iommu/io-pgtable-arm: Prepare for TTBR1 usage

Now that we can correctly extract top-level indices without relying on
the remaining upper bits being zero, the only remaining impediments to
using a given table for TTBR1 are the address validation on map/unmap
and the awkward TCR translation granule format. Add a quirk so that we
can do the right thing at those points.

Tested-by: Jordan Crouse <[e-mail]>
Signed-off-by: Robin Murphy <[e-mail]>
Signed-off-by: Will Deacon <[e-mail]>

drivers/iommu/io-pgtable-arm.c

···
 #define ARM_LPAE_TCR_TG0_64K		1
 #define ARM_LPAE_TCR_TG0_16K		2
 
+#define ARM_LPAE_TCR_TG1_16K		1
+#define ARM_LPAE_TCR_TG1_4K		2
+#define ARM_LPAE_TCR_TG1_64K		3
+
 #define ARM_LPAE_TCR_SH_NS		0
 #define ARM_LPAE_TCR_SH_OS		2
 #define ARM_LPAE_TCR_SH_IS		3
···
 	arm_lpae_iopte *ptep = data->pgd;
 	int ret, lvl = data->start_level;
 	arm_lpae_iopte prot;
+	long iaext = (long)iova >> cfg->ias;
 
 	/* If no access, then nothing to do */
 	if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
···
 	if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
 		return -EINVAL;
 
-	if (WARN_ON(iova >> data->iop.cfg.ias || paddr >> data->iop.cfg.oas))
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+		iaext = ~iaext;
+	if (WARN_ON(iaext || paddr >> cfg->oas))
 		return -ERANGE;
 
 	prot = arm_lpae_prot_to_pte(data, iommu_prot);
···
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	arm_lpae_iopte *ptep = data->pgd;
+	long iaext = (long)iova >> cfg->ias;
 
 	if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
 		return 0;
 
-	if (WARN_ON(iova >> data->iop.cfg.ias))
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+		iaext = ~iaext;
+	if (WARN_ON(iaext))
 		return 0;
 
 	return __arm_lpae_unmap(data, gather, iova, size, data->start_level, ptep);
···
 	u64 reg;
 	struct arm_lpae_io_pgtable *data;
 	typeof(&cfg->arm_lpae_s1_cfg.tcr) tcr = &cfg->arm_lpae_s1_cfg.tcr;
+	bool tg1;
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
-			    IO_PGTABLE_QUIRK_NON_STRICT))
+			    IO_PGTABLE_QUIRK_NON_STRICT |
+			    IO_PGTABLE_QUIRK_ARM_TTBR1))
 		return NULL;
 
 	data = arm_lpae_alloc_pgtable(cfg);
···
 		tcr->orgn = ARM_LPAE_TCR_RGN_NC;
 	}
 
+	tg1 = cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1;
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
-		tcr->tg = ARM_LPAE_TCR_TG0_4K;
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_4K : ARM_LPAE_TCR_TG0_4K;
 		break;
 	case SZ_16K:
-		tcr->tg = ARM_LPAE_TCR_TG0_16K;
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_16K : ARM_LPAE_TCR_TG0_16K;
 		break;
 	case SZ_64K:
-		tcr->tg = ARM_LPAE_TCR_TG0_64K;
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_64K : ARM_LPAE_TCR_TG0_64K;
 		break;
 	}
 

include/linux/io-pgtable.h

···
 	 * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs
 	 *	on unmap, for DMA domains using the flush queue mechanism for
 	 *	delayed invalidation.
+	 *
+	 * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table
+	 *	for use in the upper half of a split address space.
 	 */
 	#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)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;