File xsa304-2.patch of Package xen

x86/vtx: Disable executable EPT superpages to work around CVE-2018-12207

CVE-2018-12207 covers a set of errata on various Intel processors, whereby a
machine check exception can be generated in a corner case when an executable
mapping changes size or cacheability without TLB invalidation.  HVM guest
kernels can trigger this to DoS the host.

To mitigate, in affected hardware, all EPT superpages are marked NX.  When an
instruction fetch violation is observed against the superpage, the superpage
is shattered to 4k and has execute permissions restored.  This prevents the
guest kernel from being able to create the necessary preconditions in the iTLB
to exploit the vulnerability.

This does come with a workload-dependent performance overhead, caused by
increased TLB pressure.  Performance can be restored, if guest kernels are
trusted not to mount an attack, by specifying ept=exec-sp on the command line.

This is part of XSA-304 / CVE-2018-12207

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: George Dunlap <george.dunlap@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -849,7 +849,7 @@ virtualization, to allow the L1 hypervis
 does not provide VM\_ENTRY\_LOAD\_GUEST\_PAT.
 
 ### ept (Intel)
-> `= List of ( {no-}pml | {no-}ad )`
+> `= List of ( {no-}pml | {no-}ad | {no-}exec-sp )`
 
 Controls EPT related features.
 
@@ -872,6 +872,20 @@ Controls EPT related features.
 
 >> Have hardware keep accessed/dirty (A/D) bits updated.
 
+> `exec-sp`
+
+> Default: `false`
+
+>> Controls whether EPT superpages with execute permissions are permitted.
+>> In general this is good for performance.
+
+>> However, on processors vulnerable CVE-2018-12207, HVM guest kernels can
+>> use executable superpages to crash the host.  By default, executable
+>> superpages are disabled on affected hardware.
+
+>> If HVM guest kernels are trusted not to mount a DoS against the system,
+>>  this option can enabled to regain performance.
+
 ### gdb
 > `= com1[H,L] | com2[H,L] | dbgp`
 
--- a/xen/arch/x86/hvm/hvm.c
+++ b/xen/arch/x86/hvm/hvm.c
@@ -1650,6 +1650,7 @@ int hvm_hap_nested_page_fault(paddr_t gp
     int sharing_enomem = 0;
     vm_event_request_t *req_ptr = NULL;
     bool_t ap2m_active, sync = 0;
+    unsigned int page_order;
 
     /* On Nested Virtualization, walk the guest page table.
      * If this succeeds, all is fine.
@@ -1718,7 +1719,7 @@ int hvm_hap_nested_page_fault(paddr_t gp
     hostp2m = p2m_get_hostp2m(currd);
     mfn = get_gfn_type_access(hostp2m, gfn, &p2mt, &p2ma,
                               P2M_ALLOC | (npfec.write_access ? P2M_UNSHARE : 0),
-                              NULL);
+                              &page_order);
 
     if ( ap2m_active )
     {
@@ -1730,7 +1731,7 @@ int hvm_hap_nested_page_fault(paddr_t gp
             goto out;
         }
 
-        mfn = get_gfn_type_access(p2m, gfn, &p2mt, &p2ma, 0, NULL);
+        mfn = get_gfn_type_access(p2m, gfn, &p2mt, &p2ma, 0, &page_order);
     }
     else
         p2m = hostp2m;
@@ -1772,6 +1773,24 @@ int hvm_hap_nested_page_fault(paddr_t gp
             break;
         }
 
+        /*
+         * Workaround for XSA-304 / CVE-2018-12207.  If we take an execution
+         * fault against a non-executable superpage, shatter it to regain
+         * execute permissions.
+         */
+        if ( page_order > 0 && npfec.insn_fetch && npfec.present && !violation )
+        {
+            int res = p2m_set_entry(p2m, gfn, mfn, PAGE_ORDER_4K,
+                                    p2mt, p2ma);
+
+            if ( res )
+                printk(XENLOG_ERR "Failed to shatter gfn %"PRI_gfn": %d\n",
+                       gfn, res);
+
+            rc = !res;
+            goto out_put_gfn;
+        }
+
         if ( violation )
         {
             /* Should #VE be emulated for this fault? */
--- a/xen/arch/x86/hvm/vmx/vmcs.c
+++ b/xen/arch/x86/hvm/vmx/vmcs.c
@@ -67,6 +67,7 @@ integer_param("ple_window", ple_window);
 
 static bool_t __read_mostly opt_pml_enabled = 1;
 static s8 __read_mostly opt_ept_ad = -1;
+int8_t __read_mostly opt_ept_exec_sp = -1;
 
 /*
  * The 'ept' parameter controls functionalities that depend on, or impact the
@@ -93,6 +94,8 @@ static void __init parse_ept_param(char
             opt_pml_enabled = val;
         else if ( !strcmp(s, "ad") )
             opt_ept_ad = val;
+        else if ( !strcmp(s, "exec-sp") )
+            opt_ept_exec_sp = val;
 
         s = ss + 1;
     } while ( ss );
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -2496,6 +2496,102 @@ static void pi_notification_interrupt(st
 static void __init lbr_tsx_fixup_check(void);
 static void __init bdw_erratum_bdf14_fixup_check(void);
 
+/*
+ * Calculate whether the CPU is vulnerable to Instruction Fetch page
+ * size-change MCEs.
+ */
+static bool __init has_if_pschange_mc(void)
+{
+    uint64_t caps = 0;
+
+    /*
+     * If we are virtualised, there is nothing we can do.  Our EPT tables are
+     * shadowed by our hypervisor, and not walked by hardware.
+     */
+    if ( cpu_has_hypervisor )
+        return false;
+
+    if ( boot_cpu_has(X86_FEATURE_ARCH_CAPS) )
+        rdmsrl(MSR_ARCH_CAPABILITIES, caps);
+
+    if ( caps & ARCH_CAPS_IF_PSCHANGE_MC_NO )
+        return false;
+
+    /*
+     * IF_PSCHANGE_MC is only known to affect Intel Family 6 processors at
+     * this time.
+     */
+    if ( boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
+         boot_cpu_data.x86 != 6 )
+        return false;
+
+    switch ( boot_cpu_data.x86_model )
+    {
+        /*
+         * Core processors since at least Nehalem are vulnerable.
+         */
+    case 0x1f: /* Auburndale / Havendale */
+    case 0x1e: /* Nehalem */
+    case 0x1a: /* Nehalem EP */
+    case 0x2e: /* Nehalem EX */
+    case 0x25: /* Westmere */
+    case 0x2c: /* Westmere EP */
+    case 0x2f: /* Westmere EX */
+    case 0x2a: /* SandyBridge */
+    case 0x2d: /* SandyBridge EP/EX */
+    case 0x3a: /* IvyBridge */
+    case 0x3e: /* IvyBridge EP/EX */
+    case 0x3c: /* Haswell */
+    case 0x3f: /* Haswell EX/EP */
+    case 0x45: /* Haswell D */
+    case 0x46: /* Haswell H */
+    case 0x3d: /* Broadwell */
+    case 0x47: /* Broadwell H */
+    case 0x4f: /* Broadwell EP/EX */
+    case 0x56: /* Broadwell D */
+    case 0x4e: /* Skylake M */
+    case 0x5e: /* Skylake D */
+    case 0x55: /* Skylake-X / Cascade Lake */
+    case 0x8e: /* Kaby / Coffee / Whiskey Lake M */
+    case 0x9e: /* Kaby / Coffee / Whiskey Lake D */
+        return true;
+
+        /*
+         * Atom processors are not vulnerable.
+         */
+    case 0x1c: /* Pineview */
+    case 0x26: /* Lincroft */
+    case 0x27: /* Penwell */
+    case 0x35: /* Cloverview */
+    case 0x36: /* Cedarview */
+    case 0x37: /* Baytrail / Valleyview (Silvermont) */
+    case 0x4d: /* Avaton / Rangely (Silvermont) */
+    case 0x4c: /* Cherrytrail / Brasswell */
+    case 0x4a: /* Merrifield */
+    case 0x5a: /* Moorefield */
+    case 0x5c: /* Goldmont */
+    case 0x5d: /* SoFIA 3G Granite/ES2.1 */
+    case 0x65: /* SoFIA LTE AOSP */
+    case 0x5f: /* Denverton */
+    case 0x6e: /* Cougar Mountain */
+    case 0x75: /* Lightning Mountain */
+    case 0x7a: /* Gemini Lake */
+    case 0x86: /* Jacobsville */
+
+        /*
+         * Knights processors are not vulnerable.
+         */
+    case 0x57: /* Knights Landing */
+    case 0x85: /* Knights Mill */
+        return false;
+
+    default:
+        printk("Unrecognised CPU model %#x - assuming vulnerable to IF_PSCHANGE_MC\n",
+               boot_cpu_data.x86_model);
+        return true;
+    }
+}
+
 const struct hvm_function_table * __init start_vmx(void)
 {
     set_in_cr4(X86_CR4_VMXE);
@@ -2516,6 +2612,17 @@ const struct hvm_function_table * __init
      */
     if ( cpu_has_vmx_ept && (cpu_has_vmx_pat || opt_force_ept) )
     {
+        bool cpu_has_bug_pschange_mc = has_if_pschange_mc();
+
+        if ( opt_ept_exec_sp == -1 )
+        {
+            /* Default to non-executable superpages on vulnerable hardware. */
+            opt_ept_exec_sp = !cpu_has_bug_pschange_mc;
+
+            if ( cpu_has_bug_pschange_mc )
+                printk("VMX: Disabling executable EPT superpages due to CVE-2018-12207\n");
+        }
+
         vmx_function_table.hap_supported = 1;
         vmx_function_table.altp2m_supported = 1;
 
--- a/xen/arch/x86/mm/p2m-ept.c
+++ b/xen/arch/x86/mm/p2m-ept.c
@@ -215,6 +215,12 @@ static void ept_p2m_type_to_flags(struct
             break;
     }
     
+    /*
+     * Don't create executable superpages if we need to shatter them to
+     * protect against CVE-2018-12207.
+     */
+    if ( !opt_ept_exec_sp && is_epte_superpage(entry) )
+        entry->x = 0;
 }
 
 #define GUEST_TABLE_MAP_FAILED  0
--- a/xen/include/asm-x86/hvm/vmx/vmx.h
+++ b/xen/include/asm-x86/hvm/vmx/vmx.h
@@ -28,6 +28,8 @@
 #include <asm/hvm/trace.h>
 #include <asm/hvm/vmx/vmcs.h>
 
+extern int8_t opt_ept_exec_sp;
+
 typedef union {
     struct {
         u64 r       :   1,  /* bit 0 - Read permission */
--- a/xen/include/asm-x86/msr-index.h
+++ b/xen/include/asm-x86/msr-index.h
@@ -54,6 +54,7 @@
 #define ARCH_CAPS_SKIP_L1DFL		(_AC(1, ULL) << 3)
 #define ARCH_CAPS_SSB_NO		(_AC(1, ULL) << 4)
 #define ARCH_CAPS_MDS_NO		(_AC(1, ULL) << 5)
+#define ARCH_CAPS_IF_PSCHANGE_MC_NO	(_AC(1, ULL) << 6)
 
 #define MSR_FLUSH_CMD			0x0000010b
 #define FLUSH_CMD_L1D			(_AC(1, ULL) << 0)
openSUSE Build Service is sponsored by