From: Ankur Arora <ankur.a.arora@oracle.com>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org, x86@kernel.org
Cc: torvalds@linux-foundation.org, akpm@linux-foundation.org,
mike.kravetz@oracle.com, mingo@kernel.org, luto@kernel.org,
tglx@linutronix.de, bp@alien8.de, peterz@infradead.org,
ak@linux.intel.com, arnd@arndb.de, jgg@nvidia.com,
jon.grimm@amd.com, boris.ostrovsky@oracle.com,
konrad.wilk@oracle.com, joao.m.martins@oracle.com,
ankur.a.arora@oracle.com
Subject: [PATCH v3 07/21] x86/asm: add memset_movnti()
Date: Mon, 6 Jun 2022 20:37:11 +0000 [thread overview]
Message-ID: <20220606203725.1313715-3-ankur.a.arora@oracle.com> (raw)
In-Reply-To: <20220606202109.1306034-1-ankur.a.arora@oracle.com>
Add a MOVNTI based non-caching implementation of memset().
memset_movnti() only needs to differ from memset_orig() in the opcode
used in the inner loop, so move the memset_orig() logic into a macro,
and use that to generate memset_orig() (now memset_movq()) and
memset_movnti().
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
---
arch/x86/lib/memset_64.S | 68 ++++++++++++++++++++++------------------
1 file changed, 38 insertions(+), 30 deletions(-)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index fc9ffd3ff3b2..307b753ca03a 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -24,7 +24,7 @@ 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
--
2.31.1
next prev parent reply other threads:[~2022-06-06 20:48 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-06 20:20 [PATCH v3 00/21] huge page clearing optimizations Ankur Arora
2022-06-06 20:20 ` [PATCH v3 01/21] mm, huge-page: reorder arguments to process_huge_page() Ankur Arora
2022-06-06 20:20 ` [PATCH v3 02/21] mm, huge-page: refactor process_subpage() Ankur Arora
2022-06-06 20:20 ` [PATCH v3 03/21] clear_page: add generic clear_user_pages() Ankur Arora
2022-06-06 20:20 ` [PATCH v3 04/21] mm, clear_huge_page: support clear_user_pages() Ankur Arora
2022-06-06 20:37 ` [PATCH v3 05/21] mm/huge_page: generalize process_huge_page() Ankur Arora
2022-06-06 20:37 ` [PATCH v3 06/21] x86/clear_page: add clear_pages() Ankur Arora
2022-06-06 20:37 ` Ankur Arora [this message]
2022-06-06 20:37 ` [PATCH v3 08/21] perf bench: add memset_movnti() Ankur Arora
2022-06-06 20:37 ` [PATCH v3 09/21] x86/asm: add clear_pages_movnt() Ankur Arora
2022-06-10 22:11 ` Noah Goldstein
2022-06-10 22:15 ` Noah Goldstein
2022-06-12 11:18 ` Ankur Arora
2022-06-06 20:37 ` [PATCH v3 10/21] x86/asm: add clear_pages_clzero() Ankur Arora
2022-06-06 20:37 ` [PATCH v3 11/21] x86/cpuid: add X86_FEATURE_MOVNT_SLOW Ankur Arora
2022-06-06 20:37 ` [PATCH v3 12/21] sparse: add address_space __incoherent Ankur Arora
2022-06-06 20:37 ` [PATCH v3 13/21] clear_page: add generic clear_user_pages_incoherent() Ankur Arora
2022-06-08 0:01 ` Luc Van Oostenryck
2022-06-12 11:19 ` Ankur Arora
2022-06-06 20:37 ` [PATCH v3 14/21] x86/clear_page: add clear_pages_incoherent() Ankur Arora
2022-06-06 20:37 ` [PATCH v3 15/21] mm/clear_page: add clear_page_non_caching_threshold() Ankur Arora
2022-06-06 20:37 ` [PATCH v3 16/21] x86/clear_page: add arch_clear_page_non_caching_threshold() Ankur Arora
2022-06-06 20:37 ` [PATCH v3 17/21] clear_huge_page: use non-cached clearing Ankur Arora
2022-06-06 20:37 ` [PATCH v3 18/21] gup: add FOLL_HINT_BULK, FAULT_FLAG_NON_CACHING Ankur Arora
2022-06-06 20:37 ` [PATCH v3 19/21] gup: hint non-caching if clearing large regions Ankur Arora
2022-06-06 20:37 ` [PATCH v3 20/21] vfio_iommu_type1: specify FOLL_HINT_BULK to pin_user_pages() Ankur Arora
2022-06-06 20:37 ` [PATCH v3 21/21] x86/cpu/intel: set X86_FEATURE_MOVNT_SLOW for Skylake Ankur Arora
2022-06-06 21:53 ` [PATCH v3 00/21] huge page clearing optimizations Linus Torvalds
2022-06-07 15:08 ` Ankur Arora
2022-06-07 17:56 ` Linus Torvalds
2022-06-08 19:24 ` Ankur Arora
2022-06-08 19:39 ` Linus Torvalds
2022-06-08 20:21 ` Ankur Arora
2022-06-08 19:49 ` Matthew Wilcox
2022-06-08 19:51 ` Matthew Wilcox
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=20220606203725.1313715-3-ankur.a.arora@oracle.com \
--to=ankur.a.arora@oracle.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=arnd@arndb.de \
--cc=boris.ostrovsky@oracle.com \
--cc=bp@alien8.de \
--cc=jgg@nvidia.com \
--cc=joao.m.martins@oracle.com \
--cc=jon.grimm@amd.com \
--cc=konrad.wilk@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mike.kravetz@oracle.com \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.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).