[PATCH v7 4/4] KVM: selftests: Add selftests for dirty quota throttling

[Shivam Kumar <shivam.kumar1@nutanix.com>]

Add selftests for dirty quota throttling with an optional -d parameter
to configure by what value dirty quota should be incremented after
each dirty quota exit. With very small intervals, a smaller value of
dirty quota can ensure that the dirty quota exit code is tested. A zero
value disables dirty quota throttling and thus dirty logging, without
dirty quota throttling, can be tested.

Suggested-by: Shaju Abraham <shaju.abraham@nutanix.com>
Suggested-by: Manish Mishra <manish.mishra@nutanix.com>
Co-developed-by: Anurag Madnawat <anurag.madnawat@nutanix.com>
Signed-off-by: Anurag Madnawat <anurag.madnawat@nutanix.com>
Signed-off-by: Shivam Kumar <shivam.kumar1@nutanix.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c  | 33 +++++++++++-
 .../selftests/kvm/include/kvm_util_base.h     |  4 ++
 tools/testing/selftests/kvm/lib/kvm_util.c    | 53 +++++++++++++++++++
 3 files changed, 88 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index b5234d6efbe1..a85ca6554d17 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -64,6 +64,8 @@
 
 #define SIG_IPI SIGUSR1
 
+#define TEST_DIRTY_QUOTA_INCREMENT		8
+
 /*
  * Guest/Host shared variables. Ensure addr_gva2hva() and/or
  * sync_global_to/from_guest() are used when accessing from
@@ -190,6 +192,7 @@ 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 uint32_t test_dirty_ring_count = TEST_DIRTY_RING_COUNT;
+static uint64_t test_dirty_quota_increment = TEST_DIRTY_QUOTA_INCREMENT;
 
 static void vcpu_kick(void)
 {
@@ -209,6 +212,13 @@ static void sem_wait_until(sem_t *sem)
 	while (ret == -1 && errno == EINTR);
 }
 
+static void set_dirty_quota(struct kvm_vm *vm, uint64_t dirty_quota)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+	vcpu_set_dirty_quota(run, dirty_quota);
+}
+
 static bool clear_log_supported(void)
 {
 	return kvm_has_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
@@ -256,7 +266,11 @@ static void default_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
 	TEST_ASSERT(ret == 0 || (ret == -1 && err == EINTR),
 		    "vcpu run failed: errno=%d", err);
 
-	TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
+	if (test_dirty_quota_increment &&
+		run->exit_reason == KVM_EXIT_DIRTY_QUOTA_EXHAUSTED)
+		vcpu_handle_dirty_quota_exit(run, test_dirty_quota_increment);
+	else
+		TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
 		    "Invalid guest sync status: exit_reason=%s\n",
 		    exit_reason_str(run->exit_reason));
 
@@ -374,6 +388,9 @@ static void dirty_ring_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
 	if (get_ucall(vcpu, NULL) == UCALL_SYNC) {
 		/* We should allow this to continue */
 		;
+	} else if (test_dirty_quota_increment &&
+		run->exit_reason == KVM_EXIT_DIRTY_QUOTA_EXHAUSTED) {
+		vcpu_handle_dirty_quota_exit(run, test_dirty_quota_increment);
 	} else if (run->exit_reason == KVM_EXIT_DIRTY_RING_FULL ||
 		   (ret == -1 && err == EINTR)) {
 		/* Update the flag first before pause */
@@ -764,6 +781,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	sync_global_to_guest(vm, guest_test_virt_mem);
 	sync_global_to_guest(vm, guest_num_pages);
 
+	/* Initialise dirty quota */
+	if (test_dirty_quota_increment)
+		set_dirty_quota(vm, test_dirty_quota_increment);
+
 	/* Start the iterations */
 	iteration = 1;
 	sync_global_to_guest(vm, iteration);
@@ -805,6 +826,9 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	/* Tell the vcpu thread to quit */
 	host_quit = true;
 	log_mode_before_vcpu_join();
+	/* Terminate dirty quota throttling */
+	if (test_dirty_quota_increment)
+		set_dirty_quota(vm, 0);
 	pthread_join(vcpu_thread, NULL);
 
 	pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
@@ -826,6 +850,8 @@ static void help(char *name)
 	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(" -q: specify incemental dirty quota (default: %"PRIu32")\n",
+	       TEST_DIRTY_QUOTA_INCREMENT);
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
 	       TEST_HOST_LOOP_N);
 	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
@@ -854,11 +880,14 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "c:hi:I:p:m:M:")) != -1) {
+	while ((opt = getopt(argc, argv, "c:q:hi:I:p:m:M:")) != -1) {
 		switch (opt) {
 		case 'c':
 			test_dirty_ring_count = strtol(optarg, NULL, 10);
 			break;
+		case 'q':
+			test_dirty_quota_increment = strtol(optarg, NULL, 10);
+			break;
 		case 'i':
 			p.iterations = strtol(optarg, NULL, 10);
 			break;
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index e42a09cd24a0..d8eee61a9a7c 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -838,4 +838,8 @@ static inline int __vm_disable_nx_huge_pages(struct kvm_vm *vm)
 	return __vm_enable_cap(vm, KVM_CAP_VM_DISABLE_NX_HUGE_PAGES, 0);
 }
 
+void vcpu_set_dirty_quota(struct kvm_run *run, uint64_t dirty_quota);
+void vcpu_handle_dirty_quota_exit(struct kvm_run *run,
+			uint64_t test_dirty_quota_increment);
+
 #endif /* SELFTEST_KVM_UTIL_BASE_H */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index f1cb1627161f..2a60c7bdc778 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 
 #define KVM_UTIL_MIN_PFN	2
+#define PML_BUFFER_SIZE	512
 
 static int vcpu_mmap_sz(void);
 
@@ -1745,6 +1746,7 @@ static struct exit_reason {
 	{KVM_EXIT_X86_RDMSR, "RDMSR"},
 	{KVM_EXIT_X86_WRMSR, "WRMSR"},
 	{KVM_EXIT_XEN, "XEN"},
+	{KVM_EXIT_DIRTY_QUOTA_EXHAUSTED, "DIRTY_QUOTA_EXHAUSTED"},
 #ifdef KVM_EXIT_MEMORY_NOT_PRESENT
 	{KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"},
 #endif
@@ -2021,3 +2023,54 @@ void __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data,
 		break;
 	}
 }
+
+bool kvm_is_pml_enabled(void)
+{
+	return is_intel_cpu() && get_kvm_intel_param_bool("pml");
+}
+
+void vcpu_set_dirty_quota(struct kvm_run *run, uint64_t dirty_quota)
+{
+	run->dirty_quota = dirty_quota;
+
+	if (dirty_quota)
+		pr_info("Dirty quota throttling enabled with initial quota %lu\n",
+			dirty_quota);
+	else
+		pr_info("Dirty quota throttling disabled\n");
+}
+
+void vcpu_handle_dirty_quota_exit(struct kvm_run *run,
+			uint64_t test_dirty_quota_increment)
+{
+	uint64_t quota = run->dirty_quota_exit.quota;
+	uint64_t count = run->dirty_quota_exit.count;
+
+	/*
+	 * Allow certain pages of overrun, KVM is allowed to dirty multiple
+	 * pages before exiting to userspace, e.g. when emulating an
+	 * instruction that performs multiple memory accesses.
+	 */
+	uint64_t buffer;
+
+	/*
+	 * When Intel's Page-Modification Logging (PML) is enabled, the CPU may
+	 * dirty up to 512 pages (number of entries in the PML buffer) without
+	 * exiting, thus KVM may effectively dirty that many pages before
+	 * enforcing the dirty quota.
+	 */
+#ifdef __x86_64__
+	if (kvm_is_pml_enabled(void))
+		buffer = PML_BUFFER_SIZE;
+#endif
+
+	TEST_ASSERT(count <= (quota + buffer),
+			"KVM dirtied too many pages: count=%lu, quota=%lu, buffer=%lu\n",
+			count, quota, buffer);
+
+	TEST_ASSERT(count >= quota,
+			"Dirty quota exit happened with quota yet to be exhausted: count=%lu, quota=%lu\n",
+			count, quota);
+
+	run->dirty_quota = count + test_dirty_quota_increment;
+}
-- 
2.22.3