = secondary_seq - primary_seq */
+     tcp_seq  offset;
+     /*
 diff --git a/net/trace-events b/net/trace-events
 index XXXXXXX..XXXXXXX 100644
 --- a/net/trace-events
 +++ b/net/trace-events
 @@ -XXX,XX +XXX,XX @@ colo_compare_icmp_miscompare(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) ""
--colo_compare_pkt_info_src(const char *src, uint32_t sseq, uint32_t sack, int res, uint32_t sflag, int ssize) "src/dst: %s s: seq/ack=%u/%u res=%d flags=%x spkt_size: %d\n"
+-colo_compare_tcp_info(const char *pkt, uint32_t seq, uint32_t ack, int res, uint32_t flag, int size) "side: %s seq/ack= %u/%u res= %d flags= 0x%x pkt_size: %d\n"
--colo_compare_pkt_info_dst(const char *dst, uint32_t dseq, uint32_t dack, int res, uint32_t dflag, int dsize) "src/dst: %s d: seq/ack=%u/%u res=%d flags=%x dpkt_size: %d\n"
++colo_compare_tcp_info(const char *pkt, uint32_t seq, uint32_t ack, int hdlen, int pdlen, int offset, int flags) "%s: seq/ack= %u/%u hdlen= %d pdlen= %d offset= %d flags=%d\n"
 +colo_compare_tcp_info(const char *pkt, uint32_t seq, uint32_t ack, int res, uint32_t flag, int size) "side: %s seq/ack= %u/%u res= %d flags= %x pkt_size: %d\n"
  # net/filter-rewriter.c
  colo_filter_rewriter_debug(void) ""
 --
 .7.4

-[Qemu-devel] [PULL 7/9] net/filter-mirror.c: Rename filter_mirror_send() and fix codestyle
+[Qemu-devel] [PULL 3/6] net: Allow hubports to connect to other netdevs
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Thomas Huth <thuth@redhat.com>
-Because filter_mirror_receive_iov() and filter_redirector_receive_iov()
+QEMU can emulate hubs to connect NICs and netdevs. This is currently
-both use the filter_mirror_send() to send packet, so I change
+primarily used for the mis-named 'vlan' feature of the networking
-filter_mirror_send() to filter_send() that looks more common.
+subsystem. Now the 'vlan' feature has been marked as deprecated, since
-And fix some codestyle.
+its name is rather confusing and the users often rather mis-configure
+their network when trying to use it. But while the 'vlan' parameter
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+should be removed at one point in time, the basic idea of emulating
 a hub in QEMU is still good: It's useful for bundling up the output of
 multiple NICs into one single l2tp netdev for example.
 Now to be able to use the hubport feature without 'vlan's, there is one
 missing piece: The possibility to connect a hubport to a netdev, too.
 This patch adds this possibility by introducing a new "netdev=..."
 parameter to the hubports.
 To bundle up the output of multiple NICs into one socket netdev, you can
 now run QEMU with these parameters for example:
 qemu-system-ppc64 ... -netdev socket,id=s1,connect=:11122 \
     -netdev hubport,hubid=1,id=h1,netdev=s1 \
     -netdev hubport,hubid=1,id=h2 -device e1000,netdev=h2 \
     -netdev hubport,hubid=1,id=h3 -device virtio-net-pci,netdev=h3
 For using the socket netdev, you have got to start another QEMU as the
 receiving side first, for example with network dumping enabled:
 qemu-system-x86_64 -M isapc -netdev socket,id=s0,listen=:11122 \
     -device ne2k_isa,netdev=s0 \
     -object filter-dump,id=f1,netdev=s0,file=/tmp/dump.dat
 After the ppc64 guest tried to boot from both NICs, you can see in the
 dump file (using Wireshark, for example), that the output of both NICs
 (the e1000 and the virtio-net-pci) has been successfully transfered
 via the socket netdev in this case.
 Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
 Signed-off-by: Thomas Huth <thuth@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/filter-mirror.c | 29 ++++++++++++++++-------------
+ net/hub.c       | 27 +++++++++++++++++++++------
-file changed, 16 insertions(+), 13 deletions(-)
+ net/hub.h       |  3 ++-
+ net/net.c       |  2 +-
-diff --git a/net/filter-mirror.c b/net/filter-mirror.c
+ qapi/net.json   |  4 +++-
-index XXXXXXX..XXXXXXX 100644
+ qemu-options.hx |  8 +++++---
---- a/net/filter-mirror.c
+files changed, 32 insertions(+), 12 deletions(-)
-+++ b/net/filter-mirror.c
-@@ -XXX,XX +XXX,XX @@ typedef struct MirrorState {
+diff --git a/net/hub.c b/net/hub.c
-     SocketReadState rs;
+index XXXXXXX..XXXXXXX 100644
- } MirrorState;
+--- a/net/hub.c
++++ b/net/hub.c
--static int filter_mirror_send(CharBackend *chr_out,
+@@ -XXX,XX +XXX,XX @@
--                              const struct iovec *iov,
+  */
--                              int iovcnt)
-+static int filter_send(CharBackend *chr_out,
+ #include "qemu/osdep.h"
-+                       const struct iovec *iov,
++#include "qapi/error.h"
-+                       int iovcnt)
+ #include "monitor/monitor.h"
  #include "net/net.h"
  #include "clients.h"
@@ -XXX,XX +XXX,XX @@ static NetClientInfo net_hub_port_info = {
      .cleanup = net_hub_port_cleanup,
  };
 -static NetHubPort *net_hub_port_new(NetHub *hub, const char *name)
 +static NetHubPort *net_hub_port_new(NetHub *hub, const char *name,
 +                                    NetClientState *hubpeer)
  {
-     int ret = 0;
+     NetClientState *nc;
-     ssize_t size = 0;
+     NetHubPort *port;
-@@ -XXX,XX +XXX,XX @@ static ssize_t filter_mirror_receive_iov(NetFilterState *nf,
+@@ -XXX,XX +XXX,XX @@ static NetHubPort *net_hub_port_new(NetHub *hub, const char *name)
-     MirrorState *s = FILTER_MIRROR(nf);
+         name = default_name;
      int ret;
 -    ret = filter_mirror_send(&s->chr_out, iov, iovcnt);
 +    ret = filter_send(&s->chr_out, iov, iovcnt);
      if (ret) {
 -        error_report("filter_mirror_send failed(%s)", strerror(-ret));
 +        error_report("filter mirror send failed(%s)", strerror(-ret));
      }
-     /*
+-    nc = qemu_new_net_client(&net_hub_port_info, NULL, "hub", name);
-@@ -XXX,XX +XXX,XX @@ static ssize_t filter_redirector_receive_iov(NetFilterState *nf,
++    nc = qemu_new_net_client(&net_hub_port_info, hubpeer, "hub", name);
-     int ret;
+     port = DO_UPCAST(NetHubPort, nc, nc);
+     port->id = id;
-     if (qemu_chr_fe_get_driver(&s->chr_out)) {
+     port->hub = hub;
--        ret = filter_mirror_send(&s->chr_out, iov, iovcnt);
+@@ -XXX,XX +XXX,XX @@ static NetHubPort *net_hub_port_new(NetHub *hub, const char *name)
-+        ret = filter_send(&s->chr_out, iov, iovcnt);
-         if (ret) {
+ /**
--            error_report("filter_mirror_send failed(%s)", strerror(-ret));
+  * Create a port on a given hub
-+            error_report("filter redirector send failed(%s)", strerror(-ret));
++ * @hub_id: Number of the hub
   * @name: Net client name or NULL for default name.
 + * @hubpeer: Peer to use (if "netdev=id" has been specified)
   *
   * If there is no existing hub with the given id then a new hub is created.
   */
 -NetClientState *net_hub_add_port(int hub_id, const char *name)
 +NetClientState *net_hub_add_port(int hub_id, const char *name,
 +                                 NetClientState *hubpeer)
  {
      NetHub *hub;
      NetHubPort *port;
@@ -XXX,XX +XXX,XX @@ NetClientState *net_hub_add_port(int hub_id, const char *name)
          hub = net_hub_new(hub_id);
      }
 -    port = net_hub_port_new(hub, name);
 +    port = net_hub_port_new(hub, name, hubpeer);
      return &port->nc;
  }
@@ -XXX,XX +XXX,XX @@ NetClientState *net_hub_port_find(int hub_id)
          }
-         return iov_size(iov, iovcnt);
+     }
-     } else {
-@@ -XXX,XX +XXX,XX @@ static char *filter_redirector_get_indev(Object *obj, Error **errp)
+-    nc = net_hub_add_port(hub_id, NULL);
-     return g_strdup(s->indev);
++    nc = net_hub_add_port(hub_id, NULL, NULL);
      return nc;
  }
--static void
+@@ -XXX,XX +XXX,XX @@ int net_init_hubport(const Netdev *netdev, const char *name,
--filter_redirector_set_indev(Object *obj, const char *value, Error **errp)
+                      NetClientState *peer, Error **errp)
 +static void filter_redirector_set_indev(Object *obj,
 +                                        const char *value,
 +                                        Error **errp)
  {
-     MirrorState *s = FILTER_REDIRECTOR(obj);
+     const NetdevHubPortOptions *hubport;
++    NetClientState *hubpeer = NULL;
-@@ -XXX,XX +XXX,XX @@ static char *filter_mirror_get_outdev(Object *obj, Error **errp)
-     return g_strdup(s->outdev);
+     assert(netdev->type == NET_CLIENT_DRIVER_HUBPORT);
      assert(!peer);
      hubport = &netdev->u.hubport;
 -    net_hub_add_port(hubport->hubid, name);
 +    if (hubport->has_netdev) {
 +        hubpeer = qemu_find_netdev(hubport->netdev);
 +        if (!hubpeer) {
 +            error_setg(errp, "netdev '%s' not found", hubport->netdev);
 +            return -1;
 +        }
 +    }
 +
 +    net_hub_add_port(hubport->hubid, name, hubpeer);
 +
      return 0;
  }
--static void
+diff --git a/net/hub.h b/net/hub.h
--filter_mirror_set_outdev(Object *obj, const char *value, Error **errp)
+index XXXXXXX..XXXXXXX 100644
-+static void filter_mirror_set_outdev(Object *obj,
+--- a/net/hub.h
-+                                     const char *value,
++++ b/net/hub.h
-+                                     Error **errp)
+@@ -XXX,XX +XXX,XX @@
- {
-     MirrorState *s = FILTER_MIRROR(obj);
+ #include "qemu-common.h"
-@@ -XXX,XX +XXX,XX @@ static char *filter_redirector_get_outdev(Object *obj, Error **errp)
+-NetClientState *net_hub_add_port(int hub_id, const char *name);
-     return g_strdup(s->outdev);
++NetClientState *net_hub_add_port(int hub_id, const char *name,
- }
++                                 NetClientState *hubpeer);
+ NetClientState *net_hub_find_client_by_name(int hub_id, const char *name);
--static void
+ void net_hub_info(Monitor *mon);
--filter_redirector_set_outdev(Object *obj, const char *value, Error **errp)
+ void net_hub_check_clients(void);
-+static void filter_redirector_set_outdev(Object *obj,
+diff --git a/net/net.c b/net/net.c
-+                                         const char *value,
+index XXXXXXX..XXXXXXX 100644
-+                                         Error **errp)
+--- a/net/net.c
- {
++++ b/net/net.c
-     MirrorState *s = FILTER_REDIRECTOR(obj);
+@@ -XXX,XX +XXX,XX @@ static int net_client_init1(const void *object, bool is_netdev, Error **errp)
          /* Do not add to a vlan if it's a nic with a netdev= parameter. */
          if (netdev->type != NET_CLIENT_DRIVER_NIC ||
              !opts->u.nic.has_netdev) {
 -            peer = net_hub_add_port(net->has_vlan ? net->vlan : 0, NULL);
 +            peer = net_hub_add_port(net->has_vlan ? net->vlan : 0, NULL, NULL);
          }
          if (net->has_vlan && !vlan_warned) {
 diff --git a/qapi/net.json b/qapi/net.json
 index XXXXXXX..XXXXXXX 100644
 --- a/qapi/net.json
 +++ b/qapi/net.json
@@ -XXX,XX +XXX,XX @@
  # Connect two or more net clients through a software hub.
  #
  # @hubid: hub identifier number
 +# @netdev: used to connect hub to a netdev instead of a device (since 2.12)
  #
  # Since: 1.2
  ##
  { 'struct': 'NetdevHubPortOptions',
    'data': {
 -    'hubid':     'int32' } }
 +    'hubid':     'int32',
 +    '*netdev':    'str' } }
  ##
  # @NetdevNetmapOptions:
 diff --git a/qemu-options.hx b/qemu-options.hx
 index XXXXXXX..XXXXXXX 100644
 --- a/qemu-options.hx
 +++ b/qemu-options.hx
@@ -XXX,XX +XXX,XX @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev,
  #endif
      "-netdev vhost-user,id=str,chardev=dev[,vhostforce=on|off]\n"
      "                configure a vhost-user network, backed by a chardev 'dev'\n"
 -    "-netdev hubport,id=str,hubid=n\n"
 +    "-netdev hubport,id=str,hubid=n[,netdev=nd]\n"
      "                configure a hub port on QEMU VLAN 'n'\n", QEMU_ARCH_ALL)
  DEF("net", HAS_ARG, QEMU_OPTION_net,
      "-net nic[,vlan=n][,netdev=nd][,macaddr=mac][,model=type][,name=str][,addr=str][,vectors=v]\n"
@@ -XXX,XX +XXX,XX @@ vde_switch -F -sock /tmp/myswitch
  qemu-system-i386 linux.img -net nic -net vde,sock=/tmp/myswitch
  @end example
 -@item -netdev hubport,id=@var{id},hubid=@var{hubid}
 +@item -netdev hubport,id=@var{id},hubid=@var{hubid}[,netdev=@var{nd}]
  Create a hub port on QEMU "vlan" @var{hubid}.
  The hubport netdev lets you connect a NIC to a QEMU "vlan" instead of a single
  netdev.  @code{-net} and @code{-device} with parameter @option{vlan} create the
 -required hub automatically.
 +required hub automatically. Alternatively, you can also connect the hubport
 +to another netdev with ID @var{nd} by using the @option{netdev=@var{nd}}
 +option.
  @item -netdev vhost-user,chardev=@var{id}[,vhostforce=on|off][,queues=n]
 --
 .7.4

-[Qemu-devel] [PULL 5/9] hmp / net: Mark host_net_add/remove as deprecated
+[Qemu-devel] [PULL 4/6] net: Allow netdevs to be used with 'hostfwd_add' and 'hostfwd_remove'
 From: Thomas Huth <thuth@redhat.com>
-The netdev_add and netdev_del commands should be used nowadays instead.
+It does not make much sense to limit these commands to the legacy 'vlan'
 concept only, they should work with the modern netdevs, too. So now
 it is possible to use this command with one, two or three parameters.
 With one parameter, the command installs a hostfwd rule on the default
 "user" network:
     hostfwd_add tcp:...
 With two parameters, the command installs a hostfwd rule on a netdev
 (that's the new way of using this command):
     hostfwd_add netdev_id tcp:...
 With three parameters, the command installs a rule on a 'vlan' (aka hub):
     hostfwd_add hub_id name tcp:...
 Same applies to the hostfwd_remove command now.
 Signed-off-by: Thomas Huth <thuth@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- hmp-commands.hx |  8 ++++----
+ hmp-commands.hx |  4 ++--
- net/net.c       | 13 +++++++++++++
+ net/slirp.c     | 33 +++++++++++++++++++++++----------
-files changed, 17 insertions(+), 4 deletions(-)
+files changed, 25 insertions(+), 12 deletions(-)
 diff --git a/hmp-commands.hx b/hmp-commands.hx
 index XXXXXXX..XXXXXXX 100644
 --- a/hmp-commands.hx
 +++ b/hmp-commands.hx
 @@ -XXX,XX +XXX,XX @@ ETEXI
-         .name       = "host_net_add",
+     {
-         .args_type  = "device:s,opts:s?",
+         .name       = "hostfwd_add",
-         .params     = "tap|user|socket|vde|netmap|bridge|vhost-user|dump [options]",
+         .args_type  = "arg1:s,arg2:s?,arg3:s?",
--        .help       = "add host VLAN client",
+-        .params     = "[vlan_id name] [tcp|udp]:[hostaddr]:hostport-[guestaddr]:guestport",
-+        .help       = "add host VLAN client (deprecated, use netdev_add instead)",
++        .params     = "[hub_id name]|[netdev_id] [tcp|udp]:[hostaddr]:hostport-[guestaddr]:guestport",
-         .cmd        = hmp_host_net_add,
+         .help       = "redirect TCP or UDP connections from host to guest (requires -net user)",
-         .command_completion = host_net_add_completion,
+         .cmd        = hmp_hostfwd_add,
      },
 @@ -XXX,XX +XXX,XX @@ ETEXI
- STEXI
- @item host_net_add
- @findex host_net_add
--Add host VLAN client.
-+Add host VLAN client. Deprecated, please use @code{netdev_add} instead.
- ETEXI
      {
-         .name       = "host_net_remove",
+         .name       = "hostfwd_remove",
-         .args_type  = "vlan_id:i,device:s",
+         .args_type  = "arg1:s,arg2:s?,arg3:s?",
-         .params     = "vlan_id name",
+-        .params     = "[vlan_id name] [tcp|udp]:[hostaddr]:hostport",
--        .help       = "remove host VLAN client",
++        .params     = "[hub_id name]|[netdev_id] [tcp|udp]:[hostaddr]:hostport",
-+        .help       = "remove host VLAN client (deprecated, use netdev_del instead)",
+         .help       = "remove host-to-guest TCP or UDP redirection",
-         .cmd        = hmp_host_net_remove,
+         .cmd        = hmp_hostfwd_remove,
          .command_completion = host_net_remove_completion,
      },
-@@ -XXX,XX +XXX,XX @@ ETEXI
+diff --git a/net/slirp.c b/net/slirp.c
  STEXI
  @item host_net_remove
  @findex host_net_remove
 -Remove host VLAN client.
 +Remove host VLAN client. Deprecated, please use @code{netdev_del} instead.
  ETEXI
      {
 diff --git a/net/net.c b/net/net.c
 index XXXXXXX..XXXXXXX 100644
---- a/net/net.c
+--- a/net/slirp.c
-+++ b/net/net.c
++++ b/net/slirp.c
-@@ -XXX,XX +XXX,XX @@
+@@ -XXX,XX +XXX,XX @@ error:
- #include "qapi-visit.h"
+     return -1;
- #include "qapi/opts-visitor.h"
+ }
- #include "sysemu/sysemu.h"
-+#include "sysemu/qtest.h"
+-static SlirpState *slirp_lookup(Monitor *mon, const char *vlan,
- #include "net/filter.h"
+-                                const char *stack)
- #include "qapi/string-output-visitor.h"
++static SlirpState *slirp_lookup(Monitor *mon, const char *hub_id,
++                                const char *name)
-@@ -XXX,XX +XXX,XX @@ void hmp_host_net_add(Monitor *mon, const QDict *qdict)
+ {
-     const char *opts_str = qdict_get_try_str(qdict, "opts");
+-
-     Error *local_err = NULL;
+-    if (vlan) {
-     QemuOpts *opts;
++    if (name) {
-+    static bool warned;
+         NetClientState *nc;
-+
+-        nc = net_hub_find_client_by_name(strtol(vlan, NULL, 0), stack);
-+    if (!warned && !qtest_enabled()) {
+-        if (!nc) {
-+        error_report("host_net_add is deprecated, use netdev_add instead");
+-            monitor_printf(mon, "unrecognized (vlan-id, stackname) pair\n");
-+        warned = true;
+-            return NULL;
-+    }
++        if (hub_id) {
++            nc = net_hub_find_client_by_name(strtol(hub_id, NULL, 0), name);
-     if (!net_host_check_device(device)) {
++            if (!nc) {
-         monitor_printf(mon, "invalid host network device %s\n", device);
++                monitor_printf(mon, "unrecognized (vlan-id, stackname) pair\n");
-@@ -XXX,XX +XXX,XX @@ void hmp_host_net_remove(Monitor *mon, const QDict *qdict)
++                return NULL;
-     NetClientState *nc;
++            }
-     int vlan_id = qdict_get_int(qdict, "vlan_id");
++        } else {
-     const char *device = qdict_get_str(qdict, "device");
++            nc = qemu_find_netdev(name);
-+    static bool warned;
++            if (!nc) {
-+
++                monitor_printf(mon, "unrecognized netdev id '%s'\n", name);
-+    if (!warned && !qtest_enabled()) {
++                return NULL;
-+        error_report("host_net_remove is deprecated, use netdev_del instead");
++            }
-+        warned = true;
+         }
-+    }
+         if (strcmp(nc->model, "user")) {
+             monitor_printf(mon, "invalid device specified\n");
-     nc = net_hub_find_client_by_name(vlan_id, device);
+@@ -XXX,XX +XXX,XX @@ void hmp_hostfwd_remove(Monitor *mon, const QDict *qdict)
-     if (!nc) {
+     const char *arg2 = qdict_get_try_str(qdict, "arg2");
      const char *arg3 = qdict_get_try_str(qdict, "arg3");
 -    if (arg2) {
 +    if (arg3) {
          s = slirp_lookup(mon, arg1, arg2);
          src_str = arg3;
 +    } else if (arg2) {
 +        s = slirp_lookup(mon, NULL, arg1);
 +        src_str = arg2;
      } else {
          s = slirp_lookup(mon, NULL, NULL);
          src_str = arg1;
@@ -XXX,XX +XXX,XX @@ void hmp_hostfwd_add(Monitor *mon, const QDict *qdict)
      const char *arg2 = qdict_get_try_str(qdict, "arg2");
      const char *arg3 = qdict_get_try_str(qdict, "arg3");
 -    if (arg2) {
 +    if (arg3) {
          s = slirp_lookup(mon, arg1, arg2);
          redir_str = arg3;
 +    } else if (arg2) {
 +        s = slirp_lookup(mon, NULL, arg1);
 +        redir_str = arg2;
      } else {
          s = slirp_lookup(mon, NULL, NULL);
          redir_str = arg1;
 --
 .7.4

-[Qemu-devel] [PULL 8/9] net/filter-rewriter: Remove unused option in filter-rewriter
+[Qemu-devel] [PULL 5/6] qemu-doc: Get rid of "vlan=X" example in the documentation
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Thomas Huth <thuth@redhat.com>
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+The vlan concept is marked as deprecated, so we should not use
 this for examples in the documentation anymore.
 Signed-off-by: Thomas Huth <thuth@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- qemu-options.hx | 2 +-
+ qemu-options.hx | 4 ++--
-file changed, 1 insertion(+), 1 deletion(-)
+file changed, 2 insertions(+), 2 deletions(-)
 diff --git a/qemu-options.hx b/qemu-options.hx
 index XXXXXXX..XXXXXXX 100644
 --- a/qemu-options.hx
 +++ b/qemu-options.hx
-@@ -XXX,XX +XXX,XX @@ Create a filter-redirector we need to differ outdev id from indev id, id can not
+@@ -XXX,XX +XXX,XX @@ qemu-system-i386 linux.img -net nic -net tap
- be the same. we can just use indev or outdev, but at least one of indev or outdev
+ #launch a QEMU instance with two NICs, each one connected
- need to be specified.
+ #to a TAP device
+ qemu-system-i386 linux.img \
--@item -object filter-rewriter,id=@var{id},netdev=@var{netdevid},rewriter-mode=@var{mode}[,queue=@var{all|rx|tx}]
+-                 -net nic,vlan=0 -net tap,vlan=0,ifname=tap0 \
-+@item -object filter-rewriter,id=@var{id},netdev=@var{netdevid}[,queue=@var{all|rx|tx}]
+-                 -net nic,vlan=1 -net tap,vlan=1,ifname=tap1
++        -netdev tap,id=nd0,ifname=tap0 -device e1000,netdev=nd0 \
- Filter-rewriter is a part of COLO project.It will rewrite tcp packet to
++        -netdev tap,id=nd1,ifname=tap1 -device rtl8139,netdev=nd1
- secondary from primary to keep secondary tcp connection,and rewrite
+ @end example
  @example
 --
 .7.4

-[Qemu-devel] [PULL 3/9] virtio-net: fix wild pointer when remove virtio-net queues
+[Qemu-devel] [PULL 6/6] MAINTAINERS: update Dmitry Fleytman email
-From: Yunjian Wang <wangyunjian@huawei.com>
+From: Philippe Mathieu-Daudé <f4bug@amsat.org>
-The tx_bh or tx_timer will free in virtio_net_del_queue() function, when
+gently asked by his automatic reply :)
 removing virtio-net queues if the guest doesn't support multiqueue. But
 it might be still referenced by virtio_net_set_status(), which needs to
 be set NULL. And also the tx_waiting needs to be set zero to prevent
 virtio_net_set_status() accessing tx_bh or tx_timer.
-Cc: qemu-stable@nongnu.org
+Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
 Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- hw/net/virtio-net.c | 3 +++
+ MAINTAINERS | 8 ++++----
-file changed, 3 insertions(+)
+file changed, 4 insertions(+), 4 deletions(-)
-diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
+diff --git a/MAINTAINERS b/MAINTAINERS
 index XXXXXXX..XXXXXXX 100644
---- a/hw/net/virtio-net.c
+--- a/MAINTAINERS
-+++ b/hw/net/virtio-net.c
++++ b/MAINTAINERS
-@@ -XXX,XX +XXX,XX @@ static void virtio_net_del_queue(VirtIONet *n, int index)
+@@ -XXX,XX +XXX,XX @@ F: hw/scsi/mfi.h
-     if (q->tx_timer) {
+ F: tests/megasas-test.c
-         timer_del(q->tx_timer);
-         timer_free(q->tx_timer);
+ Network packet abstractions
-+        q->tx_timer = NULL;
+-M: Dmitry Fleytman <dmitry@daynix.com>
-     } else {
++M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
-         qemu_bh_delete(q->tx_bh);
+ S: Maintained
-+        q->tx_bh = NULL;
+ F: include/net/eth.h
-     }
+ F: net/eth.c
-+    q->tx_waiting = 0;
+@@ -XXX,XX +XXX,XX @@ F: hw/net/net_rx_pkt*
-     virtio_del_queue(vdev, index * 2 + 1);
+ F: hw/net/net_tx_pkt*
- }
  Vmware
 -M: Dmitry Fleytman <dmitry@daynix.com>
 +M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
  S: Maintained
  F: hw/net/vmxnet*
  F: hw/scsi/vmw_pvscsi*
@@ -XXX,XX +XXX,XX @@ F: hw/mem/nvdimm.c
  F: include/hw/mem/nvdimm.h
  e1000x
 -M: Dmitry Fleytman <dmitry@daynix.com>
 +M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
  S: Maintained
  F: hw/net/e1000x*
  e1000e
 -M: Dmitry Fleytman <dmitry@daynix.com>
 +M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
  S: Maintained
  F: hw/net/e1000e*
 --
 .7.4

-[Qemu-devel] [PULL 6/9] net/filter-mirror.c: Remove duplicate check code.
+Deleted patch
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-The s->outdev have checked in filter_mirror_set_outdev().
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
----
- net/filter-mirror.c | 6 ------
-file changed, 6 deletions(-)
-diff --git a/net/filter-mirror.c b/net/filter-mirror.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/filter-mirror.c
-+++ b/net/filter-mirror.c
-@@ -XXX,XX +XXX,XX @@ static void filter_mirror_setup(NetFilterState *nf, Error **errp)
-     MirrorState *s = FILTER_MIRROR(nf);
-     Chardev *chr;
--    if (!s->outdev) {
--        error_setg(errp, "filter mirror needs 'outdev' "
--                   "property set");
--        return;
--    }
--
-     chr = qemu_chr_find(s->outdev);
-     if (chr == NULL) {
-         error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
---
-.7.4

The following changes since commit 56821559f0ba682fe6b367815572e6f974d329ab:

Merge remote-tracking branch 'dgilbert/tags/pull-hmp-20170517' into staging (2017-05-18 13:36:15 +0100)

are available in the git repository at:

https://github.com/jasowang/qemu.git tags/net-pull-request

for you to fetch changes up to 82342e91b60a4a078811df4e1a545e57abffa11d:

e1000e: Fix ICR "Other" causes clear logic (2017-05-23 10:10:38 +0800)

----------------------------------------------------------------

----------------------------------------------------------------
Sameeh Jubran (1):
      e1000e: Fix ICR "Other" causes clear logic

Thomas Huth (3):
      net/tap: Replace tap-haiku.c and tap-aix.c by a generic tap-stub.c
      net/dump: Issue a warning for the deprecated "-net dump"
      hmp / net: Mark host_net_add/remove as deprecated

Yunjian Wang (1):
      virtio-net: fix wild pointer when remove virtio-net queues

Zhang Chen (4):
      COLO-compare: Improve tcp compare trace event readability
      net/filter-mirror.c: Remove duplicate check code.
      net/filter-mirror.c: Rename filter_mirror_send() and fix codestyle
      net/filter-rewriter: Remove unused option in filter-rewriter

hmp-commands.hx               |  8 ++--
 hw/net/e1000e_core.c          | 10 ++++-
 hw/net/virtio-net.c           |  3 ++
 net/Makefile.objs             | 15 ++++----
 net/colo-compare.c            | 33 ++++++++++------
 net/dump.c                    |  3 ++
 net/filter-mirror.c           | 35 ++++++++---------
 net/net.c                     | 13 +++++++
 net/tap-haiku.c               | 87 -------------------------------------------
 net/{tap-aix.c => tap-stub.c} |  3 +-
 net/trace-events              |  3 +-
 qemu-options.hx               |  2 +-
 12 files changed, 80 insertions(+), 135 deletions(-)
 delete mode 100644 net/tap-haiku.c
 rename net/{tap-aix.c => tap-stub.c} (97%)

From: Thomas Huth <thuth@redhat.com>

The files tap-haiku.c and tap-aix.c are identical (except one line
of error message). We should avoid such code duplication, so replace
these by a generic tap-stub.c file instead.

Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/Makefile.objs | 15 +++++-----
 net/tap-aix.c     | 88 -------------------------------------------------------
 net/tap-haiku.c   | 87 ------------------------------------------------------
 net/tap-stub.c    | 87 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 95 insertions(+), 182 deletions(-)
 delete mode 100644 net/tap-aix.c
 delete mode 100644 net/tap-haiku.c
 create mode 100644 net/tap-stub.c

diff --git a/net/Makefile.objs b/net/Makefile.objs
index XXXXXXX..XXXXXXX 100644
--- a/net/Makefile.objs
+++ b/net/Makefile.objs
@@ -XXX,XX +XXX,XX @@ common-obj-y += socket.o
 common-obj-y += dump.o
 common-obj-y += eth.o
 common-obj-$(CONFIG_L2TPV3) += l2tpv3.o
-common-obj-$(CONFIG_POSIX) += tap.o vhost-user.o
-common-obj-$(CONFIG_LINUX) += tap-linux.o
-common-obj-$(CONFIG_WIN32) += tap-win32.o
-common-obj-$(CONFIG_BSD) += tap-bsd.o
-common-obj-$(CONFIG_SOLARIS) += tap-solaris.o
-common-obj-$(CONFIG_AIX) += tap-aix.o
-common-obj-$(CONFIG_HAIKU) += tap-haiku.o
+common-obj-$(CONFIG_POSIX) += vhost-user.o
 common-obj-$(CONFIG_SLIRP) += slirp.o
 common-obj-$(CONFIG_VDE) += vde.o
 common-obj-$(CONFIG_NETMAP) += netmap.o
@@ -XXX,XX +XXX,XX @@ common-obj-y += colo-compare.o
 common-obj-y += colo.o
 common-obj-y += filter-rewriter.o
 common-obj-y += filter-replay.o
+
+tap-obj-$(CONFIG_LINUX) = tap-linux.o
+tap-obj-$(CONFIG_BSD) = tap-bsd.o
+tap-obj-$(CONFIG_SOLARIS) = tap-solaris.o
+tap-obj-y ?= tap-stub.o
+common-obj-$(CONFIG_POSIX) += tap.o $(tap-obj-y)
+common-obj-$(CONFIG_WIN32) += tap-win32.o
diff --git a/net/tap-aix.c b/net/tap-aix.c
deleted file mode 100644
index XXXXXXX..XXXXXXX
--- a/net/tap-aix.c
+++ /dev/null
@@ -XXX,XX +XXX,XX @@
-/*
- * QEMU System Emulator
- *
- * Copyright (c) 2003-2008 Fabrice Bellard
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
- */
-
-#include "qemu/osdep.h"
-#include "qapi/error.h"
-#include "tap_int.h"
-
-int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
-             int vnet_hdr_required, int mq_required, Error **errp)
-{
-    error_setg(errp, "no tap on AIX");
-    return -1;
-}
-
-void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
-{
-}
-
-int tap_probe_vnet_hdr(int fd)
-{
-    return 0;
-}
-
-int tap_probe_has_ufo(int fd)
-{
-    return 0;
-}
-
-int tap_probe_vnet_hdr_len(int fd, int len)
-{
-    return 0;
-}
-
-void tap_fd_set_vnet_hdr_len(int fd, int len)
-{
-}
-
-int tap_fd_set_vnet_le(int fd, int is_le)
-{
-    return -EINVAL;
-}
-
-int tap_fd_set_vnet_be(int fd, int is_be)
-{
-    return -EINVAL;
-}
-
-void tap_fd_set_offload(int fd, int csum, int tso4,
-                        int tso6, int ecn, int ufo)
-{
-}
-
-int tap_fd_enable(int fd)
-{
-    return -1;
-}
-
-int tap_fd_disable(int fd)
-{
-    return -1;
-}
-
-int tap_fd_get_ifname(int fd, char *ifname)
-{
-    return -1;
-}
-
diff --git a/net/tap-haiku.c b/net/tap-haiku.c
deleted file mode 100644
index XXXXXXX..XXXXXXX
--- a/net/tap-haiku.c
+++ /dev/null
@@ -XXX,XX +XXX,XX @@
-/*
- * QEMU System Emulator
- *
- * Copyright (c) 2003-2008 Fabrice Bellard
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
- */
-
-#include "qemu/osdep.h"
-#include "qapi/error.h"
-#include "tap_int.h"
-
-int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
-             int vnet_hdr_required, int mq_required, Error **errp)
-{
-    error_setg(errp, "no tap on Haiku");
-    return -1;
-}
-
-void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
-{
-}
-
-int tap_probe_vnet_hdr(int fd)
-{
-    return 0;
-}
-
-int tap_probe_has_ufo(int fd)
-{
-    return 0;
-}
-
-int tap_probe_vnet_hdr_len(int fd, int len)
-{
-    return 0;
-}
-
-void tap_fd_set_vnet_hdr_len(int fd, int len)
-{
-}
-
-int tap_fd_set_vnet_le(int fd, int is_le)
-{
-    return -EINVAL;
-}
-
-int tap_fd_set_vnet_be(int fd, int is_be)
-{
-    return -EINVAL;
-}
-
-void tap_fd_set_offload(int fd, int csum, int tso4,
-                        int tso6, int ecn, int ufo)
-{
-}
-
-int tap_fd_enable(int fd)
-{
-    return -1;
-}
-
-int tap_fd_disable(int fd)
-{
-    return -1;
-}
-
-int tap_fd_get_ifname(int fd, char *ifname)
-{
-    return -1;
-}
diff --git a/net/tap-stub.c b/net/tap-stub.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/net/tap-stub.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * QEMU System Emulator
+ *
+ * Copyright (c) 2003-2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "tap_int.h"
+
+int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
+             int vnet_hdr_required, int mq_required, Error **errp)
+{
+    error_setg(errp, "tap is not supported in this build");
+    return -1;
+}
+
+void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
+{
+}
+
+int tap_probe_vnet_hdr(int fd)
+{
+    return 0;
+}
+
+int tap_probe_has_ufo(int fd)
+{
+    return 0;
+}
+
+int tap_probe_vnet_hdr_len(int fd, int len)
+{
+    return 0;
+}
+
+void tap_fd_set_vnet_hdr_len(int fd, int len)
+{
+}
+
+int tap_fd_set_vnet_le(int fd, int is_le)
+{
+    return -EINVAL;
+}
+
+int tap_fd_set_vnet_be(int fd, int is_be)
+{
+    return -EINVAL;
+}
+
+void tap_fd_set_offload(int fd, int csum, int tso4,
+                        int tso6, int ecn, int ufo)
+{
+}
+
+int tap_fd_enable(int fd)
+{
+    return -1;
+}
+
+int tap_fd_disable(int fd)
+{
+    return -1;
+}
+
+int tap_fd_get_ifname(int fd, char *ifname)
+{
+    return -1;
+}
-- 
2.7.4

From: Yunjian Wang <wangyunjian@huawei.com>

The tx_bh or tx_timer will free in virtio_net_del_queue() function, when
removing virtio-net queues if the guest doesn't support multiqueue. But
it might be still referenced by virtio_net_set_status(), which needs to
be set NULL. And also the tx_waiting needs to be set zero to prevent
virtio_net_set_status() accessing tx_bh or tx_timer.

Cc: qemu-stable@nongnu.org
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/virtio-net.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -XXX,XX +XXX,XX @@ static void virtio_net_del_queue(VirtIONet *n, int index)
     if (q->tx_timer) {
         timer_del(q->tx_timer);
         timer_free(q->tx_timer);
+        q->tx_timer = NULL;
     } else {
         qemu_bh_delete(q->tx_bh);
+        q->tx_bh = NULL;
     }
+    q->tx_waiting = 0;
     virtio_del_queue(vdev, index * 2 + 1);
 }
 
-- 
2.7.4

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

Because of previous patch's trace arguments over the limit
of UST backend, so I rewrite the patch.

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/colo-compare.c | 33 ++++++++++++++++++++++-----------
 net/trace-events   |  3 +--
 2 files changed, 23 insertions(+), 13 deletions(-)

diff --git a/net/colo-compare.c b/net/colo-compare.c
index XXXXXXX..XXXXXXX 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
     }
 
     if (res != 0 && trace_event_get_state(TRACE_COLO_COMPARE_MISCOMPARE)) {
-        trace_colo_compare_pkt_info_src(inet_ntoa(ppkt->ip->ip_src),
-                                        ntohl(stcp->th_seq),
-                                        ntohl(stcp->th_ack),
-                                        res, stcp->th_flags,
-                                        spkt->size);
-
-        trace_colo_compare_pkt_info_dst(inet_ntoa(ppkt->ip->ip_dst),
-                                        ntohl(ptcp->th_seq),
-                                        ntohl(ptcp->th_ack),
-                                        res, ptcp->th_flags,
-                                        ppkt->size);
+        char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
+
+        strcpy(pri_ip_src, inet_ntoa(ppkt->ip->ip_src));
+        strcpy(pri_ip_dst, inet_ntoa(ppkt->ip->ip_dst));
+        strcpy(sec_ip_src, inet_ntoa(spkt->ip->ip_src));
+        strcpy(sec_ip_dst, inet_ntoa(spkt->ip->ip_dst));
+
+        trace_colo_compare_ip_info(ppkt->size, pri_ip_src,
+                                   pri_ip_dst, spkt->size,
+                                   sec_ip_src, sec_ip_dst);
+
+        trace_colo_compare_tcp_info("pri tcp packet",
+                                    ntohl(ptcp->th_seq),
+                                    ntohl(ptcp->th_ack),
+                                    res, ptcp->th_flags,
+                                    ppkt->size);
+
+        trace_colo_compare_tcp_info("sec tcp packet",
+                                    ntohl(stcp->th_seq),
+                                    ntohl(stcp->th_ack),
+                                    res, stcp->th_flags,
+                                    spkt->size);
 
         qemu_hexdump((char *)ppkt->data, stderr,
                      "colo-compare ppkt", ppkt->size);
diff --git a/net/trace-events b/net/trace-events
index XXXXXXX..XXXXXXX 100644
--- a/net/trace-events
+++ b/net/trace-events
@@ -XXX,XX +XXX,XX @@ colo_compare_icmp_miscompare(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) ""
-colo_compare_pkt_info_src(const char *src, uint32_t sseq, uint32_t sack, int res, uint32_t sflag, int ssize) "src/dst: %s s: seq/ack=%u/%u res=%d flags=%x spkt_size: %d\n"
-colo_compare_pkt_info_dst(const char *dst, uint32_t dseq, uint32_t dack, int res, uint32_t dflag, int dsize) "src/dst: %s d: seq/ack=%u/%u res=%d flags=%x dpkt_size: %d\n"
+colo_compare_tcp_info(const char *pkt, uint32_t seq, uint32_t ack, int res, uint32_t flag, int size) "side: %s seq/ack= %u/%u res= %d flags= %x pkt_size: %d\n"
 
 # net/filter-rewriter.c
 colo_filter_rewriter_debug(void) ""
-- 
2.7.4

From: Thomas Huth <thuth@redhat.com>

The netdev_add and netdev_del commands should be used nowadays instead.

Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hmp-commands.hx |  8 ++++----
 net/net.c       | 13 +++++++++++++
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/hmp-commands.hx b/hmp-commands.hx
index XXXXXXX..XXXXXXX 100644
--- a/hmp-commands.hx
+++ b/hmp-commands.hx
@@ -XXX,XX +XXX,XX @@ ETEXI
         .name       = "host_net_add",
         .args_type  = "device:s,opts:s?",
         .params     = "tap|user|socket|vde|netmap|bridge|vhost-user|dump [options]",
-        .help       = "add host VLAN client",
+        .help       = "add host VLAN client (deprecated, use netdev_add instead)",
         .cmd        = hmp_host_net_add,
         .command_completion = host_net_add_completion,
     },
@@ -XXX,XX +XXX,XX @@ ETEXI
 STEXI
 @item host_net_add
 @findex host_net_add
-Add host VLAN client.
+Add host VLAN client. Deprecated, please use @code{netdev_add} instead.
 ETEXI
 
     {
         .name       = "host_net_remove",
         .args_type  = "vlan_id:i,device:s",
         .params     = "vlan_id name",
-        .help       = "remove host VLAN client",
+        .help       = "remove host VLAN client (deprecated, use netdev_del instead)",
         .cmd        = hmp_host_net_remove,
         .command_completion = host_net_remove_completion,
     },
@@ -XXX,XX +XXX,XX @@ ETEXI
 STEXI
 @item host_net_remove
 @findex host_net_remove
-Remove host VLAN client.
+Remove host VLAN client. Deprecated, please use @code{netdev_del} instead.
 ETEXI
 
     {
diff --git a/net/net.c b/net/net.c
index XXXXXXX..XXXXXXX 100644
--- a/net/net.c
+++ b/net/net.c
@@ -XXX,XX +XXX,XX @@
 #include "qapi-visit.h"
 #include "qapi/opts-visitor.h"
 #include "sysemu/sysemu.h"
+#include "sysemu/qtest.h"
 #include "net/filter.h"
 #include "qapi/string-output-visitor.h"
 
@@ -XXX,XX +XXX,XX @@ void hmp_host_net_add(Monitor *mon, const QDict *qdict)
     const char *opts_str = qdict_get_try_str(qdict, "opts");
     Error *local_err = NULL;
     QemuOpts *opts;
+    static bool warned;
+
+    if (!warned && !qtest_enabled()) {
+        error_report("host_net_add is deprecated, use netdev_add instead");
+        warned = true;
+    }
 
     if (!net_host_check_device(device)) {
         monitor_printf(mon, "invalid host network device %s\n", device);
@@ -XXX,XX +XXX,XX @@ void hmp_host_net_remove(Monitor *mon, const QDict *qdict)
     NetClientState *nc;
     int vlan_id = qdict_get_int(qdict, "vlan_id");
     const char *device = qdict_get_str(qdict, "device");
+    static bool warned;
+
+    if (!warned && !qtest_enabled()) {
+        error_report("host_net_remove is deprecated, use netdev_del instead");
+        warned = true;
+    }
 
     nc = net_hub_find_client_by_name(vlan_id, device);
     if (!nc) {
-- 
2.7.4

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

Because filter_mirror_receive_iov() and filter_redirector_receive_iov()
both use the filter_mirror_send() to send packet, so I change
filter_mirror_send() to filter_send() that looks more common.
And fix some codestyle.

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/filter-mirror.c | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/net/filter-mirror.c b/net/filter-mirror.c
index XXXXXXX..XXXXXXX 100644
--- a/net/filter-mirror.c
+++ b/net/filter-mirror.c
@@ -XXX,XX +XXX,XX @@ typedef struct MirrorState {
     SocketReadState rs;
 } MirrorState;
 
-static int filter_mirror_send(CharBackend *chr_out,
-                              const struct iovec *iov,
-                              int iovcnt)
+static int filter_send(CharBackend *chr_out,
+                       const struct iovec *iov,
+                       int iovcnt)
 {
     int ret = 0;
     ssize_t size = 0;
@@ -XXX,XX +XXX,XX @@ static ssize_t filter_mirror_receive_iov(NetFilterState *nf,
     MirrorState *s = FILTER_MIRROR(nf);
     int ret;
 
-    ret = filter_mirror_send(&s->chr_out, iov, iovcnt);
+    ret = filter_send(&s->chr_out, iov, iovcnt);
     if (ret) {
-        error_report("filter_mirror_send failed(%s)", strerror(-ret));
+        error_report("filter mirror send failed(%s)", strerror(-ret));
     }
 
     /*
@@ -XXX,XX +XXX,XX @@ static ssize_t filter_redirector_receive_iov(NetFilterState *nf,
     int ret;
 
     if (qemu_chr_fe_get_driver(&s->chr_out)) {
-        ret = filter_mirror_send(&s->chr_out, iov, iovcnt);
+        ret = filter_send(&s->chr_out, iov, iovcnt);
         if (ret) {
-            error_report("filter_mirror_send failed(%s)", strerror(-ret));
+            error_report("filter redirector send failed(%s)", strerror(-ret));
         }
         return iov_size(iov, iovcnt);
     } else {
@@ -XXX,XX +XXX,XX @@ static char *filter_redirector_get_indev(Object *obj, Error **errp)
     return g_strdup(s->indev);
 }
 
-static void
-filter_redirector_set_indev(Object *obj, const char *value, Error **errp)
+static void filter_redirector_set_indev(Object *obj,
+                                        const char *value,
+                                        Error **errp)
 {
     MirrorState *s = FILTER_REDIRECTOR(obj);
 
@@ -XXX,XX +XXX,XX @@ static char *filter_mirror_get_outdev(Object *obj, Error **errp)
     return g_strdup(s->outdev);
 }
 
-static void
-filter_mirror_set_outdev(Object *obj, const char *value, Error **errp)
+static void filter_mirror_set_outdev(Object *obj,
+                                     const char *value,
+                                     Error **errp)
 {
     MirrorState *s = FILTER_MIRROR(obj);
 
@@ -XXX,XX +XXX,XX @@ static char *filter_redirector_get_outdev(Object *obj, Error **errp)
     return g_strdup(s->outdev);
 }
 
-static void
-filter_redirector_set_outdev(Object *obj, const char *value, Error **errp)
+static void filter_redirector_set_outdev(Object *obj,
+                                         const char *value,
+                                         Error **errp)
 {
     MirrorState *s = FILTER_REDIRECTOR(obj);
 
-- 
2.7.4

From: Sameeh Jubran <sameeh@daynix.com>

This commit fixes a bug which causes the guest to hang. The bug was
observed upon a "receive overrun" (bit #6 of the ICR register)
interrupt which could be triggered post migration in a heavy traffic
environment. Even though the "receive overrun" bit (#6) is masked out
by the IMS register (refer to the log below) the driver still receives
an interrupt as the "receive overrun" bit (#6) causes the "Other" -
bit #24 of the ICR register - bit to be set as documented below. The
driver handles the interrupt and clears the "Other" bit (#24) but
doesn't clear the "receive overrun" bit (#6) which leads to an
infinite loop. Apparently the Windows driver expects that the "receive
overrun" bit and other ones - documented below - to be cleared when
the "Other" bit (#24) is cleared.

So to sum that up:
1. Bit #6 of the ICR register is set by heavy traffic
2. As a results of setting bit #6, bit #24 is set
3. The driver receives an interrupt for bit 24 (it doesn't receieve an
   interrupt for bit #6 as it is masked out by IMS)
4. The driver handles and clears the interrupt of bit #24
5. Bit #6 is still set.
6. 2 happens all over again

The Interrupt Cause Read - ICR register:

The ICR has the "Other" bit - bit #24 - that is set when one or more
of the following ICR register's bits are set:

LSC - bit #2, RXO - bit #6, MDAC - bit #9, SRPD - bit #16, ACK - bit
#17, MNG - bit #18

This bug can occur with any of these bits depending on the driver's
behaviour and the way it configures the device. However, trying to
reproduce it with any bit other than RX0 is challenging and came to
failure as the drivers don't implement most of these bits, trying to
reproduce it with LSC (Link Status Change - bit #2) bit didn't succeed
too as it seems that Windows handles this bit differently.

Log sample of the storm:

27563@1494850819.411877:e1000e_irq_pending_interrupts ICR PENDING: 0x1000000 (ICR: 0x815000c2, IMS: 0x1a00004)
27563@1494850819.411900:e1000e_irq_pending_interrupts ICR PENDING: 0x0 (ICR: 0x815000c2, IMS: 0xa00004)
27563@1494850819.411915:e1000e_irq_pending_interrupts ICR PENDING: 0x0 (ICR: 0x815000c2, IMS: 0xa00004)
27563@1494850819.412380:e1000e_irq_pending_interrupts ICR PENDING: 0x0 (ICR: 0x815000c2, IMS: 0xa00004)
27563@1494850819.412395:e1000e_irq_pending_interrupts ICR PENDING: 0x0 (ICR: 0x815000c2, IMS: 0xa00004)
27563@1494850819.412436:e1000e_irq_pending_interrupts ICR PENDING: 0x0 (ICR: 0x815000c2, IMS: 0xa00004)
27563@1494850819.412441:e1000e_irq_pending_interrupts ICR PENDING: 0x0 (ICR: 0x815000c2, IMS: 0xa00004)
27563@1494850819.412998:e1000e_irq_pending_interrupts ICR PENDING: 0x1000000 (ICR: 0x815000c2, IMS: 0x1a00004)

* This bug behaviour wasn't observed with the Linux driver.

This commit solves:
https://bugzilla.redhat.com/show_bug.cgi?id=1447935
https://bugzilla.redhat.com/show_bug.cgi?id=1449490

Cc: qemu-stable@nongnu.org
Signed-off-by: Sameeh Jubran <sjubran@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/e1000e_core.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/hw/net/e1000e_core.c b/hw/net/e1000e_core.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/e1000e_core.c
+++ b/hw/net/e1000e_core.c
@@ -XXX,XX +XXX,XX @@ e1000e_set_ics(E1000ECore *core, int index, uint32_t val)
 static void
 e1000e_set_icr(E1000ECore *core, int index, uint32_t val)
 {
+    uint32_t icr = 0;
     if ((core->mac[ICR] & E1000_ICR_ASSERTED) &&
         (core->mac[CTRL_EXT] & E1000_CTRL_EXT_IAME)) {
         trace_e1000e_irq_icr_process_iame();
         e1000e_clear_ims_bits(core, core->mac[IAM]);
     }
 
-    trace_e1000e_irq_icr_write(val, core->mac[ICR], core->mac[ICR] & ~val);
-    core->mac[ICR] &= ~val;
+    icr = core->mac[ICR] & ~val;
+    /* Windows driver expects that the "receive overrun" bit and other
+     * ones to be cleared when the "Other" bit (#24) is cleared.
+     */
+    icr = (val & E1000_ICR_OTHER) ? (icr & ~E1000_ICR_OTHER_CAUSES) : icr;
+    trace_e1000e_irq_icr_write(val, core->mac[ICR], icr);
+    core->mac[ICR] = icr;
     e1000e_update_interrupt_state(core);
 }
 
-- 
2.7.4

The following changes since commit e607bbee553cfe73072870cef458cfa4e78133e2:

Merge remote-tracking branch 'remotes/edgar/tags/edgar/xilinx-next-2018-01-26.for-upstream' into staging (2018-01-26 14:24:25 +0000)

are available in the git repository at:

https://github.com/jasowang/qemu.git tags/net-pull-request

for you to fetch changes up to bf4835a4d5338bb7424827715df22570a8adc67c:

MAINTAINERS: update Dmitry Fleytman email (2018-01-29 16:05:38 +0800)

----------------------------------------------------------------

----------------------------------------------------------------
Mao Zhongyi (2):
      colo: modified the payload compare function
      colo: compare the packet based on the tcp sequence number

Philippe Mathieu-Daudé (1):
      MAINTAINERS: update Dmitry Fleytman email

Thomas Huth (3):
      net: Allow hubports to connect to other netdevs
      net: Allow netdevs to be used with 'hostfwd_add' and 'hostfwd_remove'
      qemu-doc: Get rid of "vlan=X" example in the documentation

From: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>

Modified the function colo_packet_compare_common to prepare for the
tcp packet comparison in the next patch.

Cc: Zhang Chen <zhangckid@gmail.com>
Cc: Li Zhijian <lizhijian@cn.fujitsu.com>
Cc: Jason Wang <jasowang@redhat.com>

Signed-off-by: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Signed-off-by: Zhang Chen <zhangckid@gmail.com>
Reviewed-by: Zhang Chen <zhangckid@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/colo-compare.c | 88 +++++++++++++++++++++++++++---------------------------
 1 file changed, 44 insertions(+), 44 deletions(-)

diff --git a/net/colo-compare.c b/net/colo-compare.c
index XXXXXXX..XXXXXXX 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode, Connection **con)
  * return:    0  means packet same
  *            > 0 || < 0 means packet different
  */
-static int colo_packet_compare_common(Packet *ppkt,
-                                      Packet *spkt,
-                                      int poffset,
-                                      int soffset)
+static int colo_compare_packet_payload(Packet *ppkt,
+                                       Packet *spkt,
+                                       uint16_t poffset,
+                                       uint16_t soffset,
+                                       uint16_t len)
+
 {
     if (trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
         char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_common(Packet *ppkt,
                                    sec_ip_src, sec_ip_dst);
     }
 
-    poffset = ppkt->vnet_hdr_len + poffset;
-    soffset = ppkt->vnet_hdr_len + soffset;
-
-    if (ppkt->size - poffset == spkt->size - soffset) {
-        return memcmp(ppkt->data + poffset,
-                      spkt->data + soffset,
-                      spkt->size - soffset);
-    } else {
-        trace_colo_compare_main("Net packet size are not the same");
-        return -1;
-    }
+    return memcmp(ppkt->data + poffset, spkt->data + soffset, len);
 }
 
 /*
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
      * the secondary guest's timestamp. COLO just focus on payload,
      * so we just need skip this field.
      */
-    if (ptcp->th_off > 5) {
-        ptrdiff_t ptcp_offset, stcp_offset;
 
-        ptcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
-                      + (ptcp->th_off * 4) - ppkt->vnet_hdr_len;
-        stcp_offset = spkt->transport_header - (uint8_t *)spkt->data
-                      + (stcp->th_off * 4) - spkt->vnet_hdr_len;
+    ptrdiff_t ptcp_offset, stcp_offset;
 
-        /*
-         * When network is busy, some tcp options(like sack) will unpredictable
-         * occur in primary side or secondary side. it will make packet size
-         * not same, but the two packet's payload is identical. colo just
-         * care about packet payload, so we skip the option field.
-         */
-        res = colo_packet_compare_common(ppkt, spkt, ptcp_offset, stcp_offset);
-    } else if (ptcp->th_sum == stcp->th_sum) {
-        res = colo_packet_compare_common(ppkt, spkt, ETH_HLEN, ETH_HLEN);
+    ptcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
+                  + (ptcp->th_off << 2) - ppkt->vnet_hdr_len;
+    stcp_offset = spkt->transport_header - (uint8_t *)spkt->data
+                  + (stcp->th_off << 2) - spkt->vnet_hdr_len;
+    if (ppkt->size - ptcp_offset == spkt->size - stcp_offset) {
+        res = colo_compare_packet_payload(ppkt, spkt,
+                                          ptcp_offset, stcp_offset,
+                                          ppkt->size - ptcp_offset);
     } else {
+        trace_colo_compare_main("TCP: payload size of packets are different");
         res = -1;
     }
 
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
  */
 static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
 {
-    int ret;
-    int network_header_length = ppkt->ip->ip_hl * 4;
+    uint16_t network_header_length = ppkt->ip->ip_hl << 2;
+    uint16_t offset = network_header_length + ETH_HLEN + ppkt->vnet_hdr_len;
 
     trace_colo_compare_main("compare udp");
 
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
      * other field like TOS,TTL,IP Checksum. we only need to compare
      * the ip payload here.
      */
-    ret = colo_packet_compare_common(ppkt, spkt,
-                                     network_header_length + ETH_HLEN,
-                                     network_header_length + ETH_HLEN);
-
-    if (ret) {
+    if (ppkt->size != spkt->size) {
+        trace_colo_compare_main("UDP: payload size of packets are different");
+        return -1;
+    }
+    if (colo_compare_packet_payload(ppkt, spkt, offset, offset,
+                                    ppkt->size - offset)) {
         trace_colo_compare_udp_miscompare("primary pkt size", ppkt->size);
         trace_colo_compare_udp_miscompare("Secondary pkt size", spkt->size);
         if (trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
             qemu_hexdump((char *)spkt->data, stderr, "colo-compare sec pkt",
                          spkt->size);
         }
+        return -1;
+    } else {
+        return 0;
     }
-
-    return ret;
 }
 
 /*
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
  */
 static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
 {
-    int network_header_length = ppkt->ip->ip_hl * 4;
+    uint16_t network_header_length = ppkt->ip->ip_hl << 2;
+    uint16_t offset = network_header_length + ETH_HLEN + ppkt->vnet_hdr_len;
 
     trace_colo_compare_main("compare icmp");
 
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
      * other field like TOS,TTL,IP Checksum. we only need to compare
      * the ip payload here.
      */
-    if (colo_packet_compare_common(ppkt, spkt,
-                                   network_header_length + ETH_HLEN,
-                                   network_header_length + ETH_HLEN)) {
+    if (ppkt->size != spkt->size) {
+        trace_colo_compare_main("ICMP: payload size of packets are different");
+        return -1;
+    }
+    if (colo_compare_packet_payload(ppkt, spkt, offset, offset,
+                                    ppkt->size - offset)) {
         trace_colo_compare_icmp_miscompare("primary pkt size",
                                            ppkt->size);
         trace_colo_compare_icmp_miscompare("Secondary pkt size",
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
  */
 static int colo_packet_compare_other(Packet *spkt, Packet *ppkt)
 {
+    uint16_t offset = ppkt->vnet_hdr_len;
+
     trace_colo_compare_main("compare other");
     if (trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
         char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_other(Packet *spkt, Packet *ppkt)
                                    sec_ip_src, sec_ip_dst);
     }
 
-    return colo_packet_compare_common(ppkt, spkt, 0, 0);
+    if (ppkt->size != spkt->size) {
+        trace_colo_compare_main("Other: payload size of packets are different");
+        return -1;
+    }
+    return colo_compare_packet_payload(ppkt, spkt, offset, offset,
+                                       ppkt->size - offset);
 }
 
 static int colo_old_packet_check_one(Packet *pkt, int64_t *check_time)
-- 
2.7.4

From: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>

Packet size some time different or when network is busy.
Based on same payload size, but TCP protocol can not
guarantee send the same one packet in the same way,

like that:
We send this payload:
------------------------------
| header |1|2|3|4|5|6|7|8|9|0|
------------------------------

primary:
ppkt1:
----------------
| header |1|2|3|
----------------
ppkt2:
------------------------
| header |4|5|6|7|8|9|0|
------------------------

secondary:
spkt1:
------------------------------
| header |1|2|3|4|5|6|7|8|9|0|
------------------------------

In the original method, ppkt1 and ppkt2 are different in size and
spkt1, so they can't compare and trigger the checkpoint.

I have tested FTP get 200M and 1G file many times, I found that
the performance was less than 1% of the native.

Now I reconstructed the comparison of TCP packets based on the
TCP sequence number. first of all, ppkt1 and spkt1 have the same
starting sequence number, so they can compare, even though their
length is different. And then ppkt1 with a smaller payload length
is used as the comparison length, if the payload is same, send
out the ppkt1 and record the offset(the length of ppkt1 payload)
in spkt1. The next comparison, ppkt2 and spkt1 can be compared
from the recorded position of spkt1.

like that:
----------------
| header |1|2|3| ppkt1
---------|-----|
         |     |
---------v-----v--------------
| header |1|2|3|4|5|6|7|8|9|0| spkt1
---------------|\------------|
               | \offset     |
      ---------v-------------v
      | header |4|5|6|7|8|9|0| ppkt2
      ------------------------

In this way, the performance can reach native 20% in my multiple
tests.

Cc: Zhang Chen <zhangckid@gmail.com>
Cc: Li Zhijian <lizhijian@cn.fujitsu.com>
Cc: Jason Wang <jasowang@redhat.com>

Signed-off-by: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Signed-off-by: Zhang Chen <zhangckid@gmail.com>
Reviewed-by: Zhang Chen <zhangckid@gmail.com>
Tested-by: Zhang Chen <zhangckid@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/colo-compare.c | 343 +++++++++++++++++++++++++++++++++++------------------
 net/colo.c         |   9 ++
 net/colo.h         |  15 +++
 net/trace-events   |   2 +-
 4 files changed, 250 insertions(+), 119 deletions(-)

diff --git a/net/colo-compare.c b/net/colo-compare.c
index XXXXXXX..XXXXXXX 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -XXX,XX +XXX,XX @@
 #define COMPARE_READ_LEN_MAX NET_BUFSIZE
 #define MAX_QUEUE_SIZE 1024
 
+#define COLO_COMPARE_FREE_PRIMARY     0x01
+#define COLO_COMPARE_FREE_SECONDARY   0x02
+
 /* TODO: Should be configurable */
 #define REGULAR_PACKET_CHECK_MS 3000
 
@@ -XXX,XX +XXX,XX @@ static gint seq_sorter(Packet *a, Packet *b, gpointer data)
     return ntohl(atcp->th_seq) - ntohl(btcp->th_seq);
 }
 
+static void fill_pkt_tcp_info(void *data, uint32_t *max_ack)
+{
+    Packet *pkt = data;
+    struct tcphdr *tcphd;
+
+    tcphd = (struct tcphdr *)pkt->transport_header;
+
+    pkt->tcp_seq = ntohl(tcphd->th_seq);
+    pkt->tcp_ack = ntohl(tcphd->th_ack);
+    *max_ack = *max_ack > pkt->tcp_ack ? *max_ack : pkt->tcp_ack;
+    pkt->header_size = pkt->transport_header - (uint8_t *)pkt->data
+                       + (tcphd->th_off << 2) - pkt->vnet_hdr_len;
+    pkt->payload_size = pkt->size - pkt->header_size;
+    pkt->seq_end = pkt->tcp_seq + pkt->payload_size;
+    pkt->flags = tcphd->th_flags;
+}
+
 /*
  * Return 1 on success, if return 0 means the
  * packet will be dropped
  */
-static int colo_insert_packet(GQueue *queue, Packet *pkt)
+static int colo_insert_packet(GQueue *queue, Packet *pkt, uint32_t *max_ack)
 {
     if (g_queue_get_length(queue) <= MAX_QUEUE_SIZE) {
         if (pkt->ip->ip_p == IPPROTO_TCP) {
+            fill_pkt_tcp_info(pkt, max_ack);
             g_queue_insert_sorted(queue,
                                   pkt,
                                   (GCompareDataFunc)seq_sorter,
@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode, Connection **con)
     }
 
     if (mode == PRIMARY_IN) {
-        if (!colo_insert_packet(&conn->primary_list, pkt)) {
+        if (!colo_insert_packet(&conn->primary_list, pkt, &conn->pack)) {
             error_report("colo compare primary queue size too big,"
                          "drop packet");
         }
     } else {
-        if (!colo_insert_packet(&conn->secondary_list, pkt)) {
+        if (!colo_insert_packet(&conn->secondary_list, pkt, &conn->sack)) {
             error_report("colo compare secondary queue size too big,"
                          "drop packet");
         }
@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode, Connection **con)
     return 0;
 }
 
+static inline bool after(uint32_t seq1, uint32_t seq2)
+{
+        return (int32_t)(seq1 - seq2) > 0;
+}
+
+static void colo_release_primary_pkt(CompareState *s, Packet *pkt)
+{
+    int ret;
+    ret = compare_chr_send(s,
+                           pkt->data,
+                           pkt->size,
+                           pkt->vnet_hdr_len);
+    if (ret < 0) {
+        error_report("colo send primary packet failed");
+    }
+    trace_colo_compare_main("packet same and release packet");
+    packet_destroy(pkt, NULL);
+}
+
 /*
  * The IP packets sent by primary and secondary
  * will be compared in here
@@ -XXX,XX +XXX,XX @@ static int colo_compare_packet_payload(Packet *ppkt,
 }
 
 /*
- * Called from the compare thread on the primary
- * for compare tcp packet
- * compare_tcp copied from Dr. David Alan Gilbert's branch
- */
-static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
+ * return true means that the payload is consist and
+ * need to make the next comparison, false means do
+ * the checkpoint
+*/
+static bool colo_mark_tcp_pkt(Packet *ppkt, Packet *spkt,
+                              int8_t *mark, uint32_t max_ack)
 {
-    struct tcphdr *ptcp, *stcp;
-    int res;
+    *mark = 0;
+
+    if (ppkt->tcp_seq == spkt->tcp_seq && ppkt->seq_end == spkt->seq_end) {
+        if (colo_compare_packet_payload(ppkt, spkt,
+                                        ppkt->header_size, spkt->header_size,
+                                        ppkt->payload_size)) {
+            *mark = COLO_COMPARE_FREE_SECONDARY | COLO_COMPARE_FREE_PRIMARY;
+            return true;
+        }
+    }
+    if (ppkt->tcp_seq == spkt->tcp_seq && ppkt->seq_end == spkt->seq_end) {
+        if (colo_compare_packet_payload(ppkt, spkt,
+                                        ppkt->header_size, spkt->header_size,
+                                        ppkt->payload_size)) {
+            *mark = COLO_COMPARE_FREE_SECONDARY | COLO_COMPARE_FREE_PRIMARY;
+            return true;
+        }
+    }
+
+    /* one part of secondary packet payload still need to be compared */
+    if (!after(ppkt->seq_end, spkt->seq_end)) {
+        if (colo_compare_packet_payload(ppkt, spkt,
+                                        ppkt->header_size + ppkt->offset,
+                                        spkt->header_size + spkt->offset,
+                                        ppkt->payload_size - ppkt->offset)) {
+            if (!after(ppkt->tcp_ack, max_ack)) {
+                *mark = COLO_COMPARE_FREE_PRIMARY;
+                spkt->offset += ppkt->payload_size - ppkt->offset;
+                return true;
+            } else {
+                /* secondary guest hasn't ack the data, don't send
+                 * out this packet
+                 */
+                return false;
+            }
+        }
+    } else {
+        /* primary packet is longer than secondary packet, compare
+         * the same part and mark the primary packet offset
+         */
+        if (colo_compare_packet_payload(ppkt, spkt,
+                                        ppkt->header_size + ppkt->offset,
+                                        spkt->header_size + spkt->offset,
+                                        spkt->payload_size - spkt->offset)) {
+            *mark = COLO_COMPARE_FREE_SECONDARY;
+            ppkt->offset += spkt->payload_size - spkt->offset;
+            return true;
+        }
+    }
 
-    trace_colo_compare_main("compare tcp");
+    return false;
+}
 
-    ptcp = (struct tcphdr *)ppkt->transport_header;
-    stcp = (struct tcphdr *)spkt->transport_header;
+static void colo_compare_tcp(CompareState *s, Connection *conn)
+{
+    Packet *ppkt = NULL, *spkt = NULL;
+    int8_t mark;
 
     /*
-     * The 'identification' field in the IP header is *very* random
-     * it almost never matches.  Fudge this by ignoring differences in
-     * unfragmented packets; they'll normally sort themselves out if different
-     * anyway, and it should recover at the TCP level.
-     * An alternative would be to get both the primary and secondary to rewrite
-     * somehow; but that would need some sync traffic to sync the state
-     */
-    if (ntohs(ppkt->ip->ip_off) & IP_DF) {
-        spkt->ip->ip_id = ppkt->ip->ip_id;
-        /* and the sum will be different if the IDs were different */
-        spkt->ip->ip_sum = ppkt->ip->ip_sum;
+     * If ppkt and spkt have the same payload, but ppkt's ACK
+     * is greater than spkt's ACK, in this case we can not
+     * send the ppkt because it will cause the secondary guest
+     * to miss sending some data in the next. Therefore, we
+     * record the maximum ACK in the current queue at both
+     * primary side and secondary side. Only when the ack is
+     * less than the smaller of the two maximum ack, then we
+     * can ensure that the packet's payload is acknowledged by
+     * primary and secondary.
+    */
+    uint32_t min_ack = conn->pack > conn->sack ? conn->sack : conn->pack;
+
+pri:
+    if (g_queue_is_empty(&conn->primary_list)) {
+        return;
     }
+    ppkt = g_queue_pop_head(&conn->primary_list);
+sec:
+    if (g_queue_is_empty(&conn->secondary_list)) {
+        g_queue_push_head(&conn->primary_list, ppkt);
+        return;
+    }
+    spkt = g_queue_pop_head(&conn->secondary_list);
 
-    /*
-     * Check tcp header length for tcp option field.
-     * th_off > 5 means this tcp packet have options field.
-     * The tcp options maybe always different.
-     * for example:
-     * From RFC 7323.
-     * TCP Timestamps option (TSopt):
-     * Kind: 8
-     *
-     * Length: 10 bytes
-     *
-     *    +-------+-------+---------------------+---------------------+
-     *    |Kind=8 |  10   |   TS Value (TSval)  |TS Echo Reply (TSecr)|
-     *    +-------+-------+---------------------+---------------------+
-     *       1       1              4                     4
-     *
-     * In this case the primary guest's timestamp always different with
-     * the secondary guest's timestamp. COLO just focus on payload,
-     * so we just need skip this field.
-     */
+    if (ppkt->tcp_seq == ppkt->seq_end) {
+        colo_release_primary_pkt(s, ppkt);
+        ppkt = NULL;
+    }
 
-    ptrdiff_t ptcp_offset, stcp_offset;
+    if (ppkt && conn->compare_seq && !after(ppkt->seq_end, conn->compare_seq)) {
+        trace_colo_compare_main("pri: this packet has compared");
+        colo_release_primary_pkt(s, ppkt);
+        ppkt = NULL;
+    }
 
-    ptcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
-                  + (ptcp->th_off << 2) - ppkt->vnet_hdr_len;
-    stcp_offset = spkt->transport_header - (uint8_t *)spkt->data
-                  + (stcp->th_off << 2) - spkt->vnet_hdr_len;
-    if (ppkt->size - ptcp_offset == spkt->size - stcp_offset) {
-        res = colo_compare_packet_payload(ppkt, spkt,
-                                          ptcp_offset, stcp_offset,
-                                          ppkt->size - ptcp_offset);
+    if (spkt->tcp_seq == spkt->seq_end) {
+        packet_destroy(spkt, NULL);
+        if (!ppkt) {
+            goto pri;
+        } else {
+            goto sec;
+        }
     } else {
-        trace_colo_compare_main("TCP: payload size of packets are different");
-        res = -1;
+        if (conn->compare_seq && !after(spkt->seq_end, conn->compare_seq)) {
+            trace_colo_compare_main("sec: this packet has compared");
+            packet_destroy(spkt, NULL);
+            if (!ppkt) {
+                goto pri;
+            } else {
+                goto sec;
+            }
+        }
+        if (!ppkt) {
+            g_queue_push_head(&conn->secondary_list, spkt);
+            goto pri;
+        }
     }
 
-    if (res != 0 &&
-        trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
-        char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
-
-        strcpy(pri_ip_src, inet_ntoa(ppkt->ip->ip_src));
-        strcpy(pri_ip_dst, inet_ntoa(ppkt->ip->ip_dst));
-        strcpy(sec_ip_src, inet_ntoa(spkt->ip->ip_src));
-        strcpy(sec_ip_dst, inet_ntoa(spkt->ip->ip_dst));
-
-        trace_colo_compare_ip_info(ppkt->size, pri_ip_src,
-                                   pri_ip_dst, spkt->size,
-                                   sec_ip_src, sec_ip_dst);
-
-        trace_colo_compare_tcp_info("pri tcp packet",
-                                    ntohl(ptcp->th_seq),
-                                    ntohl(ptcp->th_ack),
-                                    res, ptcp->th_flags,
-                                    ppkt->size);
-
-        trace_colo_compare_tcp_info("sec tcp packet",
-                                    ntohl(stcp->th_seq),
-                                    ntohl(stcp->th_ack),
-                                    res, stcp->th_flags,
-                                    spkt->size);
+    if (colo_mark_tcp_pkt(ppkt, spkt, &mark, min_ack)) {
+        trace_colo_compare_tcp_info("pri",
+                                    ppkt->tcp_seq, ppkt->tcp_ack,
+                                    ppkt->header_size, ppkt->payload_size,
+                                    ppkt->offset, ppkt->flags);
+
+        trace_colo_compare_tcp_info("sec",
+                                    spkt->tcp_seq, spkt->tcp_ack,
+                                    spkt->header_size, spkt->payload_size,
+                                    spkt->offset, spkt->flags);
+
+        if (mark == COLO_COMPARE_FREE_PRIMARY) {
+            conn->compare_seq = ppkt->seq_end;
+            colo_release_primary_pkt(s, ppkt);
+            g_queue_push_head(&conn->secondary_list, spkt);
+            goto pri;
+        }
+        if (mark == COLO_COMPARE_FREE_SECONDARY) {
+            conn->compare_seq = spkt->seq_end;
+            packet_destroy(spkt, NULL);
+            goto sec;
+        }
+        if (mark == (COLO_COMPARE_FREE_PRIMARY | COLO_COMPARE_FREE_SECONDARY)) {
+            conn->compare_seq = ppkt->seq_end;
+            colo_release_primary_pkt(s, ppkt);
+            packet_destroy(spkt, NULL);
+            goto pri;
+        }
+    } else {
+        g_queue_push_head(&conn->primary_list, ppkt);
+        g_queue_push_head(&conn->secondary_list, spkt);
 
         qemu_hexdump((char *)ppkt->data, stderr,
                      "colo-compare ppkt", ppkt->size);
         qemu_hexdump((char *)spkt->data, stderr,
                      "colo-compare spkt", spkt->size);
-    }
 
-    return res;
+        /*
+         * colo_compare_inconsistent_notify();
+         * TODO: notice to checkpoint();
+         */
+    }
 }
 
+
 /*
  * Called from the compare thread on the primary
  * for compare udp packet
@@ -XXX,XX +XXX,XX @@ static void colo_old_packet_check(void *opaque)
                         (GCompareFunc)colo_old_packet_check_one_conn);
 }
 
-/*
- * Called from the compare thread on the primary
- * for compare packet with secondary list of the
- * specified connection when a new packet was
- * queued to it.
- */
-static void colo_compare_connection(void *opaque, void *user_data)
+static void colo_compare_packet(CompareState *s, Connection *conn,
+                                int (*HandlePacket)(Packet *spkt,
+                                Packet *ppkt))
 {
-    CompareState *s = user_data;
-    Connection *conn = opaque;
     Packet *pkt = NULL;
     GList *result = NULL;
-    int ret;
 
     while (!g_queue_is_empty(&conn->primary_list) &&
            !g_queue_is_empty(&conn->secondary_list)) {
         pkt = g_queue_pop_head(&conn->primary_list);
-        switch (conn->ip_proto) {
-        case IPPROTO_TCP:
-            result = g_queue_find_custom(&conn->secondary_list,
-                     pkt, (GCompareFunc)colo_packet_compare_tcp);
-            break;
-        case IPPROTO_UDP:
-            result = g_queue_find_custom(&conn->secondary_list,
-                     pkt, (GCompareFunc)colo_packet_compare_udp);
-            break;
-        case IPPROTO_ICMP:
-            result = g_queue_find_custom(&conn->secondary_list,
-                     pkt, (GCompareFunc)colo_packet_compare_icmp);
-            break;
-        default:
-            result = g_queue_find_custom(&conn->secondary_list,
-                     pkt, (GCompareFunc)colo_packet_compare_other);
-            break;
-        }
+        result = g_queue_find_custom(&conn->secondary_list,
+                 pkt, (GCompareFunc)HandlePacket);
 
         if (result) {
-            ret = compare_chr_send(s,
-                                   pkt->data,
-                                   pkt->size,
-                                   pkt->vnet_hdr_len);
-            if (ret < 0) {
-                error_report("colo_send_primary_packet failed");
-            }
-            trace_colo_compare_main("packet same and release packet");
+            colo_release_primary_pkt(s, pkt);
             g_queue_remove(&conn->secondary_list, result->data);
-            packet_destroy(pkt, NULL);
         } else {
             /*
              * If one packet arrive late, the secondary_list or
@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
     }
 }
 
+/*
+ * Called from the compare thread on the primary
+ * for compare packet with secondary list of the
+ * specified connection when a new packet was
+ * queued to it.
+ */
+static void colo_compare_connection(void *opaque, void *user_data)
+{
+    CompareState *s = user_data;
+    Connection *conn = opaque;
+
+    switch (conn->ip_proto) {
+    case IPPROTO_TCP:
+        colo_compare_tcp(s, conn);
+        break;
+    case IPPROTO_UDP:
+        colo_compare_packet(s, conn, colo_packet_compare_udp);
+        break;
+    case IPPROTO_ICMP:
+        colo_compare_packet(s, conn, colo_packet_compare_icmp);
+        break;
+    default:
+        colo_compare_packet(s, conn, colo_packet_compare_other);
+        break;
+    }
+}
+
 static int compare_chr_send(CompareState *s,
                             const uint8_t *buf,
                             uint32_t size,
diff --git a/net/colo.c b/net/colo.c
index XXXXXXX..XXXXXXX 100644
--- a/net/colo.c
+++ b/net/colo.c
@@ -XXX,XX +XXX,XX @@ Connection *connection_new(ConnectionKey *key)
     conn->processing = false;
     conn->offset = 0;
     conn->syn_flag = 0;
+    conn->pack = 0;
+    conn->sack = 0;
     g_queue_init(&conn->primary_list);
     g_queue_init(&conn->secondary_list);
 
@@ -XXX,XX +XXX,XX @@ Packet *packet_new(const void *data, int size, int vnet_hdr_len)
     pkt->size = size;
     pkt->creation_ms = qemu_clock_get_ms(QEMU_CLOCK_HOST);
     pkt->vnet_hdr_len = vnet_hdr_len;
+    pkt->tcp_seq = 0;
+    pkt->tcp_ack = 0;
+    pkt->seq_end = 0;
+    pkt->header_size = 0;
+    pkt->payload_size = 0;
+    pkt->offset = 0;
+    pkt->flags = 0;
 
     return pkt;
 }
diff --git a/net/colo.h b/net/colo.h
index XXXXXXX..XXXXXXX 100644
--- a/net/colo.h
+++ b/net/colo.h
@@ -XXX,XX +XXX,XX @@ typedef struct Packet {
     int64_t creation_ms;
     /* Get vnet_hdr_len from filter */
     uint32_t vnet_hdr_len;
+    uint32_t tcp_seq; /* sequence number */
+    uint32_t tcp_ack; /* acknowledgement number */
+    /* the sequence number of the last byte of the packet */
+    uint32_t seq_end;
+    uint8_t header_size;  /* the header length */
+    uint16_t payload_size; /* the payload length */
+    /* record the payload offset(the length that has been compared) */
+    uint16_t offset;
+    uint8_t flags; /* Flags(aka Control bits) */
 } Packet;
 
 typedef struct ConnectionKey {
@@ -XXX,XX +XXX,XX @@ typedef struct Connection {
     /* flag to enqueue unprocessed_connections */
     bool processing;
     uint8_t ip_proto;
+    /* record the sequence number that has been compared */
+    uint32_t compare_seq;
+    /* the maximum of acknowledgement number in primary_list queue */
+    uint32_t pack;
+    /* the maximum of acknowledgement number in secondary_list queue */
+    uint32_t sack;
     /* offset = secondary_seq - primary_seq */
     tcp_seq  offset;
     /*
diff --git a/net/trace-events b/net/trace-events
index XXXXXXX..XXXXXXX 100644
--- a/net/trace-events
+++ b/net/trace-events
@@ -XXX,XX +XXX,XX @@ colo_compare_icmp_miscompare(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) ""
-colo_compare_tcp_info(const char *pkt, uint32_t seq, uint32_t ack, int res, uint32_t flag, int size) "side: %s seq/ack= %u/%u res= %d flags= 0x%x pkt_size: %d\n"
+colo_compare_tcp_info(const char *pkt, uint32_t seq, uint32_t ack, int hdlen, int pdlen, int offset, int flags) "%s: seq/ack= %u/%u hdlen= %d pdlen= %d offset= %d flags=%d\n"
 
 # net/filter-rewriter.c
 colo_filter_rewriter_debug(void) ""
-- 
2.7.4

From: Thomas Huth <thuth@redhat.com>

QEMU can emulate hubs to connect NICs and netdevs. This is currently
primarily used for the mis-named 'vlan' feature of the networking
subsystem. Now the 'vlan' feature has been marked as deprecated, since
its name is rather confusing and the users often rather mis-configure
their network when trying to use it. But while the 'vlan' parameter
should be removed at one point in time, the basic idea of emulating
a hub in QEMU is still good: It's useful for bundling up the output of
multiple NICs into one single l2tp netdev for example.

Now to be able to use the hubport feature without 'vlan's, there is one
missing piece: The possibility to connect a hubport to a netdev, too.
This patch adds this possibility by introducing a new "netdev=..."
parameter to the hubports.

To bundle up the output of multiple NICs into one socket netdev, you can
now run QEMU with these parameters for example:

qemu-system-ppc64 ... -netdev socket,id=s1,connect=:11122 \
    -netdev hubport,hubid=1,id=h1,netdev=s1 \
    -netdev hubport,hubid=1,id=h2 -device e1000,netdev=h2 \
    -netdev hubport,hubid=1,id=h3 -device virtio-net-pci,netdev=h3

For using the socket netdev, you have got to start another QEMU as the
receiving side first, for example with network dumping enabled:

qemu-system-x86_64 -M isapc -netdev socket,id=s0,listen=:11122 \
    -device ne2k_isa,netdev=s0 \
    -object filter-dump,id=f1,netdev=s0,file=/tmp/dump.dat

After the ppc64 guest tried to boot from both NICs, you can see in the
dump file (using Wireshark, for example), that the output of both NICs
(the e1000 and the virtio-net-pci) has been successfully transfered
via the socket netdev in this case.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/hub.c       | 27 +++++++++++++++++++++------
 net/hub.h       |  3 ++-
 net/net.c       |  2 +-
 qapi/net.json   |  4 +++-
 qemu-options.hx |  8 +++++---
 5 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/net/hub.c b/net/hub.c
index XXXXXXX..XXXXXXX 100644
--- a/net/hub.c
+++ b/net/hub.c
@@ -XXX,XX +XXX,XX @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "monitor/monitor.h"
 #include "net/net.h"
 #include "clients.h"
@@ -XXX,XX +XXX,XX @@ static NetClientInfo net_hub_port_info = {
     .cleanup = net_hub_port_cleanup,
 };
 
-static NetHubPort *net_hub_port_new(NetHub *hub, const char *name)
+static NetHubPort *net_hub_port_new(NetHub *hub, const char *name,
+                                    NetClientState *hubpeer)
 {
     NetClientState *nc;
     NetHubPort *port;
@@ -XXX,XX +XXX,XX @@ static NetHubPort *net_hub_port_new(NetHub *hub, const char *name)
         name = default_name;
     }
 
-    nc = qemu_new_net_client(&net_hub_port_info, NULL, "hub", name);
+    nc = qemu_new_net_client(&net_hub_port_info, hubpeer, "hub", name);
     port = DO_UPCAST(NetHubPort, nc, nc);
     port->id = id;
     port->hub = hub;
@@ -XXX,XX +XXX,XX @@ static NetHubPort *net_hub_port_new(NetHub *hub, const char *name)
 
 /**
  * Create a port on a given hub
+ * @hub_id: Number of the hub
  * @name: Net client name or NULL for default name.
+ * @hubpeer: Peer to use (if "netdev=id" has been specified)
  *
  * If there is no existing hub with the given id then a new hub is created.
  */
-NetClientState *net_hub_add_port(int hub_id, const char *name)
+NetClientState *net_hub_add_port(int hub_id, const char *name,
+                                 NetClientState *hubpeer)
 {
     NetHub *hub;
     NetHubPort *port;
@@ -XXX,XX +XXX,XX @@ NetClientState *net_hub_add_port(int hub_id, const char *name)
         hub = net_hub_new(hub_id);
     }
 
-    port = net_hub_port_new(hub, name);
+    port = net_hub_port_new(hub, name, hubpeer);
     return &port->nc;
 }
 
@@ -XXX,XX +XXX,XX @@ NetClientState *net_hub_port_find(int hub_id)
         }
     }
 
-    nc = net_hub_add_port(hub_id, NULL);
+    nc = net_hub_add_port(hub_id, NULL, NULL);
     return nc;
 }
 
@@ -XXX,XX +XXX,XX @@ int net_init_hubport(const Netdev *netdev, const char *name,
                      NetClientState *peer, Error **errp)
 {
     const NetdevHubPortOptions *hubport;
+    NetClientState *hubpeer = NULL;
 
     assert(netdev->type == NET_CLIENT_DRIVER_HUBPORT);
     assert(!peer);
     hubport = &netdev->u.hubport;
 
-    net_hub_add_port(hubport->hubid, name);
+    if (hubport->has_netdev) {
+        hubpeer = qemu_find_netdev(hubport->netdev);
+        if (!hubpeer) {
+            error_setg(errp, "netdev '%s' not found", hubport->netdev);
+            return -1;
+        }
+    }
+
+    net_hub_add_port(hubport->hubid, name, hubpeer);
+
     return 0;
 }
 
diff --git a/net/hub.h b/net/hub.h
index XXXXXXX..XXXXXXX 100644
--- a/net/hub.h
+++ b/net/hub.h
@@ -XXX,XX +XXX,XX @@
 
 #include "qemu-common.h"
 
-NetClientState *net_hub_add_port(int hub_id, const char *name);
+NetClientState *net_hub_add_port(int hub_id, const char *name,
+                                 NetClientState *hubpeer);
 NetClientState *net_hub_find_client_by_name(int hub_id, const char *name);
 void net_hub_info(Monitor *mon);
 void net_hub_check_clients(void);
diff --git a/net/net.c b/net/net.c
index XXXXXXX..XXXXXXX 100644
--- a/net/net.c
+++ b/net/net.c
@@ -XXX,XX +XXX,XX @@ static int net_client_init1(const void *object, bool is_netdev, Error **errp)
         /* Do not add to a vlan if it's a nic with a netdev= parameter. */
         if (netdev->type != NET_CLIENT_DRIVER_NIC ||
             !opts->u.nic.has_netdev) {
-            peer = net_hub_add_port(net->has_vlan ? net->vlan : 0, NULL);
+            peer = net_hub_add_port(net->has_vlan ? net->vlan : 0, NULL, NULL);
         }
 
         if (net->has_vlan && !vlan_warned) {
diff --git a/qapi/net.json b/qapi/net.json
index XXXXXXX..XXXXXXX 100644
--- a/qapi/net.json
+++ b/qapi/net.json
@@ -XXX,XX +XXX,XX @@
 # Connect two or more net clients through a software hub.
 #
 # @hubid: hub identifier number
+# @netdev: used to connect hub to a netdev instead of a device (since 2.12)
 #
 # Since: 1.2
 ##
 { 'struct': 'NetdevHubPortOptions',
   'data': {
-    'hubid':     'int32' } }
+    'hubid':     'int32',
+    '*netdev':    'str' } }
 
 ##
 # @NetdevNetmapOptions:
diff --git a/qemu-options.hx b/qemu-options.hx
index XXXXXXX..XXXXXXX 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -XXX,XX +XXX,XX @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev,
 #endif
     "-netdev vhost-user,id=str,chardev=dev[,vhostforce=on|off]\n"
     "                configure a vhost-user network, backed by a chardev 'dev'\n"
-    "-netdev hubport,id=str,hubid=n\n"
+    "-netdev hubport,id=str,hubid=n[,netdev=nd]\n"
     "                configure a hub port on QEMU VLAN 'n'\n", QEMU_ARCH_ALL)
 DEF("net", HAS_ARG, QEMU_OPTION_net,
     "-net nic[,vlan=n][,netdev=nd][,macaddr=mac][,model=type][,name=str][,addr=str][,vectors=v]\n"
@@ -XXX,XX +XXX,XX @@ vde_switch -F -sock /tmp/myswitch
 qemu-system-i386 linux.img -net nic -net vde,sock=/tmp/myswitch
 @end example
 
-@item -netdev hubport,id=@var{id},hubid=@var{hubid}
+@item -netdev hubport,id=@var{id},hubid=@var{hubid}[,netdev=@var{nd}]
 
 Create a hub port on QEMU "vlan" @var{hubid}.
 
 The hubport netdev lets you connect a NIC to a QEMU "vlan" instead of a single
 netdev.  @code{-net} and @code{-device} with parameter @option{vlan} create the
-required hub automatically.
+required hub automatically. Alternatively, you can also connect the hubport
+to another netdev with ID @var{nd} by using the @option{netdev=@var{nd}}
+option.
 
 @item -netdev vhost-user,chardev=@var{id}[,vhostforce=on|off][,queues=n]
 
-- 
2.7.4

From: Thomas Huth <thuth@redhat.com>

It does not make much sense to limit these commands to the legacy 'vlan'
concept only, they should work with the modern netdevs, too. So now
it is possible to use this command with one, two or three parameters.

With one parameter, the command installs a hostfwd rule on the default
"user" network:
    hostfwd_add tcp:...

With two parameters, the command installs a hostfwd rule on a netdev
(that's the new way of using this command):
    hostfwd_add netdev_id tcp:...

With three parameters, the command installs a rule on a 'vlan' (aka hub):
    hostfwd_add hub_id name tcp:...

Same applies to the hostfwd_remove command now.

Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hmp-commands.hx |  4 ++--
 net/slirp.c     | 33 +++++++++++++++++++++++----------
 2 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/hmp-commands.hx b/hmp-commands.hx
index XXXXXXX..XXXXXXX 100644
--- a/hmp-commands.hx
+++ b/hmp-commands.hx
@@ -XXX,XX +XXX,XX @@ ETEXI
     {
         .name       = "hostfwd_add",
         .args_type  = "arg1:s,arg2:s?,arg3:s?",
-        .params     = "[vlan_id name] [tcp|udp]:[hostaddr]:hostport-[guestaddr]:guestport",
+        .params     = "[hub_id name]|[netdev_id] [tcp|udp]:[hostaddr]:hostport-[guestaddr]:guestport",
         .help       = "redirect TCP or UDP connections from host to guest (requires -net user)",
         .cmd        = hmp_hostfwd_add,
     },
@@ -XXX,XX +XXX,XX @@ ETEXI
     {
         .name       = "hostfwd_remove",
         .args_type  = "arg1:s,arg2:s?,arg3:s?",
-        .params     = "[vlan_id name] [tcp|udp]:[hostaddr]:hostport",
+        .params     = "[hub_id name]|[netdev_id] [tcp|udp]:[hostaddr]:hostport",
         .help       = "remove host-to-guest TCP or UDP redirection",
         .cmd        = hmp_hostfwd_remove,
     },
diff --git a/net/slirp.c b/net/slirp.c
index XXXXXXX..XXXXXXX 100644
--- a/net/slirp.c
+++ b/net/slirp.c
@@ -XXX,XX +XXX,XX @@ error:
     return -1;
 }
 
-static SlirpState *slirp_lookup(Monitor *mon, const char *vlan,
-                                const char *stack)
+static SlirpState *slirp_lookup(Monitor *mon, const char *hub_id,
+                                const char *name)
 {
-
-    if (vlan) {
+    if (name) {
         NetClientState *nc;
-        nc = net_hub_find_client_by_name(strtol(vlan, NULL, 0), stack);
-        if (!nc) {
-            monitor_printf(mon, "unrecognized (vlan-id, stackname) pair\n");
-            return NULL;
+        if (hub_id) {
+            nc = net_hub_find_client_by_name(strtol(hub_id, NULL, 0), name);
+            if (!nc) {
+                monitor_printf(mon, "unrecognized (vlan-id, stackname) pair\n");
+                return NULL;
+            }
+        } else {
+            nc = qemu_find_netdev(name);
+            if (!nc) {
+                monitor_printf(mon, "unrecognized netdev id '%s'\n", name);
+                return NULL;
+            }
         }
         if (strcmp(nc->model, "user")) {
             monitor_printf(mon, "invalid device specified\n");
@@ -XXX,XX +XXX,XX @@ void hmp_hostfwd_remove(Monitor *mon, const QDict *qdict)
     const char *arg2 = qdict_get_try_str(qdict, "arg2");
     const char *arg3 = qdict_get_try_str(qdict, "arg3");
 
-    if (arg2) {
+    if (arg3) {
         s = slirp_lookup(mon, arg1, arg2);
         src_str = arg3;
+    } else if (arg2) {
+        s = slirp_lookup(mon, NULL, arg1);
+        src_str = arg2;
     } else {
         s = slirp_lookup(mon, NULL, NULL);
         src_str = arg1;
@@ -XXX,XX +XXX,XX @@ void hmp_hostfwd_add(Monitor *mon, const QDict *qdict)
     const char *arg2 = qdict_get_try_str(qdict, "arg2");
     const char *arg3 = qdict_get_try_str(qdict, "arg3");
 
-    if (arg2) {
+    if (arg3) {
         s = slirp_lookup(mon, arg1, arg2);
         redir_str = arg3;
+    } else if (arg2) {
+        s = slirp_lookup(mon, NULL, arg1);
+        redir_str = arg2;
     } else {
         s = slirp_lookup(mon, NULL, NULL);
         redir_str = arg1;
-- 
2.7.4

From: Philippe Mathieu-Daudé <f4bug@amsat.org>

gently asked by his automatic reply :)

Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 MAINTAINERS | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/scsi/mfi.h
 F: tests/megasas-test.c
 
 Network packet abstractions
-M: Dmitry Fleytman <dmitry@daynix.com>
+M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
 S: Maintained
 F: include/net/eth.h
 F: net/eth.c
@@ -XXX,XX +XXX,XX @@ F: hw/net/net_rx_pkt*
 F: hw/net/net_tx_pkt*
 
 Vmware
-M: Dmitry Fleytman <dmitry@daynix.com>
+M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
 S: Maintained
 F: hw/net/vmxnet*
 F: hw/scsi/vmw_pvscsi*
@@ -XXX,XX +XXX,XX @@ F: hw/mem/nvdimm.c
 F: include/hw/mem/nvdimm.h
 
 e1000x
-M: Dmitry Fleytman <dmitry@daynix.com>
+M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
 S: Maintained
 F: hw/net/e1000x*
 
 e1000e
-M: Dmitry Fleytman <dmitry@daynix.com>
+M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
 S: Maintained
 F: hw/net/e1000e*
 
-- 
2.7.4