From: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
The main purpose of this patch is to add a way to register PCI device
(which is behind the IOMMU) using the generic PCI-IOMMU DT bindings [1]
before assigning that device to a domain.
This behaves similarly to the existing iommu_add_dt_device API, except it
handles PCI devices, and it is to be invoked from the add_device hook in the
SMMU driver.
The function dt_map_id to translate an ID through a downstream mapping
(which is also suitable for mapping Requester ID) was borrowed from Linux
(v5.10-rc6) and updated according to the Xen code base.
[1] https://www.kernel.org/doc/Documentation/devicetree/bindings/pci/pci-iommu.txt
Signed-off-by: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Signed-off-by: Stewart Hildebrand <stewart.hildebrand@amd.com>
Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
---
Regarding pci_for_each_dma_alias question: getting host bridge node
directly seems like a simpler solution with the same result. AFAIU
with pci_for_each_dma_alias in linux we would arrive to the host brige
node anyway, but also try to call dt_map_id for each device along the
way. I am not sure why exactly it is done this way in linux, as
according to the pci-iommu.txt, iommu-map node can only be present in
the PCI root.
v6->v7:
* put iommu_add_pci_sideband_ids under ifdef
* remove ifdef CONFIG_APCI
* style: add newline for symmetry
v5->v6:
* pass ops to iommu_dt_xlate()
v4->v5:
* style: add newlines after variable declarations and before return in iommu.h
* drop device_is_protected() check in iommu_add_dt_pci_sideband_ids()
* rebase on top of ("dynamic node programming using overlay dtbo") series
* fix typo in commit message
* remove #ifdef around dt_map_id() prototype
* move dt_map_id() to xen/common/device_tree.c
* add function name in error prints
* use dprintk for debug prints
* use GENMASK and #include <xen/bitops.h>
* fix typo in comment
* remove unnecessary (int) cast in loop condition
* assign *id_out and return success in case of no translation in dt_map_id()
* don't initialize local variable unnecessarily
* return error in case of ACPI/no DT in iommu_add_{dt_}pci_sideband_ids()
v3->v4:
* wrap #include <asm/acpi.h> and if ( acpi_disabled ) in #ifdef CONFIG_ACPI
* fix Michal's remarks about style, parenthesis, and print formats
* remove !ops->dt_xlate check since it is already in iommu_dt_xlate helper
* rename s/iommu_dt_pci_map_id/dt_map_id/ because it is generic, not specific
to iommu
* update commit description
v2->v3:
* new patch title (was: iommu/arm: Introduce iommu_add_dt_pci_device API)
* renamed function
from: iommu_add_dt_pci_device
to: iommu_add_dt_pci_sideband_ids
* removed stale ops->add_device check
* iommu.h: add empty stub iommu_add_dt_pci_sideband_ids for !HAS_DEVICE_TREE
* iommu.h: add iommu_add_pci_sideband_ids helper
* iommu.h: don't wrap prototype in #ifdef CONFIG_HAS_PCI
* s/iommu_fwspec_free(pci_to_dev(pdev))/iommu_fwspec_free(dev)/
v1->v2:
* remove extra devfn parameter since pdev fully describes the device
* remove ops->add_device() call from iommu_add_dt_pci_device(). Instead, rely on
the existing iommu call in iommu_add_device().
* move the ops->add_device and ops->dt_xlate checks earlier
downstream->v1:
* rebase
* add const qualifier to struct dt_device_node *np arg in dt_map_id()
* add const qualifier to struct dt_device_node *np declaration in iommu_add_pci_device()
* use stdint.h types instead of u8/u32/etc...
* rename functions:
s/dt_iommu_xlate/iommu_dt_xlate/
s/dt_map_id/iommu_dt_pci_map_id/
s/iommu_add_pci_device/iommu_add_dt_pci_device/
* add device_is_protected check in iommu_add_dt_pci_device
* wrap prototypes in CONFIG_HAS_PCI
(cherry picked from commit 734e3bf6ee77e7947667ab8fa96c25b349c2e1da from
the downstream branch poc/pci-passthrough from
https://gitlab.com/xen-project/people/bmarquis/xen-arm-poc.git)
---
xen/common/device-tree/device-tree.c | 91 +++++++++++++++++++++++++++
xen/drivers/passthrough/device_tree.c | 42 +++++++++++++
xen/include/xen/device_tree.h | 23 +++++++
xen/include/xen/iommu.h | 28 ++++++++-
4 files changed, 183 insertions(+), 1 deletion(-)
diff --git a/xen/common/device-tree/device-tree.c b/xen/common/device-tree/device-tree.c
index d0528c5825..3de7858df6 100644
--- a/xen/common/device-tree/device-tree.c
+++ b/xen/common/device-tree/device-tree.c
@@ -10,6 +10,7 @@
* published by the Free Software Foundation.
*/
+#include <xen/bitops.h>
#include <xen/types.h>
#include <xen/init.h>
#include <xen/guest_access.h>
@@ -2243,6 +2244,96 @@ int dt_get_pci_domain_nr(struct dt_device_node *node)
return (u16)domain;
}
+int dt_map_id(const struct dt_device_node *np, uint32_t id,
+ const char *map_name, const char *map_mask_name,
+ struct dt_device_node **target, uint32_t *id_out)
+{
+ uint32_t map_mask, masked_id, map_len;
+ const __be32 *map = NULL;
+
+ if ( !np || !map_name || (!target && !id_out) )
+ return -EINVAL;
+
+ map = dt_get_property(np, map_name, &map_len);
+ if ( !map )
+ {
+ if ( target )
+ return -ENODEV;
+
+ /* Otherwise, no map implies no translation */
+ *id_out = id;
+ return 0;
+ }
+
+ if ( !map_len || (map_len % (4 * sizeof(*map))) )
+ {
+ printk(XENLOG_ERR "%s(): %s: Error: Bad %s length: %u\n", __func__,
+ np->full_name, map_name, map_len);
+ return -EINVAL;
+ }
+
+ /* The default is to select all bits. */
+ map_mask = GENMASK(31, 0);
+
+ /*
+ * Can be overridden by "{iommu,msi}-map-mask" property.
+ * If dt_property_read_u32() fails, the default is used.
+ */
+ if ( map_mask_name )
+ dt_property_read_u32(np, map_mask_name, &map_mask);
+
+ masked_id = map_mask & id;
+ for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4 )
+ {
+ struct dt_device_node *phandle_node;
+ uint32_t id_base = be32_to_cpup(map + 0);
+ uint32_t phandle = be32_to_cpup(map + 1);
+ uint32_t out_base = be32_to_cpup(map + 2);
+ uint32_t id_len = be32_to_cpup(map + 3);
+
+ if ( id_base & ~map_mask )
+ {
+ printk(XENLOG_ERR "%s(): %s: Invalid %s translation - %s-mask (0x%"PRIx32") ignores id-base (0x%"PRIx32")\n",
+ __func__, np->full_name, map_name, map_name, map_mask,
+ id_base);
+ return -EFAULT;
+ }
+
+ if ( (masked_id < id_base) || (masked_id >= (id_base + id_len)) )
+ continue;
+
+ phandle_node = dt_find_node_by_phandle(phandle);
+ if ( !phandle_node )
+ return -ENODEV;
+
+ if ( target )
+ {
+ if ( !*target )
+ *target = phandle_node;
+
+ if ( *target != phandle_node )
+ continue;
+ }
+
+ if ( id_out )
+ *id_out = masked_id - id_base + out_base;
+
+ dprintk(XENLOG_DEBUG, "%s: %s, using mask %08"PRIx32", id-base: %08"PRIx32", out-base: %08"PRIx32", length: %08"PRIx32", id: %08"PRIx32" -> %08"PRIx32"\n",
+ np->full_name, map_name, map_mask, id_base, out_base, id_len, id,
+ masked_id - id_base + out_base);
+ return 0;
+ }
+
+ dprintk(XENLOG_DEBUG, "%s: no %s translation for id 0x%"PRIx32" on %s\n",
+ np->full_name, map_name, id,
+ (target && *target) ? (*target)->full_name : NULL);
+
+ if ( id_out )
+ *id_out = id;
+
+ return 0;
+}
+
/*
* Local variables:
* mode: C
diff --git a/xen/drivers/passthrough/device_tree.c b/xen/drivers/passthrough/device_tree.c
index 4c35281d98..edbd3f17ad 100644
--- a/xen/drivers/passthrough/device_tree.c
+++ b/xen/drivers/passthrough/device_tree.c
@@ -161,6 +161,48 @@ static int iommu_dt_xlate(struct device *dev,
return ops->dt_xlate(dev, iommu_spec);
}
+#ifdef CONFIG_HAS_PCI
+int iommu_add_dt_pci_sideband_ids(struct pci_dev *pdev)
+{
+ const struct iommu_ops *ops = iommu_get_ops();
+ struct dt_phandle_args iommu_spec = { .args_count = 1 };
+ struct device *dev = pci_to_dev(pdev);
+ const struct dt_device_node *np;
+ int rc;
+
+ if ( !iommu_enabled )
+ return NO_IOMMU;
+
+ if ( !ops )
+ return -EINVAL;
+
+ if ( dev_iommu_fwspec_get(dev) )
+ return -EEXIST;
+
+ np = pci_find_host_bridge_node(pdev);
+ if ( !np )
+ return -ENODEV;
+
+ /*
+ * According to the Documentation/devicetree/bindings/pci/pci-iommu.txt
+ * from Linux.
+ */
+ rc = dt_map_id(np, PCI_BDF(pdev->bus, pdev->devfn), "iommu-map",
+ "iommu-map-mask", &iommu_spec.np, iommu_spec.args);
+ if ( rc )
+ return (rc == -ENODEV) ? NO_IOMMU : rc;
+
+ rc = iommu_dt_xlate(dev, &iommu_spec, ops);
+ if ( rc < 0 )
+ {
+ iommu_fwspec_free(dev);
+ return -EINVAL;
+ }
+
+ return rc;
+}
+#endif /* CONFIG_HAS_PCI */
+
int iommu_remove_dt_device(struct dt_device_node *np)
{
const struct iommu_ops *ops = iommu_get_ops();
diff --git a/xen/include/xen/device_tree.h b/xen/include/xen/device_tree.h
index 5ff763bb80..9254204af6 100644
--- a/xen/include/xen/device_tree.h
+++ b/xen/include/xen/device_tree.h
@@ -946,6 +946,29 @@ int dt_count_phandle_with_args(const struct dt_device_node *np,
*/
int dt_get_pci_domain_nr(struct dt_device_node *node);
+/**
+ * dt_map_id - Translate an ID through a downstream mapping.
+ * @np: root complex device node.
+ * @id: device ID to map.
+ * @map_name: property name of the map to use.
+ * @map_mask_name: optional property name of the mask to use.
+ * @target: optional pointer to a target device node.
+ * @id_out: optional pointer to receive the translated ID.
+ *
+ * Given a device ID, look up the appropriate implementation-defined
+ * platform ID and/or the target device which receives transactions on that
+ * ID, as per the "iommu-map" and "msi-map" bindings. Either of @target or
+ * @id_out may be NULL if only the other is required. If @target points to
+ * a non-NULL device node pointer, only entries targeting that node will be
+ * matched; if it points to a NULL value, it will receive the device node of
+ * the first matching target phandle, with a reference held.
+ *
+ * Return: 0 on success or a standard error code on failure.
+ */
+int dt_map_id(const struct dt_device_node *np, uint32_t id,
+ const char *map_name, const char *map_mask_name,
+ struct dt_device_node **target, uint32_t *id_out);
+
struct dt_device_node *dt_find_node_by_phandle(dt_phandle handle);
#ifdef CONFIG_DEVICE_TREE_DEBUG
diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index c3b8df9815..d2b9f04f81 100644
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -27,6 +27,7 @@
#include <xen/errno.h>
#include <public/domctl.h>
#include <public/hvm/ioreq.h>
+#include <xen/acpi.h>
#include <asm/device.h>
TYPE_SAFE(uint64_t, dfn);
@@ -215,7 +216,8 @@ int iommu_dt_domain_init(struct domain *d);
int iommu_release_dt_devices(struct domain *d);
/*
- * Helper to add master device to the IOMMU using generic IOMMU DT bindings.
+ * Helpers to add master device to the IOMMU using generic (PCI-)IOMMU
+ * DT bindings.
*
* Return values:
* 0 : device is protected by an IOMMU
@@ -224,6 +226,7 @@ int iommu_release_dt_devices(struct domain *d);
* (IOMMU is not enabled/present or device is not connected to it).
*/
int iommu_add_dt_device(struct dt_device_node *np);
+int iommu_add_dt_pci_sideband_ids(struct pci_dev *pdev);
int iommu_do_dt_domctl(struct xen_domctl *domctl, struct domain *d,
XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl);
@@ -241,8 +244,31 @@ int iommu_remove_dt_device(struct dt_device_node *np);
/* Error code for reporting no IOMMU is present */
#define NO_IOMMU 1
+#else /* !HAS_DEVICE_TREE */
+static inline int iommu_add_dt_pci_sideband_ids(struct pci_dev *pdev)
+{
+ return -ENOSYS;
+}
+
#endif /* HAS_DEVICE_TREE */
+#ifdef CONFIG_HAS_PCI
+static inline int iommu_add_pci_sideband_ids(struct pci_dev *pdev)
+{
+ int ret = -ENOSYS;
+
+ if ( acpi_disabled )
+ ret = iommu_add_dt_pci_sideband_ids(pdev);
+
+ return ret;
+}
+#else /* !HAS_PCI */
+static inline int iommu_add_pci_sideband_ids(struct pci_dev *pdev)
+{
+ return -ENOSYS;
+}
+#endif
+
struct page_info;
/*
--
2.34.1
On 04.02.2025 14:54, Mykyta Poturai wrote: > --- a/xen/include/xen/iommu.h > +++ b/xen/include/xen/iommu.h > @@ -27,6 +27,7 @@ > #include <xen/errno.h> > #include <public/domctl.h> > #include <public/hvm/ioreq.h> > +#include <xen/acpi.h> > #include <asm/device.h> Please insert where the other xen/ #include-s are. (Those aren't sorted yet, so there is more than one place where you could reasonably put it. I'd recommend ahead of xen/errno.h.) > @@ -241,8 +244,31 @@ int iommu_remove_dt_device(struct dt_device_node *np); > /* Error code for reporting no IOMMU is present */ > #define NO_IOMMU 1 > > +#else /* !HAS_DEVICE_TREE */ > +static inline int iommu_add_dt_pci_sideband_ids(struct pci_dev *pdev) > +{ > + return -ENOSYS; No abuse of ENOSYS please. EOPNOTSUPP if nothing better can be found. > +} > + > #endif /* HAS_DEVICE_TREE */ > > +#ifdef CONFIG_HAS_PCI > +static inline int iommu_add_pci_sideband_ids(struct pci_dev *pdev) From its name it's unclear whether the function actually means to alter the passed in pdev (my initial guess was that it wouldn't, but the call tree from iommu_add_dt_pci_sideband_ids() is getting deep-ish). If not, the parameter should be pointer-to-const. > +{ > + int ret = -ENOSYS; > + > + if ( acpi_disabled ) > + ret = iommu_add_dt_pci_sideband_ids(pdev); > + > + return ret; > +} > +#else /* !HAS_PCI */ > +static inline int iommu_add_pci_sideband_ids(struct pci_dev *pdev) > +{ > + return -ENOSYS; > +} > +#endif Why the redundancy? static inline int iommu_add_pci_sideband_ids(struct pci_dev *pdev) { int ret = -EOPNOTSUPP; #ifdef CONFIG_HAS_PCI if ( acpi_disabled ) ret = iommu_add_dt_pci_sideband_ids(pdev); #endif return ret; } Jan
© 2016 - 2025 Red Hat, Inc.