To implement preempt-to-busy (and so efficient timeslicing and best utilization
of the hardware submission ports) we let the GPU run asynchronously in respect
to the ELSP submission queue. This created challenges in keeping and accessing
the driver state mirroring the asynchronous GPU execution.
The latest occurence of this was spotted by KCSAN:
[ 1413.563200] BUG: KCSAN: data-race in __await_execution+0x217/0x370 [i915]
[ 1413.563221]
[ 1413.563236] race at unknown origin, with read to 0xffff88885bb6c478 of 8 bytes by task 9654 on cpu 1:
[ 1413.563548] __await_execution+0x217/0x370 [i915]
[ 1413.563891] i915_request_await_dma_fence+0x4eb/0x6a0 [i915]
[ 1413.564235] i915_request_await_object+0x421/0x490 [i915]
[ 1413.564577] i915_gem_do_execbuffer+0x29b7/0x3c40 [i915]
[ 1413.564967] i915_gem_execbuffer2_ioctl+0x22f/0x5c0 [i915]
[ 1413.564998] drm_ioctl_kernel+0x156/0x1b0
[ 1413.565022] drm_ioctl+0x2ff/0x480
[ 1413.565046] __x64_sys_ioctl+0x87/0xd0
[ 1413.565069] do_syscall_64+0x4d/0x80
[ 1413.565094] entry_SYSCALL_64_after_hwframe+0x44/0xa9
To complicate matters, we have to both avoid the read tearing of *active and
avoid any write tearing as perform the pending[] -> inflight[] promotion of the
execlists.
This is because we cannot rely on the memcpy doing u64 aligned copies on all
kernels/platforms and so we opt to open-code it with explicit WRITE_ONCE
annotations to satisfy KCSAN.
v2: When in doubt, write the same comment again.
v3: Expanded commit message.
Fixes: b55230e5e8 ("drm/i915: Check for awaits on still currently executing requests")
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>
Link: https://patchwork.freedesktop.org/patch/msgid/20200716142207.13003-1-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Joonas: Rebased and reordered into drm-intel-gt-next branch]
[Joonas: Added expanded commit message from Tvrtko and Chris]
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
(cherry picked from commit b4d9145b01)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Pull drm updates from Dave Airlie:
"New xilinx displayport driver, AMD support for two new GPUs (more
header files), i915 initial support for RocketLake and some work on
their DG1 (discrete chip).
The core also grew some lockdep annotations to try and constrain what
drivers do with dma-fences, and added some documentation on why the
idea of indefinite fences doesn't work.
The long list is below.
I do have some fixes trees outstanding, but I'll follow up with those
later.
core:
- add user def flag to cmd line modes
- dma_fence_wait added might_sleep
- dma-fence lockdep annotations
- indefinite fences are bad documentation
- gem CMA functions used in more drivers
- struct mutex removal
- more drm_ debug macro usage
- set/drop master api fixes
- fix for drm/mm hole size comparison
- drm/mm remove invalid entry optimization
- optimise drm/mm hole handling
- VRR debugfs added
- uncompressed AFBC modifier support
- multiple display id blocks in EDID
- multiple driver sg handling fixes
- __drm_atomic_helper_crtc_reset in all drivers
- managed vram helpers
ttm:
- ttm_mem_reg handling cleanup
- remove bo offset field
- drop CMA memtype flag
- drop mappable flag
xilinx:
- New Xilinx ZynqMP DisplayPort Subsystem driver
nouveau:
- add CRC support
- start using NVIDIA published class header files
- convert all push buffer emission to new macros
- Proper push buffer space management for EVO/NVD channels.
- firmware loading fixes
- 2MiB system memory pages support on Pascal and newer
vkms:
- larger cursor support
i915:
- Rocketlake platform enablement
- Early DG1 enablement
- Numerous GEM refactorings
- DP MST fixes
- FBC, PSR, Cursor, Color, Gamma fixes
- TGL, RKL, EHL workaround updates
- TGL 8K display support fixes
- SDVO/HDMI/DVI fixes
amdgpu:
- Initial support for Sienna Cichlid GPU
- Initial support for Navy Flounder GPU
- SI UVD/VCE support
- expose rotation property
- Add support for unique id on Arcturus
- Enable runtime PM on vega10 boards that support BACO
- Skip BAR resizing if the bios already did id
- Major swSMU code cleanup
- Fixes for DCN bandwidth calculations
amdkfd:
- Track SDMA usage per process
- SMI events interface
radeon:
- Default to on chip GART for AGP boards on all arches
- Runtime PM reference count fixes
msm:
- headers regenerated causing churn
- a650/a640 display and GPU enablement
- dpu dither support for 6bpc panels
- dpu cursor fix
- dsi/mdp5 enablement for sdm630/sdm636/sdm66
tegra:
- video capture prep support
- reflection support
mediatek:
- convert mtk_dsi to bridge API
meson:
- FBC support
sun4i:
- iommu support
rockchip:
- register locking fix
- per-pixel alpha support PX30 VOP
mgag200:
- ported to simple and shmem helpers
- device init cleanups
- use managed pci functions
- dropped hw cursor support
ast:
- use managed pci functions
- use managed VRAM helpers
- rework cursor support
malidp:
- dev_groups support
hibmc:
- refactor hibmc_drv_vdac:
vc4:
- create TXP CRTC
imx:
- error path fixes and cleanups
etnaviv:
- clock handling and error handling cleanups
- use pin_user_pages"
* tag 'drm-next-2020-08-06' of git://anongit.freedesktop.org/drm/drm: (1747 commits)
drm/msm: use kthread_create_worker instead of kthread_run
drm/msm/mdp5: Add MDP5 configuration for SDM636/660
drm/msm/dsi: Add DSI configuration for SDM660
drm/msm/mdp5: Add MDP5 configuration for SDM630
drm/msm/dsi: Add phy configuration for SDM630/636/660
drm/msm/a6xx: add A640/A650 hwcg
drm/msm/a6xx: hwcg tables in gpulist
drm/msm/dpu: add SM8250 to hw catalog
drm/msm/dpu: add SM8150 to hw catalog
drm/msm/dpu: intf timing path for displayport
drm/msm/dpu: set missing flush bits for INTF_2 and INTF_3
drm/msm/dpu: don't use INTF_INPUT_CTRL feature on sdm845
drm/msm/dpu: move some sspp caps to dpu_caps
drm/msm/dpu: update UBWC config for sm8150 and sm8250
drm/msm/dpu: use right setup_blend_config for sm8150 and sm8250
drm/msm/a6xx: set ubwc config for A640 and A650
drm/msm/adreno: un-open-code some packets
drm/msm: sync generated headers
drm/msm/a6xx: add build_bw_table for A640/A650
drm/msm/a6xx: fix crashstate capture for A650
...
Preempt-to-busy introduces various fascinating complications in that the
requests may complete as we are unsubmitting them from HW. As they may
then signal after unsubmission, we may find ourselves having to cleanup
the signaling request from within the signaling callback. This causes us
to recurse onto the same i915_request.lock.
However, if the request is already signaled (as it will be before we
enter the signal callbacks), we know we can skip the signaling of that
request during submission, neatly evading the spinlock recursion.
unsubmit(ve.rq0) # timeslice expiration or other preemption
-> virtual_submit_request(ve.rq0)
dma_fence_signal(ve.rq0) # request completed before preemption ack
-> submit_notify(ve.rq1)
-> virtual_submit_request(ve.rq1) # sees that we have completed ve.rq0
-> __i915_request_submit(ve.rq0)
[ 264.210142] BUG: spinlock recursion on CPU#2, sample_multi_tr/2093
[ 264.210150] lock: 0xffff9efd6ac55080, .magic: dead4ead, .owner: sample_multi_tr/2093, .owner_cpu: 2
[ 264.210155] CPU: 2 PID: 2093 Comm: sample_multi_tr Tainted: G U
[ 264.210158] Hardware name: Intel Corporation CoffeeLake Client Platform/CoffeeLake S UDIMM RVP, BIOS CNLSFWR1.R00.X212.B01.1909060036 09/06/2019
[ 264.210160] Call Trace:
[ 264.210167] dump_stack+0x98/0xda
[ 264.210174] spin_dump.cold+0x24/0x3c
[ 264.210178] do_raw_spin_lock+0x9a/0xd0
[ 264.210184] _raw_spin_lock_nested+0x6a/0x70
[ 264.210314] __i915_request_submit+0x10a/0x3c0 [i915]
[ 264.210415] virtual_submit_request+0x9b/0x380 [i915]
[ 264.210516] submit_notify+0xaf/0x14c [i915]
[ 264.210602] __i915_sw_fence_complete+0x8a/0x230 [i915]
[ 264.210692] i915_sw_fence_complete+0x2d/0x40 [i915]
[ 264.210762] __dma_i915_sw_fence_wake+0x19/0x30 [i915]
[ 264.210767] dma_fence_signal_locked+0xb1/0x1c0
[ 264.210772] dma_fence_signal+0x29/0x50
[ 264.210871] i915_request_wait+0x5cb/0x830 [i915]
[ 264.210876] ? dma_resv_get_fences_rcu+0x294/0x5d0
[ 264.210974] i915_gem_object_wait_fence+0x2f/0x40 [i915]
[ 264.211084] i915_gem_object_wait+0xce/0x400 [i915]
[ 264.211178] i915_gem_wait_ioctl+0xff/0x290 [i915]
Fixes: 22b7a426bb ("drm/i915/execlists: Preempt-to-busy")
References: 6d06779e86 ("drm/i915: Load balancing across a virtual engine")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: "Nayana, Venkata Ramana" <venkata.ramana.nayana@intel.com>
Cc: <stable@vger.kernel.org> # v5.4+
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200713141636.29326-1-chris@chris-wilson.co.uk
If something has gone awry with the CSB processing, we need to pause,
unwind and restart the request submission and event processing. However,
currently we skip the engine reset if we raise an error but discover no
active context, in the mistaken belief that it was merely a glitch in
the matrix. The glitches are real enough, and we do need to unwind even
if the engine appears idle (as it has gone permanently idle!) The
simplest way to unwind and recover is simply do the engine reset, which
should be very fast and _safe_ as nothing is active.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200711091349.28865-1-chris@chris-wilson.co.uk
If the HW throws a curve ball and reports either en event before it is
possible, or just a completely impossible event, we have to grin and
bear it. The first few events, we will likely not notice as we would be
expecting some event, but as soon as we stop expecting an event and yet
they still keep coming, then we enter into undefined state territory.
In which case, bail out, stop processing the events, and reset the
engine and our set of queued requests to recover.
The sporadic hangs and warnings will continue to plague CI, but at least
system stability should not be compromised.
v2: Commentary and force the reset-on-error.
v3: Customised user facing message for forced resets from internal errors.
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2045
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>
Link: https://patchwork.freedesktop.org/patch/msgid/20200710133125.30194-1-chris@chris-wilson.co.uk
We removed retiring requests from the shrinker in order to decouple the
mutexes from reclaim in preparation for unravelling the struct_mutex.
The impact of not retiring is that we are much less agressive in making
global objects available for shrinking, as such objects remain pinned
until they are flushed by a heartbeat pulse following the last retired
request along their timeline. In order to ensure that pulse occurs in
time for memory reclamation, we should kick it from kswapd.
The catch is that we have added some flush_work() into the retirement
phase (to ensure that we reach a global idle in a timely manner), but
these flush_work() are not eligible (i.e do not belong to WQ_MEM_RELCAIM)
for use from inside kswapd. To avoid flushing those workqueues, we teach
the retirer not to do so unless we are actually waiting, and only do the
plain retire from inside the shrinker.
Note that for execlists, we already retire completed contexts as they
are scheduled out, so it should not be keeping global state
unnecessarily pinned. The legacy ringbuffer however...
References: 9e9539800d ("drm/i915: Remove waiting & retiring from shrinker paths")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200708173748.32734-1-chris@chris-wilson.co.uk
Getting wedged device on driver init is pretty much unrecoverable.
Since we're running various scenarios that may potentially hit this in
CI (module reload / selftests / hotunplug), and if it happens, it means
that we can't trust any subsequent CI results, we should just apply the
taint to let the CI know that it should reboot (CI checks taint between
test runs).
v2: Comment that WEDGED_ON_INIT is non-recoverable, distinguish
WEDGED_ON_INIT from WEDGED_ON_FINI (Chris)
v3: Appease checkpatch, fixup search-replace logic expression mindbomb
in assert (Chris)
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Petri Latvala <petri.latvala@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200706144107.204821-1-michal@hardline.pl
If the driver gets stuck holding the kernel timeline, we cannot issue a
heartbeat and so fail to discover that the driver is indeed stuck and do
not issue a GPU reset (which would hopefully unstick the driver!).
Switch to using a trylock so that we can query if the heartbeat's
timeline mutex is locked elsewhere, and then use the timer to probe if it
remains stuck at the same spot for consecutive heartbeats, indicating
that the mutex has not been released and the engine has not progressed.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200702095219.963-1-chris@chris-wilson.co.uk
Alexandre Oliva has recently removed these files from Linux Libre
with concerns that the sources weren't available.
The sources are available on IGT repository, and only open source
tools are used to generate the {ivb,hsw}_clear_kernel.c files.
However, the remaining concern from Alexandre Oliva was around
GPL license and the source not been present when distributing
the code.
So, it looks like 2 alternatives are possible, the use of
linux-firmware.git repository to store the blob or making sure
that the source is also present in our tree. Since the goal
is to limit the i915 firmware to only the micro-controller blobs
let's make sure that we do include the asm sources here in our tree.
Btw, I tried to have some diligence here and make sure that the
asms that these commits are adding are truly the source for
the mentioned files:
igt$ ./scripts/generate_clear_kernel.sh -g ivb \
-m ~/mesa/build/src/intel/tools/i965_asm
Output file not specified - using default file "ivb-cb_assembled"
Generating gen7 CB Kernel assembled file "ivb_clear_kernel.c"
for i915 driver...
igt$ diff ~/i915/drm-tip/drivers/gpu/drm/i915/gt/ivb_clear_kernel.c \
ivb_clear_kernel.c
< * Generated by: IGT Gpu Tools on Fri 21 Feb 2020 05:29:32 AM UTC
> * Generated by: IGT Gpu Tools on Mon 08 Jun 2020 10:00:54 AM PDT
61c61
< };
> };
\ No newline at end of file
igt$ ./scripts/generate_clear_kernel.sh -g hsw \
-m ~/mesa/build/src/intel/tools/i965_asm
Output file not specified - using default file "hsw-cb_assembled"
Generating gen7.5 CB Kernel assembled file "hsw_clear_kernel.c"
for i915 driver...
igt$ diff ~/i915/drm-tip/drivers/gpu/drm/i915/gt/hsw_clear_kernel.c \
hsw_clear_kernel.c
5c5
< * Generated by: IGT Gpu Tools on Fri 21 Feb 2020 05:30:13 AM UTC
> * Generated by: IGT Gpu Tools on Mon 08 Jun 2020 10:01:42 AM PDT
61c61
< };
> };
\ No newline at end of file
Used IGT and Mesa master repositories from Fri Jun 5 2020)
IGT: 53e8c878a6fb ("tests/kms_chamelium: Force reprobe after replugging
the connector")
Mesa: 5d13c7477eb1 ("radv: set keep_statistic_info with
RADV_DEBUG=shaderstats")
Mesa built with: meson build -D platforms=drm,x11 -D dri-drivers=i965 \
-D gallium-drivers=iris -D prefix=/usr \
-D libdir=/usr/lib64/ -Dtools=intel \
-Dkulkan-drivers=intel && ninja -C build
v2: Header clean-up and include build instructions in a readme (Chris)
Modified commit message to respect check-patch
Reference: http://www.fsfla.org/pipermail/linux-libre/2020-June/003374.html
Reference: http://www.fsfla.org/pipermail/linux-libre/2020-June/003375.html
Fixes: 47f8253d2b ("drm/i915/gen7: Clear all EU/L3 residual contexts")
Cc: <stable@vger.kernel.org> # v5.7+
Cc: Alexandre Oliva <lxoliva@fsfla.org>
Cc: Prathap Kumar Valsan <prathap.kumar.valsan@intel.com>
Cc: Akeem G Abodunrin <akeem.g.abodunrin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200610201807.191440-1-rodrigo.vivi@intel.com
(cherry picked from commit 5a7eeb8ba1)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Start using device specific parameters instead of module parameters for
most things. The module parameters become the immutable initial values
for i915 parameters. The device specific parameters in i915->params
start life as a copy of i915_modparams. Any later changes are only
reflected in the debugfs.
The stragglers are:
* i915.force_probe and i915.modeset. Needed before dev_priv is
available. This is fine because the parameters are read-only and never
modified.
* i915.verbose_state_checks. Passing dev_priv to I915_STATE_WARN and
I915_STATE_WARN_ON would result in massive and ugly churn. This is
handled by not exposing the parameter via debugfs, and leaving the
parameter writable in sysfs. This may be fixed up in follow-up work.
* i915.inject_probe_failure. Only makes sense in terms of the module,
not the device. This is handled by not exposing the parameter via
debugfs.
v2: Fix uc i915 lookup code (Michał Winiarski)
Cc: Juha-Pekka Heikkilä <juha-pekka.heikkila@intel.com>
Cc: Venkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Michał Winiarski <michal.winiarski@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20200618150402.14022-1-jani.nikula@intel.com
We only emit the renderstate once now during module load, it is no
longer a concern that we are delaying context creation and so do not
need to so eagerly optimise. Since the last time we have looked at the
renderstate, we have a pin_map / flush_map facility that supports simple
single mappings, replacing the open-coded kmap_atomic() and
prepare_write. As it should be a single page, of which we only write a
small portion, we stick to a simple WB [kmap] and use clflush on !llc
platforms, rather than creating a temporary WC vmapping for the single
page.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200619234543.17499-2-chris@chris-wilson.co.uk
Not too long ago, we realised we had issues with a rolling back a
context so far for a preemption request we considered the resubmit not
to be a rollback but a forward roll. This means we would issue a lite
restore instead of forcing a full restore, continuing execution of the
old requests rather than causing a preemption. Add a selftest to
exercise such a far rollback, such that if we were to skip the full
restore, we would execute invalid instructions in the ring and hang.
Note that while I was able to confirm that this causes us to do a
lite-restore preemption rollback (with commit e36ba817fa ("drm/i915/gt:
Incrementally check for rewinding") disabled), it did not trick the HW
into rolling past the old RING_TAIL. Myybe on other HW.
References: e36ba817fa ("drm/i915/gt: Incrementally check for rewinding")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200616185518.11948-1-chris@chris-wilson.co.uk
