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.

2 files changed, 96 insertions, 65 deletions

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 9da388100f3a..0f5197548da7 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/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));
diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
index f4eef6eb2dc2..0ba866c4af69 100644
--- a/tools/testing/selftests/kvm/lib/userfaultfd_util.c
+++ b/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);
 }