migration/postcopy: Cache the tid->vcpu mapping for blocktime

Looking up the vCPU index for each fault can be expensive when there're
hundreds of vCPUs.  Provide a cache for tid->vcpu instead with a hash
table, then lookup from there.

When at it, add another counter to record how many non-vCPU faults it gets.
For example, the main thread can also access a guest page that was missing.
These kind of faults are not accounted by blocktime so far.

Reviewed-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/r/20250613141217.474825-11-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Fabiano Rosas <farosas@suse.de>

1 files changed, 58 insertions, 10 deletions

diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index dd3615663f..bf65d6035c 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -128,6 +128,17 @@ typedef struct PostcopyBlocktimeContext {
     int smp_cpus_down;
 
     /*
+     * Fast path for looking up vcpu_index from tid.  NOTE: this result
+     * only reflects the vcpu setup when postcopy is running.  It may not
+     * always match with the current vcpu setup because vcpus can be hot
+     * attached/detached after migration completes.  However this should be
+     * stable when blocktime is using the structure.
+     */
+    GHashTable *tid_to_vcpu_hash;
+    /* Count of non-vCPU faults.  This is only for debugging purpose. */
+    uint64_t non_vcpu_faults;
+
+    /*
      * Handler for exit event, necessary for
      * releasing whole blocktime_ctx
      */
@@ -136,6 +147,7 @@ typedef struct PostcopyBlocktimeContext {
 
 static void destroy_blocktime_context(struct PostcopyBlocktimeContext *ctx)
 {
+    g_hash_table_destroy(ctx->tid_to_vcpu_hash);
     g_free(ctx->vcpu_blocktime_start);
     g_free(ctx->vcpu_blocktime_total);
     g_free(ctx->vcpu_faults_count);
@@ -150,6 +162,36 @@ static void migration_exit_cb(Notifier *n, void *data)
     destroy_blocktime_context(ctx);
 }
 
+static GHashTable *blocktime_init_tid_to_vcpu_hash(void)
+{
+    /*
+     * TID as an unsigned int can be directly used as the key.  However,
+     * CPU index can NOT be directly used as value, because CPU index can
+     * be 0, which means NULL.  Then when lookup we can never know whether
+     * it's 0 or "not found".  Hence use an indirection for CPU index.
+     */
+    GHashTable *table = g_hash_table_new_full(g_direct_hash, g_direct_equal,
+                                              NULL, g_free);
+    CPUState *cpu;
+
+    /*
+     * Initialize the tid->cpu_id mapping for lookups.  The caller needs to
+     * make sure when reaching here the CPU topology is frozen and will be
+     * stable for the whole blocktime trapping period.
+     */
+    CPU_FOREACH(cpu) {
+        int *value = g_new(int, 1);
+
+        *value = cpu->cpu_index;
+        g_hash_table_insert(table,
+                            GUINT_TO_POINTER((uint32_t)cpu->thread_id),
+                            value);
+        trace_postcopy_blocktime_tid_cpu_map(cpu->cpu_index, cpu->thread_id);
+    }
+
+    return table;
+}
+
 static struct PostcopyBlocktimeContext *blocktime_context_new(void)
 {
     MachineState *ms = MACHINE(qdev_get_machine());
@@ -160,6 +202,8 @@ static struct PostcopyBlocktimeContext *blocktime_context_new(void)
     ctx->vcpu_blocktime_total = g_new0(uint64_t, smp_cpus);
     ctx->vcpu_faults_count = g_new0(uint64_t, smp_cpus);
     ctx->vcpu_addr = g_new0(uintptr_t, smp_cpus);
+    ctx->tid_to_vcpu_hash = blocktime_init_tid_to_vcpu_hash();
+
     ctx->exit_notifier.notify = migration_exit_cb;
     qemu_add_exit_notifier(&ctx->exit_notifier);
 
@@ -827,18 +871,21 @@ int postcopy_request_shared_page(struct PostCopyFD *pcfd, RAMBlock *rb,
     return 0;
 }
 
-static int get_mem_fault_cpu_index(uint32_t pid)
+static int blocktime_get_vcpu(PostcopyBlocktimeContext *ctx, uint32_t tid)
 {
-    CPUState *cpu_iter;
+    int *found;
 
-    CPU_FOREACH(cpu_iter) {
-        if (cpu_iter->thread_id == pid) {
-            trace_get_mem_fault_cpu_index(cpu_iter->cpu_index, pid);
-            return cpu_iter->cpu_index;
-        }
+    found = g_hash_table_lookup(ctx->tid_to_vcpu_hash, GUINT_TO_POINTER(tid));
+    if (!found) {
+        /*
+         * NOTE: this is possible, because QEMU's non-vCPU threads can
+         * also access a missing page.  Or, when KVM async pf is enabled, a
+         * fault can even happen from a kworker..
+         */
+        return -1;
     }
-    trace_get_mem_fault_cpu_index(-1, pid);
-    return -1;
+
+    return *found;
 }
 
 static uint64_t get_current_ns(void)
@@ -865,8 +912,9 @@ void mark_postcopy_blocktime_begin(uintptr_t addr, uint32_t ptid,
     if (!dc || ptid == 0) {
         return;
     }
-    cpu = get_mem_fault_cpu_index(ptid);
+    cpu = blocktime_get_vcpu(dc, ptid);
     if (cpu < 0) {
+        dc->non_vcpu_faults++;
         return;
     }