Merge tag 'kvm-x86-selftests-6.10' of https://github.com/kvm-x86/linux into HEAD

KVM selftests cleanups and fixes for 6.10:

 - Enhance the demand paging test to allow for better reporting and stressing
   of UFFD performance.

 - Convert the steal time test to generate TAP-friendly output.

 - Fix a flaky false positive in the xen_shinfo_test due to comparing elapsed
   time across two different clock domains.

 - Skip the MONITOR/MWAIT test if the host doesn't actually support MWAIT.

 - Avoid unnecessary use of "sudo" in the NX hugepage test to play nice with
   running in a minimal userspace environment.

 - Allow skipping the RSEQ test's sanity check that the vCPU was able to
   complete a reasonable number of KVM_RUNs, as the assert can fail on a
   completely valid setup.  If the test is run on a large-ish system that is
   otherwise idle, and the test isn't affined to a low-ish number of CPUs, the
   vCPU task can be repeatedly migrated to CPUs that are in deep sleep states,
   which results in the vCPU having very little net runtime before the next
   migration due to high wakeup latencies.

tools/testing/selftests/kvm/aarch64/page_fault_test.c

@@ -375,14 +375,14 @@ static void setup_uffd(struct kvm_vm *vm, struct test_params *p,
 		*pt_uffd = uffd_setup_demand_paging(uffd_mode, 0,
 						    pt_args.hva,
 						    pt_args.paging_size,
-						    test->uffd_pt_handler);
+						    1, test->uffd_pt_handler);
 
 	*data_uffd = NULL;
 	if (test->uffd_data_handler)
 		*data_uffd = uffd_setup_demand_paging(uffd_mode, 0,
 						      data_args.hva,
 						      data_args.paging_size,
-						      test->uffd_data_handler);
+						      1, test->uffd_data_handler);
 }
 
 static void free_uffd(struct test_desc *test, struct uffd_desc *pt_uffd,

tools/testing/selftests/kvm/demand_paging_test.c

@@ -13,7 +13,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <time.h>
-#include <poll.h>
 #include <pthread.h>
 #include <linux/userfaultfd.h>
 #include <sys/syscall.h>
@@ -77,8 +76,20 @@ static int handle_uffd_page_request(int uffd_mode, int uffd,
 		copy.mode = 0;
 
 		r = ioctl(uffd, UFFDIO_COPY, &copy);
-		if (r == -1) {
-			pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d with errno: %d\n",
+		/*
+		 * With multiple vCPU threads fault on a single page and there are
+		 * multiple readers for the UFFD, at least one of the UFFDIO_COPYs
+		 * will fail with EEXIST: handle that case without signaling an
+		 * error.
+		 *
+		 * Note that this also suppress any EEXISTs occurring from,
+		 * e.g., the first UFFDIO_COPY/CONTINUEs on a page. That never
+		 * happens here, but a realistic VMM might potentially maintain
+		 * some external state to correctly surface EEXISTs to userspace
+		 * (or prevent duplicate COPY/CONTINUEs in the first place).
+		 */
+		if (r == -1 && errno != EEXIST) {
+			pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d, errno = %d\n",
 				addr, tid, errno);
 			return r;
 		}
@@ -89,8 +100,20 @@ static int handle_uffd_page_request(int uffd_mode, int uffd,
 		cont.range.len = demand_paging_size;
 
 		r = ioctl(uffd, UFFDIO_CONTINUE, &cont);
-		if (r == -1) {
-			pr_info("Failed UFFDIO_CONTINUE in 0x%lx from thread %d with errno: %d\n",
+		/*
+		 * With multiple vCPU threads fault on a single page and there are
+		 * multiple readers for the UFFD, at least one of the UFFDIO_COPYs
+		 * will fail with EEXIST: handle that case without signaling an
+		 * error.
+		 *
+		 * Note that this also suppress any EEXISTs occurring from,
+		 * e.g., the first UFFDIO_COPY/CONTINUEs on a page. That never
+		 * happens here, but a realistic VMM might potentially maintain
+		 * some external state to correctly surface EEXISTs to userspace
+		 * (or prevent duplicate COPY/CONTINUEs in the first place).
+		 */
+		if (r == -1 && errno != EEXIST) {
+			pr_info("Failed UFFDIO_CONTINUE in 0x%lx, thread %d, errno = %d\n",
 				addr, tid, errno);
 			return r;
 		}
@@ -110,7 +133,9 @@ static int handle_uffd_page_request(int uffd_mode, int uffd,
 
 struct test_params {
 	int uffd_mode;
+	bool single_uffd;
 	useconds_t uffd_delay;
+	int readers_per_uffd;
 	enum vm_mem_backing_src_type src_type;
 	bool partition_vcpu_memory_access;
 };
@@ -131,10 +156,12 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct memstress_vcpu_args *vcpu_args;
 	struct test_params *p = arg;
 	struct uffd_desc **uffd_descs = NULL;
+	uint64_t uffd_region_size;
 	struct timespec start;
 	struct timespec ts_diff;
+	double vcpu_paging_rate;
 	struct kvm_vm *vm;
-	int i;
+	int i, num_uffds = 0;
 
 	vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
 				 p->src_type, p->partition_vcpu_memory_access);
@@ -147,7 +174,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	memset(guest_data_prototype, 0xAB, demand_paging_size);
 
 	if (p->uffd_mode == UFFDIO_REGISTER_MODE_MINOR) {
-		for (i = 0; i < nr_vcpus; i++) {
+		num_uffds = p->single_uffd ? 1 : nr_vcpus;
+		for (i = 0; i < num_uffds; i++) {
 			vcpu_args = &memstress_args.vcpu_args[i];
 			prefault_mem(addr_gpa2alias(vm, vcpu_args->gpa),
 				     vcpu_args->pages * memstress_args.guest_page_size);
@@ -155,9 +183,13 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	}
 
 	if (p->uffd_mode) {
-		uffd_descs = malloc(nr_vcpus * sizeof(struct uffd_desc *));
+		num_uffds = p->single_uffd ? 1 : nr_vcpus;
+		uffd_region_size = nr_vcpus * guest_percpu_mem_size / num_uffds;
+
+		uffd_descs = malloc(num_uffds * sizeof(struct uffd_desc *));
 		TEST_ASSERT(uffd_descs, "Memory allocation failed");
-		for (i = 0; i < nr_vcpus; i++) {
+		for (i = 0; i < num_uffds; i++) {
+			struct memstress_vcpu_args *vcpu_args;
 			void *vcpu_hva;
 
 			vcpu_args = &memstress_args.vcpu_args[i];
@@ -170,7 +202,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 			 */
 			uffd_descs[i] = uffd_setup_demand_paging(
 				p->uffd_mode, p->uffd_delay, vcpu_hva,
-				vcpu_args->pages * memstress_args.guest_page_size,
+				uffd_region_size,
+				p->readers_per_uffd,
 				&handle_uffd_page_request);
 		}
 	}
@@ -187,15 +220,19 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	if (p->uffd_mode) {
 		/* Tell the user fault fd handler threads to quit */
-		for (i = 0; i < nr_vcpus; i++)
+		for (i = 0; i < num_uffds; i++)
 			uffd_stop_demand_paging(uffd_descs[i]);
 	}
 
-	pr_info("Total guest execution time: %ld.%.9lds\n",
+	pr_info("Total guest execution time:\t%ld.%.9lds\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
-	pr_info("Overall demand paging rate: %f pgs/sec\n",
-		memstress_args.vcpu_args[0].pages * nr_vcpus /
-		((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / NSEC_PER_SEC));
+
+	vcpu_paging_rate = memstress_args.vcpu_args[0].pages /
+			   ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / NSEC_PER_SEC);
+	pr_info("Per-vcpu demand paging rate:\t%f pgs/sec/vcpu\n",
+		vcpu_paging_rate);
+	pr_info("Overall demand paging rate:\t%f pgs/sec\n",
+		vcpu_paging_rate * nr_vcpus);
 
 	memstress_destroy_vm(vm);
 
@@ -207,15 +244,20 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 static void help(char *name)
 {
 	puts("");
-	printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n"
-	       "          [-b memory] [-s type] [-v vcpus] [-c cpu_list] [-o]\n", name);
+	printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-a]\n"
+		   "          [-d uffd_delay_usec] [-r readers_per_uffd] [-b memory]\n"
+		   "          [-s type] [-v vcpus] [-c cpu_list] [-o]\n", name);
 	guest_modes_help();
 	printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n"
 	       "     UFFD registration mode: 'MISSING' or 'MINOR'.\n");
 	kvm_print_vcpu_pinning_help();
+	printf(" -a: Use a single userfaultfd for all of guest memory, instead of\n"
+	       "     creating one for each region paged by a unique vCPU\n"
+	       "     Set implicitly with -o, and no effect without -u.\n");
 	printf(" -d: add a delay in usec to the User Fault\n"
 	       "     FD handler to simulate demand paging\n"
 	       "     overheads. Ignored without -u.\n");
+	printf(" -r: Set the number of reader threads per uffd.\n");
 	printf(" -b: specify the size of the memory region which should be\n"
 	       "     demand paged by each vCPU. e.g. 10M or 3G.\n"
 	       "     Default: 1G\n");
@@ -234,12 +276,14 @@ int main(int argc, char *argv[])
 	struct test_params p = {
 		.src_type = DEFAULT_VM_MEM_SRC,
 		.partition_vcpu_memory_access = true,
+		.readers_per_uffd = 1,
+		.single_uffd = false,
 	};
 	int opt;
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:c:o")) != -1) {
+	while ((opt = getopt(argc, argv, "ahom:u:d:b:s:v:c:r:")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
@@ -251,6 +295,9 @@ int main(int argc, char *argv[])
 				p.uffd_mode = UFFDIO_REGISTER_MODE_MINOR;
 			TEST_ASSERT(p.uffd_mode, "UFFD mode must be 'MISSING' or 'MINOR'.");
 			break;
+		case 'a':
+			p.single_uffd = true;
+			break;
 		case 'd':
 			p.uffd_delay = strtoul(optarg, NULL, 0);
 			TEST_ASSERT(p.uffd_delay >= 0, "A negative UFFD delay is not supported.");
@@ -271,6 +318,13 @@ int main(int argc, char *argv[])
 			break;
 		case 'o':
 			p.partition_vcpu_memory_access = false;
+			p.single_uffd = true;
+			break;
+		case 'r':
+			p.readers_per_uffd = atoi(optarg);
+			TEST_ASSERT(p.readers_per_uffd >= 1,
+				    "Invalid number of readers per uffd %d: must be >=1",
+				    p.readers_per_uffd);
 			break;
 		case 'h':
 		default:

tools/testing/selftests/kvm/include/userfaultfd_util.h

@@ -17,17 +17,27 @@
 
 typedef int (*uffd_handler_t)(int uffd_mode, int uffd, struct uffd_msg *msg);
 
-struct uffd_desc {
+struct uffd_reader_args {
 	int uffd_mode;
 	int uffd;
-	int pipefds[2];
 	useconds_t delay;
 	uffd_handler_t handler;
-	pthread_t thread;
+	/* Holds the read end of the pipe for killing the reader. */
+	int pipe;
+};
+
+struct uffd_desc {
+	int uffd;
+	uint64_t num_readers;
+	/* Holds the write ends of the pipes for killing the readers. */
+	int *pipefds;
+	pthread_t *readers;
+	struct uffd_reader_args *reader_args;
 };
 
 struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
 					   void *hva, uint64_t len,
+					   uint64_t num_readers,
 					   uffd_handler_t handler);
 
 void uffd_stop_demand_paging(struct uffd_desc *uffd);

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -929,6 +929,10 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 		    errno, strerror(errno));
 }
 
+#define TEST_REQUIRE_SET_USER_MEMORY_REGION2()			\
+	__TEST_REQUIRE(kvm_has_cap(KVM_CAP_USER_MEMORY2),	\
+		       "KVM selftests now require KVM_SET_USER_MEMORY_REGION2 (introduced in v6.8)")
+
 int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 				 uint64_t gpa, uint64_t size, void *hva,
 				 uint32_t guest_memfd, uint64_t guest_memfd_offset)
@@ -943,6 +947,8 @@ int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flag
 		.guest_memfd_offset = guest_memfd_offset,
 	};
 
+	TEST_REQUIRE_SET_USER_MEMORY_REGION2();
+
 	return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION2, &region);
 }
 
@@ -969,6 +975,8 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 	size_t mem_size = npages * vm->page_size;
 	size_t alignment;
 
+	TEST_REQUIRE_SET_USER_MEMORY_REGION2();
+
 	TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages,
 		"Number of guest pages is not compatible with the host. "
 		"Try npages=%d", vm_adjust_num_guest_pages(vm->mode, npages));

tools/testing/selftests/kvm/lib/userfaultfd_util.c

@@ -16,6 +16,7 @@
 #include <poll.h>
 #include <pthread.h>
 #include <linux/userfaultfd.h>
+#include <sys/epoll.h>
 #include <sys/syscall.h>
 
 #include "kvm_util.h"
@@ -27,76 +28,69 @@
 
 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;
+	struct uffd_reader_args *reader_args = (struct uffd_reader_args *)arg;
+	int uffd = reader_args->uffd;
 	int64_t pages = 0;
 	struct timespec start;
 	struct timespec ts_diff;
+	struct epoll_event evt;
+	int epollfd;
+
+	epollfd = epoll_create(1);
+	TEST_ASSERT(epollfd >= 0, "Failed to create epollfd.");
+
+	evt.events = EPOLLIN | EPOLLEXCLUSIVE;
+	evt.data.u32 = 0;
+	TEST_ASSERT(!epoll_ctl(epollfd, EPOLL_CTL_ADD, uffd, &evt),
+		    "Failed to add uffd to epollfd");
+
+	evt.events = EPOLLIN;
+	evt.data.u32 = 1;
+	TEST_ASSERT(!epoll_ctl(epollfd, EPOLL_CTL_ADD, reader_args->pipe, &evt),
+		    "Failed to add pipe to epollfd");
 
 	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;
-		}
+		r = epoll_wait(epollfd, &evt, 1, -1);
+		TEST_ASSERT(r == 1,
+			    "Unexpected number of events (%d) from epoll, errno = %d",
+			    r, errno);
 
-		if (pollfd[0].revents & POLLERR) {
-			pr_info("uffd revents has POLLERR");
-			return NULL;
-		}
+		if (evt.data.u32 == 1) {
+			char tmp_chr;
 
-		if (pollfd[1].revents & POLLIN) {
-			r = read(pollfd[1].fd, &tmp_chr, 1);
+			TEST_ASSERT(!(evt.events & (EPOLLERR | EPOLLHUP)),
+				    "Reader thread received EPOLLERR or EPOLLHUP on pipe.");
+			r = read(reader_args->pipe, &tmp_chr, 1);
 			TEST_ASSERT(r == 1,
-				    "Error reading pipefd in UFFD thread");
+				    "Error reading pipefd in uffd reader thread");
 			break;
 		}
 
-		if (!(pollfd[0].revents & POLLIN))
-			continue;
+		TEST_ASSERT(!(evt.events & (EPOLLERR | EPOLLHUP)),
+			    "Reader thread received EPOLLERR or EPOLLHUP on uffd.");
 
 		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;
+			TEST_ASSERT(errno == EAGAIN,
+				    "Error reading from UFFD: errno = %d", errno);
+			continue;
 		}
 
-		if (r != sizeof(msg)) {
-			pr_info("Read on uffd returned unexpected size: %d bytes", r);
-			return NULL;
-		}
+		TEST_ASSERT(r == sizeof(msg),
+			    "Read on uffd returned unexpected number of bytes (%d)", r);
 
 		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;
+		if (reader_args->delay)
+			usleep(reader_args->delay);
+		r = reader_args->handler(reader_args->uffd_mode, uffd, &msg);
+		TEST_ASSERT(r >= 0,
+			    "Reader thread handler fn returned negative value %d", r);
 		pages++;
 	}
 
@@ -110,6 +104,7 @@ static void *uffd_handler_thread_fn(void *arg)
 
 struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
 					   void *hva, uint64_t len,
+					   uint64_t num_readers,
 					   uffd_handler_t handler)
 {
 	struct uffd_desc *uffd_desc;
@@ -118,14 +113,25 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
 	struct uffdio_api uffdio_api;
 	struct uffdio_register uffdio_register;
 	uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY;
-	int ret;
+	int ret, i;
 
 	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");
+	TEST_ASSERT(uffd_desc, "Failed to malloc uffd descriptor");
+
+	uffd_desc->pipefds = calloc(sizeof(int), num_readers);
+	TEST_ASSERT(uffd_desc->pipefds, "Failed to alloc pipes");
+
+	uffd_desc->readers = calloc(sizeof(pthread_t), num_readers);
+	TEST_ASSERT(uffd_desc->readers, "Failed to alloc reader threads");
+
+	uffd_desc->reader_args = calloc(sizeof(struct uffd_reader_args), num_readers);
+	TEST_ASSERT(uffd_desc->reader_args, "Failed to alloc reader_args");
+
+	uffd_desc->num_readers = num_readers;
 
 	/* In order to get minor faults, prefault via the alias. */
 	if (is_minor)
@@ -148,18 +154,28 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
 	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 = delay;
-	uffd_desc->handler = handler;
-	pthread_create(&uffd_desc->thread, NULL, uffd_handler_thread_fn,
-		       uffd_desc);
+	for (i = 0; i < uffd_desc->num_readers; ++i) {
+		int pipes[2];
+
+		ret = pipe2((int *) &pipes, O_CLOEXEC | O_NONBLOCK);
+		TEST_ASSERT(!ret, "Failed to set up pipefd %i for uffd_desc %p",
+			    i, uffd_desc);
 
-	PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
-		       hva, hva + len);
+		uffd_desc->pipefds[i] = pipes[1];
+
+		uffd_desc->reader_args[i].uffd_mode = uffd_mode;
+		uffd_desc->reader_args[i].uffd = uffd;
+		uffd_desc->reader_args[i].delay = delay;
+		uffd_desc->reader_args[i].handler = handler;
+		uffd_desc->reader_args[i].pipe = pipes[0];
+
+		pthread_create(&uffd_desc->readers[i], NULL, uffd_handler_thread_fn,
+			       &uffd_desc->reader_args[i]);
+
+		PER_VCPU_DEBUG("Created uffd thread %i for HVA range [%p, %p)\n",
+			       i, hva, hva + len);
+	}
 
 	return uffd_desc;
 }
@@ -167,19 +183,26 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
 void uffd_stop_demand_paging(struct uffd_desc *uffd)
 {
 	char c = 0;
-	int ret;
+	int i;
 
-	ret = write(uffd->pipefds[1], &c, 1);
-	TEST_ASSERT(ret == 1, "Unable to write to pipefd");
+	for (i = 0; i < uffd->num_readers; ++i)
+		TEST_ASSERT(write(uffd->pipefds[i], &c, 1) == 1,
+			    "Unable to write to pipefd %i for uffd_desc %p", i, uffd);
 
-	ret = pthread_join(uffd->thread, NULL);
-	TEST_ASSERT(ret == 0, "Pthread_join failed.");
+	for (i = 0; i < uffd->num_readers; ++i)
+		TEST_ASSERT(!pthread_join(uffd->readers[i], NULL),
+			    "Pthread_join failed on reader %i for uffd_desc %p", i, uffd);
 
 	close(uffd->uffd);
 
-	close(uffd->pipefds[1]);
-	close(uffd->pipefds[0]);
+	for (i = 0; i < uffd->num_readers; ++i) {
+		close(uffd->pipefds[i]);
+		close(uffd->reader_args[i].pipe);
+	}
 
+	free(uffd->pipefds);
+	free(uffd->readers);
+	free(uffd->reader_args);
 	free(uffd);
 }
 

tools/testing/selftests/kvm/rseq_test.c

@@ -186,12 +186,35 @@ static void calc_min_max_cpu(void)
 		       "Only one usable CPU, task migration not possible");
 }
 
+static void help(const char *name)
+{
+	puts("");
+	printf("usage: %s [-h] [-u]\n", name);
+	printf(" -u: Don't sanity check the number of successful KVM_RUNs\n");
+	puts("");
+	exit(0);
+}
+
 int main(int argc, char *argv[])
 {
+	bool skip_sanity_check = false;
 	int r, i, snapshot;
 	struct kvm_vm *vm;
 	struct kvm_vcpu *vcpu;
 	u32 cpu, rseq_cpu;
+	int opt;
+
+	while ((opt = getopt(argc, argv, "hu")) != -1) {
+		switch (opt) {
+		case 'u':
+			skip_sanity_check = true;
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			break;
+		}
+	}
 
 	r = sched_getaffinity(0, sizeof(possible_mask), &possible_mask);
 	TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno,
@@ -254,9 +277,17 @@ int main(int argc, char *argv[])
 	 * getcpu() to stabilize.  A 2:1 migration:KVM_RUN ratio is a fairly
 	 * conservative ratio on x86-64, which can do _more_ KVM_RUNs than
 	 * migrations given the 1us+ delay in the migration task.
+	 *
+	 * Another reason why it may have small migration:KVM_RUN ratio is that,
+	 * on systems with large low power mode wakeup latency, it may happen
+	 * quite often that the scheduler is not able to wake up the target CPU
+	 * before the vCPU thread is scheduled to another CPU.
 	 */
-	TEST_ASSERT(i > (NR_TASK_MIGRATIONS / 2),
-		    "Only performed %d KVM_RUNs, task stalled too much?", i);
+	TEST_ASSERT(skip_sanity_check || i > (NR_TASK_MIGRATIONS / 2),
+		    "Only performed %d KVM_RUNs, task stalled too much?\n\n"
+		    "  Try disabling deep sleep states to reduce CPU wakeup latency,\n"
+		    "  e.g. via cpuidle.off=1 or setting /dev/cpu_dma_latency to '0',\n"
+		    "  or run with -u to disable this sanity check.", i);
 
 	pthread_join(migration_thread, NULL);
 

tools/testing/selftests/kvm/steal_time.c

@@ -85,20 +85,18 @@ static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i)
 static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx)
 {
 	struct kvm_steal_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]);
-	int i;
 
-	pr_info("VCPU%d:\n", vcpu_idx);
-	pr_info("    steal:     %lld\n", st->steal);
-	pr_info("    version:   %d\n", st->version);
-	pr_info("    flags:     %d\n", st->flags);
-	pr_info("    preempted: %d\n", st->preempted);
-	pr_info("    u8_pad:    ");
-	for (i = 0; i < 3; ++i)
-		pr_info("%d", st->u8_pad[i]);
-	pr_info("\n    pad:       ");
-	for (i = 0; i < 11; ++i)
-		pr_info("%d", st->pad[i]);
-	pr_info("\n");
+	ksft_print_msg("VCPU%d:\n", vcpu_idx);
+	ksft_print_msg("    steal:     %lld\n", st->steal);
+	ksft_print_msg("    version:   %d\n", st->version);
+	ksft_print_msg("    flags:     %d\n", st->flags);
+	ksft_print_msg("    preempted: %d\n", st->preempted);
+	ksft_print_msg("    u8_pad:    %d %d %d\n",
+			st->u8_pad[0], st->u8_pad[1], st->u8_pad[2]);
+	ksft_print_msg("    pad:       %d %d %d %d %d %d %d %d %d %d %d\n",
+			st->pad[0], st->pad[1], st->pad[2], st->pad[3],
+			st->pad[4], st->pad[5], st->pad[6], st->pad[7],
+			st->pad[8], st->pad[9], st->pad[10]);
 }
 
 #elif defined(__aarch64__)
@@ -201,10 +199,10 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx)
 {
 	struct st_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]);
 
-	pr_info("VCPU%d:\n", vcpu_idx);
-	pr_info("    rev:     %d\n", st->rev);
-	pr_info("    attr:    %d\n", st->attr);
-	pr_info("    st_time: %ld\n", st->st_time);
+	ksft_print_msg("VCPU%d:\n", vcpu_idx);
+	ksft_print_msg("    rev:     %d\n", st->rev);
+	ksft_print_msg("    attr:    %d\n", st->attr);
+	ksft_print_msg("    st_time: %ld\n", st->st_time);
 }
 
 #elif defined(__riscv)
@@ -368,7 +366,9 @@ int main(int ac, char **av)
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, gpages, 0);
 	virt_map(vm, ST_GPA_BASE, ST_GPA_BASE, gpages);
 
+	ksft_print_header();
 	TEST_REQUIRE(is_steal_time_supported(vcpus[0]));
+	ksft_set_plan(NR_VCPUS);
 
 	/* Run test on each VCPU */
 	for (i = 0; i < NR_VCPUS; ++i) {
@@ -409,14 +409,15 @@ int main(int ac, char **av)
 			    run_delay, stolen_time);
 
 		if (verbose) {
-			pr_info("VCPU%d: total-stolen-time=%ld test-stolen-time=%ld", i,
-				guest_stolen_time[i], stolen_time);
-			if (stolen_time == run_delay)
-				pr_info(" (BONUS: guest test-stolen-time even exactly matches test-run_delay)");
-			pr_info("\n");
+			ksft_print_msg("VCPU%d: total-stolen-time=%ld test-stolen-time=%ld%s\n",
+				       i, guest_stolen_time[i], stolen_time,
+				       stolen_time == run_delay ?
+				       " (BONUS: guest test-stolen-time even exactly matches test-run_delay)" : "");
 			steal_time_dump(vm, i);
 		}
+		ksft_test_result_pass("vcpu%d\n", i);
 	}
 
-	return 0;
+	/* Print results and exit() accordingly */
+	ksft_finished();
 }

tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c

@@ -75,6 +75,7 @@ int main(int argc, char *argv[])
 	struct ucall uc;
 	int testcase;
 
+	TEST_REQUIRE(this_cpu_has(X86_FEATURE_MWAIT));
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2));
 
 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);

tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh

@@ -13,10 +13,21 @@ NX_HUGE_PAGES_RECOVERY_RATIO=$(cat /sys/module/kvm/parameters/nx_huge_pages_reco
 NX_HUGE_PAGES_RECOVERY_PERIOD=$(cat /sys/module/kvm/parameters/nx_huge_pages_recovery_period_ms)
 HUGE_PAGES=$(cat /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages)
 
+# If we're already root, the host might not have sudo.
+if [ $(whoami) == "root" ]; then
+	function do_sudo () {
+		"$@"
+	}
+else
+	function do_sudo () {
+		sudo "$@"
+	}
+fi
+
 set +e
 
 function sudo_echo () {
-	echo "$1" | sudo tee -a "$2" > /dev/null
+	echo "$1" | do_sudo tee -a "$2" > /dev/null
 }
 
 NXECUTABLE="$(dirname $0)/nx_huge_pages_test"

tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c

@@ -125,7 +125,7 @@ struct compat_vcpu_runstate_info {
 	uint32_t state;
 	uint64_t state_entry_time;
 	uint64_t time[5];
-} __attribute__((__packed__));;
+} __attribute__((__packed__));
 
 struct arch_vcpu_info {
 	unsigned long cr2;
@@ -380,20 +380,6 @@ static void guest_code(void)
 	GUEST_SYNC(TEST_DONE);
 }
 
-static int cmp_timespec(struct timespec *a, struct timespec *b)
-{
-	if (a->tv_sec > b->tv_sec)
-		return 1;
-	else if (a->tv_sec < b->tv_sec)
-		return -1;
-	else if (a->tv_nsec > b->tv_nsec)
-		return 1;
-	else if (a->tv_nsec < b->tv_nsec)
-		return -1;
-	else
-		return 0;
-}
-
 static struct shared_info *shinfo;
 static struct vcpu_info *vinfo;
 static struct kvm_vcpu *vcpu;
@@ -449,7 +435,6 @@ static void *juggle_shinfo_state(void *arg)
 
 int main(int argc, char *argv[])
 {
-	struct timespec min_ts, max_ts, vm_ts;
 	struct kvm_xen_hvm_attr evt_reset;
 	struct kvm_vm *vm;
 	pthread_t thread;
@@ -468,8 +453,6 @@ int main(int argc, char *argv[])
 	bool do_evtchn_tests = do_eventfd_tests && !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_SEND);
 	bool has_shinfo_hva = !!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA);
 
-	clock_gettime(CLOCK_REALTIME, &min_ts);
-
 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 
 	/* Map a region for the shared_info page */
@@ -1010,7 +993,6 @@ int main(int argc, char *argv[])
 	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset);
 
 	alarm(0);
-	clock_gettime(CLOCK_REALTIME, &max_ts);
 
 	/*
 	 * Just a *really* basic check that things are being put in the
@@ -1019,6 +1001,8 @@ int main(int argc, char *argv[])
 	 */
 	struct pvclock_wall_clock *wc;
 	struct pvclock_vcpu_time_info *ti, *ti2;
+	struct kvm_clock_data kcdata;
+	long long delta;
 
 	wc = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0xc00);
 	ti = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0x40 + 0x20);
@@ -1034,12 +1018,34 @@ int main(int argc, char *argv[])
 		       ti2->tsc_shift, ti2->flags);
 	}
 
-	vm_ts.tv_sec = wc->sec;
-	vm_ts.tv_nsec = wc->nsec;
 	TEST_ASSERT(wc->version && !(wc->version & 1),
 		    "Bad wallclock version %x", wc->version);
-	TEST_ASSERT(cmp_timespec(&min_ts, &vm_ts) <= 0, "VM time too old");
-	TEST_ASSERT(cmp_timespec(&max_ts, &vm_ts) >= 0, "VM time too new");
+
+	vm_ioctl(vm, KVM_GET_CLOCK, &kcdata);
+
+	if (kcdata.flags & KVM_CLOCK_REALTIME) {
+		if (verbose) {
+			printf("KVM_GET_CLOCK clock: %lld.%09lld\n",
+			       kcdata.clock / NSEC_PER_SEC, kcdata.clock % NSEC_PER_SEC);
+			printf("KVM_GET_CLOCK realtime: %lld.%09lld\n",
+			       kcdata.realtime / NSEC_PER_SEC, kcdata.realtime % NSEC_PER_SEC);
+		}
+
+		delta = (wc->sec * NSEC_PER_SEC + wc->nsec) - (kcdata.realtime - kcdata.clock);
+
+		/*
+		 * KVM_GET_CLOCK gives CLOCK_REALTIME which jumps on leap seconds updates but
+		 * unfortunately KVM doesn't currently offer a CLOCK_TAI alternative. Accept 1s
+		 * delta as testing clock accuracy is not the goal here. The test just needs to
+		 * check that the value in shinfo is somewhat sane.
+		 */
+		TEST_ASSERT(llabs(delta) < NSEC_PER_SEC,
+			    "Guest's epoch from shinfo %d.%09d differs from KVM_GET_CLOCK %lld.%lld",
+			    wc->sec, wc->nsec, (kcdata.realtime - kcdata.clock) / NSEC_PER_SEC,
+			    (kcdata.realtime - kcdata.clock) % NSEC_PER_SEC);
+	} else {
+		pr_info("Missing KVM_CLOCK_REALTIME, skipping shinfo epoch sanity check\n");
+	}
 
 	TEST_ASSERT(ti->version && !(ti->version & 1),
 		    "Bad time_info version %x", ti->version);