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

@@ -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

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);
 

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

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);