1 files changed, 109 insertions, 65 deletions

diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 5f7a229c3af1..b74704305835 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -9,6 +9,7 @@
 
 #define _GNU_SOURCE /* for pipe2 */
 
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <time.h>
@@ -38,6 +39,7 @@
 
 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;
 
 static void *vcpu_worker(void *data)
@@ -71,36 +73,51 @@ static void *vcpu_worker(void *data)
 	return NULL;
 }
 
-static int handle_uffd_page_request(int uffd, uint64_t addr)
+static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr)
 {
-	pid_t tid;
+	pid_t tid = syscall(__NR_gettid);
 	struct timespec start;
 	struct timespec ts_diff;
-	struct uffdio_copy copy;
 	int r;
 
-	tid = syscall(__NR_gettid);
+	clock_gettime(CLOCK_MONOTONIC, &start);
 
-	copy.src = (uint64_t)guest_data_prototype;
-	copy.dst = addr;
-	copy.len = perf_test_args.host_page_size;
-	copy.mode = 0;
+	if (uffd_mode == UFFDIO_REGISTER_MODE_MISSING) {
+		struct uffdio_copy copy;
 
-	clock_gettime(CLOCK_MONOTONIC, &start);
+		copy.src = (uint64_t)guest_data_prototype;
+		copy.dst = addr;
+		copy.len = demand_paging_size;
+		copy.mode = 0;
 
-	r = ioctl(uffd, UFFDIO_COPY, &copy);
-	if (r == -1) {
-		pr_info("Failed Paged in 0x%lx from thread %d with errno: %d\n",
-			addr, tid, errno);
-		return r;
+		r = ioctl(uffd, UFFDIO_COPY, &copy);
+		if (r == -1) {
+			pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d with errno: %d\n",
+				addr, tid, errno);
+			return r;
+		}
+	} else if (uffd_mode == UFFDIO_REGISTER_MODE_MINOR) {
+		struct uffdio_continue cont = {0};
+
+		cont.range.start = addr;
+		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",
+				addr, tid, errno);
+			return r;
+		}
+	} else {
+		TEST_FAIL("Invalid uffd mode %d", uffd_mode);
 	}
 
 	ts_diff = timespec_elapsed(start);
 
-	PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid,
+	PER_PAGE_DEBUG("UFFD page-in %d \t%ld ns\n", tid,
 		       timespec_to_ns(ts_diff));
 	PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n",
-		       perf_test_args.host_page_size, addr, tid);
+		       demand_paging_size, addr, tid);
 
 	return 0;
 }
@@ -108,6 +125,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr)
 bool quit_uffd_thread;
 
 struct uffd_handler_args {
+	int uffd_mode;
 	int uffd;
 	int pipefd;
 	useconds_t delay;
@@ -169,7 +187,7 @@ static void *uffd_handler_thread_fn(void *arg)
 		if (r == -1) {
 			if (errno == EAGAIN)
 				continue;
-			pr_info("Read of uffd gor errno %d", errno);
+			pr_info("Read of uffd got errno %d\n", errno);
 			return NULL;
 		}
 
@@ -184,7 +202,7 @@ static void *uffd_handler_thread_fn(void *arg)
 		if (delay)
 			usleep(delay);
 		addr =  msg.arg.pagefault.address;
-		r = handle_uffd_page_request(uffd, addr);
+		r = handle_uffd_page_request(uffd_args->uffd_mode, uffd, addr);
 		if (r < 0)
 			return NULL;
 		pages++;
@@ -198,43 +216,53 @@ static void *uffd_handler_thread_fn(void *arg)
 	return NULL;
 }
 
-static int setup_demand_paging(struct kvm_vm *vm,
-			       pthread_t *uffd_handler_thread, int pipefd,
-			       useconds_t uffd_delay,
-			       struct uffd_handler_args *uffd_args,
-			       void *hva, uint64_t len)
+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)
 {
+	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;
 
-	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
-	if (uffd == -1) {
-		pr_info("uffd creation failed\n");
-		return -1;
+	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);
+		}
 	}
 
+	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;
-	if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) {
-		pr_info("ioctl uffdio_api failed\n");
-		return -1;
-	}
+	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 = UFFDIO_REGISTER_MODE_MISSING;
-	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) {
-		pr_info("ioctl uffdio_register failed\n");
-		return -1;
-	}
-
-	if ((uffdio_register.ioctls & UFFD_API_RANGE_IOCTLS) !=
-			UFFD_API_RANGE_IOCTLS) {
-		pr_info("unexpected userfaultfd ioctl set\n");
-		return -1;
-	}
+	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");
 
+	uffd_args->uffd_mode = uffd_mode;
 	uffd_args->uffd = uffd;
 	uffd_args->pipefd = pipefd;
 	uffd_args->delay = uffd_delay;
@@ -243,13 +271,12 @@ static int setup_demand_paging(struct kvm_vm *vm,
 
 	PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
 		       hva, hva + len);
-
-	return 0;
 }
 
 struct test_params {
-	bool use_uffd;
+	int uffd_mode;
 	useconds_t uffd_delay;
+	enum vm_mem_backing_src_type src_type;
 	bool partition_vcpu_memory_access;
 };
 
@@ -267,14 +294,16 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	int r;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
-				 VM_MEM_SRC_ANONYMOUS);
+				 p->src_type);
 
 	perf_test_args.wr_fract = 1;
 
-	guest_data_prototype = malloc(perf_test_args.host_page_size);
+	demand_paging_size = get_backing_src_pagesz(p->src_type);
+
+	guest_data_prototype = malloc(demand_paging_size);
 	TEST_ASSERT(guest_data_prototype,
 		    "Failed to allocate buffer for guest data pattern");
-	memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size);
+	memset(guest_data_prototype, 0xAB, demand_paging_size);
 
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
@@ -282,7 +311,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
 			      p->partition_vcpu_memory_access);
 
-	if (p->use_uffd) {
+	if (p->uffd_mode) {
 		uffd_handler_threads =
 			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
 		TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
@@ -296,6 +325,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
 			vm_paddr_t vcpu_gpa;
 			void *vcpu_hva;
+			void *vcpu_alias;
 			uint64_t vcpu_mem_size;
 
 
@@ -310,8 +340,9 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 			PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
 				       vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size);
 
-			/* Cache the HVA pointer of the region */
+			/* Cache the host addresses of the region */
 			vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
+			vcpu_alias = addr_gpa2alias(vm, vcpu_gpa);
 
 			/*
 			 * Set up user fault fd to handle demand paging
@@ -321,13 +352,11 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 				  O_CLOEXEC | O_NONBLOCK);
 			TEST_ASSERT(!r, "Failed to set up pipefd");
 
-			r = setup_demand_paging(vm,
-						&uffd_handler_threads[vcpu_id],
-						pipefds[vcpu_id * 2],
-						p->uffd_delay, &uffd_args[vcpu_id],
-						vcpu_hva, vcpu_mem_size);
-			if (r < 0)
-				exit(-r);
+			setup_demand_paging(vm, &uffd_handler_threads[vcpu_id],
+					    pipefds[vcpu_id * 2], p->uffd_mode,
+					    p->uffd_delay, &uffd_args[vcpu_id],
+					    vcpu_hva, vcpu_alias,
+					    vcpu_mem_size);
 		}
 	}
 
@@ -355,7 +384,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	pr_info("All vCPU threads joined\n");
 
-	if (p->use_uffd) {
+	if (p->uffd_mode) {
 		char c;
 
 		/* Tell the user fault fd handler threads to quit */
@@ -377,7 +406,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	free(guest_data_prototype);
 	free(vcpu_threads);
-	if (p->use_uffd) {
+	if (p->uffd_mode) {
 		free(uffd_handler_threads);
 		free(uffd_args);
 		free(pipefds);
@@ -387,17 +416,19 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 static void help(char *name)
 {
 	puts("");
-	printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n"
-	       "          [-b memory] [-v vcpus] [-o]\n", name);
+	printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n"
+	       "          [-b memory] [-t type] [-v vcpus] [-o]\n", name);
 	guest_modes_help();
-	printf(" -u: use User Fault FD to handle vCPU page\n"
-	       "     faults.\n");
+	printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n"
+	       "     UFFD registration mode: 'MISSING' or 'MINOR'.\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(" -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");
+	printf(" -t: The type of backing memory to use. Default: anonymous\n");
+	backing_src_help();
 	printf(" -v: specify the number of vCPUs to run.\n");
 	printf(" -o: Overlap guest memory accesses instead of partitioning\n"
 	       "     them into a separate region of memory for each vCPU.\n");
@@ -409,19 +440,24 @@ int main(int argc, char *argv[])
 {
 	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
 	struct test_params p = {
+		.src_type = VM_MEM_SRC_ANONYMOUS,
 		.partition_vcpu_memory_access = true,
 	};
 	int opt;
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:ud:b:v:o")) != -1) {
+	while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
 			break;
 		case 'u':
-			p.use_uffd = true;
+			if (!strcmp("MISSING", optarg))
+				p.uffd_mode = UFFDIO_REGISTER_MODE_MISSING;
+			else if (!strcmp("MINOR", optarg))
+				p.uffd_mode = UFFDIO_REGISTER_MODE_MINOR;
+			TEST_ASSERT(p.uffd_mode, "UFFD mode must be 'MISSING' or 'MINOR'.");
 			break;
 		case 'd':
 			p.uffd_delay = strtoul(optarg, NULL, 0);
@@ -430,6 +466,9 @@ int main(int argc, char *argv[])
 		case 'b':
 			guest_percpu_mem_size = parse_size(optarg);
 			break;
+		case 't':
+			p.src_type = parse_backing_src_type(optarg);
+			break;
 		case 'v':
 			nr_vcpus = atoi(optarg);
 			TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
@@ -445,6 +484,11 @@ int main(int argc, char *argv[])
 		}
 	}
 
+	if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR &&
+	    !backing_src_is_shared(p.src_type)) {
+		TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t");
+	}
+
 	for_each_guest_mode(run_test, &p);
 
 	return 0;