iommu/arm-smmu-v3: Move the CD generation for S1 domains into a function

Introduce arm_smmu_make_s1_cd() to build the CD from the paging S1 domain,
and reorganize all the places programming S1 domain CD table entries to
call it.

Split arm_smmu_update_s1_domain_cd_entry() from
arm_smmu_update_ctx_desc_devices() so that the S1 path has its own call
chain separate from the unrelated SVA path.

arm_smmu_update_s1_domain_cd_entry() only works on S1 domains attached to
RIDs and refreshes all their CDs. Remove case (3) from
arm_smmu_write_ctx_desc() as it is now handled by directly calling
arm_smmu_write_cd_entry().

Remove the forced clear of the CD during S1 domain attach,
arm_smmu_write_cd_entry() will do this automatically if necessary.

Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Reviewed-by: Michael Shavit <mshavit@google.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Mostafa Saleh <smostafa@google.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/3-v9-5040dc602008+177d7-smmuv3_newapi_p2_jgg@nvidia.com
[will: Drop unused arm_smmu_clean_cd_entry() function]
Signed-off-by: Will Deacon <will@kernel.org>

Author: jgunthorpe

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

@@ -53,6 +53,29 @@ static void arm_smmu_update_ctx_desc_devices(struct arm_smmu_domain *smmu_domain
 	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
 }
 
+static void
+arm_smmu_update_s1_domain_cd_entry(struct arm_smmu_domain *smmu_domain)
+{
+	struct arm_smmu_master *master;
+	struct arm_smmu_cd target_cd;
+	unsigned long flags;
+
+	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
+		struct arm_smmu_cd *cdptr;
+
+		/* S1 domains only support RID attachment right now */
+		cdptr = arm_smmu_get_cd_ptr(master, IOMMU_NO_PASID);
+		if (WARN_ON(!cdptr))
+			continue;
+
+		arm_smmu_make_s1_cd(&target_cd, master, smmu_domain);
+		arm_smmu_write_cd_entry(master, IOMMU_NO_PASID, cdptr,
+					&target_cd);
+	}
+	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
+}
+
 /*
  * Check if the CPU ASID is available on the SMMU side. If a private context
  * descriptor is using it, try to replace it.
@@ -96,7 +119,7 @@ arm_smmu_share_asid(struct mm_struct *mm, u16 asid)
 	 * be some overlap between use of both ASIDs, until we invalidate the
 	 * TLB.
 	 */
-	arm_smmu_update_ctx_desc_devices(smmu_domain, IOMMU_NO_PASID, cd);
+	arm_smmu_update_s1_domain_cd_entry(smmu_domain);
 
 	/* Invalidate TLB entries previously associated with that context */
 	arm_smmu_tlb_inv_asid(smmu, asid);

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

@@ -1203,8 +1203,8 @@ static void arm_smmu_write_cd_l1_desc(__le64 *dst,
 	WRITE_ONCE(*dst, cpu_to_le64(val));
 }
 
-static struct arm_smmu_cd *arm_smmu_get_cd_ptr(struct arm_smmu_master *master,
-					       u32 ssid)
+struct arm_smmu_cd *arm_smmu_get_cd_ptr(struct arm_smmu_master *master,
+					u32 ssid)
 {
 	__le64 *l1ptr;
 	unsigned int idx;
@@ -1269,9 +1269,9 @@ static const struct arm_smmu_entry_writer_ops arm_smmu_cd_writer_ops = {
 	.get_used = arm_smmu_get_cd_used,
 };
 
-static void arm_smmu_write_cd_entry(struct arm_smmu_master *master, int ssid,
-				    struct arm_smmu_cd *cdptr,
-				    const struct arm_smmu_cd *target)
+void arm_smmu_write_cd_entry(struct arm_smmu_master *master, int ssid,
+			     struct arm_smmu_cd *cdptr,
+			     const struct arm_smmu_cd *target)
 {
 	struct arm_smmu_cd_writer cd_writer = {
 		.writer = {
@@ -1284,6 +1284,32 @@ static void arm_smmu_write_cd_entry(struct arm_smmu_master *master, int ssid,
 	arm_smmu_write_entry(&cd_writer.writer, cdptr->data, target->data);
 }
 
+void arm_smmu_make_s1_cd(struct arm_smmu_cd *target,
+			 struct arm_smmu_master *master,
+			 struct arm_smmu_domain *smmu_domain)
+{
+	struct arm_smmu_ctx_desc *cd = &smmu_domain->cd;
+
+	memset(target, 0, sizeof(*target));
+
+	target->data[0] = cpu_to_le64(
+		cd->tcr |
+#ifdef __BIG_ENDIAN
+		CTXDESC_CD_0_ENDI |
+#endif
+		CTXDESC_CD_0_V |
+		CTXDESC_CD_0_AA64 |
+		(master->stall_enabled ? CTXDESC_CD_0_S : 0) |
+		CTXDESC_CD_0_R |
+		CTXDESC_CD_0_A |
+		CTXDESC_CD_0_ASET |
+		FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid)
+		);
+
+	target->data[1] = cpu_to_le64(cd->ttbr & CTXDESC_CD_1_TTB0_MASK);
+	target->data[3] = cpu_to_le64(cd->mair);
+}
+
 int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 			    struct arm_smmu_ctx_desc *cd)
 {
@@ -1292,14 +1318,11 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 	 *
 	 * (1) Install primary CD, for normal DMA traffic (SSID = IOMMU_NO_PASID = 0).
 	 * (2) Install a secondary CD, for SID+SSID traffic.
-	 * (3) Update ASID of a CD. Atomically write the first 64 bits of the
-	 *     CD, then invalidate the old entry and mappings.
 	 * (4) Quiesce the context without clearing the valid bit. Disable
 	 *     translation, and ignore any translation fault.
 	 * (5) Remove a secondary CD.
 	 */
 	u64 val;
-	bool cd_live;
 	struct arm_smmu_cd target;
 	struct arm_smmu_cd *cdptr = ⌖
 	struct arm_smmu_cd *cd_table_entry;
@@ -1315,7 +1338,6 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 
 	target = *cd_table_entry;
 	val = le64_to_cpu(cdptr->data[0]);
-	cd_live = !!(val & CTXDESC_CD_0_V);
 
 	if (!cd) { /* (5) */
 		memset(cdptr, 0, sizeof(*cdptr));
@@ -1328,13 +1350,6 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 			val &= ~(CTXDESC_CD_0_S | CTXDESC_CD_0_R);
 		val |= CTXDESC_CD_0_TCR_EPD0;
 		cdptr->data[1] &= ~cpu_to_le64(CTXDESC_CD_1_TTB0_MASK);
-	} else if (cd_live) { /* (3) */
-		val &= ~CTXDESC_CD_0_ASID;
-		val |= FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid);
-		/*
-		 * Until CD+TLB invalidation, both ASIDs may be used for tagging
-		 * this substream's traffic
-		 */
 	} else { /* (1) and (2) */
 		cdptr->data[1] = cpu_to_le64(cd->ttbr & CTXDESC_CD_1_TTB0_MASK);
 		cdptr->data[2] = 0;
@@ -2633,29 +2648,29 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
 
 	switch (smmu_domain->stage) {
-	case ARM_SMMU_DOMAIN_S1:
+	case ARM_SMMU_DOMAIN_S1: {
+		struct arm_smmu_cd target_cd;
+		struct arm_smmu_cd *cdptr;
+
 		if (!master->cd_table.cdtab) {
 			ret = arm_smmu_alloc_cd_tables(master);
 			if (ret)
 				goto out_list_del;
-		} else {
-			/*
-			 * arm_smmu_write_ctx_desc() relies on the entry being
-			 * invalid to work, clear any existing entry.
-			 */
-			ret = arm_smmu_write_ctx_desc(master, IOMMU_NO_PASID,
-						      NULL);
-			if (ret)
-				goto out_list_del;
 		}
 
-		ret = arm_smmu_write_ctx_desc(master, IOMMU_NO_PASID, &smmu_domain->cd);
-		if (ret)
+		cdptr = arm_smmu_get_cd_ptr(master, IOMMU_NO_PASID);
+		if (!cdptr) {
+			ret = -ENOMEM;
 			goto out_list_del;
+		}
 
+		arm_smmu_make_s1_cd(&target_cd, master, smmu_domain);
+		arm_smmu_write_cd_entry(master, IOMMU_NO_PASID, cdptr,
+					&target_cd);
 		arm_smmu_make_cdtable_ste(&target, master);
 		arm_smmu_install_ste_for_dev(master, &target);
 		break;
+	}
 	case ARM_SMMU_DOMAIN_S2:
 		arm_smmu_make_s2_domain_ste(&target, master, smmu_domain);
 		arm_smmu_install_ste_for_dev(master, &target);

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

@@ -751,6 +751,15 @@ extern struct xarray arm_smmu_asid_xa;
 extern struct mutex arm_smmu_asid_lock;
 extern struct arm_smmu_ctx_desc quiet_cd;
 
+struct arm_smmu_cd *arm_smmu_get_cd_ptr(struct arm_smmu_master *master,
+					u32 ssid);
+void arm_smmu_make_s1_cd(struct arm_smmu_cd *target,
+			 struct arm_smmu_master *master,
+			 struct arm_smmu_domain *smmu_domain);
+void arm_smmu_write_cd_entry(struct arm_smmu_master *master, int ssid,
+			     struct arm_smmu_cd *cdptr,
+			     const struct arm_smmu_cd *target);
+
 int arm_smmu_write_ctx_desc(struct arm_smmu_master *smmu_master, int ssid,
 			    struct arm_smmu_ctx_desc *cd);
 void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid);