lkml.org 
[lkml]   [2009]   [Jun]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
SubjectRe: [tip:perfcounters/core] perf_counter: Implement generalized cache event types
From
Date
On Sat, 2009-06-06 at 11:16 +0000, tip-bot for Ingo Molnar wrote:
> Commit-ID: 8326f44da090d6d304d29b9fdc7fb3e20889e329
> Gitweb: http://git.kernel.org/tip/8326f44da090d6d304d29b9fdc7fb3e20889e329
> Author: Ingo Molnar <mingo@elte.hu>
> AuthorDate: Fri, 5 Jun 2009 20:22:46 +0200
> Committer: Ingo Molnar <mingo@elte.hu>
> CommitDate: Sat, 6 Jun 2009 13:14:47 +0200
>
> perf_counter: Implement generalized cache event types
>
> Extend generic event enumeration with the PERF_TYPE_HW_CACHE
> method.
>
> This is a 3-dimensional space:
>
> { L1-D, L1-I, L2, ITLB, DTLB, BPU } x
> { load, store, prefetch } x
> { accesses, misses }
>
> User-space passes in the 3 coordinates and the kernel provides
> a counter. (if the hardware supports that type and if the
> combination makes sense.)
>
> Combinations that make no sense produce a -EINVAL.
> Combinations that are not supported by the hardware produce -ENOTSUP.
>
> Extend the tools to deal with this, and rewrite the event symbol
> parsing code with various popular aliases for the units and
> access methods above. So 'l1-cache-miss' and 'l1d-read-ops' are
> both valid aliases.
>
> ( x86 is supported for now, with the Nehalem event table filled in,
> and with Core2 and Atom having placeholder tables. )
>

> +++ b/include/linux/perf_counter.h
> @@ -28,6 +28,7 @@ enum perf_event_types {
> PERF_TYPE_HARDWARE = 0,
> PERF_TYPE_SOFTWARE = 1,
> PERF_TYPE_TRACEPOINT = 2,
> + PERF_TYPE_HW_CACHE = 3,
>
> /*
> * available TYPE space, raw is the max value.
> @@ -56,6 +57,39 @@ enum attr_ids {
> };
>
> /*
> + * Generalized hardware cache counters:
> + *
> + * { L1-D, L1-I, L2, LLC, ITLB, DTLB, BPU } x
> + * { read, write, prefetch } x
> + * { accesses, misses }
> + */
> +enum hw_cache_id {
> + PERF_COUNT_HW_CACHE_L1D,
> + PERF_COUNT_HW_CACHE_L1I,
> + PERF_COUNT_HW_CACHE_L2,
> + PERF_COUNT_HW_CACHE_DTLB,
> + PERF_COUNT_HW_CACHE_ITLB,
> + PERF_COUNT_HW_CACHE_BPU,
> +
> + PERF_COUNT_HW_CACHE_MAX,
> +};
> +
> +enum hw_cache_op_id {
> + PERF_COUNT_HW_CACHE_OP_READ,
> + PERF_COUNT_HW_CACHE_OP_WRITE,
> + PERF_COUNT_HW_CACHE_OP_PREFETCH,
> +
> + PERF_COUNT_HW_CACHE_OP_MAX,
> +};
> +
> +enum hw_cache_op_result_id {
> + PERF_COUNT_HW_CACHE_RESULT_ACCESS,
> + PERF_COUNT_HW_CACHE_RESULT_MISS,
> +
> + PERF_COUNT_HW_CACHE_RESULT_MAX,
> +};

May I suggest we do the below instead? Some hardware doesn't make the
read/write distinction and would therefore have an utterly empty table.

Furthermore, also splitting the hit/miss into a bitfield allows us to
have hit/miss and the combined value.

---
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 3586df8..1fb72fc 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -64,29 +64,32 @@ enum attr_ids {
* { accesses, misses }
*/
enum hw_cache_id {
- PERF_COUNT_HW_CACHE_L1D,
- PERF_COUNT_HW_CACHE_L1I,
- PERF_COUNT_HW_CACHE_L2,
- PERF_COUNT_HW_CACHE_DTLB,
- PERF_COUNT_HW_CACHE_ITLB,
- PERF_COUNT_HW_CACHE_BPU,
+ PERF_COUNT_HW_CACHE_L1D = 0,
+ PERF_COUNT_HW_CACHE_L1I = 1,
+ PERF_COUNT_HW_CACHE_L2 = 2,
+ PERF_COUNT_HW_CACHE_DTLB = 3,
+ PERF_COUNT_HW_CACHE_ITLB = 4,
+ PERF_COUNT_HW_CACHE_BPU = 5,

PERF_COUNT_HW_CACHE_MAX,
};

enum hw_cache_op_id {
- PERF_COUNT_HW_CACHE_OP_READ,
- PERF_COUNT_HW_CACHE_OP_WRITE,
- PERF_COUNT_HW_CACHE_OP_PREFETCH,
+ PERF_COUNT_HW_CACHE_OP_READ = 0x1,
+ PERF_COUNT_HW_CACHE_OP_WRITE = 0x2,
+ PERF_COUNT_HW_CACHE_OP_ACCESS = 0x3, /* either READ or WRITE */
+ PERF_COUNT_HW_CACHE_OP_PREFETCH = 0x4, /* XXX should we qualify this with either READ/WRITE? */

- PERF_COUNT_HW_CACHE_OP_MAX,
+
+ PERF_COUNT_HW_CACHE_OP_MAX = 0x8,
};

enum hw_cache_op_result_id {
- PERF_COUNT_HW_CACHE_RESULT_ACCESS,
- PERF_COUNT_HW_CACHE_RESULT_MISS,
+ PERF_COUNT_HW_CACHE_RESULT_HIT = 0x1,
+ PERF_COUNT_HW_CACHE_RESULT_MISS = 0x2,
+ PERF_COUNT_HW_CACHE_RESULT_SUM = 0x3,

- PERF_COUNT_HW_CACHE_RESULT_MAX,
+ PERF_COUNT_HW_CACHE_RESULT_MAX = 0x4,
};

/*



\
 
 \ /
  Last update: 2009-06-09 10:19    [W:0.045 / U:0.432 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site