From 6556aadc18c560e493b29dd99cae2cbf86d214cb Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 14 Oct 2022 15:47:14 +0200 Subject: util: Cleanup and rename os_mem_prealloc() Let's * give the function a "qemu_*" style name * make sure the parameters in the implementation match the prototype * rename smp_cpus to max_threads, which makes the semantics of that parameter clearer ... and add a function documentation. Reviewed-by: Michal Privoznik Message-Id: <20221014134720.168738-2-david@redhat.com> Signed-off-by: David Hildenbrand --- include/qemu/osdep.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h index b1c161c035..e556e45143 100644 --- a/include/qemu/osdep.h +++ b/include/qemu/osdep.h @@ -568,8 +568,21 @@ unsigned long qemu_getauxval(unsigned long type); void qemu_set_tty_echo(int fd, bool echo); -void os_mem_prealloc(int fd, char *area, size_t sz, int smp_cpus, - Error **errp); +/** + * qemu_prealloc_mem: + * @fd: the fd mapped into the area, -1 for anonymous memory + * @area: start address of the are to preallocate + * @sz: the size of the area to preallocate + * @max_threads: maximum number of threads to use + * @errp: returns an error if this function fails + * + * Preallocate memory (populate/prefault page tables writable) for the virtual + * memory area starting at @area with the size of @sz. After a successful call, + * each page in the area was faulted in writable at least once, for example, + * after allocating file blocks for mapped files. + */ +void qemu_prealloc_mem(int fd, char *area, size_t sz, int max_threads, + Error **errp); /** * qemu_get_pid_name: -- cgit v1.2.3-55-g7522 From 7730f32c281f6005b5d35e0ba4b537a47d2dbf32 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 14 Oct 2022 15:47:15 +0200 Subject: 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 Message-Id: <20221014134720.168738-3-david@redhat.com> Signed-off-by: David Hildenbrand --- include/qemu/thread.h | 4 +++ meson.build | 16 +++++++++++ util/qemu-thread-posix.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++++ util/qemu-thread-win32.c | 12 +++++++++ 4 files changed, 102 insertions(+) (limited to 'include') diff --git a/include/qemu/thread.h b/include/qemu/thread.h index af19f2b3fc..79e507c7f0 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 b686dfef75..3e0aa4925d 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 + 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 #include diff --git a/util/qemu-thread-posix.c b/util/qemu-thread-posix.c index ac1d56e673..bae938c670 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 b9a467d7db..69db254ac7 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; -- cgit v1.2.3-55-g7522 From e2de2c497e5744bc2c009aadd0af7633f2947948 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 14 Oct 2022 15:47:16 +0200 Subject: util: Introduce ThreadContext user-creatable object Setting the CPU affinity of QEMU threads is a bit problematic, because QEMU doesn't always have permissions to set the CPU affinity itself, for example, with seccomp after initialized by QEMU: -sandbox enable=on,resourcecontrol=deny General information about CPU affinities can be found in the man page of taskset: CPU affinity is a scheduler property that "bonds" a process to a given set of CPUs on the system. The Linux scheduler will honor the given CPU affinity and the process will not run on any other CPUs. While upper layers are already aware of how to handle CPU affinities for long-lived threads like iothreads or vcpu threads, especially short-lived threads, as used for memory-backend preallocation, are more involved to handle. These threads are created on demand and upper layers are not even able to identify and configure them. Introduce the concept of a ThreadContext, that is essentially a thread used for creating new threads. All threads created via that context thread inherit the configured CPU affinity. Consequently, it's sufficient to create a ThreadContext and configure it once, and have all threads created via that ThreadContext inherit the same CPU affinity. The CPU affinity of a ThreadContext can be configured two ways: (1) Obtaining the thread id via the "thread-id" property and setting the CPU affinity manually (e.g., via taskset). (2) Setting the "cpu-affinity" property and letting QEMU try set the CPU affinity itself. This will fail if QEMU doesn't have permissions to do so anymore after seccomp was initialized. A simple QEMU example to set the CPU affinity to host CPU 0,1,6,7 would be: qemu-system-x86_64 -S \ -object thread-context,id=tc1,cpu-affinity=0-1,cpu-affinity=6-7 And we can query it via HMP/QMP: (qemu) qom-get tc1 cpu-affinity [ 0, 1, 6, 7 ] But note that due to dynamic library loading this example will not work before we actually make use of thread_context_create_thread() in QEMU code, because the type will otherwise not get registered. We'll wire this up next to make it work. In general, the interface behaves like pthread_setaffinity_np(): host CPU numbers that are currently not available are ignored; only host CPU numbers that are impossible with the current kernel will fail. If the list of host CPU numbers does not include a single CPU that is available, setting the CPU affinity will fail. A ThreadContext can be reused, simply by reconfiguring the CPU affinity. Note that the CPU affinity of previously created threads will not get adjusted. Reviewed-by: Michal Privoznik Acked-by: Markus Armbruster Message-Id: <20221014134720.168738-4-david@redhat.com> Signed-off-by: David Hildenbrand --- include/qemu/thread-context.h | 57 +++++++++ qapi/qom.json | 17 +++ util/meson.build | 1 + util/oslib-posix.c | 1 + util/thread-context.c | 278 ++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 354 insertions(+) create mode 100644 include/qemu/thread-context.h create mode 100644 util/thread-context.c (limited to 'include') diff --git a/include/qemu/thread-context.h b/include/qemu/thread-context.h new file mode 100644 index 0000000000..2ebd6b7fe1 --- /dev/null +++ b/include/qemu/thread-context.h @@ -0,0 +1,57 @@ +/* + * QEMU Thread Context + * + * Copyright Red Hat Inc., 2022 + * + * Authors: + * David Hildenbrand + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef SYSEMU_THREAD_CONTEXT_H +#define SYSEMU_THREAD_CONTEXT_H + +#include "qapi/qapi-types-machine.h" +#include "qemu/thread.h" +#include "qom/object.h" + +#define TYPE_THREAD_CONTEXT "thread-context" +OBJECT_DECLARE_TYPE(ThreadContext, ThreadContextClass, + THREAD_CONTEXT) + +struct ThreadContextClass { + ObjectClass parent_class; +}; + +struct ThreadContext { + /* private */ + Object parent; + + /* private */ + unsigned int thread_id; + QemuThread thread; + + /* Semaphore to wait for context thread action. */ + QemuSemaphore sem; + /* Semaphore to wait for action in context thread. */ + QemuSemaphore sem_thread; + /* Mutex to synchronize requests. */ + QemuMutex mutex; + + /* Commands for the thread to execute. */ + int thread_cmd; + void *thread_cmd_data; + + /* CPU affinity bitmap used for initialization. */ + unsigned long *init_cpu_bitmap; + int init_cpu_nbits; +}; + +void thread_context_create_thread(ThreadContext *tc, QemuThread *thread, + const char *name, + void *(*start_routine)(void *), void *arg, + int mode); + +#endif /* SYSEMU_THREAD_CONTEXT_H */ diff --git a/qapi/qom.json b/qapi/qom.json index 80dd419b39..8013ba4b82 100644 --- a/qapi/qom.json +++ b/qapi/qom.json @@ -830,6 +830,21 @@ 'reduced-phys-bits': 'uint32', '*kernel-hashes': 'bool' } } +## +# @ThreadContextProperties: +# +# Properties for thread context objects. +# +# @cpu-affinity: the list of host CPU numbers used as CPU affinity for all +# threads created in the thread context (default: QEMU main +# thread CPU affinity) +# +# Since: 7.2 +## +{ 'struct': 'ThreadContextProperties', + 'data': { '*cpu-affinity': ['uint16'] } } + + ## # @ObjectType: # @@ -882,6 +897,7 @@ { 'name': 'secret_keyring', 'if': 'CONFIG_SECRET_KEYRING' }, 'sev-guest', + 'thread-context', 's390-pv-guest', 'throttle-group', 'tls-creds-anon', @@ -948,6 +964,7 @@ 'secret_keyring': { 'type': 'SecretKeyringProperties', 'if': 'CONFIG_SECRET_KEYRING' }, 'sev-guest': 'SevGuestProperties', + 'thread-context': 'ThreadContextProperties', 'throttle-group': 'ThrottleGroupProperties', 'tls-creds-anon': 'TlsCredsAnonProperties', 'tls-creds-psk': 'TlsCredsPskProperties', diff --git a/util/meson.build b/util/meson.build index 5e282130df..e97cd2d779 100644 --- a/util/meson.build +++ b/util/meson.build @@ -1,4 +1,5 @@ util_ss.add(files('osdep.c', 'cutils.c', 'unicode.c', 'qemu-timer-common.c')) +util_ss.add(files('thread-context.c')) if not config_host_data.get('CONFIG_ATOMIC64') util_ss.add(files('atomic64.c')) endif diff --git a/util/oslib-posix.c b/util/oslib-posix.c index 905cbc27cc..28305cdea3 100644 --- a/util/oslib-posix.c +++ b/util/oslib-posix.c @@ -42,6 +42,7 @@ #include "qemu/cutils.h" #include "qemu/compiler.h" #include "qemu/units.h" +#include "qemu/thread-context.h" #ifdef CONFIG_LINUX #include diff --git a/util/thread-context.c b/util/thread-context.c new file mode 100644 index 0000000000..c921905396 --- /dev/null +++ b/util/thread-context.c @@ -0,0 +1,278 @@ +/* + * QEMU Thread Context + * + * Copyright Red Hat Inc., 2022 + * + * Authors: + * David Hildenbrand + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/thread-context.h" +#include "qapi/error.h" +#include "qapi/qapi-builtin-visit.h" +#include "qapi/visitor.h" +#include "qemu/config-file.h" +#include "qapi/qapi-builtin-visit.h" +#include "qom/object_interfaces.h" +#include "qemu/module.h" +#include "qemu/bitmap.h" + +enum { + TC_CMD_NONE = 0, + TC_CMD_STOP, + TC_CMD_NEW, +}; + +typedef struct ThreadContextCmdNew { + QemuThread *thread; + const char *name; + void *(*start_routine)(void *); + void *arg; + int mode; +} ThreadContextCmdNew; + +static void *thread_context_run(void *opaque) +{ + ThreadContext *tc = opaque; + + tc->thread_id = qemu_get_thread_id(); + qemu_sem_post(&tc->sem); + + while (true) { + /* + * Threads inherit the CPU affinity of the creating thread. For this + * reason, we create new (especially short-lived) threads from our + * persistent context thread. + * + * Especially when QEMU is not allowed to set the affinity itself, + * management tools can simply set the affinity of the context thread + * after creating the context, to have new threads created via + * the context inherit the CPU affinity automatically. + */ + switch (tc->thread_cmd) { + case TC_CMD_NONE: + break; + case TC_CMD_STOP: + tc->thread_cmd = TC_CMD_NONE; + qemu_sem_post(&tc->sem); + return NULL; + case TC_CMD_NEW: { + ThreadContextCmdNew *cmd_new = tc->thread_cmd_data; + + qemu_thread_create(cmd_new->thread, cmd_new->name, + cmd_new->start_routine, cmd_new->arg, + cmd_new->mode); + tc->thread_cmd = TC_CMD_NONE; + tc->thread_cmd_data = NULL; + qemu_sem_post(&tc->sem); + break; + } + default: + g_assert_not_reached(); + } + qemu_sem_wait(&tc->sem_thread); + } +} + +static void thread_context_set_cpu_affinity(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + ThreadContext *tc = THREAD_CONTEXT(obj); + uint16List *l, *host_cpus = NULL; + unsigned long *bitmap = NULL; + int nbits = 0, ret; + Error *err = NULL; + + visit_type_uint16List(v, name, &host_cpus, &err); + if (err) { + error_propagate(errp, err); + return; + } + + if (!host_cpus) { + error_setg(errp, "CPU list is empty"); + goto out; + } + + for (l = host_cpus; l; l = l->next) { + nbits = MAX(nbits, l->value + 1); + } + bitmap = bitmap_new(nbits); + for (l = host_cpus; l; l = l->next) { + set_bit(l->value, bitmap); + } + + if (tc->thread_id != -1) { + /* + * Note: we won't be adjusting the affinity of any thread that is still + * around, but only the affinity of the context thread. + */ + ret = qemu_thread_set_affinity(&tc->thread, bitmap, nbits); + if (ret) { + error_setg(errp, "Setting CPU affinity failed: %s", strerror(ret)); + } + } else { + tc->init_cpu_bitmap = bitmap; + bitmap = NULL; + tc->init_cpu_nbits = nbits; + } +out: + g_free(bitmap); + qapi_free_uint16List(host_cpus); +} + +static void thread_context_get_cpu_affinity(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + unsigned long *bitmap, nbits, value; + ThreadContext *tc = THREAD_CONTEXT(obj); + uint16List *host_cpus = NULL; + uint16List **tail = &host_cpus; + int ret; + + if (tc->thread_id == -1) { + error_setg(errp, "Object not initialized yet"); + return; + } + + ret = qemu_thread_get_affinity(&tc->thread, &bitmap, &nbits); + if (ret) { + error_setg(errp, "Getting CPU affinity failed: %s", strerror(ret)); + return; + } + + value = find_first_bit(bitmap, nbits); + while (value < nbits) { + QAPI_LIST_APPEND(tail, value); + + value = find_next_bit(bitmap, nbits, value + 1); + } + g_free(bitmap); + + visit_type_uint16List(v, name, &host_cpus, errp); + qapi_free_uint16List(host_cpus); +} + +static void thread_context_get_thread_id(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + ThreadContext *tc = THREAD_CONTEXT(obj); + uint64_t value = tc->thread_id; + + visit_type_uint64(v, name, &value, errp); +} + +static void thread_context_instance_complete(UserCreatable *uc, Error **errp) +{ + ThreadContext *tc = THREAD_CONTEXT(uc); + char *thread_name; + int ret; + + thread_name = g_strdup_printf("TC %s", + object_get_canonical_path_component(OBJECT(uc))); + qemu_thread_create(&tc->thread, thread_name, thread_context_run, tc, + QEMU_THREAD_JOINABLE); + g_free(thread_name); + + /* Wait until initialization of the thread is done. */ + while (tc->thread_id == -1) { + qemu_sem_wait(&tc->sem); + } + + if (tc->init_cpu_bitmap) { + ret = qemu_thread_set_affinity(&tc->thread, tc->init_cpu_bitmap, + tc->init_cpu_nbits); + if (ret) { + error_setg(errp, "Setting CPU affinity failed: %s", strerror(ret)); + } + g_free(tc->init_cpu_bitmap); + tc->init_cpu_bitmap = NULL; + } +} + +static void thread_context_class_init(ObjectClass *oc, void *data) +{ + UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc); + + ucc->complete = thread_context_instance_complete; + object_class_property_add(oc, "thread-id", "int", + thread_context_get_thread_id, NULL, NULL, + NULL); + object_class_property_add(oc, "cpu-affinity", "int", + thread_context_get_cpu_affinity, + thread_context_set_cpu_affinity, NULL, NULL); +} + +static void thread_context_instance_init(Object *obj) +{ + ThreadContext *tc = THREAD_CONTEXT(obj); + + tc->thread_id = -1; + qemu_sem_init(&tc->sem, 0); + qemu_sem_init(&tc->sem_thread, 0); + qemu_mutex_init(&tc->mutex); +} + +static void thread_context_instance_finalize(Object *obj) +{ + ThreadContext *tc = THREAD_CONTEXT(obj); + + if (tc->thread_id != -1) { + tc->thread_cmd = TC_CMD_STOP; + qemu_sem_post(&tc->sem_thread); + qemu_thread_join(&tc->thread); + } + qemu_sem_destroy(&tc->sem); + qemu_sem_destroy(&tc->sem_thread); + qemu_mutex_destroy(&tc->mutex); +} + +static const TypeInfo thread_context_info = { + .name = TYPE_THREAD_CONTEXT, + .parent = TYPE_OBJECT, + .class_init = thread_context_class_init, + .instance_size = sizeof(ThreadContext), + .instance_init = thread_context_instance_init, + .instance_finalize = thread_context_instance_finalize, + .interfaces = (InterfaceInfo[]) { + { TYPE_USER_CREATABLE }, + { } + } +}; + +static void thread_context_register_types(void) +{ + type_register_static(&thread_context_info); +} +type_init(thread_context_register_types) + +void thread_context_create_thread(ThreadContext *tc, QemuThread *thread, + const char *name, + void *(*start_routine)(void *), void *arg, + int mode) +{ + ThreadContextCmdNew data = { + .thread = thread, + .name = name, + .start_routine = start_routine, + .arg = arg, + .mode = mode, + }; + + qemu_mutex_lock(&tc->mutex); + tc->thread_cmd = TC_CMD_NEW; + tc->thread_cmd_data = &data; + qemu_sem_post(&tc->sem_thread); + + while (tc->thread_cmd != TC_CMD_NONE) { + qemu_sem_wait(&tc->sem); + } + qemu_mutex_unlock(&tc->mutex); +} -- cgit v1.2.3-55-g7522 From e04a34e55cf1911099e2d8a680f9bee4f6d90e4a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 14 Oct 2022 15:47:18 +0200 Subject: util: Make qemu_prealloc_mem() optionally consume a ThreadContext ... and implement it under POSIX. When a ThreadContext is provided, create new threads via the context such that these new threads obtain a properly configured CPU affinity. Reviewed-by: Michal Privoznik Message-Id: <20221014134720.168738-6-david@redhat.com> Signed-off-by: David Hildenbrand --- backends/hostmem.c | 5 +++-- hw/virtio/virtio-mem.c | 2 +- include/qemu/osdep.h | 4 +++- util/oslib-posix.c | 20 ++++++++++++++------ util/oslib-win32.c | 2 +- 5 files changed, 22 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/backends/hostmem.c b/backends/hostmem.c index 491cb10b97..76f0394490 100644 --- a/backends/hostmem.c +++ b/backends/hostmem.c @@ -232,7 +232,8 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value, void *ptr = memory_region_get_ram_ptr(&backend->mr); uint64_t sz = memory_region_size(&backend->mr); - qemu_prealloc_mem(fd, ptr, sz, backend->prealloc_threads, &local_err); + qemu_prealloc_mem(fd, ptr, sz, backend->prealloc_threads, NULL, + &local_err); if (local_err) { error_propagate(errp, local_err); return; @@ -384,7 +385,7 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp) */ if (backend->prealloc) { qemu_prealloc_mem(memory_region_get_fd(&backend->mr), ptr, sz, - backend->prealloc_threads, &local_err); + backend->prealloc_threads, NULL, &local_err); if (local_err) { goto out; } diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c index 0e9ef4ff19..ed170def48 100644 --- a/hw/virtio/virtio-mem.c +++ b/hw/virtio/virtio-mem.c @@ -467,7 +467,7 @@ static int virtio_mem_set_block_state(VirtIOMEM *vmem, uint64_t start_gpa, int fd = memory_region_get_fd(&vmem->memdev->mr); Error *local_err = NULL; - qemu_prealloc_mem(fd, area, size, 1, &local_err); + qemu_prealloc_mem(fd, area, size, 1, NULL, &local_err); if (local_err) { static bool warned; diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h index e556e45143..625298c8bc 100644 --- a/include/qemu/osdep.h +++ b/include/qemu/osdep.h @@ -568,6 +568,8 @@ unsigned long qemu_getauxval(unsigned long type); void qemu_set_tty_echo(int fd, bool echo); +typedef struct ThreadContext ThreadContext; + /** * qemu_prealloc_mem: * @fd: the fd mapped into the area, -1 for anonymous memory @@ -582,7 +584,7 @@ void qemu_set_tty_echo(int fd, bool echo); * after allocating file blocks for mapped files. */ void qemu_prealloc_mem(int fd, char *area, size_t sz, int max_threads, - Error **errp); + ThreadContext *tc, Error **errp); /** * qemu_get_pid_name: diff --git a/util/oslib-posix.c b/util/oslib-posix.c index 28305cdea3..59a891b6a8 100644 --- a/util/oslib-posix.c +++ b/util/oslib-posix.c @@ -419,7 +419,8 @@ static inline int get_memset_num_threads(size_t hpagesize, size_t numpages, } static int touch_all_pages(char *area, size_t hpagesize, size_t numpages, - int max_threads, bool use_madv_populate_write) + int max_threads, ThreadContext *tc, + bool use_madv_populate_write) { static gsize initialized = 0; MemsetContext context = { @@ -458,9 +459,16 @@ static int touch_all_pages(char *area, size_t hpagesize, size_t numpages, context.threads[i].numpages = numpages_per_thread + (i < leftover); context.threads[i].hpagesize = hpagesize; context.threads[i].context = &context; - qemu_thread_create(&context.threads[i].pgthread, "touch_pages", - touch_fn, &context.threads[i], - QEMU_THREAD_JOINABLE); + if (tc) { + thread_context_create_thread(tc, &context.threads[i].pgthread, + "touch_pages", + touch_fn, &context.threads[i], + QEMU_THREAD_JOINABLE); + } else { + qemu_thread_create(&context.threads[i].pgthread, "touch_pages", + touch_fn, &context.threads[i], + QEMU_THREAD_JOINABLE); + } addr += context.threads[i].numpages * hpagesize; } @@ -496,7 +504,7 @@ static bool madv_populate_write_possible(char *area, size_t pagesize) } void qemu_prealloc_mem(int fd, char *area, size_t sz, int max_threads, - Error **errp) + ThreadContext *tc, Error **errp) { static gsize initialized; int ret; @@ -537,7 +545,7 @@ void qemu_prealloc_mem(int fd, char *area, size_t sz, int max_threads, } /* touch pages simultaneously */ - ret = touch_all_pages(area, hpagesize, numpages, max_threads, + ret = touch_all_pages(area, hpagesize, numpages, max_threads, tc, use_madv_populate_write); if (ret) { error_setg_errno(errp, -ret, diff --git a/util/oslib-win32.c b/util/oslib-win32.c index e1cb725ecc..a67cb3822e 100644 --- a/util/oslib-win32.c +++ b/util/oslib-win32.c @@ -269,7 +269,7 @@ int getpagesize(void) } void qemu_prealloc_mem(int fd, char *area, size_t sz, int max_threads, - Error **errp) + ThreadContext *tc, Error **errp) { int i; size_t pagesize = qemu_real_host_page_size(); -- cgit v1.2.3-55-g7522 From e6816458624813de4a31f89096a620b410e1c2b8 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 14 Oct 2022 15:47:19 +0200 Subject: hostmem: Allow for specifying a ThreadContext for preallocation Let's allow for specifying a thread context via the "prealloc-context" property. When set, preallcoation threads will be crated via the thread context -- inheriting the same CPU affinity as the thread context. Pinning preallcoation threads to CPUs can heavily increase performance in NUMA setups, because, preallocation from a CPU close to the target NUMA node(s) is faster then preallocation from a CPU further remote, simply because of memory bandwidth for initializing memory with zeroes. This is especially relevant for very large VMs backed by huge/gigantic pages, whereby preallocation is mandatory. Reviewed-by: Michal Privoznik Message-Id: <20221014134720.168738-7-david@redhat.com> Signed-off-by: David Hildenbrand --- backends/hostmem.c | 12 +++++++++--- include/sysemu/hostmem.h | 2 ++ qapi/qom.json | 4 ++++ 3 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/backends/hostmem.c b/backends/hostmem.c index 76f0394490..8640294c10 100644 --- a/backends/hostmem.c +++ b/backends/hostmem.c @@ -232,8 +232,8 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value, void *ptr = memory_region_get_ram_ptr(&backend->mr); uint64_t sz = memory_region_size(&backend->mr); - qemu_prealloc_mem(fd, ptr, sz, backend->prealloc_threads, NULL, - &local_err); + qemu_prealloc_mem(fd, ptr, sz, backend->prealloc_threads, + backend->prealloc_context, &local_err); if (local_err) { error_propagate(errp, local_err); return; @@ -385,7 +385,8 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp) */ if (backend->prealloc) { qemu_prealloc_mem(memory_region_get_fd(&backend->mr), ptr, sz, - backend->prealloc_threads, NULL, &local_err); + backend->prealloc_threads, + backend->prealloc_context, &local_err); if (local_err) { goto out; } @@ -493,6 +494,11 @@ host_memory_backend_class_init(ObjectClass *oc, void *data) NULL, NULL); object_class_property_set_description(oc, "prealloc-threads", "Number of CPU threads to use for prealloc"); + object_class_property_add_link(oc, "prealloc-context", + TYPE_THREAD_CONTEXT, offsetof(HostMemoryBackend, prealloc_context), + object_property_allow_set_link, OBJ_PROP_LINK_STRONG); + object_class_property_set_description(oc, "prealloc-context", + "Context to use for creating CPU threads for preallocation"); object_class_property_add(oc, "size", "int", host_memory_backend_get_size, host_memory_backend_set_size, diff --git a/include/sysemu/hostmem.h b/include/sysemu/hostmem.h index 9ff5c16963..39326f1d4f 100644 --- a/include/sysemu/hostmem.h +++ b/include/sysemu/hostmem.h @@ -18,6 +18,7 @@ #include "qom/object.h" #include "exec/memory.h" #include "qemu/bitmap.h" +#include "qemu/thread-context.h" #define TYPE_MEMORY_BACKEND "memory-backend" OBJECT_DECLARE_TYPE(HostMemoryBackend, HostMemoryBackendClass, @@ -66,6 +67,7 @@ struct HostMemoryBackend { bool merge, dump, use_canonical_path; bool prealloc, is_mapped, share, reserve; uint32_t prealloc_threads; + ThreadContext *prealloc_context; DECLARE_BITMAP(host_nodes, MAX_NODES + 1); HostMemPolicy policy; diff --git a/qapi/qom.json b/qapi/qom.json index 20b5735d78..87fcad2423 100644 --- a/qapi/qom.json +++ b/qapi/qom.json @@ -578,6 +578,9 @@ # # @prealloc-threads: number of CPU threads to use for prealloc (default: 1) # +# @prealloc-context: thread context to use for creation of preallocation threads +# (default: none) (since 7.2) +# # @share: if false, the memory is private to QEMU; if true, it is shared # (default: false) # @@ -608,6 +611,7 @@ '*policy': 'HostMemPolicy', '*prealloc': 'bool', '*prealloc-threads': 'uint32', + '*prealloc-context': 'str', '*share': 'bool', '*reserve': 'bool', 'size': 'size', -- cgit v1.2.3-55-g7522