migration/postcopy: blocktime allows track / report non-vCPU faults

When used to report page fault latencies, the blocktime feature can be
almost useless when KVM async page fault is enabled, because in most cases
such remote fault will kickoff async page faults, then it's not trackable
from blocktime layer.

After all these recent rewrites to blocktime layer, it's finally so easy to
also support tracking non-vCPU faults.  It'll be even faster if we could
always index fault records with TIDs, unfortunately we need to maintain the
blocktime API which report things in vCPU indexes.

Of course this can work not only for kworkers, but also any guest accesses
that may reach a missing page, for example, very likely when in the QEMU
main thread too (and all other threads whenever applicable).

In this case, we don't care about "how long the threads are blocked", but
we only care about "how long the fault will be resolved".

Cc: Markus Armbruster <armbru@redhat.com>
Cc: Dr. David Alan Gilbert <dave@treblig.org>
Reviewed-by: Fabiano Rosas <farosas@suse.de>
Tested-by: Mario Casquero <mcasquer@redhat.com>
Link: https://lore.kernel.org/r/20250613141217.474825-14-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Fabiano Rosas <farosas@suse.de>

1 files changed, 50 insertions, 14 deletions

diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 91c23b446e..f4cb23b3e0 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -192,6 +192,8 @@ typedef struct PostcopyBlocktimeContext {
     GHashTable *tid_to_vcpu_hash;
     /* Count of non-vCPU faults.  This is only for debugging purpose. */
     uint64_t non_vcpu_faults;
+    /* total blocktime when a non-vCPU thread is stopped */
+    uint64_t non_vcpu_blocktime_total;
 
     /*
      * Handler for exit event, necessary for
@@ -203,7 +205,10 @@ typedef struct PostcopyBlocktimeContext {
 typedef struct {
     /* The time the fault was triggered */
     uint64_t fault_time;
-    /* The vCPU index that was blocked */
+    /*
+     * The vCPU index that was blocked, when cpu==-1, it means it's a
+     * fault from non-vCPU threads.
+     */
     int cpu;
 } BlocktimeVCPUEntry;
 
@@ -344,6 +349,12 @@ void fill_destination_postcopy_migration_info(MigrationInfo *info)
         QAPI_LIST_PREPEND(list_latency, latency);
     }
 
+    latency_total += bc->non_vcpu_blocktime_total;
+    faults += bc->non_vcpu_faults;
+
+    info->has_postcopy_non_vcpu_latency = true;
+    info->postcopy_non_vcpu_latency = bc->non_vcpu_faults ?
+        (bc->non_vcpu_blocktime_total / bc->non_vcpu_faults) : 0;
     info->has_postcopy_blocktime = true;
     /* Convert ns -> ms */
     info->postcopy_blocktime = (uint32_t)(bc->total_blocktime / SCALE_MS);
@@ -983,7 +994,10 @@ static uint64_t get_current_ns(void)
     return (uint64_t)qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
 }
 
-/* Inject an (cpu, fault_time) entry into the database, using addr as key */
+/*
+ * Inject an (cpu, fault_time) entry into the database, using addr as key.
+ * When cpu==-1, it means it's a non-vCPU fault.
+ */
 static void blocktime_fault_inject(PostcopyBlocktimeContext *ctx,
                                    uintptr_t addr, int cpu, uint64_t time)
 {
@@ -1066,9 +1080,17 @@ void mark_postcopy_blocktime_begin(uintptr_t addr, uint32_t ptid,
         /* Making sure it won't overflow - it really should never! */
         assert(dc->vcpu_faults_current[cpu] <= 255);
     } else {
-        /* We do not support non-vCPU thread tracking yet */
+        /*
+         * For non-vCPU thread faults, we don't care about tid or cpu index
+         * or time the thread is blocked (e.g., a kworker trying to help
+         * KVM when async_pf=on is OK to be blocked and not affect guest
+         * responsiveness), but we care about latency.  Track it with
+         * cpu=-1.
+         *
+         * Note that this will NOT affect blocktime reports on vCPU being
+         * blocked, but only about system-wide latency reports.
+         */
         dc->non_vcpu_faults++;
-        return;
     }
 
     blocktime_fault_inject(dc, addr, cpu, current);
@@ -1078,6 +1100,7 @@ typedef struct {
     PostcopyBlocktimeContext *ctx;
     uint64_t current;
     int affected_cpus;
+    int affected_non_cpus;
 } BlockTimeVCPUIter;
 
 static void blocktime_cpu_list_iter_fn(gpointer data, gpointer user_data)
@@ -1085,6 +1108,7 @@ static void blocktime_cpu_list_iter_fn(gpointer data, gpointer user_data)
     BlockTimeVCPUIter *iter = user_data;
     PostcopyBlocktimeContext *ctx = iter->ctx;
     BlocktimeVCPUEntry *entry = data;
+    uint64_t time_passed;
     int cpu = entry->cpu;
 
     /*
@@ -1092,17 +1116,27 @@ static void blocktime_cpu_list_iter_fn(gpointer data, gpointer user_data)
      * later than when it was faulted.
      */
     assert(iter->current >= entry->fault_time);
+    time_passed = iter->current - entry->fault_time;
 
-    /*
-     * If we resolved all pending faults on one vCPU due to this page
-     * resolution, take a note.
-     */
-    if (--ctx->vcpu_faults_current[cpu] == 0) {
-        ctx->vcpu_blocktime_total[cpu] += iter->current - entry->fault_time;
-        iter->affected_cpus += 1;
+    if (cpu >= 0) {
+        /*
+         * If we resolved all pending faults on one vCPU due to this page
+         * resolution, take a note.
+         */
+        if (--ctx->vcpu_faults_current[cpu] == 0) {
+            ctx->vcpu_blocktime_total[cpu] += time_passed;
+            iter->affected_cpus += 1;
+        }
+        trace_postcopy_blocktime_end_one(cpu, ctx->vcpu_faults_current[cpu]);
+    } else {
+        iter->affected_non_cpus++;
+        ctx->non_vcpu_blocktime_total += time_passed;
+        /*
+         * We do not maintain how many pending non-vCPU faults because we
+         * do not care about blocktime, only latency.
+         */
+        trace_postcopy_blocktime_end_one(-1, 0);
     }
-
-    trace_postcopy_blocktime_end_one(cpu, ctx->vcpu_faults_current[cpu]);
 }
 
 /*
@@ -1141,6 +1175,7 @@ static void mark_postcopy_blocktime_end(uintptr_t addr)
     BlockTimeVCPUIter iter = {
         .current = get_current_ns(),
         .affected_cpus = 0,
+        .affected_non_cpus = 0,
         .ctx = dc,
     };
     gpointer key = (gpointer)addr;
@@ -1174,7 +1209,8 @@ static void mark_postcopy_blocktime_end(uintptr_t addr)
     }
     dc->smp_cpus_down -= iter.affected_cpus;
 
-    trace_postcopy_blocktime_end(addr, iter.current, iter.affected_cpus);
+    trace_postcopy_blocktime_end(addr, iter.current, iter.affected_cpus,
+                                 iter.affected_non_cpus);
 }
 
 static void postcopy_pause_fault_thread(MigrationIncomingState *mis)