Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "This tree contains tooling fixes plus some additions:

   - fixes to the vdso2c build environment that Stephen Rothwell is
     using for the linux-next build (Arnaldo Carvalho de Melo)

   - AVX-512 instruction mappings (Adrian Hunter)

   - misc fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  Revert "perf tools: event.h needs asm/perf_regs.h"
  x86: Make the vdso2c compiler use the host architecture headers
  tools build: Fix objtool build with ARCH=x86_64
  objtool: Always use host headers
  objtool: Use tools/scripts/Makefile.arch to get ARCH and HOSTARCH
  tools build: Add HOSTARCH Makefile variable
  perf tests kmod-path: Fix build on ubuntu:16.04-x-armhf
  perf tools: Add AVX-512 instructions to the new instructions test
  perf tools: Add AVX-512 support to the instruction decoder used by Intel PT
  x86/insn: Add AVX-512 support to the instruction decoder
  x86/insn: perf tools: Fix vcvtph2ps instruction decoding

arch/x86/entry/vdso/Makefile

@@ -55,7 +55,7 @@ VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
 $(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
 
-HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/x86/include/uapi
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi
 hostprogs-y			+= vdso2c
 
 quiet_cmd_vdso2c = VDSO2C  $@

arch/x86/include/asm/inat.h

@@ -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

arch/x86/include/asm/insn.h

@@ -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)

arch/x86/lib/insn.c

@@ -155,14 +155,24 @@ void insn_get_prefixes(struct insn *insn)
 			/*
 			 * 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 */
 	}

arch/x86/tools/gen-insn-attr-x86.awk

@@ -72,12 +72,14 @@ BEGIN {
 	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
-	# All opcodes starting with lower-case 'v' or with (v1) superscript
+	# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
 	# accepts VEX prefix
-	vexok_opcode_expr = "^v.*"
+	vexok_opcode_expr = "^[vk].*"
 	vexok_expr = "\\(v1\\)"
 	# All opcodes with (v) superscript supports *only* VEX prefix
 	vexonly_expr = "\\(v\\)"
+	# All opcodes with (ev) superscript supports *only* EVEX prefix
+	evexonly_expr = "\\(ev\\)"
 
 	prefix_expr = "\\(Prefix\\)"
 	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
@@ -95,6 +97,7 @@ BEGIN {
 	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
 	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
 	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
+	prefix_num["EVEX"] = "INAT_PFX_EVEX"
 
 	clear_vars()
 }
@@ -319,7 +322,9 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 			flags = add_flags(flags, "INAT_MODRM")
 
 		# check VEX codes
-		if (match(ext, vexonly_expr))
+		if (match(ext, evexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
+		else if (match(ext, vexonly_expr))
 			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
 		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
 			flags = add_flags(flags, "INAT_VEXOK")

tools/objtool/Build

-objtool-y += arch/$(ARCH)/
+objtool-y += arch/$(SRCARCH)/
 objtool-y += builtin-check.o
 objtool-y += elf.o
 objtool-y += special.o

tools/objtool/Makefile

 include ../scripts/Makefile.include
+include ../scripts/Makefile.arch
 
-ifndef ($(ARCH))
-ARCH ?= $(shell uname -m)
 ifeq ($(ARCH),x86_64)
 ARCH := x86
 endif
-endif
 
 # always use the host compiler
 CC = gcc
@@ -26,7 +24,7 @@ OBJTOOL_IN := $(OBJTOOL)-in.o
 
 all: $(OBJTOOL)
 
-INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi
+INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi
 CFLAGS   += -Wall -Werror $(EXTRA_WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
 LDFLAGS  += -lelf $(LIBSUBCMD)
 
@@ -35,7 +33,7 @@ elfshdr := $(shell echo '\#include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | gre
 CFLAGS += $(if $(elfshdr),,-DLIBELF_USE_DEPRECATED)
 
 AWK = awk
-export srctree OUTPUT CFLAGS ARCH AWK
+export srctree OUTPUT CFLAGS SRCARCH AWK
 include $(srctree)/tools/build/Makefile.include
 
 $(OBJTOOL_IN): fixdep FORCE

tools/perf/tests/kmod-path.c

 #include <stdbool.h>
+#include <stdlib.h>
 #include "tests.h"
 #include "dso.h"
 #include "debug.h"

tools/perf/util/event.h

@@ -8,7 +8,6 @@
 #include "map.h"
 #include "build-id.h"
 #include "perf_regs.h"
-#include <asm/perf_regs.h>
 
 struct mmap_event {
 	struct perf_event_header header;

tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk

@@ -72,12 +72,14 @@ BEGIN {
 	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
-	# All opcodes starting with lower-case 'v' or with (v1) superscript
+	# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
 	# accepts VEX prefix
-	vexok_opcode_expr = "^v.*"
+	vexok_opcode_expr = "^[vk].*"
 	vexok_expr = "\\(v1\\)"
 	# All opcodes with (v) superscript supports *only* VEX prefix
 	vexonly_expr = "\\(v\\)"
+	# All opcodes with (ev) superscript supports *only* EVEX prefix
+	evexonly_expr = "\\(ev\\)"
 
 	prefix_expr = "\\(Prefix\\)"
 	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
@@ -95,6 +97,7 @@ BEGIN {
 	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
 	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
 	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
+	prefix_num["EVEX"] = "INAT_PFX_EVEX"
 
 	clear_vars()
 }
@@ -319,7 +322,9 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 			flags = add_flags(flags, "INAT_MODRM")
 
 		# check VEX codes
-		if (match(ext, vexonly_expr))
+		if (match(ext, evexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
+		else if (match(ext, vexonly_expr))
 			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
 		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
 			flags = add_flags(flags, "INAT_VEXOK")

tools/perf/util/intel-pt-decoder/inat.h

@@ -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

tools/perf/util/intel-pt-decoder/insn.c

@@ -155,14 +155,24 @@ void insn_get_prefixes(struct insn *insn)
 			/*
 			 * 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 */
 	}

tools/perf/util/intel-pt-decoder/insn.h

@@ -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)

tools/scripts/Makefile.arch

-ifndef ARCH
-ARCH := $(shell uname -m 2>/dev/null || echo not)
-endif
-
-ARCH := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
+HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
                                   -e s/sun4u/sparc/ -e s/sparc64/sparc/ \
                                   -e /arm64/!s/arm.*/arm/ -e s/sa110/arm/ \
                                   -e s/s390x/s390/ -e s/parisc64/parisc/ \
@@ -10,6 +6,41 @@ ARCH := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
                                   -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
                                   -e s/tile.*/tile/ )
 
+ifndef ARCH
+ARCH := $(HOSTARCH)
+endif
+
+SRCARCH := $(ARCH)
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),i386)
+        SRCARCH := x86
+endif
+ifeq ($(ARCH),x86_64)
+        SRCARCH := x86
+endif
+
+# Additional ARCH settings for sparc
+ifeq ($(ARCH),sparc32)
+       SRCARCH := sparc
+endif
+ifeq ($(ARCH),sparc64)
+       SRCARCH := sparc
+endif
+
+# Additional ARCH settings for sh
+ifeq ($(ARCH),sh64)
+       SRCARCH := sh
+endif
+
+# Additional ARCH settings for tile
+ifeq ($(ARCH),tilepro)
+       SRCARCH := tile
+endif
+ifeq ($(ARCH),tilegx)
+       SRCARCH := tile
+endif
+
 LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
 ifeq ($(LP64), 1)
   IS_64_BIT := 1