postcopy: OS support test

Provide a check to see if the OS we're running on has all the bits
needed for postcopy.

Creates postcopy-ram.c which will get most of the other helpers we need.
Signed-off-by: NDr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: NAmit Shah <amit.shah@redhat.com>
Reviewed-by: NJuan Quintela <quintela@redhat.com>
Signed-off-by: NJuan Quintela <quintela@redhat.com>

include/migration/postcopy-ram.h

+/*
+ * Postcopy migration for RAM
+ *
+ * Copyright 2013 Red Hat, Inc. and/or its affiliates
+ *
+ * Authors:
+ *  Dave Gilbert  <dgilbert@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+#ifndef QEMU_POSTCOPY_RAM_H
+#define QEMU_POSTCOPY_RAM_H
+
+/* Return true if the host supports everything we need to do postcopy-ram */
+bool postcopy_ram_supported_by_host(void);
+
+#endif

migration/Makefile.objs

 common-obj-y += migration.o tcp.o
 common-obj-y += vmstate.o
 common-obj-y += qemu-file.o qemu-file-buf.o qemu-file-unix.o qemu-file-stdio.o
-common-obj-y += xbzrle.o
+common-obj-y += xbzrle.o postcopy-ram.o
 
 common-obj-$(CONFIG_RDMA) += rdma.o
 common-obj-$(CONFIG_POSIX) += exec.o unix.o fd.o

migration/postcopy-ram.c

+/*
+ * Postcopy migration for RAM
+ *
+ * Copyright 2013-2015 Red Hat, Inc. and/or its affiliates
+ *
+ * Authors:
+ *  Dave Gilbert  <dgilbert@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+/*
+ * Postcopy is a migration technique where the execution flips from the
+ * source to the destination before all the data has been copied.
+ */
+
+#include <glib.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#include "qemu-common.h"
+#include "migration/migration.h"
+#include "migration/postcopy-ram.h"
+#include "sysemu/sysemu.h"
+#include "qemu/error-report.h"
+#include "trace.h"
+
+/* Postcopy needs to detect accesses to pages that haven't yet been copied
+ * across, and efficiently map new pages in, the techniques for doing this
+ * are target OS specific.
+ */
+#if defined(__linux__)
+
+#include <sys/mman.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <asm/types.h> /* for __u64 */
+#endif
+
+#if defined(__linux__) && defined(__NR_userfaultfd)
+#include <linux/userfaultfd.h>
+
+static bool ufd_version_check(int ufd)
+{
+    struct uffdio_api api_struct;
+    uint64_t ioctl_mask;
+
+    api_struct.api = UFFD_API;
+    api_struct.features = 0;
+    if (ioctl(ufd, UFFDIO_API, &api_struct)) {
+        error_report("postcopy_ram_supported_by_host: UFFDIO_API failed: %s",
+                     strerror(errno));
+        return false;
+    }
+
+    ioctl_mask = (__u64)1 << _UFFDIO_REGISTER |
+                 (__u64)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;
+}
+
+bool postcopy_ram_supported_by_host(void)
+{
+    long pagesize = getpagesize();
+    int ufd = -1;
+    bool ret = false; /* Error unless we change it */
+    void *testarea = NULL;
+    struct uffdio_register reg_struct;
+    struct uffdio_range range_struct;
+    uint64_t feature_mask;
+
+    if ((1ul << qemu_target_page_bits()) > pagesize) {
+        error_report("Target page size bigger than host page size");
+        goto out;
+    }
+
+    ufd = syscall(__NR_userfaultfd, O_CLOEXEC);
+    if (ufd == -1) {
+        error_report("%s: userfaultfd not available: %s", __func__,
+                     strerror(errno));
+        goto out;
+    }
+
+    /* Version and features check */
+    if (!ufd_version_check(ufd)) {
+        goto out;
+    }
+
+    /*
+     *  We need to check that the ops we need are supported on anon memory
+     *  To do that we need to register a chunk and see the flags that
+     *  are returned.
+     */
+    testarea = mmap(NULL, pagesize, PROT_READ | PROT_WRITE, MAP_PRIVATE |
+                                    MAP_ANONYMOUS, -1, 0);
+    if (testarea == MAP_FAILED) {
+        error_report("%s: Failed to map test area: %s", __func__,
+                     strerror(errno));
+        goto out;
+    }
+    g_assert(((size_t)testarea & (pagesize-1)) == 0);
+
+    reg_struct.range.start = (uintptr_t)testarea;
+    reg_struct.range.len = pagesize;
+    reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
+
+    if (ioctl(ufd, UFFDIO_REGISTER, &reg_struct)) {
+        error_report("%s userfault register: %s", __func__, strerror(errno));
+        goto out;
+    }
+
+    range_struct.start = (uintptr_t)testarea;
+    range_struct.len = pagesize;
+    if (ioctl(ufd, UFFDIO_UNREGISTER, &range_struct)) {
+        error_report("%s userfault unregister: %s", __func__, strerror(errno));
+        goto out;
+    }
+
+    feature_mask = (__u64)1 << _UFFDIO_WAKE |
+                   (__u64)1 << _UFFDIO_COPY |
+                   (__u64)1 << _UFFDIO_ZEROPAGE;
+    if ((reg_struct.ioctls & feature_mask) != feature_mask) {
+        error_report("Missing userfault map features: %" PRIx64,
+                     (uint64_t)(~reg_struct.ioctls & feature_mask));
+        goto out;
+    }
+
+    /* Success! */
+    ret = true;
+out:
+    if (testarea) {
+        munmap(testarea, pagesize);
+    }
+    if (ufd != -1) {
+        close(ufd);
+    }
+    return ret;
+}
+
+#else
+/* No target OS support, stubs just fail */
+bool postcopy_ram_supported_by_host(void)
+{
+    error_report("%s: No OS support", __func__);
+    return false;
+}
+
+#endif
+

migration/savevm.c

@@ -37,6 +37,7 @@
 #include "qemu/timer.h"
 #include "audio/audio.h"
 #include "migration/migration.h"
+#include "migration/postcopy-ram.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/error-report.h"
 #include "qemu/sockets.h"
@@ -1205,6 +1206,10 @@ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis)
         return -1;
     }
 
+    if (!postcopy_ram_supported_by_host()) {
+        return -1;
+    }
+
     remote_hps = qemu_get_be64(mis->from_src_file);
     if (remote_hps != getpagesize())  {
         /*