iommu/io-pgtable: Move Apple DART support to its own file

The pte format used by the DARTs found in the Apple M1 (t8103) is not
fully compatible with io-pgtable-arm. The 24 MSB are used for subpage
protection (mapping only parts of page) and conflict with the address
mask. In addition bit 1 is not available for tagging entries but disables
subpage protection. Subpage protection could be useful to support a CPU
granule of 4k with the fixed IOMMU page size of 16k.

The DARTs found on Apple M1 Pro/Max/Ultra use another different pte
format which is even less compatible. To support an output address size
of 42 bit the address is shifted down by 4. Subpage protection is
mandatory and bit 1 signifies uncached mappings used by the display
controller.

It would be advantageous to share code for all known Apple DART
variants to support common features. The page table allocator for DARTs
is less complex since it uses a two levels of translation table without
support for huge pages.
Signed-off-by: Janne Grunau <j@jannau.net>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Sven Peter <sven@svenpeter.dev>
Acked-by: Hector Martin <marcan@marcan.st>
Link: https://lore.kernel.org/r/20220916094152.87137-3-j@jannau.net
[ joro: Fix compile warning in __dart_alloc_pages()]
Signed-off-by: Joerg Roedel <jroedel@suse.de>

MAINTAINERS

@@ -1887,6 +1887,7 @@ F:	drivers/dma/apple-admac.c
 F:	drivers/i2c/busses/i2c-pasemi-core.c
 F:	drivers/i2c/busses/i2c-pasemi-platform.c
 F:	drivers/iommu/apple-dart.c
+F:	drivers/iommu/io-pgtable-dart.c
 F:	drivers/irqchip/irq-apple-aic.c
 F:	drivers/mailbox/apple-mailbox.c
 F:	drivers/nvme/host/apple.c

drivers/iommu/Kconfig

@@ -67,6 +67,17 @@ config IOMMU_IO_PGTABLE_ARMV7S_SELFTEST
 
 	  If unsure, say N here.
 
+config IOMMU_IO_PGTABLE_DART
+	bool "Apple DART Formats"
+	select IOMMU_IO_PGTABLE
+	depends on ARM64 || (COMPILE_TEST && !GENERIC_ATOMIC64)
+	help
+	  Enable support for the Apple DART pagetable formats. These include
+	  the t8020 and t6000/t8110 DART formats used in Apple M1/M2 family
+	  SoCs.
+
+	  If unsure, say N here.
+
 endmenu
 
 config IOMMU_DEBUGFS
@@ -294,7 +305,7 @@ config APPLE_DART
 	tristate "Apple DART IOMMU Support"
 	depends on ARCH_APPLE || (COMPILE_TEST && !GENERIC_ATOMIC64)
 	select IOMMU_API
-	select IOMMU_IO_PGTABLE_LPAE
+	select IOMMU_IO_PGTABLE_DART
 	default ARCH_APPLE
 	help
 	  Support for Apple DART (Device Address Resolution Table) IOMMUs

drivers/iommu/Makefile

@@ -8,6 +8,7 @@ obj-$(CONFIG_IOMMU_DMA) += dma-iommu.o
 obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o
 obj-$(CONFIG_IOMMU_IO_PGTABLE_ARMV7S) += io-pgtable-arm-v7s.o
 obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
+obj-$(CONFIG_IOMMU_IO_PGTABLE_DART) += io-pgtable-dart.o
 obj-$(CONFIG_IOASID) += ioasid.o
 obj-$(CONFIG_IOMMU_IOVA) += iova.o
 obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o

drivers/iommu/io-pgtable-arm.c

@@ -130,9 +130,6 @@
 #define ARM_MALI_LPAE_MEMATTR_IMP_DEF	0x88ULL
 #define ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC 0x8DULL
 
-#define APPLE_DART_PTE_PROT_NO_WRITE (1<<7)
-#define APPLE_DART_PTE_PROT_NO_READ (1<<8)
-
 /* IOPTE accessors */
 #define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d))
 
@@ -406,15 +403,6 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 {
 	arm_lpae_iopte pte;
 
-	if (data->iop.fmt == APPLE_DART) {
-		pte = 0;
-		if (!(prot & IOMMU_WRITE))
-			pte |= APPLE_DART_PTE_PROT_NO_WRITE;
-		if (!(prot & IOMMU_READ))
-			pte |= APPLE_DART_PTE_PROT_NO_READ;
-		return pte;
-	}
-
 	if (data->iop.fmt == ARM_64_LPAE_S1 ||
 	    data->iop.fmt == ARM_32_LPAE_S1) {
 		pte = ARM_LPAE_PTE_nG;
@@ -1107,52 +1095,6 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 	return NULL;
 }
 
-static struct io_pgtable *
-apple_dart_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
-{
-	struct arm_lpae_io_pgtable *data;
-	int i;
-
-	if (cfg->oas > 36)
-		return NULL;
-
-	data = arm_lpae_alloc_pgtable(cfg);
-	if (!data)
-		return NULL;
-
-	/*
-	 * The table format itself always uses two levels, but the total VA
-	 * space is mapped by four separate tables, making the MMIO registers
-	 * an effective "level 1". For simplicity, though, we treat this
-	 * equivalently to LPAE stage 2 concatenation at level 2, with the
-	 * additional TTBRs each just pointing at consecutive pages.
-	 */
-	if (data->start_level < 1)
-		goto out_free_data;
-	if (data->start_level == 1 && data->pgd_bits > 2)
-		goto out_free_data;
-	if (data->start_level > 1)
-		data->pgd_bits = 0;
-	data->start_level = 2;
-	cfg->apple_dart_cfg.n_ttbrs = 1 << data->pgd_bits;
-	data->pgd_bits += data->bits_per_level;
-
-	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), GFP_KERNEL,
-					   cfg);
-	if (!data->pgd)
-		goto out_free_data;
-
-	for (i = 0; i < cfg->apple_dart_cfg.n_ttbrs; ++i)
-		cfg->apple_dart_cfg.ttbr[i] =
-			virt_to_phys(data->pgd + i * ARM_LPAE_GRANULE(data));
-
-	return &data->iop;
-
-out_free_data:
-	kfree(data);
-	return NULL;
-}
-
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {
 	.alloc	= arm_64_lpae_alloc_pgtable_s1,
 	.free	= arm_lpae_free_pgtable,
@@ -1178,11 +1120,6 @@ struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns = {
 	.free	= arm_lpae_free_pgtable,
 };
 
-struct io_pgtable_init_fns io_pgtable_apple_dart_init_fns = {
-	.alloc	= apple_dart_alloc_pgtable,
-	.free	= arm_lpae_free_pgtable,
-};
-
 #ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE_SELFTEST
 
 static struct io_pgtable_cfg *cfg_cookie __initdata;

drivers/iommu/io-pgtable.c

@@ -20,6 +20,8 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = {
 	[ARM_64_LPAE_S1] = &io_pgtable_arm_64_lpae_s1_init_fns,
 	[ARM_64_LPAE_S2] = &io_pgtable_arm_64_lpae_s2_init_fns,
 	[ARM_MALI_LPAE] = &io_pgtable_arm_mali_lpae_init_fns,
+#endif
+#ifdef CONFIG_IOMMU_IO_PGTABLE_DART
 	[APPLE_DART] = &io_pgtable_apple_dart_init_fns,
 #endif
 #ifdef CONFIG_IOMMU_IO_PGTABLE_ARMV7S