Re: [PATCH v9 2/3] x86/mce: Add per-bank CMCI storm mitigation

[Feng Tang <feng.tang@intel.com>]

On Thu, Oct 12, 2023 at 01:23:54AM +0800, Luck, Tony wrote:
> > IIRC, CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B was enabled in 0Day's
> > kernel config for quite a while, to force each funtion's start
> > address aligned on 64 bytes. Don't know if this has been changed
> > recently.
> >
> > Also I noticed the patch introduce a new per-cpu variable 'storm_desc",
> > if the function address is 64B aligned, then per-cpu data alignment
> > may be related.
> 
> If adding (removing, changing) per-cpu variables can cause 8% performance
> changes, then maybe there needs to be some way to insulate the builds
> from these side effects (as was done with the 64-byte function alignment).
> I've no ideas on how to achieve that :-(

Philip helped to clarify that 0Day kernel build does enable the 64 bytes
function address alignment.

> "storm_desc" is a largish per-cpu variable at 1568 bytes. But that doesn't
> quite get it into the top 20.
> 
> In the config used for my kernel build, it does appear just before a bunch
> of interrupt related per-cpu variables. Those might be sensitive to alignment?
> 
> 000000000001ff40 d smca_misc_banks_map
> 000000000001ff48 d bank_map
> 000000000001ff50 d threshold_banks
> 000000000001ff60 d storm_desc
> 0000000000020580 d tsc_adjust
> 00000000000205c0 d lapic_events
> 00000000000206c0 d vector_cleanup
> 0000000000020720 D __uv_cpu_info
> 0000000000020738 d ipi_mask

I did further check by putting 'storm_desc' into another section with
below patch, and the regression is restored, which indictes it is
related with these per-cpu data alignment change.

diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index ecdf13f1bb7d5..7f32126f216bc 100644
--- a/arch/x86/kernel/cpu/mce/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -41,7 +41,7 @@ struct mca_storm_desc {
 	bool			poll_mode;
 };
 
-static DEFINE_PER_CPU(struct mca_storm_desc, storm_desc);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct mca_storm_desc, storm_desc);

Thanks,
Feng

> 
> -Tony