1 files changed, 149 insertions, 26 deletions

diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 7a2932772fdf..94b9d8e5b9a4 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -21,7 +21,6 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/of.h>
-#include <linux/of_iommu.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -96,6 +95,15 @@ static const char * const rk_iommu_clocks[] = {
 	"aclk", "iface",
 };
 
+struct rk_iommu_ops {
+	phys_addr_t (*pt_address)(u32 dte);
+	u32 (*mk_dtentries)(dma_addr_t pt_dma);
+	u32 (*mk_ptentries)(phys_addr_t page, int prot);
+	phys_addr_t (*dte_addr_phys)(u32 addr);
+	u32 (*dma_addr_dte)(dma_addr_t dt_dma);
+	u64 dma_bit_mask;
+};
+
 struct rk_iommu {
 	struct device *dev;
 	void __iomem **bases;
@@ -116,6 +124,7 @@ struct rk_iommudata {
 };
 
 static struct device *dma_dev;
+static const struct rk_iommu_ops *rk_ops;
 
 static inline void rk_table_flush(struct rk_iommu_domain *dom, dma_addr_t dma,
 				  unsigned int count)
@@ -179,6 +188,33 @@ static inline phys_addr_t rk_dte_pt_address(u32 dte)
 	return (phys_addr_t)dte & RK_DTE_PT_ADDRESS_MASK;
 }
 
+/*
+ * In v2:
+ * 31:12 - PT address bit 31:0
+ * 11: 8 - PT address bit 35:32
+ *  7: 4 - PT address bit 39:36
+ *  3: 1 - Reserved
+ *     0 - 1 if PT @ PT address is valid
+ */
+#define RK_DTE_PT_ADDRESS_MASK_V2 GENMASK_ULL(31, 4)
+#define DTE_HI_MASK1	GENMASK(11, 8)
+#define DTE_HI_MASK2	GENMASK(7, 4)
+#define DTE_HI_SHIFT1	24 /* shift bit 8 to bit 32 */
+#define DTE_HI_SHIFT2	32 /* shift bit 4 to bit 36 */
+#define PAGE_DESC_HI_MASK1	GENMASK_ULL(39, 36)
+#define PAGE_DESC_HI_MASK2	GENMASK_ULL(35, 32)
+
+static inline phys_addr_t rk_dte_pt_address_v2(u32 dte)
+{
+	u64 dte_v2 = dte;
+
+	dte_v2 = ((dte_v2 & DTE_HI_MASK2) << DTE_HI_SHIFT2) |
+		 ((dte_v2 & DTE_HI_MASK1) << DTE_HI_SHIFT1) |
+		 (dte_v2 & RK_DTE_PT_ADDRESS_MASK);
+
+	return (phys_addr_t)dte_v2;
+}
+
 static inline bool rk_dte_is_pt_valid(u32 dte)
 {
 	return dte & RK_DTE_PT_VALID;
@@ -189,6 +225,15 @@ static inline u32 rk_mk_dte(dma_addr_t pt_dma)
 	return (pt_dma & RK_DTE_PT_ADDRESS_MASK) | RK_DTE_PT_VALID;
 }
 
+static inline u32 rk_mk_dte_v2(dma_addr_t pt_dma)
+{
+	pt_dma = (pt_dma & RK_DTE_PT_ADDRESS_MASK) |
+		 ((pt_dma & PAGE_DESC_HI_MASK1) >> DTE_HI_SHIFT1) |
+		 (pt_dma & PAGE_DESC_HI_MASK2) >> DTE_HI_SHIFT2;
+
+	return (pt_dma & RK_DTE_PT_ADDRESS_MASK_V2) | RK_DTE_PT_VALID;
+}
+
 /*
  * Each PTE has a Page address, some flags and a valid bit:
  * +---------------------+---+-------+-+
@@ -215,11 +260,6 @@ static inline u32 rk_mk_dte(dma_addr_t pt_dma)
 #define RK_PTE_PAGE_READABLE      BIT(1)
 #define RK_PTE_PAGE_VALID         BIT(0)
 
-static inline phys_addr_t rk_pte_page_address(u32 pte)
-{
-	return (phys_addr_t)pte & RK_PTE_PAGE_ADDRESS_MASK;
-}
-
 static inline bool rk_pte_is_page_valid(u32 pte)
 {
 	return pte & RK_PTE_PAGE_VALID;
@@ -235,6 +275,29 @@ static u32 rk_mk_pte(phys_addr_t page, int prot)
 	return page | flags | RK_PTE_PAGE_VALID;
 }
 
+/*
+ * In v2:
+ * 31:12 - Page address bit 31:0
+ *  11:9 - Page address bit 34:32
+ *   8:4 - Page address bit 39:35
+ *     3 - Security
+ *     2 - Readable
+ *     1 - Writable
+ *     0 - 1 if Page @ Page address is valid
+ */
+#define RK_PTE_PAGE_READABLE_V2      BIT(2)
+#define RK_PTE_PAGE_WRITABLE_V2      BIT(1)
+
+static u32 rk_mk_pte_v2(phys_addr_t page, int prot)
+{
+	u32 flags = 0;
+
+	flags |= (prot & IOMMU_READ) ? RK_PTE_PAGE_READABLE_V2 : 0;
+	flags |= (prot & IOMMU_WRITE) ? RK_PTE_PAGE_WRITABLE_V2 : 0;
+
+	return rk_mk_dte_v2(page) | flags;
+}
+
 static u32 rk_mk_pte_invalid(u32 pte)
 {
 	return pte & ~RK_PTE_PAGE_VALID;
@@ -448,10 +511,10 @@ static int rk_iommu_force_reset(struct rk_iommu *iommu)
 	 * and verifying that upper 5 nybbles are read back.
 	 */
 	for (i = 0; i < iommu->num_mmu; i++) {
-		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, DTE_ADDR_DUMMY);
+		dte_addr = rk_ops->pt_address(DTE_ADDR_DUMMY);
+		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, dte_addr);
 
-		dte_addr = rk_iommu_read(iommu->bases[i], RK_MMU_DTE_ADDR);
-		if (dte_addr != (DTE_ADDR_DUMMY & RK_DTE_PT_ADDRESS_MASK)) {
+		if (dte_addr != rk_iommu_read(iommu->bases[i], RK_MMU_DTE_ADDR)) {
 			dev_err(iommu->dev, "Error during raw reset. MMU_DTE_ADDR is not functioning\n");
 			return -EFAULT;
 		}
@@ -470,6 +533,31 @@ static int rk_iommu_force_reset(struct rk_iommu *iommu)
 	return 0;
 }
 
+static inline phys_addr_t rk_dte_addr_phys(u32 addr)
+{
+	return (phys_addr_t)addr;
+}
+
+static inline u32 rk_dma_addr_dte(dma_addr_t dt_dma)
+{
+	return dt_dma;
+}
+
+#define DT_HI_MASK GENMASK_ULL(39, 32)
+#define DT_SHIFT   28
+
+static inline phys_addr_t rk_dte_addr_phys_v2(u32 addr)
+{
+	return (phys_addr_t)(addr & RK_DTE_PT_ADDRESS_MASK) |
+	       ((addr & DT_HI_MASK) << DT_SHIFT);
+}
+
+static inline u32 rk_dma_addr_dte_v2(dma_addr_t dt_dma)
+{
+	return (dt_dma & RK_DTE_PT_ADDRESS_MASK) |
+	       ((dt_dma & DT_HI_MASK) >> DT_SHIFT);
+}
+
 static void log_iova(struct rk_iommu *iommu, int index, dma_addr_t iova)
 {
 	void __iomem *base = iommu->bases[index];
@@ -489,7 +577,7 @@ static void log_iova(struct rk_iommu *iommu, int index, dma_addr_t iova)
 	page_offset = rk_iova_page_offset(iova);
 
 	mmu_dte_addr = rk_iommu_read(base, RK_MMU_DTE_ADDR);
-	mmu_dte_addr_phys = (phys_addr_t)mmu_dte_addr;
+	mmu_dte_addr_phys = rk_ops->dte_addr_phys(mmu_dte_addr);
 
 	dte_addr_phys = mmu_dte_addr_phys + (4 * dte_index);
 	dte_addr = phys_to_virt(dte_addr_phys);
@@ -498,14 +586,14 @@ static void log_iova(struct rk_iommu *iommu, int index, dma_addr_t iova)
 	if (!rk_dte_is_pt_valid(dte))
 		goto print_it;
 
-	pte_addr_phys = rk_dte_pt_address(dte) + (pte_index * 4);
+	pte_addr_phys = rk_ops->pt_address(dte) + (pte_index * 4);
 	pte_addr = phys_to_virt(pte_addr_phys);
 	pte = *pte_addr;
 
 	if (!rk_pte_is_page_valid(pte))
 		goto print_it;
 
-	page_addr_phys = rk_pte_page_address(pte) + page_offset;
+	page_addr_phys = rk_ops->pt_address(pte) + page_offset;
 	page_flags = pte & RK_PTE_PAGE_FLAGS_MASK;
 
 print_it:
@@ -601,13 +689,13 @@ static phys_addr_t rk_iommu_iova_to_phys(struct iommu_domain *domain,
 	if (!rk_dte_is_pt_valid(dte))
 		goto out;
 
-	pt_phys = rk_dte_pt_address(dte);
+	pt_phys = rk_ops->pt_address(dte);
 	page_table = (u32 *)phys_to_virt(pt_phys);
 	pte = page_table[rk_iova_pte_index(iova)];
 	if (!rk_pte_is_page_valid(pte))
 		goto out;
 
-	phys = rk_pte_page_address(pte) + rk_iova_page_offset(iova);
+	phys = rk_ops->pt_address(pte) + rk_iova_page_offset(iova);
 out:
 	spin_unlock_irqrestore(&rk_domain->dt_lock, flags);
 
@@ -679,14 +767,13 @@ static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	dte = rk_mk_dte(pt_dma);
+	dte = rk_ops->mk_dtentries(pt_dma);
 	*dte_addr = dte;
 
-	rk_table_flush(rk_domain, pt_dma, NUM_PT_ENTRIES);
 	rk_table_flush(rk_domain,
 		       rk_domain->dt_dma + dte_index * sizeof(u32), 1);
 done:
-	pt_phys = rk_dte_pt_address(dte);
+	pt_phys = rk_ops->pt_address(dte);
 	return (u32 *)phys_to_virt(pt_phys);
 }
 
@@ -728,7 +815,7 @@ static int rk_iommu_map_iova(struct rk_iommu_domain *rk_domain, u32 *pte_addr,
 		if (rk_pte_is_page_valid(pte))
 			goto unwind;
 
-		pte_addr[pte_count] = rk_mk_pte(paddr, prot);
+		pte_addr[pte_count] = rk_ops->mk_ptentries(paddr, prot);
 
 		paddr += SPAGE_SIZE;
 	}
@@ -750,7 +837,7 @@ unwind:
 			    pte_count * SPAGE_SIZE);
 
 	iova += pte_count * SPAGE_SIZE;
-	page_phys = rk_pte_page_address(pte_addr[pte_count]);
+	page_phys = rk_ops->pt_address(pte_addr[pte_count]);
 	pr_err("iova: %pad already mapped to %pa cannot remap to phys: %pa prot: %#x\n",
 	       &iova, &page_phys, &paddr, prot);
 
@@ -785,7 +872,8 @@ static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova,
 	dte_index = rk_domain->dt[rk_iova_dte_index(iova)];
 	pte_index = rk_iova_pte_index(iova);
 	pte_addr = &page_table[pte_index];
-	pte_dma = rk_dte_pt_address(dte_index) + pte_index * sizeof(u32);
+
+	pte_dma = rk_ops->pt_address(dte_index) + pte_index * sizeof(u32);
 	ret = rk_iommu_map_iova(rk_domain, pte_addr, pte_dma, iova,
 				paddr, size, prot);
 
@@ -821,7 +909,7 @@ static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova,
 		return 0;
 	}
 
-	pt_phys = rk_dte_pt_address(dte);
+	pt_phys = rk_ops->pt_address(dte);
 	pte_addr = (u32 *)phys_to_virt(pt_phys) + rk_iova_pte_index(iova);
 	pte_dma = pt_phys + rk_iova_pte_index(iova) * sizeof(u32);
 	unmap_size = rk_iommu_unmap_iova(rk_domain, pte_addr, pte_dma, size);
@@ -879,7 +967,7 @@ static int rk_iommu_enable(struct rk_iommu *iommu)
 
 	for (i = 0; i < iommu->num_mmu; i++) {
 		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR,
-			       rk_domain->dt_dma);
+			       rk_ops->dma_addr_dte(rk_domain->dt_dma));
 		rk_iommu_base_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE);
 		rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, RK_MMU_IRQ_MASK);
 	}
@@ -1004,8 +1092,6 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
 		goto err_free_dt;
 	}
 
-	rk_table_flush(rk_domain, rk_domain->dt_dma, NUM_DT_ENTRIES);
-
 	spin_lock_init(&rk_domain->iommus_lock);
 	spin_lock_init(&rk_domain->dt_lock);
 	INIT_LIST_HEAD(&rk_domain->iommus);
@@ -1037,7 +1123,7 @@ static void rk_iommu_domain_free(struct iommu_domain *domain)
 	for (i = 0; i < NUM_DT_ENTRIES; i++) {
 		u32 dte = rk_domain->dt[i];
 		if (rk_dte_is_pt_valid(dte)) {
-			phys_addr_t pt_phys = rk_dte_pt_address(dte);
+			phys_addr_t pt_phys = rk_ops->pt_address(dte);
 			u32 *page_table = phys_to_virt(pt_phys);
 			dma_unmap_single(dma_dev, pt_phys,
 					 SPAGE_SIZE, DMA_TO_DEVICE);
@@ -1127,6 +1213,7 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct rk_iommu *iommu;
 	struct resource *res;
+	const struct rk_iommu_ops *ops;
 	int num_res = pdev->num_resources;
 	int err, i;
 
@@ -1138,6 +1225,17 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	iommu->dev = dev;
 	iommu->num_mmu = 0;
 
+	ops = of_device_get_match_data(dev);
+	if (!rk_ops)
+		rk_ops = ops;
+
+	/*
+	 * That should not happen unless different versions of the
+	 * hardware block are embedded the same SoC
+	 */
+	if (WARN_ON(rk_ops != ops))
+		return -EINVAL;
+
 	iommu->bases = devm_kcalloc(dev, num_res, sizeof(*iommu->bases),
 				    GFP_KERNEL);
 	if (!iommu->bases)
@@ -1226,6 +1324,8 @@ static int rk_iommu_probe(struct platform_device *pdev)
 		}
 	}
 
+	dma_set_mask_and_coherent(dev, rk_ops->dma_bit_mask);
+
 	return 0;
 err_remove_sysfs:
 	iommu_device_sysfs_remove(&iommu->iommu);
@@ -1277,8 +1377,31 @@ static const struct dev_pm_ops rk_iommu_pm_ops = {
 				pm_runtime_force_resume)
 };
 
+static struct rk_iommu_ops iommu_data_ops_v1 = {
+	.pt_address = &rk_dte_pt_address,
+	.mk_dtentries = &rk_mk_dte,
+	.mk_ptentries = &rk_mk_pte,
+	.dte_addr_phys = &rk_dte_addr_phys,
+	.dma_addr_dte = &rk_dma_addr_dte,
+	.dma_bit_mask = DMA_BIT_MASK(32),
+};
+
+static struct rk_iommu_ops iommu_data_ops_v2 = {
+	.pt_address = &rk_dte_pt_address_v2,
+	.mk_dtentries = &rk_mk_dte_v2,
+	.mk_ptentries = &rk_mk_pte_v2,
+	.dte_addr_phys = &rk_dte_addr_phys_v2,
+	.dma_addr_dte = &rk_dma_addr_dte_v2,
+	.dma_bit_mask = DMA_BIT_MASK(40),
+};
+
 static const struct of_device_id rk_iommu_dt_ids[] = {
-	{ .compatible = "rockchip,iommu" },
+	{	.compatible = "rockchip,iommu",
+		.data = &iommu_data_ops_v1,
+	},
+	{	.compatible = "rockchip,rk3568-iommu",
+		.data = &iommu_data_ops_v2,
+	},
 	{ /* sentinel */ }
 };