IOMMU/x86: disallow device assignment to PoD guests

While it is okay for IOMMU page tables to be set up for guests starting
in PoD mode, actual device assignment may only occur once all PoD
entries have been removed from the P2M. So far this was enforced only
for boot-time assignment, and only in the tool stack.

Also use the new function to replace p2m_pod_entry_count(): Its unlocked
access to p2m->pod.entry_count wasn't really okay (irrespective of the
result being stale by the time the caller gets to see it). Nor was the
use of that function in line with the immediately preceding comment: A
PoD guest isn't just one with a non-zero entry count, but also one with
a non-empty cache (e.g. prior to actually launching the guest).

To allow the tool stack to see a consistent snapshot of PoD state, move
the tail of XENMEM_{get,set}_pod_target handling into a function, adding
proper locking there.

In libxl take the liberty to use the new local variable r also for a
pre-existing call into libxc.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>

diff --git a/xen/arch/x86/include/asm/p2m.h b/xen/arch/x86/include/asm/p2m.h
index 6f14e7b46d5eb5e49331f97242d46a342e3ae851..0a0f7114f318c2f065bc69cc2914f3c4356e919e 100644 (file)
--- a/xen/arch/x86/include/asm/p2m.h
+++ b/xen/arch/x86/include/asm/p2m.h
@@ -701,6 +701,12 @@ int p2m_pod_empty_cache(struct domain *d);
  * domain matches target */
 int p2m_pod_set_mem_target(struct domain *d, unsigned long target);
 
+/* Obtain a consistent snapshot of PoD related domain state. */
+void p2m_pod_get_mem_target(const struct domain *d, xen_pod_target_t *target);
+
+/* Check whether PoD is (still) active in a domain. */
+bool p2m_pod_active(const struct domain *d);
+
 /* Scan pod cache when offline/broken page triggered */
 int
 p2m_pod_offline_or_broken_hit(struct page_info *p);
@@ -709,11 +715,6 @@ p2m_pod_offline_or_broken_hit(struct page_info *p);
 void
 p2m_pod_offline_or_broken_replace(struct page_info *p);
 
-static inline long p2m_pod_entry_count(const struct p2m_domain *p2m)
-{
-    return p2m->pod.entry_count;
-}
-
 #else
 
 static inline bool
@@ -727,6 +728,11 @@ static inline int p2m_pod_empty_cache(struct domain *d)
     return 0;
 }
 
+static inline bool p2m_pod_active(const struct domain *d)
+{
+    return false;
+}
+
 static inline int p2m_pod_offline_or_broken_hit(struct page_info *p)
 {
     return 0;
@@ -737,11 +743,6 @@ static inline void p2m_pod_offline_or_broken_replace(struct page_info *p)
     ASSERT_UNREACHABLE();
 }
 
-static inline long p2m_pod_entry_count(const struct p2m_domain *p2m)
-{
-    return 0;
-}
-
 #endif
 
 

diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 74fa9205f43fcceed8a403033937adf27f207165..67c04279632cd8014cb13525281b1d23fb4dc96a 100644 (file)
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -4804,7 +4804,6 @@ long arch_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
     {
         xen_pod_target_t target;
         struct domain *d;
-        struct p2m_domain *p2m;
 
         if ( copy_from_guest(&target, arg, 1) )
             return -EFAULT;
@@ -4835,10 +4834,7 @@ long arch_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
         }
         else if ( rc >= 0 )
         {
-            p2m = p2m_get_hostp2m(d);
-            target.tot_pages       = domain_tot_pages(d);
-            target.pod_cache_pages = p2m->pod.count;
-            target.pod_entries     = p2m->pod.entry_count;
+            p2m_pod_get_mem_target(d, &target);
 
             if ( __copy_to_guest(arg, &target, 1) )
                 rc = -EFAULT;

diff --git a/xen/arch/x86/mm/p2m-pod.c b/xen/arch/x86/mm/p2m-pod.c
index fd12f8ca73366fb6ede6ab371ec909fdc874f876..fc110506dce29a9b0303171952921f421929e616 100644 (file)
--- a/xen/arch/x86/mm/p2m-pod.c
+++ b/xen/arch/x86/mm/p2m-pod.c
@@ -20,6 +20,7 @@
  */
 
 #include <xen/event.h>
+#include <xen/iocap.h>
 #include <xen/ioreq.h>
 #include <xen/mm.h>
 #include <xen/sched.h>
@@ -360,7 +361,10 @@ p2m_pod_set_mem_target(struct domain *d, unsigned long target)
 
     ASSERT( pod_target >= p2m->pod.count );
 
-    ret = p2m_pod_set_cache_target(p2m, pod_target, 1/*preemptible*/);
+    if ( has_arch_pdevs(d) || cache_flush_permitted(d) )
+        ret = -ENOTEMPTY;
+    else
+        ret = p2m_pod_set_cache_target(p2m, pod_target, 1/*preemptible*/);
 
 out:
     pod_unlock(p2m);
@@ -368,6 +372,23 @@ out:
     return ret;
 }
 
+void p2m_pod_get_mem_target(const struct domain *d, xen_pod_target_t *target)
+{
+    struct p2m_domain *p2m = p2m_get_hostp2m(d);
+
+    ASSERT(is_hvm_domain(d));
+
+    pod_lock(p2m);
+    lock_page_alloc(p2m);
+
+    target->tot_pages       = domain_tot_pages(d);
+    target->pod_cache_pages = p2m->pod.count;
+    target->pod_entries     = p2m->pod.entry_count;
+
+    unlock_page_alloc(p2m);
+    pod_unlock(p2m);
+}
+
 int p2m_pod_empty_cache(struct domain *d)
 {
     struct p2m_domain *p2m = p2m_get_hostp2m(d);
@@ -1391,6 +1412,9 @@ guest_physmap_mark_populate_on_demand(struct domain *d, unsigned long gfn,
     if ( !paging_mode_translate(d) )
         return -EINVAL;
 
+    if ( has_arch_pdevs(d) || cache_flush_permitted(d) )
+        return -ENOTEMPTY;
+
     do {
         rc = mark_populate_on_demand(d, gfn, chunk_order);
 
@@ -1412,3 +1436,20 @@ void p2m_pod_init(struct p2m_domain *p2m)
     for ( i = 0; i < ARRAY_SIZE(p2m->pod.mrp.list); ++i )
         p2m->pod.mrp.list[i] = gfn_x(INVALID_GFN);
 }
+
+bool p2m_pod_active(const struct domain *d)
+{
+    struct p2m_domain *p2m;
+    bool res;
+
+    if ( !is_hvm_domain(d) )
+        return false;
+
+    p2m = p2m_get_hostp2m(d);
+
+    pod_lock(p2m);
+    res = p2m->pod.entry_count | p2m->pod.count;
+    pod_unlock(p2m);
+
+    return res;
+}

diff --git a/xen/common/vm_event.c b/xen/common/vm_event.c
index 4a8f02893e69ff49125ed8a2951f13e8ef819b1f..0b99a6ea72fd65f8b924e5a043a0c52f0086c485 100644 (file)
--- a/xen/common/vm_event.c
+++ b/xen/common/vm_event.c
@@ -655,7 +655,7 @@ int vm_event_domctl(struct domain *d, struct xen_domctl_vm_event_op *vec)
 
             rc = -EXDEV;
             /* Disallow paging in a PoD guest */
-            if ( p2m_pod_entry_count(p2m_get_hostp2m(d)) )
+            if ( p2m_pod_active(d) )
                 break;
 
             /* domain_pause() not required here, see XSA-99 */

diff --git a/xen/drivers/passthrough/x86/iommu.c b/xen/drivers/passthrough/x86/iommu.c
index d5bf4d324196ebd30323720f24a30ab1cde3b3fa..616b66e755deb3385e13043a689776151e8b2545 100644 (file)
--- a/xen/drivers/passthrough/x86/iommu.c
+++ b/xen/drivers/passthrough/x86/iommu.c
@@ -513,11 +513,12 @@ bool arch_iommu_use_permitted(const struct domain *d)
 {
     /*
      * Prevent device assign if mem paging, mem sharing or log-dirty
-     * have been enabled for this domain.
+     * have been enabled for this domain, or if PoD is still in active use.
      */
     return d == dom_io ||
            (likely(!mem_sharing_enabled(d)) &&
             likely(!mem_paging_enabled(d)) &&
+            likely(!p2m_pod_active(d)) &&
             likely(!p2m_is_global_logdirty(d)));
 }