copy.mode = 0;
r = ioctl(uffd, UFFDIO_COPY, ©);
- if (r == -1) {
- pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d with errno: %d\n",
+ /*
+ * With multiple vCPU threads fault on a single page and there are
+ * multiple readers for the UFFD, at least one of the UFFDIO_COPYs
+ * will fail with EEXIST: handle that case without signaling an
+ * error.
+ *
+ * Note that this also suppress any EEXISTs occurring from,
+ * e.g., the first UFFDIO_COPY/CONTINUEs on a page. That never
+ * happens here, but a realistic VMM might potentially maintain
+ * some external state to correctly surface EEXISTs to userspace
+ * (or prevent duplicate COPY/CONTINUEs in the first place).
+ */
+ if (r == -1 && errno != EEXIST) {
+ pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d, errno = %d\n",
addr, tid, errno);
return r;
}
cont.range.len = demand_paging_size;
r = ioctl(uffd, UFFDIO_CONTINUE, &cont);
- if (r == -1) {
- pr_info("Failed UFFDIO_CONTINUE in 0x%lx from thread %d with errno: %d\n",
+ /*
+ * With multiple vCPU threads fault on a single page and there are
+ * multiple readers for the UFFD, at least one of the UFFDIO_COPYs
+ * will fail with EEXIST: handle that case without signaling an
+ * error.
+ *
+ * Note that this also suppress any EEXISTs occurring from,
+ * e.g., the first UFFDIO_COPY/CONTINUEs on a page. That never
+ * happens here, but a realistic VMM might potentially maintain
+ * some external state to correctly surface EEXISTs to userspace
+ * (or prevent duplicate COPY/CONTINUEs in the first place).
+ */
+ if (r == -1 && errno != EEXIST) {
+ pr_info("Failed UFFDIO_CONTINUE in 0x%lx, thread %d, errno = %d\n",
addr, tid, errno);
return r;
}
struct test_params {
int uffd_mode;
+ bool single_uffd;
useconds_t uffd_delay;
+ int readers_per_uffd;
enum vm_mem_backing_src_type src_type;
bool partition_vcpu_memory_access;
};
struct memstress_vcpu_args *vcpu_args;
struct test_params *p = arg;
struct uffd_desc **uffd_descs = NULL;
+ uint64_t uffd_region_size;
struct timespec start;
struct timespec ts_diff;
double vcpu_paging_rate;
struct kvm_vm *vm;
- int i;
+ int i, num_uffds = 0;
vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
p->src_type, p->partition_vcpu_memory_access);
memset(guest_data_prototype, 0xAB, demand_paging_size);
if (p->uffd_mode == UFFDIO_REGISTER_MODE_MINOR) {
- for (i = 0; i < nr_vcpus; i++) {
+ num_uffds = p->single_uffd ? 1 : nr_vcpus;
+ for (i = 0; i < num_uffds; i++) {
vcpu_args = &memstress_args.vcpu_args[i];
prefault_mem(addr_gpa2alias(vm, vcpu_args->gpa),
vcpu_args->pages * memstress_args.guest_page_size);
}
if (p->uffd_mode) {
- uffd_descs = malloc(nr_vcpus * sizeof(struct uffd_desc *));
+ num_uffds = p->single_uffd ? 1 : nr_vcpus;
+ uffd_region_size = nr_vcpus * guest_percpu_mem_size / num_uffds;
+
+ uffd_descs = malloc(num_uffds * sizeof(struct uffd_desc *));
TEST_ASSERT(uffd_descs, "Memory allocation failed");
- for (i = 0; i < nr_vcpus; i++) {
+ for (i = 0; i < num_uffds; i++) {
+ struct memstress_vcpu_args *vcpu_args;
void *vcpu_hva;
vcpu_args = &memstress_args.vcpu_args[i];
*/
uffd_descs[i] = uffd_setup_demand_paging(
p->uffd_mode, p->uffd_delay, vcpu_hva,
- vcpu_args->pages * memstress_args.guest_page_size,
+ uffd_region_size,
+ p->readers_per_uffd,
&handle_uffd_page_request);
}
}
if (p->uffd_mode) {
/* Tell the user fault fd handler threads to quit */
- for (i = 0; i < nr_vcpus; i++)
+ for (i = 0; i < num_uffds; i++)
uffd_stop_demand_paging(uffd_descs[i]);
}
static void help(char *name)
{
puts("");
- printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n"
- " [-b memory] [-s type] [-v vcpus] [-c cpu_list] [-o]\n", name);
+ printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-a]\n"
+ " [-d uffd_delay_usec] [-r readers_per_uffd] [-b memory]\n"
+ " [-s type] [-v vcpus] [-c cpu_list] [-o]\n", name);
guest_modes_help();
printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n"
" UFFD registration mode: 'MISSING' or 'MINOR'.\n");
kvm_print_vcpu_pinning_help();
+ printf(" -a: Use a single userfaultfd for all of guest memory, instead of\n"
+ " creating one for each region paged by a unique vCPU\n"
+ " Set implicitly with -o, and no effect without -u.\n");
printf(" -d: add a delay in usec to the User Fault\n"
" FD handler to simulate demand paging\n"
" overheads. Ignored without -u.\n");
+ printf(" -r: Set the number of reader threads per uffd.\n");
printf(" -b: specify the size of the memory region which should be\n"
" demand paged by each vCPU. e.g. 10M or 3G.\n"
" Default: 1G\n");
struct test_params p = {
.src_type = DEFAULT_VM_MEM_SRC,
.partition_vcpu_memory_access = true,
+ .readers_per_uffd = 1,
+ .single_uffd = false,
};
int opt;
guest_modes_append_default();
- while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:c:o")) != -1) {
+ while ((opt = getopt(argc, argv, "ahom:u:d:b:s:v:c:r:")) != -1) {
switch (opt) {
case 'm':
guest_modes_cmdline(optarg);
p.uffd_mode = UFFDIO_REGISTER_MODE_MINOR;
TEST_ASSERT(p.uffd_mode, "UFFD mode must be 'MISSING' or 'MINOR'.");
break;
+ case 'a':
+ p.single_uffd = true;
+ break;
case 'd':
p.uffd_delay = strtoul(optarg, NULL, 0);
TEST_ASSERT(p.uffd_delay >= 0, "A negative UFFD delay is not supported.");
break;
case 'o':
p.partition_vcpu_memory_access = false;
+ p.single_uffd = true;
+ break;
+ case 'r':
+ p.readers_per_uffd = atoi(optarg);
+ TEST_ASSERT(p.readers_per_uffd >= 1,
+ "Invalid number of readers per uffd %d: must be >=1",
+ p.readers_per_uffd);
break;
case 'h':
default:
static void *uffd_handler_thread_fn(void *arg)
{
- struct uffd_desc *uffd_desc = (struct uffd_desc *)arg;
- int uffd = uffd_desc->uffd;
- int pipefd = uffd_desc->pipefds[0];
- useconds_t delay = uffd_desc->delay;
+ struct uffd_reader_args *reader_args = (struct uffd_reader_args *)arg;
+ int uffd = reader_args->uffd;
int64_t pages = 0;
struct timespec start;
struct timespec ts_diff;
pollfd[0].fd = uffd;
pollfd[0].events = POLLIN;
- pollfd[1].fd = pipefd;
+ pollfd[1].fd = reader_args->pipe;
pollfd[1].events = POLLIN;
r = poll(pollfd, 2, -1);
if (!(msg.event & UFFD_EVENT_PAGEFAULT))
continue;
- if (delay)
- usleep(delay);
- r = uffd_desc->handler(uffd_desc->uffd_mode, uffd, &msg);
+ if (reader_args->delay)
+ usleep(reader_args->delay);
+ r = reader_args->handler(reader_args->uffd_mode, uffd, &msg);
if (r < 0)
return NULL;
pages++;
struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
void *hva, uint64_t len,
+ uint64_t num_readers,
uffd_handler_t handler)
{
struct uffd_desc *uffd_desc;
struct uffdio_api uffdio_api;
struct uffdio_register uffdio_register;
uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY;
- int ret;
+ int ret, i;
PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n",
is_minor ? "MINOR" : "MISSING",
is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY");
uffd_desc = malloc(sizeof(struct uffd_desc));
- TEST_ASSERT(uffd_desc, "malloc failed");
+ TEST_ASSERT(uffd_desc, "Failed to malloc uffd descriptor");
+
+ uffd_desc->pipefds = calloc(sizeof(int), num_readers);
+ TEST_ASSERT(uffd_desc->pipefds, "Failed to alloc pipes");
+
+ uffd_desc->readers = calloc(sizeof(pthread_t), num_readers);
+ TEST_ASSERT(uffd_desc->readers, "Failed to alloc reader threads");
+
+ uffd_desc->reader_args = calloc(sizeof(struct uffd_reader_args), num_readers);
+ TEST_ASSERT(uffd_desc->reader_args, "Failed to alloc reader_args");
+
+ uffd_desc->num_readers = num_readers;
/* In order to get minor faults, prefault via the alias. */
if (is_minor)
TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) ==
expected_ioctls, "missing userfaultfd ioctls");
- ret = pipe2(uffd_desc->pipefds, O_CLOEXEC | O_NONBLOCK);
- TEST_ASSERT(!ret, "Failed to set up pipefd");
-
- uffd_desc->uffd_mode = uffd_mode;
uffd_desc->uffd = uffd;
- uffd_desc->delay = delay;
- uffd_desc->handler = handler;
- pthread_create(&uffd_desc->thread, NULL, uffd_handler_thread_fn,
- uffd_desc);
+ for (i = 0; i < uffd_desc->num_readers; ++i) {
+ int pipes[2];
+
+ ret = pipe2((int *) &pipes, O_CLOEXEC | O_NONBLOCK);
+ TEST_ASSERT(!ret, "Failed to set up pipefd %i for uffd_desc %p",
+ i, uffd_desc);
- PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
- hva, hva + len);
+ uffd_desc->pipefds[i] = pipes[1];
+
+ uffd_desc->reader_args[i].uffd_mode = uffd_mode;
+ uffd_desc->reader_args[i].uffd = uffd;
+ uffd_desc->reader_args[i].delay = delay;
+ uffd_desc->reader_args[i].handler = handler;
+ uffd_desc->reader_args[i].pipe = pipes[0];
+
+ pthread_create(&uffd_desc->readers[i], NULL, uffd_handler_thread_fn,
+ &uffd_desc->reader_args[i]);
+
+ PER_VCPU_DEBUG("Created uffd thread %i for HVA range [%p, %p)\n",
+ i, hva, hva + len);
+ }
return uffd_desc;
}
void uffd_stop_demand_paging(struct uffd_desc *uffd)
{
char c = 0;
- int ret;
+ int i;
- ret = write(uffd->pipefds[1], &c, 1);
- TEST_ASSERT(ret == 1, "Unable to write to pipefd");
+ for (i = 0; i < uffd->num_readers; ++i)
+ TEST_ASSERT(write(uffd->pipefds[i], &c, 1) == 1,
+ "Unable to write to pipefd %i for uffd_desc %p", i, uffd);
- ret = pthread_join(uffd->thread, NULL);
- TEST_ASSERT(ret == 0, "Pthread_join failed.");
+ for (i = 0; i < uffd->num_readers; ++i)
+ TEST_ASSERT(!pthread_join(uffd->readers[i], NULL),
+ "Pthread_join failed on reader %i for uffd_desc %p", i, uffd);
close(uffd->uffd);
- close(uffd->pipefds[1]);
- close(uffd->pipefds[0]);
+ for (i = 0; i < uffd->num_readers; ++i) {
+ close(uffd->pipefds[i]);
+ close(uffd->reader_args[i].pipe);
+ }
+ free(uffd->pipefds);
+ free(uffd->readers);
+ free(uffd->reader_args);
free(uffd);
}
projects / linux.git / commitdiff