From: Xuefeng Wang <wxf.wang@hisilicon.com>
To: <arnd@arndb.de>, <akpm@linux-foundation.org>,
<catalin.marinas@arm.com>, <will@kernel.org>,
<mark.rutland@arm.com>
Cc: <linux-arch@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
<linux-mm@kvack.org>, <linux-arm-kernel@lists.infradead.org>,
<chenzhou10@huawei.com>
Subject: [PATCH 0/2] mm/thp: rework the pmd protect changing flow
Date: Thu, 16 Jan 2020 11:09:15 +0800 [thread overview]
Message-ID: <1579144157-7736-1-git-send-email-wxf.wang@hisilicon.com> (raw)
On KunPeng920 board. When changing permission of a large range region,
pmdp_invalidate() takes about 65% in profile (with hugepages) in JIT tool.
Kernel will flush tlb twice: first flush happens in pmdp_invalidate, second
flush happens at the end of change_protect_range(). The first pmdp_invalidate
is not necessary if the hardware support atomic pmdp changing. The atomic
changing pimd to zero can prevent the hardware from update asynchronous.
So reconstruct it and remove the first pmdp_invalidate. And the second tlb
flush can make sure the new tlb entry valid.
This patch series add a pmdp_modify_prot transaction abstraction firstly.
Then add pmdp_modify_prot_start() in arm64, which uses pmdp_huge_get_and_clear()
to atomically fetch the pmd and zero the entry.
After rework, the mprotect can get 3~13 times performace gain in range
64M to 512M on KunPeng920:
4K granule/THP on
memory size(M) 64 128 256 320 448 512
pre-patch 0.77 1.40 2.64 3.23 4.49 5.10
post-patch 0.20 0.23 0.28 0.31 0.37 0.39
Xuefeng Wang (2):
mm: add helpers pmdp_modify_prot_start/commit
arm64: mm: rework the pmd protect changing flow
arch/arm64/include/asm/pgtable.h | 14 +++++++++++++
include/asm-generic/pgtable.h | 35 ++++++++++++++++++++++++++++++++
mm/huge_memory.c | 19 ++++++++---------
3 files changed, 57 insertions(+), 11 deletions(-)
--
2.17.1
next reply other threads:[~2020-01-16 3:14 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-16 3:09 Xuefeng Wang [this message]
2020-01-16 3:09 ` [PATCH 1/2] mm: add helpers pmdp_modify_prot_start/commit Xuefeng Wang
2020-01-17 22:37 ` kbuild test robot
2020-01-20 15:05 ` kbuild test robot
2020-01-16 3:09 ` [PATCH 2/2] arm64: mm: rework the pmd protect changing flow Xuefeng Wang
2020-01-23 7:55 [PATCH 0/2] mm/thp: " Xuefeng Wang
2020-01-23 8:24 ` Anshuman Khandual
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=1579144157-7736-1-git-send-email-wxf.wang@hisilicon.com \
--to=wxf.wang@hisilicon.com \
--cc=akpm@linux-foundation.org \
--cc=arnd@arndb.de \
--cc=catalin.marinas@arm.com \
--cc=chenzhou10@huawei.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mark.rutland@arm.com \
--cc=will@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