Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1252803

Re: [PATCH 1/5] x86, perf: Fix LBR call stack save/restore

Show all headers | View raw

On Tue, Oct 20, 2015 at 11:46:33AM -0700, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> This fixes a bug added with the earlier 90405aa02. The bug
> could lead to lost LBR call stacks. When restoring the LBR
> state we need to use the TOS of the previous context, not
> the current context. To do that we need to save/restore the tos.

Current best practise also asks for:

Fixes: 90405aa02247 ("perf/x86/intel/lbr: Limit LBR accesses to TOS in callstack mode")
> Cc: <stable@vger.kernel.org> # 4.2+
> Signed-off-by: Andi Kleen <ak@linux.intel.com>

> --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
> +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
> @@ -239,7 +239,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
>  	}
>  
>  	mask = x86_pmu.lbr_nr - 1;
> -	tos = intel_pmu_lbr_tos();
> +	tos = task_ctx->tos;
>  	for (i = 0; i < tos; i++) {
>  		lbr_idx = (tos - i) & mask;
>  		wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
> @@ -247,6 +247,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
>  		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
>  			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
>  	}
> +	wrmsrl(x86_pmu.lbr_tos, tos);
>  	task_ctx->lbr_stack_state = LBR_NONE;
>  }

Any idea who much more expensive that wrmsr() is compared to the rdmsr()
it replaces?

If its significant we could think about having this behaviour depend on
callstacks.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH 1/5] x86, perf: Fix LBR call stack save/restore Andi Kleen <andi@firstfloor.org> - 2015-10-20 20:50 +0200
  [PATCH 5/5] x86, perf: Avoid context switching LBR_INFO when not needed Andi Kleen <andi@firstfloor.org> - 2015-10-20 20:50 +0200
    Re: [PATCH 5/5] x86, perf: Avoid context switching LBR_INFO when not  needed Peter Zijlstra <peterz@infradead.org> - 2015-10-21 15:50 +0200
  [PATCH 3/5] perf, tools: Disable branch flags/cycles for --callgraph lbr Andi Kleen <andi@firstfloor.org> - 2015-10-20 21:00 +0200
    Re: [PATCH 3/5] perf, tools: Disable branch flags/cycles for  --callgraph lbr Peter Zijlstra <peterz@infradead.org> - 2015-10-21 15:30 +0200
      Re: [PATCH 3/5] perf, tools: Disable branch flags/cycles for  --callgraph lbr Arnaldo Carvalho de Melo <acme@kernel.org> - 2015-10-21 20:10 +0200
  Re: [PATCH 1/5] x86, perf: Fix LBR call stack save/restore Peter Zijlstra <peterz@infradead.org> - 2015-10-21 15:20 +0200
    Re: [PATCH 1/5] x86, perf: Fix LBR call stack save/restore Andi Kleen <andi@firstfloor.org> - 2015-10-21 16:40 +0200
    Re: [PATCH 1/5] x86, perf: Fix LBR call stack save/restore Ingo Molnar <mingo@kernel.org> - 2015-10-21 18:30 +0200

csiph-web