- 25 May, 2018 1 commit
-
-
Arnd Bergmann authored
Casting a pointer to a 64-bit type causes a warning on 32-bit targets: drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c:473:24: error: cast from pointer to integer of different size [-Werror=pointer-to-int-cast] lower_32_bits((uint64_t)wptr)); ^ drivers/gpu/drm/amd/amdgpu/amdgpu.h:1701:53: note: in definition of macro 'WREG32' #define WREG32(reg, v) amdgpu_mm_wreg(adev, (reg), (v), 0) ^ drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c:473:10: note: in expansion of macro 'lower_32_bits' lower_32_bits((uint64_t)wptr)); ^~~~~~~~~~~~~ The correct method is to cast to 'uintptr_t'. Fixes: d5a114a6 ("drm/amdgpu: Add GFXv9 kfd2kgd interface functions") Signed-off-by:Arnd Bergmann <arnd@arndb.de> Reviewed-by:
Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by:
-
- 24 May, 2018 1 commit
-
-
Tom Stellard authored
This is an important message, so it should be visible to users without having to enable extra debugging. Signed-off-by:
Tom Stellard <tstellar@redhat.com> Reviewed-by:
-
- 18 May, 2018 1 commit
-
-
Oded Gabbay authored
In case CONFIG_HSA_AMD is not chosen, there is no need to compile amdkfd files that reside inside amdgpu dirver. In addition, because amdkfd depends on x86_64 architecture and amdgpu is not, compiling amdkfd files under i386 architecture can cause compiler errors and warnings. This patch modifies amdgpu's makefile to build amdkfd files only if CONFIG_HSA_AMD is chosen. The only file to be compiled unconditionally is amdgpu_amdkfd.c There are stub functions that are compiled only if amdkfd is not compiled. In that case, calls from amdgpu driver proper will go to those functions instead of the real functions. v2: instead of using function pointers, use stub functions v3: initialize kgd2kfd to NULL in case amdkfd is not compiled Reviewed-by:
Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by:
-
- 25 May, 2018 1 commit
-
-
git://people.freedesktop.org/~agd5f/linuxDave Airlie authored
Last feature request for 4.18. Mostly vega20 support. - Vega20 support - clock and powergating for VCN - misc bug fixes Signed-off-by:
Dave Airlie <airlied@redhat.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180524152427.32713-1-alexander.deucher@amd.com
-
- 24 May, 2018 26 commits
-
-
David Francis authored
In fixed31_32.h, in dc_fixpt_shl,'/' was used for division of one long long int by another long long int. As there is no inbuilt long long int division function in c, gcc inserted its own. However, gcc does not link the library that contains this function. To avoid this, use bitwise operators instead of / Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
David Francis <David.Francis@amd.com> Reviewed-by:
Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com> Signed-off-by:
-
Shaoyun Liu authored
Update to the latest version from the vbios team. Signed-off-by:
Shaoyun Liu <Shaoyun.Liu@amd.com> Acked-by:
-
Alex Deucher authored
is_dpm_running callback was assigned to the same value twice. Drop the duplicate. Reviewed-by:
Michel Dänzer <michel.daenzer@amd.com> Signed-off-by:
-
Emily Deng authored
To free the fence from the amdgpu_fence_slab, need twice call_rcu, to avoid the amdgpu_fence_slab_fini call kmem_cache_destroy(amdgpu_fence_slab) before kmem_cache_free(amdgpu_fence_slab, fence), add rcu_barrier after drm_sched_entity_fini. The kmem_cache_free(amdgpu_fence_slab, fence)'s call trace as below: 1.drm_sched_entity_fini -> drm_sched_entity_cleanup -> dma_fence_put(entity->last_scheduled) -> drm_sched_fence_release_finished -> drm_sched_fence_release_scheduled -> call_rcu(&fence->finished.rcu, drm_sched_fence_free) 2.drm_sched_fence_free -> dma_fence_put(fence->parent) -> amdgpu_fence_release -> call_rcu(&f->rcu, amdgpu_fence_free) -> kmem_cache_free(amdgpu_fence_slab, fence); v2:put the barrier before the kmem_cache_destroy v3:put the dma_fence_put(fence->parent) before call_rcu in drm_sched_fence_release_scheduled Signed-off-by:
Emily Deng <Emily.Deng@amd.com> Reviewed-by:
Christian König <christian.koenig@amd.com> Signed-off-by:
-
Christian König authored
Move all BOs belonging to a VM on the LRU with every submission. Signed-off-by:
Chunming Zhou <david1.zhou@amd.com> Signed-off-by:
-
Christian König authored
Instead of sometimes checking if the vm_status is empty use the moved flag and also reset it when the BO leaves the state machine. Signed-off-by:
Junwei Zhang <Jerry.Zhang@amd.com> Signed-off-by:
-
Christian König authored
In theory it is possible that PDs/PTs can move without eviction. Signed-off-by:
-
Christian König authored
Splice the moved list to a local one to avoid taking the lock over and over again. Signed-off-by:
-
Christian König authored
Use list_for_each_entry_safe here. v2: Drop the optimization, it doesn't work as expected. Signed-off-by:
-
Christian König authored
Only the moved state needs a separate spin lock protection. All other states are protected by reserving the VM anyway. v2: fix some more incorrect cases Signed-off-by:
-
Rex Zhu authored
Enable support for dynamically powering up/down VCN on demand. Reviewed-by:
Rex Zhu <Rex.Zhu@amd.com> Signed-off-by:
-
Rex Zhu authored
Enable static VCN powergating by default on Raven. Reviewed-by:
-
Rex Zhu authored
Implement static powergating suport on VCN. Reviewed-by:
-
Rex Zhu authored
Enable VCN clockgating by default on Raven. Reviewed-by:
-
Rex Zhu authored
Implement proper static clockgating support for VCN. Reviewed-by:
-
Rex Zhu authored
Add new macro to wait on a register field to be a specific value. Reviewed-by:
-
Rex Zhu authored
Define new clock and powergating flags for VCN block. Reviewed-by:
-
Rex Zhu authored
Add the powerplay callback for powergating VCN (same as UVD and VCE). Reviewed-by:
-
Rex Zhu authored
VCN clockgating is handled manually like VCE and UVD. Reviewed-by:
-
Rex Zhu authored
We should return unlock on the error path Reviewed-by:
-
Rex Zhu authored
error: uninitialized symbol 'xxxx' Reviewed-by:
-
Alex Deucher authored
The vbios mistakenly sets this bit on some boards without ECC. This can lead to reduced performance in some workloads. Disable the bit if the board does not have ECC. Reviewed-by:
Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by:
-
Alex Deucher authored
Needed for proper memory setup depending on whether ECC is enabled on a particular board. Reviewed-by:
-
Alex Deucher authored
The ForceParWrRMW setting needs to be enabled for ECC, but disabled when ECC is not enabled. Reviewed-by:
-
Alex Deucher authored
Reviewed-by:
-
Andrey Grodzovsky authored
First of all it's already being called from the display code from amd_ip_funcs.suspend/resume hooks. Second of all, the place in amdgpu_device_gpu_recover it's being called is wrong for GPU stalls since it is called BEFORE we cancel and force completion of all in flight jobs which were not yet processed. So, as Bas pointed in the ticket we will try to wait for fence in amdgpu_pm_compute_clocks but the pipe is hanged so we end up in deadlock. v2: remove unused variable Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106500Signed-off-by:
Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by:
Harry Wentland <harry.wentland@amd.com> Reviewed-by:
-
- 22 May, 2018 4 commits
-
-
git://anongit.freedesktop.org/tegra/linuxDave Airlie authored
drm/tegra: Changes for v4.18-rc1 This set enables IOMMU support in the gr2d and gr3d drivers and adds support for the zpos property on older Tegra generations. It also enables scaling filters and incorporates some rework to eliminate a private wrapper around struct drm_framebuffer. The remainder is mostly a random assortment of fixes and cleanups, as well as some preparatory work for destaging the userspace ABI, which is almost ready and is targetted for v4.19-rc1. Signed-off-by:
-
http://git.agner.ch/git/linux-drm-fsl-dcuDave Airlie authored
drm/fsl-dcu updates - Update MAINTAINERS file to reflect correct email address Signed-off-by:
-
https://git.pengutronix.de/git/lst/linuxDave Airlie authored
So what we have for this cycle is a bit of spring cleaning with removal of unused register logging code and getting rid of the license text in favor of SPDX, a few smaller MMU handling improvements and a timeout calculation change, fixing premature fence wait timeouts after 50 days of uptime. Signed-off-by:
-
git://git.armlinux.org.uk/~rmk/linux-armDave Airlie authored
Please incorporate support for TDA998x I2C driver CEC Signed-off-by:
-
- 20 May, 2018 1 commit
-
-
Fabio Estevam authored
The freescale.com email domain is not valid anymore, so use the nxp.com domain instead. Signed-off-by:
Fabio Estevam <fabio.estevam@nxp.com> Signed-off-by:
Stefan Agner <stefan@agner.ch>
-
- 18 May, 2018 5 commits
-
-
Thierry Reding authored
Document the userspace ABI with kerneldoc to provide some information on how to use it. v3: - reword description of arrays and array lengths v2: - keep GEM object creation flags for ABI compatibility - fix typo in struct drm_tegra_syncpt_incr kerneldoc - fix typos in struct drm_tegra_submit kerneldoc - reworded some descriptions as suggested Reviewed-by:
Dmitry Osipenko <digetx@gmail.com> Signed-off-by:
Thierry Reding <treding@nvidia.com>
-
Leo Liu authored
NO_OP register should be writen to 0 Signed-off-by:
Leo Liu <leo.liu@amd.com> Reviewed-by:
-
Leo Liu authored
NO_OP register should be writen to 0 Signed-off-by:
-
Leo Liu authored
NO_OP register should be writen to 0 Signed-off-by:
-
Leo Liu authored
NO_OP register should be writen to 0 Signed-off-by:
-
