Message ID | 20210526064237.77853-7-matthew.brost@intel.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Series | Non-interface changing GuC CTBs updates | expand |
On Thu, May 27, 2021 at 10:17:20AM -0700, John Harrison wrote: > On 5/25/2021 23:42, Matthew Brost wrote: > > Drop the variable guc->interrupts.enabled as this variable is just > > leading to bugs creeping into the code. > > > > e.g. A full GPU reset disables the GuC interrupts but forgot to clear > > guc->interrupts.enabled, guc->interrupts.enabled being true suppresses > > interrupts from getting re-enabled and now we are broken. > > > > It is harmless to enable interrupt while already enabled so let's just > > delete this variable to avoid bugs like this going forward. > Is it worth leaving the enabled flag in place but only using it to trip a > WARN to catch such cases in a less catastrophic manner? Or are there valid > reasons for calling enable when already enabled? > I don't think so as mentioned above a reset disables these interrupts and if we didn't clear this field the WARN_ON would be triggered making CI unhappy. Yes, the bug would less catastrophic but we'd still have to waste time and energy chasing it. Matt > Either way, it seems like a plausible change and CI is happy with it, so: > Reviewed-by: John Harrison <John.C.Harrison@Intel.com> > > John. > > > Signed-off-by: Matthew Brost <matthew.brost@intel.com> > > --- > > drivers/gpu/drm/i915/gt/uc/intel_guc.c | 27 +++++++++----------------- > > drivers/gpu/drm/i915/gt/uc/intel_guc.h | 1 - > > 2 files changed, 9 insertions(+), 19 deletions(-) > > > > diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c > > index ab2c8fe8cdfa..18da9ed15728 100644 > > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c > > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c > > @@ -96,12 +96,9 @@ static void gen9_enable_guc_interrupts(struct intel_guc *guc) > > assert_rpm_wakelock_held(>->i915->runtime_pm); > > spin_lock_irq(>->irq_lock); > > - if (!guc->interrupts.enabled) { > > - WARN_ON_ONCE(intel_uncore_read(gt->uncore, GEN8_GT_IIR(2)) & > > - gt->pm_guc_events); > > - guc->interrupts.enabled = true; > > - gen6_gt_pm_enable_irq(gt, gt->pm_guc_events); > > - } > > + WARN_ON_ONCE(intel_uncore_read(gt->uncore, GEN8_GT_IIR(2)) & > > + gt->pm_guc_events); > > + gen6_gt_pm_enable_irq(gt, gt->pm_guc_events); > > spin_unlock_irq(>->irq_lock); > > } > > @@ -112,7 +109,6 @@ static void gen9_disable_guc_interrupts(struct intel_guc *guc) > > assert_rpm_wakelock_held(>->i915->runtime_pm); > > spin_lock_irq(>->irq_lock); > > - guc->interrupts.enabled = false; > > gen6_gt_pm_disable_irq(gt, gt->pm_guc_events); > > @@ -134,18 +130,14 @@ static void gen11_reset_guc_interrupts(struct intel_guc *guc) > > static void gen11_enable_guc_interrupts(struct intel_guc *guc) > > { > > struct intel_gt *gt = guc_to_gt(guc); > > + u32 events = REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST); > > spin_lock_irq(>->irq_lock); > > - if (!guc->interrupts.enabled) { > > - u32 events = REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST); > > - > > - WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_GUC)); > > - intel_uncore_write(gt->uncore, > > - GEN11_GUC_SG_INTR_ENABLE, events); > > - intel_uncore_write(gt->uncore, > > - GEN11_GUC_SG_INTR_MASK, ~events); > > - guc->interrupts.enabled = true; > > - } > > + WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_GUC)); > > + intel_uncore_write(gt->uncore, > > + GEN11_GUC_SG_INTR_ENABLE, events); > > + intel_uncore_write(gt->uncore, > > + GEN11_GUC_SG_INTR_MASK, ~events); > > spin_unlock_irq(>->irq_lock); > > } > > @@ -154,7 +146,6 @@ static void gen11_disable_guc_interrupts(struct intel_guc *guc) > > struct intel_gt *gt = guc_to_gt(guc); > > spin_lock_irq(>->irq_lock); > > - guc->interrupts.enabled = false; > > intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_MASK, ~0); > > intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_ENABLE, 0); > > diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h > > index c20f3839de12..4abc59f6f3cd 100644 > > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h > > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h > > @@ -33,7 +33,6 @@ struct intel_guc { > > unsigned int msg_enabled_mask; > > struct { > > - bool enabled; > > void (*reset)(struct intel_guc *guc); > > void (*enable)(struct intel_guc *guc); > > void (*disable)(struct intel_guc *guc); >
On 5/25/2021 23:42, Matthew Brost wrote: > Drop the variable guc->interrupts.enabled as this variable is just > leading to bugs creeping into the code. > > e.g. A full GPU reset disables the GuC interrupts but forgot to clear > guc->interrupts.enabled, guc->interrupts.enabled being true suppresses > interrupts from getting re-enabled and now we are broken. > > It is harmless to enable interrupt while already enabled so let's just > delete this variable to avoid bugs like this going forward. Is it worth leaving the enabled flag in place but only using it to trip a WARN to catch such cases in a less catastrophic manner? Or are there valid reasons for calling enable when already enabled? Either way, it seems like a plausible change and CI is happy with it, so: Reviewed-by: John Harrison <John.C.Harrison@Intel.com> John. > Signed-off-by: Matthew Brost <matthew.brost@intel.com> > --- > drivers/gpu/drm/i915/gt/uc/intel_guc.c | 27 +++++++++----------------- > drivers/gpu/drm/i915/gt/uc/intel_guc.h | 1 - > 2 files changed, 9 insertions(+), 19 deletions(-) > > diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c > index ab2c8fe8cdfa..18da9ed15728 100644 > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c > @@ -96,12 +96,9 @@ static void gen9_enable_guc_interrupts(struct intel_guc *guc) > assert_rpm_wakelock_held(>->i915->runtime_pm); > > spin_lock_irq(>->irq_lock); > - if (!guc->interrupts.enabled) { > - WARN_ON_ONCE(intel_uncore_read(gt->uncore, GEN8_GT_IIR(2)) & > - gt->pm_guc_events); > - guc->interrupts.enabled = true; > - gen6_gt_pm_enable_irq(gt, gt->pm_guc_events); > - } > + WARN_ON_ONCE(intel_uncore_read(gt->uncore, GEN8_GT_IIR(2)) & > + gt->pm_guc_events); > + gen6_gt_pm_enable_irq(gt, gt->pm_guc_events); > spin_unlock_irq(>->irq_lock); > } > > @@ -112,7 +109,6 @@ static void gen9_disable_guc_interrupts(struct intel_guc *guc) > assert_rpm_wakelock_held(>->i915->runtime_pm); > > spin_lock_irq(>->irq_lock); > - guc->interrupts.enabled = false; > > gen6_gt_pm_disable_irq(gt, gt->pm_guc_events); > > @@ -134,18 +130,14 @@ static void gen11_reset_guc_interrupts(struct intel_guc *guc) > static void gen11_enable_guc_interrupts(struct intel_guc *guc) > { > struct intel_gt *gt = guc_to_gt(guc); > + u32 events = REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST); > > spin_lock_irq(>->irq_lock); > - if (!guc->interrupts.enabled) { > - u32 events = REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST); > - > - WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_GUC)); > - intel_uncore_write(gt->uncore, > - GEN11_GUC_SG_INTR_ENABLE, events); > - intel_uncore_write(gt->uncore, > - GEN11_GUC_SG_INTR_MASK, ~events); > - guc->interrupts.enabled = true; > - } > + WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_GUC)); > + intel_uncore_write(gt->uncore, > + GEN11_GUC_SG_INTR_ENABLE, events); > + intel_uncore_write(gt->uncore, > + GEN11_GUC_SG_INTR_MASK, ~events); > spin_unlock_irq(>->irq_lock); > } > > @@ -154,7 +146,6 @@ static void gen11_disable_guc_interrupts(struct intel_guc *guc) > struct intel_gt *gt = guc_to_gt(guc); > > spin_lock_irq(>->irq_lock); > - guc->interrupts.enabled = false; > > intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_MASK, ~0); > intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_ENABLE, 0); > diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h > index c20f3839de12..4abc59f6f3cd 100644 > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h > @@ -33,7 +33,6 @@ struct intel_guc { > unsigned int msg_enabled_mask; > > struct { > - bool enabled; > void (*reset)(struct intel_guc *guc); > void (*enable)(struct intel_guc *guc); > void (*disable)(struct intel_guc *guc);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index ab2c8fe8cdfa..18da9ed15728 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -96,12 +96,9 @@ static void gen9_enable_guc_interrupts(struct intel_guc *guc) assert_rpm_wakelock_held(>->i915->runtime_pm); spin_lock_irq(>->irq_lock); - if (!guc->interrupts.enabled) { - WARN_ON_ONCE(intel_uncore_read(gt->uncore, GEN8_GT_IIR(2)) & - gt->pm_guc_events); - guc->interrupts.enabled = true; - gen6_gt_pm_enable_irq(gt, gt->pm_guc_events); - } + WARN_ON_ONCE(intel_uncore_read(gt->uncore, GEN8_GT_IIR(2)) & + gt->pm_guc_events); + gen6_gt_pm_enable_irq(gt, gt->pm_guc_events); spin_unlock_irq(>->irq_lock); } @@ -112,7 +109,6 @@ static void gen9_disable_guc_interrupts(struct intel_guc *guc) assert_rpm_wakelock_held(>->i915->runtime_pm); spin_lock_irq(>->irq_lock); - guc->interrupts.enabled = false; gen6_gt_pm_disable_irq(gt, gt->pm_guc_events); @@ -134,18 +130,14 @@ static void gen11_reset_guc_interrupts(struct intel_guc *guc) static void gen11_enable_guc_interrupts(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); + u32 events = REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST); spin_lock_irq(>->irq_lock); - if (!guc->interrupts.enabled) { - u32 events = REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST); - - WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_GUC)); - intel_uncore_write(gt->uncore, - GEN11_GUC_SG_INTR_ENABLE, events); - intel_uncore_write(gt->uncore, - GEN11_GUC_SG_INTR_MASK, ~events); - guc->interrupts.enabled = true; - } + WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_GUC)); + intel_uncore_write(gt->uncore, + GEN11_GUC_SG_INTR_ENABLE, events); + intel_uncore_write(gt->uncore, + GEN11_GUC_SG_INTR_MASK, ~events); spin_unlock_irq(>->irq_lock); } @@ -154,7 +146,6 @@ static void gen11_disable_guc_interrupts(struct intel_guc *guc) struct intel_gt *gt = guc_to_gt(guc); spin_lock_irq(>->irq_lock); - guc->interrupts.enabled = false; intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_MASK, ~0); intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_ENABLE, 0); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index c20f3839de12..4abc59f6f3cd 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -33,7 +33,6 @@ struct intel_guc { unsigned int msg_enabled_mask; struct { - bool enabled; void (*reset)(struct intel_guc *guc); void (*enable)(struct intel_guc *guc); void (*disable)(struct intel_guc *guc);
Drop the variable guc->interrupts.enabled as this variable is just leading to bugs creeping into the code. e.g. A full GPU reset disables the GuC interrupts but forgot to clear guc->interrupts.enabled, guc->interrupts.enabled being true suppresses interrupts from getting re-enabled and now we are broken. It is harmless to enable interrupt while already enabled so let's just delete this variable to avoid bugs like this going forward. Signed-off-by: Matthew Brost <matthew.brost@intel.com> --- drivers/gpu/drm/i915/gt/uc/intel_guc.c | 27 +++++++++----------------- drivers/gpu/drm/i915/gt/uc/intel_guc.h | 1 - 2 files changed, 9 insertions(+), 19 deletions(-)