aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
AgeCommit message (Collapse)AuthorFilesLines
2018-08-21Revert "drm/amdgpu/display: Replace CONFIG_DRM_AMD_DC_DCN1_0 with CONFIG_X86"Leo (Sunpeng) Li1-1/+1
This reverts commit 8624c3c4dbfe24fc6740687236a2e196f5f4bfb0. We need CONFIG_DRM_AMD_DC_DCN1_0 to guard code that is using fp math. Acked-by: Alex Deucher <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Leo (Sunpeng) Li <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-08-10Merge branch 'drm-next-4.19' of git://people.freedesktop.org/~agd5f/linux ↵Dave Airlie1-1/+1
into drm-next More fixes for 4.19: - Fixes for scheduler - Fix for SR-IOV - Fixes for display Signed-off-by: Dave Airlie <[email protected]> From: Alex Deucher <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2018-08-09drm/amdgpu/sriov: give 8s for recover vram under RUNTIMEEmily Deng1-1/+1
Extend the timeout for recovering vram bos from shadows on sr-iov to cover the worst case scenario for timeslices and VFs Under runtime, the wait fence time could be quite long when other VFs are in exclusive mode. For example, for 4 VF, every VF's exclusive timeout time is set to 3s, then the worst case is 9s. If the VF number is more than 4,then the worst case time will be longer. The 8s is the test data, with setting to 8s, it will pass the TDR test for 1000 times. SWDEV-161490 Signed-off-by: Monk Liu <[email protected]> Signed-off-by: Emily Deng <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-30BackMerge v4.18-rc7 into drm-nextDave Airlie1-0/+3
rmk requested this for armada and I think we've had a few conflicts build up. Signed-off-by: Dave Airlie <[email protected]>
2018-07-24drm/amdgpu: move the amdgpu_fbdev_set_suspend() further upShirish S1-3/+3
This patch moves amdgpu_fbdev_set_suspend() to the beginning of suspend sequence. This is to ensure fbcon does not to write to the VRAM after GPU is powerd down. Signed-off-by: Shirish S <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-20drm/amdgpu: rework suspend and resume to deal with atomic changesAlex Deucher1-41/+45
Use the newly split ip suspend functions to do suspend displays first (to deal with atomic so that FBs can be unpinned before attempting to evict vram), then evict vram, then suspend the other IPs. Also move the non-DC pinning code to only be called in the non-DC cases since atomic should take care of DC. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107065 Fixes: e00fb85 drm: Stop updating plane->crtc/fb/old_fb on atomic drivers Acked-by: Harry Wentland <[email protected]> Reviewed-and-tested-by: Andrey Grodzovsky <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-20drm/amdgpu: split ip suspend into 2 phasesAlex Deucher1-2/+76
We need to do some IPs earlier to deal with ordering issues similar to how resume is split into two phases. Do DCE first to deal with atomic, then do the rest. Acked-by: Harry Wentland <[email protected]> Reviewed-and-tested-by: Andrey Grodzovsky <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-20drm/amdgpu: use drm_fb helper for console_(un)lockShirish S1-6/+2
This patch removes the usage of console_(un)lock by replacing drm_fb_helper_set_suspend() to drm_fb_helper_set_suspend_unlocked() which locks and unlocks the console instead of locking ourselves. Signed-off-by: Shirish S <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-20drm/amdgpu: lock and unlock console only for amdgpu_fbdev_set_suspend [V5]Shirish S1-15/+7
[Why] While the console_lock is held, console output will be buffered, till its unlocked it wont be emitted, hence its ideal to unlock sooner to enable debugging/detecting/fixing of any issue in the remaining sequence of events in resume path. The concern here is about consoles other than fbcon on the device, e.g. a serial console [How] This patch restructures the console_lock, console_unlock around amdgpu_fbdev_set_suspend() and moves this new block appropriately. V2: Kept amdgpu_fbdev_set_suspend after pci_set_power_state V3: Updated the commit message to clarify the real concern that this patch addresses. V4: code clean-up. V5: fixed return value Signed-off-by: Shirish S <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-20drm/amdgpu: fix spelling mistake "successed" -> "succeeded"Colin Ian King1-5/+5
Trivial fix to spelling mistake in dev_err error message. Signed-off-by: Colin Ian King <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-19drm/amdgpu/display: Replace CONFIG_DRM_AMD_DC_DCN1_0 with CONFIG_X86Michel Dänzer1-1/+1
Allowing CONFIG_DRM_AMD_DC_DCN1_0 to be disabled on X86 was an opportunity for display with Raven Ridge accidentally not working. Reviewed-by: Harry Wentland <[email protected]> Signed-off-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-17drm/amdgpu: Make sure IB tests flushed after IP resumeLeo Liu1-0/+3
Fixes: 2c773de2 (drm/amdgpu: defer test IBs on the rings at boot (V3)) Signed-off-by: Leo Liu <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-16drm/amdgpu: remove job->ringChristian König1-2/+2
We can easily get that from the scheduler. Signed-off-by: Christian König <[email protected]> Reviewed-by: Junwei Zhang <[email protected]> Acked-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-11drm/amdgpu: Check NULL pointer for job before reset job's ringShaoyun Liu1-1/+1
job could be NULL when amdgpu_device_gpu_recover is called Signed-off-by: Shaoyun Liu <[email protected]> Reviewed-by: Andrey Grodzovsky <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-07-11drm/amdgpu: Call KFD reset handlers during GPU resetShaoyun Liu1-0/+5
Signed-off-by: Shaoyun Liu <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2018-07-10drm/amdgpu: separate gpu address from bo pinJunwei Zhang1-3/+2
It could be got by amdgpu_bo_gpu_offset() if need Signed-off-by: Junwei Zhang <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-05drm/amd: Remove errors from sphinx documentationDarren Powell1-8/+12
Eliminating the warnings produced by sphinx when processing the sphinx comments in amdgpu_device.c & amdgpu_mn.c Signed-off-by: Darren Powell <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-05drm/amdgpu: use pcie functions for link width and speedAlex Deucher1-25/+58
Use the newly exported pci functions to get the link width and speed rather than using the drm duplicated versions. Also query the GPU link caps directly rather than hardcoding them. Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-05drm/amdgpu: Move CG/PG setting out of delay worker threadRex Zhu1-6/+8
Partially revert commit 2dc80b00652f ("drm/amdgpu: optimize amdgpu driver load & resume time")' 1. CG/PG enablement are part of gpu hw ip initialize, we should wait for them complete. otherwise, there are some potential conflicts, for example, Suspend and CG enablement concurrently. 2. better run ib test after hw initialize completely. That is to say, ib test should be after CG/PG enablement. otherwise, the test will not cover the cg/pg/poweroff enable case. Reviewed-by: Evan Quan <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-05drm/amdgpu: Split set_pg_state into separate functionRex Zhu1-5/+28
1. add amdgpu_device_ip_late_set_pg_state function for set pg state. 2. delete duplicate pg state setting on gfx_v8_0's late_init. Reviewed-by: Evan Quan <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-05drm/amdgpu: Add gfx_off support in smu through pp_set_powergating_by_smuRex Zhu1-12/+7
we can take gfx off feature as gfx power gate. gfx off feature is also controled by smu. so add gfx_off support in pp_set_powergating_by_smu. Reviewed-by: Evan Quan <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-07-04Merge v4.18-rc3 into drm-nextDave Airlie1-1/+9
Two requests have come in for a backmerge, and I've got some pull reqs on rc2, so this just makes sense. Signed-off-by: Dave Airlie <[email protected]>
2018-06-19drm/amdgpu: Use correct enum to set powergating stateStefan Agner1-1/+1
Use enum amd_powergating_state instead of enum amd_clockgating_state. The underlying value stays the same, so there is no functional change in practise. This fixes a warning seen with clang: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:1930:14: warning: implicit conversion from enumeration type 'enum amd_clockgating_state' to different enumeration type 'enum amd_powergating_state' [-Wenum-conversion] AMD_CG_STATE_UNGATE); ^~~~~~~~~~~~~~~~~~~ Signed-off-by: Stefan Agner <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-06-19drm/amdgpu: correct GART location infoJunwei Zhang1-8/+6
Avoid confusing the GART with the GTT domain. Signed-off-by: Junwei Zhang <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-06-19drm/amdgpu: Don't default to DC support for Kaveri and olderHarry Wentland1-1/+9
We've had a number of users report failures to detect and light up display with DC with LVDS and VGA. These connector types are not currently supported with DC. I'd like to add support but unfortunately don't have a system with LVDS or VGA available. In order not to cause regressions we should probably fallback to the non-DC driver for ASICs that support VGA and LVDS. These ASICs are: * Bonaire * Kabini * Kaveri * Mullins ASIC support can always be force enabled with amdgpu.dc=1 v2: Keep Hawaii on DC v3: Added Mullins to the list Cc: [email protected] Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-06-15drm/amdgpu: Get real power source to initizlize ac_powerRex Zhu1-0/+3
driver need to know the real power source to do some power related configuration when initialize. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-06-13drm/amdgpu: fix CG enabling hang with gfxoff enabledHuang Rui1-0/+12
After defer the execution of clockgating enabling, at that time, gfx already enter into "off" state. Howerver, clockgating enabling will use MMIO to access the gfx registers, then get the gfx hung. So here we should move the gfx powergating and gfxoff enabling behavior at the end of initialization behind clockgating. Signed-off-by: Huang Rui <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Acked-by: Christian König <[email protected]> Cc: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-24drm/amdgpu: skip CG for VCN when late_init/finiRex Zhu1-0/+2
VCN clockgating is handled manually like VCE and UVD. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-23Remove calls to suspend/resume atomic helpers from ↵Andrey Grodzovsky1-9/+1
amdgpu_device_gpu_recover. (v2) 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=106500 Signed-off-by: Andrey Grodzovsky <[email protected]> Reviewed-by: Harry Wentland <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-17drm/amdgpu: Add vega20 to dc support check (v2)Feifei Xu1-0/+1
v2: fix whitespace Signed-off-by: Feifei Xu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-17drm/amdgpu: set asic family for vega20.Feifei Xu1-0/+1
Reviewed-by: Christian König <[email protected]> Signed-off-by: Feifei Xu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-17drm/amdgpu: Add gpu_info firmware for vega20. (v2)Feifei Xu1-0/+1
vega20_gpu_info firmware stores gpu configuration for vega20. v2: drop gpu info firmware for vega20 Squash of: drm/amdgpu: Add gpu_info firmware for vega20. drm/amdgpu: drop gpu_info firmware for vega20 Reviewed-by: Christian König <[email protected]> Signed-off-by: Feifei Xu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-17drm/amdgpu: Add vega20 to asic_type enum.Feifei Xu1-0/+1
Add vega20 to amd_asic_type enum and amdgpu_asic_name[]. Reviewed-by: Christian König <[email protected]> Signed-off-by: Feifei Xu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-15drm/amdgpu: For sriov reset, move IB test into exclusive modeEmily Deng1-3/+2
When put the IB test out of exclusive mode, and do sriov reset, the IB test will randomly fail. As out of exclusive mode it uses kiq to do read and write registers, but as it has world switch, the kiq read and write time will be random, sometimes it will beyond the MAX_KIQ_REG_WAIT and then the read or write register will fail, which will result the IB test fail. Signed-off-by: Emily Deng <[email protected]> Reviewed-by: Monk Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-15drm/amdgpu: add VEGAM dc support checkLeo Liu1-1/+2
Signed-off-by: Leo Liu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-15drm/amdgpu: set VEGAM to ASIC family and ip blocksLeo Liu1-1/+2
Signed-off-by: Leo Liu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-15drm/amdgpu: bypass GPU info firmware load for VEGAMLeo Liu1-1/+2
Signed-off-by: Leo Liu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-15drm/amdgpu: add VEGAM ASIC typeLeo Liu1-0/+1
Signed-off-by: Leo Liu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-15drm/amdgpu: it should disable gfxoff when system is going to suspendHuang Rui1-0/+6
Signed-off-by: Huang Rui <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-15drm/amdgpu: use pp_feature member to store the maskHuang Rui1-0/+2
Signed-off-by: Huang Rui <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-15drm/amdgpu: Reserved vram for smu to save debug info.Rex Zhu1-0/+44
v2: check reserved vram size before allocate. Reviewed-by: Evan Quan <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-15drm/amdgpu: defer test IBs on the rings at boot (V3)Shirish S1-11/+6
amdgpu_ib_ring_tests() runs test IB's on rings at boot contributes to ~500 ms of amdgpu driver's boot time. This patch defers it and ensures that its executed in amdgpu_info_ioctl() if it wasn't scheduled. V2: Use queue_delayed_work() & flush_delayed_work(). V3: removed usage of separate wq, ensure ib tests is run before enabling clockgating. Signed-off-by: Shirish S <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-15drm/amd/display: Remove PRE_VEGA flagHarry Wentland1-3/+0
We enabled this upstream by default now and no longer need the flag. Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-04-11drm/amdgpu: use new asic need_full_reset callbackAlex Deucher1-0/+6
Use the new callback to determine whether to use full asic reset or per IP soft reset. Enables reset to actually proceed on asics which don't support soft reset yet. Reviewed-by: Christian König <[email protected]> Reviewed-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-04-11drm/amdgpu: Move GEM BO to drm_framebufferDaniel Stone1-3/+3
Since drm_framebuffer can now store GEM objects directly, place them there rather than in our own subclass. As this makes the framebuffer create_handle and destroy functions the same as the GEM framebuffer helper, we can reuse those. Acked-by: Alex Deucher <[email protected]> Signed-off-by: Daniel Stone <[email protected]> Cc: Alex Deucher <[email protected]> Cc: Christian König <[email protected]> Cc: David (ChunMing) Zhou <[email protected]> Cc: [email protected] Signed-off-by: Alex Deucher <[email protected]>
2018-04-11drm/amdgpu: remove duplicate cg/pg wrapper functionsRex Zhu1-2/+4
Reviewed-by: Alex Deucher <[email protected]> Acked-by: Christian König<[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-03-21drm/amdgpu: Fix NULL ptr on driver unload due to init failure.Andrey Grodzovsky1-1/+0
Problem: When unloading due to failure amdgpu_device_fini was called twice which was leading to NULL ptr in amdgpu_irq_disable_all. Fix: Call amdgpu_device_fini only once from amdgpu_driver_unload_kms. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Andrey Grodzovsky <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-03-21drm/amdgpu: add vega12 to dc support checkAlex Deucher1-0/+1
DC is used for modesetting on vega12. Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Reviewed-by: Feifei Xu <[email protected]>
2018-03-21drm/amdgpu: set asic family and ip blocks for vega12Alex Deucher1-2/+3
soc15 just like vega10 and raven. Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Reviewed-by: Feifei Xu <[email protected]>
2018-03-21drm/amdgpu: add gpu_info firmware for vega12Alex Deucher1-0/+4
Stores gpu configuration details. Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Reviewed-by: Feifei Xu <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.