Pull the repeated check for the last active request being completed to a
single spot, when deciding whether or not execlist preemption is
required.
In doing so, we remove the tasklet kick, introduced with the completion
checks in commit 35f3fd8182 ("drm/i915/execlists: Workaround switching
back to a completed context"), if we find the request was completed but
have not yet seen the corresponding CS event. This was devolving into a
busy spin of the tasklet while we waited for the event as the delivery
was not as instantaneous as expected. Under load this is sufficient to
exhaust the tasklet softirq timeslice, and force ksoftirqd. Quite
noticeable overhead for no apparent improvement in latency.
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/20201126140407.31952-2-chris@chris-wilson.co.uk
Since the introduction of preempt-to-busy, requests can complete in the
background, even while they are not on the engine->active.requests list.
As such, the engine->active.request list itself is not in strict
retirement order, and we have to scan the entire list while unwinding to
not miss any. However, if the request is completed we currently leave it
on the list [until retirement], but we could just as simply remove it
and stop treating it as active. We would only have to then traverse it
once while unwinding in quick succession.
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/20201126140407.31952-1-chris@chris-wilson.co.uk
Since preempt-to-busy, we may unsubmit a request while it is still on
the HW and completes asynchronously. That means it may be retired and in
the process destroy the virtual engine (as the user has closed their
context), but that engine may still be holding onto the unsubmitted
compelted request. Therefore we need to potentially cleanup the old
request on destroying the virtual engine. We also have to keep the
virtual_engine alive until after the sibling's execlists_dequeue() have
finished peeking into the virtual engines, for which we serialise with
RCU.
v2: Be paranoid and flush the tasklet as well.
v3: And flush the tasklet before the engines, as the tasklet may
re-attach an rb_node after our removal from the siblings.
Fixes: 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>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201123113717.20500-4-chris@chris-wilson.co.uk
Move the register slow register write and readback from out of the
critical path for execlists submission and delay it until the following
worker, shaving off around 200us. Note that the same signal_irq_work() is
allowed to run concurrently on each CPU (but it will only be queued once,
once running though it can be requeued and reexecuted) so we have to
remember to lock the global interactions as we cannot rely on the
signal_irq_work() itself providing the serialisation (in constrast to a
tasklet).
By pushing the arm/disarm into the central signaling worker we can close
the race for disarming the interrupt (and dropping its associated
GT wakeref) on parking the engine. If we loose the race, that GT wakeref
may be held indefinitely, preventing the machine from sleeping while
the GPU is ostensibly idle.
v2: Move the self-arming parking of the signal_irq_work to a flush of
the irq-work from intel_breadcrumbs_park().
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2271
Fixes: e23005604b ("drm/i915/gt: Hold context/request reference while breadcrumbs are active")
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/20201123113717.20500-1-chris@chris-wilson.co.uk
Include the signalers each request in the timeline is waiting on, as a
means to try and identify the cause of a stall. This can be quite
verbose, even as for now we only show each request in the timeline and
its immediate antecedents.
This generates output like:
Timeline 886: { count 1, ready: 0, inflight: 0, seqno: { current: 664, last: 666 }, engine: rcs0 }
U 886:29a- prio=0 @ 134ms: gem_exec_parall<4621>
U bc1:27a- prio=0 @ 134ms: gem_exec_parall[4917]
Timeline 825: { count 1, ready: 0, inflight: 0, seqno: { current: 802, last: 804 }, engine: vcs0 }
U 825:324 prio=0 @ 107ms: gem_exec_parall<4518>
U b75:140- prio=0 @ 110ms: gem_exec_parall<5486>
Timeline b46: { count 1, ready: 0, inflight: 0, seqno: { current: 782, last: 784 }, engine: vcs0 }
U b46:310- prio=0 @ 70ms: gem_exec_parall<5428>
U c11:170- prio=0 @ 70ms: gem_exec_parall[5501]
Timeline 96b: { count 1, ready: 0, inflight: 0, seqno: { current: 632, last: 634 }, engine: vcs0 }
U 96b:27a- prio=0 @ 67ms: gem_exec_parall<4878>
U b75:19e- prio=0 @ 67ms: gem_exec_parall<5486>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@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/20201119165616.10834-6-chris@chris-wilson.co.uk
We plan to expand upon the number of available statuses for when we
pretty-print the requests along the timelines, and so need a new set of
flags. We have settled upon:
Unready [U]
- initial status after being submitted, the request is not
ready for execution as it is waiting for external fences
Ready [R]
- all fences the request was waiting on have been signaled,
and the request is now ready for execution and will be
in a backend queue
- a ready request may still need to wait on semaphores
[internal fences]
Ready/virtual [V]
- same as ready, but queued over multiple backends
Executing [E]
- the request has been transferred from the backend queue and
submitted for execution on HW
- a completed request may still be regarded as executing, its
status may not be updated until it is retired and removed
from the lists
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/20201119165616.10834-3-chris@chris-wilson.co.uk
Just a normal comment, not a kerneldoc function description.
drivers/gpu/drm/i915/gvt/handlers.c:1666: warning: Function parameter or member 'vgpu' not described in 'bxt_ppat_low_write'
drivers/gpu/drm/i915/gvt/handlers.c:1666: warning: Function parameter or member 'offset' not described in 'bxt_ppat_low_write'
drivers/gpu/drm/i915/gvt/handlers.c:1666: warning: Function parameter or member 'p_data' not described in 'bxt_ppat_low_write'
drivers/gpu/drm/i915/gvt/handlers.c:1666: warning: Function parameter or member 'bytes' not described in 'bxt_ppat_low_write'
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201103204307.15723-1-chris@chris-wilson.co.uk
Pre-NV50 chipsets don't currently use the MMU subsystem that later
chipsets use, and type_vram is negative here, leading to an OOB memory
access.
This was previously guarded by a chipset check, restore that.
Reported-by: Thomas Zimmermann <tzimmermann@suse.de>
Fixes: 5839172f09 ("drm/nouveau: explicitly specify caching to use")
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Cross-subsystem Changes:
- DMA mapped scatterlist fixes in i915 to unblock merging of
https://lkml.org/lkml/2020/9/27/70 (Tvrtko, Tom)
Driver Changes:
- Fix for user reported issue #2381 (Graphical output stops with "switching to inteldrmfb from simple"):
Mark ininitial fb obj as WT on eLLC machines to avoid rcu lockup during fbdev init (Ville, Chris)
- Fix for Tigerlake (and earlier) to avoid spurious empty CSB events leading to hang (Chris, Bruce)
- Delay execlist processing for Tigerlake to avoid hang (Chris)
- Fix for Tigerlake RCS engine health check through heartbeat (Chris)
- Fix for Tigerlake reserved MOCS entries (Ayaz, Chris)
- Fix Media power gate sequence on Tigerlake (Rodrigo)
- Enable eLLC caching of display buffers for SKL+ (Ville)
- Support parsing of oversize batches on Gen9 (Matt, Chris)
- Exclude low pages (128KiB) of stolen from use to avoid thrashing during reset (Chris)
- Flush engines before Tigerlake breadcrumbs (Chris)
- Use the local HWSP offset during submission (Chris)
- Flush coherency domains on first set-domain-ioctl (Chris, Zbigniew)
- Use the active reference on the vma while capturing to avoid use-after-free (Chris)
- Fix MOCS PTE setting for gen9+ (Ville)
- Avoid NULL dereference on IPS driver callback while unbinding i915 (Chris)
- Avoid NULL dereference from PT/PD stash allocation error (Matt)
- Hold request reference for canceling an active context (Chris)
- Avoid infinite loop on x86-32 when mapping a lot of objects (Chris)
- Disallow WC mappings when processor doesn't support them (Chris)
- Return correct error in i915_gem_object_copy_blt() error path (Dan)
- Return correct error in intel_context_create_request() error path (Maarten)
- Tune down GuC communication enabled/disabled messages to debug (Jani)
- Fix rebased commit "Remove i915_request.lock requirement for execution callbacks" (Chris)
- Cancel outstanding work after disabling heartbeats on an engine (Chris)
- Signal cancelled requests (Chris)
- Retire cancelled requests on unload (Chris)
- Scrub HW state on driver remove (Chris)
- Undo forced context restores after trivial preemptions (Chris)
- Handle PCI unbind in PMU code (Tvrtko)
- Fix CPU hotplug with multiple GPUs in PMU code (Trtkko)
- Correctly set SFC capability for video engines (Venkata)
- Update GuC code to use firmware v49.0.1 (John, Matthew B., Daniele, Oscar, Michel, Rodrigo, Michal)
- Improve GuC warnings on loading failure (John)
- Avoid ownership race in buffer pool by clearing age (Chris)
- Use MMIO to read CSB in case of failure (Chris, Mika)
- Show engine properties in engine state dump to indicate changes (Chris, Joonas)
- Break up error capture compression loops with cond_resched() (Chris)
- Reduce GPU error capture mutex hold time to avoid khungtaskd (Chris)
- Serialise debugfs i915_gem_objects with ctx->mutex (Chris)
- Always test execution status on closing the context and close if not persistent (Chris)
- Avoid mixing integer types during batch copies (Chris, Jared)
- Skip over MI_NOOP when parsing to avoid overhead (Chris)
- Hold onto an explicit ref to i915_vma_work.pinned (Chris)
- Perform all asynchronous waits prior to marking payload start (Chris)
- Pull phys pread/pwrite implementations to the backend (Matt)
- Improve record of hung engines in error state (Tvrtko)
- Allow backends to override pread implementation (Matt)
- Reinforce LRC poisoning checks to confirm context survives execution (Chris)
- Fix memory region max size calculation (Matt)
- Fix order when adding blocks to memory region (Matt)
- Eliminate unused intel_virtual_engine_get_sibling func (Chris)
- Cleanup kasan warning for on-stack (unsigned long) casting (Chris)
- Onion unwind for scratch page allocation failure (Chris)
- Poison stolen pages before use (Chris)
- Selftest improvements (Chris)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201112163407.GA20320@jlahtine-mobl.ger.corp.intel.com
Increase the scaled image's theorical width/height until we find a
configuration that has valid scaling coefficients, up to 102% of the
screen's resolution. This makes sure that we can scale from almost
every resolution possible at the cost of a very small distorsion.
The CRTC_W / CRTC_H are not modified.
This algorithm was already in place but would not try to go above the
screen's resolution, and as a result would only work if the CRTC_W /
CRTC_H were smaller than the screen resolution. It will now try until it
reaches 102% of the screen's resolution.
Note that this algorithm exists mostly as a band-aid for a missing
functionality: it is not possible for userspace to request the closest
mode that would encapsulate the provided one, because the GEM buffer is
created beforehand. If there was a way to let the kernel tweak the mode,
I could write a better algorithm that would result in a better looking
picture.
Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20201105083905.8780-1-paul@crapouillou.net
Currently drivers get called to move a buffer, but if they have to
move it temporarily through another space (SYSTEM->VRAM via TT)
then they can end up with a lot of ttm->driver->ttm call stacks,
if the temprorary space moves requires eviction.
Instead of letting the driver do all the placement/space for the
temporary, allow it to report back (-EMULTIHOP) and a placement (hop)
to the move code, which will then do the temporary move, and the
correct placement move afterwards.
This removes a lot of code from drivers, at the expense of
adding some midlayering. I've some further ideas on how to turn
it inside out, but I think this is a good solution to the call
stack problems.
v2: separate out the driver patches, add WARN for getting
MULTHOP in paths we shouldn't (Daniel)
v3: use memset (Christian)
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: hristian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201109005432.861936-2-airlied@gmail.com
commit f8f6ae5d07 ("mm: always have io_remap_pfn_range() set
pgprot_decrypted()") moves the pgprot_decrypted() into
io_remap_pfn_range(). Delete any, now confusing, open coded calls that
directly precede io_remap_pfn_range():
- drm_io_prot() is only in drm_mmap_locked() to call io_remap_pfn_range()
- fb_mmap() immediately calls vm_iomap_memory() which is a convenience
wrapper for io_remap_pfn_range()
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/0-v1-2e6a0db57868+166-drm_sme_clean_jgg@nvidia.com
The Intel Keem Bay display controller is only present on Intel Keem Bay
SoCs. Hence add a dependency on ARCH_KEEMBAY, to prevent asking the
user about this driver when configuring a kernel without Intel Keem Bay
platform support.
Note that:
1. The dependency on ARM is dropped, as Keem Bay SoCs are only
supported in arm64 kernel builds,
2. The dependencies on OF and COMMON_CLK can be dropped for
compile-testing, as the driver builds fine regardless.
Fixes: ed794057b0 ("drm/kmb: Build files for KeemBay Display driver")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20201110144350.3279147-1-geert+renesas@glider.be
If CONFIG_DRM_MIPI_DSI=n:
aarch64-linux-gnu-ld: drivers/gpu/drm/kmb/kmb_dsi.o: in function `kmb_dsi_host_unregister':
kmb_dsi.c:(.text+0xa48): undefined reference to `mipi_dsi_host_unregister'
aarch64-linux-gnu-ld: drivers/gpu/drm/kmb/kmb_dsi.o: in function `kmb_dsi_host_bridge_init':
kmb_dsi.c:(.text+0xb14): undefined reference to `mipi_dsi_host_register'
Fix this be selecting DRM_MIPI_DSI, like other drivers do.
Fixes: ed794057b0 ("drm/kmb: Build files for KeemBay Display driver")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20201110144219.3278831-1-geert+renesas@glider.be
We need commit f8f6ae5d07 ("mm: always have io_remap_pfn_range() set
pgprot_decrypted()") to be able to merge Jason's cleanup patch.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
This will make sure applications which use the IN_FORMATS blob
to figure out which modifiers they can use will pick up the
linear modifier which is needed by mxsfb. Such applications
will not work otherwise if an incompatible implicit modifier
ends up being selected.
Before commit ae1ed00932 ("drm: mxsfb: Stop using DRM simple
display pipeline helper"), the DRM simple display pipeline
helper took care of this.
Signed-off-by: Daniel Abrecht <public@danielabrecht.ch>
Fixes: ae1ed00932 ("drm: mxsfb: Stop using DRM simple display pipeline helper")
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/2a99ffffc2378209307e0992a6e97e70@nodmarc.danielabrecht.ch
We need commit f8f6ae5d07 ("mm: always have io_remap_pfn_range() set
pgprot_decrypted()") to be able to merge Jason's cleanup patch.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
