This adds the infrastructure needed to quirk displays
using edid and to mark them a non-desktop.

A non-desktop display is one which shouldn't normally be included
as a part of a desktop environment.

This is meant to cover head mounted devices like HTC Vive.

v2: Change description from non-standard to non-desktop, add docs
Reviewed-by: NKeith Packard <keithp@keithp.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

fixup docs

If  gfx_v8_0_hw_fini is called after amdgpu_ucode_fini_bo, we will
hit KCQ disabled failed. Let amdgpu_ucode_fini_bo run after
gfx_v8_0_hw_fini.

BUG: SWDEV-135547
Reviewed-by: NRex Zhu <Rex.Zhu@amd.com>
Signed-off-by: NWang Hongcheng <Annie.Wang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

After starting VNC server or running CTS test, kernel will hang and
can see below call trace:

[961816] INFO: task khugepaged:42 blocked for more than 120 seconds.
[968581]       Tainted: G           OE   4.13.0 #1
[973495] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables
          this message.
[980962] khugepaged      D    0    42      2 0x00000000
[980967] Call Trace:
[980977]  __schedule+0x28d/0x890
[980982]  schedule+0x36/0x80
[980986]  rwsem_down_read_failed+0x139/0x1c0
[980991]  ? update_curr+0x100/0x1c0
[981004]  call_rwsem_down_read_failed+0x18/0x30
[981007]  down_read+0x20/0x40
[981012]  khugepaged_scan_mm_slot+0x78/0x1ac0
[981018]  ? __switch_to+0x23e/0x4a0
[981022]  ? finish_task_switch+0x79/0x240
[981026]  khugepaged+0x146/0x480
[981031]  ? remove_wait_queue+0x60/0x60
[981035]  kthread+0x109/0x140
[981037]  ? khugepaged_scan_mm_slot+0x1ac0/0x1ac0
[981039]  ? kthread_park+0x60/0x60
[981044]  ret_from_fork+0x25/0x30

After checking code and found 'commit b72cf4fc ("drm/amdgpu: move
taking mmap_sem into get_user_pages v2")' forget to drop one case of
up_read.
Signed-off-by: NXiangliang.Yu <Xiangliang.Yu@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The function checks non-powerplay structures so regressed when
the pp_enabled check was removed.  This should ideally be
implemented similarly for powerplay.

Fixes: 6d07fe7b ("drm/amdgpu: delete pp_enable in adev")
Tested-by: NDieter Nützel <Dieter@nuetzel-hh.de>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

resulted in unexpected data truncation
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NRex Zhu <Rex.Zhu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

This patch removes DRM_TILCDC_SLAVE_COMPAT option for supporting the
obsolete "ti,tilcdc,slave" device tree binding. The new of_graph based
binding - that is widely used in other drm driver too - has been
supported since Linux v4.2. Maintaining the the backwards dts
conversion code in the DRM_TILCDC_SLAVE_COMPAT has become a nuisance
for the device/of development so the we decided to drop it after Linux
v4.14, the 2017 LTS.
Signed-off-by: NJyri Sarha <jsarha@ti.com>
Acked-by: NRob Herring <robh@kernel.org>

The current implementation of the pad clock isn't quite correct. This
has the side-effect of being incompatible with the implementation for
Tegra186 (provided by the BPMP) and therefore would require a massive
change to the driver to cope with the differences. Instead, simply do
what Tegra186 does and add some code to fallback to the old behaviour
for existing device trees.
Signed-off-by: NThierry Reding <treding@nvidia.com>

Fixes distorted colors on some cards on resume from suspend.

This reverts commit b9729b17.

Bug: https://bugs.freedesktop.org/show_bug.cgi?id=98832
Bug: https://bugs.freedesktop.org/show_bug.cgi?id=99163
Bug: https://bugzilla.kernel.org/show_bug.cgi?id=107001Reviewed-by: NMichel Dänzer <michel.daenzer@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

Fixes an oops in amdgpu_cs_wait_any_fence.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NChunming Zhou <david1.zhou@amd.com>
Signed-off-by: NRoger He <Hongbo.He@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Copy paste typo.
Signed-off-by: NEric Huang <JinHuiEric.Huang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

those RLC used buffers are not cleared in GFX's sw_fini
Signed-off-by: NMonk Liu <Monk.Liu@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

this can fix the memory leak under the case that not all
BO are freed during "takedown" stage, because originally
it blocks following kfree on mgr.
Signed-off-by: NMonk Liu <Monk.Liu@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Signed-off-by: NRex Zhu <Rex.Zhu@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Otherwise we can't correctly CPU map TTM buffers.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

v1: Properly allocate TLB invalidation engine to avoid conflict.
v2: Added comments to codes
Signed-off-by: NOak Zeng <Oak.Zeng@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Acked-by: NChristian Konig <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

The resume helpers wait for a vblank to occurre hence IRQ need
to be enabled. This avoids a warning as follows during resume:
  WARNING: CPU: 0 PID: 314 at drivers/gpu/drm/drm_atomic_helper.c:1249 drm_atomic_helper_wait_for_vblanks.part.1+0x284/0x288
  [CRTC:28:crtc-0] vblank wait timed out
Signed-off-by: NStefan Agner <stefan@agner.ch>

With commit 0a70c998 ("drm/fsl-dcu: enable pixel clock when
enabling CRTC") the pixel clock is controlled by the CRTC code.
Disabling the pixel clock in suspend leads to a warning due to
the second clk_disable_unprepare call:
  WARNING: CPU: 0 PID: 359 at drivers/clk/clk.c:594 clk_core_disable+0x8c/0x90

Remove clk_disable_unprepare call for pixel clock to avoid
unbalanced clock disable on suspend.

Fixes: 0a70c998 ("drm/fsl-dcu: enable pixel clock when enabling CRTC")
Signed-off-by: NStefan Agner <stefan@agner.ch>

Since commit 4a97a3da ("drm: Don't update property values for atomic
drivers") atomic drivers must not update property values as properties
are read from the state instead. To catch remaining users, the
drm_object_property_set_value() function now throws a warning when
called by atomic drivers on non-immutable properties, and we hit that
warning when creating connectors.

The easy fix is to just remove the drm_object_property_set_value() as it
is used here to set the initial value of the connector's DPMS property
to OFF. The DPMS property applies on top of the connector's state crtc
pointer (initialized to NULL) that is the main connector on/off control,
and should thus default to ON.

Fixes: 4a97a3da ("drm: Don't update property values for atomic drivers")
Cc: stable@vger.kernel.org
Signed-off-by: NLaurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: NStefan Agner <stefan@agner.ch>

Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NRoger He <Hongbo.He@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The bottom two bits of the simd value were being put into
the upper bits of the wave value which was likely working due
to the bits being ignored (or aliased).

Eitherway, now we mask it correctly.

(v2) Touch up using GENMASK_ULL to a couple of other functions too
Signed-off-by: NTom St Denis <tom.stdenis@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Even when it's a small handle it as 64bit value as well.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This is already hooked up to the "amdgpu_gpr" debugfs file used by
the umr userspace debugging tool.
Signed-off-by: NNicolai Hähnle <nicolai.haehnle@amd.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Signed-off-by: NKen Wang <Ken.Wang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

On the Samsung Chromebook Plus I get this error with 4.14-rc3:

BUG: scheduling while atomic: kworker/3:1/50/0x00000002
Modules linked in:
CPU: 3 PID: 50 Comm: kworker/3:1 Not tainted 4.14.0-0.rc3-kevin #2
Hardware name: Google Kevin (DT)
Workqueue: events analogix_dp_psr_work
Call trace:
[<ffffff80080873b0>] dump_backtrace+0x0/0x320
[<ffffff80080876e4>] show_stack+0x14/0x20
[<ffffff8008606d38>] dump_stack+0x9c/0xbc
[<ffffff80080c6b5c>] __schedule_bug+0x4c/0x70
[<ffffff80086188c0>] __schedule+0x3f0/0x458
[<ffffff8008618960>] schedule+0x38/0xa0
[<ffffff800861c20c>] schedule_hrtimeout_range_clock+0x84/0xe8
[<ffffff800861c2a0>] schedule_hrtimeout_range+0x10/0x18
[<ffffff800861bcec>] usleep_range+0x64/0x78
[<ffffff8008415a6c>] analogix_dp_transfer+0x16c/0x340
[<ffffff8008412550>] analogix_dpaux_transfer+0x10/0x18
[<ffffff80083ceb14>] drm_dp_dpcd_access+0x4c/0xf0
[<ffffff80083cf614>] drm_dp_dpcd_write+0x1c/0x28
[<ffffff8008413b98>] analogix_dp_disable_psr+0x60/0xa8
[<ffffff800840da3c>] analogix_dp_psr_work+0x4c/0x90
[<ffffff80080bb09c>] process_one_work+0x1d4/0x348
[<ffffff80080bb258>] worker_thread+0x48/0x478
[<ffffff80080c11fc>] kthread+0x12c/0x130
[<ffffff8008084290>] ret_from_fork+0x10/0x18

Changing rockchip_dp_device::psr_lock to a mutex rather
than spinlock seems to fix the issue.
Signed-off-by: NEmil Renner Berthing <kernel@esmil.dk>
Tested-by: NEnric Balletbo i Serra <enric.balletbo@collabora.com>
Signed-off-by: NMark Yao <mark.yao@rock-chips.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171004175346.11956-1-kernel@esmil.dk

The lease updates missed a few bits of docs, fixed up
the wrong name on the property lookup fn as well.
Reviewed-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: NDave Airlie <airlied@redhat.com>

The index to vddci_buf is using profile->ucElbVDDC_Num rather
than profile->ucElbVDDCI_Num; this looks like a copy-n-paste
error from previous code for the vddc_buf array and I'm pretty
sure this is incorrect. Fix this by using the correct variable.

Detected by CoverityScan, CID#1457172 ("Copy-paste error")

Fixes: 970d9804 ("drm/amd/powerplay: Add support functions for CI to ppatomctrl.c")
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The array[first] may be null when the fence has already been signaled.

BUG: SWDEV-136239
Signed-off-by: NEmily Deng <Emily.Deng@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Fixes vbios fetching on certain headless boards.
Signed-off-by: NKen Wang <Ken.Wang@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

When we close the VMA, we unbind it from the ppgtt and tear down the
page directory pointing at it. That may trigger us to return WC pages
back to the system, requiring conversion back to WB which itself may
sleep. That makes i915_vma_close() unsuitable for use inside the RCU
read lock, which we need to hold to iterate the radixtree.

The fix is quite simple, we can close all the VMA as we close the ppgtt,
we only need to do that instead of closing them during destruction of
the LUT.

v2: Order between closing the LUT and the ppgtt is important; we use the
vma inside the LUT as a means of retrieving the object, and so we must
clear the LUT before freeing the VMA when closing the ppgtt.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103638
Fixes: 547da76b ("drm/i915: Hold rcu_read_lock when iterating over the radixtree (vma idr)")
Fixes: d1b48c1e ("drm/i915: Replace execbuf vma ht with an idr")
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171109085540.32264-1-chris@chris-wilson.co.ukReviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
(cherry picked from commit 94dec871)
Signed-off-by: NJani Nikula <jani.nikula@intel.com>

Apparently setting up a bunch of GT registers before we've properly
initialized the rest of the GT hardware leads to these setting being
lost. So looks like I broke HSW with commit b7048ea1 ("drm/i915:
Do .init_clock_gating() earlier to avoid it clobbering watermarks")
by doing init_clock_gating() too early. This should actually affect
other platforms as well, but apparently not to such a great degree.

What I was ultimately after in that commit was to move the
ilk_init_lp_watermarks() call earlier. So let's undo the damage and
move init_clock_gating() back to where it was, and call
ilk_init_lp_watermarks() just before the watermark state readout.

This highlights how fragile and messed up our init order really is.
I wonder why we even initialize the display before gem. The opposite
order would make much more sense to me...

v2: Keep WaRsPkgCStateDisplayPMReq:hsw early as it really must
    be done before all planes might get disabled.

Cc: stable@vger.kernel.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mark Janes <mark.a.janes@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reported-by: NMark Janes <mark.a.janes@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103549
Fixes: b7048ea1 ("drm/i915: Do .init_clock_gating() earlier to avoid it clobbering watermarks")
References: https://lists.freedesktop.org/archives/intel-gfx/2017-November/145432.htmlSigned-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171108133555.14091-1-ville.syrjala@linux.intel.comTested-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
(cherry picked from commit f72b84c6)
Signed-off-by: NJani Nikula <jani.nikula@intel.com>

The shared fence array is not autopruning and may continue to grow as an
object is shared between new timelines. Take the opportunity when we
think the object is idle (we have to confirm that any external fence is
also signaled) to decouple all the fences.

We apply a similar trick after waiting on an object, see commit
e54ca977 ("drm/i915: Remove completed fences after a wait")

v2: No longer need to handle the batch pool as a special case.
v3: Need to trylock from within i915_vma_retire as this may be called
form the shrinker - and we may later try to allocate underneath the
reservation lock, so a deadlock is possible.

References: https://bugs.freedesktop.org/show_bug.cgi?id=102936
Fixes: d07f0e59 ("drm/i915: Move GEM activity tracking into a common struct reservation_object")
Fixes: 80b204bc ("drm/i915: Enable multiple timelines")
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171107220656.5020-1-chris@chris-wilson.co.ukReviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
(cherry picked from commit 1ab22356)
Signed-off-by: NJani Nikula <jani.nikula@intel.com>

The handling of contexts are peculiar. Instead of tieing their vma to
activity, we pin the context. This means that we cannot simply unbind
the context object itself at will (which would normally cause us to wait
for the vma to be idle), but must manually idle the GPU and retire
requests first.

A consequence of this peculiarity is when doing a last desperate attempt
to recover memory. If the memory is tied up inside active context
objects, we will fail to recover any memory simply by trying to unbind
the objects without first doing a wait-for-idle.

A side-effect of removing the call to shrinker_lock_uninterruptible()
from i915_gem_shrinker_oom() was that we removed an unlocked
wait-for-idle, and so lost the "natural" shrinkage of context objects.
By replacing that with a locked wait from inside i915_gem_shrink(), we
not only replace it with the ability to recover all context objects, but
do so for all i915_gem_shrink_all() callers.

v2: Switching requires request allocation, which is not permitted from
inside the shrinker as it only uses ordinary allocations.

References: https://bugs.freedesktop.org/show_bug.cgi?id=102936
Fixes: f2123818 ("drm/i915: Move dev_priv->mm.[un]bound_list to its own lock")
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171108094400.1386-1-chris@chris-wilson.co.ukReviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
(cherry picked from commit 2f6a3783)
Signed-off-by: NJani Nikula <jani.nikula@intel.com>

An oversight in commit 87701b4b ("drm/i915: Only free the oldest
stale object before a fresh allocation") was that not only do we have to
serialise concurrent users of llist_del_first(), but we also have to
lock llist_del_first() vs llist_del_all().

From llist.h,

 * This can be summarized as follows:
 *
 *           |   add    | del_first |  del_all
 * add       |    -     |     -     |     -
 * del_first |          |     L     |     L
 * del_all   |          |           |     -
 *
 * Where, a particular row's operation can happen concurrently with a column's
 * operation, with "-" being no lock needed, while "L" being lock is needed.

This should hopefully explain:

<4>[   89.287106] general protection fault: 0000 [#1] PREEMPT SMP
<4>[   89.287126] Modules linked in: snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic x86_pkg_temp_thermal intel_powerclamp coretemp i915 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core r8169 mii mei_me mei snd_pcm prime_numbers i2c_hid pinctrl_geminilake pinctrl_intel
<4>[   89.287226] CPU: 2 PID: 23 Comm: ksoftirqd/2 Tainted: G     U          4.14.0-rc8-CI-CI_DRM_3315+ #1
<4>[   89.287247] Hardware name: Intel Corp. Geminilake/GLK RVP2 LP4SD (07), BIOS GELKRVPA.X64.0062.B30.1708222146 08/22/2017
<4>[   89.287270] task: ffff88017ab34ec0 task.stack: ffffc90000128000
<4>[   89.287290] RIP: 0010:llist_add_batch+0x4/0x20
<4>[   89.287301] RSP: 0018:ffffc9000012bdb8 EFLAGS: 00010296
<4>[   89.287314] RAX: ffffffff811017ad RBX: 6e468801a1560000 RCX: ef3e53fceecdeb81
<4>[   89.287330] RDX: 6e468801a1566130 RSI: ffff880103d73d98 RDI: ffff880103d73d98
<4>[   89.287346] RBP: ffffc9000012bdb8 R08: ffff88017ab35780 R09: 0000000000000000
<4>[   89.287361] R10: ffffc9000012bd68 R11: 00000000abb18c3d R12: ffffffffa01369e0
<4>[   89.287377] R13: ffff88017fd1b8f8 R14: ffff88017ab34ec0 R15: 000000000000000a
<4>[   89.287393] FS:  0000000000000000(0000) GS:ffff88017fd00000(0000) knlGS:0000000000000000
<4>[   89.287411] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
<4>[   89.287424] CR2: 00007ff0c0755018 CR3: 000000016df9b000 CR4: 00000000003406e0
<4>[   89.287440] Call Trace:
<4>[   89.287511]  __i915_gem_free_object_rcu+0x20/0x40 [i915]
<4>[   89.287527]  rcu_process_callbacks+0x27a/0x730
<4>[   89.287544]  __do_softirq+0xc0/0x4ae
<4>[   89.287559]  ? smpboot_thread_fn+0x2d/0x280
<4>[   89.287571]  run_ksoftirqd+0x1f/0x70
<4>[   89.287582]  smpboot_thread_fn+0x18a/0x280
<4>[   89.287595]  kthread+0x114/0x150
<4>[   89.287605]  ? sort_range+0x30/0x30
<4>[   89.287615]  ? kthread_create_on_node+0x40/0x40
<4>[   89.287628]  ret_from_fork+0x27/0x40
<4>[   89.287641] Code: 0d 48 83 ea 01 4c 89 c1 48 83 fa ff 74 12 48 23 0c d7 74 ed 48 c1 e2 06 48 0f bd c9 48 8d 04 0a 5d c3 90 90 90 90 90 55 48 89 e5 <48> 8b 0a 48 89 0e 48 89 c8 f0 48 0f b1 3a 48 39 c1 75 ed 48 85
<1>[   89.287774] RIP: llist_add_batch+0x4/0x20 RSP: ffffc9000012bdb8
<4>[   89.287826] ---[ end trace e775d15174d8ae02 ]---

(Lockless lists are only easy (and lockless) when only using
llist_add/llist_del_all!)

Fixes: 87701b4b ("drm/i915: Only free the oldest stale object before
a fresh allocation")
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171106111508.11941-1-chris@chris-wilson.co.ukReviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
(cherry picked from commit f991c492)
Signed-off-by: NJani Nikula <jani.nikula@intel.com>

The watermarks it should calculate against are the old optimal watermarks.
The currently active crtc watermarks are pure fiction, and are invalid in
case of a nonblocking modeset, page flip enabling/disabling planes or any
other reason.

When the crtc is disabled or during a modeset the intermediate watermarks
don't need to be programmed separately, and could be directly assigned
to the optimal watermarks.

Changes since v1:
- Use intel_atomic_get_old_crtc_state. (ville)
Signed-off-by: NMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMatt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171019151341.4579-2-maarten.lankhorst@linux.intel.com
[mlankhorst: Add cc stable and bugzilla link, since previous patch doesn't fix issue by itself]
Cc: stable@vger.kernel.org #v4.8+
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102373
(cherry picked from commit b6b178a7)
Signed-off-by: NJani Nikula <jani.nikula@intel.com>

When running under virtualization (vGPU active), we must disable
the lazy PPGTT page table initialization optimization introduced by
commit 14826673 ("drm/i915: Only initialize partially filled
pagetables").

We must do this because GVT-g makes unduly assumptions about guest
behaviour, which this optimization breaks. This results in following
looking errors in the host:

ERROR gvt: guest page write error -22, gfn 0x7ada8, pa 0x7ada89a8, var 0x6, len 1

The real fix is to not to depend on i915 driver behaviour, but instead
either rely on only the contracts that i915 has with the hardware, or
add some paravirtualization. While the real fix is en route, it won't
be finished in time for 4.15, so the best option is to disable the
optimization for now when vGPU is active to avoid breaking 4.15 guests
in existing VM environments.

Fixes: 14826673 ("drm/i915: Only initialize partially filled pagetables")
Suggested-by: NXiaolin Zhang <xiaolin.zhang@intel.com>
Signed-off-by: NXiaolin Zhang <xiaolin.zhang@intel.com>
[Joonas: Rewrote the commit message and added tags.]
Signed-off-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: NChris Wilson <chris@chris-wilson.co.uk>
Acked-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171023153209.10527-1-joonas.lahtinen@linux.intel.com
(cherry picked from commit 22a8a4fc)
Signed-off-by: NJani Nikula <jani.nikula@intel.com>

Originally we set the priority to max upon inserting the request into
the execlists queue (and removing it from the scheduler lists). We could
then use the prio==INT_MAX as a shortcut within execlists_schedule() to
detect the end of the dependency chain. Since commit 1f181225
("drm/i915/execlists: Keep request->priority for its lifetime") this is
no longer true as we use the request completion as an indicator the
schedule dependency chain is complete instead. (This allows us to then
reschedule requests even when its context is in flight.) However, this
makes the GEM_BUG_ON() inside execlists_schedule() racy as we may change
the rq->prio at the same time. As the assertion is useful, let's keep
the assertion and remove the micro-optimisation.

Fixes: 1f181225 ("drm/i915/execlists: Keep request->priority for its lifetime")
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024115501.21033-1-chris@chris-wilson.co.ukReviewed-by: NMichał Winiarski <michal.winiarski@intel.com>
(cherry picked from commit 64b80085)
Signed-off-by: NJani Nikula <jani.nikula@intel.com>

Back in commit a4b2b015 ("drm/i915: Don't mark an execlists
context-switch when idle") we noticed the presence of late
context-switch interrupts. We were able to filter those out by looking
at whether the ELSP remained active, but in commit beecec90
("drm/i915/execlists: Preemption!") that became problematic as we now
anticipate receiving a context-switch event for preemption while ELSP
may be empty. To restore the spurious interrupt suppression, add a
counter for the expected number of pending context-switches and skip if
we do not need to handle this interrupt to make forward progress.

v2: Don't forget to switch on for preempt.
v3: Reduce the counter to a on/off boolean tracker. Declare the HW as
active when we first submit, and idle after the final completion event
(with which we confirm the HW says it is idle), and track each source
of activity separately. With a finite number of sources, it should aide
us in debugging which gets stuck.

Fixes: beecec90 ("drm/i915/execlists: Preemption!")
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Arkadiusz Hiler <arkadiusz.hiler@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171023213237.26536-3-chris@chris-wilson.co.ukReviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
(cherry picked from commit 4a118ecb)
Signed-off-by: NJani Nikula <jani.nikula@intel.com>

This lock is used during register accessing in SRIOV guest.
The register accessing could happen both in irq enabled and
irq disabled cases. Always use irq-safe lock.
Signed-off-by: NPixel Ding <Pixel.Ding@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

KIQ ring submission is used for register accessing on SRIOV
VF that could happen both in irq enabled and irq disabled cases.
Inversion lock could happen on adev->ring_lru_list_lock, while
this operation is useless and just adds overhead in this use
case.
Signed-off-by: NPixel Ding <Pixel.Ding@amd.com>
Reviewed-by: NMonk Liu <Monk.Liu@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

After commit ea09729c ("drm/amdgpu: rework page directory filling
v2") then it becomes a lot harder to verify that "r" is initialized.  My
static checker complains and so I've reviewed the code.  It does look
like it might be buggy... Anyway, it doesn't hurt to set "r" to zero
at the start.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org