On Mon, May 18, 2020 at 5:15 PM Nick Desaulniers
<ndesaulni...@google.com> wrote:
>
> On Sun, May 17, 2020 at 8:29 AM Brian Gerst <brge...@gmail.com> wrote:
> >
> > The core percpu macros already have a switch on the data size, so the switch
> > in the x86 code is redundant and produces more dead code.
> >
> > Also use appropriate types for the width of the instructions. This avoids
> > errors when compiling with Clang.
> >
> > Signed-off-by: Brian Gerst <brge...@gmail.com>
> > ---
> > arch/x86/include/asm/percpu.h | 90 ++++++++++++++---------------------
> > 1 file changed, 35 insertions(+), 55 deletions(-)
> >
> > diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
> > index 89f918a3e99b..233c7a78d1a6 100644
> > --- a/arch/x86/include/asm/percpu.h
> > +++ b/arch/x86/include/asm/percpu.h
> > @@ -117,37 +117,17 @@ extern void __bad_percpu_size(void);
> > #define __pcpu_reg_imm_4(x) "ri" (x)
> > #define __pcpu_reg_imm_8(x) "re" (x)
> >
> > -#define percpu_to_op(qual, op, var, val) \
> > -do { \
> > - typedef typeof(var) pto_T__; \
> > - if (0) { \
> > - pto_T__ pto_tmp__; \
> > - pto_tmp__ = (val); \
> > - (void)pto_tmp__; \
> > - } \
> > - switch (sizeof(var)) { \
> > - case 1: \
> > - asm qual (op "b %1,"__percpu_arg(0) \
> > - : "+m" (var) \
> > - : "qi" ((pto_T__)(val))); \
> > - break; \
> > - case 2: \
> > - asm qual (op "w %1,"__percpu_arg(0) \
> > - : "+m" (var) \
> > - : "ri" ((pto_T__)(val))); \
> > - break; \
> > - case 4: \
> > - asm qual (op "l %1,"__percpu_arg(0) \
> > - : "+m" (var) \
> > - : "ri" ((pto_T__)(val))); \
> > - break; \
> > - case 8: \
> > - asm qual (op "q %1,"__percpu_arg(0) \
> > - : "+m" (var) \
> > - : "re" ((pto_T__)(val))); \
> > - break; \
> > - default: __bad_percpu_size(); \
> > - } \
> > +#define percpu_to_op(size, qual, op, _var, _val) \
> > +do { \
> > + __pcpu_type_##size pto_val__ = __pcpu_cast_##size(_val); \
> > + if (0) { \
> > + typeof(_var) pto_tmp__; \
> > + pto_tmp__ = (_val); \
> > + (void)pto_tmp__; \
> > + } \
>
> Please replace the whole `if (0)` block with:
> ```c
> __same_type(_var, _val);
> ```
> from include/linux/compiler.h.
The problem with __builtin_types_compatible_p() is that it considers
unsigned long and u64 (aka unsigned long long) as different types even
though they are the same width on x86-64. While this may be a good
cleanup to look at in the future, it's not a simple drop-in
replacement.
--
Brian Gerst
