KVM: selftests: Add option to overlap vCPU memory access

Add an option to overlap the ranges of memory each vCPU accesses instead
of partitioning them. This option will increase the probability of
multiple vCPUs faulting on the same page at the same time, and causing
interesting races, if there are bugs in the page fault handler or
elsewhere in the kernel.

Reviewed-by: Jacob Xu <[email protected]>
Reviewed-by: Makarand Sonare <[email protected]>

Signed-off-by: Ben Gardon <[email protected]>
Message-Id: <[email protected]>
Signed-off-by: Paolo Bonzini <[email protected]>

Author: Ben Gardon

tools/testing/selftests/kvm/demand_paging_test.c

@@ -250,6 +250,7 @@ static int setup_demand_paging(struct kvm_vm *vm,
 struct test_params {
 	bool use_uffd;
 	useconds_t uffd_delay;
+	bool partition_vcpu_memory_access;
 };
 
 static void run_test(enum vm_guest_mode mode, void *arg)
@@ -277,7 +278,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
+			      p->partition_vcpu_memory_access);
 
 	if (p->use_uffd) {
 		uffd_handler_threads =
@@ -293,10 +295,19 @@ 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;
+			uint64_t vcpu_mem_size;
 
-			vcpu_gpa = guest_test_phys_mem + (vcpu_id * guest_percpu_mem_size);
+
+			if (p->partition_vcpu_memory_access) {
+				vcpu_gpa = guest_test_phys_mem +
+					   (vcpu_id * guest_percpu_mem_size);
+				vcpu_mem_size = guest_percpu_mem_size;
+			} else {
+				vcpu_gpa = guest_test_phys_mem;
+				vcpu_mem_size = guest_percpu_mem_size * nr_vcpus;
+			}
 			PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-				       vcpu_id, vcpu_gpa, vcpu_gpa + guest_percpu_mem_size);
+				       vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size);
 
 			/* Cache the HVA pointer of the region */
 			vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
@@ -313,7 +324,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 						&uffd_handler_threads[vcpu_id],
 						pipefds[vcpu_id * 2],
 						p->uffd_delay, &uffd_args[vcpu_id],
-						vcpu_hva, guest_percpu_mem_size);
+						vcpu_hva, vcpu_mem_size);
 			if (r < 0)
 				exit(-r);
 		}
@@ -376,7 +387,7 @@ static void help(char *name)
 {
 	puts("");
 	printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n"
-	       "          [-b memory] [-v vcpus]\n", name);
+	       "          [-b memory] [-v vcpus] [-o]\n", name);
 	guest_modes_help();
 	printf(" -u: use User Fault FD to handle vCPU page\n"
 	       "     faults.\n");
@@ -387,19 +398,23 @@ static void help(char *name)
 	       "     demand paged by each vCPU. e.g. 10M or 3G.\n"
 	       "     Default: 1G\n");
 	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");
 	puts("");
 	exit(0);
 }
 
 int main(int argc, char *argv[])
 {
 	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
-	struct test_params p = {};
+	struct test_params p = {
+		.partition_vcpu_memory_access = true,
+	};
 	int opt;
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:ud:b:v:")) != -1) {
+	while ((opt = getopt(argc, argv, "hm:ud:b:v:o")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
@@ -419,6 +434,9 @@ int main(int argc, char *argv[])
 			TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
 				    "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
 			break;
+		case 'o':
+			p.partition_vcpu_memory_access = false;
+			break;
 		case 'h':
 		default:
 			help(argv[0]);

tools/testing/selftests/kvm/dirty_log_perf_test.c

@@ -92,6 +92,7 @@ struct test_params {
 	unsigned long iterations;
 	uint64_t phys_offset;
 	int wr_fract;
+	bool partition_vcpu_memory_access;
 };
 
 static void run_test(enum vm_guest_mode mode, void *arg)
@@ -129,7 +130,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
+			      p->partition_vcpu_memory_access);
 
 	sync_global_to_guest(vm, perf_test_args);
 
@@ -240,7 +242,7 @@ static void help(char *name)
 {
 	puts("");
 	printf("usage: %s [-h] [-i iterations] [-p offset] "
-	       "[-m mode] [-b vcpu bytes] [-v vcpus]\n", name);
+	       "[-m mode] [-b vcpu bytes] [-v vcpus] [-o]\n", name);
 	puts("");
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
 	       TEST_HOST_LOOP_N);
@@ -255,6 +257,8 @@ static void help(char *name)
 	       "     1/<fraction of pages to write>.\n"
 	       "     (default: 1 i.e. all pages are written to.)\n");
 	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");
 	puts("");
 	exit(0);
 }
@@ -265,6 +269,7 @@ int main(int argc, char *argv[])
 	struct test_params p = {
 		.iterations = TEST_HOST_LOOP_N,
 		.wr_fract = 1,
+		.partition_vcpu_memory_access = true,
 	};
 	int opt;
 
@@ -275,7 +280,7 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) {
+	while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:o")) != -1) {
 		switch (opt) {
 		case 'i':
 			p.iterations = atoi(optarg);
@@ -299,6 +304,9 @@ int main(int argc, char *argv[])
 			TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
 				    "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
 			break;
+		case 'o':
+			p.partition_vcpu_memory_access = false;
+			break;
 		case 'h':
 		default:
 			help(argv[0]);

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

@@ -46,6 +46,8 @@ extern uint64_t guest_test_phys_mem;
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				uint64_t vcpu_memory_bytes);
 void perf_test_destroy_vm(struct kvm_vm *vm);
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes);
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
+			   uint64_t vcpu_memory_bytes,
+			   bool partition_vcpu_memory_access);
 
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */

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

@@ -112,7 +112,9 @@ void perf_test_destroy_vm(struct kvm_vm *vm)
 	kvm_vm_free(vm);
 }
 
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes)
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
+			   uint64_t vcpu_memory_bytes,
+			   bool partition_vcpu_memory_access)
 {
 	vm_paddr_t vcpu_gpa;
 	struct perf_test_vcpu_args *vcpu_args;
@@ -122,13 +124,22 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_by
 		vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
 
 		vcpu_args->vcpu_id = vcpu_id;
-		vcpu_args->gva = guest_test_virt_mem +
-				 (vcpu_id * vcpu_memory_bytes);
-		vcpu_args->pages = vcpu_memory_bytes /
-				   perf_test_args.guest_page_size;
+		if (partition_vcpu_memory_access) {
+			vcpu_args->gva = guest_test_virt_mem +
+					 (vcpu_id * vcpu_memory_bytes);
+			vcpu_args->pages = vcpu_memory_bytes /
+					   perf_test_args.guest_page_size;
+			vcpu_gpa = guest_test_phys_mem +
+				   (vcpu_id * vcpu_memory_bytes);
+		} else {
+			vcpu_args->gva = guest_test_virt_mem;
+			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
+					   perf_test_args.guest_page_size;
+			vcpu_gpa = guest_test_phys_mem;
+		}
 
-		vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
 		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-			 vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+			 vcpu_id, vcpu_gpa, vcpu_gpa +
+			 (vcpu_args->pages * perf_test_args.guest_page_size));
 	}
 }