2 files changed, 55 insertions, 56 deletions

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 7445454c2a..f3f2e47b6d 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1063,6 +1063,7 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 	bool cd_live;
 	__le64 *cdptr;
 	struct arm_smmu_ctx_desc_cfg *cd_table = &master->cd_table;
+	struct arm_smmu_device *smmu = master->smmu;
 
 	if (WARN_ON(ssid >= (1 << cd_table->s1cdmax)))
 		return -E2BIG;
@@ -1077,6 +1078,8 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 	if (!cd) { /* (5) */
 		val = 0;
 	} else if (cd == &quiet_cd) { /* (4) */
+		if (!(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))
+			val &= ~(CTXDESC_CD_0_S | CTXDESC_CD_0_R);
 		val |= CTXDESC_CD_0_TCR_EPD0;
 	} else if (cd_live) { /* (3) */
 		val &= ~CTXDESC_CD_0_ASID;
@@ -1249,7 +1252,7 @@ static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
 }
 
 static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
-				      __le64 *dst)
+				      struct arm_smmu_ste *dst)
 {
 	/*
 	 * This is hideously complicated, but we only really care about
@@ -1267,12 +1270,12 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	 * 2. Write everything apart from dword 0, sync, write dword 0, sync
 	 * 3. Update Config, sync
 	 */
-	u64 val = le64_to_cpu(dst[0]);
+	u64 val = le64_to_cpu(dst->data[0]);
 	bool ste_live = false;
-	struct arm_smmu_device *smmu = NULL;
+	struct arm_smmu_device *smmu = master->smmu;
 	struct arm_smmu_ctx_desc_cfg *cd_table = NULL;
 	struct arm_smmu_s2_cfg *s2_cfg = NULL;
-	struct arm_smmu_domain *smmu_domain = NULL;
+	struct arm_smmu_domain *smmu_domain = master->domain;
 	struct arm_smmu_cmdq_ent prefetch_cmd = {
 		.opcode		= CMDQ_OP_PREFETCH_CFG,
 		.prefetch	= {
@@ -1280,18 +1283,12 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		},
 	};
 
-	if (master) {
-		smmu_domain = master->domain;
-		smmu = master->smmu;
-	}
-
 	if (smmu_domain) {
 		switch (smmu_domain->stage) {
 		case ARM_SMMU_DOMAIN_S1:
 			cd_table = &master->cd_table;
 			break;
 		case ARM_SMMU_DOMAIN_S2:
-		case ARM_SMMU_DOMAIN_NESTED:
 			s2_cfg = &smmu_domain->s2_cfg;
 			break;
 		default:
@@ -1325,10 +1322,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		else
 			val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
 
-		dst[0] = cpu_to_le64(val);
-		dst[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
+		dst->data[0] = cpu_to_le64(val);
+		dst->data[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
 						STRTAB_STE_1_SHCFG_INCOMING));
-		dst[2] = 0; /* Nuke the VMID */
+		dst->data[2] = 0; /* Nuke the VMID */
 		/*
 		 * The SMMU can perform negative caching, so we must sync
 		 * the STE regardless of whether the old value was live.
@@ -1343,7 +1340,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			STRTAB_STE_1_STRW_EL2 : STRTAB_STE_1_STRW_NSEL1;
 
 		BUG_ON(ste_live);
-		dst[1] = cpu_to_le64(
+		dst->data[1] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
 			 FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
 			 FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
@@ -1352,7 +1349,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 
 		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
 		    !master->stall_enabled)
-			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
+			dst->data[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
 
 		val |= (cd_table->cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
 			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) |
@@ -1362,7 +1359,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 
 	if (s2_cfg) {
 		BUG_ON(ste_live);
-		dst[2] = cpu_to_le64(
+		dst->data[2] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) |
 			 FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) |
 #ifdef __BIG_ENDIAN
@@ -1371,18 +1368,18 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			 STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
 			 STRTAB_STE_2_S2R);
 
-		dst[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
+		dst->data[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
 
 		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS);
 	}
 
 	if (master->ats_enabled)
-		dst[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
+		dst->data[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
 						 STRTAB_STE_1_EATS_TRANS));
 
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 	/* See comment in arm_smmu_write_ctx_desc() */
-	WRITE_ONCE(dst[0], cpu_to_le64(val));
+	WRITE_ONCE(dst->data[0], cpu_to_le64(val));
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 
 	/* It's likely that we'll want to use the new STE soon */
@@ -1390,7 +1387,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
 }
 
-static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool force)
+static void arm_smmu_init_bypass_stes(struct arm_smmu_ste *strtab,
+				      unsigned int nent, bool force)
 {
 	unsigned int i;
 	u64 val = STRTAB_STE_0_V;
@@ -1401,11 +1399,11 @@ static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool fo
 		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
 
 	for (i = 0; i < nent; ++i) {
-		strtab[0] = cpu_to_le64(val);
-		strtab[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
-						   STRTAB_STE_1_SHCFG_INCOMING));
-		strtab[2] = 0;
-		strtab += STRTAB_STE_DWORDS;
+		strtab->data[0] = cpu_to_le64(val);
+		strtab->data[1] = cpu_to_le64(FIELD_PREP(
+			STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING));
+		strtab->data[2] = 0;
+		strtab++;
 	}
 }
 
@@ -2171,7 +2169,6 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 		fmt = ARM_64_LPAE_S1;
 		finalise_stage_fn = arm_smmu_domain_finalise_s1;
 		break;
-	case ARM_SMMU_DOMAIN_NESTED:
 	case ARM_SMMU_DOMAIN_S2:
 		ias = smmu->ias;
 		oas = smmu->oas;
@@ -2209,26 +2206,23 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	return 0;
 }
 
-static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
+static struct arm_smmu_ste *
+arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
 {
-	__le64 *step;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
 
 	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
-		struct arm_smmu_strtab_l1_desc *l1_desc;
-		int idx;
+		unsigned int idx1, idx2;
 
 		/* Two-level walk */
-		idx = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
-		l1_desc = &cfg->l1_desc[idx];
-		idx = (sid & ((1 << STRTAB_SPLIT) - 1)) * STRTAB_STE_DWORDS;
-		step = &l1_desc->l2ptr[idx];
+		idx1 = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
+		idx2 = sid & ((1 << STRTAB_SPLIT) - 1);
+		return &cfg->l1_desc[idx1].l2ptr[idx2];
 	} else {
 		/* Simple linear lookup */
-		step = &cfg->strtab[sid * STRTAB_STE_DWORDS];
+		return (struct arm_smmu_ste *)&cfg
+			       ->strtab[sid * STRTAB_STE_DWORDS];
 	}
-
-	return step;
 }
 
 static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
@@ -2238,7 +2232,8 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
 
 	for (i = 0; i < master->num_streams; ++i) {
 		u32 sid = master->streams[i].id;
-		__le64 *step = arm_smmu_get_step_for_sid(smmu, sid);
+		struct arm_smmu_ste *step =
+			arm_smmu_get_step_for_sid(smmu, sid);
 
 		/* Bridged PCI devices may end up with duplicated IDs */
 		for (j = 0; j < i; j++)
@@ -2403,8 +2398,6 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		return -EBUSY;
 	}
 
-	arm_smmu_detach_dev(master);
-
 	mutex_lock(&smmu_domain->init_mutex);
 
 	if (!smmu_domain->smmu) {
@@ -2419,6 +2412,16 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	if (ret)
 		return ret;
 
+	/*
+	 * Prevent arm_smmu_share_asid() from trying to change the ASID
+	 * of either the old or new domain while we are working on it.
+	 * This allows the STE and the smmu_domain->devices list to
+	 * be inconsistent during this routine.
+	 */
+	mutex_lock(&arm_smmu_asid_lock);
+
+	arm_smmu_detach_dev(master);
+
 	master->domain = smmu_domain;
 
 	/*
@@ -2444,13 +2447,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 			}
 		}
 
-		/*
-		 * Prevent SVA from concurrently modifying the CD or writing to
-		 * the CD entry
-		 */
-		mutex_lock(&arm_smmu_asid_lock);
 		ret = arm_smmu_write_ctx_desc(master, IOMMU_NO_PASID, &smmu_domain->cd);
-		mutex_unlock(&arm_smmu_asid_lock);
 		if (ret) {
 			master->domain = NULL;
 			goto out_list_del;
@@ -2460,13 +2457,15 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	arm_smmu_install_ste_for_dev(master);
 
 	arm_smmu_enable_ats(master);
-	return 0;
+	goto out_unlock;
 
 out_list_del:
 	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
 	list_del(&master->domain_head);
 	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
 
+out_unlock:
+	mutex_unlock(&arm_smmu_asid_lock);
 	return ret;
 }
 
@@ -2649,9 +2648,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 	struct arm_smmu_master *master;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 
-	if (!fwspec || fwspec->ops != &arm_smmu_ops)
-		return ERR_PTR(-ENODEV);
-
 	if (WARN_ON_ONCE(dev_iommu_priv_get(dev)))
 		return ERR_PTR(-EBUSY);
 
@@ -2698,7 +2694,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 
 err_free_master:
 	kfree(master);
-	dev_iommu_priv_set(dev, NULL);
 	return ERR_PTR(ret);
 }
 
@@ -2742,7 +2737,7 @@ static int arm_smmu_enable_nesting(struct iommu_domain *domain)
 	if (smmu_domain->smmu)
 		ret = -EPERM;
 	else
-		smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
 	mutex_unlock(&smmu_domain->init_mutex);
 
 	return ret;
@@ -3769,7 +3764,7 @@ static void arm_smmu_rmr_install_bypass_ste(struct arm_smmu_device *smmu)
 	iort_get_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
 
 	list_for_each_entry(e, &rmr_list, list) {
-		__le64 *step;
+		struct arm_smmu_ste *step;
 		struct iommu_iort_rmr_data *rmr;
 		int ret, i;
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 961205ba86..65fb388d51 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -188,7 +188,7 @@
 #ifdef CONFIG_CMA_ALIGNMENT
 #define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + CONFIG_CMA_ALIGNMENT)
 #else
-#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_ORDER)
+#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_PAGE_ORDER)
 #endif
 
 /*
@@ -206,6 +206,11 @@
 #define STRTAB_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 6)
 
 #define STRTAB_STE_DWORDS		8
+
+struct arm_smmu_ste {
+	__le64 data[STRTAB_STE_DWORDS];
+};
+
 #define STRTAB_STE_0_V			(1UL << 0)
 #define STRTAB_STE_0_CFG		GENMASK_ULL(3, 1)
 #define STRTAB_STE_0_CFG_ABORT		0
@@ -571,7 +576,7 @@ struct arm_smmu_priq {
 struct arm_smmu_strtab_l1_desc {
 	u8				span;
 
-	__le64				*l2ptr;
+	struct arm_smmu_ste		*l2ptr;
 	dma_addr_t			l2ptr_dma;
 };
 
@@ -710,7 +715,6 @@ struct arm_smmu_master {
 enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
-	ARM_SMMU_DOMAIN_NESTED,
 	ARM_SMMU_DOMAIN_BYPASS,
 };