lkml.org 
[lkml]   [2011]   [May]   [10]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCH] perf events, x86: Implement Sandybridge last-level cache events
From
Date
On Mon, 2011-05-09 at 16:39 +0800, Lin Ming wrote:

>
> +/*
> + * Sandy Bridge MSR_OFFCORE_RESPONSE bits;
> + * See IA32 SDM Vol 3B 30.8.5
> + */
> +
> +#define SNB_DMND_DATA_RD (1ULL << 0)
> +#define SNB_DMND_RFO (1ULL << 1)
> +#define SNB_DMND_IFETCH (1ULL << 2)
> +#define SNB_DMND_WB (1ULL << 3)
> +#define SNB_PF_DATA_RD (1ULL << 4)
> +#define SNB_PF_DATA_RFO (1ULL << 5)
> +#define SNB_PF_IFETCH (1ULL << 6)
> +#define SNB_PF_LLC_DATA_RD (1ULL << 7)
> +#define SNB_PF_LLC_RFO (1ULL << 8)
> +#define SNB_PF_LLC_IFETCH (1ULL << 9)
> +#define SNB_BUS_LOCKS (1ULL << 10)
> +#define SNB_STRM_ST (1ULL << 11)
> + /* hole */
> +#define SNB_OFFCORE_OTHER (1ULL << 15)
> +#define SNB_COMMON (1ULL << 16)
> +#define SNB_NO_SUPP (1ULL << 17)
> +#define SNB_LLC_HITM (1ULL << 18)
> +#define SNB_LLC_HITE (1ULL << 19)
> +#define SNB_LLC_HITS (1ULL << 20)
> +#define SNB_LLC_HITF (1ULL << 21)
> + /* hole */
> +#define SNB_SNP_NONE (1ULL << 31)
> +#define SNB_SNP_NOT_NEEDED (1ULL << 32)
> +#define SNB_SNP_MISS (1ULL << 33)
> +#define SNB_SNP_NO_FWD (1ULL << 34)
> +#define SNB_SNP_FWD (1ULL << 35)
> +#define SNB_HITM (1ULL << 36)
> +#define SNB_NON_DRAM (1ULL << 37)
> +
> +#define SNB_DMND_READ (SNB_DMND_DATA_RD)
> +#define SNB_DMND_WRITE (SNB_DMND_RFO | SNB_DMND_WB|SNB_STRM_ST)
> +#define SNB_DMND_PREFETCH (SNB_PF_DATA_RD | SNB_PF_DATA_RFO)
> +
> +#define SNB_SUPPLIER_INFO (SNB_NO_SUPP | SNB_LLC_HITM | SNB_LLC_HITE | \
> + SNB_LLC_HITS | SNB_LLC_HITF)
> +
> +#define SNB_L3_HIT (SNB_SUPPLIER_INFO | SNB_SNP_NOT_NEEDED | SNB_SNP_NO_FWD | SNB_HITM)
> +#define SNB_L3_MISS (SNB_SUPPLIER_INFO | SNB_SNP_MISS | SNB_SNP_FWD | SNB_NON_DRAM)
> +#define SNB_L3_ACCESS (SNB_L3_HIT | SNB_L3_MISS)

I would very much like to know how these bits work.. Since the SDM
doesn't explain anything could you please add a big comment explaining
things?

Otherwise the patch looks good, but unverifiable so for me.

> +static __initconst const u64 snb_hw_cache_extra_regs
> + [PERF_COUNT_HW_CACHE_MAX]
> + [PERF_COUNT_HW_CACHE_OP_MAX]
> + [PERF_COUNT_HW_CACHE_RESULT_MAX] =
> +{
> + [ C(LL ) ] = {
> + [ C(OP_READ) ] = {
> + [ C(RESULT_ACCESS) ] = SNB_DMND_READ | SNB_L3_ACCESS,
> + [ C(RESULT_MISS) ] = SNB_DMND_READ | SNB_L3_MISS,
> + },
> + [ C(OP_WRITE) ] = {
> + [ C(RESULT_ACCESS) ] = SNB_DMND_WRITE | SNB_L3_ACCESS,
> + [ C(RESULT_MISS) ] = SNB_DMND_WRITE | SNB_L3_MISS,
> + },
> + [ C(OP_PREFETCH) ] = {
> + [ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH | SNB_L3_ACCESS,
> + [ C(RESULT_MISS) ] = SNB_DMND_PREFETCH | SNB_L3_MISS,
> + },
> + }
> +};



\
 
 \ /
  Last update: 2011-05-10 12:07    [W:0.054 / U:0.336 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site