kernel/KVM-x86-fix-missing-checks-in-syscall-emulation.patch

From e28ba7bb020f07193bc000453c8775e9d2c0dda7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Stephan=20B=C3=A4rwolf?= <stephan.baerwolf@tu-ilmenau.de>
Date: Thu, 12 Jan 2012 16:43:04 +0100
Subject: [PATCH 2/2] KVM: x86: fix missing checks in syscall emulation

On hosts without this patch, 32bit guests will crash (and 64bit guests
may behave in a wrong way) for example by simply executing following
nasm-demo-application:

    [bits 32]
    global _start
    SECTION .text
    _start: syscall

(I tested it with winxp and linux - both always crashed)

    Disassembly of section .text:

    00000000 <_start>:
       0:   0f 05                   syscall

The reason seems a missing "invalid opcode"-trap (int6) for the
syscall opcode "0f05", which is not available on Intel CPUs
within non-longmodes, as also on some AMD CPUs within legacy-mode.
(depending on CPU vendor, MSR_EFER and cpuid)

Because previous mentioned OSs may not engage corresponding
syscall target-registers (STAR, LSTAR, CSTAR), they remain
NULL and (non trapping) syscalls are leading to multiple
faults and finally crashs.

Depending on the architecture (AMD or Intel) pretended by
guests, various checks according to vendor's documentation
are implemented to overcome the current issue and behave
like the CPUs physical counterparts.

[mtosatti: cleanup/beautify code]

Signed-off-by: Stephan Baerwolf <stephan.baerwolf@tu-ilmenau.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_emulate.h |   13 +++++++++
 arch/x86/kvm/emulate.c             |   51 ++++++++++++++++++++++++++++++++++++
 2 files changed, 64 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index c8b2868..7b9cfc4 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -301,6 +301,19 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_PROT     (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \
 			       X86EMUL_MODE_PROT64)
 
+/* CPUID vendors */
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65
+
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx 0x69444d41
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx 0x21726574
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_edx 0x74656273
+
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_ebx 0x756e6547
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69
+
 enum x86_intercept_stage {
 	X86_ICTP_NONE = 0,   /* Allow zero-init to not match anything */
 	X86_ICPT_PRE_EXCEPT,
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 05a562b..0982507 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1891,6 +1891,51 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
 	ss->p = 1;
 }
 
+static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
+{
+	struct x86_emulate_ops *ops = ctxt->ops;
+	u32 eax, ebx, ecx, edx;
+
+	/*
+	 * syscall should always be enabled in longmode - so only become
+	 * vendor specific (cpuid) if other modes are active...
+	 */
+	if (ctxt->mode == X86EMUL_MODE_PROT64)
+		return true;
+
+	eax = 0x00000000;
+	ecx = 0x00000000;
+	if (ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx)) {
+		/*
+		 * Intel ("GenuineIntel")
+		 * remark: Intel CPUs only support "syscall" in 64bit
+		 * longmode. Also an 64bit guest with a
+		 * 32bit compat-app running will #UD !! While this
+		 * behaviour can be fixed (by emulating) into AMD
+		 * response - CPUs of AMD can't behave like Intel.
+		 */
+		if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx &&
+		    ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx &&
+		    edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx)
+			return false;
+
+		/* AMD ("AuthenticAMD") */
+		if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx &&
+		    ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx &&
+		    edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx)
+			return true;
+
+		/* AMD ("AMDisbetter!") */
+		if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx &&
+		    ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx &&
+		    edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx)
+			return true;
+	}
+
+	/* default: (not Intel, not AMD), apply Intel's stricter rules... */
+	return false;
+}
+
 static int em_syscall(struct x86_emulate_ctxt *ctxt)
 {
 	struct x86_emulate_ops *ops = ctxt->ops;
@@ -1904,9 +1949,15 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
 	    ctxt->mode == X86EMUL_MODE_VM86)
 		return emulate_ud(ctxt);
 
+	if (!(em_syscall_is_enabled(ctxt)))
+		return emulate_ud(ctxt);
+
 	ops->get_msr(ctxt, MSR_EFER, &efer);
 	setup_syscalls_segments(ctxt, &cs, &ss);
 
+	if (!(efer & EFER_SCE))
+		return emulate_ud(ctxt);
+
 	ops->get_msr(ctxt, MSR_STAR, &msr_data);
 	msr_data >>= 32;
 	cs_sel = (u16)(msr_data & 0xfffc);
-- 
1.7.7.5