Merge tag 'hw-cpus-20240119' of https://github.com/philmd/qemu into staging

[mirror_qemu.git] / util / userfaultfd.c

diff --git a/util/userfaultfd.c b/util/userfaultfd.c
index 4953b3137d5e75091d16293e430e25ed8abe3233..fdff4867e8bd8c0adaac44a4aec468c198214897 100644 (file)
--- 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;