From: Namhyung Kim <namhyung@kernel.org>
To: Ankur Arora <ankur.a.arora@oracle.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, x86@kernel.org,
akpm@linux-foundation.org, david@redhat.com, bp@alien8.de,
dave.hansen@linux.intel.com, hpa@zytor.com, mingo@redhat.com,
mjguzik@gmail.com, luto@kernel.org, peterz@infradead.org,
acme@kernel.org, tglx@linutronix.de, willy@infradead.org,
raghavendra.kt@amd.com, boris.ostrovsky@oracle.com,
konrad.wilk@oracle.com
Subject: Re: [PATCH v5 04/14] perf bench mem: Pull out init/fini logic
Date: Tue, 15 Jul 2025 13:09:14 -0700 [thread overview]
Message-ID: <aHa1avFkfdqoo69S@google.com> (raw)
In-Reply-To: <20250710005926.1159009-5-ankur.a.arora@oracle.com>
On Wed, Jul 09, 2025 at 05:59:16PM -0700, Ankur Arora wrote:
> No functional change.
>
> Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
A nitpick below.
> ---
> tools/perf/bench/mem-functions.c | 103 +++++++++++++------
> tools/perf/bench/mem-memcpy-arch.h | 2 +-
> tools/perf/bench/mem-memcpy-x86-64-asm-def.h | 4 +
> tools/perf/bench/mem-memset-arch.h | 2 +-
> tools/perf/bench/mem-memset-x86-64-asm-def.h | 4 +
> 5 files changed, 81 insertions(+), 34 deletions(-)
>
> diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
> index fb17d36a6f6c..06d3ee6f5d69 100644
> --- a/tools/perf/bench/mem-functions.c
> +++ b/tools/perf/bench/mem-functions.c
> @@ -62,15 +62,31 @@ struct bench_params {
> unsigned int nr_loops;
> };
>
> +struct bench_mem_info {
> + const struct function *functions;
> + int (*do_op)(const struct function *r, struct bench_params *p,
> + void *src, void *dst, union bench_clock *rt);
> + const char *const *usage;
> + bool alloc_src;
> +};
> +
> +typedef bool (*mem_init_t)(struct bench_mem_info *, struct bench_params *,
> + void **, void **);
> +typedef void (*mem_fini_t)(struct bench_mem_info *, struct bench_params *,
> + void **, void **);
> typedef void *(*memcpy_t)(void *, const void *, size_t);
> typedef void *(*memset_t)(void *, int, size_t);
>
> struct function {
> const char *name;
> const char *desc;
> - union {
> - memcpy_t memcpy;
> - memset_t memset;
> + struct {
> + mem_init_t init;
> + mem_fini_t fini;
> + union {
> + memcpy_t memcpy;
> + memset_t memset;
> + };
> } fn;
> };
>
> @@ -138,37 +154,24 @@ static double timeval2double(struct timeval *ts)
> printf(" %14lf GB/sec\n", x / K / K / K); \
> } while (0)
>
> -struct bench_mem_info {
> - const struct function *functions;
> - union bench_clock (*do_op)(const struct function *r, struct bench_params *p,
> - void *src, void *dst);
> - const char *const *usage;
> - bool alloc_src;
> -};
> -
> static void __bench_mem_function(struct bench_mem_info *info, struct bench_params *p,
> int r_idx)
> {
> const struct function *r = &info->functions[r_idx];
> double result_bps = 0.0;
> union bench_clock rt = { 0 };
> - void *src = NULL, *dst = zalloc(p->size);
> + void *src = NULL, *dst = NULL;
>
> printf("# function '%s' (%s)\n", r->name, r->desc);
>
> - if (dst == NULL)
> - goto out_alloc_failed;
> -
> - if (info->alloc_src) {
> - src = zalloc(p->size);
> - if (src == NULL)
> - goto out_alloc_failed;
> - }
> + if (r->fn.init && r->fn.init(info, p, &src, &dst))
> + goto out_init_failed;
>
> if (bench_format == BENCH_FORMAT_DEFAULT)
> printf("# Copying %s bytes ...\n\n", size_str);
>
> - rt = info->do_op(r, p, src, dst);
> + if (info->do_op(r, p, src, dst, &rt))
> + goto out_test_failed;
>
> switch (bench_format) {
> case BENCH_FORMAT_DEFAULT:
> @@ -194,11 +197,11 @@ static void __bench_mem_function(struct bench_mem_info *info, struct bench_param
> break;
> }
>
> +out_test_failed:
> out_free:
> - free(src);
> - free(dst);
> + if (r->fn.fini) r->fn.fini(info, p, &src, &dst);
> return;
> -out_alloc_failed:
> +out_init_failed:
> printf("# Memory allocation failed - maybe size (%s) is too large?\n", size_str);
> goto out_free;
> }
> @@ -264,8 +267,8 @@ static void memcpy_prefault(memcpy_t fn, size_t size, void *src, void *dst)
> fn(dst, src, size);
> }
>
> -static union bench_clock do_memcpy(const struct function *r, struct bench_params *p,
> - void *src, void *dst)
> +static int do_memcpy(const struct function *r, struct bench_params *p,
> + void *src, void *dst, union bench_clock *rt)
> {
> union bench_clock start, end;
> memcpy_t fn = r->fn.memcpy;
> @@ -277,16 +280,47 @@ static union bench_clock do_memcpy(const struct function *r, struct bench_params
> fn(dst, src, p->size);
> clock_get(&end);
>
> - return clock_diff(&start, &end);
> + *rt = clock_diff(&start, &end);
> +
> + return 0;
> +}
> +
> +static bool mem_alloc(struct bench_mem_info *info, struct bench_params *p,
> + void **src, void **dst)
> +{
> + bool failed;
> +
> + *dst = zalloc(p->size);
> + failed = *dst == NULL;
> +
> + if (info->alloc_src) {
> + *src = zalloc(p->size);
> + failed = failed || *src == NULL;
> + }
> +
> + return failed;
> +}
> +
> +static void mem_free(struct bench_mem_info *info __maybe_unused,
> + struct bench_params *p __maybe_unused,
> + void **src, void **dst)
> +{
> + free(*dst);
> + free(*src);
> +
> + *dst = *src = NULL;
There's zfree() to handle free and reset together. But probably not
needed as you want to convert it to mmap later.
Thanks,
Namhyung
> }
>
> struct function memcpy_functions[] = {
> { .name = "default",
> .desc = "Default memcpy() provided by glibc",
> + .fn.init = mem_alloc,
> + .fn.fini = mem_free,
> .fn.memcpy = memcpy },
>
> #ifdef HAVE_ARCH_X86_64_SUPPORT
> -# define MEMCPY_FN(_fn, _name, _desc) {.name = _name, .desc = _desc, .fn.memcpy = _fn},
> +# define MEMCPY_FN(_fn, _init, _fini, _name, _desc) \
> + {.name = _name, .desc = _desc, .fn.memcpy = _fn, .fn.init = _init, .fn.fini = _fini },
> # include "mem-memcpy-x86-64-asm-def.h"
> # undef MEMCPY_FN
> #endif
> @@ -311,8 +345,8 @@ int bench_mem_memcpy(int argc, const char **argv)
> return bench_mem_common(argc, argv, &info);
> }
>
> -static union bench_clock do_memset(const struct function *r, struct bench_params *p,
> - void *src __maybe_unused, void *dst)
> +static int do_memset(const struct function *r, struct bench_params *p,
> + void *src __maybe_unused, void *dst, union bench_clock *rt)
> {
> union bench_clock start, end;
> memset_t fn = r->fn.memset;
> @@ -328,7 +362,9 @@ static union bench_clock do_memset(const struct function *r, struct bench_params
> fn(dst, i, p->size);
> clock_get(&end);
>
> - return clock_diff(&start, &end);
> + *rt = clock_diff(&start, &end);
> +
> + return 0;
> }
>
> static const char * const bench_mem_memset_usage[] = {
> @@ -339,10 +375,13 @@ static const char * const bench_mem_memset_usage[] = {
> static const struct function memset_functions[] = {
> { .name = "default",
> .desc = "Default memset() provided by glibc",
> + .fn.init = mem_alloc,
> + .fn.fini = mem_free,
> .fn.memset = memset },
>
> #ifdef HAVE_ARCH_X86_64_SUPPORT
> -# define MEMSET_FN(_fn, _name, _desc) { .name = _name, .desc = _desc, .fn.memset = _fn },
> +# define MEMSET_FN(_fn, _init, _fini, _name, _desc) \
> + {.name = _name, .desc = _desc, .fn.memset = _fn, .fn.init = _init, .fn.fini = _fini },
> # include "mem-memset-x86-64-asm-def.h"
> # undef MEMSET_FN
> #endif
> diff --git a/tools/perf/bench/mem-memcpy-arch.h b/tools/perf/bench/mem-memcpy-arch.h
> index 5bcaec5601a8..852e48cfd8fe 100644
> --- a/tools/perf/bench/mem-memcpy-arch.h
> +++ b/tools/perf/bench/mem-memcpy-arch.h
> @@ -2,7 +2,7 @@
>
> #ifdef HAVE_ARCH_X86_64_SUPPORT
>
> -#define MEMCPY_FN(fn, name, desc) \
> +#define MEMCPY_FN(fn, init, fini, name, desc) \
> void *fn(void *, const void *, size_t);
>
> #include "mem-memcpy-x86-64-asm-def.h"
> diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
> index 6188e19d3129..f43038f4448b 100644
> --- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
> +++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
> @@ -1,9 +1,13 @@
> /* SPDX-License-Identifier: GPL-2.0 */
>
> MEMCPY_FN(memcpy_orig,
> + mem_alloc,
> + mem_free,
> "x86-64-unrolled",
> "unrolled memcpy() in arch/x86/lib/memcpy_64.S")
>
> MEMCPY_FN(__memcpy,
> + mem_alloc,
> + mem_free,
> "x86-64-movsq",
> "movsq-based memcpy() in arch/x86/lib/memcpy_64.S")
> diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h
> index 53f45482663f..278c5da12d63 100644
> --- a/tools/perf/bench/mem-memset-arch.h
> +++ b/tools/perf/bench/mem-memset-arch.h
> @@ -2,7 +2,7 @@
>
> #ifdef HAVE_ARCH_X86_64_SUPPORT
>
> -#define MEMSET_FN(fn, name, desc) \
> +#define MEMSET_FN(fn, init, fini, name, desc) \
> void *fn(void *, int, size_t);
>
> #include "mem-memset-x86-64-asm-def.h"
> diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h
> index 247c72fdfb9d..80ad1b7ea770 100644
> --- a/tools/perf/bench/mem-memset-x86-64-asm-def.h
> +++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h
> @@ -1,9 +1,13 @@
> /* SPDX-License-Identifier: GPL-2.0 */
>
> MEMSET_FN(memset_orig,
> + mem_alloc,
> + mem_free,
> "x86-64-unrolled",
> "unrolled memset() in arch/x86/lib/memset_64.S")
>
> MEMSET_FN(__memset,
> + mem_alloc,
> + mem_free,
> "x86-64-stosq",
> "movsq-based memset() in arch/x86/lib/memset_64.S")
> --
> 2.43.5
>
next prev parent reply other threads:[~2025-07-15 20:09 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-10 0:59 [PATCH v5 00/14] mm: folio_zero_user: clearing of page-extents Ankur Arora
2025-07-10 0:59 ` [PATCH v5 01/14] perf bench mem: Remove repetition around time measurement Ankur Arora
2025-07-15 20:04 ` Namhyung Kim
2025-07-10 0:59 ` [PATCH v5 02/14] perf bench mem: Defer type munging of size to float Ankur Arora
2025-07-15 20:05 ` Namhyung Kim
2025-07-16 2:17 ` Ankur Arora
2025-07-10 0:59 ` [PATCH v5 03/14] perf bench mem: Move mem op parameters into a structure Ankur Arora
2025-07-15 20:06 ` Namhyung Kim
2025-07-10 0:59 ` [PATCH v5 04/14] perf bench mem: Pull out init/fini logic Ankur Arora
2025-07-15 20:09 ` Namhyung Kim [this message]
2025-07-10 0:59 ` [PATCH v5 05/14] perf bench mem: Switch from zalloc() to mmap() Ankur Arora
2025-07-15 20:09 ` Namhyung Kim
2025-07-10 0:59 ` [PATCH v5 06/14] perf bench mem: Allow mapping of hugepages Ankur Arora
2025-07-15 20:12 ` Namhyung Kim
2025-07-16 2:32 ` Ankur Arora
2025-07-10 0:59 ` [PATCH v5 07/14] perf bench mem: Allow chunking on a memory region Ankur Arora
2025-07-15 20:17 ` Namhyung Kim
2025-07-16 2:34 ` Ankur Arora
2025-07-10 0:59 ` [PATCH v5 08/14] perf bench mem: Refactor mem_options Ankur Arora
2025-07-15 20:18 ` Namhyung Kim
2025-07-10 0:59 ` [PATCH v5 09/14] perf bench mem: Add mmap() workloads Ankur Arora
2025-07-15 20:20 ` Namhyung Kim
2025-07-16 2:40 ` Ankur Arora
2025-07-10 0:59 ` [PATCH v5 10/14] x86/mm: Simplify clear_page_* Ankur Arora
2025-07-11 11:47 ` David Hildenbrand
2025-07-11 17:26 ` Ankur Arora
2025-07-11 19:03 ` David Hildenbrand
2025-07-11 19:24 ` Ankur Arora
2025-07-11 19:27 ` David Hildenbrand
2025-07-10 0:59 ` [PATCH v5 11/14] x86/clear_page: Introduce clear_pages() Ankur Arora
2025-07-10 0:59 ` [PATCH v5 12/14] mm: add config option for clearing page-extents Ankur Arora
2025-07-10 7:58 ` Andrew Morton
2025-07-10 16:31 ` Ankur Arora
2025-07-11 11:39 ` David Hildenbrand
2025-07-11 17:25 ` Ankur Arora
2025-07-11 19:14 ` David Hildenbrand
2025-07-11 19:35 ` Ankur Arora
2025-07-11 11:40 ` David Hildenbrand
2025-07-11 17:32 ` Ankur Arora
2025-07-11 19:26 ` David Hildenbrand
2025-07-11 19:42 ` Ankur Arora
2025-07-14 20:35 ` Ankur Arora
2025-07-15 20:59 ` David Hildenbrand
2025-07-10 0:59 ` [PATCH v5 13/14] mm: memory: support " Ankur Arora
2025-07-11 11:44 ` David Hildenbrand
2025-07-11 13:27 ` Raghavendra K T
2025-07-11 17:39 ` Ankur Arora
2025-07-15 22:08 ` David Hildenbrand
2025-07-16 3:19 ` Ankur Arora
2025-07-16 8:03 ` David Hildenbrand
2025-07-16 17:54 ` Ankur Arora
2025-07-10 0:59 ` [PATCH v5 14/14] x86/clear_pages: Support clearing of page-extents Ankur Arora
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=aHa1avFkfdqoo69S@google.com \
--to=namhyung@kernel.org \
--cc=acme@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=ankur.a.arora@oracle.com \
--cc=boris.ostrovsky@oracle.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=david@redhat.com \
--cc=hpa@zytor.com \
--cc=konrad.wilk@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=mjguzik@gmail.com \
--cc=peterz@infradead.org \
--cc=raghavendra.kt@amd.com \
--cc=tglx@linutronix.de \
--cc=willy@infradead.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).