rfc v1 - rfc v2:
- rebased onto tip/objtool/core
- reformatted couple of lines
rfc v2 - rfc v3:
- reused __*_ENDIAN_BITFIELD and dropped unneeded byteswap if __KERNEL__
is defined following David's suggestions,
- re-splitted changes and made x86 instruction decoder a separate patch,
- extra patch to add -Wno-nested-externs build flag to enable BUILD_BUG()
usage,
- added a safer and more readable leXX_to_cpu macro in x86 instruction
decoder,
- simplified includes. Switched to using leXX_to_cpu/cpu_to_leXX in
the objtool and x86 instruction decoder since
<linux/kernel.h> is included in the objtool already.
Currently objtool seems to be the only tool from all the build tools
needed for x86 build which breaks x86 cross compilation on big endian
systems.
But besides x86 cross compilation, endianness awareness is also needed
for big endian architectures objtool support in general.
We have working prototype of objtool support and orc unwinder for s390
made originally by Martin Schwidefsky. I'm trying to bring it in shape
again and refactor to share more code with "generic" part.
But first things first. This patch series points to endianness problems
which should be addressed. Recent "other architectures support" patches
currently moved only some problematic parts into x86 arch specific folder.
Besides that even though big endian stuff is only needed for the objtool
arch/x86/lib/insn.c and arch/x86/include/asm/insn.h are shared across
the kernel source and the tools, so changes are applied to both.
Any suggestions how to make patches more acceptable are welcome.
Martin Schwidefsky (2):
objtool: x86 instruction decoder and big endian cross compiles
objtool: correct rebuilding of reloc sections
Vasily Gorbik (2):
objtool: allow nested externs to enable BUILD_BUG()
objtool: fix x86 orc generation on big endian cross compiles
arch/x86/include/asm/insn.h | 35 ++++++++
arch/x86/include/asm/orc_types.h | 10 +++
arch/x86/lib/insn.c | 108 ++++++++++++-------------
tools/arch/x86/include/asm/insn.h | 35 ++++++++
tools/arch/x86/include/asm/orc_types.h | 10 +++
tools/arch/x86/lib/insn.c | 108 ++++++++++++-------------
tools/objtool/Makefile | 2 +-
tools/objtool/arch/x86/special.c | 2 +-
tools/objtool/check.c | 4 +-
tools/objtool/elf.c | 34 ++++----
tools/objtool/orc_dump.c | 4 +-
tools/objtool/orc_gen.c | 2 +
12 files changed, 225 insertions(+), 129 deletions(-)
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
From: Martin Schwidefsky <[email protected]>
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 of the objtool usable on big endian machines.
Signed-off-by: Martin Schwidefsky <[email protected]>
Co-developed-by: Vasily Gorbik <[email protected]>
Signed-off-by: Vasily Gorbik <[email protected]>
---
arch/x86/include/asm/insn.h | 35 ++++++++++
arch/x86/lib/insn.c | 108 +++++++++++++++---------------
tools/arch/x86/include/asm/insn.h | 35 ++++++++++
tools/arch/x86/lib/insn.c | 108 +++++++++++++++---------------
4 files changed, 178 insertions(+), 108 deletions(-)
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 5c1ae3eff9d4..bff79b22da54 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 +23,38 @@ 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;
+#ifndef __KERNEL__
+ p->little = __bswap_32(v);
+#endif
+ 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..bbd4a5f15d83 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 +16,35 @@
#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 +178,7 @@ void insn_get_prefixes(struct insn *insn)
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 +315,7 @@ 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 +353,7 @@ 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 +372,11 @@ 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 +426,18 @@ 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 +453,14 @@ 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 +478,11 @@ 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 +499,15 @@ 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 +524,10 @@ 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 +535,7 @@ 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 +571,17 @@ 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 +600,7 @@ 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/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index 568854b14d0a..a5d33602e9d7 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 +23,38 @@ 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;
+#ifndef __KERNEL__
+ p->little = __bswap_32(v);
+#endif
+ 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..def6277d56c0 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 +16,35 @@
#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 +178,7 @@ void insn_get_prefixes(struct insn *insn)
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 +315,7 @@ 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 +353,7 @@ 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 +372,11 @@ 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 +426,18 @@ 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 +453,14 @@ 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 +478,11 @@ 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 +499,15 @@ 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 +524,10 @@ 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 +535,7 @@ 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 +571,17 @@ 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 +600,7 @@ 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;
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
Correct objtool orc generation endianness problems to enable fully
functional x86 cross compiles on big endian hardware.
Signed-off-by: Vasily Gorbik <[email protected]>
---
arch/x86/include/asm/orc_types.h | 10 ++++++++++
tools/arch/x86/include/asm/orc_types.h | 10 ++++++++++
tools/objtool/arch/x86/special.c | 2 +-
tools/objtool/check.c | 4 ++--
tools/objtool/orc_dump.c | 4 ++--
tools/objtool/orc_gen.c | 2 ++
6 files changed, 27 insertions(+), 5 deletions(-)
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/special.c b/tools/objtool/arch/x86/special.c
index fd4af88c0ea5..8349842aac82 100644
--- a/tools/objtool/arch/x86/special.c
+++ b/tools/objtool/arch/x86/special.c
@@ -9,7 +9,7 @@
void arch_handle_alternative(unsigned short feature, struct special_alt *alt)
{
- switch (feature) {
+ switch (le16_to_cpu(feature)) {
case X86_FEATURE_SMAP:
/*
* If UACCESS validation is enabled; force that alternative;
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 2df9f769412e..f20a4be2fb22 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1370,7 +1370,7 @@ 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 = le16_to_cpu(hint->sp_offset);
continue;
}
@@ -1382,7 +1382,7 @@ static int read_unwind_hints(struct objtool_file *file)
return -1;
}
- cfa->offset = hint->sp_offset;
+ cfa->offset = le16_to_cpu(hint->sp_offset);
insn->cfi.type = hint->type;
insn->cfi.end = hint->end;
}
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index 5e6a95368d35..4cea20520ca7 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -197,11 +197,11 @@ int orc_dump(const char *_objname)
printf(" sp:");
- print_reg(orc[i].sp_reg, orc[i].sp_offset);
+ print_reg(orc[i].sp_reg, (s16)le16_to_cpu(orc[i].sp_offset));
printf(" bp:");
- print_reg(orc[i].bp_reg, orc[i].bp_offset);
+ print_reg(orc[i].bp_reg, (s16)le16_to_cpu(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 235663b96adc..123fd718ea9a 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -96,6 +96,8 @@ 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 = cpu_to_le16(orc->sp_offset);
+ orc->bp_offset = cpu_to_le16(orc->bp_offset);
/* populate reloc for ip */
reloc = malloc(sizeof(*reloc));
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
From: Martin Schwidefsky <[email protected]>
Currently relocations generated in elf_rebuild_rel_reloc_section/
elf_rebuild_rela_reloc_section functions are broken if the objtool is
built and run on big endian system. E.g. the following errors pop up
during x86 cross compilation:
x86_64-9.1.0-ld: fs/efivarfs/inode.o: bad reloc symbol index (0x2000000 >=
0x22) for offset 0 in section `.orc_unwind_ip'
x86_64-9.1.0-ld: final link failed: bad value
To address that convert those functions to do things similar to
elf_write_reloc(), reuse gelf_update_rel/gelf_update_rela libelf library
functions.
Signed-off-by: Martin Schwidefsky <[email protected]>
Co-developed-by: Vasily Gorbik <[email protected]>
Signed-off-by: Vasily Gorbik <[email protected]>
---
tools/objtool/elf.c | 34 +++++++++++++++++++---------------
1 file changed, 19 insertions(+), 15 deletions(-)
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 4e1d7460574b..5c0341b0cde3 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -829,25 +829,27 @@ static int elf_rebuild_rel_reloc_section(struct section *sec, int nr)
{
struct reloc *reloc;
int idx = 0, size;
- GElf_Rel *relocs;
+ void *buf;
/* Allocate a buffer for relocations */
- size = nr * sizeof(*relocs);
- relocs = malloc(size);
- if (!relocs) {
+ size = nr * sizeof(GElf_Rel);
+ buf = malloc(size);
+ if (!buf) {
perror("malloc");
return -1;
}
- sec->data->d_buf = relocs;
+ sec->data->d_buf = buf;
sec->data->d_size = size;
+ sec->data->d_type = ELF_T_REL;
sec->sh.sh_size = size;
idx = 0;
list_for_each_entry(reloc, &sec->reloc_list, list) {
- relocs[idx].r_offset = reloc->offset;
- relocs[idx].r_info = GELF_R_INFO(reloc->sym->idx, reloc->type);
+ reloc->rel.r_offset = reloc->offset;
+ reloc->rel.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type);
+ gelf_update_rel(sec->data, idx, &reloc->rel);
idx++;
}
@@ -858,26 +860,28 @@ static int elf_rebuild_rela_reloc_section(struct section *sec, int nr)
{
struct reloc *reloc;
int idx = 0, size;
- GElf_Rela *relocs;
+ void *buf;
/* Allocate a buffer for relocations with addends */
- size = nr * sizeof(*relocs);
- relocs = malloc(size);
- if (!relocs) {
+ size = nr * sizeof(GElf_Rela);
+ buf = malloc(size);
+ if (!buf) {
perror("malloc");
return -1;
}
- sec->data->d_buf = relocs;
+ sec->data->d_buf = buf;
sec->data->d_size = size;
+ sec->data->d_type = ELF_T_RELA;
sec->sh.sh_size = size;
idx = 0;
list_for_each_entry(reloc, &sec->reloc_list, list) {
- relocs[idx].r_offset = reloc->offset;
- relocs[idx].r_addend = reloc->addend;
- relocs[idx].r_info = GELF_R_INFO(reloc->sym->idx, reloc->type);
+ reloc->rela.r_offset = reloc->offset;
+ reloc->rela.r_addend = reloc->addend;
+ reloc->rela.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type);
+ gelf_update_rela(sec->data, idx, &reloc->rela);
idx++;
}
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
Currently BUILD_BUG() macro is expanded to smth like the following:
do {
extern void __compiletime_assert_0(void)
__attribute__((error("BUILD_BUG failed")));
if (!(!(1)))
__compiletime_assert_0();
} while (0);
If used in a function body this obviously would produce build errors
with -Wnested-externs and -Werror.
Build objtool with -Wno-nested-externs to enable BUILD_BUG() usage.
Signed-off-by: Vasily Gorbik <[email protected]>
---
tools/objtool/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 33d1e3ca8efd..4ea9a833dde7 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -37,7 +37,7 @@ INCLUDES := -I$(srctree)/tools/include \
-I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
-I$(srctree)/tools/arch/$(SRCARCH)/include \
-I$(srctree)/tools/objtool/arch/$(SRCARCH)/include
-WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
+WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed -Wno-nested-externs
CFLAGS := -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS)
LDFLAGS += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
On Thu, Oct 01, 2020 at 12:17:25AM +0200, Vasily Gorbik wrote:
> From: Martin Schwidefsky <[email protected]>
>
> 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 of the objtool usable on big endian machines.
>
> Signed-off-by: Martin Schwidefsky <[email protected]>
> Co-developed-by: Vasily Gorbik <[email protected]>
> Signed-off-by: Vasily Gorbik <[email protected]>
Since this changes the decoder (which is shared with the kernel), please
prefix the subject with "x86/insn:" instead of "objtool".
This patch is a bit ugly, but I don't necessarily have a better idea.
Masami?
--
Josh
On Thu, Oct 01, 2020 at 12:17:32AM +0200, Vasily Gorbik wrote:
> +++ b/tools/objtool/arch/x86/special.c
> @@ -9,7 +9,7 @@
>
> void arch_handle_alternative(unsigned short feature, struct special_alt *alt)
> {
> - switch (feature) {
> + switch (le16_to_cpu(feature)) {
It might be cleaner for the endian conversion to be done when the
'feature' value is first read.
feature = *(unsigned short *)(sec->data->d_buf + offset +
entry->feature);
> case X86_FEATURE_SMAP:
> /*
> * If UACCESS validation is enabled; force that alternative;
> diff --git a/tools/objtool/check.c b/tools/objtool/check.c
> index 2df9f769412e..f20a4be2fb22 100644
> --- a/tools/objtool/check.c
> +++ b/tools/objtool/check.c
> @@ -1370,7 +1370,7 @@ 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 = le16_to_cpu(hint->sp_offset);
Since this is common code, we might not always be able to assume the
value is little endian. Could you make a more generic conversion macro
which -- when the target ELF file's endianness doesn't match the host
CPU's -- does a byte swap? For example:
insn->ret_offset = bswap_if_needed(hint->sp_offset);
The macro could detect the type size, and would also know the
host/target endianness, and could swap accordingly. It could then be
called for all such multi-byte reads.
--
Josh
rfc v1 - rfc v2:
- rebased onto tip/objtool/core
- reformatted couple of lines
rfc v2 - rfc v3:
- reused __*_ENDIAN_BITFIELD and dropped unneeded byteswap if __KERNEL__
is defined following David's suggestions,
- re-splitted changes and made x86 instruction decoder a separate patch,
- extra patch to add -Wno-nested-externs build flag to enable BUILD_BUG()
usage,
- added a safer and more readable leXX_to_cpu macro in x86 instruction
decoder,
- simplified includes. Switched to using leXX_to_cpu/cpu_to_leXX in
the objtool and x86 instruction decoder since
<linux/kernel.h> is included in the objtool already.
rfc v3 - rfc v4:
- patch 4: objtool: fix x86 orc generation on big endian cross compiles
- introduced "bswap_if_needed()" macro for multi-byte values
conversion, which are read from / about to be written to a target
native endianness ELF file.
- patch 2: x86/insn: instruction decoder and big endian cross compiles
- changed subject prefix from objtool to x86/insn
- reformated leXX_to_cpu macro make it easier to read
Currently objtool seems to be the only tool from all the build tools
needed for x86 build which breaks x86 cross compilation on big endian
systems.
But besides x86 cross compilation, endianness awareness is also needed
for big endian architectures objtool support in general.
We have working prototype of objtool support and orc unwinder for s390
made originally by Martin Schwidefsky. I'm trying to bring it in shape
again and refactor to share more code with "generic" part.
But first things first. This patch series points to endianness problems
which should be addressed. Recent "other architectures support" patches
currently moved only some problematic parts into x86 arch specific folder.
Besides that even though big endian stuff is only needed for the objtool
arch/x86/lib/insn.c and arch/x86/include/asm/insn.h are shared across
the kernel source and the tools, so changes are applied to both.
Any suggestions how to make patches more acceptable are welcome.
Martin Schwidefsky (2):
x86/insn: instruction decoder and big endian cross compiles
objtool: correct rebuilding of reloc sections
Vasily Gorbik (2):
objtool: allow nested externs to enable BUILD_BUG()
objtool: fix x86 orc generation on big endian cross compiles
arch/x86/include/asm/insn.h | 33 ++++++
arch/x86/include/asm/orc_types.h | 10 ++
arch/x86/lib/insn.c | 101 ++++++++----------
tools/arch/x86/include/asm/insn.h | 33 ++++++
tools/arch/x86/include/asm/orc_types.h | 10 ++
tools/arch/x86/lib/insn.c | 101 ++++++++----------
tools/objtool/Makefile | 2 +-
.../arch/x86/include/arch_endianness.h | 9 ++
tools/objtool/check.c | 5 +-
tools/objtool/elf.c | 34 +++---
tools/objtool/endianness.h | 38 +++++++
tools/objtool/orc_dump.c | 5 +-
tools/objtool/orc_gen.c | 3 +
tools/objtool/special.c | 6 +-
14 files changed, 260 insertions(+), 130 deletions(-)
create mode 100644 tools/objtool/arch/x86/include/arch_endianness.h
create mode 100644 tools/objtool/endianness.h
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
Correct objtool orc generation endianness problems to enable fully
functional x86 cross compiles on big endian hardware.
Introduces 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. To be used for multi-byte values
conversion, which are read from / about to be written to a target native
endianness ELF file.
Signed-off-by: Vasily Gorbik <[email protected]>
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 2df9f769412e..fd892b77e98f 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>
@@ -1370,7 +1371,7 @@ 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;
}
@@ -1382,7 +1383,7 @@ 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 235663b96adc..134d7863093d 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);
}
---
arch/x86/include/asm/orc_types.h | 10 +++++
tools/arch/x86/include/asm/orc_types.h | 10 +++++
.../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
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 2df9f769412e..fd892b77e98f 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>
@@ -1370,7 +1371,7 @@ 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;
}
@@ -1382,7 +1383,7 @@ 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 235663b96adc..134d7863093d 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);
}
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
From: Martin Schwidefsky <[email protected]>
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 <[email protected]>
Co-developed-by: Vasily Gorbik <[email protected]>
Signed-off-by: Vasily Gorbik <[email protected]>
---
arch/x86/include/asm/insn.h | 33 ++++++++++
arch/x86/lib/insn.c | 101 ++++++++++++++----------------
tools/arch/x86/include/asm/insn.h | 33 ++++++++++
tools/arch/x86/lib/insn.c | 101 ++++++++++++++----------------
4 files changed, 160 insertions(+), 108 deletions(-)
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 5c1ae3eff9d4..004e27bdf121 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 @@ void insn_get_prefixes(struct insn *insn)
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/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index 568854b14d0a..b9b6928cb62b 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 @@ void insn_get_prefixes(struct insn *insn)
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;
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
Currently BUILD_BUG() macro is expanded to smth like the following:
do {
extern void __compiletime_assert_0(void)
__attribute__((error("BUILD_BUG failed")));
if (!(!(1)))
__compiletime_assert_0();
} while (0);
If used in a function body this obviously would produce build errors
with -Wnested-externs and -Werror.
Build objtool with -Wno-nested-externs to enable BUILD_BUG() usage.
Signed-off-by: Vasily Gorbik <[email protected]>
---
tools/objtool/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 33d1e3ca8efd..4ea9a833dde7 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -37,7 +37,7 @@ INCLUDES := -I$(srctree)/tools/include \
-I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
-I$(srctree)/tools/arch/$(SRCARCH)/include \
-I$(srctree)/tools/objtool/arch/$(SRCARCH)/include
-WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
+WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed -Wno-nested-externs
CFLAGS := -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS)
LDFLAGS += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
From: Martin Schwidefsky <[email protected]>
Currently relocations generated in elf_rebuild_rel_reloc_section/
elf_rebuild_rela_reloc_section functions are broken if the objtool is
built and run on big endian system. E.g. the following errors pop up
during x86 cross compilation:
x86_64-9.1.0-ld: fs/efivarfs/inode.o: bad reloc symbol index (0x2000000 >=
0x22) for offset 0 in section `.orc_unwind_ip'
x86_64-9.1.0-ld: final link failed: bad value
To address that convert those functions to do things similar to
elf_write_reloc(), reuse gelf_update_rel/gelf_update_rela libelf library
functions.
Signed-off-by: Martin Schwidefsky <[email protected]>
Co-developed-by: Vasily Gorbik <[email protected]>
Signed-off-by: Vasily Gorbik <[email protected]>
---
tools/objtool/elf.c | 34 +++++++++++++++++++---------------
1 file changed, 19 insertions(+), 15 deletions(-)
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 4e1d7460574b..5c0341b0cde3 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -829,25 +829,27 @@ static int elf_rebuild_rel_reloc_section(struct section *sec, int nr)
{
struct reloc *reloc;
int idx = 0, size;
- GElf_Rel *relocs;
+ void *buf;
/* Allocate a buffer for relocations */
- size = nr * sizeof(*relocs);
- relocs = malloc(size);
- if (!relocs) {
+ size = nr * sizeof(GElf_Rel);
+ buf = malloc(size);
+ if (!buf) {
perror("malloc");
return -1;
}
- sec->data->d_buf = relocs;
+ sec->data->d_buf = buf;
sec->data->d_size = size;
+ sec->data->d_type = ELF_T_REL;
sec->sh.sh_size = size;
idx = 0;
list_for_each_entry(reloc, &sec->reloc_list, list) {
- relocs[idx].r_offset = reloc->offset;
- relocs[idx].r_info = GELF_R_INFO(reloc->sym->idx, reloc->type);
+ reloc->rel.r_offset = reloc->offset;
+ reloc->rel.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type);
+ gelf_update_rel(sec->data, idx, &reloc->rel);
idx++;
}
@@ -858,26 +860,28 @@ static int elf_rebuild_rela_reloc_section(struct section *sec, int nr)
{
struct reloc *reloc;
int idx = 0, size;
- GElf_Rela *relocs;
+ void *buf;
/* Allocate a buffer for relocations with addends */
- size = nr * sizeof(*relocs);
- relocs = malloc(size);
- if (!relocs) {
+ size = nr * sizeof(GElf_Rela);
+ buf = malloc(size);
+ if (!buf) {
perror("malloc");
return -1;
}
- sec->data->d_buf = relocs;
+ sec->data->d_buf = buf;
sec->data->d_size = size;
+ sec->data->d_type = ELF_T_RELA;
sec->sh.sh_size = size;
idx = 0;
list_for_each_entry(reloc, &sec->reloc_list, list) {
- relocs[idx].r_offset = reloc->offset;
- relocs[idx].r_addend = reloc->addend;
- relocs[idx].r_info = GELF_R_INFO(reloc->sym->idx, reloc->type);
+ reloc->rela.r_offset = reloc->offset;
+ reloc->rela.r_addend = reloc->addend;
+ reloc->rela.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type);
+ gelf_update_rela(sec->data, idx, &reloc->rela);
idx++;
}
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
On Fri, 2 Oct 2020 10:18:41 -0500
Josh Poimboeuf <[email protected]> wrote:
> On Thu, Oct 01, 2020 at 12:17:25AM +0200, Vasily Gorbik wrote:
> > From: Martin Schwidefsky <[email protected]>
> >
> > 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 of the objtool usable on big endian machines.
> >
> > Signed-off-by: Martin Schwidefsky <[email protected]>
> > Co-developed-by: Vasily Gorbik <[email protected]>
> > Signed-off-by: Vasily Gorbik <[email protected]>
>
> Since this changes the decoder (which is shared with the kernel), please
> prefix the subject with "x86/insn:" instead of "objtool".
Thanks for pointing it.
>
> This patch is a bit ugly, but I don't necessarily have a better idea.
>
> Masami?
Yeah, agreed. Maybe we can split that part in different header, but
that makes it more ugly. And code itself looks good to me.
(I like insn_field_set() idea :) )
Acked-by: Masami Hiramatsu <[email protected]>
Thank you!
> --
> Josh
>
--
Masami Hiramatsu <[email protected]>
On Sun, Oct 04, 2020 at 04:30:54PM +0200, Vasily Gorbik wrote:
> @@ -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);
> }
> ---
> arch/x86/include/asm/orc_types.h | 10 +++++
> tools/arch/x86/include/asm/orc_types.h | 10 +++++
> .../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
>
> diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
> index fdbffec4cfde..5a2baf28a1dc 100644
This patch is misformatted. Almost like it was concatenated with
itself?
--
Josh
Sorry for the extra noise. Patches has been resent because one of them
has been corrupted. That's what you get for post-editing mailbox in vim,
few wrong extra strokes and your wife wants to divorce you because you
just copied and pretty-formatted her threatening message to your internet
service provider from another buffer.
rfc v1 - rfc v2:
- rebased onto tip/objtool/core
- reformatted couple of lines
rfc v2 - rfc v3:
- reused __*_ENDIAN_BITFIELD and dropped unneeded byteswap if __KERNEL__
is defined following David's suggestions,
- re-splitted changes and made x86 instruction decoder a separate patch,
- extra patch to add -Wno-nested-externs build flag to enable BUILD_BUG()
usage,
- added a safer and more readable leXX_to_cpu macro in x86 instruction
decoder,
- simplified includes. Switched to using leXX_to_cpu/cpu_to_leXX in
the objtool and x86 instruction decoder since
<linux/kernel.h> is included in the objtool already.
rfc v3 - rfc v4:
- patch 4: objtool: fix x86 orc generation on big endian cross compiles
- introduced "bswap_if_needed()" macro for multi-byte values
conversion, which are read from / about to be written to a target
native endianness ELF file.
- patch 2: x86/insn: instruction decoder and big endian cross compiles
- changed subject prefix from objtool to x86/insn
- reformated leXX_to_cpu macro make it easier to read
Currently objtool seems to be the only tool from all the build tools
needed for x86 build which breaks x86 cross compilation on big endian
systems.
But besides x86 cross compilation, endianness awareness is also needed
for big endian architectures objtool support in general.
We have working prototype of objtool support and orc unwinder for s390
made originally by Martin Schwidefsky. I'm trying to bring it in shape
again and refactor to share more code with "generic" part.
But first things first. This patch series points to endianness problems
which should be addressed. Recent "other architectures support" patches
currently moved only some problematic parts into x86 arch specific folder.
Besides that even though big endian stuff is only needed for the objtool
arch/x86/lib/insn.c and arch/x86/include/asm/insn.h are shared across
the kernel source and the tools, so changes are applied to both.
Any suggestions how to make patches more acceptable are welcome.
Martin Schwidefsky (2):
x86/insn: instruction decoder and big endian cross compiles
objtool: correct rebuilding of reloc sections
Vasily Gorbik (2):
objtool: allow nested externs to enable BUILD_BUG()
objtool: fix x86 orc generation on big endian cross compiles
arch/x86/include/asm/insn.h | 33 ++++++
arch/x86/include/asm/orc_types.h | 10 ++
arch/x86/lib/insn.c | 101 ++++++++----------
tools/arch/x86/include/asm/insn.h | 33 ++++++
tools/arch/x86/include/asm/orc_types.h | 10 ++
tools/arch/x86/lib/insn.c | 101 ++++++++----------
tools/objtool/Makefile | 2 +-
.../arch/x86/include/arch_endianness.h | 9 ++
tools/objtool/check.c | 5 +-
tools/objtool/elf.c | 34 +++---
tools/objtool/endianness.h | 38 +++++++
tools/objtool/orc_dump.c | 5 +-
tools/objtool/orc_gen.c | 3 +
tools/objtool/special.c | 6 +-
14 files changed, 260 insertions(+), 130 deletions(-)
create mode 100644 tools/objtool/arch/x86/include/arch_endianness.h
create mode 100644 tools/objtool/endianness.h
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
Currently BUILD_BUG() macro is expanded to smth like the following:
do {
extern void __compiletime_assert_0(void)
__attribute__((error("BUILD_BUG failed")));
if (!(!(1)))
__compiletime_assert_0();
} while (0);
If used in a function body this obviously would produce build errors
with -Wnested-externs and -Werror.
Build objtool with -Wno-nested-externs to enable BUILD_BUG() usage.
Signed-off-by: Vasily Gorbik <[email protected]>
---
tools/objtool/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 33d1e3ca8efd..4ea9a833dde7 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -37,7 +37,7 @@ INCLUDES := -I$(srctree)/tools/include \
-I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
-I$(srctree)/tools/arch/$(SRCARCH)/include \
-I$(srctree)/tools/objtool/arch/$(SRCARCH)/include
-WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
+WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed -Wno-nested-externs
CFLAGS := -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS)
LDFLAGS += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
From: Martin Schwidefsky <[email protected]>
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 <[email protected]>
Co-developed-by: Vasily Gorbik <[email protected]>
Signed-off-by: Vasily Gorbik <[email protected]>
---
arch/x86/include/asm/insn.h | 33 ++++++++++
arch/x86/lib/insn.c | 101 ++++++++++++++----------------
tools/arch/x86/include/asm/insn.h | 33 ++++++++++
tools/arch/x86/lib/insn.c | 101 ++++++++++++++----------------
4 files changed, 160 insertions(+), 108 deletions(-)
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 5c1ae3eff9d4..004e27bdf121 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 @@ void insn_get_prefixes(struct insn *insn)
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/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index 568854b14d0a..b9b6928cb62b 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 @@ void insn_get_prefixes(struct insn *insn)
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;
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
From: Martin Schwidefsky <[email protected]>
Currently relocations generated in elf_rebuild_rel_reloc_section/
elf_rebuild_rela_reloc_section functions are broken if the objtool is
built and run on big endian system. E.g. the following errors pop up
during x86 cross compilation:
x86_64-9.1.0-ld: fs/efivarfs/inode.o: bad reloc symbol index (0x2000000 >=
0x22) for offset 0 in section `.orc_unwind_ip'
x86_64-9.1.0-ld: final link failed: bad value
To address that convert those functions to do things similar to
elf_write_reloc(), reuse gelf_update_rel/gelf_update_rela libelf library
functions.
Signed-off-by: Martin Schwidefsky <[email protected]>
Co-developed-by: Vasily Gorbik <[email protected]>
Signed-off-by: Vasily Gorbik <[email protected]>
---
tools/objtool/elf.c | 34 +++++++++++++++++++---------------
1 file changed, 19 insertions(+), 15 deletions(-)
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 4e1d7460574b..5c0341b0cde3 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -829,25 +829,27 @@ static int elf_rebuild_rel_reloc_section(struct section *sec, int nr)
{
struct reloc *reloc;
int idx = 0, size;
- GElf_Rel *relocs;
+ void *buf;
/* Allocate a buffer for relocations */
- size = nr * sizeof(*relocs);
- relocs = malloc(size);
- if (!relocs) {
+ size = nr * sizeof(GElf_Rel);
+ buf = malloc(size);
+ if (!buf) {
perror("malloc");
return -1;
}
- sec->data->d_buf = relocs;
+ sec->data->d_buf = buf;
sec->data->d_size = size;
+ sec->data->d_type = ELF_T_REL;
sec->sh.sh_size = size;
idx = 0;
list_for_each_entry(reloc, &sec->reloc_list, list) {
- relocs[idx].r_offset = reloc->offset;
- relocs[idx].r_info = GELF_R_INFO(reloc->sym->idx, reloc->type);
+ reloc->rel.r_offset = reloc->offset;
+ reloc->rel.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type);
+ gelf_update_rel(sec->data, idx, &reloc->rel);
idx++;
}
@@ -858,26 +860,28 @@ static int elf_rebuild_rela_reloc_section(struct section *sec, int nr)
{
struct reloc *reloc;
int idx = 0, size;
- GElf_Rela *relocs;
+ void *buf;
/* Allocate a buffer for relocations with addends */
- size = nr * sizeof(*relocs);
- relocs = malloc(size);
- if (!relocs) {
+ size = nr * sizeof(GElf_Rela);
+ buf = malloc(size);
+ if (!buf) {
perror("malloc");
return -1;
}
- sec->data->d_buf = relocs;
+ sec->data->d_buf = buf;
sec->data->d_size = size;
+ sec->data->d_type = ELF_T_RELA;
sec->sh.sh_size = size;
idx = 0;
list_for_each_entry(reloc, &sec->reloc_list, list) {
- relocs[idx].r_offset = reloc->offset;
- relocs[idx].r_addend = reloc->addend;
- relocs[idx].r_info = GELF_R_INFO(reloc->sym->idx, reloc->type);
+ reloc->rela.r_offset = reloc->offset;
+ reloc->rela.r_addend = reloc->addend;
+ reloc->rela.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type);
+ gelf_update_rela(sec->data, idx, &reloc->rela);
idx++;
}
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
On Mon, Oct 05, 2020 at 09:03:28AM -0500, Josh Poimboeuf wrote:
> On Sun, Oct 04, 2020 at 04:30:54PM +0200, Vasily Gorbik wrote:
> > @@ -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);
> > }
> > ---
> > arch/x86/include/asm/orc_types.h | 10 +++++
> > tools/arch/x86/include/asm/orc_types.h | 10 +++++
> > .../arch/x86/include/arch_endianness.h | 9 +++++
>
> This patch is misformatted. Almost like it was concatenated with
> itself?
Indeed. I wonder how that could have happened. Sorry for that. I've
resent patches with rebased patch
"objtool: avoid ../ headers includes and name clashes"
on top. This time I checked patches could be applied from outgoing
mailbox before sending it.