All of lore.kernel.org
 help / color / mirror / Atom feed
From: Daniel Kolesa <daniel@octaforge.org>
To: amd-gfx@lists.freedesktop.org
Cc: Daniel Kolesa <daniel@octaforge.org>
Subject: [PATCH 0/1] Fix Navi cards crashing with FP exception on 5.6+
Date: Wed, 29 Apr 2020 17:02:35 +0200	[thread overview]
Message-ID: <20200429150236.4626-1-daniel@octaforge.org> (raw)

This is not a real fix, but rather a workaround that should be applied to the
5.6 tree and newer. The idea here is to work around the compiler emitting FP
instructions outside the DC_FP_START/DC_FP_END blocks, which it currently does,
which causes crashes at least on ppc64le.

A proper solution would be to move all the floating point code into its own
files, then compile those with hard-float and strictly wrap all calls into
those with the DC_FP_START/DC_FP_END blocks, with the rest of the code being
compiled without floating point, but that's too extensive of a change to do,
and would not be possible in a stable tree.

The proper solution is already being discussed, it seems:

https://lore.kernel.org/lkml/CAG48ez2Sx4ELkM94aD_h_J7K7KBOeuGmvZLKRkg3n_f2WoZ_cg@mail.gmail.com/

Daniel Kolesa (1):
  drm/amd/display: work around fp code being emitted outside of
    DC_FP_START/END

 .../drm/amd/display/dc/dcn20/dcn20_resource.c | 31 ++++++++++++++-----
 1 file changed, 23 insertions(+), 8 deletions(-)

-- 
2.26.2

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

             reply	other threads:[~2020-04-29 15:08 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-29 15:02 Daniel Kolesa [this message]
2020-04-29 15:02 ` [PATCH 1/1] drm/amd/display: work around fp code being emitted outside of DC_FP_START/END Daniel Kolesa
2020-04-30 14:58   ` Alex Deucher

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=20200429150236.4626-1-daniel@octaforge.org \
    --to=daniel@octaforge.org \
    --cc=amd-gfx@lists.freedesktop.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.