From c8d7b7e592f471ec1da39d872dc6bbf767a812e7 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Fri, 13 Nov 2020 00:03:20 +0100
Subject: x86/tools: Use tools headers for instruction decoder selftests

Currently the x86 instruction decoder is used from:
- the kernel itself,
- from tools like objtool and perf,
- within x86 tools, i.e. instruction decoder selftests.

The first two cases are similar, because tools headers try to mimic
kernel headers.

Instruction decoder selftests include some of the kernel headers
directly, including uapi headers. This works until headers dependencies
are kept to a minimum and tools are not cross-compiled. Since the goal
of the x86 instruction decoder selftests is not to verify uapi headers,
move it to using tools headers, like is already done for vdso2c tool,
mkpiggy and other tools in arch/x86/boot/.

Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 arch/x86/tools/Makefile | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index 55b1ab378974..bddfc9a46645 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -29,14 +29,14 @@ posttest: $(obj)/insn_decoder_test vmlinux $(obj)/insn_sanity
 hostprogs += insn_decoder_test insn_sanity
 
 # -I needed for generated C source and C source which in the kernel tree.
-HOSTCFLAGS_insn_decoder_test.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/uapi/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/uapi/
+HOSTCFLAGS_insn_decoder_test.o := -Wall -I$(srctree)/tools/arch/x86/lib/ -I$(srctree)/tools/arch/x86/include/ -I$(objtree)/arch/x86/lib/
 
-HOSTCFLAGS_insn_sanity.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/
+HOSTCFLAGS_insn_sanity.o := -Wall -I$(srctree)/tools/arch/x86/lib/ -I$(srctree)/tools/arch/x86/include/ -I$(objtree)/arch/x86/lib/
 
 # Dependencies are also needed.
-$(obj)/insn_decoder_test.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+$(obj)/insn_decoder_test.o: $(srctree)/tools/arch/x86/lib/insn.c $(srctree)/tools/arch/x86/lib/inat.c $(srctree)/tools/arch/x86/include/asm/inat_types.h $(srctree)/tools/arch/x86/include/asm/inat.h $(srctree)/tools/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
 
-$(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+$(obj)/insn_sanity.o: $(srctree)/tools/arch/x86/lib/insn.c $(srctree)/tools/arch/x86/lib/inat.c $(srctree)/tools/arch/x86/include/asm/inat_types.h $(srctree)/tools/arch/x86/include/asm/inat.h $(srctree)/tools/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
 
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 hostprogs	+= relocs
-- 
cgit v1.2.3


From 1d509f2a6ebca1aea3089c769f6375f01a832e9b Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Fri, 13 Nov 2020 00:03:23 +0100
Subject: x86/insn: Support big endian cross-compiles

The x86 instruction decoder code is shared across the kernel source and
the tools. Currently objtool seems to be the only tool from build tools
needed which breaks x86 cross-compilation on big endian systems. Make
the x86 instruction decoder build host endianness agnostic to support
x86 cross-compilation and enable objtool to implement endianness
awareness for big endian architectures support.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Co-developed-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 arch/x86/include/asm/insn.h       |  33 +++++++++++++
 arch/x86/lib/insn.c               | 101 ++++++++++++++++++--------------------
 arch/x86/tools/insn_sanity.c      |   4 --
 tools/arch/x86/include/asm/insn.h |  33 +++++++++++++
 tools/arch/x86/lib/insn.c         | 101 ++++++++++++++++++--------------------
 5 files changed, 160 insertions(+), 112 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index a8c3d284fa46..090863cfb7f3 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -7,9 +7,12 @@
  * Copyright (C) IBM Corporation, 2009
  */
 
+#include <asm/byteorder.h>
 /* insn_attr_t is defined in inat.h */
 #include <asm/inat.h>
 
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+
 struct insn_field {
 	union {
 		insn_value_t value;
@@ -20,6 +23,36 @@ struct insn_field {
 	unsigned char nbytes;
 };
 
+static inline void insn_field_set(struct insn_field *p, insn_value_t v,
+				  unsigned char n)
+{
+	p->value = v;
+	p->nbytes = n;
+}
+
+#else
+
+struct insn_field {
+	insn_value_t value;
+	union {
+		insn_value_t little;
+		insn_byte_t bytes[4];
+	};
+	/* !0 if we've run insn_get_xxx() for this field */
+	unsigned char got;
+	unsigned char nbytes;
+};
+
+static inline void insn_field_set(struct insn_field *p, insn_value_t v,
+				  unsigned char n)
+{
+	p->value = v;
+	p->little = __cpu_to_le32(v);
+	p->nbytes = n;
+}
+
+#endif
+
 struct insn {
 	struct insn_field prefixes;	/*
 					 * Prefixes
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 404279563891..520b31fc1f1a 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -5,6 +5,7 @@
  * Copyright (C) IBM Corporation, 2002, 2004, 2009
  */
 
+#include <linux/kernel.h>
 #ifdef __KERNEL__
 #include <linux/string.h>
 #else
@@ -15,15 +16,28 @@
 
 #include <asm/emulate_prefix.h>
 
+#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 = *(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 = *(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); })
@@ -157,8 +171,7 @@ 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 */
@@ -295,8 +308,7 @@ void insn_get_modrm(struct insn *insn)
 
 	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,
@@ -334,7 +346,7 @@ int insn_rip_relative(struct insn *insn)
 	 * 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);
 }
 
 /**
@@ -353,11 +365,11 @@ void insn_get_sib(struct insn *insn)
 	if (!insn->modrm.got)
 		insn_get_modrm(insn);
 	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;
@@ -407,19 +419,18 @@ 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);
 			}
 		}
 	}
@@ -435,18 +446,14 @@ 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 +471,11 @@ 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 +492,15 @@ 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 +517,10 @@ 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 +528,7 @@ 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;
@@ -565,22 +564,17 @@ 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))
@@ -599,8 +593,7 @@ 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;
diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c
index 185ceba9d289..c6a0000ae635 100644
--- a/arch/x86/tools/insn_sanity.c
+++ b/arch/x86/tools/insn_sanity.c
@@ -14,10 +14,6 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
-
-#define unlikely(cond) (cond)
-#define ARRAY_SIZE(a)	(sizeof(a)/sizeof(a[0]))
-
 #include <asm/insn.h>
 #include <inat.c>
 #include <insn.c>
diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index 52c6262e6bfd..c1fab7a570be 100644
--- a/tools/arch/x86/include/asm/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
@@ -7,9 +7,12 @@
  * Copyright (C) IBM Corporation, 2009
  */
 
+#include <asm/byteorder.h>
 /* insn_attr_t is defined in inat.h */
 #include "inat.h"
 
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+
 struct insn_field {
 	union {
 		insn_value_t value;
@@ -20,6 +23,36 @@ struct insn_field {
 	unsigned char nbytes;
 };
 
+static inline void insn_field_set(struct insn_field *p, insn_value_t v,
+				  unsigned char n)
+{
+	p->value = v;
+	p->nbytes = n;
+}
+
+#else
+
+struct insn_field {
+	insn_value_t value;
+	union {
+		insn_value_t little;
+		insn_byte_t bytes[4];
+	};
+	/* !0 if we've run insn_get_xxx() for this field */
+	unsigned char got;
+	unsigned char nbytes;
+};
+
+static inline void insn_field_set(struct insn_field *p, insn_value_t v,
+				  unsigned char n)
+{
+	p->value = v;
+	p->little = __cpu_to_le32(v);
+	p->nbytes = n;
+}
+
+#endif
+
 struct insn {
 	struct insn_field prefixes;	/*
 					 * Prefixes
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index 0151dfc6da61..77e92aa52cdc 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -5,6 +5,7 @@
  * Copyright (C) IBM Corporation, 2002, 2004, 2009
  */
 
+#include <linux/kernel.h>
 #ifdef __KERNEL__
 #include <linux/string.h>
 #else
@@ -15,15 +16,28 @@
 
 #include "../include/asm/emulate_prefix.h"
 
+#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 = *(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 = *(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); })
@@ -157,8 +171,7 @@ 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 */
@@ -295,8 +308,7 @@ void insn_get_modrm(struct insn *insn)
 
 	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,
@@ -334,7 +346,7 @@ int insn_rip_relative(struct insn *insn)
 	 * 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);
 }
 
 /**
@@ -353,11 +365,11 @@ void insn_get_sib(struct insn *insn)
 	if (!insn->modrm.got)
 		insn_get_modrm(insn);
 	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;
@@ -407,19 +419,18 @@ 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);
 			}
 		}
 	}
@@ -435,18 +446,14 @@ 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 +471,11 @@ 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 +492,15 @@ 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 +517,10 @@ 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 +528,7 @@ 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;
@@ -565,22 +564,17 @@ 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))
@@ -599,8 +593,7 @@ 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;
-- 
cgit v1.2.3


From 8bfe273238d77d3cee18e4c03b2f26ae360b5661 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Fri, 13 Nov 2020 00:03:29 +0100
Subject: objtool: Fix x86 orc generation on big endian cross-compiles

Correct objtool orc generation endianness problems to enable fully
functional x86 cross-compiles on big endian hardware.

Introduce bswap_if_needed() macro, which does a byte swap if target
endianness doesn't match the host, i.e. cross-compilation for little
endian on big endian and vice versa.  The macro is used for conversion
of multi-byte values which are read from / about to be written to a
target native endianness ELF file.

Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 arch/x86/include/asm/orc_types.h                 | 10 +++++++
 tools/arch/x86/include/asm/orc_types.h           | 10 +++++++
 tools/objtool/arch/x86/include/arch_endianness.h |  9 ++++++
 tools/objtool/check.c                            |  5 ++--
 tools/objtool/endianness.h                       | 38 ++++++++++++++++++++++++
 tools/objtool/orc_dump.c                         |  5 ++--
 tools/objtool/orc_gen.c                          |  3 ++
 tools/objtool/special.c                          |  6 ++--
 8 files changed, 80 insertions(+), 6 deletions(-)
 create mode 100644 tools/objtool/arch/x86/include/arch_endianness.h
 create mode 100644 tools/objtool/endianness.h

(limited to 'arch/x86')

diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index fdbffec4cfde..5a2baf28a1dc 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -40,6 +40,8 @@
 #define ORC_REG_MAX			15
 
 #ifndef __ASSEMBLY__
+#include <asm/byteorder.h>
+
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
  * Frame Information standard.  It contains only the necessary parts of DWARF
@@ -51,10 +53,18 @@
 struct orc_entry {
 	s16		sp_offset;
 	s16		bp_offset;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
 	unsigned	sp_reg:4;
 	unsigned	bp_reg:4;
 	unsigned	type:2;
 	unsigned	end:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	unsigned	bp_reg:4;
+	unsigned	sp_reg:4;
+	unsigned	unused:5;
+	unsigned	end:1;
+	unsigned	type:2;
+#endif
 } __packed;
 
 #endif /* __ASSEMBLY__ */
diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h
index fdbffec4cfde..5a2baf28a1dc 100644
--- a/tools/arch/x86/include/asm/orc_types.h
+++ b/tools/arch/x86/include/asm/orc_types.h
@@ -40,6 +40,8 @@
 #define ORC_REG_MAX			15
 
 #ifndef __ASSEMBLY__
+#include <asm/byteorder.h>
+
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
  * Frame Information standard.  It contains only the necessary parts of DWARF
@@ -51,10 +53,18 @@
 struct orc_entry {
 	s16		sp_offset;
 	s16		bp_offset;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
 	unsigned	sp_reg:4;
 	unsigned	bp_reg:4;
 	unsigned	type:2;
 	unsigned	end:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	unsigned	bp_reg:4;
+	unsigned	sp_reg:4;
+	unsigned	unused:5;
+	unsigned	end:1;
+	unsigned	type:2;
+#endif
 } __packed;
 
 #endif /* __ASSEMBLY__ */
diff --git a/tools/objtool/arch/x86/include/arch_endianness.h b/tools/objtool/arch/x86/include/arch_endianness.h
new file mode 100644
index 000000000000..7c362527da20
--- /dev/null
+++ b/tools/objtool/arch/x86/include/arch_endianness.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ARCH_ENDIANNESS_H
+#define _ARCH_ENDIANNESS_H
+
+#include <endian.h>
+
+#define __TARGET_BYTE_ORDER __LITTLE_ENDIAN
+
+#endif /* _ARCH_ENDIANNESS_H */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 270adc38d896..8cda0ef06522 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -13,6 +13,7 @@
 #include "special.h"
 #include "warn.h"
 #include "arch_elf.h"
+#include "endianness.h"
 
 #include <linux/objtool.h>
 #include <linux/hashtable.h>
@@ -1435,7 +1436,7 @@ static int read_unwind_hints(struct objtool_file *file)
 		cfa = &insn->cfi.cfa;
 
 		if (hint->type == UNWIND_HINT_TYPE_RET_OFFSET) {
-			insn->ret_offset = hint->sp_offset;
+			insn->ret_offset = bswap_if_needed(hint->sp_offset);
 			continue;
 		}
 
@@ -1447,7 +1448,7 @@ static int read_unwind_hints(struct objtool_file *file)
 			return -1;
 		}
 
-		cfa->offset = hint->sp_offset;
+		cfa->offset = bswap_if_needed(hint->sp_offset);
 		insn->cfi.type = hint->type;
 		insn->cfi.end = hint->end;
 	}
diff --git a/tools/objtool/endianness.h b/tools/objtool/endianness.h
new file mode 100644
index 000000000000..ebece3191b58
--- /dev/null
+++ b/tools/objtool/endianness.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _OBJTOOL_ENDIANNESS_H
+#define _OBJTOOL_ENDIANNESS_H
+
+#include <linux/kernel.h>
+#include <endian.h>
+#include "arch_endianness.h"
+
+#ifndef __TARGET_BYTE_ORDER
+#error undefined arch __TARGET_BYTE_ORDER
+#endif
+
+#if __BYTE_ORDER != __TARGET_BYTE_ORDER
+#define __NEED_BSWAP 1
+#else
+#define __NEED_BSWAP 0
+#endif
+
+/*
+ * Does a byte swap if target endianness doesn't match the host, i.e. cross
+ * compilation for little endian on big endian and vice versa.
+ * To be used for multi-byte values conversion, which are read from / about
+ * to be written to a target native endianness ELF file.
+ */
+#define bswap_if_needed(val)						\
+({									\
+	__typeof__(val) __ret;						\
+	switch (sizeof(val)) {						\
+	case 8: __ret = __NEED_BSWAP ? bswap_64(val) : (val); break;	\
+	case 4: __ret = __NEED_BSWAP ? bswap_32(val) : (val); break;	\
+	case 2: __ret = __NEED_BSWAP ? bswap_16(val) : (val); break;	\
+	default:							\
+		BUILD_BUG(); break;					\
+	}								\
+	__ret;								\
+})
+
+#endif /* _OBJTOOL_ENDIANNESS_H */
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index 5e6a95368d35..4e818a22e44b 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -8,6 +8,7 @@
 #include <asm/orc_types.h>
 #include "objtool.h"
 #include "warn.h"
+#include "endianness.h"
 
 static const char *reg_name(unsigned int reg)
 {
@@ -197,11 +198,11 @@ int orc_dump(const char *_objname)
 
 		printf(" sp:");
 
-		print_reg(orc[i].sp_reg, orc[i].sp_offset);
+		print_reg(orc[i].sp_reg, bswap_if_needed(orc[i].sp_offset));
 
 		printf(" bp:");
 
-		print_reg(orc[i].bp_reg, orc[i].bp_offset);
+		print_reg(orc[i].bp_reg, bswap_if_needed(orc[i].bp_offset));
 
 		printf(" type:%s end:%d\n",
 		       orc_type_name(orc[i].type), orc[i].end);
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 9ce68b385a1b..1be7e16b2595 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -11,6 +11,7 @@
 
 #include "check.h"
 #include "warn.h"
+#include "endianness.h"
 
 int create_orc(struct objtool_file *file)
 {
@@ -96,6 +97,8 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti
 	/* populate ORC data */
 	orc = (struct orc_entry *)u_sec->data->d_buf + idx;
 	memcpy(orc, o, sizeof(*orc));
+	orc->sp_offset = bswap_if_needed(orc->sp_offset);
+	orc->bp_offset = bswap_if_needed(orc->bp_offset);
 
 	/* populate reloc for ip */
 	reloc = malloc(sizeof(*reloc));
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index 1a2420febd08..ab7cb1e13411 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -15,6 +15,7 @@
 #include "special.h"
 #include "warn.h"
 #include "arch_special.h"
+#include "endianness.h"
 
 struct special_entry {
 	const char *sec;
@@ -77,8 +78,9 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
 	if (entry->feature) {
 		unsigned short feature;
 
-		feature = *(unsigned short *)(sec->data->d_buf + offset +
-					      entry->feature);
+		feature = bswap_if_needed(*(unsigned short *)(sec->data->d_buf +
+							      offset +
+							      entry->feature));
 		arch_handle_alternative(feature, alt);
 	}
 
-- 
cgit v1.2.3


From 5ed934e57e712b676ca62e1904ad672a9fa1505a Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Fri, 13 Nov 2020 17:09:54 +0100
Subject: x86/insn: Fix vector instruction decoding on big endian
 cross-compiles

Running instruction decoder posttest on an s390 host with an x86 target
with allyesconfig shows errors. Instructions used in a couple of kernel
objects could not be correctly decoded on big endian system.

  insn_decoder_test: warning: objdump says 6 bytes, but insn_get_length() says 5
  insn_decoder_test: warning: Found an x86 instruction decoder bug, please report this.
  insn_decoder_test: warning: ffffffff831eb4e1:    62 d1 fd 48 7f 04 24    vmovdqa64 %zmm0,(%r12)
  insn_decoder_test: warning: objdump says 7 bytes, but insn_get_length() says 6
  insn_decoder_test: warning: Found an x86 instruction decoder bug, please report this.
  insn_decoder_test: warning: ffffffff831eb4e8:    62 51 fd 48 7f 44 24 01         vmovdqa64 %zmm8,0x40(%r12)
  insn_decoder_test: warning: objdump says 8 bytes, but insn_get_length() says 6

This is because in a few places instruction field bytes are set directly
with further usage of "value". To address that introduce and use a
insn_set_byte() helper, which correctly updates "value" on big endian
systems.

Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 arch/x86/include/asm/insn.h       | 12 ++++++++++++
 arch/x86/lib/insn.c               | 18 +++++++++---------
 tools/arch/x86/include/asm/insn.h | 12 ++++++++++++
 tools/arch/x86/lib/insn.c         | 18 +++++++++---------
 4 files changed, 42 insertions(+), 18 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 090863cfb7f3..95a448fbb44c 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -30,6 +30,12 @@ static inline void insn_field_set(struct insn_field *p, insn_value_t v,
 	p->nbytes = n;
 }
 
+static inline void insn_set_byte(struct insn_field *p, unsigned char n,
+				 insn_byte_t v)
+{
+	p->bytes[n] = v;
+}
+
 #else
 
 struct insn_field {
@@ -51,6 +57,12 @@ static inline void insn_field_set(struct insn_field *p, insn_value_t v,
 	p->nbytes = n;
 }
 
+static inline void insn_set_byte(struct insn_field *p, unsigned char n,
+				 insn_byte_t v)
+{
+	p->bytes[n] = v;
+	p->value = __le32_to_cpu(p->little);
+}
 #endif
 
 struct insn {
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 520b31fc1f1a..435630a6ec97 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -161,9 +161,9 @@ 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 */
@@ -194,13 +194,13 @@ 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))
@@ -208,7 +208,7 @@ 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))
@@ -220,7 +220,7 @@ 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;
 		}
@@ -256,7 +256,7 @@ void insn_get_opcode(struct insn *insn)
 
 	/* 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 */
diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index c1fab7a570be..cc777c185212 100644
--- a/tools/arch/x86/include/asm/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
@@ -30,6 +30,12 @@ static inline void insn_field_set(struct insn_field *p, insn_value_t v,
 	p->nbytes = n;
 }
 
+static inline void insn_set_byte(struct insn_field *p, unsigned char n,
+				 insn_byte_t v)
+{
+	p->bytes[n] = v;
+}
+
 #else
 
 struct insn_field {
@@ -51,6 +57,12 @@ static inline void insn_field_set(struct insn_field *p, insn_value_t v,
 	p->nbytes = n;
 }
 
+static inline void insn_set_byte(struct insn_field *p, unsigned char n,
+				 insn_byte_t v)
+{
+	p->bytes[n] = v;
+	p->value = __le32_to_cpu(p->little);
+}
 #endif
 
 struct insn {
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index 77e92aa52cdc..3d9355ed1246 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -161,9 +161,9 @@ 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 */
@@ -194,13 +194,13 @@ 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))
@@ -208,7 +208,7 @@ 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))
@@ -220,7 +220,7 @@ 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;
 		}
@@ -256,7 +256,7 @@ void insn_get_opcode(struct insn *insn)
 
 	/* 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 */
-- 
cgit v1.2.3


From 18660698a3d30868524cefb60dcd4e0e297f71bb Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Thu, 21 Jan 2021 15:29:21 -0600
Subject: x86/ftrace: Add UNWIND_HINT_FUNC annotation for ftrace_stub

Prevent an unreachable objtool warning after the sibling call detection
gets improved.  ftrace_stub() is basically a function, annotate it as
such.

Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/6845e1b2fb0723a95740c6674e548ba38c5ea489.1611263461.git.jpoimboe@redhat.com
---
 arch/x86/kernel/ftrace_64.S | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 0d54099c2a3a..58d125ed9d1a 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -184,6 +184,7 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
  * It is also used to copy the retq for trampolines.
  */
 SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
+	UNWIND_HINT_FUNC
 	retq
 SYM_FUNC_END(ftrace_epilogue)
 
-- 
cgit v1.2.3


From b735bd3e68824316655252a931a3353a6ebc036f Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Thu, 21 Jan 2021 15:29:24 -0600
Subject: objtool: Combine UNWIND_HINT_RET_OFFSET and UNWIND_HINT_FUNC

The ORC metadata generated for UNWIND_HINT_FUNC isn't actually very
func-like.  With certain usages it can cause stack state mismatches
because it doesn't set the return address (CFI_RA).

Also, users of UNWIND_HINT_RET_OFFSET no longer need to set a custom
return stack offset.  Instead they just need to specify a func-like
situation, so the current ret_offset code is hacky for no good reason.

Solve both problems by simplifying the RET_OFFSET handling and
converting it into a more useful UNWIND_HINT_FUNC.

If we end up needing the old 'ret_offset' functionality again in the
future, we should be able to support it pretty easily with the addition
of a custom 'sp_offset' in UNWIND_HINT_FUNC.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/db9d1f5d79dddfbb3725ef6d8ec3477ad199948d.1611263462.git.jpoimboe@redhat.com
---
 arch/x86/include/asm/unwind_hints.h   | 13 ++----------
 arch/x86/kernel/ftrace_64.S           |  2 +-
 arch/x86/lib/retpoline.S              |  2 +-
 include/linux/objtool.h               |  5 ++++-
 tools/include/linux/objtool.h         |  5 ++++-
 tools/objtool/arch/x86/decode.c       |  4 ++--
 tools/objtool/check.c                 | 37 ++++++++++++++---------------------
 tools/objtool/include/objtool/check.h |  1 -
 8 files changed, 29 insertions(+), 40 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index 664d4610d700..8e574c0afef8 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -48,17 +48,8 @@
 	UNWIND_HINT_REGS base=\base offset=\offset partial=1
 .endm
 
-.macro UNWIND_HINT_FUNC sp_offset=8
-	UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=\sp_offset type=UNWIND_HINT_TYPE_CALL
-.endm
-
-/*
- * RET_OFFSET: Used on instructions that terminate a function; mostly RETURN
- * and sibling calls. On these, sp_offset denotes the expected offset from
- * initial_func_cfi.
- */
-.macro UNWIND_HINT_RET_OFFSET sp_offset=8
-	UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset
+.macro UNWIND_HINT_FUNC
+	UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=8 type=UNWIND_HINT_TYPE_FUNC
 .endm
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 58d125ed9d1a..1bf568d901b1 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -277,7 +277,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 	restore_mcount_regs 8
 	/* Restore flags */
 	popfq
-	UNWIND_HINT_RET_OFFSET
+	UNWIND_HINT_FUNC
 	jmp	ftrace_epilogue
 
 SYM_FUNC_END(ftrace_regs_caller)
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index b4c43a9b1483..f6fb1d218dcc 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -28,7 +28,7 @@ SYM_FUNC_START_NOALIGN(__x86_retpoline_\reg)
 	jmp	.Lspec_trap_\@
 .Ldo_rop_\@:
 	mov	%\reg, (%_ASM_SP)
-	UNWIND_HINT_RET_OFFSET
+	UNWIND_HINT_FUNC
 	ret
 SYM_FUNC_END(__x86_retpoline_\reg)
 
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index add1c6eb157e..7e72d975cb76 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -29,11 +29,14 @@ struct unwind_hint {
  *
  * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that
  * sp_reg+sp_offset points to the iret return frame.
+ *
+ * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function.
+ * Useful for code which doesn't have an ELF function annotation.
  */
 #define UNWIND_HINT_TYPE_CALL		0
 #define UNWIND_HINT_TYPE_REGS		1
 #define UNWIND_HINT_TYPE_REGS_PARTIAL	2
-#define UNWIND_HINT_TYPE_RET_OFFSET	3
+#define UNWIND_HINT_TYPE_FUNC		3
 
 #ifdef CONFIG_STACK_VALIDATION
 
diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h
index add1c6eb157e..7e72d975cb76 100644
--- a/tools/include/linux/objtool.h
+++ b/tools/include/linux/objtool.h
@@ -29,11 +29,14 @@ struct unwind_hint {
  *
  * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that
  * sp_reg+sp_offset points to the iret return frame.
+ *
+ * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function.
+ * Useful for code which doesn't have an ELF function annotation.
  */
 #define UNWIND_HINT_TYPE_CALL		0
 #define UNWIND_HINT_TYPE_REGS		1
 #define UNWIND_HINT_TYPE_REGS_PARTIAL	2
-#define UNWIND_HINT_TYPE_RET_OFFSET	3
+#define UNWIND_HINT_TYPE_FUNC		3
 
 #ifdef CONFIG_STACK_VALIDATION
 
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 6baa22732ca6..9637e3bf5ab8 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -563,8 +563,8 @@ void arch_initial_func_cfi_state(struct cfi_init_state *state)
 	state->cfa.offset = 8;
 
 	/* initial RA (return address) */
-	state->regs[16].base = CFI_CFA;
-	state->regs[16].offset = -8;
+	state->regs[CFI_RA].base = CFI_CFA;
+	state->regs[CFI_RA].offset = -8;
 }
 
 const char *arch_nop_insn(int len)
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index b4e1655017de..f88f20327bf2 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1404,13 +1404,20 @@ static int add_jump_table_alts(struct objtool_file *file)
 	return 0;
 }
 
+static void set_func_state(struct cfi_state *state)
+{
+	state->cfa = initial_func_cfi.cfa;
+	memcpy(&state->regs, &initial_func_cfi.regs,
+	       CFI_NUM_REGS * sizeof(struct cfi_reg));
+	state->stack_size = initial_func_cfi.cfa.offset;
+}
+
 static int read_unwind_hints(struct objtool_file *file)
 {
 	struct section *sec, *relocsec;
 	struct reloc *reloc;
 	struct unwind_hint *hint;
 	struct instruction *insn;
-	struct cfi_reg *cfa;
 	int i;
 
 	sec = find_section_by_name(file->elf, ".discard.unwind_hints");
@@ -1445,22 +1452,20 @@ static int read_unwind_hints(struct objtool_file *file)
 			return -1;
 		}
 
-		cfa = &insn->cfi.cfa;
+		insn->hint = true;
 
-		if (hint->type == UNWIND_HINT_TYPE_RET_OFFSET) {
-			insn->ret_offset = bswap_if_needed(hint->sp_offset);
+		if (hint->type == UNWIND_HINT_TYPE_FUNC) {
+			set_func_state(&insn->cfi);
 			continue;
 		}
 
-		insn->hint = true;
-
 		if (arch_decode_hint_reg(insn, hint->sp_reg)) {
 			WARN_FUNC("unsupported unwind_hint sp base reg %d",
 				  insn->sec, insn->offset, hint->sp_reg);
 			return -1;
 		}
 
-		cfa->offset = bswap_if_needed(hint->sp_offset);
+		insn->cfi.cfa.offset = bswap_if_needed(hint->sp_offset);
 		insn->cfi.type = hint->type;
 		insn->cfi.end = hint->end;
 	}
@@ -1716,27 +1721,18 @@ static bool is_fentry_call(struct instruction *insn)
 
 static bool has_modified_stack_frame(struct instruction *insn, struct insn_state *state)
 {
-	u8 ret_offset = insn->ret_offset;
 	struct cfi_state *cfi = &state->cfi;
 	int i;
 
 	if (cfi->cfa.base != initial_func_cfi.cfa.base || cfi->drap)
 		return true;
 
-	if (cfi->cfa.offset != initial_func_cfi.cfa.offset + ret_offset)
+	if (cfi->cfa.offset != initial_func_cfi.cfa.offset)
 		return true;
 
-	if (cfi->stack_size != initial_func_cfi.cfa.offset + ret_offset)
+	if (cfi->stack_size != initial_func_cfi.cfa.offset)
 		return true;
 
-	/*
-	 * If there is a ret offset hint then don't check registers
-	 * because a callee-saved register might have been pushed on
-	 * the stack.
-	 */
-	if (ret_offset)
-		return false;
-
 	for (i = 0; i < CFI_NUM_REGS; i++) {
 		if (cfi->regs[i].base != initial_func_cfi.regs[i].base ||
 		    cfi->regs[i].offset != initial_func_cfi.regs[i].offset)
@@ -2880,10 +2876,7 @@ static int validate_section(struct objtool_file *file, struct section *sec)
 			continue;
 
 		init_insn_state(&state, sec);
-		state.cfi.cfa = initial_func_cfi.cfa;
-		memcpy(&state.cfi.regs, &initial_func_cfi.regs,
-		       CFI_NUM_REGS * sizeof(struct cfi_reg));
-		state.cfi.stack_size = initial_func_cfi.cfa.offset;
+		set_func_state(&state.cfi);
 
 		warnings += validate_symbol(file, sec, func, &state);
 	}
diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h
index b408636c0201..4891ead0e85f 100644
--- a/tools/objtool/include/objtool/check.h
+++ b/tools/objtool/include/objtool/check.h
@@ -50,7 +50,6 @@ struct instruction {
 	bool retpoline_safe;
 	s8 instr;
 	u8 visited;
-	u8 ret_offset;
 	struct alt_group *alt_group;
 	struct symbol *call_dest;
 	struct instruction *jump_dest;
-- 
cgit v1.2.3


From cde07a4e4434ddfb9b1616ac971edf6d66329804 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Thu, 21 Jan 2021 15:29:28 -0600
Subject: x86/xen: Support objtool validation in xen-asm.S

The OBJECT_FILES_NON_STANDARD annotation is used to tell objtool to
ignore a file.  File-level ignores won't work when validating vmlinux.o.

Tweak the ELF metadata and unwind hints to allow objtool to follow the
code.

Cc: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/8b042a09c69e8645f3b133ef6653ba28f896807d.1611263462.git.jpoimboe@redhat.com
---
 arch/x86/xen/Makefile  |  1 -
 arch/x86/xen/xen-asm.S | 29 +++++++++++++++++++----------
 2 files changed, 19 insertions(+), 11 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index fc5c5ba4aacb..40b5779fce21 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-OBJECT_FILES_NON_STANDARD_xen-asm.o := y
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not profile debug and lowlevel utilities
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 1cb0e84b9161..a05e80b552c0 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -14,6 +14,7 @@
 #include <asm/thread_info.h>
 #include <asm/asm.h>
 #include <asm/frame.h>
+#include <asm/unwind_hints.h>
 
 #include <xen/interface/xen.h>
 
@@ -146,6 +147,7 @@ SYM_FUNC_END(xen_read_cr2_direct);
 
 .macro xen_pv_trap name
 SYM_CODE_START(xen_\name)
+	UNWIND_HINT_EMPTY
 	pop %rcx
 	pop %r11
 	jmp  \name
@@ -184,6 +186,7 @@ xen_pv_trap asm_exc_xen_hypervisor_callback
 SYM_CODE_START(xen_early_idt_handler_array)
 	i = 0
 	.rept NUM_EXCEPTION_VECTORS
+	UNWIND_HINT_EMPTY
 	pop %rcx
 	pop %r11
 	jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE
@@ -210,11 +213,13 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
  * rsp->rax		}
  */
 SYM_CODE_START(xen_iret)
+	UNWIND_HINT_EMPTY
 	pushq $0
 	jmp hypercall_iret
 SYM_CODE_END(xen_iret)
 
 SYM_CODE_START(xen_sysret64)
+	UNWIND_HINT_EMPTY
 	/*
 	 * We're already on the usermode stack at this point, but
 	 * still with the kernel gs, so we can easily switch back.
@@ -250,7 +255,8 @@ SYM_CODE_END(xen_sysret64)
  */
 
 /* Normal 64-bit system call target */
-SYM_FUNC_START(xen_syscall_target)
+SYM_CODE_START(xen_syscall_target)
+	UNWIND_HINT_EMPTY
 	popq %rcx
 	popq %r11
 
@@ -263,12 +269,13 @@ SYM_FUNC_START(xen_syscall_target)
 	movq $__USER_CS, 1*8(%rsp)
 
 	jmp entry_SYSCALL_64_after_hwframe
-SYM_FUNC_END(xen_syscall_target)
+SYM_CODE_END(xen_syscall_target)
 
 #ifdef CONFIG_IA32_EMULATION
 
 /* 32-bit compat syscall target */
-SYM_FUNC_START(xen_syscall32_target)
+SYM_CODE_START(xen_syscall32_target)
+	UNWIND_HINT_EMPTY
 	popq %rcx
 	popq %r11
 
@@ -281,10 +288,11 @@ SYM_FUNC_START(xen_syscall32_target)
 	movq $__USER32_CS, 1*8(%rsp)
 
 	jmp entry_SYSCALL_compat_after_hwframe
-SYM_FUNC_END(xen_syscall32_target)
+SYM_CODE_END(xen_syscall32_target)
 
 /* 32-bit compat sysenter target */
-SYM_FUNC_START(xen_sysenter_target)
+SYM_CODE_START(xen_sysenter_target)
+	UNWIND_HINT_EMPTY
 	/*
 	 * NB: Xen is polite and clears TF from EFLAGS for us.  This means
 	 * that we don't need to guard against single step exceptions here.
@@ -301,17 +309,18 @@ SYM_FUNC_START(xen_sysenter_target)
 	movq $__USER32_CS, 1*8(%rsp)
 
 	jmp entry_SYSENTER_compat_after_hwframe
-SYM_FUNC_END(xen_sysenter_target)
+SYM_CODE_END(xen_sysenter_target)
 
 #else /* !CONFIG_IA32_EMULATION */
 
-SYM_FUNC_START_ALIAS(xen_syscall32_target)
-SYM_FUNC_START(xen_sysenter_target)
+SYM_CODE_START(xen_syscall32_target)
+SYM_CODE_START(xen_sysenter_target)
+	UNWIND_HINT_EMPTY
 	lea 16(%rsp), %rsp	/* strip %rcx, %r11 */
 	mov $-ENOSYS, %rax
 	pushq $0
 	jmp hypercall_iret
-SYM_FUNC_END(xen_sysenter_target)
-SYM_FUNC_END_ALIAS(xen_syscall32_target)
+SYM_CODE_END(xen_sysenter_target)
+SYM_CODE_END(xen_syscall32_target)
 
 #endif	/* CONFIG_IA32_EMULATION */
-- 
cgit v1.2.3


From f4b4bc10b0b85ec66f1a9bf5dddf475e6695b6d2 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Thu, 21 Jan 2021 15:29:29 -0600
Subject: x86/xen: Support objtool vmlinux.o validation in xen-head.S

The Xen hypercall page is filled with zeros, causing objtool to fall
through all the empty hypercall functions until it reaches a real
function, resulting in a stack state mismatch.

The build-time contents of the hypercall page don't matter because the
page gets rewritten by the hypervisor.  Make it more palatable to
objtool by making each hypervisor function a true empty function, with
nops and a return.

Cc: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/0883bde1d7a1fb3b6a4c952bc0200e873752f609.1611263462.git.jpoimboe@redhat.com
---
 arch/x86/xen/xen-head.S | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 2d7c8f34f56c..cb6538ae2fe0 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -68,8 +68,9 @@ SYM_CODE_END(asm_cpu_bringup_and_idle)
 	.balign PAGE_SIZE
 SYM_CODE_START(hypercall_page)
 	.rept (PAGE_SIZE / 32)
-		UNWIND_HINT_EMPTY
-		.skip 32
+		UNWIND_HINT_FUNC
+		.skip 31, 0x90
+		ret
 	.endr
 
 #define HYPERCALL(n) \
-- 
cgit v1.2.3


From 82694854caa8badab7c5d3a19c0139e8b471b1d3 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Thu, 21 Jan 2021 15:29:30 -0600
Subject: x86/xen/pvh: Annotate indirect branch as safe

This indirect jump is harmless; annotate it to keep objtool's retpoline
validation happy.

Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/4797c72a258b26e06741c58ccd4a75c42db39c1d.1611263462.git.jpoimboe@redhat.com
---
 arch/x86/platform/pvh/head.S | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index 43b4d864817e..d2ccadc247e6 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -16,6 +16,7 @@
 #include <asm/boot.h>
 #include <asm/processor-flags.h>
 #include <asm/msr.h>
+#include <asm/nospec-branch.h>
 #include <xen/interface/elfnote.h>
 
 	__HEAD
@@ -105,6 +106,7 @@ SYM_CODE_START_LOCAL(pvh_start_xen)
 	/* startup_64 expects boot_params in %rsi. */
 	mov $_pa(pvh_bootparams), %rsi
 	mov $_pa(startup_64), %rax
+	ANNOTATE_RETPOLINE_SAFE
 	jmp *%rax
 
 #else /* CONFIG_X86_64 */
-- 
cgit v1.2.3


From 7cae4b1cf1cc42f490422e20662169e8656c915a Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Thu, 21 Jan 2021 15:29:31 -0600
Subject: x86/ftrace: Support objtool vmlinux.o validation in ftrace_64.S

With objtool vmlinux.o validation of return_to_handler(), now that
objtool has visibility inside the retpoline, jumping from EMPTY state to
a proper function state results in a stack state mismatch.

return_to_handler() is actually quite normal despite the underlying
magic.  Just annotate it as a normal function.

Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/14f48e623f61dbdcd84cf27a56ed8ccae73199ef.1611263462.git.jpoimboe@redhat.com
---
 arch/x86/kernel/ftrace_64.S | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 1bf568d901b1..7c273846c687 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -334,8 +334,7 @@ SYM_FUNC_START(ftrace_graph_caller)
 	retq
 SYM_FUNC_END(ftrace_graph_caller)
 
-SYM_CODE_START(return_to_handler)
-	UNWIND_HINT_EMPTY
+SYM_FUNC_START(return_to_handler)
 	subq  $24, %rsp
 
 	/* Save the return values */
@@ -350,5 +349,5 @@ SYM_CODE_START(return_to_handler)
 	movq (%rsp), %rax
 	addq $24, %rsp
 	JMP_NOSPEC rdi
-SYM_CODE_END(return_to_handler)
+SYM_FUNC_END(return_to_handler)
 #endif
-- 
cgit v1.2.3


From f83d1a0190bf6ac788a848454d21daee2299d085 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Thu, 21 Jan 2021 15:29:32 -0600
Subject: x86/acpi: Annotate indirect branch as safe

This indirect jump is harmless; annotate it to keep objtool's retpoline
validation happy.

Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <len.brown@intel.com>
Cc: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/a7288e7043265d95c1a5d64f9fd751ead4854bdc.1611263462.git.jpoimboe@redhat.com
---
 arch/x86/kernel/acpi/wakeup_64.S | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 5d3a0b8fd379..9c9c66662ada 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -7,6 +7,7 @@
 #include <asm/msr.h>
 #include <asm/asm-offsets.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 
 # Copyright 2003 Pavel Machek <pavel@suse.cz
 
@@ -39,6 +40,7 @@ SYM_FUNC_START(wakeup_long64)
 	movq	saved_rbp, %rbp
 
 	movq	saved_rip, %rax
+	ANNOTATE_RETPOLINE_SAFE
 	jmp	*%rax
 SYM_FUNC_END(wakeup_long64)
 
-- 
cgit v1.2.3


From aeb818fcc94071e44203b3a36392562e5b88d9ec Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Thu, 21 Jan 2021 15:29:33 -0600
Subject: x86/acpi: Support objtool validation in wakeup_64.S

The OBJECT_FILES_NON_STANDARD annotation is used to tell objtool to
ignore a file.  File-level ignores won't work when validating vmlinux.o.

Instead, tell objtool to ignore do_suspend_lowlevel() directly with the
STACK_FRAME_NON_STANDARD annotation.

Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <len.brown@intel.com>
Cc: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/269eda576c53bc9ecc8167c211989111013a67aa.1611263462.git.jpoimboe@redhat.com
---
 arch/x86/kernel/acpi/Makefile    | 1 -
 arch/x86/kernel/acpi/wakeup_64.S | 2 ++
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile
index f1bb57b0e41e..cf340d85946a 100644
--- a/arch/x86/kernel/acpi/Makefile
+++ b/arch/x86/kernel/acpi/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-OBJECT_FILES_NON_STANDARD_wakeup_$(BITS).o := y
 
 obj-$(CONFIG_ACPI)		+= boot.o
 obj-$(CONFIG_ACPI_SLEEP)	+= sleep.o wakeup_$(BITS).o
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 9c9c66662ada..56b6865afb2a 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 .text
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/segment.h>
 #include <asm/pgtable_types.h>
 #include <asm/page_types.h>
@@ -128,6 +129,7 @@ SYM_FUNC_START(do_suspend_lowlevel)
 	FRAME_END
 	jmp	restore_processor_state
 SYM_FUNC_END(do_suspend_lowlevel)
+STACK_FRAME_NON_STANDARD do_suspend_lowlevel
 
 .data
 saved_rbp:		.quad	0
-- 
cgit v1.2.3


From b682369d47df66ebc157426f7eb991c3eec32e7e Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Thu, 21 Jan 2021 15:29:34 -0600
Subject: x86/power: Annotate indirect branches as safe

These indirect jumps are harmless; annotate them to make objtool's
retpoline validation happy.

Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/ba7a141c98f2c09c255b19bf78ee4a5f45d4ecb6.1611263462.git.jpoimboe@redhat.com
---
 arch/x86/power/hibernate_asm_64.S | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 7918b8415f13..715509d94fa3 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -21,6 +21,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/processor-flags.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 
 SYM_FUNC_START(swsusp_arch_suspend)
 	movq	$saved_context, %rax
@@ -66,6 +67,7 @@ SYM_CODE_START(restore_image)
 
 	/* jump to relocated restore code */
 	movq	relocated_restore_code(%rip), %rcx
+	ANNOTATE_RETPOLINE_SAFE
 	jmpq	*%rcx
 SYM_CODE_END(restore_image)
 
@@ -97,6 +99,7 @@ SYM_CODE_START(core_restore_code)
 
 .Ldone:
 	/* jump to the restore_registers address from the image header */
+	ANNOTATE_RETPOLINE_SAFE
 	jmpq	*%r8
 SYM_CODE_END(core_restore_code)
 
-- 
cgit v1.2.3


From 125f0b7d24216f37a9683b3899fa45101090f098 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Thu, 21 Jan 2021 15:29:35 -0600
Subject: x86/power: Move restore_registers() to top of the file

Because restore_registers() is page-aligned, the assembler inexplicably
adds an unreachable jump from after the end of the previous function to
the beginning of restore_registers().

That confuses objtool, understandably.  It also creates significant text
fragmentation.  As a result, most of the object file is wasted text
(nops).

Move restore_registers() to the beginning of the file to both prevent
the text fragmentation and avoid the dead jump instruction.

$ size /tmp/hibernate_asm_64.before.o /tmp/hibernate_asm_64.after.o
   text	   data	    bss	    dec	    hex	filename
   4415	      0	      0	   4415	   113f	/tmp/hibernate_asm_64.before.o
    524	      0	      0	    524	    20c	/tmp/hibernate_asm_64.after.o

Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/8c7f634201d26453d73fe55032cbbdc05d004387.1611263462.git.jpoimboe@redhat.com
---
 arch/x86/power/hibernate_asm_64.S | 92 +++++++++++++++++++--------------------
 1 file changed, 46 insertions(+), 46 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 715509d94fa3..91c4602d2b5d 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -23,6 +23,52 @@
 #include <asm/frame.h>
 #include <asm/nospec-branch.h>
 
+	 /* code below belongs to the image kernel */
+	.align PAGE_SIZE
+SYM_FUNC_START(restore_registers)
+	/* go back to the original page tables */
+	movq    %r9, %cr3
+
+	/* Flush TLB, including "global" things (vmalloc) */
+	movq	mmu_cr4_features(%rip), %rax
+	movq	%rax, %rdx
+	andq	$~(X86_CR4_PGE), %rdx
+	movq	%rdx, %cr4;  # turn off PGE
+	movq	%cr3, %rcx;  # flush TLB
+	movq	%rcx, %cr3
+	movq	%rax, %cr4;  # turn PGE back on
+
+	/* We don't restore %rax, it must be 0 anyway */
+	movq	$saved_context, %rax
+	movq	pt_regs_sp(%rax), %rsp
+	movq	pt_regs_bp(%rax), %rbp
+	movq	pt_regs_si(%rax), %rsi
+	movq	pt_regs_di(%rax), %rdi
+	movq	pt_regs_bx(%rax), %rbx
+	movq	pt_regs_cx(%rax), %rcx
+	movq	pt_regs_dx(%rax), %rdx
+	movq	pt_regs_r8(%rax), %r8
+	movq	pt_regs_r9(%rax), %r9
+	movq	pt_regs_r10(%rax), %r10
+	movq	pt_regs_r11(%rax), %r11
+	movq	pt_regs_r12(%rax), %r12
+	movq	pt_regs_r13(%rax), %r13
+	movq	pt_regs_r14(%rax), %r14
+	movq	pt_regs_r15(%rax), %r15
+	pushq	pt_regs_flags(%rax)
+	popfq
+
+	/* Saved in save_processor_state. */
+	lgdt	saved_context_gdt_desc(%rax)
+
+	xorl	%eax, %eax
+
+	/* tell the hibernation core that we've just restored the memory */
+	movq	%rax, in_suspend(%rip)
+
+	ret
+SYM_FUNC_END(restore_registers)
+
 SYM_FUNC_START(swsusp_arch_suspend)
 	movq	$saved_context, %rax
 	movq	%rsp, pt_regs_sp(%rax)
@@ -102,49 +148,3 @@ SYM_CODE_START(core_restore_code)
 	ANNOTATE_RETPOLINE_SAFE
 	jmpq	*%r8
 SYM_CODE_END(core_restore_code)
-
-	 /* code below belongs to the image kernel */
-	.align PAGE_SIZE
-SYM_FUNC_START(restore_registers)
-	/* go back to the original page tables */
-	movq    %r9, %cr3
-
-	/* Flush TLB, including "global" things (vmalloc) */
-	movq	mmu_cr4_features(%rip), %rax
-	movq	%rax, %rdx
-	andq	$~(X86_CR4_PGE), %rdx
-	movq	%rdx, %cr4;  # turn off PGE
-	movq	%cr3, %rcx;  # flush TLB
-	movq	%rcx, %cr3
-	movq	%rax, %cr4;  # turn PGE back on
-
-	/* We don't restore %rax, it must be 0 anyway */
-	movq	$saved_context, %rax
-	movq	pt_regs_sp(%rax), %rsp
-	movq	pt_regs_bp(%rax), %rbp
-	movq	pt_regs_si(%rax), %rsi
-	movq	pt_regs_di(%rax), %rdi
-	movq	pt_regs_bx(%rax), %rbx
-	movq	pt_regs_cx(%rax), %rcx
-	movq	pt_regs_dx(%rax), %rdx
-	movq	pt_regs_r8(%rax), %r8
-	movq	pt_regs_r9(%rax), %r9
-	movq	pt_regs_r10(%rax), %r10
-	movq	pt_regs_r11(%rax), %r11
-	movq	pt_regs_r12(%rax), %r12
-	movq	pt_regs_r13(%rax), %r13
-	movq	pt_regs_r14(%rax), %r14
-	movq	pt_regs_r15(%rax), %r15
-	pushq	pt_regs_flags(%rax)
-	popfq
-
-	/* Saved in save_processor_state. */
-	lgdt	saved_context_gdt_desc(%rax)
-
-	xorl	%eax, %eax
-
-	/* tell the hibernation core that we've just restored the memory */
-	movq	%rax, in_suspend(%rip)
-
-	ret
-SYM_FUNC_END(restore_registers)
-- 
cgit v1.2.3


From 9077c016a39c78054f03e0354ad8409b47af68dc Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Thu, 21 Jan 2021 15:29:36 -0600
Subject: x86/power: Support objtool validation in hibernate_asm_64.S

The OBJECT_FILES_NON_STANDARD annotation is used to tell objtool to
ignore a file.  File-level ignores won't work when validating vmlinux.o.

Instead, convert restore_image() and core_restore_code() to be ELF
functions.  Their code is conventional enough for objtool to be able to
understand them.

Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/974f8ceb5385e470f72e93974c70ab5c894bb0dc.1611263462.git.jpoimboe@redhat.com
---
 arch/x86/power/Makefile           | 1 -
 arch/x86/power/hibernate_asm_64.S | 8 ++++----
 2 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile
index 6907b523e856..3ff80156f21a 100644
--- a/arch/x86/power/Makefile
+++ b/arch/x86/power/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-OBJECT_FILES_NON_STANDARD_hibernate_asm_$(BITS).o := y
 
 # __restore_processor_state() restores %gs after S3 resume and so should not
 # itself be stack-protected
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 91c4602d2b5d..d9bed596d849 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -99,7 +99,7 @@ SYM_FUNC_START(swsusp_arch_suspend)
 	ret
 SYM_FUNC_END(swsusp_arch_suspend)
 
-SYM_CODE_START(restore_image)
+SYM_FUNC_START(restore_image)
 	/* prepare to jump to the image kernel */
 	movq	restore_jump_address(%rip), %r8
 	movq	restore_cr3(%rip), %r9
@@ -115,10 +115,10 @@ SYM_CODE_START(restore_image)
 	movq	relocated_restore_code(%rip), %rcx
 	ANNOTATE_RETPOLINE_SAFE
 	jmpq	*%rcx
-SYM_CODE_END(restore_image)
+SYM_FUNC_END(restore_image)
 
 	/* code below has been relocated to a safe page */
-SYM_CODE_START(core_restore_code)
+SYM_FUNC_START(core_restore_code)
 	/* switch to temporary page tables */
 	movq	%rax, %cr3
 	/* flush TLB */
@@ -147,4 +147,4 @@ SYM_CODE_START(core_restore_code)
 	/* jump to the restore_registers address from the image header */
 	ANNOTATE_RETPOLINE_SAFE
 	jmpq	*%r8
-SYM_CODE_END(core_restore_code)
+SYM_FUNC_END(core_restore_code)
-- 
cgit v1.2.3


From 87ccc826bf1c9e5ab4c2f649b404e02c63e47622 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 3 Feb 2021 12:02:21 +0100
Subject: x86/unwind/orc: Change REG_SP_INDIRECT

Currently REG_SP_INDIRECT is unused but means (%rsp + offset),
change it to mean (%rsp) + offset.

The reason is that we're going to swizzle stack in the middle of a C
function with non-trivial stack footprint. This means that when the
unwinder finds the ToS, it needs to dereference it (%rsp) and then add
the offset to the next frame, resulting in: (%rsp) + offset

This is somewhat unfortunate, since REG_BP_INDIRECT is used (by DRAP)
and thus needs to retain the current (%rbp + offset).

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 arch/x86/kernel/unwind_orc.c | 5 ++++-
 tools/objtool/orc_dump.c     | 2 +-
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 73f800100066..2a1d47f47eee 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -471,7 +471,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_REG_SP_INDIRECT:
-		sp = state->sp + orc->sp_offset;
+		sp = state->sp;
 		indirect = true;
 		break;
 
@@ -521,6 +521,9 @@ bool unwind_next_frame(struct unwind_state *state)
 	if (indirect) {
 		if (!deref_stack_reg(state, sp, &sp))
 			goto err;
+
+		if (orc->sp_reg == ORC_REG_SP_INDIRECT)
+			sp += orc->sp_offset;
 	}
 
 	/* Find IP, SP and possibly regs: */
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index c53fae9dbe93..f5a8508c42d6 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -55,7 +55,7 @@ static void print_reg(unsigned int reg, int offset)
 	if (reg == ORC_REG_BP_INDIRECT)
 		printf("(bp%+d)", offset);
 	else if (reg == ORC_REG_SP_INDIRECT)
-		printf("(sp%+d)", offset);
+		printf("(sp)%+d", offset);
 	else if (reg == ORC_REG_UNDEFINED)
 		printf("(und)");
 	else
-- 
cgit v1.2.3