Merge tag 'pull-migration-20220720c' of https://gitlab.com/dagrh/qemu into staging

Migration pull 2022-07-20

This replaces yesterdays pull and:
  a) Fixes some test build errors without TLS
  b) Reenabled the zlib acceleration on s390
     now that we have Ilya's fix

  Hyman's dirty page rate limit set
  Ilya's fix for zlib vs migration
  Peter's postcopy-preempt
  Cleanup from Dan
  zero-copy tidy ups from Leo
  multifd doc fix from Juan
  Revert disable of zlib acceleration on s390x

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

# gpg: Signature made Wed 20 Jul 2022 12:18:56 BST
# gpg:                using RSA key 45F5C71B4A0CB7FB977A9FA90516331EBC5BFDE7
# gpg: Good signature from "Dr. David Alan Gilbert (RH2) <dgilbert@redhat.com>" [full]
# Primary key fingerprint: 45F5 C71B 4A0C B7FB 977A  9FA9 0516 331E BC5B FDE7

* tag 'pull-migration-20220720c' of https://gitlab.com/dagrh/qemu: (30 commits)
  Revert "gitlab: disable accelerated zlib for s390x"
  migration: Avoid false-positive on non-supported scenarios for zero-copy-send
  multifd: Document the locking of MultiFD{Send/Recv}Params
  migration/multifd: Report to user when zerocopy not working
  Add dirty-sync-missed-zero-copy migration stat
  QIOChannelSocket: Fix zero-copy flush returning code 1 when nothing sent
  migration: remove unreachable code after reading data
  tests: Add postcopy preempt tests
  tests: Add postcopy tls recovery migration test
  tests: Add postcopy tls migration test
  tests: Move MigrateCommon upper
  migration: Respect postcopy request order in preemption mode
  migration: Enable TLS for preempt channel
  migration: Export tls-[creds|hostname|authz] params to cmdline too
  migration: Add helpers to detect TLS capability
  migration: Add property x-postcopy-preempt-break-huge
  migration: Create the postcopy preempt channel asynchronously
  migration: Postcopy recover with preempt enabled
  migration: Postcopy preemption enablement
  migration: Postcopy preemption preparation on channel creation
  ...

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

1 files changed, 458 insertions, 85 deletions

diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index 9e64125f02..71595a74fd 100644
--- a/tests/qtest/migration-test.c
+++ b/tests/qtest/migration-test.c
@@ -24,6 +24,7 @@
 #include "qapi/qobject-input-visitor.h"
 #include "qapi/qobject-output-visitor.h"
 #include "crypto/tlscredspsk.h"
+#include "qapi/qmp/qlist.h"
 
 #include "migration-helpers.h"
 #include "tests/migration/migration-test.h"
@@ -46,6 +47,12 @@ unsigned start_address;
 unsigned end_address;
 static bool uffd_feature_thread_id;
 
+/*
+ * Dirtylimit stop working if dirty page rate error
+ * value less than DIRTYLIMIT_TOLERANCE_RANGE
+ */
+#define DIRTYLIMIT_TOLERANCE_RANGE  25  /* MB/s */
+
 #if defined(__linux__)
 #include <sys/syscall.h>
 #include <sys/vfs.h>
@@ -496,6 +503,82 @@ typedef struct {
     const char *opts_target;
 } MigrateStart;
 
+/*
+ * A hook that runs after the src and dst QEMUs have been
+ * created, but before the migration is started. This can
+ * be used to set migration parameters and capabilities.
+ *
+ * Returns: NULL, or a pointer to opaque state to be
+ *          later passed to the TestMigrateFinishHook
+ */
+typedef void * (*TestMigrateStartHook)(QTestState *from,
+                                       QTestState *to);
+
+/*
+ * A hook that runs after the migration has finished,
+ * regardless of whether it succeeded or failed, but
+ * before QEMU has terminated (unless it self-terminated
+ * due to migration error)
+ *
+ * @opaque is a pointer to state previously returned
+ * by the TestMigrateStartHook if any, or NULL.
+ */
+typedef void (*TestMigrateFinishHook)(QTestState *from,
+                                      QTestState *to,
+                                      void *opaque);
+
+typedef struct {
+    /* Optional: fine tune start parameters */
+    MigrateStart start;
+
+    /* Required: the URI for the dst QEMU to listen on */
+    const char *listen_uri;
+
+    /*
+     * Optional: the URI for the src QEMU to connect to
+     * If NULL, then it will query the dst QEMU for its actual
+     * listening address and use that as the connect address.
+     * This allows for dynamically picking a free TCP port.
+     */
+    const char *connect_uri;
+
+    /* Optional: callback to run at start to set migration parameters */
+    TestMigrateStartHook start_hook;
+    /* Optional: callback to run at finish to cleanup */
+    TestMigrateFinishHook finish_hook;
+
+    /*
+     * Optional: normally we expect the migration process to complete.
+     *
+     * There can be a variety of reasons and stages in which failure
+     * can happen during tests.
+     *
+     * If a failure is expected to happen at time of establishing
+     * the connection, then MIG_TEST_FAIL will indicate that the dst
+     * QEMU is expected to stay running and accept future migration
+     * connections.
+     *
+     * If a failure is expected to happen while processing the
+     * migration stream, then MIG_TEST_FAIL_DEST_QUIT_ERR will indicate
+     * that the dst QEMU is expected to quit with non-zero exit status
+     */
+    enum {
+        /* This test should succeed, the default */
+        MIG_TEST_SUCCEED = 0,
+        /* This test should fail, dest qemu should keep alive */
+        MIG_TEST_FAIL,
+        /* This test should fail, dest qemu should fail with abnormal status */
+        MIG_TEST_FAIL_DEST_QUIT_ERR,
+    } result;
+
+    /* Optional: set number of migration passes to wait for */
+    unsigned int iterations;
+
+    /* Postcopy specific fields */
+    void *postcopy_data;
+    bool postcopy_preempt;
+} MigrateCommon;
+
 static int test_migrate_start(QTestState **from, QTestState **to,
                               const char *uri, MigrateStart *args)
 {
@@ -982,19 +1065,28 @@ test_migrate_tls_x509_finish(QTestState *from,
 
 static int migrate_postcopy_prepare(QTestState **from_ptr,
                                     QTestState **to_ptr,
-                                    MigrateStart *args)
+                                    MigrateCommon *args)
 {
     g_autofree char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
     QTestState *from, *to;
 
-    if (test_migrate_start(&from, &to, uri, args)) {
+    if (test_migrate_start(&from, &to, uri, &args->start)) {
         return -1;
     }
 
+    if (args->start_hook) {
+        args->postcopy_data = args->start_hook(from, to);
+    }
+
     migrate_set_capability(from, "postcopy-ram", true);
     migrate_set_capability(to, "postcopy-ram", true);
     migrate_set_capability(to, "postcopy-blocktime", true);
 
+    if (args->postcopy_preempt) {
+        migrate_set_capability(from, "postcopy-preempt", true);
+        migrate_set_capability(to, "postcopy-preempt", true);
+    }
+
     migrate_ensure_non_converge(from);
 
     /* Wait for the first serial output from the source */
@@ -1010,7 +1102,8 @@ static int migrate_postcopy_prepare(QTestState **from_ptr,
     return 0;
 }
 
-static void migrate_postcopy_complete(QTestState *from, QTestState *to)
+static void migrate_postcopy_complete(QTestState *from, QTestState *to,
+                                      MigrateCommon *args)
 {
     wait_for_migration_complete(from);
 
@@ -1021,30 +1114,73 @@ static void migrate_postcopy_complete(QTestState *from, QTestState *to)
         read_blocktime(to);
     }
 
+    if (args->finish_hook) {
+        args->finish_hook(from, to, args->postcopy_data);
+        args->postcopy_data = NULL;
+    }
+
     test_migrate_end(from, to, true);
 }
 
-static void test_postcopy(void)
+static void test_postcopy_common(MigrateCommon *args)
 {
-    MigrateStart args = {};
     QTestState *from, *to;
 
-    if (migrate_postcopy_prepare(&from, &to, &args)) {
+    if (migrate_postcopy_prepare(&from, &to, args)) {
         return;
     }
     migrate_postcopy_start(from, to);
-    migrate_postcopy_complete(from, to);
+    migrate_postcopy_complete(from, to, args);
 }
 
-static void test_postcopy_recovery(void)
+static void test_postcopy(void)
 {
-    MigrateStart args = {
-        .hide_stderr = true,
+    MigrateCommon args = { };
+
+    test_postcopy_common(&args);
+}
+
+static void test_postcopy_preempt(void)
+{
+    MigrateCommon args = {
+        .postcopy_preempt = true,
     };
+
+    test_postcopy_common(&args);
+}
+
+#ifdef CONFIG_GNUTLS
+static void test_postcopy_tls_psk(void)
+{
+    MigrateCommon args = {
+        .start_hook = test_migrate_tls_psk_start_match,
+        .finish_hook = test_migrate_tls_psk_finish,
+    };
+
+    test_postcopy_common(&args);
+}
+
+static void test_postcopy_preempt_tls_psk(void)
+{
+    MigrateCommon args = {
+        .postcopy_preempt = true,
+        .start_hook = test_migrate_tls_psk_start_match,
+        .finish_hook = test_migrate_tls_psk_finish,
+    };
+
+    test_postcopy_common(&args);
+}
+#endif
+
+static void test_postcopy_recovery_common(MigrateCommon *args)
+{
     QTestState *from, *to;
     g_autofree char *uri = NULL;
 
-    if (migrate_postcopy_prepare(&from, &to, &args)) {
+    /* Always hide errors for postcopy recover tests since they're expected */
+    args->start.hide_stderr = true;
+
+    if (migrate_postcopy_prepare(&from, &to, args)) {
         return;
     }
 
@@ -1095,9 +1231,51 @@ static void test_postcopy_recovery(void)
     /* Restore the postcopy bandwidth to unlimited */
     migrate_set_parameter_int(from, "max-postcopy-bandwidth", 0);
 
-    migrate_postcopy_complete(from, to);
+    migrate_postcopy_complete(from, to, args);
 }
 
+static void test_postcopy_recovery(void)
+{
+    MigrateCommon args = { };
+
+    test_postcopy_recovery_common(&args);
+}
+
+#ifdef CONFIG_GNUTLS
+static void test_postcopy_recovery_tls_psk(void)
+{
+    MigrateCommon args = {
+        .start_hook = test_migrate_tls_psk_start_match,
+        .finish_hook = test_migrate_tls_psk_finish,
+    };
+
+    test_postcopy_recovery_common(&args);
+}
+#endif
+
+static void test_postcopy_preempt_recovery(void)
+{
+    MigrateCommon args = {
+        .postcopy_preempt = true,
+    };
+
+    test_postcopy_recovery_common(&args);
+}
+
+#ifdef CONFIG_GNUTLS
+/* This contains preempt+recovery+tls test altogether */
+static void test_postcopy_preempt_all(void)
+{
+    MigrateCommon args = {
+        .postcopy_preempt = true,
+        .start_hook = test_migrate_tls_psk_start_match,
+        .finish_hook = test_migrate_tls_psk_finish,
+    };
+
+    test_postcopy_recovery_common(&args);
+}
+#endif
+
 static void test_baddest(void)
 {
     MigrateStart args = {
@@ -1113,78 +1291,6 @@ static void test_baddest(void)
     test_migrate_end(from, to, false);
 }
 
-/*
- * A hook that runs after the src and dst QEMUs have been
- * created, but before the migration is started. This can
- * be used to set migration parameters and capabilities.
- *
- * Returns: NULL, or a pointer to opaque state to be
- *          later passed to the TestMigrateFinishHook
- */
-typedef void * (*TestMigrateStartHook)(QTestState *from,
-                                       QTestState *to);
-
-/*
- * A hook that runs after the migration has finished,
- * regardless of whether it succeeded or failed, but
- * before QEMU has terminated (unless it self-terminated
- * due to migration error)
- *
- * @opaque is a pointer to state previously returned
- * by the TestMigrateStartHook if any, or NULL.
- */
-typedef void (*TestMigrateFinishHook)(QTestState *from,
-                                      QTestState *to,
-                                      void *opaque);
-
-typedef struct {
-    /* Optional: fine tune start parameters */
-    MigrateStart start;
-
-    /* Required: the URI for the dst QEMU to listen on */
-    const char *listen_uri;
-
-    /*
-     * Optional: the URI for the src QEMU to connect to
-     * If NULL, then it will query the dst QEMU for its actual
-     * listening address and use that as the connect address.
-     * This allows for dynamically picking a free TCP port.
-     */
-    const char *connect_uri;
-
-    /* Optional: callback to run at start to set migration parameters */
-    TestMigrateStartHook start_hook;
-    /* Optional: callback to run at finish to cleanup */
-    TestMigrateFinishHook finish_hook;
-
-    /*
-     * Optional: normally we expect the migration process to complete.
-     *
-     * There can be a variety of reasons and stages in which failure
-     * can happen during tests.
-     *
-     * If a failure is expected to happen at time of establishing
-     * the connection, then MIG_TEST_FAIL will indicate that the dst
-     * QEMU is expected to stay running and accept future migration
-     * connections.
-     *
-     * If a failure is expected to happen while processing the
-     * migration stream, then MIG_TEST_FAIL_DEST_QUIT_ERR will indicate
-     * that the dst QEMU is expected to quit with non-zero exit status
-     */
-    enum {
-        /* This test should succeed, the default */
-        MIG_TEST_SUCCEED = 0,
-        /* This test should fail, dest qemu should keep alive */
-        MIG_TEST_FAIL,
-        /* This test should fail, dest qemu should fail with abnormal status */
-        MIG_TEST_FAIL_DEST_QUIT_ERR,
-    } result;
-
-    /* Optional: set number of migration passes to wait for */
-    unsigned int iterations;
-} MigrateCommon;
-
 static void test_precopy_common(MigrateCommon *args)
 {
     QTestState *from, *to;
@@ -2059,6 +2165,253 @@ static void test_multifd_tcp_cancel(void)
     test_migrate_end(from, to2, true);
 }
 
+static void calc_dirty_rate(QTestState *who, uint64_t calc_time)
+{
+    qobject_unref(qmp_command(who,
+                  "{ 'execute': 'calc-dirty-rate',"
+                  "'arguments': { "
+                  "'calc-time': %ld,"
+                  "'mode': 'dirty-ring' }}",
+                  calc_time));
+}
+
+static QDict *query_dirty_rate(QTestState *who)
+{
+    return qmp_command(who, "{ 'execute': 'query-dirty-rate' }");
+}
+
+static void dirtylimit_set_all(QTestState *who, uint64_t dirtyrate)
+{
+    qobject_unref(qmp_command(who,
+                  "{ 'execute': 'set-vcpu-dirty-limit',"
+                  "'arguments': { "
+                  "'dirty-rate': %ld } }",
+                  dirtyrate));
+}
+
+static void cancel_vcpu_dirty_limit(QTestState *who)
+{
+    qobject_unref(qmp_command(who,
+                  "{ 'execute': 'cancel-vcpu-dirty-limit' }"));
+}
+
+static QDict *query_vcpu_dirty_limit(QTestState *who)
+{
+    QDict *rsp;
+
+    rsp = qtest_qmp(who, "{ 'execute': 'query-vcpu-dirty-limit' }");
+    g_assert(!qdict_haskey(rsp, "error"));
+    g_assert(qdict_haskey(rsp, "return"));
+
+    return rsp;
+}
+
+static bool calc_dirtyrate_ready(QTestState *who)
+{
+    QDict *rsp_return;
+    gchar *status;
+
+    rsp_return = query_dirty_rate(who);
+    g_assert(rsp_return);
+
+    status = g_strdup(qdict_get_str(rsp_return, "status"));
+    g_assert(status);
+
+    return g_strcmp0(status, "measuring");
+}
+
+static void wait_for_calc_dirtyrate_complete(QTestState *who,
+                                             int64_t time_s)
+{
+    int max_try_count = 10000;
+    usleep(time_s * 1000000);
+
+    while (!calc_dirtyrate_ready(who) && max_try_count--) {
+        usleep(1000);
+    }
+
+    /*
+     * Set the timeout with 10 s(max_try_count * 1000us),
+     * if dirtyrate measurement not complete, fail test.
+     */
+    g_assert_cmpint(max_try_count, !=, 0);
+}
+
+static int64_t get_dirty_rate(QTestState *who)
+{
+    QDict *rsp_return;
+    gchar *status;
+    QList *rates;
+    const QListEntry *entry;
+    QDict *rate;
+    int64_t dirtyrate;
+
+    rsp_return = query_dirty_rate(who);
+    g_assert(rsp_return);
+
+    status = g_strdup(qdict_get_str(rsp_return, "status"));
+    g_assert(status);
+    g_assert_cmpstr(status, ==, "measured");
+
+    rates = qdict_get_qlist(rsp_return, "vcpu-dirty-rate");
+    g_assert(rates && !qlist_empty(rates));
+
+    entry = qlist_first(rates);
+    g_assert(entry);
+
+    rate = qobject_to(QDict, qlist_entry_obj(entry));
+    g_assert(rate);
+
+    dirtyrate = qdict_get_try_int(rate, "dirty-rate", -1);
+
+    qobject_unref(rsp_return);
+    return dirtyrate;
+}
+
+static int64_t get_limit_rate(QTestState *who)
+{
+    QDict *rsp_return;
+    QList *rates;
+    const QListEntry *entry;
+    QDict *rate;
+    int64_t dirtyrate;
+
+    rsp_return = query_vcpu_dirty_limit(who);
+    g_assert(rsp_return);
+
+    rates = qdict_get_qlist(rsp_return, "return");
+    g_assert(rates && !qlist_empty(rates));
+
+    entry = qlist_first(rates);
+    g_assert(entry);
+
+    rate = qobject_to(QDict, qlist_entry_obj(entry));
+    g_assert(rate);
+
+    dirtyrate = qdict_get_try_int(rate, "limit-rate", -1);
+
+    qobject_unref(rsp_return);
+    return dirtyrate;
+}
+
+static QTestState *dirtylimit_start_vm(void)
+{
+    QTestState *vm = NULL;
+    g_autofree gchar *cmd = NULL;
+    const char *arch = qtest_get_arch();
+    g_autofree char *bootpath = NULL;
+
+    assert((strcmp(arch, "x86_64") == 0));
+    bootpath = g_strdup_printf("%s/bootsect", tmpfs);
+    assert(sizeof(x86_bootsect) == 512);
+    init_bootfile(bootpath, x86_bootsect, sizeof(x86_bootsect));
+
+    cmd = g_strdup_printf("-accel kvm,dirty-ring-size=4096 "
+                          "-name dirtylimit-test,debug-threads=on "
+                          "-m 150M -smp 1 "
+                          "-serial file:%s/vm_serial "
+                          "-drive file=%s,format=raw ",
+                          tmpfs, bootpath);
+
+    vm = qtest_init(cmd);
+    return vm;
+}
+
+static void dirtylimit_stop_vm(QTestState *vm)
+{
+    qtest_quit(vm);
+    cleanup("bootsect");
+    cleanup("vm_serial");
+}
+
+static void test_vcpu_dirty_limit(void)
+{
+    QTestState *vm;
+    int64_t origin_rate;
+    int64_t quota_rate;
+    int64_t rate ;
+    int max_try_count = 20;
+    int hit = 0;
+
+    /* Start vm for vcpu dirtylimit test */
+    vm = dirtylimit_start_vm();
+
+    /* Wait for the first serial output from the vm*/
+    wait_for_serial("vm_serial");
+
+    /* Do dirtyrate measurement with calc time equals 1s */
+    calc_dirty_rate(vm, 1);
+
+    /* Sleep calc time and wait for calc dirtyrate complete */
+    wait_for_calc_dirtyrate_complete(vm, 1);
+
+    /* Query original dirty page rate */
+    origin_rate = get_dirty_rate(vm);
+
+    /* VM booted from bootsect should dirty memory steadily */
+    assert(origin_rate != 0);
+
+    /* Setup quota dirty page rate at half of origin */
+    quota_rate = origin_rate / 2;
+
+    /* Set dirtylimit */
+    dirtylimit_set_all(vm, quota_rate);
+
+    /*
+     * Check if set-vcpu-dirty-limit and query-vcpu-dirty-limit
+     * works literally
+     */
+    g_assert_cmpint(quota_rate, ==, get_limit_rate(vm));
+
+    /* Sleep a bit to check if it take effect */
+    usleep(2000000);
+
+    /*
+     * Check if dirtylimit take effect realistically, set the
+     * timeout with 20 s(max_try_count * 1s), if dirtylimit
+     * doesn't take effect, fail test.
+     */
+    while (--max_try_count) {
+        calc_dirty_rate(vm, 1);
+        wait_for_calc_dirtyrate_complete(vm, 1);
+        rate = get_dirty_rate(vm);
+
+        /*
+         * Assume hitting if current rate is less
+         * than quota rate (within accepting error)
+         */
+        if (rate < (quota_rate + DIRTYLIMIT_TOLERANCE_RANGE)) {
+            hit = 1;
+            break;
+        }
+    }
+
+    g_assert_cmpint(hit, ==, 1);
+
+    hit = 0;
+    max_try_count = 20;
+
+    /* Check if dirtylimit cancellation take effect */
+    cancel_vcpu_dirty_limit(vm);
+    while (--max_try_count) {
+        calc_dirty_rate(vm, 1);
+        wait_for_calc_dirtyrate_complete(vm, 1);
+        rate = get_dirty_rate(vm);
+
+        /*
+         * Assume dirtylimit be canceled if current rate is
+         * greater than quota rate (within accepting error)
+         */
+        if (rate > (quota_rate + DIRTYLIMIT_TOLERANCE_RANGE)) {
+            hit = 1;
+            break;
+        }
+    }
+
+    g_assert_cmpint(hit, ==, 1);
+    dirtylimit_stop_vm(vm);
+}
+
 static bool kvm_dirty_ring_supported(void)
 {
 #if defined(__linux__) && defined(HOST_X86_64)
@@ -2123,13 +2476,31 @@ int main(int argc, char **argv)
     module_call_init(MODULE_INIT_QOM);
 
     qtest_add_func("/migration/postcopy/unix", test_postcopy);
-    qtest_add_func("/migration/postcopy/recovery", test_postcopy_recovery);
+    qtest_add_func("/migration/postcopy/plain", test_postcopy);
+    qtest_add_func("/migration/postcopy/recovery/plain",
+                   test_postcopy_recovery);
+    qtest_add_func("/migration/postcopy/preempt/plain", test_postcopy_preempt);
+    qtest_add_func("/migration/postcopy/preempt/recovery/plain",
+                    test_postcopy_preempt_recovery);
+
     qtest_add_func("/migration/bad_dest", test_baddest);
     qtest_add_func("/migration/precopy/unix/plain", test_precopy_unix_plain);
     qtest_add_func("/migration/precopy/unix/xbzrle", test_precopy_unix_xbzrle);
 #ifdef CONFIG_GNUTLS
     qtest_add_func("/migration/precopy/unix/tls/psk",
                    test_precopy_unix_tls_psk);
+    /*
+     * NOTE: psk test is enough for postcopy, as other types of TLS
+     * channels are tested under precopy.  Here what we want to test is the
+     * general postcopy path that has TLS channel enabled.
+     */
+    qtest_add_func("/migration/postcopy/tls/psk", test_postcopy_tls_psk);
+    qtest_add_func("/migration/postcopy/recovery/tls/psk",
+                   test_postcopy_recovery_tls_psk);
+    qtest_add_func("/migration/postcopy/preempt/tls/psk",
+                   test_postcopy_preempt_tls_psk);
+    qtest_add_func("/migration/postcopy/preempt/recovery/tls/psk",
+                   test_postcopy_preempt_all);
 #ifdef CONFIG_TASN1
     qtest_add_func("/migration/precopy/unix/tls/x509/default-host",
                    test_precopy_unix_tls_x509_default_host);
@@ -2204,6 +2575,8 @@ int main(int argc, char **argv)
     if (kvm_dirty_ring_supported()) {
         qtest_add_func("/migration/dirty_ring",
                        test_precopy_unix_dirty_ring);
+        qtest_add_func("/migration/vcpu_dirty_limit",
+                       test_vcpu_dirty_limit);
     }
 
     ret = g_test_run();