Merge tag 'arm-smmu-updates' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into arm/smmu

Arm SMMU updates for 6.4

- Device-tree binding updates:
  * Allow Qualcomm GPU SMMUs to accept relevant clock properties
  * Document Qualcomm 8550 SoC as implementing an MMU-500
  * Favour new "qcom,smmu-500" binding for Adreno SMMUs

- Fix S2CR quirk detection on non-architectural Qualcomm SMMU
  implementations

- Acknowledge SMMUv3 PRI queue overflow when consuming events

- Document (in a comment) why ATS is disabled for bypass streams

Author: joergroedel

Documentation/devicetree/bindings/iommu/arm,smmu.yaml

@@ -53,6 +53,7 @@ properties:
               - qcom,sm8250-smmu-500
               - qcom,sm8350-smmu-500
               - qcom,sm8450-smmu-500
+              - qcom,sm8550-smmu-500
           - const: qcom,smmu-500
           - const: arm,mmu-500
 
@@ -75,9 +76,22 @@ properties:
               - qcom,sm8350-smmu-500
               - qcom,sm8450-smmu-500
           - const: arm,mmu-500
-
-      - description: Qcom Adreno GPUs implementing "arm,smmu-500"
+      - description: Qcom Adreno GPUs implementing "qcom,smmu-500" and "arm,mmu-500"
+        items:
+          - enum:
+              - qcom,sc7280-smmu-500
+              - qcom,sm6115-smmu-500
+              - qcom,sm6125-smmu-500
+              - qcom,sm8150-smmu-500
+              - qcom,sm8250-smmu-500
+              - qcom,sm8350-smmu-500
+          - const: qcom,adreno-smmu
+          - const: qcom,smmu-500
+          - const: arm,mmu-500
+      - description: Qcom Adreno GPUs implementing "arm,mmu-500" (legacy binding)
+        deprecated: true
         items:
+          # Do not add additional SoC to this list. Instead use previous list.
           - enum:
               - qcom,sc7280-smmu-500
               - qcom,sm8150-smmu-500
@@ -364,6 +378,30 @@ allOf:
             - description: interface clock required to access smmu's registers
                 through the TCU's programming interface.
 
+  - if:
+      properties:
+        compatible:
+          items:
+            - enum:
+                - qcom,sm6115-smmu-500
+                - qcom,sm6125-smmu-500
+            - const: qcom,adreno-smmu
+            - const: qcom,smmu-500
+            - const: arm,mmu-500
+    then:
+      properties:
+        clock-names:
+          items:
+            - const: mem
+            - const: hlos
+            - const: iface
+
+        clocks:
+          items:
+            - description: GPU memory bus clock
+            - description: Voter clock required for HLOS SMMU access
+            - description: Interface clock required for register access
+
   # Disallow clocks for all other platforms with specific compatibles
   - if:
       properties:
@@ -383,12 +421,11 @@ allOf:
               - qcom,sdm845-smmu-500
               - qcom,sdx55-smmu-500
               - qcom,sdx65-smmu-500
-              - qcom,sm6115-smmu-500
-              - qcom,sm6125-smmu-500
               - qcom,sm6350-smmu-500
               - qcom,sm6375-smmu-500
               - qcom,sm8350-smmu-500
               - qcom,sm8450-smmu-500
+              - qcom,sm8550-smmu-500
     then:
       properties:
         clock-names: false

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c

@@ -152,6 +152,18 @@ static void queue_inc_cons(struct arm_smmu_ll_queue *q)
 	q->cons = Q_OVF(q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
 }
 
+static void queue_sync_cons_ovf(struct arm_smmu_queue *q)
+{
+	struct arm_smmu_ll_queue *llq = &q->llq;
+
+	if (likely(Q_OVF(llq->prod) == Q_OVF(llq->cons)))
+		return;
+
+	llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
+		      Q_IDX(llq, llq->cons);
+	queue_sync_cons_out(q);
+}
+
 static int queue_sync_prod_in(struct arm_smmu_queue *q)
 {
 	u32 prod;
@@ -1577,8 +1589,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
 	} while (!queue_empty(llq));
 
 	/* Sync our overflow flag, as we believe we're up to speed */
-	llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
-		    Q_IDX(llq, llq->cons);
+	queue_sync_cons_ovf(q);
 	return IRQ_HANDLED;
 }
 
@@ -1636,9 +1647,7 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
 	} while (!queue_empty(llq));
 
 	/* Sync our overflow flag, as we believe we're up to speed */
-	llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
-		      Q_IDX(llq, llq->cons);
-	queue_sync_cons_out(q);
+	queue_sync_cons_ovf(q);
 	return IRQ_HANDLED;
 }
 
@@ -2447,6 +2456,13 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 
 	master->domain = smmu_domain;
 
+	/*
+	 * The SMMU does not support enabling ATS with bypass. When the STE is
+	 * in bypass (STE.Config[2:0] == 0b100), ATS Translation Requests and
+	 * Translated transactions are denied as though ATS is disabled for the
+	 * stream (STE.EATS == 0b00), causing F_BAD_ATS_TREQ and
+	 * F_TRANSL_FORBIDDEN events (IHI0070Ea 5.2 Stream Table Entry).
+	 */
 	if (smmu_domain->stage != ARM_SMMU_DOMAIN_BYPASS)
 		master->ats_enabled = arm_smmu_ats_supported(master);
 

drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c

@@ -268,12 +268,26 @@ static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 
 static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
 {
-	unsigned int last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1);
 	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu);
+	unsigned int last_s2cr;
 	u32 reg;
 	u32 smr;
 	int i;
 
+	/*
+	 * Some platforms support more than the Arm SMMU architected maximum of
+	 * 128 stream matching groups. For unknown reasons, the additional
+	 * groups don't exhibit the same behavior as the architected registers,
+	 * so limit the groups to 128 until the behavior is fixed for the other
+	 * groups.
+	 */
+	if (smmu->num_mapping_groups > 128) {
+		dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n");
+		smmu->num_mapping_groups = 128;
+	}
+
+	last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1);
+
 	/*
 	 * With some firmware versions writes to S2CR of type FAULT are
 	 * ignored, and writing BYPASS will end up written as FAULT in the