Merge tag 'iommu-updates-v4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:

 - support for interrupt virtualization in the AMD IOMMU driver. These
   patches were shared with the KVM tree and are already merged through
   that tree.

 - generic DT-binding support for the ARM-SMMU driver. With this the
   driver now makes use of the generic DMA-API code. This also required
   some changes outside of the IOMMU code, but these are acked by the
   respective maintainers.

 - more cleanups and fixes all over the place.

* tag 'iommu-updates-v4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (40 commits)
  iommu/amd: No need to wait iommu completion if no dte irq entry change
  iommu/amd: Free domain id when free a domain of struct dma_ops_domain
  iommu/amd: Use standard bitmap operation to set bitmap
  iommu/amd: Clean up the cmpxchg64 invocation
  iommu/io-pgtable-arm: Check for v7s-incapable systems
  iommu/dma: Avoid PCI host bridge windows
  iommu/dma: Add support for mapping MSIs
  iommu/arm-smmu: Set domain geometry
  iommu/arm-smmu: Wire up generic configuration support
  Docs: dt: document ARM SMMU generic binding usage
  iommu/arm-smmu: Convert to iommu_fwspec
  iommu/arm-smmu: Intelligent SMR allocation
  iommu/arm-smmu: Add a stream map entry iterator
  iommu/arm-smmu: Streamline SMMU data lookups
  iommu/arm-smmu: Refactor mmu-masters handling
  iommu/arm-smmu: Keep track of S2CR state
  iommu/arm-smmu: Consolidate stream map entry state
  iommu/arm-smmu: Handle stream IDs more dynamically
  iommu/arm-smmu: Set PRIVCFG in stage 1 STEs
  iommu/arm-smmu: Support non-PCI devices with SMMUv3
  ...

2 files changed, 106 insertions, 74 deletions

diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index a2e68f740eda..393fea85eb4e 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
+#include <linux/of_pci.h>
 #include <linux/string.h>
 #include <linux/slab.h>
 
@@ -592,87 +593,16 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np,
 			    u32 rid_in)
 {
 	struct device *parent_dev;
-	struct device_node *msi_controller_node;
-	struct device_node *msi_np = *np;
-	u32 map_mask, masked_rid, rid_base, msi_base, rid_len, phandle;
-	int msi_map_len;
-	bool matched;
 	u32 rid_out = rid_in;
-	const __be32 *msi_map = NULL;
 
 	/*
 	 * Walk up the device parent links looking for one with a
 	 * "msi-map" property.
 	 */
-	for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent) {
-		if (!parent_dev->of_node)
-			continue;
-
-		msi_map = of_get_property(parent_dev->of_node,
-					  "msi-map", &msi_map_len);
-		if (!msi_map)
-			continue;
-
-		if (msi_map_len % (4 * sizeof(__be32))) {
-			dev_err(parent_dev, "Error: Bad msi-map length: %d\n",
-				msi_map_len);
-			return rid_out;
-		}
-		/* We have a good parent_dev and msi_map, let's use them. */
-		break;
-	}
-	if (!msi_map)
-		return rid_out;
-
-	/* The default is to select all bits. */
-	map_mask = 0xffffffff;
-
-	/*
-	 * Can be overridden by "msi-map-mask" property.  If
-	 * of_property_read_u32() fails, the default is used.
-	 */
-	of_property_read_u32(parent_dev->of_node, "msi-map-mask", &map_mask);
-
-	masked_rid = map_mask & rid_in;
-	matched = false;
-	while (!matched && msi_map_len >= 4 * sizeof(__be32)) {
-		rid_base = be32_to_cpup(msi_map + 0);
-		phandle = be32_to_cpup(msi_map + 1);
-		msi_base = be32_to_cpup(msi_map + 2);
-		rid_len = be32_to_cpup(msi_map + 3);
-
-		if (rid_base & ~map_mask) {
-			dev_err(parent_dev,
-				"Invalid msi-map translation - msi-map-mask (0x%x) ignores rid-base (0x%x)\n",
-				map_mask, rid_base);
-			return rid_out;
-		}
-
-		msi_controller_node = of_find_node_by_phandle(phandle);
-
-		matched = (masked_rid >= rid_base &&
-			   masked_rid < rid_base + rid_len);
-		if (msi_np)
-			matched &= msi_np == msi_controller_node;
-
-		if (matched && !msi_np) {
-			*np = msi_np = msi_controller_node;
+	for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent)
+		if (!of_pci_map_rid(parent_dev->of_node, rid_in, "msi-map",
+				    "msi-map-mask", np, &rid_out))
 			break;
-		}
-
-		of_node_put(msi_controller_node);
-		msi_map_len -= 4 * sizeof(__be32);
-		msi_map += 4;
-	}
-	if (!matched)
-		return rid_out;
-
-	rid_out = masked_rid - rid_base + msi_base;
-	dev_dbg(dev,
-		"msi-map at: %s, using mask %08x, rid-base: %08x, msi-base: %08x, length: %08x, rid: %08x -> %08x\n",
-		dev_name(parent_dev), map_mask, rid_base, msi_base,
-		rid_len, rid_in, rid_out);
-
 	return rid_out;
 }
 
diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c
index 589b30c68e14..b58be12ab277 100644
--- a/drivers/of/of_pci.c
+++ b/drivers/of/of_pci.c
@@ -308,3 +308,105 @@ struct msi_controller *of_pci_find_msi_chip_by_node(struct device_node *of_node)
 EXPORT_SYMBOL_GPL(of_pci_find_msi_chip_by_node);
 
 #endif /* CONFIG_PCI_MSI */
+
+/**
+ * of_pci_map_rid - Translate a requester ID through a downstream mapping.
+ * @np: root complex device node.
+ * @rid: PCI requester 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 PCI requester 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 of_pci_map_rid(struct device_node *np, u32 rid,
+		   const char *map_name, const char *map_mask_name,
+		   struct device_node **target, u32 *id_out)
+{
+	u32 map_mask, masked_rid;
+	int map_len;
+	const __be32 *map = NULL;
+
+	if (!np || !map_name || (!target && !id_out))
+		return -EINVAL;
+
+	map = of_get_property(np, map_name, &map_len);
+	if (!map) {
+		if (target)
+			return -ENODEV;
+		/* Otherwise, no map implies no translation */
+		*id_out = rid;
+		return 0;
+	}
+
+	if (!map_len || map_len % (4 * sizeof(*map))) {
+		pr_err("%s: Error: Bad %s length: %d\n", np->full_name,
+			map_name, map_len);
+		return -EINVAL;
+	}
+
+	/* The default is to select all bits. */
+	map_mask = 0xffffffff;
+
+	/*
+	 * Can be overridden by "{iommu,msi}-map-mask" property.
+	 * If of_property_read_u32() fails, the default is used.
+	 */
+	if (map_mask_name)
+		of_property_read_u32(np, map_mask_name, &map_mask);
+
+	masked_rid = map_mask & rid;
+	for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4) {
+		struct device_node *phandle_node;
+		u32 rid_base = be32_to_cpup(map + 0);
+		u32 phandle = be32_to_cpup(map + 1);
+		u32 out_base = be32_to_cpup(map + 2);
+		u32 rid_len = be32_to_cpup(map + 3);
+
+		if (rid_base & ~map_mask) {
+			pr_err("%s: Invalid %s translation - %s-mask (0x%x) ignores rid-base (0x%x)\n",
+				np->full_name, map_name, map_name,
+				map_mask, rid_base);
+			return -EFAULT;
+		}
+
+		if (masked_rid < rid_base || masked_rid >= rid_base + rid_len)
+			continue;
+
+		phandle_node = of_find_node_by_phandle(phandle);
+		if (!phandle_node)
+			return -ENODEV;
+
+		if (target) {
+			if (*target)
+				of_node_put(phandle_node);
+			else
+				*target = phandle_node;
+
+			if (*target != phandle_node)
+				continue;
+		}
+
+		if (id_out)
+			*id_out = masked_rid - rid_base + out_base;
+
+		pr_debug("%s: %s, using mask %08x, rid-base: %08x, out-base: %08x, length: %08x, rid: %08x -> %08x\n",
+			np->full_name, map_name, map_mask, rid_base, out_base,
+			rid_len, rid, *id_out);
+		return 0;
+	}
+
+	pr_err("%s: Invalid %s translation - no match for rid 0x%x on %s\n",
+		np->full_name, map_name, rid,
+		target && *target ? (*target)->full_name : "any target");
+	return -EFAULT;
+}