qemu-kvm/SOURCES/kvm-tests-migration-tests-Cover-postcopy-failure-on-reco.patch

From e503d6466ec8dd6c51b5891bd52f6f4076210f8b Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 19 Jun 2024 18:30:46 -0400
Subject: [PATCH 11/11] tests/migration-tests: Cover postcopy failure on
 reconnect

RH-Author: Juraj Marcin <None>
RH-MergeRequest: 419: migration: New postcopy state, and some cleanups [rhel-9.5.z]
RH-Jira: RHEL-63874
RH-Acked-by: Peter Xu <peterx@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [11/11] 0295f627c0e8e7bae6dcd695c063b17717c7590f

Make sure there will be an event for postcopy recovery, irrelevant of
whether the reconnect will success, or when the failure happens.

The added new case is to fail early in postcopy recovery, in which case it
didn't even reach RECOVER stage on src (and in real life it'll be the same
to dest, but the test case is just slightly more involved due to the dual
socketpair setup).

To do that, rename the postcopy_recovery_test_fail to reflect either stage
to fail, instead of a boolean.

Reviewed-by: Fabiano Rosas <farosas@suse.de>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Fabiano Rosas <farosas@suse.de>

(cherry picked from commit 6cf56a87baf8b99c4296a943d220eb8276ca035a)

JIRA: https://issues.redhat.com/browse/RHEL-63874
Y-JIRA: https://issues.redhat.com/browse/RHEL-38485

Signed-off-by: Juraj Marcin <jmarcin@redhat.com>
---
 tests/qtest/migration-test.c | 95 +++++++++++++++++++++++++++++-------
 1 file changed, 77 insertions(+), 18 deletions(-)

diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index afe8270dd0..d903e3e0fa 100644
--- a/tests/qtest/migration-test.c
+++ b/tests/qtest/migration-test.c
@@ -74,6 +74,17 @@ static QTestMigrationState dst_state;
 #define QEMU_ENV_SRC "QTEST_QEMU_BINARY_SRC"
 #define QEMU_ENV_DST "QTEST_QEMU_BINARY_DST"
 
+typedef enum PostcopyRecoveryFailStage {
+    /*
+     * "no failure" must be 0 as it's the default.  OTOH, real failure
+     * cases must be >0 to make sure they trigger by a "if" test.
+     */
+    POSTCOPY_FAIL_NONE = 0,
+    POSTCOPY_FAIL_CHANNEL_ESTABLISH,
+    POSTCOPY_FAIL_RECOVERY,
+    POSTCOPY_FAIL_MAX
+} PostcopyRecoveryFailStage;
+
 #if defined(__linux__)
 #include <sys/syscall.h>
 #include <sys/vfs.h>
@@ -753,7 +764,7 @@ typedef struct {
     /* Postcopy specific fields */
     void *postcopy_data;
     bool postcopy_preempt;
-    bool postcopy_recovery_test_fail;
+    PostcopyRecoveryFailStage postcopy_recovery_fail_stage;
 } MigrateCommon;
 
 static int test_migrate_start(QTestState **from, QTestState **to,
@@ -1467,12 +1478,16 @@ static void wait_for_postcopy_status(QTestState *one, const char *status)
                                                   "completed", NULL });
 }
 
-static void postcopy_recover_fail(QTestState *from, QTestState *to)
+static void postcopy_recover_fail(QTestState *from, QTestState *to,
+                                  PostcopyRecoveryFailStage stage)
 {
 #ifndef _WIN32
+    bool fail_early = (stage == POSTCOPY_FAIL_CHANNEL_ESTABLISH);
     int ret, pair1[2], pair2[2];
     char c;
 
+    g_assert(stage > POSTCOPY_FAIL_NONE && stage < POSTCOPY_FAIL_MAX);
+
     /* Create two unrelated socketpairs */
     ret = qemu_socketpair(PF_LOCAL, SOCK_STREAM, 0, pair1);
     g_assert_cmpint(ret, ==, 0);
@@ -1506,6 +1521,14 @@ static void postcopy_recover_fail(QTestState *from, QTestState *to)
     ret = send(pair2[1], &c, 1, 0);
     g_assert_cmpint(ret, ==, 1);
 
+    if (stage == POSTCOPY_FAIL_CHANNEL_ESTABLISH) {
+        /*
+         * This will make src QEMU to fail at an early stage when trying to
+         * resume later, where it shouldn't reach RECOVER stage at all.
+         */
+        close(pair1[1]);
+    }
+
     migrate_recover(to, "fd:fd-mig");
     migrate_qmp(from, "fd:fd-mig", "{'resume': true}");
 
@@ -1515,28 +1538,53 @@ static void postcopy_recover_fail(QTestState *from, QTestState *to)
      */
     migration_event_wait(from, "postcopy-recover-setup");
 
+    if (fail_early) {
+        /*
+         * When fails at reconnection, src QEMU will automatically goes
+         * back to PAUSED state.  Making sure there is an event in this
+         * case: Libvirt relies on this to detect early reconnection
+         * errors.
+         */
+        migration_event_wait(from, "postcopy-paused");
+    } else {
+        /*
+         * We want to test "fail later" at RECOVER stage here.  Make sure
+         * both QEMU instances will go into RECOVER stage first, then test
+         * kicking them out using migrate-pause.
+         *
+         * Explicitly check the RECOVER event on src, that's what Libvirt
+         * relies on, rather than polling.
+         */
+        migration_event_wait(from, "postcopy-recover");
+        wait_for_postcopy_status(from, "postcopy-recover");
+
+        /* Need an explicit kick on src QEMU in this case */
+        migrate_pause(from);
+    }
+
     /*
-     * Make sure both QEMU instances will go into RECOVER stage, then test
-     * kicking them out using migrate-pause.
+     * For all failure cases, we'll reach such states on both sides now.
+     * Check them.
      */
-    wait_for_postcopy_status(from, "postcopy-recover");
+    wait_for_postcopy_status(from, "postcopy-paused");
     wait_for_postcopy_status(to, "postcopy-recover");
 
     /*
-     * This would be issued by the admin upon noticing the hang, we should
-     * make sure we're able to kick this out.
+     * Kick dest QEMU out too. This is normally not needed in reality
+     * because when the channel is shutdown it should also happen on src.
+     * However here we used separate socket pairs so we need to do that
+     * explicitly.
      */
-    migrate_pause(from);
-    wait_for_postcopy_status(from, "postcopy-paused");
-
-    /* Do the same test on dest */
     migrate_pause(to);
     wait_for_postcopy_status(to, "postcopy-paused");
 
     close(pair1[0]);
-    close(pair1[1]);
     close(pair2[0]);
     close(pair2[1]);
+
+    if (stage != POSTCOPY_FAIL_CHANNEL_ESTABLISH) {
+        close(pair1[1]);
+    }
 #endif
 }
 
@@ -1578,12 +1626,12 @@ static void test_postcopy_recovery_common(MigrateCommon *args)
     wait_for_postcopy_status(to, "postcopy-paused");
     wait_for_postcopy_status(from, "postcopy-paused");
 
-    if (args->postcopy_recovery_test_fail) {
+    if (args->postcopy_recovery_fail_stage) {
         /*
          * Test when a wrong socket specified for recover, and then the
          * ability to kick it out, and continue with a correct socket.
          */
-        postcopy_recover_fail(from, to);
+        postcopy_recover_fail(from, to, args->postcopy_recovery_fail_stage);
         /* continue with a good recovery */
     }
 
@@ -1623,10 +1671,19 @@ static void test_postcopy_recovery_compress(void)
     test_postcopy_recovery_common(&args);
 }
 
-static void test_postcopy_recovery_double_fail(void)
+static void test_postcopy_recovery_fail_handshake(void)
+{
+    MigrateCommon args = {
+        .postcopy_recovery_fail_stage = POSTCOPY_FAIL_RECOVERY,
+    };
+
+    test_postcopy_recovery_common(&args);
+}
+
+static void test_postcopy_recovery_fail_reconnect(void)
 {
     MigrateCommon args = {
-        .postcopy_recovery_test_fail = true,
+        .postcopy_recovery_fail_stage = POSTCOPY_FAIL_CHANNEL_ESTABLISH,
     };
 
     test_postcopy_recovery_common(&args);
@@ -3604,8 +3661,10 @@ int main(int argc, char **argv)
             migration_test_add("/migration/postcopy/recovery/compress/plain",
                                test_postcopy_recovery_compress);
         }
-        migration_test_add("/migration/postcopy/recovery/double-failures",
-                           test_postcopy_recovery_double_fail);
+        migration_test_add("/migration/postcopy/recovery/double-failures/handshake",
+                           test_postcopy_recovery_fail_handshake);
+        migration_test_add("/migration/postcopy/recovery/double-failures/reconnect",
+                           test_postcopy_recovery_fail_reconnect);
         if (is_x86) {
             migration_test_add("/migration/postcopy/suspend",
                                test_postcopy_suspend);
-- 
2.39.3