[PATCH v5 0/5] iommu: M1 Pro/Max DART support

[PATCH v5 0/5] iommu: M1 Pro/Max DART support

[Janne Grunau]

Hej,

this is the next attempt adding support for the DART found in Apple's
M1 Pro/Max/Ultra. This adds a separate io-pgtable implementation for
DART. As already mentioned in v2 the pte format is not fully compatible
with io-pgtable-arm. Especially the 2nd least significant bit is used
and is not available to tag tables/pages.
io-pgtable-dart.c is copied from io-pgtable-arm.c and support for
unused features is removed. Support for 4k IO pages is left for A7 to
A11 SoCs as there's work underway to run Linux on them.

The incompatibilities between both Apple DART pte seems manageable in
their own io-pgtable implementation. A short list of the known
differences:

 - the physical addresses are shifted left by 4 bits and and have 2 more
   bits inside the PTE entries
 - the read/write protection flags are at a different position
 - the subpage protection feature is now mandatory. For Linux we can
   just configure it to always allow access to the entire page.
 - BIT(1) tags "uncached" mappings (used for the display controller)

There is second type of DART (t8110) present on M1 Pro/Max SoCs which
uses the same PTE format as t6000.

Changes in v5:
- collected Sven's ack
- minor fixes in "iommu/io-pgtable: Move Apple DART support to its own
  file"

Changes in v4:
- split dart and io-pgtable-dart build to allow building dart as module
- add missing "SELECT IOMMU_IO_PGTABLE"
- made map/unmap_pages/iova_to_phys inon-recursive
- replace pgd concatenation with multiple table handling
- simplified config and page size checks
- collected Robin's Ack

Changes in v3:
- move APPLE_DART to its own io-pgtable implementation, copied from
  io-pgtable-arm and simplified

Changes in v2:
- added Rob's Acked-by:
- add APPLE_DART2 io-pgtable format

Janne Grunau (1):
  iommu/io-pgtable: Move Apple DART support to its own file

Sven Peter (4):
  dt-bindings: iommu: dart: add t6000 compatible
  iommu/io-pgtable: Add DART subpage protection support
  iommu/io-pgtable-dart: Add DART PTE support for t6000
  iommu: dart: Support t6000 variant

 .../devicetree/bindings/iommu/apple,dart.yaml |   4 +-
 MAINTAINERS                                   |   1 +
 drivers/iommu/Kconfig                         |  13 +-
 drivers/iommu/Makefile                        |   1 +
 drivers/iommu/apple-dart.c                    |  24 +-
 drivers/iommu/io-pgtable-arm.c                |  63 ---
 drivers/iommu/io-pgtable-dart.c               | 470 ++++++++++++++++++
 drivers/iommu/io-pgtable.c                    |   3 +
 include/linux/io-pgtable.h                    |   1 +
 9 files changed, 512 insertions(+), 68 deletions(-)
 create mode 100644 drivers/iommu/io-pgtable-dart.c

-- 
2.35.1

[PATCH v5 0/5] iommu: M1 Pro/Max DART support

[Janne Grunau]

Hej,

this is the next attempt adding support for the DART found in Apple's
M1 Pro/Max/Ultra. This adds a separate io-pgtable implementation for
DART. As already mentioned in v2 the pte format is not fully compatible
with io-pgtable-arm. Especially the 2nd least significant bit is used
and is not available to tag tables/pages.
io-pgtable-dart.c is copied from io-pgtable-arm.c and support for
unused features is removed. Support for 4k IO pages is left for A7 to
A11 SoCs as there's work underway to run Linux on them.

The incompatibilities between both Apple DART pte seems manageable in
their own io-pgtable implementation. A short list of the known
differences:

 - the physical addresses are shifted left by 4 bits and and have 2 more
   bits inside the PTE entries
 - the read/write protection flags are at a different position
 - the subpage protection feature is now mandatory. For Linux we can
   just configure it to always allow access to the entire page.
 - BIT(1) tags "uncached" mappings (used for the display controller)

There is second type of DART (t8110) present on M1 Pro/Max SoCs which
uses the same PTE format as t6000.

Changes in v5:
- collected Sven's ack
- minor fixes in "iommu/io-pgtable: Move Apple DART support to its own
  file"

Changes in v4:
- split dart and io-pgtable-dart build to allow building dart as module
- add missing "SELECT IOMMU_IO_PGTABLE"
- made map/unmap_pages/iova_to_phys inon-recursive
- replace pgd concatenation with multiple table handling
- simplified config and page size checks
- collected Robin's Ack

Changes in v3:
- move APPLE_DART to its own io-pgtable implementation, copied from
  io-pgtable-arm and simplified

Changes in v2:
- added Rob's Acked-by:
- add APPLE_DART2 io-pgtable format

Janne Grunau (1):
  iommu/io-pgtable: Move Apple DART support to its own file

Sven Peter (4):
  dt-bindings: iommu: dart: add t6000 compatible
  iommu/io-pgtable: Add DART subpage protection support
  iommu/io-pgtable-dart: Add DART PTE support for t6000
  iommu: dart: Support t6000 variant

 .../devicetree/bindings/iommu/apple,dart.yaml |   4 +-
 MAINTAINERS                                   |   1 +
 drivers/iommu/Kconfig                         |  13 +-
 drivers/iommu/Makefile                        |   1 +
 drivers/iommu/apple-dart.c                    |  24 +-
 drivers/iommu/io-pgtable-arm.c                |  63 ---
 drivers/iommu/io-pgtable-dart.c               | 470 ++++++++++++++++++
 drivers/iommu/io-pgtable.c                    |   3 +
 include/linux/io-pgtable.h                    |   1 +
 9 files changed, 512 insertions(+), 68 deletions(-)
 create mode 100644 drivers/iommu/io-pgtable-dart.c

-- 
2.35.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v5 1/5] dt-bindings: iommu: dart: add t6000 compatible

[Janne Grunau]

From: Sven Peter <sven@svenpeter.dev>

The M1 Max/Pro SoCs come with a new DART variant that is incompatible with
the previous one. Add a new compatible for those.

Signed-off-by: Sven Peter <sven@svenpeter.dev>
Acked-by: Rob Herring <robh@kernel.org>

Signed-off-by: Janne Grunau <j@jannau.net>
---

(no changes since v2)

Changes in v2:
- added Rob's Acked-by:

 Documentation/devicetree/bindings/iommu/apple,dart.yaml | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/iommu/apple,dart.yaml b/Documentation/devicetree/bindings/iommu/apple,dart.yaml
index 82ad669feef7..06af2bacbe97 100644
--- a/Documentation/devicetree/bindings/iommu/apple,dart.yaml
+++ b/Documentation/devicetree/bindings/iommu/apple,dart.yaml
@@ -22,7 +22,9 @@ description: |+
 
 properties:
   compatible:
-    const: apple,t8103-dart
+    enum:
+      - apple,t8103-dart
+      - apple,t6000-dart
 
   reg:
     maxItems: 1
-- 
2.35.1

[PATCH v5 1/5] dt-bindings: iommu: dart: add t6000 compatible

[Janne Grunau]

From: Sven Peter <sven@svenpeter.dev>

The M1 Max/Pro SoCs come with a new DART variant that is incompatible with
the previous one. Add a new compatible for those.

Signed-off-by: Sven Peter <sven@svenpeter.dev>
Acked-by: Rob Herring <robh@kernel.org>

Signed-off-by: Janne Grunau <j@jannau.net>
---

(no changes since v2)

Changes in v2:
- added Rob's Acked-by:

 Documentation/devicetree/bindings/iommu/apple,dart.yaml | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/iommu/apple,dart.yaml b/Documentation/devicetree/bindings/iommu/apple,dart.yaml
index 82ad669feef7..06af2bacbe97 100644
--- a/Documentation/devicetree/bindings/iommu/apple,dart.yaml
+++ b/Documentation/devicetree/bindings/iommu/apple,dart.yaml
@@ -22,7 +22,9 @@ description: |+
 
 properties:
   compatible:
-    const: apple,t8103-dart
+    enum:
+      - apple,t8103-dart
+      - apple,t6000-dart
 
   reg:
     maxItems: 1
-- 
2.35.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v5 2/5] iommu/io-pgtable: Move Apple DART support to its own file

[Janne Grunau]

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>

---

Changes in v5:
- collected Sven's ack
- use alloc_pages instead alloc_pages_node
- do not return '0' as NULL pointer, Reported-by: kernel test robot <lkp@intel.com>

Changes in v4:
- split dart and io-pgtable-dart build to allow building dart as module
- add missing "SELECT IOMMU_IO_PGTABLE"
- made map/unmap_pages/iova_to_phys inon-recursive
- replace pgd concatenation with multiple table handling
- simplified config and page size checks
- collected Robin's Ack

Changes in v3:
- move APPLE_DART to its own io-pgtable implementation, copied from
  io-pgtable-arm and simplified

Changes in v2:
- add APPLE_DART2 io-pgtable format

 MAINTAINERS                     |   1 +
 drivers/iommu/Kconfig           |  13 +-
 drivers/iommu/Makefile          |   1 +
 drivers/iommu/io-pgtable-arm.c  |  63 -----
 drivers/iommu/io-pgtable-dart.c | 427 ++++++++++++++++++++++++++++++++
 drivers/iommu/io-pgtable.c      |   2 +
 6 files changed, 443 insertions(+), 64 deletions(-)
 create mode 100644 drivers/iommu/io-pgtable-dart.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 1fc9ead83d2a..028b7e31e589 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1848,6 +1848,7 @@ F:	drivers/clk/clk-apple-nco.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
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index c79a0df090c0..026921c1df53 100644
--- a/drivers/iommu/Kconfig
+++ b/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
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 44475a9b3eea..cc9f381013c3 100644
--- a/drivers/iommu/Makefile
+++ b/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
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 94ff319ae8ac..d7f5e23da643 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/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;
diff --git a/drivers/iommu/io-pgtable-dart.c b/drivers/iommu/io-pgtable-dart.c
new file mode 100644
index 000000000000..312d40528748
--- /dev/null
+++ b/drivers/iommu/io-pgtable-dart.c
@@ -0,0 +1,427 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Apple DART page table allocator.
+ *
+ * Copyright (C) 2022 The Asahi Linux Contributors
+ *
+ * Based on io-pgtable-arm.
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#define pr_fmt(fmt)	"dart io-pgtable: " fmt
+
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/io-pgtable.h>
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <asm/barrier.h>
+
+#define DART1_MAX_ADDR_BITS	36
+
+#define DART_MAX_TABLES		4
+#define DART_LEVELS		2
+
+/* Struct accessors */
+#define io_pgtable_to_data(x)						\
+	container_of((x), struct dart_io_pgtable, iop)
+
+#define io_pgtable_ops_to_data(x)					\
+	io_pgtable_to_data(io_pgtable_ops_to_pgtable(x))
+
+#define DART_GRANULE(d)						\
+	(sizeof(dart_iopte) << (d)->bits_per_level)
+#define DART_PTES_PER_TABLE(d)					\
+	(DART_GRANULE(d) >> ilog2(sizeof(dart_iopte)))
+
+#define APPLE_DART1_PADDR_MASK	GENMASK_ULL(35, 12)
+
+/* Apple DART1 protection bits */
+#define APPLE_DART1_PTE_PROT_NO_READ	BIT(8)
+#define APPLE_DART1_PTE_PROT_NO_WRITE	BIT(7)
+#define APPLE_DART1_PTE_PROT_SP_DIS	BIT(1)
+
+/* marks PTE as valid */
+#define APPLE_DART_PTE_VALID		BIT(0)
+
+/* IOPTE accessors */
+#define iopte_deref(pte, d) __va(iopte_to_paddr(pte, d))
+
+struct dart_io_pgtable {
+	struct io_pgtable	iop;
+
+	int			tbl_bits;
+	int			bits_per_level;
+
+	void			*pgd[DART_MAX_TABLES];
+};
+
+typedef u64 dart_iopte;
+
+
+static dart_iopte paddr_to_iopte(phys_addr_t paddr,
+				     struct dart_io_pgtable *data)
+{
+	return paddr & APPLE_DART1_PADDR_MASK;
+}
+
+static phys_addr_t iopte_to_paddr(dart_iopte pte,
+				  struct dart_io_pgtable *data)
+{
+	return pte & APPLE_DART1_PADDR_MASK;
+}
+
+static void *__dart_alloc_pages(size_t size, gfp_t gfp,
+				    struct io_pgtable_cfg *cfg)
+{
+	struct device *dev = cfg->iommu_dev;
+	int order = get_order(size);
+	struct page *p;
+
+	VM_BUG_ON((gfp & __GFP_HIGHMEM));
+	p = alloc_pages(gfp | __GFP_ZERO, order);
+	if (!p)
+		return NULL;
+
+	return page_address(p);
+}
+
+static int dart_init_pte(struct dart_io_pgtable *data,
+			     unsigned long iova, phys_addr_t paddr,
+			     dart_iopte prot, int num_entries,
+			     dart_iopte *ptep)
+{
+	int i;
+	dart_iopte pte = prot;
+	size_t sz = data->iop.cfg.pgsize_bitmap;
+
+	for (i = 0; i < num_entries; i++)
+		if (ptep[i] & APPLE_DART_PTE_VALID) {
+			/* We require an unmap first */
+			WARN_ON(ptep[i] & APPLE_DART_PTE_VALID);
+			return -EEXIST;
+		}
+
+	pte |= APPLE_DART1_PTE_PROT_SP_DIS;
+	pte |= APPLE_DART_PTE_VALID;
+
+	for (i = 0; i < num_entries; i++)
+		ptep[i] = pte | paddr_to_iopte(paddr + i * sz, data);
+
+	return 0;
+}
+
+static dart_iopte dart_install_table(dart_iopte *table,
+					     dart_iopte *ptep,
+					     dart_iopte curr,
+					     struct dart_io_pgtable *data)
+{
+	dart_iopte old, new;
+
+	new = paddr_to_iopte(__pa(table), data) | APPLE_DART_PTE_VALID;
+
+	/*
+	 * Ensure the table itself is visible before its PTE can be.
+	 * Whilst we could get away with cmpxchg64_release below, this
+	 * doesn't have any ordering semantics when !CONFIG_SMP.
+	 */
+	dma_wmb();
+
+	old = cmpxchg64_relaxed(ptep, curr, new);
+
+	return old;
+}
+
+static int dart_get_table(struct dart_io_pgtable *data, unsigned long iova)
+{
+	return (iova >> (3 * data->bits_per_level + ilog2(sizeof(dart_iopte)))) &
+		((1 << data->tbl_bits) - 1);
+}
+
+static int dart_get_l1_index(struct dart_io_pgtable *data, unsigned long iova)
+{
+
+	return (iova >> (2 * data->bits_per_level + ilog2(sizeof(dart_iopte)))) &
+		 ((1 << data->bits_per_level) - 1);
+}
+
+static int dart_get_l2_index(struct dart_io_pgtable *data, unsigned long iova)
+{
+
+	return (iova >> (data->bits_per_level + ilog2(sizeof(dart_iopte)))) &
+		 ((1 << data->bits_per_level) - 1);
+}
+
+static  dart_iopte *dart_get_l2(struct dart_io_pgtable *data, unsigned long iova)
+{
+	dart_iopte pte, *ptep;
+	int tbl = dart_get_table(data, iova);
+
+	ptep = data->pgd[tbl];
+	if (!ptep)
+		return NULL;
+
+	ptep += dart_get_l1_index(data, iova);
+	pte = READ_ONCE(*ptep);
+
+	/* Valid entry? */
+	if (!pte)
+		return NULL;
+
+	/* Deref to get level 2 table */
+	return iopte_deref(pte, data);
+}
+
+static dart_iopte dart_prot_to_pte(struct dart_io_pgtable *data,
+					   int prot)
+{
+	dart_iopte pte = 0;
+
+	if (!(prot & IOMMU_WRITE))
+		pte |= APPLE_DART1_PTE_PROT_NO_WRITE;
+	if (!(prot & IOMMU_READ))
+		pte |= APPLE_DART1_PTE_PROT_NO_READ;
+
+	return pte;
+}
+
+static int dart_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
+			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			      int iommu_prot, gfp_t gfp, size_t *mapped)
+{
+	struct dart_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	size_t tblsz = DART_GRANULE(data);
+	int ret = 0, tbl, num_entries, max_entries, map_idx_start;
+	dart_iopte pte, *cptep, *ptep;
+	dart_iopte prot;
+
+	if (WARN_ON(pgsize != cfg->pgsize_bitmap))
+		return -EINVAL;
+
+	if (WARN_ON(paddr >> cfg->oas))
+		return -ERANGE;
+
+	/* If no access, then nothing to do */
+	if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
+		return 0;
+
+	tbl = dart_get_table(data, iova);
+
+	ptep = data->pgd[tbl];
+	ptep += dart_get_l1_index(data, iova);
+	pte = READ_ONCE(*ptep);
+
+	/* no L2 table present */
+	if (!pte) {
+		cptep = __dart_alloc_pages(tblsz, gfp, cfg);
+		if (!cptep)
+			return -ENOMEM;
+
+		pte = dart_install_table(cptep, ptep, 0, data);
+		if (pte)
+			free_pages((unsigned long)cptep, get_order(tblsz));
+
+		/* L2 table is present (now) */
+		pte = READ_ONCE(*ptep);
+	}
+
+	ptep = iopte_deref(pte, data);
+
+	/* install a leaf entries into L2 table */
+	prot = dart_prot_to_pte(data, iommu_prot);
+	map_idx_start = dart_get_l2_index(data, iova);
+	max_entries = DART_PTES_PER_TABLE(data) - map_idx_start;
+	num_entries = min_t(int, pgcount, max_entries);
+	ptep += map_idx_start;
+	ret = dart_init_pte(data, iova, paddr, prot, num_entries, ptep);
+	if (!ret && mapped)
+		*mapped += num_entries * pgsize;
+
+	/*
+	 * Synchronise all PTE updates for the new mapping before there's
+	 * a chance for anything to kick off a table walk for the new iova.
+	 */
+	wmb();
+
+	return ret;
+}
+
+static size_t dart_unmap_pages(struct io_pgtable_ops *ops, unsigned long iova,
+				   size_t pgsize, size_t pgcount,
+				   struct iommu_iotlb_gather *gather)
+{
+	struct dart_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	int i = 0, num_entries, max_entries, unmap_idx_start;
+	dart_iopte pte, *ptep;
+
+	if (WARN_ON(pgsize != cfg->pgsize_bitmap || !pgcount))
+		return 0;
+
+	ptep = dart_get_l2(data, iova);
+
+	/* Valid L2 IOPTE pointer? */
+	if (WARN_ON(!ptep))
+		return 0;
+
+	unmap_idx_start = dart_get_l2_index(data, iova);
+	ptep += unmap_idx_start;
+
+	max_entries = DART_PTES_PER_TABLE(data) - unmap_idx_start;
+	num_entries = min_t(int, pgcount, max_entries);
+
+	while (i < num_entries) {
+		pte = READ_ONCE(*ptep);
+		if (WARN_ON(!pte))
+			break;
+
+		/* clear pte */
+		*ptep = 0;
+
+		if (!iommu_iotlb_gather_queued(gather))
+			io_pgtable_tlb_add_page(&data->iop, gather,
+						iova + i * pgsize, pgsize);
+
+		ptep++;
+		i++;
+	}
+
+	return i * pgsize;
+}
+
+static phys_addr_t dart_iova_to_phys(struct io_pgtable_ops *ops,
+					 unsigned long iova)
+{
+	struct dart_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	dart_iopte pte, *ptep;
+
+	ptep = dart_get_l2(data, iova);
+
+	/* Valid L2 IOPTE pointer? */
+	if (!ptep)
+		return 0;
+
+	ptep += dart_get_l2_index(data, iova);
+
+	pte = READ_ONCE(*ptep);
+	/* Found translation */
+	if (pte) {
+		iova &= (data->iop.cfg.pgsize_bitmap - 1);
+		return iopte_to_paddr(pte, data) | iova;
+	}
+
+	/* Ran out of page tables to walk */
+	return 0;
+}
+
+static struct dart_io_pgtable *
+dart_alloc_pgtable(struct io_pgtable_cfg *cfg)
+{
+	struct dart_io_pgtable *data;
+	int tbl_bits, bits_per_level, va_bits, pg_shift;
+
+	pg_shift = __ffs(cfg->pgsize_bitmap);
+	bits_per_level = pg_shift - ilog2(sizeof(dart_iopte));
+
+	va_bits = cfg->ias - pg_shift;
+
+	tbl_bits = max_t(int, 0, va_bits - (bits_per_level * DART_LEVELS));
+	if ((1 << tbl_bits) > DART_MAX_TABLES)
+		return NULL;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return NULL;
+
+	data->tbl_bits = tbl_bits;
+	data->bits_per_level = bits_per_level;
+
+	data->iop.ops = (struct io_pgtable_ops) {
+		.map_pages	= dart_map_pages,
+		.unmap_pages	= dart_unmap_pages,
+		.iova_to_phys	= dart_iova_to_phys,
+	};
+
+	return data;
+}
+
+static struct io_pgtable *
+apple_dart_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	struct dart_io_pgtable *data;
+	int i;
+
+	if (!cfg->coherent_walk)
+		return NULL;
+
+	if (cfg->oas > DART1_MAX_ADDR_BITS)
+		return NULL;
+
+	if (cfg->ias > cfg->oas)
+		return NULL;
+
+	if (!(cfg->pgsize_bitmap == SZ_4K || cfg->pgsize_bitmap == SZ_16K))
+		return NULL;
+
+	data = dart_alloc_pgtable(cfg);
+	if (!data)
+		return NULL;
+
+	cfg->apple_dart_cfg.n_ttbrs = 1 << data->tbl_bits;
+
+	for (i = 0; i < cfg->apple_dart_cfg.n_ttbrs; ++i) {
+		data->pgd[i] = __dart_alloc_pages(DART_GRANULE(data), GFP_KERNEL,
+					   cfg);
+		if (!data->pgd[i])
+			goto out_free_data;
+		cfg->apple_dart_cfg.ttbr[i] = virt_to_phys(data->pgd[i]);
+	}
+
+	return &data->iop;
+
+out_free_data:
+	while (--i >= 0)
+		free_pages((unsigned long)data->pgd[i],
+			   get_order(DART_GRANULE(data)));
+	kfree(data);
+	return NULL;
+}
+
+static void apple_dart_free_pgtable(struct io_pgtable *iop)
+{
+	struct dart_io_pgtable *data = io_pgtable_to_data(iop);
+	dart_iopte *ptep, *end;
+	int i;
+
+	for (i = 0; i < (1 << data->tbl_bits) && data->pgd[i]; ++i) {
+		ptep = data->pgd[i];
+		end = (void *)ptep + DART_GRANULE(data);
+
+		while (ptep != end) {
+			dart_iopte pte = *ptep++;
+
+			if (pte) {
+				unsigned long page =
+					(unsigned long)iopte_deref(pte, data);
+
+				free_pages(page, get_order(DART_GRANULE(data)));
+			}
+		}
+		free_pages((unsigned long)data->pgd[i],
+			   get_order(DART_GRANULE(data)));
+	}
+
+	kfree(data);
+}
+
+struct io_pgtable_init_fns io_pgtable_apple_dart_init_fns = {
+	.alloc	= apple_dart_alloc_pgtable,
+	.free	= apple_dart_free_pgtable,
+};
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index f4bfcef98297..16205ea9272c 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/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
-- 
2.35.1

[PATCH v5 2/5] iommu/io-pgtable: Move Apple DART support to its own file

[Janne Grunau]

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>

---

Changes in v5:
- collected Sven's ack
- use alloc_pages instead alloc_pages_node
- do not return '0' as NULL pointer, Reported-by: kernel test robot <lkp@intel.com>

Changes in v4:
- split dart and io-pgtable-dart build to allow building dart as module
- add missing "SELECT IOMMU_IO_PGTABLE"
- made map/unmap_pages/iova_to_phys inon-recursive
- replace pgd concatenation with multiple table handling
- simplified config and page size checks
- collected Robin's Ack

Changes in v3:
- move APPLE_DART to its own io-pgtable implementation, copied from
  io-pgtable-arm and simplified

Changes in v2:
- add APPLE_DART2 io-pgtable format

 MAINTAINERS                     |   1 +
 drivers/iommu/Kconfig           |  13 +-
 drivers/iommu/Makefile          |   1 +
 drivers/iommu/io-pgtable-arm.c  |  63 -----
 drivers/iommu/io-pgtable-dart.c | 427 ++++++++++++++++++++++++++++++++
 drivers/iommu/io-pgtable.c      |   2 +
 6 files changed, 443 insertions(+), 64 deletions(-)
 create mode 100644 drivers/iommu/io-pgtable-dart.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 1fc9ead83d2a..028b7e31e589 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1848,6 +1848,7 @@ F:	drivers/clk/clk-apple-nco.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
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index c79a0df090c0..026921c1df53 100644
--- a/drivers/iommu/Kconfig
+++ b/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
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 44475a9b3eea..cc9f381013c3 100644
--- a/drivers/iommu/Makefile
+++ b/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
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 94ff319ae8ac..d7f5e23da643 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/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;
diff --git a/drivers/iommu/io-pgtable-dart.c b/drivers/iommu/io-pgtable-dart.c
new file mode 100644
index 000000000000..312d40528748
--- /dev/null
+++ b/drivers/iommu/io-pgtable-dart.c
@@ -0,0 +1,427 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Apple DART page table allocator.
+ *
+ * Copyright (C) 2022 The Asahi Linux Contributors
+ *
+ * Based on io-pgtable-arm.
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#define pr_fmt(fmt)	"dart io-pgtable: " fmt
+
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/io-pgtable.h>
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <asm/barrier.h>
+
+#define DART1_MAX_ADDR_BITS	36
+
+#define DART_MAX_TABLES		4
+#define DART_LEVELS		2
+
+/* Struct accessors */
+#define io_pgtable_to_data(x)						\
+	container_of((x), struct dart_io_pgtable, iop)
+
+#define io_pgtable_ops_to_data(x)					\
+	io_pgtable_to_data(io_pgtable_ops_to_pgtable(x))
+
+#define DART_GRANULE(d)						\
+	(sizeof(dart_iopte) << (d)->bits_per_level)
+#define DART_PTES_PER_TABLE(d)					\
+	(DART_GRANULE(d) >> ilog2(sizeof(dart_iopte)))
+
+#define APPLE_DART1_PADDR_MASK	GENMASK_ULL(35, 12)
+
+/* Apple DART1 protection bits */
+#define APPLE_DART1_PTE_PROT_NO_READ	BIT(8)
+#define APPLE_DART1_PTE_PROT_NO_WRITE	BIT(7)
+#define APPLE_DART1_PTE_PROT_SP_DIS	BIT(1)
+
+/* marks PTE as valid */
+#define APPLE_DART_PTE_VALID		BIT(0)
+
+/* IOPTE accessors */
+#define iopte_deref(pte, d) __va(iopte_to_paddr(pte, d))
+
+struct dart_io_pgtable {
+	struct io_pgtable	iop;
+
+	int			tbl_bits;
+	int			bits_per_level;
+
+	void			*pgd[DART_MAX_TABLES];
+};
+
+typedef u64 dart_iopte;
+
+
+static dart_iopte paddr_to_iopte(phys_addr_t paddr,
+				     struct dart_io_pgtable *data)
+{
+	return paddr & APPLE_DART1_PADDR_MASK;
+}
+
+static phys_addr_t iopte_to_paddr(dart_iopte pte,
+				  struct dart_io_pgtable *data)
+{
+	return pte & APPLE_DART1_PADDR_MASK;
+}
+
+static void *__dart_alloc_pages(size_t size, gfp_t gfp,
+				    struct io_pgtable_cfg *cfg)
+{
+	struct device *dev = cfg->iommu_dev;
+	int order = get_order(size);
+	struct page *p;
+
+	VM_BUG_ON((gfp & __GFP_HIGHMEM));
+	p = alloc_pages(gfp | __GFP_ZERO, order);
+	if (!p)
+		return NULL;
+
+	return page_address(p);
+}
+
+static int dart_init_pte(struct dart_io_pgtable *data,
+			     unsigned long iova, phys_addr_t paddr,
+			     dart_iopte prot, int num_entries,
+			     dart_iopte *ptep)
+{
+	int i;
+	dart_iopte pte = prot;
+	size_t sz = data->iop.cfg.pgsize_bitmap;
+
+	for (i = 0; i < num_entries; i++)
+		if (ptep[i] & APPLE_DART_PTE_VALID) {
+			/* We require an unmap first */
+			WARN_ON(ptep[i] & APPLE_DART_PTE_VALID);
+			return -EEXIST;
+		}
+
+	pte |= APPLE_DART1_PTE_PROT_SP_DIS;
+	pte |= APPLE_DART_PTE_VALID;
+
+	for (i = 0; i < num_entries; i++)
+		ptep[i] = pte | paddr_to_iopte(paddr + i * sz, data);
+
+	return 0;
+}
+
+static dart_iopte dart_install_table(dart_iopte *table,
+					     dart_iopte *ptep,
+					     dart_iopte curr,
+					     struct dart_io_pgtable *data)
+{
+	dart_iopte old, new;
+
+	new = paddr_to_iopte(__pa(table), data) | APPLE_DART_PTE_VALID;
+
+	/*
+	 * Ensure the table itself is visible before its PTE can be.
+	 * Whilst we could get away with cmpxchg64_release below, this
+	 * doesn't have any ordering semantics when !CONFIG_SMP.
+	 */
+	dma_wmb();
+
+	old = cmpxchg64_relaxed(ptep, curr, new);
+
+	return old;
+}
+
+static int dart_get_table(struct dart_io_pgtable *data, unsigned long iova)
+{
+	return (iova >> (3 * data->bits_per_level + ilog2(sizeof(dart_iopte)))) &
+		((1 << data->tbl_bits) - 1);
+}
+
+static int dart_get_l1_index(struct dart_io_pgtable *data, unsigned long iova)
+{
+
+	return (iova >> (2 * data->bits_per_level + ilog2(sizeof(dart_iopte)))) &
+		 ((1 << data->bits_per_level) - 1);
+}
+
+static int dart_get_l2_index(struct dart_io_pgtable *data, unsigned long iova)
+{
+
+	return (iova >> (data->bits_per_level + ilog2(sizeof(dart_iopte)))) &
+		 ((1 << data->bits_per_level) - 1);
+}
+
+static  dart_iopte *dart_get_l2(struct dart_io_pgtable *data, unsigned long iova)
+{
+	dart_iopte pte, *ptep;
+	int tbl = dart_get_table(data, iova);
+
+	ptep = data->pgd[tbl];
+	if (!ptep)
+		return NULL;
+
+	ptep += dart_get_l1_index(data, iova);
+	pte = READ_ONCE(*ptep);
+
+	/* Valid entry? */
+	if (!pte)
+		return NULL;
+
+	/* Deref to get level 2 table */
+	return iopte_deref(pte, data);
+}
+
+static dart_iopte dart_prot_to_pte(struct dart_io_pgtable *data,
+					   int prot)
+{
+	dart_iopte pte = 0;
+
+	if (!(prot & IOMMU_WRITE))
+		pte |= APPLE_DART1_PTE_PROT_NO_WRITE;
+	if (!(prot & IOMMU_READ))
+		pte |= APPLE_DART1_PTE_PROT_NO_READ;
+
+	return pte;
+}
+
+static int dart_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
+			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			      int iommu_prot, gfp_t gfp, size_t *mapped)
+{
+	struct dart_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	size_t tblsz = DART_GRANULE(data);
+	int ret = 0, tbl, num_entries, max_entries, map_idx_start;
+	dart_iopte pte, *cptep, *ptep;
+	dart_iopte prot;
+
+	if (WARN_ON(pgsize != cfg->pgsize_bitmap))
+		return -EINVAL;
+
+	if (WARN_ON(paddr >> cfg->oas))
+		return -ERANGE;
+
+	/* If no access, then nothing to do */
+	if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
+		return 0;
+
+	tbl = dart_get_table(data, iova);
+
+	ptep = data->pgd[tbl];
+	ptep += dart_get_l1_index(data, iova);
+	pte = READ_ONCE(*ptep);
+
+	/* no L2 table present */
+	if (!pte) {
+		cptep = __dart_alloc_pages(tblsz, gfp, cfg);
+		if (!cptep)
+			return -ENOMEM;
+
+		pte = dart_install_table(cptep, ptep, 0, data);
+		if (pte)
+			free_pages((unsigned long)cptep, get_order(tblsz));
+
+		/* L2 table is present (now) */
+		pte = READ_ONCE(*ptep);
+	}
+
+	ptep = iopte_deref(pte, data);
+
+	/* install a leaf entries into L2 table */
+	prot = dart_prot_to_pte(data, iommu_prot);
+	map_idx_start = dart_get_l2_index(data, iova);
+	max_entries = DART_PTES_PER_TABLE(data) - map_idx_start;
+	num_entries = min_t(int, pgcount, max_entries);
+	ptep += map_idx_start;
+	ret = dart_init_pte(data, iova, paddr, prot, num_entries, ptep);
+	if (!ret && mapped)
+		*mapped += num_entries * pgsize;
+
+	/*
+	 * Synchronise all PTE updates for the new mapping before there's
+	 * a chance for anything to kick off a table walk for the new iova.
+	 */
+	wmb();
+
+	return ret;
+}
+
+static size_t dart_unmap_pages(struct io_pgtable_ops *ops, unsigned long iova,
+				   size_t pgsize, size_t pgcount,
+				   struct iommu_iotlb_gather *gather)
+{
+	struct dart_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	int i = 0, num_entries, max_entries, unmap_idx_start;
+	dart_iopte pte, *ptep;
+
+	if (WARN_ON(pgsize != cfg->pgsize_bitmap || !pgcount))
+		return 0;
+
+	ptep = dart_get_l2(data, iova);
+
+	/* Valid L2 IOPTE pointer? */
+	if (WARN_ON(!ptep))
+		return 0;
+
+	unmap_idx_start = dart_get_l2_index(data, iova);
+	ptep += unmap_idx_start;
+
+	max_entries = DART_PTES_PER_TABLE(data) - unmap_idx_start;
+	num_entries = min_t(int, pgcount, max_entries);
+
+	while (i < num_entries) {
+		pte = READ_ONCE(*ptep);
+		if (WARN_ON(!pte))
+			break;
+
+		/* clear pte */
+		*ptep = 0;
+
+		if (!iommu_iotlb_gather_queued(gather))
+			io_pgtable_tlb_add_page(&data->iop, gather,
+						iova + i * pgsize, pgsize);
+
+		ptep++;
+		i++;
+	}
+
+	return i * pgsize;
+}
+
+static phys_addr_t dart_iova_to_phys(struct io_pgtable_ops *ops,
+					 unsigned long iova)
+{
+	struct dart_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	dart_iopte pte, *ptep;
+
+	ptep = dart_get_l2(data, iova);
+
+	/* Valid L2 IOPTE pointer? */
+	if (!ptep)
+		return 0;
+
+	ptep += dart_get_l2_index(data, iova);
+
+	pte = READ_ONCE(*ptep);
+	/* Found translation */
+	if (pte) {
+		iova &= (data->iop.cfg.pgsize_bitmap - 1);
+		return iopte_to_paddr(pte, data) | iova;
+	}
+
+	/* Ran out of page tables to walk */
+	return 0;
+}
+
+static struct dart_io_pgtable *
+dart_alloc_pgtable(struct io_pgtable_cfg *cfg)
+{
+	struct dart_io_pgtable *data;
+	int tbl_bits, bits_per_level, va_bits, pg_shift;
+
+	pg_shift = __ffs(cfg->pgsize_bitmap);
+	bits_per_level = pg_shift - ilog2(sizeof(dart_iopte));
+
+	va_bits = cfg->ias - pg_shift;
+
+	tbl_bits = max_t(int, 0, va_bits - (bits_per_level * DART_LEVELS));
+	if ((1 << tbl_bits) > DART_MAX_TABLES)
+		return NULL;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return NULL;
+
+	data->tbl_bits = tbl_bits;
+	data->bits_per_level = bits_per_level;
+
+	data->iop.ops = (struct io_pgtable_ops) {
+		.map_pages	= dart_map_pages,
+		.unmap_pages	= dart_unmap_pages,
+		.iova_to_phys	= dart_iova_to_phys,
+	};
+
+	return data;
+}
+
+static struct io_pgtable *
+apple_dart_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	struct dart_io_pgtable *data;
+	int i;
+
+	if (!cfg->coherent_walk)
+		return NULL;
+
+	if (cfg->oas > DART1_MAX_ADDR_BITS)
+		return NULL;
+
+	if (cfg->ias > cfg->oas)
+		return NULL;
+
+	if (!(cfg->pgsize_bitmap == SZ_4K || cfg->pgsize_bitmap == SZ_16K))
+		return NULL;
+
+	data = dart_alloc_pgtable(cfg);
+	if (!data)
+		return NULL;
+
+	cfg->apple_dart_cfg.n_ttbrs = 1 << data->tbl_bits;
+
+	for (i = 0; i < cfg->apple_dart_cfg.n_ttbrs; ++i) {
+		data->pgd[i] = __dart_alloc_pages(DART_GRANULE(data), GFP_KERNEL,
+					   cfg);
+		if (!data->pgd[i])
+			goto out_free_data;
+		cfg->apple_dart_cfg.ttbr[i] = virt_to_phys(data->pgd[i]);
+	}
+
+	return &data->iop;
+
+out_free_data:
+	while (--i >= 0)
+		free_pages((unsigned long)data->pgd[i],
+			   get_order(DART_GRANULE(data)));
+	kfree(data);
+	return NULL;
+}
+
+static void apple_dart_free_pgtable(struct io_pgtable *iop)
+{
+	struct dart_io_pgtable *data = io_pgtable_to_data(iop);
+	dart_iopte *ptep, *end;
+	int i;
+
+	for (i = 0; i < (1 << data->tbl_bits) && data->pgd[i]; ++i) {
+		ptep = data->pgd[i];
+		end = (void *)ptep + DART_GRANULE(data);
+
+		while (ptep != end) {
+			dart_iopte pte = *ptep++;
+
+			if (pte) {
+				unsigned long page =
+					(unsigned long)iopte_deref(pte, data);
+
+				free_pages(page, get_order(DART_GRANULE(data)));
+			}
+		}
+		free_pages((unsigned long)data->pgd[i],
+			   get_order(DART_GRANULE(data)));
+	}
+
+	kfree(data);
+}
+
+struct io_pgtable_init_fns io_pgtable_apple_dart_init_fns = {
+	.alloc	= apple_dart_alloc_pgtable,
+	.free	= apple_dart_free_pgtable,
+};
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index f4bfcef98297..16205ea9272c 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/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
-- 
2.35.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v5 3/5] iommu/io-pgtable: Add DART subpage protection support

[Janne Grunau]

From: Sven Peter <sven@svenpeter.dev>

DART allows to only expose a subpage to the device. While this is an
optional feature on the M1 DARTs the new ones present on the Pro/Max
models require this field in every PTE.

Signed-off-by: Sven Peter <sven@svenpeter.dev>
Signed-off-by: Janne Grunau <j@jannau.net>

---

(no changes since v3)

Changes in v3:
- apply change to io-pgtable-dart.c

 drivers/iommu/io-pgtable-dart.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/iommu/io-pgtable-dart.c b/drivers/iommu/io-pgtable-dart.c
index 312d40528748..665a52e5c9b0 100644
--- a/drivers/iommu/io-pgtable-dart.c
+++ b/drivers/iommu/io-pgtable-dart.c
@@ -14,6 +14,7 @@
 #define pr_fmt(fmt)	"dart io-pgtable: " fmt
 
 #include <linux/atomic.h>
+#include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/io-pgtable.h>
 #include <linux/kernel.h>
@@ -40,6 +41,9 @@
 #define DART_PTES_PER_TABLE(d)					\
 	(DART_GRANULE(d) >> ilog2(sizeof(dart_iopte)))
 
+#define APPLE_DART_PTE_SUBPAGE_START   GENMASK_ULL(63, 52)
+#define APPLE_DART_PTE_SUBPAGE_END     GENMASK_ULL(51, 40)
+
 #define APPLE_DART1_PADDR_MASK	GENMASK_ULL(35, 12)
 
 /* Apple DART1 protection bits */
@@ -108,6 +112,10 @@ static int dart_init_pte(struct dart_io_pgtable *data,
 			return -EEXIST;
 		}
 
+	/* subpage protection: always allow access to the entire page */
+	pte |= FIELD_PREP(APPLE_DART_PTE_SUBPAGE_START, 0);
+	pte |= FIELD_PREP(APPLE_DART_PTE_SUBPAGE_END, 0xfff);
+
 	pte |= APPLE_DART1_PTE_PROT_SP_DIS;
 	pte |= APPLE_DART_PTE_VALID;
 
-- 
2.35.1

[PATCH v5 3/5] iommu/io-pgtable: Add DART subpage protection support

[Janne Grunau]

From: Sven Peter <sven@svenpeter.dev>

DART allows to only expose a subpage to the device. While this is an
optional feature on the M1 DARTs the new ones present on the Pro/Max
models require this field in every PTE.

Signed-off-by: Sven Peter <sven@svenpeter.dev>
Signed-off-by: Janne Grunau <j@jannau.net>

---

(no changes since v3)

Changes in v3:
- apply change to io-pgtable-dart.c

 drivers/iommu/io-pgtable-dart.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/iommu/io-pgtable-dart.c b/drivers/iommu/io-pgtable-dart.c
index 312d40528748..665a52e5c9b0 100644
--- a/drivers/iommu/io-pgtable-dart.c
+++ b/drivers/iommu/io-pgtable-dart.c
@@ -14,6 +14,7 @@
 #define pr_fmt(fmt)	"dart io-pgtable: " fmt
 
 #include <linux/atomic.h>
+#include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/io-pgtable.h>
 #include <linux/kernel.h>
@@ -40,6 +41,9 @@
 #define DART_PTES_PER_TABLE(d)					\
 	(DART_GRANULE(d) >> ilog2(sizeof(dart_iopte)))
 
+#define APPLE_DART_PTE_SUBPAGE_START   GENMASK_ULL(63, 52)
+#define APPLE_DART_PTE_SUBPAGE_END     GENMASK_ULL(51, 40)
+
 #define APPLE_DART1_PADDR_MASK	GENMASK_ULL(35, 12)
 
 /* Apple DART1 protection bits */
@@ -108,6 +112,10 @@ static int dart_init_pte(struct dart_io_pgtable *data,
 			return -EEXIST;
 		}
 
+	/* subpage protection: always allow access to the entire page */
+	pte |= FIELD_PREP(APPLE_DART_PTE_SUBPAGE_START, 0);
+	pte |= FIELD_PREP(APPLE_DART_PTE_SUBPAGE_END, 0xfff);
+
 	pte |= APPLE_DART1_PTE_PROT_SP_DIS;
 	pte |= APPLE_DART_PTE_VALID;
 
-- 
2.35.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v5 4/5] iommu/io-pgtable-dart: Add DART PTE support for t6000

[Janne Grunau]

From: Sven Peter <sven@svenpeter.dev>

The DARTs present in the M1 Pro/Max/Ultra SoC use a diffent PTE format.
They support a 42bit physical address space by shifting the paddr and
extending its mask inside the PTE.
They also come with mandatory sub-page protection now which we just
configure to always allow access to the entire page. This feature is
already present but optional on the previous DARTs which allows to
unconditionally configure it.

Signed-off-by: Sven Peter <sven@svenpeter.dev>
Co-developed-by: Janne Grunau <j@jannau.net>
Signed-off-by: Janne Grunau <j@jannau.net>

---

(no changes since v3)

Changes in v3:
- apply change to io-pgtable-dart.c
- handle pte <> paddr conversion based on the pte format instead of
  the output address size

Changes in v2:
- add APPLE_DART2 PTE format

 drivers/iommu/io-pgtable-dart.c | 49 ++++++++++++++++++++++++++++-----
 drivers/iommu/io-pgtable.c      |  1 +
 include/linux/io-pgtable.h      |  1 +
 3 files changed, 44 insertions(+), 7 deletions(-)

diff --git a/drivers/iommu/io-pgtable-dart.c b/drivers/iommu/io-pgtable-dart.c
index 665a52e5c9b0..cc66593318e6 100644
--- a/drivers/iommu/io-pgtable-dart.c
+++ b/drivers/iommu/io-pgtable-dart.c
@@ -45,12 +45,19 @@
 #define APPLE_DART_PTE_SUBPAGE_END     GENMASK_ULL(51, 40)
 
 #define APPLE_DART1_PADDR_MASK	GENMASK_ULL(35, 12)
+#define APPLE_DART2_PADDR_MASK	GENMASK_ULL(37, 10)
+#define APPLE_DART2_PADDR_SHIFT	(4)
 
 /* Apple DART1 protection bits */
 #define APPLE_DART1_PTE_PROT_NO_READ	BIT(8)
 #define APPLE_DART1_PTE_PROT_NO_WRITE	BIT(7)
 #define APPLE_DART1_PTE_PROT_SP_DIS	BIT(1)
 
+/* Apple DART2 protection bits */
+#define APPLE_DART2_PTE_PROT_NO_READ	BIT(3)
+#define APPLE_DART2_PTE_PROT_NO_WRITE	BIT(2)
+#define APPLE_DART2_PTE_PROT_NO_CACHE	BIT(1)
+
 /* marks PTE as valid */
 #define APPLE_DART_PTE_VALID		BIT(0)
 
@@ -72,13 +79,31 @@ typedef u64 dart_iopte;
 static dart_iopte paddr_to_iopte(phys_addr_t paddr,
 				     struct dart_io_pgtable *data)
 {
-	return paddr & APPLE_DART1_PADDR_MASK;
+	dart_iopte pte;
+
+	if (data->iop.fmt == APPLE_DART)
+		return paddr & APPLE_DART1_PADDR_MASK;
+
+	/* format is APPLE_DART2 */
+	pte = paddr >> APPLE_DART2_PADDR_SHIFT;
+	pte &= APPLE_DART2_PADDR_MASK;
+
+	return pte;
 }
 
 static phys_addr_t iopte_to_paddr(dart_iopte pte,
 				  struct dart_io_pgtable *data)
 {
-	return pte & APPLE_DART1_PADDR_MASK;
+	u64 paddr;
+
+	if (data->iop.fmt == APPLE_DART)
+		return pte & APPLE_DART1_PADDR_MASK;
+
+	/* format is APPLE_DART2 */
+	paddr = pte & APPLE_DART2_PADDR_MASK;
+	paddr <<= APPLE_DART2_PADDR_SHIFT;
+
+	return paddr;
 }
 
 static void *__dart_alloc_pages(size_t size, gfp_t gfp,
@@ -191,10 +216,20 @@ static dart_iopte dart_prot_to_pte(struct dart_io_pgtable *data,
 {
 	dart_iopte pte = 0;
 
-	if (!(prot & IOMMU_WRITE))
-		pte |= APPLE_DART1_PTE_PROT_NO_WRITE;
-	if (!(prot & IOMMU_READ))
-		pte |= APPLE_DART1_PTE_PROT_NO_READ;
+	if (data->iop.fmt == APPLE_DART) {
+		if (!(prot & IOMMU_WRITE))
+			pte |= APPLE_DART1_PTE_PROT_NO_WRITE;
+		if (!(prot & IOMMU_READ))
+			pte |= APPLE_DART1_PTE_PROT_NO_READ;
+	}
+	if (data->iop.fmt == APPLE_DART2) {
+		if (!(prot & IOMMU_WRITE))
+			pte |= APPLE_DART2_PTE_PROT_NO_WRITE;
+		if (!(prot & IOMMU_READ))
+			pte |= APPLE_DART2_PTE_PROT_NO_READ;
+		if (!(prot & IOMMU_CACHE))
+			pte |= APPLE_DART2_PTE_PROT_NO_CACHE;
+	}
 
 	return pte;
 }
@@ -369,7 +404,7 @@ apple_dart_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 	if (!cfg->coherent_walk)
 		return NULL;
 
-	if (cfg->oas > DART1_MAX_ADDR_BITS)
+	if (cfg->oas != 36 && cfg->oas != 42)
 		return NULL;
 
 	if (cfg->ias > cfg->oas)
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index 16205ea9272c..49f46e1eabf7 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/drivers/iommu/io-pgtable.c
@@ -23,6 +23,7 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = {
 #endif
 #ifdef CONFIG_IOMMU_IO_PGTABLE_DART
 	[APPLE_DART] = &io_pgtable_apple_dart_init_fns,
+	[APPLE_DART2] = &io_pgtable_apple_dart_init_fns,
 #endif
 #ifdef CONFIG_IOMMU_IO_PGTABLE_ARMV7S
 	[ARM_V7S] = &io_pgtable_arm_v7s_init_fns,
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 86af6f0a00a2..76b98511cbc8 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -17,6 +17,7 @@ enum io_pgtable_fmt {
 	ARM_MALI_LPAE,
 	AMD_IOMMU_V1,
 	APPLE_DART,
+	APPLE_DART2,
 	IO_PGTABLE_NUM_FMTS,
 };
 
-- 
2.35.1

[PATCH v5 4/5] iommu/io-pgtable-dart: Add DART PTE support for t6000

[Janne Grunau]

From: Sven Peter <sven@svenpeter.dev>

The DARTs present in the M1 Pro/Max/Ultra SoC use a diffent PTE format.
They support a 42bit physical address space by shifting the paddr and
extending its mask inside the PTE.
They also come with mandatory sub-page protection now which we just
configure to always allow access to the entire page. This feature is
already present but optional on the previous DARTs which allows to
unconditionally configure it.

Signed-off-by: Sven Peter <sven@svenpeter.dev>
Co-developed-by: Janne Grunau <j@jannau.net>
Signed-off-by: Janne Grunau <j@jannau.net>

---

(no changes since v3)

Changes in v3:
- apply change to io-pgtable-dart.c
- handle pte <> paddr conversion based on the pte format instead of
  the output address size

Changes in v2:
- add APPLE_DART2 PTE format

 drivers/iommu/io-pgtable-dart.c | 49 ++++++++++++++++++++++++++++-----
 drivers/iommu/io-pgtable.c      |  1 +
 include/linux/io-pgtable.h      |  1 +
 3 files changed, 44 insertions(+), 7 deletions(-)

diff --git a/drivers/iommu/io-pgtable-dart.c b/drivers/iommu/io-pgtable-dart.c
index 665a52e5c9b0..cc66593318e6 100644
--- a/drivers/iommu/io-pgtable-dart.c
+++ b/drivers/iommu/io-pgtable-dart.c
@@ -45,12 +45,19 @@
 #define APPLE_DART_PTE_SUBPAGE_END     GENMASK_ULL(51, 40)
 
 #define APPLE_DART1_PADDR_MASK	GENMASK_ULL(35, 12)
+#define APPLE_DART2_PADDR_MASK	GENMASK_ULL(37, 10)
+#define APPLE_DART2_PADDR_SHIFT	(4)
 
 /* Apple DART1 protection bits */
 #define APPLE_DART1_PTE_PROT_NO_READ	BIT(8)
 #define APPLE_DART1_PTE_PROT_NO_WRITE	BIT(7)
 #define APPLE_DART1_PTE_PROT_SP_DIS	BIT(1)
 
+/* Apple DART2 protection bits */
+#define APPLE_DART2_PTE_PROT_NO_READ	BIT(3)
+#define APPLE_DART2_PTE_PROT_NO_WRITE	BIT(2)
+#define APPLE_DART2_PTE_PROT_NO_CACHE	BIT(1)
+
 /* marks PTE as valid */
 #define APPLE_DART_PTE_VALID		BIT(0)
 
@@ -72,13 +79,31 @@ typedef u64 dart_iopte;
 static dart_iopte paddr_to_iopte(phys_addr_t paddr,
 				     struct dart_io_pgtable *data)
 {
-	return paddr & APPLE_DART1_PADDR_MASK;
+	dart_iopte pte;
+
+	if (data->iop.fmt == APPLE_DART)
+		return paddr & APPLE_DART1_PADDR_MASK;
+
+	/* format is APPLE_DART2 */
+	pte = paddr >> APPLE_DART2_PADDR_SHIFT;
+	pte &= APPLE_DART2_PADDR_MASK;
+
+	return pte;
 }
 
 static phys_addr_t iopte_to_paddr(dart_iopte pte,
 				  struct dart_io_pgtable *data)
 {
-	return pte & APPLE_DART1_PADDR_MASK;
+	u64 paddr;
+
+	if (data->iop.fmt == APPLE_DART)
+		return pte & APPLE_DART1_PADDR_MASK;
+
+	/* format is APPLE_DART2 */
+	paddr = pte & APPLE_DART2_PADDR_MASK;
+	paddr <<= APPLE_DART2_PADDR_SHIFT;
+
+	return paddr;
 }
 
 static void *__dart_alloc_pages(size_t size, gfp_t gfp,
@@ -191,10 +216,20 @@ static dart_iopte dart_prot_to_pte(struct dart_io_pgtable *data,
 {
 	dart_iopte pte = 0;
 
-	if (!(prot & IOMMU_WRITE))
-		pte |= APPLE_DART1_PTE_PROT_NO_WRITE;
-	if (!(prot & IOMMU_READ))
-		pte |= APPLE_DART1_PTE_PROT_NO_READ;
+	if (data->iop.fmt == APPLE_DART) {
+		if (!(prot & IOMMU_WRITE))
+			pte |= APPLE_DART1_PTE_PROT_NO_WRITE;
+		if (!(prot & IOMMU_READ))
+			pte |= APPLE_DART1_PTE_PROT_NO_READ;
+	}
+	if (data->iop.fmt == APPLE_DART2) {
+		if (!(prot & IOMMU_WRITE))
+			pte |= APPLE_DART2_PTE_PROT_NO_WRITE;
+		if (!(prot & IOMMU_READ))
+			pte |= APPLE_DART2_PTE_PROT_NO_READ;
+		if (!(prot & IOMMU_CACHE))
+			pte |= APPLE_DART2_PTE_PROT_NO_CACHE;
+	}
 
 	return pte;
 }
@@ -369,7 +404,7 @@ apple_dart_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 	if (!cfg->coherent_walk)
 		return NULL;
 
-	if (cfg->oas > DART1_MAX_ADDR_BITS)
+	if (cfg->oas != 36 && cfg->oas != 42)
 		return NULL;
 
 	if (cfg->ias > cfg->oas)
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index 16205ea9272c..49f46e1eabf7 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/drivers/iommu/io-pgtable.c
@@ -23,6 +23,7 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = {
 #endif
 #ifdef CONFIG_IOMMU_IO_PGTABLE_DART
 	[APPLE_DART] = &io_pgtable_apple_dart_init_fns,
+	[APPLE_DART2] = &io_pgtable_apple_dart_init_fns,
 #endif
 #ifdef CONFIG_IOMMU_IO_PGTABLE_ARMV7S
 	[ARM_V7S] = &io_pgtable_arm_v7s_init_fns,
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 86af6f0a00a2..76b98511cbc8 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -17,6 +17,7 @@ enum io_pgtable_fmt {
 	ARM_MALI_LPAE,
 	AMD_IOMMU_V1,
 	APPLE_DART,
+	APPLE_DART2,
 	IO_PGTABLE_NUM_FMTS,
 };
 
-- 
2.35.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v5 5/5] iommu: dart: Support t6000 variant

[Janne Grunau]

From: Sven Peter <sven@svenpeter.dev>

The M1 Pro/Max/Ultra SoCs come with a new variant of DART which
supports a larger physical address space with a different PTE format.
Pass through the correct paddr address space size and the PTE format
to the io-pgtable code which will take care of the rest.

Signed-off-by: Sven Peter <sven@svenpeter.dev>
Co-developed-by: Janne Grunau <j@jannau.net>
Signed-off-by: Janne Grunau <j@jannau.net>

---

(no changes since v3)

Changes in v3:
- apply change to io-pgtable-dart.c

Changes in v2:
- use APPLE_DART2 PTE format for dart-t6000

 drivers/iommu/apple-dart.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index 8af0242a90d9..e5793c0d08b4 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -81,10 +81,16 @@
 #define DART_TTBR_VALID BIT(31)
 #define DART_TTBR_SHIFT 12
 
+struct apple_dart_hw {
+	u32 oas;
+	enum io_pgtable_fmt fmt;
+};
+
 /*
  * Private structure associated with each DART device.
  *
  * @dev: device struct
+ * @hw: SoC-specific hardware data
  * @regs: mapped MMIO region
  * @irq: interrupt number, can be shared with other DARTs
  * @clks: clocks associated with this DART
@@ -98,6 +104,7 @@
  */
 struct apple_dart {
 	struct device *dev;
+	const struct apple_dart_hw *hw;
 
 	void __iomem *regs;
 
@@ -421,13 +428,13 @@ static int apple_dart_finalize_domain(struct iommu_domain *domain,
 	pgtbl_cfg = (struct io_pgtable_cfg){
 		.pgsize_bitmap = dart->pgsize,
 		.ias = 32,
-		.oas = 36,
+		.oas = dart->hw->oas,
 		.coherent_walk = 1,
 		.iommu_dev = dart->dev,
 	};
 
 	dart_domain->pgtbl_ops =
-		alloc_io_pgtable_ops(APPLE_DART, &pgtbl_cfg, domain);
+		alloc_io_pgtable_ops(dart->hw->fmt, &pgtbl_cfg, domain);
 	if (!dart_domain->pgtbl_ops) {
 		ret = -ENOMEM;
 		goto done;
@@ -858,6 +865,7 @@ static int apple_dart_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	dart->dev = dev;
+	dart->hw = of_device_get_match_data(dev);
 	spin_lock_init(&dart->lock);
 
 	dart->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
@@ -946,8 +954,18 @@ static int apple_dart_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct apple_dart_hw apple_dart_hw_t8103 = {
+	.oas = 36,
+	.fmt = APPLE_DART,
+};
+static const struct apple_dart_hw apple_dart_hw_t6000 = {
+	.oas = 42,
+	.fmt = APPLE_DART2,
+};
+
 static const struct of_device_id apple_dart_of_match[] = {
-	{ .compatible = "apple,t8103-dart", .data = NULL },
+	{ .compatible = "apple,t8103-dart", .data = &apple_dart_hw_t8103 },
+	{ .compatible = "apple,t6000-dart", .data = &apple_dart_hw_t6000 },
 	{},
 };
 MODULE_DEVICE_TABLE(of, apple_dart_of_match);
-- 
2.35.1

[PATCH v5 5/5] iommu: dart: Support t6000 variant

[Janne Grunau]

From: Sven Peter <sven@svenpeter.dev>

The M1 Pro/Max/Ultra SoCs come with a new variant of DART which
supports a larger physical address space with a different PTE format.
Pass through the correct paddr address space size and the PTE format
to the io-pgtable code which will take care of the rest.

Signed-off-by: Sven Peter <sven@svenpeter.dev>
Co-developed-by: Janne Grunau <j@jannau.net>
Signed-off-by: Janne Grunau <j@jannau.net>

---

(no changes since v3)

Changes in v3:
- apply change to io-pgtable-dart.c

Changes in v2:
- use APPLE_DART2 PTE format for dart-t6000

 drivers/iommu/apple-dart.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index 8af0242a90d9..e5793c0d08b4 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -81,10 +81,16 @@
 #define DART_TTBR_VALID BIT(31)
 #define DART_TTBR_SHIFT 12
 
+struct apple_dart_hw {
+	u32 oas;
+	enum io_pgtable_fmt fmt;
+};
+
 /*
  * Private structure associated with each DART device.
  *
  * @dev: device struct
+ * @hw: SoC-specific hardware data
  * @regs: mapped MMIO region
  * @irq: interrupt number, can be shared with other DARTs
  * @clks: clocks associated with this DART
@@ -98,6 +104,7 @@
  */
 struct apple_dart {
 	struct device *dev;
+	const struct apple_dart_hw *hw;
 
 	void __iomem *regs;
 
@@ -421,13 +428,13 @@ static int apple_dart_finalize_domain(struct iommu_domain *domain,
 	pgtbl_cfg = (struct io_pgtable_cfg){
 		.pgsize_bitmap = dart->pgsize,
 		.ias = 32,
-		.oas = 36,
+		.oas = dart->hw->oas,
 		.coherent_walk = 1,
 		.iommu_dev = dart->dev,
 	};
 
 	dart_domain->pgtbl_ops =
-		alloc_io_pgtable_ops(APPLE_DART, &pgtbl_cfg, domain);
+		alloc_io_pgtable_ops(dart->hw->fmt, &pgtbl_cfg, domain);
 	if (!dart_domain->pgtbl_ops) {
 		ret = -ENOMEM;
 		goto done;
@@ -858,6 +865,7 @@ static int apple_dart_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	dart->dev = dev;
+	dart->hw = of_device_get_match_data(dev);
 	spin_lock_init(&dart->lock);
 
 	dart->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
@@ -946,8 +954,18 @@ static int apple_dart_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct apple_dart_hw apple_dart_hw_t8103 = {
+	.oas = 36,
+	.fmt = APPLE_DART,
+};
+static const struct apple_dart_hw apple_dart_hw_t6000 = {
+	.oas = 42,
+	.fmt = APPLE_DART2,
+};
+
 static const struct of_device_id apple_dart_of_match[] = {
-	{ .compatible = "apple,t8103-dart", .data = NULL },
+	{ .compatible = "apple,t8103-dart", .data = &apple_dart_hw_t8103 },
+	{ .compatible = "apple,t6000-dart", .data = &apple_dart_hw_t6000 },
 	{},
 };
 MODULE_DEVICE_TABLE(of, apple_dart_of_match);
-- 
2.35.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v5 3/5] iommu/io-pgtable: Add DART subpage protection support

[Rob Herring]

On Fri, Sep 16, 2022 at 4:43 AM Janne Grunau <j@jannau.net> wrote:
>
> From: Sven Peter <sven@svenpeter.dev>
>
> DART allows to only expose a subpage to the device. While this is an
> optional feature on the M1 DARTs the new ones present on the Pro/Max
> models require this field in every PTE.
>
> Signed-off-by: Sven Peter <sven@svenpeter.dev>
> Signed-off-by: Janne Grunau <j@jannau.net>
>
> ---
>
> (no changes since v3)
>
> Changes in v3:
> - apply change to io-pgtable-dart.c
>
>  drivers/iommu/io-pgtable-dart.c | 8 ++++++++
>  1 file changed, 8 insertions(+)

Reviewed-by: Rob Herring <robh@kernel.org>

Re: [PATCH v5 3/5] iommu/io-pgtable: Add DART subpage protection support

[Rob Herring]

On Fri, Sep 16, 2022 at 4:43 AM Janne Grunau <j@jannau.net> wrote:
>
> From: Sven Peter <sven@svenpeter.dev>
>
> DART allows to only expose a subpage to the device. While this is an
> optional feature on the M1 DARTs the new ones present on the Pro/Max
> models require this field in every PTE.
>
> Signed-off-by: Sven Peter <sven@svenpeter.dev>
> Signed-off-by: Janne Grunau <j@jannau.net>
>
> ---
>
> (no changes since v3)
>
> Changes in v3:
> - apply change to io-pgtable-dart.c
>
>  drivers/iommu/io-pgtable-dart.c | 8 ++++++++
>  1 file changed, 8 insertions(+)

Reviewed-by: Rob Herring <robh@kernel.org>

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v5 4/5] iommu/io-pgtable-dart: Add DART PTE support for t6000

[Rob Herring]

On Fri, Sep 16, 2022 at 4:42 AM Janne Grunau <j@jannau.net> wrote:
>
> From: Sven Peter <sven@svenpeter.dev>
>
> The DARTs present in the M1 Pro/Max/Ultra SoC use a diffent PTE format.
> They support a 42bit physical address space by shifting the paddr and
> extending its mask inside the PTE.
> They also come with mandatory sub-page protection now which we just
> configure to always allow access to the entire page. This feature is
> already present but optional on the previous DARTs which allows to
> unconditionally configure it.
>
> Signed-off-by: Sven Peter <sven@svenpeter.dev>
> Co-developed-by: Janne Grunau <j@jannau.net>
> Signed-off-by: Janne Grunau <j@jannau.net>
>
> ---
>
> (no changes since v3)
>
> Changes in v3:
> - apply change to io-pgtable-dart.c
> - handle pte <> paddr conversion based on the pte format instead of
>   the output address size
>
> Changes in v2:
> - add APPLE_DART2 PTE format
>
>  drivers/iommu/io-pgtable-dart.c | 49 ++++++++++++++++++++++++++++-----
>  drivers/iommu/io-pgtable.c      |  1 +
>  include/linux/io-pgtable.h      |  1 +
>  3 files changed, 44 insertions(+), 7 deletions(-)

Reviewed-by: Rob Herring <robh@kernel.org>

Re: [PATCH v5 4/5] iommu/io-pgtable-dart: Add DART PTE support for t6000

[Rob Herring]

On Fri, Sep 16, 2022 at 4:42 AM Janne Grunau <j@jannau.net> wrote:
>
> From: Sven Peter <sven@svenpeter.dev>
>
> The DARTs present in the M1 Pro/Max/Ultra SoC use a diffent PTE format.
> They support a 42bit physical address space by shifting the paddr and
> extending its mask inside the PTE.
> They also come with mandatory sub-page protection now which we just
> configure to always allow access to the entire page. This feature is
> already present but optional on the previous DARTs which allows to
> unconditionally configure it.
>
> Signed-off-by: Sven Peter <sven@svenpeter.dev>
> Co-developed-by: Janne Grunau <j@jannau.net>
> Signed-off-by: Janne Grunau <j@jannau.net>
>
> ---
>
> (no changes since v3)
>
> Changes in v3:
> - apply change to io-pgtable-dart.c
> - handle pte <> paddr conversion based on the pte format instead of
>   the output address size
>
> Changes in v2:
> - add APPLE_DART2 PTE format
>
>  drivers/iommu/io-pgtable-dart.c | 49 ++++++++++++++++++++++++++++-----
>  drivers/iommu/io-pgtable.c      |  1 +
>  include/linux/io-pgtable.h      |  1 +
>  3 files changed, 44 insertions(+), 7 deletions(-)

Reviewed-by: Rob Herring <robh@kernel.org>

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v5 5/5] iommu: dart: Support t6000 variant

[Rob Herring]

On Fri, Sep 16, 2022 at 4:43 AM Janne Grunau <j@jannau.net> wrote:
>
> From: Sven Peter <sven@svenpeter.dev>
>
> The M1 Pro/Max/Ultra SoCs come with a new variant of DART which
> supports a larger physical address space with a different PTE format.
> Pass through the correct paddr address space size and the PTE format
> to the io-pgtable code which will take care of the rest.
>
> Signed-off-by: Sven Peter <sven@svenpeter.dev>
> Co-developed-by: Janne Grunau <j@jannau.net>
> Signed-off-by: Janne Grunau <j@jannau.net>
>
> ---
>
> (no changes since v3)
>
> Changes in v3:
> - apply change to io-pgtable-dart.c
>
> Changes in v2:
> - use APPLE_DART2 PTE format for dart-t6000
>
>  drivers/iommu/apple-dart.c | 24 +++++++++++++++++++++---
>  1 file changed, 21 insertions(+), 3 deletions(-)

Reviewed-by: Rob Herring <robh@kernel.org>

Re: [PATCH v5 5/5] iommu: dart: Support t6000 variant

[Rob Herring]

On Fri, Sep 16, 2022 at 4:43 AM Janne Grunau <j@jannau.net> wrote:
>
> From: Sven Peter <sven@svenpeter.dev>
>
> The M1 Pro/Max/Ultra SoCs come with a new variant of DART which
> supports a larger physical address space with a different PTE format.
> Pass through the correct paddr address space size and the PTE format
> to the io-pgtable code which will take care of the rest.
>
> Signed-off-by: Sven Peter <sven@svenpeter.dev>
> Co-developed-by: Janne Grunau <j@jannau.net>
> Signed-off-by: Janne Grunau <j@jannau.net>
>
> ---
>
> (no changes since v3)
>
> Changes in v3:
> - apply change to io-pgtable-dart.c
>
> Changes in v2:
> - use APPLE_DART2 PTE format for dart-t6000
>
>  drivers/iommu/apple-dart.c | 24 +++++++++++++++++++++---
>  1 file changed, 21 insertions(+), 3 deletions(-)

Reviewed-by: Rob Herring <robh@kernel.org>

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v5 0/5] iommu: M1 Pro/Max DART support

[Robin Murphy]

On 2022-09-16 10:41, Janne Grunau wrote:
> Hej,
> 
> this is the next attempt adding support for the DART found in Apple's
> M1 Pro/Max/Ultra. This adds a separate io-pgtable implementation for
> DART. As already mentioned in v2 the pte format is not fully compatible
> with io-pgtable-arm. Especially the 2nd least significant bit is used
> and is not available to tag tables/pages.
> io-pgtable-dart.c is copied from io-pgtable-arm.c and support for
> unused features is removed. Support for 4k IO pages is left for A7 to
> A11 SoCs as there's work underway to run Linux on them.
> 
> The incompatibilities between both Apple DART pte seems manageable in
> their own io-pgtable implementation. A short list of the known
> differences:
> 
>   - the physical addresses are shifted left by 4 bits and and have 2 more
>     bits inside the PTE entries
>   - the read/write protection flags are at a different position
>   - the subpage protection feature is now mandatory. For Linux we can
>     just configure it to always allow access to the entire page.
>   - BIT(1) tags "uncached" mappings (used for the display controller)
> 
> There is second type of DART (t8110) present on M1 Pro/Max SoCs which
> uses the same PTE format as t6000.

FWIW I think there's minimal risk in queueing this up as a late addition 
for 6.1, lest it get forgotten again. I've not been following it since 
I've been busy with other things and I largely trust that DART patches 
are well-tested, but from a quick skim it all earns a solid "yeah, why 
not" from me :)

Cheers,
Robin.

> Changes in v5:
> - collected Sven's ack
> - minor fixes in "iommu/io-pgtable: Move Apple DART support to its own
>    file"
> 
> Changes in v4:
> - split dart and io-pgtable-dart build to allow building dart as module
> - add missing "SELECT IOMMU_IO_PGTABLE"
> - made map/unmap_pages/iova_to_phys inon-recursive
> - replace pgd concatenation with multiple table handling
> - simplified config and page size checks
> - collected Robin's Ack
> 
> Changes in v3:
> - move APPLE_DART to its own io-pgtable implementation, copied from
>    io-pgtable-arm and simplified
> 
> Changes in v2:
> - added Rob's Acked-by:
> - add APPLE_DART2 io-pgtable format
> 
> Janne Grunau (1):
>    iommu/io-pgtable: Move Apple DART support to its own file
> 
> Sven Peter (4):
>    dt-bindings: iommu: dart: add t6000 compatible
>    iommu/io-pgtable: Add DART subpage protection support
>    iommu/io-pgtable-dart: Add DART PTE support for t6000
>    iommu: dart: Support t6000 variant
> 
>   .../devicetree/bindings/iommu/apple,dart.yaml |   4 +-
>   MAINTAINERS                                   |   1 +
>   drivers/iommu/Kconfig                         |  13 +-
>   drivers/iommu/Makefile                        |   1 +
>   drivers/iommu/apple-dart.c                    |  24 +-
>   drivers/iommu/io-pgtable-arm.c                |  63 ---
>   drivers/iommu/io-pgtable-dart.c               | 470 ++++++++++++++++++
>   drivers/iommu/io-pgtable.c                    |   3 +
>   include/linux/io-pgtable.h                    |   1 +
>   9 files changed, 512 insertions(+), 68 deletions(-)
>   create mode 100644 drivers/iommu/io-pgtable-dart.c
> 

Re: [PATCH v5 0/5] iommu: M1 Pro/Max DART support

[Robin Murphy]

On 2022-09-16 10:41, Janne Grunau wrote:
> Hej,
> 
> this is the next attempt adding support for the DART found in Apple's
> M1 Pro/Max/Ultra. This adds a separate io-pgtable implementation for
> DART. As already mentioned in v2 the pte format is not fully compatible
> with io-pgtable-arm. Especially the 2nd least significant bit is used
> and is not available to tag tables/pages.
> io-pgtable-dart.c is copied from io-pgtable-arm.c and support for
> unused features is removed. Support for 4k IO pages is left for A7 to
> A11 SoCs as there's work underway to run Linux on them.
> 
> The incompatibilities between both Apple DART pte seems manageable in
> their own io-pgtable implementation. A short list of the known
> differences:
> 
>   - the physical addresses are shifted left by 4 bits and and have 2 more
>     bits inside the PTE entries
>   - the read/write protection flags are at a different position
>   - the subpage protection feature is now mandatory. For Linux we can
>     just configure it to always allow access to the entire page.
>   - BIT(1) tags "uncached" mappings (used for the display controller)
> 
> There is second type of DART (t8110) present on M1 Pro/Max SoCs which
> uses the same PTE format as t6000.

FWIW I think there's minimal risk in queueing this up as a late addition 
for 6.1, lest it get forgotten again. I've not been following it since 
I've been busy with other things and I largely trust that DART patches 
are well-tested, but from a quick skim it all earns a solid "yeah, why 
not" from me :)

Cheers,
Robin.

> Changes in v5:
> - collected Sven's ack
> - minor fixes in "iommu/io-pgtable: Move Apple DART support to its own
>    file"
> 
> Changes in v4:
> - split dart and io-pgtable-dart build to allow building dart as module
> - add missing "SELECT IOMMU_IO_PGTABLE"
> - made map/unmap_pages/iova_to_phys inon-recursive
> - replace pgd concatenation with multiple table handling
> - simplified config and page size checks
> - collected Robin's Ack
> 
> Changes in v3:
> - move APPLE_DART to its own io-pgtable implementation, copied from
>    io-pgtable-arm and simplified
> 
> Changes in v2:
> - added Rob's Acked-by:
> - add APPLE_DART2 io-pgtable format
> 
> Janne Grunau (1):
>    iommu/io-pgtable: Move Apple DART support to its own file
> 
> Sven Peter (4):
>    dt-bindings: iommu: dart: add t6000 compatible
>    iommu/io-pgtable: Add DART subpage protection support
>    iommu/io-pgtable-dart: Add DART PTE support for t6000
>    iommu: dart: Support t6000 variant
> 
>   .../devicetree/bindings/iommu/apple,dart.yaml |   4 +-
>   MAINTAINERS                                   |   1 +
>   drivers/iommu/Kconfig                         |  13 +-
>   drivers/iommu/Makefile                        |   1 +
>   drivers/iommu/apple-dart.c                    |  24 +-
>   drivers/iommu/io-pgtable-arm.c                |  63 ---
>   drivers/iommu/io-pgtable-dart.c               | 470 ++++++++++++++++++
>   drivers/iommu/io-pgtable.c                    |   3 +
>   include/linux/io-pgtable.h                    |   1 +
>   9 files changed, 512 insertions(+), 68 deletions(-)
>   create mode 100644 drivers/iommu/io-pgtable-dart.c
> 

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v5 1/5] dt-bindings: iommu: dart: add t6000 compatible

[Hector Martin]

On 16/09/2022 18.41, Janne Grunau wrote:
> From: Sven Peter <sven@svenpeter.dev>
> 
> The M1 Max/Pro SoCs come with a new DART variant that is incompatible with
> the previous one. Add a new compatible for those.
> 
> Signed-off-by: Sven Peter <sven@svenpeter.dev>
> Acked-by: Rob Herring <robh@kernel.org>
> 
> Signed-off-by: Janne Grunau <j@jannau.net>
> ---
> 
> (no changes since v2)
> 
> Changes in v2:
> - added Rob's Acked-by:
> 
>  Documentation/devicetree/bindings/iommu/apple,dart.yaml | 4 +++-
>  1 file changed, 3 insertions(+), 1 deletion(-)
> 
> diff --git a/Documentation/devicetree/bindings/iommu/apple,dart.yaml b/Documentation/devicetree/bindings/iommu/apple,dart.yaml
> index 82ad669feef7..06af2bacbe97 100644
> --- a/Documentation/devicetree/bindings/iommu/apple,dart.yaml
> +++ b/Documentation/devicetree/bindings/iommu/apple,dart.yaml
> @@ -22,7 +22,9 @@ description: |+
>  
>  properties:
>    compatible:
> -    const: apple,t8103-dart
> +    enum:
> +      - apple,t8103-dart
> +      - apple,t6000-dart
>  
>    reg:
>      maxItems: 1

I'm taking this one via the Asahi-SoC tree, since it unblocks the t6000
DT series and it is already reviewed and ready to go. Thanks!

- Hector

Re: [PATCH v5 1/5] dt-bindings: iommu: dart: add t6000 compatible

[Hector Martin]

On 16/09/2022 18.41, Janne Grunau wrote:
> From: Sven Peter <sven@svenpeter.dev>
> 
> The M1 Max/Pro SoCs come with a new DART variant that is incompatible with
> the previous one. Add a new compatible for those.
> 
> Signed-off-by: Sven Peter <sven@svenpeter.dev>
> Acked-by: Rob Herring <robh@kernel.org>
> 
> Signed-off-by: Janne Grunau <j@jannau.net>
> ---
> 
> (no changes since v2)
> 
> Changes in v2:
> - added Rob's Acked-by:
> 
>  Documentation/devicetree/bindings/iommu/apple,dart.yaml | 4 +++-
>  1 file changed, 3 insertions(+), 1 deletion(-)
> 
> diff --git a/Documentation/devicetree/bindings/iommu/apple,dart.yaml b/Documentation/devicetree/bindings/iommu/apple,dart.yaml
> index 82ad669feef7..06af2bacbe97 100644
> --- a/Documentation/devicetree/bindings/iommu/apple,dart.yaml
> +++ b/Documentation/devicetree/bindings/iommu/apple,dart.yaml
> @@ -22,7 +22,9 @@ description: |+
>  
>  properties:
>    compatible:
> -    const: apple,t8103-dart
> +    enum:
> +      - apple,t8103-dart
> +      - apple,t6000-dart
>  
>    reg:
>      maxItems: 1

I'm taking this one via the Asahi-SoC tree, since it unblocks the t6000
DT series and it is already reviewed and ready to go. Thanks!

- Hector

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v5 2/5] iommu/io-pgtable: Move Apple DART support to its own file

[Hector Martin]

On 16/09/2022 18.41, Janne Grunau wrote:
> 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>
> 
> ---

[...]

> +static void *__dart_alloc_pages(size_t size, gfp_t gfp,
> +				    struct io_pgtable_cfg *cfg)
> +{
> +	struct device *dev = cfg->iommu_dev;
> +	int order = get_order(size);
> +	struct page *p;
> +
> +	VM_BUG_ON((gfp & __GFP_HIGHMEM));
> +	p = alloc_pages(gfp | __GFP_ZERO, order);
> +	if (!p)
> +		return NULL;
> +
> +	return page_address(p);
> +}

This throws a warning:

drivers/iommu/io-pgtable-dart.c: In function ‘__dart_alloc_pages’:
drivers/iommu/io-pgtable-dart.c:112:24: warning: unused variable ‘dev’
[-Wunused-variable]
  112 |         struct device *dev = cfg->iommu_dev;
      |                        ^~~

The fix is trivial, of course.

- Hector

Re: [PATCH v5 2/5] iommu/io-pgtable: Move Apple DART support to its own file

[Hector Martin]

On 16/09/2022 18.41, Janne Grunau wrote:
> 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>
> 
> ---

[...]

> +static void *__dart_alloc_pages(size_t size, gfp_t gfp,
> +				    struct io_pgtable_cfg *cfg)
> +{
> +	struct device *dev = cfg->iommu_dev;
> +	int order = get_order(size);
> +	struct page *p;
> +
> +	VM_BUG_ON((gfp & __GFP_HIGHMEM));
> +	p = alloc_pages(gfp | __GFP_ZERO, order);
> +	if (!p)
> +		return NULL;
> +
> +	return page_address(p);
> +}

This throws a warning:

drivers/iommu/io-pgtable-dart.c: In function ‘__dart_alloc_pages’:
drivers/iommu/io-pgtable-dart.c:112:24: warning: unused variable ‘dev’
[-Wunused-variable]
  112 |         struct device *dev = cfg->iommu_dev;
      |                        ^~~

The fix is trivial, of course.

- Hector

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v5 0/5] iommu: M1 Pro/Max DART support

[Hector Martin]

On 16/09/2022 18.41, Janne Grunau wrote:
> Hej,
> 
> this is the next attempt adding support for the DART found in Apple's
> M1 Pro/Max/Ultra. This adds a separate io-pgtable implementation for
> DART. As already mentioned in v2 the pte format is not fully compatible
> with io-pgtable-arm. Especially the 2nd least significant bit is used
> and is not available to tag tables/pages.
> io-pgtable-dart.c is copied from io-pgtable-arm.c and support for
> unused features is removed. Support for 4k IO pages is left for A7 to
> A11 SoCs as there's work underway to run Linux on them.
> 
> The incompatibilities between both Apple DART pte seems manageable in
> their own io-pgtable implementation. A short list of the known
> differences:
> 
>  - the physical addresses are shifted left by 4 bits and and have 2 more
>    bits inside the PTE entries
>  - the read/write protection flags are at a different position
>  - the subpage protection feature is now mandatory. For Linux we can
>    just configure it to always allow access to the entire page.
>  - BIT(1) tags "uncached" mappings (used for the display controller)
> 
> There is second type of DART (t8110) present on M1 Pro/Max SoCs which
> uses the same PTE format as t6000.
> 
> Changes in v5:
> - collected Sven's ack
> - minor fixes in "iommu/io-pgtable: Move Apple DART support to its own
>   file"
> 
> Changes in v4:
> - split dart and io-pgtable-dart build to allow building dart as module
> - add missing "SELECT IOMMU_IO_PGTABLE"
> - made map/unmap_pages/iova_to_phys inon-recursive
> - replace pgd concatenation with multiple table handling
> - simplified config and page size checks
> - collected Robin's Ack
> 
> Changes in v3:
> - move APPLE_DART to its own io-pgtable implementation, copied from
>   io-pgtable-arm and simplified
> 
> Changes in v2:
> - added Rob's Acked-by:
> - add APPLE_DART2 io-pgtable format
> 
> Janne Grunau (1):
>   iommu/io-pgtable: Move Apple DART support to its own file
> 
> Sven Peter (4):
>   dt-bindings: iommu: dart: add t6000 compatible
>   iommu/io-pgtable: Add DART subpage protection support
>   iommu/io-pgtable-dart: Add DART PTE support for t6000
>   iommu: dart: Support t6000 variant
> 
>  .../devicetree/bindings/iommu/apple,dart.yaml |   4 +-
>  MAINTAINERS                                   |   1 +
>  drivers/iommu/Kconfig                         |  13 +-
>  drivers/iommu/Makefile                        |   1 +
>  drivers/iommu/apple-dart.c                    |  24 +-
>  drivers/iommu/io-pgtable-arm.c                |  63 ---
>  drivers/iommu/io-pgtable-dart.c               | 470 ++++++++++++++++++
>  drivers/iommu/io-pgtable.c                    |   3 +
>  include/linux/io-pgtable.h                    |   1 +
>  9 files changed, 512 insertions(+), 68 deletions(-)
>  create mode 100644 drivers/iommu/io-pgtable-dart.c
> 

For the whole series, modulo the trivial warning I mentioned:

Acked-by: Hector Martin <marcan@marcan.st>

Let's get this merged please, it's been blocking t6000 support for a
long time now :)

- Hector

Re: [PATCH v5 0/5] iommu: M1 Pro/Max DART support

[Hector Martin]

On 16/09/2022 18.41, Janne Grunau wrote:
> Hej,
> 
> this is the next attempt adding support for the DART found in Apple's
> M1 Pro/Max/Ultra. This adds a separate io-pgtable implementation for
> DART. As already mentioned in v2 the pte format is not fully compatible
> with io-pgtable-arm. Especially the 2nd least significant bit is used
> and is not available to tag tables/pages.
> io-pgtable-dart.c is copied from io-pgtable-arm.c and support for
> unused features is removed. Support for 4k IO pages is left for A7 to
> A11 SoCs as there's work underway to run Linux on them.
> 
> The incompatibilities between both Apple DART pte seems manageable in
> their own io-pgtable implementation. A short list of the known
> differences:
> 
>  - the physical addresses are shifted left by 4 bits and and have 2 more
>    bits inside the PTE entries
>  - the read/write protection flags are at a different position
>  - the subpage protection feature is now mandatory. For Linux we can
>    just configure it to always allow access to the entire page.
>  - BIT(1) tags "uncached" mappings (used for the display controller)
> 
> There is second type of DART (t8110) present on M1 Pro/Max SoCs which
> uses the same PTE format as t6000.
> 
> Changes in v5:
> - collected Sven's ack
> - minor fixes in "iommu/io-pgtable: Move Apple DART support to its own
>   file"
> 
> Changes in v4:
> - split dart and io-pgtable-dart build to allow building dart as module
> - add missing "SELECT IOMMU_IO_PGTABLE"
> - made map/unmap_pages/iova_to_phys inon-recursive
> - replace pgd concatenation with multiple table handling
> - simplified config and page size checks
> - collected Robin's Ack
> 
> Changes in v3:
> - move APPLE_DART to its own io-pgtable implementation, copied from
>   io-pgtable-arm and simplified
> 
> Changes in v2:
> - added Rob's Acked-by:
> - add APPLE_DART2 io-pgtable format
> 
> Janne Grunau (1):
>   iommu/io-pgtable: Move Apple DART support to its own file
> 
> Sven Peter (4):
>   dt-bindings: iommu: dart: add t6000 compatible
>   iommu/io-pgtable: Add DART subpage protection support
>   iommu/io-pgtable-dart: Add DART PTE support for t6000
>   iommu: dart: Support t6000 variant
> 
>  .../devicetree/bindings/iommu/apple,dart.yaml |   4 +-
>  MAINTAINERS                                   |   1 +
>  drivers/iommu/Kconfig                         |  13 +-
>  drivers/iommu/Makefile                        |   1 +
>  drivers/iommu/apple-dart.c                    |  24 +-
>  drivers/iommu/io-pgtable-arm.c                |  63 ---
>  drivers/iommu/io-pgtable-dart.c               | 470 ++++++++++++++++++
>  drivers/iommu/io-pgtable.c                    |   3 +
>  include/linux/io-pgtable.h                    |   1 +
>  9 files changed, 512 insertions(+), 68 deletions(-)
>  create mode 100644 drivers/iommu/io-pgtable-dart.c
> 

For the whole series, modulo the trivial warning I mentioned:

Acked-by: Hector Martin <marcan@marcan.st>

Let's get this merged please, it's been blocking t6000 support for a
long time now :)

- Hector

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v5 0/5] iommu: M1 Pro/Max DART support

[Joerg Roedel]

On Fri, Sep 16, 2022 at 11:41:47AM +0200, Janne Grunau wrote:
> Janne Grunau (1):
>   iommu/io-pgtable: Move Apple DART support to its own file
> 
> Sven Peter (4):
>   dt-bindings: iommu: dart: add t6000 compatible
>   iommu/io-pgtable: Add DART subpage protection support
>   iommu/io-pgtable-dart: Add DART PTE support for t6000
>   iommu: dart: Support t6000 variant

Applied patches 2-5 for v6.1, thanks everyone.

Re: [PATCH v5 0/5] iommu: M1 Pro/Max DART support

[Joerg Roedel]

On Fri, Sep 16, 2022 at 11:41:47AM +0200, Janne Grunau wrote:
> Janne Grunau (1):
>   iommu/io-pgtable: Move Apple DART support to its own file
> 
> Sven Peter (4):
>   dt-bindings: iommu: dart: add t6000 compatible
>   iommu/io-pgtable: Add DART subpage protection support
>   iommu/io-pgtable-dart: Add DART PTE support for t6000
>   iommu: dart: Support t6000 variant

Applied patches 2-5 for v6.1, thanks everyone.

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel