kernel/linux.git/drivers/gpu/drm/amd/amdgpu, branch v6.6.75

Revert "drm/amdgpu: rework resume handling for display (v2)"

2025-01-23T16:21:19+00:00

This reverts commit 2daba7d857e48035d71cdd95964350b6d0d51545 which is commit 73dae652dcac776296890da215ee7dec357a1032 upstream. The original patch 73dae652dcac (drm/amdgpu: rework resume handling for display (v2)), was only targeted at kernels 6.11 and newer. It did not apply cleanly to 6.12 so I backported it and it backport landed as 99a02eab8251 ("drm/amdgpu: rework resume handling for display (v2)"), however there was a bug in the backport that was subsequently fixed in 063d380ca28e ("drm/amdgpu: fix backport of commit 73dae652dcac"). None of this was intended for kernels older than 6.11, however the original backport eventually landed in 6.6, 6.1, and 5.15. Please revert the change from kernels 6.6, 6.1, and 5.15. Link: https://lore.kernel.org/r/BL1PR12MB5144D5363FCE6F2FD3502534F7E72@BL1PR12MB5144.namprd12.prod.outlook.com Link: https://lore.kernel.org/r/BL1PR12MB51449ADCFBF2314431F8BCFDF7132@BL1PR12MB5144.namprd12.prod.outlook.com Reported-by: Salvatore Bonaccorso Reported-by: Christian König Reported-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman

drm/amdgpu: always sync the GFX pipe on ctx switch

2025-01-23T16:21:18+00:00

commit af04b320c71c4b59971f021615876808a36e5038 upstream. That is needed to enforce isolation between contexts. Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit def59436fb0d3ca0f211d14873d0273d69ebb405) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdkfd: drop struct kfd_cu_info

2025-01-02T09:32:09+00:00

[ Upstream commit 0021d70a0654e668d457758110abec33dfbd3ba5 ] I think this was an abstraction back from when kfd supported both radeon and amdgpu. Since we just support amdgpu now, there is no more need for this and we can use the amdgpu structures directly. This also avoids having the kfd_cu_info structures on the stack when inlining which can blow up the stack. Cc: Arnd Bergmann Acked-by: Arnd Bergmann Reviewed-by: Felix Kuehling Acked-by: Christian König Signed-off-by: Alex Deucher Stable-dep-of: 438b39ac74e2 ("drm/amdkfd: pause autosuspend when creating pdd") Signed-off-by: Sasha Levin

drm/amdgpu/hdp6.0: do a posting read when flushing HDP

2025-01-02T09:32:08+00:00

[ Upstream commit abe1cbaec6cfe9fde609a15cd6a12c812282ce77 ] Need to read back to make sure the write goes through. Cc: David Belanger Reviewed-by: Frank Min Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin

drm/amdgpu/hdp5.0: do a posting read when flushing HDP

2025-01-02T09:32:07+00:00

[ Upstream commit cf424020e040be35df05b682b546b255e74a420f ] Need to read back to make sure the write goes through. Cc: David Belanger Reviewed-by: Frank Min Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin

drm/amdgpu/hdp4.0: do a posting read when flushing HDP

2025-01-02T09:32:07+00:00

[ Upstream commit c9b8dcabb52afe88413ff135a0953e3cc4128483 ] Need to read back to make sure the write goes through. Cc: David Belanger Reviewed-by: Frank Min Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin

drm/amd/amdgpu: allow use kiq to do hdp flush under sriov

2025-01-02T09:32:07+00:00

[ Upstream commit bf2bc61638033d118c9ef4ab1204295ba6694401 ] when use cpu to do page table update under sriov runtime, since mmio access is blocked, kiq has to be used to flush hdp. change WREG32_NO_KIQ to WREG32 to allow kiq. Signed-off-by: Victor Zhao Reviewed-by: Emily Deng Signed-off-by: Alex Deucher Stable-dep-of: c9b8dcabb52a ("drm/amdgpu/hdp4.0: do a posting read when flushing HDP") Signed-off-by: Sasha Levin

drm/amdgpu: Handle NULL bo->tbo.resource (again) in amdgpu_vm_bo_update

2024-12-27T12:58:58+00:00

commit 85230ee36d88e7a09fb062d43203035659dd10a5 upstream. Third time's the charm, I hope? Fixes: d3116756a710 ("drm/ttm: rename bo->mem and make it a pointer") Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3837 Reviewed-by: Christian König Signed-off-by: Michel Dänzer Signed-off-by: Alex Deucher (cherry picked from commit 695c2c745e5dff201b75da8a1d237ce403600d04) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdgpu: don't access invalid sched

2024-12-27T12:58:52+00:00

[ Upstream commit a93b1020eb9386d7da11608477121b10079c076a ] Since 2320c9e6a768 ("drm/sched: memset() 'job' in drm_sched_job_init()") accessing job->base.sched can produce unexpected results as the initialisation of (*job)->base.sched done in amdgpu_job_alloc is overwritten by the memset. This commit fixes an issue when a CS would fail validation and would be rejected after job->num_ibs is incremented. In this case, amdgpu_ib_free(ring->adev, ...) will be called, which would crash the machine because the ring value is bogus. To fix this, pass a NULL pointer to amdgpu_ib_free(): we can do this because the device is actually not used in this function. The next commit will remove the ring argument completely. Fixes: 2320c9e6a768 ("drm/sched: memset() 'job' in drm_sched_job_init()") Signed-off-by: Pierre-Eric Pelloux-Prayer Reviewed-by: Alex Deucher Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit 2ae520cb12831d264ceb97c61f72c59d33c0dbd7) Signed-off-by: Sasha Levin

amdgpu/uvd: get ring reference from rq scheduler

2024-12-19T17:11:27+00:00

[ Upstream commit 47f402a3e08113e0f5d8e1e6fcc197667a16022f ] base.sched may not be set for each instance and should not be used for cases such as non-IB tests. Fixes: 2320c9e6a768 ("drm/sched: memset() 'job' in drm_sched_job_init()") Signed-off-by: David (Ming Qiang) Wu Reviewed-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin