No need to do this on every round.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>

This allows us to flush the system VM here.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>

This allows us to queue IBs which needs an up to date system domain as well.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>

Overwriting still used ring content has a low probability to cause
problems, not writing at all has 100% probability to cause problems.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>

Keep them where they belong.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>

Add function header comment to make it clear that local variable sw_cg
is used for debugging and it should not be removed.

Addresses-Coverity-ID: 1198635
Cc: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Gustavo A. R. Silva <garsilva@embeddedor.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

This was updated to 512 and the description update got missed
Signed-off-by: Kent Russell <kent.russell@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

With previous golden settings, compute task can't use
reserved LDS (32K) on CU0 and CU1. On 64K LDS system,
if compute work group allocate more than 32K LDS, then
it can't be dispatched to CU0 and CU1 because of the
reservation. This enables compute task to use reserved
LDS on CU0 and CU1.
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Otherwise we trigger a bunch of WARN_ONs when this is called.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Stop spreading the code over all GMC generations.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

This feature works for SRIOV enviroment. For non-SRIOV enviroment, the
trans_error function does nothing.

The error information includes error_code (16bit), error_flags(16bit)
and error_data(64bit). Since there are not many errors, we keep the
errors in an array and transfer all errors to Host before amdgpu
initialization function (amdgpu_device_init) exit.
Signed-off-by: Gavin Wan <Gavin.Wan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

With instantaneous high precision vblank timestamping
that updates at leading edge of vblank, a cooked hw
vblank counter which increments at leading edge of
vblank, and reliable page flip execution and completion
at leading edge of vblank, we should meet the requirements
for fast/immediate vblank irq disable/enable.

Testing on Linux-4.12-rc5 + drm-next on a Radeon R9 380
Tonga Pro (DCE 10) with timing measurement equipment
indicates this works fine, so allow immediate vblank
disable for power saving.

For debugging in case of unexpected trouble, booting
with kernel cmdline option drm.vblankoffdelay=0
(or echo 0 > /sys/module/drm/parameters/vblankoffdelay)
would keep vblank irqs permanently on to approximate old
behavior.
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

With instantaneous high precision vblank timestamping
that updates at leading edge of vblank, a cooked hw
vblank counter which increments at leading edge of
vblank, and reliable page flip execution and completion
at leading edge of vblank, we should meet the requirements
for fast/immediate vblank irq disable/enable.

Testing on Linux-4.12-rc5 + drm-next on a Radeon HD 5770
(DCE 4) with timing measurement equipment indicates this
works fine, so allow immediate vblank disable for power
saving.

For debugging in case of unexpected trouble, booting
with kernel cmdline option drm.vblankoffdelay=0
(or echo 0 > /sys/module/drm/parameters/vblankoffdelay)
would keep vblank irqs permanently on to approximate old
behavior.
Reviewed-and-Tested-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

These are no longer needed now that we use the fb_location
programmed by the vbios.
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Not used.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

No need to do this as the vbios does this for us.  As such
we no longer need to stop the mc during init.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

No need to do this as the vbios does this for us.  As such
we no longer need to stop the mc during init.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

No need to do this as the vbios does this for us.  As such
we no longer need to stop the mc during init.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

This makes mc programming much simpler in future patches.

Since evergreen, the vbios has been programming the fb location
to the proper vram size.  The only reason to reprogram it would
be to change the location.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

This makes mc programming much simpler in future patches.

Since evergreen, the vbios has been programming the fb location
to the proper vram size.  The only reason to reprogram it would
be to change the location.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

This makes mc programming much simpler in future patches.

Since evergreen, the vbios has been programming the fb location
to the proper vram size.  The only reason to reprogram it would
be to change the location.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

This got dropped accidently with the fb location changes, but for
some reason, this doesn't seem to cause an issue on all cards which
is why I never saw it despite extensive testing.  I suspect it may
only be an issue on systems with a legacy sbios that enables vga.
Tested-by: Andres Rodriguez <andresx7@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Now that we don't join PTE updates any more we don't need to call
the update function twice for this.

v2: rebased
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

v1: enable 4 level-page table on raven
v2: add back legacy 2 level page table on raven
v3: set num_level in initial switch statement
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Use the kernel provided version.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

single r700 fix.
* 'drm-next-4.13' of git://people.freedesktop.org/~agd5f/linux:
  drm/radeon: Fix eDP for single-display iMac10,1 (v2)

Merge tag 'drm-misc-next-fixes-2017-07-10' of git://anongit.freedesktop.org/git/drm-misc into drm-next

Core Changes:
- Fix empty timestamps on hw without vlbank counter (Laurent)
- Clear atomic state before retrying ww/mutex acquisition in remove_fb (Maarten)

Driver Changes:
- rockchip: Fix incorrect NULL pointer check after allocation (Gustavo)

Cc: Gustavo A. R. Silva <garsilva@embeddedor.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>

* tag 'drm-misc-next-fixes-2017-07-10' of git://anongit.freedesktop.org/git/drm-misc:
  drm/rockchip: fix NULL check on devm_kzalloc() return value
  drm/atomic: Add missing drm_atomic_state_clear to atomic_remove_fb
  drm: vblank: Fix vblank timestamp update
  DRM: Fix an incorrectly formatted table
  bridge: Fix panel-bridge error return on !panel.
  drm/rockchip: gem: add the lacks lock and trivial changes

Merge tag 'drm-intel-next-fixes-2017-07-11' of git://anongit.freedesktop.org/git/drm-intel into drm-next

drm/i915 fixes for v4.13-rc1

* tag 'drm-intel-next-fixes-2017-07-11' of git://anongit.freedesktop.org/git/drm-intel:
  drm/i915: Make DP-MST connector info work
  drm/i915/gvt: Use fence error from GVT request for workload status
  drm/i915/gvt: remove scheduler_mutex in per-engine workload_thread
  drm/i915/gvt: Revert "drm/i915/gvt: Fix possible recursive locking issue"
  drm/i915/gvt: Audit the command buffer address
  drm/i915/gvt: Fix a memory leak in intel_gvt_init_gtt()
  drm/i915/fbdev: Check for existence of ifbdev->vma before operations
  drm/i915: Hold RPM wakelock while initializing OA buffer
  drm/i915/cnl: Fix the CURSOR_COEFF_MASK used in DDI Vswing Programming
  drm/i915/cfl: Fix Workarounds.
  drm/i915: Avoid undefined behaviour of "u32 >> 32"
  drm/i915: reintroduce VLV/CHV PFI programming power domain workaround
  drm/i915: Fix an error checking test
  drm/i915: Disable MSI for all pre-gen5
  drm/i915/gvt: Make function dpy_reg_mmio_readx safe
  drm/i915/gvt: Don't read ADPA_CRT_HOTPLUG_MONITOR from host
  drm/i915/gvt: Set initial PORT_CLK_SEL vreg for BDW
  drm/i915/gvt: Fix inconsistent locks holding sequence
  drm/i915/gvt: Fix possible recursive locking issue

Merge branch 'mediatek-drm-next-4.13' of https://github.com/ckhu-mediatek/linux.git-tags into drm-next

This include new color format support and some fixups.

* 'mediatek-drm-next-4.13' of https://github.com/ckhu-mediatek/linux.git-tags:
  drm/mediatek: separate color module to fixup error memory reallocation
  drm/mediatek: check for memory allocation failure
  drm/mediatek: re-phrase DRM_INFO error message
  drm/mediatek: use platform_register_drivers
  drm/mediatek: Support UYVY and YUYV format for overlay

gvt-fixes-2017-07-11

- Revert "drm/i915/gvt: Fix possible recursive locking issue" (Chuanxiao),
  which is incomplete fix and it's actually VFIO issue, so revert.
- remove unneeded scheduler mutex for performance fix (Weinan)
- other misc error handling fix and cmd address audit
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170711055333.jhrmvx6ilvg2qlnn@zhen-hp.sh.intel.com

Commit 9a148a96 ("drm/i915/debugfs: add dp mst info") adds support
for DP-MST to intel_connector_info, but forgot to remove the early
return for DP-MST.

Remove it, and print out MST connectors directly.

Fixes: 9a148a96 ("drm/i915/debugfs: add dp mst info")
Cc: <stable@vger.kernel.org> # v4.11+
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Libin Yang <libin.yang@intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170626083349.24389-1-maarten.lankhorst@linux.intel.comReviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
(cherry picked from commit 77d1f615)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>

The req->fence.error will be set if this request caused GPU hang so
we can use this value to workload->status to indicate whether this
GVT request caused any problem. If it caused GPU hang, we shouldn't
trigger any context switch back to the guest.

v2:
- only take -EIO from fence->error. (Zhenyu)

Fixes: 8f1117ab (drm/i915/gvt: handle workload lifecycle properly)
Signed-off-by: Chuanxiao Dong <chuanxiao.dong@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

For the vGPU workloads, now GVT-g use per vGPU scheduler, the per-ring
work_thread only pick workload belongs to the current vGPU. And with time
slice based scheduler, it waits all the engines become idle before do vGPU
switch. So we can run free dispatch in per-ring work_thread, different ring
running in different 'vGPU' won't happen.

For the workloads between vGPU and Host, this scheduler_mutex can't block
host to dispatch workload into other ring engines.

Here remove this mutex since it impacts the performance when applications
use more than 1 ring engines in 1 vgpu.

ring0 running in vGPU1, ring1 running in Host. Will happen.
ring0 running in vGPU1, ring1 running in vGPU2. Won't happen.
Signed-off-by: Weinan Li <weinan.z.li@intel.com>
Signed-off-by: Ping Gao <ping.a.gao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

This reverts commit 62d02fd1.

The rwsem recursive trace should not be fixed from kvmgt side by using
a workqueue and it is an issue should be fixed in VFIO. So this one
should be reverted.
Signed-off-by: Chuanxiao Dong <chuanxiao.dong@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: stable@vger.kernel.org # v4.10+
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

The command buffer address in context like ring buffer base address
and wa_ctx address need to be audit to make sure they are in the
valid GGTT range.
Signed-off-by: Ping Gao <ping.a.gao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

It will causes memory leak, if the function setup_spt_oos() fail,
in the function intel_gvt_init_gtt(),
which allocated by get_zeroed_page() and mapped by dma_map_page().

Unmap and free the page,  after STP oos initialize fail,
it will fix this issue.
Signed-off-by: Zhou, Wenjia <zhiyuan_zhu@htc.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

The right variable to check here is port, not dp.

This issue was detected using Coccinelle and the following semantic patch:

@@
expression x;
identifier fld;
@@

* x = devm_kzalloc(...);
  ... when != x == NULL
  x->fld
Signed-off-by: Gustavo A. R. Silva <garsilva@embeddedor.com>
Acked-by: Mark Yao <mark.yao@rock-chips.com>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Link: http://patchwork.freedesktop.org/patch/msgid/20170706215833.GA25411@embeddedgus

Commit fabef825 ("drm/i915: Drop struct_mutex around frontbuffer
flushes") adds a dependency to ifbdev->vma when flushing the framebufer,
but the checks are only against the existence of the ifbdev->fb and not
against ifbdev->vma. This leaves a window of opportunity where we may
try to operate on the fbdev prior to it being probed (thanks to
asynchronous booting).

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101534
Fixes: fabef825 ("drm/i915: Drop struct_mutex around frontbuffer flushes")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170622160211.783-1-chris@chris-wilson.co.ukReviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: stable@vger.kernel.org
(cherry picked from commit 15727ed0)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>

The late 2009, 27 inch Apple iMac10,1 has an
internal eDP display and an external Mini-
Displayport output, driven by a DCE-3.2, RV730
Radeon Mobility HD-4670.

The machine worked fine in a dual-display setup
with eDP panel + externally connected HDMI
or DVI-D digital display sink, connected via
MiniDP to DVI or HDMI adapter.

However, booting the machine single-display with
only eDP panel results in a completely black
display - even backlight powering off, as soon as
the radeon modesetting driver loads.

This patch fixes the single dispay eDP case by
assigning encoders based on dig->linkb, similar
to DCE-4+. While this should not be generally
necessary (Alex: "...atom on normal boards
should be able to handle any mapping."), Apple
seems to use some special routing here.

One remaining problem not solved by this patch
is that an external Minidisplayport->DP sink
does still not work on iMac10,1, whereas external
DVI and HDMI sinks continue to work.

The problem affects at least all tested kernels
since Linux 3.13 - didn't test earlier kernels, so
backporting to stable probably makes sense.

v2: With the original patch from 2016, Alex was worried it
    will break other DCE3.2 systems. Use dmi_match() to
    apply this special encoder assignment only for the
    Apple iMac 10,1 from late 2009.
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Michel Dänzer <michel.daenzer@amd.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

the drm_file parameter is unused, so remove it.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Dave Airlie <airlied@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>