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
  ...

Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt

@@ -27,6 +27,12 @@ the PCIe specification.
                       * "cmdq-sync" - CMD_SYNC complete
                       * "gerror"    - Global Error activated
 
+- #iommu-cells      : See the generic IOMMU binding described in
+                        devicetree/bindings/pci/pci-iommu.txt
+                      for details. For SMMUv3, must be 1, with each cell
+                      describing a single stream ID. All possible stream
+                      IDs which a device may emit must be described.
+
 ** SMMUv3 optional properties:
 
 - dma-coherent      : Present if DMA operations made by the SMMU (page
@@ -54,6 +60,6 @@ the PCIe specification.
                              <GIC_SPI 79 IRQ_TYPE_EDGE_RISING>;
                 interrupt-names = "eventq", "priq", "cmdq-sync", "gerror";
                 dma-coherent;
-                #iommu-cells = <0>;
+                #iommu-cells = <1>;
                 msi-parent = <&its 0xff0000>;
         };

Documentation/devicetree/bindings/iommu/arm,smmu.txt

@@ -35,12 +35,16 @@ conditions.
                   interrupt per context bank. In the case of a single,
                   combined interrupt, it must be listed multiple times.
 
-- mmu-masters   : A list of phandles to device nodes representing bus
-                  masters for which the SMMU can provide a translation
-                  and their corresponding StreamIDs (see example below).
-                  Each device node linked from this list must have a
-                  "#stream-id-cells" property, indicating the number of
-                  StreamIDs associated with it.
+- #iommu-cells  : See Documentation/devicetree/bindings/iommu/iommu.txt
+                  for details. With a value of 1, each "iommus" entry
+                  represents a distinct stream ID emitted by that device
+                  into the relevant SMMU.
+
+                  SMMUs with stream matching support and complex masters
+                  may use a value of 2, where the second cell represents
+                  an SMR mask to combine with the ID in the first cell.
+                  Care must be taken to ensure the set of matched IDs
+                  does not result in conflicts.
 
 ** System MMU optional properties:
 
@@ -56,9 +60,20 @@ conditions.
                   aliases of secure registers have to be used during
                   SMMU configuration.
 
-Example:
+** Deprecated properties:
+
+- mmu-masters (deprecated in favour of the generic "iommus" binding) :
+                  A list of phandles to device nodes representing bus
+                  masters for which the SMMU can provide a translation
+                  and their corresponding Stream IDs. Each device node
+                  linked from this list must have a "#stream-id-cells"
+                  property, indicating the number of Stream ID
+                  arguments associated with its phandle.
 
-        smmu {
+** Examples:
+
+        /* SMMU with stream matching or stream indexing */
+        smmu1: iommu {
                 compatible = "arm,smmu-v1";
                 reg = <0xba5e0000 0x10000>;
                 #global-interrupts = <2>;
@@ -68,11 +83,29 @@ Example:
                              <0 35 4>,
                              <0 36 4>,
                              <0 37 4>;
+                #iommu-cells = <1>;
+        };
+
+        /* device with two stream IDs, 0 and 7 */
+        master1 {
+                iommus = <&smmu1 0>,
+                         <&smmu1 7>;
+        };
+
+
+        /* SMMU with stream matching */
+        smmu2: iommu {
+                ...
+                #iommu-cells = <2>;
+        };
+
+        /* device with stream IDs 0 and 7 */
+        master2 {
+                iommus = <&smmu2 0 0>,
+                         <&smmu2 7 0>;
+        };
 
-                /*
-                 * Two DMA controllers, the first with two StreamIDs (0xd01d
-                 * and 0xd01e) and the second with only one (0xd11c).
-                 */
-                mmu-masters = <&dma0 0xd01d 0xd01e>,
-                              <&dma1 0xd11c>;
+        /* device with stream IDs 1, 17, 33 and 49 */
+        master3 {
+                iommus = <&smmu2 1 0x30>;
         };

Documentation/devicetree/bindings/pci/pci-iommu.txt

@@ -0,0 +1,171 @@
+This document describes the generic device tree binding for describing the
+relationship between PCI(e) devices and IOMMU(s).
+
+Each PCI(e) device under a root complex is uniquely identified by its Requester
+ID (AKA RID). A Requester ID is a triplet of a Bus number, Device number, and
+Function number.
+
+For the purpose of this document, when treated as a numeric value, a RID is
+formatted such that:
+
+* Bits [15:8] are the Bus number.
+* Bits [7:3] are the Device number.
+* Bits [2:0] are the Function number.
+* Any other bits required for padding must be zero.
+
+IOMMUs may distinguish PCI devices through sideband data derived from the
+Requester ID. While a given PCI device can only master through one IOMMU, a
+root complex may split masters across a set of IOMMUs (e.g. with one IOMMU per
+bus).
+
+The generic 'iommus' property is insufficient to describe this relationship,
+and a mechanism is required to map from a PCI device to its IOMMU and sideband
+data.
+
+For generic IOMMU bindings, see
+Documentation/devicetree/bindings/iommu/iommu.txt.
+
+
+PCI root complex
+================
+
+Optional properties
+-------------------
+
+- iommu-map: Maps a Requester ID to an IOMMU and associated iommu-specifier
+  data.
+
+  The property is an arbitrary number of tuples of
+  (rid-base,iommu,iommu-base,length).
+
+  Any RID r in the interval [rid-base, rid-base + length) is associated with
+  the listed IOMMU, with the iommu-specifier (r - rid-base + iommu-base).
+
+- iommu-map-mask: A mask to be applied to each Requester ID prior to being
+  mapped to an iommu-specifier per the iommu-map property.
+
+
+Example (1)
+===========
+
+/ {
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	iommu: iommu@a {
+		reg = <0xa 0x1>;
+		compatible = "vendor,some-iommu";
+		#iommu-cells = <1>;
+	};
+
+	pci: pci@f {
+		reg = <0xf 0x1>;
+		compatible = "vendor,pcie-root-complex";
+		device_type = "pci";
+
+		/*
+		 * The sideband data provided to the IOMMU is the RID,
+		 * identity-mapped.
+		 */
+		iommu-map = <0x0 &iommu 0x0 0x10000>;
+	};
+};
+
+
+Example (2)
+===========
+
+/ {
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	iommu: iommu@a {
+		reg = <0xa 0x1>;
+		compatible = "vendor,some-iommu";
+		#iommu-cells = <1>;
+	};
+
+	pci: pci@f {
+		reg = <0xf 0x1>;
+		compatible = "vendor,pcie-root-complex";
+		device_type = "pci";
+
+		/*
+		 * The sideband data provided to the IOMMU is the RID with the
+		 * function bits masked out.
+		 */
+		iommu-map = <0x0 &iommu 0x0 0x10000>;
+		iommu-map-mask = <0xfff8>;
+	};
+};
+
+
+Example (3)
+===========
+
+/ {
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	iommu: iommu@a {
+		reg = <0xa 0x1>;
+		compatible = "vendor,some-iommu";
+		#iommu-cells = <1>;
+	};
+
+	pci: pci@f {
+		reg = <0xf 0x1>;
+		compatible = "vendor,pcie-root-complex";
+		device_type = "pci";
+
+		/*
+		 * The sideband data provided to the IOMMU is the RID,
+		 * but the high bits of the bus number are flipped.
+		 */
+		iommu-map = <0x0000 &iommu 0x8000 0x8000>,
+			    <0x8000 &iommu 0x0000 0x8000>;
+	};
+};
+
+
+Example (4)
+===========
+
+/ {
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	iommu_a: iommu@a {
+		reg = <0xa 0x1>;
+		compatible = "vendor,some-iommu";
+		#iommu-cells = <1>;
+	};
+
+	iommu_b: iommu@b {
+		reg = <0xb 0x1>;
+		compatible = "vendor,some-iommu";
+		#iommu-cells = <1>;
+	};
+
+	iommu_c: iommu@c {
+		reg = <0xc 0x1>;
+		compatible = "vendor,some-iommu";
+		#iommu-cells = <1>;
+	};
+
+	pci: pci@f {
+		reg = <0xf 0x1>;
+		compatible = "vendor,pcie-root-complex";
+		device_type = "pci";
+
+		/*
+		 * Devices with bus number 0-127 are mastered via IOMMU
+		 * a, with sideband data being RID[14:0].
+		 * Devices with bus number 128-255 are mastered via
+		 * IOMMU b, with sideband data being RID[14:0].
+		 * No devices master via IOMMU c.
+		 */
+		iommu-map = <0x0000 &iommu_a 0x0000 0x8000>,
+			    <0x8000 &iommu_b 0x0000 0x8000>;
+	};
+};

arch/arm64/mm/dma-mapping.c

@@ -828,7 +828,7 @@ static bool do_iommu_attach(struct device *dev, const struct iommu_ops *ops,
 	 * then the IOMMU core will have already configured a group for this
 	 * device, and allocated the default domain for that group.
 	 */
-	if (!domain || iommu_dma_init_domain(domain, dma_base, size)) {
+	if (!domain || iommu_dma_init_domain(domain, dma_base, size, dev)) {
 		pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
 			dev_name(dev));
 		return false;

arch/x86/configs/x86_64_defconfig

@@ -255,7 +255,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_DMADEVICES=y
 CONFIG_EEEPC_LAPTOP=y
 CONFIG_AMD_IOMMU=y
-CONFIG_AMD_IOMMU_STATS=y
 CONFIG_INTEL_IOMMU=y
 # CONFIG_INTEL_IOMMU_DEFAULT_ON is not set
 CONFIG_EFI_VARS=y

drivers/gpu/drm/exynos/exynos_drm_iommu.h

@@ -66,7 +66,7 @@ static inline int __exynos_iommu_create_mapping(struct exynos_drm_private *priv,
 	if (ret)
 		goto free_domain;
 
-	ret = iommu_dma_init_domain(domain, start, size);
+	ret = iommu_dma_init_domain(domain, start, size, NULL);
 	if (ret)
 		goto put_cookie;
 

drivers/iommu/Kconfig

@@ -309,7 +309,7 @@ config ARM_SMMU
 
 config ARM_SMMU_V3
 	bool "ARM Ltd. System MMU Version 3 (SMMUv3) Support"
-	depends on ARM64 && PCI
+	depends on ARM64
 	select IOMMU_API
 	select IOMMU_IO_PGTABLE_LPAE
 	select GENERIC_MSI_IRQ_DOMAIN

drivers/iommu/amd_iommu.c

@@ -103,7 +103,7 @@ struct flush_queue {
 	struct flush_queue_entry *entries;
 };
 
-DEFINE_PER_CPU(struct flush_queue, flush_queue);
+static DEFINE_PER_CPU(struct flush_queue, flush_queue);
 
 static atomic_t queue_timer_on;
 static struct timer_list queue_timer;
@@ -1361,7 +1361,8 @@ static u64 *alloc_pte(struct protection_domain *domain,
 
 			__npte = PM_LEVEL_PDE(level, virt_to_phys(page));
 
-			if (cmpxchg64(pte, __pte, __npte)) {
+			/* pte could have been changed somewhere. */
+			if (cmpxchg64(pte, __pte, __npte) != __pte) {
 				free_page((unsigned long)page);
 				continue;
 			}
@@ -1741,6 +1742,9 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom)
 
 	free_pagetable(&dom->domain);
 
+	if (dom->domain.id)
+		domain_id_free(dom->domain.id);
+
 	kfree(dom);
 }
 
@@ -3649,7 +3653,7 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
 
 	table = irq_lookup_table[devid];
 	if (table)
-		goto out;
+		goto out_unlock;
 
 	alias = amd_iommu_alias_table[devid];
 	table = irq_lookup_table[alias];
@@ -3663,7 +3667,7 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
 	/* Nothing there yet, allocate new irq remapping table */
 	table = kzalloc(sizeof(*table), GFP_ATOMIC);
 	if (!table)
-		goto out;
+		goto out_unlock;
 
 	/* Initialize table spin-lock */
 	spin_lock_init(&table->lock);
@@ -3676,7 +3680,7 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
 	if (!table->table) {
 		kfree(table);
 		table = NULL;
-		goto out;
+		goto out_unlock;
 	}
 
 	if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
@@ -4153,6 +4157,7 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 	}
 	if (index < 0) {
 		pr_warn("Failed to allocate IRTE\n");
+		ret = index;
 		goto out_free_parent;
 	}
 

drivers/iommu/amd_iommu_init.c

@@ -20,6 +20,7 @@
 #include <linux/pci.h>
 #include <linux/acpi.h>
 #include <linux/list.h>
+#include <linux/bitmap.h>
 #include <linux/slab.h>
 #include <linux/syscore_ops.h>
 #include <linux/interrupt.h>
@@ -2285,7 +2286,7 @@ static int __init early_amd_iommu_init(void)
 	 * never allocate domain 0 because its used as the non-allocated and
 	 * error value placeholder
 	 */
-	amd_iommu_pd_alloc_bitmap[0] = 1;
+	__set_bit(0, amd_iommu_pd_alloc_bitmap);
 
 	spin_lock_init(&amd_iommu_pd_lock);