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.

Author: bonzini

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);
@@ -147,17 +174,22 @@ 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);
 		}
 	}
 
 	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));