virtio, vhost: fixes, features, performance

new iommu device
 vhost guest memory access using vmap (just meta-data for now)
 minor fixes
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 
 Note: due to code driver changes the driver-core tree, the following
 patch is needed when merging tree with commit 92ce7e83b4
 ("driver_find_device: Unify the match function with
 class_find_device()") in the driver-core tree:
 
 From: Nathan Chancellor <natechancellor@gmail.com>
 Subject: [PATCH] iommu/virtio: Constify data parameter in viommu_match_node
 
 After commit 92ce7e83b4 ("driver_find_device: Unify the match
 function with class_find_device()") in the driver-core tree.
 
 Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 
 ---
  drivers/iommu/virtio-iommu.c | 2 +-
  1 file changed, 1 insertion(+), 1 deletion(-)
 
 diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
 index 4620dd221ffd..433f4d2ee956 100644
 --- a/drivers/iommu/virtio-iommu.c
 +++ b/drivers/iommu/virtio-iommu.c
 @@ -839,7 +839,7 @@ static void viommu_put_resv_regions(struct device *dev, struct list_head *head)
  static struct iommu_ops viommu_ops;
  static struct virtio_driver virtio_iommu_drv;
 
 -static int viommu_match_node(struct device *dev, void *data)
 +static int viommu_match_node(struct device *dev, const void *data)
  {
  	return dev->parent->fwnode == data;
  }
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJdJ5qUAAoJECgfDbjSjVRpQs0H/2qWcIG1zjGKyh9KWrfgOusG
 /QIqeP50d7SC6oqdyd00tzmExqO1xdGLPFzYixdOsU817te1gHBP4Rfmzo01jZRd
 CUzZNnZQ2JRsDshiA6G2ui+wn1/a/cB3RPN4rT1mquDYS53QmsRGDQDnpp84TXMV
 aocB8TS6halbRzKMq3VmaWHIvzNXnt4dwQR542+PyeLLn9bUx2QwWj2ON3QwxixK
 dVRZow3GwLGBhKTA/Z1Z/Bta4fEfOKjUGP2XWgvL6zOr+nZR4eQ8w5WXVJYzR+d6
 1JCfqTxleweT2k6Tu5VwtTNlQkxn/XvQAeisppOiEE6NnPjubyI9wMQIvL7bkpo=
 =uJbC
 -----END PGP SIGNATURE-----

Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio, vhost updates from Michael Tsirkin:
 "Fixes, features, performance:

   - new iommu device

   - vhost guest memory access using vmap (just meta-data for now)

   - minor fixes"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio-mmio: add error check for platform_get_irq
  scsi: virtio_scsi: Use struct_size() helper
  iommu/virtio: Add event queue
  iommu/virtio: Add probe request
  iommu: Add virtio-iommu driver
  PCI: OF: Initialize dev->fwnode appropriately
  of: Allow the iommu-map property to omit untranslated devices
  dt-bindings: virtio: Add virtio-pci-iommu node
  dt-bindings: virtio-mmio: Add IOMMU description
  vhost: fix clang build warning
  vhost: access vq metadata through kernel virtual address
  vhost: factor out setting vring addr and num
  vhost: introduce helpers to get the size of metadata area
  vhost: rename vq_iotlb_prefetch() to vq_meta_prefetch()
  vhost: fine grain userspace memory accessors
  vhost: generalize adding used elem

Documentation/devicetree/bindings/virtio/iommu.txt

@@ -0,0 +1,66 @@
+* virtio IOMMU PCI device
+
+When virtio-iommu uses the PCI transport, its programming interface is
+discovered dynamically by the PCI probing infrastructure. However the
+device tree statically describes the relation between IOMMU and DMA
+masters. Therefore, the PCI root complex that hosts the virtio-iommu
+contains a child node representing the IOMMU device explicitly.
+
+Required properties:
+
+- compatible:	Should be "virtio,pci-iommu"
+- reg:		PCI address of the IOMMU. As defined in the PCI Bus
+		Binding reference [1], the reg property is a five-cell
+		address encoded as (phys.hi phys.mid phys.lo size.hi
+		size.lo). phys.hi should contain the device's BDF as
+		0b00000000 bbbbbbbb dddddfff 00000000. The other cells
+		should be zero.
+- #iommu-cells:	Each platform DMA master managed by the IOMMU is assigned
+		an endpoint ID, described by the "iommus" property [2].
+		For virtio-iommu, #iommu-cells must be 1.
+
+Notes:
+
+- DMA from the IOMMU device isn't managed by another IOMMU. Therefore the
+  virtio-iommu node doesn't have an "iommus" property, and is omitted from
+  the iommu-map property of the root complex.
+
+Example:
+
+pcie@10000000 {
+	compatible = "pci-host-ecam-generic";
+	...
+
+	/* The IOMMU programming interface uses slot 00:01.0 */
+	iommu0: iommu@0008 {
+		compatible = "virtio,pci-iommu";
+		reg = <0x00000800 0 0 0 0>;
+		#iommu-cells = <1>;
+	};
+
+	/*
+	 * The IOMMU manages all functions in this PCI domain except
+	 * itself. Omit BDF 00:01.0.
+	 */
+	iommu-map = <0x0 &iommu0 0x0 0x8>
+		    <0x9 &iommu0 0x9 0xfff7>;
+};
+
+pcie@20000000 {
+	compatible = "pci-host-ecam-generic";
+	...
+	/*
+	 * The IOMMU also manages all functions from this domain,
+	 * with endpoint IDs 0x10000 - 0x1ffff
+	 */
+	iommu-map = <0x0 &iommu0 0x10000 0x10000>;
+};
+
+ethernet@fe001000 {
+	...
+	/* The IOMMU manages this platform device with endpoint ID 0x20000 */
+	iommus = <&iommu0 0x20000>;
+};
+
+[1] Documentation/devicetree/bindings/pci/pci.txt
+[2] Documentation/devicetree/bindings/iommu/iommu.txt

Documentation/devicetree/bindings/virtio/mmio.txt

@@ -8,10 +8,40 @@ Required properties:
 - reg:		control registers base address and size including configuration space
 - interrupts:	interrupt generated by the device
 
+Required properties for virtio-iommu:
+
+- #iommu-cells:	When the node corresponds to a virtio-iommu device, it is
+		linked to DMA masters using the "iommus" or "iommu-map"
+		properties [1][2]. #iommu-cells specifies the size of the
+		"iommus" property. For virtio-iommu #iommu-cells must be
+		1, each cell describing a single endpoint ID.
+
+Optional properties:
+
+- iommus:	If the device accesses memory through an IOMMU, it should
+		have an "iommus" property [1]. Since virtio-iommu itself
+		does not access memory through an IOMMU, the "virtio,mmio"
+		node cannot have both an "#iommu-cells" and an "iommus"
+		property.
+
 Example:
 
 	virtio_block@3000 {
 		compatible = "virtio,mmio";
 		reg = <0x3000 0x100>;
 		interrupts = <41>;
+
+		/* Device has endpoint ID 23 */
+		iommus = <&viommu 23>
 	}
+
+	viommu: iommu@3100 {
+		compatible = "virtio,mmio";
+		reg = <0x3100 0x100>;
+		interrupts = <42>;
+
+		#iommu-cells = <1>
+	}
+
+[1] Documentation/devicetree/bindings/iommu/iommu.txt
+[2] Documentation/devicetree/bindings/pci/pci-iommu.txt

MAINTAINERS

@@ -17107,6 +17107,13 @@ S:	Maintained
 F:	drivers/virtio/virtio_input.c
 F:	include/uapi/linux/virtio_input.h
 
+VIRTIO IOMMU DRIVER
+M:	Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
+L:	virtualization@lists.linux-foundation.org
+S:	Maintained
+F:	drivers/iommu/virtio-iommu.c
+F:	include/uapi/linux/virtio_iommu.h
+
 VIRTUAL BOX GUEST DEVICE DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>
 M:	Arnd Bergmann <arnd@arndb.de>

drivers/iommu/Kconfig

@@ -473,4 +473,15 @@ config HYPERV_IOMMU
 	  Stub IOMMU driver to handle IRQs as to allow Hyper-V Linux
 	  guests to run with x2APIC mode enabled.
 
+config VIRTIO_IOMMU
+	bool "Virtio IOMMU driver"
+	depends on VIRTIO=y
+	depends on ARM64
+	select IOMMU_API
+	select INTERVAL_TREE
+	help
+	  Para-virtualised IOMMU driver with virtio.
+
+	  Say Y here if you intend to run this kernel as a guest.
+
 endif # IOMMU_SUPPORT

drivers/iommu/Makefile

@@ -33,3 +33,4 @@ obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o
 obj-$(CONFIG_S390_IOMMU) += s390-iommu.o
 obj-$(CONFIG_QCOM_IOMMU) += qcom_iommu.o
 obj-$(CONFIG_HYPERV_IOMMU) += hyperv-iommu.o
+obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o

drivers/of/base.c

@@ -2294,8 +2294,12 @@ int of_map_rid(struct device_node *np, u32 rid,
 		return 0;
 	}
 
-	pr_err("%pOF: Invalid %s translation - no match for rid 0x%x on %pOF\n",
-		np, map_name, rid, target && *target ? *target : NULL);
-	return -EFAULT;
+	pr_info("%pOF: no %s translation for rid 0x%x on %pOF\n", np, map_name,
+		rid, target && *target ? *target : NULL);
+
+	/* Bypasses translation */
+	if (id_out)
+		*id_out = rid;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(of_map_rid);

drivers/pci/of.c

@@ -22,12 +22,15 @@ void pci_set_of_node(struct pci_dev *dev)
 		return;
 	dev->dev.of_node = of_pci_find_child_device(dev->bus->dev.of_node,
 						    dev->devfn);
+	if (dev->dev.of_node)
+		dev->dev.fwnode = &dev->dev.of_node->fwnode;
 }
 
 void pci_release_of_node(struct pci_dev *dev)
 {
 	of_node_put(dev->dev.of_node);
 	dev->dev.of_node = NULL;
+	dev->dev.fwnode = NULL;
 }
 
 void pci_set_bus_of_node(struct pci_bus *bus)
@@ -41,13 +44,18 @@ void pci_set_bus_of_node(struct pci_bus *bus)
 		if (node && of_property_read_bool(node, "external-facing"))
 			bus->self->untrusted = true;
 	}
+
 	bus->dev.of_node = node;
+
+	if (bus->dev.of_node)
+		bus->dev.fwnode = &bus->dev.of_node->fwnode;
 }
 
 void pci_release_bus_of_node(struct pci_bus *bus)
 {
 	of_node_put(bus->dev.of_node);
 	bus->dev.of_node = NULL;
+	bus->dev.fwnode = NULL;
 }
 
 struct device_node * __weak pcibios_get_phb_of_node(struct pci_bus *bus)

drivers/scsi/virtio_scsi.c

@@ -792,7 +792,7 @@ static int virtscsi_probe(struct virtio_device *vdev)
 	num_targets = virtscsi_config_get(vdev, max_target) + 1;
 
 	shost = scsi_host_alloc(&virtscsi_host_template,
-		sizeof(*vscsi) + sizeof(vscsi->req_vqs[0]) * num_queues);
+				struct_size(vscsi, req_vqs, num_queues));
 	if (!shost)
 		return -ENOMEM;
 

drivers/vhost/net.c

@@ -956,7 +956,7 @@ static void handle_tx(struct vhost_net *net)
 	if (!sock)
 		goto out;
 
-	if (!vq_iotlb_prefetch(vq))
+	if (!vq_meta_prefetch(vq))
 		goto out;
 
 	vhost_disable_notify(&net->dev, vq);
@@ -1125,7 +1125,7 @@ static void handle_rx(struct vhost_net *net)
 	if (!sock)
 		goto out;
 
-	if (!vq_iotlb_prefetch(vq))
+	if (!vq_meta_prefetch(vq))
 		goto out;
 
 	vhost_disable_notify(&net->dev, vq);

drivers/vhost/vhost.h

@@ -12,6 +12,9 @@
 #include <linux/virtio_config.h>
 #include <linux/virtio_ring.h>
 #include <linux/atomic.h>
+#include <linux/pagemap.h>
+#include <linux/mmu_notifier.h>
+#include <asm/cacheflush.h>
 
 struct vhost_work;
 typedef void (*vhost_work_fn_t)(struct vhost_work *work);
@@ -80,6 +83,24 @@ enum vhost_uaddr_type {
 	VHOST_NUM_ADDRS = 3,
 };
 
+struct vhost_map {
+	int npages;
+	void *addr;
+	struct page **pages;
+};
+
+struct vhost_uaddr {
+	unsigned long uaddr;
+	size_t size;
+	bool write;
+};
+
+#if defined(CONFIG_MMU_NOTIFIER) && ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+#define VHOST_ARCH_CAN_ACCEL_UACCESS 1
+#else
+#define VHOST_ARCH_CAN_ACCEL_UACCESS 0
+#endif
+
 /* The virtqueue structure describes a queue attached to a device. */
 struct vhost_virtqueue {
 	struct vhost_dev *dev;
@@ -90,7 +111,22 @@ struct vhost_virtqueue {
 	struct vring_desc __user *desc;
 	struct vring_avail __user *avail;
 	struct vring_used __user *used;
+
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	/* Read by memory accessors, modified by meta data
+	 * prefetching, MMU notifier and vring ioctl().
+	 * Synchonrized through mmu_lock (writers) and RCU (writers
+	 * and readers).
+	 */
+	struct vhost_map __rcu *maps[VHOST_NUM_ADDRS];
+	/* Read by MMU notifier, modified by vring ioctl(),
+	 * synchronized through MMU notifier
+	 * registering/unregistering.
+	 */
+	struct vhost_uaddr uaddrs[VHOST_NUM_ADDRS];
+#endif
 	const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
+
 	struct file *kick;
 	struct eventfd_ctx *call_ctx;
 	struct eventfd_ctx *error_ctx;
@@ -145,6 +181,8 @@ struct vhost_virtqueue {
 	bool user_be;
 #endif
 	u32 busyloop_timeout;
+	spinlock_t mmu_lock;
+	int invalidate_count;
 };
 
 struct vhost_msg_node {
@@ -158,6 +196,9 @@ struct vhost_msg_node {
 
 struct vhost_dev {
 	struct mm_struct *mm;
+#ifdef CONFIG_MMU_NOTIFIER
+	struct mmu_notifier mmu_notifier;
+#endif
 	struct mutex mutex;
 	struct vhost_virtqueue **vqs;
 	int nvqs;
@@ -212,7 +253,7 @@ bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
 		    unsigned int log_num, u64 len,
 		    struct iovec *iov, int count);
-int vq_iotlb_prefetch(struct vhost_virtqueue *vq);
+int vq_meta_prefetch(struct vhost_virtqueue *vq);
 
 struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type);
 void vhost_enqueue_msg(struct vhost_dev *dev,

drivers/virtio/virtio_mmio.c

@@ -463,9 +463,14 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		       struct irq_affinity *desc)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
-	unsigned int irq = platform_get_irq(vm_dev->pdev, 0);
+	int irq = platform_get_irq(vm_dev->pdev, 0);
 	int i, err, queue_idx = 0;
 
+	if (irq < 0) {
+		dev_err(&vdev->dev, "Cannot get IRQ resource\n");
+		return irq;
+	}
+
 	err = request_irq(irq, vm_interrupt, IRQF_SHARED,
 			dev_name(&vdev->dev), vm_dev);
 	if (err)

include/uapi/linux/virtio_ids.h

@@ -43,5 +43,6 @@
 #define VIRTIO_ID_INPUT        18 /* virtio input */
 #define VIRTIO_ID_VSOCK        19 /* virtio vsock transport */
 #define VIRTIO_ID_CRYPTO       20 /* virtio crypto */
+#define VIRTIO_ID_IOMMU        23 /* virtio IOMMU */
 
 #endif /* _LINUX_VIRTIO_IDS_H */

include/uapi/linux/virtio_iommu.h

@@ -0,0 +1,161 @@
+/* SPDX-License-Identifier: BSD-3-Clause */
+/*
+ * Virtio-iommu definition v0.9
+ *
+ * Copyright (C) 2018 Arm Ltd.
+ */
+#ifndef _UAPI_LINUX_VIRTIO_IOMMU_H
+#define _UAPI_LINUX_VIRTIO_IOMMU_H
+
+#include <linux/types.h>
+
+/* Feature bits */
+#define VIRTIO_IOMMU_F_INPUT_RANGE		0
+#define VIRTIO_IOMMU_F_DOMAIN_BITS		1
+#define VIRTIO_IOMMU_F_MAP_UNMAP		2
+#define VIRTIO_IOMMU_F_BYPASS			3
+#define VIRTIO_IOMMU_F_PROBE			4
+
+struct virtio_iommu_range {
+	__u64					start;
+	__u64					end;
+};
+
+struct virtio_iommu_config {
+	/* Supported page sizes */
+	__u64					page_size_mask;
+	/* Supported IOVA range */
+	struct virtio_iommu_range		input_range;
+	/* Max domain ID size */
+	__u8					domain_bits;
+	__u8					padding[3];
+	/* Probe buffer size */
+	__u32					probe_size;
+};
+
+/* Request types */
+#define VIRTIO_IOMMU_T_ATTACH			0x01
+#define VIRTIO_IOMMU_T_DETACH			0x02
+#define VIRTIO_IOMMU_T_MAP			0x03
+#define VIRTIO_IOMMU_T_UNMAP			0x04
+#define VIRTIO_IOMMU_T_PROBE			0x05
+
+/* Status types */
+#define VIRTIO_IOMMU_S_OK			0x00
+#define VIRTIO_IOMMU_S_IOERR			0x01
+#define VIRTIO_IOMMU_S_UNSUPP			0x02
+#define VIRTIO_IOMMU_S_DEVERR			0x03
+#define VIRTIO_IOMMU_S_INVAL			0x04
+#define VIRTIO_IOMMU_S_RANGE			0x05
+#define VIRTIO_IOMMU_S_NOENT			0x06
+#define VIRTIO_IOMMU_S_FAULT			0x07
+
+struct virtio_iommu_req_head {
+	__u8					type;
+	__u8					reserved[3];
+};
+
+struct virtio_iommu_req_tail {
+	__u8					status;
+	__u8					reserved[3];
+};
+
+struct virtio_iommu_req_attach {
+	struct virtio_iommu_req_head		head;
+	__le32					domain;
+	__le32					endpoint;
+	__u8					reserved[8];
+	struct virtio_iommu_req_tail		tail;
+};
+
+struct virtio_iommu_req_detach {
+	struct virtio_iommu_req_head		head;
+	__le32					domain;
+	__le32					endpoint;
+	__u8					reserved[8];
+	struct virtio_iommu_req_tail		tail;
+};
+
+#define VIRTIO_IOMMU_MAP_F_READ			(1 << 0)
+#define VIRTIO_IOMMU_MAP_F_WRITE		(1 << 1)
+#define VIRTIO_IOMMU_MAP_F_EXEC			(1 << 2)
+#define VIRTIO_IOMMU_MAP_F_MMIO			(1 << 3)
+
+#define VIRTIO_IOMMU_MAP_F_MASK			(VIRTIO_IOMMU_MAP_F_READ |	\
+						 VIRTIO_IOMMU_MAP_F_WRITE |	\
+						 VIRTIO_IOMMU_MAP_F_EXEC |	\
+						 VIRTIO_IOMMU_MAP_F_MMIO)
+
+struct virtio_iommu_req_map {
+	struct virtio_iommu_req_head		head;
+	__le32					domain;
+	__le64					virt_start;
+	__le64					virt_end;
+	__le64					phys_start;
+	__le32					flags;
+	struct virtio_iommu_req_tail		tail;
+};
+
+struct virtio_iommu_req_unmap {
+	struct virtio_iommu_req_head		head;
+	__le32					domain;
+	__le64					virt_start;
+	__le64					virt_end;
+	__u8					reserved[4];
+	struct virtio_iommu_req_tail		tail;
+};
+
+#define VIRTIO_IOMMU_PROBE_T_NONE		0
+#define VIRTIO_IOMMU_PROBE_T_RESV_MEM		1
+
+#define VIRTIO_IOMMU_PROBE_T_MASK		0xfff
+
+struct virtio_iommu_probe_property {
+	__le16					type;
+	__le16					length;
+};
+
+#define VIRTIO_IOMMU_RESV_MEM_T_RESERVED	0
+#define VIRTIO_IOMMU_RESV_MEM_T_MSI		1
+
+struct virtio_iommu_probe_resv_mem {
+	struct virtio_iommu_probe_property	head;
+	__u8					subtype;
+	__u8					reserved[3];
+	__le64					start;
+	__le64					end;
+};
+
+struct virtio_iommu_req_probe {
+	struct virtio_iommu_req_head		head;
+	__le32					endpoint;
+	__u8					reserved[64];
+
+	__u8					properties[];
+
+	/*
+	 * Tail follows the variable-length properties array. No padding,
+	 * property lengths are all aligned on 8 bytes.
+	 */
+};
+
+/* Fault types */
+#define VIRTIO_IOMMU_FAULT_R_UNKNOWN		0
+#define VIRTIO_IOMMU_FAULT_R_DOMAIN		1
+#define VIRTIO_IOMMU_FAULT_R_MAPPING		2
+
+#define VIRTIO_IOMMU_FAULT_F_READ		(1 << 0)
+#define VIRTIO_IOMMU_FAULT_F_WRITE		(1 << 1)
+#define VIRTIO_IOMMU_FAULT_F_EXEC		(1 << 2)
+#define VIRTIO_IOMMU_FAULT_F_ADDRESS		(1 << 8)
+
+struct virtio_iommu_fault {
+	__u8					reason;
+	__u8					reserved[3];
+	__le32					flags;
+	__le32					endpoint;
+	__u8					reserved2[4];
+	__le64					address;
+};
+
+#endif