Merge tag 'migration-20250520-pull-request' of https://gitlab.com/peterx/qemu into staging

Migration pull - Peter's vmstate static checker entry for recent hpet change - Zhijian's rdma test patch to properly skip tests when locked_vm too low, and ipv6 test - Fabiano's few CI changes - Prasad's last patches to enable postcopy on precopy-multifd - Maciej's fix to disable multifd zerocopy for device states - Peter's HMP change to "info migrate", plus a small fix on cap set # -----BEGIN PGP SIGNATURE----- # # iIgEABYKADAWIQS5GE3CDMRX2s990ak7X8zN86vXBgUCaCy2xxIccGV0ZXJ4QHJl # ZGhhdC5jb20ACgkQO1/MzfOr1waNZgD9HRflpY6sqcXt9wPKYgJFAyPN9Jg05kGO # jeRIhD9cvyIBAN5AjbE0gaN8f+BLR5vcNk0Q5uOaHHIFZxL7tJl8ob4L # =WTpL # -----END PGP SIGNATURE----- # gpg: Signature made Tue 20 May 2025 13:07:19 EDT # gpg: using EDDSA key B9184DC20CC457DACF7DD1A93B5FCCCDF3ABD706 # gpg: issuer "peterx@redhat.com" # gpg: Good signature from "Peter Xu <xzpeter@gmail.com>" [full] # gpg: aka "Peter Xu <peterx@redhat.com>" [full] # Primary key fingerprint: B918 4DC2 0CC4 57DA CF7D D1A9 3B5F CCCD F3AB D706 * tag 'migration-20250520-pull-request' of https://gitlab.com/peterx/qemu: migration/hmp: Add "info migrate -a", reorg the dump migration: Allow caps to be set when preempt or multifd cap enabled migration/multifd: Don't send device state packets with zerocopy flag tests/qtest/migration: add postcopy tests with multifd migration: enable multifd and postcopy together migration: write zero pages when postcopy enabled ci: Reduce the size of artifacts for build-previous-qemu ci: Fix build-previous-qemu when the version tag is absent ci: Re-enable python subtests in qtest migration suite qtest/migration/rdma: Add test for rdma migration with ipv6 qtest/migration/rdma: Enforce RLIMIT_MEMLOCK >= 128MB requirement scripts/vmstate-static-checker.py: Add new hpet entry for num_timers Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2026-07-06 00:20:22 -07:00 · 2025-05-21 10:25:55 -04:00
parent f0737158b4 e09c6d8375
commit c6e1f60cc7
14 changed files with 373 additions and 136 deletions
@@ -188,12 +188,11 @@ build-previous-qemu:
    when: on_success
    expire_in: 2 days
    paths:
-      - build-previous
-    exclude:
-      - build-previous/**/*.p
-      - build-previous/**/*.a.p
-      - build-previous/**/*.c.o
-      - build-previous/**/*.c.o.d
+      - build-previous/qemu-bundle
+      - build-previous/qemu-system-aarch64
+      - build-previous/qemu-system-x86_64
+      - build-previous/tests/qtest/migration-test
+      - build-previous/scripts
  needs:
    job: amd64-opensuse-leap-container
  variables:
@@ -203,6 +202,11 @@ build-previous-qemu:
    GIT_FETCH_EXTRA_FLAGS: --prune --quiet
  before_script:
    - source scripts/ci/gitlab-ci-section
+    # Skip if this series contains the release bump commit. During the
+    # release process there might be a window of commits when the
+    # version tag is not yet present in the remote and git fetch would
+    # fail.
+    - if grep -q "\.0$" VERSION; then exit 0; fi
    - export QEMU_PREV_VERSION="$(sed 's/\([0-9.]*\)\.[0-9]*/v\1.0/' VERSION)"
    - git remote add upstream https://gitlab.com/qemu-project/qemu
    - git fetch upstream refs/tags/$QEMU_PREV_VERSION:refs/tags/$QEMU_PREV_VERSION
@@ -223,18 +227,13 @@ build-previous-qemu:
    IMAGE: opensuse-leap
    MAKE_CHECK_ARGS: check-build
  script:
+    # Skip for round release numbers, this job is only relevant for
+    # testing a development tree.
+    - if grep -q "\.0$" VERSION; then exit 0; fi
    # Use the migration-tests from the older QEMU tree. This avoids
    # testing an old QEMU against new features/tests that it is not
    # compatible with.
    - cd build-previous
-    # Don't allow python-based tests to run. The
-    # vmstate-checker-script test has a race that causes it to fail
-    # sometimes. It cannot be fixed it because this job runs the test
-    # from the old QEMU version. The test will be removed on master,
-    # but this job will only see the change in the next release.
-    #
-    # TODO: remove this line after 9.2 release
-    - unset PYTHON
    # old to new
    - QTEST_QEMU_BINARY_SRC=./qemu-system-${TARGET}
          QTEST_QEMU_BINARY=../build/qemu-system-${TARGET} ./tests/qtest/migration-test
@@ -475,9 +475,9 @@ ERST

    {
        .name       = "migrate",
-        .args_type  = "",
-        .params     = "",
-        .help       = "show migration status",
+        .args_type  = "all:-a",
+        .params     = "[-a]",
+        .help       = "show migration status (-a: all, dump all status)",
        .cmd        = hmp_info_migrate,
    },

@@ -37,29 +37,28 @@ static void migration_global_dump(Monitor *mon)
 {
    MigrationState *ms = migrate_get_current();

-    monitor_printf(mon, "globals:\n");
-    monitor_printf(mon, "store-global-state: %s\n",
+    monitor_printf(mon, "Globals:\n");
+    monitor_printf(mon, "  store-global-state: %s\n",
                   ms->store_global_state ? "on" : "off");
-    monitor_printf(mon, "only-migratable: %s\n",
+    monitor_printf(mon, "  only-migratable: %s\n",
                   only_migratable ? "on" : "off");
-    monitor_printf(mon, "send-configuration: %s\n",
+    monitor_printf(mon, "  send-configuration: %s\n",
                   ms->send_configuration ? "on" : "off");
-    monitor_printf(mon, "send-section-footer: %s\n",
+    monitor_printf(mon, "  send-section-footer: %s\n",
                   ms->send_section_footer ? "on" : "off");
-    monitor_printf(mon, "send-switchover-start: %s\n",
+    monitor_printf(mon, "  send-switchover-start: %s\n",
                   ms->send_switchover_start ? "on" : "off");
-    monitor_printf(mon, "clear-bitmap-shift: %u\n",
+    monitor_printf(mon, "  clear-bitmap-shift: %u\n",
                   ms->clear_bitmap_shift);
 }

 void hmp_info_migrate(Monitor *mon, const QDict *qdict)
 {
+    bool show_all = qdict_get_try_bool(qdict, "all", false);
    MigrationInfo *info;

    info = qmp_query_migrate(NULL);

-    migration_global_dump(mon);
-
    if (info->blocked_reasons) {
        strList *reasons = info->blocked_reasons;
        monitor_printf(mon, "Outgoing migration blocked:\n");
@@ -70,7 +69,7 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
    }

    if (info->has_status) {
-        monitor_printf(mon, "Migration status: %s",
+        monitor_printf(mon, "Status: %s",
                       MigrationStatus_str(info->status));
        if (info->status == MIGRATION_STATUS_FAILED && info->error_desc) {
            monitor_printf(mon, " (%s)\n", info->error_desc);
@@ -78,107 +77,130 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
            monitor_printf(mon, "\n");
        }

-        monitor_printf(mon, "total time: %" PRIu64 " ms\n",
-                       info->total_time);
-        if (info->has_expected_downtime) {
-            monitor_printf(mon, "expected downtime: %" PRIu64 " ms\n",
-                           info->expected_downtime);
+        if (info->total_time) {
+            monitor_printf(mon, "Time (ms): total=%" PRIu64,
+                           info->total_time);
+            if (info->has_setup_time) {
+                monitor_printf(mon, ", setup=%" PRIu64,
+                               info->setup_time);
+            }
+            if (info->has_expected_downtime) {
+                monitor_printf(mon, ", exp_down=%" PRIu64,
+                               info->expected_downtime);
+            }
+            if (info->has_downtime) {
+                monitor_printf(mon, ", down=%" PRIu64,
+                               info->downtime);
+            }
+            monitor_printf(mon, "\n");
        }
-        if (info->has_downtime) {
-            monitor_printf(mon, "downtime: %" PRIu64 " ms\n",
-                           info->downtime);
-        }
-        if (info->has_setup_time) {
-            monitor_printf(mon, "setup: %" PRIu64 " ms\n",
-                           info->setup_time);
+    }
+
+    if (info->has_socket_address) {
+        SocketAddressList *addr;
+
+        monitor_printf(mon, "Sockets: [\n");
+
+        for (addr = info->socket_address; addr; addr = addr->next) {
+            char *s = socket_uri(addr->value);
+            monitor_printf(mon, "\t%s\n", s);
+            g_free(s);
        }
+        monitor_printf(mon, "]\n");
    }

    if (info->ram) {
-        monitor_printf(mon, "transferred ram: %" PRIu64 " kbytes\n",
-                       info->ram->transferred >> 10);
-        monitor_printf(mon, "throughput: %0.2f mbps\n",
+        monitor_printf(mon, "RAM info:\n");
+        monitor_printf(mon, "  Throughput (Mbps): %0.2f\n",
                       info->ram->mbps);
-        monitor_printf(mon, "remaining ram: %" PRIu64 " kbytes\n",
-                       info->ram->remaining >> 10);
-        monitor_printf(mon, "total ram: %" PRIu64 " kbytes\n",
+        monitor_printf(mon, "  Sizes (KiB): pagesize=%" PRIu64
+                       ", total=%" PRIu64 ",\n",
+                       info->ram->page_size >> 10,
                       info->ram->total >> 10);
-        monitor_printf(mon, "duplicate: %" PRIu64 " pages\n",
-                       info->ram->duplicate);
-        monitor_printf(mon, "normal: %" PRIu64 " pages\n",
-                       info->ram->normal);
-        monitor_printf(mon, "normal bytes: %" PRIu64 " kbytes\n",
-                       info->ram->normal_bytes >> 10);
-        monitor_printf(mon, "dirty sync count: %" PRIu64 "\n",
-                       info->ram->dirty_sync_count);
-        monitor_printf(mon, "page size: %" PRIu64 " kbytes\n",
-                       info->ram->page_size >> 10);
-        monitor_printf(mon, "multifd bytes: %" PRIu64 " kbytes\n",
-                       info->ram->multifd_bytes >> 10);
-        monitor_printf(mon, "pages-per-second: %" PRIu64 "\n",
+        monitor_printf(mon, "    transferred=%" PRIu64
+                       ", remain=%" PRIu64 ",\n",
+                       info->ram->transferred >> 10,
+                       info->ram->remaining >> 10);
+        monitor_printf(mon, "    precopy=%" PRIu64
+                       ", multifd=%" PRIu64
+                       ", postcopy=%" PRIu64,
+                       info->ram->precopy_bytes >> 10,
+                       info->ram->multifd_bytes >> 10,
+                       info->ram->postcopy_bytes >> 10);
+
+        if (info->vfio) {
+            monitor_printf(mon, ", vfio=%" PRIu64,
+                           info->vfio->transferred >> 10);
+        }
+        monitor_printf(mon, "\n");
+
+        monitor_printf(mon, "  Pages: normal=%" PRIu64 ", zero=%" PRIu64
+                       ", rate_per_sec=%" PRIu64 "\n",
+                       info->ram->normal,
+                       info->ram->duplicate,
                       info->ram->pages_per_second);
+        monitor_printf(mon, "  Others: dirty_syncs=%" PRIu64,
+                       info->ram->dirty_sync_count);

        if (info->ram->dirty_pages_rate) {
-            monitor_printf(mon, "dirty pages rate: %" PRIu64 " pages\n",
+            monitor_printf(mon, ", dirty_pages_rate=%" PRIu64,
                           info->ram->dirty_pages_rate);
        }
        if (info->ram->postcopy_requests) {
-            monitor_printf(mon, "postcopy request count: %" PRIu64 "\n",
+            monitor_printf(mon, ", postcopy_req=%" PRIu64,
                           info->ram->postcopy_requests);
        }
-        if (info->ram->precopy_bytes) {
-            monitor_printf(mon, "precopy ram: %" PRIu64 " kbytes\n",
-                           info->ram->precopy_bytes >> 10);
-        }
        if (info->ram->downtime_bytes) {
-            monitor_printf(mon, "downtime ram: %" PRIu64 " kbytes\n",
-                           info->ram->downtime_bytes >> 10);
-        }
-        if (info->ram->postcopy_bytes) {
-            monitor_printf(mon, "postcopy ram: %" PRIu64 " kbytes\n",
-                           info->ram->postcopy_bytes >> 10);
+            monitor_printf(mon, ", downtime_ram=%" PRIu64,
+                           info->ram->downtime_bytes);
        }
        if (info->ram->dirty_sync_missed_zero_copy) {
-            monitor_printf(mon,
-                           "Zero-copy-send fallbacks happened: %" PRIu64 " times\n",
+            monitor_printf(mon, ", zerocopy_fallbacks=%" PRIu64,
                           info->ram->dirty_sync_missed_zero_copy);
        }
+        monitor_printf(mon, "\n");
    }

+    if (!show_all) {
+        goto out;
+    }
+
+    migration_global_dump(mon);
+
    if (info->xbzrle_cache) {
-        monitor_printf(mon, "cache size: %" PRIu64 " bytes\n",
-                       info->xbzrle_cache->cache_size);
-        monitor_printf(mon, "xbzrle transferred: %" PRIu64 " kbytes\n",
-                       info->xbzrle_cache->bytes >> 10);
-        monitor_printf(mon, "xbzrle pages: %" PRIu64 " pages\n",
-                       info->xbzrle_cache->pages);
-        monitor_printf(mon, "xbzrle cache miss: %" PRIu64 " pages\n",
-                       info->xbzrle_cache->cache_miss);
-        monitor_printf(mon, "xbzrle cache miss rate: %0.2f\n",
-                       info->xbzrle_cache->cache_miss_rate);
-        monitor_printf(mon, "xbzrle encoding rate: %0.2f\n",
-                       info->xbzrle_cache->encoding_rate);
-        monitor_printf(mon, "xbzrle overflow: %" PRIu64 "\n",
+        monitor_printf(mon, "XBZRLE: size=%" PRIu64
+                       ", transferred=%" PRIu64
+                       ", pages=%" PRIu64
+                       ", miss=%" PRIu64 "\n"
+                       "  miss_rate=%0.2f"
+                       ", encode_rate=%0.2f"
+                       ", overflow=%" PRIu64 "\n",
+                       info->xbzrle_cache->cache_size,
+                       info->xbzrle_cache->bytes,
+                       info->xbzrle_cache->pages,
+                       info->xbzrle_cache->cache_miss,
+                       info->xbzrle_cache->cache_miss_rate,
+                       info->xbzrle_cache->encoding_rate,
                       info->xbzrle_cache->overflow);
    }

    if (info->has_cpu_throttle_percentage) {
-        monitor_printf(mon, "cpu throttle percentage: %" PRIu64 "\n",
+        monitor_printf(mon, "CPU Throttle (%%): %" PRIu64 "\n",
                       info->cpu_throttle_percentage);
    }

    if (info->has_dirty_limit_throttle_time_per_round) {
-        monitor_printf(mon, "dirty-limit throttle time: %" PRIu64 " us\n",
+        monitor_printf(mon, "Dirty-limit Throttle (us): %" PRIu64 "\n",
                       info->dirty_limit_throttle_time_per_round);
    }

    if (info->has_dirty_limit_ring_full_time) {
-        monitor_printf(mon, "dirty-limit ring full time: %" PRIu64 " us\n",
+        monitor_printf(mon, "Dirty-limit Ring Full (us): %" PRIu64 "\n",
                       info->dirty_limit_ring_full_time);
    }

    if (info->has_postcopy_blocktime) {
-        monitor_printf(mon, "postcopy blocktime: %u\n",
+        monitor_printf(mon, "Postcopy Blocktime (ms): %" PRIu32 "\n",
                       info->postcopy_blocktime);
    }

@@ -189,28 +211,12 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
        visit_type_uint32List(v, NULL, &info->postcopy_vcpu_blocktime,
                              &error_abort);
        visit_complete(v, &str);
-        monitor_printf(mon, "postcopy vcpu blocktime: %s\n", str);
+        monitor_printf(mon, "Postcopy vCPU Blocktime: %s\n", str);
        g_free(str);
        visit_free(v);
    }
-    if (info->has_socket_address) {
-        SocketAddressList *addr;
-
-        monitor_printf(mon, "socket address: [\n");
-
-        for (addr = info->socket_address; addr; addr = addr->next) {
-            char *s = socket_uri(addr->value);
-            monitor_printf(mon, "\t%s\n", s);
-            g_free(s);
-        }
-        monitor_printf(mon, "]\n");
-    }
-
-    if (info->vfio) {
-        monitor_printf(mon, "vfio device transferred: %" PRIu64 " kbytes\n",
-                       info->vfio->transferred >> 10);
-    }

+out:
    qapi_free_MigrationInfo(info);
 }

@@ -17,6 +17,7 @@
 #include "migration-stats.h"
 #include "multifd.h"
 #include "options.h"
+#include "migration.h"
 #include "qapi/error.h"
 #include "qemu/cutils.h"
 #include "qemu/error-report.h"
@@ -398,7 +399,7 @@ int multifd_ram_flush_and_sync(QEMUFile *f)
    MultiFDSyncReq req;
    int ret;

-    if (!migrate_multifd()) {
+    if (!migrate_multifd() || migration_in_postcopy()) {
        return 0;
    }

@@ -85,9 +85,27 @@ void multifd_recv_zero_page_process(MultiFDRecvParams *p)
 {
    for (int i = 0; i < p->zero_num; i++) {
        void *page = p->host + p->zero[i];
-        if (ramblock_recv_bitmap_test_byte_offset(p->block, p->zero[i])) {
+        bool received =
+                ramblock_recv_bitmap_test_byte_offset(p->block, p->zero[i]);
+
+        /*
+         * During multifd migration zero page is written to the memory
+         * only if it is migrated more than once.
+         *
+         * It becomes a problem when both multifd & postcopy options are
+         * enabled. If the zero page which was skipped during multifd phase,
+         * is accessed during the postcopy phase of the migration, a page
+         * fault occurs. But this page fault is not served because the
+         * 'receivedmap' says the zero page is already received. Thus the
+         * thread accessing that page may hang.
+         *
+         * When postcopy is enabled, always write the zero page as and when
+         * it is migrated.
+         */
+        if (migrate_postcopy_ram() || received) {
            memset(page, 0, multifd_ram_page_size());
-        } else {
+        }
+        if (!received) {
            ramblock_recv_bitmap_set_offset(p->block, p->zero[i]);
        }
    }
@@ -690,6 +690,7 @@ static void *multifd_send_thread(void *opaque)
        if (qatomic_load_acquire(&p->pending_job)) {
            bool is_device_state = multifd_payload_device_state(p->data);
            size_t total_size;
+            int write_flags_masked = 0;

            p->flags = 0;
            p->iovs_num = 0;
@@ -697,6 +698,9 @@ static void *multifd_send_thread(void *opaque)

            if (is_device_state) {
                multifd_device_state_send_prepare(p);
+
+                /* Device state packets cannot be sent via zerocopy */
+                write_flags_masked |= QIO_CHANNEL_WRITE_FLAG_ZERO_COPY;
            } else {
                ret = multifd_send_state->ops->send_prepare(p, &local_err);
                if (ret != 0) {
@@ -718,7 +722,8 @@ static void *multifd_send_thread(void *opaque)
                                              &p->data->u.ram, &local_err);
            } else {
                ret = qio_channel_writev_full_all(p->c, p->iov, p->iovs_num,
-                                                  NULL, 0, p->write_flags,
+                                                  NULL, 0,
+                                                  p->write_flags & ~write_flags_masked,
                                                  &local_err);
            }

@@ -1379,6 +1384,13 @@ static void *multifd_recv_thread(void *opaque)
        }

        if (has_data) {
+            /*
+             * multifd thread should not be active and receive data
+             * when migration is in the Postcopy phase. Two threads
+             * writing the same memory area could easily corrupt
+             * the guest state.
+             */
+            assert(!migration_in_postcopy());
            if (is_device_state) {
                assert(use_packets);
                ret = multifd_device_state_recv(p, &local_err);
@@ -509,11 +509,6 @@ bool migrate_caps_check(bool *old_caps, bool *new_caps, Error **errp)
            error_setg(errp, "Postcopy is not compatible with ignore-shared");
            return false;
        }
-
-        if (new_caps[MIGRATION_CAPABILITY_MULTIFD]) {
-            error_setg(errp, "Postcopy is not yet compatible with multifd");
-            return false;
-        }
    }

    if (new_caps[MIGRATION_CAPABILITY_BACKGROUND_SNAPSHOT]) {
@@ -573,7 +568,7 @@ bool migrate_caps_check(bool *old_caps, bool *new_caps, Error **errp)
            return false;
        }

-        if (migrate_incoming_started()) {
+        if (!migrate_postcopy_preempt() && migrate_incoming_started()) {
            error_setg(errp,
                       "Postcopy preempt must be set before incoming starts");
            return false;
@@ -581,7 +576,7 @@ bool migrate_caps_check(bool *old_caps, bool *new_caps, Error **errp)
    }

    if (new_caps[MIGRATION_CAPABILITY_MULTIFD]) {
-        if (migrate_incoming_started()) {
+        if (!migrate_multifd() && migrate_incoming_started()) {
            error_setg(errp, "Multifd must be set before incoming starts");
            return false;
        }
@@ -1993,9 +1993,8 @@ static int ram_save_target_page(RAMState *rs, PageSearchStatus *pss)
        }
    }

-    if (migrate_multifd()) {
-        RAMBlock *block = pss->block;
-        return ram_save_multifd_page(block, offset);
+    if (migrate_multifd() && !migration_in_postcopy()) {
+        return ram_save_multifd_page(pss->block, offset);
    }

    return ram_save_page(rs, pss);
@@ -8,23 +8,44 @@ get_ipv4_addr()
        head -1 | tr -d '\n'
 }

+get_ipv6_addr() {
+    ipv6=$(ip -6 -o addr show dev "$1" |
+        sed -n 's/.*[[:blank:]]inet6[[:blank:]]*\([^[:blank:]/]*\).*/\1/p' |
+        head -1 | tr -d '\n')
+
+    [ $? -eq 0 ] || return
+
+    if [[ "$ipv6" =~ ^fe80: ]]; then
+        echo -n "[$ipv6%$1]"
+    else
+        echo -n "[$ipv6]"
+    fi
+}
+
 # existing rdma interfaces
 rdma_interfaces()
 {
-    rdma link show | sed -nE 's/^link .* netdev ([^ ]+).*$/\1 /p'
+    rdma link show | sed -nE 's/^link .* netdev ([^ ]+).*$/\1 /p' |
+    grep -Ev '^(lo|tun|tap)'
 }

 # existing valid ipv4 interfaces
 ipv4_interfaces()
 {
-    ip -o addr show | awk '/inet / {print $2}' | grep -v -w lo
+    ip -o addr show | awk '/inet / {print $2}' | grep -Ev '^(lo|tun|tap)'
+}
+
+ipv6_interfaces()
+{
+    ip -o addr show | awk '/inet6 / {print $2}' | grep -Ev '^(lo|tun|tap)'
 }

 rdma_rxe_detect()
 {
+    family=$1
    for r in $(rdma_interfaces)
    do
-        ipv4_interfaces | grep -qw $r && get_ipv4_addr $r && return
+        "$family"_interfaces | grep -qw $r && get_"$family"_addr $r && return
    done

    return 1
@@ -32,16 +53,23 @@ rdma_rxe_detect()

 rdma_rxe_setup()
 {
-    for i in $(ipv4_interfaces)
+    family=$1
+    for i in $("$family"_interfaces)
    do
-        rdma_interfaces | grep -qw $i && continue
+        if rdma_interfaces | grep -qw $i; then
+            echo "$family: Reuse the existing rdma/rxe ${i}_rxe" \
+                 "for $i with $(get_"$family"_addr $i)"
+            return
+        fi
+
        rdma link add "${i}_rxe" type rxe netdev "$i" && {
-            echo "Setup new rdma/rxe ${i}_rxe for $i with $(get_ipv4_addr $i)"
+            echo "$family: Setup new rdma/rxe ${i}_rxe" \
+                 "for $i with $(get_"$family"_addr $i)"
            return
        }
    done

-    echo "Failed to setup any new rdma/rxe link" >&2
+    echo "$family: Failed to setup any new rdma/rxe link" >&2
    return 1
 }

@@ -50,6 +78,12 @@ rdma_rxe_clean()
    modprobe -r rdma_rxe
 }

+IP_FAMILY=${IP_FAMILY:-ipv4}
+if [ "$IP_FAMILY" != "ipv6" ] && [ "$IP_FAMILY" != "ipv4" ]; then
+    echo "Unknown ip family '$IP_FAMILY', only ipv4 or ipv6 is supported." >&2
+    exit 1
+fi
+
 operation=${1:-detect}

 command -v rdma >/dev/null || {
@@ -62,9 +96,14 @@ if [ "$operation" == "setup" ] || [ "$operation" == "clean" ]; then
        echo "Root privilege is required to setup/clean a rdma/rxe link" >&2
        exit 1
    }
-    rdma_rxe_"$operation"
+    if [ "$operation" == "setup" ]; then
+        rdma_rxe_setup ipv4
+        rdma_rxe_setup ipv6
+    else
+        rdma_rxe_clean
+    fi
 elif [ "$operation" == "detect" ]; then
-    rdma_rxe_detect
+    rdma_rxe_detect "$IP_FAMILY"
 else
    echo "Usage: $0 [setup | detect | clean]"
 fi
@@ -91,6 +91,7 @@ def check_fields_match(name, s_field, d_field):
                      'mem_win_size', 'mig_mem_win_size',
                      'io_win_addr', 'mig_io_win_addr',
                      'io_win_size', 'mig_io_win_size'],
+        'hpet': ['num_timers', 'num_timers_save'],
    }

    if not name in changed_names:
@@ -42,6 +42,20 @@ static void test_multifd_tcp_zstd(void)
    };
    test_precopy_common(&args);
 }
+
+static void test_multifd_postcopy_tcp_zstd(void)
+{
+    MigrateCommon args = {
+        .listen_uri = "defer",
+        .start = {
+            .caps[MIGRATION_CAPABILITY_MULTIFD] = true,
+            .caps[MIGRATION_CAPABILITY_POSTCOPY_RAM] = true,
+        },
+        .start_hook = migrate_hook_start_precopy_tcp_multifd_zstd,
+    };
+
+    test_precopy_common(&args);
+}
 #endif /* CONFIG_ZSTD */

 #ifdef CONFIG_QATZIP
@@ -184,6 +198,10 @@ void migration_test_add_compression(MigrationTestEnv *env)
 #ifdef CONFIG_ZSTD
    migration_test_add("/migration/multifd/tcp/plain/zstd",
                       test_multifd_tcp_zstd);
+    if (env->has_uffd) {
+        migration_test_add("/migration/multifd+postcopy/tcp/plain/zstd",
+                           test_multifd_postcopy_tcp_zstd);
+    }
 #endif

 #ifdef CONFIG_QATZIP
@@ -94,6 +94,29 @@ static void migration_test_add_postcopy_smoke(MigrationTestEnv *env)
    }
 }

+static void test_multifd_postcopy(void)
+{
+    MigrateCommon args = {
+        .start = {
+            .caps[MIGRATION_CAPABILITY_MULTIFD] = true,
+        },
+    };
+
+    test_postcopy_common(&args);
+}
+
+static void test_multifd_postcopy_preempt(void)
+{
+    MigrateCommon args = {
+        .start = {
+            .caps[MIGRATION_CAPABILITY_MULTIFD] = true,
+            .caps[MIGRATION_CAPABILITY_POSTCOPY_PREEMPT] = true,
+        },
+    };
+
+    test_postcopy_common(&args);
+}
+
 void migration_test_add_postcopy(MigrationTestEnv *env)
 {
    migration_test_add_postcopy_smoke(env);
@@ -114,6 +137,10 @@ void migration_test_add_postcopy(MigrationTestEnv *env)
            "/migration/postcopy/recovery/double-failures/reconnect",
            test_postcopy_recovery_fail_reconnect);

+        migration_test_add("/migration/multifd+postcopy/plain",
+                           test_multifd_postcopy);
+        migration_test_add("/migration/multifd+postcopy/preempt/plain",
+                           test_multifd_postcopy_preempt);
        if (env->is_x86) {
            migration_test_add("/migration/postcopy/suspend",
                               test_postcopy_suspend);
@@ -101,13 +101,43 @@ static void test_precopy_unix_dirty_ring(void)

 #ifdef CONFIG_RDMA

+#include <sys/resource.h>
+
+/*
+ * During migration over RDMA, it will try to pin portions of guest memory,
+ * typically exceeding 100MB in this test, while the remainder will be
+ * transmitted as compressed zero pages.
+ *
+ * REQUIRED_MEMLOCK_SZ indicates the minimal mlock size in the current context.
+ */
+#define REQUIRED_MEMLOCK_SZ (128 << 20) /* 128MB */
+
+/* check 'ulimit -l' */
+static bool mlock_check(void)
+{
+    uid_t uid;
+    struct rlimit rlim;
+
+    uid = getuid();
+    if (uid == 0) {
+        return true;
+    }
+
+    if (getrlimit(RLIMIT_MEMLOCK, &rlim) != 0) {
+        return false;
+    }
+
+    return rlim.rlim_cur >= REQUIRED_MEMLOCK_SZ;
+}
+
 #define RDMA_MIGRATION_HELPER "scripts/rdma-migration-helper.sh"
-static int new_rdma_link(char *buffer)
+static int new_rdma_link(char *buffer, bool ipv6)
 {
    char cmd[256];
    bool verbose = g_getenv("QTEST_LOG");

-    snprintf(cmd, sizeof(cmd), "%s detect %s", RDMA_MIGRATION_HELPER,
+    snprintf(cmd, sizeof(cmd), "IP_FAMILY=%s %s detect %s",
+             ipv6 ? "ipv6" : "ipv4", RDMA_MIGRATION_HELPER,
             verbose ? "" : "2>/dev/null");

    FILE *pipe = popen(cmd, "r");
@@ -132,11 +162,16 @@ static int new_rdma_link(char *buffer)
    return -1;
 }

-static void test_precopy_rdma_plain(void)
+static void __test_precopy_rdma_plain(bool ipv6)
 {
    char buffer[128] = {};

-    if (new_rdma_link(buffer)) {
+    if (!mlock_check()) {
+        g_test_skip("'ulimit -l' is too small, require >=128M");
+        return;
+    }
+
+    if (new_rdma_link(buffer, ipv6)) {
        g_test_skip("No rdma link available\n"
                    "# To enable the test:\n"
                    "# Run \'" RDMA_MIGRATION_HELPER " setup\' with root to "
@@ -159,6 +194,16 @@ static void test_precopy_rdma_plain(void)

    test_precopy_common(&args);
 }
+
+static void test_precopy_rdma_plain(void)
+{
+    __test_precopy_rdma_plain(false);
+}
+
+static void test_precopy_rdma_plain_ipv6(void)
+{
+    __test_precopy_rdma_plain(true);
+}
 #endif

 static void test_precopy_tcp_plain(void)
@@ -524,7 +569,7 @@ static void test_multifd_tcp_channels_none(void)
 *
 *  And see that it works
 */
-static void test_multifd_tcp_cancel(void)
+static void test_multifd_tcp_cancel(bool postcopy_ram)
 {
    MigrateStart args = {
        .hide_stderr = true,
@@ -538,6 +583,11 @@ static void test_multifd_tcp_cancel(void)
    migrate_ensure_non_converge(from);
    migrate_prepare_for_dirty_mem(from);

+    if (postcopy_ram) {
+        migrate_set_capability(from, "postcopy-ram", true);
+        migrate_set_capability(to, "postcopy-ram", true);
+    }
+
    migrate_set_parameter_int(from, "multifd-channels", 16);
    migrate_set_parameter_int(to, "multifd-channels", 16);

@@ -579,6 +629,10 @@ static void test_multifd_tcp_cancel(void)
        return;
    }

+    if (postcopy_ram) {
+        migrate_set_capability(to2, "postcopy-ram", true);
+    }
+
    migrate_set_parameter_int(to2, "multifd-channels", 16);

    migrate_set_capability(to2, "multifd", true);
@@ -602,6 +656,16 @@ static void test_multifd_tcp_cancel(void)
    migrate_end(from, to2, true);
 }

+static void test_multifd_precopy_tcp_cancel(void)
+{
+    test_multifd_tcp_cancel(false);
+}
+
+static void test_multifd_postcopy_tcp_cancel(void)
+{
+    test_multifd_tcp_cancel(true);
+}
+
 static void test_cancel_src_after_failed(QTestState *from, QTestState *to,
                                         const char *uri, const char *phase)
 {
@@ -1188,10 +1252,17 @@ static void migration_test_add_precopy_smoke(MigrationTestEnv *env)
    migration_test_add("/migration/multifd/tcp/uri/plain/none",
                       test_multifd_tcp_uri_none);
    migration_test_add("/migration/multifd/tcp/plain/cancel",
-                       test_multifd_tcp_cancel);
+                       test_multifd_precopy_tcp_cancel);
+    if (env->has_uffd) {
+        migration_test_add("/migration/multifd+postcopy/tcp/plain/cancel",
+                           test_multifd_postcopy_tcp_cancel);
+    }
+
 #ifdef CONFIG_RDMA
    migration_test_add("/migration/precopy/rdma/plain",
                       test_precopy_rdma_plain);
+    migration_test_add("/migration/precopy/rdma/plain/ipv6",
+                       test_precopy_rdma_plain_ipv6);
 #endif
 }

@@ -395,6 +395,19 @@ static void test_postcopy_recovery_tls_psk(void)
    test_postcopy_recovery_common(&args);
 }

+static void test_multifd_postcopy_recovery_tls_psk(void)
+{
+    MigrateCommon args = {
+        .start_hook = migrate_hook_start_tls_psk_match,
+        .end_hook = migrate_hook_end_tls_psk,
+        .start = {
+            .caps[MIGRATION_CAPABILITY_MULTIFD] = true,
+        },
+    };
+
+    test_postcopy_recovery_common(&args);
+}
+
 /* This contains preempt+recovery+tls test altogether */
 static void test_postcopy_preempt_all(void)
 {
@@ -409,6 +422,20 @@ static void test_postcopy_preempt_all(void)
    test_postcopy_recovery_common(&args);
 }

+static void test_multifd_postcopy_preempt_recovery_tls_psk(void)
+{
+    MigrateCommon args = {
+        .start_hook = migrate_hook_start_tls_psk_match,
+        .end_hook = migrate_hook_end_tls_psk,
+        .start = {
+            .caps[MIGRATION_CAPABILITY_MULTIFD] = true,
+            .caps[MIGRATION_CAPABILITY_POSTCOPY_PREEMPT] = true,
+        },
+    };
+
+    test_postcopy_recovery_common(&args);
+}
+
 static void test_precopy_unix_tls_psk(void)
 {
    g_autofree char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
@@ -657,6 +684,21 @@ static void test_multifd_tcp_tls_psk_mismatch(void)
    test_precopy_common(&args);
 }

+static void test_multifd_postcopy_tcp_tls_psk_match(void)
+{
+    MigrateCommon args = {
+        .start = {
+            .caps[MIGRATION_CAPABILITY_MULTIFD] = true,
+            .caps[MIGRATION_CAPABILITY_POSTCOPY_RAM] = true,
+        },
+        .listen_uri = "defer",
+        .start_hook = migrate_hook_start_multifd_tcp_tls_psk_match,
+        .end_hook = migrate_hook_end_tls_psk,
+    };
+
+    test_precopy_common(&args);
+}
+
 #ifdef CONFIG_TASN1
 static void test_multifd_tcp_tls_x509_default_host(void)
 {
@@ -774,6 +816,11 @@ void migration_test_add_tls(MigrationTestEnv *env)
                           test_postcopy_preempt_tls_psk);
        migration_test_add("/migration/postcopy/preempt/recovery/tls/psk",
                           test_postcopy_preempt_all);
+        migration_test_add("/migration/multifd+postcopy/recovery/tls/psk",
+                           test_multifd_postcopy_recovery_tls_psk);
+        migration_test_add(
+            "/migration/multifd+postcopy/preempt/recovery/tls/psk",
+            test_multifd_postcopy_preempt_recovery_tls_psk);
    }
 #ifdef CONFIG_TASN1
    migration_test_add("/migration/precopy/unix/tls/x509/default-host",
@@ -805,6 +852,10 @@ void migration_test_add_tls(MigrationTestEnv *env)
                       test_multifd_tcp_tls_psk_match);
    migration_test_add("/migration/multifd/tcp/tls/psk/mismatch",
                       test_multifd_tcp_tls_psk_mismatch);
+    if (env->has_uffd) {
+        migration_test_add("/migration/multifd+postcopy/tcp/tls/psk/match",
+                           test_multifd_postcopy_tcp_tls_psk_match);
+    }
 #ifdef CONFIG_TASN1
    migration_test_add("/migration/multifd/tcp/tls/x509/default-host",
                       test_multifd_tcp_tls_x509_default_host);