This will cause a subtle behaviour change on GPUs that are in mixed-memory
configurations in that VRAM in the degraded section of VRAM will no longer
be used for TTM buffer objects.
That section of VRAM is not meant to be used for displayable/compressed
surfaces, and we have no reliable way with the current interfaces to be
able to make that decision properly.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Another transition step to allow finer-grained patches transitioning to
new MMU backends.
Old backends will continue operate as before (accessing nvkm_mem::tag),
and new backends will get a reference to the tags allocated here.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Upcoming MMU changes use nvkm_memory as its basic representation of memory,
so we need to be able to allocate VRAM like this.
The code is basically identical to the current chipset-specific allocators,
minus support for compression tags (which will be handled elsewhere anyway).
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Adds support for 64-bit writes, and optimised filling of buffers with
fixed 32/64-bit values.
These will all be used by the upcoming MMU changes.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
We need to be able to prevent memory from being freed while it's still
mapped in a GPU's address-space.
Will be used by upcoming MMU changes.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Needed by VMM code to determine whether an allocation is compatible with
a given page size (ie. you can't map 4KiB system memory pages into 64KiB
GPU pages).
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Map flags (access, kind, etc) are currently defined in either the VMA,
or the memory object, which turns out to not be ideal for things like
suballocated buffers, etc.
These will become per-map flags instead, so we need to support passing
these arguments in nvkm_memory_map().
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
nvkm_memory is going to be used by the upcoming mmu rework for the basic
representation of a memory allocation, as such, this commit adds support
for comptag allocation to nvkm_memory.
This is very simple for now, in that it requires comptags for the entire
memory allocation even if only certain ranges are compressed.
Support for tracking ranges will be added at a later date.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
We're moving towards having a central place to handle comptag allocation,
and as some GPUs don't have a ram submodule (ie. Tegra), we need to move
the mm somewhere else.
It probably never belonged in ram anyways.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Different sections of VRAM may have different properties (ie. can't be used
for compression/display, can't be mapped, etc).
We currently already support this, but it's a bit magic. This change makes
it more obvious where we're allocating from.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
TTM memory allocations will be hanging off the DRM's client, but the
locking needed to do so gets really tricky with all the other use of
the DRM's object tree.
To solve this, we make the normal DRM client a child of a new master,
where the memory allocations will be done from instead.
This also solves a potential race with client creation.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
We don't really care about where the memory is, just that it's compatible
with a VMA allocated for a given page size.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Before: "imem: init completed in 299277us"
After: "imem: init completed in 11574us"
Suspend from Fedora 26 gnome desktop on GP102.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Before: "imem: suspend completed in 5540487us"
After: "imem: suspend completed in 1871526us"
Suspend from Fedora 26 gnome desktop on GP102.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
A good deal of the structures we map into here aren't accessed very often
at all, and Fedora 26 has exposed an issue where after creating a heap of
channels, BAR2 space would run out, and we'd need to make use of the slow
path while accessing important structures like page tables.
This implements an LRU on BAR2 space, which allows eviction of mappings
that aren't currently needed, to make space for other objects.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Another piece of solving the "GP100 BAR2 VMM bootstrap" puzzle.
Without doing this, we'd attempt to write PDEs for the lower page table
levels through BAR2 before BAR2 access has been fully initialised.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This is not as simple as it was for earlier GPUs, due to the need to swap
accessor functions depending on whether BAR2 is usable or not.
We were previously protected by nvkm_instobj's accessor functions keeping
an object mapped permanently, with some unclear magic that managed to hit
the slow-path where needed even if an object was marked as mapped.
That's been replaced here by reference counting maps (some objects, like
page tables can be accessed concurrently), and swapping the functions as
necessary.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This is to simplify upcoming changes. The slow-path is something that
currently occurs during bootstrap of the BAR2 VMM, while backing up an
object during suspend/resume, or when BAR2 address space runs out.
The latter is a real problem that can happen at runtime, and occurs in
Fedora 26 already (due to some change that causes a lot of channels to
be created at login), so ideally we'd prefer not to make it any slower.
We'd also like suspend/resume speed to not suffer.
Upcoming commits will solve those problems in a better way, making the
extra overhead of moving the locking here a non-issue.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
The accessor functions can change as a result of acquire()/release() calls,
and are protected by any refcounting done there.
Other functions must remain constant, as they can be called any time.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Discovered by accident while working to use BAR2 access to instmem objects
on more paths.
We've apparently been relying on luck up until now!
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
GP100's page table nests a lot more deeply than the GF100-compatible
layout we're currently using, which means our hackish-but-simple way
of dealing with BAR2 VMM teardown won't work anymore.
In order to sanely handle the chicken-and-egg (BAR2's PTs get mapped
into themselves) problem, we need prevent page tables getting mapped
back into BAR2 during the destruction of its VMM.
To do this, we simply key off the state that's now maintained by the
BAR2 init/fini functions.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Upcoming changes will remove the nvkm_vmm pointer from nvkm_vma, instead
requiring it to be explicitly specified on each operation.
It's not currently possible to get this information for BAR1 mappings,
so let's fix that ahead of time.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Will prevent spurious MMU fault interrupts if something decides to touch
BAR1 after we've unloaded the driver.
Exposed external to BAR so that INSTMEM can use it to better control the
suspend/resume fast-path access.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
If we want to be able to hit the instmem fast-path in a few trickier cases,
we need to be more flexible with when we can initialise BAR2 access.
There's probably a decent case to be made for merging BAR/INSTMEM into BUS,
but that's something to ponder another day.
Flushes have been added after the write to bind the instance block,
as later commits will reveal the need for them.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Will prevent spurious MMU fault interrupts if something decides to touch
BAR1 after we've unloaded the driver.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
BAR2 being done for practical reasons, this is just for consistency.
Flushes have been added after the write to bind the instance block,
as later commits will reveal the need for them.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
NVIDIA call it BAR2, Linux APIs treat it as BAR3 due to BAR1 being a
64-bit BAR, which I presume take two slots or something.
No actual code changes here, just to make future commits less messy.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Will already be done by MMU as a result of the PT writes that occur
during BAR2 bootstrapping.
This is likely just a left-over from the days when it was hardcoded.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
RM appears to do this really early in its initialisation, before DEVINIT.
We currently do this before BAR2 initialisation for some reason.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
MMU will be needing this to specify kind info on BAR mappings.
We have no userspace currently using these interfaces, so break the ABI
instead of supporting both. NVIF version bump so any future use can be
guarded.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
The correct thing to do on OOM is to return 0 and set mm_node to NULL,
otherwise TTM will assume some other kind of error, and not attempt to
evict other buffers to make space.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This was already done in dcb.c inside nvkm, but the other parser did not
get the update.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Using the ARRAY_SIZE macro improves the readability of the code. Also,
it is useless to re-invent it.
Found with Coccinelle with the following semantic patch:
@r depends on (org || report)@
type T;
T[] E;
position p;
@@
(
(sizeof(E)@p /sizeof(*E))
|
(sizeof(E)@p /sizeof(E[...]))
|
(sizeof(E)@p /sizeof(T))
)
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Jérémy Lefaure <jeremy.lefaure@lse.epita.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
nouveau supports the Tegra K1 and higher after the SoC-based GPUs converged
with the main GeForce GPU families.
v2:
- Qualify that support is Tegra K1+ (Martin Peres)
Signed-off-by: Rhys Kidd <rhyskidd@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Acked-by: Pierre Moreau <pierre.morrow@free.fr>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
v2:
- add nv138 and drop nv13b chipsets (Ilia Mirkin)
- refactor out status variable and instead mask tsensor (Ilia Mirkin)
- switch SHADOWed state message away from nvkm_error() (Ilia Mirkin)
- rename internal temperature variable (Karol Herbst)
v3:
- use nvkm_trace() for SHADOWed state message (Ben Skeggs)
Signed-off-by: Rhys Kidd <rhyskidd@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
The fan control mode can either be FDO_PWM_MODE_STATIC or FDO_PWM_MODE_STATIC_RPM.
Setting it as AMD_FAN_CTRL_AUTO will cause the fan spin faster wrongly.
This can be reproduced by:
'# cat /sys/class/hwmon/hwmon0/pwm1
38
'# cat /sys/class/hwmon/hwmon0/pwm1_enable
2
'# echo "2" > /sys/class/hwmon/hwmon0/pwm1_enable
'# cat /sys/class/hwmon/hwmon0/pwm1
122
The fan speed get faster wrongly even with its original mode echo back.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
otherwise PF & VF exchange is broken
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
-----BEGIN PGP SIGNATURE-----
iQEcBAABAgAGBQJZ9kEFAAoJEHm+PkMAQRiGw6wH/0j197qyGd0hkVFMJO6LAgN3
KQWS4nZ5BkVDocwv0RVnUJTtXqU1eozFgdVEtSoaFXpzlHGuptR2Tau9efDCJ7w3
/utZxqvhGebZd2T+j+/o/LE8BRQxhADBNJq2D/o0WNt8ecxuG0GIkhkEYt/o3z1v
/sxlwVwzXB7Dc/h1WcgGJG7cS6L9KzzAzGAS/iNvdFrPOygHBv8c0MxVZIiBIeeK
1nZdyvbyM8uenSyG+prGt9ENrqXZxxfwUxIchi2V7A9m1WmD5zijNkf1JCWji/O+
UsA1auxna7MwoxjxqZuGm4MlKOwZ+8xutk4JGgc+aP/ulndJbJYu+4op/3vaFBM=
=Mhx+
-----END PGP SIGNATURE-----
Backmerge tag 'v4.14-rc7' into drm-next
Linux 4.14-rc7
Requested by Ben Skeggs for nouveau to avoid major conflicts,
and things were getting a bit conflicty already, esp around amdgpu
reverts.
+ preemption support for a5xx[1][2]
+ display fixes for 8x96 (snapdragon 820) including fixes for 4k scanout
(hwpipe assignment re-work to handle multiple hwpipe assigned to plane
for wide scanout)
+ async cursor plane updates and fixes
+ refactor adreno_bind/hwinit.. still defer fw loading until device open,
but move clk/irq/etc to probe/bind time to fix issues when fw isn't
present in filesys
+ clk/dt bindings cleanups w/ backward compat via msm_clk_get() (dt docs
part ack'ed by Rob Herring)
+ fw loading re-work with helper to handle either /lib/firmware/qcom/$fw
or /lib/firmware/$fw.. background, we've started landing fw for some of
generations in linux-firmware, but there is a preference to put fw files
under 'qcom' subdirectory, which is not what was done on android or for
people who copied fw from android. So now we first look in qcom subdir
and then fallback to the original location.
+ bunch of GPU debugging enhancements, to dump full cmdline of processes
that trigger faults, and to add a new debugfs to capture cmdstream of
just submits that triggered faults.. both quite useful for piglit ;-)
* tag 'drm-msm-next-2017-11-01' of git://people.freedesktop.org/~robclark/linux: (38 commits)
drm/msm: use %z format modifier for printing size_t
drm/msm/mdp5: Don't use async plane update path if plane visibility changes
drm/msm/mdp5: mdp5_crtc: Restore cursor state only if LM cursors are enabled
drm/msm/mdp5: Update mdp5_pipe_assign to spit out both planes
drm/msm/mdp5: Prepare mdp5_pipe_assign for some rework
drm/msm: remove mdp5_cursor_plane_funcs
drm/msm: update cursors asynchronously through atomic
drm/msm/atomic: switch to drm_atomic_helper_check
drm/msm/mdp5: restore cursor state when enabling crtc
drm/msm/mdp5: don't use autosuspend
drm/msm/mdp5: ignore planes that are not visible
drm/msm: dump submits which triggered gpu hang
drm/msm: preserve IOVAs in submit's bo table
drm/msm/rd: allow adding addition msg to top of dump
drm/msm: split rd debugfs file
drm/msm: add special _get_vaddr_active() for cmdstream dumps
drm/msm: show task cmdline in gpu recovery messages
drm/msm: dump a rd GPUADDR header for all buffers in the command
drm/msm: Removed unused struct_mutex_task
drm/msm: Implement preemption for A5XX targets
...
map_queues_cpsch uses the queue_count to decide whether to upload
a new runlist. So update the counter before calling it.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Process registration needs to happen on each device. So use per-device
queue lists to determine when to register/deregister the process.
Signed-off-by: Ben Goz <ben.goz@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Take the dbgmgr lock and unregister before destroying the debug manager.
Do this before destroying the queues.
v2: Correct locking order in kfd_ioctl_dbg_register to ake sure the
process mutex and dbgmgr mutex are always taken in the same order.
Signed-off-by: Yair Shachar <yair.shachar@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
When kfd suspending on APU, we do not need to call
amd_iommu_unbind_pasid(), because pasid will be unbound automatically
when power goes off.
On the other hand, calling amd_iommu_unbind_pasid() will trigger
kfd_process_iommu_unbind_callback() if the process is not terminating.
By design, kfd_process_iommu_unbind_callback() should only be called
for process terminating. So we would rather not to call
amd_iommu_unbind_pasid() when suspending.
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
The MQD represents an inactive context and should not have ring or
doorbell enable bits set. Doing so interferes with HWS which streams
the MQD onto the HQD. If enable bits are set this activates the ring
or doorbell before the HQD is fully configured.
Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
A list of per-process queues is maintained in the
kfd_process_queue_manager, so the queues array in kfd_process is
redundant and in fact unused.
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
For Cannonlake the number of scalers for each pipe is 2. Let's increase
the number of scalers for pipe C.
v2: Use INTEL_GEN() instead of IS_CANNONLAKE()
Signed-off-by: Mika Kahola <mika.kahola@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1509530930-24960-1-git-send-email-mika.kahola@intel.com
The return type of ARRAY_SIZE() is size_t, so we have to use
%zu instead of %lu to avoid this warning:
drivers/gpu/drm/msm/msm_gpu.c: In function 'msm_gpu_init':
drivers/gpu/drm/msm/msm_gpu.c:742:31: error: format '%lu' expects argument of type 'long unsigned int', but argument 7 has type 'unsigned int' [-Werror=format=]
The warning it otherwise harmless as size_t is always the
same size as unsigned long in all supported architectures,
but gcc doesn't know that.
Fixes: c2fceabca6d5 ("drm/msm: Support multiple ringbuffers")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Rob Clark <robdclark@gmail.com>
We will want to break this down to give detailed per-engine warnings as
to why we still think we are active as we attempt to park the engines.
For the first step, just move the warning verbatim from the idle-worker
to intel_engines_park().
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171027110617.31745-3-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
We will disarm the breadcrumb interrupt if we see a user interrupt
whilst no one is waiting. This may race with the call to
intel_engine_disarm_breadcrumbs() triggering an assert that we aren't
trying to do the same job twice. Prevent this by checking that the irq
is still armed after flushing the interrupt (for the irq spinlock).
Fixes: bcbd5c33a3 ("drm/i915/guc: Always enable the breadcrumbs irq")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171031122235.1395-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
In case the object has changed tiling between calls to execbuf, we need
to check if the existing offset inside the GTT matches the new tiling
constraint. We even need to do this for "unfenced" tiled objects, where
the 3D commands use an implied fence and so the object still needs to
match the physical fence restrictions on alignment (only required for
gen2 and early gen3).
In commit 2889caa923 ("drm/i915: Eliminate lots of iterations over
the execobjects array"), the idea was to remove the second guessing and
only set the NEEDS_MAP flag when required. However, the entire check
for an unusable offset for fencing was removed and not just the
secondary check. I.e.
/* avoid costly ping-pong once a batch bo ended up non-mappable */
if (entry->flags & __EXEC_OBJECT_NEEDS_MAP &&
!i915_vma_is_map_and_fenceable(vma))
return !only_mappable_for_reloc(entry->flags);
was entirely removed as the ping-pong between execbuf passes was fixed,
but its primary purpose in forcing unaligned unfenced access to be
rebound was forgotten.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103502
Fixes: 2889caa923 ("drm/i915: Eliminate lots of iterations over the execobjects array")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171031103607.17836-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
This patch fixes the following soft lockup:
BUG: soft lockup - CPU#0 stuck for 23s! [weston:307]
On weston idle-timeout the IP is powered down and reset
asserted. On weston resume we get a massive vblank
IRQ storm due to the LDI registers having lost some state.
This state loss is caused by ade_crtc_atomic_begin() not
calling ade_ldi_set_mode(). With this patch applied
resuming from Weston idle-timeout works well.
Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Tested-by: John Stultz <john.stultz@linaro.org>
Cc: stable@vger.kernel.org
Reviewed-by: Xinliang Liu <xinliang.liu@linaro.org>
Signed-off-by: Xinliang Liu <xinliang.liu@linaro.org>
There is no need check if PPGTT is disabled because that not possible
in CNL. Execlists and GuC submission modes rely on at least aliasing
PPGTT and even intel_sanitize_enable_ppgtt says: "We don't allow disabling
PPGTT for gen9+ as it's a requirement for execlists, the sole mechanism
available to submit work."
Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171027223207.7869-1-michel.thierry@intel.com
The function for byteswapping the data send to/from atombios was buggy for
num_bytes not divisible by four. The function must be aware of the fact
that after byte-swapping the u32 units, valid bytes might end up after the
num_bytes boundary.
This patch was tested on kernel 3.12 and allowed us to sucesfully use
DisplayPort on and Radeon SI card. Namely it fixed the link training and
EDID readout.
The function is patched both in radeon and amd drivers, since the functions
and the fixes are identical.
Signed-off-by: Roman Kapl <rka@sysgo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
after individualize we need manually call reservation_object_fini()
if all fences on resv signaled during test, otherwise kmemory leak
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The bo structure is freed up in case of an error, so we can't do any
accounting if that happens.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
CC: stable@vger.kernel.org
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When the mutex is locked just in the moment we copy it we end up with a
warning that we release a locked mutex.
Fix this by properly reinitializing the mutex.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
CC: stable@vger.kernel.org
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
encoder->type isn't genreally safe around DDI ports, so let's
replace some uses in the audio code with the crtc state's
output_types instead.
Actually in these cases encoder->type would work since the DP
SST case is only relevant for VLV/CHV and encoder->type==DP
is a thing on those platforms. The DP MST cases would work
as well since MST encoder->type==DP_MST always. But I think
it's best to try and minimize the encoder->type use in general
to avoid showing a bad example to people.
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171030184654.17429-2-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Explicitly pass the crtc and connector states into the audio
code enable/disable hooks, and plumb them all the way down.
This gets rid of almost all crtc->config and encoder->crtc
uses. The one place where we still use them is
i915_audio_component_sync_audio_rate() since that gets called from
the audio driver and we don't have explicit states around then.
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171030184654.17429-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
To acquire all modeset locks requires a ww_ctx to be allocated. As this
is the legacy path and the allocation small, to reduce the changes
required (and complex untested error handling) to the legacy drivers, we
simply assume that the allocation succeeds. At present, it relies on the
too-small-to-fail rule, but syzbot found that by injecting a failure
here we would hit the WARN. Document that this allocation must succeed
with __GFP_NOFAIL.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171031115535.15166-1-chris@chris-wilson.co.uk
To quote kbuild/makefiles.txt:
cc-disable-warning checks if gcc supports a given warning and returns
the commandline switch to disable it. This special function is needed,
because gcc 4.4 and later accept any unknown -Wno-* option and only
warn about it if there is another warning in the source file.
This is exactly what we were trying to achieve with cc-option -Wno-foo and
failed miserably.
Reported-by: kbuild-all@01.org
Fixes: 39bf4de89f ("drm/i915: Add -Wall -Wextra to our build, set warnings to full")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171030172927.18158-1-chris@chris-wilson.co.uk
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Eliminate the partially duplicated DDI readout code from MST, and
instead just call intel_ddi_get_config(). As a nice bonus we get
more cross checking as intel_ddi_get_config() will populate
output_types based on the actual mode of the DDI port.
Additonally intel_ddi_get_config() must be changed to get the crtc
from the passed in crtc state rather than from the encoder->crtc link.
encoder->crtc really shouldn't be used anyway.
v2: Rebased on BXT MST latency_optim fix
Make intel_ddi_clock_get() static
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171027193128.14483-7-ville.syrjala@linux.intel.com
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Pass an old crtc state to intel_ddi_post_disable() from the MST code.
Note that this crtc state won't necessaitly match the one that was
passed to intel_ddi_pre_enable() if the first stream to be enabled isn't
the last stream to be disabled. But this is fine since the states should
be identical in every important way. This does mean people frobbing
the DDI pre_enable/post_disable hooks have to pay attention in what
parts of the state they consult.
The alternative would be to inline the relevant code into the MST code.
That is actually what we used to do for pre_enable before
commit e081c8463a ("drm/i915: Remove duplicate DDI enabling logic
from MST path"). For post_disable we've always called the DDI hook.
v2: Pimp up the comments explaining the MST issues
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171027193128.14483-6-ville.syrjala@linux.intel.com
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
We should be using the DPLL hw state we got from the current crtc state
to determine the corresponding port clock frequency rather than getting
it via the current state programmed into the DPLL.
v2: Rebase due to intel_dpll_id changes
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171027193128.14483-5-ville.syrjala@linux.intel.com
encoder->port works for FDI, and it also works for MST (regardless of
whether we're dealing with the "fake" MST encoder, or mst->primary).
So let's eliminate intel_ddi_get_encoder_port().
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171027193128.14483-4-ville.syrjala@linux.intel.com
Currently the DDI encoder->type will change at runtime depending on
what kind of hotplugs we've processed. That's quite bad since we can't
really trust that that current value of encoder->type actually matches
the type of signal we're trying to drive through it.
Let's eliminate that problem by declaring that non-eDP DDI port will
always have the encoder type as INTEL_OUTPUT_DDI. This means the code
can no longer try to distinguish DP vs. HDMI based on encoder->type.
We'll leave eDP as INTEL_OUTPUT_EDP, since it'll never change and
there's a bunch of code that relies on that value to identify eDP
encoders.
We'll introduce a new encoder .compute_output_type() hook. This allows
us to compute the full output_types before any encoder .compute_config()
hooks get called, thus those hooks can rely on output_types being
correct, which is useful for cloning on oldr platforms. For now we'll
just look at the connector type and pick the correct mode based on that.
In the future the new hook could be used to implement dynamic switching
between LS and PCON modes for LSPCON.
v2: Fix BXT/GLK PPS explosion with DSI/MST encoders
v3: Avoid the PPS warn on pure HDMI/DVI DDI encoders by checking dp.output_reg
v4: Rebase
v5: Populate output_types in .get_config() rather than in the caller
v5: Split out populating output_types in .get_config() (Maarten)
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171027193128.14483-3-ville.syrjala@linux.intel.com
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Rather than having the caller of .get_config() set output_types based on
encoder->type, let's just have .get_config() itself populate
output_types. This way we are isolated from encoder->type, which won't
be useable for this purpose anyway soon (at least for DDI encoders).
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171027193128.14483-2-ville.syrjala@linux.intel.com
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Starting from version 204 VBT can specify the max TMDS clock we are
allowed to use with HDMI ports. Parse that information and take it
into account when filtering modes and computing a crtc state.
Also take the opportunity to sort the platform check if ladder
from new to old.
v2: Add defines for the values into intel_vbt_defs.h (Jani)
Don't fall back to 0 silently for unknown values (Jani)
Skip the debug print for the 0 case (Jani)
Cc: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171030145702.23662-1-ville.syrjala@linux.intel.com
To quote Felix: "For testing KV with current user mode stack, please use
amdgpu. I don't expect this to work with radeon and I'm not planning to
spend any effort on making radeon work with a current user mode stack."
Only compile tested, but should be straight forward.
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
When a plane moves out of bounds (i.e, outside the crtc clip region), the
plane state's "visible" parameter changes to false. When this happens, we
(a) release the hwpipe resources away from it, and
(b) unstage the corresponding hwpipe(s) from the Layer Mixers in the CRTC.
(a) requires use to acquire the global atomic state and assign a new
hwpipe. (b) requires us to re-configure the Layer Mixer, which is done in
the CRTC. We don't want to do these things in the async plane update path,
so return an error if the new state's "visible" isn't the same as the
current state's "visible".
Cc: Gustavo Padovan <gustavo.padovan@collabora.com>
Signed-off-by: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
MDP5 on newer SoCs support cursor planes (i.e, cursor SSPPs). They are a
separate entity unlike the cursors within LM.
Do not try to restore the MDP5 LM cursor registers, or the corresponding
CTL bits if we are not using LM cursors.
Also, since we've introduced a new variable 'lm_cursor_enabled', we can
now use it to avoid creating a different sets of crtc_funcs for CRTCs
with LM cursors and CRTCs with cursor planes.
Fixes: "drm/msm/mdp5: restore cursor state when enabling crtc"
Signed-off-by: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
We currently call mdp5_pipe_assign() twice to assign the left and right
hwpipes for our drm_plane. When merging 2 hwpipes, there are a few
constraints that we need to keep in mind:
- Only the same types of SSPPs are preferred. I.e, a RGB pipe should
be paired with another RGB pipe, VIG with VIG etc.
- The hwpipe staged on the left should have a higher priority than
the hwpipe staged on the right. The priorities are as follows:
VIG0 > VIG1 > VIG2 > VIG3
RGB0 > RGB1 > RGB2 > RGB3
DMA0 > DMA1
We can't apply these constraints easily if mdp5_pipe_assign() is
called twice. Update mdp5_pipe_assign() to find both hwpipes in
one go, and add the extra constraints needed.
Signed-off-by: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
mdp5_pipe_assign currently returns the hwpipe pointer for the drm_plane.
Return it indirectly by setting a pointer passed as an argument. This
is needed because we want the func to find out the right hwpipe too.
Signed-off-by: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
After converting legacy cursor updates to atomic async commits
mdp5_cursor_plane_funcs just duplicates mdp5_plane_funcs now.
Cc: Rob Clark <robdclark@gmail.com>
Cc: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Tested-by: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
Add support to async updates of cursors by using the new atomic
interface for that. Basically what this commit does is do what
mdp5_update_cursor_plane_legacy() did but through atomic.
v5: call drm_atomic_helper_async_check() from the check hook
v4: add missing atomic async commit call to msm_atomic_commit(Archit Taneja)
v3: move size checks back to drivers (Ville Syrjälä)
v2: move fb setting to core and use new state (Eric Anholt)
Cc: Rob Clark <robdclark@gmail.com>
Cc: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Tested-by: Archit Taneja <architt@codeaurora.org> (v4)
[added comment about not hitting async update path if hwpipes are
re-assigned or global state is touched]
Signed-off-by: Rob Clark <robdclark@gmail.com>
Since we enabled runtime PM, we cannot count on cursor registers to
retain their values. This can result in situations where we think the
cursor is enabled when we enable the CRTC but it is trying to scan out
null (and the rest of cursor position/size is lost), resulting in faults
and generally angering the hw when coming out of DPMS with a cursor
enabled.
stable backport note: reverting 774e39ee35 is also a suitable fix
Fixes: 774e39ee35 drm/msm/mdp5: Set up runtime PM for MDSS
Signed-off-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Archit Taneja <architt@codeaurora.org>
It's only likely to paper over bugs. Unlike the gpu, where we want to
keep things alive a bit longer in expectation of the next frame's
submit, when the display is shut down we can power off immediately.
Signed-off-by: Rob Clark <robdclark@gmail.com>
Acked-by: Archit Taneja <architt@codeaurora.org>
Note we need to move update_fences() to after msm_rd_dump_submit(),
otherwise the bo's referenced by the submit may no longer be valid.
Signed-off-by: Rob Clark <robdclark@gmail.com>
We need this if we want to dump the submit after cleanup (ie. from hang
or fault). But in the backoff/unpin case we want to clear them. So add
a flag so we can skip clearing the IOVAs in at cleanup.
Signed-off-by: Rob Clark <robdclark@gmail.com>
Split into two instances, the existing $debugfs/rd which continues to
dump all submits, and $debugfs/hangrd which will be used to dump just
submits that cause gpu hangs (and eventually faults, but that will
require some iommu framework enhancements).
Signed-off-by: Rob Clark <robdclark@gmail.com>
Prep work for adding a debugfs file that dumps just submits which
trigger hangs/faults. In this case the bo may already be in the
MADV_DONTNEED state, but will be still on the active list (since
the submit hasn't completed yet). So the normal check that the
bo is in the WILLNEED state does not apply. (But of course the bo
should definitely not be in the PURGED state!)
Signed-off-by: Rob Clark <robdclark@gmail.com>
Now that freedreno gallium driver defaults to using submit_queue task
(render reordering), just showing task->comm is not so useful (ie. it is
always "flush_queue:0"), so also dump the cmdline. This should also be
more useful for piglit/shader_runner.
Signed-off-by: Rob Clark <robdclark@gmail.com>
Currently the rd dump avoids any buffers marked as WRITE under
the assumption that the contents are not interesting. While it
is true that the contents are uninteresting we should still print
the iova and size for all buffers so that any listening replay
tools can correctly construct the submission.
Print the header for all buffers but only dump the contents for
buffers marked as READ.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
Recent changes to locking have rendered struct_mutex_task
unused.
Unused since 0e08270a1f.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
Implement preemption for A5XX targets - this allows multiple
ringbuffers for different priorities with automatic preemption
of a lower priority ringbuffer if a higher one is ready.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
We use a global ringbuffer size and block size for all targets and
at least for 5XX preemption we need to know the value the RB_CNTL
in several locations so it makes sense to calculate it once and use
it everywhere.
The only monkey wrench is that we need to disable the RPTR shadow
for A430 targets but that only needs to be done once and doesn't
affect A5XX so we can or in the value at init time.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
Add a shadow pointer to track the current command being written into
the ring. Don't commit it as 'cur' until the command is submitted.
Because 'cur' is used to construct the software copy of the wptr this
ensures that somebody peeking in on the ring doesn't assume that a
command is inflight while it is being written. This isn't a huge deal
with a single ring (though technically the hangcheck could assume
the system is prematurely busy when it isn't) but it will be rather
important for preemption where the decision to preempt is based
on a non-empty ringbuffer. Without a shadow an aggressive preemption
scheme could assume that the ringbuffer is non empty and switch to it
before the CPU is done writing the command and boom.
Even though preemption won't be supported for all targets because of
the way the code is organized it is simpler to make this generic for
all targets. The extra load for non-preemption targets should be
minimal.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
In order to manage ringbuffer priority to its fullest userspace
should know how many ringbuffers it has to work with. Add a
parameter to return the number of active rings.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
Add the infrastructure to support the idea of multiple ringbuffers.
Assign each ringbuffer an id and use that as an index for the various
ring specific operations.
The biggest delta is to support legacy fences. Each fence gets its own
sequence number but the legacy functions expect to use a unique integer.
To handle this we return a unique identifier for each submission but
map it to a specific ring/sequence under the covers. Newer users use
a dma_fence pointer anyway so they don't care about the actual sequence
ID or ring.
The actual mechanics for multiple ringbuffers are very target specific
so this code just allows for the possibility but still only defines
one ringbuffer for each target family.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
When we move to multiple ringbuffers we're going to store the data
in the memptrs on a per-ring basis. In order to prepare for that
move the current memptrs from the adreno namespace into msm_gpu.
This is way cleaner and immediately lets us kill off some sub
functions so there is much less cost later when we do move to
per-ring structs.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
Currently the behavior of a command stream is provided by the user
application during submission and the application is expected to internally
maintain the settings for each 'context' or 'rendering queue' and specify
the correct ones.
This works okay for simple cases but as applications become more
complex we will want to set context specific flags and do various
permission checks to allow certain contexts to enable additional
privileges.
Add kernel-side submit queues to be analogous to 'contexts' or
'rendering queues' on the application side. Each file descriptor
instance will maintain its own list of queues. Queues cannot be
shared between file descriptors.
For backwards compatibility context id '0' is defined as a default
context specifying no priority and no special flags. This is
intended to be the usual configuration for 99% of applications so
that a garden variety application can function correctly without
creating a queue. Only those applications requiring the specific
benefit of different queues need create one.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
We already have, as a result of upstreaming the gpu bindings,
msm_clk_get() which will try to get the clock both without and with a
"_clk" suffix. Use this in HDMI code so we can drop the "_clk" suffix
in bindings while maintaing backwards compatibility.
Signed-off-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
We already have, as a result of upstreaming the gpu bindings,
msm_clk_get() which will try to get the clock both without and with a
"_clk" suffix. Use this in eDP code so we can drop the "_clk" suffix
in bindings while maintaing backwards compatibility.
Signed-off-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
We already have, as a result of upstreaming the gpu bindings,
msm_clk_get() which will try to get the clock both without and with a
"_clk" suffix. Use this in DSI code so we can drop the "_clk" suffix
in bindings while maintaing backwards compatibility.
Signed-off-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
When firmware was added to linux-firmware, it was put in a qcom sub-
directory, unlike what we'd been using before. For a300_pfp.fw and
a300_pm4.fw symlinks were created, but we'd prefer not to have to do
this in the future. So add support to look in both places when
loading firmware.
Signed-off-by: Rob Clark <robdclark@gmail.com>
Previously, in an effort to defer initializing the gpu until firmware
was available (ie. rootfs mounted), the gpu was not loaded at when the
subdevice was bound. Which resulted that clks/etc were requested in a
place that devm couldn't really help unwind if something failed.
Instead move request_firmware() to gpu->hw_init() and construct the gpu
earlier in adreno_bind(). To avoid the rest of the driver needing to
be aware of a gpu that hasn't managed to load firmware and hw_init()
yet, stash the gpu ptr in the adreno device's drvdata, and don't set
priv->gpu() until hw_init() succeeds.
Signed-off-by: Rob Clark <robdclark@gmail.com>
This was used as a placeholder. It was never really input to the MDSS/HDMI
clocks.
Signed-off-by: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
We need to call reservation_object_reserve_shared() in both cases, but
this wasn't happening in the _NO_IMPLICIT submit case.
Fixes: f0a42bb ("drm/msm: submit support for in-fences")
Reported-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
In systems under heavy load the IH work may experience significant
scheduling delays.
Under load + system workqueue:
Max Latency: 7.023695 ms
Avg Latency: 0.263994 ms
Under load + high priority workqueue:
Max Latency: 1.162568 ms
Avg Latency: 0.163213 ms
Further work is required to measure the impact of per-cpu settings on IH
performance.
Signed-off-by: Andres Rodriguez <andres.rodriguez@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
We don't need to wait for all work to complete in the IH exit function.
We only need to make sure the interrupt_work has finished executing to
guarantee that ih_kfifo is no longer in use.
Signed-off-by: Andres Rodriguez <andres.rodriguez@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
A larger buffer will let us accommodate applications with a large amount
of semi-simultaneous event signals.
Signed-off-by: Andres Rodriguez <andres.rodriguez@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Replace our implementation of a lockless ring buffer with the standard
linux kernel kfifo.
We shouldn't maintain our own version of a standard data structure.
Signed-off-by: Andres Rodriguez <andres.rodriguez@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This allows increasing the KFD_SIGNAL_EVENT_LIMIT in kfd_ioctl.h
without breaking processes built with older kfd_ioctl.h versions.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This speeds up signal lookup when the IH ring entry includes a
valid context ID or partial context ID. Only if the context ID is
found to be invalid, fall back to an exhaustive search of all
signaled events.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Signal slots are identical to event IDs.
Replace the used_slot_bitmap and events hash table with an IDR to
allocate and lookup event IDs and signal slots more efficiently.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
The first event page is always big enough to handle all events.
Handling of multiple events pages is not supported by user mode, and
not necessary.
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Use standard wait queues for waiting and waking up waiting threads
instead of inventing our own. We still have our own wait loop
because the HSA event semantics require the ability to have one
thread waiting on multiple wait queues (events) at the same time.
Signed-off-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This always identical with the index of the event_waiter in the array.
No need to store it in the waiter record.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
When an event with pending waiters is destroyed, those waiters may
end up sleeping forever unless they are notified and woken up.
Implement the notification by clearing the waiter->event pointer,
which becomes invalid anyway, when the event is freed, and waking
up the waiting tasks.
Waiters on an event that's destroyed return failure.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Cleaned up the code while resolving some potential bugs and
inconsistencies in the process.
Clean-ups:
* Remove enum kfd_event_wait_result, which duplicates
KFD_IOC_EVENT_RESULT definitions
* alloc_event_waiters can be called without holding p->event_mutex
* Return an error code from copy_signaled_event_data instead of bool
* Clean up error handling code paths to minimize duplication in
kfd_wait_on_events
Fixes:
* Consistently return an error code from kfd_wait_on_events and set
wait_result to KFD_IOC_WAIT_RESULT_FAIL in all failure cases.
* Always call free_waiters while holding p->event_mutex
* copy_signaled_event_data might sleep. Don't call it while the task state
is TASK_INTERRUPTIBLE.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
If kfd_wait_on_events can return immediately, we don't need to populate
the wait list and don't need to enter the sleep-loop.
Signed-off-by: Sean Keely <sean.keely@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
The kfd_process doesn't own a reference to the mm_struct, so it can
disappear without warning even while the kfd_process still exists.
Therefore, avoid dereferencing the kfd_process.mm pointer and make
it opaque. Use get_task_mm to get a temporary reference to the mm
when it's needed.
v2: removed unnecessary WARN_ON
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
ASIC temperature reading from HOTSPOT to ASIC edge which makes
things consistent with previous asics.
Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Move the crtc state related 12bpc checks into hdmi_12bpc_possible()
since that one already examines other parts of the crtc state.
Note that we can drop the !force_dvi check since
crtc_state->has_hdmi_sink already accounts for that.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171026151405.30710-1-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
DP dongles may signal downstream HPD via short HPD pulses. Setting the
sink to DPMS off apparently kills the downstream HPD (at least on my
DP->VGA dongle), so skip the DPMS off for such dongles when we turn
off the port.
v2: Deal with DDI as well by moving the check into
intel_dp_sink_dpms() (Dhinakaran)
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Pablo <pablodebiase@nanalysis.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103472
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=99114
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171027094523.9317-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Call the DDI .pre_pll_enable() hook from the MST code so that BXT gets
the correct lane latency optimal setting applied. And we obviously need
to compute the correct value, and read it out to keep the state checker
happy.
While at it drop the useless 'encoder' parameter to
bxt_ddi_phy_calc_lane_lat_optim_mask()
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171027134348.31190-1-ville.syrjala@linux.intel.com
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Kasan spotted
[IGT] gem_tiled_pread_pwrite: exiting, ret=0
==================================================================
BUG: KASAN: use-after-free in __i915_gem_object_reset_page_iter+0x15c/0x170 [i915]
Read of size 8 at addr ffff8801359da310 by task kworker/3:2/182
CPU: 3 PID: 182 Comm: kworker/3:2 Tainted: G U 4.14.0-rc6-CI-Custom_3340+ #1
Hardware name: Intel Corp. Geminilake/GLK RVP1 DDR4 (05), BIOS GELKRVPA.X64.0062.B30.1708222146 08/22/2017
Workqueue: events __i915_gem_free_work [i915]
Call Trace:
dump_stack+0x68/0xa0
print_address_description+0x78/0x290
? __i915_gem_object_reset_page_iter+0x15c/0x170 [i915]
kasan_report+0x23d/0x350
__asan_report_load8_noabort+0x19/0x20
__i915_gem_object_reset_page_iter+0x15c/0x170 [i915]
? i915_gem_object_truncate+0x100/0x100 [i915]
? lock_acquire+0x380/0x380
__i915_gem_object_put_pages+0x30d/0x530 [i915]
__i915_gem_free_objects+0x551/0xbd0 [i915]
? lock_acquire+0x13e/0x380
__i915_gem_free_work+0x4e/0x70 [i915]
process_one_work+0x6f6/0x1590
? pwq_dec_nr_in_flight+0x2b0/0x2b0
worker_thread+0xe6/0xe90
? pci_mmcfg_check_reserved+0x110/0x110
kthread+0x309/0x410
? process_one_work+0x1590/0x1590
? kthread_create_on_node+0xb0/0xb0
ret_from_fork+0x27/0x40
Allocated by task 1801:
save_stack_trace+0x1b/0x20
kasan_kmalloc+0xee/0x190
kasan_slab_alloc+0x12/0x20
kmem_cache_alloc+0xdc/0x2e0
radix_tree_node_alloc.constprop.12+0x48/0x330
__radix_tree_create+0x274/0x480
__radix_tree_insert+0xa2/0x610
i915_gem_object_get_sg+0x224/0x670 [i915]
i915_gem_object_get_page+0xb5/0x1c0 [i915]
i915_gem_pread_ioctl+0x822/0xf60 [i915]
drm_ioctl_kernel+0x13f/0x1c0
drm_ioctl+0x6cf/0x980
do_vfs_ioctl+0x184/0xf30
SyS_ioctl+0x41/0x70
entry_SYSCALL_64_fastpath+0x1c/0xb1
Freed by task 37:
save_stack_trace+0x1b/0x20
kasan_slab_free+0xaf/0x190
kmem_cache_free+0xbf/0x340
radix_tree_node_rcu_free+0x79/0x90
rcu_process_callbacks+0x46d/0xf40
__do_softirq+0x21c/0x8d3
The buggy address belongs to the object at ffff8801359da0f0
which belongs to the cache radix_tree_node of size 576
The buggy address is located 544 bytes inside of
576-byte region [ffff8801359da0f0, ffff8801359da330)
The buggy address belongs to the page:
page:ffffea0004d67600 count:1 mapcount:0 mapping: (null) index:0x0 compound_mapcount: 0
flags: 0x8000000000008100(slab|head)
raw: 8000000000008100 0000000000000000 0000000000000000 0000000100110011
raw: ffffea0004b52920 ffffea0004b38020 ffff88015b416a80 0000000000000000
page dumped because: kasan: bad access detected
Memory state around the buggy address:
ffff8801359da200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff8801359da280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8801359da300: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc
^
ffff8801359da380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
ffff8801359da400: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
==================================================================
Disabling lock debugging due to kernel taint
which looks like the slab containing the radixtree iter was freed as we
traversed the tree, taking the rcu read lock across the loop should
prevent that (deferring all the frees until the end).
Reported-by: Tomi Sarvela <tomi.p.sarvela@intel.com>
Fixes: d1b48c1e71 ("drm/i915: Replace execbuf vma ht with an idr")
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>
Link: https://patchwork.freedesktop.org/patch/msgid/20171026130032.10677-2-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Kasan spotted
[IGT] gem_tiled_pread_pwrite: exiting, ret=0
==================================================================
BUG: KASAN: use-after-free in __i915_gem_object_reset_page_iter+0x15c/0x170 [i915]
Read of size 8 at addr ffff8801359da310 by task kworker/3:2/182
CPU: 3 PID: 182 Comm: kworker/3:2 Tainted: G U 4.14.0-rc6-CI-Custom_3340+ #1
Hardware name: Intel Corp. Geminilake/GLK RVP1 DDR4 (05), BIOS GELKRVPA.X64.0062.B30.1708222146 08/22/2017
Workqueue: events __i915_gem_free_work [i915]
Call Trace:
dump_stack+0x68/0xa0
print_address_description+0x78/0x290
? __i915_gem_object_reset_page_iter+0x15c/0x170 [i915]
kasan_report+0x23d/0x350
__asan_report_load8_noabort+0x19/0x20
__i915_gem_object_reset_page_iter+0x15c/0x170 [i915]
? i915_gem_object_truncate+0x100/0x100 [i915]
? lock_acquire+0x380/0x380
__i915_gem_object_put_pages+0x30d/0x530 [i915]
__i915_gem_free_objects+0x551/0xbd0 [i915]
? lock_acquire+0x13e/0x380
__i915_gem_free_work+0x4e/0x70 [i915]
process_one_work+0x6f6/0x1590
? pwq_dec_nr_in_flight+0x2b0/0x2b0
worker_thread+0xe6/0xe90
? pci_mmcfg_check_reserved+0x110/0x110
kthread+0x309/0x410
? process_one_work+0x1590/0x1590
? kthread_create_on_node+0xb0/0xb0
ret_from_fork+0x27/0x40
Allocated by task 1801:
save_stack_trace+0x1b/0x20
kasan_kmalloc+0xee/0x190
kasan_slab_alloc+0x12/0x20
kmem_cache_alloc+0xdc/0x2e0
radix_tree_node_alloc.constprop.12+0x48/0x330
__radix_tree_create+0x274/0x480
__radix_tree_insert+0xa2/0x610
i915_gem_object_get_sg+0x224/0x670 [i915]
i915_gem_object_get_page+0xb5/0x1c0 [i915]
i915_gem_pread_ioctl+0x822/0xf60 [i915]
drm_ioctl_kernel+0x13f/0x1c0
drm_ioctl+0x6cf/0x980
do_vfs_ioctl+0x184/0xf30
SyS_ioctl+0x41/0x70
entry_SYSCALL_64_fastpath+0x1c/0xb1
Freed by task 37:
save_stack_trace+0x1b/0x20
kasan_slab_free+0xaf/0x190
kmem_cache_free+0xbf/0x340
radix_tree_node_rcu_free+0x79/0x90
rcu_process_callbacks+0x46d/0xf40
__do_softirq+0x21c/0x8d3
The buggy address belongs to the object at ffff8801359da0f0
which belongs to the cache radix_tree_node of size 576
The buggy address is located 544 bytes inside of
576-byte region [ffff8801359da0f0, ffff8801359da330)
The buggy address belongs to the page:
page:ffffea0004d67600 count:1 mapcount:0 mapping: (null) index:0x0 compound_mapcount: 0
flags: 0x8000000000008100(slab|head)
raw: 8000000000008100 0000000000000000 0000000000000000 0000000100110011
raw: ffffea0004b52920 ffffea0004b38020 ffff88015b416a80 0000000000000000
page dumped because: kasan: bad access detected
Memory state around the buggy address:
ffff8801359da200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff8801359da280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8801359da300: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc
^
ffff8801359da380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
ffff8801359da400: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
==================================================================
Disabling lock debugging due to kernel taint
which looks like the slab containing the radixtree iter was freed as we
traversed the tree, taking the rcu read lock across the loop should
prevent that (deferring all the frees until the end).
Reported-by: Tomi Sarvela <tomi.p.sarvela@intel.com>
Fixes: 96d7763452 ("drm/i915: Use a radixtree for random access to the object's backing storage")
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>
Link: https://patchwork.freedesktop.org/patch/msgid/20171026130032.10677-1-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
An interesting snippet from Sandybridge's prm:
"Although a Ring Buffer can be enabled in the non-empty state, it must
not be disabled unless it is empty. Attempting to disable a Ring Buffer
in the non-empty state is UNDEFINED."
Let's avoid the undefined behaviour as we disable the rings prior to
reset and resume.
v2: Tell HEAD to catch up to TAIL (empty ring) first, then reset both to
0 (supposedly while stopped).
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/20171027094311.30380-1-chris@chris-wilson.co.uk
Per my reading of the eDP spec, DP_DPCD_DISPLAY_CONTROL_CAPABLE bit in
DP_EDP_CONFIGURATION_CAP should be set if the eDP display control
registers starting at offset DP_EDP_DPCD_REV are "enabled". Currently we
check the bit before reading the registers, and DP_EDP_DPCD_REV is the
only way to detect eDP revision.
Turns out there are (likely buggy) displays that require eDP 1.4+
features, such as supported link rates and link rate select, but do not
have the bit set. Read the display control registers
unconditionally. They are supposed to read zero anyway if they are not
supported, so there should be no harm in this.
This fixes the referenced bug by enabling the eDP version check, and
thus reading of the supported link rates. The panel in question has 0 in
DP_MAX_LINK_RATE which is only supported in eDP 1.4+. Without the
supported link rates method we default to RBR which is insufficient for
the panel native mode. As a curiosity, the panel also has a bogus value
of 0x12 in DP_EDP_DPCD_REV, but that passes our check for >= DP_EDP_14
(which is 0x03).
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103400
Reported-and-tested-by: Nicolas P. <issun.artiste@gmail.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171026142932.17737-1-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: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Matt 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
The original intent was to preserve watermarks as much as possible
in intel_pipe_wm.raw_wm, and put the validated ones in intel_pipe_wm.wm.
It seems this approach is insufficient and we don't always preserve
the raw watermarks, so just use the atomic iterator we're already using
to get a const pointer to all bound planes on the crtc.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102373
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: stable@vger.kernel.org #v4.8+
Acked-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171019151341.4579-1-maarten.lankhorst@linux.intel.com
One fix for stable:
- fix perf enable/disable ioctls for 32bits (Lionel)
Plus GVT fixes:
- Fix per_ctx_bb check (Zhenyu)
- Fix GPU hang of Linux guest (Xion)
- Refine MMIO_RING_F to check for presence of VCS2 ring (Zhi)
* tag 'drm-intel-fixes-2017-10-26' of git://anongit.freedesktop.org/drm/drm-intel:
drm/i915/gvt: Adding ACTHD mmio read handler
drm/i915/gvt: Extract mmio_read_from_hw() common function
drm/i915/gvt: Refine MMIO_RING_F()
drm/i915/gvt: properly check per_ctx bb valid state
Recently W=1 on gcc-7.2 (-Wunused-const-variable) caught a regression
that had been lurking for 6 months, so lets try enabling the full set of
warnings for CI builds. This means more patches will be rejected early
that contain trivial and sometimes not so trivial bugs. However, our
code does not yet compile cleanly with W=1, so we have to apply a filter
to the set of warnings until we can eliminate the mistakes. It also
means that developers will have to be running the full gamut of gcc to
ensure that as warnings come and go with gcc updates, we have the CI
build prepared.
v2: Use fine-grained -Wno overrides. Inside the makefile, we can
specify CFLAGS on a per-object level, which allows us to limit the scope
of any particular warning override.
v3: Place per-file overrides after the main enabling block.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Tomi Sarvela <tomi.p.sarvela@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Acked-by: Tomi Sarvela <tomi.p.sarvela@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024181547.27889-1-chris@chris-wilson.co.uk
Acked-by: Jani Nikula <jani.nikula@intel.com>
Knowing the RING_MODE flags is useful for checking the state of the
engine, such as whether the CS is idle after trying to stop the engines
before reset.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171026115048.20144-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Waiting for DMA status register can be done with dedicated function.
Lets use it as additional bonus will be smaller driver footprint.
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.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/20171024105056.43276-1-michal.wajdeczko@intel.com
Pretty similar to what we have on execlists.
We're reusing most of the GEM code, however, due to GuC quirks we need a
couple of extra bits.
Preemption is implemented as GuC action, and actions can be pretty slow.
Because of that, we're using a mutex to serialize them. Since we're
requesting preemption from the tasklet, the task of creating a workitem
and wrapping it in GuC action is delegated to a worker.
To distinguish that preemption has finished, we're using additional
piece of HWSP, and since we're not getting context switch interrupts,
we're also adding a user interrupt.
The fact that our special preempt context has completed unfortunately
doesn't mean that we're ready to submit new work. We also need to wait
for GuC to finish its own processing.
v2: Don't compile out the wait for GuC, handle workqueue flush on reset,
no need for ordered workqueue, put on a reviewer hat when looking at my own
patches (Chris)
Move struct work around in intel_guc, move user interruput outside of
conditional (Michał)
Keep ring around rather than chase though intel_context
v3: Extract WA for flushing ggtt writes to a helper (Chris)
Keep work_struct in intel_guc rather than engine (Michał)
Use ordered workqueue for inject_preempt worker to avoid GuC quirks.
v4: Drop now unused INTEL_GUC_PREEMPT_OPTION_IMMEDIATE (Daniele)
Drop stray newlines, use container_of for intel_guc in worker,
check for presence of workqueue when flushing it, rather than
enable_guc_submission modparam, reorder preempt postprocessing (Chris)
v5: Make wq NULL after destroying it
v6: Swap struct guc_preempt_work members (Michał)
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: 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/20171026133558.19580-1-michal.winiarski@intel.com
We would also like to make use of execlist_cancel_port_requests and
unwind_incomplete_requests in GuC preemption backend.
Let's rename the functions to use the correct prefixes, so that we can
simply add the declarations in the following patch.
Similar thing for applies for can_preempt, except we're introducing
HAS_LOGICAL_RING_PREEMPTION macro instad, converting other users that
were previously touching device info directly.
v2: s/intel_engine/execlists and pass execlists to unwind (Chris)
v3: use locked version for exporting, drop const qual (Chris)
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@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/20171025200020.16636-11-michal.winiarski@intel.com
We also want to support preemption with GuC submission backend.
In order to do that, we need to remember the priority, like we do on
execlists path.
v2: Remove completed prio == INT_MAX optimization
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.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/20171025200020.16636-10-michal.winiarski@intel.com
We shouldn't inspect ELSP context status (or any other bits depending on
specific submission backend) when using GuC submission.
Let's use another piece of HWSP for preempt context, to write its bit of
information, meaning that preemption has finished, and hardware is now
idle.
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Jeff McGee <jeff.mcgee@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171025200020.16636-9-michal.winiarski@intel.com
Let's separate the "emit" part from touching any internal structures,
this way we can have a generic "emit coherent GGTT write" function.
We would like to reuse this functionality for emitting HWSP write, to
confirm that preempt-to-idle has finished.
v2: Reorder args to match emit_pipe_control, s/render/rcs (Chris)
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: 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/20171025200020.16636-8-michal.winiarski@intel.com
We're using a special preempt context for HW to preempt into. We don't
want to emit any requests there, but we still need to wrap this context
into a valid GuC work item.
Let's cleanup the functions operating on GuC work items.
We can extract guc_request_add - responsible for adding GuC work item and
ringing the doorbell, and guc_wq_item_append - used by the function
above, not tied to the concept of gem request.
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Jeff McGee <jeff.mcgee@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171025200020.16636-7-michal.winiarski@intel.com
This second client is created with priority KMD_HIGH, and marked
as preemptive. This will allow us to request preemption using GuC actions.
v2: Extract clients creation into a helper, debugfs fixups. (Michał)
Recreate doorbell on init. (Daniele)
Move clients into an array.
v3: And move clients back from an array, to get rid of the enum (Michał)
v4: Use is_high_priority, move DRM_ERROR into __create_doorbell, move
GEM_BUG_ON inside guc_clients_create (Michał)
v5: Split the BUG_ON (Michał)
v6: Cleanup after error during doorbell reinit (Michał)
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171026141737.31656-1-michal.winiarski@intel.com
We're using GuC action to request preemption. However, after requesting
preemption we need to wait for GuC to finish its own post-processing
before we start submitting our requests. Firmware is using shared
context to report its status.
Let's update GuC firmware interface with those new definitions.
v2: Drop unused INTEL_GUC_PREEMPT_OPTION_IMMEDIATE
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Jeff McGee <jeff.mcgee@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171025200020.16636-5-michal.winiarski@intel.com
We were using first page of kernel context render state for sharing data
with GuC. While it's justified by the fact that those pages are not used
(note, GuC still enforces this layout and refuses to work if we remove
the extra page in front), it's also confusing (why are we using this
particular page?). Let's allocate a separate object instead.
v2: Drop kernel_context from GuC suspend/resume action handlers (Michel)
Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171025200020.16636-4-michal.winiarski@intel.com
Since it's a two-step process, we can have a cleaner error handling in
the caller if we do the allocations in a helper.
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171025200020.16636-3-michal.winiarski@intel.com
Apparently, this value is reserved and may be interpreted as changing
doorbell ownership. Even though we're not observing any side effects
now, let's skip over it to be consistent with the spec.
v2: Apply checkpatch (Sagar)
Suggested-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171025200020.16636-2-michal.winiarski@intel.com
CNL adds an extra register for slice/subslice information.
Although no SKU is planed with an extra slice let's already
handle this extra piece of information so we don't have the
risk in future of getting a part that might have chosen this
part of the die instead of other slices or anything like that.
Also if subslice is disabled the information of eu ack for that
is garbage, so let's skip checks for eu if subslice is disabled
as we skip the subslice if slice is disabled.
The rest is pretty much like gen9.
v2: Remove IS_CANNONLAKE from gen9 status function.
v3: Consider s_max = 6 and ss_max=4 to run over all possible
slices and subslices possible by spec. Although no real
hardware will have that many slices/subslices.
To match with sseu info init.
v4: Fix offset calculation for slices 4 and 5.
Removed Oscar's rv-b since this change also needs review.
v5: Let's consider only valid bits for SLICE*_PGCTL_ACK.
This looks like wrong in Spec, but seems to be enough
for now. Whenever Spec gets updated and fixed we come
back and properly update the masks. Also add a FIXME,
so we can revisit this later when we find some strange
info on debugfs or when we noitce spec got updated.
Cc: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171026001546.28203-1-rodrigo.vivi@intel.com
When a workload is too heavy to finish it in gpu hang check timer
intervals(1.5), gpu hang check function will check ACTHD register
value to decide whether gpu is real dead or not. On real hw,
ACTHD is updated by HW when workload is running, then host kernel
won't think it is gpu hang. while guest kernel always read a constant
ACTHD value as GVT doesn't supply ACTHD emulate handler, then
guest kernel detects a fake gpu hang.
To remove such guest fake gpu hang, this patch supply ACTHD
mmio read handler which read real HW ACTHD register directly.
Signed-off-by: Xiong Zhang <xiong.y.zhang@intel.com>
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/b4c9a097-3e62-124e-6856-b0c37764df7b@intel.com
The mmio read handler for ring timestmap / instdone register are same
as reading hw value directly.
Extract it as common function to reduce code duplications.
Signed-off-by: Xiong Zhang <xiong.y.zhang@intel.com>
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Inspect if the host has VCS2 ring by host i915 macro in MMIO_RING_F().
Also this helps on reducing some LOCs.
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Need to check valid state for per_ctx bb and bypass batch buffer
combine for scan if necessary. Otherwise adding invalid MI batch
buffer start cmd for per_ctx bb will cause scan failure, which is
taken as -EFAULT now so vGPU would be put in failsafe. This trys
to fix that by checking per_ctx bb valid state. Also remove old
invalid WARNING that indirect ctx bb shouldn't depend on valid
per_ctx bb.
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Just a few fixes for 4.15.
* 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/linux:
drm/amd/amdgpu: Remove workaround for suspend/resume in uvd7
drm/amdgpu: don't flush the TLB before initializing GART
drm/amdgpu: minor cleanup for amdgpu_ttm_bind
drm/amdgpu/psp: prevent page fault by checking write_frame address(v4)
drm/amd/powerplay: retrieve the real-time coreClock values
drm/amd/powerplay: fix performance drop on Vega10
drm/amd/powerplay: add one smc message for Vega10
drm/amd/powerplay: fix amd_powerplay_reset()
amdgpu: add padding to the fence to handle ioctl.
drm/amdgpu:fix wb_clear
drm/amdgpu:fix vf_error_put
drm/amdgpu/sriov:now must reinit psp
drm/amdgpu: merge bios post checking functions
The workaround is not required anymor and would result in
hangs during suspend/resume cycles if the uvd block were busy.
Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
No point in doing this.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Filter the placement mask before using it. In theory it could be that we
have other flags set here as well.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
- Prevent a possible buffer overflow when updating the ring buffer by
bounds checking the command frame against the available space in the
ring buffer.
v2: update the ring_buffer_end address
v3: update the commit log
v4: squash in print fix (Michel)
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
- Currently, the coreClock value for min/max performance level on raven
is hard-coded. Use the real-time value retrieved by GetGfxMinFreqLimit
and GetGfxMaxFreqLimit PPSMC messages
Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Setting package power PID to 1 fixes performance drop caused by
updated SMU FW, before DPM is enabled.
Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This is used to fix performance drop caused by updated SMU FW.
Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm-intel-fixes-2017-10-25:
only 1 fix for stable:
- fix perf enable/disable ioctls for 32bits (lionel)
* tag 'drm-intel-fixes-2017-10-25' of git://anongit.freedesktop.org/drm/drm-intel:
drm/i915/perf: fix perf enable/disable ioctls with 32bits userspace
The hdmi-codec interface added in this patch is required to properly
support HDMI audio. Currently the audio part of the SoC internal
HDMI transmitter is configured with fixed values, which makes HDMI
audio working by chance, only on boards having an external audio
codec connected in parallel with the HDMI audio transmitter's input
I2S interface.
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Reviewed-by: Andrzej Hajda <a.hajda@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Configuration details from Samsung. This enables 1366x768@60Hz,
which also needs the 256px timing hack to work around a mixer
limitation.
Signed-off-by: Daniel Drake <drake@endlessm.com>
Signed-off-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
[a.hajda@samsung.com: rebased onto proposed patchset]
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Since HDMI can handle these modes despite of MIXER limitations let's
enable them.
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Reviewed-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
MIXER in SoCs prior to Exynos5420 supports only 4 video modes:
720x480, 720x576, 1280x720, 1920x1080. Support for other modes
can be enabled by manipulating timings of HDMI. To do it
adjusted_mode should contain actual mode set on crtc.
With this patch it is possible to enable 1024x768 and 1280x1024
modes in MIXER.
Suggested-by: Daniel Drake <drake@endlessm.com>
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Reviewed-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
MIXER in SoCs prior to Exynos5420 supports only 4 video modes:
720x480, 720x576, 1280x720, 1920x1080. Support for other modes can be
enabled by manipulating timings of HDMI. To allow it MIXER must pass
actual video mode to HDMI, the proper way to do it is to modify
adjusted_mode property in crtc::mode_fixup callback. Adding such callback
allows also to simplify mixer_cfg_scan code - choosing mode is performed
already in crtc::mode_fixup. mode_fixup is also better place to check
interlace flag.
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Reviewed-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
crtc::mode_fixup callback is required by crtcs which internally use
a different mode than requested by user - case of Exynos Mixer.
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Reviewed-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Display mode is preserved in CRTC state, there is no need to keep local
copy of it. Moreover since HDMI should configure registers according to
requested mode, use it instead of adjusted_mode, which should contain
mode produced by CRTC - functionally it does not change anything, but
subsequent patches will make the difference.
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Reviewed-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
mixer_resources adds only unnecessary redirection, removing it makes the
code shorter and cleaner.
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Reviewed-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Mode limitation checked in mixer driver affects only older HW.
Mixer in Exynos542x has no such limitations. While at it patch changes
validation callback to recently introduced mode_valid which is more
suitable for the check. Additionally little cleanup is performed.
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Reviewed-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Screen resolution configuration depends on HW version, let's put it into
single function to make it consistent and simplify the code.
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Reviewed-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Mode commit should not be called for every plane separately. It is enough
to call it once in enable callback. The change also requires that
the interlace check is moved to mixer_commit. It should be done in
the same patch to avoid regression.
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Reviewed-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Mode setup code is called from video plane update and mixer plane update.
Let's group it together in mixer_commit function like in case of other
Exynos CRTCs.
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Reviewed-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
We accidentally inverted an if statement and turned amd_powerplay_reset()
into a no-op.
Fixes: ae97988fc8 ("drm/amd/powerplay: tidy up ret checks in amd_powerplay.c (v3)")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Now that we're handling request resubmission the same way as regular
submission (from the tasklet), we can move GuC initialization earlier,
before restarting the engines. This way, we're no longer being in the
state of flux during engine restart - we're already in user requested
submission mode.
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: Michel Thierry <michel.thierry@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171025172519.10670-5-chris@chris-wilson.co.uk
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
The execlists emulation on top of the GuC (used for scheduling and
preemption) depends on the MI_USER_INTERRUPT for its notifications and
tasklet action. As we always employ the irq, there is no advantage in
ever disabling it while we are using the GuC, so allow us to arm the
breadcrumb irq when enabling GuC submission and disarm upon disabling.
The impact should be lessened by the delayed irq disabling we do (we
only disable after receiving an interrupt for which no one was wanting),
but allowing guc to explicitly manage the irq in relation to itself is
simpler and prevents an issue with losing an interrupt for preemption
as it is not coupled to an active request.
Internally, we add a reference counter (breadcrumbs.irq_enabled) as a
simple mechanism to allow GuC to keep the breadcrumb irq enabled. To
improve upon always enabling the irq while guc is selected, we need
to hook into the parking facility of intel_engines so that we only enable
the breadcrumbs while the GT is active (one step better would be to
individually park/unpark each engine).
In effect, this means that we keep the breadcrumb irq always enabled for
the entire duration the guc is busy, whereas before we would try to
switch it off whenever we idled for more than interrupt with no
associated waiters. The difference *should* be negligible in practice!
v2: Stop abusing fence signaling (and its auxiliary data structures) to
enable the breadcrumbs irqs.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>,
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>,
Link: https://patchwork.freedesktop.org/patch/msgid/20171025143943.7661-3-chris@chris-wilson.co.uk
In the next patch, we will want to install a callback when the engines
(GT as a whole) become idle and similarly when they first become busy.
To enable that callback, first rename intel_engines_mark_idle() to
intel_engines_park() and provide the companion intel_engines_unpark().
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171025143943.7661-2-chris@chris-wilson.co.uk
This is heavily based on a initial patch provided by Ville
plus all changes provided later by Ander.
As Geminilake, Cannonlake also supports 2 pixels per clock.
Different from Geminilake we are not implementing the 99% Wa.
But we can revisit that decision later if we find out
any limitation on later CNL SKUs.
v2: Rebase on top of commit 'd305e0614601 ("drm/i915: Track
minimum acceptable cdclk instead of "minimum dotclock")'
v3: When fixing HDMI on CNL I noticed that I missed to convert
back the doubled pixel rate to cdclk.
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171003223142.26264-1-rodrigo.vivi@intel.com
The compat callback was missing and triggered failures in 32bits
userspace when enabling/disable the perf stream. We don't require any
particular processing here as these ioctls don't take any argument.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: eec688e142 ("drm/i915: Add i915 perf infrastructure")
Cc: linux-stable <stable@vger.kernel.org>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024152728.4873-1-lionel.g.landwerlin@intel.com
(cherry picked from commit 191f896085)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
When running under virtualization (vGPU active), we must disable
the lazy PPGTT page table initialization optimization introduced by
commit 1482667324 ("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: 1482667324 ("drm/i915: Only initialize partially filled pagetables")
Suggested-by: Xiaolin Zhang <xiaolin.zhang@intel.com>
Signed-off-by: Xiaolin Zhang <xiaolin.zhang@intel.com>
[Joonas: Rewrote the commit message and added tags.]
Signed-off-by: Joonas 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: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171023153209.10527-1-joonas.lahtinen@linux.intel.com
On APUs the uvd6 driver was skipping proper suspend/resume routines resulting
in a broken state upon resume.
Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This reverts commit 6d0dbd3096.
timer_setup_on_stack() does not yet exist:
In file included from drivers/gpu/drm/i915/i915_sw_fence.c:517:0:
drivers/gpu/drm/i915/selftests/lib_sw_fence.c: In function ‘timed_fence_init’:
drivers/gpu/drm/i915/selftests/lib_sw_fence.c:63:2: error: implicit declaration of function ‘timer_setup_on_stack’; did you mean ‘hrtimer_init_on_stack’? [-Werror=implicit-function-declaration]
timer_setup_on_stack(&tf->timer, timed_fence_wake, 0);
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171025131336.2584-1-chris@chris-wilson.co.uk
Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
In preparation for unconditionally passing the struct timer_list pointer to
all timer callbacks, switch to using the new timer_setup() and from_timer()
to pass the timer pointer explicitly.
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: intel-gfx@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024151344.GA104417@beast
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
During evict, we wish to idle the GPU if we see that the GGTT is full.
However, our test for idle in i915_gem_evict_something() and in
i915_gem_switch_to_kernel_context() do not match leading to
disappointment - we never believe that we are idle and keep trying to
flush the GGTT ad infinitum.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103438
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024220855.30155-2-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Instead of trying to create a timer with zero delay (i.e. with expires
set to the current jiffies and not the future, an already expired
timer), execute that request immediately.
v2: Refactor list_del_init+signal into its own little function.
v3: Reorder testing so as not to immediately signal a delayed request.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024220855.30155-1-chris@chris-wilson.co.uk
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Insert a breakpoint, a chance to escape back to the scheduler and run
something else for a bit, if we find that the GGTT is full and needs to
be idled in order to make some room. In practice, this should only be an
issue in stress tests as the wait itself will normally give the chance
for the scheduler to intervene and make progress.
References: https://bugs.freedesktop.org/show_bug.cgi?id=103438
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024205053.7845-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
WARN if the cdclk state doesn't match what we expect after programming.
And let's remove the WARN from bdw_set_cdclk() that's trying to achieve
the same thing in a more limite fashion.
Also take the opportunity to refactor the code to use a common function
for dumping out a cdclk state.
Cc: Mika Kahola <mika.kahola@intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024095216.1638-11-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
chv_set_cdclk() sanity checks that the cdclk frequency is one of the
legal values. Do the same in the VLV function.
Cc: Mika Kahola <mika.kahola@intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024095216.1638-10-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
On CNL we may need to bump up the system agent voltage not only due
to CDCLK but also when driving DDI port with a sufficiently high clock.
To that end start tracking the minimum acceptable voltage for each crtc.
We do the tracking via crtcs because we don't have any kind of encoder
state. Also there's no downside to doing it this way, and it matches how
we track cdclk requirements on account of pixel rate.
v2: Allow disabled crtcs to use the min voltage
Add IS_CNL check to intel_ddi_compute_min_voltage() since
we're using CNL specific values there
s/intel_compute_min_voltage/cnl_compute_min_voltage/ since
the function makes hw specific assumptions about the voltage
values
v3: Drop the test hack leftovers from skl_modeset_calc_cdclk()
v4: s/voltage/voltage_level/ (Rodrigo)
Replace DPLL DVFS FIXMEs with an explanation why we don't
do anything there (Rodrigo)
Cc: Mika Kahola <mika.kahola@intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024095216.1638-9-ville.syrjala@linux.intel.com
Ben Skeggs