Merge tag 'kvm-x86-fixes-6.9-rcN' of https://github.com/kvm-x86/linux into HEAD

- Fix a mostly benign bug in the gfn_to_pfn_cache infrastructure where KVM
  would allow userspace to refresh the cache with a bogus GPA.  The bug has
  existed for quite some time, but was exposed by a new sanity check added in
  6.9 (to ensure a cache is either GPA-based or HVA-based).

- Drop an unused param from gfn_to_pfn_cache_invalidate_start() that got left
  behind during a 6.9 cleanup.

- Disable support for virtualizing adaptive PEBS, as KVM's implementation is
  architecturally broken and can leak host LBRs to the guest.

- Fix a bug where KVM neglects to set the enable bits for general purpose
  counters in PERF_GLOBAL_CTRL when initializing the virtual PMU.  Both Intel
  and AMD architectures require the bits to be set at RESET in order for v2
  PMUs to be backwards compatible with software that was written for v1 PMUs,
  i.e. for software that will never manually set the global enables.

- Disable LBR virtualization on CPUs that don't support LBR callstacks, as
  KVM unconditionally uses PERF_SAMPLE_BRANCH_CALL_STACK when creating the
  virtual LBR perf event, i.e. KVM will always fail to create LBR events on
  such CPUs.

- Fix a math goof in x86's hugepage logic for KVM_SET_MEMORY_ATTRIBUTES that
  results in an array overflow (detected by KASAN).

- Fix a flaw in the max_guest_memory selftest that results in it exhausting
  the supply of ucall structures when run with more than 256 vCPUs.

- Mark KVM_MEM_READONLY as supported for RISC-V in set_memory_region_test.

- Fix a bug where KVM incorrectly thinks a TDP MMU root is an indirect shadow
  root due KVM unnecessarily clobbering root_role.direct when userspace sets
  guest CPUID.

- Fix a dirty logging bug in the where KVM fails to write-protect TDP MMU
  SPTEs used for L2 if Page-Modification Logging is enabled for L1 and the L1
  hypervisor is NOT using EPT (if nEPT is enabled, KVM doesn't use the TDP MMU
  to run L2).  For simplicity, KVM always disables PML when running L2, but
  the TDP MMU wasn't accounting for root-specific conditions that force write-
  protect based dirty logging.

4 files changed, 72 insertions, 25 deletions

diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c
index 6628dc4dda89..1a6da7389bf1 100644
--- a/tools/testing/selftests/kvm/max_guest_memory_test.c
+++ b/tools/testing/selftests/kvm/max_guest_memory_test.c
@@ -22,10 +22,11 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 {
 	uint64_t gpa;
 
-	for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
-		*((volatile uint64_t *)gpa) = gpa;
-
-	GUEST_DONE();
+	for (;;) {
+		for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
+			*((volatile uint64_t *)gpa) = gpa;
+		GUEST_SYNC(0);
+	}
 }
 
 struct vcpu_info {
@@ -55,7 +56,7 @@ static void rendezvous_with_boss(void)
 static void run_vcpu(struct kvm_vcpu *vcpu)
 {
 	vcpu_run(vcpu);
-	TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
+	TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC);
 }
 
 static void *vcpu_worker(void *data)
@@ -64,17 +65,13 @@ static void *vcpu_worker(void *data)
 	struct kvm_vcpu *vcpu = info->vcpu;
 	struct kvm_vm *vm = vcpu->vm;
 	struct kvm_sregs sregs;
-	struct kvm_regs regs;
 
 	vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size);
 
-	/* Snapshot regs before the first run. */
-	vcpu_regs_get(vcpu, &regs);
 	rendezvous_with_boss();
 
 	run_vcpu(vcpu);
 	rendezvous_with_boss();
-	vcpu_regs_set(vcpu, &regs);
 	vcpu_sregs_get(vcpu, &sregs);
 #ifdef __x86_64__
 	/* Toggle CR0.WP to trigger a MMU context reset. */
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 06b43ed23580..bd57d991e27d 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -333,7 +333,7 @@ static void test_invalid_memory_region_flags(void)
 	struct kvm_vm *vm;
 	int r, i;
 
-#if defined __aarch64__ || defined __x86_64__
+#if defined __aarch64__ || defined __riscv || defined __x86_64__
 	supported_flags |= KVM_MEM_READONLY;
 #endif
 
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
index 29609b52f8fa..26c85815f7e9 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
@@ -416,12 +416,30 @@ static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters
 
 static void guest_test_gp_counters(void)
 {
+	uint8_t pmu_version = guest_get_pmu_version();
 	uint8_t nr_gp_counters = 0;
 	uint32_t base_msr;
 
-	if (guest_get_pmu_version())
+	if (pmu_version)
 		nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS);
 
+	/*
+	 * For v2+ PMUs, PERF_GLOBAL_CTRL's architectural post-RESET value is
+	 * "Sets bits n-1:0 and clears the upper bits", where 'n' is the number
+	 * of GP counters.  If there are no GP counters, require KVM to leave
+	 * PERF_GLOBAL_CTRL '0'.  This edge case isn't covered by the SDM, but
+	 * follow the spirit of the architecture and only globally enable GP
+	 * counters, of which there are none.
+	 */
+	if (pmu_version > 1) {
+		uint64_t global_ctrl = rdmsr(MSR_CORE_PERF_GLOBAL_CTRL);
+
+		if (nr_gp_counters)
+			GUEST_ASSERT_EQ(global_ctrl, GENMASK_ULL(nr_gp_counters - 1, 0));
+		else
+			GUEST_ASSERT_EQ(global_ctrl, 0);
+	}
+
 	if (this_cpu_has(X86_FEATURE_PDCM) &&
 	    rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES)
 		base_msr = MSR_IA32_PMC0;
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index 7f6f5f23fb9b..977948fd52e6 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -28,16 +28,16 @@
 #define NESTED_TEST_MEM1		0xc0001000
 #define NESTED_TEST_MEM2		0xc0002000
 
-static void l2_guest_code(void)
+static void l2_guest_code(u64 *a, u64 *b)
 {
-	*(volatile uint64_t *)NESTED_TEST_MEM1;
-	*(volatile uint64_t *)NESTED_TEST_MEM1 = 1;
+	READ_ONCE(*a);
+	WRITE_ONCE(*a, 1);
 	GUEST_SYNC(true);
 	GUEST_SYNC(false);
 
-	*(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+	WRITE_ONCE(*b, 1);
 	GUEST_SYNC(true);
-	*(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+	WRITE_ONCE(*b, 1);
 	GUEST_SYNC(true);
 	GUEST_SYNC(false);
 
@@ -45,17 +45,33 @@ static void l2_guest_code(void)
 	vmcall();
 }
 
+static void l2_guest_code_ept_enabled(void)
+{
+	l2_guest_code((u64 *)NESTED_TEST_MEM1, (u64 *)NESTED_TEST_MEM2);
+}
+
+static void l2_guest_code_ept_disabled(void)
+{
+	/* Access the same L1 GPAs as l2_guest_code_ept_enabled() */
+	l2_guest_code((u64 *)GUEST_TEST_MEM, (u64 *)GUEST_TEST_MEM);
+}
+
 void l1_guest_code(struct vmx_pages *vmx)
 {
 #define L2_GUEST_STACK_SIZE 64
 	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	void *l2_rip;
 
 	GUEST_ASSERT(vmx->vmcs_gpa);
 	GUEST_ASSERT(prepare_for_vmx_operation(vmx));
 	GUEST_ASSERT(load_vmcs(vmx));
 
-	prepare_vmcs(vmx, l2_guest_code,
-		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+	if (vmx->eptp_gpa)
+		l2_rip = l2_guest_code_ept_enabled;
+	else
+		l2_rip = l2_guest_code_ept_disabled;
+
+	prepare_vmcs(vmx, l2_rip, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
 
 	GUEST_SYNC(false);
 	GUEST_ASSERT(!vmlaunch());
@@ -64,7 +80,7 @@ void l1_guest_code(struct vmx_pages *vmx)
 	GUEST_DONE();
 }
 
-int main(int argc, char *argv[])
+static void test_vmx_dirty_log(bool enable_ept)
 {
 	vm_vaddr_t vmx_pages_gva = 0;
 	struct vmx_pages *vmx;
@@ -76,8 +92,7 @@ int main(int argc, char *argv[])
 	struct ucall uc;
 	bool done = false;
 
-	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
-	TEST_REQUIRE(kvm_cpu_has_ept());
+	pr_info("Nested EPT: %s\n", enable_ept ? "enabled" : "disabled");
 
 	/* Create VM */
 	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
@@ -103,11 +118,16 @@ int main(int argc, char *argv[])
 	 *
 	 * Note that prepare_eptp should be called only L1's GPA map is done,
 	 * meaning after the last call to virt_map.
+	 *
+	 * When EPT is disabled, the L2 guest code will still access the same L1
+	 * GPAs as the EPT enabled case.
 	 */
-	prepare_eptp(vmx, vm, 0);
-	nested_map_memslot(vmx, vm, 0);
-	nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096);
-	nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096);
+	if (enable_ept) {
+		prepare_eptp(vmx, vm, 0);
+		nested_map_memslot(vmx, vm, 0);
+		nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096);
+		nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096);
+	}
 
 	bmap = bitmap_zalloc(TEST_MEM_PAGES);
 	host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM);
@@ -148,3 +168,15 @@ int main(int argc, char *argv[])
 		}
 	}
 }
+
+int main(int argc, char *argv[])
+{
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+
+	test_vmx_dirty_log(/*enable_ept=*/false);
+
+	if (kvm_cpu_has_ept())
+		test_vmx_dirty_log(/*enable_ept=*/true);
+
+	return 0;
+}