x86, vtd: [CVE-2011-1898] Protect against malicious MSIs from untrusted devices.

In the absence of VT-d interrupt remapping support, a device can send
arbitrary APIC messages to host CPUs. One class of attack that results
is to confuse the hypervisor by delivering asynchronous interrupts to
vectors that are expected to handle only synchronous
traps/exceptions.

We block this class of attack by:
(1) setting APIC.TPR=0x10, to block all interrupts below vector
0x20. This blocks delivery to all architectural exception vectors.
(2) checking APIC.ISR[vec] for vectors 0x80 (fast syscall) and 0x82
(hypercall). In these cases we BUG if we detect we are handling a
hardware interrupt -- turning a potentially more severe infiltration
into a straightforward system crash (i.e, DoS).

Thanks to Invisible Things Lab <http://www.invisiblethingslab.com>
for discovery and detailed investigation of this attack.

Signed-off-by: Keir Fraser <keir@xen.org>
xen-unstable changeset:   23337:cc91832a02c7
xen-unstable date:        Thu May 12 16:39:31 2011 +0100

4 files changed, 37 insertions, 5 deletions

diff --git a/xen/arch/x86/apic.c b/xen/arch/x86/apic.c
index 1590c3a171..3a0f6fb725 100644
--- a/xen/arch/x86/apic.c
+++ b/xen/arch/x86/apic.c
@@ -575,12 +575,9 @@ void __devinit setup_local_APIC(void)
     init_apic_ldr();
 
     /*
-     * Set Task Priority to 'accept all'. We never change this
-     * later on.
+     * Set Task Priority to reject any interrupts below FIRST_DYNAMIC_VECTOR.
      */
-    value = apic_read(APIC_TASKPRI);
-    value &= ~APIC_TPRI_MASK;
-    apic_write_around(APIC_TASKPRI, value);
+    apic_write_around(APIC_TASKPRI, (FIRST_DYNAMIC_VECTOR & 0xF0) - 0x10);
 
     /*
      * After a crash, we no longer service the interrupts and a pending
@@ -1483,3 +1480,9 @@ int __init APIC_init_uniprocessor (void)
 
     return 0;
 }
+
+void check_for_unexpected_msi(unsigned int vector)
+{
+    unsigned long v = apic_read(APIC_ISR + ((vector & ~0x1f) >> 1));
+    BUG_ON(v & (1 << (vector & 0x1f)));
+}
diff --git a/xen/arch/x86/x86_64/compat/entry.S b/xen/arch/x86/x86_64/compat/entry.S
index d87ef0cfde..8208b6b54f 100644
--- a/xen/arch/x86/x86_64/compat/entry.S
+++ b/xen/arch/x86/x86_64/compat/entry.S
@@ -10,12 +10,22 @@
 #include <asm/page.h>
 #include <asm/desc.h>
 #include <public/xen.h>
+#include <irq_vectors.h>
 
         ALIGN
 ENTRY(compat_hypercall)
         pushq $0
         movl  $TRAP_syscall,4(%rsp)
         SAVE_ALL
+
+        cmpb  $0,untrusted_msi(%rip)
+UNLIKELY_START(ne, msi_check)
+        movl  $HYPERCALL_VECTOR,%edi
+        call  check_for_unexpected_msi
+        RESTORE_ALL
+        SAVE_ALL
+UNLIKELY_END(msi_check)
+
         GET_CURRENT(%rbx)
 
         cmpl  $NR_hypercalls,%eax
diff --git a/xen/arch/x86/x86_64/entry.S b/xen/arch/x86/x86_64/entry.S
index a6c68220c8..61938f8f49 100644
--- a/xen/arch/x86/x86_64/entry.S
+++ b/xen/arch/x86/x86_64/entry.S
@@ -296,6 +296,14 @@ ENTRY(int80_direct_trap)
         pushq $0
         SAVE_ALL
 
+        cmpb  $0,untrusted_msi(%rip)
+UNLIKELY_START(ne, msi_check)
+        movl  $0x80,%edi
+        call  check_for_unexpected_msi
+        RESTORE_ALL
+        SAVE_ALL
+UNLIKELY_END(msi_check)
+
         GET_CURRENT(%rbx)
 
         /* Check that the callback is non-null. */
diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c
index abcf022454..b33cff22e1 100644
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -48,6 +48,9 @@
 static int sharept = 0;
 boolean_param("sharept", sharept);
 
+/* Possible unfiltered LAPIC/MSI messages from untrusted sources? */
+bool_t __read_mostly untrusted_msi;
+
 int nr_iommus;
 
 static void setup_dom0_devices(struct domain *d);
@@ -1582,6 +1585,14 @@ static int reassign_device_ownership(
     if (!pdev)
         return -ENODEV;
 
+    /*
+     * Devices assigned to untrusted domains (here assumed to be any domU)
+     * can attempt to send arbitrary LAPIC/MSI messages. We are unprotected
+     * by the root complex unless interrupt remapping is enabled.
+     */
+    if ( (target != dom0) && !iommu_intremap )
+        untrusted_msi = 1;
+
     ret = domain_context_unmap(source, bus, devfn);
     if ( ret )
         return ret;