gnttab: Avoid potential double-put of maptrack entry

Each grant mapping for a particular domain is tracked by an in-Xen
"maptrack" entry.  This entry is is referenced by a "handle", which is
given to the guest when it calls gnttab_map_grant_ref().

There are two types of mapping a particular handle can refer to:
GNTMAP_host_map and GNTMAP_device_map.  A given
gnttab_unmap_grant_ref() call can remove either only one or both of
these entries.  When a particular handle has no entries left, it must
be freed.

gnttab_unmap_grant_ref() loops through its grant unmap request list
twice.  It first removes entries from any host pagetables and (if
appropraite) iommus; then it does a single domain TLB flush; then it
does the clean-up, including telling the granter that entries are no
longer being used (if appropriate).

At the moment, it's during the first pass that the maptrack flags are
cleared, but the second pass that the maptrack entry is freed.

Unfortunately this allows the following race, which results in a
double-free:

 A: (pass 1) clear host_map
 B: (pass 1) clear device_map
 A: (pass 2) See that maptrack entry has no mappings, free it
 B: (pass 2) See that maptrack entry has no mappings, free it #

Unfortunately, unlike the active entry pinning update, we can't simply
move the maptrack flag changes to the second half, because the
maptrack flags are used to determine if iommu entries need to be
added: a domain's iommu must never have fewer permissions than the
maptrack flags indicate, or a subsequent map_grant_ref() might fail to
add the necessary iommu entries.

Instead, free the maptrack entry in the first pass if there are no
further mappings.

This is part of XSA-218.

Reported-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: George Dunlap <george.dunlap@citrix.com>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
master commit: b7f6cbb9d43f7384e1f38f8764b9a48216c8a525
master date: 2017-06-20 14:33:13 +0200

diff --git a/xen/common/grant_table.c b/xen/common/grant_table.c
index 9ef0a6f6462f3748684a8f8183feb51d92badb9f..52039296eb407123ab0e3bbdb41d93cf40338cd6 100644 (file)
--- a/xen/common/grant_table.c
+++ b/xen/common/grant_table.c
@@ -98,8 +98,8 @@ struct gnttab_unmap_common {
     /* Shared state beteen *_unmap and *_unmap_complete */
     u16 flags;
     unsigned long frame;
-    struct grant_mapping *map;
     struct domain *rd;
+    grant_ref_t ref;
 };
 
 /* Number of unmap operations that are done between each tlb flush */
@@ -893,6 +893,8 @@ __gnttab_unmap_common(
     struct grant_table *lgt, *rgt;
     struct active_grant_entry *act;
     s16              rc = 0;
+    struct grant_mapping *map;
+    bool_t put_handle = 0;
 
     ld = current->domain;
     lgt = ld->grant_table;
@@ -906,10 +908,10 @@ __gnttab_unmap_common(
         return;
     }
 
-    op->map = &maptrack_entry(lgt, op->handle);
+    map = &maptrack_entry(lgt, op->handle);
     spin_lock(&lgt->lock);
 
-    if ( unlikely(!op->map->flags) )
+    if ( unlikely(!map->flags) )
     {
         spin_unlock(&lgt->lock);
         gdprintk(XENLOG_INFO, "Zero flags for handle (%d).\n", op->handle);
@@ -917,7 +919,7 @@ __gnttab_unmap_common(
         return;
     }
 
-    dom = op->map->domid;
+    dom = map->domid;
     spin_unlock(&lgt->lock);
 
     if ( unlikely((rd = rcu_lock_domain_by_id(dom)) == NULL) )
@@ -941,8 +943,8 @@ __gnttab_unmap_common(
     rgt = rd->grant_table;
     double_gt_lock(lgt, rgt);
 
-    op->flags = op->map->flags;
-    if ( unlikely(!op->flags) || unlikely(op->map->domid != dom) )
+    op->flags = map->flags;
+    if ( unlikely(!op->flags) || unlikely(map->domid != dom) )
     {
         gdprintk(XENLOG_WARNING, "Unstable handle %u\n", op->handle);
         rc = GNTST_bad_handle;
@@ -950,7 +952,8 @@ __gnttab_unmap_common(
     }
 
     op->rd = rd;
-    act = &active_entry(rgt, op->map->ref);
+    op->ref = map->ref;
+    act = &active_entry(rgt, map->ref);
 
     if ( op->frame == 0 )
     {
@@ -963,7 +966,7 @@ __gnttab_unmap_common(
                      "Bad frame number doesn't match gntref. (%lx != %lx)\n",
                      op->frame, act->frame);
 
-        op->map->flags &= ~GNTMAP_device_map;
+        map->flags &= ~GNTMAP_device_map;
     }
 
     if ( (op->host_addr != 0) && (op->flags & GNTMAP_host_map) )
@@ -973,31 +976,44 @@ __gnttab_unmap_common(
                                               op->flags)) < 0 )
             goto unmap_out;
 
-        op->map->flags &= ~GNTMAP_host_map;
+        map->flags &= ~GNTMAP_host_map;
     }
 
-    if ( gnttab_need_iommu_mapping(ld) )
+    if ( !(map->flags & (GNTMAP_device_map|GNTMAP_host_map)) )
+    {
+        map->flags = 0;
+        put_handle = 1;
+    }
+
+ unmap_out:
+    double_gt_unlock(lgt, rgt);
+
+    if ( put_handle )
+        put_maptrack_handle(lgt, op->handle);
+
+    if ( rc == GNTST_okay && gnttab_need_iommu_mapping(ld) )
     {
         unsigned int wrc, rdc;
         int err = 0;
+
+        double_gt_lock(lgt, rgt);
+
         mapcount(lgt, rd, op->frame, &wrc, &rdc);
         if ( (wrc + rdc) == 0 )
             err = iommu_unmap_page(ld, op->frame);
         else if ( wrc == 0 )
             err = iommu_map_page(ld, op->frame, op->frame, IOMMUF_readable);
+
+        double_gt_unlock(lgt, rgt);
+
         if ( err )
-        {
             rc = GNTST_general_error;
-            goto unmap_out;
-        }
     }
 
     /* If just unmapped a writable mapping, mark as dirtied */
-    if ( !(op->flags & GNTMAP_readonly) )
+    if ( rc == GNTST_okay && !(op->flags & GNTMAP_readonly) )
          gnttab_mark_dirty(rd, op->frame);
 
- unmap_out:
-    double_gt_unlock(lgt, rgt);
     op->status = rc;
     rcu_unlock_domain(rd);
 }
@@ -1011,7 +1027,6 @@ __gnttab_unmap_common_complete(struct gnttab_unmap_common *op)
     grant_entry_header_t *sha;
     struct page_info *pg;
     uint16_t *status;
-    bool_t put_handle = 0;
 
     if ( rd == NULL )
     { 
@@ -1032,13 +1047,13 @@ __gnttab_unmap_common_complete(struct gnttab_unmap_common *op)
     if ( rgt->gt_version == 0 )
         goto unmap_out;
 
-    act = &active_entry(rgt, op->map->ref);
-    sha = shared_entry_header(rgt, op->map->ref);
+    act = &active_entry(rgt, op->ref);
+    sha = shared_entry_header(rgt, op->ref);
 
     if ( rgt->gt_version == 1 )
         status = &sha->flags;
     else
-        status = &status_entry(rgt, op->map->ref);
+        status = &status_entry(rgt, op->ref);
 
     if ( unlikely(op->frame != act->frame) ) 
     {
@@ -1095,9 +1110,6 @@ __gnttab_unmap_common_complete(struct gnttab_unmap_common *op)
             act->pin -= GNTPIN_hstw_inc;
     }
 
-    if ( (op->map->flags & (GNTMAP_device_map|GNTMAP_host_map)) == 0 )
-        put_handle = 1;
-
     if ( ((act->pin & (GNTPIN_devw_mask|GNTPIN_hstw_mask)) == 0) &&
          !(op->flags & GNTMAP_readonly) )
         gnttab_clear_flag(_GTF_writing, status);
@@ -1107,11 +1119,6 @@ __gnttab_unmap_common_complete(struct gnttab_unmap_common *op)
 
  unmap_out:
     spin_unlock(&rgt->lock);
-    if ( put_handle )
-    {
-        op->map->flags = 0;
-        put_maptrack_handle(ld->grant_table, op->handle);
-    }
     rcu_unlock_domain(rd);
 }