1 files changed, 155 insertions, 58 deletions

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 82e4be4dfdaf..67a483c1a935 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -28,6 +28,7 @@
 #include "mtk_iommu.h"
 
 #define REG_MMU_PT_BASE_ADDR			0x000
+#define MMU_PT_ADDR_MASK			GENMASK(31, 7)
 
 #define REG_MMU_INVALIDATE			0x020
 #define F_ALL_INVLD				0x2
@@ -44,12 +45,9 @@
 #define REG_MMU_DCM_DIS				0x050
 
 #define REG_MMU_CTRL_REG			0x110
+#define F_MMU_TF_PROT_TO_PROGRAM_ADDR		(2 << 4)
 #define F_MMU_PREFETCH_RT_REPLACE_MOD		BIT(4)
-#define F_MMU_TF_PROTECT_SEL_SHIFT(data) \
-	((data)->m4u_plat == M4U_MT2712 ? 4 : 5)
-/* It's named by F_MMU_TF_PROT_SEL in mt2712. */
-#define F_MMU_TF_PROTECT_SEL(prot, data) \
-	(((prot) & 0x3) << F_MMU_TF_PROTECT_SEL_SHIFT(data))
+#define F_MMU_TF_PROT_TO_PROGRAM_ADDR_MT8173	(2 << 5)
 
 #define REG_MMU_IVRP_PADDR			0x114
 
@@ -66,26 +64,32 @@
 #define F_INT_CLR_BIT				BIT(12)
 
 #define REG_MMU_INT_MAIN_CONTROL		0x124
-#define F_INT_TRANSLATION_FAULT			BIT(0)
-#define F_INT_MAIN_MULTI_HIT_FAULT		BIT(1)
-#define F_INT_INVALID_PA_FAULT			BIT(2)
-#define F_INT_ENTRY_REPLACEMENT_FAULT		BIT(3)
-#define F_INT_TLB_MISS_FAULT			BIT(4)
-#define F_INT_MISS_TRANSACTION_FIFO_FAULT	BIT(5)
-#define F_INT_PRETETCH_TRANSATION_FIFO_FAULT	BIT(6)
+						/* mmu0 | mmu1 */
+#define F_INT_TRANSLATION_FAULT			(BIT(0) | BIT(7))
+#define F_INT_MAIN_MULTI_HIT_FAULT		(BIT(1) | BIT(8))
+#define F_INT_INVALID_PA_FAULT			(BIT(2) | BIT(9))
+#define F_INT_ENTRY_REPLACEMENT_FAULT		(BIT(3) | BIT(10))
+#define F_INT_TLB_MISS_FAULT			(BIT(4) | BIT(11))
+#define F_INT_MISS_TRANSACTION_FIFO_FAULT	(BIT(5) | BIT(12))
+#define F_INT_PRETETCH_TRANSATION_FIFO_FAULT	(BIT(6) | BIT(13))
 
 #define REG_MMU_CPE_DONE			0x12C
 
 #define REG_MMU_FAULT_ST1			0x134
+#define F_REG_MMU0_FAULT_MASK			GENMASK(6, 0)
+#define F_REG_MMU1_FAULT_MASK			GENMASK(13, 7)
 
-#define REG_MMU_FAULT_VA			0x13c
+#define REG_MMU0_FAULT_VA			0x13c
 #define F_MMU_FAULT_VA_WRITE_BIT		BIT(1)
 #define F_MMU_FAULT_VA_LAYER_BIT		BIT(0)
 
-#define REG_MMU_INVLD_PA			0x140
-#define REG_MMU_INT_ID				0x150
-#define F_MMU0_INT_ID_LARB_ID(a)		(((a) >> 7) & 0x7)
-#define F_MMU0_INT_ID_PORT_ID(a)		(((a) >> 2) & 0x1f)
+#define REG_MMU0_INVLD_PA			0x140
+#define REG_MMU1_FAULT_VA			0x144
+#define REG_MMU1_INVLD_PA			0x148
+#define REG_MMU0_INT_ID				0x150
+#define REG_MMU1_INT_ID				0x154
+#define F_MMU_INT_ID_LARB_ID(a)			(((a) >> 7) & 0x7)
+#define F_MMU_INT_ID_PORT_ID(a)			(((a) >> 2) & 0x1f)
 
 #define MTK_PROTECT_PA_ALIGN			128
 
@@ -107,6 +111,30 @@ struct mtk_iommu_domain {
 
 static const struct iommu_ops mtk_iommu_ops;
 
+/*
+ * In M4U 4GB mode, the physical address is remapped as below:
+ *
+ * CPU Physical address:
+ * ====================
+ *
+ * 0      1G       2G     3G       4G     5G
+ * |---A---|---B---|---C---|---D---|---E---|
+ * +--I/O--+------------Memory-------------+
+ *
+ * IOMMU output physical address:
+ *  =============================
+ *
+ *                                 4G      5G     6G      7G      8G
+ *                                 |---E---|---B---|---C---|---D---|
+ *                                 +------------Memory-------------+
+ *
+ * The Region 'A'(I/O) can NOT be mapped by M4U; For Region 'B'/'C'/'D', the
+ * bit32 of the CPU physical address always is needed to set, and for Region
+ * 'E', the CPU physical address keep as is.
+ * Additionally, The iommu consumers always use the CPU phyiscal address.
+ */
+#define MTK_IOMMU_4GB_MODE_REMAP_BASE	 0x140000000UL
+
 static LIST_HEAD(m4ulist);	/* List all the M4U HWs */
 
 #define for_each_m4u(data)	list_for_each_entry(data, &m4ulist, list)
@@ -188,10 +216,32 @@ static void mtk_iommu_tlb_sync(void *cookie)
 	}
 }
 
-static const struct iommu_gather_ops mtk_iommu_gather_ops = {
+static void mtk_iommu_tlb_flush_walk(unsigned long iova, size_t size,
+				     size_t granule, void *cookie)
+{
+	mtk_iommu_tlb_add_flush_nosync(iova, size, granule, false, cookie);
+	mtk_iommu_tlb_sync(cookie);
+}
+
+static void mtk_iommu_tlb_flush_leaf(unsigned long iova, size_t size,
+				     size_t granule, void *cookie)
+{
+	mtk_iommu_tlb_add_flush_nosync(iova, size, granule, true, cookie);
+	mtk_iommu_tlb_sync(cookie);
+}
+
+static void mtk_iommu_tlb_flush_page_nosync(struct iommu_iotlb_gather *gather,
+					    unsigned long iova, size_t granule,
+					    void *cookie)
+{
+	mtk_iommu_tlb_add_flush_nosync(iova, granule, granule, true, cookie);
+}
+
+static const struct iommu_flush_ops mtk_iommu_flush_ops = {
 	.tlb_flush_all = mtk_iommu_tlb_flush_all,
-	.tlb_add_flush = mtk_iommu_tlb_add_flush_nosync,
-	.tlb_sync = mtk_iommu_tlb_sync,
+	.tlb_flush_walk = mtk_iommu_tlb_flush_walk,
+	.tlb_flush_leaf = mtk_iommu_tlb_flush_leaf,
+	.tlb_add_page = mtk_iommu_tlb_flush_page_nosync,
 };
 
 static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
@@ -204,13 +254,21 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
 
 	/* Read error info from registers */
 	int_state = readl_relaxed(data->base + REG_MMU_FAULT_ST1);
-	fault_iova = readl_relaxed(data->base + REG_MMU_FAULT_VA);
+	if (int_state & F_REG_MMU0_FAULT_MASK) {
+		regval = readl_relaxed(data->base + REG_MMU0_INT_ID);
+		fault_iova = readl_relaxed(data->base + REG_MMU0_FAULT_VA);
+		fault_pa = readl_relaxed(data->base + REG_MMU0_INVLD_PA);
+	} else {
+		regval = readl_relaxed(data->base + REG_MMU1_INT_ID);
+		fault_iova = readl_relaxed(data->base + REG_MMU1_FAULT_VA);
+		fault_pa = readl_relaxed(data->base + REG_MMU1_INVLD_PA);
+	}
 	layer = fault_iova & F_MMU_FAULT_VA_LAYER_BIT;
 	write = fault_iova & F_MMU_FAULT_VA_WRITE_BIT;
-	fault_pa = readl_relaxed(data->base + REG_MMU_INVLD_PA);
-	regval = readl_relaxed(data->base + REG_MMU_INT_ID);
-	fault_larb = F_MMU0_INT_ID_LARB_ID(regval);
-	fault_port = F_MMU0_INT_ID_PORT_ID(regval);
+	fault_larb = F_MMU_INT_ID_LARB_ID(regval);
+	fault_port = F_MMU_INT_ID_PORT_ID(regval);
+
+	fault_larb = data->plat_data->larbid_remap[fault_larb];
 
 	if (report_iommu_fault(&dom->domain, data->dev, fault_iova,
 			       write ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ)) {
@@ -242,7 +300,7 @@ static void mtk_iommu_config(struct mtk_iommu_data *data,
 	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->smi_imu.larb_imu[larbid];
+		larb_mmu = &data->larb_imu[larbid];
 
 		dev_dbg(dev, "%s iommu port: %d\n",
 			enable ? "enable" : "disable", portid);
@@ -263,17 +321,15 @@ 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_TLBI_ON_MAP |
+			IO_PGTABLE_QUIRK_ARM_MTK_EXT,
 		.pgsize_bitmap = mtk_iommu_ops.pgsize_bitmap,
 		.ias = 32,
-		.oas = 32,
-		.tlb = &mtk_iommu_gather_ops,
+		.oas = 34,
+		.tlb = &mtk_iommu_flush_ops,
 		.iommu_dev = data->dev,
 	};
 
-	if (data->enable_4GB)
-		dom->cfg.quirks |= IO_PGTABLE_QUIRK_ARM_MTK_4GB;
-
 	dom->iop = alloc_io_pgtable_ops(ARM_V7S, &dom->cfg, data);
 	if (!dom->iop) {
 		dev_err(data->dev, "Failed to alloc io pgtable\n");
@@ -336,7 +392,7 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 	/* Update the pgtable base address register of the M4U HW */
 	if (!data->m4u_dom) {
 		data->m4u_dom = dom;
-		writel(dom->cfg.arm_v7s_cfg.ttbr[0],
+		writel(dom->cfg.arm_v7s_cfg.ttbr[0] & MMU_PT_ADDR_MASK,
 		       data->base + REG_MMU_PT_BASE_ADDR);
 	}
 
@@ -359,32 +415,43 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
 			 phys_addr_t paddr, size_t size, int prot)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
 	unsigned long flags;
 	int ret;
 
+	/* The "4GB mode" M4U physically can not use the lower remap of Dram. */
+	if (data->enable_4GB)
+		paddr |= BIT_ULL(32);
+
 	spin_lock_irqsave(&dom->pgtlock, flags);
-	ret = dom->iop->map(dom->iop, iova, paddr & DMA_BIT_MASK(32),
-			    size, prot);
+	ret = dom->iop->map(dom->iop, iova, paddr, size, prot);
 	spin_unlock_irqrestore(&dom->pgtlock, flags);
 
 	return ret;
 }
 
 static size_t mtk_iommu_unmap(struct iommu_domain *domain,
-			      unsigned long iova, size_t size)
+			      unsigned long iova, size_t size,
+			      struct iommu_iotlb_gather *gather)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	unsigned long flags;
 	size_t unmapsz;
 
 	spin_lock_irqsave(&dom->pgtlock, flags);
-	unmapsz = dom->iop->unmap(dom->iop, iova, size);
+	unmapsz = dom->iop->unmap(dom->iop, iova, size, gather);
 	spin_unlock_irqrestore(&dom->pgtlock, flags);
 
 	return unmapsz;
 }
 
-static void mtk_iommu_iotlb_sync(struct iommu_domain *domain)
+static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
+}
+
+static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
+				 struct iommu_iotlb_gather *gather)
 {
 	mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
 }
@@ -401,8 +468,8 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 	pa = dom->iop->iova_to_phys(dom->iop, iova);
 	spin_unlock_irqrestore(&dom->pgtlock, flags);
 
-	if (data->enable_4GB)
-		pa |= BIT_ULL(32);
+	if (data->enable_4GB && pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
+		pa &= ~BIT_ULL(32);
 
 	return pa;
 }
@@ -490,7 +557,7 @@ static const struct iommu_ops mtk_iommu_ops = {
 	.detach_dev	= mtk_iommu_detach_device,
 	.map		= mtk_iommu_map,
 	.unmap		= mtk_iommu_unmap,
-	.flush_iotlb_all = mtk_iommu_iotlb_sync,
+	.flush_iotlb_all = mtk_iommu_flush_iotlb_all,
 	.iotlb_sync	= mtk_iommu_iotlb_sync,
 	.iova_to_phys	= mtk_iommu_iova_to_phys,
 	.add_device	= mtk_iommu_add_device,
@@ -511,9 +578,11 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
 		return ret;
 	}
 
-	regval = F_MMU_TF_PROTECT_SEL(2, data);
-	if (data->m4u_plat == M4U_MT8173)
-		regval |= F_MMU_PREFETCH_RT_REPLACE_MOD;
+	if (data->plat_data->m4u_plat == M4U_MT8173)
+		regval = F_MMU_PREFETCH_RT_REPLACE_MOD |
+			 F_MMU_TF_PROT_TO_PROGRAM_ADDR_MT8173;
+	else
+		regval = F_MMU_TF_PROT_TO_PROGRAM_ADDR;
 	writel_relaxed(regval, data->base + REG_MMU_CTRL_REG);
 
 	regval = F_L2_MULIT_HIT_EN |
@@ -533,14 +602,14 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
 		F_INT_PRETETCH_TRANSATION_FIFO_FAULT;
 	writel_relaxed(regval, data->base + REG_MMU_INT_MAIN_CONTROL);
 
-	if (data->m4u_plat == M4U_MT8173)
+	if (data->plat_data->m4u_plat == M4U_MT8173)
 		regval = (data->protect_base >> 1) | (data->enable_4GB << 31);
 	else
 		regval = lower_32_bits(data->protect_base) |
 			 upper_32_bits(data->protect_base);
 	writel_relaxed(regval, data->base + REG_MMU_IVRP_PADDR);
 
-	if (data->enable_4GB && data->m4u_plat != M4U_MT8173) {
+	if (data->enable_4GB && data->plat_data->has_vld_pa_rng) {
 		/*
 		 * If 4GB mode is enabled, the validate PA range is from
 		 * 0x1_0000_0000 to 0x1_ffff_ffff. here record bit[32:30].
@@ -550,8 +619,7 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
 	}
 	writel_relaxed(0, data->base + REG_MMU_DCM_DIS);
 
-	/* It's MISC control register whose default value is ok except mt8173.*/
-	if (data->m4u_plat == M4U_MT8173)
+	if (data->plat_data->reset_axi)
 		writel_relaxed(0, data->base + REG_MMU_STANDARD_AXI_MODE);
 
 	if (devm_request_irq(data->dev, data->irq, mtk_iommu_isr, 0,
@@ -584,7 +652,7 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	if (!data)
 		return -ENOMEM;
 	data->dev = dev;
-	data->m4u_plat = (enum mtk_iommu_plat)of_device_get_match_data(dev);
+	data->plat_data = of_device_get_match_data(dev);
 
 	/* Protect memory. HW will access here while translation fault.*/
 	protect = devm_kzalloc(dev, MTK_PROTECT_PA_ALIGN * 2, GFP_KERNEL);
@@ -594,6 +662,8 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 
 	/* Whether the current dram is over 4GB */
 	data->enable_4GB = !!(max_pfn > (BIT_ULL(32) >> PAGE_SHIFT));
+	if (!data->plat_data->has_4gb_mode)
+		data->enable_4GB = false;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	data->base = devm_ioremap_resource(dev, res);
@@ -605,15 +675,16 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	if (data->irq < 0)
 		return data->irq;
 
-	data->bclk = devm_clk_get(dev, "bclk");
-	if (IS_ERR(data->bclk))
-		return PTR_ERR(data->bclk);
+	if (data->plat_data->has_bclk) {
+		data->bclk = devm_clk_get(dev, "bclk");
+		if (IS_ERR(data->bclk))
+			return PTR_ERR(data->bclk);
+	}
 
 	larb_nr = of_count_phandle_with_args(dev->of_node,
 					     "mediatek,larbs", NULL);
 	if (larb_nr < 0)
 		return larb_nr;
-	data->smi_imu.larb_nr = larb_nr;
 
 	for (i = 0; i < larb_nr; i++) {
 		struct device_node *larbnode;
@@ -638,7 +709,7 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 			of_node_put(larbnode);
 			return -EPROBE_DEFER;
 		}
-		data->smi_imu.larb_imu[id].dev = &plarbdev->dev;
+		data->larb_imu[id].dev = &plarbdev->dev;
 
 		component_match_add_release(dev, &match, release_of,
 					    compare_of, larbnode);
@@ -699,6 +770,7 @@ static int __maybe_unused mtk_iommu_suspend(struct device *dev)
 	reg->int_control0 = readl_relaxed(base + REG_MMU_INT_CONTROL0);
 	reg->int_main_control = readl_relaxed(base + REG_MMU_INT_MAIN_CONTROL);
 	reg->ivrp_paddr = readl_relaxed(base + REG_MMU_IVRP_PADDR);
+	reg->vld_pa_rng = readl_relaxed(base + REG_MMU_VLD_PA_RNG);
 	clk_disable_unprepare(data->bclk);
 	return 0;
 }
@@ -707,6 +779,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
 {
 	struct mtk_iommu_data *data = dev_get_drvdata(dev);
 	struct mtk_iommu_suspend_reg *reg = &data->reg;
+	struct mtk_iommu_domain *m4u_dom = data->m4u_dom;
 	void __iomem *base = data->base;
 	int ret;
 
@@ -722,8 +795,9 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
 	writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL0);
 	writel_relaxed(reg->int_main_control, base + REG_MMU_INT_MAIN_CONTROL);
 	writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR);
-	if (data->m4u_dom)
-		writel(data->m4u_dom->cfg.arm_v7s_cfg.ttbr[0],
+	writel_relaxed(reg->vld_pa_rng, base + REG_MMU_VLD_PA_RNG);
+	if (m4u_dom)
+		writel(m4u_dom->cfg.arm_v7s_cfg.ttbr[0] & MMU_PT_ADDR_MASK,
 		       base + REG_MMU_PT_BASE_ADDR);
 	return 0;
 }
@@ -732,9 +806,32 @@ static const struct dev_pm_ops mtk_iommu_pm_ops = {
 	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_iommu_suspend, mtk_iommu_resume)
 };
 
+static const struct mtk_iommu_plat_data mt2712_data = {
+	.m4u_plat     = M4U_MT2712,
+	.has_4gb_mode = true,
+	.has_bclk     = true,
+	.has_vld_pa_rng   = true,
+	.larbid_remap = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9},
+};
+
+static const struct mtk_iommu_plat_data mt8173_data = {
+	.m4u_plat     = M4U_MT8173,
+	.has_4gb_mode = true,
+	.has_bclk     = true,
+	.reset_axi    = true,
+	.larbid_remap = {0, 1, 2, 3, 4, 5}, /* Linear mapping. */
+};
+
+static const struct mtk_iommu_plat_data mt8183_data = {
+	.m4u_plat     = M4U_MT8183,
+	.reset_axi    = true,
+	.larbid_remap = {0, 4, 5, 6, 7, 2, 3, 1},
+};
+
 static const struct of_device_id mtk_iommu_of_ids[] = {
-	{ .compatible = "mediatek,mt2712-m4u", .data = (void *)M4U_MT2712},
-	{ .compatible = "mediatek,mt8173-m4u", .data = (void *)M4U_MT8173},
+	{ .compatible = "mediatek,mt2712-m4u", .data = &mt2712_data},
+	{ .compatible = "mediatek,mt8173-m4u", .data = &mt8173_data},
+	{ .compatible = "mediatek,mt8183-m4u", .data = &mt8183_data},
 	{}
 };