Re: [Intel-gfx] [PATCH 06/27] drm/i915/guc: Take engine PM when a context is pinned with GuC submission

On 9/9/2021 17:41, Matthew Brost wrote:

On Thu, Sep 09, 2021 at 03:46:43PM -0700, John Harrison wrote:

...

On 8/20/2021 15:44, Matthew Brost wrote:

...

Taking a PM reference to prevent intel_gt_wait_for_idle from short circuiting while a scheduling of user context could be enabled.

As with earlier PM patch, needs more explanation of what the problem is and why it is only now a problem.

Same explaination, will add here.

...

...

v2: (Daniel Vetter) - Add might_lock annotations to pin / unpin function

Signed-off-by: Matthew Brost matthew.brost@intel.com

drivers/gpu/drm/i915/gt/intel_context.c | 3 ++ drivers/gpu/drm/i915/gt/intel_engine_pm.h | 15 ++++++++ drivers/gpu/drm/i915/gt/intel_gt_pm.h | 10 ++++++ .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 36 +++++++++++++++++-- drivers/gpu/drm/i915/intel_wakeref.h | 12 +++++++ 5 files changed, 73 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index c8595da64ad8..508cfe5770c0 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -240,6 +240,8 @@ int __intel_context_do_pin_ww(struct intel_context *ce, if (err) goto err_post_unpin;

• intel_engine_pm_might_get(ce->engine);
• if (unlikely(intel_context_is_closed(ce))) { err = -ENOENT; goto err_unlock;

@@ -313,6 +315,7 @@ void __intel_context_do_unpin(struct intel_context *ce, int sub) return; CE_TRACE(ce, "unpin\n");

• intel_engine_pm_might_put(ce->engine); ce->ops->unpin(ce); ce->ops->post_unpin(ce);

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h index 17a5028ea177..3fe2ae1bcc26 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h @@ -9,6 +9,7 @@ #include "i915_request.h" #include "intel_engine_types.h" #include "intel_wakeref.h" +#include "intel_gt_pm.h" static inline bool intel_engine_pm_is_awake(const struct intel_engine_cs *engine) @@ -31,6 +32,13 @@ static inline bool intel_engine_pm_get_if_awake(struct intel_engine_cs *engine) return intel_wakeref_get_if_active(&engine->wakeref); } +static inline void intel_engine_pm_might_get(struct intel_engine_cs *engine) +{

• if (!intel_engine_is_virtual(engine))

• intel_wakeref_might_get(&engine->wakeref);
  

Why doesn't this need to iterate through the physical engines of the virtual engine?

Yea, technically it should. This is just an annotation though to check if we do something horribly wrong in our code. If we use any physical engine in our stack this annotation should pop and we can fix it. I just don't see what making this 100% correct for virtual engines buys us. If you want I can fix this but thinking the more complex we make this annotation the less likely it just gets compiled out with lockdep off which is what we are aiming for.

But if the annotation is missing a fundamental lock then it is surely not actually going to do any good? Not sure if you need to iterate over all child engines + parent but it seems like you should be calling might_lock() on at least one engine's mutex to feed the lockdep annotation.

John.

Matt

...

John.

...

• intel_gt_pm_might_get(engine->gt);

+}

• static inline void intel_engine_pm_put(struct intel_engine_cs *engine) { intel_wakeref_put(&engine->wakeref);

@@ -52,6 +60,13 @@ static inline void intel_engine_pm_flush(struct intel_engine_cs *engine) intel_wakeref_unlock_wait(&engine->wakeref); } +static inline void intel_engine_pm_might_put(struct intel_engine_cs *engine) +{

• if (!intel_engine_is_virtual(engine))

• intel_wakeref_might_put(&engine->wakeref);
  

• intel_gt_pm_might_put(engine->gt);

+}

• static inline struct i915_request * intel_engine_create_kernel_request(struct intel_engine_cs *engine) {

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h index a17bf0d4592b..3c173033ce23 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h @@ -31,6 +31,11 @@ static inline bool intel_gt_pm_get_if_awake(struct intel_gt *gt) return intel_wakeref_get_if_active(&gt->wakeref); } +static inline void intel_gt_pm_might_get(struct intel_gt *gt) +{

• intel_wakeref_might_get(&gt->wakeref);

+}

• static inline void intel_gt_pm_put(struct intel_gt *gt) { intel_wakeref_put(&gt->wakeref);

@@ -41,6 +46,11 @@ static inline void intel_gt_pm_put_async(struct intel_gt *gt) intel_wakeref_put_async(&gt->wakeref); } +static inline void intel_gt_pm_might_put(struct intel_gt *gt) +{

• intel_wakeref_might_put(&gt->wakeref);

+}

• #define with_intel_gt_pm(gt, tmp) \ for (tmp = 1, intel_gt_pm_get(gt); tmp; \ intel_gt_pm_put(gt), tmp = 0)

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 dbf919801de2..e0eed70f9b92 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1550,7 +1550,12 @@ static int guc_context_pre_pin(struct intel_context *ce, static int guc_context_pin(struct intel_context *ce, void *vaddr) {

• return __guc_context_pin(ce, ce->engine, vaddr);

• int ret = __guc_context_pin(ce, ce->engine, vaddr);
• if (likely(!ret && !intel_context_is_barrier(ce)))

• intel_engine_pm_get(ce->engine);
  

• return ret; } static void guc_context_unpin(struct intel_context *ce)

@@ -1559,6 +1564,9 @@ static void guc_context_unpin(struct intel_context *ce) unpin_guc_id(guc, ce); lrc_unpin(ce);

• if (likely(!intel_context_is_barrier(ce)))

• intel_engine_pm_put_async(ce->engine);
  

  } static void guc_context_post_unpin(struct intel_context *ce)

@@ -2328,8 +2336,30 @@ static int guc_virtual_context_pre_pin(struct intel_context *ce, static int guc_virtual_context_pin(struct intel_context *ce, void *vaddr) { struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0);

• int ret = __guc_context_pin(ce, engine, vaddr);
• intel_engine_mask_t tmp, mask = ce->engine->mask;
• if (likely(!ret))

• for_each_engine_masked(engine, ce->engine->gt, mask, tmp)
  

• 	intel_engine_pm_get(engine);
  

• return __guc_context_pin(ce, engine, vaddr);

• return ret;

+}

+static void guc_virtual_context_unpin(struct intel_context *ce) +{

• intel_engine_mask_t tmp, mask = ce->engine->mask;
• struct intel_engine_cs *engine;
• struct intel_guc *guc = ce_to_guc(ce);
• GEM_BUG_ON(context_enabled(ce));
• GEM_BUG_ON(intel_context_is_barrier(ce));
• unpin_guc_id(guc, ce);
• lrc_unpin(ce);
• for_each_engine_masked(engine, ce->engine->gt, mask, tmp)

• intel_engine_pm_put_async(engine);
  

  } static void guc_virtual_context_enter(struct intel_context *ce)

@@ -2366,7 +2396,7 @@ static const struct intel_context_ops virtual_guc_context_ops = { .pre_pin = guc_virtual_context_pre_pin, .pin = guc_virtual_context_pin,

• .unpin = guc_context_unpin,

• .unpin = guc_virtual_context_unpin, .post_unpin = guc_context_post_unpin, .ban = guc_context_ban,

diff --git a/drivers/gpu/drm/i915/intel_wakeref.h b/drivers/gpu/drm/i915/intel_wakeref.h index ef7e6a698e8a..dd530ae028e0 100644 --- a/drivers/gpu/drm/i915/intel_wakeref.h +++ b/drivers/gpu/drm/i915/intel_wakeref.h @@ -124,6 +124,12 @@ enum { __INTEL_WAKEREF_PUT_LAST_BIT__ }; +static inline void +intel_wakeref_might_get(struct intel_wakeref *wf) +{

• might_lock(&wf->mutex);

+}

• /**
  • intel_wakeref_put_flags: Release the wakeref
  • @wf: the wakeref

@@ -171,6 +177,12 @@ intel_wakeref_put_delay(struct intel_wakeref *wf, unsigned long delay) FIELD_PREP(INTEL_WAKEREF_PUT_DELAY, delay)); } +static inline void +intel_wakeref_might_put(struct intel_wakeref *wf) +{

• might_lock(&wf->mutex);

+}

• /**
  • intel_wakeref_lock: Lock the wakeref (mutex)
  • @wf: the wakeref