objtool warning fixes

index 17fa7fc..8d1296a 100644
@@ -107,6 +107,12 @@ static struct instruction *next_insn_same_sec(struct objtool_file *file,
 		insn->offset < func->offset + func->len;		\
 	     insn = list_next_entry(insn, list))
 
+#define func_for_each_insn_continue_reverse(file, func, insn)		\
+	for (insn = list_prev_entry(insn, list);			\
+	     &insn->list != &file->insn_list &&				\
+		insn->sec == func->sec && insn->offset >= func->offset;	\
+	     insn = list_prev_entry(insn, list))
+
 #define sec_for_each_insn_from(file, insn)				\
 	for (; insn; insn = next_insn_same_sec(file, insn))
 

@@ -664,65 +670,95 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func,
 	return 0;
 }
 
-static int add_func_switch_tables(struct objtool_file *file,
-				  struct symbol *func)
+/*
+ * find_switch_table() - Given a dynamic jump, find the switch jump table in
+ * .rodata associated with it.
+ *
+ * There are 3 basic patterns:
+ *
+ * 1. jmpq *[rodata addr](,%reg,8)
+ *
+ *    This is the most common case by far.  It jumps to an address in a simple
+ *    jump table which is stored in .rodata.
+ *
+ * 2. jmpq *[rodata addr](%rip)
+ *
+ *    This is caused by a rare gcc quirk, currently only seen in three driver
+ *    functions in the kernel, only with certain obscure non-distro configs.
+ *
+ *    As part of an optimization, gcc makes a copy of an existing switch jump
+ *    table, modifies it, and then hard-codes the jump (albeit with an indirect
+ *    jump) to use a single entry in the table.  The rest of the jump table and
+ *    some of its jump targets remain as dead code.
+ *
+ *    In such a case we can just crudely ignore all unreachable instruction
+ *    warnings for the entire object file.  Ideally we would just ignore them
+ *    for the function, but that would require redesigning the code quite a
+ *    bit.  And honestly that's just not worth doing: unreachable instruction
+ *    warnings are of questionable value anyway, and this is such a rare issue.
+ *
+ * 3. mov [rodata addr],%reg1
+ *    ... some instructions ...
+ *    jmpq *(%reg1,%reg2,8)
+ *
+ *    This is a fairly uncommon pattern which is new for gcc 6.  As of this
+ *    writing, there are 11 occurrences of it in the allmodconfig kernel.
+ *
+ *    TODO: Once we have DWARF CFI and smarter instruction decoding logic,
+ *    ensure the same register is used in the mov and jump instructions.
+ */
+static struct rela *find_switch_table(struct objtool_file *file,
+				      struct symbol *func,
+				      struct instruction *insn)
 {
-	struct instruction *insn, *prev_jump;
-	struct rela *text_rela, *rodata_rela, *prev_rela = NULL;
-	int ret;
+	struct rela *text_rela, *rodata_rela;
 
-	prev_jump = NULL;
+	text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len);
+	if (text_rela && text_rela->sym == file->rodata->sym) {
+		/* case 1 */
+		rodata_rela = find_rela_by_dest(file->rodata,
+						text_rela->addend);
+		if (rodata_rela)
+			return rodata_rela;
 
-	func_for_each_insn(file, func, insn) {
-		if (insn->type != INSN_JUMP_DYNAMIC)
-			continue;
+		/* case 2 */
+		rodata_rela = find_rela_by_dest(file->rodata,
+						text_rela->addend + 4);
+		if (!rodata_rela)
+			return NULL;
+		file->ignore_unreachables = true;
+		return rodata_rela;
+	}
+
+	/* case 3 */
+	func_for_each_insn_continue_reverse(file, func, insn) {
+		if (insn->type == INSN_JUMP_UNCONDITIONAL ||
+		    insn->type == INSN_JUMP_DYNAMIC)
+			break;
 
 		text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
 						    insn->len);
-		if (!text_rela || text_rela->sym != file->rodata->sym)
-			continue;
+		if (text_rela && text_rela->sym == file->rodata->sym)
+			return find_rela_by_dest(file->rodata,
+						 text_rela->addend);
+	}
 
-		/* common case: jmpq *[addr](,%rax,8) */
-		rodata_rela = find_rela_by_dest(file->rodata,
-						text_rela->addend);
+	return NULL;
+}
 
-		/*
-		 * rare case:   jmpq *[addr](%rip)
-		 *
-		 * This check is for a rare gcc quirk, currently only seen in
-		 * three driver functions in the kernel, only with certain
-		 * obscure non-distro configs.
-		 *
-		 * As part of an optimization, gcc makes a copy of an existing
-		 * switch jump table, modifies it, and then hard-codes the jump
-		 * (albeit with an indirect jump) to use a single entry in the
-		 * table.  The rest of the jump table and some of its jump
-		 * targets remain as dead code.
-		 *
-		 * In such a case we can just crudely ignore all unreachable
-		 * instruction warnings for the entire object file.  Ideally we
-		 * would just ignore them for the function, but that would
-		 * require redesigning the code quite a bit.  And honestly
-		 * that's just not worth doing: unreachable instruction
-		 * warnings are of questionable value anyway, and this is such
-		 * a rare issue.
-		 *
-		 * kbuild reports:
-		 * - https://lkml.kernel.org/r/201603231906.LWcVUpxm%[email protected]
-		 * - https://lkml.kernel.org/r/201603271114.K9i45biy%[email protected]
-		 * - https://lkml.kernel.org/r/201603291058.zuJ6ben1%[email protected]
-		 *
-		 * gcc bug:
-		 * - https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70604
-		 */
-		if (!rodata_rela) {
-			rodata_rela = find_rela_by_dest(file->rodata,
-							text_rela->addend + 4);
-			if (rodata_rela)
-				file->ignore_unreachables = true;
-		}
+static int add_func_switch_tables(struct objtool_file *file,
+				  struct symbol *func)
+{
+	struct instruction *insn, *prev_jump = NULL;
+	struct rela *rela, *prev_rela = NULL;
+	int ret;
 
-		if (!rodata_rela)
+	func_for_each_insn(file, func, insn) {
+		if (insn->type != INSN_JUMP_DYNAMIC)
+			continue;
+
+		rela = find_switch_table(file, func, insn);
+		if (!rela)
 			continue;
 
 		/*

@@ -732,13 +768,13 @@ static int add_func_switch_tables(struct objtool_file *file,
 		 */
 		if (prev_jump) {
 			ret = add_switch_table(file, func, prev_jump, prev_rela,
-					       rodata_rela);
+					       rela);
 			if (ret)
 				return ret;
 		}
 
 		prev_jump = insn;
-		prev_rela = rodata_rela;
+		prev_rela = rela;
 	}
 
 	if (prev_jump) {

index 611645e..125ecd2 100644
@@ -48,6 +48,7 @@
 /* AVX VEX prefixes */
 #define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
 #define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
+#define INAT_PFX_EVEX	15	/* EVEX prefix */
 
 #define INAT_LSTPFX_MAX	3
 #define INAT_LGCPFX_MAX	11

@@ -89,6 +90,7 @@
 #define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
 #define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
 #define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
+#define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)

@@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr)
 static inline int inat_is_vex_prefix(insn_attr_t attr)
 {
 	attr &= INAT_PFX_MASK;
-	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
+	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
+	       attr == INAT_PFX_EVEX;
+}
+
+static inline int inat_is_evex_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
 }
 
 static inline int inat_is_vex3_prefix(insn_attr_t attr)

@@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr)
 
 static inline int inat_must_vex(insn_attr_t attr)
 {
-	return attr & INAT_VEXONLY;
+	return attr & (INAT_VEXONLY | INAT_EVEXONLY);
+}
+
+static inline int inat_must_evex(insn_attr_t attr)
+{
+	return attr & INAT_EVEXONLY;
 }
 #endif

index 9f26eae..ca983e2 100644
@@ -155,14 +155,24 @@ found:
 			/*
 			 * In 32-bits mode, if the [7:6] bits (mod bits of
 			 * ModRM) on the second byte are not 11b, it is
-			 * LDS or LES.
+			 * LDS or LES or BOUND.
 			 */
 			if (X86_MODRM_MOD(b2) != 3)
 				goto vex_end;
 		}
 		insn->vex_prefix.bytes[0] = b;
 		insn->vex_prefix.bytes[1] = b2;
-		if (inat_is_vex3_prefix(attr)) {
+		if (inat_is_evex_prefix(attr)) {
+			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+			insn->vex_prefix.bytes[2] = b2;
+			b2 = peek_nbyte_next(insn_byte_t, insn, 3);
+			insn->vex_prefix.bytes[3] = b2;
+			insn->vex_prefix.nbytes = 4;
+			insn->next_byte += 4;
+			if (insn->x86_64 && X86_VEX_W(b2))
+				/* VEX.W overrides opnd_size */
+				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->vex_prefix.nbytes = 3;

@@ -221,7 +231,9 @@ void insn_get_opcode(struct insn *insn)
 		m = insn_vex_m_bits(insn);
 		p = insn_vex_p_bits(insn);
 		insn->attr = inat_get_avx_attribute(op, m, p);
-		if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))
+		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 */
 	}

index dd12da0..e23578c 100644
@@ -91,6 +91,7 @@ struct insn {
 #define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
 #define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
 /* VEX bit fields */
+#define X86_EVEX_M(vex)	((vex) & 0x03)		/* EVEX Byte1 */
 #define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
 #define X86_VEX2_M	1			/* VEX2.M always 1 */
 #define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */

@@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn)
 	return (insn->vex_prefix.value != 0);
 }
 
+static inline int insn_is_evex(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return (insn->vex_prefix.nbytes == 4);
+}
+
 /* Ensure this instruction is decoded completely */
 static inline int insn_complete(struct insn *insn)
 {

@@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
 {
 	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
 		return X86_VEX2_M;
-	else
+	else if (insn->vex_prefix.nbytes == 3)	/* 3 bytes VEX */
 		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+	else					/* EVEX */
+		return X86_EVEX_M(insn->vex_prefix.bytes[1]);
 }
 
 static inline insn_byte_t insn_vex_p_bits(struct insn *insn)