This is based on v5.9-rc7, before "other architectures support" patches
starting pouring in.
Currently objtool seems to be the only tool from build tools needed
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. These 2 patches point to endianness problems
which should be addressed. And I'd be glad to get any ideas how to make
them less ugly.
New "other architectures support" patches currently move only some
problematic parts into x86 arch specific folder. But the main problem
is that arch/x86/lib/insn.c and arch/x86/include/asm/insn.h are shared
across the kernel source and the tools, and there is no common way to
address endianness problems.
Since big endian stuff is only needed for the objtool and not for the
kernel I can try to hide alternative big endian definitions in tools
only header which is included only if __KERNEL__ is not defined. But
that kind of defeats the idea of sharing those files 1 to 1 with tools.
Thoughts? Any suggestions are welcome.
Martin Schwidefsky (1):
objtool: x86 instruction decoder and big endian cross compiles
Vasily Gorbik (1):
objtool: fix x86 orc generation on big endian cross compiles
arch/x86/include/asm/insn.h | 43 ++++++++++++
arch/x86/include/asm/orc_types.h | 24 +++++++
arch/x86/lib/insn.c | 95 +++++++++++---------------
tools/arch/x86/include/asm/insn.h | 43 ++++++++++++
tools/arch/x86/include/asm/orc_types.h | 24 +++++++
tools/arch/x86/lib/insn.c | 95 +++++++++++---------------
tools/objtool/check.c | 4 +-
tools/objtool/elf.c | 34 +++++----
tools/objtool/orc_dump.c | 4 +-
tools/objtool/orc_gen.c | 2 +
tools/objtool/special.c | 4 +-
11 files changed, 243 insertions(+), 129 deletions(-)
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
From: Martin Schwidefsky <[email protected]>
Make the x86 instruction decoder of the objtool usable on big endian
machines. This is useful for compile tests on non x86, big endian
hardware.
Co-developed-by: Vasily Gorbik <[email protected]>
[ gor: more endianness problems findings fixes / rebasing ]
Signed-off-by: Martin Schwidefsky <[email protected]>
Signed-off-by: Vasily Gorbik <[email protected]>
---
arch/x86/include/asm/insn.h | 43 ++++++++++++++
arch/x86/lib/insn.c | 95 +++++++++++++------------------
tools/arch/x86/include/asm/insn.h | 43 ++++++++++++++
tools/arch/x86/lib/insn.c | 95 +++++++++++++------------------
tools/objtool/check.c | 4 +-
tools/objtool/elf.c | 34 ++++++-----
tools/objtool/special.c | 4 +-
7 files changed, 191 insertions(+), 127 deletions(-)
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 5c1ae3eff9d4..8d9864b09552 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -8,8 +8,17 @@
*/
/* insn_attr_t is defined in inat.h */
+#ifdef __KERNEL__
+#include <linux/swab.h>
+#include <asm/byteorder.h>
+#else
+#include <endian.h>
+#endif
#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 +29,40 @@ 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;
+#ifdef __KERNEL__
+ p->little = __swap32(v);
+#else
+ 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..9150bdc8a6d6 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -15,15 +15,23 @@
#include <asm/emulate_prefix.h>
+#ifdef __KERNEL__
+#define letoh(t, r) \
+ ((sizeof(t) == 4) ? le32_to_cpu(r) : (sizeof(t) == 2) ? le16_to_cpu(r) : r)
+#else
+#define letoh(t, r) \
+ ((sizeof(t) == 4) ? le32toh(r) : (sizeof(t) == 2) ? le16toh(r) : r)
+#endif
+
/* 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); letoh(t, r); })
#define __peek_nbyte_next(t, insn, n) \
- ({ t r = *(t*)((insn)->next_byte + n); r; })
+ ({ t r = *(t*)((insn)->next_byte + n); letoh(t, r); })
#define get_next(t, insn) \
({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
@@ -157,8 +165,7 @@ 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 +302,7 @@ 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 +340,7 @@ 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 +359,11 @@ 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 +413,18 @@ 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 +440,14 @@ 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 +465,11 @@ 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 +486,15 @@ 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 +511,10 @@ 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 +522,7 @@ 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 +558,17 @@ 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 +587,7 @@ 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..cb794102dff2 100644
--- a/tools/arch/x86/include/asm/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
@@ -8,8 +8,17 @@
*/
/* insn_attr_t is defined in inat.h */
+#ifdef __KERNEL__
+#include <linux/swab.h>
+#include <asm/byteorder.h>
+#else
+#include <endian.h>
+#endif
#include "inat.h"
+#if defined(__BYTE_ORDER) ? \
+ __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+
struct insn_field {
union {
insn_value_t value;
@@ -20,6 +29,40 @@ 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;
+#ifdef __KERNEL__
+ p->little = __swap32(v);
+#else
+ 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..b4a41e2c7c8b 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -15,15 +15,23 @@
#include "../include/asm/emulate_prefix.h"
+#ifdef __KERNEL__
+#define letoh(t, r) \
+ ((sizeof(t) == 4) ? le32_to_cpu(r) : (sizeof(t) == 2) ? le16_to_cpu(r) : r)
+#else
+#define letoh(t, r) \
+ ((sizeof(t) == 4) ? le32toh(r) : (sizeof(t) == 2) ? le16toh(r) : r)
+#endif
+
/* 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); letoh(t, r); })
#define __peek_nbyte_next(t, insn, n) \
- ({ t r = *(t*)((insn)->next_byte + n); r; })
+ ({ t r = *(t*)((insn)->next_byte + n); letoh(t, r); })
#define get_next(t, insn) \
({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
@@ -157,8 +165,7 @@ 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 +302,7 @@ 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 +340,7 @@ 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 +359,11 @@ 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 +413,18 @@ 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 +440,14 @@ 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 +465,11 @@ 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 +486,15 @@ 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 +511,10 @@ 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 +522,7 @@ 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 +558,17 @@ 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 +587,7 @@ 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/objtool/check.c b/tools/objtool/check.c
index 90a66891441a..010a8296e381 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1344,7 +1344,7 @@ 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 = le16toh(hint->sp_offset);
continue;
}
@@ -1381,7 +1381,7 @@ static int read_unwind_hints(struct objtool_file *file)
return -1;
}
- cfa->offset = hint->sp_offset;
+ cfa->offset = le16toh(hint->sp_offset);
insn->cfi.type = hint->type;
insn->cfi.end = hint->end;
}
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 3ddbd66f1a37..6e77735a7505 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++;
}
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index e893f1e48e44..230f14f766b4 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -90,8 +90,8 @@ 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 = le16toh(*(unsigned short *)(sec->data->d_buf +
+ offset + entry->feature));
/*
* It has been requested that we don't validate the !POPCNT
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
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 | 24 ++++++++++++++++++++++++
tools/arch/x86/include/asm/orc_types.h | 24 ++++++++++++++++++++++++
tools/objtool/orc_dump.c | 4 ++--
tools/objtool/orc_gen.c | 2 ++
4 files changed, 52 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index d25534940bde..931f99b70af3 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -61,6 +61,13 @@
#define UNWIND_HINT_TYPE_RET_OFFSET 3
#ifndef __ASSEMBLY__
+#ifdef __KERNEL__
+#include <linux/swab.h>
+#include <asm/byteorder.h>
+#else
+#include <endian.h>
+#endif
+
/*
* 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
@@ -69,6 +76,9 @@
* the stack for a given code address. Each instance of the struct corresponds
* to one or more code locations.
*/
+#if defined(__BYTE_ORDER) ? \
+ __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+
struct orc_entry {
s16 sp_offset;
s16 bp_offset;
@@ -78,6 +88,20 @@ struct orc_entry {
unsigned end:1;
} __packed;
+#else
+
+struct orc_entry {
+ s16 sp_offset;
+ s16 bp_offset;
+ unsigned bp_reg:4;
+ unsigned sp_reg:4;
+ unsigned unused:5;
+ unsigned end:1;
+ unsigned type:2;
+} __packed;
+
+#endif
+
/*
* This struct is used by asm and inline asm code to manually annotate the
* location of registers on the stack for the ORC unwinder.
diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h
index d25534940bde..931f99b70af3 100644
--- a/tools/arch/x86/include/asm/orc_types.h
+++ b/tools/arch/x86/include/asm/orc_types.h
@@ -61,6 +61,13 @@
#define UNWIND_HINT_TYPE_RET_OFFSET 3
#ifndef __ASSEMBLY__
+#ifdef __KERNEL__
+#include <linux/swab.h>
+#include <asm/byteorder.h>
+#else
+#include <endian.h>
+#endif
+
/*
* 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
@@ -69,6 +76,9 @@
* the stack for a given code address. Each instance of the struct corresponds
* to one or more code locations.
*/
+#if defined(__BYTE_ORDER) ? \
+ __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+
struct orc_entry {
s16 sp_offset;
s16 bp_offset;
@@ -78,6 +88,20 @@ struct orc_entry {
unsigned end:1;
} __packed;
+#else
+
+struct orc_entry {
+ s16 sp_offset;
+ s16 bp_offset;
+ unsigned bp_reg:4;
+ unsigned sp_reg:4;
+ unsigned unused:5;
+ unsigned end:1;
+ unsigned type:2;
+} __packed;
+
+#endif
+
/*
* This struct is used by asm and inline asm code to manually annotate the
* location of registers on the stack for the ORC unwinder.
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index fca46e006fc2..0fbf8521c891 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -196,11 +196,11 @@ 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)le16toh(orc[i].sp_offset));
printf(" bp:");
- print_reg(orc[i].bp_reg, orc[i].bp_offset);
+ print_reg(orc[i].bp_reg, (s16)le16toh(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 968f55e6dd94..b3978fad93e6 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -90,6 +90,8 @@ 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 = htole16(orc->sp_offset);
+ orc->bp_offset = htole16(orc->bp_offset);
/* populate reloc for ip */
reloc = malloc(sizeof(*reloc));
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
On Wed, Sep 30, 2020 at 11:58:24AM +0200, Vasily Gorbik wrote:
> This is based on v5.9-rc7, before "other architectures support" patches
> starting pouring in.
Please base on: tip/objtool/core, as is they no longer apply.
rfc v1 - rfc v2:
- rebased onto tip/objtool/core
- reformatted couple of lines
Currently objtool seems to be the only tool from build tools needed
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. These 2 patches point to endianness problems
which should be addressed. And I'd be glad to get any ideas how to make
them less ugly.
New "other architectures support" patches currently move only some
problematic parts into x86 arch specific folder. But the main problem
is that arch/x86/lib/insn.c and arch/x86/include/asm/insn.h are shared
across the kernel source and the tools, and there is no common way to
address endianness problems.
Since big endian stuff is only needed for the objtool and not for the
kernel I can try to hide alternative big endian definitions in tools
only header which is included only if __KERNEL__ is not defined. But
that kind of defeats the idea of sharing those files 1 to 1 with tools.
Thoughts? Any suggestions are welcome.
Martin Schwidefsky (1):
objtool: x86 instruction decoder and big endian cross compiles
Vasily Gorbik (1):
objtool: fix x86 orc generation on big endian cross compiles
arch/x86/include/asm/insn.h | 42 ++++++++++++
arch/x86/include/asm/orc_types.h | 24 +++++++
arch/x86/lib/insn.c | 95 +++++++++++---------------
tools/arch/x86/include/asm/insn.h | 42 ++++++++++++
tools/arch/x86/include/asm/orc_types.h | 24 +++++++
tools/arch/x86/lib/insn.c | 95 +++++++++++---------------
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 +
11 files changed, 240 insertions(+), 128 deletions(-)
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
From: Martin Schwidefsky <[email protected]>
Make the x86 instruction decoder of the objtool usable on big endian
machines. This is useful for compile tests on non x86, big endian
hardware.
Co-developed-by: Vasily Gorbik <[email protected]>
[ gor: more endianness problems findings fixes / rebasing ]
Signed-off-by: Martin Schwidefsky <[email protected]>
Signed-off-by: Vasily Gorbik <[email protected]>
---
arch/x86/include/asm/insn.h | 42 ++++++++++++++
arch/x86/lib/insn.c | 95 +++++++++++++------------------
tools/arch/x86/include/asm/insn.h | 42 ++++++++++++++
tools/arch/x86/lib/insn.c | 95 +++++++++++++------------------
tools/objtool/arch/x86/special.c | 2 +-
tools/objtool/check.c | 4 +-
tools/objtool/elf.c | 34 ++++++-----
7 files changed, 188 insertions(+), 126 deletions(-)
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 5c1ae3eff9d4..e5a2bcc41ac4 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -8,8 +8,16 @@
*/
/* insn_attr_t is defined in inat.h */
+#ifdef __KERNEL__
+#include <linux/swab.h>
+#include <asm/byteorder.h>
+#else
+#include <endian.h>
+#endif
#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 +28,40 @@ 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;
+#ifdef __KERNEL__
+ p->little = __swap32(v);
+#else
+ 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..9150bdc8a6d6 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -15,15 +15,23 @@
#include <asm/emulate_prefix.h>
+#ifdef __KERNEL__
+#define letoh(t, r) \
+ ((sizeof(t) == 4) ? le32_to_cpu(r) : (sizeof(t) == 2) ? le16_to_cpu(r) : r)
+#else
+#define letoh(t, r) \
+ ((sizeof(t) == 4) ? le32toh(r) : (sizeof(t) == 2) ? le16toh(r) : r)
+#endif
+
/* 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); letoh(t, r); })
#define __peek_nbyte_next(t, insn, n) \
- ({ t r = *(t*)((insn)->next_byte + n); r; })
+ ({ t r = *(t*)((insn)->next_byte + n); letoh(t, r); })
#define get_next(t, insn) \
({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
@@ -157,8 +165,7 @@ 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 +302,7 @@ 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 +340,7 @@ 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 +359,11 @@ 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 +413,18 @@ 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 +440,14 @@ 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 +465,11 @@ 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 +486,15 @@ 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 +511,10 @@ 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 +522,7 @@ 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 +558,17 @@ 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 +587,7 @@ 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..85de3ad97699 100644
--- a/tools/arch/x86/include/asm/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
@@ -8,8 +8,16 @@
*/
/* insn_attr_t is defined in inat.h */
+#ifdef __KERNEL__
+#include <linux/swab.h>
+#include <asm/byteorder.h>
+#else
+#include <endian.h>
+#endif
#include "inat.h"
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+
struct insn_field {
union {
insn_value_t value;
@@ -20,6 +28,40 @@ 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;
+#ifdef __KERNEL__
+ p->little = __swap32(v);
+#else
+ 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..b4a41e2c7c8b 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -15,15 +15,23 @@
#include "../include/asm/emulate_prefix.h"
+#ifdef __KERNEL__
+#define letoh(t, r) \
+ ((sizeof(t) == 4) ? le32_to_cpu(r) : (sizeof(t) == 2) ? le16_to_cpu(r) : r)
+#else
+#define letoh(t, r) \
+ ((sizeof(t) == 4) ? le32toh(r) : (sizeof(t) == 2) ? le16toh(r) : r)
+#endif
+
/* 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); letoh(t, r); })
#define __peek_nbyte_next(t, insn, n) \
- ({ t r = *(t*)((insn)->next_byte + n); r; })
+ ({ t r = *(t*)((insn)->next_byte + n); letoh(t, r); })
#define get_next(t, insn) \
({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
@@ -157,8 +165,7 @@ 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 +302,7 @@ 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 +340,7 @@ 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 +359,11 @@ 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 +413,18 @@ 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 +440,14 @@ 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 +465,11 @@ 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 +486,15 @@ 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 +511,10 @@ 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 +522,7 @@ 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 +558,17 @@ 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 +587,7 @@ 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/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c
index fd4af88c0ea5..287ddf6d8a9e 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 (le16toh(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..6f2574bf0008 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 = le16toh(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 = le16toh(hint->sp_offset);
insn->cfi.type = hint->type;
insn->cfi.end = hint->end;
}
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++;
}
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
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 | 24 ++++++++++++++++++++++++
tools/arch/x86/include/asm/orc_types.h | 24 ++++++++++++++++++++++++
tools/objtool/orc_dump.c | 4 ++--
tools/objtool/orc_gen.c | 2 ++
4 files changed, 52 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index fdbffec4cfde..c72bee8e6ec0 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -40,6 +40,13 @@
#define ORC_REG_MAX 15
#ifndef __ASSEMBLY__
+#ifdef __KERNEL__
+#include <linux/swab.h>
+#include <asm/byteorder.h>
+#else
+#include <endian.h>
+#endif
+
/*
* 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
@@ -48,6 +55,9 @@
* the stack for a given code address. Each instance of the struct corresponds
* to one or more code locations.
*/
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+
struct orc_entry {
s16 sp_offset;
s16 bp_offset;
@@ -57,6 +67,20 @@ struct orc_entry {
unsigned end:1;
} __packed;
+#else
+
+struct orc_entry {
+ s16 sp_offset;
+ s16 bp_offset;
+ unsigned bp_reg:4;
+ unsigned sp_reg:4;
+ unsigned unused:5;
+ unsigned end:1;
+ unsigned type:2;
+} __packed;
+
+#endif
+
#endif /* __ASSEMBLY__ */
#endif /* _ORC_TYPES_H */
diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h
index fdbffec4cfde..c72bee8e6ec0 100644
--- a/tools/arch/x86/include/asm/orc_types.h
+++ b/tools/arch/x86/include/asm/orc_types.h
@@ -40,6 +40,13 @@
#define ORC_REG_MAX 15
#ifndef __ASSEMBLY__
+#ifdef __KERNEL__
+#include <linux/swab.h>
+#include <asm/byteorder.h>
+#else
+#include <endian.h>
+#endif
+
/*
* 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
@@ -48,6 +55,9 @@
* the stack for a given code address. Each instance of the struct corresponds
* to one or more code locations.
*/
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+
struct orc_entry {
s16 sp_offset;
s16 bp_offset;
@@ -57,6 +67,20 @@ struct orc_entry {
unsigned end:1;
} __packed;
+#else
+
+struct orc_entry {
+ s16 sp_offset;
+ s16 bp_offset;
+ unsigned bp_reg:4;
+ unsigned sp_reg:4;
+ unsigned unused:5;
+ unsigned end:1;
+ unsigned type:2;
+} __packed;
+
+#endif
+
#endif /* __ASSEMBLY__ */
#endif /* _ORC_TYPES_H */
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index 5e6a95368d35..19fa6f65040e 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)le16toh(orc[i].sp_offset));
printf(" bp:");
- print_reg(orc[i].bp_reg, orc[i].bp_offset);
+ print_reg(orc[i].bp_reg, (s16)le16toh(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..ab9cff93fabd 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 = htole16(orc->sp_offset);
+ orc->bp_offset = htole16(orc->bp_offset);
/* populate reloc for ip */
reloc = malloc(sizeof(*reloc));
--
⣿⣿⣿⣿⢋⡀⣀⠹⣿⣿⣿⣿
⣿⣿⣿⣿⠠⣶⡦⠀⣿⣿⣿⣿
⣿⣿⣿⠏⣴⣮⣴⣧⠈⢿⣿⣿
⣿⣿⡏⢰⣿⠖⣠⣿⡆⠈⣿⣿
⣿⢛⣵⣄⠙⣶⣶⡟⣅⣠⠹⣿
⣿⣜⣛⠻⢎⣉⣉⣀⠿⣫⣵⣿
From: Vasily Gorbik
> Sent: 30 September 2020 13:24
>
> Correct objtool orc generation endianness problems to enable fully
> functional x86 cross compiles on big endian hardware.
>
...
> +
> +#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
> +
> struct orc_entry {
> s16 sp_offset;
> s16 bp_offset;
> @@ -57,6 +67,20 @@ struct orc_entry {
> unsigned end:1;
> } __packed;
>
> +#else
> +
> +struct orc_entry {
> + s16 sp_offset;
> + s16 bp_offset;
> + unsigned bp_reg:4;
> + unsigned sp_reg:4;
> + unsigned unused:5;
> + unsigned end:1;
> + unsigned type:2;
> +} __packed;
> +
> +#endif
Shouldn't that be checking BITFIELD_ENDIAN.
I also think that (in the other patch) you can assume
that you don't need to byteswap if __KERNEL__ is defined.
David
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
On Wed, Sep 30, 2020 at 02:24:19PM +0200, Vasily Gorbik wrote:
> From: Martin Schwidefsky <[email protected]>
>
> Make the x86 instruction decoder of the objtool usable on big endian
> machines. This is useful for compile tests on non x86, big endian
> hardware.
>
> Co-developed-by: Vasily Gorbik <[email protected]>
> [ gor: more endianness problems findings fixes / rebasing ]
> Signed-off-by: Martin Schwidefsky <[email protected]>
> Signed-off-by: Vasily Gorbik <[email protected]>
> ---
> arch/x86/include/asm/insn.h | 42 ++++++++++++++
> arch/x86/lib/insn.c | 95 +++++++++++++------------------
> tools/arch/x86/include/asm/insn.h | 42 ++++++++++++++
> tools/arch/x86/lib/insn.c | 95 +++++++++++++------------------
> tools/objtool/arch/x86/special.c | 2 +-
> tools/objtool/check.c | 4 +-
> tools/objtool/elf.c | 34 ++++++-----
> 7 files changed, 188 insertions(+), 126 deletions(-)
Can the insn changes be done in a separate patch from the objtool
changes?
Also, 'Masami Hiramatsu <[email protected]>' should be on Cc for the
insn changes since he wrote the original code.
--
Josh