qemu-kvm/SOURCES/kvm-kvm-reuse-per-vcpu-stats-fd-to-avoid-vcpu-interrupti.patch

From 6319eaee8c2206c4eca858a11ed7c9b7a2f3dff9 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Thu, 29 Jun 2023 15:13:57 -0300
Subject: [PATCH] kvm: reuse per-vcpu stats fd to avoid vcpu interruption

RH-Author: Marcelo Tosatti <None>
RH-MergeRequest: 290: kvm: reuse per-vcpu stats fd to avoid vcpu interruption
RH-Bugzilla: 2221219
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/1] cf6c3188e26c6eae99b48db1f75837e11d1e4489

Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2214884
Commit: 3b6f485275ae95a81eec589d2773b86ca9ddec4d

A regression has been detected in latency testing of KVM guests.
More specifically, it was observed that the cyclictest
numbers inside of an isolated vcpu (running on isolated pcpu) are:

Where a maximum of 50us is acceptable.

The implementation of KVM_GET_STATS_FD uses run_on_cpu to query
per vcpu statistics, which interrupts the vcpu (and is unnecessary).

To fix this, open the per vcpu stats fd on vcpu initialization,
and read from that fd from QEMU's main thread.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 accel/kvm/kvm-all.c   | 30 +++++++++++++++---------------
 include/hw/core/cpu.h |  1 +
 2 files changed, 16 insertions(+), 15 deletions(-)

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 39ed30ab59..c86a6798c6 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -450,6 +450,8 @@ int kvm_init_vcpu(CPUState *cpu, Error **errp)
                          "kvm_init_vcpu: kvm_arch_init_vcpu failed (%lu)",
                          kvm_arch_vcpu_id(cpu));
     }
+    cpu->kvm_vcpu_stats_fd = kvm_vcpu_ioctl(cpu, KVM_GET_STATS_FD, NULL);
+
 err:
     return ret;
 }
@@ -3950,7 +3952,7 @@ static StatsDescriptors *find_stats_descriptors(StatsTarget target, int stats_fd
 
     /* Read stats header */
     kvm_stats_header = &descriptors->kvm_stats_header;
-    ret = read(stats_fd, kvm_stats_header, sizeof(*kvm_stats_header));
+    ret = pread(stats_fd, kvm_stats_header, sizeof(*kvm_stats_header), 0);
     if (ret != sizeof(*kvm_stats_header)) {
         error_setg(errp, "KVM stats: failed to read stats header: "
                    "expected %zu actual %zu",
@@ -3981,7 +3983,8 @@ static StatsDescriptors *find_stats_descriptors(StatsTarget target, int stats_fd
 }
 
 static void query_stats(StatsResultList **result, StatsTarget target,
-                        strList *names, int stats_fd, Error **errp)
+                        strList *names, int stats_fd, CPUState *cpu,
+                        Error **errp)
 {
     struct kvm_stats_desc *kvm_stats_desc;
     struct kvm_stats_header *kvm_stats_header;
@@ -4039,7 +4042,7 @@ static void query_stats(StatsResultList **result, StatsTarget target,
         break;
     case STATS_TARGET_VCPU:
         add_stats_entry(result, STATS_PROVIDER_KVM,
-                        current_cpu->parent_obj.canonical_path,
+                        cpu->parent_obj.canonical_path,
                         stats_list);
         break;
     default:
@@ -4076,10 +4079,9 @@ static void query_stats_schema(StatsSchemaList **result, StatsTarget target,
     add_stats_schema(result, STATS_PROVIDER_KVM, target, stats_list);
 }
 
-static void query_stats_vcpu(CPUState *cpu, run_on_cpu_data data)
+static void query_stats_vcpu(CPUState *cpu, StatsArgs *kvm_stats_args)
 {
-    StatsArgs *kvm_stats_args = (StatsArgs *) data.host_ptr;
-    int stats_fd = kvm_vcpu_ioctl(cpu, KVM_GET_STATS_FD, NULL);
+    int stats_fd = cpu->kvm_vcpu_stats_fd;
     Error *local_err = NULL;
 
     if (stats_fd == -1) {
@@ -4088,14 +4090,13 @@ static void query_stats_vcpu(CPUState *cpu, run_on_cpu_data data)
         return;
     }
     query_stats(kvm_stats_args->result.stats, STATS_TARGET_VCPU,
-                kvm_stats_args->names, stats_fd, kvm_stats_args->errp);
-    close(stats_fd);
+                kvm_stats_args->names, stats_fd, cpu,
+                kvm_stats_args->errp);
 }
 
-static void query_stats_schema_vcpu(CPUState *cpu, run_on_cpu_data data)
+static void query_stats_schema_vcpu(CPUState *cpu, StatsArgs *kvm_stats_args)
 {
-    StatsArgs *kvm_stats_args = (StatsArgs *) data.host_ptr;
-    int stats_fd = kvm_vcpu_ioctl(cpu, KVM_GET_STATS_FD, NULL);
+    int stats_fd = cpu->kvm_vcpu_stats_fd;
     Error *local_err = NULL;
 
     if (stats_fd == -1) {
@@ -4105,7 +4106,6 @@ static void query_stats_schema_vcpu(CPUState *cpu, run_on_cpu_data data)
     }
     query_stats_schema(kvm_stats_args->result.schema, STATS_TARGET_VCPU, stats_fd,
                        kvm_stats_args->errp);
-    close(stats_fd);
 }
 
 static void query_stats_cb(StatsResultList **result, StatsTarget target,
@@ -4123,7 +4123,7 @@ static void query_stats_cb(StatsResultList **result, StatsTarget target,
             error_setg_errno(errp, errno, "KVM stats: ioctl failed");
             return;
         }
-        query_stats(result, target, names, stats_fd, errp);
+        query_stats(result, target, names, stats_fd, NULL, errp);
         close(stats_fd);
         break;
     }
@@ -4137,7 +4137,7 @@ static void query_stats_cb(StatsResultList **result, StatsTarget target,
             if (!apply_str_list_filter(cpu->parent_obj.canonical_path, targets)) {
                 continue;
             }
-            run_on_cpu(cpu, query_stats_vcpu, RUN_ON_CPU_HOST_PTR(&stats_args));
+            query_stats_vcpu(cpu, &stats_args);
         }
         break;
     }
@@ -4163,6 +4163,6 @@ void query_stats_schemas_cb(StatsSchemaList **result, Error **errp)
     if (first_cpu) {
         stats_args.result.schema = result;
         stats_args.errp = errp;
-        run_on_cpu(first_cpu, query_stats_schema_vcpu, RUN_ON_CPU_HOST_PTR(&stats_args));
+        query_stats_schema_vcpu(first_cpu, &stats_args);
     }
 }
diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index 2417597236..362f22ca06 100644
--- a/include/hw/core/cpu.h
+++ b/include/hw/core/cpu.h
@@ -397,6 +397,7 @@ struct CPUState {
     struct kvm_dirty_gfn *kvm_dirty_gfns;
     uint32_t kvm_fetch_index;
     uint64_t dirty_pages;
+    int kvm_vcpu_stats_fd;
 
     /* Use by accel-block: CPU is executing an ioctl() */
     QemuLockCnt in_ioctl_lock;
-- 
2.39.3