iommu/mediatek: Adjust the PA for the 4GB Mode

After extending the v7s support PA[33:32] for MediaTek, we have to adjust
the PA ourself for the 4GB mode.

In the 4GB Mode, the PA will remap like this:
CPU PA         ->    M4U output PA
0x4000_0000          0x1_4000_0000 (Add bit32)
0x8000_0000          0x1_8000_0000 ...
0xc000_0000          0x1_c000_0000 ...
0x1_0000_0000        0x1_0000_0000 (No change)

1) Always add bit32 for CPU PA in ->map.
2) Discard the bit32 in iova_to_phys if PA > 0x1_4000_0000 since the
iommu consumer always use the CPU PA.

Besides, the "oas" always is set to 34 since v7s has already supported our
case.

Both mt2712 and mt8173 support this "4GB mode" while the mt8183 don't.
The PA in mt8183 won't remap.
Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/mtk_iommu.c

@@ -129,7 +129,7 @@ static const struct iommu_ops mtk_iommu_ops;
  * '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	 0x40000000
+#define MTK_IOMMU_4GB_MODE_REMAP_BASE	 0x140000000UL
 
 static LIST_HEAD(m4ulist);	/* List all the M4U HWs */
 
@@ -287,17 +287,15 @@ 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,
+		.oas = 34,
 		.tlb = &mtk_iommu_gather_ops,
 		.iommu_dev = data->dev,
 	};
 
-	if (data->enable_4GB)
-		dom->cfg.quirks |= IO_PGTABLE_QUIRK_ARM_MTK_EXT;
-
 	dom->iop = alloc_io_pgtable_ops(ARM_V7S, &dom->cfg, data);
 	if (!dom->iop) {
 		dev_err(data->dev, "Failed to alloc io pgtable\n");
@@ -383,12 +381,16 @@ 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;
@@ -425,8 +427,8 @@ 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 < MTK_IOMMU_4GB_MODE_REMAP_BASE)
-		pa |= BIT_ULL(32);
+	if (data->enable_4GB && pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
+		pa &= ~BIT_ULL(32);
 
 	return pa;
 }
@@ -618,6 +620,8 @@ 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);
@@ -758,10 +762,12 @@ static const struct dev_pm_ops mtk_iommu_pm_ops = {
 
 static const struct mtk_iommu_plat_data mt2712_data = {
 	.m4u_plat     = M4U_MT2712,
+	.has_4gb_mode = true,
 };
 
 static const struct mtk_iommu_plat_data mt8173_data = {
 	.m4u_plat     = M4U_MT8173,
+	.has_4gb_mode = true,
 };
 
 static const struct of_device_id mtk_iommu_of_ids[] = {

drivers/iommu/mtk_iommu.h

@@ -34,6 +34,7 @@ enum mtk_iommu_plat {
 
 struct mtk_iommu_plat_data {
 	enum mtk_iommu_plat m4u_plat;
+	bool                has_4gb_mode;
 };
 
 struct mtk_iommu_domain;