diff options
| -rw-r--r-- | util/trace-events | 1 | ||||
| -rw-r--r-- | util/userfaultfd.c | 32 |
2 files changed, 33 insertions, 0 deletions
diff --git a/util/trace-events b/util/trace-events index c8f53d7d9f..16f78d8fe5 100644 --- a/util/trace-events +++ b/util/trace-events @@ -93,6 +93,7 @@ qemu_vfio_region_info(const char *desc, uint64_t region_ofs, uint64_t region_siz qemu_vfio_pci_map_bar(int index, uint64_t region_ofs, uint64_t region_size, int ofs, void *host) "map region bar#%d addr 0x%"PRIx64" size 0x%"PRIx64" ofs 0x%x host %p" #userfaultfd.c +uffd_detect_open_mode(int mode) "%d" uffd_query_features_nosys(int err) "errno: %i" uffd_query_features_api_failed(int err) "errno: %i" uffd_create_fd_nosys(int err) "errno: %i" diff --git a/util/userfaultfd.c b/util/userfaultfd.c index 4953b3137d..fdff4867e8 100644 --- a/util/userfaultfd.c +++ b/util/userfaultfd.c @@ -18,10 +18,42 @@ #include <poll.h> #include <sys/syscall.h> #include <sys/ioctl.h> +#include <fcntl.h> + +typedef enum { + UFFD_UNINITIALIZED = 0, + UFFD_USE_DEV_PATH, + UFFD_USE_SYSCALL, +} uffd_open_mode; int uffd_open(int flags) { #if defined(__NR_userfaultfd) + static uffd_open_mode open_mode; + static int uffd_dev; + + /* Detect how to generate uffd desc when run the 1st time */ + if (open_mode == UFFD_UNINITIALIZED) { + /* + * Make /dev/userfaultfd the default approach because it has better + * permission controls, meanwhile allows kernel faults without any + * privilege requirement (e.g. SYS_CAP_PTRACE). + */ + uffd_dev = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); + if (uffd_dev >= 0) { + open_mode = UFFD_USE_DEV_PATH; + } else { + /* Fallback to the system call */ + open_mode = UFFD_USE_SYSCALL; + } + trace_uffd_detect_open_mode(open_mode); + } + + if (open_mode == UFFD_USE_DEV_PATH) { + assert(uffd_dev >= 0); + return ioctl(uffd_dev, USERFAULTFD_IOC_NEW, flags); + } + return syscall(__NR_userfaultfd, flags); #else return -EINVAL; |