lkml.org 
[lkml]   [2020]   [May]   [18]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    From
    Date
    SubjectRe: [PATCH 6/7] x86/percpu: Clean up percpu_xchg_op()
    On Sun, May 17, 2020 at 8:29 AM Brian Gerst <brgerst@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 <brgerst@gmail.com>

    Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>

    > ---
    > arch/x86/include/asm/percpu.h | 61 +++++++++++------------------------
    > 1 file changed, 18 insertions(+), 43 deletions(-)
    >
    > diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
    > index ac8c391a190e..3c95ab3c99cd 100644
    > --- a/arch/x86/include/asm/percpu.h
    > +++ b/arch/x86/include/asm/percpu.h
    > @@ -215,46 +215,21 @@ do { \
    > * expensive due to the implied lock prefix. The processor cannot prefetch
    > * cachelines if xchg is used.
    > */
    > -#define percpu_xchg_op(qual, var, nval) \
    > +#define percpu_xchg_op(size, qual, _var, _nval) \
    > ({ \
    > - typeof(var) pxo_ret__; \
    > - typeof(var) pxo_new__ = (nval); \
    > - switch (sizeof(var)) { \
    > - case 1: \
    > - asm qual ("\n\tmov "__percpu_arg(1)",%%al" \
    > - "\n1:\tcmpxchgb %2, "__percpu_arg(1) \
    > - "\n\tjnz 1b" \
    > - : "=&a" (pxo_ret__), "+m" (var) \
    > - : "q" (pxo_new__) \
    > - : "memory"); \
    > - break; \
    > - case 2: \
    > - asm qual ("\n\tmov "__percpu_arg(1)",%%ax" \
    > - "\n1:\tcmpxchgw %2, "__percpu_arg(1) \
    > - "\n\tjnz 1b" \
    > - : "=&a" (pxo_ret__), "+m" (var) \
    > - : "r" (pxo_new__) \
    > - : "memory"); \
    > - break; \
    > - case 4: \
    > - asm qual ("\n\tmov "__percpu_arg(1)",%%eax" \
    > - "\n1:\tcmpxchgl %2, "__percpu_arg(1) \
    > - "\n\tjnz 1b" \
    > - : "=&a" (pxo_ret__), "+m" (var) \
    > - : "r" (pxo_new__) \
    > - : "memory"); \
    > - break; \
    > - case 8: \
    > - asm qual ("\n\tmov "__percpu_arg(1)",%%rax" \
    > - "\n1:\tcmpxchgq %2, "__percpu_arg(1) \
    > - "\n\tjnz 1b" \
    > - : "=&a" (pxo_ret__), "+m" (var) \
    > - : "r" (pxo_new__) \
    > - : "memory"); \
    > - break; \
    > - default: __bad_percpu_size(); \
    > - } \
    > - pxo_ret__; \
    > + __pcpu_type_##size pxo_old__; \
    > + __pcpu_type_##size pxo_new__ = __pcpu_cast_##size(_nval); \
    > + asm qual (__pcpu_op2_##size("mov", __percpu_arg([var]), \
    > + "%[oval]") \
    > + "\n1:\t" \
    > + __pcpu_op2_##size("cmpxchg", "%[nval]", \
    > + __percpu_arg([var])) \
    > + "\n\tjnz 1b" \
    > + : [oval] "=&a" (pxo_old__), \
    > + [var] "+m" (_var) \
    > + : [nval] __pcpu_reg_##size(, pxo_new__) \
    > + : "memory"); \
    > + (typeof(_var))(unsigned long) pxo_old__; \
    > })
    >
    > /*
    > @@ -354,9 +329,9 @@ do { \
    > #define this_cpu_or_1(pcp, val) percpu_to_op(1, volatile, "or", (pcp), val)
    > #define this_cpu_or_2(pcp, val) percpu_to_op(2, volatile, "or", (pcp), val)
    > #define this_cpu_or_4(pcp, val) percpu_to_op(4, volatile, "or", (pcp), val)
    > -#define this_cpu_xchg_1(pcp, nval) percpu_xchg_op(volatile, pcp, nval)
    > -#define this_cpu_xchg_2(pcp, nval) percpu_xchg_op(volatile, pcp, nval)
    > -#define this_cpu_xchg_4(pcp, nval) percpu_xchg_op(volatile, pcp, nval)
    > +#define this_cpu_xchg_1(pcp, nval) percpu_xchg_op(1, volatile, pcp, nval)
    > +#define this_cpu_xchg_2(pcp, nval) percpu_xchg_op(2, volatile, pcp, nval)
    > +#define this_cpu_xchg_4(pcp, nval) percpu_xchg_op(4, volatile, pcp, nval)
    >
    > #define raw_cpu_add_return_1(pcp, val) percpu_add_return_op(1, , pcp, val)
    > #define raw_cpu_add_return_2(pcp, val) percpu_add_return_op(2, , pcp, val)
    > @@ -409,7 +384,7 @@ do { \
    > #define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val)
    > #define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val)
    > #define this_cpu_add_return_8(pcp, val) percpu_add_return_op(8, volatile, pcp, val)
    > -#define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(volatile, pcp, nval)
    > +#define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(8, volatile, pcp, nval)
    > #define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(volatile, pcp, oval, nval)
    >
    > /*
    > --
    > 2.25.4
    >


    --
    Thanks,
    ~Nick Desaulniers

    \
     
     \ /
      Last update: 2020-05-19 00:16    [W:2.523 / U:0.016 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site