x86: xen: insn: Decode Xen and KVM emulate-prefix signature

Decode Xen and KVM's emulate-prefix signature by x86 insn decoder.
It is called "prefix" but actually not x86 instruction prefix, so
this adds insn.emulate_prefix_size field instead of reusing
insn.prefixes.

If x86 decoder finds a special sequence of instructions of
XEN_EMULATE_PREFIX and 'ud2a; .ascii "kvm"', it just counts the
length, set insn.emulate_prefix_size and fold it with the next
instruction. In other words, the signature and the next instruction
is treated as a single instruction.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: x86@kernel.org
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: xen-devel@lists.xenproject.org
Cc: Randy Dunlap <rdunlap@infradead.org>
Link: https://lkml.kernel.org/r/156777564986.25081.4964537658500952557.stgit@devnote2

arch/x86/include/asm/insn.h

@@ -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)
 {

arch/x86/lib/insn.c

@@ -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);

tools/arch/x86/include/asm/emulate_prefix.h

@@ -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

tools/arch/x86/include/asm/insn.h

@@ -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)
 {

tools/arch/x86/lib/insn.c

@@ -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);

tools/objtool/sync-check.sh

@@ -4,6 +4,7 @@
 FILES='
 arch/x86/include/asm/inat_types.h
 arch/x86/include/asm/orc_types.h
+arch/x86/include/asm/emulate_prefix.h
 arch/x86/lib/x86-opcode-map.txt
 arch/x86/tools/gen-insn-attr-x86.awk
 '
@@ -46,6 +47,6 @@ done
 check arch/x86/include/asm/inat.h     '-I "^#include [\"<]\(asm/\)*inat_types.h[\">]"'
 check arch/x86/include/asm/insn.h     '-I "^#include [\"<]\(asm/\)*inat.h[\">]"'
 check arch/x86/lib/inat.c             '-I "^#include [\"<]\(../include/\)*asm/insn.h[\">]"'
-check arch/x86/lib/insn.c             '-I "^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]"'
+check arch/x86/lib/insn.c             '-I "^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]" -I "^#include [\"<]\(../include/\)*asm/emulate_prefix.h[\">]"'
 
 cd -

tools/perf/check-headers.sh

@@ -28,6 +28,7 @@ arch/x86/include/asm/disabled-features.h
 arch/x86/include/asm/required-features.h
 arch/x86/include/asm/cpufeatures.h
 arch/x86/include/asm/inat_types.h
+arch/x86/include/asm/emulate_prefix.h
 arch/x86/include/uapi/asm/prctl.h
 arch/x86/lib/x86-opcode-map.txt
 arch/x86/tools/gen-insn-attr-x86.awk
@@ -116,7 +117,7 @@ check lib/ctype.c		      '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B
 check arch/x86/include/asm/inat.h     '-I "^#include [\"<]\(asm/\)*inat_types.h[\">]"'
 check arch/x86/include/asm/insn.h     '-I "^#include [\"<]\(asm/\)*inat.h[\">]"'
 check arch/x86/lib/inat.c	      '-I "^#include [\"<]\(../include/\)*asm/insn.h[\">]"'
-check arch/x86/lib/insn.c	      '-I "^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]"'
+check arch/x86/lib/insn.c             '-I "^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]" -I "^#include [\"<]\(../include/\)*asm/emulate_prefix.h[\">]"'
 
 # diff non-symmetric files
 check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl