| Age | Commit message (Collapse) | Author |
|---|
|
Since most of the HVS channel is setup in the init function, let's move the
gamma setup there too. As this makes the HVS mode_set function empty, let's
remove it in the process.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Link: https://patchwork.freedesktop.org/patch/msgid/d439da8f1592a450a6ad35ab1f9e77def17c7965.1599120059.git-series.maxime@cerno.tech
|
|
In order to make further refactoring easier, let's move the HVS channel
setup / teardown to their own function.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Link: https://patchwork.freedesktop.org/patch/msgid/fb1b5299d1636ddce8340b51a80d51641839f83b.1599120059.git-series.maxime@cerno.tech
|
|
Now that we only configure the PixelValve in vc4_crtc_config_pv, it doesn't
really make much sense to dump its register content in its caller.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Link: https://patchwork.freedesktop.org/patch/msgid/c195af7d9e140a2a6db32992ee7e54071c6f94ba.1599120059.git-series.maxime@cerno.tech
|
|
The driver resets the pixelvalve FIFO in a number of occurences without
always using the same sequence.
Since this will be critical for BCM2711, let's move that sequence to a
function so that we are consistent.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/fb31003a9eee02c4b949556299ff41f0a113499a.1599120059.git-series.maxime@cerno.tech
|
|
The HVS5 uses different color matrices. Disable color management support
for now.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/e528e2edf0a1be3930196d437e548114dd9fcf59.1599120059.git-series.maxime@cerno.tech
|
|
The BCM2711 sports a second HDMI controller, so let's add that second HDMI
encoder type.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/6ba56d2421a4ad59ce72178e8f37eacfbd72cb33.1599120059.git-series.maxime@cerno.tech
|
|
The previous generations were only supporting a single HDMI controller, but
that's about to change, so put an index as well to differentiate between
the two controllers.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/84e11e4793aaa30d6e5c56e305d22404ac5a932d.1599120059.git-series.maxime@cerno.tech
|
|
The longer FIFOs in vc5 pixelvalves means that the FIFO full level
doesn't fit in the original register field and that we also have a
secondary field. In order to prepare for this, let's move the registers
fill part to a helper function.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/e46a3823128af50c1c833de8fa9b95e9b86c2f66.1599120059.git-series.maxime@cerno.tech
|
|
Not all pixelvalve FIFOs in vc5 have the same depth, so we need to add that
to our vc4_crtc_data structure to be able to compute the fill level
properly later on.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/7df3549c1bea9b0a27c784dc416bb9a831e4e18f.1599120059.git-series.maxime@cerno.tech
|
|
The HVS found in the BCM2711 has 6 outputs and 3 FIFOs, with each output
being connected to a pixelvalve, and some muxing between the FIFOs and
outputs.
Any output cannot feed from any FIFO though, and they all have a bunch of
constraints.
In order to support this, let's store the possible FIFOs each output can be
assigned to in the vc4_crtc_data, and use that information at atomic_check
time to iterate over all the CRTCs enabled and assign them FIFOs.
The channel assigned is then set in the vc4_crtc_state so that the rest of
the driver can use it.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Link: https://patchwork.freedesktop.org/patch/msgid/f9aba3814ef37156ff36f310118cdd3954dd3dc5.1599120059.git-series.maxime@cerno.tech
|
|
The vc4 atomic commit loop has an handrolled loop that is basically
identical to for_each_new_crtc_state, let's convert it to that helper.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Link: https://patchwork.freedesktop.org/patch/msgid/a712d2b70aaee20379cfc52c2141aa2f6e2a9d5b.1599120059.git-series.maxime@cerno.tech
|
|
The VIDEN bit in the pixelvalve currently being used to enable or disable
the pixelvalve seems to not be enough in some situations, which whill end
up with the pixelvalve stalling.
In such a case, even re-enabling VIDEN doesn't bring it back and we need to
clear the FIFO. This can only be done if the pixelvalve is disabled though.
In order to overcome this, we can configure the pixelvalve during
mode_set_no_fb by calling vc4_crtc_config_pv, but only enable it in
atomic_enable and flush the FIFO there, and in atomic_disable disable the
pixelvalve again.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Link: https://patchwork.freedesktop.org/patch/msgid/e97596f62f4df83424d994a23465463ac60f986e.1599120059.git-series.maxime@cerno.tech
|
|
The vc4_crtc_handle_page_flip already has a local variable holding the
value of vc4_crtc->channel, so let's use it instead.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Link: https://patchwork.freedesktop.org/patch/msgid/439c589baec72ddb89159857a2d078fdd77b02a2.1599120059.git-series.maxime@cerno.tech
|
|
In vc5, the HVS has 6 outputs and 3 FIFOs (or channels), with
pixelvalves each being assigned to a given output, but each output can
then be muxed to feed from multiple FIFOs.
Since vc4 had that entirely static, both were probably equivalent, but
since that changes, let's rename hvs_channel to hvs_output in the
vc4_crtc_data, since a pixelvalve is really connected to an output, and
not to a FIFO.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Link: https://patchwork.freedesktop.org/patch/msgid/b7618bb17b1c435c5d6ce50bcde2fe9243281d02.1599120059.git-series.maxime@cerno.tech
|
|
The COB allocation depends on the HVS channel used for a given
pixelvalve.
While the channel allocation was entirely static in vc4, vc5 changes
that and at bind time, a pixelvalve can be assigned to multiple
HVS channels.
Let's prepare that rework by allocating the COB when it's actually
needed.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/484cbd4b00cfeee425295df438222258cc39a3dd.1599120059.git-series.maxime@cerno.tech
|
|
Some pixelvalves in vc5 use the same interrupt line so let's register our
interrupt handler as a shared one.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/5a915d374357f41083ac71779fa9b2c35a339c2f.1599120059.git-series.maxime@cerno.tech
|
|
Some of the HDMI pixelvalves in vc5 output two pixels per clock cycle.
Let's put the number of pixel output per clock cycle in the CRTC data and
update the various calculations to reflect that.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/18a3bb079981ba820132b37e736a4bb371234d2e.1599120059.git-series.maxime@cerno.tech
|
|
Let's now create more planes that can be affected to all the CRTCs.
vc4 has 3 CRTCs, 1 primary and 1 cursor each, and was having 24 (8
planes per CRTC) overlays.
However, vc5 has 5 CRTCs, so keeping the same logic would put us at 50
planes which is well above the 32 planes limit imposed by DRM.
Using 16 seems like a good tradeoff between staying under 32 and yet
providing enough planes.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/b41003001541fc2bb23668c699c0369ff7983be8.1599120059.git-series.maxime@cerno.tech
|
|
The current code is using the maximum of the source line size and the
destination line size to compute the size of the LBM to allocate.
While this is simpler, it starts to be an issue with modes such as 4k with
a quite long that will consume all the available memory, so we no longer
have that luxury.
Signed-off-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Link: https://patchwork.freedesktop.org/patch/msgid/b9e091883a4f7395c5b6a4f7c6070225934293db.1599120059.git-series.maxime@cerno.tech
|
|
The HVS5 needs an alignment of 64bytes for its LBM memory, so let's reflect
it.
Signed-off-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Link: https://patchwork.freedesktop.org/patch/msgid/6f9c4fe1eb9258a3f1d0f21af6a99c42472ac531.1599120059.git-series.maxime@cerno.tech
|
|
In order to prevent timeouts and stalls in the pipeline, the core clock
needs to be maxed at 500MHz during a modeset on the BCM2711.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/37ed9e0124c5cce005ddc8dafe821d8b0da036ff.1599120059.git-series.maxime@cerno.tech
|
|
The HVS found in the BCM2711 is slightly different from the previous
generations.
Most notably, the display list layout changes a bit, the LBM doesn't have
the same size and the formats ordering for some formats is swapped.
Signed-off-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Tested-by: Hoegeun Kwon <hoegeun.kwon@samsung.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/1d02fab3b916d639c2dc05608c117bbd8230ebe8.1599120059.git-series.maxime@cerno.tech
|
|
The hwsp_gtt object is used for sub-allocation and could therefore
be shared by many contexts causing unnecessary contention during
concurrent context pinning.
However since we're currently locking it only for pinning, it remains
resident until we unpin it, and therefore it's safe to drop the
lock early, allowing for concurrent thread access.
Signed-off-by: Thomas Hellström <thomas.hellstrom@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
(NOTE: This is the minimal backportable fix, a full fix is being
developed at https://patchwork.freedesktop.org/patch/388048/)
The flags passed to the wait_entry.func are passed onwards to
try_to_wake_up(), which has a very particular interpretation for its
wake_flags. In particular, beyond the published WF_SYNC, it has a few
internal flags as well. Since we passed the fence->error down the chain
via the flags argument, these ended up in the default_wake_function
confusing the kernel/sched.
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2110
Fixes: ef4688497512 ("drm/i915: Propagate fence errors")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: <stable@vger.kernel.org> # v5.4+
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200728152144.1100-1-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Joonas: Rebased and reordered into drm-intel-gt-next branch]
[Joonas: Added a note and link about more complete fix]
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
To implement preempt-to-busy (and so efficient timeslicing and best utilization
of the hardware submission ports) we let the GPU run asynchronously in respect
to the ELSP submission queue. This created challenges in keeping and accessing
the driver state mirroring the asynchronous GPU execution.
Previous fix 1d9221e9d395 ("drm/i915: Skip signaling a signaled request")
however did not correctly serialize request retirement with the execution
callbacks.
We were using the i915_request.lock to serialise adding an execution callback
with __i915_request_submit. However, if we use an atomic llist_add to serialise
multiple waiters and then check to see if the request is already executing, we
can remove the irq-spinlock and fix serialization between retirement and
execution callbacks in one go.
v2: Avoid using the irq_work when outside of the irq-spinlocks, where we
can execute the callbacks immediately.
v3: Pay close attention to the order of setting ACTIVE on retirement, we
need to ensure the request is signaled and breadcrumbs detached before
we finish removing the request from the engine.
v4: Expanded commit message.
Fixes: 1d9221e9d395 ("drm/i915: Skip signaling a signaled request")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200716142207.13003-2-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Joonas: Rebased and reordered into drm-intel-gt-next branch]
[Joonas: Added expanded commit message from Tvrtko and Chris]
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
To implement preempt-to-busy (and so efficient timeslicing and best utilization
of the hardware submission ports) we let the GPU run asynchronously in respect
to the ELSP submission queue. This created challenges in keeping and accessing
the driver state mirroring the asynchronous GPU execution.
The latest occurence of this was spotted by KCSAN:
[ 1413.563200] BUG: KCSAN: data-race in __await_execution+0x217/0x370 [i915]
[ 1413.563221]
[ 1413.563236] race at unknown origin, with read to 0xffff88885bb6c478 of 8 bytes by task 9654 on cpu 1:
[ 1413.563548] __await_execution+0x217/0x370 [i915]
[ 1413.563891] i915_request_await_dma_fence+0x4eb/0x6a0 [i915]
[ 1413.564235] i915_request_await_object+0x421/0x490 [i915]
[ 1413.564577] i915_gem_do_execbuffer+0x29b7/0x3c40 [i915]
[ 1413.564967] i915_gem_execbuffer2_ioctl+0x22f/0x5c0 [i915]
[ 1413.564998] drm_ioctl_kernel+0x156/0x1b0
[ 1413.565022] drm_ioctl+0x2ff/0x480
[ 1413.565046] __x64_sys_ioctl+0x87/0xd0
[ 1413.565069] do_syscall_64+0x4d/0x80
[ 1413.565094] entry_SYSCALL_64_after_hwframe+0x44/0xa9
To complicate matters, we have to both avoid the read tearing of *active and
avoid any write tearing as perform the pending[] -> inflight[] promotion of the
execlists.
This is because we cannot rely on the memcpy doing u64 aligned copies on all
kernels/platforms and so we opt to open-code it with explicit WRITE_ONCE
annotations to satisfy KCSAN.
v2: When in doubt, write the same comment again.
v3: Expanded commit message.
Fixes: b55230e5e800 ("drm/i915: Check for awaits on still currently executing requests")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200716142207.13003-1-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Joonas: Rebased and reordered into drm-intel-gt-next branch]
[Joonas: Added expanded commit message from Tvrtko and Chris]
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Use ww locking for pin_to_display_plane for all the pinning and locking.
With the locking removed from set_cache_level, we need to fix
i915_gem_set_caching_ioctl to take the object reservation lock.
As this is a single lock, we don't need to use the ww dance.
Changes since v1:
- Do not use ww locking in i915_gem_set_caching_ioctl (Thomas).
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-24-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
We want to start requiring the reservation_lock instead of obj->mm.lock
for pinning objects, take the ww lock inside vm_fault_gtt as a first step
towards the legacy lock removal.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-23-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Make sure vma_lock is not used as inner lock when kernel context is used,
and add ww handling where appropriate.
Ensure that execbuf selftests keep passing by using ww handling.
Changes since v2:
- Fix i915_gem_context finally.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-22-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
We want to get rid of intel_context_pin(), convert
intel_context_create_request() first. :)
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-21-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
This function does not use intel_context_create_request, so it has
to use the same locking order as normal code. This is required to
shut up lockdep in selftests.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-20-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Some i915 selftests still use i915_vma_lock() as inner lock, and
intel_context_create_request() intel_timeline->mutex as outer lock.
Fortunately for selftests this is not an issue, they should be fixed
but we can move ahead and cleanify lockdep now.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-19-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
We have the ordering of timeline->mutex vs resv_lock wrong,
convert the i915_pin_vma and intel_context_pin as well to
future-proof this.
We may need to do future changes to do this more transaction-like,
and only get down to a single i915_gem_ww_ctx, but for now this
should work.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-18-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Instead of using intel_context_create_request(), use intel_context_pin()
and i915_create_request directly.
Now all those calls are gone outside of selftests. :)
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-17-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
This is the last part outside of selftests that still don't use the
correct lock ordering of timeline->mutex vs resv_lock.
With gem fixed, there are a few places that still get locking wrong:
- gvt/scheduler.c
- i915_perf.c
- Most if not all selftests.
Changes since v1:
- Add intel_engine_pm_get/put() calls to fix use-after-free when using
intel_engine_get_pool().
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-16-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
As a preparation step for full object locking and wait/wound handling
during pin and object mapping, ensure that we always pass the ww context
in i915_gem_execbuffer.c to i915_vma_pin, use lockdep to ensure this
happens.
This also requires changing the order of eb_parse slightly, to ensure
we pass ww at a point where we could still handle -EDEADLK safely.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-15-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Instead of doing everything inside of pin_mutex, we move all pinning
outside. Because i915_active has its own reference counting and
pinning is also having the same issues vs mutexes, we make sure
everything is pinned first, so the pinning in i915_active only needs
to bump refcounts. This allows us to take pin refcounts correctly
all the time.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-14-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
We want to lock all gem objects, including the engine context objects,
rework the throttling to ensure that we can do this. Now we only throttle
once, but can take eb_pin_engine while acquiring objects. This means we
will have to drop the lock to wait. If we don't have to throttle we can
still take the fastpath, if not we will take the slowpath and wait for
the throttle request while unlocked.
The engine has to be pinned as first step, otherwise gpu relocations
won't work.
Changes since v1:
- Only need to get a throttled request in the fastpath, no need for
a global flag any more.
- Always free the waited request correctly.
Changes since v2:
- Use intel_engine_pm_get()/put() to keeep engine pool alive during
EDEADLK handling.
Changes since v3:
- Fix small rq leak.
Changes since v4:
- Use a single reloc_context, for intel_context_pin_ww().
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-13-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Those arguments are already set as eb.file and eb.args, so kill off
the extra arguments. This will allow us to move eb_pin_engine() to
after we reserved all BO's.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-12-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
This is required if we want to pass a ww context in intel_context_pin
and gen6_ppgtt_pin().
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-11-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
We want to start using ww locking in intel_context_pin, for this
we need to lock multiple objects, and the single i915_gem_object_lock
is not enough.
Convert to using ww-waiting, and make sure we always pin intel_context_state,
even if we don't have a renderstate object.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-10-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Now that we changed execbuf submission slightly to allow us to do all
pinning in one place, we can now simply add ww versions on top of
struct_mutex. All we have to do is a separate path for -EDEADLK
handling, which needs to unpin all gem bo's before dropping the lock,
then starting over.
This finally allows us to do parallel submission, but because not
all of the pinning code uses the ww ctx yet, we cannot completely
drop struct_mutex yet.
Changes since v1:
- Keep struct_mutex for now. :(
Changes since v2:
- Make sure we always lock the ww context in slowpath.
Changes since v3:
- Don't call __eb_unreserve_vma in eb_move_to_gpu now; this can be
done on normal unlock path.
- Unconditionally release vmas and context.
Changes since v4:
- Rebased on top of struct_mutex reduction.
Changes since v5:
- Remove training wheels.
Changes since v6:
- Fix accidentally broken -ENOSPC handling.
Changes since v7:
- Handle gt buffer pool better.
Changes since v8:
- Properly clear variables, to make -EDEADLK handling not BUG.
Change since v9:
- Fix unpinning fence on pnv and below.
Changes since v10:
- Make relocation gpu chaining working again.
Changes since v11:
- Remove relocation chaining, pain to make it work.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-9-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
We want to introduce backoff logic, but we need to lock the
pool object as well for command parsing. Because of this, we
will need backoff logic for the engine pool obj, move the batch
validation up slightly to eb_lookup_vmas, and the actual command
parsing in a separate function which can get called from execbuf
relocation fast and slowpath.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-8-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Execbuffer submission will perform its own WW locking, and we
cannot rely on the implicit lock there.
This also makes it clear that the GVT code will get a lockdep splat when
multiple batchbuffer shadows need to be performed in the same instance,
fix that up.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-7-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
i915_gem_ww_ctx is used to lock all gem bo's for pinning and memory
eviction. We don't use it yet, but lets start adding the definition
first.
To use it, we have to pass a non-NULL ww to gem_object_lock, and don't
unlock directly. It is done in i915_gem_ww_ctx_fini.
Changes since v1:
- Change ww_ctx and obj order in locking functions (Jonas Lahtinen)
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-6-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
This reverts commit 0f1dd02295f3 ("drm/i915/gem: Split eb_vma into
its own allocation") and also moves all unreserving to a single
place at the end, which is a minor simplification.
With the WW locking, we will drop all references only at the
end when unlocking, so refcounting can now be removed.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-5-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
This reverts commit 7dc8f1143778 ("drm/i915/gem: Drop relocation
slowpath"). We need the slowpath relocation for taking ww-mutex
inside the page fault handler, and we will take this mutex when
pinning all objects.
We also functionally revert ef398881d27d ("drm/i915/gem: Limit
struct_mutex to eb_reserve"), as we need the struct_mutex in
the slowpath as well, and a tiny part of 003d8b9143a6 ("drm/i915/gem:
Only call eb_lookup_vma once during execbuf ioctl"). Specifically,
we make the -EAGAIN handling part of fallback to slowpath again.
With this, we have a proper working slowpath again, which
will allow us to do fault handling with WW locks held.
[mlankhorst: Adjusted for reloc_gpu_flush() changes]
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
[mlankhorst: Removed extra reloc_gpu_flush()]
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-4-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
This reverts commit 964a9b0f611ee ("drm/i915/gem: Use chained reloc batches")
and commit 0e97fbb080553 ("drm/i915/gem: Use a single chained reloc batches
for a single execbuf").
When adding ww locking to execbuf, it's hard enough to deal with a
single BO that is part of relocation execution. Chaining is hard to
get right, and with GPU relocation deprecated, it's best to drop this
altogether, instead of trying to fix something we will remove.
This is not a completely 1:1 revert, we reset rq_size to 0 in
reloc_cache_init, this was from e3d291301f99 ("drm/i915/gem: Implement legacy
MI_STORE_DATA_IMM"), because we don't want to break the selftests. (Daniel)
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-3-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
This reverts commit 9e0f9464e2ab ("drm/i915/gem: Async GPU relocations only"),
and related commit 7ac2d2536dfa7 ("drm/i915/gem: Delete unused code").
Async GPU relocations are not the path forward, we want to remove
GPU accelerated relocation support eventually when userspace is fixed
to use VM_BIND, and this is the first step towards that. We will keep
async gpu relocations around for now, until userspace is fixed.
Relocation support will be disabled completely on platforms where there
was never any userspace that depends on it, as the hardware doesn't
require it from at least gen9+ onward. For older platforms, the plan
is to use cpu relocations only.
The igt side is fixed in igt commit 39e9aa1032a4e ("tests/i915: Remove
subtests that rely on async relocation behavior").
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-2-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
If dma_fence_chain_find_seqno() reports an error, it does so in its
preamble before it disposes of the input fence. On handling the
error, we need to drop the reference to the fence.
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2292
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 13149e8bafc4 ("drm/i915: add syncobj timeline support")
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200806161056.17593-1-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
