KVM: VMX: Don't intercept MSR_KERNEL_GS_BASE

Windows 2008 accesses this MSR often on context switch intensive workloads;
since we run in guest context with the guest MSR value loaded (so swapgs can
work correctly), we can simply disable interception of rdmsr/wrmsr for this
MSR.

A complication occurs since in legacy mode, we run with the host MSR value
loaded. In this case we enable interception.  This means we need two MSR
bitmaps, one for legacy mode and one for long mode.

Signed-off-by: Avi Kivity <avi@redhat.com>
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b20c9e4..b5eae7a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -113,7 +113,8 @@
 
 static unsigned long *vmx_io_bitmap_a;
 static unsigned long *vmx_io_bitmap_b;
-static unsigned long *vmx_msr_bitmap;
+static unsigned long *vmx_msr_bitmap_legacy;
+static unsigned long *vmx_msr_bitmap_longmode;
 
 static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
 static DEFINE_SPINLOCK(vmx_vpid_lock);
@@ -812,6 +813,7 @@
 static void setup_msrs(struct vcpu_vmx *vmx)
 {
 	int save_nmsrs;
+	unsigned long *msr_bitmap;
 
 	vmx_load_host_state(vmx);
 	save_nmsrs = 0;
@@ -847,6 +849,15 @@
 		__find_msr_index(vmx, MSR_KERNEL_GS_BASE);
 #endif
 	vmx->msr_offset_efer = __find_msr_index(vmx, MSR_EFER);
+
+	if (cpu_has_vmx_msr_bitmap()) {
+		if (is_long_mode(&vmx->vcpu))
+			msr_bitmap = vmx_msr_bitmap_longmode;
+		else
+			msr_bitmap = vmx_msr_bitmap_legacy;
+
+		vmcs_write64(MSR_BITMAP, __pa(msr_bitmap));
+	}
 }
 
 /*
@@ -2082,7 +2093,7 @@
 	spin_unlock(&vmx_vpid_lock);
 }
 
-static void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr)
+static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr)
 {
 	int f = sizeof(unsigned long);
 
@@ -2104,6 +2115,13 @@
 	}
 }
 
+static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only)
+{
+	if (!longmode_only)
+		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, msr);
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, msr);
+}
+
 /*
  * Sets up the vmcs for emulated real mode.
  */
@@ -2123,7 +2141,7 @@
 	vmcs_write64(IO_BITMAP_B, __pa(vmx_io_bitmap_b));
 
 	if (cpu_has_vmx_msr_bitmap())
-		vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap));
+		vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy));
 
 	vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
 
@@ -3705,12 +3723,18 @@
 		goto out;
 	}
 
-	vmx_msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap) {
+	vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL);
+	if (!vmx_msr_bitmap_legacy) {
 		r = -ENOMEM;
 		goto out1;
 	}
 
+	vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL);
+	if (!vmx_msr_bitmap_longmode) {
+		r = -ENOMEM;
+		goto out2;
+	}
+
 	/*
 	 * Allow direct access to the PC debug port (it is often used for I/O
 	 * delays, but the vmexits simply slow things down).
@@ -3720,19 +3744,21 @@
 
 	memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
 
-	memset(vmx_msr_bitmap, 0xff, PAGE_SIZE);
+	memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
+	memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
 
 	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
 
 	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE);
 	if (r)
-		goto out2;
+		goto out3;
 
-	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_FS_BASE);
-	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_GS_BASE);
-	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_CS);
-	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_ESP);
-	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_EIP);
+	vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
+	vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
+	vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
+	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
+	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
+	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
 
 	if (vm_need_ept()) {
 		bypass_guest_pf = 0;
@@ -3752,8 +3778,10 @@
 
 	return 0;
 
+out3:
+	free_page((unsigned long)vmx_msr_bitmap_longmode);
 out2:
-	free_page((unsigned long)vmx_msr_bitmap);
+	free_page((unsigned long)vmx_msr_bitmap_legacy);
 out1:
 	free_page((unsigned long)vmx_io_bitmap_b);
 out:
@@ -3763,7 +3791,8 @@
 
 static void __exit vmx_exit(void)
 {
-	free_page((unsigned long)vmx_msr_bitmap);
+	free_page((unsigned long)vmx_msr_bitmap_legacy);
+	free_page((unsigned long)vmx_msr_bitmap_longmode);
 	free_page((unsigned long)vmx_io_bitmap_b);
 	free_page((unsigned long)vmx_io_bitmap_a);