1 files changed, 240 insertions, 112 deletions

diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index 0151dfc6da61..8fd63a067308 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -5,25 +5,43 @@
  * Copyright (C) IBM Corporation, 2002, 2004, 2009
  */
 
+#include <linux/kernel.h>
 #ifdef __KERNEL__
 #include <linux/string.h>
 #else
 #include <string.h>
 #endif
-#include "../include/asm/inat.h"
-#include "../include/asm/insn.h"
-
-#include "../include/asm/emulate_prefix.h"
+#include "../include/asm/inat.h" /* __ignore_sync_check__ */
+#include "../include/asm/insn.h" /* __ignore_sync_check__ */
+#include "../include/asm-generic/unaligned.h" /* __ignore_sync_check__ */
+
+#include <linux/errno.h>
+#include <linux/kconfig.h>
+
+#include "../include/asm/emulate_prefix.h" /* __ignore_sync_check__ */
+
+#define leXX_to_cpu(t, r)						\
+({									\
+	__typeof__(t) v;						\
+	switch (sizeof(t)) {						\
+	case 4: v = le32_to_cpu(r); break;				\
+	case 2: v = le16_to_cpu(r); break;				\
+	case 1:	v = r; break;						\
+	default:							\
+		BUILD_BUG(); break;					\
+	}								\
+	v;								\
+})
 
 /* 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)
 
 #define __get_next(t, insn)	\
-	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
+	({ t r = get_unaligned((t *)(insn)->next_byte); (insn)->next_byte += sizeof(t); leXX_to_cpu(t, r); })
 
 #define __peek_nbyte_next(t, insn, n)	\
-	({ t r = *(t*)((insn)->next_byte + n); r; })
+	({ t r = get_unaligned((t *)(insn)->next_byte + n); leXX_to_cpu(t, r); })
 
 #define get_next(t, insn)	\
 	({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
@@ -37,6 +55,7 @@
  * insn_init() - initialize struct insn
  * @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
  * @x86_64:	!0 for 64-bit kernel or 64-bit app
  */
 void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
@@ -97,8 +116,12 @@ 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;
@@ -106,7 +129,7 @@ void insn_get_prefixes(struct insn *insn)
 	int i, nb;
 
 	if (prefixes->got)
-		return;
+		return 0;
 
 	insn_get_emulate_prefix(insn);
 
@@ -147,9 +170,9 @@ found:
 			b = insn->prefixes.bytes[3];
 			for (i = 0; i < nb; i++)
 				if (prefixes->bytes[i] == lb)
-					prefixes->bytes[i] = b;
+					insn_set_byte(prefixes, i, b);
 		}
-		insn->prefixes.bytes[3] = lb;
+		insn_set_byte(&insn->prefixes, 3, lb);
 	}
 
 	/* Decode REX prefix */
@@ -157,8 +180,7 @@ found:
 		b = peek_next(insn_byte_t, insn);
 		attr = inat_get_opcode_attribute(b);
 		if (inat_is_rex_prefix(attr)) {
-			insn->rex_prefix.value = b;
-			insn->rex_prefix.nbytes = 1;
+			insn_field_set(&insn->rex_prefix, b, 1);
 			insn->next_byte++;
 			if (X86_REX_W(b))
 				/* REX.W overrides opnd_size */
@@ -181,13 +203,13 @@ found:
 			if (X86_MODRM_MOD(b2) != 3)
 				goto vex_end;
 		}
-		insn->vex_prefix.bytes[0] = b;
-		insn->vex_prefix.bytes[1] = b2;
+		insn_set_byte(&insn->vex_prefix, 0, b);
+		insn_set_byte(&insn->vex_prefix, 1, b2);
 		if (inat_is_evex_prefix(attr)) {
 			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
-			insn->vex_prefix.bytes[2] = b2;
+			insn_set_byte(&insn->vex_prefix, 2, b2);
 			b2 = peek_nbyte_next(insn_byte_t, insn, 3);
-			insn->vex_prefix.bytes[3] = b2;
+			insn_set_byte(&insn->vex_prefix, 3, b2);
 			insn->vex_prefix.nbytes = 4;
 			insn->next_byte += 4;
 			if (insn->x86_64 && X86_VEX_W(b2))
@@ -195,7 +217,7 @@ found:
 				insn->opnd_bytes = 8;
 		} else if (inat_is_vex3_prefix(attr)) {
 			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
-			insn->vex_prefix.bytes[2] = b2;
+			insn_set_byte(&insn->vex_prefix, 2, b2);
 			insn->vex_prefix.nbytes = 3;
 			insn->next_byte += 3;
 			if (insn->x86_64 && X86_VEX_W(b2))
@@ -207,7 +229,7 @@ found:
 			 * Makes it easier to decode vex.W, vex.vvvv,
 			 * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0.
 			 */
-			insn->vex_prefix.bytes[2] = b2 & 0x7f;
+			insn_set_byte(&insn->vex_prefix, 2, b2 & 0x7f);
 			insn->vex_prefix.nbytes = 2;
 			insn->next_byte += 2;
 		}
@@ -217,8 +239,10 @@ vex_end:
 
 	prefixes->got = 1;
 
+	return 0;
+
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /**
@@ -230,20 +254,29 @@ 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);
-	opcode->bytes[0] = op;
+	insn_set_byte(opcode, 0, op);
 	opcode->nbytes = 1;
 
 	/* Check if there is VEX prefix or not */
@@ -254,9 +287,13 @@ 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);
@@ -267,13 +304,18 @@ 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;
 }
 
 /**
@@ -283,35 +325,49 @@ 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);
-		modrm->value = mod;
-		modrm->nbytes = 1;
+		insn_field_set(modrm, mod, 1);
 		if (inat_is_group(insn->attr)) {
 			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;
 }
 
 
@@ -325,16 +381,21 @@ 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.
 	 */
-	return (modrm->nbytes && (modrm->value & 0xc7) == 0x5);
+	return (modrm->nbytes && (modrm->bytes[0] & 0xc7) == 0x5);
 }
 
 /**
@@ -343,27 +404,39 @@ 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_byte_t)insn->modrm.value;
+		modrm = insn->modrm.bytes[0];
 		if (insn->addr_bytes != 2 &&
 		    X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) {
-			insn->sib.value = get_next(insn_byte_t, insn);
-			insn->sib.nbytes = 1;
+			insn_field_set(&insn->sib,
+				       get_next(insn_byte_t, insn), 1);
 		}
 	}
 	insn->sib.got = 1;
 
+	return 0;
+
 err_out:
-	return;
+	return -ENODATA;
 }
 
 
@@ -374,15 +447,25 @@ 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:
@@ -407,27 +490,27 @@ void insn_get_displacement(struct insn *insn)
 		if (mod == 3)
 			goto out;
 		if (mod == 1) {
-			insn->displacement.value = get_next(signed char, insn);
-			insn->displacement.nbytes = 1;
+			insn_field_set(&insn->displacement,
+				       get_next(signed char, insn), 1);
 		} else if (insn->addr_bytes == 2) {
 			if ((mod == 0 && rm == 6) || mod == 2) {
-				insn->displacement.value =
-					 get_next(short, insn);
-				insn->displacement.nbytes = 2;
+				insn_field_set(&insn->displacement,
+					       get_next(short, insn), 2);
 			}
 		} else {
 			if ((mod == 0 && rm == 5) || mod == 2 ||
 			    (mod == 0 && base == 5)) {
-				insn->displacement.value = get_next(int, insn);
-				insn->displacement.nbytes = 4;
+				insn_field_set(&insn->displacement,
+					       get_next(int, insn), 4);
 			}
 		}
 	}
 out:
 	insn->displacement.got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /* Decode moffset16/32/64. Return 0 if failed */
@@ -435,18 +518,14 @@ static int __get_moffset(struct insn *insn)
 {
 	switch (insn->addr_bytes) {
 	case 2:
-		insn->moffset1.value = get_next(short, insn);
-		insn->moffset1.nbytes = 2;
+		insn_field_set(&insn->moffset1, get_next(short, insn), 2);
 		break;
 	case 4:
-		insn->moffset1.value = get_next(int, insn);
-		insn->moffset1.nbytes = 4;
+		insn_field_set(&insn->moffset1, get_next(int, insn), 4);
 		break;
 	case 8:
-		insn->moffset1.value = get_next(int, insn);
-		insn->moffset1.nbytes = 4;
-		insn->moffset2.value = get_next(int, insn);
-		insn->moffset2.nbytes = 4;
+		insn_field_set(&insn->moffset1, get_next(int, insn), 4);
+		insn_field_set(&insn->moffset2, get_next(int, insn), 4);
 		break;
 	default:	/* opnd_bytes must be modified manually */
 		goto err_out;
@@ -464,13 +543,11 @@ static int __get_immv32(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
-		insn->immediate.value = get_next(short, insn);
-		insn->immediate.nbytes = 2;
+		insn_field_set(&insn->immediate, get_next(short, insn), 2);
 		break;
 	case 4:
 	case 8:
-		insn->immediate.value = get_next(int, insn);
-		insn->immediate.nbytes = 4;
+		insn_field_set(&insn->immediate, get_next(int, insn), 4);
 		break;
 	default:	/* opnd_bytes must be modified manually */
 		goto err_out;
@@ -487,18 +564,15 @@ static int __get_immv(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
-		insn->immediate1.value = get_next(short, insn);
-		insn->immediate1.nbytes = 2;
+		insn_field_set(&insn->immediate1, get_next(short, insn), 2);
 		break;
 	case 4:
-		insn->immediate1.value = get_next(int, insn);
+		insn_field_set(&insn->immediate1, get_next(int, insn), 4);
 		insn->immediate1.nbytes = 4;
 		break;
 	case 8:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		insn->immediate2.value = get_next(int, insn);
-		insn->immediate2.nbytes = 4;
+		insn_field_set(&insn->immediate1, get_next(int, insn), 4);
+		insn_field_set(&insn->immediate2, get_next(int, insn), 4);
 		break;
 	default:	/* opnd_bytes must be modified manually */
 		goto err_out;
@@ -515,12 +589,10 @@ static int __get_immptr(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
-		insn->immediate1.value = get_next(short, insn);
-		insn->immediate1.nbytes = 2;
+		insn_field_set(&insn->immediate1, get_next(short, insn), 2);
 		break;
 	case 4:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
+		insn_field_set(&insn->immediate1, get_next(int, insn), 4);
 		break;
 	case 8:
 		/* ptr16:64 is not exist (no segment) */
@@ -528,8 +600,7 @@ static int __get_immptr(struct insn *insn)
 	default:	/* opnd_bytes must be modified manually */
 		goto err_out;
 	}
-	insn->immediate2.value = get_next(unsigned short, insn);
-	insn->immediate2.nbytes = 2;
+	insn_field_set(&insn->immediate2, get_next(unsigned short, insn), 2);
 	insn->immediate1.got = insn->immediate2.got = 1;
 
 	return 1;
@@ -538,20 +609,30 @@ 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))
@@ -565,22 +646,17 @@ void insn_get_immediate(struct insn *insn)
 
 	switch (inat_immediate_size(insn->attr)) {
 	case INAT_IMM_BYTE:
-		insn->immediate.value = get_next(signed char, insn);
-		insn->immediate.nbytes = 1;
+		insn_field_set(&insn->immediate, get_next(signed char, insn), 1);
 		break;
 	case INAT_IMM_WORD:
-		insn->immediate.value = get_next(short, insn);
-		insn->immediate.nbytes = 2;
+		insn_field_set(&insn->immediate, get_next(short, insn), 2);
 		break;
 	case INAT_IMM_DWORD:
-		insn->immediate.value = get_next(int, insn);
-		insn->immediate.nbytes = 4;
+		insn_field_set(&insn->immediate, get_next(int, insn), 4);
 		break;
 	case INAT_IMM_QWORD:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		insn->immediate2.value = get_next(int, insn);
-		insn->immediate2.nbytes = 4;
+		insn_field_set(&insn->immediate1, get_next(int, insn), 4);
+		insn_field_set(&insn->immediate2, get_next(int, insn), 4);
 		break;
 	case INAT_IMM_PTR:
 		if (!__get_immptr(insn))
@@ -599,14 +675,14 @@ void insn_get_immediate(struct insn *insn)
 		goto err_out;
 	}
 	if (inat_has_second_immediate(insn->attr)) {
-		insn->immediate2.value = get_next(signed char, insn);
-		insn->immediate2.nbytes = 1;
+		insn_field_set(&insn->immediate2, get_next(signed char, insn), 1);
 	}
 done:
 	insn->immediate.got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /**
@@ -615,13 +691,65 @@ 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;
+}
+
+/* Ensure this instruction is decoded completely */
+static inline int insn_complete(struct insn *insn)
+{
+	return insn->opcode.got && insn->modrm.got && insn->sib.got &&
+		insn->displacement.got && insn->immediate.got;
+}
+
+/**
+ * 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;
 }