iommu/arm: Introduce iommu_add_dt_pci_sideband_ids API

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>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Acked-by: Jan Beulich <jbeulich@suse.com>

xen/arch/arm/include/asm/iommu.h

@@ -34,6 +34,21 @@ int __must_check arm_iommu_unmap_page(struct domain *d, dfn_t dfn,
                                       unsigned int order,
                                       unsigned int *flush_flags);
 
+/*
+ * This function is not strictly ARM-specific, but it is only used by ARM
+ * as of now. So put it here to avoid creating dead code on other
+ * architectures. When usage is extended to other architectures, it should
+ * be moved to the generic header.
+ *
+ *
+ * Fills out the device's IOMMU fwspec with IOMMU ids.
+ *
+ * Return values:
+ *  0 : iommu_fwspec is filled out successfully.
+ * <0 : error while filling out the iommu_fwspec.
+ * >0 : IOMMU is not enabled/present or device is not connected to it.
+ */
+int iommu_add_pci_sideband_ids(struct pci_dev *pdev);
 #endif /* __ARCH_ARM_IOMMU_H__ */
 
 /*

xen/common/device-tree/device-tree.c

@@ -7,6 +7,7 @@
  * benh@kernel.crashing.org
  */
 
+#include <xen/bitops.h>
 #include <xen/types.h>
 #include <xen/init.h>
 #include <xen/guest_access.h>
@@ -2221,6 +2222,96 @@ 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_cpu(*(map + 0));
+        uint32_t phandle = be32_to_cpu(*(map + 1));
+        uint32_t out_base = be32_to_cpu(*(map + 2));
+        uint32_t id_len = be32_to_cpu(*(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

xen/drivers/passthrough/arm/iommu.c

@@ -15,6 +15,7 @@
  * GNU General Public License for more details.
  */
 
+#include <xen/acpi.h>
 #include <xen/device_tree.h>
 #include <xen/iommu.h>
 #include <xen/lib.h>
@@ -151,3 +152,15 @@ bool arch_iommu_use_permitted(const struct domain *d)
 {
     return true;
 }
+
+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;
+}

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 1;
+
+    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) ? 1 : 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();

xen/include/xen/device_tree.h

@@ -959,6 +959,29 @@ 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);
 
 void device_tree_get_reg(const __be32 **cell, uint32_t address_cells,

xen/include/xen/iommu.h

@@ -241,7 +241,8 @@ 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
@@ -251,6 +252,19 @@ int iommu_release_dt_devices(struct domain *d);
  */
 int iommu_add_dt_device(struct dt_device_node *np);
 
+/*
+ * Fills out the device's IOMMU fwspec with IOMMU ids from the DT.
+ * Ids are specified in the iommu-map property in the host bridge node.
+ * More information on the iommu-map property format can be found in
+ * Documentation/devicetree/bindings/pci/pci-iommu.txt from Linux.
+ *
+ * Return values:
+ *  0 : iommu_fwspec is filled out successfully.
+ * <0 : error while filling out the iommu_fwspec.
+ * >0 : IOMMU is not enabled/present or device is not connected to it.
+ */
+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);
 
@@ -286,6 +300,11 @@ static inline int iommu_release_dt_devices(struct domain *d)
     return 0;
 }
 
+static inline int iommu_add_dt_pci_sideband_ids(struct pci_dev *pdev)
+{
+    return -EOPNOTSUPP;
+}
+
 #endif /* HAS_PASSTHROUGH */
 
 #endif /* HAS_DEVICE_TREE */