#include <stdio.h>
#include <stdlib.h>
-#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"
+#include "test_util.h"
+#include "guest_modes.h"
#include "processor.h"
#define VCPU_ID 1
# define test_and_clear_bit_le test_and_clear_bit
#endif
+#define TEST_DIRTY_RING_COUNT 65536
+
+#define SIG_IPI SIGUSR1
+
/*
* Guest/Host shared variables. Ensure addr_gva2hva() and/or
* sync_global_to/from_guest() are used when accessing from
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 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
+ * 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,
/* 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 */
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)
+{
+ 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
+ */
+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)
{
kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
}
+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)
+{
+ /* This makes sure that hardware PML cache flushed */
+ vcpu_kick();
+ 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;
+ 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);
+
+ 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);
+
+ 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);
+}
+
+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 ||
+ (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 %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 {
+ 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 */
/* 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, int ret, int err);
+ void (*before_vcpu_join) (void);
} 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,
+ },
+ {
+ .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,
},
};
mode->collect_dirty_pages(vm, slot, bitmap, num_pages);
}
+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, 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)
{
uint64_t i;
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;
- struct kvm_run *run;
+ struct kvm_signal_mask *sigmask = alloca(offsetof(struct kvm_signal_mask, sigset)
+ + sizeof(sigset_t));
+ sigset_t *sigset = (sigset_t *) &sigmask->sigset;
- run = vcpu_state(vm, VCPU_ID);
+ 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);
- generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
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);
- 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));
+ 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);
}
pr_info("Dirtied %"PRIu64" pages\n", pages_count);
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;
}
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);
#define DIRTY_MEM_BITS 30 /* 1G */
#define PAGE_SHIFT_4K 12
-static void run_test(enum vm_guest_mode mode, unsigned long iterations,
- unsigned long interval, uint64_t phys_offset)
+struct test_params {
+ unsigned long iterations;
+ unsigned long interval;
+ uint64_t phys_offset;
+};
+
+static void run_test(enum vm_guest_mode mode, void *arg)
{
- pthread_t vcpu_thread;
+ struct test_params *p = arg;
struct kvm_vm *vm;
unsigned long *bmap;
host_page_size = getpagesize();
host_num_pages = vm_num_host_pages(mode, guest_num_pages);
- if (!phys_offset) {
+ if (!p->phys_offset) {
guest_test_phys_mem = (vm_get_max_gfn(vm) -
guest_num_pages) * guest_page_size;
guest_test_phys_mem &= ~(host_page_size - 1);
} else {
- guest_test_phys_mem = phys_offset;
+ guest_test_phys_mem = p->phys_offset;
}
#ifdef __s390x__
/* Cache the HVA pointer of the region */
host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem);
-#ifdef __x86_64__
- vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-#endif
ucall_init(vm, NULL);
/* Export the shared variables to the guest */
pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
- while (iteration < iterations) {
+ while (iteration < p->iterations) {
/* Give the vcpu thread some time to dirty some pages */
- usleep(interval * 1000);
+ usleep(p->interval * 1000);
log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX,
bmap, host_num_pages);
vm_dirty_log_verify(mode, bmap);
/* 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"), "
kvm_vm_free(vm);
}
-struct guest_mode {
- bool supported;
- bool enabled;
-};
-static struct guest_mode guest_modes[NUM_VM_MODES];
-
-#define guest_mode_init(mode, supported, enabled) ({ \
- guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
-})
-
static void help(char *name)
{
- int i;
-
puts("");
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",
printf(" -M: specify the host logging mode "
"(default: run all log modes). Supported modes: \n\t");
log_modes_dump();
- printf(" -m: specify the guest mode ID to test "
- "(default: test all supported modes)\n"
- " This option may be used multiple times.\n"
- " Guest mode IDs:\n");
- for (i = 0; i < NUM_VM_MODES; ++i) {
- printf(" %d: %s%s\n", i, vm_guest_mode_string(i),
- guest_modes[i].supported ? " (supported)" : "");
- }
+ guest_modes_help();
puts("");
exit(0);
}
int main(int argc, char *argv[])
{
- unsigned long iterations = TEST_HOST_LOOP_N;
- unsigned long interval = TEST_HOST_LOOP_INTERVAL;
- bool mode_selected = false;
- uint64_t phys_offset = 0;
- unsigned int mode;
- int opt, i, j;
+ struct test_params p = {
+ .iterations = TEST_HOST_LOOP_N,
+ .interval = TEST_HOST_LOOP_INTERVAL,
+ };
+ int opt, i;
-#ifdef __x86_64__
- guest_mode_init(VM_MODE_PXXV48_4K, true, true);
-#endif
-#ifdef __aarch64__
- guest_mode_init(VM_MODE_P40V48_4K, true, true);
- guest_mode_init(VM_MODE_P40V48_64K, true, true);
-
- {
- unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+ sem_init(&dirty_ring_vcpu_stop, 0, 0);
+ sem_init(&dirty_ring_vcpu_cont, 0, 0);
- if (limit >= 52)
- guest_mode_init(VM_MODE_P52V48_64K, true, true);
- if (limit >= 48) {
- guest_mode_init(VM_MODE_P48V48_4K, true, true);
- guest_mode_init(VM_MODE_P48V48_64K, true, true);
- }
- }
-#endif
-#ifdef __s390x__
- guest_mode_init(VM_MODE_P40V48_4K, true, true);
-#endif
+ guest_modes_append_default();
- 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);
+ p.iterations = strtol(optarg, NULL, 10);
break;
case 'I':
- interval = strtol(optarg, NULL, 10);
+ p.interval = strtol(optarg, NULL, 10);
break;
case 'p':
- phys_offset = strtoull(optarg, NULL, 0);
+ p.phys_offset = strtoull(optarg, NULL, 0);
break;
case 'm':
- if (!mode_selected) {
- for (i = 0; i < NUM_VM_MODES; ++i)
- guest_modes[i].enabled = false;
- mode_selected = true;
- }
- mode = strtoul(optarg, NULL, 10);
- TEST_ASSERT(mode < NUM_VM_MODES,
- "Guest mode ID %d too big", mode);
- guest_modes[mode].enabled = true;
+ guest_modes_cmdline(optarg);
break;
case 'M':
if (!strcmp(optarg, "all")) {
}
}
- TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
- TEST_ASSERT(interval > 0, "Interval must be greater than zero");
+ TEST_ASSERT(p.iterations > 2, "Iterations must be greater than two");
+ TEST_ASSERT(p.interval > 0, "Interval must be greater than zero");
pr_info("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
- iterations, interval);
+ p.iterations, p.interval);
srandom(time(0));
- for (i = 0; i < NUM_VM_MODES; ++i) {
- if (!guest_modes[i].enabled)
- continue;
- TEST_ASSERT(guest_modes[i].supported,
- "Guest mode ID %d (%s) not supported.",
- i, vm_guest_mode_string(i));
- if (host_log_mode_option == LOG_MODE_ALL) {
- /* Run each log mode */
- for (j = 0; j < LOG_MODE_NUM; j++) {
- pr_info("Testing Log Mode '%s'\n",
- log_modes[j].name);
- host_log_mode = j;
- run_test(i, iterations, interval, phys_offset);
- }
- } else {
- host_log_mode = host_log_mode_option;
- run_test(i, iterations, interval, phys_offset);
+ if (host_log_mode_option == LOG_MODE_ALL) {
+ /* Run each log mode */
+ for (i = 0; i < LOG_MODE_NUM; i++) {
+ pr_info("Testing Log Mode '%s'\n", log_modes[i].name);
+ host_log_mode = i;
+ for_each_guest_mode(run_test, &p);
}
+ } else {
+ host_log_mode = host_log_mode_option;
+ for_each_guest_mode(run_test, &p);
}
return 0;