On 2022-09-05 18:08, Thierry Reding wrote:
From: Thierry Reding <treding@xxxxxxxxxx>
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.
Cc: Frank Rowand <frowand.list@xxxxxxxxx>
Cc: devicetree@xxxxxxxxxxxxxxx
Reviewed-by: Rob Herring <robh@xxxxxxxxxx>
Signed-off-by: Thierry Reding <treding@xxxxxxxxxx>
---
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 | 85 ++++++++++++++++++++++++++++++++++++++++
include/linux/of_iommu.h | 8 ++++
2 files changed, 93 insertions(+)
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 5696314ae69e..6617096ad15f 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -11,6 +11,7 @@
#include <linux/module.h>
#include <linux/msi.h>
#include <linux/of.h>
+#include <linux/of_address.h>
#include <linux/of_iommu.h>
#include <linux/of_pci.h>
#include <linux/pci.h>
@@ -172,3 +173,87 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
return ops;
}
+
+/**
+ * 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) {
+ struct iommu_resv_region *region;
+ struct resource res;
+ const __be32 *maps;
+ int size;
+
+ memset(&res, 0, sizeof(res));
+
+ /*
+ * 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, &res);
+ 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) {
Nit: "if (!maps) continue;" and save some indentation.
+ const __be32 *end = maps + size / sizeof(__be32);
+ struct device_node *np;
+ u32 phandle;
+ int na, ns;
+
+ while (maps < end) {
+ phys_addr_t start;
+ size_t length;
+
+ phandle = be32_to_cpup(maps++);
+ np = of_find_node_by_phandle(phandle);
+ na = of_n_addr_cells(np);
+ ns = of_n_size_cells(np);
+
+ start = of_translate_dma_address(np, maps);
+ length = of_read_number(maps + na, ns);
Nit: these could go inside the if condition.
+
+ if (np == dev->of_node) {
+ int prot = IOMMU_READ | IOMMU_WRITE;
+ enum iommu_resv_type type;
+
+ /*
+ * IOMMU regions without an associated physical region
+ * cannot be mapped and are simply reservations.
+ */
+ if (res.end > res.start)
+ type = IOMMU_RESV_DIRECT_RELAXABLE;
There may be reservations that have a PA but are expected to live beyond
boot-time handover, like device firmware or a shared-memory
communication buffer which the kernel driver can't reconfigure, or some
kind of black hole that needs a PA because it's also "no-map" for the
CPUs. Those are not relaxable. Might it be reasonable to expect to infer
this from the compatible, or should we have an additional explicit flag
to distinguish ephemeral boot-time mappings from permanent ones?
Furthermore, we should only use IOMMU_RESV_DIRECT (in either form) if
start and length actually match res here; if not then we should warn
that we're reserving the IOVA space but not actually honouring the
specified mapping (we'd need a new resv_region type for arbitrary
translations).
Thanks,
Robin.
+ else
+ type = IOMMU_RESV_RESERVED;
+
+ region = iommu_alloc_resv_region(start, length, prot, type);
+ if (region)
+ list_add_tail(®ion->list, list);
+ }
+
+ maps += na + ns;
+ }
+ }
+ }
+#endif
+}
+EXPORT_SYMBOL(of_iommu_get_resv_regions);
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index 55c1eb300a86..9a5e6b410dd2 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -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 */
