From: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
To: Rob Herring <robh@kernel.org>
Cc: Rob Clark <robdclark@chromium.org>,
Tomeu Vizoso <tomeu.vizoso@collabora.com>,
David Airlie <airlied@linux.ie>,
dri-devel@lists.freedesktop.org,
Steven Price <steven.price@arm.com>
Subject: Re: [PATCH 2/2] drm/panfrost: Add madvise and shrinker support
Date: Mon, 5 Aug 2019 08:52:09 -0700 [thread overview]
Message-ID: <20190805155209.GA5909@kevin> (raw)
In-Reply-To: <20190805143358.21245-2-robh@kernel.org>
[-- Attachment #1.1: Type: text/plain, Size: 1220 bytes --]
> +/* madvise provides a way to tell the kernel in case a buffers contents
> + * can be discarded under memory pressure, which is useful for userspace
> + * bo cache where we want to optimistically hold on to buffer allocate
> + * and potential mmap, but allow the pages to be discarded under memory
> + * pressure.
> + *
> + * Typical usage would involve madvise(DONTNEED) when buffer enters BO
> + * cache, and madvise(WILLNEED) if trying to recycle buffer from BO cache.
> + * In the WILLNEED case, 'retained' indicates to userspace whether the
> + * backing pages still exist.
> + */
> +#define PANFROST_MADV_WILLNEED 0 /* backing pages are needed, status returned in 'retained' */
> +#define PANFROST_MADV_DONTNEED 1 /* backing pages not needed */
> +
> +struct drm_panfrost_madvise {
> + __u32 handle; /* in, GEM handle */
> + __u32 madv; /* in, PANFROST_MADV_x */
> + __u32 retained; /* out, whether backing store still exists */
> +};
Just to clarify about the `retained` flag: if userspace does a
madvise(WILLNEED) and we find out that retained=0, what's supposed to
happen?
Should userspace evict the BO from its local cache and allocate one
fresh? Or just remmap? Or something else?
[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
[-- Attachment #2: Type: text/plain, Size: 159 bytes --]
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2019-08-05 15:52 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-05 14:33 [PATCH 1/2] drm/shmem: Add madvise state and purge helpers Rob Herring
2019-08-05 14:33 ` [PATCH 2/2] drm/panfrost: Add madvise and shrinker support Rob Herring
2019-08-05 15:52 ` Alyssa Rosenzweig [this message]
2019-08-05 20:55 ` Rob Herring
2019-08-05 21:08 ` Alyssa Rosenzweig
2019-08-05 16:35 ` [PATCH 1/2] drm/shmem: Add madvise state and purge helpers Daniel Vetter
2019-08-05 17:47 ` Rob Clark
2019-08-05 21:17 ` Rob Herring
2019-10-16 19:20 ` Sean Paul
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=20190805155209.GA5909@kevin \
--to=alyssa.rosenzweig@collabora.com \
--cc=airlied@linux.ie \
--cc=dri-devel@lists.freedesktop.org \
--cc=robdclark@chromium.org \
--cc=robh@kernel.org \
--cc=steven.price@arm.com \
--cc=tomeu.vizoso@collabora.com \
/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).