Re: [Intel-gfx] [PATCH 23/51] drm/i915/guc: Direct all breadcrumbs for a class to single breadcrumbs

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Thu, Jul 22, 2021 at 01:46:08PM +0100, Tvrtko Ursulin wrote:
> 
> On 16/07/2021 21:16, Matthew Brost wrote:
> > With GuC virtual engines the physical engine which a request executes
> > and completes on isn't known to the i915. Therefore we can't attach a
> > request to a physical engines breadcrumbs. To work around this we create
> > a single breadcrumbs per engine class when using GuC submission and
> > direct all physical engine interrupts to this breadcrumbs.
> > 
> > v2:
> >   (John H)
> >    - Rework header file structure so intel_engine_mask_t can be in
> >      intel_engine_types.h
> > 
> > Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
> > CC: John Harrison <John.C.Harrison@xxxxxxxxx>
> > ---
> >   drivers/gpu/drm/i915/gt/intel_breadcrumbs.c   | 41 +++++-------
> >   drivers/gpu/drm/i915/gt/intel_breadcrumbs.h   | 16 ++++-
> >   .../gpu/drm/i915/gt/intel_breadcrumbs_types.h |  7 ++
> >   drivers/gpu/drm/i915/gt/intel_engine.h        |  3 +
> >   drivers/gpu/drm/i915/gt/intel_engine_cs.c     | 28 +++++++-
> >   drivers/gpu/drm/i915/gt/intel_engine_types.h  |  2 +-
> >   .../drm/i915/gt/intel_execlists_submission.c  |  2 +-
> >   drivers/gpu/drm/i915/gt/mock_engine.c         |  4 +-
> >   .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 67 +++++++++++++++++--
> >   9 files changed, 133 insertions(+), 37 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
> > index 38cc42783dfb..2007dc6f6b99 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
> > @@ -15,28 +15,14 @@
> >   #include "intel_gt_pm.h"
> >   #include "intel_gt_requests.h"
> > -static bool irq_enable(struct intel_engine_cs *engine)
> > +static bool irq_enable(struct intel_breadcrumbs *b)
> >   {
> > -	if (!engine->irq_enable)
> > -		return false;
> > -
> > -	/* Caller disables interrupts */
> > -	spin_lock(&engine->gt->irq_lock);
> > -	engine->irq_enable(engine);
> > -	spin_unlock(&engine->gt->irq_lock);
> > -
> > -	return true;
> > +	return intel_engine_irq_enable(b->irq_engine);
> >   }
> > -static void irq_disable(struct intel_engine_cs *engine)
> > +static void irq_disable(struct intel_breadcrumbs *b)
> >   {
> > -	if (!engine->irq_disable)
> > -		return;
> > -
> > -	/* Caller disables interrupts */
> > -	spin_lock(&engine->gt->irq_lock);
> > -	engine->irq_disable(engine);
> > -	spin_unlock(&engine->gt->irq_lock);
> > +	intel_engine_irq_disable(b->irq_engine);
> >   }
> >   static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
> > @@ -57,7 +43,7 @@ static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
> >   	WRITE_ONCE(b->irq_armed, true);
> >   	/* Requests may have completed before we could enable the interrupt. */
> > -	if (!b->irq_enabled++ && irq_enable(b->irq_engine))
> > +	if (!b->irq_enabled++ && b->irq_enable(b))
> >   		irq_work_queue(&b->irq_work);
> >   }
> > @@ -76,7 +62,7 @@ static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
> >   {
> >   	GEM_BUG_ON(!b->irq_enabled);
> >   	if (!--b->irq_enabled)
> > -		irq_disable(b->irq_engine);
> > +		b->irq_disable(b);
> >   	WRITE_ONCE(b->irq_armed, false);
> >   	intel_gt_pm_put_async(b->irq_engine->gt);
> > @@ -281,7 +267,7 @@ intel_breadcrumbs_create(struct intel_engine_cs *irq_engine)
> >   	if (!b)
> >   		return NULL;
> > -	b->irq_engine = irq_engine;
> > +	kref_init(&b->ref);
> >   	spin_lock_init(&b->signalers_lock);
> >   	INIT_LIST_HEAD(&b->signalers);
> > @@ -290,6 +276,10 @@ intel_breadcrumbs_create(struct intel_engine_cs *irq_engine)
> >   	spin_lock_init(&b->irq_lock);
> >   	init_irq_work(&b->irq_work, signal_irq_work);
> > +	b->irq_engine = irq_engine;
> > +	b->irq_enable = irq_enable;
> > +	b->irq_disable = irq_disable;
> > +
> >   	return b;
> >   }
> > @@ -303,9 +293,9 @@ void intel_breadcrumbs_reset(struct intel_breadcrumbs *b)
> >   	spin_lock_irqsave(&b->irq_lock, flags);
> >   	if (b->irq_enabled)
> > -		irq_enable(b->irq_engine);
> > +		b->irq_enable(b);
> >   	else
> > -		irq_disable(b->irq_engine);
> > +		b->irq_disable(b);
> >   	spin_unlock_irqrestore(&b->irq_lock, flags);
> >   }
> > @@ -325,11 +315,14 @@ void __intel_breadcrumbs_park(struct intel_breadcrumbs *b)
> >   	}
> >   }
> > -void intel_breadcrumbs_free(struct intel_breadcrumbs *b)
> > +void intel_breadcrumbs_free(struct kref *kref)
> >   {
> > +	struct intel_breadcrumbs *b = container_of(kref, typeof(*b), ref);
> > +
> >   	irq_work_sync(&b->irq_work);
> >   	GEM_BUG_ON(!list_empty(&b->signalers));
> >   	GEM_BUG_ON(b->irq_armed);
> > +
> >   	kfree(b);
> >   }
> > diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h
> > index 3ce5ce270b04..be0d4f379a85 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h
> > +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h
> > @@ -9,7 +9,7 @@
> >   #include <linux/atomic.h>
> >   #include <linux/irq_work.h>
> > -#include "intel_engine_types.h"
> > +#include "intel_breadcrumbs_types.h"
> >   struct drm_printer;
> >   struct i915_request;
> > @@ -17,7 +17,7 @@ struct intel_breadcrumbs;
> >   struct intel_breadcrumbs *
> >   intel_breadcrumbs_create(struct intel_engine_cs *irq_engine);
> > -void intel_breadcrumbs_free(struct intel_breadcrumbs *b);
> > +void intel_breadcrumbs_free(struct kref *kref);
> >   void intel_breadcrumbs_reset(struct intel_breadcrumbs *b);
> >   void __intel_breadcrumbs_park(struct intel_breadcrumbs *b);
> > @@ -48,4 +48,16 @@ void i915_request_cancel_breadcrumb(struct i915_request *request);
> >   void intel_context_remove_breadcrumbs(struct intel_context *ce,
> >   				      struct intel_breadcrumbs *b);
> > +static inline struct intel_breadcrumbs *
> > +intel_breadcrumbs_get(struct intel_breadcrumbs *b)
> > +{
> > +	kref_get(&b->ref);
> > +	return b;
> > +}
> > +
> > +static inline void intel_breadcrumbs_put(struct intel_breadcrumbs *b)
> > +{
> > +	kref_put(&b->ref, intel_breadcrumbs_free);
> > +}
> > +
> >   #endif /* __INTEL_BREADCRUMBS__ */
> > diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
> > index 3a084ce8ff5e..72dfd3748c4c 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
> > +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
> > @@ -7,10 +7,13 @@
> >   #define __INTEL_BREADCRUMBS_TYPES__
> >   #include <linux/irq_work.h>
> > +#include <linux/kref.h>
> >   #include <linux/list.h>
> >   #include <linux/spinlock.h>
> >   #include <linux/types.h>
> > +#include "intel_engine_types.h"
> > +
> >   /*
> >    * Rather than have every client wait upon all user interrupts,
> >    * with the herd waking after every interrupt and each doing the
> > @@ -29,6 +32,7 @@
> >    * the overhead of waking that client is much preferred.
> >    */
> >   struct intel_breadcrumbs {
> > +	struct kref ref;
> >   	atomic_t active;
> >   	spinlock_t signalers_lock; /* protects the list of signalers */
> > @@ -42,7 +46,10 @@ struct intel_breadcrumbs {
> >   	bool irq_armed;
> >   	/* Not all breadcrumbs are attached to physical HW */
> > +	intel_engine_mask_t	engine_mask;
> >   	struct intel_engine_cs *irq_engine;
> > +	bool	(*irq_enable)(struct intel_breadcrumbs *b);
> > +	void	(*irq_disable)(struct intel_breadcrumbs *b);
> >   };
> >   #endif /* __INTEL_BREADCRUMBS_TYPES__ */
> > diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
> > index 9fec0aca5f4b..edbde6171bca 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_engine.h
> > +++ b/drivers/gpu/drm/i915/gt/intel_engine.h
> > @@ -212,6 +212,9 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
> >   void intel_engine_init_execlists(struct intel_engine_cs *engine);
> > +bool intel_engine_irq_enable(struct intel_engine_cs *engine);
> > +void intel_engine_irq_disable(struct intel_engine_cs *engine);
> > +
> >   static inline void __intel_engine_reset(struct intel_engine_cs *engine,
> >   					bool stalled)
> >   {
> > diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
> > index b7292d5cb7da..d95d666407f5 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
> > @@ -739,7 +739,7 @@ static int engine_setup_common(struct intel_engine_cs *engine)
> >   err_cmd_parser:
> >   	i915_sched_engine_put(engine->sched_engine);
> >   err_sched_engine:
> > -	intel_breadcrumbs_free(engine->breadcrumbs);
> > +	intel_breadcrumbs_put(engine->breadcrumbs);
> >   err_status:
> >   	cleanup_status_page(engine);
> >   	return err;
> > @@ -948,7 +948,7 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
> >   	GEM_BUG_ON(!list_empty(&engine->sched_engine->requests));
> >   	i915_sched_engine_put(engine->sched_engine);
> > -	intel_breadcrumbs_free(engine->breadcrumbs);
> > +	intel_breadcrumbs_put(engine->breadcrumbs);
> >   	intel_engine_fini_retire(engine);
> >   	intel_engine_cleanup_cmd_parser(engine);
> > @@ -1265,6 +1265,30 @@ bool intel_engines_are_idle(struct intel_gt *gt)
> >   	return true;
> >   }
> > +bool intel_engine_irq_enable(struct intel_engine_cs *engine)
> > +{
> > +	if (!engine->irq_enable)
> > +		return false;
> > +
> > +	/* Caller disables interrupts */
> > +	spin_lock(&engine->gt->irq_lock);
> > +	engine->irq_enable(engine);
> > +	spin_unlock(&engine->gt->irq_lock);
> > +
> > +	return true;
> > +}
> > +
> > +void intel_engine_irq_disable(struct intel_engine_cs *engine)
> > +{
> > +	if (!engine->irq_disable)
> > +		return;
> > +
> > +	/* Caller disables interrupts */
> > +	spin_lock(&engine->gt->irq_lock);
> > +	engine->irq_disable(engine);
> > +	spin_unlock(&engine->gt->irq_lock);
> > +}
> > +
> >   void intel_engines_reset_default_submission(struct intel_gt *gt)
> >   {
> >   	struct intel_engine_cs *engine;
> > diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
> > index 8ad304b2f2e4..03a81e8d87f4 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
> > +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
> > @@ -21,7 +21,6 @@
> >   #include "i915_pmu.h"
> >   #include "i915_priolist_types.h"
> >   #include "i915_selftest.h"
> > -#include "intel_breadcrumbs_types.h"
> >   #include "intel_sseu.h"
> >   #include "intel_timeline_types.h"
> >   #include "intel_uncore.h"
> > @@ -63,6 +62,7 @@ struct i915_sched_engine;
> >   struct intel_gt;
> >   struct intel_ring;
> >   struct intel_uncore;
> > +struct intel_breadcrumbs;
> >   typedef u8 intel_engine_mask_t;
> >   #define ALL_ENGINES ((intel_engine_mask_t)~0ul)
> > diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
> > index 920707e22eb0..abe48421fd7a 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
> > @@ -3407,7 +3407,7 @@ static void rcu_virtual_context_destroy(struct work_struct *wrk)
> >   	intel_context_fini(&ve->context);
> >   	if (ve->base.breadcrumbs)
> > -		intel_breadcrumbs_free(ve->base.breadcrumbs);
> > +		intel_breadcrumbs_put(ve->base.breadcrumbs);
> >   	if (ve->base.sched_engine)
> >   		i915_sched_engine_put(ve->base.sched_engine);
> >   	intel_engine_free_request_pool(&ve->base);
> > diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
> > index 9203c766db80..fc5a65ab1937 100644
> > --- a/drivers/gpu/drm/i915/gt/mock_engine.c
> > +++ b/drivers/gpu/drm/i915/gt/mock_engine.c
> > @@ -284,7 +284,7 @@ static void mock_engine_release(struct intel_engine_cs *engine)
> >   	GEM_BUG_ON(timer_pending(&mock->hw_delay));
> >   	i915_sched_engine_put(engine->sched_engine);
> > -	intel_breadcrumbs_free(engine->breadcrumbs);
> > +	intel_breadcrumbs_put(engine->breadcrumbs);
> >   	intel_context_unpin(engine->kernel_context);
> >   	intel_context_put(engine->kernel_context);
> > @@ -376,7 +376,7 @@ int mock_engine_init(struct intel_engine_cs *engine)
> >   	return 0;
> >   err_breadcrumbs:
> > -	intel_breadcrumbs_free(engine->breadcrumbs);
> > +	intel_breadcrumbs_put(engine->breadcrumbs);
> >   err_schedule:
> >   	i915_sched_engine_put(engine->sched_engine);
> >   	return -ENOMEM;
> > diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> > index 372e0dc7617a..9f28899ff17f 100644
> > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> > @@ -1076,6 +1076,9 @@ static void __guc_context_destroy(struct intel_context *ce)
> >   		struct guc_virtual_engine *ve =
> >   			container_of(ce, typeof(*ve), context);
> > +		if (ve->base.breadcrumbs)
> > +			intel_breadcrumbs_put(ve->base.breadcrumbs);
> > +
> >   		kfree(ve);
> >   	} else {
> >   		intel_context_free(ce);
> > @@ -1366,6 +1369,62 @@ static const struct intel_context_ops virtual_guc_context_ops = {
> >   	.get_sibling = guc_virtual_get_sibling,
> >   };
> > +static bool
> > +guc_irq_enable_breadcrumbs(struct intel_breadcrumbs *b)
> > +{
> > +	struct intel_engine_cs *sibling;
> > +	intel_engine_mask_t tmp, mask = b->engine_mask;
> > +	bool result = false;
> > +
> > +	for_each_engine_masked(sibling, b->irq_engine->gt, mask, tmp)
> > +		result |= intel_engine_irq_enable(sibling);
> > +
> > +	return result;
> > +}
> > +
> > +static void
> > +guc_irq_disable_breadcrumbs(struct intel_breadcrumbs *b)
> > +{
> > +	struct intel_engine_cs *sibling;
> > +	intel_engine_mask_t tmp, mask = b->engine_mask;
> > +
> > +	for_each_engine_masked(sibling, b->irq_engine->gt, mask, tmp)
> > +		intel_engine_irq_disable(sibling);
> > +}
> > +
> > +static void guc_init_breadcrumbs(struct intel_engine_cs *engine)
> > +{
> > +	int i;
> > +
> > +       /*
> > +        * In GuC submission mode we do not know which physical engine a request
> > +        * will be scheduled on, this creates a problem because the breadcrumb
> > +        * interrupt is per physical engine. To work around this we attach
> > +        * requests and direct all breadcrumb interrupts to the first instance
> > +        * of an engine per class. In addition all breadcrumb interrupts are
> > +	* enabled / disabled across an engine class in unison.
> > +        */
> > +	for (i = 0; i < MAX_ENGINE_INSTANCE; ++i) {
> > +		struct intel_engine_cs *sibling =
> > +			engine->gt->engine_class[engine->class][i];
> > +
> > +		if (sibling) {
> > +			if (engine->breadcrumbs != sibling->breadcrumbs) {
> > +				intel_breadcrumbs_put(engine->breadcrumbs);
> 
> So it's still only me that is bothered by the lazyness of the proposed init
> path?
> 

IMO this really isn't all that bad nor the first place I've seen
something like this done. In a quick 2 minute search of the i915 I found
that we do basically the exact same thing in
intel_engine_create_pinned_context for the ce->vm. I doubt this is the
only place in the driver that does something similar to this too.

> intel_engines_init
>   for_each_engine
>     engine_setup_common
>       engine->breadcrumbs = intel_breadcrumbs_create(engine);
>     intel_guc_submission_setup
>       intel_breadcrumbs_put(engine->breadcrumbs);
>       ...
> 
> In other words leaves the code to allocate N objects in common and then it
> frees all but one of them, overriding vfuncs in the remaining instance.
> 
> Why not pull out the setup out of common, when it is obviously not common
> any more?
> 

We can write down your concerns and revisit after this series merges. That
will give a clear side by side of what we have and what you purpose. It
should be easy at that point to make a decision and move on.

Matt

> Regards,
> 
> Tvrtko
> 
> > +				engine->breadcrumbs =
> > +					intel_breadcrumbs_get(sibling->breadcrumbs);
> > +			}
> > +			break;
> > +		}
> > +	}
> > +
> > +	if (engine->breadcrumbs) {
> > +		engine->breadcrumbs->engine_mask |= engine->mask;
> > +		engine->breadcrumbs->irq_enable = guc_irq_enable_breadcrumbs;
> > +		engine->breadcrumbs->irq_disable = guc_irq_disable_breadcrumbs;
> > +	}
> > +}
> > +
> >   static void sanitize_hwsp(struct intel_engine_cs *engine)
> >   {
> >   	struct intel_timeline *tl;
> > @@ -1589,6 +1648,7 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine)
> >   	guc_default_vfuncs(engine);
> >   	guc_default_irqs(engine);
> > +	guc_init_breadcrumbs(engine);
> >   	if (engine->class == RENDER_CLASS)
> >   		rcs_submission_override(engine);
> > @@ -1831,11 +1891,6 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count)
> >   	ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
> >   	ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
> >   	ve->base.saturated = ALL_ENGINES;
> > -	ve->base.breadcrumbs = intel_breadcrumbs_create(&ve->base);
> > -	if (!ve->base.breadcrumbs) {
> > -		kfree(ve);
> > -		return ERR_PTR(-ENOMEM);
> > -	}
> >   	snprintf(ve->base.name, sizeof(ve->base.name), "virtual");
> > @@ -1884,6 +1939,8 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count)
> >   				sibling->emit_fini_breadcrumb;
> >   			ve->base.emit_fini_breadcrumb_dw =
> >   				sibling->emit_fini_breadcrumb_dw;
> > +			ve->base.breadcrumbs =
> > +				intel_breadcrumbs_get(sibling->breadcrumbs);
> >   			ve->base.flags |= sibling->flags;
> > 



[Index of Archives]     [Linux DRI Users]     [Linux Intel Graphics]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [XFree86]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Linux Kernel]     [Linux SCSI]     [XFree86]
  Powered by Linux