[PATCH v2 3/3] util/userfaultfd: Support /dev/userfaultfd

[Peter Xu <peterx@redhat.com>]

Teach QEMU to use /dev/userfaultfd when it existed and fallback to the
system call if either it's not there or doesn't have enough permission.

Firstly, as long as the app has permission to access /dev/userfaultfd, it
always have the ability to trap kernel faults which QEMU mostly wants.
Meanwhile, in some context (e.g. containers) the userfaultfd syscall can be
forbidden, so it can be the major way to use postcopy in a restricted
environment with strict seccomp setup.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 util/trace-events  |  1 +
 util/userfaultfd.c | 37 +++++++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

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 9845a2ec81..7dceab51d6 100644
--- a/util/userfaultfd.c
+++ b/util/userfaultfd.c
@@ -18,10 +18,47 @@
 #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;
+
+static int uffd_dev;
+
+static uffd_open_mode uffd_detect_open_mode(void)
+{
+    static uffd_open_mode open_mode;
+
+    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);
+    }
+
+    return open_mode;
+}
 
 int uffd_open(int flags)
 {
 #if defined(__linux__) && defined(__NR_userfaultfd)
+    if (uffd_detect_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;
-- 
2.37.3