Skip to contentSkip to conversation

iommu/arm-smmu: fix "hang" when games exit

PATCH Superseded Rob Clark 4 participants 9 messages Sep 7, 2019 – Oct 29, 2019

Subsystems (2)
lore
Share & tools
lore

Rob Clark

author
#0 lore raw

PATCH 1/1 iommu/arm-smmu: fix "hang" when games exit

From: Rob Clark <[email protected]>

When games, browser, or anything using a lot of GPU buffers exits, there can be many hundreds or thousands of buffers to unmap and free. If the GPU is otherwise suspended, this can cause arm-smmu to resume/suspend for each buffer, resulting 5-10 seconds worth of reprogramming the context bank (arm_smmu_write_context_bank()/arm_smmu_write_s2cr()/etc). To the user it would appear that the system is locked up.

A simple solution is to use pm_runtime_put_autosuspend() instead, so we don't immediately suspend the SMMU device.

---
Note: I've tied the autosuspend enable/delay to the consumer device, based on the reasoning that if the consumer device benefits from using an autosuspend delay, then it's corresponding SMMU probably does too. Maybe that is overkill and we should just unconditionally enable autosuspend.

 drivers/iommu/arm-smmu.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)
drivers/iommu/arm-smmu.c +10 -1
index c2733b447d9c..73a0dd53c8a3 100644
@@ -289,7 +289,7 @@ static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
 static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
 {
 	if (pm_runtime_enabled(smmu->dev))
-		pm_runtime_put(smmu->dev);
+		pm_runtime_put_autosuspend(smmu->dev);
 }
 
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
@@ -1445,6 +1445,15 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	/* Looks ok, so add the device to the domain */
 	ret = arm_smmu_domain_add_master(smmu_domain, fwspec);
 
+#ifdef CONFIG_PM
+	/* TODO maybe device_link_add() should do this for us? */
+	if (dev->power.use_autosuspend) {
+		pm_runtime_set_autosuspend_delay(smmu->dev,
+			dev->power.autosuspend_delay);
+		pm_runtime_use_autosuspend(smmu->dev);
+	}
+#endif
+
 rpm_put:
 	arm_smmu_rpm_put(smmu);
 	return ret;
Signature · 1 line
2.21.0
reviewer
#1 lore raw
Quoted 12 lines · Rob Clark

From: Rob Clark <[email protected]>

When games, browser, or anything using a lot of GPU buffers exits, there can be many hundreds or thousands of buffers to unmap and free. If the GPU is otherwise suspended, this can cause arm-smmu to resume/suspend for each buffer, resulting 5-10 seconds worth of reprogramming the context bank (arm_smmu_write_context_bank()/arm_smmu_write_s2cr()/etc). To the user it would appear that the system is locked up.

A simple solution is to use pm_runtime_put_autosuspend() instead, so we don't immediately suspend the SMMU device.

Quoted 7 lines

---
Note: I've tied the autosuspend enable/delay to the consumer device, based on the reasoning that if the consumer device benefits from using an autosuspend delay, then it's corresponding SMMU probably does too. Maybe that is overkill and we should just unconditionally enable autosuspend.

I'm not sure there's really any reason to expect that a supplier's usage model when doing things for itself bears any relation to that of its consumer(s), so I'd certainly lean towards the "unconditional" argument myself.

Of course ideally we'd skip resuming altogether in the map/unmap paths (since resume implies a full TLB reset anyway), but IIRC that approach started to get messy in the context of the initial RPM patchset. I'm planning to fiddle around a bit more to clean up the implementation of the new iommu_flush_ops stuff, so I've made a note to myself to revisit RPM to see if there's a sufficiently clean way to do better. In the meantime, though, I don't have any real objection to using some reasonable autosuspend delay on the principle that if we've been woken up to map/unmap one page, there's a high likelihood that more will follow in short order (and in the configuration slow-paths it won't have much impact either way).

Robin.

Quoted 33 lines
  drivers/iommu/arm-smmu.c | 11 ++++++++++-
  1 file changed, 10 insertions(+), 1 deletion(-)
drivers/iommu/arm-smmu.c +10 -1
index c2733b447d9c..73a0dd53c8a3 100644
@@ -289,7 +289,7 @@ static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
  static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
  {
  	if (pm_runtime_enabled(smmu->dev))
-		pm_runtime_put(smmu->dev);
+		pm_runtime_put_autosuspend(smmu->dev);
  }
 
  static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
@@ -1445,6 +1445,15 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
  	/* Looks ok, so add the device to the domain */
  	ret = arm_smmu_domain_add_master(smmu_domain, fwspec);
 
+#ifdef CONFIG_PM
+	/* TODO maybe device_link_add() should do this for us? */
+	if (dev->power.use_autosuspend) {
+		pm_runtime_set_autosuspend_delay(smmu->dev,
+			dev->power.autosuspend_delay);
+		pm_runtime_use_autosuspend(smmu->dev);
+	}
+#endif
+
  rpm_put:
  	arm_smmu_rpm_put(smmu);
  	return ret;
author
#2 lore raw
Quoted 22 lines · Robin Murphy
Quoted 12 lines · Rob Clark

From: Rob Clark <[email protected]>

When games, browser, or anything using a lot of GPU buffers exits, there can be many hundreds or thousands of buffers to unmap and free. If the GPU is otherwise suspended, this can cause arm-smmu to resume/suspend for each buffer, resulting 5-10 seconds worth of reprogramming the context bank (arm_smmu_write_context_bank()/arm_smmu_write_s2cr()/etc). To the user it would appear that the system is locked up.

A simple solution is to use pm_runtime_put_autosuspend() instead, so we don't immediately suspend the SMMU device.

Quoted 7 lines

---
Note: I've tied the autosuspend enable/delay to the consumer device, based on the reasoning that if the consumer device benefits from using an autosuspend delay, then it's corresponding SMMU probably does too. Maybe that is overkill and we should just unconditionally enable autosuspend.

Quoted 4 lines

I'm not sure there's really any reason to expect that a supplier's usage model when doing things for itself bears any relation to that of its consumer(s), so I'd certainly lean towards the "unconditional" argument myself.

Sounds good, I'll respin w/ unconditional autosuspend

Quoted 11 lines

Of course ideally we'd skip resuming altogether in the map/unmap paths (since resume implies a full TLB reset anyway), but IIRC that approach started to get messy in the context of the initial RPM patchset. I'm planning to fiddle around a bit more to clean up the implementation of the new iommu_flush_ops stuff, so I've made a note to myself to revisit RPM to see if there's a sufficiently clean way to do better. In the meantime, though, I don't have any real objection to using some reasonable autosuspend delay on the principle that if we've been woken up to map/unmap one page, there's a high likelihood that more will follow in short order (and in the configuration slow-paths it won't have much impact either way).

It does sort of remind me about something I was chatting with Jordan the other day.. about how we could possibly skip the TLB inv for unmaps from non-current pagetables once we have per-context pagetables.

The challenge is, since the GPU's command parser is the one switching pagetables, we don't have any race-free way to know which pagetables are current. But we do know which contexts have work queued up for the GPU, so we can know either that a given context definitely isn't current, or that it might be current. And in the "definitely not current" case we could skip TLB inv.

BR,
-R

Quoted 36 lines

Robin.

Quoted 33 lines
  drivers/iommu/arm-smmu.c | 11 ++++++++++-
  1 file changed, 10 insertions(+), 1 deletion(-)
drivers/iommu/arm-smmu.c +10 -1
index c2733b447d9c..73a0dd53c8a3 100644
@@ -289,7 +289,7 @@ static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
  static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
  {
      if (pm_runtime_enabled(smmu->dev))
-             pm_runtime_put(smmu->dev);
+             pm_runtime_put_autosuspend(smmu->dev);
  }
 
  static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
@@ -1445,6 +1445,15 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
      /* Looks ok, so add the device to the domain */
      ret = arm_smmu_domain_add_master(smmu_domain, fwspec);
 
+#ifdef CONFIG_PM
+     /* TODO maybe device_link_add() should do this for us? */
+     if (dev->power.use_autosuspend) {
+             pm_runtime_set_autosuspend_delay(smmu->dev,
+                     dev->power.autosuspend_delay);
+             pm_runtime_use_autosuspend(smmu->dev);
+     }
+#endif
+
  rpm_put:
      arm_smmu_rpm_put(smmu);
      return ret;
author
#3 lore raw

PATCH v2 1/1 iommu/arm-smmu: fix "hang" when games exit

In reply to Robin Murphy

From: Rob Clark <[email protected]>

When games, browser, or anything using a lot of GPU buffers exits, there can be many hundreds or thousands of buffers to unmap and free. If the GPU is otherwise suspended, this can cause arm-smmu to resume/suspend for each buffer, resulting 5-10 seconds worth of reprogramming the context bank (arm_smmu_write_context_bank()/arm_smmu_write_s2cr()/etc). To the user it would appear that the system just locked up.

A simple solution is to use pm_runtime_put_autosuspend() instead, so we don't immediately suspend the SMMU device.

---
v1: original
v2: unconditionally use autosuspend, rather than deciding based on what
consumer does

 drivers/iommu/arm-smmu.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/iommu/arm-smmu.c +4 -1
index 3f1d55fb43c4..b7b41f5001bc 100644
@@ -289,7 +289,7 @@ static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
 static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
 {
 	if (pm_runtime_enabled(smmu->dev))
-		pm_runtime_put(smmu->dev);
+		pm_runtime_put_autosuspend(smmu->dev);
 }
 
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
@@ -1445,6 +1445,9 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	/* Looks ok, so add the device to the domain */
 	ret = arm_smmu_domain_add_master(smmu_domain, fwspec);
 
+	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
+	pm_runtime_use_autosuspend(smmu->dev);
+
 rpm_put:
 	arm_smmu_rpm_put(smmu);
 	return ret;
Signature · 1 line
2.21.0
reviewer Reviewed-by on v2 1/1
#4 lore raw
Quoted 11 lines · Rob Clark

From: Rob Clark <[email protected]>

When games, browser, or anything using a lot of GPU buffers exits, there can be many hundreds or thousands of buffers to unmap and free. If the GPU is otherwise suspended, this can cause arm-smmu to resume/suspend for each buffer, resulting 5-10 seconds worth of reprogramming the context bank (arm_smmu_write_context_bank()/arm_smmu_write_s2cr()/etc). To the user it would appear that the system just locked up.

A simple solution is to use pm_runtime_put_autosuspend() instead, so we don't immediately suspend the SMMU device.

Quoted 33 lines

---
v1: original
v2: unconditionally use autosuspend, rather than deciding based on what
consumer does

  drivers/iommu/arm-smmu.c | 5 ++++-
  1 file changed, 4 insertions(+), 1 deletion(-)
drivers/iommu/arm-smmu.c +4 -1
index 3f1d55fb43c4..b7b41f5001bc 100644
@@ -289,7 +289,7 @@ static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
  static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
  {
  	if (pm_runtime_enabled(smmu->dev))
-		pm_runtime_put(smmu->dev);
+		pm_runtime_put_autosuspend(smmu->dev);
  }
 
  static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
@@ -1445,6 +1445,9 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
  	/* Looks ok, so add the device to the domain */
  	ret = arm_smmu_domain_add_master(smmu_domain, fwspec);
 
+	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
+	pm_runtime_use_autosuspend(smmu->dev);
+
  rpm_put:
  	arm_smmu_rpm_put(smmu);
  	return ret;
maintainer
#5 lore raw
In reply to Rob Clark

Hi Rob,

Quoted 11 lines · Rob Clark

From: Rob Clark <[email protected]>

When games, browser, or anything using a lot of GPU buffers exits, there can be many hundreds or thousands of buffers to unmap and free. If the GPU is otherwise suspended, this can cause arm-smmu to resume/suspend for each buffer, resulting 5-10 seconds worth of reprogramming the context bank (arm_smmu_write_context_bank()/arm_smmu_write_s2cr()/etc). To the user it would appear that the system just locked up.

A simple solution is to use pm_runtime_put_autosuspend() instead, so we don't immediately suspend the SMMU device.

Please can you reword the subject to be a bit more useful? The commit message is great, but the subject is a bit like "fix bug in code" to me.

Quoted 23 lines

---
v1: original
v2: unconditionally use autosuspend, rather than deciding based on what
consumer does

 drivers/iommu/arm-smmu.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/iommu/arm-smmu.c +1 -1
index 3f1d55fb43c4..b7b41f5001bc 100644
@@ -289,7 +289,7 @@ static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
 static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
 {
 	if (pm_runtime_enabled(smmu->dev))
-		pm_runtime_put(smmu->dev);
+		pm_runtime_put_autosuspend(smmu->dev);
 }
 
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)

drivers/iommu/arm-smmu.c static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) · line 1446

Quoted 2 lines
drivers/iommu/arm-smmu.c +0 -0
@@ -1445,6 +1445,9 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	/* Looks ok, so add the device to the domain */
 	ret = arm_smmu_domain_add_master(smmu_domain, fwspec);

Please can you put a comment here explaining what this is doing? An abridged version of the commit message is fine.

drivers/iommu/arm-smmu.c static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) · line 1449

Quoted 2 lines
drivers/iommu/arm-smmu.c +2 -0
+	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
+	pm_runtime_use_autosuspend(smmu->dev);

Cheers,

Will

#6 lore raw
Quoted 13 lines · Will Deacon

Hi Rob,

Quoted 9 lines · Rob Clark

From: Rob Clark <[email protected]>

When games, browser, or anything using a lot of GPU buffers exits, there can be many hundreds or thousands of buffers to unmap and free. If the GPU is otherwise suspended, this can cause arm-smmu to resume/suspend for each buffer, resulting 5-10 seconds worth of reprogramming the context bank (arm_smmu_write_context_bank()/arm_smmu_write_s2cr()/etc). To the user it would appear that the system just locked up.

Quoted 5 lines
Quoted 2 lines

A simple solution is to use pm_runtime_put_autosuspend() instead, so we don't immediately suspend the SMMU device.

Please can you reword the subject to be a bit more useful? The commit message is great, but the subject is a bit like "fix bug in code" to me.

yeah, not the best $subject, but I wasn't quite sure how to fit something better in a reasonable # of chars.. maybe something like:
"iommu/arm-smmu: optimize unmap but avoiding toggling runpm state"?

BR,
-R

Quoted 36 lines
Quoted 24 lines

---
v1: original
v2: unconditionally use autosuspend, rather than deciding based on what
consumer does

 drivers/iommu/arm-smmu.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/iommu/arm-smmu.c +1 -1
index 3f1d55fb43c4..b7b41f5001bc 100644
@@ -289,7 +289,7 @@ static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
 static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
 {
      if (pm_runtime_enabled(smmu->dev))
-             pm_runtime_put(smmu->dev);
+             pm_runtime_put_autosuspend(smmu->dev);
 }
 
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)

drivers/iommu/arm-smmu.c static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) · line 1446

Quoted 2 lines
drivers/iommu/arm-smmu.c +0 -0
@@ -1445,6 +1445,9 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
      /* Looks ok, so add the device to the domain */
      ret = arm_smmu_domain_add_master(smmu_domain, fwspec);

Please can you put a comment here explaining what this is doing? An abridged version of the commit message is fine.

drivers/iommu/arm-smmu.c static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) · line 1449

Quoted 2 lines
drivers/iommu/arm-smmu.c +2 -0
+     pm_runtime_set_autosuspend_delay(smmu->dev, 20);
+     pm_runtime_use_autosuspend(smmu->dev);

Cheers,

Will

reviewer
#7 lore raw
Quoted 17 lines · Rob Clark
Quoted 16 lines · Will Deacon

Hi Rob,

Quoted 11 lines · Rob Clark

From: Rob Clark <[email protected]>

When games, browser, or anything using a lot of GPU buffers exits, there can be many hundreds or thousands of buffers to unmap and free. If the GPU is otherwise suspended, this can cause arm-smmu to resume/suspend for each buffer, resulting 5-10 seconds worth of reprogramming the context bank (arm_smmu_write_context_bank()/arm_smmu_write_s2cr()/etc). To the user it would appear that the system just locked up.

A simple solution is to use pm_runtime_put_autosuspend() instead, so we don't immediately suspend the SMMU device.

Quoted 6 lines
Quoted 2 lines

Please can you reword the subject to be a bit more useful? The commit message is great, but the subject is a bit like "fix bug in code" to me.

yeah, not the best $subject, but I wasn't quite sure how to fit something better in a reasonable # of chars.. maybe something like:
"iommu/arm-smmu: optimize unmap but avoiding toggling runpm state"?

FWIW, I'd be inclined to frame it as something like "avoid pathological RPM behaviour for unmaps".

Robin.

maintainer
#8 lore raw
Quoted 18 lines · Robin Murphy
Quoted 17 lines · Rob Clark
Quoted 15 lines · Will Deacon
Quoted 11 lines · Rob Clark

From: Rob Clark <[email protected]>

When games, browser, or anything using a lot of GPU buffers exits, there can be many hundreds or thousands of buffers to unmap and free. If the GPU is otherwise suspended, this can cause arm-smmu to resume/suspend for each buffer, resulting 5-10 seconds worth of reprogramming the context bank (arm_smmu_write_context_bank()/arm_smmu_write_s2cr()/etc). To the user it would appear that the system just locked up.

A simple solution is to use pm_runtime_put_autosuspend() instead, so we don't immediately suspend the SMMU device.

Please can you reword the subject to be a bit more useful? The commit message is great, but the subject is a bit like "fix bug in code" to me.

Quoted 6 lines
Quoted 3 lines

yeah, not the best $subject, but I wasn't quite sure how to fit something better in a reasonable # of chars.. maybe something like:
"iommu/arm-smmu: optimize unmap but avoiding toggling runpm state"?

FWIW, I'd be inclined to frame it as something like "avoid pathological RPM behaviour for unmaps".

LGTM!

Will