iommu: Support mappings/reservations in reserved-memory regions

From: Thierry Reding <[email protected]>

Hi,

This version is a rebase on top of v6.2-rc4 to resolve a minor conflict. Version 12 can be found here:

https://lore.kernel.org/all/[email protected]/

The only change here is that the #dma-{address,size}-cells is dropped. It turns out to be much simpler to just update #{address,size}-cells to what they should be rather than add extra complexity for the DMA work- around. There's a minor update to the DT binding so that it can now properly validate cases where we have both reg and iommu-addresses properties.

An example is included in the DT bindings, but here is an extract of what I've used to test this:

        reserved-memory {
                #address-cells = <2>;
                #size-cells = <2>;
                ranges;

                /*
                 * Creates an identity mapping for the framebuffer that
                 * the firmware has setup to scan out a bootsplash from.
                 */
                fb: framebuffer@92cb2000 {
                        reg = <0x0 0x92cb2000 0x0 0x00800000>;
                        iommu-addresses = <&dc0 0x0 0x92cb2000 0x0 0x00800000>;
                };

                /*
                 * Creates a reservation in the IOVA space to prevent
                 * any buffers from being mapped to that region. Note
                 * that on Tegra the range is actually quite different
                 * from this, but it would conflict with the display
                 * driver that I tested this against, so this is just
                 * a dummy region for testing.
                 */
                adsp: reservation-adsp {
                        iommu-addresses = <&dc0 0x0 0x90000000 0x0 0x00010000>;
                };
        };

        host1x@50000000 {
                dc@54200000 {
                        memory-region = <&fb>, <&adsp>;
                };
        };

This is abbreviated a little to focus on the essentials. Note also that the ADSP reservation is not actually used on this device and the driver for this doesn't exist yet, but I wanted to include this variant for testing, because we'll want to use these bindings for the reservation use-case as well at some point.

I've also been able to make use of this binding and the IOMMU code in conjunction with the simple-framebuffer driver to hand over a display configuration set up by UEFI to the Linux kernel.

Janne has confirmed[0] this to be suitable for indirect mappings as well, though these patches don't implement that feature yet. Potential extensions to this have been discussed but are not yet included at this time to not further complicate things.

Thierry

[0]: https://lore.kernel.org/all/[email protected]/

Thierry Reding (4):
of: Introduce of_translate_dma_region()
dt-bindings: reserved-memory: Document iommu-addresses
iommu: Implement of_iommu_get_resv_regions()
iommu: dma: Use of_iommu_get_resv_regions()

 .../reserved-memory/reserved-memory.yaml      | 89 +++++++++++++++++-
 drivers/iommu/dma-iommu.c                     |  3 +
 drivers/iommu/of_iommu.c                      | 94 +++++++++++++++++++
 drivers/of/address.c                          | 41 ++++++++
 include/linux/of_address.h                    |  2 +
 include/linux/of_iommu.h                      |  8 ++
 6 files changed, 233 insertions(+), 4 deletions(-)

2.39.0

From: Thierry Reding <[email protected]>

This function is similar to of_translate_dma_address() but also reads a length in addition to an address from a device tree property.

---
 drivers/of/address.c       | 41 ++++++++++++++++++++++++++++++++++++++
 include/linux/of_address.h |  2 ++
 2 files changed, 43 insertions(+)

index c34ac33b7338..14f137a21b0c 100644
@@ -626,6 +626,47 @@ u64 of_translate_dma_address(struct device_node *dev, const __be32 *in_addr)
 }
 EXPORT_SYMBOL(of_translate_dma_address);
 
+/**
+ * of_translate_dma_region - Translate device tree address and size tuple
+ * @dev: device tree node for which to translate
+ * @prop: pointer into array of cells
+ * @start: return value for the start of the DMA range
+ * @length: return value for the length of the DMA range
+ *
+ * Returns a pointer to the cell immediately following the translated DMA region.
+ */
+const __be32 *of_translate_dma_region(struct device_node *dev, const __be32 *prop,
+				      phys_addr_t *start, size_t *length)
+{
+	struct device_node *parent;
+	u64 address, size;
+	int na, ns;
+
+	parent = __of_get_dma_parent(dev);
+	if (!parent)
+		return NULL;
+
+	na = of_bus_n_addr_cells(parent);
+	ns = of_bus_n_size_cells(parent);
+
+	of_node_put(parent);
+
+	address = of_translate_dma_address(dev, prop);
+	if (address == OF_BAD_ADDR)
+		return NULL;
+
+	size = of_read_number(prop + na, ns);
+
+	if (start)
+		*start = address;
+
+	if (length)
+		*length = size;
+
+	return prop + na + ns;
+}
+EXPORT_SYMBOL(of_translate_dma_region);
+
 const __be32 *__of_get_address(struct device_node *dev, int index, int bar_no,
 			       u64 *size, unsigned int *flags)
 {

index 265f26eeaf6b..376671594746 100644
@@ -38,6 +38,8 @@ struct of_pci_range {
 /* Translate a DMA address from device space to CPU space */
 extern u64 of_translate_dma_address(struct device_node *dev,
 				    const __be32 *in_addr);
+extern const __be32 *of_translate_dma_region(struct device_node *dev, const __be32 *addr,
+					     phys_addr_t *start, size_t *length);
 
 #ifdef CONFIG_OF_ADDRESS
 extern u64 of_translate_address(struct device_node *np, const __be32 *addr);

2.39.0

From: Thierry Reding <[email protected]>

This adds the "iommu-addresses" property to reserved-memory nodes, which allow describing the interaction of memory regions with IOMMUs. Two use- cases are supported:

1. Static mappings can be described by pairing the "iommu-addresses" property with a "reg" property. This is mostly useful for adopting firmware-allocated buffers via identity mappings. One common use- case where this is required is if early firmware or bootloaders have set up a bootsplash framebuffer that a display controller is actively scanning out from during the operating system boot process.

2. If an "iommu-addresses" property exists without a "reg" property, the reserved-memory node describes an IOVA reservation. Such memory regions are excluded from the IOVA space available to operating system drivers and can be used for regions that must not be used to map arbitrary buffers.

Each mapping or reservation is tied to a specific device via a phandle to the device's device tree node. This allows a reserved-memory region to be reused across multiple devices.

---
Changes in v12:
- allow iommu-addresses to be specified when reg is present

Changes in v10:
- mark iommu-addresses as required in the absence of reg and size

Changes in v9:
- add Reviewed-by tags

Changes in v8:
- include validation warnings that had crept into an unrelated patch

Changes in v7:
- keep reserved-memory.txt to avoid broken references

Changes in v6:
- add device phandle to iommu-addresses property in examples
- remove now unused dt-bindings/reserved-memory.h header

 .../reserved-memory/reserved-memory.yaml      | 89 ++++++++++++++++++-
 1 file changed, 85 insertions(+), 4 deletions(-)

index 44f72bcf1782..010219138858 100644
@@ -52,6 +52,30 @@ properties:
       Address and Length pairs. Specifies regions of memory that are
       acceptable to allocate from.
 
+  iommu-addresses:
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    description: >
+      A list of phandle and specifier pairs that describe static IO virtual
+      address space mappings and carveouts associated with a given reserved
+      memory region. The phandle in the first cell refers to the device for
+      which the mapping or carveout is to be created.
+
+      The specifier consists of an address/size pair and denotes the IO
+      virtual address range of the region for the given device. The exact
+      format depends on the values of the "#address-cells" and "#size-cells"
+      properties of the device referenced via the phandle.
+
+      When used in combination with a "reg" property, an IOVA mapping is to
+      be established for this memory region. One example where this can be
+      useful is to create an identity mapping for physical memory that the
+      firmware has configured some hardware to access (such as a bootsplash
+      framebuffer).
+
+      If no "reg" property is specified, the "iommu-addresses" property
+      defines carveout regions in the IOVA space for the given device. This
+      can be useful if a certain memory region should not be mapped through
+      the IOMMU.
+
   no-map:
     type: boolean
     description: >

@@ -89,12 +113,69 @@ allOf:
           - no-map
 
 oneOf:
-  - required:
-      - reg
+  - oneOf:
+      - required:
+          - reg
+
+      - required:
+          - size
+
+  - oneOf:
+      # IOMMU reservations
+      - required:
+          - iommu-addresses
 
-  - required:
-      - size
+      # IOMMU mappings
+      - required:
+          - reg
+          - iommu-addresses
 
 additionalProperties: true
 
+examples:
+  - |
+    / {
+      compatible = "foo";
+      model = "foo";
+
+      #address-cells = <2>;
+      #size-cells = <2>;
+
+      reserved-memory {
+        #address-cells = <2>;
+        #size-cells = <2>;
+        ranges;
+
+        adsp_resv: reservation-adsp {
+          /*
+           * Restrict IOVA mappings for ADSP buffers to the 512 MiB region
+           * from 0x40000000 - 0x5fffffff. Anything outside is reserved by
+           * the ADSP for I/O memory and private memory allocations.
+           */
+          iommu-addresses = <&adsp 0x0 0x00000000 0x00 0x40000000>,
+                            <&adsp 0x0 0x60000000 0xff 0xa0000000>;
+        };
+
+        fb: framebuffer@90000000 {
+          reg = <0x0 0x90000000 0x0 0x00800000>;
+          iommu-addresses = <&dc0 0x0 0x90000000 0x0 0x00800000>;
+        };
+      };
+
+      bus@0 {
+        #address-cells = <1>;
+        #size-cells = <1>;
+        ranges = <0x0 0x0 0x0 0x40000000>;
+
+        adsp: adsp@2990000 {
+          reg = <0x2990000 0x2000>;
+          memory-region = <&adsp_resv>;
+        };
+
+        dc0: display@15200000 {
+          reg = <0x15200000 0x10000>;
+          memory-region = <&fb>;
+        };
+      };
+    };
 ...

2.39.0

From: Thierry Reding <[email protected]>

This is an implementation that IOMMU drivers can use to obtain reserved memory regions from a device tree node. It uses the reserved-memory DT bindings to find the regions associated with a given device. If these regions are marked accordingly, identity mappings will be created for them in the IOMMU domain that the devices will be attached to.

---
Changes in v10:
- extract more code into the new iommu_resv_region_get_type() function
- rename variables for physical and I/O virtual addresses for clarity
- default to IOMMU_RESV_DIRECT instead of IOMMU_RESV_DIRECT_RELAXABLE
- use newly introduced of_translate_dma_region()

Changes in v9:
- address review comments by Robin Murphy:
- warn about non-direct mappings since they are not supported yet
- cleanup code to require less indentation
- narrow scope of variables

Changes in v8:
- cleanup set-but-unused variables

Changes in v6:
- remove reference to now unused dt-bindings/reserved-memory.h include

Changes in v5:
- update for new "iommu-addresses" device tree bindings

Changes in v4:
- fix build failure on !CONFIG_OF_ADDRESS

Changes in v3:
- change "active" property to identity mapping flag that is part of the memory region specifier (as defined by #memory-region-cells) to allow per-reference flags to be used

Changes in v2:
- use "active" property to determine whether direct mappings are needed

 drivers/iommu/of_iommu.c | 94 ++++++++++++++++++++++++++++++++++++++++
 include/linux/of_iommu.h |  8 ++++
 2 files changed, 102 insertions(+)

index 00d98f08732f..3c2e2a13cf9c 100644
@@ -10,6 +10,7 @@
 #include <linux/limits.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_iommu.h>
 #include <linux/of_pci.h>
 #include <linux/pci.h>

@@ -171,3 +172,96 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 
 	return ops;
 }
+
+static enum iommu_resv_type iommu_resv_region_get_type(struct device *dev, struct resource *phys,
+						       phys_addr_t start, size_t length)
+{
+	phys_addr_t end = start + length - 1;
+
+	/*
+	 * IOMMU regions without an associated physical region cannot be
+	 * mapped and are simply reservations.
+	 */
+	if (phys->start >= phys->end)
+		return IOMMU_RESV_RESERVED;
+
+	/* may be IOMMU_RESV_DIRECT_RELAXABLE for certain cases */
+	if (start == phys->start && end == phys->end)
+		return IOMMU_RESV_DIRECT;
+
+	dev_warn(dev, "treating non-direct mapping [%pr] -> [%pap-%pap] as reservation\n", &phys,
+		 &start, &end);
+	return IOMMU_RESV_RESERVED;
+}
+
+/**
+ * of_iommu_get_resv_regions - reserved region driver helper for device tree
+ * @dev: device for which to get reserved regions
+ * @list: reserved region list
+ *
+ * IOMMU drivers can use this to implement their .get_resv_regions() callback
+ * for memory regions attached to a device tree node. See the reserved-memory
+ * device tree bindings on how to use these:
+ *
+ *   Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
+ */
+void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
+{
+#if IS_ENABLED(CONFIG_OF_ADDRESS)
+	struct of_phandle_iterator it;
+	int err;
+
+	of_for_each_phandle(&it, err, dev->of_node, "memory-region", NULL, 0) {
+		const __be32 *maps, *end;
+		struct resource phys;
+		int size;
+
+		memset(&phys, 0, sizeof(phys));
+
+		/*
+		 * The "reg" property is optional and can be omitted by reserved-memory regions
+		 * that represent reservations in the IOVA space, which are regions that should
+		 * not be mapped.
+		 */
+		if (of_find_property(it.node, "reg", NULL)) {
+			err = of_address_to_resource(it.node, 0, &phys);
+			if (err < 0) {
+				dev_err(dev, "failed to parse memory region %pOF: %d\n",
+					it.node, err);
+				continue;
+			}
+		}
+
+		maps = of_get_property(it.node, "iommu-addresses", &size);
+		if (!maps)
+			continue;
+
+		end = maps + size / sizeof(__be32);
+
+		while (maps < end) {
+			struct device_node *np;
+			u32 phandle;
+
+			phandle = be32_to_cpup(maps++);
+			np = of_find_node_by_phandle(phandle);
+
+			if (np == dev->of_node) {
+				int prot = IOMMU_READ | IOMMU_WRITE;
+				struct iommu_resv_region *region;
+				enum iommu_resv_type type;
+				phys_addr_t iova;
+				size_t length;
+
+				maps = of_translate_dma_region(np, maps, &iova, &length);
+				type = iommu_resv_region_get_type(dev, &phys, iova, length);
+
+				region = iommu_alloc_resv_region(iova, length, prot, type,
+								 GFP_KERNEL);
+				if (region)
+					list_add_tail(&region->list, list);
+			}
+		}
+	}
+#endif
+}
+EXPORT_SYMBOL(of_iommu_get_resv_regions);

index 55c1eb300a86..9a5e6b410dd2 100644
@@ -12,6 +12,9 @@ extern const struct iommu_ops *of_iommu_configure(struct device *dev,
 					struct device_node *master_np,
 					const u32 *id);
 
+extern void of_iommu_get_resv_regions(struct device *dev,
+				      struct list_head *list);
+
 #else
 
 static inline const struct iommu_ops *of_iommu_configure(struct device *dev,

@@ -21,6 +24,11 @@ static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
 	return NULL;
 }
 
+static inline void of_iommu_get_resv_regions(struct device *dev,
+					     struct list_head *list)
+{
+}
+
 #endif	/* CONFIG_OF_IOMMU */
 
 #endif /* __OF_IOMMU_H */

2.39.0

From: Thierry Reding <[email protected]>

For device tree nodes, use the standard of_iommu_get_resv_regions() implementation to obtain the reserved memory regions associated with a device.

---
 drivers/iommu/dma-iommu.c | 3 +++
 1 file changed, 3 insertions(+)

index f798c44e0903..8e023f032b76 100644
@@ -23,6 +23,7 @@
 #include <linux/memremap.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
+#include <linux/of_iommu.h>
 #include <linux/pci.h>
 #include <linux/scatterlist.h>
 #include <linux/spinlock.h>

@@ -391,6 +392,8 @@ void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
 	if (!is_of_node(dev_iommu_fwspec_get(dev)->iommu_fwnode))
 		iort_iommu_get_resv_regions(dev, list);
 
+	if (dev->of_node)
+		of_iommu_get_resv_regions(dev, list);
 }
 EXPORT_SYMBOL(iommu_dma_get_resv_regions);
 

2.39.0

Hej,

The dt-bindings are sufficient for various firmware based co-processors on Apple silicon systems. This version and several before with additional straight forward changes to support indirect mappings are tested on the downstream asahi kernel with display processor support.

Janne

Applied for 6.3, thanks.