From: Jarkko Sakkinen <jarkko@kernel.org>
To: Dave Hansen <dave.hansen@intel.com>
Cc: linux-sgx@vger.kernel.org,
Dave Hansen <dave.hansen@linux.intel.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3 4/5] x86/sgx: Replace section->page_list with a global free page list
Date: Wed, 10 Mar 2021 12:54:49 +0200 [thread overview]
Message-ID: <YEilecZyT93xdtc1@kernel.org> (raw)
In-Reply-To: <49b4f4d9-3f49-efd0-ce44-c24d1ee3daa6@intel.com>
On Wed, Mar 03, 2021 at 03:48:46PM -0800, Dave Hansen wrote:
> On 3/3/21 7:03 AM, Jarkko Sakkinen wrote:
> > Background
> > ==========
> >
> > EPC section is covered by one or more SRAT entries that are associated with
> > one and only one PXM (NUMA node). The current implementation overheats a
>
> Overheats?
>
> > single NUMA node, because sgx_alloc_epc_page() always starts looking for
> > pages from the same EPC section everytime.
>
> "every time"
>
> > Only within a section it does pick pages in FIFO fashion, i.e. the oldest
> > freed in that section is the EPC page given back to the caller. That does
> > not do any good, as the pages in the same node are performance-wise equal.
>
> I'm not sure why all of this is relevant and it doesn't really tell me
> anything about this patch's place in the *series*.
>
> Why are we destroying all of the per-node structures just before adding
> NUMA support?
These are per-section structures, not per-node structures. Probably most
times, if not all times, they are equal, but conceptually I'm not
destroying per-node structures :-) I'm introducing them in 5/5.
/Jarkko
next prev parent reply other threads:[~2021-03-10 10:56 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20210303150323.433207-1-jarkko@kernel.org>
2021-03-03 15:03 ` [PATCH v3 1/5] x86/sgx: Fix a resource leak in sgx_init() Jarkko Sakkinen
2021-03-03 16:56 ` Dave Hansen
2021-03-10 15:00 ` Jarkko Sakkinen
2021-03-10 15:49 ` Sean Christopherson
2021-03-10 21:52 ` Jarkko Sakkinen
2021-03-03 15:03 ` [PATCH v3 2/5] x86/sgx: Use sgx_free_epc_page() in sgx_reclaim_pages() Jarkko Sakkinen
2021-03-03 16:59 ` Dave Hansen
2021-03-10 15:11 ` Jarkko Sakkinen
2021-03-10 15:55 ` Dave Hansen
2021-03-10 21:56 ` Jarkko Sakkinen
2021-03-10 20:36 ` Kai Huang
2021-03-10 22:10 ` Jarkko Sakkinen
2021-03-10 22:12 ` Jarkko Sakkinen
2021-03-10 22:35 ` Jarkko Sakkinen
2021-03-10 22:43 ` Kai Huang
2021-03-10 22:52 ` Kai Huang
2021-03-03 15:03 ` [PATCH v3 3/5] x86/sgx: Replace section->init_laundry_list with a temp list Jarkko Sakkinen
2021-03-03 18:02 ` Dave Hansen
2021-03-10 14:50 ` Jarkko Sakkinen
2021-03-03 15:03 ` [PATCH v3 4/5] x86/sgx: Replace section->page_list with a global free page list Jarkko Sakkinen
2021-03-03 23:48 ` Dave Hansen
2021-03-10 10:54 ` Jarkko Sakkinen [this message]
2021-03-03 15:03 ` [PATCH v3 5/5] x86/sgx: Add a basic NUMA allocation scheme to sgx_alloc_epc_page() Jarkko Sakkinen
2021-03-04 0:20 ` Dave Hansen
2021-03-10 11:30 ` Jarkko Sakkinen
2021-03-10 15:44 ` Dave Hansen
2021-03-10 21:48 ` Jarkko Sakkinen
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=YEilecZyT93xdtc1@kernel.org \
--to=jarkko@kernel.org \
--cc=bp@alien8.de \
--cc=dave.hansen@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-sgx@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