From 7a873e4555679a0e749422db071c142b57f80be9 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Tue, 6 Oct 2020 18:44:17 -0700
Subject: KVM: selftests: Verify supported CR4 bits can be set before
 KVM_SET_CPUID2

Extend the KVM_SET_SREGS test to verify that all supported CR4 bits, as
enumerated by KVM, can be set before KVM_SET_CPUID2, i.e. without first
defining the vCPU model.  KVM is supposed to skip guest CPUID checks
when host userspace is stuffing guest state.

Check the inverse as well, i.e. that KVM rejects KVM_SET_REGS if CR4
has one or more unsupported bits set.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20201007014417.29276-7-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/include/x86_64/processor.h       | 17 ++++
 tools/testing/selftests/kvm/include/x86_64/vmx.h   |  4 -
 .../testing/selftests/kvm/x86_64/set_sregs_test.c  | 92 +++++++++++++++++++++-
 3 files changed, 108 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 8e61340b3911..90cd5984751b 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -27,6 +27,7 @@
 #define X86_CR4_OSFXSR		(1ul << 9)
 #define X86_CR4_OSXMMEXCPT	(1ul << 10)
 #define X86_CR4_UMIP		(1ul << 11)
+#define X86_CR4_LA57		(1ul << 12)
 #define X86_CR4_VMXE		(1ul << 13)
 #define X86_CR4_SMXE		(1ul << 14)
 #define X86_CR4_FSGSBASE	(1ul << 16)
@@ -36,6 +37,22 @@
 #define X86_CR4_SMAP		(1ul << 21)
 #define X86_CR4_PKE		(1ul << 22)
 
+/* CPUID.1.ECX */
+#define CPUID_VMX		(1ul << 5)
+#define CPUID_SMX		(1ul << 6)
+#define CPUID_PCID		(1ul << 17)
+#define CPUID_XSAVE		(1ul << 26)
+
+/* CPUID.7.EBX */
+#define CPUID_FSGSBASE		(1ul << 0)
+#define CPUID_SMEP		(1ul << 7)
+#define CPUID_SMAP		(1ul << 20)
+
+/* CPUID.7.ECX */
+#define CPUID_UMIP		(1ul << 2)
+#define CPUID_PKU		(1ul << 3)
+#define CPUID_LA57		(1ul << 16)
+
 #define UNEXPECTED_VECTOR_PORT 0xfff0u
 
 /* General Registers in 64-Bit Mode */
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index e78d7e26ba61..65eb1079a161 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -11,10 +11,6 @@
 #include <stdint.h>
 #include "processor.h"
 
-#define CPUID_VMX_BIT				5
-
-#define CPUID_VMX				(1 << 5)
-
 /*
  * Definitions of Primary Processor-Based VM-Execution Controls.
  */
diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
index 9f7656184f31..318be0bf77ab 100644
--- a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
@@ -24,16 +24,106 @@
 
 #define VCPU_ID                  5
 
+static void test_cr4_feature_bit(struct kvm_vm *vm, struct kvm_sregs *orig,
+				 uint64_t feature_bit)
+{
+	struct kvm_sregs sregs;
+	int rc;
+
+	/* Skip the sub-test, the feature is supported. */
+	if (orig->cr4 & feature_bit)
+		return;
+
+	memcpy(&sregs, orig, sizeof(sregs));
+	sregs.cr4 |= feature_bit;
+
+	rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(rc, "KVM allowed unsupported CR4 bit (0x%lx)", feature_bit);
+
+	/* Sanity check that KVM didn't change anything. */
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(!memcmp(&sregs, orig, sizeof(sregs)), "KVM modified sregs");
+}
+
+static uint64_t calc_cr4_feature_bits(struct kvm_vm *vm)
+{
+	struct kvm_cpuid_entry2 *cpuid_1, *cpuid_7;
+	uint64_t cr4;
+
+	cpuid_1 = kvm_get_supported_cpuid_entry(1);
+	cpuid_7 = kvm_get_supported_cpuid_entry(7);
+
+	cr4 = X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE |
+	      X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE | X86_CR4_PGE |
+	      X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT;
+	if (cpuid_7->ecx & CPUID_UMIP)
+		cr4 |= X86_CR4_UMIP;
+	if (cpuid_7->ecx & CPUID_LA57)
+		cr4 |= X86_CR4_LA57;
+	if (cpuid_1->ecx & CPUID_VMX)
+		cr4 |= X86_CR4_VMXE;
+	if (cpuid_1->ecx & CPUID_SMX)
+		cr4 |= X86_CR4_SMXE;
+	if (cpuid_7->ebx & CPUID_FSGSBASE)
+		cr4 |= X86_CR4_FSGSBASE;
+	if (cpuid_1->ecx & CPUID_PCID)
+		cr4 |= X86_CR4_PCIDE;
+	if (cpuid_1->ecx & CPUID_XSAVE)
+		cr4 |= X86_CR4_OSXSAVE;
+	if (cpuid_7->ebx & CPUID_SMEP)
+		cr4 |= X86_CR4_SMEP;
+	if (cpuid_7->ebx & CPUID_SMAP)
+		cr4 |= X86_CR4_SMAP;
+	if (cpuid_7->ecx & CPUID_PKU)
+		cr4 |= X86_CR4_PKE;
+
+	return cr4;
+}
+
 int main(int argc, char *argv[])
 {
 	struct kvm_sregs sregs;
 	struct kvm_vm *vm;
+	uint64_t cr4;
 	int rc;
 
 	/* Tell stdout not to buffer its content */
 	setbuf(stdout, NULL);
 
-	/* Create VM */
+	/*
+	 * Create a dummy VM, specifically to avoid doing KVM_SET_CPUID2, and
+	 * use it to verify all supported CR4 bits can be set prior to defining
+	 * the vCPU model, i.e. without doing KVM_SET_CPUID2.
+	 */
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+	vm_vcpu_add(vm, VCPU_ID);
+
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+
+	sregs.cr4 |= calc_cr4_feature_bits(vm);
+	cr4 = sregs.cr4;
+
+	rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(!rc, "Failed to set supported CR4 bits (0x%lx)", cr4);
+
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(sregs.cr4 == cr4, "sregs.CR4 (0x%llx) != CR4 (0x%lx)",
+		    sregs.cr4, cr4);
+
+	/* Verify all unsupported features are rejected by KVM. */
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_UMIP);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_LA57);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_VMXE);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_SMXE);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_FSGSBASE);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_PCIDE);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_OSXSAVE);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_SMEP);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_SMAP);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_PKE);
+	kvm_vm_free(vm);
+
+	/* Create a "real" VM and verify APIC_BASE can be set. */
 	vm = vm_create_default(VCPU_ID, 0, NULL);
 
 	vcpu_sregs_get(vm, VCPU_ID, &sregs);
-- 
cgit v1.2.3


From 8b460692fee46a47cebd66d70df88dc9aa6d6b8b Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 29 Sep 2020 17:09:44 +0200
Subject: KVM: selftests: test KVM_GET_SUPPORTED_HV_CPUID as a system ioctl

KVM_GET_SUPPORTED_HV_CPUID is now supported as both vCPU and VM ioctl,
test that.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200929150944.1235688-3-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h    |  2 +
 tools/testing/selftests/kvm/lib/kvm_util.c        | 26 +++++++
 tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c | 87 +++++++++++++----------
 3 files changed, 77 insertions(+), 38 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 7d29aa786959..b2c1364c0402 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -114,6 +114,8 @@ void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
 int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
 		void *arg);
 void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
 void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
 void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
 void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 126c6727a6b0..ef2114e1b7ad 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1582,6 +1582,32 @@ void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
 		cmd, ret, errno, strerror(errno));
 }
 
+/*
+ * KVM system ioctl
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   cmd - Ioctl number
+ *   arg - Argument to pass to the ioctl
+ *
+ * Return: None
+ *
+ * Issues an arbitrary ioctl on a KVM fd.
+ */
+void kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
+{
+	int ret;
+
+	ret = ioctl(vm->kvm_fd, cmd, arg);
+	TEST_ASSERT(ret == 0, "KVM ioctl %lu failed, rc: %i errno: %i (%s)",
+		cmd, ret, errno, strerror(errno));
+}
+
+int _kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
+{
+	return ioctl(vm->kvm_fd, cmd, arg);
+}
+
 /*
  * VM Dump
  *
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
index 745b708c2d3b..88a595b7fbdd 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
@@ -46,19 +46,19 @@ static bool smt_possible(void)
 }
 
 static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
-			  bool evmcs_enabled)
+			  bool evmcs_expected)
 {
 	int i;
 	int nent = 9;
 	u32 test_val;
 
-	if (evmcs_enabled)
+	if (evmcs_expected)
 		nent += 1; /* 0x4000000A */
 
 	TEST_ASSERT(hv_cpuid_entries->nent == nent,
 		    "KVM_GET_SUPPORTED_HV_CPUID should return %d entries"
 		    " with evmcs=%d (returned %d)",
-		    nent, evmcs_enabled, hv_cpuid_entries->nent);
+		    nent, evmcs_expected, hv_cpuid_entries->nent);
 
 	for (i = 0; i < hv_cpuid_entries->nent; i++) {
 		struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i];
@@ -68,7 +68,7 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
 			    "function %x is our of supported range",
 			    entry->function);
 
-		TEST_ASSERT(evmcs_enabled || (entry->function != 0x4000000A),
+		TEST_ASSERT(evmcs_expected || (entry->function != 0x4000000A),
 			    "0x4000000A leaf should not be reported");
 
 		TEST_ASSERT(entry->index == 0,
@@ -87,7 +87,7 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
 			TEST_ASSERT(entry->eax == test_val,
 				    "Wrong max leaf report in 0x40000000.EAX: %x"
 				    " (evmcs=%d)",
-				    entry->eax, evmcs_enabled
+				    entry->eax, evmcs_expected
 				);
 			break;
 		case 0x40000004:
@@ -110,20 +110,23 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
 
 }
 
-void test_hv_cpuid_e2big(struct kvm_vm *vm)
+void test_hv_cpuid_e2big(struct kvm_vm *vm, bool system)
 {
 	static struct kvm_cpuid2 cpuid = {.nent = 0};
 	int ret;
 
-	ret = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, &cpuid);
+	if (!system)
+		ret = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, &cpuid);
+	else
+		ret = _kvm_ioctl(vm, KVM_GET_SUPPORTED_HV_CPUID, &cpuid);
 
 	TEST_ASSERT(ret == -1 && errno == E2BIG,
-		    "KVM_GET_SUPPORTED_HV_CPUID didn't fail with -E2BIG when"
-		    " it should have: %d %d", ret, errno);
+		    "%s KVM_GET_SUPPORTED_HV_CPUID didn't fail with -E2BIG when"
+		    " it should have: %d %d", system ? "KVM" : "vCPU", ret, errno);
 }
 
 
-struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm)
+struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm, bool system)
 {
 	int nent = 20; /* should be enough */
 	static struct kvm_cpuid2 *cpuid;
@@ -137,7 +140,10 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm)
 
 	cpuid->nent = nent;
 
-	vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
+	if (!system)
+		vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
+	else
+		kvm_ioctl(vm, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
 
 	return cpuid;
 }
@@ -146,45 +152,50 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm)
 int main(int argc, char *argv[])
 {
 	struct kvm_vm *vm;
-	int rv, stage;
 	struct kvm_cpuid2 *hv_cpuid_entries;
-	bool evmcs_enabled;
 
 	/* Tell stdout not to buffer its content */
 	setbuf(stdout, NULL);
 
-	rv = kvm_check_cap(KVM_CAP_HYPERV_CPUID);
-	if (!rv) {
+	if (!kvm_check_cap(KVM_CAP_HYPERV_CPUID)) {
 		print_skip("KVM_CAP_HYPERV_CPUID not supported");
 		exit(KSFT_SKIP);
 	}
 
-	for (stage = 0; stage < 3; stage++) {
-		evmcs_enabled = false;
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
 
-		vm = vm_create_default(VCPU_ID, 0, guest_code);
-		switch (stage) {
-		case 0:
-			test_hv_cpuid_e2big(vm);
-			continue;
-		case 1:
-			break;
-		case 2:
-			if (!nested_vmx_supported() ||
-			    !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
-				print_skip("Enlightened VMCS is unsupported");
-				continue;
-			}
-			vcpu_enable_evmcs(vm, VCPU_ID);
-			evmcs_enabled = true;
-			break;
-		}
+	/* Test vCPU ioctl version */
+	test_hv_cpuid_e2big(vm, false);
+
+	hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm, false);
+	test_hv_cpuid(hv_cpuid_entries, false);
+	free(hv_cpuid_entries);
 
-		hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
-		test_hv_cpuid(hv_cpuid_entries, evmcs_enabled);
-		free(hv_cpuid_entries);
-		kvm_vm_free(vm);
+	if (!nested_vmx_supported() ||
+	    !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
+		print_skip("Enlightened VMCS is unsupported");
+		goto do_sys;
 	}
+	vcpu_enable_evmcs(vm, VCPU_ID);
+	hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm, false);
+	test_hv_cpuid(hv_cpuid_entries, true);
+	free(hv_cpuid_entries);
+
+do_sys:
+	/* Test system ioctl version */
+	if (!kvm_check_cap(KVM_CAP_SYS_HYPERV_CPUID)) {
+		print_skip("KVM_CAP_SYS_HYPERV_CPUID not supported");
+		goto out;
+	}
+
+	test_hv_cpuid_e2big(vm, true);
+
+	hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm, true);
+	test_hv_cpuid(hv_cpuid_entries, nested_vmx_supported());
+	free(hv_cpuid_entries);
+
+out:
+	kvm_vm_free(vm);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 60f644fb519831edff38c79755f7970c475e2ece Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 30 Sep 2020 21:22:35 -0400
Subject: KVM: selftests: Introduce after_vcpu_run hook for dirty log test

Provide a hook for the checks after vcpu_run() completes.  Preparation
for the dirty ring test because we'll need to take care of another
exit reason.

Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201001012235.6063-1-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c | 36 ++++++++++++++++++----------
 1 file changed, 24 insertions(+), 12 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 54da9cc20db4..9215b26af10c 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -178,6 +178,15 @@ static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
 }
 
+static void default_after_vcpu_run(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+	TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC,
+		    "Invalid guest sync status: exit_reason=%s\n",
+		    exit_reason_str(run->exit_reason));
+}
+
 struct log_mode {
 	const char *name;
 	/* Return true if this mode is supported, otherwise false */
@@ -187,16 +196,20 @@ struct log_mode {
 	/* Hook to collect the dirty pages into the bitmap provided */
 	void (*collect_dirty_pages) (struct kvm_vm *vm, int slot,
 				     void *bitmap, uint32_t num_pages);
+	/* Hook to call when after each vcpu run */
+	void (*after_vcpu_run)(struct kvm_vm *vm);
 } log_modes[LOG_MODE_NUM] = {
 	{
 		.name = "dirty-log",
 		.collect_dirty_pages = dirty_log_collect_dirty_pages,
+		.after_vcpu_run = default_after_vcpu_run,
 	},
 	{
 		.name = "clear-log",
 		.supported = clear_log_supported,
 		.create_vm_done = clear_log_create_vm_done,
 		.collect_dirty_pages = clear_log_collect_dirty_pages,
+		.after_vcpu_run = default_after_vcpu_run,
 	},
 };
 
@@ -247,6 +260,14 @@ static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	mode->collect_dirty_pages(vm, slot, bitmap, num_pages);
 }
 
+static void log_mode_after_vcpu_run(struct kvm_vm *vm)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	if (mode->after_vcpu_run)
+		mode->after_vcpu_run(vm);
+}
+
 static void generate_random_array(uint64_t *guest_array, uint64_t size)
 {
 	uint64_t i;
@@ -261,25 +282,16 @@ static void *vcpu_worker(void *data)
 	struct kvm_vm *vm = data;
 	uint64_t *guest_array;
 	uint64_t pages_count = 0;
-	struct kvm_run *run;
-
-	run = vcpu_state(vm, VCPU_ID);
 
 	guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array);
-	generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
 
 	while (!READ_ONCE(host_quit)) {
+		generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+		pages_count += TEST_PAGES_PER_LOOP;
 		/* Let the guest dirty the random pages */
 		ret = _vcpu_run(vm, VCPU_ID);
 		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
-		if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) {
-			pages_count += TEST_PAGES_PER_LOOP;
-			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
-		} else {
-			TEST_FAIL("Invalid guest sync status: "
-				  "exit_reason=%s\n",
-				  exit_reason_str(run->exit_reason));
-		}
+		log_mode_after_vcpu_run(vm);
 	}
 
 	pr_info("Dirtied %"PRIu64" pages\n", pages_count);
-- 
cgit v1.2.3


From 84292e565951cecfe2718e43905a6103c9e8ac29 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 30 Sep 2020 21:22:37 -0400
Subject: KVM: selftests: Add dirty ring buffer test

Add the initial dirty ring buffer test.

The current test implements the userspace dirty ring collection, by
only reaping the dirty ring when the ring is full.

So it's still running synchronously like this:

            vcpu                             main thread

  1. vcpu dirties pages
  2. vcpu gets dirty ring full
     (userspace exit)

                                       3. main thread waits until full
                                          (so hardware buffers flushed)
                                       4. main thread collects
                                       5. main thread continues vcpu

  6. vcpu continues, goes back to 1

We can't directly collects dirty bits during vcpu execution because
otherwise we can't guarantee the hardware dirty bits were flushed when
we collect and we're very strict on the dirty bits so otherwise we can
fail the future verify procedure.  A follow up patch will make this
test to support async just like the existing dirty log test, by adding
a vcpu kick mechanism.

Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201001012237.6111-1-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c       | 254 ++++++++++++++++++++-
 tools/testing/selftests/kvm/include/kvm_util.h     |   3 +
 tools/testing/selftests/kvm/lib/kvm_util.c         |  72 +++++-
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |   4 +
 4 files changed, 320 insertions(+), 13 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 9215b26af10c..a7da4d9471e1 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -12,8 +12,13 @@
 #include <unistd.h>
 #include <time.h>
 #include <pthread.h>
+#include <semaphore.h>
+#include <sys/types.h>
+#include <signal.h>
+#include <errno.h>
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
+#include <asm/barrier.h>
 
 #include "test_util.h"
 #include "kvm_util.h"
@@ -57,6 +62,8 @@
 # define test_and_clear_bit_le	test_and_clear_bit
 #endif
 
+#define TEST_DIRTY_RING_COUNT		1024
+
 /*
  * Guest/Host shared variables. Ensure addr_gva2hva() and/or
  * sync_global_to/from_guest() are used when accessing from
@@ -128,6 +135,25 @@ static uint64_t host_dirty_count;
 static uint64_t host_clear_count;
 static uint64_t host_track_next_count;
 
+/* Whether dirty ring reset is requested, or finished */
+static sem_t dirty_ring_vcpu_stop;
+static sem_t dirty_ring_vcpu_cont;
+/*
+ * This is only used for verifying the dirty pages.  Dirty ring has a very
+ * tricky case when the ring just got full, kvm will do userspace exit due to
+ * ring full.  When that happens, the very last PFN is set but actually the
+ * data is not changed (the guest WRITE is not really applied yet), because
+ * we found that the dirty ring is full, refused to continue the vcpu, and
+ * recorded the dirty gfn with the old contents.
+ *
+ * For this specific case, it's safe to skip checking this pfn for this
+ * bit, because it's a redundant bit, and when the write happens later the bit
+ * will be set again.  We use this variable to always keep track of the latest
+ * dirty gfn we've collected, so that if a mismatch of data found later in the
+ * verifying process, we let it pass.
+ */
+static uint64_t dirty_ring_last_page;
+
 enum log_mode_t {
 	/* Only use KVM_GET_DIRTY_LOG for logging */
 	LOG_MODE_DIRTY_LOG = 0,
@@ -135,6 +161,9 @@ enum log_mode_t {
 	/* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */
 	LOG_MODE_CLEAR_LOG = 1,
 
+	/* Use dirty ring for logging */
+	LOG_MODE_DIRTY_RING = 2,
+
 	LOG_MODE_NUM,
 
 	/* Run all supported modes */
@@ -145,6 +174,20 @@ enum log_mode_t {
 static enum log_mode_t host_log_mode_option = LOG_MODE_ALL;
 /* Logging mode for current run */
 static enum log_mode_t host_log_mode;
+static pthread_t vcpu_thread;
+
+/*
+ * In our test we do signal tricks, let's use a better version of
+ * sem_wait to avoid signal interrupts
+ */
+static void sem_wait_until(sem_t *sem)
+{
+	int ret;
+
+	do
+		ret = sem_wait(sem);
+	while (ret == -1 && errno == EINTR);
+}
 
 static bool clear_log_supported(void)
 {
@@ -178,15 +221,131 @@ static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
 }
 
-static void default_after_vcpu_run(struct kvm_vm *vm)
+static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 {
 	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
 
+	TEST_ASSERT(ret == 0 || (ret == -1 && err == EINTR),
+		    "vcpu run failed: errno=%d", err);
+
 	TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC,
 		    "Invalid guest sync status: exit_reason=%s\n",
 		    exit_reason_str(run->exit_reason));
 }
 
+static bool dirty_ring_supported(void)
+{
+	return kvm_check_cap(KVM_CAP_DIRTY_LOG_RING);
+}
+
+static void dirty_ring_create_vm_done(struct kvm_vm *vm)
+{
+	/*
+	 * Switch to dirty ring mode after VM creation but before any
+	 * of the vcpu creation.
+	 */
+	vm_enable_dirty_ring(vm, TEST_DIRTY_RING_COUNT *
+			     sizeof(struct kvm_dirty_gfn));
+}
+
+static inline bool dirty_gfn_is_dirtied(struct kvm_dirty_gfn *gfn)
+{
+	return gfn->flags == KVM_DIRTY_GFN_F_DIRTY;
+}
+
+static inline void dirty_gfn_set_collected(struct kvm_dirty_gfn *gfn)
+{
+	gfn->flags = KVM_DIRTY_GFN_F_RESET;
+}
+
+static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns,
+				       int slot, void *bitmap,
+				       uint32_t num_pages, uint32_t *fetch_index)
+{
+	struct kvm_dirty_gfn *cur;
+	uint32_t count = 0;
+
+	while (true) {
+		cur = &dirty_gfns[*fetch_index % TEST_DIRTY_RING_COUNT];
+		if (!dirty_gfn_is_dirtied(cur))
+			break;
+		TEST_ASSERT(cur->slot == slot, "Slot number didn't match: "
+			    "%u != %u", cur->slot, slot);
+		TEST_ASSERT(cur->offset < num_pages, "Offset overflow: "
+			    "0x%llx >= 0x%x", cur->offset, num_pages);
+		//pr_info("fetch 0x%x page %llu\n", *fetch_index, cur->offset);
+		set_bit_le(cur->offset, bitmap);
+		dirty_ring_last_page = cur->offset;
+		dirty_gfn_set_collected(cur);
+		(*fetch_index)++;
+		count++;
+	}
+
+	return count;
+}
+
+static void dirty_ring_wait_vcpu(void)
+{
+	sem_wait_until(&dirty_ring_vcpu_stop);
+}
+
+static void dirty_ring_continue_vcpu(void)
+{
+	pr_info("Notifying vcpu to continue\n");
+	sem_post(&dirty_ring_vcpu_cont);
+}
+
+static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot,
+					   void *bitmap, uint32_t num_pages)
+{
+	/* We only have one vcpu */
+	static uint32_t fetch_index = 0;
+	uint32_t count = 0, cleared;
+
+	dirty_ring_wait_vcpu();
+
+	/* Only have one vcpu */
+	count = dirty_ring_collect_one(vcpu_map_dirty_ring(vm, VCPU_ID),
+				       slot, bitmap, num_pages, &fetch_index);
+
+	cleared = kvm_vm_reset_dirty_ring(vm);
+
+	/* Cleared pages should be the same as collected */
+	TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch "
+		    "with collected (%u)", cleared, count);
+
+	dirty_ring_continue_vcpu();
+
+	pr_info("Iteration %ld collected %u pages\n", iteration, count);
+}
+
+static void dirty_ring_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+	/* A ucall-sync or ring-full event is allowed */
+	if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) {
+		/* We should allow this to continue */
+		;
+	} else if (run->exit_reason == KVM_EXIT_DIRTY_RING_FULL) {
+		/* Update the flag first before pause */
+		sem_post(&dirty_ring_vcpu_stop);
+		pr_info("vcpu stops because dirty ring is full...\n");
+		sem_wait_until(&dirty_ring_vcpu_cont);
+		pr_info("vcpu continues now.\n");
+	} else {
+		TEST_ASSERT(false, "Invalid guest sync status: "
+			    "exit_reason=%s\n",
+			    exit_reason_str(run->exit_reason));
+	}
+}
+
+static void dirty_ring_before_vcpu_join(void)
+{
+	/* Kick another round of vcpu just to make sure it will quit */
+	sem_post(&dirty_ring_vcpu_cont);
+}
+
 struct log_mode {
 	const char *name;
 	/* Return true if this mode is supported, otherwise false */
@@ -197,7 +356,8 @@ struct log_mode {
 	void (*collect_dirty_pages) (struct kvm_vm *vm, int slot,
 				     void *bitmap, uint32_t num_pages);
 	/* Hook to call when after each vcpu run */
-	void (*after_vcpu_run)(struct kvm_vm *vm);
+	void (*after_vcpu_run)(struct kvm_vm *vm, int ret, int err);
+	void (*before_vcpu_join) (void);
 } log_modes[LOG_MODE_NUM] = {
 	{
 		.name = "dirty-log",
@@ -211,6 +371,14 @@ struct log_mode {
 		.collect_dirty_pages = clear_log_collect_dirty_pages,
 		.after_vcpu_run = default_after_vcpu_run,
 	},
+	{
+		.name = "dirty-ring",
+		.supported = dirty_ring_supported,
+		.create_vm_done = dirty_ring_create_vm_done,
+		.collect_dirty_pages = dirty_ring_collect_dirty_pages,
+		.before_vcpu_join = dirty_ring_before_vcpu_join,
+		.after_vcpu_run = dirty_ring_after_vcpu_run,
+	},
 };
 
 /*
@@ -260,12 +428,20 @@ static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	mode->collect_dirty_pages(vm, slot, bitmap, num_pages);
 }
 
-static void log_mode_after_vcpu_run(struct kvm_vm *vm)
+static void log_mode_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 {
 	struct log_mode *mode = &log_modes[host_log_mode];
 
 	if (mode->after_vcpu_run)
-		mode->after_vcpu_run(vm);
+		mode->after_vcpu_run(vm, ret, err);
+}
+
+static void log_mode_before_vcpu_join(void)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	if (mode->before_vcpu_join)
+		mode->before_vcpu_join();
 }
 
 static void generate_random_array(uint64_t *guest_array, uint64_t size)
@@ -278,20 +454,22 @@ static void generate_random_array(uint64_t *guest_array, uint64_t size)
 
 static void *vcpu_worker(void *data)
 {
-	int ret;
+	int ret, vcpu_fd;
 	struct kvm_vm *vm = data;
 	uint64_t *guest_array;
 	uint64_t pages_count = 0;
 
+	vcpu_fd = vcpu_get_fd(vm, VCPU_ID);
+
 	guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array);
 
 	while (!READ_ONCE(host_quit)) {
+		/* Clear any existing kick signals */
 		generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
 		pages_count += TEST_PAGES_PER_LOOP;
 		/* Let the guest dirty the random pages */
-		ret = _vcpu_run(vm, VCPU_ID);
-		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
-		log_mode_after_vcpu_run(vm);
+		ret = ioctl(vcpu_fd, KVM_RUN, NULL);
+		log_mode_after_vcpu_run(vm, ret, errno);
 	}
 
 	pr_info("Dirtied %"PRIu64" pages\n", pages_count);
@@ -304,6 +482,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 	uint64_t step = vm_num_host_pages(mode, 1);
 	uint64_t page;
 	uint64_t *value_ptr;
+	uint64_t min_iter = 0;
 
 	for (page = 0; page < host_num_pages; page += step) {
 		value_ptr = host_test_mem + page * host_page_size;
@@ -318,14 +497,64 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 		}
 
 		if (test_and_clear_bit_le(page, bmap)) {
+			bool matched;
+
 			host_dirty_count++;
+
 			/*
 			 * If the bit is set, the value written onto
 			 * the corresponding page should be either the
 			 * previous iteration number or the current one.
 			 */
-			TEST_ASSERT(*value_ptr == iteration ||
-				    *value_ptr == iteration - 1,
+			matched = (*value_ptr == iteration ||
+				   *value_ptr == iteration - 1);
+
+			if (host_log_mode == LOG_MODE_DIRTY_RING && !matched) {
+				if (*value_ptr == iteration - 2 && min_iter <= iteration - 2) {
+					/*
+					 * Short answer: this case is special
+					 * only for dirty ring test where the
+					 * page is the last page before a kvm
+					 * dirty ring full in iteration N-2.
+					 *
+					 * Long answer: Assuming ring size R,
+					 * one possible condition is:
+					 *
+					 *      main thr       vcpu thr
+					 *      --------       --------
+					 *    iter=1
+					 *                   write 1 to page 0~(R-1)
+					 *                   full, vmexit
+					 *    collect 0~(R-1)
+					 *    kick vcpu
+					 *                   write 1 to (R-1)~(2R-2)
+					 *                   full, vmexit
+					 *    iter=2
+					 *    collect (R-1)~(2R-2)
+					 *    kick vcpu
+					 *                   write 1 to (2R-2)
+					 *                   (NOTE!!! "1" cached in cpu reg)
+					 *                   write 2 to (2R-1)~(3R-3)
+					 *                   full, vmexit
+					 *    iter=3
+					 *    collect (2R-2)~(3R-3)
+					 *    (here if we read value on page
+					 *     "2R-2" is 1, while iter=3!!!)
+					 *
+					 * This however can only happen once per iteration.
+					 */
+					min_iter = iteration - 1;
+					continue;
+				} else if (page == dirty_ring_last_page) {
+					/*
+					 * Please refer to comments in
+					 * dirty_ring_last_page.
+					 */
+					continue;
+				}
+			}
+
+			TEST_ASSERT(matched,
 				    "Set page %"PRIu64" value %"PRIu64
 				    " incorrect (iteration=%"PRIu64")",
 				    page, *value_ptr, iteration);
@@ -390,7 +619,6 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
 static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		     unsigned long interval, uint64_t phys_offset)
 {
-	pthread_t vcpu_thread;
 	struct kvm_vm *vm;
 	unsigned long *bmap;
 
@@ -488,6 +716,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	/* Tell the vcpu thread to quit */
 	host_quit = true;
+	log_mode_before_vcpu_join();
 	pthread_join(vcpu_thread, NULL);
 
 	pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
@@ -548,6 +777,9 @@ int main(int argc, char *argv[])
 	unsigned int mode;
 	int opt, i, j;
 
+	sem_init(&dirty_ring_vcpu_stop, 0, 0);
+	sem_init(&dirty_ring_vcpu_cont, 0, 0);
+
 #ifdef __x86_64__
 	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
 #endif
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index b2c1364c0402..710009cc17fd 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -74,6 +74,7 @@ void kvm_vm_release(struct kvm_vm *vmp);
 void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
 void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
 			    uint64_t first_page, uint32_t num_pages);
+uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm);
 
 int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
 		       size_t len);
@@ -148,6 +149,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
 struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid,
 			  struct kvm_guest_debug *debug);
@@ -201,6 +203,7 @@ void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid,
 int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
 			  struct kvm_nested_state *state, bool ignore_error);
 #endif
+void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid);
 
 const char *exit_reason_str(unsigned int exit_reason);
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index ef2114e1b7ad..a04302666b02 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -114,6 +114,16 @@ int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
 	return r;
 }
 
+void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size)
+{
+	struct kvm_enable_cap cap = { 0 };
+
+	cap.cap = KVM_CAP_DIRTY_LOG_RING;
+	cap.args[0] = ring_size;
+	vm_enable_cap(vm, &cap);
+	vm->dirty_ring_size = ring_size;
+}
+
 static void vm_open(struct kvm_vm *vm, int perm)
 {
 	vm->kvm_fd = open(KVM_DEV_PATH, perm);
@@ -328,6 +338,11 @@ void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
 		    __func__, strerror(-ret));
 }
 
+uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm)
+{
+	return ioctl(vm->fd, KVM_RESET_DIRTY_RINGS);
+}
+
 /*
  * Userspace Memory Region Find
  *
@@ -432,10 +447,17 @@ struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid)
  *
  * Removes a vCPU from a VM and frees its resources.
  */
-static void vm_vcpu_rm(struct vcpu *vcpu)
+static void vm_vcpu_rm(struct kvm_vm *vm, struct vcpu *vcpu)
 {
 	int ret;
 
+	if (vcpu->dirty_gfns) {
+		ret = munmap(vcpu->dirty_gfns, vm->dirty_ring_size);
+		TEST_ASSERT(ret == 0, "munmap of VCPU dirty ring failed, "
+			    "rc: %i errno: %i", ret, errno);
+		vcpu->dirty_gfns = NULL;
+	}
+
 	ret = munmap(vcpu->state, sizeof(*vcpu->state));
 	TEST_ASSERT(ret == 0, "munmap of VCPU fd failed, rc: %i "
 		"errno: %i", ret, errno);
@@ -453,7 +475,7 @@ void kvm_vm_release(struct kvm_vm *vmp)
 	int ret;
 
 	list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list)
-		vm_vcpu_rm(vcpu);
+		vm_vcpu_rm(vmp, vcpu);
 
 	ret = close(vmp->fd);
 	TEST_ASSERT(ret == 0, "Close of vm fd failed,\n"
@@ -1233,6 +1255,15 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
 	return rc;
 }
 
+int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+	return vcpu->fd;
+}
+
 void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
@@ -1561,6 +1592,42 @@ int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid,
 	return ret;
 }
 
+void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu;
+	uint32_t size = vm->dirty_ring_size;
+
+	TEST_ASSERT(size > 0, "Should enable dirty ring first");
+
+	vcpu = vcpu_find(vm, vcpuid);
+
+	TEST_ASSERT(vcpu, "Cannot find vcpu %u", vcpuid);
+
+	if (!vcpu->dirty_gfns) {
+		void *addr;
+
+		addr = mmap(NULL, size, PROT_READ,
+			    MAP_PRIVATE, vcpu->fd,
+			    vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET);
+		TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped private");
+
+		addr = mmap(NULL, size, PROT_READ | PROT_EXEC,
+			    MAP_PRIVATE, vcpu->fd,
+			    vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET);
+		TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped exec");
+
+		addr = mmap(NULL, size, PROT_READ | PROT_WRITE,
+			    MAP_SHARED, vcpu->fd,
+			    vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET);
+		TEST_ASSERT(addr != MAP_FAILED, "Dirty ring map failed");
+
+		vcpu->dirty_gfns = addr;
+		vcpu->dirty_gfns_count = size / sizeof(struct kvm_dirty_gfn);
+	}
+
+	return vcpu->dirty_gfns;
+}
+
 /*
  * VM Ioctl
  *
@@ -1680,6 +1747,7 @@ static struct exit_reason {
 	{KVM_EXIT_INTERNAL_ERROR, "INTERNAL_ERROR"},
 	{KVM_EXIT_OSI, "OSI"},
 	{KVM_EXIT_PAPR_HCALL, "PAPR_HCALL"},
+	{KVM_EXIT_DIRTY_RING_FULL, "DIRTY_RING_FULL"},
 #ifdef KVM_EXIT_MEMORY_NOT_PRESENT
 	{KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"},
 #endif
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index f07d383d03a1..34465dc562d8 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -28,6 +28,9 @@ struct vcpu {
 	uint32_t id;
 	int fd;
 	struct kvm_run *state;
+	struct kvm_dirty_gfn *dirty_gfns;
+	uint32_t fetch_index;
+	uint32_t dirty_gfns_count;
 };
 
 struct kvm_vm {
@@ -52,6 +55,7 @@ struct kvm_vm {
 	vm_vaddr_t tss;
 	vm_vaddr_t idt;
 	vm_vaddr_t handlers;
+	uint32_t dirty_ring_size;
 };
 
 struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);
-- 
cgit v1.2.3


From 019d321a68ea07efcfcbc308443251644ff3e71c Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 30 Sep 2020 21:22:39 -0400
Subject: KVM: selftests: Run dirty ring test asynchronously

Previously the dirty ring test was working in synchronous way, because
only with a vmexit (with that it was the ring full event) we'll know
the hardware dirty bits will be flushed to the dirty ring.

With this patch we first introduce a vcpu kick mechanism using SIGUSR1,
which guarantees a vmexit and also therefore the flushing of hardware
dirty bits.  Once this is in place, we can keep the vcpu dirty work
asynchronous of the whole collection procedure now.  Still, we need
to be very careful that when reaching the ring buffer soft limit
(KVM_EXIT_DIRTY_RING_FULL) we must collect the dirty bits before
continuing the vcpu.

Further increase the dirty ring size to current maximum to make sure
we torture more on the no-ring-full case, which should be the major
scenario when the hypervisors like QEMU would like to use this feature.

Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201001012239.6159-1-peterx@redhat.com>
[Use KVM_SET_SIGNAL_MASK+sigwait instead of a signal handler. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c | 64 ++++++++++++++++++++++++++--
 1 file changed, 60 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index a7da4d9471e1..85c5d07dd243 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -62,7 +62,9 @@
 # define test_and_clear_bit_le	test_and_clear_bit
 #endif
 
-#define TEST_DIRTY_RING_COUNT		1024
+#define TEST_DIRTY_RING_COUNT		65536
+
+#define SIG_IPI SIGUSR1
 
 /*
  * Guest/Host shared variables. Ensure addr_gva2hva() and/or
@@ -138,6 +140,12 @@ static uint64_t host_track_next_count;
 /* Whether dirty ring reset is requested, or finished */
 static sem_t dirty_ring_vcpu_stop;
 static sem_t dirty_ring_vcpu_cont;
+/*
+ * This is updated by the vcpu thread to tell the host whether it's a
+ * ring-full event.  It should only be read until a sem_wait() of
+ * dirty_ring_vcpu_stop and before vcpu continues to run.
+ */
+static bool dirty_ring_vcpu_ring_full;
 /*
  * This is only used for verifying the dirty pages.  Dirty ring has a very
  * tricky case when the ring just got full, kvm will do userspace exit due to
@@ -176,6 +184,11 @@ static enum log_mode_t host_log_mode_option = LOG_MODE_ALL;
 static enum log_mode_t host_log_mode;
 static pthread_t vcpu_thread;
 
+static void vcpu_kick(void)
+{
+	pthread_kill(vcpu_thread, SIG_IPI);
+}
+
 /*
  * In our test we do signal tricks, let's use a better version of
  * sem_wait to avoid signal interrupts
@@ -286,6 +299,8 @@ static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns,
 
 static void dirty_ring_wait_vcpu(void)
 {
+	/* This makes sure that hardware PML cache flushed */
+	vcpu_kick();
 	sem_wait_until(&dirty_ring_vcpu_stop);
 }
 
@@ -301,9 +316,19 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	/* We only have one vcpu */
 	static uint32_t fetch_index = 0;
 	uint32_t count = 0, cleared;
+	bool continued_vcpu = false;
 
 	dirty_ring_wait_vcpu();
 
+	if (!dirty_ring_vcpu_ring_full) {
+		/*
+		 * This is not a ring-full event, it's safe to allow
+		 * vcpu to continue
+		 */
+		dirty_ring_continue_vcpu();
+		continued_vcpu = true;
+	}
+
 	/* Only have one vcpu */
 	count = dirty_ring_collect_one(vcpu_map_dirty_ring(vm, VCPU_ID),
 				       slot, bitmap, num_pages, &fetch_index);
@@ -314,7 +339,11 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch "
 		    "with collected (%u)", cleared, count);
 
-	dirty_ring_continue_vcpu();
+	if (!continued_vcpu) {
+		TEST_ASSERT(dirty_ring_vcpu_ring_full,
+			    "Didn't continue vcpu even without ring full");
+		dirty_ring_continue_vcpu();
+	}
 
 	pr_info("Iteration %ld collected %u pages\n", iteration, count);
 }
@@ -327,10 +356,15 @@ static void dirty_ring_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 	if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) {
 		/* We should allow this to continue */
 		;
-	} else if (run->exit_reason == KVM_EXIT_DIRTY_RING_FULL) {
+	} else if (run->exit_reason == KVM_EXIT_DIRTY_RING_FULL ||
+		   (ret == -1 && err == EINTR)) {
 		/* Update the flag first before pause */
+		WRITE_ONCE(dirty_ring_vcpu_ring_full,
+			   run->exit_reason == KVM_EXIT_DIRTY_RING_FULL);
 		sem_post(&dirty_ring_vcpu_stop);
-		pr_info("vcpu stops because dirty ring is full...\n");
+		pr_info("vcpu stops because %s...\n",
+			dirty_ring_vcpu_ring_full ?
+			"dirty ring is full" : "vcpu is kicked out");
 		sem_wait_until(&dirty_ring_vcpu_cont);
 		pr_info("vcpu continues now.\n");
 	} else {
@@ -458,9 +492,26 @@ static void *vcpu_worker(void *data)
 	struct kvm_vm *vm = data;
 	uint64_t *guest_array;
 	uint64_t pages_count = 0;
+	struct kvm_signal_mask *sigmask = alloca(offsetof(struct kvm_signal_mask, sigset)
+						 + sizeof(sigset_t));
+	sigset_t *sigset = (sigset_t *) &sigmask->sigset;
 
 	vcpu_fd = vcpu_get_fd(vm, VCPU_ID);
 
+	/*
+	 * SIG_IPI is unblocked atomically while in KVM_RUN.  It causes the
+	 * ioctl to return with -EINTR, but it is still pending and we need
+	 * to accept it with the sigwait.
+	 */
+	sigmask->len = 8;
+	pthread_sigmask(0, NULL, sigset);
+	vcpu_ioctl(vm, VCPU_ID, KVM_SET_SIGNAL_MASK, sigmask);
+	sigaddset(sigset, SIG_IPI);
+	pthread_sigmask(SIG_BLOCK, sigset, NULL);
+
+	sigemptyset(sigset);
+	sigaddset(sigset, SIG_IPI);
+
 	guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array);
 
 	while (!READ_ONCE(host_quit)) {
@@ -469,6 +520,11 @@ static void *vcpu_worker(void *data)
 		pages_count += TEST_PAGES_PER_LOOP;
 		/* Let the guest dirty the random pages */
 		ret = ioctl(vcpu_fd, KVM_RUN, NULL);
+		if (ret == -1 && errno == EINTR) {
+			int sig = -1;
+			sigwait(sigset, &sig);
+			assert(sig == SIG_IPI);
+		}
 		log_mode_after_vcpu_run(vm, ret, errno);
 	}
 
-- 
cgit v1.2.3


From edd3de6fc3d57deddb5cc7c7f1d8316ad26ac4e4 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 30 Sep 2020 21:22:41 -0400
Subject: KVM: selftests: Add "-c" parameter to dirty log test

It's only used to override the existing dirty ring size/count.  If
with a bigger ring count, we test async of dirty ring.  If with a
smaller ring count, we test ring full code path.  Async is default.

It has no use for non-dirty-ring tests.

Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201001012241.6208-1-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 85c5d07dd243..b1f8731721b9 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -183,6 +183,7 @@ static enum log_mode_t host_log_mode_option = LOG_MODE_ALL;
 /* Logging mode for current run */
 static enum log_mode_t host_log_mode;
 static pthread_t vcpu_thread;
+static uint32_t test_dirty_ring_count = TEST_DIRTY_RING_COUNT;
 
 static void vcpu_kick(void)
 {
@@ -257,7 +258,7 @@ static void dirty_ring_create_vm_done(struct kvm_vm *vm)
 	 * Switch to dirty ring mode after VM creation but before any
 	 * of the vcpu creation.
 	 */
-	vm_enable_dirty_ring(vm, TEST_DIRTY_RING_COUNT *
+	vm_enable_dirty_ring(vm, test_dirty_ring_count *
 			     sizeof(struct kvm_dirty_gfn));
 }
 
@@ -279,7 +280,7 @@ static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns,
 	uint32_t count = 0;
 
 	while (true) {
-		cur = &dirty_gfns[*fetch_index % TEST_DIRTY_RING_COUNT];
+		cur = &dirty_gfns[*fetch_index % test_dirty_ring_count];
 		if (!dirty_gfn_is_dirtied(cur))
 			break;
 		TEST_ASSERT(cur->slot == slot, "Slot number didn't match: "
@@ -803,6 +804,9 @@ static void help(char *name)
 	printf("usage: %s [-h] [-i iterations] [-I interval] "
 	       "[-p offset] [-m mode]\n", name);
 	puts("");
+	printf(" -c: specify dirty ring size, in number of entries\n");
+	printf("     (only useful for dirty-ring test; default: %"PRIu32")\n",
+	       TEST_DIRTY_RING_COUNT);
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
 	       TEST_HOST_LOOP_N);
 	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
@@ -858,8 +862,11 @@ int main(int argc, char *argv[])
 	guest_mode_init(VM_MODE_P40V48_4K, true, true);
 #endif
 
-	while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) {
+	while ((opt = getopt(argc, argv, "c:hi:I:p:m:M:")) != -1) {
 		switch (opt) {
+		case 'c':
+			test_dirty_ring_count = strtol(optarg, NULL, 10);
+			break;
 		case 'i':
 			iterations = strtol(optarg, NULL, 10);
 			break;
-- 
cgit v1.2.3


From 8aa426e854c475504033c176a66d038259bf64ea Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 6 Nov 2020 07:39:26 -0500
Subject: selftests: kvm: keep .gitignore add to date

Add tsc_msrs_test, remove clear_dirty_log_test and alphabetize
everything.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 7a2c242b7152..5468db7dd674 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -14,17 +14,17 @@
 /x86_64/set_sregs_test
 /x86_64/smm_test
 /x86_64/state_test
-/x86_64/user_msr_test
-/x86_64/vmx_preemption_timer_test
 /x86_64/svm_vmcall_test
 /x86_64/sync_regs_test
+/x86_64/tsc_msrs_test
+/x86_64/user_msr_test
 /x86_64/vmx_apic_access_test
 /x86_64/vmx_close_while_nested_test
 /x86_64/vmx_dirty_log_test
+/x86_64/vmx_preemption_timer_test
 /x86_64/vmx_set_nested_state_test
 /x86_64/vmx_tsc_adjust_test
 /x86_64/xss_msr_test
-/clear_dirty_log_test
 /demand_paging_test
 /dirty_log_test
 /dirty_log_perf_test
-- 
cgit v1.2.3


From f63f0b68c864edea801de678bed279a3d7674f1a Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 13 Nov 2020 11:36:49 -0500
Subject: KVM: selftests: always use manual clear in dirty_log_perf_test

Nothing sets USE_CLEAR_DIRTY_LOG anymore, so anything it surrounds
is dead code.

However, it is the recommended way to use the dirty page bitmap
for new enough kernel, so use it whenever KVM has the
KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 capability.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_perf_test.c | 55 +++++++++--------------
 1 file changed, 22 insertions(+), 33 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 85c9b8f73142..9c6a7be31e03 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -27,6 +27,7 @@
 #define TEST_HOST_LOOP_N		2UL
 
 /* Host variables */
+static u64 dirty_log_manual_caps;
 static bool host_quit;
 static uint64_t iteration;
 static uint64_t vcpu_last_completed_iteration[MAX_VCPUS];
@@ -88,10 +89,6 @@ static void *vcpu_worker(void *data)
 	return NULL;
 }
 
-#ifdef USE_CLEAR_DIRTY_LOG
-static u64 dirty_log_manual_caps;
-#endif
-
 static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		     uint64_t phys_offset, int wr_fract)
 {
@@ -106,10 +103,8 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	struct timespec get_dirty_log_total = (struct timespec){0};
 	struct timespec vcpu_dirty_total = (struct timespec){0};
 	struct timespec avg;
-#ifdef USE_CLEAR_DIRTY_LOG
 	struct kvm_enable_cap cap = {};
 	struct timespec clear_dirty_log_total = (struct timespec){0};
-#endif
 
 	vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
 
@@ -120,11 +115,11 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	host_num_pages = vm_num_host_pages(mode, guest_num_pages);
 	bmap = bitmap_alloc(host_num_pages);
 
-#ifdef USE_CLEAR_DIRTY_LOG
-	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
-	cap.args[0] = dirty_log_manual_caps;
-	vm_enable_cap(vm, &cap);
-#endif
+	if (dirty_log_manual_caps) {
+		cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
+		cap.args[0] = dirty_log_manual_caps;
+		vm_enable_cap(vm, &cap);
+	}
 
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
@@ -190,17 +185,17 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n",
 			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
 
-#ifdef USE_CLEAR_DIRTY_LOG
-		clock_gettime(CLOCK_MONOTONIC, &start);
-		kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
-				       host_num_pages);
+		if (dirty_log_manual_caps) {
+			clock_gettime(CLOCK_MONOTONIC, &start);
+			kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
+					       host_num_pages);
 
-		ts_diff = timespec_diff_now(start);
-		clear_dirty_log_total = timespec_add(clear_dirty_log_total,
-						     ts_diff);
-		pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n",
-			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
-#endif
+			ts_diff = timespec_diff_now(start);
+			clear_dirty_log_total = timespec_add(clear_dirty_log_total,
+							     ts_diff);
+			pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n",
+				iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+		}
 	}
 
 	/* Tell the vcpu thread to quit */
@@ -220,12 +215,12 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		iterations, get_dirty_log_total.tv_sec,
 		get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
 
-#ifdef USE_CLEAR_DIRTY_LOG
-	avg = timespec_div(clear_dirty_log_total, iterations);
-	pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
-		iterations, clear_dirty_log_total.tv_sec,
-		clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
-#endif
+	if (dirty_log_manual_caps) {
+		avg = timespec_div(clear_dirty_log_total, iterations);
+		pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+			iterations, clear_dirty_log_total.tv_sec,
+			clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+	}
 
 	free(bmap);
 	free(vcpu_threads);
@@ -284,16 +279,10 @@ int main(int argc, char *argv[])
 	int opt, i;
 	int wr_fract = 1;
 
-#ifdef USE_CLEAR_DIRTY_LOG
 	dirty_log_manual_caps =
 		kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
-	if (!dirty_log_manual_caps) {
-		print_skip("KVM_CLEAR_DIRTY_LOG not available");
-		exit(KSFT_SKIP);
-	}
 	dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
 				  KVM_DIRTY_LOG_INITIALLY_SET);
-#endif
 
 #ifdef __x86_64__
 	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
-- 
cgit v1.2.3


From ec2f18bb4783648041498b06d4bff222821efed1 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Wed, 11 Nov 2020 13:26:29 +0100
Subject: KVM: selftests: Make vm_create_default common

The code is almost 100% the same anyway. Just move it to common
and add a few arch-specific macros.

Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Andrew Jones <drjones@redhat.com>
Message-Id: <20201111122636.73346-5-drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h     | 23 +++++++++++++---
 .../testing/selftests/kvm/lib/aarch64/processor.c  | 17 ------------
 tools/testing/selftests/kvm/lib/kvm_util.c         | 26 ++++++++++++++++++
 tools/testing/selftests/kvm/lib/s390x/processor.c  | 22 ---------------
 tools/testing/selftests/kvm/lib/x86_64/processor.c | 32 ----------------------
 5 files changed, 45 insertions(+), 75 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 710009cc17fd..8154785196cb 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -45,13 +45,28 @@ enum vm_guest_mode {
 };
 
 #if defined(__aarch64__)
-#define VM_MODE_DEFAULT VM_MODE_P40V48_4K
+
+#define VM_MODE_DEFAULT			VM_MODE_P40V48_4K
+#define MIN_PAGE_SHIFT			12U
+#define ptes_per_page(page_size)	((page_size) / 8)
+
 #elif defined(__x86_64__)
-#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K
-#else
-#define VM_MODE_DEFAULT VM_MODE_P52V48_4K
+
+#define VM_MODE_DEFAULT			VM_MODE_PXXV48_4K
+#define MIN_PAGE_SHIFT			12U
+#define ptes_per_page(page_size)	((page_size) / 8)
+
+#elif defined(__s390x__)
+
+#define VM_MODE_DEFAULT			VM_MODE_P52V48_4K
+#define MIN_PAGE_SHIFT			12U
+#define ptes_per_page(page_size)	((page_size) / 16)
+
 #endif
 
+#define MIN_PAGE_SIZE		(1U << MIN_PAGE_SHIFT)
+#define PTES_PER_MIN_PAGE	ptes_per_page(MIN_PAGE_SIZE)
+
 #define vm_guest_mode_string(m) vm_guest_mode_string[m]
 extern const char * const vm_guest_mode_string[];
 
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index d6c32c328e9a..cee92d477dc0 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -5,8 +5,6 @@
  * Copyright (C) 2018, Red Hat, Inc.
  */
 
-#define _GNU_SOURCE /* for program_invocation_name */
-
 #include <linux/compiler.h>
 
 #include "kvm_util.h"
@@ -219,21 +217,6 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 	}
 }
 
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
-				 void *guest_code)
-{
-	uint64_t ptrs_per_4k_pte = 512;
-	uint64_t extra_pg_pages = (extra_mem_pages / ptrs_per_4k_pte) * 2;
-	struct kvm_vm *vm;
-
-	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
-
-	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-	vm_vcpu_add_default(vm, vcpuid, guest_code);
-
-	return vm;
-}
-
 void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *init)
 {
 	struct kvm_vcpu_init default_init = { .target = -1, };
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index a04302666b02..70676a305523 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2018, Google LLC.
  */
 
+#define _GNU_SOURCE /* for program_invocation_name */
 #include "test_util.h"
 #include "kvm_util.h"
 #include "kvm_util_internal.h"
@@ -281,6 +282,31 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	return vm;
 }
 
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+				 void *guest_code)
+{
+	/* The maximum page table size for a memory region will be when the
+	 * smallest pages are used. Considering each page contains x page
+	 * table descriptors, the total extra size for page tables (for extra
+	 * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller
+	 * than N/x*2.
+	 */
+	uint64_t extra_pg_pages = (extra_mem_pages / PTES_PER_MIN_PAGE) * 2;
+	struct kvm_vm *vm;
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+
+#ifdef __x86_64__
+	vm_create_irqchip(vm);
+#endif
+
+	vm_vcpu_add_default(vm, vcpuid, guest_code);
+
+	return vm;
+}
+
 /*
  * VM Restart
  *
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 7349bb2e1a24..0152f356c099 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -5,8 +5,6 @@
  * Copyright (C) 2019, Red Hat, Inc.
  */
 
-#define _GNU_SOURCE /* for program_invocation_name */
-
 #include "processor.h"
 #include "kvm_util.h"
 #include "../kvm_util_internal.h"
@@ -160,26 +158,6 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 	virt_dump_region(stream, vm, indent, vm->pgd);
 }
 
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
-				 void *guest_code)
-{
-	/*
-	 * The additional amount of pages required for the page tables is:
-	 * 1 * n / 256 + 4 * (n / 256) / 2048 + 4 * (n / 256) / 2048^2 + ...
-	 * which is definitely smaller than (n / 256) * 2.
-	 */
-	uint64_t extra_pg_pages = extra_mem_pages / 256 * 2;
-	struct kvm_vm *vm;
-
-	vm = vm_create(VM_MODE_DEFAULT,
-		       DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
-
-	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-	vm_vcpu_add_default(vm, vcpuid, guest_code);
-
-	return vm;
-}
-
 void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
 {
 	size_t stack_size =  DEFAULT_STACK_PGS * getpagesize();
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index d10c5c05bdf0..95e1a757c629 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -5,8 +5,6 @@
  * Copyright (C) 2018, Google LLC.
  */
 
-#define _GNU_SOURCE /* for program_invocation_name */
-
 #include "test_util.h"
 #include "kvm_util.h"
 #include "../kvm_util_internal.h"
@@ -731,36 +729,6 @@ void vcpu_set_cpuid(struct kvm_vm *vm,
 
 }
 
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
-				 void *guest_code)
-{
-	struct kvm_vm *vm;
-	/*
-	 * For x86 the maximum page table size for a memory region
-	 * will be when only 4K pages are used.  In that case the
-	 * total extra size for page tables (for extra N pages) will
-	 * be: N/512+N/512^2+N/512^3+... which is definitely smaller
-	 * than N/512*2.
-	 */
-	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
-
-	/* Create VM */
-	vm = vm_create(VM_MODE_DEFAULT,
-		       DEFAULT_GUEST_PHY_PAGES + extra_pg_pages,
-		       O_RDWR);
-
-	/* Setup guest code */
-	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-
-	/* Setup IRQ Chip */
-	vm_create_irqchip(vm);
-
-	/* Add the first vCPU. */
-	vm_vcpu_add_default(vm, vcpuid, guest_code);
-
-	return vm;
-}
-
 /*
  * VCPU Get MSR
  *
-- 
cgit v1.2.3


From 0aa9ec45d42779af711c7a209b5780ff7391b5bd Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Wed, 11 Nov 2020 13:26:30 +0100
Subject: KVM: selftests: Introduce vm_create_[default_]_with_vcpus

Introduce new vm_create variants that also takes a number of vcpus,
an amount of per-vcpu pages, and optionally a list of vcpuids. These
variants will create default VMs with enough additional pages to
cover the vcpu stacks, per-vcpu pages, and pagetable pages for all.
The new 'default' variant uses VM_MODE_DEFAULT, whereas the other
new variant accepts the mode as a parameter.

Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Andrew Jones <drjones@redhat.com>
Message-Id: <20201111122636.73346-6-drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h | 10 ++++++++
 tools/testing/selftests/kvm/lib/kvm_util.c     | 35 ++++++++++++++++++++++----
 2 files changed, 40 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 8154785196cb..dfa9d369e8fc 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -266,6 +266,16 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
 struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 				 void *guest_code);
 
+/* Same as vm_create_default, but can be used for more than one vcpu */
+struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages,
+					    uint32_t num_percpu_pages, void *guest_code,
+					    uint32_t vcpuids[]);
+
+/* Like vm_create_default_with_vcpus, but accepts mode as a parameter */
+struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+				    uint64_t extra_mem_pages, uint32_t num_percpu_pages,
+				    void *guest_code, uint32_t vcpuids[]);
+
 /*
  * Adds a vCPU with reasonable defaults (e.g. a stack)
  *
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 70676a305523..df2035ac54a6 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -282,8 +282,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	return vm;
 }
 
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
-				 void *guest_code)
+struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+				    uint64_t extra_mem_pages, uint32_t num_percpu_pages,
+				    void *guest_code, uint32_t vcpuids[])
 {
 	/* The maximum page table size for a memory region will be when the
 	 * smallest pages are used. Considering each page contains x page
@@ -291,10 +292,18 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 	 * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller
 	 * than N/x*2.
 	 */
-	uint64_t extra_pg_pages = (extra_mem_pages / PTES_PER_MIN_PAGE) * 2;
+	uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus;
+	uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2;
+	uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages;
 	struct kvm_vm *vm;
+	int i;
+
+	TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS),
+		    "nr_vcpus = %d too large for host, max-vcpus = %d",
+		    nr_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS));
 
-	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+	pages = vm_adjust_num_guest_pages(mode, pages);
+	vm = vm_create(mode, pages, O_RDWR);
 
 	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
 
@@ -302,11 +311,27 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 	vm_create_irqchip(vm);
 #endif
 
-	vm_vcpu_add_default(vm, vcpuid, guest_code);
+	for (i = 0; i < nr_vcpus; ++i)
+		vm_vcpu_add_default(vm, vcpuids ? vcpuids[i] : i, guest_code);
 
 	return vm;
 }
 
+struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages,
+					    uint32_t num_percpu_pages, void *guest_code,
+					    uint32_t vcpuids[])
+{
+	return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, extra_mem_pages,
+				    num_percpu_pages, guest_code, vcpuids);
+}
+
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+				 void *guest_code)
+{
+	return vm_create_default_with_vcpus(1, extra_mem_pages, 0, guest_code,
+					    (uint32_t []){ vcpuid });
+}
+
 /*
  * VM Restart
  *
-- 
cgit v1.2.3


From 87c5f35e5c958278174979f13a9e40d3c9962c0f Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Wed, 11 Nov 2020 13:26:34 +0100
Subject: KVM: selftests: Also build dirty_log_perf_test on AArch64

Signed-off-by: Andrew Jones <drjones@redhat.com>
Message-Id: <20201111122636.73346-10-drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 3d14ef77755e..4febf4d5ead9 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -70,6 +70,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/ge