If the GPU is terminally wedged we cannot submit any requests into a
context, completely unfulfilling our purpose of doing so. As this
expectedly fails, skip over the test.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-9-chris@chris-wilson.co.uk
We test the GPU handling of huge pages by submitting requests that write
into a huge page, but if the GPU is irrecoverably wedged we cannot
submit any requests. As the test expectedly fails, skip over it.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-8-chris@chris-wilson.co.uk
If the GPU is irrecoverably wedged, we cannot submit any requests and so
cannot make the GTT busy in order to test evicting active objects. As
this expectedly fails, skip over the test.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-7-chris@chris-wilson.co.uk
If the GPU is irrecoverably wedged, we cannot submit any request and
therefore cannot query the register state of the context (which is done
using the GPU command stream). So skip over the test as it expectedly
fails.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-6-chris@chris-wilson.co.uk
As we keep VMA around until the object is destroyed, when testing
partial tiling we instantiate many, many VMA (as the object is huge
allowing for many different partial regions). We test elsewhere our
handling of populating large objects with a full set of VMA and checking
we can retrieve them afterwards, but in this test we incur the cost of
flushing all VMA after every GTT write, dramatically slowing down the
test.
References: https://bugs.freedesktop.org/show_bug.cgi?id=107130
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-2-chris@chris-wilson.co.uk
Having found the error causing the IGT test to fail, downgrade the
verbose logging so that we stop flooding the syslogs as we deliberately
provoke it many thousands of time during selftests.
References: 10195b1e44 ("drm/i915: Show vma allocator stack when in doubt")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-1-chris@chris-wilson.co.uk
This patch defines AUX lane registers for PORT_PCS_DW1,
PORT_TX_DW2, PORT_TX_DW4, PORT_TX_DW5 used during
dsi enabling.
v2: Review comments from Jani N:
- Define _ICL_PORT_PCS_DW1_AUX_A for consistency
- Three spaces for bitfield definition.
Signed-off-by: Madhav Chauhan <madhav.chauhan@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530798591-2077-8-git-send-email-madhav.chauhan@intel.com
To save power, unused lanes should be powered
down using the bitfield of PORT_CL_DW10.
v2: Review comments from Jani N
- Put default label next to case 4
- Include the shifts in the macros
Signed-off-by: Madhav Chauhan <madhav.chauhan@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530798591-2077-7-git-send-email-madhav.chauhan@intel.com
This register used to power down individual lanes for
DDI/DSI ports. Bitfields to power up/down various
combinations of lanes are also added in this patch.
v2: Review comments from Jani N
- Use override instead of "override" for bitfields
- Define mask for override bitfield
- Define PWR_DOWN_LN* macros shifted in place
v3: Correct PWR_DOWN_LN_MASK value (Jani N)
Signed-off-by: Madhav Chauhan <madhav.chauhan@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530798591-2077-6-git-send-email-madhav.chauhan@intel.com
Escape Clock is used for LP communication across the DSI
Link. To achieve the constant frequency of the escape clock
from the variable DPLL frequency output, a variable divider(M)
is needed. This patch programs the same.
v2: (Jani N) Don't end line with "(".
Signed-off-by: Madhav Chauhan <madhav.chauhan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1530798591-2077-3-git-send-email-madhav.chauhan@intel.com
Use the more customary order of latest platform first, and don't bother
with an if in the last branch.
Cc: Madhav Chauhan <madhav.chauhan@intel.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Madhav Chauhan <madhav.chauhan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705132509.12881-3-jani.nikula@intel.com
Avoid confusion with the functions to be added for the new ICL or gen 11
DSI implementation by renaming the current DSI functions. While at it,
permutate the words in the function names to make them all start with
"vlv_dsi" or "vlv_dsi_pll" etc.
Reduce the platform abstractions in the PLL file while at it, moving the
checks to vlv_dsi.c instead, where we typically already have the
necessary if ladders.
Leave the static functions as-is for now; they could be renamed later if
needed.
No functional changes.
v2: use "gen7" prefix.
v3: use "vlv" and "bxt" prefixes, reduce the abstractions.
References: https://patchwork.freedesktop.org/series/44823/
Cc: Madhav Chauhan <madhav.chauhan@intel.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Madhav Chauhan <madhav.chauhan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705132509.12881-2-jani.nikula@intel.com
Starting from ICL or gen 11 we have a new DSI block which requires
completely different programming from the current implementation. Having
them in the same file would be confusing. Rename the current DSI and DSI
PLL implementation files as vlv_dsi.c and vlv_dsi_pll.c.
No functional changes.
v2: use "gen7" prefix.
v3: use "vlv" prefix.
References: https://patchwork.freedesktop.org/series/44823/
Cc: Madhav Chauhan <madhav.chauhan@intel.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Madhav Chauhan <madhav.chauhan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705132509.12881-1-jani.nikula@intel.com
If the GPU is irrecoverably wedged on startup, it means that it failed
on initialisation and we have already tried to reset it but failed. We
can ignore all further testing, as it is already dead. Failing early,
prevents us from slowly failing in our endeavours later and timing out.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705150214.28316-1-chris@chris-wilson.co.uk
i915_gem_detect_bit_6_swizzle() tries to hide unknown swizzling from
userspace (and ourselves) leaving us with the only clue inside
i915->quirks & QUIRK_PIN_SWIZZLED_PAGES. If we see this bit set, it
means that we really have no clue as to what the swizzle pattern is
being used in any one page and so cannot compute what the reference
value should be in our tiling selftests. We have to skip the test.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107133
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705171523.18462-1-chris@chris-wilson.co.uk
In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.
Addresses-Coverity-ID: 141432
Addresses-Coverity-ID: 141433
Addresses-Coverity-ID: 141434
Addresses-Coverity-ID: 141435
Addresses-Coverity-ID: 141436
Addresses-Coverity-ID: 1357360
Addresses-Coverity-ID: 1357403
Addresses-Coverity-ID: 1357433
Addresses-Coverity-ID: 1392622
Addresses-Coverity-ID: 1415273
Addresses-Coverity-ID: 1435752
Addresses-Coverity-ID: 1441500
Addresses-Coverity-ID: 1454596
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628223541.GA17665@embeddedor.com
This patch adds the new registers and corresponding bit definitions
which will be used for programming/enable DSI PLL.
v2: Review comments from Jani N
- Fix spaces while defining ICL_ESC_CLK_DIV_MASK
- Define shift and mask for bitfields.
Signed-off-by: Madhav Chauhan <madhav.chauhan@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530795727-28644-2-git-send-email-madhav.chauhan@intel.com
Currently, the wc-stash used for providing flushed WC pages ready for
constructing the page directories is assumed to be protected by the
struct_mutex. However, we want to remove this global lock and so must
install a replacement global lock for accessing the global wc-stash (the
per-vm stash continues to be guarded by the vm).
We need to push ahead on this patch due to an oversight in hastily
removing the struct_mutex guard around the igt_ppgtt_alloc selftest. No
matter, it will prove very useful (i.e. will be required) in the near
future.
v2: Restore the onstack stash so that we can drop the vm->mutex in
future across the allocation.
v3: Restore the lost pagevec_init of the onstack allocation, and repaint
function names.
v4: Reorder init so that we don't try and use i915_address_space before
it is ininitialised.
Fixes: 1f6f00238a ("drm/i915/selftests: Drop struct_mutex around lowlevel pggtt allocation")
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/20180704185518.4193-1-chris@chris-wilson.co.uk
Adjust the EIR clearing to cope with the edge triggered IIR
on i965/g4x. To guarantee an edge in the ISR master error bit
we temporarily mask everything in EMR. As some of the EIR bits
can't even be directly cleared we also borrow a trick from
i915_clear_error_registers() and permanently mask any bit that
remains high. No real thought given to how we might unmask them
again once the cause for the error has been clered. I suppose
on pre-g4x GPU reset will reinitialize EMR from scratch.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611200258.27121-3-ville.syrjala@linux.intel.com
Reviewed-by: Imre Deak <imre.deak@intel.com>
Just like with PIPESTAT, the edge triggered IIR on i965/g4x
also causes problems for hotplug interrupts. To make sure
we don't get the IIR port interrupt bit stuck low with the
ISR bit high we must force an edge in ISR. Unfortunately
we can't borrow the PIPESTAT trick and toggle the enable
bits in PORT_HOTPLUG_EN as that act itself generates hotplug
interrupts. Instead we just have to loop until we've cleared
PORT_HOTPLUG_STAT, or we just give up and WARN.
v2: Don't frob with PORT_HOTPLUG_EN
Cc: stable@vger.kernel.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614175625.1615-1-ville.syrjala@linux.intel.com
Reviewed-by: Imre Deak <imre.deak@intel.com>
For a ppgtt that we are constructing, there is no struct_mutex
dependence so skip it. In the process, also ping the scheduler
frequently to try and avoid the NMI watchdog.
v2: gen6 requires struct_mutex to clean up (currently)
Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
References: https://bugs.freedesktop.org/show_bug.cgi?id=107094
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/20180703135331.12265-1-chris@chris-wilson.co.uk
live_gtt is a very slow test to run, simply because it tries to allocate
and use as much as the 48b address space as possibly can and in the
process will try to own all of the system memory. This leads to resource
exhaustion and CPU starvation; the latter impacts us when the NMI
watchdog declares a task hung due to a mutex contention with ourselves.
This we can prevent by releasing the struct_mutex and forcing our
i915/rcu workers to run, and in particular flushing the freed object
worker that is the cause for concern.
References: https://bugs.freedesktop.org/show_bug.cgi?id=107094
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/20180703101829.7360-1-chris@chris-wilson.co.uk
The PIPEDSL freezes on PSR entry and if PSR hasn't fully exited, then
the pipe_update_start call schedules itself out to check back later.
On ChromeOS-4.4 kernel, which is fairly up-to-date w.r.t drm/i915 but
lags w.r.t core kernel code, hot plugging an external display triggers
tons of "potential atomic update errors" in the dmesg, on *pipe A*. A
closer analysis reveals that we try to read the scanline 3 times and
eventually timeout, b/c PSR hasn't exited fully leading to a PIPEDSL
stuck @ 1599. This issue is not seen on upstream kernels, b/c for *some*
reason we loop inside intel_pipe_update start for ~2+ msec which in this
case is more than enough to exit PSR fully, hence an *unstuck* PIPEDSL
counter, hence no error. On the other hand, the ChromeOS kernel spends
~1.1 msec looping inside intel_pipe_update_start and hence errors out
b/c the source is still in PSR.
Regardless, we should wait for PSR exit (if PSR is disabled, we incur
a ~1-2 usec penalty) before reading the PIPEDSL, b/c if we haven't
fully exited PSR, then checking for vblank evasion isn't actually
applicable.
v4: Comment explaining psr_wait after enabling VBL interrupts (DK)
v5: CAN_PSR() to handle platforms that don't support PSR.
v6: Handle local_irq_disable on early return (Chris)
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Tarun Vyas <tarun.vyas@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180627200250.1515-2-tarun.vyas@intel.com
This is a lockless version of the exisiting psr_wait_for_idle().
We want to wait for PSR to idle out inside intel_pipe_update_start.
At the time of a pipe update, we should never race with any psr
enable or disable code, which is a part of crtc enable/disable.
The follow up patch will use this lockless wait inside pipe_update_
start to wait for PSR to idle out before checking for vblank evasion.
We need to keep the wait in pipe_update_start to as less as it can be.
So,we can live and flourish w/o taking any psr locks at all.
Even if psr is never enabled, psr2_enabled will be false and this
function will wait for PSR1 to idle out, which should just return
immediately, so a very short (~1-2 usec) wait for cases where PSR
is disabled.
v2: Add comment to explain the 25msec timeout (DK)
v3: Rename psr_wait_for_idle to __psr_wait_for_idle_locked to avoid
naming conflicts and propagate err (if any) to the caller (Chris)
v5: Form a series with the next patch
v7: Better explain the need for lockless wait and increase the max
timeout to handle refresh rates < 60 Hz (Daniel Vetter)
v8: Rebase
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Tarun Vyas <tarun.vyas@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180627200250.1515-1-tarun.vyas@intel.com
Prints live state of psr1.Extending the existing
PSR2 live state function to cover psr1.
Tested on KBL with psr2 and psr1 panel.
v2: rebase
v3: DK
Rename psr2_live_status to psr_source_status.
v4: DK
Move EDP_PSR_STATUS_STATE_SHIFT below EDP_PSR_STATUS_STATE_MASK.
Pass seq to psr_source_status, handle source status prints in
psr_source_status.
v5: Fixed CI warning messages
v6:
Remove extra space in the title before the colon.(DK)
Rebase. (Jani)
v7: Use tabs for indenting the values.(Jani)
v8: Addressed dk's review comments.
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530086910-15914-1-git-send-email-vathsala.nagaraju@intel.com
If the whole object is already pinned by HW for use as scanout, we will
fail to move it to the mappable region and so must resort to using a
partial VMA covering the whole object.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104513
Fixes: aa136d9d72 ("drm/i915: Convert partial ggtt vma to full ggtt if it spans the entire object")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180630090509.469-1-chris@chris-wilson.co.uk
While debugging we may want to examine params passed to GuC.
v2: drop #ifdef DEBUG_GUC - Michal
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com> #1
Cc: Michal Winiarski <michal.winiarski@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618111821.47088-1-michal.wajdeczko@intel.com
make_obj_busy() makes a dummy busy object, but didn't attach the fence
to the reservation object, so it would not have registered as busy. For
completeness, attach the dummy request as the exclusive fence and mark
the object as written (in i915_vma_move_to_active)
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/20180629133717.11761-2-chris@chris-wilson.co.uk
We correctly attach the exclusive fetch for the scratch object when
emitting a request that writes into it, but for completeness we should
also declared the write to i915_vma_move_to_active()
Reported-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
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/20180629133717.11761-1-chris@chris-wilson.co.uk
The only time we should start FBC is when we have waited a vblank
after the atomic update. We've already forced a vblank wait by doing
wait_for_flip_done before intel_post_plane_update(), so we don't need
to wait a second time before enabling.
Removing the worker simplifies the code and removes possible race
conditions, like happening in 103167.
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103167
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625163758.10871-2-maarten.lankhorst@linux.intel.com
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Back in commit 27af5eea54 ("drm/i915: Move execlists irq handler to a
bottom half"), we came to the conclusion that running our CSB processing
and ELSP submission from inside the irq handler was a bad idea. A really
bad idea as we could impose nearly 1s latency on other users of the
system, on average! Deferring our work to a tasklet allowed us to do the
processing with irqs enabled, reducing the impact to an average of about
50us.
We have since eradicated the use of forcewaked mmio from inside the CSB
processing and ELSP submission, bringing the impact down to around 5us
(on Kabylake); an order of magnitude better than our measurements 2
years ago on Broadwell and only about 2x worse on average than the
gem_syslatency on an unladen system.
In this iteration of the tasklet-vs-direct submission debate, we seek a
compromise where by we submit new requests immediately to the HW but
defer processing the CS interrupt onto a tasklet. We gain the advantage
of low-latency and ksoftirqd avoidance when waking up the HW, while
avoiding the system-wide starvation of our CS irq-storms.
Comparing the impact on the maximum latency observed (that is the time
stolen from an RT process) over a 120s interval, repeated several times
(using gem_syslatency, similar to RT's cyclictest) while the system is
fully laden with i915 nops, we see that direct submission an actually
improve the worse case.
Maximum latency in microseconds of a third party RT thread
(gem_syslatency -t 120 -f 2)
x Always using tasklets (a couple of >1000us outliers removed)
+ Only using tasklets from CS irq, direct submission of requests
+------------------------------------------------------------------------+
| + |
| + |
| + |
| + + |
| + + + |
| + + + + x x x |
| +++ + + + x x x x x x |
| +++ + ++ + + *x x x x x x |
| +++ + ++ + * *x x * x x x |
| + +++ + ++ * * +*xxx * x x xx |
| * +++ + ++++* *x+**xx+ * x x xxxx x |
| **x++++*++**+*x*x****x+ * +x xx xxxx x x |
|x* ******+***************++*+***xxxxxx* xx*x xxx + x+|
| |__________MA___________| |
| |______M__A________| |
+------------------------------------------------------------------------+
N Min Max Median Avg Stddev
x 118 91 186 124 125.28814 16.279137
+ 120 92 187 109 112.00833 13.458617
Difference at 95.0% confidence
-13.2798 +/- 3.79219
-10.5994% +/- 3.02677%
(Student's t, pooled s = 14.9237)
However the mean latency is adversely affected:
Mean latency in microseconds of a third party RT thread
(gem_syslatency -t 120 -f 1)
x Always using tasklets
+ Only using tasklets from CS irq, direct submission of requests
+------------------------------------------------------------------------+
| xxxxxx + ++ |
| xxxxxx + ++ |
| xxxxxx + +++ ++ |
| xxxxxxx +++++ ++ |
| xxxxxxx +++++ ++ |
| xxxxxxx +++++ +++ |
| xxxxxxx + ++++++++++ |
| xxxxxxxx ++ ++++++++++ |
| xxxxxxxx ++ ++++++++++ |
| xxxxxxxxxx +++++++++++++++ |
| xxxxxxxxxxx x +++++++++++++++ |
|x xxxxxxxxxxxxx x + + ++++++++++++++++++ +|
| |__A__| |
| |____A___| |
+------------------------------------------------------------------------+
N Min Max Median Avg Stddev
x 120 3.506 3.727 3.631 3.6321417 0.02773109
+ 120 3.834 4.149 4.039 4.0375167 0.041221676
Difference at 95.0% confidence
0.405375 +/- 0.00888913
11.1608% +/- 0.244735%
(Student's t, pooled s = 0.03513)
However, since the mean latency corresponds to the amount of irqsoff
processing we have to do for a CS interrupt, we only need to speed that
up to benefit not just system latency but our own throughput.
v2: Remember to defer submissions when under reset.
v4: Only use direct submission for new requests
v5: Be aware that with mixing direct tasklet evaluation and deferred
tasklets, we may end up idling before running the deferred tasklet.
v6: Remove the redudant likely() from tasklet_is_enabled(), restrict the
annotation to reset_in_progress().
v7: Take the full timeline.lock when enabling perf_pmu stats as the
tasklet is no longer a valid guard. A consequence is that the stats are
now only valid for engines also using the timeline.lock to process
state.
Testcase: igt/gem_exec_latency/*rthog*
References: 27af5eea54 ("drm/i915: Move execlists irq handler to a bottom half")
Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
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/20180628201211.13837-9-chris@chris-wilson.co.uk
Now that we use the CSB stored in the CPU friendly HWSP, we do not need
to track interrupts for when the mmio CSB registers are valid and can
just check where we read up to last from the cached HWSP. This means we
can forgo the atomic bit tracking from interrupt, and in the next patch
it means we can check the CSB at any time.
v2: Change the splitting inside reset_prepare, we only want to lose
testing the interrupt in this patch, the next patch requires the change
in locking
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/20180628201211.13837-8-chris@chris-wilson.co.uk
As we now never read back our current head position from the CSB
pointers register, and the HW itself doesn't use it to prevent
overwriting unread CSB entries, we do not need to keep updating the
register. As it turns out this register is not listed as being shadowed,
and so requires forcewake -- but we haven't been taking forcewake around
it so the writes has probably been regularly dropped. Fortuitously, we
only read the value after a reset where it did not matter, and zero was
the right answer (well, close enough).
Mika pointed out that this was how we used to do it (accidentally!)
before he fixed it in commit cc53699b25 ("drm/i915: Use masked write
for Context Status Buffer Pointer").
References: cc53699b25 ("drm/i915: Use masked write for Context Status Buffer Pointer")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628201211.13837-7-chris@chris-wilson.co.uk
On HW reset, the HW clears the write pointer (to 0). But since it also
writes its first CSB entry to slot 0, we need to reset the write pointer
back to the element before (so the first entry we read is 0).
This is required for the next patch, where we trust the CSB completely!
v2: Use _MASKED_FIELD
v3: Store the reset value, so that we differentiate between mmio/hwsp
transparently and without pretense.
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/20180628201211.13837-6-chris@chris-wilson.co.uk
Following the removal of the last workarounds, the only CSB mmio access
is for the old vGPU interface. The mmio registers presented by vGPU do
not require forcewake and can be treated as ordinary volatile memory,
i.e. they behave just like the HWSP access just at a different location.
We can reduce the CSB access to a set of read/write/buffer pointers and
treat the various paths identically and not worry about forcewake.
(Forcewake is nightmare for worstcase latency, and we want to process
this all with irqsoff -- no latency allowed!)
v2: Comments, comments, comments. Well, 2 bonus comments.
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/20180628201211.13837-5-chris@chris-wilson.co.uk
In the next patch, we will process the CSB events directly from the
submission path, rather than only after a CS interrupt. Hence, we will
no longer have the need for a loop until the has-interrupt bit is clear,
and in the meantime can remove that small optimisation.
v2: Tvrtko pointed out it was safer to unconditionally kick the tasklet
after each irq, when assuming that the tasklet is called for each irq.
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/20180628201211.13837-4-chris@chris-wilson.co.uk
