x86/insn: Add an insn_decode() API

Users of the instruction decoder should use this to decode instruction
bytes. For that, have insn*() helpers return an int value to denote
success/failure. When there's an error fetching the next insn byte and
the insn falls short, return -ENODATA to denote that.

While at it, make insn_get_opcode() more stricter as to whether what has
seen so far is a valid insn and if not.

Copy linux/kconfig.h for the tools-version of the decoder so that it can
use IS_ENABLED().

Also, cast the INSN_MODE_KERN dummy define value to (enum insn_mode)
for tools use of the decoder because perf tool builds with -Werror and
errors out with -Werror=sign-compare otherwise.

Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lkml.kernel.org/r/20210304174237.31945-5-bp@alien8.de

2 files changed, 191 insertions, 55 deletions

diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index 7e1239aa7dd9..2fe19b1a8765 100644
--- a/tools/arch/x86/include/asm/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
@@ -132,13 +132,23 @@ struct insn {
 #define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
 
 extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
-extern void insn_get_prefixes(struct insn *insn);
-extern void insn_get_opcode(struct insn *insn);
-extern void insn_get_modrm(struct insn *insn);
-extern void insn_get_sib(struct insn *insn);
-extern void insn_get_displacement(struct insn *insn);
-extern void insn_get_immediate(struct insn *insn);
-extern void insn_get_length(struct insn *insn);
+extern int insn_get_prefixes(struct insn *insn);
+extern int insn_get_opcode(struct insn *insn);
+extern int insn_get_modrm(struct insn *insn);
+extern int insn_get_sib(struct insn *insn);
+extern int insn_get_displacement(struct insn *insn);
+extern int insn_get_immediate(struct insn *insn);
+extern int insn_get_length(struct insn *insn);
+
+enum insn_mode {
+	INSN_MODE_32,
+	INSN_MODE_64,
+	/* Mode is determined by the current kernel build. */
+	INSN_MODE_KERN,
+	INSN_NUM_MODES,
+};
+
+extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m);
 
 /* Attribute will be determined after getting ModRM (for opcode groups) */
 static inline void insn_get_attribute(struct insn *insn)
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index 1174c43b3944..be2b057f91d4 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -11,10 +11,13 @@
 #else
 #include <string.h>
 #endif
-#include "../include/asm/inat.h" /* __ignore_sync_check__ */
-#include "../include/asm/insn.h" /* __ignore_sync_check__ */
+#include <asm/inat.h> /*__ignore_sync_check__ */
+#include <asm/insn.h> /* __ignore_sync_check__ */
 
-#include "../include/asm/emulate_prefix.h" /* __ignore_sync_check__ */
+#include <linux/errno.h>
+#include <linux/kconfig.h>
+
+#include <asm/emulate_prefix.h> /* __ignore_sync_check__ */
 
 #define leXX_to_cpu(t, r)						\
 ({									\
@@ -112,8 +115,12 @@ static void insn_get_emulate_prefix(struct insn *insn)
  * Populates the @insn->prefixes bitmap, and updates @insn->next_byte
  * to point to the (first) opcode.  No effect if @insn->prefixes.got
  * is already set.
+ *
+ * * Returns:
+ * 0:  on success
+ * < 0: on error
  */
-void insn_get_prefixes(struct insn *insn)
+int insn_get_prefixes(struct insn *insn)
 {
 	struct insn_field *prefixes = &insn->prefixes;
 	insn_attr_t attr;
@@ -121,7 +128,7 @@ void insn_get_prefixes(struct insn *insn)
 	int i, nb;
 
 	if (prefixes->got)
-		return;
+		return 0;
 
 	insn_get_emulate_prefix(insn);
 
@@ -231,8 +238,10 @@ vex_end:
 
 	prefixes->got = 1;
 
+	return 0;
+
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /**
@@ -244,16 +253,25 @@ err_out:
  * If necessary, first collects any preceding (prefix) bytes.
  * Sets @insn->opcode.value = opcode1.  No effect if @insn->opcode.got
  * is already 1.
+ *
+ * Returns:
+ * 0:  on success
+ * < 0: on error
  */
-void insn_get_opcode(struct insn *insn)
+int insn_get_opcode(struct insn *insn)
 {
 	struct insn_field *opcode = &insn->opcode;
+	int pfx_id, ret;
 	insn_byte_t op;
-	int pfx_id;
+
 	if (opcode->got)
-		return;
-	if (!insn->prefixes.got)
-		insn_get_prefixes(insn);
+		return 0;
+
+	if (!insn->prefixes.got) {
+		ret = insn_get_prefixes(insn);
+		if (ret)
+			return ret;
+	}
 
 	/* Get first opcode */
 	op = get_next(insn_byte_t, insn);
@@ -268,9 +286,13 @@ void insn_get_opcode(struct insn *insn)
 		insn->attr = inat_get_avx_attribute(op, m, p);
 		if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
 		    (!inat_accept_vex(insn->attr) &&
-		     !inat_is_group(insn->attr)))
-			insn->attr = 0;	/* This instruction is bad */
-		goto end;	/* VEX has only 1 byte for opcode */
+		     !inat_is_group(insn->attr))) {
+			/* This instruction is bad */
+			insn->attr = 0;
+			return -EINVAL;
+		}
+		/* VEX has only 1 byte for opcode */
+		goto end;
 	}
 
 	insn->attr = inat_get_opcode_attribute(op);
@@ -281,13 +303,18 @@ void insn_get_opcode(struct insn *insn)
 		pfx_id = insn_last_prefix_id(insn);
 		insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
 	}
-	if (inat_must_vex(insn->attr))
-		insn->attr = 0;	/* This instruction is bad */
+
+	if (inat_must_vex(insn->attr)) {
+		/* This instruction is bad */
+		insn->attr = 0;
+		return -EINVAL;
+	}
 end:
 	opcode->got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /**
@@ -297,15 +324,25 @@ err_out:
  * Populates @insn->modrm and updates @insn->next_byte to point past the
  * ModRM byte, if any.  If necessary, first collects the preceding bytes
  * (prefixes and opcode(s)).  No effect if @insn->modrm.got is already 1.
+ *
+ * Returns:
+ * 0:  on success
+ * < 0: on error
  */
-void insn_get_modrm(struct insn *insn)
+int insn_get_modrm(struct insn *insn)
 {
 	struct insn_field *modrm = &insn->modrm;
 	insn_byte_t pfx_id, mod;
+	int ret;
+
 	if (modrm->got)
-		return;
-	if (!insn->opcode.got)
-		insn_get_opcode(insn);
+		return 0;
+
+	if (!insn->opcode.got) {
+		ret = insn_get_opcode(insn);
+		if (ret)
+			return ret;
+	}
 
 	if (inat_has_modrm(insn->attr)) {
 		mod = get_next(insn_byte_t, insn);
@@ -314,17 +351,22 @@ void insn_get_modrm(struct insn *insn)
 			pfx_id = insn_last_prefix_id(insn);
 			insn->attr = inat_get_group_attribute(mod, pfx_id,
 							      insn->attr);
-			if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
-				insn->attr = 0;	/* This is bad */
+			if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) {
+				/* Bad insn */
+				insn->attr = 0;
+				return -EINVAL;
+			}
 		}
 	}
 
 	if (insn->x86_64 && inat_is_force64(insn->attr))
 		insn->opnd_bytes = 8;
+
 	modrm->got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 
@@ -338,11 +380,16 @@ err_out:
 int insn_rip_relative(struct insn *insn)
 {
 	struct insn_field *modrm = &insn->modrm;
+	int ret;
 
 	if (!insn->x86_64)
 		return 0;
-	if (!modrm->got)
-		insn_get_modrm(insn);
+
+	if (!modrm->got) {
+		ret = insn_get_modrm(insn);
+		if (ret)
+			return 0;
+	}
 	/*
 	 * For rip-relative instructions, the mod field (top 2 bits)
 	 * is zero and the r/m field (bottom 3 bits) is 0x5.
@@ -356,15 +403,25 @@ int insn_rip_relative(struct insn *insn)
  *
  * If necessary, first collects the instruction up to and including the
  * ModRM byte.
+ *
+ * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
  */
-void insn_get_sib(struct insn *insn)
+int insn_get_sib(struct insn *insn)
 {
 	insn_byte_t modrm;
+	int ret;
 
 	if (insn->sib.got)
-		return;
-	if (!insn->modrm.got)
-		insn_get_modrm(insn);
+		return 0;
+
+	if (!insn->modrm.got) {
+		ret = insn_get_modrm(insn);
+		if (ret)
+			return ret;
+	}
+
 	if (insn->modrm.nbytes) {
 		modrm = insn->modrm.bytes[0];
 		if (insn->addr_bytes != 2 &&
@@ -375,8 +432,10 @@ void insn_get_sib(struct insn *insn)
 	}
 	insn->sib.got = 1;
 
+	return 0;
+
 err_out:
-	return;
+	return -ENODATA;
 }
 
 
@@ -387,15 +446,25 @@ err_out:
  * If necessary, first collects the instruction up to and including the
  * SIB byte.
  * Displacement value is sign-expanded.
+ *
+ * * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
  */
-void insn_get_displacement(struct insn *insn)
+int insn_get_displacement(struct insn *insn)
 {
 	insn_byte_t mod, rm, base;
+	int ret;
 
 	if (insn->displacement.got)
-		return;
-	if (!insn->sib.got)
-		insn_get_sib(insn);
+		return 0;
+
+	if (!insn->sib.got) {
+		ret = insn_get_sib(insn);
+		if (ret)
+			return ret;
+	}
+
 	if (insn->modrm.nbytes) {
 		/*
 		 * Interpreting the modrm byte:
@@ -437,9 +506,10 @@ void insn_get_displacement(struct insn *insn)
 	}
 out:
 	insn->displacement.got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /* Decode moffset16/32/64. Return 0 if failed */
@@ -538,20 +608,30 @@ err_out:
 }
 
 /**
- * insn_get_immediate() - Get the immediates of instruction
+ * insn_get_immediate() - Get the immediate in an instruction
  * @insn:	&struct insn containing instruction
  *
  * If necessary, first collects the instruction up to and including the
  * displacement bytes.
  * Basically, most of immediates are sign-expanded. Unsigned-value can be
- * get by bit masking with ((1 << (nbytes * 8)) - 1)
+ * computed by bit masking with ((1 << (nbytes * 8)) - 1)
+ *
+ * Returns:
+ * 0:  on success
+ * < 0: on error
  */
-void insn_get_immediate(struct insn *insn)
+int insn_get_immediate(struct insn *insn)
 {
+	int ret;
+
 	if (insn->immediate.got)
-		return;
-	if (!insn->displacement.got)
-		insn_get_displacement(insn);
+		return 0;
+
+	if (!insn->displacement.got) {
+		ret = insn_get_displacement(insn);
+		if (ret)
+			return ret;
+	}
 
 	if (inat_has_moffset(insn->attr)) {
 		if (!__get_moffset(insn))
@@ -598,9 +678,10 @@ void insn_get_immediate(struct insn *insn)
 	}
 done:
 	insn->immediate.got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /**
@@ -609,13 +690,58 @@ err_out:
  *
  * If necessary, first collects the instruction up to and including the
  * immediates bytes.
- */
-void insn_get_length(struct insn *insn)
+ *
+ * Returns:
+ *  - 0 on success
+ *  - < 0 on error
+*/
+int insn_get_length(struct insn *insn)
 {
+	int ret;
+
 	if (insn->length)
-		return;
-	if (!insn->immediate.got)
-		insn_get_immediate(insn);
+		return 0;
+
+	if (!insn->immediate.got) {
+		ret = insn_get_immediate(insn);
+		if (ret)
+			return ret;
+	}
+
 	insn->length = (unsigned char)((unsigned long)insn->next_byte
 				     - (unsigned long)insn->kaddr);
+
+	return 0;
+}
+
+/**
+ * insn_decode() - Decode an x86 instruction
+ * @insn:	&struct insn to be initialized
+ * @kaddr:	address (in kernel memory) of instruction (or copy thereof)
+ * @buf_len:	length of the insn buffer at @kaddr
+ * @m:		insn mode, see enum insn_mode
+ *
+ * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
+ */
+int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m)
+{
+	int ret;
+
+#define INSN_MODE_KERN (enum insn_mode)-1 /* __ignore_sync_check__ mode is only valid in the kernel */
+
+	if (m == INSN_MODE_KERN)
+		insn_init(insn, kaddr, buf_len, IS_ENABLED(CONFIG_X86_64));
+	else
+		insn_init(insn, kaddr, buf_len, m == INSN_MODE_64);
+
+	ret = insn_get_length(insn);
+	if (ret)
+		return ret;
+
+	if (insn_complete(insn))
+		return 0;
+
+	return -EINVAL;
 }