x86: handle resumed instruction based on previous mem_event reply

In a scenario where a page fault that triggered a mem_event occured,
p2m_mem_access_check() will now be able to either 1) emulate the
current instruction, or 2) emulate it, but don't allow it to perform
any writes.

Signed-off-by: Razvan Cojocaru <rcojocaru@bitdefender.com>
Acked-by: Tim Deegan <tim@xen.org>
Acked-by: Jan Beulich <jbeulich@suse.com>

diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index f7e0e7856c49568a26dc5f202f187d0339f43141..7b1dfe6408bb5e1624e909416cdb0086d2d7ba95 100644 (file)
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -415,6 +415,9 @@ int vcpu_initialise(struct vcpu *v)
 
     v->arch.flags = TF_kernel_mode;
 
+    /* By default, do not emulate */
+    v->arch.mem_event.emulate_flags = 0;
+
     rc = mapcache_vcpu_init(v);
     if ( rc )
         return rc;

diff --git a/xen/arch/x86/mm/p2m.c b/xen/arch/x86/mm/p2m.c
index 7587797347b99cba10f204c805d72f10bcbf0e71..54859c8d844835bcbd73dcc9a6f928cd3ca404ed 100644 (file)
--- a/xen/arch/x86/mm/p2m.c
+++ b/xen/arch/x86/mm/p2m.c
@@ -1395,6 +1395,7 @@ bool_t p2m_mem_access_check(paddr_t gpa, unsigned long gla,
     p2m_access_t p2ma;
     mem_event_request_t *req;
     int rc;
+    unsigned long eip = guest_cpu_user_regs()->eip;
 
     /* First, handle rx2rw conversion automatically.
      * These calls to p2m->set_entry() must succeed: we have the gfn
@@ -1448,6 +1449,30 @@ bool_t p2m_mem_access_check(paddr_t gpa, unsigned long gla,
         }
     }
 
+    /* The previous mem_event reply does not match the current state. */
+    if ( v->arch.mem_event.gpa != gpa || v->arch.mem_event.eip != eip )
+    {
+        /* Don't emulate the current instruction, send a new mem_event. */
+        v->arch.mem_event.emulate_flags = 0;
+
+        /*
+         * Make sure to mark the current state to match it again against
+         * the new mem_event about to be sent.
+         */
+        v->arch.mem_event.gpa = gpa;
+        v->arch.mem_event.eip = eip;
+    }
+
+    if ( v->arch.mem_event.emulate_flags )
+    {
+        hvm_mem_event_emulate_one((v->arch.mem_event.emulate_flags &
+                                   MEM_EVENT_FLAG_EMULATE_NOWRITE) != 0,
+                                  TRAP_invalid_op, HVM_DELIVER_NO_ERROR_CODE);
+
+        v->arch.mem_event.emulate_flags = 0;
+        return 1;
+    }
+
     *req_ptr = NULL;
     req = xzalloc(mem_event_request_t);
     if ( req )
@@ -1502,6 +1527,56 @@ void p2m_mem_access_resume(struct domain *d)
 
         v = d->vcpu[rsp.vcpu_id];
 
+        /* Mark vcpu for skipping one instruction upon rescheduling. */
+        if ( rsp.flags & MEM_EVENT_FLAG_EMULATE )
+        {
+            xenmem_access_t access;
+            bool_t violation = 1;
+
+            if ( p2m_get_mem_access(d, rsp.gfn, &access) == 0 )
+            {
+                switch ( access )
+                {
+                case XENMEM_access_n:
+                case XENMEM_access_n2rwx:
+                default:
+                    violation = rsp.access_r || rsp.access_w || rsp.access_x;
+                    break;
+
+                case XENMEM_access_r:
+                    violation = rsp.access_w || rsp.access_x;
+                    break;
+
+                case XENMEM_access_w:
+                    violation = rsp.access_r || rsp.access_x;
+                    break;
+
+                case XENMEM_access_x:
+                    violation = rsp.access_r || rsp.access_w;
+                    break;
+
+                case XENMEM_access_rx:
+                case XENMEM_access_rx2rw:
+                    violation = rsp.access_w;
+                    break;
+
+                case XENMEM_access_wx:
+                    violation = rsp.access_r;
+                    break;
+
+                case XENMEM_access_rw:
+                    violation = rsp.access_x;
+                    break;
+
+                case XENMEM_access_rwx:
+                    violation = 0;
+                    break;
+                }
+            }
+
+            v->arch.mem_event.emulate_flags = violation ? rsp.flags : 0;
+        }
+
         /* Unpause domain */
         if ( rsp.flags & MEM_EVENT_FLAG_VCPU_PAUSED )
             mem_event_vcpu_unpause(v);

diff --git a/xen/include/asm-x86/domain.h b/xen/include/asm-x86/domain.h
index 8fc5a45bc05ce81a717f18eae715d999c727f3fe..7abe1b3a8809a4ed148412f0ebe52552c95feca5 100644 (file)
--- a/xen/include/asm-x86/domain.h
+++ b/xen/include/asm-x86/domain.h
@@ -459,6 +459,17 @@ struct arch_vcpu
 
     /* A secondary copy of the vcpu time info. */
     XEN_GUEST_HANDLE(vcpu_time_info_t) time_info_guest;
+
+    /*
+     * Should we emulate the next matching instruction on VCPU resume
+     * after a mem_event?
+     */
+    struct {
+        uint32_t emulate_flags;
+        unsigned long gpa;
+        unsigned long eip;
+    } mem_event;
+
 } __cacheline_aligned;
 
 smap_check_policy_t smap_policy_change(struct vcpu *v,

diff --git a/xen/include/public/mem_event.h b/xen/include/public/mem_event.h
index d3dd9c67e81763a65b6fc5c66bc511bf22e70217..599f9e8074cf4043308eef4f491a3c1befd5db9d 100644 (file)
--- a/xen/include/public/mem_event.h
+++ b/xen/include/public/mem_event.h
@@ -31,11 +31,22 @@
 #include "io/ring.h"
 
 /* Memory event flags */
-#define MEM_EVENT_FLAG_VCPU_PAUSED  (1 << 0)
-#define MEM_EVENT_FLAG_DROP_PAGE    (1 << 1)
-#define MEM_EVENT_FLAG_EVICT_FAIL   (1 << 2)
-#define MEM_EVENT_FLAG_FOREIGN      (1 << 3)
-#define MEM_EVENT_FLAG_DUMMY        (1 << 4)
+#define MEM_EVENT_FLAG_VCPU_PAUSED     (1 << 0)
+#define MEM_EVENT_FLAG_DROP_PAGE       (1 << 1)
+#define MEM_EVENT_FLAG_EVICT_FAIL      (1 << 2)
+#define MEM_EVENT_FLAG_FOREIGN         (1 << 3)
+#define MEM_EVENT_FLAG_DUMMY           (1 << 4)
+/*
+ * Emulate the fault-causing instruction (if set in the event response flags).
+ * This will allow the guest to continue execution without lifting the page
+ * access restrictions.
+ */
+#define MEM_EVENT_FLAG_EMULATE         (1 << 5)
+/*
+ * Same as MEM_EVENT_FLAG_EMULATE, but with write operations or operations
+ * potentially having side effects (like memory mapped or port I/O) disabled.
+ */
+#define MEM_EVENT_FLAG_EMULATE_NOWRITE (1 << 6)
 
 /* Reasons for the memory event request */
 #define MEM_EVENT_REASON_UNKNOWN     0    /* typical reason */