Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1622656 > unrolled thread
| Started by | Eric Anholt <eric@anholt.net> |
|---|---|
| First post | 2017-04-13 03:20 +0200 |
| Last post | 2017-04-13 03:20 +0200 |
| Articles | 1 — 1 participant |
Back to article view | Back to linux.kernel
This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by
below is the oldest one visible, not the original post.
Re: [PATCH] drm/vc4: Allow using more than 256MB of CMA memory. Eric Anholt <eric@anholt.net> - 2017-04-13 03:20 +0200
| From | Eric Anholt <eric@anholt.net> |
|---|---|
| Date | 2017-04-13 03:20 +0200 |
| Subject | Re: [PATCH] drm/vc4: Allow using more than 256MB of CMA memory. |
| Message-ID | <tvBAt-42S-5@gated-at.bofh.it> |
[Multipart message — attachments visible in raw view] — view raw
Eric Anholt <eric@anholt.net> writes: > Until now, we've had to limit Raspberry Pi to 256MB of CMA memory to > keep from triggering the hardware addressing bug between of the tile > binner of the tile alloc memory (where the top 4 bits come from the > tile state data array's address). > > To work around that and allow more memory to be reserved for graphics, > allocate a single BO to store tile state data arrays and tile > alloc/overflow memory while the GPU is active, and make sure that that > one BO doesn't happen to cross a 256MB boundary. With that in place, > we can allocate textures and shaders anywhere in system memory (still > contiguous, of course). Ping for reviewers on this one -- it's a pretty big usability win.
Back to top | Article view | linux.kernel
csiph-web