summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm
AgeCommit message (Collapse)AuthorFilesLines
2019-07-08drm/komeda: Computing image enhancer internallyjames qian wang (Arm Technology China)3-10/+6
Enable image enhancer when the input data flow is 2x+ upscaling. Signed-off-by: james qian wang (Arm Technology China) <james.qian.wang@arm.com> Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190708070000.4945-1-james.qian.wang@arm.com
2019-07-08drm/komeda: Computing layer_split internallyjames qian wang (Arm Technology China)4-13/+14
For layer_split no need user to enable/disable it, but compute it in komeda internally, komeda will enable it if the scaling exceed the acceptable range of scaler. Signed-off-by: james qian wang (Arm Technology China) <james.qian.wang@arm.com> Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190708065923.4887-1-james.qian.wang@arm.com
2019-07-08drm/komeda: Remove layer_split propertyDaniel Vetter2-64/+0
Properties are uapi like anything else, with all the usual rules regarding review, testcases, open source userspace ... Furthermore driver-private kms properties are highly discouraged, over the past few years we've realized we need to make a serious effort at better standardizing this stuff. Again this probably needs multiple pieces to solve this properly: - Instead of expecting userspace to compute this (and duplicating modeset code), the kernel driver should compute when it's necessary to enable layer_split mode to make a configuration possible. I.e. in komeda_plane_atomic_check() first try komeda_build_layer_data_flow() and if that fails, try komeda_build_layer_split_data_flow(), and set dflow.en_split accordingly. Assuming I understand somewhat correctly what this does. - If this is needed for validation then you want a debugfs file to force this one way or the other, or alternatively use ->atomic_print_state to dump such hidden driver-private state. Depends upon how you do your validation ofc. Fixes: a407a6509393 ("drm/komeda: Add layer split support") Cc: Lowry Li (Arm Technology China) <lowry.li@arm.com> Cc: James Qian Wang (Arm Technology China) <james.qian.wang@arm.com> Cc: Liviu Dudau <liviu.dudau@arm.com> Cc: Mali DP Maintainers <malidp@foss.arm.com> Cc: Brian Starkey <brian.starkey@arm.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190705121006.26085-4-daniel.vetter@ffwll.ch
2019-07-08drm/komeda: remove img_enhancement propertyDaniel Vetter2-19/+2
Properties are uapi like anything else, with all the usual rules regarding review, testcases, open source userspace ... Furthermore driver-private kms properties are highly discouraged, over the past few years we've realized we need to make a serious effort at better standardizing this stuff. Again this probably needs multiple pieces to solve this properly: - Instead of expecting userspace to compute this (and duplicating modeset code), the kernel driver should compute when it's possible to enable this better up/downscale mode (assuming I understood Liviu correctly on what this does) automatically. - If this is needed for validation then you want a debugfs file to force this one way or the other, or alternatively use ->atomic_print_state to dump such hidden driver-private state. Depends upon how you do your validation ofc. Fixes: 42b6f118f6d1 ("drm/komeda: Add image enhancement support") Cc: Lowry Li (Arm Technology China) <lowry.li@arm.com> Cc: James Qian Wang (Arm Technology China) <james.qian.wang@arm.com> Cc: Liviu Dudau <liviu.dudau@arm.com> Cc: Mali DP Maintainers <malidp@foss.arm.com> Cc: Brian Starkey <brian.starkey@arm.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190705121006.26085-3-daniel.vetter@ffwll.ch
2019-07-08drm/komeda: remove slave_planes propertyDaniel Vetter2-27/+0
Properties are uapi like anything else, with all the usual rules regarding review, testcases, open source userspace ... Furthermore driver-private kms properties are highly discouraged, over the past few years we've realized we need to make a serious effort at better standardizing this stuff. Again this probably needs multiple pieces to solve this properly: - To make plane configuration less surprising to userspace you propably need to virtualize planes, and reorder which logical plane you map to which physical one dynamically. Instead of exposing a komeda-specific limitation to userspace and expecting them to dtrt. I think msm and rcar-du do that already (and others), if you need people to chat with or example code. - If this is needed for validation, again ->atomic_print_state and the infrastructure around that is your friend. Fixes: 3b9dfa4ef28c ("drm/komeda: Add slave pipeline support") Cc: Lowry Li (Arm Technology China) <lowry.li@arm.com> Cc: James Qian Wang (Arm Technology China) <james.qian.wang@arm.com> Cc: Liviu Dudau <liviu.dudau@arm.com> Cc: Mali DP Maintainers <malidp@foss.arm.com> Cc: Brian Starkey <brian.starkey@arm.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190705121006.26085-2-daniel.vetter@ffwll.ch
2019-07-08drm/komeda: Remove clock ratio propertyDaniel Vetter2-42/+0
Properties are uapi like anything else, with all the usual rules regarding review, testcases, open source userspace ... Furthermore driver-private kms properties are highly discouraged, over the past few years we've realized we need to make a serious effort at better standardizing this stuff. From the discussion with Liviu the solution for these here needs multiple pieces: - For being able to reliably read the memory clock we need a DT property, plus maybe DT override snippets to fix it if it's wrong. - For exposing plane limitations to userspace there's TEST_ONLY. There is a bit a gap in telling userspace better that scaling doesn't work due to limits (atm a good strategy is to retry again without scaling when adding a plane didn't work the first time around). But that needs a more generic solution, not exposing something extremely komeda specific. - If this is needed by validation tools, you can still expose it in debugfs. We have an entire nice infrastructure for debug printing of kms objects already, see the various atomic_print_state callbacks and infrastructure around them. Fixes: 1f7f9ab7900e ("drm/komeda: Add engine clock requirement check for the downscaling") Cc: Lowry Li (Arm Technology China) <lowry.li@arm.com> Cc: James Qian Wang (Arm Technology China) <james.qian.wang@arm.com> Cc: Liviu Dudau <liviu.dudau@arm.com> Cc: Mali DP Maintainers <malidp@foss.arm.com> Cc: Brian Starkey <brian.starkey@arm.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190705121006.26085-1-daniel.vetter@ffwll.ch
2019-07-05drm/amdgpu: add mode1 (psp) reset for navi asicKevin Wang1-2/+36
add mode1 (by psp) reset for navi asic. Signed-off-by: Kevin Wang <kevin1.wang@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-05drm/amdgpu: Disable ras features on all IPs before gpu resetxinhui pan1-0/+4
Perform a ras_suspend to disable ras on all IPs to workaround some ROCm stability issue. Signed-off-by: xinhui pan <xinhui.pan@amd.com> Acked-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-05drm/amd/powerplay: add baco smu reset function for smu11Kevin Wang7-3/+158
add baco reset support for smu11. it can help gpu do asic reset when gpu recovery. Signed-off-by: Kevin Wang <kevin1.wang@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-05drm/amd/powerplay: increase waiting time for smu responseJack Xiao1-3/+3
We observed some SMU commands take more time for execution, so increase waiting time for response. Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-05drm/amd/powerplay/smu7_hwmgr: replace blocking delay with non-blockingYrjan Skrimstad1-1/+1
This driver currently contains a repeated 500ms blocking delay call which causes frequent major buffer underruns in PulseAudio. This patch fixes this issue by replacing the blocking delay with a non-blocking sleep call. Signed-off-by: Yrjan Skrimstad <yrjan@skrimstad.net> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-05drm/amdgpu: Use kmemdup rather than duplicating its implementationFuqian Huang4-13/+7
kmemdup is introduced to duplicate a region of memory in a neat way. Rather than kmalloc/kzalloc + memcpy, which the programmer needs to write the size twice (sometimes lead to mistakes), kmemdup improves readability, leads to smaller code and also reduce the chances of mistakes. Suggestion to use kmemdup rather than using kmalloc/kzalloc + memcpy. Reviewed-by: Christian König <Christian.Koenig@amd.com> Reviewed-by: Emil Velikov <emil.velikov@collabora.com> Signed-off-by: Fuqian Huang <huangfq.daxian@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-05Merge tag 'imx-drm-fixes-2019-07-04' of ↵Dave Airlie1-3/+3
git://git.pengutronix.de/git/pza/linux into drm-fixes drm/imx: fix stale vblank timestamp after a modeset This series fixes stale vblank timestamps in the first event sent after a crtc was disabled. The core now is notified via drm_crtc_vblank_off before sending the last pending event in atomic_disable. If the crtc is reenabled right away during to a modeset, the event is not sent at all, as the next vblank will take care of it. Signed-off-by: Dave Airlie <airlied@redhat.com> From: Philipp Zabel <p.zabel@pengutronix.de> Link: https://patchwork.freedesktop.org/patch/msgid/1562237119.6641.16.camel@pengutronix.de
2019-07-04drm/imx: only send event on crtc disable if kept disabledRobert Beckett1-1/+1
The event will be sent as part of the vblank enable during the modeset if the crtc is not being kept disabled. Fixes: 5f2f911578fb ("drm/imx: atomic phase 3 step 1: Use atomic configuration") Signed-off-by: Robert Beckett <bob.beckett@collabora.com> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
2019-07-04drm/imx: notify drm core before sending event during crtc disableRobert Beckett1-2/+2
Notify drm core before sending pending events during crtc disable. This fixes the first event after disable having an old stale timestamp by having drm_crtc_vblank_off update the timestamp to now. This was seen while debugging weston log message: Warning: computed repaint delay is insane: -8212 msec This occurred due to: 1. driver starts up 2. fbcon comes along and restores fbdev, enabling vblank 3. vblank_disable_fn fires via timer disabling vblank, keeping vblank seq number and time set at current value (some time later) 4. weston starts and does a modeset 5. atomic commit disables crtc while it does the modeset 6. ipu_crtc_atomic_disable sends vblank with old seq number and time Fixes: a474478642d5 ("drm/imx: fix crtc vblank state regression") Signed-off-by: Robert Beckett <bob.beckett@collabora.com> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
2019-07-04Merge tag 'drm-next-5.3-2019-06-27' of ↵Dave Airlie10-21/+192
git://people.freedesktop.org/~agd5f/linux into drm-next drm-next-5.3-2019-06-27: amdgpu: - Fix warning on 32 bit ARM - Fix compilation on big endian - Misc bug fixes ttm: - Live lock fix Signed-off-by: Dave Airlie <airlied@redhat.com> From: Alex Deucher <alexdeucher@gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190628015555.3384-1-alexander.deucher@amd.com
2019-07-04Merge tag 'drm-misc-next-fixes-2019-06-27' of ↵Dave Airlie1-2/+8
git://anongit.freedesktop.org/drm/drm-misc into drm-next drm-misc-next-fixes for v5.3: - Fixes to the tfp410 bridge. - Small build fix for vga_switcheroo to prevent building against modular fbcon. Signed-off-by: Dave Airlie <airlied@redhat.com> From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20a62234-bc27-00eb-e0e2-22b55eec1cb2@linux.intel.com
2019-07-04Merge tag 'for-airlie-armada' of git://git.armlinux.org.uk/~rmk/linux-arm ↵Dave Airlie10-212/+522
into drm-next Armada DRM updates: - Fix interlace support. - use __drm_atomic_helper_plane_reset in overlay reset. - since the overlay and video planes use essentially the same format registers, precompute their values while validating. - fix a long-standing deficiency with overlay planes and interlace modes - calculate plane starting address at atomic_check stage rather than when we're programming the registers. - add gamma support. - ensure mode adjustments made by other components are properly handled in the driver and applied to the CRTC-programmed mode. - add and use register definitions for the "REG4F" register. - use drm_atomic_helper_shutdown() when tearing down to ensure that the hardware is properly shutdown. - add CRTC-level mode validation to ensure that we don't allow a mode that the CRTC-level hardware can not support. - improve the clocking selection for Armada 510 support. - move CRTC debugfs files into the crtc-specific directory, using the DRM helper to create these files. - patch from Lubomir Rintel to replace a simple framebuffer. - use the OF graph walker rather than open-coding this. - eliminate a useless check for the availability of the remote's parent which isn't required. Signed-off-by: Dave Airlie <airlied@redhat.com> From: Russell King <rmk@armlinux.org.uk> Link: https://patchwork.freedesktop.org/patch/msgid/20190702091313.GA23442@rmk-PC.armlinux.org.uk
2019-07-04Merge tag 'exynos-drm-next-for-v5.3' of ↵Dave Airlie25-139/+158
git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos into drm-next - Drop the use of drmP.h header file drmP.h header file has been deprecated so this patch drops the use of this header, and instead includes appropriate header files required. - Add COMPILE_TEST flag This patch adds COMPILE_TEST dependency to exynos drm driver to increase build test coverage. And also, it includes vmalloc.h header file to fix one build warning which is introduced when building the Linux kernel using sh. Signed-off-by: Dave Airlie <airlied@redhat.com> From: Inki Dae <inki.dae@samsung.com> Link: https://patchwork.freedesktop.org/patch/msgid/CAAQKjZMdBdD8oEa0cNv78FjrpOqu20ozTTvuPEm_XnVo2gRhCQ@mail.gmail.com
2019-07-04Merge branch 'etnaviv/fixes' of https://git.pengutronix.de/git/lst/linux ↵Dave Airlie1-2/+5
into drm-fixes Fix a kernel nullptr deref on module unload when any etnaviv GPU failed to initialize properly. Signed-off-by: Dave Airlie <airlied@redhat.com> From: Lucas Stach <l.stach@pengutronix.de> Link: https://patchwork.freedesktop.org/patch/msgid/1561974148.2321.1.camel@pengutronix.de
2019-07-04Merge tag 'drm-misc-fixes-2019-07-03' of ↵Dave Airlie1-1/+1
git://anongit.freedesktop.org/drm/drm-misc into drm-fixes panfrost- Avoid double free by deleting GEM handle in create_bo failure path (Boris) Cc: Boris Brezillon <boris.brezillon@collabora.com> Signed-off-by: Dave Airlie <airlied@redhat.com> From: Sean Paul <sean@poorly.run> Link: https://patchwork.freedesktop.org/patch/msgid/20190704001302.GA260390@art_vandelay
2019-07-04Merge tag 'drm-fixes-5.2-2019-07-02' of ↵Dave Airlie5-21/+9
git://people.freedesktop.org/~agd5f/linux into drm-fixes drm-fixes-5.2-2019-07-02: Fixes for stable amdgpu: - stability fix for gfx9 - regression fix for HG on some polaris boards - crash fix for some new OEM boards Signed-off-by: Dave Airlie <airlied@redhat.com> From: Alex Deucher <alexdeucher@gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190703015705.3162-1-alexander.deucher@amd.com
2019-07-03drm/amdkfd: Disable idle optimization for chained runlistFelix Kuehling1-0/+1
This works around difficult-to-reproduce soft hangs on oversubscribed runlists. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-03drm/amdkfd: Add chained_runlist_idle_disable flag to pm4_mes_runlistFelix Kuehling1-1/+1
New flag to disable an idle runlist optimization that is causing soft hangs with some diffult-to-reproduce customer workloads. This will serve as a workaround until the problem can be reproduced and the root-cause determined. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-03drm/amdgpu: Fix tracking of invalid userptrsFelix Kuehling1-0/+6
Restore the code that resets mem->invalid. Othewise so mapping userptrs after they got an MMU notifiers would always be skipped. This also avoids unnecessarily calling get_user_pages on BOs that have not been invalidated since the last try. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-03drm/amdgpu: Use FENCE_OWNER_KFD in process_sync_pds_resvFelix Kuehling1-1/+1
We don't want eviction fences to trigger when waiting for page table updates to complete during restore. In theory there shouldn't be any unsignaled eviction fences in the PD reservation object, but I'm seeing them in instrumented code for reasons not fully understood. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-03drm/amdkfd: Print a warning when the runlist becomes oversubscribedFelix Kuehling2-1/+6
Oversubscription of queues or processes results in poor performance mostly because HWS blinbly schedules busy and idle queues, resulting in poor occupancy if many queues are idle. Let users know with a warning message when transitioning from a non-oversubscribed to an oversubscribed runlist. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-03Merge branch 'timers/vdso' into timers/coreThomas Gleixner267-2241/+439
so the hyper-v clocksource update can be applied.
2019-07-03drm/amdkfd: remove an unused variableJack Xiao1-1/+0
Just for cleanup. Reviewed-by: Prike Liang <Prike.Liang@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-02drm/amdgpu/display: fix interrupt client id for naviAlex Deucher1-4/+1
All asics newer than vega10 use client ids, so simplify the check. Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-02Merge branch 'hmm-devmem-cleanup.4' into rdma.git hmmJason Gunthorpe2-59/+50
Christoph Hellwig says: ==================== Below is a series that cleans up the dev_pagemap interface so that it is more easily usable, which removes the need to wrap it in hmm and thus allowing to kill a lot of code Changes since v3: - pull in "mm/swap: Fix release_pages() when releasing devmap pages" and rebase the other patches on top of that - fold the hmm_devmem_add_resource into the DEVICE_PUBLIC memory removal patch - remove _vm_normal_page as it isn't needed without DEVICE_PUBLIC memory - pick up various ACKs Changes since v2: - fix nvdimm kunit build - add a new memory type for device dax - fix a few issues in intermediate patches that didn't show up in the end result - incorporate feedback from Michal Hocko, including killing of the DEVICE_PUBLIC memory type entirely Changes since v1: - rebase - also switch p2pdma to the internal refcount - add type checking for pgmap->type - rename the migrate method to migrate_to_ram - cleanup the altmap_valid flag - various tidbits from the reviews ==================== Conflicts resolved by: - Keeping Ira's version of the code in swap.c - Using the delete for the section in hmm.rst - Using the delete for the devmap code in hmm.c and .h * branch 'hmm-devmem-cleanup.4': (24 commits) mm: don't select MIGRATE_VMA_HELPER from HMM_MIRROR mm: remove the HMM config option mm: sort out the DEVICE_PRIVATE Kconfig mess mm: simplify ZONE_DEVICE page private data mm: remove hmm_devmem_add mm: remove hmm_vma_alloc_locked_page nouveau: use devm_memremap_pages directly nouveau: use alloc_page_vma directly PCI/P2PDMA: use the dev_pagemap internal refcount device-dax: use the dev_pagemap internal refcount memremap: provide an optional internal refcount in struct dev_pagemap memremap: replace the altmap_valid field with a PGMAP_ALTMAP_VALID flag memremap: remove the data field in struct dev_pagemap memremap: add a migrate_to_ram method to struct dev_pagemap_ops memremap: lift the devmap_enable manipulation into devm_memremap_pages memremap: pass a struct dev_pagemap to ->kill and ->cleanup memremap: move dev_pagemap callbacks into a separate structure memremap: validate the pagemap type passed to devm_memremap_pages mm: factor out a devm_request_free_mem_region helper mm: export alloc_pages_vma ... Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02Merge tag 'v5.2-rc7' into rdma.git hmmJason Gunthorpe521-4207/+1379
Required for dependencies in the next patches.
2019-07-02mm: don't select MIGRATE_VMA_HELPER from HMM_MIRRORChristoph Hellwig1-0/+1
The migrate_vma helper is only used by noveau to migrate device private pages around. Other HMM_MIRROR users like amdgpu or infiniband don't need it. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02mm: remove the HMM config optionChristoph Hellwig1-2/+1
All the mm/hmm.c code is better keyed off HMM_MIRROR. Also let nouveau depend on it instead of the mix of a dummy dependency symbol plus the actually selected one. Drop various odd dependencies, as the code is pretty portable. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02mm: sort out the DEVICE_PRIVATE Kconfig messChristoph Hellwig1-1/+1
The ZONE_DEVICE support doesn't depend on anything HMM related, just on various bits of arch support as indicated by the architecture. Also don't select the option from nouveau as it isn't present in many setups, and depend on it instead. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02mm: simplify ZONE_DEVICE page private dataChristoph Hellwig1-11/+7
Remove the clumsy hmm_devmem_page_{get,set}_drvdata helpers, and instead just access the page directly. Also make the page data a void pointer, and thus much easier to use. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02nouveau: use devm_memremap_pages directlyChristoph Hellwig1-44/+38
Just use devm_memremap_pages instead of hmm_devmem_add pages to allow killing that wrapper which doesn't provide a whole lot of benefits. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02nouveau: use alloc_page_vma directlyChristoph Hellwig1-1/+2
hmm_vma_alloc_locked_page is scheduled to go away, use the proper mm function directly. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02drm: connector: remove bogus NULL checkArnd Bergmann1-1/+1
mode->name is a character array in a structure, checking it's address is pointless and causes a warning with some compilers: drivers/gpu/drm/drm_connector.c:144:15: error: address of array 'mode->name' will always evaluate to 'true' [-Werror,-Wpointer-bool-conversion] mode->name ? mode->name : "", ~~~~~~^~~~ ~ include/drm/drm_print.h:366:29: note: expanded from macro 'DRM_DEBUG_KMS' drm_dbg(DRM_UT_KMS, fmt, ##__VA_ARGS__) ^~~~~~~~~~~ Remove the check here. Fixes: 3aeeb13d8996 ("drm/modes: Support modes names on the command line") Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Ramalingam C <ramlaingam.c@intel.com> Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com> Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190628103925.2686249-1-arnd@arndb.de
2019-07-02drm/i915/ringbuffer: EMIT_INVALIDATE *before* switch contextChris Wilson1-3/+3
Despite what I think the prm recommends, commit f2253bd9859b ("drm/i915/ringbuffer: EMIT_INVALIDATE after switch context") turned out to be a huge mistake when enabling Ironlake contexts as the GPU would hang on either a MI_FLUSH or PIPE_CONTROL immediately following the MI_SET_CONTEXT of an active mesa context (more vanilla contexts, e.g. simple rendercopies with igt, do not suffer). Ville found the following clue, "[DevCTG+]: For the invalidate operation of the pipe control, the following pointers are affected. The invalidate operation affects the restore of these packets. If the pipe control invalidate operation is completed before the context save, the indirect pointers will not be restored from memory. 1. Pipeline State Pointer 2. Media State Pointer 3. Constant Buffer Packet" which suggests by us emitting the INVALIDATE prior to the MI_SET_CONTEXT, we prevent the context-restore from chasing the dangling pointers within the image, and explains why this likely prevents the GPU hang. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190419111749.3910-1-chris@chris-wilson.co.uk (cherry picked from commit 928f8f42310f244501a7c70daac82c196112c190 in drm-intel-next) Cc: stable@vger.kernel.org Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111014 Fixes: f2253bd9859b ("drm/i915/ringbuffer: EMIT_INVALIDATE after switch context") Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2019-07-01drm/amdkfd: remove duplicated PCIE atomics requestJack Xiao3-6/+12
Since amdgpu has always requested PCIE atomics, kfd don't need duplicated PCIE atomics enablement. Referring to amdgpu request result is enough. Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01drm/amdgpu: enable PCIE atomics ops supportJack Xiao1-0/+11
GPU atomics operation depends on PCIE atomics support. Always enable PCIE atomics ops support in case that it hasn't been enabled. Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01drm/amdgpu: add field indicating if has PCIE atomics supportJack Xiao1-0/+1
The new field in amdgpu device is used to record whether the system has PCIE atomics support. The field can be exposed to UMD or kfd whether PCIE atomics have supported. Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01drm/amd/powerplay: use hardware fan control if no powerplay fan tableEvan Quan3-1/+8
Otherwise, you may get divided-by-zero error or corrput the SMU fan control feature. Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Tested-by: Slava Abramov <slava.abramov@amd.com> Acked-by: Slava Abramov <slava.abramov@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01drm/amdgpu: fix MGPU fan boost enablement for XGMI resetEvan Quan3-2/+19
MGPU fan boost feature should not be enabled until all the devices from the same hive are all back from reset. Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01drm/amdgpu: handle AMDGPU_IB_FLAG_RESET_GDS_MAX_WAVE_ID on gfx10Marek Olšák1-2/+19
Add the gfx10 equivalent of the gfx9 code. Signed-off-by: Marek Olšák <marek.olsak@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01drm/amdgpu: fix transform feedback GDS hang on gfx10 (v2)Marek Olšák2-4/+13
v2: update emit_ib_size (though it's still wrong because it was wrong before) Signed-off-by: Marek Olšák <marek.olsak@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01drm/amdgpu/gfx9: use reset default for PA_SC_FIFO_SIZEAlex Deucher1-19/+0
Recommended by the hw team. Reviewed-and-Tested-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
2019-07-01drm/amdgpu/gfx10: use reset default for PA_SC_FIFO_SIZEAlex Deucher1-18/+0
Recommended by the hw team. Reviewed-and-Tested-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01drm/amdgpu/gfx9: use reset default for PA_SC_FIFO_SIZEAlex Deucher1-19/+0
Recommended by the hw team. Reviewed-and-Tested-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
generated by cgit v1.2.3 (git 2.39.0) at 2025-09-27 00:46:57 +0300