x86: kvm: use alternatives for VMCALL vs. VMMCALL if kernel text is read-only

On x86_64, kernel text mappings are mapped read-only with CONFIG_DEBUG_RODATA.
In that case, KVM will fail to patch VMCALL instructions to VMMCALL
as required on AMD processors.

The failure mode is currently a divide-by-zero exception, which obviously
is a KVM bug that has to be fixed.  However, picking the right instruction
between VMCALL and VMMCALL will be faster and will help if you cannot upgrade
the hypervisor.

Reported-by: Chris Webb <chris@arachsys.com>
Tested-by: Chris Webb <chris@arachsys.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index bb9b258d60e76e9c3dfc3cefe8c7f74ac80e3caf..2075e6c34c78ce9bc6ae4fcfc0f865ab34350626 100644 (file)
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -202,6 +202,7 @@
 #define X86_FEATURE_DECODEASSISTS ( 8*32+12) /* AMD Decode Assists support */
 #define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */
 #define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */
+#define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
 
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */

diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index c7678e43465bd64a3750bb912b9abc7984ac54cd..e62cf897f7819bc9795ab096a15689b3543e07b2 100644 (file)
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_KVM_PARA_H
 
 #include <asm/processor.h>
+#include <asm/alternative.h>
 #include <uapi/asm/kvm_para.h>
 
 extern void kvmclock_init(void);
@@ -16,10 +17,15 @@ static inline bool kvm_check_and_clear_guest_paused(void)
 }
 #endif /* CONFIG_KVM_GUEST */
 
-/* This instruction is vmcall.  On non-VT architectures, it will generate a
- * trap that we will then rewrite to the appropriate instruction.
+#ifdef CONFIG_DEBUG_RODATA
+#define KVM_HYPERCALL \
+        ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL)
+#else
+/* On AMD processors, vmcall will generate a trap that we will
+ * then rewrite to the appropriate instruction.
  */
 #define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
+#endif
 
 /* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall
  * instruction.  The hypervisor may replace it with something else but only the

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 60e5497681f5ecc5083f6a31c1e2067301c58bb2..813d29d00a175cccecc0d673b1f94a817addbbd7 100644 (file)
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -525,6 +525,13 @@ static void early_init_amd(struct cpuinfo_x86 *c)
        }
 #endif
 
+       /*
+        * This is only needed to tell the kernel whether to use VMCALL
+        * and VMMCALL.  VMMCALL is never executed except under virt, so
+        * we can set it unconditionally.
+        */
+       set_cpu_cap(c, X86_FEATURE_VMMCALL);
+
        /* F16h erratum 793, CVE-2013-6885 */
        if (c->x86 == 0x16 && c->x86_model <= 0xf)
                msr_set_bit(MSR_AMD64_LS_CFG, 15);