From 1a7180ff81aadd21556a5b5df7d0a3280f7d744f Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@linaro.org>
Date: Wed, 20 Jan 2021 17:40:05 -0800
Subject: iommu/arm-smmu-qcom: Add Qualcomm SC8180X impl

The primary SMMU found in Qualcomm SC8180X platform needs to use the
Qualcomm implementation, so add a specific compatible for this.

Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Link: https://lore.kernel.org/r/20210121014005.1612382-2-bjorn.andersson@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index bcda17012aee..82c7edc6e025 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -166,6 +166,7 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,mdss" },
 	{ .compatible = "qcom,sc7180-mdss" },
 	{ .compatible = "qcom,sc7180-mss-pil" },
+	{ .compatible = "qcom,sc8180x-mdss" },
 	{ .compatible = "qcom,sdm845-mdss" },
 	{ .compatible = "qcom,sdm845-mss-pil" },
 	{ }
@@ -327,6 +328,7 @@ static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
 static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
 	{ .compatible = "qcom,msm8998-smmu-v2" },
 	{ .compatible = "qcom,sc7180-smmu-500" },
+	{ .compatible = "qcom,sc8180x-smmu-500" },
 	{ .compatible = "qcom,sdm630-smmu-v2" },
 	{ .compatible = "qcom,sdm845-smmu-500" },
 	{ .compatible = "qcom,sm8150-smmu-500" },
-- 
cgit v1.2.3


From d8498b1e4ecc75d023c59acb30e15e3d8d8f07ea Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Fri, 15 Jan 2021 14:33:22 +0530
Subject: iommu: arm-smmu-impl: Add SM8350 qcom iommu implementation

Add SM8350 qcom iommu implementation to the table of
qcom_smmu_impl_of_match table which brings in iommu support for SM8350
SoC

Signed-off-by: Vinod Koul <vkoul@kernel.org>
Link: https://lore.kernel.org/r/20210115090322.2287538-2-vkoul@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 82c7edc6e025..3b6fdbb6c916 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -333,6 +333,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
 	{ .compatible = "qcom,sdm845-smmu-500" },
 	{ .compatible = "qcom,sm8150-smmu-500" },
 	{ .compatible = "qcom,sm8250-smmu-500" },
+	{ .compatible = "qcom,sm8350-smmu-500" },
 	{ }
 };
 
-- 
cgit v1.2.3


From 86d2d9214880c1879cb0ff466cce2fcd9c853e44 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Thu, 21 Jan 2021 14:09:42 +0000
Subject: iommu/arm-smmu-v3: Remove the page 1 fixup

Since we now keep track of page 1 via a separate pointer that already
encapsulates aliasing to page 0 as necessary, we can remove the clunky
fixup routine and simply use the relevant bases directly. The current
architecture spec (IHI0070D.a) defines SMMU_{EVENTQ,PRIQ}_{PROD,CONS} as
offsets relative to page 1, so the cleanup represents a little bit of
convergence as well as just lines of code saved.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/08d9bda570bb5681f11a2f250a31be9ef763b8c5.1611238182.git.robin.murphy@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 42 +++++++++++------------------
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  8 +++---
 2 files changed, 20 insertions(+), 30 deletions(-)

(limited to 'drivers/iommu')

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 8ca7415d785d..bca458c00e48 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -88,15 +88,6 @@ static struct arm_smmu_option_prop arm_smmu_options[] = {
 	{ 0, NULL},
 };
 
-static inline void __iomem *arm_smmu_page1_fixup(unsigned long offset,
-						 struct arm_smmu_device *smmu)
-{
-	if (offset > SZ_64K)
-		return smmu->page1 + offset - SZ_64K;
-
-	return smmu->base + offset;
-}
-
 static void parse_driver_options(struct arm_smmu_device *smmu)
 {
 	int i = 0;
@@ -2611,6 +2602,7 @@ static struct iommu_ops arm_smmu_ops = {
 /* Probing and initialisation functions */
 static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
 				   struct arm_smmu_queue *q,
+				   void __iomem *page,
 				   unsigned long prod_off,
 				   unsigned long cons_off,
 				   size_t dwords, const char *name)
@@ -2639,8 +2631,8 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
 			 1 << q->llq.max_n_shift, name);
 	}
 
-	q->prod_reg	= arm_smmu_page1_fixup(prod_off, smmu);
-	q->cons_reg	= arm_smmu_page1_fixup(cons_off, smmu);
+	q->prod_reg	= page + prod_off;
+	q->cons_reg	= page + cons_off;
 	q->ent_dwords	= dwords;
 
 	q->q_base  = Q_BASE_RWA;
@@ -2684,9 +2676,9 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
 	int ret;
 
 	/* cmdq */
-	ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD,
-				      ARM_SMMU_CMDQ_CONS, CMDQ_ENT_DWORDS,
-				      "cmdq");
+	ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, smmu->base,
+				      ARM_SMMU_CMDQ_PROD, ARM_SMMU_CMDQ_CONS,
+				      CMDQ_ENT_DWORDS, "cmdq");
 	if (ret)
 		return ret;
 
@@ -2695,9 +2687,9 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
 		return ret;
 
 	/* evtq */
-	ret = arm_smmu_init_one_queue(smmu, &smmu->evtq.q, ARM_SMMU_EVTQ_PROD,
-				      ARM_SMMU_EVTQ_CONS, EVTQ_ENT_DWORDS,
-				      "evtq");
+	ret = arm_smmu_init_one_queue(smmu, &smmu->evtq.q, smmu->page1,
+				      ARM_SMMU_EVTQ_PROD, ARM_SMMU_EVTQ_CONS,
+				      EVTQ_ENT_DWORDS, "evtq");
 	if (ret)
 		return ret;
 
@@ -2705,9 +2697,9 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
 	if (!(smmu->features & ARM_SMMU_FEAT_PRI))
 		return 0;
 
-	return arm_smmu_init_one_queue(smmu, &smmu->priq.q, ARM_SMMU_PRIQ_PROD,
-				       ARM_SMMU_PRIQ_CONS, PRIQ_ENT_DWORDS,
-				       "priq");
+	return arm_smmu_init_one_queue(smmu, &smmu->priq.q, smmu->page1,
+				       ARM_SMMU_PRIQ_PROD, ARM_SMMU_PRIQ_CONS,
+				       PRIQ_ENT_DWORDS, "priq");
 }
 
 static int arm_smmu_init_l1_strtab(struct arm_smmu_device *smmu)
@@ -3099,10 +3091,8 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 
 	/* Event queue */
 	writeq_relaxed(smmu->evtq.q.q_base, smmu->base + ARM_SMMU_EVTQ_BASE);
-	writel_relaxed(smmu->evtq.q.llq.prod,
-		       arm_smmu_page1_fixup(ARM_SMMU_EVTQ_PROD, smmu));
-	writel_relaxed(smmu->evtq.q.llq.cons,
-		       arm_smmu_page1_fixup(ARM_SMMU_EVTQ_CONS, smmu));
+	writel_relaxed(smmu->evtq.q.llq.prod, smmu->page1 + ARM_SMMU_EVTQ_PROD);
+	writel_relaxed(smmu->evtq.q.llq.cons, smmu->page1 + ARM_SMMU_EVTQ_CONS);
 
 	enables |= CR0_EVTQEN;
 	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
@@ -3117,9 +3107,9 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 		writeq_relaxed(smmu->priq.q.q_base,
 			       smmu->base + ARM_SMMU_PRIQ_BASE);
 		writel_relaxed(smmu->priq.q.llq.prod,
-			       arm_smmu_page1_fixup(ARM_SMMU_PRIQ_PROD, smmu));
+			       smmu->page1 + ARM_SMMU_PRIQ_PROD);
 		writel_relaxed(smmu->priq.q.llq.cons,
-			       arm_smmu_page1_fixup(ARM_SMMU_PRIQ_CONS, smmu));
+			       smmu->page1 + ARM_SMMU_PRIQ_CONS);
 
 		enables |= CR0_PRIQEN;
 		ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
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 96c2e9565e00..da525f46dab4 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -139,15 +139,15 @@
 #define ARM_SMMU_CMDQ_CONS		0x9c
 
 #define ARM_SMMU_EVTQ_BASE		0xa0
-#define ARM_SMMU_EVTQ_PROD		0x100a8
-#define ARM_SMMU_EVTQ_CONS		0x100ac
+#define ARM_SMMU_EVTQ_PROD		0xa8
+#define ARM_SMMU_EVTQ_CONS		0xac
 #define ARM_SMMU_EVTQ_IRQ_CFG0		0xb0
 #define ARM_SMMU_EVTQ_IRQ_CFG1		0xb8
 #define ARM_SMMU_EVTQ_IRQ_CFG2		0xbc
 
 #define ARM_SMMU_PRIQ_BASE		0xc0
-#define ARM_SMMU_PRIQ_PROD		0x100c8
-#define ARM_SMMU_PRIQ_CONS		0x100cc
+#define ARM_SMMU_PRIQ_PROD		0xc8
+#define ARM_SMMU_PRIQ_CONS		0xcc
 #define ARM_SMMU_PRIQ_IRQ_CFG0		0xd0
 #define ARM_SMMU_PRIQ_IRQ_CFG1		0xd8
 #define ARM_SMMU_PRIQ_IRQ_CFG2		0xdc
-- 
cgit v1.2.3


From 932bc8c7d742c30ce61f2add6cd1340795b0051c Mon Sep 17 00:00:00 2001
From: Zhen Lei <thunder.leizhen@huawei.com>
Date: Fri, 22 Jan 2021 21:14:48 +0800
Subject: iommu/arm-smmu-v3: Use DEFINE_RES_MEM() to simplify code

No functional change.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Link: https://lore.kernel.org/r/20210122131448.1167-1-thunder.leizhen@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

(limited to 'drivers/iommu')

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 bca458c00e48..f04c55a7503c 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -3479,11 +3479,7 @@ err_reset_pci_ops: __maybe_unused;
 static void __iomem *arm_smmu_ioremap(struct device *dev, resource_size_t start,
 				      resource_size_t size)
 {
-	struct resource res = {
-		.flags = IORESOURCE_MEM,
-		.start = start,
-		.end = start + size - 1,
-	};
+	struct resource res = DEFINE_RES_MEM(start, size);
 
 	return devm_ioremap_resource(dev, &res);
 }
-- 
cgit v1.2.3


From eba8d2f8f80315094b61eaf2bc6cd481741d6d93 Mon Sep 17 00:00:00 2001
From: Jean-Philippe Brucker <jean-philippe@linaro.org>
Date: Fri, 22 Jan 2021 16:10:54 +0100
Subject: iommu/arm-smmu-v3: Split arm_smmu_tlb_inv_range()

Extract some of the cmd initialization and the ATC invalidation from
arm_smmu_tlb_inv_range(), to allow an MMU notifier to invalidate a VA
range by ASID.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/r/20210122151054.2833521-2-jean-philippe@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 63 ++++++++++++++++-------------
 1 file changed, 36 insertions(+), 27 deletions(-)

(limited to 'drivers/iommu')

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 f04c55a7503c..86cbac77c941 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1658,40 +1658,28 @@ 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_range(unsigned long iova, size_t size,
-				   size_t granule, bool leaf,
-				   struct arm_smmu_domain *smmu_domain)
+static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd,
+				     unsigned long iova, size_t size,
+				     size_t granule,
+				     struct arm_smmu_domain *smmu_domain)
 {
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
-	unsigned long start = iova, end = iova + size, num_pages = 0, tg = 0;
+	unsigned long end = iova + size, num_pages = 0, tg = 0;
 	size_t inv_range = granule;
 	struct arm_smmu_cmdq_batch cmds = {};
-	struct arm_smmu_cmdq_ent cmd = {
-		.tlbi = {
-			.leaf	= leaf,
-		},
-	};
 
 	if (!size)
 		return;
 
-	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
-		cmd.opcode	= CMDQ_OP_TLBI_NH_VA;
-		cmd.tlbi.asid	= smmu_domain->s1_cfg.cd.asid;
-	} else {
-		cmd.opcode	= CMDQ_OP_TLBI_S2_IPA;
-		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
-	}
-
 	if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) {
 		/* Get the leaf page size */
 		tg = __ffs(smmu_domain->domain.pgsize_bitmap);
 
 		/* Convert page size of 12,14,16 (log2) to 1,2,3 */
-		cmd.tlbi.tg = (tg - 10) / 2;
+		cmd->tlbi.tg = (tg - 10) / 2;
 
 		/* Determine what level the granule is at */
-		cmd.tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3));
+		cmd->tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3));
 
 		num_pages = size >> tg;
 	}
@@ -1709,11 +1697,11 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size,
 
 			/* Determine the power of 2 multiple number of pages */
 			scale = __ffs(num_pages);
-			cmd.tlbi.scale = scale;
+			cmd->tlbi.scale = scale;
 
 			/* Determine how many chunks of 2^scale size we have */
 			num = (num_pages >> scale) & CMDQ_TLBI_RANGE_NUM_MAX;
-			cmd.tlbi.num = num - 1;
+			cmd->tlbi.num = num - 1;
 
 			/* range is num * 2^scale * pgsize */
 			inv_range = num << (scale + tg);
@@ -1722,17 +1710,37 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size,
 			num_pages -= num << scale;
 		}
 
-		cmd.tlbi.addr = iova;
-		arm_smmu_cmdq_batch_add(smmu, &cmds, &cmd);
+		cmd->tlbi.addr = iova;
+		arm_smmu_cmdq_batch_add(smmu, &cmds, cmd);
 		iova += inv_range;
 	}
 	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)
+{
+	struct arm_smmu_cmdq_ent cmd = {
+		.tlbi = {
+			.leaf	= leaf,
+		},
+	};
+
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+		cmd.opcode	= CMDQ_OP_TLBI_NH_VA;
+		cmd.tlbi.asid	= smmu_domain->s1_cfg.cd.asid;
+	} else {
+		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);
 
 	/*
 	 * Unfortunately, this can't be leaf-only since we may have
 	 * zapped an entire table.
 	 */
-	arm_smmu_atc_inv_domain(smmu_domain, 0, start, size);
+	arm_smmu_atc_inv_domain(smmu_domain, 0, iova, size);
 }
 
 static void arm_smmu_tlb_inv_page_nosync(struct iommu_iotlb_gather *gather,
@@ -1748,7 +1756,7 @@ 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(iova, size, granule, false, cookie);
+	arm_smmu_tlb_inv_range_domain(iova, size, granule, false, cookie);
 }
 
 static const struct iommu_flush_ops arm_smmu_flush_ops = {
@@ -2271,8 +2279,9 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
-	arm_smmu_tlb_inv_range(gather->start, gather->end - gather->start,
-			       gather->pgsize, true, smmu_domain);
+	arm_smmu_tlb_inv_range_domain(gather->start,
+				      gather->end - gather->start,
+				      gather->pgsize, true, smmu_domain);
 }
 
 static phys_addr_t
-- 
cgit v1.2.3


From 51d113c3be09ff5b916576b1109daf413549cacc Mon Sep 17 00:00:00 2001
From: Jean-Philippe Brucker <jean-philippe@linaro.org>
Date: Fri, 22 Jan 2021 16:10:55 +0100
Subject: iommu/arm-smmu-v3: Make BTM optional for SVA

When BTM isn't supported by the SMMU, send invalidations on the
command queue.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/r/20210122151054.2833521-3-jean-philippe@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 10 +++++++---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c     | 15 +++++++++++++++
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h     |  3 +++
 3 files changed, 25 insertions(+), 3 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index e13b092e6004..bb251cab61f3 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -182,9 +182,13 @@ static void arm_smmu_mm_invalidate_range(struct mmu_notifier *mn,
 					 unsigned long start, unsigned long end)
 {
 	struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn);
+	struct arm_smmu_domain *smmu_domain = smmu_mn->domain;
+	size_t size = end - start + 1;
 
-	arm_smmu_atc_inv_domain(smmu_mn->domain, mm->pasid, start,
-				end - start + 1);
+	if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_BTM))
+		arm_smmu_tlb_inv_range_asid(start, size, smmu_mn->cd->asid,
+					    PAGE_SIZE, false, smmu_domain);
+	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, start, size);
 }
 
 static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
@@ -391,7 +395,7 @@ bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
 	unsigned long reg, fld;
 	unsigned long oas;
 	unsigned long asid_bits;
-	u32 feat_mask = ARM_SMMU_FEAT_BTM | ARM_SMMU_FEAT_COHERENCY;
+	u32 feat_mask = ARM_SMMU_FEAT_COHERENCY;
 
 	if (vabits_actual == 52)
 		feat_mask |= ARM_SMMU_FEAT_VAX;
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 86cbac77c941..111467888e88 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1743,6 +1743,21 @@ static void arm_smmu_tlb_inv_range_domain(unsigned long iova, size_t size,
 	arm_smmu_atc_inv_domain(smmu_domain, 0, iova, size);
 }
 
+void arm_smmu_tlb_inv_range_asid(unsigned long iova, size_t size, int asid,
+				 size_t granule, bool leaf,
+				 struct arm_smmu_domain *smmu_domain)
+{
+	struct arm_smmu_cmdq_ent cmd = {
+		.opcode	= CMDQ_OP_TLBI_NH_VA,
+		.tlbi = {
+			.asid	= asid,
+			.leaf	= leaf,
+		},
+	};
+
+	__arm_smmu_tlb_inv_range(&cmd, iova, size, granule, smmu_domain);
+}
+
 static void arm_smmu_tlb_inv_page_nosync(struct iommu_iotlb_gather *gather,
 					 unsigned long iova, size_t granule,
 					 void *cookie)
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 da525f46dab4..56bc0c3d4f4a 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -694,6 +694,9 @@ extern struct arm_smmu_ctx_desc quiet_cd;
 int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
 			    struct arm_smmu_ctx_desc *cd);
 void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid);
+void arm_smmu_tlb_inv_range_asid(unsigned long iova, size_t size, int asid,
+				 size_t granule, bool leaf,
+				 struct arm_smmu_domain *smmu_domain);
 bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd);
 int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, int ssid,
 			    unsigned long iova, size_t size);
-- 
cgit v1.2.3


From 9111aebf770d6a6c9fcfd6301da4a0025f2d610f Mon Sep 17 00:00:00 2001
From: Jean-Philippe Brucker <jean-philippe@linaro.org>
Date: Fri, 22 Jan 2021 16:10:56 +0100
Subject: iommu/arm-smmu-v3: Add support for VHE

ARMv8.1 extensions added Virtualization Host Extensions (VHE), which allow
to run a host kernel at EL2. When using normal DMA, Device and CPU address
spaces are dissociated, and do not need to implement the same
capabilities, so VHE hasn't been used in the SMMU until now.

With shared address spaces however, ASIDs are shared between MMU and SMMU,
and broadcast TLB invalidations issued by a CPU are taken into account by
the SMMU. TLB entries on both sides need to have identical exception level
in order to be cleared with a single invalidation.

When the CPU is using VHE, enable VHE in the SMMU for all STEs. Normal DMA
mappings will need to use TLBI_EL2 commands instead of TLBI_NH, but
shouldn't be otherwise affected by this change.

Acked-by: Will Deacon <will@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/r/20210122151054.2833521-4-jean-philippe@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 32 ++++++++++++++++++++++-------
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  3 +++
 2 files changed, 28 insertions(+), 7 deletions(-)

(limited to 'drivers/iommu')

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 111467888e88..baebaac34a83 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -263,9 +263,11 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31);
 		break;
 	case CMDQ_OP_TLBI_NH_VA:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
+		fallthrough;
+	case CMDQ_OP_TLBI_EL2_VA:
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num);
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale);
-		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid);
 		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf);
 		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl);
@@ -287,6 +289,9 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 	case CMDQ_OP_TLBI_S12_VMALL:
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
 		break;
+	case CMDQ_OP_TLBI_EL2_ASID:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid);
+		break;
 	case CMDQ_OP_ATC_INV:
 		cmd[0] |= FIELD_PREP(CMDQ_0_SSV, ent->substream_valid);
 		cmd[0] |= FIELD_PREP(CMDQ_ATC_0_GLOBAL, ent->atc.global);
@@ -877,7 +882,8 @@ static int arm_smmu_cmdq_batch_submit(struct arm_smmu_device *smmu,
 void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid)
 {
 	struct arm_smmu_cmdq_ent cmd = {
-		.opcode = CMDQ_OP_TLBI_NH_ASID,
+		.opcode	= smmu->features & ARM_SMMU_FEAT_E2H ?
+			CMDQ_OP_TLBI_EL2_ASID : CMDQ_OP_TLBI_NH_ASID,
 		.tlbi.asid = asid,
 	};
 
@@ -1260,13 +1266,16 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	}
 
 	if (s1_cfg) {
+		u64 strw = smmu->features & ARM_SMMU_FEAT_E2H ?
+			STRTAB_STE_1_STRW_EL2 : STRTAB_STE_1_STRW_NSEL1;
+
 		BUG_ON(ste_live);
 		dst[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) |
 			 FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) |
-			 FIELD_PREP(STRTAB_STE_1_STRW, STRTAB_STE_1_STRW_NSEL1));
+			 FIELD_PREP(STRTAB_STE_1_STRW, strw));
 
 		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
 		   !(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))
@@ -1728,7 +1737,8 @@ static void arm_smmu_tlb_inv_range_domain(unsigned long iova, size_t size,
 	};
 
 	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
-		cmd.opcode	= CMDQ_OP_TLBI_NH_VA;
+		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;
 	} else {
 		cmd.opcode	= CMDQ_OP_TLBI_S2_IPA;
@@ -1748,7 +1758,8 @@ void arm_smmu_tlb_inv_range_asid(unsigned long iova, size_t size, int asid,
 				 struct arm_smmu_domain *smmu_domain)
 {
 	struct arm_smmu_cmdq_ent cmd = {
-		.opcode	= CMDQ_OP_TLBI_NH_VA,
+		.opcode	= smmu_domain->smmu->features & ARM_SMMU_FEAT_E2H ?
+			  CMDQ_OP_TLBI_EL2_VA : CMDQ_OP_TLBI_NH_VA,
 		.tlbi = {
 			.asid	= asid,
 			.leaf	= leaf,
@@ -3076,7 +3087,11 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 	writel_relaxed(reg, smmu->base + ARM_SMMU_CR1);
 
 	/* CR2 (random crap) */
-	reg = CR2_PTM | CR2_RECINVSID | CR2_E2H;
+	reg = CR2_PTM | CR2_RECINVSID;
+
+	if (smmu->features & ARM_SMMU_FEAT_E2H)
+		reg |= CR2_E2H;
+
 	writel_relaxed(reg, smmu->base + ARM_SMMU_CR2);
 
 	/* Stream table */
@@ -3235,8 +3250,11 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 			smmu->options |= ARM_SMMU_OPT_MSIPOLL;
 	}
 
-	if (reg & IDR0_HYP)
+	if (reg & IDR0_HYP) {
 		smmu->features |= ARM_SMMU_FEAT_HYP;
+		if (cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN))
+			smmu->features |= ARM_SMMU_FEAT_E2H;
+	}
 
 	/*
 	 * The coherency feature as set by FW is used in preference to the ID
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 56bc0c3d4f4a..f985817c967a 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -430,6 +430,8 @@ struct arm_smmu_cmdq_ent {
 		#define CMDQ_OP_TLBI_NH_ASID	0x11
 		#define CMDQ_OP_TLBI_NH_VA	0x12
 		#define CMDQ_OP_TLBI_EL2_ALL	0x20
+		#define CMDQ_OP_TLBI_EL2_ASID	0x21
+		#define CMDQ_OP_TLBI_EL2_VA	0x22
 		#define CMDQ_OP_TLBI_S12_VMALL	0x28
 		#define CMDQ_OP_TLBI_S2_IPA	0x2a
 		#define CMDQ_OP_TLBI_NSNH_ALL	0x30
@@ -604,6 +606,7 @@ struct arm_smmu_device {
 #define ARM_SMMU_FEAT_RANGE_INV		(1 << 15)
 #define ARM_SMMU_FEAT_BTM		(1 << 16)
 #define ARM_SMMU_FEAT_SVA		(1 << 17)
+#define ARM_SMMU_FEAT_E2H		(1 << 18)
 	u32				features;
 
 #define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
-- 
cgit v1.2.3


From dead723e6f049e9fb6b05e5b93456982798ea961 Mon Sep 17 00:00:00 2001
From: "Isaac J. Manjarres" <isaacm@codeaurora.org>
Date: Mon, 25 Jan 2021 13:52:25 -0800
Subject: iommu/arm-smmu-qcom: Fix mask extraction for bootloader programmed
 SMRs

When extracting the mask for a SMR that was programmed by the
bootloader, the SMR's valid bit is also extracted and is treated
as part of the mask, which is not correct. Consider the scenario
where an SMMU master whose context is determined by a bootloader
programmed SMR is removed (omitting parts of device/driver core):

->iommu_release_device()
 -> arm_smmu_release_device()
  -> arm_smmu_master_free_smes()
   -> arm_smmu_free_sme() /* Assume that the SME is now free */
   -> arm_smmu_write_sme()
    -> arm_smmu_write_smr() /* Construct SMR value using mask and SID */

Since the valid bit was considered as part of the mask, the SMR will
be programmed as valid.

Fix the SMR mask extraction step for bootloader programmed SMRs
by masking out the valid bit when we know that we're already
working with a valid SMR.

Fixes: 07a7f2caaa5a ("iommu/arm-smmu-qcom: Read back stream mappings")
Signed-off-by: Isaac J. Manjarres <isaacm@codeaurora.org>
Cc: stable@vger.kernel.org
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/1611611545-19055-1-git-send-email-isaacm@codeaurora.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 3b6fdbb6c916..98b3a1c2a181 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -207,6 +207,8 @@ static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
 		smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(i));
 
 		if (FIELD_GET(ARM_SMMU_SMR_VALID, smr)) {
+			/* Ignore valid bit for SMR mask extraction. */
+			smr &= ~ARM_SMMU_SMR_VALID;
 			smmu->smrs[i].id = FIELD_GET(ARM_SMMU_SMR_ID, smr);
 			smmu->smrs[i].mask = FIELD_GET(ARM_SMMU_SMR_MASK, smr);
 			smmu->smrs[i].valid = true;
-- 
cgit v1.2.3


From d8c1df02ac7f2c802a9b2afc0f5c888c4217f1d5 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Thu, 7 Jan 2021 20:29:03 +0800
Subject: iommu: Move iotlb_sync_map out from __iommu_map

In the end of __iommu_map, It alway call iotlb_sync_map.

This patch moves iotlb_sync_map out from __iommu_map since it is
unnecessary to call this for each sg segment especially iotlb_sync_map
is flush tlb all currently. Add a little helper _iommu_map for this.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20210107122909.16317-2-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/iommu.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index ffeebda8d6de..c304a6a30d42 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2426,9 +2426,6 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
 		size -= pgsize;
 	}
 
-	if (ops->iotlb_sync_map)
-		ops->iotlb_sync_map(domain);
-
 	/* unroll mapping in case something went wrong */
 	if (ret)
 		iommu_unmap(domain, orig_iova, orig_size - size);
@@ -2438,18 +2435,31 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
 	return ret;
 }
 
+static int _iommu_map(struct iommu_domain *domain, unsigned long iova,
+		      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	const struct iommu_ops *ops = domain->ops;
+	int ret;
+
+	ret = __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
+	if (ret == 0 && ops->iotlb_sync_map)
+		ops->iotlb_sync_map(domain);
+
+	return ret;
+}
+
 int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	      phys_addr_t paddr, size_t size, int prot)
 {
 	might_sleep();
-	return __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
+	return _iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(iommu_map);
 
 int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
 	      phys_addr_t paddr, size_t size, int prot)
 {
-	return __iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC);
+	return _iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC);
 }
 EXPORT_SYMBOL_GPL(iommu_map_atomic);
 
@@ -2533,6 +2543,7 @@ static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			     struct scatterlist *sg, unsigned int nents, int prot,
 			     gfp_t gfp)
 {
+	const struct iommu_ops *ops = domain->ops;
 	size_t len = 0, mapped = 0;
 	phys_addr_t start;
 	unsigned int i = 0;
@@ -2563,6 +2574,8 @@ static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			sg = sg_next(sg);
 	}
 
+	if (ops->iotlb_sync_map)
+		ops->iotlb_sync_map(domain);
 	return mapped;
 
 out_err:
-- 
cgit v1.2.3


From 2ebbd25873cef06f739489fd8ff9f707a3dfa2fa Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Thu, 7 Jan 2021 20:29:04 +0800
Subject: iommu: Add iova and size as parameters in iotlb_sync_map

iotlb_sync_map allow IOMMU drivers tlb sync after completing the whole
mapping. This patch adds iova and size as the parameters in it. then the
IOMMU driver could flush tlb with the whole range once after iova mapping
to improve performance.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20210107122909.16317-3-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/iommu.c      | 4 ++--
 drivers/iommu/tegra-gart.c | 7 +++++--
 include/linux/iommu.h      | 3 ++-
 3 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index c304a6a30d42..3d099a31ddca 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2443,7 +2443,7 @@ static int _iommu_map(struct iommu_domain *domain, unsigned long iova,
 
 	ret = __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
 	if (ret == 0 && ops->iotlb_sync_map)
-		ops->iotlb_sync_map(domain);
+		ops->iotlb_sync_map(domain, iova, size);
 
 	return ret;
 }
@@ -2575,7 +2575,7 @@ static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 	}
 
 	if (ops->iotlb_sync_map)
-		ops->iotlb_sync_map(domain);
+		ops->iotlb_sync_map(domain, iova, mapped);
 	return mapped;
 
 out_err:
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index fac720273889..05e8e19b8269 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -261,7 +261,8 @@ static int gart_iommu_of_xlate(struct device *dev,
 	return 0;
 }
 
-static void gart_iommu_sync_map(struct iommu_domain *domain)
+static void gart_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+				size_t size)
 {
 	FLUSH_GART_REGS(gart_handle);
 }
@@ -269,7 +270,9 @@ static void gart_iommu_sync_map(struct iommu_domain *domain)
 static void gart_iommu_sync(struct iommu_domain *domain,
 			    struct iommu_iotlb_gather *gather)
 {
-	gart_iommu_sync_map(domain);
+	size_t length = gather->end - gather->start;
+
+	gart_iommu_sync_map(domain, gather->start, length);
 }
 
 static const struct iommu_ops gart_iommu_ops = {
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index b3f0e2018c62..9ce0aa9e236b 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -246,7 +246,8 @@ struct iommu_ops {
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
 		     size_t size, struct iommu_iotlb_gather *iotlb_gather);
 	void (*flush_iotlb_all)(struct iommu_domain *domain);
-	void (*iotlb_sync_map)(struct iommu_domain *domain);
+	void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova,
+			       size_t size);
 	void (*iotlb_sync)(struct iommu_domain *domain,
 			   struct iommu_iotlb_gather *iotlb_gather);
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova);
-- 
cgit v1.2.3


From 20143451eff044310520932fb372704c99658b33 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Thu, 7 Jan 2021 20:29:05 +0800
Subject: iommu/mediatek: Add iotlb_sync_map to sync whole the iova range

Remove IO_PGTABLE_QUIRK_TLBI_ON_MAP to avoid tlb sync for each a small
chunk memory, Use the new iotlb_sync_map to tlb_sync once for whole the
iova range of iommu_map.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20210107122909.16317-4-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 8e56cec532e7..f579fc21971e 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -322,7 +322,6 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
 	dom->cfg = (struct io_pgtable_cfg) {
 		.quirks = IO_PGTABLE_QUIRK_ARM_NS |
 			IO_PGTABLE_QUIRK_NO_PERMS |
-			IO_PGTABLE_QUIRK_TLBI_ON_MAP |
 			IO_PGTABLE_QUIRK_ARM_MTK_EXT,
 		.pgsize_bitmap = mtk_iommu_ops.pgsize_bitmap,
 		.ias = 32,
@@ -453,6 +452,14 @@ static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
 				       data);
 }
 
+static void mtk_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+			       size_t size)
+{
+	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
+
+	mtk_iommu_tlb_flush_range_sync(iova, size, size, data);
+}
+
 static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 					  dma_addr_t iova)
 {
@@ -539,6 +546,7 @@ static const struct iommu_ops mtk_iommu_ops = {
 	.unmap		= mtk_iommu_unmap,
 	.flush_iotlb_all = mtk_iommu_flush_iotlb_all,
 	.iotlb_sync	= mtk_iommu_iotlb_sync,
+	.iotlb_sync_map	= mtk_iommu_sync_map,
 	.iova_to_phys	= mtk_iommu_iova_to_phys,
 	.probe_device	= mtk_iommu_probe_device,
 	.release_device	= mtk_iommu_release_device,
-- 
cgit v1.2.3


From 862c3715de8f3e5350489240c951d697f04bd8c9 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Thu, 7 Jan 2021 20:29:06 +0800
Subject: iommu: Switch gather->end to the inclusive end

Currently gather->end is "unsigned long" which may be overflow in
arch32 in the corner case: 0xfff00000 + 0x100000(iova + size).
Although it doesn't affect the size(end - start), it affects the checking
"gather->end < end"

This patch changes this "end" to the real end address
(end = start + size - 1). Correspondingly, update the length to
"end - start + 1".

Fixes: a7d20dc19d9e ("iommu: Introduce struct iommu_iotlb_gather for batching TLB flushes")
Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20210107122909.16317-5-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 +-
 drivers/iommu/mtk_iommu.c                   | 2 +-
 drivers/iommu/tegra-gart.c                  | 2 +-
 include/linux/iommu.h                       | 4 ++--
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'drivers/iommu')

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 8ca7415d785d..c70d6e79f534 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2280,7 +2280,7 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
-	arm_smmu_tlb_inv_range(gather->start, gather->end - gather->start,
+	arm_smmu_tlb_inv_range(gather->start, gather->end - gather->start + 1,
 			       gather->pgsize, true, smmu_domain);
 }
 
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index f579fc21971e..66a00a2cb445 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -443,7 +443,7 @@ static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
 				 struct iommu_iotlb_gather *gather)
 {
 	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
-	size_t length = gather->end - gather->start;
+	size_t length = gather->end - gather->start + 1;
 
 	if (gather->start == ULONG_MAX)
 		return;
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index 05e8e19b8269..6f130e51f072 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -270,7 +270,7 @@ static void gart_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
 static void gart_iommu_sync(struct iommu_domain *domain,
 			    struct iommu_iotlb_gather *gather)
 {
-	size_t length = gather->end - gather->start;
+	size_t length = gather->end - gather->start + 1;
 
 	gart_iommu_sync_map(domain, gather->start, length);
 }
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 9ce0aa9e236b..ae8eddd4621b 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -170,7 +170,7 @@ enum iommu_dev_features {
  * struct iommu_iotlb_gather - Range information for a pending IOTLB flush
  *
  * @start: IOVA representing the start of the range to be flushed
- * @end: IOVA representing the end of the range to be flushed (exclusive)
+ * @end: IOVA representing the end of the range to be flushed (inclusive)
  * @pgsize: The interval at which to perform the flush
  *
  * This structure is intended to be updated by multiple calls to the
@@ -539,7 +539,7 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain,
 					       struct iommu_iotlb_gather *gather,
 					       unsigned long iova, size_t size)
 {
-	unsigned long start = iova, end = start + size;
+	unsigned long start = iova, end = start + size - 1;
 
 	/*
 	 * If the new page is disjoint from the current range or is mapped at
-- 
cgit v1.2.3


From f21ae3b100840c1439fb326841f24641cf3de4a1 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Thu, 7 Jan 2021 20:29:08 +0800
Subject: iommu/mediatek: Gather iova in iommu_unmap to achieve tlb sync once

In current iommu_unmap, this code is:

	iommu_iotlb_gather_init(&iotlb_gather);
	ret = __iommu_unmap(domain, iova, size, &iotlb_gather);
	iommu_iotlb_sync(domain, &iotlb_gather);

We could gather the whole iova range in __iommu_unmap, and then do tlb
synchronization in the iommu_iotlb_sync.

This patch implement this, Gather the range in mtk_iommu_unmap.
then iommu_iotlb_sync call tlb synchronization for the gathered iova range.
we don't call iommu_iotlb_gather_add_page since our tlb synchronization
could be regardless of granule size.

In this way, gather->start is impossible ULONG_MAX, remove the checking.

This patch aims to do tlb synchronization *once* in the iommu_unmap.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20210107122909.16317-7-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 66a00a2cb445..d3b8a1649093 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -430,7 +430,12 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain,
 			      struct iommu_iotlb_gather *gather)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	unsigned long end = iova + size - 1;
 
+	if (gather->start > iova)
+		gather->start = iova;
+	if (gather->end < end)
+		gather->end = end;
 	return dom->iop->unmap(dom->iop, iova, size, gather);
 }
 
@@ -445,9 +450,6 @@ static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
 	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
 	size_t length = gather->end - gather->start + 1;
 
-	if (gather->start == ULONG_MAX)
-		return;
-
 	mtk_iommu_tlb_flush_range_sync(gather->start, length, gather->pgsize,
 				       data);
 }
-- 
cgit v1.2.3


From 0954d61a59e3c014e52b8d938bc12dc5a2e4949c Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Thu, 7 Jan 2021 20:29:09 +0800
Subject: iommu/mediatek: Remove the tlb-ops for v7s

Until now, we have already used the tlb operations from iommu framework,
then the tlb operations for v7s can be removed.

Correspondingly, Switch the paramenter "cookie" to the internal structure.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20210107122909.16317-8-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 27 ++++-----------------------
 1 file changed, 4 insertions(+), 23 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index d3b8a1649093..86ab577c9520 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -182,10 +182,8 @@ static struct mtk_iommu_domain *to_mtk_domain(struct iommu_domain *dom)
 	return container_of(dom, struct mtk_iommu_domain, domain);
 }
 
-static void mtk_iommu_tlb_flush_all(void *cookie)
+static void mtk_iommu_tlb_flush_all(struct mtk_iommu_data *data)
 {
-	struct mtk_iommu_data *data = cookie;
-
 	for_each_m4u(data) {
 		writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
 			       data->base + data->plat_data->inv_sel_reg);
@@ -195,9 +193,9 @@ static void mtk_iommu_tlb_flush_all(void *cookie)
 }
 
 static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
-					   size_t granule, void *cookie)
+					   size_t granule,
+					   struct mtk_iommu_data *data)
 {
-	struct mtk_iommu_data *data = cookie;
 	unsigned long flags;
 	int ret;
 	u32 tmp;
@@ -219,7 +217,7 @@ static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
 		if (ret) {
 			dev_warn(data->dev,
 				 "Partial TLB flush timed out, falling back to full flush\n");
-			mtk_iommu_tlb_flush_all(cookie);
+			mtk_iommu_tlb_flush_all(data);
 		}
 		/* Clear the CPE status */
 		writel_relaxed(0, data->base + REG_MMU_CPE_DONE);
@@ -227,22 +225,6 @@ static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
 	}
 }
 
-static void mtk_iommu_tlb_flush_page_nosync(struct iommu_iotlb_gather *gather,
-					    unsigned long iova, size_t granule,
-					    void *cookie)
-{
-	struct mtk_iommu_data *data = cookie;
-	struct iommu_domain *domain = &data->m4u_dom->domain;
-
-	iommu_iotlb_gather_add_page(domain, gather, iova, granule);
-}
-
-static const struct iommu_flush_ops mtk_iommu_flush_ops = {
-	.tlb_flush_all = mtk_iommu_tlb_flush_all,
-	.tlb_flush_walk = mtk_iommu_tlb_flush_range_sync,
-	.tlb_add_page = mtk_iommu_tlb_flush_page_nosync,
-};
-
 static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
 {
 	struct mtk_iommu_data *data = dev_id;
@@ -326,7 +308,6 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
 		.pgsize_bitmap = mtk_iommu_ops.pgsize_bitmap,
 		.ias = 32,
 		.oas = 34,
-		.tlb = &mtk_iommu_flush_ops,
 		.iommu_dev = data->dev,
 	};
 
-- 
cgit v1.2.3


From c867c78acae96fc359f2a2f375ce64b5f0871802 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Wed, 27 Jan 2021 16:29:28 +0000
Subject: iommu/msm: Hook up iotlb_sync_map

The core API can now accommodate invalidate-on-map style behaviour in a
single efficient call, so hook that up instead of having io-pgatble do
it piecemeal.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/e95223a0abf129230a0bec6743f837075f0a2fcb.1611764372.git.robin.murphy@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/msm_iommu.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 040e85f70861..f0ba6a09b434 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -343,7 +343,6 @@ static int msm_iommu_domain_config(struct msm_priv *priv)
 	spin_lock_init(&priv->pgtlock);
 
 	priv->cfg = (struct io_pgtable_cfg) {
-		.quirks = IO_PGTABLE_QUIRK_TLBI_ON_MAP,
 		.pgsize_bitmap = msm_iommu_ops.pgsize_bitmap,
 		.ias = 32,
 		.oas = 32,
@@ -490,6 +489,14 @@ static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova,
 	return ret;
 }
 
+static void msm_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+			       size_t size)
+{
+	struct msm_priv *priv = to_msm_priv(domain);
+
+	__flush_iotlb_range(iova, size, SZ_4K, false, priv);
+}
+
 static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 			      size_t len, struct iommu_iotlb_gather *gather)
 {
@@ -680,6 +687,7 @@ static struct iommu_ops msm_iommu_ops = {
 	 * kick starting the other master.
 	 */
 	.iotlb_sync = NULL,
+	.iotlb_sync_map = msm_iommu_sync_map,
 	.iova_to_phys = msm_iommu_iova_to_phys,
 	.probe_device = msm_iommu_probe_device,
 	.release_device = msm_iommu_release_device,
-- 
cgit v1.2.3


From 3d5eab41451f8e28f3e45eef8f6b372bf56612fb Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Wed, 27 Jan 2021 16:29:29 +0000
Subject: iommu/io-pgtable: Remove TLBI_ON_MAP quirk

IO_PGTABLE_QUIRK_TLBI_ON_MAP is now fully superseded by the
core API's iotlb_sync_map callback.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/5abb80bba3a7c371d5ffb7e59c05586deddb9a91.1611764372.git.robin.murphy@arm.com
[will: Remove unused 'iop' local variable from arm_v7s_map()]
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/io-pgtable-arm-v7s.c | 9 +--------
 include/linux/io-pgtable.h         | 5 -----
 2 files changed, 1 insertion(+), 13 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 1d92ac948db7..929cb1518db1 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -519,7 +519,6 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova,
 			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
-	struct io_pgtable *iop = &data->iop;
 	int ret;
 
 	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias) ||
@@ -535,12 +534,7 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova,
 	 * Synchronise all PTE updates for the new mapping before there's
 	 * a chance for anything to kick off a table walk for the new iova.
 	 */
-	if (iop->cfg.quirks & IO_PGTABLE_QUIRK_TLBI_ON_MAP) {
-		io_pgtable_tlb_flush_walk(iop, iova, size,
-					  ARM_V7S_BLOCK_SIZE(2));
-	} else {
-		wmb();
-	}
+	wmb();
 
 	return ret;
 }
@@ -759,7 +753,6 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
 			    IO_PGTABLE_QUIRK_NO_PERMS |
-			    IO_PGTABLE_QUIRK_TLBI_ON_MAP |
 			    IO_PGTABLE_QUIRK_ARM_MTK_EXT |
 			    IO_PGTABLE_QUIRK_NON_STRICT))
 		return NULL;
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 2a5686ca2ba3..06753323a15e 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -68,10 +68,6 @@ struct io_pgtable_cfg {
 	 *	hardware which does not implement the permissions of a given
 	 *	format, and/or requires some format-specific default value.
 	 *
-	 * IO_PGTABLE_QUIRK_TLBI_ON_MAP: If the format forbids caching invalid
-	 *	(unmapped) entries but the hardware might do so anyway, perform
-	 *	TLB maintenance when mapping as well as when unmapping.
-	 *
 	 * IO_PGTABLE_QUIRK_ARM_MTK_EXT: (ARM v7s format) MediaTek IOMMUs extend
 	 *	to support up to 34 bits PA where the bit32 and bit33 are
 	 *	encoded in the bit9 and bit4 of the PTE respectively.
@@ -88,7 +84,6 @@ struct io_pgtable_cfg {
 	 */
 	#define IO_PGTABLE_QUIRK_ARM_NS		BIT(0)
 	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
-	#define IO_PGTABLE_QUIRK_TLBI_ON_MAP	BIT(2)
 	#define IO_PGTABLE_QUIRK_ARM_MTK_EXT	BIT(3)
 	#define IO_PGTABLE_QUIRK_NON_STRICT	BIT(4)
 	#define IO_PGTABLE_QUIRK_ARM_TTBR1	BIT(5)
-- 
cgit v1.2.3


From 66a28915541549f0fe0f4c705dab77443f22b5d6 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:18:49 +0800
Subject: iommu/mediatek: Use the common mtk-memory-port.h

Use the common memory header(larb-port) in the source code.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Acked-by: Krzysztof Kozlowski <krzk@kernel.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-9-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c  | 7 -------
 drivers/iommu/mtk_iommu.h  | 1 +
 drivers/memory/mtk-smi.c   | 1 +
 include/soc/mediatek/smi.h | 2 --
 4 files changed, 2 insertions(+), 9 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 86ab577c9520..f594971dbeb2 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -103,13 +103,6 @@
 
 #define MTK_PROTECT_PA_ALIGN			256
 
-/*
- * Get the local arbiter ID and the portid within the larb arbiter
- * from mtk_m4u_id which is defined by MTK_M4U_ID.
- */
-#define MTK_M4U_TO_LARB(id)		(((id) >> 5) & 0xf)
-#define MTK_M4U_TO_PORT(id)		((id) & 0x1f)
-
 #define HAS_4GB_MODE			BIT(0)
 /* HW will use the EMI clock if there isn't the "bclk". */
 #define HAS_BCLK			BIT(1)
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
index df32b3e3408b..c1584dea66cb 100644
--- a/drivers/iommu/mtk_iommu.h
+++ b/drivers/iommu/mtk_iommu.h
@@ -17,6 +17,7 @@
 #include <linux/spinlock.h>
 #include <linux/dma-mapping.h>
 #include <soc/mediatek/smi.h>
+#include <dt-bindings/memory/mtk-memory-port.h>
 
 #define MTK_LARB_COM_MAX	8
 #define MTK_LARB_SUBCOM_MAX	4
diff --git a/drivers/memory/mtk-smi.c b/drivers/memory/mtk-smi.c
index ac350f8d1e20..89f92fa2afa5 100644
--- a/drivers/memory/mtk-smi.c
+++ b/drivers/memory/mtk-smi.c
@@ -15,6 +15,7 @@
 #include <linux/pm_runtime.h>
 #include <soc/mediatek/smi.h>
 #include <dt-bindings/memory/mt2701-larb-port.h>
+#include <dt-bindings/memory/mtk-memory-port.h>
 
 /* mt8173 */
 #define SMI_LARB_MMU_EN		0xf00
diff --git a/include/soc/mediatek/smi.h b/include/soc/mediatek/smi.h
index 5a34b87d89e3..9371bf572ab8 100644
--- a/include/soc/mediatek/smi.h
+++ b/include/soc/mediatek/smi.h
@@ -11,8 +11,6 @@
 
 #ifdef CONFIG_MTK_SMI
 
-#define MTK_LARB_NR_MAX		16
-
 #define MTK_SMI_MMU_EN(port)	BIT(port)
 
 struct mtk_smi_larb_iommu {
-- 
cgit v1.2.3


From 859da21112520829638a82f458ac2c8c2637e17d Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:18:50 +0800
Subject: iommu/io-pgtable-arm-v7s: Use ias to check the valid iova in unmap

Use the ias for the valid iova checking in arm_v7s_unmap. This is a
preparing patch for supporting iova 34bit for MediaTek.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-10-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/io-pgtable-arm-v7s.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 929cb1518db1..03f35065acff 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -711,7 +711,7 @@ static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 {
 	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
 
-	if (WARN_ON(upper_32_bits(iova)))
+	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias)))
 		return 0;
 
 	return __arm_v7s_unmap(data, gather, iova, size, 1, data->pgd);
-- 
cgit v1.2.3


From 40596d2f2b6075f6c33180b2f55c814ff4885475 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:18:51 +0800
Subject: iommu/io-pgtable-arm-v7s: Extend PA34 for MediaTek

MediaTek extend the bit5 in lvl1 and lvl2 descriptor as PA34.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Acked-by: Will Deacon <will@kernel.org>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-11-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/io-pgtable-arm-v7s.c | 9 +++++++--
 drivers/iommu/mtk_iommu.c          | 2 +-
 include/linux/io-pgtable.h         | 4 ++--
 3 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 03f35065acff..b1b2ff069040 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -112,9 +112,10 @@
 #define ARM_V7S_TEX_MASK		0x7
 #define ARM_V7S_ATTR_TEX(val)		(((val) & ARM_V7S_TEX_MASK) << ARM_V7S_TEX_SHIFT)
 
-/* MediaTek extend the two bits for PA 32bit/33bit */
+/* MediaTek extend the bits below for PA 32bit/33bit/34bit */
 #define ARM_V7S_ATTR_MTK_PA_BIT32	BIT(9)
 #define ARM_V7S_ATTR_MTK_PA_BIT33	BIT(4)
+#define ARM_V7S_ATTR_MTK_PA_BIT34	BIT(5)
 
 /* *well, except for TEX on level 2 large pages, of course :( */
 #define ARM_V7S_CONT_PAGE_TEX_SHIFT	6
@@ -194,6 +195,8 @@ static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl,
 		pte |= ARM_V7S_ATTR_MTK_PA_BIT32;
 	if (paddr & BIT_ULL(33))
 		pte |= ARM_V7S_ATTR_MTK_PA_BIT33;
+	if (paddr & BIT_ULL(34))
+		pte |= ARM_V7S_ATTR_MTK_PA_BIT34;
 	return pte;
 }
 
@@ -218,6 +221,8 @@ static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl,
 		paddr |= BIT_ULL(32);
 	if (pte & ARM_V7S_ATTR_MTK_PA_BIT33)
 		paddr |= BIT_ULL(33);
+	if (pte & ARM_V7S_ATTR_MTK_PA_BIT34)
+		paddr |= BIT_ULL(34);
 	return paddr;
 }
 
@@ -748,7 +753,7 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	if (cfg->ias > ARM_V7S_ADDR_BITS)
 		return NULL;
 
-	if (cfg->oas > (arm_v7s_is_mtk_enabled(cfg) ? 34 : ARM_V7S_ADDR_BITS))
+	if (cfg->oas > (arm_v7s_is_mtk_enabled(cfg) ? 35 : ARM_V7S_ADDR_BITS))
 		return NULL;
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index f594971dbeb2..485f3b6d1a21 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -300,7 +300,7 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
 			IO_PGTABLE_QUIRK_ARM_MTK_EXT,
 		.pgsize_bitmap = mtk_iommu_ops.pgsize_bitmap,
 		.ias = 32,
-		.oas = 34,
+		.oas = 35,
 		.iommu_dev = data->dev,
 	};
 
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 06753323a15e..d69234a4a65e 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -69,8 +69,8 @@ struct io_pgtable_cfg {
 	 *	format, and/or requires some format-specific default value.
 	 *
 	 * IO_PGTABLE_QUIRK_ARM_MTK_EXT: (ARM v7s format) MediaTek IOMMUs extend
-	 *	to support up to 34 bits PA where the bit32 and bit33 are
-	 *	encoded in the bit9 and bit4 of the PTE respectively.
+	 *	to support up to 35 bits PA where the bit32, bit33 and bit34 are
+	 *	encoded in the bit9, bit4 and bit5 of the PTE respectively.
 	 *
 	 * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs
 	 *	on unmap, for DMA domains using the flush queue mechanism for
-- 
cgit v1.2.3


From 00ab6f2d61583e072a0cced0420ee1134d853a35 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:18:52 +0800
Subject: iommu/io-pgtable-arm-v7s: Clarify LVL_SHIFT/BITS macro

The current _ARM_V7S_LVL_BITS/ARM_V7S_LVL_SHIFT use a formula to calculate
the corresponding value for level1 and level2 to pretend the code sane.
Actually their level1 and level2 values are different from each other.
This patch only clarify the two macro. No functional change.

Suggested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-12-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/io-pgtable-arm-v7s.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index b1b2ff069040..a129988cc1a6 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -44,13 +44,11 @@
 
 /*
  * We have 32 bits total; 12 bits resolved at level 1, 8 bits at level 2,
- * and 12 bits in a page. With some carefully-chosen coefficients we can
- * hide the ugly inconsistencies behind these macros and at least let the
- * rest of the code pretend to be somewhat sane.
+ * and 12 bits in a page.
  */
 #define ARM_V7S_ADDR_BITS		32
-#define _ARM_V7S_LVL_BITS(lvl)		(16 - (lvl) * 4)
-#define ARM_V7S_LVL_SHIFT(lvl)		(ARM_V7S_ADDR_BITS - (4 + 8 * (lvl)))
+#define _ARM_V7S_LVL_BITS(lvl)		((lvl) == 1 ? 12 : 8)
+#define ARM_V7S_LVL_SHIFT(lvl)		((lvl) == 1 ? 20 : 12)
 #define ARM_V7S_TABLE_SHIFT		10
 
 #define ARM_V7S_PTES_PER_LVL(lvl)	(1 << _ARM_V7S_LVL_BITS(lvl))
-- 
cgit v1.2.3


From 468ea0bfaecd097c223e13400d8e8fbae75e1f68 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:18:53 +0800
Subject: iommu/io-pgtable-arm-v7s: Add cfg as a param in some macros

Add "cfg" as a parameter for some macros. This is a preparing patch for
mediatek extend the lvl1 pgtable. No functional change.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Acked-by: Will Deacon <will@kernel.org>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-13-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/io-pgtable-arm-v7s.c | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index a129988cc1a6..2e161f0a65f0 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -47,21 +47,21 @@
  * and 12 bits in a page.
  */
 #define ARM_V7S_ADDR_BITS		32
-#define _ARM_V7S_LVL_BITS(lvl)		((lvl) == 1 ? 12 : 8)
+#define _ARM_V7S_LVL_BITS(lvl, cfg)	((lvl) == 1 ? 12 : 8)
 #define ARM_V7S_LVL_SHIFT(lvl)		((lvl) == 1 ? 20 : 12)
 #define ARM_V7S_TABLE_SHIFT		10
 
-#define ARM_V7S_PTES_PER_LVL(lvl)	(1 << _ARM_V7S_LVL_BITS(lvl))
-#define ARM_V7S_TABLE_SIZE(lvl)						\
-	(ARM_V7S_PTES_PER_LVL(lvl) * sizeof(arm_v7s_iopte))
+#define ARM_V7S_PTES_PER_LVL(lvl, cfg)	(1 << _ARM_V7S_LVL_BITS(lvl, cfg))
+#define ARM_V7S_TABLE_SIZE(lvl, cfg)						\
+	(ARM_V7S_PTES_PER_LVL(lvl, cfg) * sizeof(arm_v7s_iopte))
 
 #define ARM_V7S_BLOCK_SIZE(lvl)		(1UL << ARM_V7S_LVL_SHIFT(lvl))
 #define ARM_V7S_LVL_MASK(lvl)		((u32)(~0U << ARM_V7S_LVL_SHIFT(lvl)))
 #define ARM_V7S_TABLE_MASK		((u32)(~0U << ARM_V7S_TABLE_SHIFT))
-#define _ARM_V7S_IDX_MASK(lvl)		(ARM_V7S_PTES_PER_LVL(lvl) - 1)
-#define ARM_V7S_LVL_IDX(addr, lvl)	({				\
+#define _ARM_V7S_IDX_MASK(lvl, cfg)	(ARM_V7S_PTES_PER_LVL(lvl, cfg) - 1)
+#define ARM_V7S_LVL_IDX(addr, lvl, cfg)	({				\
 	int _l = lvl;							\
-	((u32)(addr) >> ARM_V7S_LVL_SHIFT(_l)) & _ARM_V7S_IDX_MASK(_l); \
+	((u32)(addr) >> ARM_V7S_LVL_SHIFT(_l)) & _ARM_V7S_IDX_MASK(_l, cfg); \
 })
 
 /*
@@ -237,7 +237,7 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp,
 	struct device *dev = cfg->iommu_dev;
 	phys_addr_t phys;
 	dma_addr_t dma;
-	size_t size = ARM_V7S_TABLE_SIZE(lvl);
+	size_t size = ARM_V7S_TABLE_SIZE(lvl, cfg);
 	void *table = NULL;
 
 	if (lvl == 1)
@@ -283,7 +283,7 @@ static void __arm_v7s_free_table(void *table, int lvl,
 {
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	struct device *dev = cfg->iommu_dev;
-	size_t size = ARM_V7S_TABLE_SIZE(lvl);
+	size_t size = ARM_V7S_TABLE_SIZE(lvl, cfg);
 
 	if (!cfg->coherent_walk)
 		dma_unmap_single(dev, __arm_v7s_dma_addr(table), size,
@@ -427,7 +427,7 @@ static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
 			arm_v7s_iopte *tblp;
 			size_t sz = ARM_V7S_BLOCK_SIZE(lvl);
 
-			tblp = ptep - ARM_V7S_LVL_IDX(iova, lvl);
+			tblp = ptep - ARM_V7S_LVL_IDX(iova, lvl, cfg);
 			if (WARN_ON(__arm_v7s_unmap(data, NULL, iova + i * sz,
 						    sz, lvl, tblp) != sz))
 				return -EINVAL;
@@ -480,7 +480,7 @@ static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova,
 	int num_entries = size >> ARM_V7S_LVL_SHIFT(lvl);
 
 	/* Find our entry at the current level */
-	ptep += ARM_V7S_LVL_IDX(iova, lvl);
+	ptep += ARM_V7S_LVL_IDX(iova, lvl, cfg);
 
 	/* If we can install a leaf entry at this level, then do so */
 	if (num_entries)
@@ -547,7 +547,7 @@ static void arm_v7s_free_pgtable(struct io_pgtable *iop)
 	struct arm_v7s_io_pgtable *data = io_pgtable_to_data(iop);
 	int i;
 
-	for (i = 0; i < ARM_V7S_PTES_PER_LVL(1); i++) {
+	for (i = 0; i < ARM_V7S_PTES_PER_LVL(1, &data->iop.cfg); i++) {
 		arm_v7s_iopte pte = data->pgd[i];
 
 		if (ARM_V7S_PTE_IS_TABLE(pte, 1))
@@ -599,9 +599,9 @@ static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
 	if (!tablep)
 		return 0; /* Bytes unmapped */
 
-	num_ptes = ARM_V7S_PTES_PER_LVL(2);
+	num_ptes = ARM_V7S_PTES_PER_LVL(2, cfg);
 	num_entries = size >> ARM_V7S_LVL_SHIFT(2);
-	unmap_idx = ARM_V7S_LVL_IDX(iova, 2);
+	unmap_idx = ARM_V7S_LVL_IDX(iova, 2, cfg);
 
 	pte = arm_v7s_prot_to_pte(arm_v7s_pte_to_prot(blk_pte, 1), 2, cfg);
 	if (num_entries > 1)
@@ -643,7 +643,7 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
 	if (WARN_ON(lvl > 2))
 		return 0;
 
-	idx = ARM_V7S_LVL_IDX(iova, lvl);
+	idx = ARM_V7S_LVL_IDX(iova, lvl, &iop->cfg);
 	ptep += idx;
 	do {
 		pte[i] = READ_ONCE(ptep[i]);
@@ -729,7 +729,7 @@ static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops,
 	u32 mask;
 
 	do {
-		ptep += ARM_V7S_LVL_IDX(iova, ++lvl);
+		ptep += ARM_V7S_LVL_IDX(iova, ++lvl, &data->iop.cfg);
 		pte = READ_ONCE(*ptep);
 		ptep = iopte_deref(pte, lvl, data);
 	} while (ARM_V7S_PTE_IS_TABLE(pte, lvl));
@@ -771,8 +771,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 
 	spin_lock_init(&data->split_lock);
 	data->l2_tables = kmem_cache_create("io-pgtable_armv7s_l2",
-					    ARM_V7S_TABLE_SIZE(2),
-					    ARM_V7S_TABLE_SIZE(2),
+					    ARM_V7S_TABLE_SIZE(2, cfg),
+					    ARM_V7S_TABLE_SIZE(2, cfg),
 					    ARM_V7S_TABLE_SLAB_FLAGS, NULL);
 	if (!data->l2_tables)
 		goto out_free_data;
-- 
cgit v1.2.3


From f3a8a46d714fd67b856f09e4c783363076ebac62 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:18:54 +0800
Subject: iommu/io-pgtable-arm-v7s: Quad lvl1 pgtable for MediaTek

The standard input iova bits is 32. MediaTek quad the lvl1 pagetable
(4 * lvl1). No change for lvl2 pagetable. Then the iova bits can reach
34bit.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-14-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/io-pgtable-arm-v7s.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 2e161f0a65f0..d4004bcf333a 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -45,9 +45,10 @@
 /*
  * We have 32 bits total; 12 bits resolved at level 1, 8 bits at level 2,
  * and 12 bits in a page.
+ * MediaTek extend 2 bits to reach 34bits, 14 bits at lvl1 and 8 bits at lvl2.
  */
 #define ARM_V7S_ADDR_BITS		32
-#define _ARM_V7S_LVL_BITS(lvl, cfg)	((lvl) == 1 ? 12 : 8)
+#define _ARM_V7S_LVL_BITS(lvl, cfg)	((lvl) == 1 ? ((cfg)->ias - 20) : 8)
 #define ARM_V7S_LVL_SHIFT(lvl)		((lvl) == 1 ? 20 : 12)
 #define ARM_V7S_TABLE_SHIFT		10
 
@@ -61,7 +62,7 @@
 #define _ARM_V7S_IDX_MASK(lvl, cfg)	(ARM_V7S_PTES_PER_LVL(lvl, cfg) - 1)
 #define ARM_V7S_LVL_IDX(addr, lvl, cfg)	({				\
 	int _l = lvl;							\
-	((u32)(addr) >> ARM_V7S_LVL_SHIFT(_l)) & _ARM_V7S_IDX_MASK(_l, cfg); \
+	((addr) >> ARM_V7S_LVL_SHIFT(_l)) & _ARM_V7S_IDX_MASK(_l, cfg); \
 })
 
 /*
@@ -748,7 +749,7 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 {
 	struct arm_v7s_io_pgtable *data;
 
-	if (cfg->ias > ARM_V7S_ADDR_BITS)
+	if (cfg->ias > (arm_v7s_is_mtk_enabled(cfg) ? 34 : ARM_V7S_ADDR_BITS))
 		return NULL;
 
 	if (cfg->oas > (arm_v7s_is_mtk_enabled(cfg) ? 35 : ARM_V7S_ADDR_BITS))
-- 
cgit v1.2.3


From 2f317da4332a145be76ccd49d0a38803b499c39c Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:18:55 +0800
Subject: iommu/mediatek: Add a flag for iova 34bits case

Add a HW flag for if the HW support 34bit IOVA. the previous SoC
still use 32bit. normally the lvl1 pgtable size is 16KB when ias == 32.
if ias == 34, lvl1 pgtable size is 16KB * 4. The purpose of this patch
is to save 16KB*3 continuous memory for the previous SoC.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-15-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 485f3b6d1a21..bf1277d58121 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -112,6 +112,7 @@
 #define HAS_SUB_COMM			BIT(5)
 #define WR_THROT_EN			BIT(6)
 #define HAS_LEGACY_IVRP_PADDR		BIT(7)
+#define IOVA_34_EN			BIT(8)
 
 #define MTK_IOMMU_HAS_FLAG(pdata, _x) \
 		((((pdata)->flags) & (_x)) == (_x))
@@ -299,7 +300,7 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
 			IO_PGTABLE_QUIRK_NO_PERMS |
 			IO_PGTABLE_QUIRK_ARM_MTK_EXT,
 		.pgsize_bitmap = mtk_iommu_ops.pgsize_bitmap,
-		.ias = 32,
+		.ias = MTK_IOMMU_HAS_FLAG(data->plat_data, IOVA_34_EN) ? 34 : 32,
 		.oas = 35,
 		.iommu_dev = data->dev,
 	};
-- 
cgit v1.2.3


From 9bdfe4c175c8a9ea4959f7ad087e3d66d3917bc8 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:18:56 +0800
Subject: iommu/mediatek: Update oas for v7s

This patch only updates oas in different SoCs.

If the SoC supports 4GB-mode and current dram size is 4GB, the oas is 33.
otherwise, it's still 32. In the lastest SoC, the oas is 35bits.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-16-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index bf1277d58121..1c4af574f5f7 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -301,10 +301,14 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
 			IO_PGTABLE_QUIRK_ARM_MTK_EXT,
 		.pgsize_bitmap = mtk_iommu_ops.pgsize_bitmap,
 		.ias = MTK_IOMMU_HAS_FLAG(data->plat_data, IOVA_34_EN) ? 34 : 32,
-		.oas = 35,
 		.iommu_dev = data->dev,
 	};
 
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE))
+		dom->cfg.oas = data->enable_4GB ? 33 : 32;
+	else
+		dom->cfg.oas = 35;
+
 	dom->iop = alloc_io_pgtable_ops(ARM_V7S, &dom->cfg, data);
 	if (!dom->iop) {
 		dev_err(data->dev, "Failed to alloc io pgtable\n");
-- 
cgit v1.2.3


From 7f37a91dc85e37ed06422c6e460724375a86f40c Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:18:57 +0800
Subject: iommu/mediatek: Move hw_init into attach_device

In attach device, it will update the pagetable base address register.
Move the hw_init function also here. Then it only need call
pm_runtime_get/put one time here if m4u has power domain.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-17-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 1c4af574f5f7..87c4626c9072 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -126,6 +126,8 @@ struct mtk_iommu_domain {
 
 static const struct iommu_ops mtk_iommu_ops;
 
+static int mtk_iommu_hw_init(const struct mtk_iommu_data *data);
+
 /*
  * In M4U 4GB mode, the physical address is remapped as below:
  *
@@ -364,12 +366,15 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 {
 	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	int ret;
 
 	if (!data)
 		return -ENODEV;
 
-	/* Update the pgtable base address register of the M4U HW */
-	if (!data->m4u_dom) {
+	if (!data->m4u_dom) { /* Initialize the M4U HW */
+		ret = mtk_iommu_hw_init(data);
+		if (ret)
+			return ret;
 		data->m4u_dom = dom;
 		writel(dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
 		       data->base + REG_MMU_PT_BASE_ADDR);
@@ -724,10 +729,6 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, data);
 
-	ret = mtk_iommu_hw_init(data);
-	if (ret)
-		return ret;
-
 	ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
 				     "mtk-iommu.%pa", &ioaddr);
 	if (ret)
-- 
cgit v1.2.3


From 986d9ec5f176ff1a539e849d57b3d6ecc937c4a6 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:18:58 +0800
Subject: iommu/mediatek: Add error handle for mtk_iommu_probe

In the original code, we lack the error handle. This patch adds them.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-18-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 87c4626c9072..189165e7a2ab 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -739,15 +739,30 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 
 	ret = iommu_device_register(&data->iommu);
 	if (ret)
-		return ret;
+		goto out_sysfs_remove;
 
 	spin_lock_init(&data->tlb_lock);
 	list_add_tail(&data->list, &m4ulist);
 
-	if (!iommu_present(&platform_bus_type))
-		bus_set_iommu(&platform_bus_type, &mtk_iommu_ops);
+	if (!iommu_present(&platform_bus_type)) {
+		ret = bus_set_iommu(&platform_bus_type, &mtk_iommu_ops);
+		if (ret)
+			goto out_list_del;
+	}
 
-	return component_master_add_with_match(dev, &mtk_iommu_com_ops, match);
+	ret = component_master_add_with_match(dev, &mtk_iommu_com_ops, match);
+	if (ret)
+		goto out_bus_set_null;
+	return ret;
+
+out_bus_set_null:
+	bus_set_iommu(&platform_bus_type, NULL);
+out_list_del:
+	list_del(&data->list);
+	iommu_device_unregister(&data->iommu);
+out_sysfs_remove:
+	iommu_device_sysfs_remove(&data->iommu);
+	return ret;
 }
 
 static int mtk_iommu_remove(struct platform_device *pdev)
-- 
cgit v1.2.3


From baf94e6ebff9622f60c4a87ff59c85bf756b7e20 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:18:59 +0800
Subject: iommu/mediatek: Add device link for smi-common and m4u

In the lastest SoC, M4U has its special power domain. thus, If the engine
begin to work, it should help enable the power for M4U firstly.
Currently if the engine work, it always enable the power/clocks for
smi-larbs/smi-common. This patch adds device_link for smi-common and M4U.
then, if smi-common power is enabled, the M4U power also is powered on
automatically.

Normally M4U connect with several smi-larbs and their smi-common always
are the same, In this patch it get smi-common dev from the last smi-larb
device, then add the device_link.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-19-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 27 ++++++++++++++++++++++++---
 drivers/iommu/mtk_iommu.h |  1 +
 2 files changed, 25 insertions(+), 3 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 189165e7a2ab..0fe7c1617dc3 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -20,6 +20,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -633,6 +634,9 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 {
 	struct mtk_iommu_data   *data;
 	struct device           *dev = &pdev->dev;
+	struct device_node	*larbnode, *smicomm_node;
+	struct platform_device	*plarbdev;
+	struct device_link	*link;
 	struct resource         *res;
 	resource_size_t		ioaddr;
 	struct component_match  *match = NULL;
@@ -699,8 +703,6 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 		return larb_nr;
 
 	for (i = 0; i < larb_nr; i++) {
-		struct device_node *larbnode;
-		struct platform_device *plarbdev;
 		u32 id;
 
 		larbnode = of_parse_phandle(dev->of_node, "mediatek,larbs", i);
@@ -727,12 +729,28 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 					    compare_of, larbnode);
 	}
 
+	/* Get smi-common dev from the last larb. */
+	smicomm_node = of_parse_phandle(larbnode, "mediatek,smi", 0);
+	if (!smicomm_node)
+		return -EINVAL;
+
+	plarbdev = of_find_device_by_node(smicomm_node);
+	of_node_put(smicomm_node);
+	data->smicomm_dev = &plarbdev->dev;
+
+	link = device_link_add(data->smicomm_dev, dev,
+			DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME);
+	if (!link) {
+		dev_err(dev, "Unable link %s.\n", dev_name(data->smicomm_dev));
+		return -EINVAL;
+	}
+
 	platform_set_drvdata(pdev, data);
 
 	ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
 				     "mtk-iommu.%pa", &ioaddr);
 	if (ret)
-		return ret;
+		goto out_link_remove;
 
 	iommu_device_set_ops(&data->iommu, &mtk_iommu_ops);
 	iommu_device_set_fwnode(&data->iommu, &pdev->dev.of_node->fwnode);
@@ -762,6 +780,8 @@ out_list_del:
 	iommu_device_unregister(&data->iommu);
 out_sysfs_remove:
 	iommu_device_sysfs_remove(&data->iommu);
+out_link_remove:
+	device_link_remove(data->smicomm_dev, dev);
 	return ret;
 }
 
@@ -776,6 +796,7 @@ static int mtk_iommu_remove(struct platform_device *pdev)
 		bus_set_iommu(&platform_bus_type, NULL);
 
 	clk_disable_unprepare(data->bclk);
+	device_link_remove(data->smicomm_dev, &pdev->dev);
 	devm_free_irq(&pdev->dev, data->irq, data);
 	component_master_del(&pdev->dev, &mtk_iommu_com_ops);
 	return 0;
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
index c1584dea66cb..a9b79e118f02 100644
--- a/drivers/iommu/mtk_iommu.h
+++ b/drivers/iommu/mtk_iommu.h
@@ -68,6 +68,7 @@ struct mtk_iommu_data {
 
 	struct iommu_device		iommu;
 	const struct mtk_iommu_plat_data *plat_data;
+	struct device			*smicomm_dev;
 
 	struct dma_iommu_mapping	*mapping; /* For mtk_iommu_v1.c */
 
-- 
cgit v1.2.3


From 34665c7929fc27351ee3f45554e8991a6fd6e284 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:00 +0800
Subject: iommu/mediatek: Add pm runtime callback

In pm runtime case, all the registers backup/restore and bclk are
controlled in the pm_runtime callback, Rename the original
suspend/resume to the runtime_suspend/resume.

Use pm_runtime_force_suspend/resume as the normal suspend/resume.
iommu should suspend after iommu consumer devices, thus use _LATE_.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-20-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 0fe7c1617dc3..3682137b789a 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -802,7 +802,7 @@ static int mtk_iommu_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int __maybe_unused mtk_iommu_suspend(struct device *dev)
+static int __maybe_unused mtk_iommu_runtime_suspend(struct device *dev)
 {
 	struct mtk_iommu_data *data = dev_get_drvdata(dev);
 	struct mtk_iommu_suspend_reg *reg = &data->reg;
@@ -820,7 +820,7 @@ static int __maybe_unused mtk_iommu_suspend(struct device *dev)
 	return 0;
 }
 
-static int __maybe_unused mtk_iommu_resume(struct device *dev)
+static int __maybe_unused mtk_iommu_runtime_resume(struct device *dev)
 {
 	struct mtk_iommu_data *data = dev_get_drvdata(dev);
 	struct mtk_iommu_suspend_reg *reg = &data->reg;
@@ -848,7 +848,9 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
 }
 
 static const struct dev_pm_ops mtk_iommu_pm_ops = {
-	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_iommu_suspend, mtk_iommu_resume)
+	SET_RUNTIME_PM_OPS(mtk_iommu_runtime_suspend, mtk_iommu_runtime_resume, NULL)
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				     pm_runtime_force_resume)
 };
 
 static const struct mtk_iommu_plat_data mt2712_data = {
-- 
cgit v1.2.3


From c0b57581b73be7b43f39e0dff201c93413f6a668 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:01 +0800
Subject: iommu/mediatek: Add power-domain operation

In the previous SoC, the M4U HW is in the EMI power domain which is
always on. the latest M4U is in the display power domain which may be
turned on/off, thus we have to add pm_runtime interface for it.

When the engine work, the engine always enable the power and clocks for
smi-larb/smi-common, then the M4U's power will always be powered on
automatically via the device link with smi-common.

Note: we don't enable the M4U power in iommu_map/unmap for tlb flush.
If its power already is on, of course it is ok. if the power is off,
the main tlb will be reset while M4U power on, thus the tlb flush while
m4u power off is unnecessary, just skip it.
Therefore, we increase the ref_count for pm when pm status is ACTIVE,
otherwise, skip it. Meanwhile, the tlb_flush_range is called so often,
thus, update pm ref_count while the SoC has power-domain to avoid touch the
dev->power.lock. and the tlb_flush_all only is called when boot, so no
need check if the SoC has power-domain to keep code clean.

There will be one case that pm runctime status is not expected when tlb
flush. After boot, the display may call dma_alloc_attrs before it call
pm_runtime_get(disp-dev), then the m4u's pm status is not active inside
the dma_alloc_attrs. Since it only happens after boot, the tlb is clean
at that time, I also think this is ok.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-21-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 39 ++++++++++++++++++++++++++++++++++-----
 1 file changed, 34 insertions(+), 5 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 3682137b789a..b9c63c8de33e 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -182,10 +182,15 @@ static struct mtk_iommu_domain *to_mtk_domain(struct iommu_domain *dom)
 static void mtk_iommu_tlb_flush_all(struct mtk_iommu_data *data)
 {
 	for_each_m4u(data) {
+		if (pm_runtime_get_if_in_use(data->dev) <= 0)
+			continue;
+
 		writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
 			       data->base + data->plat_data->inv_sel_reg);
 		writel_relaxed(F_ALL_INVLD, data->base + REG_MMU_INVALIDATE);
 		wmb(); /* Make sure the tlb flush all done */
+
+		pm_runtime_put(data->dev);
 	}
 }
 
@@ -193,11 +198,17 @@ static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
 					   size_t granule,
 					   struct mtk_iommu_data *data)
 {
+	bool has_pm = !!data->dev->pm_domain;
 	unsigned long flags;
 	int ret;
 	u32 tmp;
 
 	for_each_m4u(data) {
+		if (has_pm) {
+			if (pm_runtime_get_if_in_use(data->dev) <= 0)
+				continue;
+		}
+
 		spin_lock_irqsave(&data->tlb_lock, flags);
 		writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
 			       data->base + data->plat_data->inv_sel_reg);
@@ -219,6 +230,9 @@ static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
 		/* Clear the CPE status */
 		writel_relaxed(0, data->base + REG_MMU_CPE_DONE);
 		spin_unlock_irqrestore(&data->tlb_lock, flags);
+
+		if (has_pm)
+			pm_runtime_put(data->dev);
 	}
 }
 
@@ -367,18 +381,27 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 {
 	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	struct device *m4udev = data->dev;
 	int ret;
 
 	if (!data)
 		return -ENODEV;
 
 	if (!data->m4u_dom) { /* Initialize the M4U HW */
+		ret = pm_runtime_resume_and_get(m4udev);
+		if (ret < 0)
+			return ret;
+
 		ret = mtk_iommu_hw_init(data);
-		if (ret)
+		if (ret) {
+			pm_runtime_put(m4udev);
 			return ret;
+		}
 		data->m4u_dom = dom;
 		writel(dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
 		       data->base + REG_MMU_PT_BASE_ADDR);
+
+		pm_runtime_put(m4udev);
 	}
 
 	mtk_iommu_config(data, dev, true);
@@ -738,11 +761,13 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	of_node_put(smicomm_node);
 	data->smicomm_dev = &plarbdev->dev;
 
+	pm_runtime_enable(dev);
+
 	link = device_link_add(data->smicomm_dev, dev,
 			DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME);
 	if (!link) {
 		dev_err(dev, "Unable link %s.\n", dev_name(data->smicomm_dev));
-		return -EINVAL;
+		goto out_runtime_disable;
 	}
 
 	platform_set_drvdata(pdev, data);
@@ -782,6 +807,8 @@ out_sysfs_remove:
 	iommu_device_sysfs_remove(&data->iommu);
 out_link_remove:
 	device_link_remove(data->smicomm_dev, dev);
+out_runtime_disable:
+	pm_runtime_disable(dev);
 	return ret;
 }
 
@@ -797,6 +824,7 @@ static int mtk_iommu_remove(struct platform_device *pdev)
 
 	clk_disable_unprepare(data->bclk);
 	device_link_remove(data->smicomm_dev, &pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 	devm_free_irq(&pdev->dev, data->irq, data);
 	component_master_del(&pdev->dev, &mtk_iommu_com_ops);
 	return 0;
@@ -828,6 +856,9 @@ static int __maybe_unused mtk_iommu_runtime_resume(struct device *dev)
 	void __iomem *base = data->base;
 	int ret;
 
+	/* Avoid first resume to affect the default value of registers below. */
+	if (!m4u_dom)
+		return 0;
 	ret = clk_prepare_enable(data->bclk);
 	if (ret) {
 		dev_err(data->dev, "Failed to enable clk(%d) in resume\n", ret);
@@ -841,9 +872,7 @@ static int __maybe_unused mtk_iommu_runtime_resume(struct device *dev)
 	writel_relaxed(reg->int_main_control, base + REG_MMU_INT_MAIN_CONTROL);
 	writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR);
 	writel_relaxed(reg->vld_pa_rng, base + REG_MMU_VLD_PA_RNG);
-	if (m4u_dom)
-		writel(m4u_dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
-		       base + REG_MMU_PT_BASE_ADDR);
+	writel(m4u_dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK, base + REG_MMU_PT_BASE_ADDR);
 	return 0;
 }
 
-- 
cgit v1.2.3


From bfed873114c5fbb8982113abbab17cde7788dcba Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:02 +0800
Subject: iommu/mediatek: Support up to 34bit iova in tlb flush

If the iova is 34bit, the iova[32][33] is the bit0/1 in the tlb flush
register. Add a new macro for this.

In the macro, since (iova + size - 1) may be end with 0xfff, then the
bit0/1 always is 1, thus add a mask.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-22-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index b9c63c8de33e..468be7ca62e4 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -129,6 +129,11 @@ static const struct iommu_ops mtk_iommu_ops;
 
 static int mtk_iommu_hw_init(const struct mtk_iommu_data *data);
 
+#define MTK_IOMMU_TLB_ADDR(iova) ({					\
+	dma_addr_t _addr = iova;					\
+	((lower_32_bits(_addr) & GENMASK(31, 12)) | upper_32_bits(_addr));\
+})
+
 /*
  * In M4U 4GB mode, the physical address is remapped as below:
  *
@@ -213,8 +218,9 @@ static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
 		writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
 			       data->base + data->plat_data->inv_sel_reg);
 
-		writel_relaxed(iova, data->base + REG_MMU_INVLD_START_A);
-		writel_relaxed(iova + size - 1,
+		writel_relaxed(MTK_IOMMU_TLB_ADDR(iova),
+			       data->base + REG_MMU_INVLD_START_A);
+		writel_relaxed(MTK_IOMMU_TLB_ADDR(iova + size - 1),
 			       data->base + REG_MMU_INVLD_END_A);
 		writel_relaxed(F_MMU_INV_RANGE,
 			       data->base + REG_MMU_INVALIDATE);
-- 
cgit v1.2.3


From ef0f0986b670cb1627bff055102cab70a7d3852a Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:03 +0800
Subject: iommu/mediatek: Support report iova 34bit translation fault in ISR

If the iova is over 32bit, the fault status register bit is a little
different.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-23-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 468be7ca62e4..f3666b0d7577 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2015-2016 MediaTek Inc.
  * Author: Yong Wu <yong.wu@mediatek.com>
  */
+#include <linux/bitfield.h>
 #include <linux/bug.h>
 #include <linux/clk.h>
 #include <linux/component.h>
@@ -89,6 +90,9 @@
 #define F_REG_MMU1_FAULT_MASK			GENMASK(13, 7)
 
 #define REG_MMU0_FAULT_VA			0x13c
+#define F_MMU_INVAL_VA_31_12_MASK		GENMASK(31, 12)
+#define F_MMU_INVAL_VA_34_32_MASK		GENMASK(11, 9)
+#define F_MMU_INVAL_PA_34_32_MASK		GENMASK(8, 6)
 #define F_MMU_FAULT_VA_WRITE_BIT		BIT(1)
 #define F_MMU_FAULT_VA_LAYER_BIT		BIT(0)
 
@@ -246,8 +250,9 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
 {
 	struct mtk_iommu_data *data = dev_id;
 	struct mtk_iommu_domain *dom = data->m4u_dom;
-	u32 int_state, regval, fault_iova, fault_pa;
 	unsigned int fault_larb, fault_port, sub_comm = 0;
+	u32 int_state, regval, va34_32, pa34_32;
+	u64 fault_iova, fault_pa;
 	bool layer, write;
 
 	/* Read error info from registers */
@@ -263,6 +268,14 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
 	}
 	layer = fault_iova & F_MMU_FAULT_VA_LAYER_BIT;
 	write = fault_iova & F_MMU_FAULT_VA_WRITE_BIT;
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, IOVA_34_EN)) {
+		va34_32 = FIELD_GET(F_MMU_INVAL_VA_34_32_MASK, fault_iova);
+		pa34_32 = FIELD_GET(F_MMU_INVAL_PA_34_32_MASK, fault_iova);
+		fault_iova = fault_iova & F_MMU_INVAL_VA_31_12_MASK;
+		fault_iova |= (u64)va34_32 << 32;
+		fault_pa |= (u64)pa34_32 << 32;
+	}
+
 	fault_port = F_MMU_INT_ID_PORT_ID(regval);
 	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_SUB_COMM)) {
 		fault_larb = F_MMU_INT_ID_COMM_ID(regval);
@@ -276,7 +289,7 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
 			       write ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ)) {
 		dev_err_ratelimited(
 			data->dev,
-			"fault type=0x%x iova=0x%x pa=0x%x larb=%d port=%d layer=%d %s\n",
+			"fault type=0x%x iova=0x%llx pa=0x%llx larb=%d port=%d layer=%d %s\n",
 			int_state, fault_iova, fault_pa, fault_larb, fault_port,
 			layer, write ? "write" : "read");
 	}
-- 
cgit v1.2.3


From 08500c43d4f70c1e8be6beda8a2aea0ecfb845d8 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:04 +0800
Subject: iommu/mediatek: Adjust the structure

Add "struct mtk_iommu_data *" in the "struct mtk_iommu_domain",
reduce the call mtk_iommu_get_m4u_data().
No functional change.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-24-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index f3666b0d7577..f1941608ccb7 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -126,6 +126,7 @@ struct mtk_iommu_domain {
 	struct io_pgtable_cfg		cfg;
 	struct io_pgtable_ops		*iop;
 
+	struct mtk_iommu_data		*data;
 	struct iommu_domain		domain;
 };
 
@@ -351,6 +352,7 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
 		return -EINVAL;
 	}
 
+	dom->data = data;
 	/* Update our support page sizes bitmap */
 	dom->domain.pgsize_bitmap = dom->cfg.pgsize_bitmap;
 	return 0;
@@ -442,10 +444,9 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
 			 phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
-	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
 
 	/* The "4GB mode" M4U physically can not use the lower remap of Dram. */
-	if (data->enable_4GB)
+	if (dom->data->enable_4GB)
 		paddr |= BIT_ULL(32);
 
 	/* Synchronize with the tlb_lock */
@@ -468,36 +469,37 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain,
 
 static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain)
 {
-	mtk_iommu_tlb_flush_all(mtk_iommu_get_m4u_data());
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+
+	mtk_iommu_tlb_flush_all(dom->data);
 }
 
 static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
 				 struct iommu_iotlb_gather *gather)
 {
-	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	size_t length = gather->end - gather->start + 1;
 
 	mtk_iommu_tlb_flush_range_sync(gather->start, length, gather->pgsize,
-				       data);
+				       dom->data);
 }
 
 static void mtk_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
 			       size_t size)
 {
-	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 
-	mtk_iommu_tlb_flush_range_sync(iova, size, size, data);
+	mtk_iommu_tlb_flush_range_sync(iova, size, size, dom->data);
 }
 
 static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 					  dma_addr_t iova)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
-	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
 	phys_addr_t pa;
 
 	pa = dom->iop->iova_to_phys(dom->iop, iova);
-	if (data->enable_4GB && pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
+	if (dom->data->enable_4GB && pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
 		pa &= ~BIT_ULL(32);
 
 	return pa;
-- 
cgit v1.2.3


From 4f956c97d26be65aea580e943f470ec70f7b0bb6 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:05 +0800
Subject: iommu/mediatek: Move domain_finalise into attach_device

Currently domain_alloc only has a parameter(type), We have no chance to
input some special data. This patch moves the domain_finalise into
attach_device which has the device information, then could update
the domain's geometry.aperture ranges for each a device.

Strictly, I should use the data from mtk_iommu_get_m4u_data as the
parameter of mtk_iommu_domain_finalise in this patch. but dom->data
only is used in tlb ops in which the data is get from the m4u_list, thus
it is ok here.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-25-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 31 ++++++++++++-------------------
 1 file changed, 12 insertions(+), 19 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index f1941608ccb7..d321d09ac4c2 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -328,10 +328,9 @@ static void mtk_iommu_config(struct mtk_iommu_data *data,
 	}
 }
 
-static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
+static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom,
+				     struct mtk_iommu_data *data)
 {
-	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
-
 	dom->cfg = (struct io_pgtable_cfg) {
 		.quirks = IO_PGTABLE_QUIRK_ARM_NS |
 			IO_PGTABLE_QUIRK_NO_PERMS |
@@ -352,7 +351,6 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
 		return -EINVAL;
 	}
 
-	dom->data = data;
 	/* Update our support page sizes bitmap */
 	dom->domain.pgsize_bitmap = dom->cfg.pgsize_bitmap;
 	return 0;
@@ -369,30 +367,19 @@ static struct iommu_domain *mtk_iommu_domain_alloc(unsigned type)
 	if (!dom)
 		return NULL;
 
-	if (iommu_get_dma_cookie(&dom->domain))
-		goto  free_dom;
-
-	if (mtk_iommu_domain_finalise(dom))
-		goto  put_dma_cookie;
+	if (iommu_get_dma_cookie(&dom->domain)) {
+		kfree(dom);
+		return NULL;
+	}
 
 	dom->domain.geometry.aperture_start = 0;
 	dom->domain.geometry.aperture_end = DMA_BIT_MASK(32);
 	dom->domain.geometry.force_aperture = true;
-
 	return &dom->domain;
-
-put_dma_cookie:
-	iommu_put_dma_cookie(&dom->domain);
-free_dom:
-	kfree(dom);
-	return NULL;
 }
 
 static void mtk_iommu_domain_free(struct iommu_domain *domain)
 {
-	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
-
-	free_io_pgtable_ops(dom->iop);
 	iommu_put_dma_cookie(domain);
 	kfree(to_mtk_domain(domain));
 }
@@ -408,6 +395,12 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 	if (!data)
 		return -ENODEV;
 
+	if (!dom->data) {
+		if (mtk_iommu_domain_finalise(dom, data))
+			return -ENODEV;
+		dom->data = data;
+	}
+
 	if (!data->m4u_dom) { /* Initialize the M4U HW */
 		ret = pm_runtime_resume_and_get(m4udev);
 		if (ret < 0)
-- 
cgit v1.2.3


From b7875eb9458983ade0c780276b21cfbc0c22d70b Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:06 +0800
Subject: iommu/mediatek: Move geometry.aperture updating into domain_finalise

Move the domain geometry.aperture updating into domain_finalise.
This is a preparing patch for updating the domain region. We know the
detailed iova region in the attach_device.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-26-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index d321d09ac4c2..309b06d5e1f9 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -353,6 +353,10 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom,
 
 	/* Update our support page sizes bitmap */
 	dom->domain.pgsize_bitmap = dom->cfg.pgsize_bitmap;
+
+	dom->domain.geometry.aperture_start = 0;
+	dom->domain.geometry.aperture_end = DMA_BIT_MASK(32);
+	dom->domain.geometry.force_aperture = true;
 	return 0;
 }
 
@@ -372,9 +376,6 @@ static struct iommu_domain *mtk_iommu_domain_alloc(unsigned type)
 		return NULL;
 	}
 
-	dom->domain.geometry.aperture_start = 0;
-	dom->domain.geometry.aperture_end = DMA_BIT_MASK(32);
-	dom->domain.geometry.force_aperture = true;
 	return &dom->domain;
 }
 
-- 
cgit v1.2.3


From 585e58f498a2855dc7a8d351df34dd645447f337 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:07 +0800
Subject: iommu/mediatek: Add iova_region structure

Add a new structure for the iova_region. Each a region will be a
independent iommu domain.

For the previous SoC, there is single iova region(0~4G). For the SoC
that need support multi-domains, there will be several regions.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-27-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 19 +++++++++++++++++++
 drivers/iommu/mtk_iommu.h |  5 +++++
 2 files changed, 24 insertions(+)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 309b06d5e1f9..6875ca1225f0 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -167,6 +167,15 @@ static LIST_HEAD(m4ulist);	/* List all the M4U HWs */
 
 #define for_each_m4u(data)	list_for_each_entry(data, &m4ulist, list)
 
+struct mtk_iommu_iova_region {
+	dma_addr_t		iova_base;
+	unsigned long long	size;
+};
+
+static const struct mtk_iommu_iova_region single_domain[] = {
+	{.iova_base = 0,		.size = SZ_4G},
+};
+
 /*
  * There may be 1 or 2 M4U HWs, But we always expect they are in the same domain
  * for the performance.
@@ -901,6 +910,8 @@ static const struct mtk_iommu_plat_data mt2712_data = {
 	.m4u_plat     = M4U_MT2712,
 	.flags        = HAS_4GB_MODE | HAS_BCLK | HAS_VLD_PA_RNG,
 	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.iova_region  = single_domain,
+	.iova_region_nr = ARRAY_SIZE(single_domain),
 	.larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}, {6}, {7}},
 };
 
@@ -908,6 +919,8 @@ static const struct mtk_iommu_plat_data mt6779_data = {
 	.m4u_plat      = M4U_MT6779,
 	.flags         = HAS_SUB_COMM | OUT_ORDER_WR_EN | WR_THROT_EN,
 	.inv_sel_reg   = REG_MMU_INV_SEL_GEN2,
+	.iova_region   = single_domain,
+	.iova_region_nr = ARRAY_SIZE(single_domain),
 	.larbid_remap  = {{0}, {1}, {2}, {3}, {5}, {7, 8}, {10}, {9}},
 };
 
@@ -915,6 +928,8 @@ static const struct mtk_iommu_plat_data mt8167_data = {
 	.m4u_plat     = M4U_MT8167,
 	.flags        = RESET_AXI | HAS_LEGACY_IVRP_PADDR,
 	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.iova_region  = single_domain,
+	.iova_region_nr = ARRAY_SIZE(single_domain),
 	.larbid_remap = {{0}, {1}, {2}}, /* Linear mapping. */
 };
 
@@ -923,6 +938,8 @@ static const struct mtk_iommu_plat_data mt8173_data = {
 	.flags	      = HAS_4GB_MODE | HAS_BCLK | RESET_AXI |
 			HAS_LEGACY_IVRP_PADDR,
 	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.iova_region  = single_domain,
+	.iova_region_nr = ARRAY_SIZE(single_domain),
 	.larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}}, /* Linear mapping. */
 };
 
@@ -930,6 +947,8 @@ static const struct mtk_iommu_plat_data mt8183_data = {
 	.m4u_plat     = M4U_MT8183,
 	.flags        = RESET_AXI,
 	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.iova_region  = single_domain,
+	.iova_region_nr = ARRAY_SIZE(single_domain),
 	.larbid_remap = {{0}, {4}, {5}, {6}, {7}, {2}, {3}, {1}},
 };
 
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
index a9b79e118f02..118170af1974 100644
--- a/drivers/iommu/mtk_iommu.h
+++ b/drivers/iommu/mtk_iommu.h
@@ -45,10 +45,15 @@ enum mtk_iommu_plat {
 	M4U_MT8183,
 };
 
+struct mtk_iommu_iova_region;
+
 struct mtk_iommu_plat_data {
 	enum mtk_iommu_plat m4u_plat;
 	u32                 flags;
 	u32                 inv_sel_reg;
+
+	unsigned int				iova_region_nr;
+	const struct mtk_iommu_iova_region	*iova_region;
 	unsigned char       larbid_remap[MTK_LARB_COM_MAX][MTK_LARB_SUBCOM_MAX];
 };
 
-- 
cgit v1.2.3


From 803cf9e5a6aa64e94f9c554190bc0031929f6857 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:08 +0800
Subject: iommu/mediatek: Add get_domain_id from dev->dma_range_map

Add a new interface _get_domain_id from dev->dma_range_map,
The iommu consumer device will use dma-ranges in dtsi node to indicate
its dma address region requirement. In this iommu driver, we will get
the requirement and decide which iova domain it should locate.

In the lastest SoC, there will be several iova-regions(domains), we will
compare and calculate which domain is right. If the start/end of device
requirement equal some region. it is best fit of course. If it is inside
some region, it is also ok. the iova requirement of a device should not
be inside two or more regions.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-28-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 42 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 41 insertions(+), 1 deletion(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 6875ca1225f0..8fc17158bc28 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -8,6 +8,7 @@
 #include <linux/clk.h>
 #include <linux/component.h>
 #include <linux/device.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-iommu.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
@@ -314,6 +315,36 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static int mtk_iommu_get_domain_id(struct device *dev,
+				   const struct mtk_iommu_plat_data *plat_data)
+{
+	const struct mtk_iommu_iova_region *rgn = plat_data->iova_region;
+	const struct bus_dma_region *dma_rgn = dev->dma_range_map;
+	int i, candidate = -1;
+	dma_addr_t dma_end;
+
+	if (!dma_rgn || plat_data->iova_region_nr == 1)
+		return 0;
+
+	dma_end = dma_rgn->dma_start + dma_rgn->size - 1;
+	for (i = 0; i < plat_data->iova_region_nr; i++, rgn++) {
+		/* Best fit. */
+		if (dma_rgn->dma_start == rgn->iova_base &&
+		    dma_end == rgn->iova_base + rgn->size - 1)
+			return i;
+		/* ok if it is inside this region. */
+		if (dma_rgn->dma_start >= rgn->iova_base &&
+		    dma_end < rgn->iova_base + rgn->size)
+			candidate = i;
+	}
+
+	if (candidate >= 0)
+		return candidate;
+	dev_err(dev, "Can NOT find the iommu domain id(%pad 0x%llx).\n",
+		&dma_rgn->dma_start, dma_rgn->size);
+	return -EINVAL;
+}
+
 static void mtk_iommu_config(struct mtk_iommu_data *data,
 			     struct device *dev, bool enable)
 {
@@ -400,11 +431,15 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	struct device *m4udev = data->dev;
-	int ret;
+	int ret, domid;
 
 	if (!data)
 		return -ENODEV;
 
+	domid = mtk_iommu_get_domain_id(dev, data->plat_data);
+	if (domid < 0)
+		return domid;
+
 	if (!dom->data) {
 		if (mtk_iommu_domain_finalise(dom, data))
 			return -ENODEV;
@@ -534,10 +569,15 @@ static void mtk_iommu_release_device(struct device *dev)
 static struct iommu_group *mtk_iommu_device_group(struct device *dev)
 {
 	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
+	int domid;
 
 	if (!data)
 		return ERR_PTR(-ENODEV);
 
+	domid = mtk_iommu_get_domain_id(dev, data->plat_data);
+	if (domid < 0)
+		return ERR_PTR(domid);
+
 	/* All the client devices are in the same m4u iommu-group */
 	if (!data->m4u_group) {
 		data->m4u_group = iommu_group_alloc();
-- 
cgit v1.2.3


From c3045f39244e90c4c45a404e35aa66403ca68815 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:09 +0800
Subject: iommu/mediatek: Support for multi domains

Some HW IP(ex: CCU) require the special iova range. That means the iova
got from dma_alloc_attrs for that devices must locate in his special range.
In this patch, we prepare a iommu group(domain) for each a iova range
requirement.

Meanwhile we still use one pagetable which support 16GB iova.

After this patch, If the iova range of a master is over 4G, the master
should:
a) Declare its special dma-ranges in its dtsi node. For example, If we
   preassign the iova 4G-8G for vcodec, then the vcodec dtsi node should
   add this:
   /*
    * iova start at 0x1_0000_0000, pa still start at 0x4000_0000
    * size is 0x1_0000_0000.
    */
   dma-ranges = <0x1 0x0 0x0 0x40000000 0x1 0x0>;  /* 4G ~ 8G */
 Note: we don't have a actual bus concept here. the master doesn't have its
 special parent node, thus this dma-ranges can only be put in the master's
 node.

b) Update the dma_mask:
  dma_set_mask_and_coherent(dev, DMA_BIT_MASK(33));

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-29-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 37 ++++++++++++++++++++++++++-----------
 drivers/iommu/mtk_iommu.h |  4 +++-
 2 files changed, 29 insertions(+), 12 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 8fc17158bc28..b42fd2535b77 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -369,8 +369,19 @@ static void mtk_iommu_config(struct mtk_iommu_data *data,
 }
 
 static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom,
-				     struct mtk_iommu_data *data)
+				     struct mtk_iommu_data *data,
+				     unsigned int domid)
 {
+	const struct mtk_iommu_iova_region *region;
+
+	/* Use the exist domain as there is only one pgtable here. */
+	if (data->m4u_dom) {
+		dom->iop = data->m4u_dom->iop;
+		dom->cfg = data->m4u_dom->cfg;
+		dom->domain.pgsize_bitmap = data->m4u_dom->cfg.pgsize_bitmap;
+		goto update_iova_region;
+	}
+
 	dom->cfg = (struct io_pgtable_cfg) {
 		.quirks = IO_PGTABLE_QUIRK_ARM_NS |
 			IO_PGTABLE_QUIRK_NO_PERMS |
@@ -394,8 +405,11 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom,
 	/* Update our support page sizes bitmap */
 	dom->domain.pgsize_bitmap = dom->cfg.pgsize_bitmap;
 
-	dom->domain.geometry.aperture_start = 0;
-	dom->domain.geometry.aperture_end = DMA_BIT_MASK(32);
+update_iova_region:
+	/* Update the iova region for this domain */
+	region = data->plat_data->iova_region + domid;
+	dom->domain.geometry.aperture_start = region->iova_base;
+	dom->domain.geometry.aperture_end = region->iova_base + region->size - 1;
 	dom->domain.geometry.force_aperture = true;
 	return 0;
 }
@@ -441,7 +455,7 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 		return domid;
 
 	if (!dom->data) {
-		if (mtk_iommu_domain_finalise(dom, data))
+		if (mtk_iommu_domain_finalise(dom, data, domid))
 			return -ENODEV;
 		dom->data = data;
 	}
@@ -569,6 +583,7 @@ static void mtk_iommu_release_device(struct device *dev)
 static struct iommu_group *mtk_iommu_device_group(struct device *dev)
 {
 	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
+	struct iommu_group *group;
 	int domid;
 
 	if (!data)
@@ -578,15 +593,15 @@ static struct iommu_group *mtk_iommu_device_group(struct device *dev)
 	if (domid < 0)
 		return ERR_PTR(domid);
 
-	/* All the client devices are in the same m4u iommu-group */
-	if (!data->m4u_group) {
-		data->m4u_group = iommu_group_alloc();
-		if (IS_ERR(data->m4u_group))
-			dev_err(dev, "Failed to allocate M4U IOMMU group\n");
+	group = data->m4u_group[domid];
+	if (!group) {
+		group = iommu_group_alloc();
+		if (!IS_ERR(group))
+			data->m4u_group[domid] = group;
 	} else {
-		iommu_group_ref_get(data->m4u_group);
+		iommu_group_ref_get(group);
 	}
-	return data->m4u_group;
+	return group;
 }
 
 static int mtk_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
index 118170af1974..6f2168e3222d 100644
--- a/drivers/iommu/mtk_iommu.h
+++ b/drivers/iommu/mtk_iommu.h
@@ -22,6 +22,8 @@
 #define MTK_LARB_COM_MAX	8
 #define MTK_LARB_SUBCOM_MAX	4
 
+#define MTK_IOMMU_GROUP_MAX	8
+
 struct mtk_iommu_suspend_reg {
 	union {
 		u32			standard_axi_mode;/* v1 */
@@ -67,7 +69,7 @@ struct mtk_iommu_data {
 	phys_addr_t			protect_base; /* protect memory base */
 	struct mtk_iommu_suspend_reg	reg;
 	struct mtk_iommu_domain		*m4u_dom;
-	struct iommu_group		*m4u_group;
+	struct iommu_group		*m4u_group[MTK_IOMMU_GROUP_MAX];
 	bool                            enable_4GB;
 	spinlock_t			tlb_lock; /* lock for tlb range flush */
 
-- 
cgit v1.2.3


From ab1d5281a62bafbd611fffdce7eab6eb9577aa0d Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:10 +0800
Subject: iommu/mediatek: Add iova reserved function

For multiple iommu_domains, we need to reserve some iova regions. Take a
example, If the default iova region is 0 ~ 4G, but the 0x4000_0000 ~
0x43ff_ffff is only for the special CCU0 domain. Thus we should exclude
this region for the default iova region.

Signed-off-by: Anan sun <anan.sun@mediatek.com>
Signed-off-by: Chao Hao <chao.hao@mediatek.com>
Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-30-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index b42fd2535b77..764dc0b93477 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -626,6 +626,35 @@ static int mtk_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 	return iommu_fwspec_add_ids(dev, args->args, 1);
 }
 
+static void mtk_iommu_get_resv_regions(struct device *dev,
+				       struct list_head *head)
+{
+	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
+	unsigned int domid = mtk_iommu_get_domain_id(dev, data->plat_data), i;
+	const struct mtk_iommu_iova_region *resv, *curdom;
+	struct iommu_resv_region *region;
+	int prot = IOMMU_WRITE | IOMMU_READ;
+
+	if (domid < 0)
+		return;
+	curdom = data->plat_data->iova_region + domid;
+	for (i = 0; i < data->plat_data->iova_region_nr; i++) {
+		resv = data->plat_data->iova_region + i;
+
+		/* Only reserve when the region is inside the current domain */
+		if (resv->iova_base <= curdom->iova_base ||
+		    resv->iova_base + resv->size >= curdom->iova_base + curdom->size)
+			continue;
+
+		region = iommu_alloc_resv_region(resv->iova_base, resv->size,
+						 prot, IOMMU_RESV_RESERVED);
+		if (!region)
+			return;
+
+		list_add_tail(&region->list, head);
+	}
+}
+
 static const struct iommu_ops mtk_iommu_ops = {
 	.domain_alloc	= mtk_iommu_domain_alloc,
 	.domain_free	= mtk_iommu_domain_free,
@@ -641,6 +670,8 @@ static const struct iommu_ops mtk_iommu_ops = {
 	.release_device	= mtk_iommu_release_device,
 	.device_group	= mtk_iommu_device_group,
 	.of_xlate	= mtk_iommu_of_xlate,
+	.get_resv_regions = mtk_iommu_get_resv_regions,
+	.put_resv_regions = generic_iommu_put_resv_regions,
 	.pgsize_bitmap	= SZ_4K | SZ_64K | SZ_1M | SZ_16M,
 };
 
-- 
cgit v1.2.3


From 8d2c749e5252466d8fc1917101f137966c61fd1c Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:11 +0800
Subject: iommu/mediatek: Support master use iova over 32bit

After extending v7s, our pagetable already support iova reach
16GB(34bit). the master got the iova via dma_alloc_attrs may reach
34bits, but its HW register still is 32bit. then how to set the
bit32/bit33 iova? this depend on a SMI larb setting(bank_sel).

we separate whole 16GB iova to four banks:
bank: 0: 0~4G; 1: 4~8G; 2: 8-12G; 3: 12-16G;
The bank number is (iova >> 32).

We will preassign which bank the larbs belong to. currently we don't
have a interface for master to adjust its bank number.

Each a bank is a iova_region which is a independent iommu-domain.
the iova range for each iommu-domain can't cross 4G.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Acked-by: Krzysztof Kozlowski <krzk@kernel.org> #for memory part
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-31-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c  | 18 ++++++++++++------
 drivers/memory/mtk-smi.c   |  7 +++++++
 include/soc/mediatek/smi.h |  1 +
 3 files changed, 20 insertions(+), 6 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 764dc0b93477..7403a7cb90ea 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -345,21 +345,27 @@ static int mtk_iommu_get_domain_id(struct device *dev,
 	return -EINVAL;
 }
 
-static void mtk_iommu_config(struct mtk_iommu_data *data,
-			     struct device *dev, bool enable)
+static void mtk_iommu_config(struct mtk_iommu_data *data, struct device *dev,
+			     bool enable, unsigned int domid)
 {
 	struct mtk_smi_larb_iommu    *larb_mmu;
 	unsigned int                 larbid, portid;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	const struct mtk_iommu_iova_region *region;
 	int i;
 
 	for (i = 0; i < fwspec->num_ids; ++i) {
 		larbid = MTK_M4U_TO_LARB(fwspec->ids[i]);
 		portid = MTK_M4U_TO_PORT(fwspec->ids[i]);
+
 		larb_mmu = &data->larb_imu[larbid];
 
-		dev_dbg(dev, "%s iommu port: %d\n",
-			enable ? "enable" : "disable", portid);
+		region = data->plat_data->iova_region + domid;
+		larb_mmu->bank[portid] = upper_32_bits(region->iova_base);
+
+		dev_dbg(dev, "%s iommu for larb(%s) port %d dom %d bank %d.\n",
+			enable ? "enable" : "disable", dev_name(larb_mmu->dev),
+			portid, domid, larb_mmu->bank[portid]);
 
 		if (enable)
 			larb_mmu->mmu |= MTK_SMI_MMU_EN(portid);
@@ -477,7 +483,7 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 		pm_runtime_put(m4udev);
 	}
 
-	mtk_iommu_config(data, dev, true);
+	mtk_iommu_config(data, dev, true, domid);
 	return 0;
 }
 
@@ -489,7 +495,7 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain,
 	if (!data)
 		return;
 
-	mtk_iommu_config(data, dev, false);
+	mtk_iommu_config(data, dev, false, 0);
 }
 
 static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
diff --git a/drivers/memory/mtk-smi.c b/drivers/memory/mtk-smi.c
index 89f92fa2afa5..fae61c5fbd70 100644
--- a/drivers/memory/mtk-smi.c
+++ b/drivers/memory/mtk-smi.c
@@ -44,6 +44,10 @@
 /* mt2712 */
 #define SMI_LARB_NONSEC_CON(id)	(0x380 + ((id) * 4))
 #define F_MMU_EN		BIT(0)
+#define BANK_SEL(id)		({			\
+	u32 _id = (id) & 0x3;				\
+	(_id << 8 | _id << 10 | _id << 12 | _id << 14);	\
+})
 
 /* SMI COMMON */
 #define SMI_BUS_SEL			0x220
@@ -88,6 +92,7 @@ struct mtk_smi_larb { /* larb: local arbiter */
 	const struct mtk_smi_larb_gen	*larb_gen;
 	int				larbid;
 	u32				*mmu;
+	unsigned char			*bank;
 };
 
 static int mtk_smi_clk_enable(const struct mtk_smi *smi)
@@ -154,6 +159,7 @@ mtk_smi_larb_bind(struct device *dev, struct device *master, void *data)
 		if (dev == larb_mmu[i].dev) {
 			larb->larbid = i;
 			larb->mmu = &larb_mmu[i].mmu;
+			larb->bank = larb_mmu[i].bank;
 			return 0;
 		}
 	}
@@ -172,6 +178,7 @@ static void mtk_smi_larb_config_port_gen2_general(struct device *dev)
 	for_each_set_bit(i, (unsigned long *)larb->mmu, 32) {
 		reg = readl_relaxed(larb->base + SMI_LARB_NONSEC_CON(i));
 		reg |= F_MMU_EN;
+		reg |= BANK_SEL(larb->bank[i]);
 		writel(reg, larb->base + SMI_LARB_NONSEC_CON(i));
 	}
 }
diff --git a/include/soc/mediatek/smi.h b/include/soc/mediatek/smi.h
index 9371bf572ab8..4cf445dbbdaa 100644
--- a/include/soc/mediatek/smi.h
+++ b/include/soc/mediatek/smi.h
@@ -16,6 +16,7 @@
 struct mtk_smi_larb_iommu {
 	struct device *dev;
 	unsigned int   mmu;
+	unsigned char  bank[32];
 };
 
 /*
-- 
cgit v1.2.3


From 23357572bec6b7f900d855f6dda9c77bb6d1c2de Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:12 +0800
Subject: iommu/mediatek: Remove unnecessary check in attach_device

This priv_data is set in the of_xlate. if of_xlate failed, it should
not enter attach_device. remove the unnecessary check.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-32-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 7403a7cb90ea..084fb4394ffc 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -453,9 +453,6 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 	struct device *m4udev = data->dev;
 	int ret, domid;
 
-	if (!data)
-		return -ENODEV;
-
 	domid = mtk_iommu_get_domain_id(dev, data->plat_data);
 	if (domid < 0)
 		return domid;
@@ -492,9 +489,6 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain,
 {
 	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
 
-	if (!data)
-		return;
-
 	mtk_iommu_config(data, dev, false, 0);
 }
 
-- 
cgit v1.2.3


From 9e3489e06fb94a7908c3c8f098c191ff711a8182 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Mon, 11 Jan 2021 19:19:13 +0800
Subject: iommu/mediatek: Add mt8192 support

Add mt8192 iommu support.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://lore.kernel.org/r/20210111111914.22211-33-yong.wu@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/mtk_iommu.c | 22 ++++++++++++++++++++++
 drivers/iommu/mtk_iommu.h |  1 +
 2 files changed, 23 insertions(+)

(limited to 'drivers/iommu')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 084fb4394ffc..0ad14a7604b1 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -177,6 +177,16 @@ static const struct mtk_iommu_iova_region single_domain[] = {
 	{.iova_base = 0,		.size = SZ_4G},
 };
 
+static const struct mtk_iommu_iova_region mt8192_multi_dom[] = {
+	{ .iova_base = 0x0,		.size = SZ_4G},		/* disp: 0 ~ 4G */
+	#if IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT)
+	{ .iova_base = SZ_4G,		.size = SZ_4G},		/* vdec: 4G ~ 8G */
+	{ .iova_base = SZ_4G * 2,	.size = SZ_4G},		/* CAM/MDP: 8G ~ 12G */
+	{ .iova_base = 0x240000000ULL,	.size = 0x4000000},	/* CCU0 */
+	{ .iova_base = 0x244000000ULL,	.size = 0x4000000},	/* CCU1 */
+	#endif
+};
+
 /*
  * There may be 1 or 2 M4U HWs, But we always expect they are in the same domain
  * for the performance.
@@ -1038,12 +1048,24 @@ static const struct mtk_iommu_plat_data mt8183_data = {
 	.larbid_remap = {{0}, {4}, {5}, {6}, {7}, {2}, {3}, {1}},
 };
 
+static const struct mtk_iommu_plat_data mt8192_data = {
+	.m4u_plat       = M4U_MT8192,
+	.flags          = HAS_BCLK | HAS_SUB_COMM | OUT_ORDER_WR_EN |
+			  WR_THROT_EN | IOVA_34_EN,
+	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
+	.iova_region    = mt8192_multi_dom,
+	.iova_region_nr = ARRAY_SIZE(mt8192_multi_dom),
+	.larbid_remap   = {{0}, {1}, {4, 5}, {7}, {2}, {9, 11, 19, 20},
+			   {0, 14, 16}, {0, 13, 18, 17}},
+};
+
 static const struct of_device_id mtk_iommu_of_ids[] = {
 	{ .compatible = "mediatek,mt2712-m4u", .data = &mt2712_data},
 	{ .compatible = "mediatek,mt6779-m4u", .data = &mt6779_data},
 	{ .compatible = "mediatek,mt8167-m4u", .data = &mt8167_data},
 	{ .compatible = "mediatek,mt8173-m4u", .data = &mt8173_data},
 	{ .compatible = "mediatek,mt8183-m4u", .data = &mt8183_data},
+	{ .compatible = "mediatek,mt8192-m4u", .data = &mt8192_data},
 	{}
 };
 
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
index 6f2168e3222d..f81fa8862ed0 100644
--- a/drivers/iommu/mtk_iommu.h
+++ b/drivers/iommu/mtk_iommu.h
@@ -45,6 +45,7 @@ enum mtk_iommu_plat {
 	M4U_MT8167,
 	M4U_MT8173,
 	M4U_MT8183,
+	M4U_MT8192,
 };
 
 struct mtk_iommu_iova_region;
-- 
cgit v1.2.3