linux.git/drivers/gpu/drm/amd/amdgpu, branch v5.3-rc1

Merge tag 'drm-next-2019-07-19' of git://anongit.freedesktop.org/drm/drm

2019-07-19T19:29:43+00:00

Pull drm fixes from Daniel Vetter:
 "Dave is back in shape, but now family got it so I'm doing the pull.
  Two things worthy of note:

   - nouveau feature pull was way too late, Dave&me decided to not take
     that, so Ben spun up a pull with just the fixes.

   - after some chatting with the arm display maintainers we decided to
     change a bit how that's maintained, for more oversight/review and
     cross vendor collab.

  More details below:

  nouveau:
   - bugfixes
   - TU116 enabling (minor iteration) :w

  amdgpu:
   - large pile of fixes for new hw support this release (navi, vega20)
   - audio hotplug fix
   - bunch of corner cases and small fixes all over for amdgpu/kfd

  komeda:
   - back out some new properties (from this merge window) that needs
     more pondering.

  bochs:
   - fb pitch setup

  core:
   - a new panel quirk
   - misc fixes"

* tag 'drm-next-2019-07-19' of git://anongit.freedesktop.org/drm/drm: (73 commits)
  drm/nouveau/secboot/gp102-: remove WAR for SEC2 RTOS start bug
  drm/nouveau/flcn/gp102-: improve implementation of bind_context() on SEC2/GSP
  drm/nouveau: fix memory leak in nouveau_conn_reset()
  drm/nouveau/dmem: missing mutex_lock in error path
  drm/nouveau/hwmon: return EINVAL if the GPU is powered down for sensors reads
  drm/nouveau: fix bogus GPL-2 license header
  drm/nouveau: fix bogus GPL-2 license header
  drm/nouveau/i2c: Enable i2c pads & busses during preinit
  drm/nouveau/disp/tu102-: wire up scdc parameter setter
  drm/nouveau/core: recognise TU116 chipset
  drm/nouveau/kms: disallow dual-link harder if hdmi connection detected
  drm/nouveau/disp/nv50-: fix center/aspect-corrected scaling
  drm/nouveau/disp/nv50-: force scaler for any non-default LVDS/eDP modes
  drm/nouveau/mcp89/mmu: Use mcp77_mmu_new instead of g84_mmu_new on MCP89.
  drm/amd/display: init res_pool dccg_ref, dchub_ref with xtalin_freq
  drm/amdgpu/pm: remove check for pp funcs in freq sysfs handlers
  drm/amd/display: Force uclk to max for every state
  drm/amdkfd: Remove GWS from process during uninit
  drm/amd/amdgpu: Fix offset for vmid selection in debugfs interface
  drm/amd/powerplay: update vega20 driver if to fit latest SMU firmware
  ...

drm/amdgpu/pm: remove check for pp funcs in freq sysfs handlers

2019-07-18T19:11:47+00:00

The dpm sensor function already does this for us.  This fixes
the freq*_input files with the new SMU implementation.

Reviewed-by: Evan Quan 
Signed-off-by: Alex Deucher

drm/amd/amdgpu: Fix offset for vmid selection in debugfs interface

2019-07-17T18:34:30+00:00

The register debugfs interface was using the wrong bitmask for vmid
selection for GFX_CNTL.

Signed-off-by: Tom St Denis 
Acked-by: Christian König 
Reviewed-by: Alex Deucher 
Signed-off-by: Alex Deucher

drm/amd/powerplay: fix deadlock around smu_handle_task V2

2019-07-17T18:34:30+00:00

As the lock was already held on the entrance to smu_handle_task.

- V2: lock in small granularity

Signed-off-by: Evan Quan 
Reviewed-by: Kevin Wang 
Signed-off-by: Alex Deucher

drm/amdgpu: Fix silent amdgpu_bo_move failures

2019-07-17T18:34:30+00:00

Under memory pressure, buffer moves between RAM to VRAM  can
fail when there is no GTT space available. In those cases
amdgpu_bo_move falls back to ttm_bo_move_memcpy, which seems to
succeed, although it doesn't really support non-contiguous or
invisible VRAM. This manifests as VM faults with corrupted page
table entries in KFD eviction stress tests.

Print some helpful messages when lack of GTT space is causing buffer
moves to fail. Check that source and destination memory regions are
supported by ttm_bo_move_memcpy before taking that fallback.

Signed-off-by: Felix Kuehling 
Reviewed-by: Christian König 
Signed-off-by: Alex Deucher

drm/amdgpu: drop dead header

2019-07-17T18:34:20+00:00

Not used anymore.

Reviewed-by: Evan Quan 
Acked-by: Christian König 
Noticed-by: Dave Airlie 
Signed-off-by: Alex Deucher

drm/amdgpu/gfx10: set SH_MEM_CONFIG.INITIAL_INST_PREFETCH

2019-07-16T19:49:57+00:00

Prefetch mode 0 is not supported and can lead to hangs with certain very
specific code patterns. Set a sound prefetch mode for all VMIDs rather
than forcing all shaders to set the prefetch mode at the beginning.

Reduce code duplication a bit while we're at it. Note that the 64-bit
address mode enum and the retry all enum are both 0, so the only
functional change is in the INITIAL_INST_PREFETCH field.

Signed-off-by: Nicolai Hähnle 
Reviewed-by: Marek Olšák 
Acked-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdgpu: check kdb_bin_size to exclude kdb loading sequence

2019-07-16T19:49:57+00:00

The legacy navi10 sos binary will not carry on kdb image. the kdb_start_addr
is actually the start address of sys_drv image and shouldn't be sent to psp
bootloader.

Signed-off-by: Hawking Zhang 
Reviewed-by: John Clements 
Signed-off-by: Alex Deucher

drm/amdgpu: Fix unaligned memory copies

2019-07-16T19:49:36+00:00

When starting a new mm_node, the page_offset becomes 0.

Signed-off-by: Felix Kuehling 
Reviewed-by: Alex Deucher 
Reviewed-by: Christian König 
Signed-off-by: Alex Deucher

drm/amdgpu: replace simple_strtol() by kstrtou32()

2019-07-16T18:09:09+00:00

The simple_strtol() function is deprecated. kstrto[l,u32]() is
the correct replacement as it can properly handle overflows.

This patch replaces the deprecated simple_strtol() use introduced recently.
As clk is of type uint32_t, we are safe to use kstrtou32().

It is also safe to return zero on string parsing error,
similar to the case of returning zero if buf is empty in parse_clk().

Fixes: bb5a2bdf36a8 ("drm/amdgpu: support dpm level modification under virtualization v3")
Signed-off-by: Wang Xiayang 
Signed-off-by: Alex Deucher