Re: [RFC PATCH v3 4/4] objtool: fix x86 orc generation on big endian cross compiles

[Josh Poimboeuf]

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 = >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 PATCH v3 4/4] objtool: fix x86 orc generation on big endian cross compiles

[Vasily Gorbik]

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

Signed-off-by: Vasily Gorbik 
---
 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_MAX15
 
 #ifndef __ASSEMBLY__
+#include 
+
 /*
  * 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)
unsignedsp_reg:4;
unsignedbp_reg:4;
unsignedtype:2;
unsignedend:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+   unsignedbp_reg:4;
+   unsignedsp_reg:4;
+   unsignedunused:5;
+   unsignedend:1;
+   unsignedtype: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_MAX15
 
 #ifndef __ASSEMBLY__
+#include 
+
 /*
  * 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)
unsignedsp_reg:4;
unsignedbp_reg:4;
unsignedtype:2;
unsignedend:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+   unsignedbp_reg:4;
+   unsignedsp_reg:4;
+   unsignedunused:5;
+   unsignedend:1;
+   unsignedtype: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 = >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 =