Nested VMX: fix IA32_VMX_CR4_FIXED1 msr emulation

Currently, it use hardcode value for IA32_VMX_CR4_FIXED1. This is wrong.
We should check guest's cpuid to know which bits are writeable in CR4 by guest
and allow the guest to set the corresponding bit only when guest has the feature.

Signed-off-by: Yang Zhang <yang.z.zhang@Intel.com>

Cleanup.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Jun Nakajima <jun.nakajima@intel.com>

3 files changed, 53 insertions, 4 deletions

diff --git a/xen/arch/x86/hvm/vmx/vvmx.c b/xen/arch/x86/hvm/vmx/vvmx.c
index b911eb1499..eb0218e0db 100644
--- a/xen/arch/x86/hvm/vmx/vvmx.c
+++ b/xen/arch/x86/hvm/vmx/vvmx.c
@@ -1815,7 +1815,7 @@ int nvmx_handle_invvpid(struct cpu_user_regs *regs)
 int nvmx_msr_read_intercept(unsigned int msr, u64 *msr_content)
 {
     struct vcpu *v = current;
-    unsigned int ecx, dummy;
+    unsigned int eax, ebx, ecx, edx, dummy;
     u64 data = 0, host_data = 0;
     int r = 1;
 
@@ -1823,7 +1823,7 @@ int nvmx_msr_read_intercept(unsigned int msr, u64 *msr_content)
         return 0;
 
     /* VMX capablity MSRs are available only when guest supports VMX. */
-    hvm_cpuid(0x1, &dummy, &dummy, &ecx, &dummy);
+    hvm_cpuid(0x1, &dummy, &dummy, &ecx, &edx);
     if ( !(ecx & cpufeat_mask(X86_FEATURE_VMXE)) )
         return 0;
 
@@ -1948,8 +1948,55 @@ int nvmx_msr_read_intercept(unsigned int msr, u64 *msr_content)
         data = X86_CR4_VMXE;
         break;
     case MSR_IA32_VMX_CR4_FIXED1:
-        /* allow 0-settings except SMXE */
-        data = 0x267ff & ~X86_CR4_SMXE;
+        if ( edx & cpufeat_mask(X86_FEATURE_VME) )
+            data |= X86_CR4_VME | X86_CR4_PVI;
+        if ( edx & cpufeat_mask(X86_FEATURE_TSC) )
+            data |= X86_CR4_TSD;
+        if ( edx & cpufeat_mask(X86_FEATURE_DE) )
+            data |= X86_CR4_DE;
+        if ( edx & cpufeat_mask(X86_FEATURE_PSE) )
+            data |= X86_CR4_PSE;
+        if ( edx & cpufeat_mask(X86_FEATURE_PAE) )
+            data |= X86_CR4_PAE;
+        if ( edx & cpufeat_mask(X86_FEATURE_MCE) )
+            data |= X86_CR4_MCE;
+        if ( edx & cpufeat_mask(X86_FEATURE_PGE) )
+            data |= X86_CR4_PGE;
+        if ( edx & cpufeat_mask(X86_FEATURE_FXSR) )
+            data |= X86_CR4_OSFXSR;
+        if ( edx & cpufeat_mask(X86_FEATURE_XMM) )
+            data |= X86_CR4_OSXMMEXCPT;
+        if ( ecx & cpufeat_mask(X86_FEATURE_VMXE) )
+            data |= X86_CR4_VMXE;
+        if ( ecx & cpufeat_mask(X86_FEATURE_SMXE) )
+            data |= X86_CR4_SMXE;
+        if ( ecx & cpufeat_mask(X86_FEATURE_PCID) )
+            data |= X86_CR4_PCIDE;
+        if ( ecx & cpufeat_mask(X86_FEATURE_XSAVE) )
+            data |= X86_CR4_OSXSAVE;
+
+        hvm_cpuid(0x0, &eax, &dummy, &dummy, &dummy);
+        switch ( eax )
+        {
+        default:
+            hvm_cpuid(0xa, &eax, &dummy, &dummy, &dummy);
+            /* Check whether guest has the perf monitor feature. */
+            if ( (eax & 0xff) && (eax & 0xff00) )
+                data |= X86_CR4_PCE;
+            /* fall through */
+        case 0x7 ... 0x9:
+            ecx = 0;
+            hvm_cpuid(0x7, &dummy, &ebx, &ecx, &dummy);
+            if ( ebx & cpufeat_mask(X86_FEATURE_FSGSBASE) )
+                data |= X86_CR4_FSGSBASE;
+            if ( ebx & cpufeat_mask(X86_FEATURE_SMEP) )
+                data |= X86_CR4_SMEP;
+            if ( ebx & cpufeat_mask(X86_FEATURE_SMAP) )
+                data |= X86_CR4_SMAP;
+            /* fall through */
+        case 0x0 ... 0x6:
+            break;
+        }
         break;
     case MSR_IA32_VMX_MISC:
         /* Do not support CR3-target feature now */
diff --git a/xen/include/asm-x86/cpufeature.h b/xen/include/asm-x86/cpufeature.h
index 065c2652a8..1cfaf948b2 100644
--- a/xen/include/asm-x86/cpufeature.h
+++ b/xen/include/asm-x86/cpufeature.h
@@ -148,6 +148,7 @@
 #define X86_FEATURE_INVPCID	(7*32+10) /* Invalidate Process Context ID */
 #define X86_FEATURE_RTM 	(7*32+11) /* Restricted Transactional Memory */
 #define X86_FEATURE_NO_FPU_SEL 	(7*32+13) /* FPU CS/DS stored as zero */
+#define X86_FEATURE_SMAP	(7*32+20) /* Supervisor Mode Access Prevention */
 
 #define cpu_has(c, bit)		test_bit(bit, (c)->x86_capability)
 #define boot_cpu_has(bit)	test_bit(bit, boot_cpu_data.x86_capability)
diff --git a/xen/include/asm-x86/processor.h b/xen/include/asm-x86/processor.h
index 5cdacc7e4d..893afa3a84 100644
--- a/xen/include/asm-x86/processor.h
+++ b/xen/include/asm-x86/processor.h
@@ -87,6 +87,7 @@
 #define X86_CR4_PCIDE		0x20000 /* enable PCID */
 #define X86_CR4_OSXSAVE	0x40000 /* enable XSAVE/XRSTOR */
 #define X86_CR4_SMEP		0x100000/* enable SMEP */
+#define X86_CR4_SMAP		0x200000/* enable SMAP */
 
 /*
  * Trap/fault mnemonics.