Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Ankur Arora <ankur.a.arora@oracle.com>
To:     linux-kernel@vger.kernel.org, linux-mm@kvack.org, x86@kernel.org
Cc:     mingo@kernel.org, bp@alien8.de, luto@kernel.org,
        akpm@linux-foundation.org, mike.kravetz@oracle.com,
        jon.grimm@amd.com, kvm@vger.kernel.org, konrad.wilk@oracle.com,
        boris.ostrovsky@oracle.com, Ankur Arora <ankur.a.arora@oracle.com>
Subject: [PATCH v2 02/14] perf bench: add memset_movnti()
Date:   Wed, 20 Oct 2021 10:02:53 -0700
Message-Id: <20211020170305.376118-3-ankur.a.arora@oracle.com>
In-Reply-To: <20211020170305.376118-1-ankur.a.arora@oracle.com>
References: <20211020170305.376118-1-ankur.a.arora@oracle.com>
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?gSuujfPlEyfuZDGwuhFkw8AGyxDvl4Vw1MAAVsjWBcift3hadWqPVyTUzWoi?=
 =?us-ascii?Q?6DPWbl/0BiefLy6i4+/7yWaSx0Zl3t1+XScPEFnMtAJcsz/4Z3W2rinNWrbB?=
 =?us-ascii?Q?L6Va0Yma38S9QpWEzZBZjHAjxXvu04LLsBb0QLURMs2KJArw9JcRrsGcaryt?=
 =?us-ascii?Q?/x7OTUkEu7EPh9jqmTa3cTsqp+WXJwMEFRuJRBMHifRRv4vhSYyQ/yIQ1t/C?=
 =?us-ascii?Q?bGqF8NFrASDhlT/BAhqeLDBUj28azH+7WUt5k04yRfuMLrlG70y8PFlAZT2y?=
 =?us-ascii?Q?6MwESoCidzdYjDflKUJGTLt3fVu5Zt4l2AkCxy8Q05aVyRPMzSwReoWASUAy?=
 =?us-ascii?Q?CuaK3wE16uvHRep138/hwAIC3+GJbR6wAqHSd059/JdOrUibnkQXERsSN/2g?=
 =?us-ascii?Q?xHPz7Z6Z2o1eTm7vmKjFsLodM0T0S+hO4LQ28jLYG+SnH6FhXdJCbzCeak6E?=
 =?us-ascii?Q?l3fhJJAxXGvDBE5N9PaooFRCw3sBYvEc7508eQ1GbNPh75CUtTp1+LmhYIDQ?=
 =?us-ascii?Q?2y96kJ+7OzKemgAozPoNU/SgoVHmz6/DItWiNqIwy+v1zzmuxuTJNR1yQaAC?=
 =?us-ascii?Q?t3PIlPBsLd0ed1wvTQQKPBpJipA+4HA+X4FcyXivg6pXUaNyjquFw28Fj8XP?=
 =?us-ascii?Q?hxN8QHPhDxjT0vNv9fL3yzvzPoga/GDh6crj9/0oX80c5QYHZvWddHyRL9Yf?=
 =?us-ascii?Q?n6pdGChrOSubLgzjzeM7l/vUvNJhUpLuDP3qvnDw+vuNVotPjGwVjWnwBoEz?=
 =?us-ascii?Q?j9Sl8ewNOGRDJTkTEyACkeTPYizbrN10LrO8JTJbQYN1Qq0K3jdlrppxa1ma?=
 =?us-ascii?Q?zbxZGrcM1ykNTFvkYp8bBG40qtiOjtjYJqeRFs9jPXVj3UiNTvKdylqKzoWr?=
 =?us-ascii?Q?r1zRuv3NZfhWILtXmbn7sCMmPFZZR6NFY0BYcgxpx1gcmX3hUKBTXY4ydJ+4?=
 =?us-ascii?Q?r2FxgQygkct21vHYa4s/a6PiVqJfa+UhR5OPJ65/mtQF1vQ/Vl2bTsljTf9P?=
 =?us-ascii?Q?ovkk4yrMLuMARBlrSfDrdS5penytkxT1jNloW8Gs3eULy/r+Mm1DtOOvRjKA?=
 =?us-ascii?Q?DDQACDiDUx60/qYMmF78QVLXT5W1l3Mw/HhHSHPSR2DMiwpFv7+GWSEddpqU?=
 =?us-ascii?Q?4Pp5xNwZU2tmETE55kY6L8yaANtYCpGtTceUNPLOMIoi13XIJtF6RrWzmsjB?=
 =?us-ascii?Q?IDkNPDBTG82dBvVqzGiraMNyKJNUIcWPQ2ZOQsK9Yo2rDzeI/ApUfmCKDeJ7?=
 =?us-ascii?Q?wn7qqDkD0EnqcUbdCqsZCqHLEdaAs0niMCpcoqppQ3r+lUIii7AKqW0MG72r?=
 =?us-ascii?Q?F473woDa/0OpL7sXmdxlcHSzGHNotaTlp2Y7f+K1nilvyDUdjPeqM9sHRmtN?=
 =?us-ascii?Q?F0wl3kzN7z1pU+WGjKA18ZjT7cqsudfzS5BWUfZBj+aBYhsUy5sJsK6yHS5M?=
 =?us-ascii?Q?GXDIZ1s13CQsST7Dc0Be8JFNqzABZG4m?=
X-OriginatorOrg: oracle.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 4278fbc0-0f2f-40fc-194e-08d993ebcb21
X-MS-Exchange-CrossTenant-AuthSource: CO6PR10MB5409.namprd10.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 20 Oct 2021 17:05:18.6646
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 4e2c6054-71cb-48f1-bd6c-3a9705aca71b
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: ankur.a.arora@oracle.com
X-MS-Exchange-Transport-CrossTenantHeadersStamped: CO1PR10MB4577
X-Proofpoint-Virus-Version: vendor=nai engine=6300 definitions=10143 signatures=668683
X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 spamscore=0 adultscore=0 malwarescore=0
 phishscore=0 mlxlogscore=999 bulkscore=0 suspectscore=0 mlxscore=0
 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2109230001
 definitions=main-2110200095
X-Proofpoint-ORIG-GUID: fNnA5ikQXi6GuGaUfXVZmUVUQJvZ63zE
X-Proofpoint-GUID: fNnA5ikQXi6GuGaUfXVZmUVUQJvZ63zE
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Clone memset_movnti() from arch/x86/lib/memset_64.S.

perf bench mem memset -f x86-64-movnt on Intel Icelake-X, AMD Milan:

  # Intel Icelake-X

  $ for i in 8 32 128 512; do
         perf bench mem memset -f x86-64-movnt -s ${i}MB -l 5
     done

  # Output pruned.
  # Running 'mem/memset' benchmark:
  # function 'x86-64-movnt' (movnt-based memset() in arch/x86/lib/memset_64.S)
  # Copying 8MB bytes ...
      12.896170 GB/sec
  # Copying 32MB bytes ...
      15.879065 GB/sec
  # Copying 128MB bytes ...
      20.813214 GB/sec
  # Copying 512MB bytes ...
      24.190817 GB/sec

  # AMD Milan

  $ for i in 8 32 128 512; do
         perf bench mem memset -f x86-64-movnt -s ${i}MB -l 5
     done

  # Output pruned.
  # Running 'mem/memset' benchmark:
  # function 'x86-64-movnt' (movnt-based memset() in arch/x86/lib/memset_64.S)
  # Copying 8MB bytes ...
        22.372566 GB/sec
  # Copying 32MB bytes ...
        22.507923 GB/sec
  # Copying 128MB bytes ...
        22.492532 GB/sec
  # Copying 512MB bytes ...
        22.434603 GB/sec

Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
---
 tools/arch/x86/lib/memset_64.S               | 68 +++++++++++---------
 tools/perf/bench/mem-memset-x86-64-asm-def.h |  6 +-
 2 files changed, 43 insertions(+), 31 deletions(-)

diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index 9827ae267f96..ef2a091563d9 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -25,7 +25,7 @@ SYM_FUNC_START(__memset)
 	 *
 	 * Otherwise, use original memset function.
 	 */
-	ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \
+	ALTERNATIVE_2 "jmp memset_movq", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memset_erms", X86_FEATURE_ERMS
 
 	movq %rdi,%r9
@@ -66,7 +66,8 @@ SYM_FUNC_START_LOCAL(memset_erms)
 	ret
 SYM_FUNC_END(memset_erms)
 
-SYM_FUNC_START_LOCAL(memset_orig)
+.macro MEMSET_MOV OP fence
+SYM_FUNC_START_LOCAL(memset_\OP)
 	movq %rdi,%r10
 
 	/* expand byte value  */
@@ -77,64 +78,71 @@ SYM_FUNC_START_LOCAL(memset_orig)
 	/* align dst */
 	movl  %edi,%r9d
 	andl  $7,%r9d
-	jnz  .Lbad_alignment
-.Lafter_bad_alignment:
+	jnz  .Lbad_alignment_\@
+.Lafter_bad_alignment_\@:
 
 	movq  %rdx,%rcx
 	shrq  $6,%rcx
-	jz	 .Lhandle_tail
+	jz	 .Lhandle_tail_\@
 
 	.p2align 4
-.Lloop_64:
+.Lloop_64_\@:
 	decq  %rcx
-	movq  %rax,(%rdi)
-	movq  %rax,8(%rdi)
-	movq  %rax,16(%rdi)
-	movq  %rax,24(%rdi)
-	movq  %rax,32(%rdi)
-	movq  %rax,40(%rdi)
-	movq  %rax,48(%rdi)
-	movq  %rax,56(%rdi)
+	\OP  %rax,(%rdi)
+	\OP  %rax,8(%rdi)
+	\OP  %rax,16(%rdi)
+	\OP  %rax,24(%rdi)
+	\OP  %rax,32(%rdi)
+	\OP  %rax,40(%rdi)
+	\OP  %rax,48(%rdi)
+	\OP  %rax,56(%rdi)
 	leaq  64(%rdi),%rdi
-	jnz    .Lloop_64
+	jnz    .Lloop_64_\@
 
 	/* Handle tail in loops. The loops should be faster than hard
 	   to predict jump tables. */
 	.p2align 4
-.Lhandle_tail:
+.Lhandle_tail_\@:
 	movl	%edx,%ecx
 	andl    $63&(~7),%ecx
-	jz 		.Lhandle_7
+	jz 		.Lhandle_7_\@
 	shrl	$3,%ecx
 	.p2align 4
-.Lloop_8:
+.Lloop_8_\@:
 	decl   %ecx
-	movq  %rax,(%rdi)
+	\OP  %rax,(%rdi)
 	leaq  8(%rdi),%rdi
-	jnz    .Lloop_8
+	jnz    .Lloop_8_\@
 
-.Lhandle_7:
+.Lhandle_7_\@:
 	andl	$7,%edx
-	jz      .Lende
+	jz      .Lende_\@
 	.p2align 4
-.Lloop_1:
+.Lloop_1_\@:
 	decl    %edx
 	movb 	%al,(%rdi)
 	leaq	1(%rdi),%rdi
-	jnz     .Lloop_1
+	jnz     .Lloop_1_\@
 
-.Lende:
+.Lende_\@:
+	.if \fence
+	sfence
+	.endif
 	movq	%r10,%rax
 	ret
 
-.Lbad_alignment:
+.Lbad_alignment_\@:
 	cmpq $7,%rdx
-	jbe	.Lhandle_7
+	jbe	.Lhandle_7_\@
 	movq %rax,(%rdi)	/* unaligned store */
 	movq $8,%r8
 	subq %r9,%r8
 	addq %r8,%rdi
 	subq %r8,%rdx
-	jmp .Lafter_bad_alignment
-.Lfinal:
-SYM_FUNC_END(memset_orig)
+	jmp .Lafter_bad_alignment_\@
+.Lfinal_\@:
+SYM_FUNC_END(memset_\OP)
+.endm
+
+MEMSET_MOV OP=movq fence=0
+MEMSET_MOV OP=movnti fence=1
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 dac6d2b7c39b..53ead7f91313 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm-def.h
+++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
-MEMSET_FN(memset_orig,
+MEMSET_FN(memset_movq,
 	"x86-64-unrolled",
 	"unrolled memset() in arch/x86/lib/memset_64.S")
 
@@ -11,3 +11,7 @@ MEMSET_FN(__memset,
 MEMSET_FN(memset_erms,
 	"x86-64-stosb",
 	"movsb-based memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_movnti,
+	"x86-64-movnt",
+	"movnt-based memset() in arch/x86/lib/memset_64.S")
-- 
2.29.2