[PATCH 0/5] drm/msm+iommu/arm-smmu-qcom: tlbinv optimizations

[PATCH 0/5] drm/msm+iommu/arm-smmu-qcom: tlbinv optimizations

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

Two additions to adreno_smmu_priv to allow for a couple of
optimizations:

 + Use a separate ASID for each set of pgtables to avoid
   over-invalidation.
 + Detect the case of unmapping from non-current pgtables
   where we can skip the redundant tlbinv

Rob Clark (5):
  iommu/arm-smmu-qcom: Fix indentation
  iommu/arm-smmu-qcom: Provide way to access current TTBR0
  iommu/arm-smmu-qcom: Add private interface to tlbinv by ASID
  drm/msm: Use separate ASID for each set of pgtables
  drm/msm: Skip tlbinv on unmap from non-current pgtables

 drivers/gpu/drm/msm/adreno/a6xx_gpu.c      |  6 +++
 drivers/gpu/drm/msm/msm_iommu.c            | 44 +++++++++++++++++++---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 10 +++++
 drivers/iommu/arm/arm-smmu/arm-smmu.c      | 43 +++++++++++++++++++--
 drivers/iommu/arm/arm-smmu/arm-smmu.h      |  1 +
 include/linux/adreno-smmu-priv.h           | 18 +++++----
 6 files changed, 106 insertions(+), 16 deletions(-)

-- 
2.37.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 2/5] iommu/arm-smmu-qcom: Provide way to access current TTBR0

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

The drm driver can skip tlbinv when unmapping from something that isn't
the current pgtables, as there is already a tlbinv on context switch.

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 9 +++++++++
 include/linux/adreno-smmu-priv.h           | 2 ++
 2 files changed, 11 insertions(+)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 7820711c4560..59b460c1c9a5 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -157,6 +157,14 @@ static int qcom_adreno_smmu_set_ttbr0_cfg(const void *cookie,
 	return 0;
 }
 
+static u64 qcom_adreno_smmu_get_ttbr0(const void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = (void *)cookie;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+
+	return arm_smmu_cb_readq(smmu_domain->smmu, cfg->cbndx, ARM_SMMU_CB_TTBR0);
+}
+
 static int qcom_adreno_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_domain,
 					       struct arm_smmu_device *smmu,
 					       struct device *dev, int start)
@@ -217,6 +225,7 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 	priv->cookie = smmu_domain;
 	priv->get_ttbr1_cfg = qcom_adreno_smmu_get_ttbr1_cfg;
 	priv->set_ttbr0_cfg = qcom_adreno_smmu_set_ttbr0_cfg;
+	priv->get_ttbr0 = qcom_adreno_smmu_get_ttbr0;
 	priv->get_fault_info = qcom_adreno_smmu_get_fault_info;
 	priv->set_stall = qcom_adreno_smmu_set_stall;
 	priv->resume_translation = qcom_adreno_smmu_resume_translation;
diff --git a/include/linux/adreno-smmu-priv.h b/include/linux/adreno-smmu-priv.h
index ac4c2c0ab724..4ad90541a095 100644
--- a/include/linux/adreno-smmu-priv.h
+++ b/include/linux/adreno-smmu-priv.h
@@ -43,6 +43,7 @@ struct adreno_smmu_fault_info {
  * @set_ttbr0_cfg: Set the TTBR0 config for the GPUs context bank.  A
  *                 NULL config disables TTBR0 translation, otherwise
  *                 TTBR0 translation is enabled with the specified cfg
+ * @get_ttbr0:     Get current TTBR0 value
  * @get_fault_info: Called by the GPU fault handler to get information about
  *                  the fault
  * @set_stall:     Configure whether stall on fault (CFCFG) is enabled.  Call
@@ -64,6 +65,7 @@ struct adreno_smmu_priv {
 	const void *cookie;
 	const struct io_pgtable_cfg *(*get_ttbr1_cfg)(const void *cookie);
 	int (*set_ttbr0_cfg)(const void *cookie, const struct io_pgtable_cfg *cfg);
+	u64 (*get_ttbr0)(const void *cookie);
 	void (*get_fault_info)(const void *cookie, struct adreno_smmu_fault_info *info);
 	void (*set_stall)(const void *cookie, bool enabled);
 	void (*resume_translation)(const void *cookie, bool terminate);
-- 
2.37.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 3/5] iommu/arm-smmu-qcom: Add private interface to tlbinv by ASID

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

This will let the drm driver use different ASID values for each set of
pgtables to avoid over-invalidation on unmap.

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c |  1 +
 drivers/iommu/arm/arm-smmu/arm-smmu.c      | 43 ++++++++++++++++++++--
 drivers/iommu/arm/arm-smmu/arm-smmu.h      |  1 +
 include/linux/adreno-smmu-priv.h           |  2 +
 4 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 59b460c1c9a5..3230348729ab 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -229,6 +229,7 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 	priv->get_fault_info = qcom_adreno_smmu_get_fault_info;
 	priv->set_stall = qcom_adreno_smmu_set_stall;
 	priv->resume_translation = qcom_adreno_smmu_resume_translation;
+	priv->tlb_inv_by_id = arm_smmu_tlb_inv_by_id;
 
 	return 0;
 }
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 2ed3594f384e..624359bb2092 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -252,7 +252,7 @@ static void arm_smmu_tlb_sync_context(struct arm_smmu_domain *smmu_domain)
 	spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
 }
 
-static void arm_smmu_tlb_inv_context_s1(void *cookie)
+static void arm_smmu_tlb_inv_context_s1_asid(void *cookie, u16 asid)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
 	/*
@@ -261,21 +261,56 @@ static void arm_smmu_tlb_inv_context_s1(void *cookie)
 	 */
 	wmb();
 	arm_smmu_cb_write(smmu_domain->smmu, smmu_domain->cfg.cbndx,
-			  ARM_SMMU_CB_S1_TLBIASID, smmu_domain->cfg.asid);
+			  ARM_SMMU_CB_S1_TLBIASID, asid);
 	arm_smmu_tlb_sync_context(smmu_domain);
 }
 
-static void arm_smmu_tlb_inv_context_s2(void *cookie)
+static void arm_smmu_tlb_inv_context_s1(void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+
+	arm_smmu_tlb_inv_context_s1_asid(cookie, smmu_domain->cfg.asid);
+}
+
+static void arm_smmu_tlb_inv_context_s2_vmid(void *cookie, u16 vmid)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 
 	/* See above */
 	wmb();
-	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, vmid);
 	arm_smmu_tlb_sync_global(smmu);
 }
 
+static void arm_smmu_tlb_inv_context_s2(void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+
+	arm_smmu_tlb_inv_context_s2_vmid(cookie, smmu_domain->cfg.vmid);
+}
+
+void arm_smmu_tlb_inv_by_id(const void *cookie, u16 id)
+{
+	struct arm_smmu_domain *smmu_domain = (void *)cookie;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	arm_smmu_rpm_get(smmu);
+	switch (smmu_domain->stage) {
+	case ARM_SMMU_DOMAIN_S1:
+		arm_smmu_tlb_inv_context_s1_asid(smmu_domain, id);
+		break;
+	case ARM_SMMU_DOMAIN_S2:
+	case ARM_SMMU_DOMAIN_NESTED:
+		arm_smmu_tlb_inv_context_s2_vmid(smmu_domain, id);
+		break;
+	case ARM_SMMU_DOMAIN_BYPASS:
+		break;
+	}
+
+	arm_smmu_rpm_put(smmu);
+}
+
 static void arm_smmu_tlb_inv_range_s1(unsigned long iova, size_t size,
 				      size_t granule, void *cookie, int reg)
 {
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index 2b9b42fb6f30..f6fb52d6f841 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -527,6 +527,7 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu);
 struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu);
 struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu);
 
+void arm_smmu_tlb_inv_by_id(const void *cookie, u16 id);
 void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx);
 int arm_mmu500_reset(struct arm_smmu_device *smmu);
 
diff --git a/include/linux/adreno-smmu-priv.h b/include/linux/adreno-smmu-priv.h
index 4ad90541a095..c44fc68d4de8 100644
--- a/include/linux/adreno-smmu-priv.h
+++ b/include/linux/adreno-smmu-priv.h
@@ -50,6 +50,7 @@ struct adreno_smmu_fault_info {
  *                 before set_ttbr0_cfg().  If stalling on fault is enabled,
  *                 the GPU driver must call resume_translation()
  * @resume_translation: Resume translation after a fault
+ * @tlb_inv_by_id: Flush TLB by ASID/VMID
  *
  *
  * The GPU driver (drm/msm) and adreno-smmu work together for controlling
@@ -69,6 +70,7 @@ struct adreno_smmu_priv {
 	void (*get_fault_info)(const void *cookie, struct adreno_smmu_fault_info *info);
 	void (*set_stall)(const void *cookie, bool enabled);
 	void (*resume_translation)(const void *cookie, bool terminate);
+	void (*tlb_inv_by_id)(const void *cookie, u16 id);
 };
 
 #endif /* __ADRENO_SMMU_PRIV_H */
-- 
2.37.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel