Re: [PATCH v2 06/27] x86/entry/64: Adapt assembly for PIE support

On Wed, Mar 14, 2018 at 8:55 AM Christopher Lameter [off-list ref] wrote:

On Wed, 14 Mar 2018, Peter Zijlstra wrote:

quoted

On Tue, Mar 13, 2018 at 01:59:24PM -0700, Thomas Garnier wrote:

quoted

@@ -1576,7 +1578,9 @@ first_nmi:
    addq    $8, (%rsp)      /* Fix up RSP */
    pushfq                  /* RFLAGS */
    pushq   $__KERNEL_CS    /* CS */
-   pushq   $1f             /* RIP */
+   pushq   %rax            /* Support Position Independent Code */
+   leaq    1f(%rip), %rax  /* RIP */
+   xchgq   %rax, (%rsp)    /* Restore RAX, put 1f */
    iretq                   /* continues at repeat_nmi below */
    UNWIND_HINT_IRET_REGS
 1:

Urgh, xchg with a memop has an implicit LOCK prefix.

this_cpu_xchg uses no lock cmpxchg as a replacement to reduce latency.

Great, I will update my implementation.

Thanks Peter and Christoph.

 From linux/arch/x86/include/asm/percpu.h

/*
  * xchg is implemented using cmpxchg without a lock prefix. xchg is
  * expensive due to the implied lock prefix.  The processor cannot

prefetch

  * cachelines if xchg is used.
  */
#define percpu_xchg_op(var, nval)                                       \
({                                                                      \
         typeof(var) pxo_ret__;                                          \
         typeof(var) pxo_new__ = (nval);                                 \
         switch (sizeof(var)) {                                          \
         case 1:                                                         \
                 asm("\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("\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("\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("\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__;                                                      \

-- 
Thomas