linux/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c, branch v5.1

drm/amd/amdgpu/sriov: Aligned the definition with libgv

2018-11-19T20:27:42Z

Aligned the amd_sriov_msg_pf2vf_info_header and amd_sriov_msg_pf2vf_info_header's definition with libgv. Signed-off-by: Emily Deng Reviewed-by: Frank.Min Signed-off-by: Alex Deucher

drm/amdgpu: cleanup GMC v9 TLB invalidation

2018-11-05T20:49:40Z

Move the kiq handling into amdgpu_virt.c and drop the fallback. Signed-off-by: Christian König Reviewed-by: Emily Deng Signed-off-by: Alex Deucher

drm/amdgpu: remove nonsense in_interrupt() checks

2018-11-05T20:49:39Z

might_sleep() is supposed to raise if warning if called in interrupt or atomic context. Signed-off-by: Christian König Reviewed-by: Emily Deng Signed-off-by: Alex Deucher

drm/amdgpu: Move csa related code to separate file

2018-11-05T19:21:49Z

In baremetal, also need to reserve csa for preemption. so move the csa related code out of sriov. Reviewed-by: Monk Liu Signed-off-by: Rex Zhu Signed-off-by: Alex Deucher

drm/amdgpu: Refine CSA related functions

2018-11-05T19:21:48Z

There is no functional changes, Use function arguments for SRIOV special variables which is hardcode in those functions. so we can share those functions in baremetal. Reviewed-by: Monk Liu Signed-off-by: Rex Zhu Signed-off-by: Alex Deucher

drm/amdgpu: Remove useless csa gpu address in vmid0

2018-11-05T19:21:48Z

driver didn't use this address so far. Reviewed-by: Monk Liu Signed-off-by: Rex Zhu Signed-off-by: Alex Deucher

drm/amdgpu: correctly sign extend 48bit addresses v3

2018-09-11T03:41:24Z

Correct sign extend the GMC addresses to 48bit. v2: sign extending turned out easier than thought. v3: clean up the defines and move them into amdgpu_gmc.h as well Signed-off-by: Christian König Reviewed-by: Junwei Zhang Signed-off-by: Alex Deucher

drm/amdgpu: use kiq to do invalidate tlb

2018-08-27T16:11:08Z

To avoid the tlb flush not interrupted by world switch, use kiq and one command to do tlb invalidate. v2: Refine the invalidate lock position. Signed-off-by: Emily Deng Reviewed-and-Tested-by: Rex Zhu Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: give warning before sleep in kiq_r/wreg

2018-03-07T21:10:13Z

to catch error that may schedule in atomic context early on Signed-off-by: Monk Liu Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: try again kiq access if not in IRQ(v4)

2018-03-01T17:04:17Z

sometimes GPU is switched to other VFs and won't swich back soon, so the kiq reg access will not signal within a short period, instead of busy waiting a long time(MAX_KEQ_REG_WAIT) and returning TMO we can istead sleep 5ms and try again later (non irq context) And since the waiting in kiq_r/weg is busy wait, so MAX_KIQ_REG_WAIT shouldn't set to a long time, set it to 10ms is more appropriate. if gpu already in reset state, don't retry the KIQ reg access otherwise it would always hang because KIQ was already die usually. v2: replace schedule() with msleep() for the wait v3: use while loop for the wait repeating use macros for the sleep period more description for it v4: drop unused variable Signed-off-by: Monk Liu Reviewed-by: Christian König Signed-off-by: Alex Deucher