From: Denis V. Lunev <[email protected]> A post_load hook which only rearranges the memory topology forces a flatview rebuild as its section is read, and the cost of a rebuild grows with the number of regions in the machine. A device which does this once per vCPU therefore scales badly on the destination.
Add post_load_deferrable. A vmsd which sets it has its hook queued during the load and run once the stream has been consumed, in the order the hooks would have fired, with the whole drain sharing one memory transaction. Opt-in, because deferral is not free in general. A hook which can fail must not be deferred: failing after the stream is consumed means the source has already been told the migration succeeded, and may release a guest the destination never started. A hook which reads guest memory must not be deferred either, since the drain runs with the topology in flux. Postcopy is excluded because its listen thread walks the same stream concurrently. CC: Peter Xu <[email protected]> CC: Fabiano Rosas <[email protected]> CC: Paolo Bonzini <[email protected]> CC: Zhao Liu <[email protected]> Signed-off-by: Denis V. Lunev <[email protected]> --- include/migration/vmstate.h | 40 +++++++++++++ migration/savevm.c | 23 ++++++++ migration/vmstate.c | 67 +++++++++++++++++++++- tests/unit/test-vmstate.c | 111 ++++++++++++++++++++++++++++++++++++ 4 files changed, 239 insertions(+), 2 deletions(-) diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index e72c3fae9a..16045319d5 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -303,6 +303,29 @@ struct VMStateDescription { bool (*pre_load_errp)(void *opaque, Error **errp); int (*post_load)(void *opaque, int version_id); bool (*post_load_errp)(void *opaque, int version_id, Error **errp); + + /* + * Run .post_load() once the whole stream has been loaded rather than + * as this section is read, so that it sees a machine whose devices + * have all been restored, and so that several of them can share the + * work they would each repeat. + * + * Three things must hold of a hook before it may be deferred. + * + * It must not fail. By the time the queue is drained the stream has + * been consumed, so a source may already have been told the migration + * succeeded and may have released the guest; there is nothing left to + * report a failure to. A hook which fails here is a bug in its vmsd + * and is fatal. + * + * Nothing else in the load may depend on what it does. The hooks run + * after every section has been read, so anything a later section needs + * to observe must not be produced here. + * + * It must not read guest memory or resolve an address space, because + * the drain runs as one batch with the memory topology in flux. + */ + bool post_load_deferrable; int (*pre_save)(void *opaque); bool (*pre_save_errp)(void *opaque, Error **errp); @@ -1299,6 +1322,23 @@ bool vmstate_save_vmsd(QEMUFile *f, const VMStateDescription *vmsd, bool vmstate_section_needed(const VMStateDescription *vmsd, void *opaque); +/** + * vmstate_post_load_defer_begin: Queue deferrable post_load hooks + * + * Between this and vmstate_post_load_defer_finish(), a post_load hook whose + * vmsd sets post_load_deferrable is recorded rather than called. Hooks are + * queued in the order they would have run. + */ +void vmstate_post_load_defer_begin(void); + +/** + * vmstate_post_load_defer_finish: Stop deferring and drain the queue + * @run: run the queued hooks, in order; when false, discard them + * + * Returns false if a hook failed, in which case the rest are discarded. + */ +bool vmstate_post_load_defer_finish(bool run, Error **errp); + #define VMSTATE_INSTANCE_ID_ANY -1 /* Returns: 0 on success, -1 on failure */ diff --git a/migration/savevm.c b/migration/savevm.c index 4b590ea672..2352dcf684 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -3128,6 +3128,7 @@ int qemu_loadvm_state(QEMUFile *f, Error **errp) { MigrationState *s = migrate_get_current(); MigrationIncomingState *mis = migration_incoming_get_current(); + bool defer_post_load; int ret; if (qemu_savevm_state_blocked(errp)) { @@ -3147,7 +3148,29 @@ int qemu_loadvm_state(QEMUFile *f, Error **errp) cpu_synchronize_all_pre_loadvm(); + /* + * The postcopy listen thread walks the same stream concurrently, so the + * queue would need locking and a defined owner for the drain. + */ + defer_post_load = !migrate_postcopy_ram(); + if (defer_post_load) { + vmstate_post_load_defer_begin(); + } + ret = qemu_loadvm_state_main(f, mis, errp); + + if (defer_post_load) { + /* + * A deferrable hook only rearranges the memory topology, so the + * whole drain can share one flatview rebuild. + */ + memory_region_transaction_begin(); + if (!vmstate_post_load_defer_finish(ret == 0, errp)) { + ret = -EINVAL; + } + memory_region_transaction_commit(); + } + qemu_event_set(&mis->main_thread_load_event); trace_qemu_loadvm_state_post_main(ret); diff --git a/migration/vmstate.c b/migration/vmstate.c index 24004565bf..3745f80dc8 100644 --- a/migration/vmstate.c +++ b/migration/vmstate.c @@ -250,8 +250,19 @@ static bool vmstate_load_field(QEMUFile *f, void *pv, size_t size, return true; } -static bool vmstate_post_load(const VMStateDescription *vmsd, - void *opaque, int version_id, Error **errp) +typedef struct VMStateDeferredPostLoad { + const VMStateDescription *vmsd; + void *opaque; + int version_id; + QSIMPLEQ_ENTRY(VMStateDeferredPostLoad) entry; +} VMStateDeferredPostLoad; + +static QSIMPLEQ_HEAD(, VMStateDeferredPostLoad) vmstate_deferred_post_loads = + QSIMPLEQ_HEAD_INITIALIZER(vmstate_deferred_post_loads); +static bool vmstate_defer_post_load; + +static bool vmstate_do_post_load(const VMStateDescription *vmsd, + void *opaque, int version_id, Error **errp) { ERRP_GUARD(); @@ -277,6 +288,58 @@ static bool vmstate_post_load(const VMStateDescription *vmsd, return true; } +static bool vmstate_post_load(const VMStateDescription *vmsd, + void *opaque, int version_id, Error **errp) +{ + VMStateDeferredPostLoad *d; + + if (!vmstate_defer_post_load || !vmsd->post_load_deferrable) { + return vmstate_do_post_load(vmsd, opaque, version_id, errp); + } + + d = g_new(VMStateDeferredPostLoad, 1); + d->vmsd = vmsd; + d->opaque = opaque; + d->version_id = version_id; + QSIMPLEQ_INSERT_TAIL(&vmstate_deferred_post_loads, d, entry); + + return true; +} + +void vmstate_post_load_defer_begin(void) +{ + assert(!vmstate_defer_post_load); + assert(QSIMPLEQ_EMPTY(&vmstate_deferred_post_loads)); + vmstate_defer_post_load = true; +} + +bool vmstate_post_load_defer_finish(bool run, Error **errp) +{ + VMStateDeferredPostLoad *d; + bool ok = true; + + vmstate_defer_post_load = false; + + while ((d = QSIMPLEQ_FIRST(&vmstate_deferred_post_loads))) { + QSIMPLEQ_REMOVE_HEAD(&vmstate_deferred_post_loads, entry); + if (run) { + ERRP_GUARD(); + + if (!vmstate_do_post_load(d->vmsd, d->opaque, d->version_id, + errp)) { + error_prepend(errp, "deferrable post load hook failed, which " + "its vmsd promised could not happen: "); + error_report_err(*errp); + *errp = NULL; + abort(); + } + } + g_free(d); + } + + return ok; +} + /* * Try to prepare loading the next element, the object pointer to be put * into @next_elem. When @next_elem is NULL, it means we should skip diff --git a/tests/unit/test-vmstate.c b/tests/unit/test-vmstate.c index df1fb4c778..e1e64b23c2 100644 --- a/tests/unit/test-vmstate.c +++ b/tests/unit/test-vmstate.c @@ -1619,6 +1619,116 @@ static void test_tmp_struct(void) g_assert_cmpint(obj.f, ==, 8); /* From the child->parent */ } +/* Deferred post_load */ + +static int defer_order; +static int defer_a_ran; +static int defer_b_ran; +static int defer_inline_ran; + +static int defer_a_post_load(void *opaque, int version_id) +{ + defer_a_ran = ++defer_order; + return 0; +} + +static int defer_b_post_load(void *opaque, int version_id) +{ + defer_b_ran = ++defer_order; + return 0; +} + +static int defer_inline_post_load(void *opaque, int version_id) +{ + defer_inline_ran = ++defer_order; + return 0; +} + +static const VMStateDescription vmstate_defer_a = { + .name = "test/defer_a", + .version_id = 1, + .post_load = defer_a_post_load, + .post_load_deferrable = true, + .fields = (const VMStateField[]) { + VMSTATE_UINT32(a, TestStruct), + VMSTATE_END_OF_LIST() + } +}; + +static const VMStateDescription vmstate_defer_b = { + .name = "test/defer_b", + .version_id = 1, + .post_load = defer_b_post_load, + .post_load_deferrable = true, + .fields = (const VMStateField[]) { + VMSTATE_UINT32(a, TestStruct), + VMSTATE_END_OF_LIST() + } +}; + +static const VMStateDescription vmstate_defer_inline = { + .name = "test/defer_inline", + .version_id = 1, + .post_load = defer_inline_post_load, + .fields = (const VMStateField[]) { + VMSTATE_UINT32(a, TestStruct), + VMSTATE_END_OF_LIST() + } +}; + +static void defer_reset(void) +{ + defer_order = 0; + defer_a_ran = 0; + defer_b_ran = 0; + defer_inline_ran = 0; +} + +static void test_post_load_defer(void) +{ + uint8_t const wire[] = { + /* uint32 a */ 0x00, 0x00, 0x00, 0x01, + QEMU_VM_EOF, + }; + TestStruct obj; + Error *err = NULL; + + /* Not deferring: a deferrable hook still runs as the section is read */ + defer_reset(); + memset(&obj, 0, sizeof(obj)); + SUCCESS(load_vmstate_one(&vmstate_defer_a, &obj, 1, wire, sizeof(wire))); + g_assert_cmpint(defer_a_ran, ==, 1); + + /* + * Deferring holds back the hooks which opted in and replays them in the + * order they would have run. A hook which did not opt in is unaffected. + */ + defer_reset(); + memset(&obj, 0, sizeof(obj)); + vmstate_post_load_defer_begin(); + SUCCESS(load_vmstate_one(&vmstate_defer_a, &obj, 1, wire, sizeof(wire))); + SUCCESS(load_vmstate_one(&vmstate_defer_inline, &obj, 1, wire, + sizeof(wire))); + SUCCESS(load_vmstate_one(&vmstate_defer_b, &obj, 1, wire, sizeof(wire))); + g_assert_cmpint(defer_a_ran, ==, 0); + g_assert_cmpint(defer_b_ran, ==, 0); + g_assert_cmpint(defer_inline_ran, ==, 1); + + g_assert(vmstate_post_load_defer_finish(true, &err)); + g_assert(!err); + g_assert_cmpint(defer_a_ran, ==, 2); + g_assert_cmpint(defer_b_ran, ==, 3); + + /* A discarded queue runs nothing */ + defer_reset(); + memset(&obj, 0, sizeof(obj)); + vmstate_post_load_defer_begin(); + SUCCESS(load_vmstate_one(&vmstate_defer_a, &obj, 1, wire, sizeof(wire))); + g_assert(vmstate_post_load_defer_finish(false, &err)); + g_assert(!err); + g_assert_cmpint(defer_a_ran, ==, 0); +} + int main(int argc, char **argv) { g_autofree char *temp_file = g_strdup_printf("%s/vmst.test.XXXXXX", @@ -1663,6 +1773,7 @@ int main(int argc, char **argv) g_test_add_func("/vmstate/qlist/save/saveqlist", test_save_qlist); g_test_add_func("/vmstate/qlist/load/loadqlist", test_load_qlist); g_test_add_func("/vmstate/tmp_struct", test_tmp_struct); + g_test_add_func("/vmstate/post_load/defer", test_post_load_defer); g_test_run(); close(temp_fd); -- 2.53.0
