Re: [PATCH v2 5/5] KVM: selftests: test userfaultfd minor for guest_memfd
From: Nikita Kalyazin
Date: Thu Apr 03 2025 - 13:03:01 EST
On 02/04/2025 22:10, James Houghton wrote:
On Wed, Apr 2, 2025 at 9:08 AM Nikita Kalyazin <kalyazin@xxxxxxxxxx> wrote:
The test demonstrates that a minor userfaultfd event in guest_memfd can
be resolved via a memcpy followed by a UFFDIO_CONTINUE ioctl.
Signed-off-by: Nikita Kalyazin <kalyazin@xxxxxxxxxx>
---
.../testing/selftests/kvm/guest_memfd_test.c | 94 +++++++++++++++++++
1 file changed, 94 insertions(+)
diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
index 38c501e49e0e..9b47b796f3aa 100644
--- a/tools/testing/selftests/kvm/guest_memfd_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -10,12 +10,16 @@
#include <errno.h>
#include <stdio.h>
#include <fcntl.h>
+#include <pthread.h>
#include <linux/bitmap.h>
#include <linux/falloc.h>
+#include <linux/userfaultfd.h>
#include <sys/mman.h>
#include <sys/types.h>
#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/ioctl.h>
#include "kvm_util.h"
#include "test_util.h"
@@ -206,6 +210,93 @@ static void test_create_guest_memfd_multiple(struct kvm_vm *vm)
close(fd1);
}
+struct fault_args {
+ char *addr;
+ volatile char value;
I think you should/must put volatile on `addr` and not on `value`.
This was to prevent the compiler from omitting the write to the value,
because it's never read later on.
+};
+
+static void *fault_thread_fn(void *arg)
+{
+ struct fault_args *args = arg;
+
+ /* Trigger page fault */
+ args->value = *args->addr;
+ return NULL;
+}
+
+static void test_uffd_missing(int fd, size_t page_size, size_t total_size)
test_uffd_minor? :)
+{
+ struct uffdio_register uffd_reg;
+ struct uffdio_continue uffd_cont;
+ struct uffd_msg msg;
+ struct fault_args args;
+ pthread_t fault_thread;
+ void *mem, *mem_nofault, *buf = NULL;
+ int uffd, ret;
+ off_t offset = page_size;
+ void *fault_addr;
+
+ ret = posix_memalign(&buf, page_size, total_size);
+ TEST_ASSERT_EQ(ret, 0);
+
+ uffd = syscall(__NR_userfaultfd, O_CLOEXEC);
+ TEST_ASSERT(uffd != -1, "userfaultfd creation should succeed");
+
+ struct uffdio_api uffdio_api = {
+ .api = UFFD_API,
+ .features = UFFD_FEATURE_MISSING_SHMEM,
I think you mean UFFD_FEATURE_MINOR_SHMEM...?
And I'm trying to think through what feature we should expose for
guest_memfd; UFFD_FEATURE_MINOR_SHMEM already indicates support for
shmem.
We could have UFFD_FEATURE_MINOR_GUESTMEMFD, perhaps that's enough.
Yes, I will introduce UFFD_FEATURE_MINOR_GUEST_MEMFD in the next version.
Or we could have UFFD_FEATURE_MINOR_GENERIC (or nothing at all!). Some
VMAs might not support the minor mode, and the user will figure that
out when UFFDIO_REGISTER fails.
My concern is the exact reason of the failure may not be apparent to the
caller in that case.
+ };
+ ret = ioctl(uffd, UFFDIO_API, &uffdio_api);
+ TEST_ASSERT(ret != -1, "ioctl(UFFDIO_API) should succeed");
+
+ mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+ TEST_ASSERT(mem != MAP_FAILED, "mmap should succeed");
+
+ mem_nofault = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+ TEST_ASSERT(mem_nofault != MAP_FAILED, "mmap should succeed");
+
+ uffd_reg.range.start = (unsigned long)mem;
+ uffd_reg.range.len = total_size;
+ uffd_reg.mode = UFFDIO_REGISTER_MODE_MINOR;
+ ret = ioctl(uffd, UFFDIO_REGISTER, &uffd_reg);
+ TEST_ASSERT(ret != -1, "ioctl(UFFDIO_REGISTER) should succeed");
+
+ ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+ offset, page_size);
+ TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) should succeed");
+
+ fault_addr = mem + offset;
+ args.addr = fault_addr;
+
+ ret = pthread_create(&fault_thread, NULL, fault_thread_fn, &args);
+ TEST_ASSERT(ret == 0, "pthread_create should succeed");
+
+ ret = read(uffd, &msg, sizeof(msg));
+ TEST_ASSERT(ret != -1, "read from userfaultfd should succeed");
+ TEST_ASSERT(msg.event == UFFD_EVENT_PAGEFAULT, "event type should be pagefault");
+ TEST_ASSERT((void *)(msg.arg.pagefault.address & ~(page_size - 1)) == fault_addr,
+ "pagefault should occur at expected address");
+
+ memcpy(mem_nofault + offset, buf + offset, page_size);
+
+ uffd_cont.range.start = (unsigned long)fault_addr;
+ uffd_cont.range.len = page_size;
+ uffd_cont.mode = 0;
+ ret = ioctl(uffd, UFFDIO_CONTINUE, &uffd_cont);
+ TEST_ASSERT(ret != -1, "ioctl(UFFDIO_CONTINUE) should succeed");
+
+ ret = pthread_join(fault_thread, NULL);
+ TEST_ASSERT(ret == 0, "pthread_join should succeed");
And maybe also:
/* Right value? */
TEST_ASSERT(args.value == *(char *)mem_nofault));
/* No second fault? */
TEST_ASSERT(args.value == *(char *)mem);
Good idea, thanks. I don't need the volatile anymore :)
+
+ ret = munmap(mem_nofault, total_size);
+ TEST_ASSERT(!ret, "munmap should succeed");
+
+ ret = munmap(mem, total_size);
+ TEST_ASSERT(!ret, "munmap should succeed");
+ free(buf);
+ close(uffd);
+}
+
unsigned long get_shared_type(void)
{
#ifdef __x86_64__
@@ -244,6 +335,9 @@ void test_vm_type(unsigned long type, bool is_shared)
test_fallocate(fd, page_size, total_size);
test_invalid_punch_hole(fd, page_size, total_size);
+ if (is_shared)
+ test_uffd_missing(fd, page_size, total_size);
+
close(fd);
kvm_vm_release(vm);
}
--
2.47.1