[Qemu-devel] [PATCH v10 06/10] migration: add postcopy blocktime ctx into MigrationIncomingState

[Alexey Perevalov <a.perevalov@samsung.com>]

This patch adds request to kernel space for UFFD_FEATURE_THREAD_ID,
in case when this feature is provided by kernel.

PostcopyBlocktimeContext is incapsulated inside postcopy-ram.c,
due to it's postcopy only feature.
Also it defines PostcopyBlocktimeContext's instance live time.
Information from PostcopyBlocktimeContext instance will be provided
much after postcopy migration end, instance of PostcopyBlocktimeContext
will live till QEMU exit, but part of it (vcpu_addr,
page_fault_vcpu_time) used only during calculation, will be released
when postcopy ended or failed.

To enable postcopy blocktime calculation on destination, need to request
proper capabiltiy (Patch for documentation will be at the tail of the patch
set).

As an example following command enable that capability, assume QEMU was
started with
-chardev socket,id=charmonitor,path=/var/lib/migrate-vm-monitor.sock
option to control it

[root@host]#printf "{\"execute\" : \"qmp_capabilities\"}\r\n \
{\"execute\": \"migrate-set-capabilities\" , \"arguments\":   {
\"capabilities\": [ { \"capability\": \"postcopy-blocktime\", \"state\":
true } ] } }" | nc -U /var/lib/migrate-vm-monitor.sock

Or just with HMP
(qemu) migrate_set_capability postcopy-blocktime on

Signed-off-by: Alexey Perevalov <a.perevalov@samsung.com>
---
 migration/migration.h    |  8 ++++++
 migration/postcopy-ram.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 73 insertions(+)

diff --git a/migration/migration.h b/migration/migration.h
index 56bf33c..770466b 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -21,6 +21,8 @@
 #include "qemu/coroutine_int.h"
 #include "hw/qdev.h"
 
+struct PostcopyBlocktimeContext;
+
 /* State for the incoming migration */
 struct MigrationIncomingState {
     QEMUFile *from_src_file;
@@ -58,6 +60,12 @@ struct MigrationIncomingState {
     /* The coroutine we should enter (back) after failover */
     Coroutine *migration_incoming_co;
     QemuSemaphore colo_incoming_sem;
+
+    /*
+     * PostcopyBlocktimeContext to keep information for postcopy
+     * live migration, to calculate vCPU block time
+     * */
+    struct PostcopyBlocktimeContext *blocktime_ctx;
 };
 
 MigrationIncomingState *migration_incoming_get_current(void);
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index bec6c2c..cc78981 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -61,6 +61,58 @@ struct PostcopyDiscardState {
 #include <sys/eventfd.h>
 #include <linux/userfaultfd.h>
 
+typedef struct PostcopyBlocktimeContext {
+    /* time when page fault initiated per vCPU */
+    int64_t *page_fault_vcpu_time;
+    /* page address per vCPU */
+    uint64_t *vcpu_addr;
+    int64_t total_blocktime;
+    /* blocktime per vCPU */
+    int64_t *vcpu_blocktime;
+    /* point in time when last page fault was initiated */
+    int64_t last_begin;
+    /* number of vCPU are suspended */
+    int smp_cpus_down;
+
+    /*
+     * Handler for exit event, necessary for
+     * releasing whole blocktime_ctx
+     */
+    Notifier exit_notifier;
+    /*
+     * Handler for postcopy event, necessary for
+     * releasing unnecessary part of blocktime_ctx
+     */
+    Notifier postcopy_notifier;
+} PostcopyBlocktimeContext;
+
+static void destroy_blocktime_context(struct PostcopyBlocktimeContext *ctx)
+{
+    g_free(ctx->page_fault_vcpu_time);
+    g_free(ctx->vcpu_addr);
+    g_free(ctx->vcpu_blocktime);
+    g_free(ctx);
+}
+
+static void migration_exit_cb(Notifier *n, void *data)
+{
+    PostcopyBlocktimeContext *ctx = container_of(n, PostcopyBlocktimeContext,
+                                                 exit_notifier);
+    destroy_blocktime_context(ctx);
+}
+
+static struct PostcopyBlocktimeContext *blocktime_context_new(void)
+{
+    PostcopyBlocktimeContext *ctx = g_new0(PostcopyBlocktimeContext, 1);
+    ctx->page_fault_vcpu_time = g_new0(int64_t, smp_cpus);
+    ctx->vcpu_addr = g_new0(uint64_t, smp_cpus);
+    ctx->vcpu_blocktime = g_new0(int64_t, smp_cpus);
+
+    ctx->exit_notifier.notify = migration_exit_cb;
+    qemu_add_exit_notifier(&ctx->exit_notifier);
+    add_migration_state_change_notifier(&ctx->postcopy_notifier);
+    return ctx;
+}
 
 /**
  * receive_ufd_features: check userfault fd features, to request only supported
@@ -153,6 +205,19 @@ static bool ufd_check_and_apply(int ufd, MigrationIncomingState *mis)
         }
     }
 
+#ifdef UFFD_FEATURE_THREAD_ID
+    if (migrate_postcopy_blocktime() && mis &&
+        UFFD_FEATURE_THREAD_ID & supported_features) {
+        /* kernel supports that feature */
+        /* don't create blocktime_context if it exists */
+        if (!mis->blocktime_ctx) {
+            mis->blocktime_ctx = blocktime_context_new();
+        }
+
+        asked_features |= UFFD_FEATURE_THREAD_ID;
+    }
+#endif
+
     /*
      * request features, even if asked_features is 0, due to
      * kernel expects UFFD_API before UFFDIO_REGISTER, per
-- 
1.9.1