perf, trace: Remove IRQ-disable from perf/tracepoint interaction
in [Kernel]
|
Prev: pacmcia:yena_socket.c Remove extra #ifdef CONFIG_YENTA_TI
Next: [PATCH] sysctl: fix kernel-doc notation and typos
From: Frank Ch. Eigler on 21 May 2010 13:50 Peter Zijlstra <a.p.zijlstra(a)chello.nl> writes: > [...] > @@ -799,13 +799,10 @@ perf_trace_templ_##call(struct ftrace_ev > static notrace void perf_trace_##call(proto) \ > { \ > struct ftrace_event_call *event_call = &event_##call; \ > - struct pt_regs *__regs = &get_cpu_var(perf_trace_regs); \ > - \ > - perf_fetch_caller_regs(__regs, 1); \ > - \ > - perf_trace_templ_##template(event_call, __regs, args); \ > + struct pt_regs __regs; \ > \ > - put_cpu_var(perf_trace_regs); \ > + perf_fetch_caller_regs(&__regs, 1); \ > + perf_trace_templ_##template(event_call, &__regs, args); \ > } > [...] To what extent are you worried about something the size of struct pt_regs being auto/stack allocated? - FChE -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Frank Ch. Eigler on 21 May 2010 14:10
Hi - On Fri, May 21, 2010 at 01:53:00PM -0400, Steven Rostedt wrote: > [...] > > > - struct pt_regs *__regs = &get_cpu_var(perf_trace_regs); \ > > > - [...] > > > + struct pt_regs __regs; \ > > > [...] > > > > To what extent are you worried about something the size of struct > > pt_regs being auto/stack allocated? > > Isn't pt_regs already allocated on the stack when interrupted? Maybe, but here we're about to ask for another multi-hundred-byte one. Does your stack-frame-size ftrace widget gripe about this change? - FChE -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |