Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "x86:

   - Support for userspace to emulate Xen hypercalls

   - Raise the maximum number of user memslots

   - Scalability improvements for the new MMU.

     Instead of the complex "fast page fault" logic that is used in
     mmu.c, tdp_mmu.c uses an rwlock so that page faults are concurrent,
     but the code that can run against page faults is limited. Right now
     only page faults take the lock for reading; in the future this will
     be extended to some cases of page table destruction. I hope to
     switch the default MMU around 5.12-rc3 (some testing was delayed
     due to Chinese New Year).

   - Cleanups for MAXPHYADDR checks

   - Use static calls for vendor-specific callbacks

   - On AMD, use VMLOAD/VMSAVE to save and restore host state

   - Stop using deprecated jump label APIs

   - Workaround for AMD erratum that made nested virtualization
     unreliable

   - Support for LBR emulation in the guest

   - Support for communicating bus lock vmexits to userspace

   - Add support for SEV attestation command

   - Miscellaneous cleanups

  PPC:

   - Support for second data watchpoint on POWER10

   - Remove some complex workarounds for buggy early versions of POWER9

   - Guest entry/exit fixes

  ARM64:

   - Make the nVHE EL2 object relocatable

   - Cleanups for concurrent translation faults hitting the same page

   - Support for the standard TRNG hypervisor call

   - A bunch of small PMU/Debug fixes

   - Simplification of the early init hypercall handling

  Non-KVM changes (with acks):

   - Detection of contended rwlocks (implemented only for qrwlocks,
     because KVM only needs it for x86)

   - Allow __DISABLE_EXPORTS from assembly code

   - Provide a saner follow_pfn replacements for modules"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (192 commits)
  KVM: x86/xen: Explicitly pad struct compat_vcpu_info to 64 bytes
  KVM: selftests: Don't bother mapping GVA for Xen shinfo test
  KVM: selftests: Fix hex vs. decimal snafu in Xen test
  KVM: selftests: Fix size of memslots created by Xen tests
  KVM: selftests: Ignore recently added Xen tests' build output
  KVM: selftests: Add missing header file needed by xAPIC IPI tests
  KVM: selftests: Add operand to vmsave/vmload/vmrun in svm.c
  KVM: SVM: Make symbol 'svm_gp_erratum_intercept' static
  locking/arch: Move qrwlock.h include after qspinlock.h
  KVM: PPC: Book3S HV: Fix host radix SLB optimisation with hash guests
  KVM: PPC: Book3S HV: Ensure radix guest has no SLB entries
  KVM: PPC: Don't always report hash MMU capability for P9 < DD2.2
  KVM: PPC: Book3S HV: Save and restore FSCR in the P9 path
  KVM: PPC: remove unneeded semicolon
  KVM: PPC: Book3S HV: Use POWER9 SLBIA IH=6 variant to clear SLB
  KVM: PPC: Book3S HV: No need to clear radix host SLB before loading HPT guest
  KVM: PPC: Book3S HV: Fix radix guest SLB side channel
  KVM: PPC: Book3S HV: Remove support for running HPT guest on RPT host without mixed mode support
  KVM: PPC: Book3S HV: Introduce new capability for 2nd DAWR
  KVM: PPC: Book3S HV: Add infrastructure to support 2nd DAWR
  ...

25 files changed, 1801 insertions, 102 deletions

diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index c3af3f324c5a..9f18fa090f1f 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -644,6 +644,8 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_MMCR3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc1)
 #define KVM_REG_PPC_SIER2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc2)
 #define KVM_REG_PPC_SIER3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3)
+#define KVM_REG_PPC_DAWR1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc4)
+#define KVM_REG_PPC_DAWRX1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc5)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 374c67875cdb..abb89bbe5635 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1058,6 +1058,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
 #define KVM_CAP_SYS_HYPERV_CPUID 191
 #define KVM_CAP_DIRTY_LOG_RING 192
+#define KVM_CAP_PPC_DAWR1 194
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index ce8f4ad39684..3a84394829ea 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -7,6 +7,7 @@
 /x86_64/cr4_cpuid_sync_test
 /x86_64/debug_regs
 /x86_64/evmcs_test
+/x86_64/get_cpuid_test
 /x86_64/kvm_pv_test
 /x86_64/hyperv_cpuid
 /x86_64/mmio_warning_test
@@ -24,10 +25,15 @@
 /x86_64/vmx_preemption_timer_test
 /x86_64/vmx_set_nested_state_test
 /x86_64/vmx_tsc_adjust_test
+/x86_64/xapic_ipi_test
+/x86_64/xen_shinfo_test
+/x86_64/xen_vmcall_test
 /x86_64/xss_msr_test
+/x86_64/vmx_pmu_msrs_test
 /demand_paging_test
 /dirty_log_test
 /dirty_log_perf_test
 /kvm_create_max_vcpus
+/memslot_modification_stress_test
 /set_memory_region_test
 /steal_time
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index fe41c6a0fa67..8c8eda429576 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -40,6 +40,7 @@ LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_ha
 
 TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
+TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
 TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
 TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
@@ -56,13 +57,18 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
+TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test
 TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
 TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
 TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test
+TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test
+TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
+TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test
 TEST_GEN_PROGS_x86_64 += set_memory_region_test
 TEST_GEN_PROGS_x86_64 += steal_time
 
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index cdad1eca72f7..5f7a229c3af1 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -64,7 +64,7 @@ static void *vcpu_worker(void *data)
 			    exit_reason_str(run->exit_reason));
 	}
 
-	ts_diff = timespec_diff_now(start);
+	ts_diff = timespec_elapsed(start);
 	PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
 		       ts_diff.tv_sec, ts_diff.tv_nsec);
 
@@ -95,7 +95,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr)
 		return r;
 	}
 
-	ts_diff = timespec_diff_now(start);
+	ts_diff = timespec_elapsed(start);
 
 	PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid,
 		       timespec_to_ns(ts_diff));
@@ -190,7 +190,7 @@ static void *uffd_handler_thread_fn(void *arg)
 		pages++;
 	}
 
-	ts_diff = timespec_diff_now(start);
+	ts_diff = timespec_elapsed(start);
 	PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
 		       pages, ts_diff.tv_sec, ts_diff.tv_nsec,
 		       pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
@@ -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)
@@ -265,7 +266,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	int vcpu_id;
 	int r;
 
-	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size);
+	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
+				 VM_MEM_SRC_ANONYMOUS);
 
 	perf_test_args.wr_fract = 1;
 
@@ -277,7 +279,8 @@ 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 +296,19 @@ 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 +325,7 @@ 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);
 		}
@@ -339,7 +351,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
 	}
 
-	ts_diff = timespec_diff_now(start);
+	ts_diff = timespec_elapsed(start);
 
 	pr_info("All vCPU threads joined\n");
 
@@ -376,7 +388,7 @@ 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");
@@ -387,6 +399,8 @@ 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);
 }
@@ -394,12 +408,14 @@ static void help(char *name)
 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 +435,9 @@ 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]);
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 2283a0ec74a9..04a2641261be 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -28,8 +28,8 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 /* Host variables */
 static u64 dirty_log_manual_caps;
 static bool host_quit;
-static uint64_t iteration;
-static uint64_t vcpu_last_completed_iteration[KVM_MAX_VCPUS];
+static int iteration;
+static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
 
 static void *vcpu_worker(void *data)
 {
@@ -48,11 +48,11 @@ static void *vcpu_worker(void *data)
 	run = vcpu_state(vm, vcpu_id);
 
 	while (!READ_ONCE(host_quit)) {
-		uint64_t current_iteration = READ_ONCE(iteration);
+		int current_iteration = READ_ONCE(iteration);
 
 		clock_gettime(CLOCK_MONOTONIC, &start);
 		ret = _vcpu_run(vm, vcpu_id);
-		ts_diff = timespec_diff_now(start);
+		ts_diff = timespec_elapsed(start);
 
 		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
 		TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC,
@@ -61,17 +61,17 @@ static void *vcpu_worker(void *data)
 
 		pr_debug("Got sync event from vCPU %d\n", vcpu_id);
 		vcpu_last_completed_iteration[vcpu_id] = current_iteration;
-		pr_debug("vCPU %d updated last completed iteration to %lu\n",
+		pr_debug("vCPU %d updated last completed iteration to %d\n",
 			 vcpu_id, vcpu_last_completed_iteration[vcpu_id]);
 
 		if (current_iteration) {
 			pages_count += vcpu_args->pages;
 			total = timespec_add(total, ts_diff);
-			pr_debug("vCPU %d iteration %lu dirty memory time: %ld.%.9lds\n",
+			pr_debug("vCPU %d iteration %d dirty memory time: %ld.%.9lds\n",
 				vcpu_id, current_iteration, ts_diff.tv_sec,
 				ts_diff.tv_nsec);
 		} else {
-			pr_debug("vCPU %d iteration %lu populate memory time: %ld.%.9lds\n",
+			pr_debug("vCPU %d iteration %d populate memory time: %ld.%.9lds\n",
 				vcpu_id, current_iteration, ts_diff.tv_sec,
 				ts_diff.tv_nsec);
 		}
@@ -81,7 +81,7 @@ static void *vcpu_worker(void *data)
 	}
 
 	avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_id]);
-	pr_debug("\nvCPU %d dirtied 0x%lx pages over %lu iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+	pr_debug("\nvCPU %d dirtied 0x%lx pages over %d iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
 		vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id],
 		total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec);
 
@@ -92,6 +92,8 @@ struct test_params {
 	unsigned long iterations;
 	uint64_t phys_offset;
 	int wr_fract;
+	bool partition_vcpu_memory_access;
+	enum vm_mem_backing_src_type backing_src;
 };
 
 static void run_test(enum vm_guest_mode mode, void *arg)
@@ -111,7 +113,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct kvm_enable_cap cap = {};
 	struct timespec clear_dirty_log_total = (struct timespec){0};
 
-	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size);
+	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
+				 p->backing_src);
 
 	perf_test_args.wr_fract = p->wr_fract;
 
@@ -129,7 +132,8 @@ 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);
 
@@ -139,17 +143,21 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
 	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+		vcpu_last_completed_iteration[vcpu_id] = -1;
+
 		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
 			       &perf_test_args.vcpu_args[vcpu_id]);
 	}
 
-	/* Allow the vCPU to populate memory */
-	pr_debug("Starting iteration %lu - Populating\n", iteration);
-	while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration)
-		pr_debug("Waiting for vcpu_last_completed_iteration == %lu\n",
-			iteration);
+	/* Allow the vCPUs to populate memory */
+	pr_debug("Starting iteration %d - Populating\n", iteration);
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+		while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) !=
+		       iteration)
+			;
+	}
 
-	ts_diff = timespec_diff_now(start);
+	ts_diff = timespec_elapsed(start);
 	pr_info("Populate memory time: %ld.%.9lds\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
 
@@ -157,7 +165,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	clock_gettime(CLOCK_MONOTONIC, &start);
 	vm_mem_region_set_flags(vm, PERF_TEST_MEM_SLOT_INDEX,
 				KVM_MEM_LOG_DIRTY_PAGES);
-	ts_diff = timespec_diff_now(start);
+	ts_diff = timespec_elapsed(start);
 	pr_info("Enabling dirty logging time: %ld.%.9lds\n\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
 
@@ -169,25 +177,25 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		clock_gettime(CLOCK_MONOTONIC, &start);
 		iteration++;
 
-		pr_debug("Starting iteration %lu\n", iteration);
+		pr_debug("Starting iteration %d\n", iteration);
 		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-			while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration)
-				pr_debug("Waiting for vCPU %d vcpu_last_completed_iteration == %lu\n",
-					 vcpu_id, iteration);
+			while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id])
+			       != iteration)
+				;
 		}
 
-		ts_diff = timespec_diff_now(start);
+		ts_diff = timespec_elapsed(start);
 		vcpu_dirty_total = timespec_add(vcpu_dirty_total, ts_diff);
-		pr_info("Iteration %lu dirty memory time: %ld.%.9lds\n",
+		pr_info("Iteration %d dirty memory time: %ld.%.9lds\n",
 			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
 
 		clock_gettime(CLOCK_MONOTONIC, &start);
 		kvm_vm_get_dirty_log(vm, PERF_TEST_MEM_SLOT_INDEX, bmap);
 
-		ts_diff = timespec_diff_now(start);
+		ts_diff = timespec_elapsed(start);
 		get_dirty_log_total = timespec_add(get_dirty_log_total,
 						   ts_diff);
-		pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n",
+		pr_info("Iteration %d get dirty log time: %ld.%.9lds\n",
 			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
 
 		if (dirty_log_manual_caps) {
@@ -195,26 +203,26 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 			kvm_vm_clear_dirty_log(vm, PERF_TEST_MEM_SLOT_INDEX, bmap, 0,
 					       host_num_pages);
 
-			ts_diff = timespec_diff_now(start);
+			ts_diff = timespec_elapsed(start);
 			clear_dirty_log_total = timespec_add(clear_dirty_log_total,
 							     ts_diff);
-			pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n",
+			pr_info("Iteration %d clear dirty log time: %ld.%.9lds\n",
 				iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
 		}
 	}
 
-	/* Tell the vcpu thread to quit */
-	host_quit = true;
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_join(vcpu_threads[vcpu_id], NULL);
-
 	/* Disable dirty logging */
 	clock_gettime(CLOCK_MONOTONIC, &start);
 	vm_mem_region_set_flags(vm, PERF_TEST_MEM_SLOT_INDEX, 0);
-	ts_diff = timespec_diff_now(start);
+	ts_diff = timespec_elapsed(start);
 	pr_info("Disabling dirty logging time: %ld.%.9lds\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
 
+	/* Tell the vcpu thread to quit */
+	host_quit = true;
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
+		pthread_join(vcpu_threads[vcpu_id], NULL);
+
 	avg = timespec_div(get_dirty_log_total, p->iterations);
 	pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
 		p->iterations, get_dirty_log_total.tv_sec,
@@ -236,7 +244,7 @@ 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] [-s mem type]\n", name);
 	puts("");
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
 	       TEST_HOST_LOOP_N);
@@ -251,6 +259,11 @@ 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");
+	printf(" -s: specify the type of memory that should be used to\n"
+	       "     back the guest data region.\n\n");
+	backing_src_help();
 	puts("");
 	exit(0);
 }
@@ -261,6 +274,8 @@ int main(int argc, char *argv[])
 	struct test_params p = {
 		.iterations = TEST_HOST_LOOP_N,
 		.wr_fract = 1,
+		.partition_vcpu_memory_access = true,
+		.backing_src = VM_MEM_SRC_ANONYMOUS,
 	};
 	int opt;
 
@@ -271,10 +286,10 @@ 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:os:")) != -1) {
 		switch (opt) {
 		case 'i':
-			p.iterations = strtol(optarg, NULL, 10);
+			p.iterations = atoi(optarg);
 			break;
 		case 'p':
 			p.phys_offset = strtoull(optarg, NULL, 0);
@@ -295,6 +310,11 @@ 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;
+		case 's':
+			p.backing_src = parse_backing_src_type(optarg);
+			break;
 		case 'h':
 		default:
 			help(argv[0]);
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 5cbb861525ed..2d7eb6989e83 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -79,12 +79,6 @@ struct vm_guest_mode_params {
 };
 extern const struct vm_guest_mode_params vm_guest_mode_params[];
 
-enum vm_mem_backing_src_type {
-	VM_MEM_SRC_ANONYMOUS,
-	VM_MEM_SRC_ANONYMOUS_THP,
-	VM_MEM_SRC_ANONYMOUS_HUGETLB,
-};
-
 int kvm_check_cap(long cap);
 int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
 int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
diff --git a/tools/testing/selftests/kvm/include/numaif.h b/tools/testing/selftests/kvm/include/numaif.h
new file mode 100644
index 000000000000..b020547403fd
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/numaif.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/numaif.h
+ *
+ * Copyright (C) 2020, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Header file that provides access to NUMA API functions not explicitly
+ * exported to user space.
+ */
+
+#ifndef SELFTEST_KVM_NUMAIF_H
+#define SELFTEST_KVM_NUMAIF_H
+
+#define __NR_get_mempolicy 239
+#define __NR_migrate_pages 256
+
+/* System calls */
+long get_mempolicy(int *policy, const unsigned long *nmask,
+		   unsigned long maxnode, void *addr, int flags)
+{
+	return syscall(__NR_get_mempolicy, policy, nmask,
+		       maxnode, addr, flags);
+}
+
+long migrate_pages(int pid, unsigned long maxnode,
+		   const unsigned long *frommask,
+		   const unsigned long *tomask)
+{
+	return syscall(__NR_migrate_pages, pid, maxnode, frommask, tomask);
+}
+
+/* Policies */
+#define MPOL_DEFAULT	 0
+#define MPOL_PREFERRED	 1
+#define MPOL_BIND	 2
+#define MPOL_INTERLEAVE	 3
+
+#define MPOL_MAX MPOL_INTERLEAVE
+
+/* Flags for get_mem_policy */
+#define MPOL_F_NODE	    (1<<0)  /* return next il node or node of address */
+				    /* Warning: MPOL_F_NODE is unsupported and
+				     * subject to change. Don't use.
+				     */
+#define MPOL_F_ADDR	    (1<<1)  /* look up vma using address */
+#define MPOL_F_MEMS_ALLOWED (1<<2)  /* query nodes allowed in cpuset */
+
+/* Flags for mbind */
+#define MPOL_MF_STRICT	     (1<<0) /* Verify existing pages in the mapping */
+#define MPOL_MF_MOVE	     (1<<1) /* Move pages owned by this process to conform to mapping */
+#define MPOL_MF_MOVE_ALL     (1<<2) /* Move every page to conform to mapping */
+
+#endif /* SELFTEST_KVM_NUMAIF_H */
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index b1188823c31b..005f2143adeb 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -44,8 +44,11 @@ extern struct perf_test_args perf_test_args;
 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);
+				   uint64_t vcpu_memory_bytes,
+				   enum vm_mem_backing_src_type backing_src);
 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 */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index ffffa560436b..b7f41399f22c 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -64,7 +64,21 @@ int64_t timespec_to_ns(struct timespec ts);
 struct timespec timespec_add_ns(struct timespec ts, int64_t ns);
 struct timespec timespec_add(struct timespec ts1, struct timespec ts2);
 struct timespec timespec_sub(struct timespec ts1, struct timespec ts2);
-struct timespec timespec_diff_now(struct timespec start);
+struct timespec timespec_elapsed(struct timespec start);
 struct timespec timespec_div(struct timespec ts, int divisor);
 
+enum vm_mem_backing_src_type {
+	VM_MEM_SRC_ANONYMOUS,
+	VM_MEM_SRC_ANONYMOUS_THP,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB,
+};
+
+struct vm_mem_backing_src_alias {
+	const char *name;
+	enum vm_mem_backing_src_type type;
+};
+
+void backing_src_help(void);
+enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
+
 #endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 90cd5984751b..0b30b4e15c38 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -263,6 +263,19 @@ static inline void outl(uint16_t port, uint32_t value)
 	__asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value));
 }
 
+static inline void cpuid(uint32_t *eax, uint32_t *ebx,
+			 uint32_t *ecx, uint32_t *edx)
+{
+	/* ecx is often an input as well as an output. */
+	asm volatile("cpuid"
+	    : "=a" (*eax),
+	      "=b" (*ebx),
+	      "=c" (*ecx),
+	      "=d" (*edx)
+	    : "0" (*eax), "2" (*ecx)
+	    : "memory");
+}
+
 #define SET_XMM(__var, __xmm) \
 	asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
 
@@ -338,8 +351,10 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid,
 		     struct kvm_x86_state *state);
 
 struct kvm_msr_list *kvm_get_msr_index_list(void);
-
+uint64_t kvm_get_feature_msr(uint64_t msr_index);
 struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
+
+struct kvm_cpuid2 *vcpu_get_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
 		    struct kvm_cpuid2 *cpuid);
 
@@ -391,6 +406,10 @@ bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent);
 uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
 		       uint64_t a3);
 
+struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void);
+void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
+struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
+
 /*
  * Basic CPU control in CR0
  */
@@ -406,8 +425,27 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
 #define X86_CR0_CD          (1UL<<30) /* Cache Disable */
 #define X86_CR0_PG          (1UL<<31) /* Paging */
 
+#define APIC_DEFAULT_GPA		0xfee00000ULL
+
+/* APIC base address MSR and fields */
+#define MSR_IA32_APICBASE		0x0000001b
+#define MSR_IA32_APICBASE_BSP		(1<<8)
+#define MSR_IA32_APICBASE_EXTD		(1<<10)
+#define MSR_IA32_APICBASE_ENABLE	(1<<11)
+#define MSR_IA32_APICBASE_BASE		(0xfffff<<12)
+#define		GET_APIC_BASE(x)	(((x) >> 12) << 12)
+
 #define APIC_BASE_MSR	0x800
 #define X2APIC_ENABLE	(1UL << 10)
+#define	APIC_ID		0x20
+#define	APIC_LVR	0x30
+#define		GET_APIC_ID_FIELD(x)	(((x) >> 24) & 0xFF)
+#define	APIC_TASKPRI	0x80
+#define	APIC_PROCPRI	0xA0
+#define	APIC_EOI	0xB0
+#define	APIC_SPIV	0xF0
+#define		APIC_SPIV_FOCUS_DISABLED	(1 << 9)
+#define		APIC_SPIV_APIC_ENABLED		(1 << 8)
 #define	APIC_ICR	0x300
 #define		APIC_DEST_SELF		0x40000
 #define		APIC_DEST_ALLINC	0x80000
@@ -432,6 +470,7 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
 #define		APIC_DM_EXTINT		0x00700
 #define		APIC_VECTOR_MASK	0x000FF
 #define	APIC_ICR2	0x310
+#define		SET_APIC_DEST_FIELD(x)	((x) << 24)
 
 /* VMX_EPT_VPID_CAP bits */
 #define VMX_EPT_VPID_CAP_AD_BITS       (1ULL << 2