X86/vMCE: handle broken page with regard to migration

At the sender
  xc_domain_save has a key point: 'to query the types of all the pages
  with xc_get_pfn_type_batch'
  1) if broken page occur before the key point, migration will be fine
     since proper pfn_type and pfn number will be transferred to the
     target and then take appropriate action;
  2) if broken page occur after the key point, whole system will crash
     and no need care migration any more;

At the target
  Target will populates pages for guest. As for the case of broken page,
  we prefer to keep the type of the page for the sake of seamless migration.
  Target will set p2m as p2m_ram_broken for broken page. If guest access
  the broken page again it will kill itself as expected.

Suggested-by: George Dunlap <george.dunlap@eu.citrix.com>
Signed-off-by: Liu Jinsong <jinsong.liu@intel.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Tim Deegan <tim@xen.org>
Committed-by: Ian Campbell <ian.campbell@citrix.com>

6 files changed, 101 insertions, 5 deletions

diff --git a/tools/libxc/xc_domain.c b/tools/libxc/xc_domain.c
index d98e68bd6d..4b82884905 100644
--- a/tools/libxc/xc_domain.c
+++ b/tools/libxc/xc_domain.c
@@ -283,6 +283,22 @@ int xc_domain_getinfolist(xc_interface *xch,
     return ret;
 }
 
+/* set broken page p2m */
+int xc_set_broken_page_p2m(xc_interface *xch,
+                           uint32_t domid,
+                           unsigned long pfn)
+{
+    int ret;
+    DECLARE_DOMCTL;
+
+    domctl.cmd = XEN_DOMCTL_set_broken_page_p2m;
+    domctl.domain = (domid_t)domid;
+    domctl.u.set_broken_page_p2m.pfn = pfn;
+    ret = do_domctl(xch, &domctl);
+
+    return ret ? -1 : 0;
+}
+
 /* get info from hvm guest for save */
 int xc_domain_hvm_getcontext(xc_interface *xch,
                              uint32_t domid,
diff --git a/tools/libxc/xc_domain_restore.c b/tools/libxc/xc_domain_restore.c
index 02bfa1c163..454d2cbd49 100644
--- a/tools/libxc/xc_domain_restore.c
+++ b/tools/libxc/xc_domain_restore.c
@@ -1023,9 +1023,15 @@ static int pagebuf_get_one(xc_interface *xch, struct restore_ctx *ctx,
 
     countpages = count;
     for (i = oldcount; i < buf->nr_pages; ++i)
-        if ((buf->pfn_types[i] & XEN_DOMCTL_PFINFO_LTAB_MASK) == XEN_DOMCTL_PFINFO_XTAB
-            ||(buf->pfn_types[i] & XEN_DOMCTL_PFINFO_LTAB_MASK) == XEN_DOMCTL_PFINFO_XALLOC)
+    {
+        unsigned long pagetype;
+
+        pagetype = buf->pfn_types[i] & XEN_DOMCTL_PFINFO_LTAB_MASK;
+        if ( pagetype == XEN_DOMCTL_PFINFO_XTAB ||
+             pagetype == XEN_DOMCTL_PFINFO_BROKEN ||
+             pagetype == XEN_DOMCTL_PFINFO_XALLOC )
             --countpages;
+    }
 
     if (!countpages)
         return count;
@@ -1267,6 +1273,17 @@ static int apply_batch(xc_interface *xch, uint32_t dom, struct restore_ctx *ctx,
             /* a bogus/unmapped/allocate-only page: skip it */
             continue;
 
+        if ( pagetype == XEN_DOMCTL_PFINFO_BROKEN )
+        {
+            if ( xc_set_broken_page_p2m(xch, dom, pfn) )
+            {
+                ERROR("Set p2m for broken page failed, "
+                      "dom=%d, pfn=%lx\n", dom, pfn);
+                goto err_mapped;
+            }
+            continue;
+        }
+
         if (pfn_err[i])
         {
             ERROR("unexpected PFN mapping failure pfn %lx map_mfn %lx p2m_mfn %lx",
diff --git a/tools/libxc/xc_domain_save.c b/tools/libxc/xc_domain_save.c
index d48e9c0fb0..dad681a1d0 100644
--- a/tools/libxc/xc_domain_save.c
+++ b/tools/libxc/xc_domain_save.c
@@ -1277,6 +1277,13 @@ int xc_domain_save(xc_interface *xch, int io_fd, uint32_t dom, uint32_t max_iter
                 if ( !hvm )
                     gmfn = pfn_to_mfn(gmfn);
 
+                if ( pfn_type[j] == XEN_DOMCTL_PFINFO_BROKEN )
+                {
+                    pfn_type[j] |= pfn_batch[j];
+                    ++run;
+                    continue;
+                }
+
                 if ( pfn_err[j] )
                 {
                     if ( pfn_type[j] == XEN_DOMCTL_PFINFO_XTAB )
@@ -1371,8 +1378,12 @@ int xc_domain_save(xc_interface *xch, int io_fd, uint32_t dom, uint32_t max_iter
                     }
                 }
 
-                /* skip pages that aren't present or are alloc-only */
+                /*
+                 * skip pages that aren't present,
+                 * or are broken, or are alloc-only
+                 */
                 if ( pagetype == XEN_DOMCTL_PFINFO_XTAB
+                    || pagetype == XEN_DOMCTL_PFINFO_BROKEN
                     || pagetype == XEN_DOMCTL_PFINFO_XALLOC )
                     continue;
 
diff --git a/tools/libxc/xenctrl.h b/tools/libxc/xenctrl.h
index 7eb57430c3..1cd13c1b34 100644
--- a/tools/libxc/xenctrl.h
+++ b/tools/libxc/xenctrl.h
@@ -575,6 +575,17 @@ int xc_domain_getinfolist(xc_interface *xch,
                           xc_domaininfo_t *info);
 
 /**
+ * This function set p2m for broken page
+ * &parm xch a handle to an open hypervisor interface
+ * @parm domid the domain id which broken page belong to
+ * @parm pfn the pfn number of the broken page
+ * @return 0 on success, -1 on failure
+ */
+int xc_set_broken_page_p2m(xc_interface *xch,
+                           uint32_t domid,
+                           unsigned long pfn);
+
+/**
  * This function returns information about the context of a hvm domain
  * @parm xch a handle to an open hypervisor interface
  * @parm domid the domain to get information from
diff --git a/xen/arch/x86/domctl.c b/xen/arch/x86/domctl.c
index 508c77c899..83daebb26a 100644
--- a/xen/arch/x86/domctl.c
+++ b/xen/arch/x86/domctl.c
@@ -209,12 +209,18 @@ long arch_do_domctl(
                 for ( j = 0; j < k; j++ )
                 {
                     unsigned long type = 0;
+                    p2m_type_t t;
 
-                    page = get_page_from_gfn(d, arr[j], NULL, P2M_ALLOC);
+                    page = get_page_from_gfn(d, arr[j], &t, P2M_ALLOC);
 
                     if ( unlikely(!page) ||
                          unlikely(is_xen_heap_page(page)) )
-                        type = XEN_DOMCTL_PFINFO_XTAB;
+                    {
+                        if ( p2m_is_broken(t) )
+                            type = XEN_DOMCTL_PFINFO_BROKEN;
+                        else
+                            type = XEN_DOMCTL_PFINFO_XTAB;
+                    }
                     else
                     {
                         switch( page->u.inuse.type_info & PGT_type_mask )
@@ -235,6 +241,9 @@ long arch_do_domctl(
 
                         if ( page->u.inuse.type_info & PGT_pinned )
                             type |= XEN_DOMCTL_PFINFO_LPINTAB;
+
+                        if ( page->count_info & PGC_broken )
+                            type = XEN_DOMCTL_PFINFO_BROKEN;
                     }
 
                     if ( page )
@@ -1568,6 +1577,29 @@ long arch_do_domctl(
     }
     break;
 
+    case XEN_DOMCTL_set_broken_page_p2m:
+    {
+        struct domain *d;
+
+        d = rcu_lock_domain_by_id(domctl->domain);
+        if ( d != NULL )
+        {
+            p2m_type_t pt;
+            unsigned long pfn = domctl->u.set_broken_page_p2m.pfn;
+            mfn_t mfn = get_gfn_query(d, pfn, &pt);
+
+            if ( unlikely(!mfn_valid(mfn_x(mfn)) || !p2m_is_ram(pt) ||
+                         (p2m_change_type(d, pfn, pt, p2m_ram_broken) != pt)) )
+                ret = -EINVAL;
+
+            put_gfn(d, pfn);
+            rcu_unlock_domain(d);
+        }
+        else
+            ret = -ESRCH;
+    }
+    break;
+
     default:
         ret = iommu_do_domctl(domctl, u_domctl);
         break;
diff --git a/xen/include/public/domctl.h b/xen/include/public/domctl.h
index 7c0f23df2e..74160b07db 100644
--- a/xen/include/public/domctl.h
+++ b/xen/include/public/domctl.h
@@ -136,6 +136,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_domctl_getmemlist_t);
 #define XEN_DOMCTL_PFINFO_LPINTAB (0x1U<<31)
 #define XEN_DOMCTL_PFINFO_XTAB    (0xfU<<28) /* invalid page */
 #define XEN_DOMCTL_PFINFO_XALLOC  (0xeU<<28) /* allocate-only page */
+#define XEN_DOMCTL_PFINFO_BROKEN  (0xdU<<28) /* broken page */
 #define XEN_DOMCTL_PFINFO_LTAB_MASK (0xfU<<28)
 
 struct xen_domctl_getpageframeinfo {
@@ -834,6 +835,12 @@ struct xen_domctl_set_access_required {
 typedef struct xen_domctl_set_access_required xen_domctl_set_access_required_t;
 DEFINE_XEN_GUEST_HANDLE(xen_domctl_set_access_required_t);
 
+struct xen_domctl_set_broken_page_p2m {
+    uint64_aligned_t pfn;
+};
+typedef struct xen_domctl_set_broken_page_p2m xen_domctl_set_broken_page_p2m_t;
+DEFINE_XEN_GUEST_HANDLE(xen_domctl_set_broken_page_p2m_t);
+
 struct xen_domctl {
     uint32_t cmd;
 #define XEN_DOMCTL_createdomain                   1
@@ -899,6 +906,7 @@ struct xen_domctl {
 #define XEN_DOMCTL_set_access_required           64
 #define XEN_DOMCTL_audit_p2m                     65
 #define XEN_DOMCTL_set_virq_handler              66
+#define XEN_DOMCTL_set_broken_page_p2m           67
 #define XEN_DOMCTL_gdbsx_guestmemio            1000
 #define XEN_DOMCTL_gdbsx_pausevcpu             1001
 #define XEN_DOMCTL_gdbsx_unpausevcpu           1002
@@ -954,6 +962,7 @@ struct xen_domctl {
         struct xen_domctl_audit_p2m         audit_p2m;
         struct xen_domctl_set_virq_handler  set_virq_handler;
         struct xen_domctl_gdbsx_memio       gdbsx_guest_memio;
+        struct xen_domctl_set_broken_page_p2m set_broken_page_p2m;
         struct xen_domctl_gdbsx_pauseunp_vcpu gdbsx_pauseunp_vcpu;
         struct xen_domctl_gdbsx_domstatus   gdbsx_domstatus;
         uint8_t                             pad[128];