Merge tag 'migration-20231103-pull-request' of https://gitlab.com/juan.quintela/qemu into staging

Migration Pull request (20231103)

Hi

In this PULL:
- dirty limit fixes (hyman)
- coverity issues (juan)

Please apply.

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEGJn/jt6/WMzuA0uC9IfvGFhy1yMFAmVE4dgACgkQ9IfvGFhy
# 1yPBgxAAvrsCHwU6/m9y+XGokyHTKKKIVysLip/14jAjDL+viLYgxdVyOGQKQGBa
# +yV+XHTaEyKdihKG4Z5nWuC0yM+sdZQpWXQAcHJLPaPs5wDGICICpdAFY2LbAWSK
# jtX9uq7crywIL4mVKiX+HOjRUPCAYUx/2TcqJf2+0+MKDEVC33ikxNbcx8ZELY+Q
# +hGyOws3mkHSQjyaNUVgnnQtGzikYqcNO2efa+zVPdXYd+TUWW2e9I++Qf48r0Hv
# OqeZAB7bSAb39PNRuj0I1gt4d3WTHzHt7BSpX1OuFqQnzLw8vS5iDQH943WAyGkY
# NblZVb8pyzSg1Jy18H/SmrJDXeufRwqFwD+1NHyxGjsF89KOuVUqGrGpRXhMBtmA
# DSzdgn5jqW5lI1po9FqGdlPTFlhstpMH3DSfPQWurvJh42oM38gmSEHLBNpc4tXo
# 8udMYI09H/kHUoNMTZNGjnZO9LfarGsag6eOJP1bMMublhRlKCaL9RIyV9oOHycE
# IeOeQFeBP/BmYFLWbVPeZej7uiqsEc7VPDJK2QXns210UYanaWmggkmpdAr0I0EV
# pEKHSfVv1qlIlFH4d7MhcJzP2/rY62EC5tYQjT0UaBnCRcDInKrNWa3kbDL0akwr
# 0aJgpbT5ipknVChtwnMWJlbqpeW/VUF5g0jVpYQ3jbe/Zf+OtmU=
# =Pv8z
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 03 Nov 2023 20:04:40 HKT
# gpg:                using RSA key 1899FF8EDEBF58CCEE034B82F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>" [full]
# gpg:                 aka "Juan Quintela <quintela@trasno.org>" [full]
# Primary key fingerprint: 1899 FF8E DEBF 58CC EE03  4B82 F487 EF18 5872 D723

* tag 'migration-20231103-pull-request' of https://gitlab.com/juan.quintela/qemu:
  migration: Unlock mutex in error case
  docs/migration: Add the dirty limit section
  tests/migration: Introduce dirty-limit into guestperf
  tests/migration: Introduce dirty-ring-size option into guestperf
  tests: Add migration dirty-limit capability test
  system/dirtylimit: Drop the reduplicative check
  system/dirtylimit: Fix a race situation

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

7 files changed, 261 insertions, 8 deletions

diff --git a/tests/migration/guestperf/comparison.py b/tests/migration/guestperf/comparison.py
index c03b3f6d7e..42cc0372d1 100644
--- a/tests/migration/guestperf/comparison.py
+++ b/tests/migration/guestperf/comparison.py
@@ -135,4 +135,27 @@ COMPARISONS = [
         Scenario("compr-multifd-channels-64",
                  multifd=True, multifd_channels=64),
     ]),
+
+    # Looking at effect of dirty-limit with
+    # varying x_vcpu_dirty_limit_period
+    Comparison("compr-dirty-limit-period", scenarios = [
+        Scenario("compr-dirty-limit-period-500",
+                 dirty_limit=True, x_vcpu_dirty_limit_period=500),
+        Scenario("compr-dirty-limit-period-800",
+                 dirty_limit=True, x_vcpu_dirty_limit_period=800),
+        Scenario("compr-dirty-limit-period-1000",
+                 dirty_limit=True, x_vcpu_dirty_limit_period=1000),
+    ]),
+
+
+    # Looking at effect of dirty-limit with
+    # varying vcpu_dirty_limit
+    Comparison("compr-dirty-limit", scenarios = [
+        Scenario("compr-dirty-limit-10MB",
+                 dirty_limit=True, vcpu_dirty_limit=10),
+        Scenario("compr-dirty-limit-20MB",
+                 dirty_limit=True, vcpu_dirty_limit=20),
+        Scenario("compr-dirty-limit-50MB",
+                 dirty_limit=True, vcpu_dirty_limit=50),
+    ]),
 ]
diff --git a/tests/migration/guestperf/engine.py b/tests/migration/guestperf/engine.py
index da96ca034a..608d7270f6 100644
--- a/tests/migration/guestperf/engine.py
+++ b/tests/migration/guestperf/engine.py
@@ -102,6 +102,8 @@ class Engine(object):
             info.get("expected-downtime", 0),
             info.get("setup-time", 0),
             info.get("cpu-throttle-percentage", 0),
+            info.get("dirty-limit-throttle-time-per-round", 0),
+            info.get("dirty-limit-ring-full-time", 0),
         )
 
     def _migrate(self, hardware, scenario, src, dst, connect_uri):
@@ -203,6 +205,21 @@ class Engine(object):
             resp = dst.cmd("migrate-set-parameters",
                            multifd_channels=scenario._multifd_channels)
 
+        if scenario._dirty_limit:
+            if not hardware._dirty_ring_size:
+                raise Exception("dirty ring size must be configured when "
+                                "testing dirty limit migration")
+
+            resp = src.cmd("migrate-set-capabilities",
+                           capabilities = [
+                               { "capability": "dirty-limit",
+                                 "state": True }
+                           ])
+            resp = src.cmd("migrate-set-parameters",
+                x_vcpu_dirty_limit_period=scenario._x_vcpu_dirty_limit_period)
+            resp = src.cmd("migrate-set-parameters",
+                           vcpu_dirty_limit=scenario._vcpu_dirty_limit)
+
         resp = src.cmd("migrate", uri=connect_uri)
 
         post_copy = False
@@ -325,7 +342,6 @@ class Engine(object):
             cmdline = "'" + cmdline + "'"
 
         argv = [
-            "-accel", "kvm",
             "-cpu", "host",
             "-kernel", self._kernel,
             "-initrd", self._initrd,
@@ -333,6 +349,11 @@ class Engine(object):
             "-m", str((hardware._mem * 1024) + 512),
             "-smp", str(hardware._cpus),
         ]
+        if hardware._dirty_ring_size:
+            argv.extend(["-accel", "kvm,dirty-ring-size=%s" %
+                         hardware._dirty_ring_size])
+        else:
+            argv.extend(["-accel", "kvm"])
 
         argv.extend(self._get_qemu_serial_args())
 
diff --git a/tests/migration/guestperf/hardware.py b/tests/migration/guestperf/hardware.py
index 3145785ffd..f779cc050b 100644
--- a/tests/migration/guestperf/hardware.py
+++ b/tests/migration/guestperf/hardware.py
@@ -23,7 +23,8 @@ class Hardware(object):
                  src_cpu_bind=None, src_mem_bind=None,
                  dst_cpu_bind=None, dst_mem_bind=None,
                  prealloc_pages = False,
-                 huge_pages=False, locked_pages=False):
+                 huge_pages=False, locked_pages=False,
+                 dirty_ring_size=0):
         self._cpus = cpus
         self._mem = mem # GiB
         self._src_mem_bind = src_mem_bind # List of NUMA nodes
@@ -33,6 +34,7 @@ class Hardware(object):
         self._prealloc_pages = prealloc_pages
         self._huge_pages = huge_pages
         self._locked_pages = locked_pages
+        self._dirty_ring_size = dirty_ring_size
 
 
     def serialize(self):
@@ -46,6 +48,7 @@ class Hardware(object):
             "prealloc_pages": self._prealloc_pages,
             "huge_pages": self._huge_pages,
             "locked_pages": self._locked_pages,
+            "dirty_ring_size": self._dirty_ring_size,
         }
 
     @classmethod
@@ -59,4 +62,5 @@ class Hardware(object):
             data["dst_mem_bind"],
             data["prealloc_pages"],
             data["huge_pages"],
-            data["locked_pages"])
+            data["locked_pages"],
+            data["dirty_ring_size"])
diff --git a/tests/migration/guestperf/progress.py b/tests/migration/guestperf/progress.py
index ab1ee57273..d490584217 100644
--- a/tests/migration/guestperf/progress.py
+++ b/tests/migration/guestperf/progress.py
@@ -81,7 +81,9 @@ class Progress(object):
                  downtime,
                  downtime_expected,
                  setup_time,
-                 throttle_pcent):
+                 throttle_pcent,
+                 dirty_limit_throttle_time_per_round,
+                 dirty_limit_ring_full_time):
 
         self._status = status
         self._ram = ram
@@ -91,6 +93,10 @@ class Progress(object):
         self._downtime_expected = downtime_expected
         self._setup_time = setup_time
         self._throttle_pcent = throttle_pcent
+        self._dirty_limit_throttle_time_per_round = \
+            dirty_limit_throttle_time_per_round
+        self._dirty_limit_ring_full_time = \
+            dirty_limit_ring_full_time
 
     def serialize(self):
         return {
@@ -102,6 +108,10 @@ class Progress(object):
             "downtime_expected": self._downtime_expected,
             "setup_time": self._setup_time,
             "throttle_pcent": self._throttle_pcent,
+            "dirty_limit_throttle_time_per_round":
+                self._dirty_limit_throttle_time_per_round,
+            "dirty_limit_ring_full_time":
+                self._dirty_limit_ring_full_time,
         }
 
     @classmethod
@@ -114,4 +124,6 @@ class Progress(object):
             data["downtime"],
             data["downtime_expected"],
             data["setup_time"],
-            data["throttle_pcent"])
+            data["throttle_pcent"],
+            data["dirty_limit_throttle_time_per_round"],
+            data["dirty_limit_ring_full_time"])
diff --git a/tests/migration/guestperf/scenario.py b/tests/migration/guestperf/scenario.py
index de70d9b2f5..154c4f5d5f 100644
--- a/tests/migration/guestperf/scenario.py
+++ b/tests/migration/guestperf/scenario.py
@@ -30,7 +30,9 @@ class Scenario(object):
                  auto_converge=False, auto_converge_step=10,
                  compression_mt=False, compression_mt_threads=1,
                  compression_xbzrle=False, compression_xbzrle_cache=10,
-                 multifd=False, multifd_channels=2):
+                 multifd=False, multifd_channels=2,
+                 dirty_limit=False, x_vcpu_dirty_limit_period=500,
+                 vcpu_dirty_limit=1):
 
         self._name = name
 
@@ -60,6 +62,10 @@ class Scenario(object):
         self._multifd = multifd
         self._multifd_channels = multifd_channels
 
+        self._dirty_limit = dirty_limit
+        self._x_vcpu_dirty_limit_period = x_vcpu_dirty_limit_period
+        self._vcpu_dirty_limit = vcpu_dirty_limit
+
     def serialize(self):
         return {
             "name": self._name,
@@ -79,6 +85,9 @@ class Scenario(object):
             "compression_xbzrle_cache": self._compression_xbzrle_cache,
             "multifd": self._multifd,
             "multifd_channels": self._multifd_channels,
+            "dirty_limit": self._dirty_limit,
+            "x_vcpu_dirty_limit_period": self._x_vcpu_dirty_limit_period,
+            "vcpu_dirty_limit": self._vcpu_dirty_limit,
         }
 
     @classmethod
diff --git a/tests/migration/guestperf/shell.py b/tests/migration/guestperf/shell.py
index 8a809e3dda..c85d89efec 100644
--- a/tests/migration/guestperf/shell.py
+++ b/tests/migration/guestperf/shell.py
@@ -60,6 +60,8 @@ class BaseShell(object):
         parser.add_argument("--prealloc-pages", dest="prealloc_pages", default=False)
         parser.add_argument("--huge-pages", dest="huge_pages", default=False)
         parser.add_argument("--locked-pages", dest="locked_pages", default=False)
+        parser.add_argument("--dirty-ring-size", dest="dirty_ring_size",
+                            default=0, type=int)
 
         self._parser = parser
 
@@ -89,7 +91,9 @@ class BaseShell(object):
 
                         locked_pages=args.locked_pages,
                         huge_pages=args.huge_pages,
-                        prealloc_pages=args.prealloc_pages)
+                        prealloc_pages=args.prealloc_pages,
+
+                        dirty_ring_size=args.dirty_ring_size)
 
 
 class Shell(BaseShell):
@@ -127,6 +131,17 @@ class Shell(BaseShell):
         parser.add_argument("--multifd-channels", dest="multifd_channels",
                             default=2, type=int)
 
+        parser.add_argument("--dirty-limit", dest="dirty_limit", default=False,
+                            action="store_true")
+
+        parser.add_argument("--x-vcpu-dirty-limit-period",
+                            dest="x_vcpu_dirty_limit_period",
+                            default=500, type=int)
+
+        parser.add_argument("--vcpu-dirty-limit",
+                            dest="vcpu_dirty_limit",
+                            default=1, type=int)
+
     def get_scenario(self, args):
         return Scenario(name="perfreport",
                         downtime=args.downtime,
@@ -150,7 +165,12 @@ class Shell(BaseShell):
                         compression_xbzrle_cache=args.compression_xbzrle_cache,
 
                         multifd=args.multifd,
-                        multifd_channels=args.multifd_channels)
+                        multifd_channels=args.multifd_channels,
+
+                        dirty_limit=args.dirty_limit,
+                        x_vcpu_dirty_limit_period=\
+                            args.x_vcpu_dirty_limit_period,
+                        vcpu_dirty_limit=args.vcpu_dirty_limit)
 
     def run(self, argv):
         args = self._parser.parse_args(argv)
diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index e803b46039..5752412b64 100644
--- a/tests/qtest/migration-test.c
+++ b/tests/qtest/migration-test.c
@@ -3091,6 +3091,166 @@ static void test_vcpu_dirty_limit(void)
     dirtylimit_stop_vm(vm);
 }
 
+static void migrate_dirty_limit_wait_showup(QTestState *from,
+                                            const int64_t period,
+                                            const int64_t value)
+{
+    /* Enable dirty limit capability */
+    migrate_set_capability(from, "dirty-limit", true);
+
+    /* Set dirty limit parameters */
+    migrate_set_parameter_int(from, "x-vcpu-dirty-limit-period", period);
+    migrate_set_parameter_int(from, "vcpu-dirty-limit", value);
+
+    /* Make sure migrate can't converge */
+    migrate_ensure_non_converge(from);
+
+    /* To check limit rate after precopy */
+    migrate_set_capability(from, "pause-before-switchover", true);
+
+    /* Wait for the serial output from the source */
+    wait_for_serial("src_serial");
+}
+
+/*
+ * This test does:
+ *  source                          destination
+ *  start vm
+ *                                  start incoming vm
+ *  migrate
+ *  wait dirty limit to begin
+ *  cancel migrate
+ *  cancellation check
+ *                                  restart incoming vm
+ *  migrate
+ *  wait dirty limit to begin
+ *  wait pre-switchover event
+ *  convergence condition check
+ *
+ * And see if dirty limit migration works correctly.
+ * This test case involves many passes, so it runs in slow mode only.
+ */
+static void test_migrate_dirty_limit(void)
+{
+    g_autofree char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
+    QTestState *from, *to;
+    int64_t remaining;
+    uint64_t throttle_us_per_full;
+    /*
+     * We want the test to be stable and as fast as possible.
+     * E.g., with 1Gb/s bandwith migration may pass without dirty limit,
+     * so we need to decrease a bandwidth.
+     */
+    const int64_t dirtylimit_period = 1000, dirtylimit_value = 50;
+    const int64_t max_bandwidth = 400000000; /* ~400Mb/s */
+    const int64_t downtime_limit = 250; /* 250ms */
+    /*
+     * We migrate through unix-socket (> 500Mb/s).
+     * Thus, expected migration speed ~= bandwidth limit (< 500Mb/s).
+     * So, we can predict expected_threshold
+     */
+    const int64_t expected_threshold = max_bandwidth * downtime_limit / 1000;
+    int max_try_count = 10;
+    MigrateCommon args = {
+        .start = {
+            .hide_stderr = true,
+            .use_dirty_ring = true,
+        },
+        .listen_uri = uri,
+        .connect_uri = uri,
+    };
+
+    /* Start src, dst vm */
+    if (test_migrate_start(&from, &to, args.listen_uri, &args.start)) {
+        return;
+    }
+
+    /* Prepare for dirty limit migration and wait src vm show up */
+    migrate_dirty_limit_wait_showup(from, dirtylimit_period, dirtylimit_value);
+
+    /* Start migrate */
+    migrate_qmp(from, uri, "{}");
+
+    /* Wait for dirty limit throttle begin */
+    throttle_us_per_full = 0;
+    while (throttle_us_per_full == 0) {
+        throttle_us_per_full =
+        read_migrate_property_int(from, "dirty-limit-throttle-time-per-round");
+        usleep(100);
+        g_assert_false(got_src_stop);
+    }
+
+    /* Now cancel migrate and wait for dirty limit throttle switch off */
+    migrate_cancel(from);
+    wait_for_migration_status(from, "cancelled", NULL);
+
+    /* Check if dirty limit throttle switched off, set timeout 1ms */
+    do {
+        throttle_us_per_full =
+        read_migrate_property_int(from, "dirty-limit-throttle-time-per-round");
+        usleep(100);
+        g_assert_false(got_src_stop);
+    } while (throttle_us_per_full != 0 && --max_try_count);
+
+    /* Assert dirty limit is not in service */
+    g_assert_cmpint(throttle_us_per_full, ==, 0);
+
+    args = (MigrateCommon) {
+        .start = {
+            .only_target = true,
+            .use_dirty_ring = true,
+        },
+        .listen_uri = uri,
+        .connect_uri = uri,
+    };
+
+    /* Restart dst vm, src vm already show up so we needn't wait anymore */
+    if (test_migrate_start(&from, &to, args.listen_uri, &args.start)) {
+        return;
+    }
+
+    /* Start migrate */
+    migrate_qmp(from, uri, "{}");
+
+    /* Wait for dirty limit throttle begin */
+    throttle_us_per_full = 0;
+    while (throttle_us_per_full == 0) {
+        throttle_us_per_full =
+        read_migrate_property_int(from, "dirty-limit-throttle-time-per-round");
+        usleep(100);
+        g_assert_false(got_src_stop);
+    }
+
+    /*
+     * The dirty limit rate should equals the return value of
+     * query-vcpu-dirty-limit if dirty limit cap set
+     */
+    g_assert_cmpint(dirtylimit_value, ==, get_limit_rate(from));
+
+    /* Now, we have tested if dirty limit works, let it converge */
+    migrate_set_parameter_int(from, "downtime-limit", downtime_limit);
+    migrate_set_parameter_int(from, "max-bandwidth", max_bandwidth);
+
+    /*
+     * Wait for pre-switchover status to check if migration
+     * satisfy the convergence condition
+     */
+    wait_for_migration_status(from, "pre-switchover", NULL);
+
+    remaining = read_ram_property_int(from, "remaining");
+    g_assert_cmpint(remaining, <,
+                    (expected_threshold + expected_threshold / 100));
+
+    migrate_continue(from, "pre-switchover");
+
+    qtest_qmp_eventwait(to, "RESUME");
+
+    wait_for_serial("dest_serial");
+    wait_for_migration_complete(from);
+
+    test_migrate_end(from, to, true);
+}
+
 static bool kvm_dirty_ring_supported(void)
 {
 #if defined(__linux__) && defined(HOST_X86_64)
@@ -3301,6 +3461,10 @@ int main(int argc, char **argv)
      */
     if (g_test_slow()) {
         qtest_add_func("/migration/auto_converge", test_migrate_auto_converge);
+        if (g_str_equal(arch, "x86_64") &&
+            has_kvm && kvm_dirty_ring_supported()) {
+            qtest_add_func("/migration/dirty_limit", test_migrate_dirty_limit);
+        }
     }
     qtest_add_func("/migration/multifd/tcp/plain/none",
                    test_multifd_tcp_none);