util: Introduce qemu_thread_set_affinity() and qemu_thread_get_affinity()

Usually, we let upper layers handle CPU pinning, because
pthread_setaffinity_np() (-> sched_setaffinity()) is blocked via
seccomp when starting QEMU with
    -sandbox enable=on,resourcecontrol=deny

However, we want to configure and observe the CPU affinity of threads
from QEMU directly in some cases when the sandbox option is either not
enabled or not active yet.

So let's add a way to configure CPU pinning via
qemu_thread_set_affinity() and obtain CPU affinity via
qemu_thread_get_affinity() and implement them under POSIX using
pthread_setaffinity_np() + pthread_getaffinity_np().

Implementation under Windows is possible using SetProcessAffinityMask()
+ GetProcessAffinityMask(), however, that is left as future work.

Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Message-Id: <20221014134720.168738-3-david@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>

4 files changed, 102 insertions, 0 deletions

diff --git a/include/qemu/thread.h b/include/qemu/thread.h
index af19f2b..79e507c 100644
--- a/include/qemu/thread.h
+++ b/include/qemu/thread.h
@@ -185,6 +185,10 @@ void qemu_event_destroy(QemuEvent *ev);
 void qemu_thread_create(QemuThread *thread, const char *name,
                         void *(*start_routine)(void *),
                         void *arg, int mode);
+int qemu_thread_set_affinity(QemuThread *thread, unsigned long *host_cpus,
+                             unsigned long nbits);
+int qemu_thread_get_affinity(QemuThread *thread, unsigned long **host_cpus,
+                             unsigned long *nbits);
 void *qemu_thread_join(QemuThread *thread);
 void qemu_thread_get_self(QemuThread *thread);
 bool qemu_thread_is_self(QemuThread *thread);
diff --git a/meson.build b/meson.build
index b686dfe..3e0aa49 100644
--- a/meson.build
+++ b/meson.build
@@ -2114,7 +2114,23 @@ config_host_data.set('CONFIG_PTHREAD_CONDATTR_SETCLOCK', cc.links(gnu_source_pre
     pthread_condattr_setclock(&attr, CLOCK_MONOTONIC);
     return 0;
   }''', dependencies: threads))
+config_host_data.set('CONFIG_PTHREAD_AFFINITY_NP', cc.links(gnu_source_prefix + '''
+  #include <pthread.h>
 
+  static void *f(void *p) { return NULL; }
+  int main(void)
+  {
+    int setsize = CPU_ALLOC_SIZE(64);
+    pthread_t thread;
+    cpu_set_t *cpuset;
+    pthread_create(&thread, 0, f, 0);
+    cpuset = CPU_ALLOC(64);
+    CPU_ZERO_S(setsize, cpuset);
+    pthread_setaffinity_np(thread, setsize, cpuset);
+    pthread_getaffinity_np(thread, setsize, cpuset);
+    CPU_FREE(cpuset);
+    return 0;
+  }''', dependencies: threads))
 config_host_data.set('CONFIG_SIGNALFD', cc.links(gnu_source_prefix + '''
   #include <sys/signalfd.h>
   #include <stddef.h>
diff --git a/util/qemu-thread-posix.c b/util/qemu-thread-posix.c
index ac1d56e..bae938c 100644
--- a/util/qemu-thread-posix.c
+++ b/util/qemu-thread-posix.c
@@ -16,6 +16,7 @@
 #include "qemu/notify.h"
 #include "qemu-thread-common.h"
 #include "qemu/tsan.h"
+#include "qemu/bitmap.h"
 
 static bool name_threads;
 
@@ -552,6 +553,75 @@ void qemu_thread_create(QemuThread *thread, const char *name,
     pthread_attr_destroy(&attr);
 }
 
+int qemu_thread_set_affinity(QemuThread *thread, unsigned long *host_cpus,
+                             unsigned long nbits)
+{
+#if defined(CONFIG_PTHREAD_AFFINITY_NP)
+    const size_t setsize = CPU_ALLOC_SIZE(nbits);
+    unsigned long value;
+    cpu_set_t *cpuset;
+    int err;
+
+    cpuset = CPU_ALLOC(nbits);
+    g_assert(cpuset);
+
+    CPU_ZERO_S(setsize, cpuset);
+    value = find_first_bit(host_cpus, nbits);
+    while (value < nbits) {
+        CPU_SET_S(value, setsize, cpuset);
+        value = find_next_bit(host_cpus, nbits, value + 1);
+    }
+
+    err = pthread_setaffinity_np(thread->thread, setsize, cpuset);
+    CPU_FREE(cpuset);
+    return err;
+#else
+    return -ENOSYS;
+#endif
+}
+
+int qemu_thread_get_affinity(QemuThread *thread, unsigned long **host_cpus,
+                             unsigned long *nbits)
+{
+#if defined(CONFIG_PTHREAD_AFFINITY_NP)
+    unsigned long tmpbits;
+    cpu_set_t *cpuset;
+    size_t setsize;
+    int i, err;
+
+    tmpbits = CPU_SETSIZE;
+    while (true) {
+        setsize = CPU_ALLOC_SIZE(tmpbits);
+        cpuset = CPU_ALLOC(tmpbits);
+        g_assert(cpuset);
+
+        err = pthread_getaffinity_np(thread->thread, setsize, cpuset);
+        if (err) {
+            CPU_FREE(cpuset);
+            if (err != -EINVAL) {
+                return err;
+            }
+            tmpbits *= 2;
+        } else {
+            break;
+        }
+    }
+
+    /* Convert the result into a proper bitmap. */
+    *nbits = tmpbits;
+    *host_cpus = bitmap_new(tmpbits);
+    for (i = 0; i < tmpbits; i++) {
+        if (CPU_ISSET(i, cpuset)) {
+            set_bit(i, *host_cpus);
+        }
+    }
+    CPU_FREE(cpuset);
+    return 0;
+#else
+    return -ENOSYS;
+#endif
+}
+
 void qemu_thread_get_self(QemuThread *thread)
 {
     thread->thread = pthread_self();
diff --git a/util/qemu-thread-win32.c b/util/qemu-thread-win32.c
index b9a467d..69db254 100644
--- a/util/qemu-thread-win32.c
+++ b/util/qemu-thread-win32.c
@@ -477,6 +477,18 @@ void qemu_thread_create(QemuThread *thread, const char *name,
     thread->data = data;
 }
 
+int qemu_thread_set_affinity(QemuThread *thread, unsigned long *host_cpus,
+                             unsigned long nbits)
+{
+    return -ENOSYS;
+}
+
+int qemu_thread_get_affinity(QemuThread *thread, unsigned long **host_cpus,
+                             unsigned long *nbits)
+{
+    return -ENOSYS;
+}
+
 void qemu_thread_get_self(QemuThread *thread)
 {
     thread->data = qemu_thread_data;