iommu/arm-smmu-v3: Populate smmu_domain->invs when attaching masters

Update the invs array with the invalidations required by each domain type
during attachment operations.

Only an SVA domain or a paging domain will have an invs array:
 a. SVA domain will add an INV_TYPE_S1_ASID per SMMU and an INV_TYPE_ATS
    per SID

 b. Non-nesting-parent paging domain with no ATS-enabled master will add
    a single INV_TYPE_S1_ASID or INV_TYPE_S2_VMID per SMMU

 c. Non-nesting-parent paging domain with ATS-enabled master(s) will do
    (b) and add an INV_TYPE_ATS per SID

 d. Nesting-parent paging domain will add an INV_TYPE_S2_VMID followed by
    an INV_TYPE_S2_VMID_S1_CLEAR per vSMMU. For an ATS-enabled master, it
    will add an INV_TYPE_ATS_FULL per SID

 Note that case #d prepares for a future implementation of VMID allocation
 which requires a followup series for S2 domain sharing. So when a nesting
 parent domain is attached through a vSMMU instance using a nested domain.
 VMID will be allocated per vSMMU instance v.s. currectly per S2 domain.

The per-domain invalidation is not needed until the domain is attached to
a master (when it starts to possibly use TLB). This will make it possible
to attach the domain to multiple SMMUs and avoid unnecessary invalidation
overhead during teardown if no STEs/CDs refer to the domain. It also means
that when the last device is detached, the old domain must flush its ASID
or VMID, since any new iommu_unmap() call would not trigger invalidations
given an empty domain->invs array.

Introduce some arm_smmu_invs helper functions for building scratch arrays,
preparing and installing old/new domain's invalidation arrays.

Co-developed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Will Deacon <will@kernel.org>

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

@@ -3147,6 +3147,121 @@ static void arm_smmu_disable_iopf(struct arm_smmu_master *master,
 		iopf_queue_remove_device(master->smmu->evtq.iopf, master->dev);
 }
 
+static struct arm_smmu_inv *
+arm_smmu_master_build_inv(struct arm_smmu_master *master,
+			  enum arm_smmu_inv_type type, u32 id, ioasid_t ssid,
+			  size_t pgsize)
+{
+	struct arm_smmu_invs *build_invs = master->build_invs;
+	struct arm_smmu_inv *cur, inv = {
+		.smmu = master->smmu,
+		.type = type,
+		.id = id,
+		.pgsize = pgsize,
+	};
+
+	if (WARN_ON(build_invs->num_invs >= build_invs->max_invs))
+		return NULL;
+	cur = &build_invs->inv[build_invs->num_invs];
+	build_invs->num_invs++;
+
+	*cur = inv;
+	switch (type) {
+	case INV_TYPE_S1_ASID:
+		/*
+		 * For S1 page tables the driver always uses VMID=0, and the
+		 * invalidation logic for this type will set it as well.
+		 */
+		if (master->smmu->features & ARM_SMMU_FEAT_E2H) {
+			cur->size_opcode = CMDQ_OP_TLBI_EL2_VA;
+			cur->nsize_opcode = CMDQ_OP_TLBI_EL2_ASID;
+		} else {
+			cur->size_opcode = CMDQ_OP_TLBI_NH_VA;
+			cur->nsize_opcode = CMDQ_OP_TLBI_NH_ASID;
+		}
+		break;
+	case INV_TYPE_S2_VMID:
+		cur->size_opcode = CMDQ_OP_TLBI_S2_IPA;
+		cur->nsize_opcode = CMDQ_OP_TLBI_S12_VMALL;
+		break;
+	case INV_TYPE_S2_VMID_S1_CLEAR:
+		cur->size_opcode = cur->nsize_opcode = CMDQ_OP_TLBI_NH_ALL;
+		break;
+	case INV_TYPE_ATS:
+	case INV_TYPE_ATS_FULL:
+		cur->size_opcode = cur->nsize_opcode = CMDQ_OP_ATC_INV;
+		cur->ssid = ssid;
+		break;
+	}
+
+	return cur;
+}
+
+/*
+ * Use the preallocated scratch array at master->build_invs, to build a to_merge
+ * or to_unref array, to pass into a following arm_smmu_invs_merge/unref() call.
+ *
+ * Do not free the returned invs array. It is reused, and will be overwritten by
+ * the next arm_smmu_master_build_invs() call.
+ */
+static struct arm_smmu_invs *
+arm_smmu_master_build_invs(struct arm_smmu_master *master, bool ats_enabled,
+			   ioasid_t ssid, struct arm_smmu_domain *smmu_domain)
+{
+	const bool nesting = smmu_domain->nest_parent;
+	size_t pgsize = 0, i;
+
+	iommu_group_mutex_assert(master->dev);
+
+	master->build_invs->num_invs = 0;
+
+	/* Range-based invalidation requires the leaf pgsize for calculation */
+	if (master->smmu->features & ARM_SMMU_FEAT_RANGE_INV)
+		pgsize = __ffs(smmu_domain->domain.pgsize_bitmap);
+
+	switch (smmu_domain->stage) {
+	case ARM_SMMU_DOMAIN_SVA:
+	case ARM_SMMU_DOMAIN_S1:
+		if (!arm_smmu_master_build_inv(master, INV_TYPE_S1_ASID,
+					       smmu_domain->cd.asid,
+					       IOMMU_NO_PASID, pgsize))
+			return NULL;
+		break;
+	case ARM_SMMU_DOMAIN_S2:
+		if (!arm_smmu_master_build_inv(master, INV_TYPE_S2_VMID,
+					       smmu_domain->s2_cfg.vmid,
+					       IOMMU_NO_PASID, pgsize))
+			return NULL;
+		break;
+	default:
+		WARN_ON(true);
+		return NULL;
+	}
+
+	/* All the nested S1 ASIDs have to be flushed when S2 parent changes */
+	if (nesting) {
+		if (!arm_smmu_master_build_inv(
+			    master, INV_TYPE_S2_VMID_S1_CLEAR,
+			    smmu_domain->s2_cfg.vmid, IOMMU_NO_PASID, 0))
+			return NULL;
+	}
+
+	for (i = 0; ats_enabled && i < master->num_streams; i++) {
+		/*
+		 * If an S2 used as a nesting parent is changed we have no
+		 * option but to completely flush the ATC.
+		 */
+		if (!arm_smmu_master_build_inv(
+			    master, nesting ? INV_TYPE_ATS_FULL : INV_TYPE_ATS,
+			    master->streams[i].id, ssid, 0))
+			return NULL;
+	}
+
+	/* Note this build_invs must have been sorted */
+
+	return master->build_invs;
+}
+
 static void arm_smmu_remove_master_domain(struct arm_smmu_master *master,
 					  struct iommu_domain *domain,
 					  ioasid_t ssid)
@@ -3176,6 +3291,135 @@ static void arm_smmu_remove_master_domain(struct arm_smmu_master *master,
 	kfree(master_domain);
 }
 
+/*
+ * During attachment, the updates of the two domain->invs arrays are sequenced:
+ *  1. new domain updates its invs array, merging master->build_invs
+ *  2. new domain starts to include the master during its invalidation
+ *  3. master updates its STE switching from the old domain to the new domain
+ *  4. old domain still includes the master during its invalidation
+ *  5. old domain updates its invs array, unreferencing master->build_invs
+ *
+ * For 1 and 5, prepare the two updated arrays in advance, handling any changes
+ * that can possibly failure. So the actual update of either 1 or 5 won't fail.
+ * arm_smmu_asid_lock ensures that the old invs in the domains are intact while
+ * we are sequencing to update them.
+ */
+static int arm_smmu_attach_prepare_invs(struct arm_smmu_attach_state *state,
+					struct iommu_domain *new_domain)
+{
+	struct arm_smmu_domain *old_smmu_domain =
+		to_smmu_domain_devices(state->old_domain);
+	struct arm_smmu_domain *new_smmu_domain =
+		to_smmu_domain_devices(new_domain);
+	struct arm_smmu_master *master = state->master;
+	ioasid_t ssid = state->ssid;
+
+	/*
+	 * At this point a NULL domain indicates the domain doesn't use the
+	 * IOTLB, see to_smmu_domain_devices().
+	 */
+	if (new_smmu_domain) {
+		struct arm_smmu_inv_state *invst = &state->new_domain_invst;
+		struct arm_smmu_invs *build_invs;
+
+		invst->invs_ptr = &new_smmu_domain->invs;
+		invst->old_invs = rcu_dereference_protected(
+			new_smmu_domain->invs,
+			lockdep_is_held(&arm_smmu_asid_lock));
+		build_invs = arm_smmu_master_build_invs(
+			master, state->ats_enabled, ssid, new_smmu_domain);
+		if (!build_invs)
+			return -EINVAL;
+
+		invst->new_invs =
+			arm_smmu_invs_merge(invst->old_invs, build_invs);
+		if (IS_ERR(invst->new_invs))
+			return PTR_ERR(invst->new_invs);
+	}
+
+	if (old_smmu_domain) {
+		struct arm_smmu_inv_state *invst = &state->old_domain_invst;
+
+		invst->invs_ptr = &old_smmu_domain->invs;
+		/* A re-attach case might have a different ats_enabled state */
+		if (new_smmu_domain == old_smmu_domain)
+			invst->old_invs = state->new_domain_invst.new_invs;
+		else
+			invst->old_invs = rcu_dereference_protected(
+				old_smmu_domain->invs,
+				lockdep_is_held(&arm_smmu_asid_lock));
+		/* For old_smmu_domain, new_invs points to master->build_invs */
+		invst->new_invs = arm_smmu_master_build_invs(
+			master, master->ats_enabled, ssid, old_smmu_domain);
+	}
+
+	return 0;
+}
+
+/* Must be installed before arm_smmu_install_ste_for_dev() */
+static void
+arm_smmu_install_new_domain_invs(struct arm_smmu_attach_state *state)
+{
+	struct arm_smmu_inv_state *invst = &state->new_domain_invst;
+
+	if (!invst->invs_ptr)
+		return;
+
+	rcu_assign_pointer(*invst->invs_ptr, invst->new_invs);
+	kfree_rcu(invst->old_invs, rcu);
+}
+
+static void arm_smmu_inv_flush_iotlb_tag(struct arm_smmu_inv *inv)
+{
+	struct arm_smmu_cmdq_ent cmd = {};
+
+	switch (inv->type) {
+	case INV_TYPE_S1_ASID:
+		cmd.tlbi.asid = inv->id;
+		break;
+	case INV_TYPE_S2_VMID:
+		/* S2_VMID using nsize_opcode covers S2_VMID_S1_CLEAR */
+		cmd.tlbi.vmid = inv->id;
+		break;
+	default:
+		return;
+	}
+
+	cmd.opcode = inv->nsize_opcode;
+	arm_smmu_cmdq_issue_cmd_with_sync(inv->smmu, &cmd);
+}
+
+/* Should be installed after arm_smmu_install_ste_for_dev() */
+static void
+arm_smmu_install_old_domain_invs(struct arm_smmu_attach_state *state)
+{
+	struct arm_smmu_inv_state *invst = &state->old_domain_invst;
+	struct arm_smmu_invs *old_invs = invst->old_invs;
+	struct arm_smmu_invs *new_invs;
+
+	lockdep_assert_held(&arm_smmu_asid_lock);
+
+	if (!invst->invs_ptr)
+		return;
+
+	arm_smmu_invs_unref(old_invs, invst->new_invs);
+	/*
+	 * When an IOTLB tag (the first entry in invs->new_invs) is no longer used,
+	 * it means the ASID or VMID will no longer be invalidated by map/unmap and
+	 * must be cleaned right now. The rule is that any ASID/VMID not in an invs
+	 * array must be left cleared in the IOTLB.
+	 */
+	if (!READ_ONCE(invst->new_invs->inv[0].users))
+		arm_smmu_inv_flush_iotlb_tag(&invst->new_invs->inv[0]);
+
+	new_invs = arm_smmu_invs_purge(old_invs);
+	if (!new_invs)
+		return;
+
+	rcu_assign_pointer(*invst->invs_ptr, new_invs);
+	kfree_rcu(old_invs, rcu);
+}
+
 /*
  * Start the sequence to attach a domain to a master. The sequence contains three
  * steps:
@@ -3233,12 +3477,16 @@ int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state,
 				     arm_smmu_ats_supported(master);
 	}
 
+	ret = arm_smmu_attach_prepare_invs(state, new_domain);
+	if (ret)
+		return ret;
+
 	if (smmu_domain) {
 		if (new_domain->type == IOMMU_DOMAIN_NESTED) {
 			ret = arm_smmu_attach_prepare_vmaster(
 				state, to_smmu_nested_domain(new_domain));
 			if (ret)
-				return ret;
+				goto err_unprepare_invs;
 		}
 
 		master_domain = kzalloc_obj(*master_domain);
@@ -3286,6 +3534,8 @@ int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state,
 			atomic_inc(&smmu_domain->nr_ats_masters);
 		list_add(&master_domain->devices_elm, &smmu_domain->devices);
 		spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
+
+		arm_smmu_install_new_domain_invs(state);
 	}
 
 	if (!state->ats_enabled && master->ats_enabled) {
@@ -3305,6 +3555,8 @@ int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state,
 	kfree(master_domain);
 err_free_vmaster:
 	kfree(state->vmaster);
+err_unprepare_invs:
+	kfree(state->new_domain_invst.new_invs);
 	return ret;
 }
 
@@ -3336,6 +3588,7 @@ void arm_smmu_attach_commit(struct arm_smmu_attach_state *state)
 	}
 
 	arm_smmu_remove_master_domain(master, state->old_domain, state->ssid);
+	arm_smmu_install_old_domain_invs(state);
 	master->ats_enabled = state->ats_enabled;
 }
 
@@ -3518,12 +3771,19 @@ static int arm_smmu_blocking_set_dev_pasid(struct iommu_domain *new_domain,
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(old_domain);
 	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+	struct arm_smmu_attach_state state = {
+		.master = master,
+		.old_domain = old_domain,
+		.ssid = pasid,
+	};
 
 	mutex_lock(&arm_smmu_asid_lock);
+	arm_smmu_attach_prepare_invs(&state, NULL);
 	arm_smmu_clear_cd(master, pasid);
 	if (master->ats_enabled)
 		arm_smmu_atc_inv_master(master, pasid);
 	arm_smmu_remove_master_domain(master, &smmu_domain->domain, pasid);
+	arm_smmu_install_old_domain_invs(&state);
 	mutex_unlock(&arm_smmu_asid_lock);
 
 	/*

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

@@ -1102,6 +1102,21 @@ static inline bool arm_smmu_master_canwbs(struct arm_smmu_master *master)
 	       IOMMU_FWSPEC_PCI_RC_CANWBS;
 }
 
+/**
+ * struct arm_smmu_inv_state - Per-domain invalidation array state
+ * @invs_ptr: points to the domain->invs (unwinding nesting/etc.) or is NULL if
+ *            no change should be made
+ * @old_invs: the original invs array
+ * @new_invs: for new domain, this is the new invs array to update domain->invs;
+ *            for old domain, this is the master->build_invs to pass in as the
+ *            to_unref argument to an arm_smmu_invs_unref() call
+ */
+struct arm_smmu_inv_state {
+	struct arm_smmu_invs __rcu **invs_ptr;
+	struct arm_smmu_invs *old_invs;
+	struct arm_smmu_invs *new_invs;
+};
+
 struct arm_smmu_attach_state {
 	/* Inputs */
 	struct iommu_domain *old_domain;
@@ -1111,6 +1126,8 @@ struct arm_smmu_attach_state {
 	ioasid_t ssid;
 	/* Resulting state */
 	struct arm_smmu_vmaster *vmaster;
+	struct arm_smmu_inv_state old_domain_invst;
+	struct arm_smmu_inv_state new_domain_invst;
 	bool ats_enabled;
 };