- 14 Apr, 2020 1 commit
-
-
Kai Vehmanen authored
Replace the TGL/ICL specific platform checks with a more generic check using INTEL_GEN(). Fixes bug with broken audio after S3 resume on JSL platforms. An initial version of state save and restore of AUD_FREQ_CNTRL register was added for subset of platforms in commit 87c16945 ("drm/i915: save AUD_FREQ_CNTRL state at audio domain suspend"). The state save has proven to work well and it is needed in newer platforms, so needs to be extended. Although the logic is not in practise needed on GEN9/10 systems, follow the hardware specification and apply state and restore on all gen9+ platforms. Bspec: 49281 Link: https://github.com/thesofproject/linux/issues/1719Signed-off-by:
Kai Vehmanen <kai.vehmanen@linux.intel.com> Signed-off-by:
Ville Syrjälä <ville.syrjala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200330144421.11632-1-kai.vehmanen@linux.intel.comReviewed-by:
Matt Roper <matthew.d.roper@intel.com>
-
- 10 Apr, 2020 2 commits
-
-
Chris Wilson authored
After changing the timing between GTT updates and execution on the GPU, we started seeing sporadic failures on Ironlake. These were narrowed down to being an insufficiently strong enough barrier/delay after updating the GTT and scheduling execution on the GPU. By forcing the uncached read, and adding the missing barrier for the singular insert_page (relocation paths), the sporadic failures go away. Fixes: 983d308c ("agp/intel: Serialise after GTT updates") Fixes: 3497971a ("agp/intel: Flush chipset writes after updating a single PTE") Signed-off-by:
Chris Wilson <chris@chris-wilson.co.uk> Acked-by:
Andi Shyti <andi.shyti@intel.com> Cc: stable@vger.kernel.org # v4.0+ Link: https://patchwork.freedesktop.org/patch/msgid/20200410083535.25464-1-chris@chris-wilson.co.uk
-
Chris Wilson authored
With timeslice yielding on a semaphore, we may complete timeslices much faster than we were expecting and already have yielded the stuck request. Before complaining that timeslicing is not enabled, check that we haven't already applied the switch. Signed-off-by:
-
- 09 Apr, 2020 1 commit
-
-
Colin Ian King authored
The variable err is being initialized with a value that is never read and it is being updated later with a new value. The initialization is redundant and can be removed. Addresses-Coverity: ("Unused value") Signed-off-by:Colin Ian King <colin.king@canonical.com> Reviewed-by:
-
- 08 Apr, 2020 22 commits
-
-
Matthew Auld authored
In an address space there can be sprinkling of I915_COLOR_UNEVICTABLE nodes, which lack a parent vma. For platforms with cache coloring we might be very unlucky and abut with such a node thinking we can simply unbind the vma. Signed-off-by:
Matthew Auld <matthew.auld@intel.com> Reviewed-by:
-
Chris Wilson authored
Since we are peeking into the batch object of the request, it is beholden on us to hold a reference to it. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1634Signed-off-by:
Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200408091723.28937-1-chris@chris-wilson.co.uk
-
Chris Wilson authored
We control b->irq_enabled inside the b->irq_lock, but we check before entering the spinlock whether or not the interrupt is currently unmasked. [ 1511.735208] BUG: KCSAN: data-race in __intel_breadcrumbs_disarm_irq [i915] / intel_engine_disarm_breadcrumbs [i915] [ 1511.735231] [ 1511.735242] write to 0xffff8881f75fc214 of 1 bytes by interrupt on cpu 2: [ 1511.735440] __intel_breadcrumbs_disarm_irq+0x4b/0x160 [i915] [ 1511.735635] signal_irq_work+0x337/0x710 [i915] [ 1511.735652] irq_work_run_list+0xd7/0x110 [ 1511.735666] irq_work_run+0x1d/0x50 [ 1511.735681] smp_irq_work_interrupt+0x21/0x30 [ 1511.735701] irq_work_interrupt+0xf/0x20 [ 1511.735722] __do_softirq+0x6f/0x206 [ 1511.735736] irq_exit+0xcd/0xe0 [ 1511.735756] do_IRQ+0x44/0xc0 [ 1511.735773] ret_from_intr+0x0/0x1c [ 1511.735787] schedule+0x0/0xb0 [ 1511.735803] worker_thread+0x194/0x670 [ 1511.735823] kthread+0x19a/0x1e0 [ 1511.735837] ret_from_fork+0x1f/0x30 [ 1511.735848] [ 1511.735867] read to 0xffff8881f75fc214 of 1 bytes by task 432 on cpu 1: [ 1511.736068] intel_engine_disarm_breadcrumbs+0x22/0x80 [i915] [ 1511.736263] __engine_park+0x107/0x5d0 [i915] [ 1511.736453] ____intel_wakeref_put_last+0x44/0x90 [i915] [ 1511.736648] __intel_wakeref_put_last+0x5a/0x70 [i915] [ 1511.736842] intel_context_exit_engine+0xf2/0x100 [i915] [ 1511.737044] i915_request_retire+0x6b2/0x770 [i915] [ 1511.737244] retire_requests+0x7a/0xd0 [i915] [ 1511.737438] intel_gt_retire_requests_timeout+0x3a7/0x6f0 [i915] [ 1511.737633] i915_drop_caches_set+0x1e7/0x260 [i915] [ 1511.737650] simple_attr_write+0xfa/0x110 [ 1511.737665] full_proxy_write+0x94/0xc0 [ 1511.737679] __vfs_write+0x4b/0x90 [ 1511.737697] vfs_write+0xfc/0x280 [ 1511.737718] ksys_write+0x78/0x100 [ 1511.737732] __x64_sys_write+0x44/0x60 [ 1511.737751] do_syscall_64+0x6e/0x2c0 [ 1511.737769] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Signed-off-by:
-
Chris Wilson authored
The intel_ring.head is updated as the requests are retired, but is sampled at any time as we submit requests. Furthermore, it tracks RING_HEAD which is inherently asynchronous. [ 148.630314] BUG: KCSAN: data-race in execlists_dequeue [i915] / i915_request_retire [i915] [ 148.630349] [ 148.630374] write to 0xffff8881f4e28ddc of 4 bytes by task 90 on cpu 2: [ 148.630752] i915_request_retire+0xed/0x770 [i915] [ 148.631123] retire_requests+0x7a/0xd0 [i915] [ 148.631491] engine_retire+0xa6/0xe0 [i915] [ 148.631523] process_one_work+0x3af/0x640 [ 148.631552] worker_thread+0x80/0x670 [ 148.631581] kthread+0x19a/0x1e0 [ 148.631609] ret_from_fork+0x1f/0x30 [ 148.631629] [ 148.631652] read to 0xffff8881f4e28ddc of 4 bytes by task 14288 on cpu 3: [ 148.632019] execlists_dequeue+0x1300/0x1680 [i915] [ 148.632384] __execlists_submission_tasklet+0x48/0x60 [i915] [ 148.632770] execlists_submit_request+0x38e/0x3c0 [i915] [ 148.633146] submit_notify+0x8f/0xc0 [i915] [ 148.633512] __i915_sw_fence_complete+0x5d/0x3e0 [i915] [ 148.633875] i915_sw_fence_complete+0x58/0x80 [i915] [ 148.634238] i915_sw_fence_commit+0x16/0x20 [i915] [ 148.634613] __i915_request_queue+0x60/0x70 [i915] [ 148.634985] i915_gem_do_execbuffer+0x2de0/0x42b0 [i915] [ 148.635366] i915_gem_execbuffer2_ioctl+0x2ab/0x580 [i915] [ 148.635400] drm_ioctl_kernel+0xe9/0x130 [ 148.635429] drm_ioctl+0x27d/0x45e [ 148.635456] ksys_ioctl+0x89/0xb0 [ 148.635482] __x64_sys_ioctl+0x42/0x60 [ 148.635510] do_syscall_64+0x6e/0x2c0 [ 148.635542] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 645.071436] BUG: KCSAN: data-race in gen8_emit_fini_breadcrumb [i915] / i915_request_retire [i915] [ 645.071456] [ 645.071467] write to 0xffff8881efe403dc of 4 bytes by task 14668 on cpu 3: [ 645.071647] i915_request_retire+0xed/0x770 [i915] [ 645.071824] i915_request_create+0x6c/0x160 [i915] [ 645.072000] i915_gem_do_execbuffer+0x206d/0x42b0 [i915] [ 645.072177] i915_gem_execbuffer2_ioctl+0x2ab/0x580 [i915] [ 645.072194] drm_ioctl_kernel+0xe9/0x130 [ 645.072208] drm_ioctl+0x27d/0x45e [ 645.072222] ksys_ioctl+0x89/0xb0 [ 645.072235] __x64_sys_ioctl+0x42/0x60 [ 645.072248] do_syscall_64+0x6e/0x2c0 [ 645.072263] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 645.072275] [ 645.072285] read to 0xffff8881efe403dc of 4 bytes by interrupt on cpu 2: [ 645.072458] gen8_emit_fini_breadcrumb+0x158/0x300 [i915] [ 645.072636] __i915_request_submit+0x204/0x430 [i915] [ 645.072809] execlists_dequeue+0x8e1/0x1680 [i915] [ 645.072982] __execlists_submission_tasklet+0x48/0x60 [i915] [ 645.073154] execlists_submit_request+0x38e/0x3c0 [i915] [ 645.073330] submit_notify+0x8f/0xc0 [i915] [ 645.073499] __i915_sw_fence_complete+0x5d/0x3e0 [i915] [ 645.073668] i915_sw_fence_wake+0xc2/0x130 [i915] [ 645.073836] __i915_sw_fence_complete+0x2cf/0x3e0 [i915] [ 645.074006] i915_sw_fence_complete+0x58/0x80 [i915] [ 645.074175] dma_i915_sw_fence_wake+0x3e/0x80 [i915] [ 645.074344] signal_irq_work+0x62f/0x710 [i915] [ 645.074360] irq_work_run_list+0xd7/0x110 [ 645.074373] irq_work_run+0x1d/0x50 [ 645.074386] smp_irq_work_interrupt+0x21/0x30 [ 645.074400] irq_work_interrupt+0xf/0x20 [ 645.074414] _raw_spin_unlock_irqrestore+0x34/0x40 [ 645.074585] execlists_submission_tasklet+0xde/0x170 [i915] [ 645.074602] tasklet_action_common.isra.0+0x42/0x90 [ 645.074617] __do_softirq+0xc8/0x206 [ 645.074629] irq_exit+0xcd/0xe0 [ 645.074642] do_IRQ+0x44/0xc0 [ 645.074654] ret_from_intr+0x0/0x1c [ 645.074667] finish_task_switch+0x73/0x230 [ 645.074679] __schedule+0x1c5/0x4c0 [ 645.074691] schedule+0x45/0xb0 [ 645.074704] worker_thread+0x194/0x670 [ 645.074716] kthread+0x19a/0x1e0 [ 645.074729] ret_from_fork+0x1f/0x30 Signed-off-by:
-
Jani Nikula authored
Prefer struct drm_device based logging over struct device based logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
Wambui Karuga <wambui.karugax@gmail.com> Signed-off-by:
Jani Nikula <jani.nikula@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200402114819.17232-17-jani.nikula@intel.com
-
Jani Nikula authored
Prefer struct drm_device based logging over struct device based logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
-
Jani Nikula authored
Prefer struct drm_device based logging over struct device based logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
-
Jani Nikula authored
Prefer struct drm_device based logging over struct device based logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
-
Jani Nikula authored
Prefer struct drm_device based logging over struct device based logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
-
Jani Nikula authored
Prefer struct drm_device based logging over struct device based logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
-
Jani Nikula authored
Prefer struct drm_device based logging over struct device based logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
-
Jani Nikula authored
Prefer struct drm_device based logging over struct device based logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
-
Jani Nikula authored
Convert all the pr_* logging macros to the struct drm_device based macros to provide device specific logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
-
Jani Nikula authored
Convert all the DRM_* logging macros to the struct drm_device based macros to provide device specific logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
-
Jani Nikula authored
Convert all the DRM_* logging macros to the struct drm_device based macros to provide device specific logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
-
Jani Nikula authored
Convert all the DRM_* logging macros to the struct drm_device based macros to provide device specific logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
-
Jani Nikula authored
Convert all the DRM_* logging macros to the struct drm_device based macros to provide device specific logging. No functional changes. Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by:
-
Jani Nikula authored
Convert all the DRM_* logging macros to the struct drm_device based macros to provide device specific logging. No functional changes. Generated using the following semantic patch, originally written by Wambui Karuga <wambui.karugax@gmail.com>, with manual fixups on top: @@ identifier fn, T; @@ fn(...,struct drm_i915_private *T,...) { <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_NOTE( +drm_notice(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } @@ identifier fn, T; @@ fn(...) { ... struct drm_i915_private *T = ...; <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_NOTE( +drm_notice(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by: -
Jani Nikula authored
Convert all the DRM_* logging macros to the struct drm_device based macros to provide device specific logging. No functional changes. Generated using the following semantic patch, originally written by Wambui Karuga <wambui.karugax@gmail.com>, with manual fixups on top: @@ identifier fn, T; @@ fn(...,struct drm_i915_private *T,...) { <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_NOTE( +drm_notice(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } @@ identifier fn, T; @@ fn(...) { ... struct drm_i915_private *T = ...; <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_NOTE( +drm_notice(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by: -
Jani Nikula authored
Convert all the DRM_* logging macros to the struct drm_device based macros to provide device specific logging. No functional changes. Generated using the following semantic patch, originally written by Wambui Karuga <wambui.karugax@gmail.com>, with manual fixups on top: @@ identifier fn, T; @@ fn(...,struct drm_i915_private *T,...) { <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_NOTE( +drm_notice(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } @@ identifier fn, T; @@ fn(...) { ... struct drm_i915_private *T = ...; <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_NOTE( +drm_notice(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by: -
Jani Nikula authored
Convert all the DRM_* logging macros to the struct drm_device based macros to provide device specific logging. No functional changes. Generated using the following semantic patch, originally written by Wambui Karuga <wambui.karugax@gmail.com>, with manual fixups on top: @@ identifier fn, T; @@ fn(...,struct drm_i915_private *T,...) { <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_NOTE( +drm_notice(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } @@ identifier fn, T; @@ fn(...) { ... struct drm_i915_private *T = ...; <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_NOTE( +drm_notice(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } Cc: Wambui Karuga <wambui.karugax@gmail.com> Reviewed-by: -
Chris Wilson authored
Since the semaphore interrupt may cause us to yield the timeslice immediately, we may cancel the timer before we notice the submission is complete. The assertion is no longer valid due to the race with the interrupt. Signed-off-by:
Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200407222625.15542-1-chris@chris-wilson.co.uk
-
- 07 Apr, 2020 2 commits
-
-
Chris Wilson authored
If we find ourselves waiting on a MI_SEMAPHORE_WAIT, either within the user batch or in our own preamble, the engine raises a GT_WAIT_ON_SEMAPHORE interrupt. We can unmask that interrupt and so respond to a semaphore wait by yielding the timeslice, if we have another context to yield to! The only real complication is that the interrupt is only generated for the start of the semaphore wait, and is asynchronous to our process_csb() -- that is, we may not have registered the timeslice before we see the interrupt. To ensure we don't miss a potential semaphore blocking forward progress (e.g. selftests/live_timeslice_preempt) we mark the interrupt and apply it to the next timeslice regardless of whether it was active at the time. v2: We use semaphores in preempt-to-busy, within the timeslicing implementation itself! Ergo, when we do insert a preemption due to an expired timeslice, the new context may start with the missed semaphore flagged by the retired context and be yielded, ad infinitum. To avoid this, read the context id at the time of the semaphore interrupt and only yield if that context is still active. Fixes: 8ee36e04 ("drm/i915/execlists: Minimalistic timeslicing") Signed-off-by:
-
Chris Wilson authored
Tidy the code by casting remain to unsigned long once for the duration of eb_relocate_vma() Signed-off-by:
-
- 06 Apr, 2020 7 commits
-
-
Chris Wilson authored
If we want to percolate information back from the HW, up through the GEM context, we need to wait until the intel_context is scheduled out for the last time. This is handled by the retirement of the intel_context's barrier, i.e. by listening to the pulse after the notional unpin. So wait until the intel_context is finally retired before releasing the engine, so that we can inspect the final context state and pass it on. Signed-off-by:
-
Chris Wilson authored
Allow the caller to also wait upon the barriers stored in i915_active. v2: Hook up i915_request_await_active(I915_ACTIVE_AWAIT_BARRIER) as well for completeness, and avoid the lazy GEM_BUG_ON()! v3: Pull flush_lazy_signals() under the active-ref protection as it too walks the rbtree and so we must be careful that we do not free it as we iterate. Signed-off-by:
-
Chris Wilson authored
Later use will require asynchronous waits on the active timelines, but will not utilize an async wait on the exclusive channel. Make the await on the exclusive fence explicit in the selection flags. Signed-off-by:
-
Chris Wilson authored
If we set the debug flag to force ourselves not to relocate via the gpu, do not relocate via the gpu. Signed-off-by:
-
Chris Wilson authored
__i915_gem_object_flush_map() takes a byte range, so feed it the written bytes and do not mistake the u32 index as bytes! Fixes: a679f58d ("drm/i915: Flush pages on acquisition") Signed-off-by:
Matthew Auld <matthew.william.auld@gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200406114821.10949-1-chris@chris-wilson.co.uk
-
Imre Deak authored
On TypeC ports if a sink deasserts/reasserts its HPD signal, generating a hotplug interrupt without the sink getting unplugged/replugged from the connector, there can be an up to 3 seconds delay until the AUX channel gets functional. To avoid detection failures this delay causes retry the detection for 5 seconds. I noticed this on ICL/TGL RVPs and a DELL XPS 13 7390 ICL laptop. References: https://gitlab.freedesktop.org/drm/intel/issues/1067Signed-off-by:
Imre Deak <imre.deak@intel.com> Reviewed-by:
José Roberto de Souza <jose.souza@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200330095425.29113-2-imre.deak@intel.com
-
Imre Deak authored
On TypeC connectors we need to retry the detection after hotplug events for a longer time, so add a retry counter to support this. The next patch will add detection retries on TypeC ports needing this. Signed-off-by:
-
- 03 Apr, 2020 5 commits
-
-
Chris Wilson authored
While extremely unlikely to be populated, we could capture a request on the virtual engine which we should free along with the virtual engine. Fixes: 43acd651 ("drm/i915: Keep a per-engine request pool") Signed-off-by:
Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200403203303.10903-1-chris@chris-wilson.co.uk
-
Chris Wilson authored
If we submit, we do not start timeslicing until we process the CS event that marks the start of the context running on HW. So in the selftest, be sure to wait until we have processed the pending events before asserting that timeslicing has begun. Signed-off-by:
Michael J. Ruhl <michael.j.ruhl@intel.com> Reviewed-by:
-
Chris Wilson authored
Do an early rejection of a i915_vma_unbind() attempt if the i915_vma is currently pinned, without waiting to see if the inflight operations may unpin it. We see this problem with the shrinker trying to unbind the active vma from inside its bind worker: <6> [472.618968] Workqueue: events_unbound fence_work [i915] <4> [472.618970] Call Trace: <4> [472.618974] ? __schedule+0x2e5/0x810 <4> [472.618978] schedule+0x37/0xe0 <4> [472.618982] schedule_preempt_disabled+0xf/0x20 <4> [472.618984] __mutex_lock+0x281/0x9c0 <4> [472.618987] ? mark_held_locks+0x49/0x70 <4> [472.618989] ? _raw_spin_unlock_irqrestore+0x47/0x60 <4> [472.619038] ? i915_vma_unbind+0xae/0x110 [i915] <4> [472.619084] ? i915_vma_unbind+0xae/0x110 [i915] <4> [472.619122] i915_vma_unbind+0xae/0x110 [i915] <4> [472.619165] i915_gem_object_unbind+0x1dc/0x400 [i915] <4> [472.619208] i915_gem_shrink+0x328/0x660 [i915] <4> [472.619250] ? i915_gem_shrink_all+0x38/0x60 [i915] <4> [472.619282] i915_gem_shrink_all+0x38/0x60 [i915] <4> [472.619325] vm_alloc_page.constprop.25+0x1aa/0x240 [i915] <4> [472.619330] ? rcu_read_lock_sched_held+0x4d/0x80 <4> [472.619363] ? __alloc_pd+0xb/0x30 [i915] <4> [472.619366] ? module_assert_mutex_or_preempt+0xf/0x30 <4> [472.619368] ? __module_address+0x23/0xe0 <4> [472.619371] ? is_module_address+0x26/0x40 <4> [472.619374] ? static_obj+0x34/0x50 <4> [472.619376] ? lockdep_init_map+0x4d/0x1e0 <4> [472.619407] setup_page_dma+0xd/0x90 [i915] <4> [472.619437] alloc_pd+0x29/0x50 [i915] <4> [472.619470] __gen8_ppgtt_alloc+0x443/0x6b0 [i915] <4> [472.619503] gen8_ppgtt_alloc+0xd7/0x300 [i915] <4> [472.619535] ppgtt_bind_vma+0x2a/0xe0 [i915] <4> [472.619577] __vma_bind+0x26/0x40 [i915] <4> [472.619611] fence_work+0x1c/0x90 [i915] <4> [472.619617] process_one_work+0x26a/0x620 Fixes: 2850748e ("drm/i915: Pull i915_vma_pin under the vm->mutex") Signed-off-by:
-
Ashutosh Dixit authored
It is wrong to block the user thread in the next poll when OA data is already available which could not fit in the user buffer provided in the previous read. In several cases the exact user buffer size is not known. Blocking user space in poll can lead to data loss when the buffer size used is smaller than the available data. This change fixes this issue and allows user space to read all OA data even when using a buffer size smaller than the available data using multiple non-blocking reads rather than staying blocked in poll till the next timer interrupt. v2: Fix ret value for blocking reads (Umesh) v3: Mistake during patch send (Ashutosh) v4: Remove -EAGAIN from comment (Umesh) v5: Improve condition for clearing pollin and return (Lionel) v6: Improve blocking read loop and other cleanups (Lionel) v7: Added Cc stable Testcase: igt/perf/polling-small-buf Reviewed-by:
Lionel Landwerlin <lionel.g.landwerlin@intel.com> Signed-off-by:
Ashutosh Dixit <ashutosh.dixit@intel.com> Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com> Cc: <stable@vger.kernel.org> Signed-off-by:
-
Chris Wilson authored
Make sure we revoke the user's mmaps of this vma to force them to take a pagefault *before* we remove the associated aperture detiling register. Fixes: 0d86ee35 ("drm/i915/gt: Make fence revocation unequivocal") Signed-off-by:
-
