drm/i915/execlists: Suppress mere WAIT preemption

WAIT is occasionally suppressed by virtue of preempted requests being
promoted to NEWCLIENT if they have not all ready received that boost.
Make thi

drm/i915/execlists: Suppress mere WAIT preemption

WAIT is occasionally suppressed by virtue of preempted requests being
promoted to NEWCLIENT if they have not all ready received that boost.
Make this consistent for all WAIT boosts that they are not allowed to
preempt executing contexts and are merely granted the right to be at the
front of the queue for the next execution slot. This is in keeping with
the desire that the WAIT boost be a minor tweak that does not give
excessive promotion to its user and open ourselves to trivial abuse.

The problem with the inconsistent WAIT preemption becomes more apparent
as the preemption is propagated across the engines, where one engine may
preempt and the other not, and we be relying on the exact execution
order being consistent across engines (e.g. using HW semaphores to
coordinate parallel execution).

v2: Also protect GuC submission from false preemption loops.
v3: Build bug safeguards and better debug messages for st.
v4: Do the priority bumping in unsubmit (i.e. on preemption/reset
unwind), applying it earlier during submit causes out-of-order execution
combined with execute fences.
v5: Call sw_fence_fini for our dummy request (Matthew)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190228220639.3173-1-chris@chris-wilson.co.uk

show more ...

drm/i915: Use __ffs() in for_each_priolist for more compact code

Gcc has a slight preference if we use __ffs() to subtract one from the
index once rather than each use:

__execlists_submission_taskl

drm/i915: Use __ffs() in for_each_priolist for more compact code

Gcc has a slight preference if we use __ffs() to subtract one from the
index once rather than each use:

__execlists_submission_tasklet 2867 2847 -20

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190226102404.29153-11-chris@chris-wilson.co.uk

show more ...

drm/i915: Make request allocation caches global

As kmem_caches share the same properties (size, allocation/free behaviour)
for all potential devices, we can use global caches. While this
potential h

drm/i915: Make request allocation caches global

As kmem_caches share the same properties (size, allocation/free behaviour)
for all potential devices, we can use global caches. While this
potential has worse fragmentation behaviour (one can argue that
different devices would have different activity lifetimes, but you can
also argue that activity is temporal across the system) it is the
default behaviour of the system at large to amalgamate matching caches.

The benefit for us is much reduced pointer dancing along the frequent
allocation paths.

v2: Defer shrinking until after a global grace period for futureproofing
multiple consumers of the slab caches, similar to the current strategy
for avoiding shrinking too early.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190228102035.5857-1-chris@chris-wilson.co.uk

show more ...

Merge tag 'v5.0-rc5' of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into fbdev-for-next

Linux 5.0-rc5

Sync with upstream (which now contains fbdev-v5.0-rc3 changes) to
prepare a

Merge tag 'v5.0-rc5' of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into fbdev-for-next

Linux 5.0-rc5

Sync with upstream (which now contains fbdev-v5.0-rc3 changes) to
prepare a base for fbdev-v5.1 changes.

show more ...

Merge tag 'v4.20' into for-linus

Sync with mainline to get linux/overflow.h among other things.

Merge tag 'v4.20' into next

Merge with mainline to bring in the new APIs.

Merge tag 'v5.0-rc1' into next-general

Linux 5.0-rc1

Sync to pick up LSM stacking work (which is based on -rc1).

Merge tag 'drm-next-2018-12-14' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
"Core:
- shared fencing staging removal
- drop transactional atomic helpers and mov

Merge tag 'drm-next-2018-12-14' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
"Core:
- shared fencing staging removal
- drop transactional atomic helpers and move helpers to new location
- DP/MST atomic cleanup
- Leasing cleanups and drop EXPORT_SYMBOL
- Convert drivers to atomic helpers and generic fbdev.
- removed deprecated obj_ref/unref in favour of get/put
- Improve dumb callback documentation
- MODESET_LOCK_BEGIN/END helpers

panels:
- CDTech panels, Banana Pi Panel, DLC1010GIG,
- Olimex LCD-O-LinuXino, Samsung S6D16D0, Truly NT35597 WQXGA,
- Himax HX8357D, simulated RTSM AEMv8.
- GPD Win2 panel
- AUO G101EVN010

vgem:
- render node support

ttm:
- move global init out of drivers
- fix LRU handling for ghost objects
- Support for simultaneous submissions to multiple engines

scheduler:
- timeout/fault handling changes to help GPU recovery
- helpers for hw with preemption support

i915:
- Scaler/Watermark fixes
- DP MST + powerwell fixes
- PSR fixes
- Break long get/put shmemfs pages
- Icelake fixes
- Icelake DSI video mode enablement
- Engine workaround improvements

amdgpu:
- freesync support
- GPU reset enabled on CI, VI, SOC15 dGPUs
- ABM support in DC
- KFD support for vega12/polaris12
- SDMA paging queue on vega
- More amdkfd code sharing
- DCC scanout on GFX9
- DC kerneldoc
- Updated SMU firmware for GFX8 chips
- XGMI PSP + hive reset support
- GPU reset
- DC trace support
- Powerplay updates for newer Polaris
- Cursor plane update fast path
- kfd dma-buf support

virtio-gpu:
- add EDID support

vmwgfx:
- pageflip with damage support

nouveau:
- Initial Turing TU104/TU106 modesetting support

msm:
- a2xx gpu support for apq8060 and imx5
- a2xx gpummu support
- mdp4 display support for apq8060
- DPU fixes and cleanups
- enhanced profiling support
- debug object naming interface
- get_iova/page pinning decoupling

tegra:
- Tegra194 host1x, VIC and display support enabled
- Audio over HDMI for Tegra186 and Tegra194

exynos:
- DMA/IOMMU refactoring
- plane alpha + blend mode support
- Color format fixes for mixer driver

rcar-du:
- R8A7744 and R8A77470 support
- R8A77965 LVDS support

imx:
- fbdev emulation fix
- multi-tiled scalling fixes
- SPDX identifiers

rockchip
- dw_hdmi support
- dw-mipi-dsi + dual dsi support
- mailbox read size fix

qxl:
- fix cursor pinning

vc4:
- YUV support (scaling + cursor)

v3d:
- enable TFU (Texture Formatting Unit)

mali-dp:
- add support for linear tiled formats

sun4i:
- Display Engine 3 support
- H6 DE3 mixer 0 support
- H6 display engine support
- dw-hdmi support
- H6 HDMI phy support
- implicit fence waiting
- BGRX8888 support

meson:
- Overlay plane support
- implicit fence waiting
- HDMI 1.4 4k modes

bridge:
- i2c fixes for sii902x"

* tag 'drm-next-2018-12-14' of git://anongit.freedesktop.org/drm/drm: (1403 commits)
drm/amd/display: Add fast path for cursor plane updates
drm/amdgpu: Enable GPU recovery by default for CI
drm/amd/display: Fix duplicating scaling/underscan connector state
drm/amd/display: Fix unintialized max_bpc state values
Revert "drm/amd/display: Set RMX_ASPECT as default"
drm/amdgpu: Fix stub function name
drm/msm/dpu: Fix clock issue after bind failure
drm/msm/dpu: Clean up dpu_media_info.h static inline functions
drm/msm/dpu: Further cleanups for static inline functions
drm/msm/dpu: Cleanup the debugfs functions
drm/msm/dpu: Remove dpu_irq and unused functions
drm/msm: Make irq_postinstall optional
drm/msm/dpu: Cleanup callers of dpu_hw_blk_init
drm/msm/dpu: Remove unused functions
drm/msm/dpu: Remove dpu_crtc_is_enabled()
drm/msm/dpu: Remove dpu_crtc_get_mixer_height
drm/msm/dpu: Remove dpu_dbg
drm/msm: dpu: Remove crtc_lock
drm/msm: dpu: Remove vblank_requested flag from dpu_crtc
drm/msm: dpu: Separate crtc assignment from vblank enable
...

show more ...

Merge remote-tracking branch 'drm/drm-next' into drm-misc-next

Requested by Boris Brezillon for some vc4 fixes that are needed for future vc4 work.

Signed-off-by: Maarten Lankhorst <maarten.lankhor

Merge remote-tracking branch 'drm/drm-next' into drm-misc-next

Requested by Boris Brezillon for some vc4 fixes that are needed for future vc4 work.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>

show more ...

Merge tag 'drm-intel-next-2018-11-22' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Changes outside i915:
- Connector property to limit max bpc (Radhakrishna)
- Fix LPE audio runtime

Merge tag 'drm-intel-next-2018-11-22' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Changes outside i915:
- Connector property to limit max bpc (Radhakrishna)
- Fix LPE audio runtime PM and deinit (Ville)
- DP FEC prep work (Anusha)
- Mark pinned shmemfs pages as unevictable (Kuo-Hsin)
- Backmerge drm-next (Jani)

Inside i915:
- Revert OA UAPI change that lacks userspace (Joonas)
- Register macro cleanup (Jani)
- 32-bit build fixes on pin flags (Chris)
- Fix MG DP mode and PHY gating for HDMI (Imre)
- DP MST race, hpd and irq fixes (Lyude)
- Combo PHY fixes and cleanup (Imre, Lucas)
- Move display init and cleanup under modeset init and cleanup (José)
- PSR fixes (José)
- Subslice size fixes (Daniele)
- Abstract and clean up fixed point helpers (Jani)
- Plane input CSC for YUV to RGB conversion (Uma)
- Break long iterations for get/put shmemfs pages (Chris)
- Improve DDI encoder hw state readout sanity checks (Imre)
- Fix power well leaks for MST (José)
- Scaler fixes (Ville)
- Watermark fixes (Ville)
- Fix VLV/CHV DSI panel orientation readout (Ville)
- ICL rawclock fixes (Paulo)
- Workaround DMC power well request issues (Imre)
- Plane allocation fix (Maarten)
- Transcoder enum value/ordering robustness fixes (Imre)
- UTS_RELEASE build dependency fix (Hans Holmberg)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/87k1l4cesj.fsf@intel.com

show more ...

drm/i915: Priority boost for waiting clients

Latency is in the eye of the beholder. In the case where a client stops
and waits for the gpu, give that request chain a small priority boost
(not so tha

drm/i915: Priority boost for waiting clients

Latency is in the eye of the beholder. In the case where a client stops
and waits for the gpu, give that request chain a small priority boost
(not so that it overtakes higher priority clients, to preserve the
external ordering) so that ideally the wait completes earlier.

v2: Tvrtko recommends to keep the boost-from-user-stall as small as
possible and to allow new client flows to be preferred for interactivity
over stalls.

Testcase: igt/gem_sync/switch-default
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181001144755.7978-3-chris@chris-wilson.co.uk

show more ...

drm/i915: Pull scheduling under standalone lock

Currently, the backend scheduling code abuses struct_mutex into order to
have a global lock to manipulate a temporary list (without widespread
allocat

drm/i915: Pull scheduling under standalone lock

Currently, the backend scheduling code abuses struct_mutex into order to
have a global lock to manipulate a temporary list (without widespread
allocation) and to protect against list modifications. This is an
extraneous coupling to struct_mutex and further can not extend beyond
the local device.

Pull all the code that needs to be under the one true lock into
i915_scheduler.c, and make it so.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181001144755.7978-2-chris@chris-wilson.co.uk

show more ...

drm/i915: Priority boost for new clients

Taken from an idea used for FQ_CODEL, we give the first request of a
new request flows a small priority boost. These flows are likely to
correspond with shor

drm/i915: Priority boost for new clients

Taken from an idea used for FQ_CODEL, we give the first request of a
new request flows a small priority boost. These flows are likely to
correspond with short, interactive tasks and so be more latency sensitive
than the longer free running queues. As soon as the client has more than
one request in the queue, further requests are not boosted and it settles
down into ordinary steady state behaviour. Such small kicks dramatically
help combat the starvation issue, by allowing each client the opportunity
to run even when the system is under heavy throughput load (within the
constraints of the user selected priority).

v2: Mark the preempted request as the start of a new flow, to prevent a
single client being continually gazumped by its peers.

Testcase: igt/benchmarks/rrul
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181001144755.7978-1-chris@chris-wilson.co.uk

show more ...

drm/i915: Reserve some priority bits for internal use

In the next few patches, we will want to give a small priority boost to
some requests/queues but not so much that we perturb the user controlled

drm/i915: Reserve some priority bits for internal use

In the next few patches, we will want to give a small priority boost to
some requests/queues but not so much that we perturb the user controlled
order. As such we will shift the user priority bits higher leaving
ourselves a few low priority bits for our internal bumping.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181001123204.23982-3-chris@chris-wilson.co.uk

show more ...

Merge tag 'v4.18-rc2' of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into fbdev-for-next

Linux 4.18-rc2

Merge tag 'v4.18-rc2' into next-general

Merge to Linux 4.18-rc2 for security subsystem developers.

Merge drm-upstream/drm-next into drm-misc-next

We got a few conflicts in drm_atomic.c after merging the DRM writeback support,
now we need a backmerge to unlock develop development on drm-misc-next.

Merge drm-upstream/drm-next into drm-misc-next

We got a few conflicts in drm_atomic.c after merging the DRM writeback support,
now we need a backmerge to unlock develop development on drm-misc-next.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>

show more ...

Merge branch 'linus' into x86/urgent

Required to queue a dependent fix.

Merge tag 'drm-next-2018-06-06-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
"This starts to support NVIDIA volta hardware with nouveau, and adds
amdgpu support f

Merge tag 'drm-next-2018-06-06-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
"This starts to support NVIDIA volta hardware with nouveau, and adds
amdgpu support for the GPU in the Kabylake-G (the intel + radeon
single package chip), along with some initial Intel icelake enabling.

Summary:

New Drivers:
- v3d - driver for broadcom V3D V3.x+ hardware
- xen-front - XEN PV display frontend

core:
- handle zpos normalization in the core
- stop looking at legacy pointers in atomic paths
- improved scheduler documentation
- improved aspect ratio validation
- aspect ratio support for 64:27 and 256:135
- drop unused control node code.

i915:
- Icelake (ICL) enabling
- GuC/HuC refactoring
- PSR/PSR2 enabling and fixes
- DPLL management refactoring
- DP MST fixes
- NV12 enabling
- HDCP improvements
- GEM/Execlist/reset improvements
- GVT improvements
- stolen memory first 4k fix

amdgpu:
- Vega 20 support
- VEGAM support (Kabylake-G)
- preOS scanout buffer reservation
- power management gfxoff support for raven
- SR-IOV fixes
- Vega10 power profiles and clock voltage control
- scatter/gather display support on CZ/ST

amdkfd:
- GFX9 dGPU support
- userptr memory mapping

nouveau:
- major refactoring for Volta GV100 support

tda998x:
- HDMI i2c CEC support

etnaviv:
- removed unused logging code
- license text cleanups
- MMU handling improvements
- timeout fence fix for 50 days uptime

tegra:
- IOMMU support in gr2d/gr3d drivers
- zpos support

vc4:
- syncobj support
- CTM, plane alpha and async cursor support

analogix_dp:
- HPD and aux chan fixes

sun4i:
- MIPI DSI support

tilcdc:
- clock divider fixes for OMAP-l138 LCDK board

rcar-du:
- R8A77965 support
- dma-buf fences fixes
- hardware indexed crtc/du group handling
- generic zplane property support

atmel-hclcdc:
- generic zplane property support

mediatek:
- use generic video mode function

exynos:
- S5PV210 FIMD variant support
- IPP v2 framework
- more HW overlays support"

* tag 'drm-next-2018-06-06-1' of git://anongit.freedesktop.org/drm/drm: (1286 commits)
drm/amdgpu: fix 32-bit build warning
drm/exynos: fimc: signedness bug in fimc_setup_clocks()
drm/exynos: scaler: fix static checker warning
drm/amdgpu: Use dev_info() to report amdkfd is not supported for this ASIC
drm/amd/display: Remove use of division operator for long longs
drm/amdgpu: Update GFX info structure to match what vega20 used
drm/amdgpu/pp: remove duplicate assignment
drm/sched: add rcu_barrier after entity fini
drm/amdgpu: move VM BOs on LRU again
drm/amdgpu: consistenly use VM moved flag
drm/amdgpu: kmap PDs/PTs in amdgpu_vm_update_directories
drm/amdgpu: further optimize amdgpu_vm_handle_moved
drm/amdgpu: cleanup amdgpu_vm_validate_pt_bos v2
drm/amdgpu: rework VM state machine lock handling v2
drm/amdgpu: Add runtime VCN PG support
drm/amdgpu: Enable VCN static PG by default on RV
drm/amdgpu: Add VCN static PG support on RV
drm/amdgpu: Enable VCN CG by default on RV
drm/amdgpu: Add static CG control for VCN on RV
drm/exynos: Fix default value for zpos plane property
...

show more ...

Merge tag 'drm-intel-next-2018-05-14' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Last drm/i915 changes for v4.18:

- NV12 enabling (Chandra, Maarten)
- ICL workarounds (Oscar)
- IC

Merge tag 'drm-intel-next-2018-05-14' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Last drm/i915 changes for v4.18:

- NV12 enabling (Chandra, Maarten)
- ICL workarounds (Oscar)
- ICL basic DPLL enabling (Paulo)
- GVT updates
- DP link config refactoring (Jani)
- Module parameter to override DMC firmware (Jani)
- PSR updates (José, DK, Daniel, Ville)
- ICL DP vswing programming (Manasi)
- ICL DBuf slice updates (Mahesh)
- Selftest fixes and updates (Chris, Matthew, Oscar)
- Execlist fixes and updates (Chris)
- Stolen memory first 4k fix (Hans de Goede)
- wait_for fixes (Mika)
- Tons of GEM improvements (Chris)
- Plenty of other fixes and improvements (Everyone)
- Crappy changelog (Me)

Signed-off-by: Dave Airlie <airlied@redhat.com>

# gpg: Signature made Mon 14 May 2018 11:04:24 PM AEST
# gpg: using RSA key D398079D26ABEE6F
# gpg: Good signature from "Jani Nikula <jani.nikula@intel.com>"
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg: There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 1565 A65B 77B0 632E 1124 E59C D398 079D 26AB EE6F

# Conflicts:
# drivers/gpu/drm/i915/intel_lrc.c
# drivers/gpu/drm/i915/intel_sprite.c
Link: https://patchwork.freedesktop.org/patch/msgid/87k1s51bvw.fsf@intel.com

show more ...

Merge branch 'drm-intel-next-queued' into gvt-next

Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>

drm/i915: Pack params to engine->schedule() into a struct

Today we only want to pass along the priority to engine->schedule(), but
in the future we want to have much more control over the various as

drm/i915: Pack params to engine->schedule() into a struct

Today we only want to pass along the priority to engine->schedule(), but
in the future we want to have much more control over the various aspects
of the GPU during a context's execution, for example controlling the
frequency allowed. As we need an ever growing number of parameters for
scheduling, move those into a struct for convenience.

v2: Move the anonymous struct into its own function for legibility and
ye olde gcc.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180418184052.7129-3-chris@chris-wilson.co.uk

show more ...

drm/i915: Rename priotree to sched

Having moved the priotree struct into i915_scheduler.h, identify it as
the scheduling element and rebrand into i915_sched. This becomes more
useful as we start att

drm/i915: Rename priotree to sched

Having moved the priotree struct into i915_scheduler.h, identify it as
the scheduling element and rebrand into i915_sched. This becomes more
useful as we start attaching more information we require to propagate
through the scheduler.

v2: Use i915_sched_node for future distinctiveness

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180418184052.7129-2-chris@chris-wilson.co.uk

show more ...

drm/i915: Move the priotree struct to its own headers

Over time the priotree has grown from a sorted list to a more
complicated structure for propagating constraints along the dependency
chain to tr

drm/i915: Move the priotree struct to its own headers

Over time the priotree has grown from a sorted list to a more
complicated structure for propagating constraints along the dependency
chain to try and resolve priority inversion. Start to segregate this
information from the rest of the request/fence tracking.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180418184052.7129-1-chris@chris-wilson.co.uk

show more ...