linux/drivers/gpu/host1x
Mikko Perttunen f0fb260a0c gpu: host1x: Implement syncpoint wait using DMA fences
In anticipation of removal of the intr API, move host1x_syncpt_wait
to use DMA fences instead. As of this patch, this means that waits
have a 30 second maximum timeout because of the implicit timeout
we have with fences, but that will be lifted in a follow-up patch.

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
2023-01-26 15:55:38 +01:00
..
hw gpu: host1x: Don't skip assigning syncpoints to channels 2023-01-26 15:55:38 +01:00
bus.c gpu: host1x: Add missing DMA API include 2021-12-16 14:07:07 +01:00
bus.h treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 201 2019-05-30 11:29:52 -07:00
cdma.c gpu: host1x: Generalize host1x_cdma_push_wide() 2022-07-08 17:36:26 +02:00
cdma.h treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 201 2019-05-30 11:29:52 -07:00
channel.c gpu: host1x: Use the bitmap API to allocate bitmaps 2022-07-08 17:38:34 +02:00
channel.h gpu: host1x: Request channels for clients, not devices 2019-10-28 11:18:33 +01:00
context_bus.c gpu: host1x: Register context bus unconditionally 2022-07-08 16:31:24 +02:00
context.c gpu: host1x: Select context device based on attached IOMMU 2022-11-25 16:14:19 +01:00
context.h gpu: host1x: Add context device management code 2022-07-08 16:27:52 +02:00
debug.c gpu: host1x: Use DEFINE_SHOW_ATTRIBUTE to simplify debugfs code 2022-11-25 16:14:59 +01:00
debug.h treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 201 2019-05-30 11:29:52 -07:00
dev.c gpu: host1x: Add stream ID register data for NVDEC on Tegra234 2022-11-25 16:14:58 +01:00
dev.h gpu: host1x: Program virtualization tables 2022-07-08 16:27:52 +02:00
fence.c gpu: host1x: Staticize host1x_syncpt_fence_ops 2022-11-25 16:14:59 +01:00
fence.h gpu: host1x: Add DMA fence implementation 2021-08-10 14:39:50 +02:00
intr.c gpu: host1x: Add initial runtime PM and OPP support 2021-12-16 14:07:07 +01:00
intr.h gpu: host1x: Add DMA fence implementation 2021-08-10 14:39:50 +02:00
job.c gpu: host1x: Do not use mapping cache for job submissions 2022-04-06 15:12:36 +02:00
job.h drm/tegra: Implement correct DMA-BUF semantics 2021-12-16 14:07:06 +01:00
Kconfig gpu: host1x: Add context bus 2022-06-01 11:50:42 +02:00
Makefile gpu: host1x: Tegra234 device data and headers 2022-07-08 16:27:52 +02:00
mipi.c media: gpu: host1x: mipi: Keep MIPI clock enabled and mutex locked till calibration done 2020-08-28 15:12:38 +02:00
syncpt.c gpu: host1x: Implement syncpoint wait using DMA fences 2023-01-26 15:55:38 +01:00
syncpt.h gpu: host1x: Add no-recovery mode 2021-08-10 14:40:23 +02:00