diff options
Diffstat (limited to 'arch/x86/lib/delay_32.c')
| -rw-r--r-- | arch/x86/lib/delay_32.c | 56 |
1 files changed, 43 insertions, 13 deletions
diff --git a/arch/x86/lib/delay_32.c b/arch/x86/lib/delay_32.c index 4535e6d..ef69131 100644 --- a/arch/x86/lib/delay_32.c +++ b/arch/x86/lib/delay_32.c @@ -3,6 +3,7 @@ * * Copyright (C) 1993 Linus Torvalds * Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz> + * Copyright (C) 2008 Jiri Hladky <hladky _dot_ jiri _at_ gmail _dot_ com> * * The __delay function must _NOT_ be inlined as its execution time * depends wildly on alignment on many x86 processors. The additional @@ -28,29 +29,58 @@ /* simple loop based delay: */ static void delay_loop(unsigned long loops) { - int d0; - __asm__ __volatile__( - "\tjmp 1f\n" - ".align 16\n" - "1:\tjmp 2f\n" - ".align 16\n" - "2:\tdecl %0\n\tjns 2b" - :"=&a" (d0) - :"0" (loops)); + " test %0,%0 \n" + " jz 3f \n" + " jmp 1f \n" + + ".align 16 \n" + "1: jmp 2f \n" + + ".align 16 \n" + "2: decl %0 \n" + " jnz 2b \n" + "3: decl %0 \n" + + : /* we don't need output */ + :"a" (loops) + ); } /* TSC based delay: */ static void delay_tsc(unsigned long loops) { unsigned long bclock, now; + int cpu; - preempt_disable(); /* TSC's are per-cpu */ + preempt_disable(); + cpu = smp_processor_id(); rdtscl(bclock); - do { - rep_nop(); + for (;;) { rdtscl(now); - } while ((now-bclock) < loops); + if ((now - bclock) >= loops) + break; + + /* Allow RT tasks to run */ + preempt_enable(); + rep_nop(); + preempt_disable(); + + /* + * It is possible that we moved to another CPU, and + * since TSC's are per-cpu we need to calculate + * that. The delay must guarantee that we wait "at + * least" the amount of time. Being moved to another + * CPU could make the wait longer but we just need to + * make sure we waited long enough. Rebalance the + * counter for this CPU. + */ + if (unlikely(cpu != smp_processor_id())) { + loops -= (now - bclock); + cpu = smp_processor_id(); + rdtscl(bclock); + } + } preempt_enable(); } |