KVM: selftests: Add demand paging content to the demand paging test

The demand paging test is currently a simple page access test which, while
potentially useful, doesn't add much versus the existing dirty logging
test. To improve the demand paging test, add a basic userfaultfd demand
paging implementation.

Signed-off-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/tools/arch/x86/include/asm/unistd_64.h b/tools/arch/x86/include/asm/unistd_64.h
index cb52a3a..4205ed4 100644 (file)
--- a/tools/arch/x86/include/asm/unistd_64.h
+++ b/tools/arch/x86/include/asm/unistd_64.h
@@ -1,4 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NR_userfaultfd
+#define __NR_userfaultfd 282
+#endif
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 298
 #endif

diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index e3d4917..6be9793 100644 (file)
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -11,16 +11,21 @@
 
 #include <stdio.h>
 #include <stdlib.h>
+#include <sys/syscall.h>
 #include <unistd.h>
+#include <asm/unistd.h>
 #include <time.h>
+#include <poll.h>
 #include <pthread.h>
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
+#include <linux/userfaultfd.h>
 
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
 
+#ifdef __NR_userfaultfd
 #define VCPU_ID                                1
 
 /* The memory slot index demand page */
@@ -39,6 +44,8 @@ static uint64_t host_page_size;
 static uint64_t guest_page_size;
 static uint64_t guest_num_pages;
 
+static char *guest_data_prototype;
+
 /*
  * Guest physical memory offset of the testing memory slot.
  * This will be set to the topmost valid physical address minus
@@ -110,13 +117,169 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
        return vm;
 }
 
+static int handle_uffd_page_request(int uffd, uint64_t addr)
+{
+       pid_t tid;
+       struct uffdio_copy copy;
+       int r;
+
+       tid = syscall(__NR_gettid);
+
+       copy.src = (uint64_t)guest_data_prototype;
+       copy.dst = addr;
+       copy.len = host_page_size;
+       copy.mode = 0;
+
+       r = ioctl(uffd, UFFDIO_COPY, &copy);
+       if (r == -1) {
+               DEBUG("Failed Paged in 0x%lx from thread %d with errno: %d\n",
+                     addr, tid, errno);
+               return r;
+       }
+
+       return 0;
+}
+
+bool quit_uffd_thread;
+
+struct uffd_handler_args {
+       int uffd;
+       int pipefd;
+};
+
+static void *uffd_handler_thread_fn(void *arg)
+{
+       struct uffd_handler_args *uffd_args = (struct uffd_handler_args *)arg;
+       int uffd = uffd_args->uffd;
+       int pipefd = uffd_args->pipefd;
+       int64_t pages = 0;
+
+       while (!quit_uffd_thread) {
+               struct uffd_msg msg;
+               struct pollfd pollfd[2];
+               char tmp_chr;
+               int r;
+               uint64_t addr;
+
+               pollfd[0].fd = uffd;
+               pollfd[0].events = POLLIN;
+               pollfd[1].fd = pipefd;
+               pollfd[1].events = POLLIN;
+
+               r = poll(pollfd, 2, -1);
+               switch (r) {
+               case -1:
+                       DEBUG("poll err");
+                       continue;
+               case 0:
+                       continue;
+               case 1:
+                       break;
+               default:
+                       DEBUG("Polling uffd returned %d", r);
+                       return NULL;
+               }
+
+               if (pollfd[0].revents & POLLERR) {
+                       DEBUG("uffd revents has POLLERR");
+                       return NULL;
+               }
+
+               if (pollfd[1].revents & POLLIN) {
+                       r = read(pollfd[1].fd, &tmp_chr, 1);
+                       TEST_ASSERT(r == 1,
+                                   "Error reading pipefd in UFFD thread\n");
+                       return NULL;
+               }
+
+               if (!pollfd[0].revents & POLLIN)
+                       continue;
+
+               r = read(uffd, &msg, sizeof(msg));
+               if (r == -1) {
+                       if (errno == EAGAIN)
+                               continue;
+                       DEBUG("Read of uffd gor errno %d", errno);
+                       return NULL;
+               }
+
+               if (r != sizeof(msg)) {
+                       DEBUG("Read on uffd returned unexpected size: %d bytes",
+                             r);
+                       return NULL;
+               }
+
+               if (!(msg.event & UFFD_EVENT_PAGEFAULT))
+                       continue;
+
+               addr =  msg.arg.pagefault.address;
+               r = handle_uffd_page_request(uffd, addr);
+               if (r < 0)
+                       return NULL;
+               pages++;
+       }
+
+       return NULL;
+}
+
+static int setup_demand_paging(struct kvm_vm *vm,
+                              pthread_t *uffd_handler_thread, int pipefd)
+{
+       int uffd;
+       struct uffdio_api uffdio_api;
+       struct uffdio_register uffdio_register;
+       struct uffd_handler_args uffd_args;
+
+       guest_data_prototype = malloc(host_page_size);
+       TEST_ASSERT(guest_data_prototype,
+                   "Failed to allocate buffer for guest data pattern");
+       memset(guest_data_prototype, 0xAB, host_page_size);
+
+       uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+       if (uffd == -1) {
+               DEBUG("uffd creation failed\n");
+               return -1;
+       }
+
+       uffdio_api.api = UFFD_API;
+       uffdio_api.features = 0;
+       if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) {
+               DEBUG("ioctl uffdio_api failed\n");
+               return -1;
+       }
+
+       uffdio_register.range.start = (uint64_t)host_test_mem;
+       uffdio_register.range.len = host_num_pages * host_page_size;
+       uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+       if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) {
+               DEBUG("ioctl uffdio_register failed\n");
+               return -1;
+       }
+
+       if ((uffdio_register.ioctls & UFFD_API_RANGE_IOCTLS) !=
+                       UFFD_API_RANGE_IOCTLS) {
+               DEBUG("unexpected userfaultfd ioctl set\n");
+               return -1;
+       }
+
+       uffd_args.uffd = uffd;
+       uffd_args.pipefd = pipefd;
+       pthread_create(uffd_handler_thread, NULL, uffd_handler_thread_fn,
+                      &uffd_args);
+
+       return 0;
+}
+
 #define GUEST_MEM_SHIFT 30 /* 1G */
 #define PAGE_SHIFT_4K  12
 
-static void run_test(enum vm_guest_mode mode)
+static void run_test(enum vm_guest_mode mode, bool use_uffd)
 {
        pthread_t vcpu_thread;
+       pthread_t uffd_handler_thread;
+       int pipefd[2];
        struct kvm_vm *vm;
+       int r;
 
        /*
         * We reserve page table for 2 times of extra dirty mem which
@@ -173,6 +336,16 @@ static void run_test(enum vm_guest_mode mode)
        /* Cache the HVA pointer of the region */
        host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem);
 
+       if (use_uffd) {
+               /* Set up user fault fd to handle demand paging requests. */
+               r = pipe2(pipefd, O_CLOEXEC | O_NONBLOCK);
+               TEST_ASSERT(!r, "Failed to set up pipefd");
+
+               r = setup_demand_paging(vm, &uffd_handler_thread, pipefd[0]);
+               if (r < 0)
+                       exit(-r);
+       }
+
 #ifdef __x86_64__
        vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 #endif
@@ -191,8 +364,20 @@ static void run_test(enum vm_guest_mode mode)
        /* Wait for the vcpu thread to quit */
        pthread_join(vcpu_thread, NULL);
 
+       if (use_uffd) {
+               char c;
+
+               /* Tell the user fault fd handler thread to quit */
+               r = write(pipefd[1], &c, 1);
+               TEST_ASSERT(r == 1, "Unable to write to pipefd");
+
+               pthread_join(uffd_handler_thread, NULL);
+       }
+
        ucall_uninit(vm);
        kvm_vm_free(vm);
+
+       free(guest_data_prototype);
 }
 
 struct guest_mode {
@@ -210,7 +395,7 @@ static void help(char *name)
        int i;
 
        puts("");
-       printf("usage: %s [-h] [-m mode]\n", name);
+       printf("usage: %s [-h] [-m mode] [-u]\n", name);
        printf(" -m: specify the guest mode ID to test\n"
               "     (default: test all supported modes)\n"
               "     This option may be used multiple times.\n"
@@ -219,6 +404,7 @@ static void help(char *name)
                printf("         %d:    %s%s\n", i, vm_guest_mode_string(i),
                       guest_modes[i].supported ? " (supported)" : "");
        }
+       printf(" -u: Use User Fault FD to handle vCPU page faults.\n");
        puts("");
        exit(0);
 }
@@ -228,6 +414,7 @@ int main(int argc, char *argv[])
        bool mode_selected = false;
        unsigned int mode;
        int opt, i;
+       bool use_uffd = false;
 
 #ifdef __x86_64__
        guest_mode_init(VM_MODE_PXXV48_4K, true, true);
@@ -250,7 +437,7 @@ int main(int argc, char *argv[])
        guest_mode_init(VM_MODE_P40V48_4K, true, true);
 #endif
 
-       while ((opt = getopt(argc, argv, "hm:")) != -1) {
+       while ((opt = getopt(argc, argv, "hm:u")) != -1) {
                switch (opt) {
                case 'm':
                        if (!mode_selected) {
@@ -263,6 +450,9 @@ int main(int argc, char *argv[])
                                    "Guest mode ID %d too big", mode);
                        guest_modes[mode].enabled = true;
                        break;
+               case 'u':
+                       use_uffd = true;
+                       break;
                case 'h':
                default:
                        help(argv[0]);
@@ -276,8 +466,20 @@ int main(int argc, char *argv[])
                TEST_ASSERT(guest_modes[i].supported,
                            "Guest mode ID %d (%s) not supported.",
                            i, vm_guest_mode_string(i));
-               run_test(i);
+               run_test(i, use_uffd);
        }
 
        return 0;
 }
+
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+        printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
+        return KSFT_SKIP;
+}
+
+#endif /* __NR_userfaultfd */