linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Ankur Arora <ankur.a.arora@oracle.com>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org, x86@kernel.org
Cc: 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, namhyung@kernel.org, tglx@linutronix.de,
	willy@infradead.org, raghavendra.kt@amd.com,
	boris.ostrovsky@oracle.com, konrad.wilk@oracle.com,
	ankur.a.arora@oracle.com
Subject: [PATCH v6 06/15] perf bench mem: Allow mapping of hugepages
Date: Tue,  2 Sep 2025 01:08:07 -0700	[thread overview]
Message-ID: <20250902080816.3715913-7-ankur.a.arora@oracle.com> (raw)
In-Reply-To: <20250902080816.3715913-1-ankur.a.arora@oracle.com>

Page sizes that can be selected: 4KB, 2MB, 1GB.

Both the reservation and node from which hugepages are allocated
from are expected to be addressed by the user.

An example of page-size selection:

  $ perf bench mem memset -s 4gb -p 2mb
  # Running 'mem/memset' benchmark:
  # function 'default' (Default memset() provided by glibc)
  # Copying 4gb bytes ...

        14.919194 GB/sec
  # function 'x86-64-unrolled' (unrolled memset() in arch/x86/lib/memset_64.S)
  # Copying 4gb bytes ...

        11.514503 GB/sec
  # function 'x86-64-stosq' (movsq-based memset() in arch/x86/lib/memset_64.S)
  # Copying 4gb bytes ...

          12.600568 GB/sec

Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
---
 tools/perf/Documentation/perf-bench.txt | 14 +++++++++--
 tools/perf/bench/mem-functions.c        | 33 ++++++++++++++++++++++---
 2 files changed, 41 insertions(+), 6 deletions(-)

diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index 8331bd28b10e..04cdc31a0b0b 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -177,11 +177,16 @@ Suite for evaluating performance of simple memory copy in various ways.
 
 Options of *memcpy*
 ^^^^^^^^^^^^^^^^^^^
--l::
+-s::
 --size::
 Specify size of memory to copy (default: 1MB).
 Available units are B, KB, MB, GB and TB (case insensitive).
 
+-p::
+--page::
+Specify page-size for mapping memory buffers (default: 4KB).
+Available values are 4KB, 2MB, 1GB (case insensitive).
+
 -f::
 --function::
 Specify function to copy (default: default).
@@ -201,11 +206,16 @@ Suite for evaluating performance of simple memory set in various ways.
 
 Options of *memset*
 ^^^^^^^^^^^^^^^^^^^
--l::
+-s::
 --size::
 Specify size of memory to set (default: 1MB).
 Available units are B, KB, MB, GB and TB (case insensitive).
 
+-p::
+--page::
+Specify page-size for mapping memory buffers (default: 4KB).
+Available values are 4KB, 2MB, 1GB (case insensitive).
+
 -f::
 --function::
 Specify function to set (default: default).
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index e97962dd8f81..6aa1f02553ba 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -25,11 +25,17 @@
 #include <sys/mman.h>
 #include <errno.h>
 #include <linux/time64.h>
+#include <linux/log2.h>
 
 #define K 1024
 
+#define PAGE_SHIFT_4KB		12
+#define PAGE_SHIFT_2MB		21
+#define PAGE_SHIFT_1GB		30
+
 static const char	*size_str	= "1MB";
 static const char	*function_str	= "all";
+static const char	*page_size_str	= "4KB";
 static unsigned int	nr_loops	= 1;
 static bool		use_cycles;
 static int		cycles_fd;
@@ -39,6 +45,10 @@ static const struct option options[] = {
 		    "Specify the size of the memory buffers. "
 		    "Available units: B, KB, MB, GB and TB (case insensitive)"),
 
+	OPT_STRING('p', "page", &page_size_str, "4KB",
+		    "Specify page-size for mapping memory buffers. "
+		    "Available sizes: 4KB, 2MB, 1GB (case insensitive)"),
+
 	OPT_STRING('f', "function", &function_str, "all",
 		    "Specify the function to run, \"all\" runs all available functions, \"help\" lists them"),
 
@@ -60,6 +70,7 @@ struct bench_params {
 	size_t		size;
 	size_t		size_total;
 	unsigned int	nr_loops;
+	unsigned int	page_shift;
 };
 
 struct bench_mem_info {
@@ -202,7 +213,8 @@ static void __bench_mem_function(struct bench_mem_info *info, struct bench_param
 	if (r->fn.fini) r->fn.fini(info, p, &src, &dst);
 	return;
 out_init_failed:
-	printf("# Memory allocation failed - maybe size (%s) is too large?\n", size_str);
+	printf("# Memory allocation failed - maybe size (%s) %s?\n", size_str,
+			p->page_shift != PAGE_SHIFT_4KB ? "has insufficient hugepages" : "is too large");
 	goto out_free;
 }
 
@@ -210,6 +222,7 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
 {
 	int i;
 	struct bench_params p = { 0 };
+	unsigned int page_size;
 
 	argc = parse_options(argc, argv, options, info->usage, 0);
 
@@ -230,6 +243,15 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
 	}
 	p.size_total = p.size * p.nr_loops;
 
+	page_size = (unsigned int)perf_atoll((char *)page_size_str);
+	if (page_size != (1 << PAGE_SHIFT_4KB) &&
+	    page_size != (1 << PAGE_SHIFT_2MB) &&
+	    page_size != (1 << PAGE_SHIFT_1GB)) {
+		fprintf(stderr, "Invalid page-size:%s\n", page_size_str);
+		return 1;
+	}
+	p.page_shift = ilog2(page_size);
+
 	if (!strncmp(function_str, "all", 3)) {
 		for (i = 0; info->functions[i].name; i++)
 			__bench_mem_function(info, &p, i);
@@ -286,11 +308,14 @@ static int do_memcpy(const struct function *r, struct bench_params *p,
 	return 0;
 }
 
-static void *bench_mmap(size_t size, bool populate)
+static void *bench_mmap(size_t size, bool populate, unsigned int page_shift)
 {
 	void *p;
 	int extra = populate ? MAP_POPULATE : 0;
 
+	if (page_shift != PAGE_SHIFT_4KB)
+		extra |= MAP_HUGETLB | (page_shift << MAP_HUGE_SHIFT);
+
 	p = mmap(NULL, size, PROT_READ|PROT_WRITE,
 		 extra | MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
 
@@ -308,11 +333,11 @@ static bool mem_alloc(struct bench_mem_info *info, struct bench_params *p,
 {
 	bool failed;
 
-	*dst = bench_mmap(p->size, true);
+	*dst = bench_mmap(p->size, true, p->page_shift);
 	failed = *dst == NULL;
 
 	if (info->alloc_src) {
-		*src = bench_mmap(p->size, true);
+		*src = bench_mmap(p->size, true, p->page_shift);
 		failed = failed || *src == NULL;
 	}
 
-- 
2.31.1



  parent reply	other threads:[~2025-09-02  8:14 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-02  8:08 [PATCH v6 00/15] mm: folio_zero_user: clear contiguous pages Ankur Arora
2025-09-02  8:08 ` [PATCH v6 01/15] perf bench mem: Remove repetition around time measurement Ankur Arora
2025-09-02  8:08 ` [PATCH v6 02/15] perf bench mem: Defer type munging of size to float Ankur Arora
2025-09-02  8:08 ` [PATCH v6 03/15] perf bench mem: Move mem op parameters into a structure Ankur Arora
2025-09-02  8:08 ` [PATCH v6 04/15] perf bench mem: Pull out init/fini logic Ankur Arora
2025-09-02  8:08 ` [PATCH v6 05/15] perf bench mem: Switch from zalloc() to mmap() Ankur Arora
2025-09-02  8:08 ` Ankur Arora [this message]
2025-09-02  8:08 ` [PATCH v6 07/15] perf bench mem: Allow chunking on a memory region Ankur Arora
2025-09-02  8:08 ` [PATCH v6 08/15] perf bench mem: Refactor mem_options Ankur Arora
2025-09-02  8:08 ` [PATCH v6 09/15] perf bench mem: Add mmap() workloads Ankur Arora
2025-09-02  8:08 ` [PATCH v6 10/15] x86/mm: Simplify clear_page_* Ankur Arora
2025-09-02  8:08 ` [PATCH v6 11/15] mm: define clear_pages(), clear_user_pages() Ankur Arora
2025-09-02 19:56   ` kernel test robot
2025-09-02 20:09   ` kernel test robot
2025-09-02 20:16   ` David Hildenbrand
2025-09-03  4:08     ` Ankur Arora
2025-09-12 21:17       ` Ankur Arora
2025-09-02  8:08 ` [PATCH v6 12/15] highmem: define clear_highpages() Ankur Arora
2025-09-02 20:20   ` David Hildenbrand
2025-09-03  4:09     ` Ankur Arora
2025-09-02  8:08 ` [PATCH v6 13/15] mm: memory: support clearing page ranges Ankur Arora
2025-09-02 19:46   ` kernel test robot
2025-09-02  8:08 ` [PATCH v6 14/15] x86/clear_page: Introduce clear_pages() Ankur Arora
2025-09-02  8:08 ` [PATCH v6 15/15] x86/clear_pages: Support clearing of page-extents Ankur Arora
2025-09-12 18:33 ` [PATCH v6 00/15] mm: folio_zero_user: clear contiguous pages Arnaldo Carvalho de Melo
2025-09-12 21:12   ` 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=20250902080816.3715913-7-ankur.a.arora@oracle.com \
    --to=ankur.a.arora@oracle.com \
    --cc=acme@kernel.org \
    --cc=akpm@linux-foundation.org \
    --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=namhyung@kernel.org \
    --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