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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - Page ownership tracking between host EL1 and EL2
   - Rely on userspace page tables to create large stage-2 mappings
   - Fix incompatibility between pKVM and kmemleak
   - Fix the PMU reset state, and improve the performance of the virtual
     PMU
   - Move over to the generic KVM entry code
   - Address PSCI reset issues w.r.t. save/restore
   - Preliminary rework for the upcoming pKVM fixed feature
   - A bunch of MM cleanups
   - a vGIC fix for timer spurious interrupts
   - Various cleanups

  s390:
   - enable interpretation of specification exceptions
   - fix a vcpu_idx vs vcpu_id mixup

  x86:
   - fast (lockless) page fault support for the new MMU
   - new MMU now the default
   - increased maximum allowed VCPU count
   - allow inhibit IRQs on KVM_RUN while debugging guests
   - let Hyper-V-enabled guests run with virtualized LAPIC as long as
     they do not enable the Hyper-V "AutoEOI" feature
   - fixes and optimizations for the toggling of AMD AVIC (virtualized
     LAPIC)
   - tuning for the case when two-dimensional paging (EPT/NPT) is
     disabled
   - bugfixes and cleanups, especially with respect to vCPU reset and
     choosing a paging mode based on CR0/CR4/EFER
   - support for 5-level page table on AMD processors

  Generic:
   - MMU notifier invalidation callbacks do not take mmu_lock unless
     necessary
   - improved caching of LRU kvm_memory_slot
   - support for histogram statistics
   - add statistics for halt polling and remote TLB flush requests"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (210 commits)
  KVM: Drop unused kvm_dirty_gfn_invalid()
  KVM: x86: Update vCPU's hv_clock before back to guest when tsc_offset is adjusted
  KVM: MMU: mark role_regs and role accessors as maybe unused
  KVM: MIPS: Remove a "set but not used" variable
  x86/kvm: Don't enable IRQ when IRQ enabled in kvm_wait
  KVM: stats: Add VM stat for remote tlb flush requests
  KVM: Remove unnecessary export of kvm_{inc,dec}_notifier_count()
  KVM: x86/mmu: Move lpage_disallowed_link further "down" in kvm_mmu_page
  KVM: x86/mmu: Relocate kvm_mmu_page.tdp_mmu_page for better cache locality
  Revert "KVM: x86: mmu: Add guest physical address check in translate_gpa()"
  KVM: x86/mmu: Remove unused field mmio_cached in struct kvm_mmu_page
  kvm: x86: Increase KVM_SOFT_MAX_VCPUS to 710
  kvm: x86: Increase MAX_VCPUS to 1024
  kvm: x86: Set KVM_MAX_VCPU_ID to 4*KVM_MAX_VCPUS
  KVM: VMX: avoid running vmx_handle_exit_irqoff in case of emulation
  KVM: x86/mmu: Don't freak out if pml5_root is NULL on 4-level host
  KVM: s390: index kvm->arch.idle_mask by vcpu_idx
  KVM: s390: Enable specification exception interpretation
  KVM: arm64: Trim guest debug exception handling
  KVM: SVM: Add 5-level page table support for SVM
  ...

12 files changed, 245 insertions, 28 deletions

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 0709af0144c8..98053d3afbda 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 /aarch64/debug-exceptions
 /aarch64/get-reg-list
+/aarch64/psci_cpu_on_test
 /aarch64/vgic_init
 /s390x/memop
 /s390x/resets
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 5832f510a16c..5d05801ab816 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -86,6 +86,7 @@ TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test
 
 TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
+TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
diff --git a/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c b/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c
new file mode 100644
index 000000000000..018c269990e1
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * psci_cpu_on_test - Test that the observable state of a vCPU targeted by the
+ * CPU_ON PSCI call matches what the caller requested.
+ *
+ * Copyright (c) 2021 Google LLC.
+ *
+ * This is a regression test for a race between KVM servicing the PSCI call and
+ * userspace reading the vCPUs registers.
+ */
+
+#define _GNU_SOURCE
+
+#include <linux/psci.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+#define VCPU_ID_SOURCE 0
+#define VCPU_ID_TARGET 1
+
+#define CPU_ON_ENTRY_ADDR 0xfeedf00dul
+#define CPU_ON_CONTEXT_ID 0xdeadc0deul
+
+static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr,
+			    uint64_t context_id)
+{
+	register uint64_t x0 asm("x0") = PSCI_0_2_FN64_CPU_ON;
+	register uint64_t x1 asm("x1") = target_cpu;
+	register uint64_t x2 asm("x2") = entry_addr;
+	register uint64_t x3 asm("x3") = context_id;
+
+	asm("hvc #0"
+	    : "=r"(x0)
+	    : "r"(x0), "r"(x1), "r"(x2), "r"(x3)
+	    : "memory");
+
+	return x0;
+}
+
+static uint64_t psci_affinity_info(uint64_t target_affinity,
+				   uint64_t lowest_affinity_level)
+{
+	register uint64_t x0 asm("x0") = PSCI_0_2_FN64_AFFINITY_INFO;
+	register uint64_t x1 asm("x1") = target_affinity;
+	register uint64_t x2 asm("x2") = lowest_affinity_level;
+
+	asm("hvc #0"
+	    : "=r"(x0)
+	    : "r"(x0), "r"(x1), "r"(x2)
+	    : "memory");
+
+	return x0;
+}
+
+static void guest_main(uint64_t target_cpu)
+{
+	GUEST_ASSERT(!psci_cpu_on(target_cpu, CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID));
+	uint64_t target_state;
+
+	do {
+		target_state = psci_affinity_info(target_cpu, 0);
+
+		GUEST_ASSERT((target_state == PSCI_0_2_AFFINITY_LEVEL_ON) ||
+			     (target_state == PSCI_0_2_AFFINITY_LEVEL_OFF));
+	} while (target_state != PSCI_0_2_AFFINITY_LEVEL_ON);
+
+	GUEST_DONE();
+}
+
+int main(void)
+{
+	uint64_t target_mpidr, obs_pc, obs_x0;
+	struct kvm_vcpu_init init;
+	struct kvm_vm *vm;
+	struct ucall uc;
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+	kvm_vm_elf_load(vm, program_invocation_name);
+	ucall_init(vm, NULL);
+
+	vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init);
+	init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2);
+
+	aarch64_vcpu_add_default(vm, VCPU_ID_SOURCE, &init, guest_main);
+
+	/*
+	 * make sure the target is already off when executing the test.
+	 */
+	init.features[0] |= (1 << KVM_ARM_VCPU_POWER_OFF);
+	aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_main);
+
+	get_reg(vm, VCPU_ID_TARGET, ARM64_SYS_REG(MPIDR_EL1), &target_mpidr);
+	vcpu_args_set(vm, VCPU_ID_SOURCE, 1, target_mpidr & MPIDR_HWID_BITMASK);
+	vcpu_run(vm, VCPU_ID_SOURCE);
+
+	switch (get_ucall(vm, VCPU_ID_SOURCE, &uc)) {
+	case UCALL_DONE:
+		break;
+	case UCALL_ABORT:
+		TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__,
+			  uc.args[1]);
+		break;
+	default:
+		TEST_FAIL("Unhandled ucall: %lu", uc.cmd);
+	}
+
+	get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.pc), &obs_pc);
+	get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.regs[0]), &obs_x0);
+
+	TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR,
+		    "unexpected target cpu pc: %lx (expected: %lx)",
+		    obs_pc, CPU_ON_ENTRY_ADDR);
+	TEST_ASSERT(obs_x0 == CPU_ON_CONTEXT_ID,
+		    "unexpected target context id: %lx (expected: %lx)",
+		    obs_x0, CPU_ON_CONTEXT_ID);
+
+	kvm_vm_free(vm);
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index e2baa187a21e..71e277c7c3f3 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -222,8 +222,6 @@ static void *vcpu_thread_main(void *arg)
 	int vcpu_id = vcpu_args->vcpu_id;
 	int current_iteration = -1;
 
-	vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
-
 	while (spin_wait_for_next_iteration(&current_iteration)) {
 		switch (READ_ONCE(iteration_work)) {
 		case ITERATION_ACCESS_MEMORY:
@@ -333,7 +331,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	pthread_t *vcpu_threads;
 	int vcpus = params->vcpus;
 
-	vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes,
+	vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1,
 				 params->backing_src);
 
 	perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes,
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index b74704305835..e79c1b64977f 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -52,7 +52,6 @@ static void *vcpu_worker(void *data)
 	struct timespec start;
 	struct timespec ts_diff;
 
-	vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
 	run = vcpu_state(vm, vcpu_id);
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
@@ -293,7 +292,7 @@ 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, 1,
 				 p->src_type);
 
 	perf_test_args.wr_fract = 1;
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 80cbd3a748c0..3c30d0045d8d 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -44,7 +44,6 @@ static void *vcpu_worker(void *data)
 	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 
-	vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
 	run = vcpu_state(vm, vcpu_id);
 
 	while (!READ_ONCE(host_quit)) {
@@ -94,8 +93,59 @@ struct test_params {
 	int wr_fract;
 	bool partition_vcpu_memory_access;
 	enum vm_mem_backing_src_type backing_src;
+	int slots;
 };
 
+static void toggle_dirty_logging(struct kvm_vm *vm, int slots, bool enable)
+{
+	int i;
+
+	for (i = 0; i < slots; i++) {
+		int slot = PERF_TEST_MEM_SLOT_INDEX + i;
+		int flags = enable ? KVM_MEM_LOG_DIRTY_PAGES : 0;
+
+		vm_mem_region_set_flags(vm, slot, flags);
+	}
+}
+
+static inline void enable_dirty_logging(struct kvm_vm *vm, int slots)
+{
+	toggle_dirty_logging(vm, slots, true);
+}
+
+static inline void disable_dirty_logging(struct kvm_vm *vm, int slots)
+{
+	toggle_dirty_logging(vm, slots, false);
+}
+
+static void get_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap,
+			  uint64_t nr_pages)
+{
+	uint64_t slot_pages = nr_pages / slots;
+	int i;
+
+	for (i = 0; i < slots; i++) {
+		int slot = PERF_TEST_MEM_SLOT_INDEX + i;
+		unsigned long *slot_bitmap = bitmap + i * slot_pages;
+
+		kvm_vm_get_dirty_log(vm, slot, slot_bitmap);
+	}
+}
+
+static void clear_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap,
+			    uint64_t nr_pages)
+{
+	uint64_t slot_pages = nr_pages / slots;
+	int i;
+
+	for (i = 0; i < slots; i++) {
+		int slot = PERF_TEST_MEM_SLOT_INDEX + i;
+		unsigned long *slot_bitmap = bitmap + i * slot_pages;
+
+		kvm_vm_clear_dirty_log(vm, slot, slot_bitmap, 0, slot_pages);
+	}
+}
+
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
@@ -114,7 +164,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct timespec clear_dirty_log_total = (struct timespec){0};
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
-				 p->backing_src);
+				 p->slots, p->backing_src);
 
 	perf_test_args.wr_fract = p->wr_fract;
 
@@ -163,8 +213,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	/* Enable dirty logging */
 	clock_gettime(CLOCK_MONOTONIC, &start);
-	vm_mem_region_set_flags(vm, PERF_TEST_MEM_SLOT_INDEX,
-				KVM_MEM_LOG_DIRTY_PAGES);
+	enable_dirty_logging(vm, p->slots);
 	ts_diff = timespec_elapsed(start);
 	pr_info("Enabling dirty logging time: %ld.%.9lds\n\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
@@ -190,8 +239,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 			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);
-
+		get_dirty_log(vm, p->slots, bmap, host_num_pages);
 		ts_diff = timespec_elapsed(start);
 		get_dirty_log_total = timespec_add(get_dirty_log_total,
 						   ts_diff);
@@ -200,9 +248,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 		if (dirty_log_manual_caps) {
 			clock_gettime(CLOCK_MONOTONIC, &start);
-			kvm_vm_clear_dirty_log(vm, PERF_TEST_MEM_SLOT_INDEX, bmap, 0,
-					       host_num_pages);
-
+			clear_dirty_log(vm, p->slots, bmap, host_num_pages);
 			ts_diff = timespec_elapsed(start);
 			clear_dirty_log_total = timespec_add(clear_dirty_log_total,
 							     ts_diff);
@@ -213,7 +259,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	/* Disable dirty logging */
 	clock_gettime(CLOCK_MONOTONIC, &start);
-	vm_mem_region_set_flags(vm, PERF_TEST_MEM_SLOT_INDEX, 0);
+	disable_dirty_logging(vm, p->slots);
 	ts_diff = timespec_elapsed(start);
 	pr_info("Disabling dirty logging time: %ld.%.9lds\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
@@ -244,7 +290,8 @@ static void help(char *name)
 {
 	puts("");
 	printf("usage: %s [-h] [-i iterations] [-p offset] "
-	       "[-m mode] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]\n", name);
+	       "[-m mode] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]"
+	       "[-x memslots]\n", name);
 	puts("");
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
 	       TEST_HOST_LOOP_N);
@@ -263,6 +310,8 @@ static void help(char *name)
 	       "     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");
+	printf(" -x: Split the memory region into this number of memslots.\n"
+	       "     (default: 1)");
 	backing_src_help();
 	puts("");
 	exit(0);
@@ -276,6 +325,7 @@ int main(int argc, char *argv[])
 		.wr_fract = 1,
 		.partition_vcpu_memory_access = true,
 		.backing_src = VM_MEM_SRC_ANONYMOUS,
+		.slots = 1,
 	};
 	int opt;
 
@@ -286,7 +336,7 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:os:")) != -1) {
+	while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:os:x:")) != -1) {
 		switch (opt) {
 		case 'i':
 			p.iterations = atoi(optarg);
@@ -316,6 +366,9 @@ int main(int argc, char *argv[])
 		case 's':
 			p.backing_src = parse_backing_src_type(optarg);
 			break;
+		case 'x':
+			p.slots = atoi(optarg);
+			break;
 		case 'h':
 		default:
 			help(argv[0]);
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index 27dc5c2e56b9..c0273aefa63d 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -17,6 +17,7 @@
 #define CPACR_EL1               3, 0,  1, 0, 2
 #define TCR_EL1                 3, 0,  2, 0, 2
 #define MAIR_EL1                3, 0, 10, 2, 0
+#define MPIDR_EL1               3, 0,  0, 0, 5
 #define TTBR0_EL1               3, 0,  2, 0, 0
 #define SCTLR_EL1               3, 0,  1, 0, 0
 #define VBAR_EL1                3, 0, 12, 0, 0
@@ -40,6 +41,8 @@
 			  (0xfful << (4 * 8)) | \
 			  (0xbbul << (5 * 8)))
 
+#define MPIDR_HWID_BITMASK (0xff00fffffful)
+
 static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t *addr)
 {
 	struct kvm_one_reg reg;
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index 005f2143adeb..df9f1a3a3ffb 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -44,7 +44,7 @@ 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, int slots,
 				   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,
diff --git a/tools/testing/selftests/kvm/kvm_binary_stats_test.c b/tools/testing/selftests/kvm/kvm_binary_stats_test.c
index 5906bbc08483..17f65d514915 100644
--- a/tools/testing/selftests/kvm/kvm_binary_stats_test.c
+++ b/tools/testing/selftests/kvm/kvm_binary_stats_test.c
@@ -109,6 +109,18 @@ static void stats_test(int stats_fd)
 		/* Check size field, which should not be zero */
 		TEST_ASSERT(pdesc->size, "KVM descriptor(%s) with size of 0",
 				pdesc->name);
+		/* Check bucket_size field */
+		switch (pdesc->flags & KVM_STATS_TYPE_MASK) {
+		case KVM_STATS_TYPE_LINEAR_HIST:
+			TEST_ASSERT(pdesc->bucket_size,
+			    "Bucket size of Linear Histogram stats (%s) is zero",
+			    pdesc->name);
+			break;
+		default:
+			TEST_ASSERT(!pdesc->bucket_size,
+			    "Bucket size of stats (%s) is not zero",
+			    pdesc->name);
+		}
 		size_data += pdesc->size * sizeof(*stats_data);
 	}
 	/* Check overlap */
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index b488f4aefea8..0ef80dbdc116 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -50,11 +50,12 @@ static void guest_code(uint32_t vcpu_id)
 }
 
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
-				   uint64_t vcpu_memory_bytes,
+				   uint64_t vcpu_memory_bytes, int slots,
 				   enum vm_mem_backing_src_type backing_src)
 {
 	struct kvm_vm *vm;
 	uint64_t guest_num_pages;
+	int i;
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
@@ -68,6 +69,9 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    "Guest memory size is not host page size aligned.");
 	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
 		    "Guest memory size is not guest page size aligned.");
+	TEST_ASSERT(guest_num_pages % slots == 0,
+		    "Guest memory cannot be evenly divided into %d slots.",
+		    slots);
 
 	vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
 				  (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size,
@@ -95,10 +99,16 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 #endif
 	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
 
-	/* Add an extra memory slot for testing */
-	vm_userspace_mem_region_add(vm, backing_src, guest_test_phys_mem,
-				    PERF_TEST_MEM_SLOT_INDEX,
-				    guest_num_pages, 0);
+	/* Add extra memory slots for testing */
+	for (i = 0; i < slots; i++) {
+		uint64_t region_pages = guest_num_pages / slots;
+		vm_paddr_t region_start = guest_test_phys_mem +
+			region_pages * perf_test_args.guest_page_size * i;
+
+		vm_userspace_mem_region_add(vm, backing_src, region_start,
+					    PERF_TEST_MEM_SLOT_INDEX + i,
+					    region_pages, 0);
+	}
 
 	/* Do mapping for the demand paging memory slot */
 	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages);
@@ -140,6 +150,8 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
 			vcpu_gpa = guest_test_phys_mem;
 		}
 
+		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+
 		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
 			 vcpu_id, vcpu_gpa, vcpu_gpa +
 			 (vcpu_args->pages * perf_test_args.guest_page_size));
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 98351ba0933c..4cfcafea9f5a 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -45,7 +45,6 @@ static void *vcpu_worker(void *data)
 	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
 
-	vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
 	run = vcpu_state(vm, vcpu_id);
 
 	/* Let the guest access its memory until a stop signal is received */
@@ -105,7 +104,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct kvm_vm *vm;
 	int vcpu_id;
 
-	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
+	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
 				 VM_MEM_SRC_ANONYMOUS);
 
 	perf_test_args.wr_fract = 1;
diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c
index 6097a8283377..5f078db1bcba 100644
--- a/tools/testing/selftests/kvm/x86_64/debug_regs.c
+++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c
@@ -8,12 +8,15 @@
 #include <string.h>
 #include "kvm_util.h"
 #include "processor.h"
+#include "apic.h"
 
 #define VCPU_ID 0
 
 #define DR6_BD		(1 << 13)
 #define DR7_GD		(1 << 13)
 
+#define IRQ_VECTOR 0xAA
+
 /* For testing data access debug BP */
 uint32_t guest_value;
 
@@ -21,6 +24,11 @@ extern unsigned char sw_bp, hw_bp, write_data, ss_start, bd_start;
 
 static void guest_code(void)
 {
+	/* Create a pending interrupt on current vCPU */
+	x2apic_enable();
+	x2apic_write_reg(APIC_ICR, APIC_DEST_SELF | APIC_INT_ASSERT |
+			 APIC_DM_FIXED | IRQ_VECTOR);
+
 	/*
 	 * Software BP tests.
 	 *
@@ -38,12 +46,19 @@ static void guest_code(void)
 		     "mov %%rax,%0;\n\t write_data:"
 		     : "=m" (guest_value) : : "rax");
 
-	/* Single step test, covers 2 basic instructions and 2 emulated */
+	/*
+	 * Single step test, covers 2 basic instructions and 2 emulated
+	 *
+	 * Enable interrupts during the single stepping to see that
+	 * pending interrupt we raised is not handled due to KVM_GUESTDBG_BLOCKIRQ
+	 */
 	asm volatile("ss_start: "
+		     "sti\n\t"
 		     "xor %%eax,%%eax\n\t"
 		     "cpuid\n\t"
 		     "movl $0x1a0,%%ecx\n\t"
 		     "rdmsr\n\t"
+		     "cli\n\t"
 		     : : : "eax", "ebx", "ecx", "edx");
 
 	/* DR6.BD test */
@@ -72,11 +87,13 @@ int main(void)
 	uint64_t cmd;
 	int i;
 	/* Instruction lengths starting at ss_start */
-	int ss_size[4] = {
+	int ss_size[6] = {
+		1,		/* sti*/
 		2,		/* xor */
 		2,		/* cpuid */
 		5,		/* mov */
 		2,		/* rdmsr */
+		1,		/* cli */
 	};
 
 	if (!kvm_check_cap(KVM_CAP_SET_GUEST_DEBUG)) {
@@ -154,7 +171,8 @@ int main(void)
 	for (i = 0; i < (sizeof(ss_size) / sizeof(ss_size[0])); i++) {
 		target_rip += ss_size[i];
 		CLEAR_DEBUG();
-		debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP;
+		debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP |
+				KVM_GUESTDBG_BLOCKIRQ;
 		debug.arch.debugreg[7] = 0x00000400;
 		APPLY_DEBUG();
 		vcpu_run(vm, VCPU_ID);