[Qemu-devel] [PATCH V4 4/9] migration: split ufd_version_check onto receive/request features part

[Alexey Perevalov]

This modification is necessary for userfault fd features which are
required to be requested from userspace.
UFFD_FEATURE_THREAD_ID is a one of such "on demand" feature, which will
be introduced in the next patch.

QEMU need to use separate userfault file descriptor, due to
userfault context has internal state, and after first call of
ioctl UFFD_API it changes its state to UFFD_STATE_RUNNING (in case of
success), but
kernel while handling ioctl UFFD_API expects UFFD_STATE_WAIT_API. So
only one ioctl with UFFD_API is possible per ufd.

Signed-off-by: Alexey Perevalov <address@hidden>
---
 migration/postcopy-ram.c | 82 ++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 73 insertions(+), 9 deletions(-)

diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index b6eccaf..a16cde8 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -59,32 +59,96 @@ struct PostcopyDiscardState {
 #include <sys/eventfd.h>
 #include <linux/userfaultfd.h>
 
-static bool ufd_version_check(int ufd, MigrationIncomingState *mis)
+
+/*
+ * Check userfault fd features, to request only supported features in
+ * future.
+ * __NR_userfaultfd - should be checked before
+ * Return obtained features
+ */
+static bool receive_ufd_features(uint64_t *features)
 {
-    struct uffdio_api api_struct;
-    uint64_t ioctl_mask;
+    struct uffdio_api api_struct = {0};
+    int ufd;
+    bool ret = true;
+
+    /* if we are here __NR_userfaultfd should exists */
+    ufd = syscall(__NR_userfaultfd, O_CLOEXEC);
+    if (ufd == -1) {
+        return false;
+    }
 
+    /* ask features */
     api_struct.api = UFFD_API;
     api_struct.features = 0;
     if (ioctl(ufd, UFFDIO_API, &api_struct)) {
-        error_report("%s: UFFDIO_API failed: %s", __func__
+        error_report("%s: UFFDIO_API failed: %s", __func__,
                      strerror(errno));
+        ret = false;
+        goto release_ufd;
+    }
+
+    *features = api_struct.features;
+
+release_ufd:
+    close(ufd);
+    return ret;
+}
+
+static bool request_ufd_features(int ufd, uint64_t features)
+{
+    struct uffdio_api api_struct = {0};
+    uint64_t ioctl_mask;
+
+    api_struct.api = UFFD_API;
+    api_struct.features = features;
+    if (ioctl(ufd, UFFDIO_API, &api_struct)) {
+        error_report("%s failed: UFFDIO_API failed: %s", __func__,
+                strerror(errno));
         return false;
     }
 
-    ioctl_mask = (__u64)1 << _UFFDIO_REGISTER |
-                 (__u64)1 << _UFFDIO_UNREGISTER;
+    ioctl_mask = 1 << _UFFDIO_REGISTER |
+                 1 << _UFFDIO_UNREGISTER;
     if ((api_struct.ioctls & ioctl_mask) != ioctl_mask) {
         error_report("Missing userfault features: %" PRIx64,
                      (uint64_t)(~api_struct.ioctls & ioctl_mask));
         return false;
     }
 
+    return true;
+}
+
+static bool ufd_check_and_apply(int ufd, MigrationIncomingState *mis)
+{
+    uint64_t asked_features = 0;
+    uint64_t supported_features;
+
+    /*
+     * it's not possible to
+     * request UFFD_API twice per one fd
+     */
+    if (!receive_ufd_features(&supported_features)) {
+        error_report("%s failed", __func__);
+        return false;
+    }
+
+    /*
+     * request features, even if asked_features is 0, due to
+     * kernel expects UFFD_API before UFFDIO_REGISTER, per
+     * userfault file descriptor
+     */
+    if (!request_ufd_features(ufd, asked_features)) {
+        error_report("%s failed: features %" PRIu64, __func__,
+                asked_features);
+        return false;
+    }
+
     if (getpagesize() != ram_pagesize_summary()) {
         bool have_hp = false;
         /* We've got a huge page */
 #ifdef UFFD_FEATURE_MISSING_HUGETLBFS
-        have_hp = api_struct.features & UFFD_FEATURE_MISSING_HUGETLBFS;
+        have_hp = supported_features & UFFD_FEATURE_MISSING_HUGETLBFS;
 #endif
         if (!have_hp) {
             error_report("Userfault on this host does not support huge pages");
@@ -135,7 +199,7 @@ bool postcopy_ram_supported_by_host(MigrationIncomingState 
*mis)
     }
 
     /* Version and features check */
-    if (!ufd_version_check(ufd, mis)) {
+    if (!ufd_check_and_apply(ufd, mis)) {
         goto out;
     }
 
@@ -512,7 +576,7 @@ int postcopy_ram_enable_notify(MigrationIncomingState *mis)
      * Although the host check already tested the API, we need to
      * do the check again as an ABI handshake on the new fd.
      */
-    if (!ufd_version_check(mis->userfault_fd, mis)) {
+    if (!ufd_check_and_apply(mis->userfault_fd, mis)) {
         return -1;
     }
 
-- 
1.8.3.1