@@ -47,6 +47,7 @@ LIBKVM += lib/perf_test_util.c
LIBKVM += lib/rbtree.c
LIBKVM += lib/sparsebit.c
LIBKVM += lib/test_util.c
+LIBKVM += lib/userfaultfd_util.c
LIBKVM_x86_64 += lib/x86_64/apic.c
LIBKVM_x86_64 += lib/x86_64/handlers.S
@@ -22,23 +22,13 @@
#include "test_util.h"
#include "perf_test_util.h"
#include "guest_modes.h"
+#include "userfaultfd_util.h"
#ifdef __NR_userfaultfd
-#ifdef PRINT_PER_PAGE_UPDATES
-#define PER_PAGE_DEBUG(...) printf(__VA_ARGS__)
-#else
-#define PER_PAGE_DEBUG(...) _no_printf(__VA_ARGS__)
-#endif
-
-#ifdef PRINT_PER_VCPU_UPDATES
-#define PER_VCPU_DEBUG(...) printf(__VA_ARGS__)
-#else
-#define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
-#endif
-
static int nr_vcpus = 1;
static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
+
static size_t demand_paging_size;
static char *guest_data_prototype;
@@ -67,9 +57,11 @@ static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
ts_diff.tv_sec, ts_diff.tv_nsec);
}
-static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr)
+static int handle_uffd_page_request(int uffd_mode, int uffd,
+ struct uffd_msg *msg)
{
pid_t tid = syscall(__NR_gettid);
+ uint64_t addr = msg->arg.pagefault.address;
struct timespec start;
struct timespec ts_diff;
int r;
@@ -116,174 +108,32 @@ static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr)
return 0;
}
-bool quit_uffd_thread;
-
-struct uffd_handler_args {
+struct test_params {
int uffd_mode;
- int uffd;
- int pipefd;
- useconds_t delay;
+ useconds_t uffd_delay;
+ enum vm_mem_backing_src_type src_type;
+ bool partition_vcpu_memory_access;
};
-static void *uffd_handler_thread_fn(void *arg)
-{
- struct uffd_handler_args *uffd_args = (struct uffd_handler_args *)arg;
- int uffd = uffd_args->uffd;
- int pipefd = uffd_args->pipefd;
- useconds_t delay = uffd_args->delay;
- int64_t pages = 0;
- struct timespec start;
- struct timespec ts_diff;
-
- clock_gettime(CLOCK_MONOTONIC, &start);
- while (!quit_uffd_thread) {
- struct uffd_msg msg;
- struct pollfd pollfd[2];
- char tmp_chr;
- int r;
- uint64_t addr;
-
- pollfd[0].fd = uffd;
- pollfd[0].events = POLLIN;
- pollfd[1].fd = pipefd;
- pollfd[1].events = POLLIN;
-
- r = poll(pollfd, 2, -1);
- switch (r) {
- case -1:
- pr_info("poll err");
- continue;
- case 0:
- continue;
- case 1:
- break;
- default:
- pr_info("Polling uffd returned %d", r);
- return NULL;
- }
-
- if (pollfd[0].revents & POLLERR) {
- pr_info("uffd revents has POLLERR");
- return NULL;
- }
-
- if (pollfd[1].revents & POLLIN) {
- r = read(pollfd[1].fd, &tmp_chr, 1);
- TEST_ASSERT(r == 1,
- "Error reading pipefd in UFFD thread\n");
- return NULL;
- }
-
- if (!(pollfd[0].revents & POLLIN))
- continue;
-
- r = read(uffd, &msg, sizeof(msg));
- if (r == -1) {
- if (errno == EAGAIN)
- continue;
- pr_info("Read of uffd got errno %d\n", errno);
- return NULL;
- }
-
- if (r != sizeof(msg)) {
- pr_info("Read on uffd returned unexpected size: %d bytes", r);
- return NULL;
- }
-
- if (!(msg.event & UFFD_EVENT_PAGEFAULT))
- continue;
-
- if (delay)
- usleep(delay);
- addr = msg.arg.pagefault.address;
- r = handle_uffd_page_request(uffd_args->uffd_mode, uffd, addr);
- if (r < 0)
- return NULL;
- pages++;
- }
-
- ts_diff = timespec_elapsed(start);
- PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
- pages, ts_diff.tv_sec, ts_diff.tv_nsec,
- pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
-
- return NULL;
-}
-
-static void setup_demand_paging(struct kvm_vm *vm,
- pthread_t *uffd_handler_thread, int pipefd,
- int uffd_mode, useconds_t uffd_delay,
- struct uffd_handler_args *uffd_args,
- void *hva, void *alias, uint64_t len)
+static void prefault_mem(void *alias, uint64_t len)
{
- bool is_minor = (uffd_mode == UFFDIO_REGISTER_MODE_MINOR);
- int uffd;
- struct uffdio_api uffdio_api;
- struct uffdio_register uffdio_register;
- uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY;
- int ret;
+ size_t p;
- PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n",
- is_minor ? "MINOR" : "MISSING",
- is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY");
-
- /* In order to get minor faults, prefault via the alias. */
- if (is_minor) {
- size_t p;
-
- expected_ioctls = ((uint64_t) 1) << _UFFDIO_CONTINUE;
-
- TEST_ASSERT(alias != NULL, "Alias required for minor faults");
- for (p = 0; p < (len / demand_paging_size); ++p) {
- memcpy(alias + (p * demand_paging_size),
- guest_data_prototype, demand_paging_size);
- }
+ TEST_ASSERT(alias != NULL, "Alias required for minor faults");
+ for (p = 0; p < (len / demand_paging_size); ++p) {
+ memcpy(alias + (p * demand_paging_size),
+ guest_data_prototype, demand_paging_size);
}
-
- uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
- TEST_ASSERT(uffd >= 0, __KVM_SYSCALL_ERROR("userfaultfd()", uffd));
-
- uffdio_api.api = UFFD_API;
- uffdio_api.features = 0;
- ret = ioctl(uffd, UFFDIO_API, &uffdio_api);
- TEST_ASSERT(ret != -1, __KVM_SYSCALL_ERROR("UFFDIO_API", ret));
-
- uffdio_register.range.start = (uint64_t)hva;
- uffdio_register.range.len = len;
- uffdio_register.mode = uffd_mode;
- ret = ioctl(uffd, UFFDIO_REGISTER, &uffdio_register);
- TEST_ASSERT(ret != -1, __KVM_SYSCALL_ERROR("UFFDIO_REGISTER", ret));
- TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) ==
- expected_ioctls, "missing userfaultfd ioctls");
-
- uffd_args->uffd_mode = uffd_mode;
- uffd_args->uffd = uffd;
- uffd_args->pipefd = pipefd;
- uffd_args->delay = uffd_delay;
- pthread_create(uffd_handler_thread, NULL, uffd_handler_thread_fn,
- uffd_args);
-
- PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
- hva, hva + len);
}
-struct test_params {
- int uffd_mode;
- useconds_t uffd_delay;
- enum vm_mem_backing_src_type src_type;
- bool partition_vcpu_memory_access;
-};
-
static void run_test(enum vm_guest_mode mode, void *arg)
{
struct test_params *p = arg;
- pthread_t *uffd_handler_threads = NULL;
- struct uffd_handler_args *uffd_args = NULL;
+ struct uffd_desc **uffd_descs = NULL;
struct timespec start;
struct timespec ts_diff;
- int *pipefds = NULL;
struct kvm_vm *vm;
- int r, i;
+ int i;
vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
p->src_type, p->partition_vcpu_memory_access);
@@ -296,15 +146,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
memset(guest_data_prototype, 0xAB, demand_paging_size);
if (p->uffd_mode) {
- uffd_handler_threads =
- malloc(nr_vcpus * sizeof(*uffd_handler_threads));
- TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
-
- uffd_args = malloc(nr_vcpus * sizeof(*uffd_args));
- TEST_ASSERT(uffd_args, "Memory allocation failed");
-
- pipefds = malloc(sizeof(int) * nr_vcpus * 2);
- TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
+ uffd_descs = malloc(nr_vcpus * sizeof(struct uffd_desc *));
+ TEST_ASSERT(uffd_descs, "Memory allocation failed");
for (i = 0; i < nr_vcpus; i++) {
struct perf_test_vcpu_args *vcpu_args;
@@ -317,19 +160,17 @@ static void run_test(enum vm_guest_mode mode, void *arg)
vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa);
vcpu_alias = addr_gpa2alias(vm, vcpu_args->gpa);
+ prefault_mem(vcpu_alias,
+ vcpu_args->pages * perf_test_args.guest_page_size);
+
/*
* Set up user fault fd to handle demand paging
* requests.
*/
- r = pipe2(&pipefds[i * 2],
- O_CLOEXEC | O_NONBLOCK);
- TEST_ASSERT(!r, "Failed to set up pipefd");
-
- setup_demand_paging(vm, &uffd_handler_threads[i],
- pipefds[i * 2], p->uffd_mode,
- p->uffd_delay, &uffd_args[i],
- vcpu_hva, vcpu_alias,
- vcpu_args->pages * perf_test_args.guest_page_size);
+ uffd_descs[i] = uffd_setup_demand_paging(
+ p->uffd_mode, p->uffd_delay, vcpu_hva,
+ vcpu_args->pages * perf_test_args.guest_page_size,
+ &handle_uffd_page_request);
}
}
@@ -344,15 +185,9 @@ static void run_test(enum vm_guest_mode mode, void *arg)
pr_info("All vCPU threads joined\n");
if (p->uffd_mode) {
- char c;
-
/* Tell the user fault fd handler threads to quit */
- for (i = 0; i < nr_vcpus; i++) {
- r = write(pipefds[i * 2 + 1], &c, 1);
- TEST_ASSERT(r == 1, "Unable to write to pipefd");
-
- pthread_join(uffd_handler_threads[i], NULL);
- }
+ for (i = 0; i < nr_vcpus; i++)
+ uffd_stop_demand_paging(uffd_descs[i]);
}
pr_info("Total guest execution time: %ld.%.9lds\n",
@@ -364,11 +199,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
perf_test_destroy_vm(vm);
free(guest_data_prototype);
- if (p->uffd_mode) {
- free(uffd_handler_threads);
- free(uffd_args);
- free(pipefds);
- }
+ if (p->uffd_mode)
+ free(uffd_descs);
}
static void help(char *name)
new file mode 100644
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM userfaultfd util
+ * Adapted from demand_paging_test.c
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ * Copyright (C) 2019-2022 Google LLC
+ */
+
+#define _GNU_SOURCE /* for pipe2 */
+
+#include <inttypes.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/userfaultfd.h>
+
+#include "test_util.h"
+
+typedef int (*uffd_handler_t)(int uffd_mode, int uffd, struct uffd_msg *msg);
+
+struct uffd_desc {
+ int uffd_mode;
+ int uffd;
+ int pipefds[2];
+ useconds_t delay;
+ uffd_handler_t handler;
+ pthread_t thread;
+};
+
+struct uffd_desc *uffd_setup_demand_paging(int uffd_mode,
+ useconds_t uffd_delay, void *hva, uint64_t len,
+ uffd_handler_t handler);
+
+void uffd_stop_demand_paging(struct uffd_desc *uffd);
+
+#ifdef PRINT_PER_PAGE_UPDATES
+#define PER_PAGE_DEBUG(...) printf(__VA_ARGS__)
+#else
+#define PER_PAGE_DEBUG(...) _no_printf(__VA_ARGS__)
+#endif
+
+#ifdef PRINT_PER_VCPU_UPDATES
+#define PER_VCPU_DEBUG(...) printf(__VA_ARGS__)
+#else
+#define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
+#endif
new file mode 100644
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM userfaultfd util
+ * Adapted from demand_paging_test.c
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ * Copyright (C) 2019, Google, Inc.
+ * Copyright (C) 2022, Google, Inc.
+ */
+
+#define _GNU_SOURCE /* for pipe2 */
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <poll.h>
+#include <pthread.h>
+#include <linux/userfaultfd.h>
+#include <sys/syscall.h>
+
+#include "kvm_util.h"
+#include "test_util.h"
+#include "perf_test_util.h"
+#include "userfaultfd_util.h"
+
+#ifdef __NR_userfaultfd
+
+static void *uffd_handler_thread_fn(void *arg)
+{
+ struct uffd_desc *uffd_desc = (struct uffd_desc *)arg;
+ int uffd = uffd_desc->uffd;
+ int pipefd = uffd_desc->pipefds[0];
+ useconds_t delay = uffd_desc->delay;
+ int64_t pages = 0;
+ struct timespec start;
+ struct timespec ts_diff;
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ while (1) {
+ struct uffd_msg msg;
+ struct pollfd pollfd[2];
+ char tmp_chr;
+ int r;
+
+ pollfd[0].fd = uffd;
+ pollfd[0].events = POLLIN;
+ pollfd[1].fd = pipefd;
+ pollfd[1].events = POLLIN;
+
+ r = poll(pollfd, 2, -1);
+ switch (r) {
+ case -1:
+ pr_info("poll err");
+ continue;
+ case 0:
+ continue;
+ case 1:
+ break;
+ default:
+ pr_info("Polling uffd returned %d", r);
+ return NULL;
+ }
+
+ if (pollfd[0].revents & POLLERR) {
+ pr_info("uffd revents has POLLERR");
+ return NULL;
+ }
+
+ if (pollfd[1].revents & POLLIN) {
+ r = read(pollfd[1].fd, &tmp_chr, 1);
+ TEST_ASSERT(r == 1,
+ "Error reading pipefd in UFFD thread\n");
+ return NULL;
+ }
+
+ if (!(pollfd[0].revents & POLLIN))
+ continue;
+
+ r = read(uffd, &msg, sizeof(msg));
+ if (r == -1) {
+ if (errno == EAGAIN)
+ continue;
+ pr_info("Read of uffd got errno %d\n", errno);
+ return NULL;
+ }
+
+ if (r != sizeof(msg)) {
+ pr_info("Read on uffd returned unexpected size: %d bytes", r);
+ return NULL;
+ }
+
+ if (!(msg.event & UFFD_EVENT_PAGEFAULT))
+ continue;
+
+ if (delay)
+ usleep(delay);
+ r = uffd_desc->handler(uffd_desc->uffd_mode, uffd, &msg);
+ if (r < 0)
+ return NULL;
+ pages++;
+ }
+
+ ts_diff = timespec_elapsed(start);
+ PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
+ pages, ts_diff.tv_sec, ts_diff.tv_nsec,
+ pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+
+ return NULL;
+}
+
+struct uffd_desc *uffd_setup_demand_paging(int uffd_mode,
+ useconds_t uffd_delay, void *hva, uint64_t len,
+ uffd_handler_t handler)
+{
+ struct uffd_desc *uffd_desc;
+ bool is_minor = (uffd_mode == UFFDIO_REGISTER_MODE_MINOR);
+ int uffd;
+ struct uffdio_api uffdio_api;
+ struct uffdio_register uffdio_register;
+ uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY;
+ int ret;
+
+ PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n",
+ is_minor ? "MINOR" : "MISSING",
+ is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY");
+
+ uffd_desc = malloc(sizeof(struct uffd_desc));
+ TEST_ASSERT(uffd_desc, "malloc failed");
+
+ /* In order to get minor faults, prefault via the alias. */
+ if (is_minor)
+ expected_ioctls = ((uint64_t) 1) << _UFFDIO_CONTINUE;
+
+ uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+ TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno);
+
+ uffdio_api.api = UFFD_API;
+ uffdio_api.features = 0;
+ TEST_ASSERT(ioctl(uffd, UFFDIO_API, &uffdio_api) != -1,
+ "ioctl UFFDIO_API failed: %" PRIu64,
+ (uint64_t)uffdio_api.api);
+
+ uffdio_register.range.start = (uint64_t)hva;
+ uffdio_register.range.len = len;
+ uffdio_register.mode = uffd_mode;
+ TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1,
+ "ioctl UFFDIO_REGISTER failed");
+ TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) ==
+ expected_ioctls, "missing userfaultfd ioctls");
+
+ ret = pipe2(uffd_desc->pipefds, O_CLOEXEC | O_NONBLOCK);
+ TEST_ASSERT(!ret, "Failed to set up pipefd");
+
+ uffd_desc->uffd_mode = uffd_mode;
+ uffd_desc->uffd = uffd;
+ uffd_desc->delay = uffd_delay;
+ uffd_desc->handler = handler;
+ pthread_create(&uffd_desc->thread, NULL, uffd_handler_thread_fn,
+ uffd_desc);
+
+ PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
+ hva, hva + len);
+
+ return uffd_desc;
+}
+
+void uffd_stop_demand_paging(struct uffd_desc *uffd)
+{
+ char c = 0;
+ int ret;
+
+ ret = write(uffd->pipefds[1], &c, 1);
+ TEST_ASSERT(ret == 1, "Unable to write to pipefd");
+
+ ret = pthread_join(uffd->thread, NULL);
+ TEST_ASSERT(ret == 0, "Pthread_join failed.");
+
+ close(uffd->uffd);
+
+ close(uffd->pipefds[1]);
+ close(uffd->pipefds[0]);
+
+ free(uffd);
+}
+
+#endif /* __NR_userfaultfd */