Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Eric Auger <eric.auger@redhat.com>
To:     eric.auger.pro@gmail.com, eric.auger@redhat.com,
        iommu@lists.linux-foundation.org, linux-kernel@vger.kernel.org,
        kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu, joro@8bytes.org,
        will@kernel.org, robin.murphy@arm.com, jean-philippe@linaro.org,
        zhukeqian1@huawei.com
Cc:     alex.williamson@redhat.com, jacob.jun.pan@linux.intel.com,
        yi.l.liu@intel.com, kevin.tian@intel.com, ashok.raj@intel.com,
        maz@kernel.org, peter.maydell@linaro.org, vivek.gautam@arm.com,
        shameerali.kolothum.thodi@huawei.com, wangxingang5@huawei.com,
        jiangkunkun@huawei.com, yuzenghui@huawei.com,
        nicoleotsuka@gmail.com, chenxiang66@hisilicon.com,
        sumitg@nvidia.com, nicolinc@nvidia.com, vdumpa@nvidia.com,
        zhangfei.gao@linaro.org, zhangfei.gao@gmail.com,
        lushenming@huawei.com, vsethi@nvidia.com
Subject: [RFC v16 6/9] iommu/smmuv3: Allow stage 1 invalidation with unmanaged ASIDs
Date:   Wed, 27 Oct 2021 12:44:25 +0200
Message-Id: <20211027104428.1059740-7-eric.auger@redhat.com>
In-Reply-To: <20211027104428.1059740-1-eric.auger@redhat.com>
References: <20211027104428.1059740-1-eric.auger@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

With nested stage support, soon we will need to invalidate
S1 contexts and ranges tagged with an unmanaged asid, this
latter being managed by the guest. So let's introduce 2 helpers
that allow to invalidate with externally managed ASIDs

Signed-off-by: Eric Auger <eric.auger@redhat.com>

---

v15 -> v16:
- Use arm_smmu_cmdq_issue_cmd_with_sync()

v14 -> v15:
- Always send CMDQ_OP_TLBI_NH_VA and do not test
  smmu_domain->smmu->features & ARM_SMMU_FEAT_E2H as the guest does
  not run in hyp mode atm (Zenghui).

v13 -> v14
- Actually send the NH_ASID command (reported by Xingang Wang)
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 41 ++++++++++++++++-----
 1 file changed, 32 insertions(+), 9 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 bb2681581283..d5e722105624 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1871,9 +1871,9 @@ int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, int ssid,
 }
 
 /* IO_PGTABLE API */
-static void arm_smmu_tlb_inv_context(void *cookie)
+static void __arm_smmu_tlb_inv_context(struct arm_smmu_domain *smmu_domain,
+				       int ext_asid)
 {
-	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_cmdq_ent cmd;
 
@@ -1884,7 +1884,12 @@ static void arm_smmu_tlb_inv_context(void *cookie)
 	 * insertion to guarantee those are observed before the TLBI. Do be
 	 * careful, 007.
 	 */
-	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+	if (ext_asid >= 0) { /* guest stage 1 invalidation */
+		cmd.opcode	= CMDQ_OP_TLBI_NH_ASID;
+		cmd.tlbi.asid	= ext_asid;
+		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
+		arm_smmu_cmdq_issue_cmd_with_sync(smmu, &cmd);
+	} else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
 		arm_smmu_tlb_inv_asid(smmu, smmu_domain->s1_cfg.cd.asid);
 	} else {
 		cmd.opcode	= CMDQ_OP_TLBI_S12_VMALL;
@@ -1894,6 +1899,13 @@ static void arm_smmu_tlb_inv_context(void *cookie)
 	arm_smmu_atc_inv_domain(smmu_domain, 0, 0, 0);
 }
 
+static void arm_smmu_tlb_inv_context(void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+
+	__arm_smmu_tlb_inv_context(smmu_domain, -1);
+}
+
 static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd,
 				     unsigned long iova, size_t size,
 				     size_t granule,
@@ -1955,9 +1967,10 @@ static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd,
 	arm_smmu_cmdq_batch_submit(smmu, &cmds);
 }
 
-static void arm_smmu_tlb_inv_range_domain(unsigned long iova, size_t size,
-					  size_t granule, bool leaf,
-					  struct arm_smmu_domain *smmu_domain)
+static void
+arm_smmu_tlb_inv_range_domain(unsigned long iova, size_t size,
+			      size_t granule, bool leaf, int ext_asid,
+			      struct arm_smmu_domain *smmu_domain)
 {
 	struct arm_smmu_cmdq_ent cmd = {
 		.tlbi = {
@@ -1965,7 +1978,16 @@ static void arm_smmu_tlb_inv_range_domain(unsigned long iova, size_t size,
 		},
 	};
 
-	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+	if (ext_asid >= 0) {  /* guest stage 1 invalidation */
+		/*
+		 * At the moment the guest only uses NS-EL1, to be
+		 * revisited when nested virt gets supported with E2H
+		 * exposed.
+		 */
+		cmd.opcode	= CMDQ_OP_TLBI_NH_VA;
+		cmd.tlbi.asid	= ext_asid;
+		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
+	} else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
 		cmd.opcode	= smmu_domain->smmu->features & ARM_SMMU_FEAT_E2H ?
 				  CMDQ_OP_TLBI_EL2_VA : CMDQ_OP_TLBI_NH_VA;
 		cmd.tlbi.asid	= smmu_domain->s1_cfg.cd.asid;
@@ -1973,6 +1995,7 @@ static void arm_smmu_tlb_inv_range_domain(unsigned long iova, size_t size,
 		cmd.opcode	= CMDQ_OP_TLBI_S2_IPA;
 		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
 	}
+
 	__arm_smmu_tlb_inv_range(&cmd, iova, size, granule, smmu_domain);
 
 	/*
@@ -2011,7 +2034,7 @@ static void arm_smmu_tlb_inv_page_nosync(struct iommu_iotlb_gather *gather,
 static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size,
 				  size_t granule, void *cookie)
 {
-	arm_smmu_tlb_inv_range_domain(iova, size, granule, false, cookie);
+	arm_smmu_tlb_inv_range_domain(iova, size, granule, false, -1, cookie);
 }
 
 static const struct iommu_flush_ops arm_smmu_flush_ops = {
@@ -2548,7 +2571,7 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
 
 	arm_smmu_tlb_inv_range_domain(gather->start,
 				      gather->end - gather->start + 1,
-				      gather->pgsize, true, smmu_domain);
+				      gather->pgsize, true, -1, smmu_domain);
 }
 
 static phys_addr_t
-- 
2.26.3