x86: kprobes: Prohibit kprobes on Xen/KVM emulate prefixes

index 3ff577c0b102..1b563f9167ea 100644
@@ -7,9 +7,11 @@
 # define __ASM_FORM_RAW(x)     x
 # define __ASM_FORM_COMMA(x) x,
 #else
-# define __ASM_FORM(x)	" " #x " "
-# define __ASM_FORM_RAW(x)     #x
-# define __ASM_FORM_COMMA(x) " " #x ","
+#include <linux/stringify.h>
+
+# define __ASM_FORM(x)	" " __stringify(x) " "
+# define __ASM_FORM_RAW(x)     __stringify(x)
+# define __ASM_FORM_COMMA(x) " " __stringify(x) ","
 #endif
 
 #ifndef __x86_64__

new file mode 100644
index 000000000000..70f5b98a5286
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_EMULATE_PREFIX_H
+#define _ASM_X86_EMULATE_PREFIX_H
+
+/*
+ * Virt escape sequences to trigger instruction emulation;
+ * ideally these would decode to 'whole' instruction and not destroy
+ * the instruction stream; sadly this is not true for the 'kvm' one :/
+ */
+
+#define __XEN_EMULATE_PREFIX  0x0f,0x0b,0x78,0x65,0x6e  /* ud2 ; .ascii "xen" */
+#define __KVM_EMULATE_PREFIX  0x0f,0x0b,0x6b,0x76,0x6d	/* ud2 ; .ascii "kvm" */
+
+#endif

index 62ca03ef5c65..9139b3e86316 100644
@@ -379,12 +379,9 @@ struct xen_pmu_arch {
  * Prefix forces emulation of some non-trapping instructions.
  * Currently only CPUID.
  */
-#ifdef __ASSEMBLY__
-#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ;
-#define XEN_CPUID          XEN_EMULATE_PREFIX cpuid
-#else
-#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; "
-#define XEN_CPUID          XEN_EMULATE_PREFIX "cpuid"
-#endif
+#include <asm/emulate_prefix.h>
+
+#define XEN_EMULATE_PREFIX __ASM_FORM(.byte __XEN_EMULATE_PREFIX ;)
+#define XEN_CPUID          XEN_EMULATE_PREFIX __ASM_FORM(cpuid)
 
 #endif /* _ASM_X86_XEN_INTERFACE_H */

index 290c3c3efb87..5f8b0a60f48b 100644
@@ -68,6 +68,7 @@
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/intel_pt.h>
+#include <asm/emulate_prefix.h>
 #include <clocksource/hyperv_timer.h>
 
 #define CREATE_TRACE_POINTS

@@ -5319,6 +5320,7 @@ EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system);
 
 int handle_ud(struct kvm_vcpu *vcpu)
 {
+	static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX };
 	int emul_type = EMULTYPE_TRAP_UD;
 	enum emulation_result er;
 	char sig[5]; /* ud2; .ascii "kvm" */

@@ -5327,7 +5329,7 @@ int handle_ud(struct kvm_vcpu *vcpu)
 	if (force_emulation_prefix &&
 	    kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu),
 				sig, sizeof(sig), &e) == 0 &&
-	    memcmp(sig, "\xf\xbkvm", sizeof(sig)) == 0) {
+	    memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) {
 		kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig));
 		emul_type = 0;
 	}

index 154f27be8bfc..5c1ae3eff9d4 100644
@@ -45,6 +45,7 @@ struct insn {
 		struct insn_field immediate2;	/* for 64bit imm or seg16 */
 	};
 
+	int	emulate_prefix_size;
 	insn_attr_t attr;
 	unsigned char opnd_bytes;
 	unsigned char addr_bytes;

@@ -128,6 +129,11 @@ static inline int insn_is_evex(struct insn *insn)
 	return (insn->vex_prefix.nbytes == 4);
 }
 
+static inline int insn_has_emulate_prefix(struct insn *insn)
+{
+	return !!insn->emulate_prefix_size;
+}
+
 /* Ensure this instruction is decoded completely */
 static inline int insn_complete(struct insn *insn)
 {

index 0b5862ba6a75..404279563891 100644
@@ -13,6 +13,8 @@
 #include <asm/inat.h>
 #include <asm/insn.h>
 
+#include <asm/emulate_prefix.h>
+
 /* Verify next sizeof(t) bytes can be on the same instruction */
 #define validate_next(t, insn, n)	\
 	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)

@@ -58,6 +60,36 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
 		insn->addr_bytes = 4;
 }
 
+static const insn_byte_t xen_prefix[] = { __XEN_EMULATE_PREFIX };
+static const insn_byte_t kvm_prefix[] = { __KVM_EMULATE_PREFIX };
+
+static int __insn_get_emulate_prefix(struct insn *insn,
+				     const insn_byte_t *prefix, size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++) {
+		if (peek_nbyte_next(insn_byte_t, insn, i) != prefix[i])
+			goto err_out;
+	}
+
+	insn->emulate_prefix_size = len;
+	insn->next_byte += len;
+
+	return 1;
+
+err_out:
+	return 0;
+}
+
+static void insn_get_emulate_prefix(struct insn *insn)
+{
+	if (__insn_get_emulate_prefix(insn, xen_prefix, sizeof(xen_prefix)))
+		return;
+
+	__insn_get_emulate_prefix(insn, kvm_prefix, sizeof(kvm_prefix));
+}
+
 /**
  * insn_get_prefixes - scan x86 instruction prefix bytes
  * @insn:	&struct insn containing instruction

@@ -76,6 +108,8 @@ void insn_get_prefixes(struct insn *insn)
 	if (prefixes->got)
 		return;
 
+	insn_get_emulate_prefix(insn);
+
 	nb = 0;
 	lb = 0;
 	b = peek_next(insn_byte_t, insn);

new file mode 100644
index 000000000000..70f5b98a5286
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_EMULATE_PREFIX_H
+#define _ASM_X86_EMULATE_PREFIX_H
+
+/*
+ * Virt escape sequences to trigger instruction emulation;
+ * ideally these would decode to 'whole' instruction and not destroy
+ * the instruction stream; sadly this is not true for the 'kvm' one :/
+ */
+
+#define __XEN_EMULATE_PREFIX  0x0f,0x0b,0x78,0x65,0x6e  /* ud2 ; .ascii "xen" */
+#define __KVM_EMULATE_PREFIX  0x0f,0x0b,0x6b,0x76,0x6d	/* ud2 ; .ascii "kvm" */
+
+#endif

index 37a4c390750b..568854b14d0a 100644
@@ -45,6 +45,7 @@ struct insn {
 		struct insn_field immediate2;	/* for 64bit imm or seg16 */
 	};
 
+	int	emulate_prefix_size;
 	insn_attr_t attr;
 	unsigned char opnd_bytes;
 	unsigned char addr_bytes;

@@ -128,6 +129,11 @@ static inline int insn_is_evex(struct insn *insn)
 	return (insn->vex_prefix.nbytes == 4);
 }
 
+static inline int insn_has_emulate_prefix(struct insn *insn)
+{
+	return !!insn->emulate_prefix_size;
+}
+
 /* Ensure this instruction is decoded completely */
 static inline int insn_complete(struct insn *insn)
 {

index 79e048f1d902..0151dfc6da61 100644
@@ -13,6 +13,8 @@
 #include "../include/asm/inat.h"
 #include "../include/asm/insn.h"
 
+#include "../include/asm/emulate_prefix.h"
+
 /* Verify next sizeof(t) bytes can be on the same instruction */
 #define validate_next(t, insn, n)	\
 	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)

@@ -58,6 +60,36 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
 		insn->addr_bytes = 4;
 }
 
+static const insn_byte_t xen_prefix[] = { __XEN_EMULATE_PREFIX };
+static const insn_byte_t kvm_prefix[] = { __KVM_EMULATE_PREFIX };
+
+static int __insn_get_emulate_prefix(struct insn *insn,
+				     const insn_byte_t *prefix, size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++) {
+		if (peek_nbyte_next(insn_byte_t, insn, i) != prefix[i])
+			goto err_out;
+	}
+
+	insn->emulate_prefix_size = len;
+	insn->next_byte += len;
+
+	return 1;
+
+err_out:
+	return 0;
+}
+
+static void insn_get_emulate_prefix(struct insn *insn)
+{
+	if (__insn_get_emulate_prefix(insn, xen_prefix, sizeof(xen_prefix)))
+		return;
+
+	__insn_get_emulate_prefix(insn, kvm_prefix, sizeof(kvm_prefix));
+}
+
 /**
  * insn_get_prefixes - scan x86 instruction prefix bytes
  * @insn:	&struct insn containing instruction

@@ -76,6 +108,8 @@ void insn_get_prefixes(struct insn *insn)
 	if (prefixes->got)
 		return;
 
+	insn_get_emulate_prefix(insn);
+
 	nb = 0;
 	lb = 0;
 	b = peek_next(insn_byte_t, insn);

index 43fc13c831af..4f13af7cbcdb 100644
@@ -351,6 +351,10 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 	kernel_insn_init(insn, dest, MAX_INSN_SIZE);
 	insn_get_length(insn);
 
+	/* We can not probe force emulate prefixed instruction */
+	if (insn_has_emulate_prefix(insn))
+		return 0;
+
 	/* Another subsystem puts a breakpoint, failed to recover */
 	if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
 		return 0;