From: Mike Snitzer <snitzer@redhat.com>
To: Ingo Molnar <mingo@kernel.org>, Thomas Gleixner <tglx@linutronix.de>
Cc: Dan Williams <dan.j.williams@intel.com>, X86 ML <x86@kernel.org>,
Mikulas Patocka <mpatocka@redhat.com>,
device-mapper development <dm-devel@redhat.com>
Subject: [PATCH v2] x86: optimize memcpy_flushcache
Date: Thu, 24 May 2018 14:20:15 -0400 [thread overview]
Message-ID: <20180524182013.GA59755@redhat.com> (raw)
In-Reply-To: <CAPcyv4jpY0x7kZtT+afAKnHKy8Uy1AC_N_QM7RrELSj_0iNrRw@mail.gmail.com>
[v2: revised header, reformatted asm, reduced indent in switch statement.
Ingo or Thomas: please review and consider picking this up for 4.18]
From: Mikulas Patocka <mpatocka@redhat.com>
Subject: [PATCH v2] x86: optimize memcpy_flushcache
In the context of constant short length stores to persistent memory,
memcpy_flushcache suffers from a 2% performance degradation compared to
explicitly using the "movnti" instruction.
Optimize 4, 8, and 16 byte memcpy_flushcache calls to explicitly use the
movnti instruction with inline assembler.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
arch/x86/include/asm/string_64.h | 28 +++++++++++++++++++++++++++-
arch/x86/lib/usercopy_64.c | 4 ++--
2 files changed, 29 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 533f74c300c2..aaba83478cdc 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -147,7 +147,33 @@ memcpy_mcsafe(void *dst, const void *src, size_t cnt)
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
#define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1
-void memcpy_flushcache(void *dst, const void *src, size_t cnt);
+void __memcpy_flushcache(void *dst, const void *src, size_t cnt);
+static __always_inline void memcpy_flushcache(void *dst, const void *src, size_t cnt)
+{
+ if (__builtin_constant_p(cnt)) {
+ switch (cnt) {
+ case 4:
+ asm volatile("movntil %1, %0"
+ : "=m" (*(u32 *)dst)
+ : "r" (*(u32 *)src));
+ return;
+ case 8:
+ asm volatile("movntiq %1, %0"
+ : "=m" (*(u64 *)dst)
+ : "r" (*(u64 *)src));
+ return;
+ case 16:
+ asm volatile("movntiq %1, %0"
+ : "=m" (*(u64 *)dst)
+ : "r" (*(u64 *)src));
+ asm volatile("movntiq %1, %0"
+ : "=m" (*(u64 *)(dst + 8))
+ : "r" (*(u64 *)(src + 8)));
+ return;
+ }
+ }
+ __memcpy_flushcache(dst, src, cnt);
+}
#endif
#endif /* __KERNEL__ */
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 75d3776123cc..26f515aa3529 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -133,7 +133,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
return rc;
}
-void memcpy_flushcache(void *_dst, const void *_src, size_t size)
+void __memcpy_flushcache(void *_dst, const void *_src, size_t size)
{
unsigned long dest = (unsigned long) _dst;
unsigned long source = (unsigned long) _src;
@@ -196,7 +196,7 @@ void memcpy_flushcache(void *_dst, const void *_src, size_t size)
clean_cache_range((void *) dest, size);
}
}
-EXPORT_SYMBOL_GPL(memcpy_flushcache);
+EXPORT_SYMBOL_GPL(__memcpy_flushcache);
void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
size_t len)
--
2.15.0
next prev parent reply other threads:[~2018-05-24 18:20 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-19 5:25 [patch 0/4] dm-writecache patches Mikulas Patocka
2018-05-19 5:25 ` [patch 1/4] x86: optimize memcpy_flushcache Mikulas Patocka
2018-05-19 14:21 ` Dan Williams
2018-05-24 18:20 ` Mike Snitzer [this message]
2018-06-18 13:23 ` [PATCH v2 RESEND] " Mike Snitzer
2018-06-21 14:31 ` Ingo Molnar
2018-06-22 1:19 ` Mikulas Patocka
2018-06-22 1:30 ` Ingo Molnar
2018-08-08 21:22 ` [PATCH v3 " Mikulas Patocka
2018-09-10 13:18 ` Ingo Molnar
2018-09-11 6:22 ` [tip:x86/asm] x86/asm: Optimize memcpy_flushcache() tip-bot for Mikulas Patocka
2018-05-19 5:25 ` [patch 2/4] swait: export the symbols __prepare_to_swait and __finish_swait Mikulas Patocka
2018-05-22 6:34 ` Christoph Hellwig
2018-05-22 18:52 ` Mike Snitzer
2018-05-23 9:21 ` Peter Zijlstra
2018-05-23 15:10 ` Mike Snitzer
2018-05-23 18:10 ` [PATCH v2] swait: export " Mike Snitzer
2018-05-23 20:38 ` Mikulas Patocka
2018-05-23 21:51 ` Mike Snitzer
2018-05-24 14:10 ` Peter Zijlstra
2018-05-24 15:09 ` Mike Snitzer
2018-05-19 5:25 ` [patch 3/4] dm-writecache Mikulas Patocka
2018-05-22 6:37 ` Christoph Hellwig
2018-05-19 5:25 ` [patch 4/4] dm-writecache: use new API for flushing Mikulas Patocka
[not found] ` <20180519052635.567438191-59tzFEB+POEAvxtiuMwx3w@public.gmane.org>
2018-05-22 6:39 ` [dm-devel] " Christoph Hellwig
[not found] ` <20180522063946.GB8054-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
2018-05-22 18:41 ` Mike Snitzer
[not found] ` <20180522184103.GA25826-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2018-05-22 19:00 ` Dan Williams
[not found] ` <CAPcyv4g395RccdEPF=sCu5RdCH9zwD+GvOfSp7-F0Oh64CeDgA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-05-22 19:19 ` Mike Snitzer
[not found] ` <20180522191942.GB25904-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2018-05-22 19:27 ` Dan Williams
[not found] ` <CAPcyv4hWswV=VCfB7KatoW_zc-kUUju2jD45N-Gsg4sW-XFe-A-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-05-22 20:52 ` Mike Snitzer
[not found] ` <20180522205214.GA26259-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2018-05-22 22:53 ` [dm-devel] " Jeff Moyer
[not found] ` <x49r2m3nvyk.fsf-RRHT56Q3PSP4kTEheFKJxxDDeQx5vsVwAInAS/Ez/D0@public.gmane.org>
2018-05-23 20:57 ` Mikulas Patocka
2018-05-28 13:52 ` Mikulas Patocka
[not found] ` <alpine.LRH.2.02.1805280943460.16538-Hpncn10jQN4oNljnaZt3ZvA+iT7yCHsGwRM8/txMwJMAicBL8TP8PQ@public.gmane.org>
2018-05-28 17:41 ` Dan Williams
[not found] ` <CAPcyv4gxCNqqG2G3R6f=kH3zNbByhgE2R-trJWurH49-p+51Gg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-05-30 13:42 ` [dm-devel] " Jeff Moyer
[not found] ` <x49h8mpmf8v.fsf-RRHT56Q3PSP4kTEheFKJxxDDeQx5vsVwAInAS/Ez/D0@public.gmane.org>
2018-05-30 13:51 ` Mikulas Patocka
2018-05-30 13:52 ` Jeff Moyer
2018-05-24 8:15 ` Mikulas Patocka
2018-05-25 3:12 ` Dan Williams
2018-05-25 6:17 ` Mikulas Patocka
[not found] ` <alpine.LRH.2.02.1805250213270.13894-Hpncn10jQN4oNljnaZt3ZvA+iT7yCHsGwRM8/txMwJMAicBL8TP8PQ@public.gmane.org>
2018-05-25 12:51 ` Mike Snitzer
[not found] ` <20180525125126.GA9275-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2018-05-25 15:57 ` Dan Williams
[not found] ` <CAPcyv4j-v5HGBg9JMBXt7UUyw=K_bGC7t5tQGfXM9G4qjOpFjQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-05-26 7:02 ` Mikulas Patocka
[not found] ` <alpine.LRH.2.02.1805260246250.15978-Hpncn10jQN4oNljnaZt3ZvA+iT7yCHsGwRM8/txMwJMAicBL8TP8PQ@public.gmane.org>
2018-05-26 15:26 ` Dan Williams
[not found] ` <CAPcyv4jwLsCNvNhgvv2DDSZuQsQXYEpKUU_5w1pTnyKj-uDBbQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-05-28 13:32 ` Mikulas Patocka
[not found] ` <alpine.LRH.2.02.1805280922190.13486-Hpncn10jQN4oNljnaZt3ZvA+iT7yCHsGwRM8/txMwJMAicBL8TP8PQ@public.gmane.org>
2018-05-28 18:14 ` Dan Williams
[not found] ` <CAPcyv4jXV4aZ6wqqjVPL8J4LxwTtXnzQCLZ0Wk5oB4_0uxpg7g-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-05-30 13:07 ` Mikulas Patocka
[not found] ` <alpine.LRH.2.02.1805300903220.1090-Hpncn10jQN4oNljnaZt3ZvA+iT7yCHsGwRM8/txMwJMAicBL8TP8PQ@public.gmane.org>
2018-05-30 13:16 ` Mike Snitzer
[not found] ` <20180530131623.GB2106-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2018-05-30 13:21 ` Mikulas Patocka
[not found] ` <alpine.LRH.2.02.1805300919070.11327-Hpncn10jQN4oNljnaZt3ZvA+iT7yCHsGwRM8/txMwJMAicBL8TP8PQ@public.gmane.org>
2018-05-30 13:26 ` Mike Snitzer
[not found] ` <20180530132647.GB5157-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2018-05-30 13:33 ` Mikulas Patocka
[not found] ` <alpine.LRH.2.02.1805300929500.11327-Hpncn10jQN4oNljnaZt3ZvA+iT7yCHsGwRM8/txMwJMAicBL8TP8PQ@public.gmane.org>
2018-05-30 13:54 ` Mike Snitzer
[not found] ` <20180530135421.GA81788-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2018-05-30 14:09 ` Mikulas Patocka
[not found] ` <alpine.LRH.2.02.1805300959460.16696-Hpncn10jQN4oNljnaZt3ZvA+iT7yCHsGwRM8/txMwJMAicBL8TP8PQ@public.gmane.org>
2018-05-30 14:21 ` Mike Snitzer
[not found] ` <20180530142104.GA5416-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2018-05-30 14:46 ` Mikulas Patocka
[not found] ` <alpine.LRH.2.02.1805301023380.21890-Hpncn10jQN4oNljnaZt3ZvA+iT7yCHsGwRM8/txMwJMAicBL8TP8PQ@public.gmane.org>
2018-05-31 3:42 ` Mike Snitzer
[not found] ` <20180531034216.GB88973-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2018-06-03 15:03 ` Mikulas Patocka
2018-05-31 3:39 ` Mike Snitzer
[not found] ` <20180531033919.GA88973-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2018-05-31 8:16 ` Mikulas Patocka
[not found] ` <alpine.LRH.2.02.1805310412240.30096-Hpncn10jQN4oNljnaZt3ZvA+iT7yCHsGwRM8/txMwJMAicBL8TP8PQ@public.gmane.org>
2018-05-31 12:09 ` Mike Snitzer
2018-05-30 15:58 ` Dan Williams
[not found] ` <CAPcyv4j3pDQ3YMK5Eije0dgGw+1CQYazPJ-zvqfvGF-9O_gVJw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-05-30 22:39 ` Dan Williams
[not found] ` <CAPcyv4gD-ZaXyV1SFAndobUYJOGLkx9rOyb5zNbzJXB_kVCzoA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-05-31 8:19 ` Mikulas Patocka
[not found] ` <alpine.LRH.2.02.1805310416540.30096-Hpncn10jQN4oNljnaZt3ZvA+iT7yCHsGwRM8/txMwJMAicBL8TP8PQ@public.gmane.org>
2018-05-31 14:51 ` Dan Williams
[not found] ` <CAPcyv4gzFbdBbUhPJ6W4mTJWAkvqVw_4FVhVdePEJzc28Sg-Sg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-05-31 15:31 ` Mikulas Patocka
[not found] ` <alpine.LRH.2.02.1805311127001.31059-Hpncn10jQN4oNljnaZt3ZvA+iT7yCHsGwRM8/txMwJMAicBL8TP8PQ@public.gmane.org>
2018-05-31 16:39 ` Dan Williams
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=20180524182013.GA59755@redhat.com \
--to=snitzer@redhat.com \
--cc=dan.j.williams@intel.com \
--cc=dm-devel@redhat.com \
--cc=mingo@kernel.org \
--cc=mpatocka@redhat.com \
--cc=tglx@linutronix.de \
--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