I am trying to use the write protection feature of Linux's userfaultfd, but it does not appear to be enabled in my kernel even though I am using version 5.13 (write protection should be fully supported in 5.10+).
When I run
#define _GNU_SOURCE
#include <errno.h>
#include <fcntl.h>
#include <inttypes.h>
#include <linux/userfaultfd.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/ioctl.h>
#include <sys/syscall.h>
#include <unistd.h>
#define errExit(msg) \
do { \
perror(msg); \
exit(EXIT_FAILURE); \
} while (0)
static int has_bit(uint64_t val, uint64_t bit) {
return (val & bit) == bit;
}
int main() {
long uffd; /* userfaultfd file descriptor */
struct uffdio_api uffdio_api;
uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
if (uffd == -1)
errExit("userfaultfd");
uffdio_api.api = UFFD_API;
uffdio_api.features = UFFD_FEATURE_PAGEFAULT_FLAG_WP;
if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1)
errExit("ioctl-UFFDIO_API");
printf("UFFDIO_API: %d\n", has_bit(uffdio_api.ioctls, 1UL << _UFFDIO_API));
printf("UFFDIO_REGISTER: %d\n", has_bit(uffdio_api.ioctls, 1UL << _UFFDIO_REGISTER));
printf("UFFDIO_UNREGISTER: %d\n", has_bit(uffdio_api.ioctls, 1UL << _UFFDIO_UNREGISTER));
printf("UFFDIO_WRITEPROTECT: %d\n", has_bit(uffdio_api.ioctls, 1UL << _UFFDIO_WRITEPROTECT));
printf("UFFD_FEATURE_PAGEFAULT_FLAG_WP: %d\n", has_bit(uffdio_api.features, UFFD_FEATURE_PAGEFAULT_FLAG_WP));
}
The output is
UFFDIO_API: 1
UFFDIO_REGISTER: 1
UFFDIO_UNREGISTER: 1
UFFDIO_WRITEPROTECT: 0
UFFD_FEATURE_PAGEFAULT_FLAG_WP: 1
The UFFD_FEATURE_PAGEFAULT_FLAG_WP feature is enabled, but the UFFDIO_WRITEPROTECT ioctl is marked as not supported, which is necessary to enable write protection.
What might lead to this feature being disabled, and how can I enable it?
I am using Ubuntu MATE 21.10 with Linux kernel version 5.13.0-30-generic.
EDIT:
It seems like despite the man page section on the UFFD_API ioctl (https://man7.org/linux/man-pages/man2/ioctl_userfaultfd.2.html), this might be the intended behavior for a system where write protection is enabled. However, when I run a full program that spawns a poller thread and writes to the protected memory, the poller thread does not receive any notification.
#define _GNU_SOURCE
#include <errno.h>
#include <fcntl.h>
#include <inttypes.h>
#include <linux/userfaultfd.h>
#include <poll.h>
#include <pthread.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <unistd.h>
#define errExit(msg) \
do { \
perror(msg); \
exit(EXIT_FAILURE); \
} while (0)
static int page_size;
static void* fault_handler_thread(void* arg) {
long uffd; /* userfaultfd file descriptor */
uffd = (long) arg;
/* Loop, handling incoming events on the userfaultfd
file descriptor. */
for (;;) {
/* See what poll() tells us about the userfaultfd. */
struct pollfd pollfd;
int nready;
pollfd.fd = uffd;
pollfd.events = POLLIN;
nready = poll(&pollfd, 1, -1);
if (nready == -1)
errExit("poll");
printf("\nfault_handler_thread():\n");
printf(
" poll() returns: nready = %d; "
"POLLIN = %d; POLLERR = %d\n",
nready, (pollfd.revents & POLLIN) != 0,
(pollfd.revents & POLLERR) != 0);
// received fault, exit the program
exit(EXIT_FAILURE);
}
}
int main() {
long uffd; /* userfaultfd file descriptor */
char* addr; /* Start of region handled by userfaultfd */
uint64_t len; /* Length of region handled by userfaultfd */
pthread_t thr; /* ID of thread that handles page faults */
struct uffdio_api uffdio_api;
struct uffdio_register uffdio_register;
struct uffdio_writeprotect uffdio_wp;
int s;
page_size = sysconf(_SC_PAGE_SIZE);
len = page_size;
/* Create and enable userfaultfd object. */
uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
if (uffd == -1)
errExit("userfaultfd");
uffdio_api.api = UFFD_API;
uffdio_api.features = UFFD_FEATURE_PAGEFAULT_FLAG_WP;
if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1)
errExit("ioctl-UFFDIO_API");
addr = mmap(NULL, len, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
if (addr == MAP_FAILED)
errExit("mmap");
printf("Address returned by mmap() = %p\n", addr);
/* Register the memory range of the mapping we just created for
handling by the userfaultfd object. */
uffdio_register.range.start = (unsigned long) addr;
uffdio_register.range.len = len;
uffdio_register.mode = UFFDIO_REGISTER_MODE_WP;
if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1)
errExit("ioctl-UFFDIO_REGISTER");
printf("uffdio_register.ioctls = 0x%llx\n", uffdio_register.ioctls);
printf("Have _UFFDIO_WRITEPROTECT? %s\n", (uffdio_register.ioctls & _UFFDIO_WRITEPROTECT) ? "YES" : "NO");
uffdio_wp.range.start = (unsigned long) addr;
uffdio_wp.range.len = len;
uffdio_wp.mode = UFFDIO_WRITEPROTECT_MODE_WP;
if (ioctl(uffd, UFFDIO_WRITEPROTECT, &uffdio_wp) == -1)
errExit("ioctl-UFFDIO_WRITEPROTECT");
/* Create a thread that will process the userfaultfd events. */
s = pthread_create(&thr, NULL, fault_handler_thread, (void*) uffd);
if (s != 0) {
errno = s;
errExit("pthread_create");
}
/* Main thread now touches memory in the mapping, touching
locations 1024 bytes apart. This will trigger userfaultfd
events for all pages in the region. */
usleep(100000);
size_t l;
l = 0xf; /* Ensure that faulting address is not on a page
boundary, in order to test that we correctly
handle that case in fault_handling_thread(). */
char i = 0;
while (l < len) {
printf("Write address %p in main(): ", addr + l);
addr[l] = i++;
printf("%d\n", addr[l]);
l += 1024;
usleep(100000); /* Slow things down a little */
}
exit(EXIT_SUCCESS);
}
