From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
To: Changbin Du <changbin.du@gmail.com>
Cc: Jonathan Corbet <corbet@lwn.net>,
tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
x86@kernel.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 09/27] Documentation: x86: convert tlb.txt to reST
Date: Sat, 27 Apr 2019 14:21:19 -0300 [thread overview]
Message-ID: <20190427142119.594f58ae@coco.lan> (raw)
In-Reply-To: <20190426153150.21228-10-changbin.du@gmail.com>
Em Fri, 26 Apr 2019 23:31:32 +0800
Changbin Du <changbin.du@gmail.com> escreveu:
> This converts the plain text documentation to reStructuredText format and
> add it to Sphinx TOC tree. No essential content change.
>
> Signed-off-by: Changbin Du <changbin.du@gmail.com>
Reviewed-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
> ---
> Documentation/x86/index.rst | 1 +
> Documentation/x86/{tlb.txt => tlb.rst} | 30 ++++++++++++++++----------
> 2 files changed, 20 insertions(+), 11 deletions(-)
> rename Documentation/x86/{tlb.txt => tlb.rst} (81%)
>
> diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst
> index 9a0b5f38ef6b..fd54b859db9b 100644
> --- a/Documentation/x86/index.rst
> +++ b/Documentation/x86/index.rst
> @@ -15,3 +15,4 @@ Linux x86 Support
> entry_64
> earlyprintk
> zero-page
> + tlb
> diff --git a/Documentation/x86/tlb.txt b/Documentation/x86/tlb.rst
> similarity index 81%
> rename from Documentation/x86/tlb.txt
> rename to Documentation/x86/tlb.rst
> index 6a0607b99ed8..82ec58ae63a8 100644
> --- a/Documentation/x86/tlb.txt
> +++ b/Documentation/x86/tlb.rst
> @@ -1,5 +1,12 @@
> +.. SPDX-License-Identifier: GPL-2.0
> +
> +=======
> +The TLB
> +=======
> +
> When the kernel unmaps or modified the attributes of a range of
> memory, it has two choices:
> +
> 1. Flush the entire TLB with a two-instruction sequence. This is
> a quick operation, but it causes collateral damage: TLB entries
> from areas other than the one we are trying to flush will be
> @@ -10,6 +17,7 @@ memory, it has two choices:
> damage to other TLB entries.
>
> Which method to do depends on a few things:
> +
> 1. The size of the flush being performed. A flush of the entire
> address space is obviously better performed by flushing the
> entire TLB than doing 2^48/PAGE_SIZE individual flushes.
> @@ -33,7 +41,7 @@ well. There is essentially no "right" point to choose.
> You may be doing too many individual invalidations if you see the
> invlpg instruction (or instructions _near_ it) show up high in
> profiles. If you believe that individual invalidations being
> -called too often, you can lower the tunable:
> +called too often, you can lower the tunable::
>
> /sys/kernel/debug/x86/tlb_single_page_flush_ceiling
>
> @@ -43,7 +51,7 @@ Setting it to 1 is a very conservative setting and it should
> never need to be 0 under normal circumstances.
>
> Despite the fact that a single individual flush on x86 is
> -guaranteed to flush a full 2MB [1], hugetlbfs always uses the full
> +guaranteed to flush a full 2MB [1]_, hugetlbfs always uses the full
> flushes. THP is treated exactly the same as normal memory.
>
> You might see invlpg inside of flush_tlb_mm_range() show up in
> @@ -54,15 +62,15 @@ Essentially, you are balancing the cycles you spend doing invlpg
> with the cycles that you spend refilling the TLB later.
>
> You can measure how expensive TLB refills are by using
> -performance counters and 'perf stat', like this:
> +performance counters and 'perf stat', like this::
>
> -perf stat -e
> - cpu/event=0x8,umask=0x84,name=dtlb_load_misses_walk_duration/,
> - cpu/event=0x8,umask=0x82,name=dtlb_load_misses_walk_completed/,
> - cpu/event=0x49,umask=0x4,name=dtlb_store_misses_walk_duration/,
> - cpu/event=0x49,umask=0x2,name=dtlb_store_misses_walk_completed/,
> - cpu/event=0x85,umask=0x4,name=itlb_misses_walk_duration/,
> - cpu/event=0x85,umask=0x2,name=itlb_misses_walk_completed/
> + perf stat -e
> + cpu/event=0x8,umask=0x84,name=dtlb_load_misses_walk_duration/,
> + cpu/event=0x8,umask=0x82,name=dtlb_load_misses_walk_completed/,
> + cpu/event=0x49,umask=0x4,name=dtlb_store_misses_walk_duration/,
> + cpu/event=0x49,umask=0x2,name=dtlb_store_misses_walk_completed/,
> + cpu/event=0x85,umask=0x4,name=itlb_misses_walk_duration/,
> + cpu/event=0x85,umask=0x2,name=itlb_misses_walk_completed/
>
> That works on an IvyBridge-era CPU (i5-3320M). Different CPUs
> may have differently-named counters, but they should at least
> @@ -70,6 +78,6 @@ be there in some form. You can use pmu-tools 'ocperf list'
> (https://github.com/andikleen/pmu-tools) to find the right
> counters for a given CPU.
>
> -1. A footnote in Intel's SDM "4.10.4.2 Recommended Invalidation"
> +.. [1] A footnote in Intel's SDM "4.10.4.2 Recommended Invalidation"
> says: "One execution of INVLPG is sufficient even for a page
> with size greater than 4 KBytes."
Thanks,
Mauro
next prev parent reply other threads:[~2019-04-27 17:21 UTC|newest]
Thread overview: 68+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-26 15:31 [PATCH 00/27] Include linux x86 docs into Sphinx TOC tree Changbin Du
2019-04-26 15:31 ` [PATCH 01/27] Documentation: add Linux x86 docs to " Changbin Du
2019-04-26 16:16 ` Borislav Petkov
2019-04-27 2:43 ` Changbin Du
2019-04-26 15:31 ` [PATCH 02/27] Documentation: x86: convert boot.txt to reST Changbin Du
2019-04-27 14:31 ` Mauro Carvalho Chehab
2019-05-02 6:59 ` Changbin Du
2019-04-26 15:31 ` [PATCH 03/27] Documentation: x86: convert topology.txt " Changbin Du
2019-04-27 14:41 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 04/27] Documentation: x86: convert exception-tables.txt " Changbin Du
2019-04-27 14:48 ` Mauro Carvalho Chehab
2019-05-02 3:19 ` Changbin Du
2019-04-26 15:31 ` [PATCH 05/27] Documentation: x86: convert kernel-stacks " Changbin Du
2019-04-27 14:50 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 06/27] Documentation: x86: convert entry_64.txt " Changbin Du
2019-04-27 14:52 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 07/27] Documentation: x86: convert earlyprintk.txt " Changbin Du
2019-04-27 17:17 ` Mauro Carvalho Chehab
2019-05-02 3:27 ` Changbin Du
2019-04-26 15:31 ` [PATCH 08/27] Documentation: x86: convert zero-page.txt " Changbin Du
2019-04-27 17:19 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 09/27] Documentation: x86: convert tlb.txt " Changbin Du
2019-04-27 17:21 ` Mauro Carvalho Chehab [this message]
2019-04-26 15:31 ` [PATCH 10/27] Documentation: x86: convert mtrr.txt " Changbin Du
2019-04-27 17:32 ` Mauro Carvalho Chehab
2019-04-27 18:10 ` Mauro Carvalho Chehab
2019-05-02 5:03 ` Changbin Du
2019-04-26 15:31 ` [PATCH 11/27] Documentation: x86: convert pat.txt " Changbin Du
2019-04-27 17:51 ` Mauro Carvalho Chehab
2019-05-02 5:25 ` Changbin Du
2019-04-26 15:31 ` [PATCH 12/27] Documentation: x86: convert protection-keys.txt " Changbin Du
2019-04-27 17:53 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 13/27] Documentation: x86: convert intel_mpx.txt " Changbin Du
2019-04-27 17:54 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 14/27] Documentation: x86: convert amd-memory-encryption.txt " Changbin Du
2019-04-27 17:55 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 15/27] Documentation: x86: convert pti.txt " Changbin Du
2019-04-27 17:57 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 16/27] Documentation: x86: convert microcode.txt " Changbin Du
2019-04-27 17:58 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 17/27] Documentation: x86: convert resctrl_ui.txt " Changbin Du
2019-04-27 18:09 ` Mauro Carvalho Chehab
2019-05-02 5:37 ` Changbin Du
2019-04-26 15:31 ` [PATCH 18/27] Documentation: x86: convert orc-unwinder.txt " Changbin Du
2019-04-27 18:16 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 19/27] Documentation: x86: convert usb-legacy-support.txt " Changbin Du
2019-04-27 18:20 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 20/27] Documentation: x86: convert i386/IO-APIC.txt " Changbin Du
2019-04-27 18:24 ` Mauro Carvalho Chehab
2019-05-02 5:42 ` Changbin Du
2019-04-26 15:31 ` [PATCH 21/27] Documentation: x86: convert x86_64/boot-options.txt " Changbin Du
2019-04-27 18:30 ` Mauro Carvalho Chehab
2019-05-02 5:49 ` Changbin Du
2019-04-26 15:31 ` [PATCH 22/27] Documentation: x86: convert x86_64/uefi.txt " Changbin Du
2019-04-27 18:31 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 23/27] Documentation: x86: convert x86_64/mm.txt " Changbin Du
2019-04-27 18:35 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 24/27] Documentation: x86: convert x86_64/5level-paging.txt " Changbin Du
2019-04-27 18:36 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 25/27] Documentation: x86: convert x86_64/fake-numa-for-cpusets " Changbin Du
2019-04-27 18:38 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 26/27] Documentation: x86: convert x86_64/cpu-hotplug-spec " Changbin Du
2019-04-27 18:40 ` Mauro Carvalho Chehab
2019-04-26 15:31 ` [PATCH 27/27] Documentation: x86: convert x86_64/machinecheck " Changbin Du
2019-04-27 18:42 ` Mauro Carvalho Chehab
2019-04-26 15:39 ` [PATCH 00/27] Include linux x86 docs into Sphinx TOC tree Mauro Carvalho Chehab
2019-04-27 2:47 ` Changbin Du
2019-04-27 9:54 ` Mauro Carvalho Chehab
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=20190427142119.594f58ae@coco.lan \
--to=mchehab+samsung@kernel.org \
--cc=bp@alien8.de \
--cc=changbin.du@gmail.com \
--cc=corbet@lwn.net \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@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;
as well as URLs for NNTP newsgroup(s).