The bulk of these changes are preparation work and addition of support
for Tegra186. Currently only HDMI output (the primary output on Jetson
TX2) is supported, but the hardware is also capable of doing DSI and
DisplayPort.
Tegra DRM now also uses the atomic commit helpers instead of the open-
coded variant that was only doing half its job. As a bit of a byproduct
of the Tegra186 support the driver also gained HDMI 2.0 as well as zpos
property support.
Along the way there are also a few patches to clean up a few things and
fix minor issues.
-----BEGIN PGP SIGNATURE-----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=FfXI
-----END PGP SIGNATURE-----
Merge tag 'drm/tegra/for-4.16-rc1-fixes' of git://anongit.freedesktop.org/tegra/linux into drm-next
drm/tegra: Changes for v4.16-rc1
The bulk of these changes are preparation work and addition of support
for Tegra186. Currently only HDMI output (the primary output on Jetson
TX2) is supported, but the hardware is also capable of doing DSI and
DisplayPort.
Tegra DRM now also uses the atomic commit helpers instead of the open-
coded variant that was only doing half its job. As a bit of a byproduct
of the Tegra186 support the driver also gained HDMI 2.0 as well as zpos
property support.
Along the way there are also a few patches to clean up a few things and
fix minor issues.
* tag 'drm/tegra/for-4.16-rc1-fixes' of git://anongit.freedesktop.org/tegra/linux: (51 commits)
drm/tegra: dc: Properly cleanup overlay planes
drm/tegra: dc: Fix possible_crtcs mask for planes
drm/tegra: dc: Restore YUV overlay support
drm/tegra: dc: Implement legacy blending
drm/tegra: Correct timeout in tegra_syncpt_wait
drm/tegra: gem: Correct iommu_map_sg() error checking
drm/tegra: dc: Link DC1 to DC0 on Tegra20
drm/tegra: Fix non-debugfs builds
drm/tegra: dpaux: Keep reset defaults for hybrid pad parameters
drm/tegra: Mark Tegra186 display hub PM functions __maybe_unused
drm/tegra: Use IOMMU groups
gpu: host1x: Use IOMMU groups
drm/tegra: Implement zpos property
drm/tegra: dc: Remove redundant spinlock
drm/tegra: dc: Use direct offset to plane registers
drm/tegra: dc: Support more formats
drm/tegra: fb: Force alpha formats
drm/tegra: dpaux: Add Tegra186 support
drm/tegra: dpaux: Implement runtime PM
drm/tegra: sor: Support HDMI 2.0 modes
...
Updates for 4.16.. fairly small this time around, main thing is
devfreq support for the gpu.
* tag 'drm-msm-next-2018-01-10' of git://people.freedesktop.org/~robclark/linux:
drm/msm: Add devfreq support for the GPU
drm/msm/adreno: a5xx: Explicitly program the CP0 performance counter
drm/msm/adreno: Read the speed bins for a5xx targets
drm/msm/adreno: Move clock parsing to adreno_gpu_init()
drm/msm/adreno: Cleanup chipid parsing
drm/msm/gpu: Remove unused bus scaling code
drm/msm/adreno: Remove a useless call to dev_pm_opp_get_freq()
drm/msm/adreno: Call dev_pm_opp_put()
drm/msm: Fix NULL deref in adreno_load_gpu
drm/msm: gpu: Only sync fences on rings that exist
drm/msm: fix leak in failed get_pages
drm/msm: avoid false-positive -Wmaybe-uninitialized warning
drm/msm/mdp4: Deduplicate bus_find_device() by name matching
drm/msm: add missing MODULE_FIRMWARE declarations
drm/msm: update adreno firmware path in MODULE_FIRMWARE
drm/msm: free kstrdup'd cmdline
drm/msm: fix msm_rd_dump_submit prototype
drm/msm: fix spelling mistake: "ringubffer" -> "ringbuffer"
Add support for devfreq to dynamically control the GPU frequency.
By default try to use the 'simple_ondemand' governor which can
adjust the frequency based on GPU load.
v2: Fix __aeabi_uldivmod issue from the 0 day bot and use
devfreq_recommended_opp() as suggested by Rob.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
Even though the default countable for CP0 is CP_ALWAYS_COUNT (0),
program the selector during HW initialization in an effort to be
up front about which counters are programmed and why.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
Some 5xx based chipsets have different bins for GPU clock speeds.
Read the fuses (if applicable) and set the appropriate OPP table.
This will only work with OPP v2 tables - the bin will be ignored
for legacy pwrlevel tables.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
Move the clock parsing to adreno_gpu_init() to allow for target
specific probing and manipulation of the clock tables.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
We don't need to convert the chipid to an intermediate value and
then back again into a struct adreno_rev.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
Remove the downstream bus scaling code. It isn't needed for for
compatibility with a downstream or vendor kernel. Get it out of the
way to clear space for devfreq support.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
Calling dev_pm_opp_find_freq_floor() returns the matched frequency
in 'freq'. We don't need to call dev_pm_opp_get_freq() again
to get the frequency value.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
We need to call dev_pm_opp_put() to put back the reference
for the OPP struct after calling the various dev_pm_opp_get_*
functions.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
The newly added get_local_mem_info() function prints a phys_addr_t
using 0x%llx, which is wrong on most 32-bit systems, as shown by
this warning:
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c: In function 'get_local_mem_info':
include/linux/kern_levels.h:5:18: error: format '%llx' expects argument of type 'long long unsigned int', but argument 2 has type 'resource_size_t {aka unsigned int}' [-Werror=format=]
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c:297:31: note: format string is defined here
pr_debug("Address base: 0x%llx limit 0x%llx public 0x%llx private 0x%llx\n",
Passing the address by reference to the special %pap format string will
produce the correct output and avoid the warning.
Fixes: 30f1c0421e ("drm/amdgpu: Implement get_local_mem_info")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Last few updates for 4.16:
- Misc fixes for amdgpu
- Enable swapout for reserved BOs during allocation for ttm
- Misc cleanups for ttm
* 'drm-next-4.16' of git://people.freedesktop.org/~agd5f/linux: (24 commits)
drm/amdgpu: Correct the IB size of bo update mapping.
drm/ttm: enable swapout for reserved BOs during allocation
drm/ttm: add new function to check if bo is allowable to evict or swapout
drm/ttm: use an operation ctx for ttm_tt_bind
drm/ttm: use an operation ctx for ttm_tt_populate in ttm_bo_driver (v2)
drm/ttm: use an operation ctx for ttm_mem_global_alloc_page
drm/ttm: use an operation ctx for ttm_mem_global_alloc
drm/ttm: call ttm_bo_swapout directly when ttm shrink
drm/vmwgfx: remove the default io_mem_pfn set
drm/virtio: remove the default io_mem_pfn set
drm/radeon: remove the default io_mem_pfn set
drm/qxl: remove the default io_mem_pfn set
drm/nouveau: remove the default io_mem_pfn set
drm/mgag200: remove the default io_mem_pfn set
drm/cirrus: remove the default io_mem_pfn set
drm/bochs: remove the default io_mem_pfn set
drm/ast: remove the default io_mem_pfn set
drm/ttm: add ttm_bo_io_mem_pfn to check io_mem_pfn
drm/amdgpu: fix VM faults with per VM BOs
drm/ttm: drop the spin in delayed delete if the trylock doesn't work
...
The first overlay plane can leak if initialization of the second overlay
plane fails. Fix this by properly destroying the first overlay plane on
error.
Suggested-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Cursor and overlay planes use a possible_crtcs mask based on the DC pipe
number. However, DRM requires each bit in the mask to correspond to the
index of the CRTC, which will be different from the DC pipe number for a
configuration where the first display controller is disabled, or where a
deferred probe leads to the first display controller being probed after
the first.
Suggested-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Commit ebae8d0743 ("drm/tegra: dc: Implement legacy blending") broke
support for YUV overlays by accident. The reason is that YUV formats are
considered opaque because they have no alpha component, but on the other
hand no corresponding format with an alpha component can be returned. In
the case of YUV formats, the opaque format is the same as the alpha
format, so add the special case to restore YUV overlay support.
Reported-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
- Add tiled prefetch support to PRE
- Add format modifier support to PRG and imx-drm-core
- Use runtime PM to control PRG clock
- Allow building ipu-v3 under COMPILE_TEST
-----BEGIN PGP SIGNATURE-----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=dt6o
-----END PGP SIGNATURE-----
Merge tag 'imx-drm-next-2018-01-02' of git://git.pengutronix.de/git/pza/linux into drm-next
drm/imx: format modifier support
- Add tiled prefetch support to PRE
- Add format modifier support to PRG and imx-drm-core
- Use runtime PM to control PRG clock
- Allow building ipu-v3 under COMPILE_TEST
* tag 'imx-drm-next-2018-01-02' of git://git.pengutronix.de/git/pza/linux:
gpu: ipu-v3: allow to build with COMPILE_TEST
drm/imx: advertise supported plane format modifiers
drm/imx: add FB modifier support
gpu: ipu-v3: prg: add modifier support
gpu: ipu-v3: pre: add tiled prefetch support
gpu: ipu-v3: prg: switch to runtime PM
This series builds upon the set of fixes previously submitted to move
Armada DRM closer to atomic modeset. We're nowhere near yet, but this
series helps to get us closer by unifying some of the differences
between the primary and overlay planes.
New features added allows userspace to disable the primary plane if
overlay is full screen and there's nothing obscuring the colorkey -
this saves having to fetch an entire buffer containing nothing but
colorkey when displaying full screen video.
[airlied: fixup for atomic plane helper rename:
a01cb8ba3f
Author: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed Nov 1 22:16:19 2017 +0200
drm: Move drm_plane_helper_check_state() into drm_atomic_helper.c
]
* 'drm-armada-devel-4.15' of git://git.armlinux.org.uk/~rmk/linux-arm: (29 commits)
drm/armada: expand overlay trace entry
drm/armada: implement primary plane update
drm/armada: extract register generation from armada_drm_primary_set()
drm/armada: wait for previous work when moving overlay window
drm/armada: move overlay plane register update generation
drm/armada: re-organise overlay register update generation
drm/armada: disable planes at next blanking period
drm/armada: avoid work allocation
drm/armada: allow armada_drm_plane_work_queue() to silently fail
drm/armada: use drm_plane_helper_check_state()
drm/armada: only enable HSMOOTH if scaling horizontally
drm/armada: move writes of LCD_SPU_SRAM_PARA1 under lock
drm/armada: move regs into armada_plane_work
drm/armada: move event sending into armada_plane_work
drm/armada: move fb retirement into armada_plane_work
drm/armada: move overlay plane work out from under spinlock
drm/armada: clear plane enable bit when disabling
drm/armada: clean up armada_drm_crtc_plane_disable()
drm/armada: allow the primary plane to be disabled
drm/armada: wait and cancel any pending frame work at disable
...
Highlights this time:
1. Fix for a nasty Kconfig dependency chain issue from Philipp.
2. Occlusion query buffer address added to the cmdstream validator by
Christian.
3. Fixes and cleanups to the job handling from me. This allows us to
turn on the GPU performance profiling added in the last cycle.
It is also prep work for hooking in the DRM GPU scheduler, which I hope
to land for the next cycle.
* 'etnaviv/next' of https://git.pengutronix.de/git/lst/linux: (32 commits)
drm/etnaviv: use memset32 to init pagetable
drm/etnaviv: move submit free out of critical section
drm/etnaviv: re-enable perfmon support
drm/etnaviv: couple runtime PM management to submit object lifetime
drm/etnaviv: move GPU active handling to bo pin/unpin
drm/etnaviv: move cmdbuf into submit object
drm/etnaviv: use submit exec_state for perfmon sampling
drm/etnaviv: move exec_state to submit object
drm/etnaviv: move PMRs to submit object
drm/etnaviv: refcount the submit object
drm/etnaviv: move ww_acquire_ctx out of submit object
drm/etnaviv: move object unpinning to submit cleanup
drm/etnaviv: attach in fence to submit and move fence wait to fence_sync
drm/etnaviv: rename submit fence to out_fence
drm/etnaviv: move object fence attachment to gem_submit path
drm/etnaviv: simplify submit_create
drm/etnaviv: add lockdep annotations to buffer manipulation functions
drm/etnaviv: hold GPU lock while inserting END command
drm/etnaviv: move workqueue to be per GPU
drm/etnaviv: remove switch_context member from etnaviv_gpu
...
- This driver isn't used anymore so remove it. Marek is preparing new one
which includes completely rewritten API so this driver will be replaced
with the new version[1] later.
And cleanups.
[1] https://patches.linaro.org/cover/118386/
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=pWLW
-----END PGP SIGNATURE-----
Merge tag 'exynos-drm-next-for-v4.16' of git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos into drm-next
Remove lagacy IPP driver
- This driver isn't used anymore so remove it. Marek is preparing new one
which includes completely rewritten API so this driver will be replaced
with the new version[1] later.
And cleanups.
[1] https://patches.linaro.org/cover/118386/
* tag 'exynos-drm-next-for-v4.16' of git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos:
drm/exynos: ipp: Remove Exynos DRM IPP subsystem
drm/exynos/decon: Add include guard to the Exynos7 header
drm/exynos/decon: Move headers from global to local place
drm/exynos: decon5433: Remove unnecessary platform_get_resource() error check
- Add CWSR (compute wave save restore) support for GFX8 (Carrizo)
- Fix SDMA user-mode queues support for GFX7 (Kaveri)
- Add SDMA user-mode queues support for GFX8 (Carrizo)
- Allow HWS (hardware scheduling) to schedule multiple processes concurrently
- Add debugfs support
- Simplify process locking and lock dependencies
- Refactoring topology code to prepare for dGPU support + fixes to that code
- Add option to generate dummy/virtual CRAT table when its missing or deformed
- Recognize CPUs other then APUs as compute entities
- Various clean ups and bug fixes
I have not yet sent the dGPU topology code because it depends on a patch
for the PCI subsystem that adds PCIe atomics support. Once that patch is
upstreamed we can continue with the rest of the dGPU code.
* tag 'drm-amdkfd-next-2017-12-24' of git://people.freedesktop.org/~gabbayo/linux: (53 commits)
drm/amdgpu: Add support for reporting VRAM usage
drm/amdkfd: Ignore ACPI CRAT for non-APU systems
drm/amdkfd: Module option to disable CRAT table
drm/amdkfd: Add AQL Queue Memory flag on topology
drm/amdkfd: Fixup incorrect info in the CZ CRAT table
drm/amdkfd: Add perf counters to topology
drm/amdkfd: Add topology support for dGPUs
drm/amdkfd: Add topology support for CPUs
drm/amdkfd: Fix sibling_map[] size
drm/amdkfd: Simplify counting of memory banks
drm/amdkfd: Turn verbose topology messages into pr_debug
drm/amdkfd: sync IOLINK defines to thunk spec
drm/amdkfd: Support enumerating non-GPU devices
drm/amdkfd: Decouple CRAT parsing from device list update
drm/amdkfd: Reorganize CRAT fetching from ACPI
drm/amdkfd: Group up CRAT related functions
drm/amdkfd: Fix memory leaks in kfd topology
drm/amdkfd: Topology: Fix location_id
drm/amdkfd: Update number of compute unit from KGD
drm/amd: Remove get_vmem_size from KGD-KFD interface
...
The msm/kms driver should work even if there is no GPU device specified
in DT. Currently, we get a NULL dereference crash in adreno_load_gpu
since the driver assumes that priv->gpu_pdev is non-NULL.
Perform an additional check on priv->gpu_pdev before trying to retrieve
the msm_gpu pointer from it.
v2: Incorporate Jordan's comments:
- Simplify the check to share the same error message.
- Use dev_err_once() to avoid an error message every time we open the
drm device fd.
Fixes: eec874ce5f (drm/msm/adreno: load gpu at probe/bind time)
Signed-off-by: Archit Taneja <architt@codeaurora.org>
Acked-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
This adds a new driver for Sitronix ST7735R display panels.
This has been tested using an Adafruit 1.8" TFT.
Signed-off-by: David Lechner <david@lechnology.com>
Reviewed-by: Noralf Trønnes <noralf@tronnes.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Link: https://patchwork.freedesktop.org/patch/msgid/1514833336-22564-4-git-send-email-david@lechnology.com
This updates the compatible string for a no-name LCD panel to
"vot,v220hf01a-t", "ilitek,ili9225".
The original bindings were the generic "ilitek,ili9225-2.2in-176x220"
because I could not find a datasheet. However, after some more research,
I finally found one, so the actual vendor and model name are now known.
This previous bindings have not made it to the mainline kernel yet, so
this is not breaking backwards compatibility.
Signed-off-by: David Lechner <david@lechnology.com>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Link: https://patchwork.freedesktop.org/patch/msgid/1513881187-3197-4-git-send-email-david@lechnology.com
There is no need to hold the GPU lock while freeing the submit
object. Only move the retired submits from the GPU active list to
a temporary retire list under the GPU lock.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Now that the PMR lifetime issues are solved we can safely re-enable
performance counter profiling support.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
As long as there is an active submit, we want the GPU to stay awake. This
is slightly complicated by the fact that we really want to wake the GPU
at the last possible moment to achieve maximum power savings.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
The active count is used to check if the BO is idle, where idle is defined
as not active on the GPU and all VM mappings and reference counts dropped
to the initial state. As the idling of the mappings and references now only
happens in the submit cleanup, the active state handling must be moved to
the same location in order to keep the userspace semantics.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Less dynamic allocations and slims down the cmdbuf object to only the
required information, as everything else is already available in the
submit object.
This also simplifies buffer and mappings lifetime management, as they
are now exlusively attached to the submit object and not additionally
to the cmdbuf.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
The GPU exec state may have changed at the time when the perfmon sampling
is done, as it reflects the state of the last submission, not the current
GPU execution state.
So for proper sampling we must use the submit exec_state.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
We'll need this in some places where only the submit is available. Also
this is a first step at slimming down the cmdbuf object.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
To make them available to the event worker even after the actual
command stream execution has finished.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
The submit object lifetime will get extended to the actual GPU
execution. As multiple users will depend on this, add a kref to
properly control destruction of the object.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
The acquire_ctx is special in that it needs to be released from the same
thread as has been used to initialize it. This collides with the intention to
extend the submit lifetime beyond the gem_submit function with potentially
other threads doing the final cleanup.
Move the ww_acquire_ctx to the function local stack as suggested in the
documentation.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
This is safe to call in all paths, as the BO_PINNED flag tells us if the BO
needs unpinning.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Simplifies the cleanup path and moves fence waiting to a central location.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
The object fencing has nothing to do with the actual GPU buffer submit,
so move it to the gem submit path to have a cleaner split.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Use kzalloc so other code doesn't need to worry about uninitialized members.
Drop the non-standard GFP flags, as we really don't want to fail the submit
when under slight memory pressure. Remove one level of indentation by using
an early return if the allocation failed. Also remove the unused drm device
member.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
When manipulating the kernel command buffer the GPU mutex must be held, as
otherwise different callers might try to replace the same part of the
buffer, wreacking havok in the GPU execution.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Inserting the END command when suspending the GPU is changing the
command buffer state, which requires the GPU to be held.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
While the etnaviv workqueue needs to be ordered, as we rely on work items
being executed in queuing order, this is only true for a single GPU.
Having a shared workqueue for all GPUs in the system limits concurrency
artificially.
Getting each GPU its own ordered workqueue still meets our ordering
expectations and enables retire workers to run concurrently.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
There is no need to store this in the gpu struct. MMU flushes are triggered
correctly in reaction to MMU maps and unmaps, independent of the current ctx.
Any required pipe switches can be infered from the current and the desired
GPU exec state.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
