From: Andrew Cooper <andrew.cooper3@citrix.com>
Subject: x86: Livepatch mitigations for LazyFPU

This is part of XSA-267 / CVE-2018-3665

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>

diff --git a/xen/arch/x86/i387.c b/xen/arch/x86/i387.c
index 86b098d..859be4d 100644
--- a/xen/arch/x86/i387.c
+++ b/xen/arch/x86/i387.c
@@ -10,6 +10,7 @@
 
 #include <xen/config.h>
 #include <xen/sched.h>
+#include <xen/livepatch_payload.h>
 #include <asm/current.h>
 #include <asm/processor.h>
 #include <asm/hvm/support.h>
@@ -202,6 +203,94 @@ static inline void fpu_fxsave(struct vcpu *v)
     fpu_ctxt->x[FPU_WORD_SIZE_OFFSET] = fip_width;
 }
 
+/* Calculate whether this CPU speculates past #NM */
+static bool should_use_eager_fpu(void)
+{
+    /*
+     * Assume all unrecognised processors are ok.  This is only known to
+     * affect Intel Family 6 processors.
+     */
+    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 0x1e: /* Nehalem */
+    case 0x1f: /* Auburndale / Havendale */
+    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 0x55: /* Skylake X */
+    case 0x5e: /* Skylake D */
+    case 0x66: /* Cannonlake */
+    case 0x67: /* Cannonlake? */
+    case 0x8e: /* Kabylake M */
+    case 0x9e: /* Kabylake 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 0x5f: /* Denverton */
+    case 0x7a: /* Gemini Lake */
+        return false;
+
+        /*
+         * Knights processors are not vulnerable.
+         */
+    case 0x57: /* Knights Landing */
+    case 0x85: /* Knights Mill */
+        return false;
+
+    default:
+        printk("Unrecognised CPU model %#x - assuming vulnerable to LazyFPU\n",
+               boot_cpu_data.x86_model);
+        return true;
+    }
+}
+
+static bool fully_eager_fpu;
+
+void lazyfpu_apply_hook(void)
+{
+    fully_eager_fpu = should_use_eager_fpu();
+
+    printk("LazyFPU Livepatch: Fam %u, Model %u => Fully Eager %u\n",
+           boot_cpu_data.x86, boot_cpu_data.x86_model, fully_eager_fpu);
+}
+
+LIVEPATCH_LOAD_HOOK(lazyfpu_apply_hook);
+
 /*******************************/
 /*       VCPU FPU Functions    */
 /*******************************/
@@ -211,7 +300,7 @@ void vcpu_restore_fpu_eager(struct vcpu *v)
     ASSERT(!is_idle_vcpu(v));
     
     /* Restore nonlazy extended state (i.e. parts not tracked by CR0.TS). */
-    if ( !v->arch.nonlazy_xstate_used )
+    if ( !fully_eager_fpu && !v->arch.nonlazy_xstate_used )
         return;
 
     /* Avoid recursion */
@@ -222,11 +311,19 @@ void vcpu_restore_fpu_eager(struct vcpu *v)
      * above) we also need to restore full state, to prevent subsequently
      * saving state belonging to another vCPU.
      */
-    if ( xstate_all(v) )
+    if ( fully_eager_fpu || (v->arch.xsave_area && xstate_all(v)) )
     {
-        fpu_xrstor(v, XSTATE_ALL);
+        if ( cpu_has_xsave )
+            fpu_xrstor(v, XSTATE_ALL);
+        else
+            fpu_fxrstor(v);
+
         v->fpu_initialised = 1;
         v->fpu_dirtied = 1;
+
+        /* Xen doesn't need TS set, but the guest might. */
+        if ( is_pv_vcpu(v) && (v->arch.pv_vcpu.ctrlreg[0] & X86_CR0_TS) )
+            stts();
     }
     else
     {