Resguardo inicial

linux-7.2.3/drivers/vhost/Kconfig

@@ -0,0 +1,116 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config VHOST_IOTLB
+	tristate
+	help
+	  Generic IOTLB implementation for vhost and vringh.
+	  This option is selected by any driver which needs to support
+	  an IOMMU in software.
+
+config VHOST_RING
+	tristate
+	select VHOST_IOTLB
+	help
+	  This option is selected by any driver which needs to access
+	  the host side of a virtio ring.
+
+config VHOST_TASK
+	bool
+	default n
+
+config VHOST
+	tristate
+	select VHOST_IOTLB
+	select VHOST_TASK
+	help
+	  This option is selected by any driver which needs to access
+	  the core of vhost.
+
+menuconfig VHOST_MENU
+	bool "VHOST drivers"
+	default y
+
+if VHOST_MENU
+
+config VHOST_NET
+	tristate "Host kernel accelerator for virtio net"
+	depends on NET && EVENTFD && (TUN || !TUN) && (TAP || !TAP)
+	select VHOST
+	help
+	  This kernel module can be loaded in host kernel to accelerate
+	  guest networking with virtio_net. Not to be confused with virtio_net
+	  module itself which needs to be loaded in guest kernel.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called vhost_net.
+
+config VHOST_SCSI
+	tristate "VHOST_SCSI TCM fabric driver"
+	depends on TARGET_CORE && EVENTFD
+	select VHOST
+	select SG_POOL
+	default n
+	help
+	Say M here to enable the vhost_scsi TCM fabric module
+	for use with virtio-scsi guests
+
+config VHOST_VSOCK
+	tristate "vhost virtio-vsock driver"
+	depends on VSOCKETS && EVENTFD
+	select VHOST
+	select VIRTIO_VSOCKETS_COMMON
+	default n
+	help
+	This kernel module can be loaded in the host kernel to provide AF_VSOCK
+	sockets for communicating with guests.  The guests must have the
+	virtio_transport.ko driver loaded to use the virtio-vsock device.
+
+	To compile this driver as a module, choose M here: the module will be called
+	vhost_vsock.
+
+config VHOST_VDPA
+	tristate "Vhost driver for vDPA-based backend"
+	depends on EVENTFD
+	select VHOST
+	select IRQ_BYPASS_MANAGER
+	depends on VDPA
+	help
+	  This kernel module can be loaded in host kernel to accelerate
+	  guest virtio devices with the vDPA-based backends.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called vhost_vdpa.
+
+config VHOST_CROSS_ENDIAN_LEGACY
+	bool "Cross-endian support for vhost"
+	default n
+	help
+	  This option allows vhost to support guests with a different byte
+	  ordering from host while using legacy virtio.
+
+	  Userspace programs can control the feature using the
+	  VHOST_SET_VRING_ENDIAN and VHOST_GET_VRING_ENDIAN ioctls.
+
+	  This is only useful on a few platforms (ppc64 and arm64). Since it
+	  adds some overhead, it is disabled by default.
+
+	  If unsure, say "N".
+
+config VHOST_ENABLE_FORK_OWNER_CONTROL
+	bool "Enable VHOST_ENABLE_FORK_OWNER_CONTROL"
+	default y
+	help
+	  This option enables two IOCTLs: VHOST_SET_FORK_FROM_OWNER and
+	  VHOST_GET_FORK_FROM_OWNER. These allow userspace applications
+	  to modify the vhost worker mode for vhost devices.
+
+	  Also expose module parameter 'fork_from_owner_default' to allow users
+	  to configure the default mode for vhost workers.
+
+	  By default, `VHOST_ENABLE_FORK_OWNER_CONTROL` is set to `y`,
+	  users can change the worker thread mode as needed.
+	  If this config is disabled (n),the related IOCTLs and parameters will
+	  be unavailable.
+
+	  If unsure, say "Y".
+
+endif

linux-7.2.3/drivers/vhost/Makefile

@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_VHOST_NET) += vhost_net.o
+vhost_net-y := net.o
+
+obj-$(CONFIG_VHOST_SCSI) += vhost_scsi.o
+vhost_scsi-y := scsi.o
+
+obj-$(CONFIG_VHOST_VSOCK) += vhost_vsock.o
+vhost_vsock-y := vsock.o
+
+obj-$(CONFIG_VHOST_RING) += vringh.o
+
+obj-$(CONFIG_VHOST_VDPA) += vhost_vdpa.o
+vhost_vdpa-y := vdpa.o
+
+obj-$(CONFIG_VHOST)	+= vhost.o
+
+obj-$(CONFIG_VHOST_IOTLB) += vhost_iotlb.o
+vhost_iotlb-y := iotlb.o

linux-7.2.3/drivers/vhost/iotlb.c

@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Red Hat, Inc.
+ * Author: Jason Wang <jasowang@redhat.com>
+ *
+ * IOTLB implementation for vhost.
+ */
+#include <linux/slab.h>
+#include <linux/vhost_iotlb.h>
+#include <linux/module.h>
+
+#define MOD_VERSION  "0.1"
+#define MOD_DESC     "VHOST IOTLB"
+#define MOD_AUTHOR   "Jason Wang <jasowang@redhat.com>"
+#define MOD_LICENSE  "GPL v2"
+
+#define START(map) ((map)->start)
+#define LAST(map) ((map)->last)
+
+INTERVAL_TREE_DEFINE(struct vhost_iotlb_map,
+		     rb, __u64, __subtree_last,
+		     START, LAST, static inline, vhost_iotlb_itree);
+
+static void vhost_iotlb_map_unlink(struct vhost_iotlb *iotlb,
+				   struct vhost_iotlb_map *map)
+{
+	vhost_iotlb_itree_remove(map, &iotlb->root);
+	list_del(&map->link);
+	iotlb->nmaps--;
+}
+
+/**
+ * vhost_iotlb_map_free - remove a map node and free it
+ * @iotlb: the IOTLB
+ * @map: the map that want to be remove and freed
+ */
+void vhost_iotlb_map_free(struct vhost_iotlb *iotlb,
+			  struct vhost_iotlb_map *map)
+{
+	vhost_iotlb_map_unlink(iotlb, map);
+	kfree(map);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_map_free);
+
+/**
+ * vhost_iotlb_add_range_ctx - add a new range to vhost IOTLB
+ * @iotlb: the IOTLB
+ * @start: start of the IOVA range
+ * @last: last of IOVA range
+ * @addr: the address that is mapped to @start
+ * @perm: access permission of this range
+ * @opaque: the opaque pointer for the new mapping
+ *
+ * Returns an error last is smaller than start or memory allocation
+ * fails
+ */
+int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb,
+			      u64 start, u64 last,
+			      u64 addr, unsigned int perm,
+			      void *opaque)
+{
+	struct vhost_iotlb_map *map;
+
+	if (last < start)
+		return -EFAULT;
+
+	if (!iotlb->limit)
+		return -EINVAL;
+
+	/* If the range being mapped is [0, ULONG_MAX], split it into two entries
+	 * otherwise its size would overflow u64.
+	 */
+	if (start == 0 && last == ULONG_MAX) {
+		u64 mid = last / 2;
+		int err;
+
+		if (iotlb->limit < 2)
+			return -ENOSPC;
+
+		if (!(iotlb->flags & VHOST_IOTLB_FLAG_RETIRE) &&
+		    iotlb->nmaps > iotlb->limit - 2)
+			return -ENOSPC;
+
+		err = vhost_iotlb_add_range_ctx(iotlb, start, mid, addr,
+						perm, opaque);
+		if (err)
+			return err;
+
+		addr += mid + 1;
+		start = mid + 1;
+	}
+
+	if (iotlb->nmaps >= iotlb->limit) {
+		if (iotlb->flags & VHOST_IOTLB_FLAG_RETIRE) {
+			map = list_first_entry(&iotlb->list, typeof(*map), link);
+			vhost_iotlb_map_unlink(iotlb, map);
+		} else {
+			return -ENOSPC;
+		}
+	} else {
+		map = kmalloc_obj(*map, GFP_ATOMIC);
+		if (!map)
+			return -ENOMEM;
+	}
+
+	map->start = start;
+	map->size = last - start + 1;
+	map->last = last;
+	map->addr = addr;
+	map->perm = perm;
+	map->opaque = opaque;
+
+	iotlb->nmaps++;
+	vhost_iotlb_itree_insert(map, &iotlb->root);
+
+	INIT_LIST_HEAD(&map->link);
+	list_add_tail(&map->link, &iotlb->list);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_add_range_ctx);
+
+int vhost_iotlb_add_range(struct vhost_iotlb *iotlb,
+			  u64 start, u64 last,
+			  u64 addr, unsigned int perm)
+{
+	return vhost_iotlb_add_range_ctx(iotlb, start, last,
+					 addr, perm, NULL);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_add_range);
+
+/**
+ * vhost_iotlb_del_range - delete overlapped ranges from vhost IOTLB
+ * @iotlb: the IOTLB
+ * @start: start of the IOVA range
+ * @last: last of IOVA range
+ */
+void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last)
+{
+	struct vhost_iotlb_map *map;
+
+	while ((map = vhost_iotlb_itree_iter_first(&iotlb->root,
+						   start, last)))
+		vhost_iotlb_map_free(iotlb, map);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_del_range);
+
+/**
+ * vhost_iotlb_init - initialize a vhost IOTLB
+ * @iotlb: the IOTLB that needs to be initialized
+ * @limit: maximum number of IOTLB entries
+ * @flags: VHOST_IOTLB_FLAG_XXX
+ */
+void vhost_iotlb_init(struct vhost_iotlb *iotlb, unsigned int limit,
+		      unsigned int flags)
+{
+	iotlb->root = RB_ROOT_CACHED;
+	iotlb->limit = limit;
+	iotlb->nmaps = 0;
+	iotlb->flags = flags;
+	INIT_LIST_HEAD(&iotlb->list);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_init);
+
+/**
+ * vhost_iotlb_alloc - add a new vhost IOTLB
+ * @limit: maximum number of IOTLB entries
+ * @flags: VHOST_IOTLB_FLAG_XXX
+ *
+ * Returns an error is memory allocation fails
+ */
+struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags)
+{
+	struct vhost_iotlb *iotlb = kzalloc_obj(*iotlb);
+
+	if (!iotlb)
+		return NULL;
+
+	vhost_iotlb_init(iotlb, limit, flags);
+
+	return iotlb;
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_alloc);
+
+/**
+ * vhost_iotlb_reset - reset vhost IOTLB (free all IOTLB entries)
+ * @iotlb: the IOTLB to be reset
+ */
+void vhost_iotlb_reset(struct vhost_iotlb *iotlb)
+{
+	vhost_iotlb_del_range(iotlb, 0ULL, 0ULL - 1);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_reset);
+
+/**
+ * vhost_iotlb_free - reset and free vhost IOTLB
+ * @iotlb: the IOTLB to be freed
+ */
+void vhost_iotlb_free(struct vhost_iotlb *iotlb)
+{
+	if (iotlb) {
+		vhost_iotlb_reset(iotlb);
+		kfree(iotlb);
+	}
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_free);
+
+/**
+ * vhost_iotlb_itree_first - return the first overlapped range
+ * @iotlb: the IOTLB
+ * @start: start of IOVA range
+ * @last: last byte in IOVA range
+ */
+struct vhost_iotlb_map *
+vhost_iotlb_itree_first(struct vhost_iotlb *iotlb, u64 start, u64 last)
+{
+	return vhost_iotlb_itree_iter_first(&iotlb->root, start, last);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_itree_first);
+
+/**
+ * vhost_iotlb_itree_next - return the next overlapped range
+ * @map: the starting map node
+ * @start: start of IOVA range
+ * @last: last byte IOVA range
+ */
+struct vhost_iotlb_map *
+vhost_iotlb_itree_next(struct vhost_iotlb_map *map, u64 start, u64 last)
+{
+	return vhost_iotlb_itree_iter_next(map, start, last);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_itree_next);
+
+MODULE_VERSION(MOD_VERSION);
+MODULE_DESCRIPTION(MOD_DESC);
+MODULE_AUTHOR(MOD_AUTHOR);
+MODULE_LICENSE(MOD_LICENSE);

linux-7.2.3/drivers/vhost/test.c

@@ -0,0 +1,379 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2009 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ *
+ * test virtio server in host kernel.
+ */
+
+#include <linux/compat.h>
+#include <linux/eventfd.h>
+#include <linux/vhost.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+
+#include "test.h"
+#include "vhost.h"
+
+/* Max number of bytes transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others. */
+#define VHOST_TEST_WEIGHT 0x80000
+
+/* Max number of packets transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others with
+ * pkts.
+ */
+#define VHOST_TEST_PKT_WEIGHT 256
+
+static const int vhost_test_bits[] = {
+	VHOST_FEATURES
+};
+
+#define VHOST_TEST_FEATURES VHOST_FEATURES_U64(vhost_test_bits, 0)
+
+enum {
+	VHOST_TEST_VQ = 0,
+	VHOST_TEST_VQ_MAX = 1,
+};
+
+struct vhost_test {
+	struct vhost_dev dev;
+	struct vhost_virtqueue vqs[VHOST_TEST_VQ_MAX];
+};
+
+/* Expects to be always run from workqueue - which acts as
+ * read-size critical section for our kind of RCU. */
+static void handle_vq(struct vhost_test *n)
+{
+	struct vhost_virtqueue *vq = &n->vqs[VHOST_TEST_VQ];
+	unsigned out, in;
+	int head;
+	size_t len, total_len = 0;
+	void *private;
+
+	mutex_lock(&vq->mutex);
+	private = vhost_vq_get_backend(vq);
+	if (!private) {
+		mutex_unlock(&vq->mutex);
+		return;
+	}
+
+	vhost_disable_notify(&n->dev, vq);
+
+	for (;;) {
+		head = vhost_get_vq_desc(vq, vq->iov,
+					 ARRAY_SIZE(vq->iov),
+					 &out, &in,
+					 NULL, NULL);
+		/* On error, stop handling until the next kick. */
+		if (unlikely(head < 0))
+			break;
+		/* Nothing new?  Wait for eventfd to tell us they refilled. */
+		if (head == vq->num) {
+			if (unlikely(vhost_enable_notify(&n->dev, vq))) {
+				vhost_disable_notify(&n->dev, vq);
+				continue;
+			}
+			break;
+		}
+		if (in) {
+			vq_err(vq, "Unexpected descriptor format for TX: "
+			       "out %d, int %d\n", out, in);
+			break;
+		}
+		len = iov_length(vq->iov, out);
+		/* Sanity check */
+		if (!len) {
+			vq_err(vq, "Unexpected 0 len for TX\n");
+			break;
+		}
+		vhost_add_used_and_signal(&n->dev, vq, head, 0);
+		total_len += len;
+		if (unlikely(vhost_exceeds_weight(vq, 0, total_len)))
+			break;
+	}
+
+	mutex_unlock(&vq->mutex);
+}
+
+static void handle_vq_kick(struct vhost_work *work)
+{
+	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
+						  poll.work);
+	struct vhost_test *n = container_of(vq->dev, struct vhost_test, dev);
+
+	handle_vq(n);
+}
+
+static int vhost_test_open(struct inode *inode, struct file *f)
+{
+	struct vhost_test *n = kmalloc_obj(*n);
+	struct vhost_dev *dev;
+	struct vhost_virtqueue **vqs;
+
+	if (!n)
+		return -ENOMEM;
+	vqs = kmalloc_objs(*vqs, VHOST_TEST_VQ_MAX);
+	if (!vqs) {
+		kfree(n);
+		return -ENOMEM;
+	}
+
+	dev = &n->dev;
+	vqs[VHOST_TEST_VQ] = &n->vqs[VHOST_TEST_VQ];
+	n->vqs[VHOST_TEST_VQ].handle_kick = handle_vq_kick;
+	vhost_dev_init(dev, vqs, VHOST_TEST_VQ_MAX, UIO_MAXIOV,
+		       VHOST_TEST_PKT_WEIGHT, VHOST_TEST_WEIGHT, true, NULL);
+
+	f->private_data = n;
+
+	return 0;
+}
+
+static void *vhost_test_stop_vq(struct vhost_test *n,
+				struct vhost_virtqueue *vq)
+{
+	void *private;
+
+	mutex_lock(&vq->mutex);
+	private = vhost_vq_get_backend(vq);
+	vhost_vq_set_backend(vq, NULL);
+	mutex_unlock(&vq->mutex);
+	return private;
+}
+
+static void vhost_test_stop(struct vhost_test *n, void **privatep)
+{
+	*privatep = vhost_test_stop_vq(n, n->vqs + VHOST_TEST_VQ);
+}
+
+static void vhost_test_flush(struct vhost_test *n)
+{
+	vhost_dev_flush(&n->dev);
+}
+
+static int vhost_test_release(struct inode *inode, struct file *f)
+{
+	struct vhost_test *n = f->private_data;
+	void  *private;
+
+	vhost_test_stop(n, &private);
+	vhost_test_flush(n);
+	vhost_dev_stop(&n->dev);
+	vhost_dev_cleanup(&n->dev);
+	kfree(n->dev.vqs);
+	kfree(n);
+	return 0;
+}
+
+static long vhost_test_run(struct vhost_test *n, int test)
+{
+	void *priv, *oldpriv;
+	struct vhost_virtqueue *vq;
+	int r, index;
+
+	if (test < 0 || test > 1)
+		return -EINVAL;
+
+	mutex_lock(&n->dev.mutex);
+	r = vhost_dev_check_owner(&n->dev);
+	if (r)
+		goto err;
+
+	for (index = 0; index < n->dev.nvqs; ++index) {
+		/* Verify that ring has been setup correctly. */
+		if (!vhost_vq_access_ok(&n->vqs[index])) {
+			r = -EFAULT;
+			goto err;
+		}
+	}
+
+	for (index = 0; index < n->dev.nvqs; ++index) {
+		vq = n->vqs + index;
+		mutex_lock(&vq->mutex);
+		priv = test ? n : NULL;
+
+		/* start polling new socket */
+		oldpriv = vhost_vq_get_backend(vq);
+		vhost_vq_set_backend(vq, priv);
+
+		r = vhost_vq_init_access(&n->vqs[index]);
+
+		mutex_unlock(&vq->mutex);
+
+		if (r)
+			goto err;
+
+		if (oldpriv) {
+			vhost_test_flush(n);
+		}
+	}
+
+	mutex_unlock(&n->dev.mutex);
+	return 0;
+
+err:
+	mutex_unlock(&n->dev.mutex);
+	return r;
+}
+
+static long vhost_test_reset_owner(struct vhost_test *n)
+{
+	void *priv = NULL;
+	long err;
+	struct vhost_iotlb *umem;
+
+	mutex_lock(&n->dev.mutex);
+	err = vhost_dev_check_owner(&n->dev);
+	if (err)
+		goto done;
+	umem = vhost_dev_reset_owner_prepare();
+	if (!umem) {
+		err = -ENOMEM;
+		goto done;
+	}
+	vhost_test_stop(n, &priv);
+	vhost_test_flush(n);
+	vhost_dev_stop(&n->dev);
+	vhost_dev_reset_owner(&n->dev, umem);
+done:
+	mutex_unlock(&n->dev.mutex);
+	return err;
+}
+
+static int vhost_test_set_features(struct vhost_test *n, u64 features)
+{
+	struct vhost_virtqueue *vq;
+
+	mutex_lock(&n->dev.mutex);
+	if ((features & (1 << VHOST_F_LOG_ALL)) &&
+	    !vhost_log_access_ok(&n->dev)) {
+		mutex_unlock(&n->dev.mutex);
+		return -EFAULT;
+	}
+	vq = &n->vqs[VHOST_TEST_VQ];
+	mutex_lock(&vq->mutex);
+	vq->acked_features = features;
+	mutex_unlock(&vq->mutex);
+	mutex_unlock(&n->dev.mutex);
+	return 0;
+}
+
+static long vhost_test_set_backend(struct vhost_test *n, unsigned index, int fd)
+{
+	static void *backend;
+
+	const bool enable = fd != -1;
+	struct vhost_virtqueue *vq;
+	int r;
+
+	mutex_lock(&n->dev.mutex);
+	r = vhost_dev_check_owner(&n->dev);
+	if (r)
+		goto err;
+
+	if (index >= VHOST_TEST_VQ_MAX) {
+		r = -ENOBUFS;
+		goto err;
+	}
+	vq = &n->vqs[index];
+	mutex_lock(&vq->mutex);
+
+	/* Verify that ring has been setup correctly. */
+	if (!vhost_vq_access_ok(vq)) {
+		r = -EFAULT;
+		goto err_vq;
+	}
+	if (!enable) {
+		vhost_poll_stop(&vq->poll);
+		backend = vhost_vq_get_backend(vq);
+		vhost_vq_set_backend(vq, NULL);
+	} else {
+		vhost_vq_set_backend(vq, backend);
+		r = vhost_vq_init_access(vq);
+		if (r == 0)
+			r = vhost_poll_start(&vq->poll, vq->kick);
+	}
+
+	mutex_unlock(&vq->mutex);
+
+	if (enable) {
+		vhost_test_flush(n);
+	}
+
+	mutex_unlock(&n->dev.mutex);
+	return 0;
+
+err_vq:
+	mutex_unlock(&vq->mutex);
+err:
+	mutex_unlock(&n->dev.mutex);
+	return r;
+}
+
+static long vhost_test_ioctl(struct file *f, unsigned int ioctl,
+			     unsigned long arg)
+{
+	struct vhost_vring_file backend;
+	struct vhost_test *n = f->private_data;
+	void __user *argp = (void __user *)arg;
+	u64 __user *featurep = argp;
+	int test;
+	u64 features;
+	int r;
+	switch (ioctl) {
+	case VHOST_TEST_RUN:
+		if (copy_from_user(&test, argp, sizeof test))
+			return -EFAULT;
+		return vhost_test_run(n, test);
+	case VHOST_TEST_SET_BACKEND:
+		if (copy_from_user(&backend, argp, sizeof backend))
+			return -EFAULT;
+		return vhost_test_set_backend(n, backend.index, backend.fd);
+	case VHOST_GET_FEATURES:
+		features = VHOST_TEST_FEATURES;
+		if (copy_to_user(featurep, &features, sizeof features))
+			return -EFAULT;
+		return 0;
+	case VHOST_SET_FEATURES:
+		if (copy_from_user(&features, featurep, sizeof features))
+			return -EFAULT;
+		if (features & ~VHOST_TEST_FEATURES)
+			return -EOPNOTSUPP;
+		return vhost_test_set_features(n, features);
+	case VHOST_RESET_OWNER:
+		return vhost_test_reset_owner(n);
+	default:
+		mutex_lock(&n->dev.mutex);
+		r = vhost_dev_ioctl(&n->dev, ioctl, argp);
+                if (r == -ENOIOCTLCMD)
+                        r = vhost_vring_ioctl(&n->dev, ioctl, argp);
+		vhost_test_flush(n);
+		mutex_unlock(&n->dev.mutex);
+		return r;
+	}
+}
+
+static const struct file_operations vhost_test_fops = {
+	.owner          = THIS_MODULE,
+	.release        = vhost_test_release,
+	.unlocked_ioctl = vhost_test_ioctl,
+	.compat_ioctl   = compat_ptr_ioctl,
+	.open           = vhost_test_open,
+	.llseek		= noop_llseek,
+};
+
+static struct miscdevice vhost_test_misc = {
+	MISC_DYNAMIC_MINOR,
+	"vhost-test",
+	&vhost_test_fops,
+};
+module_misc_device(vhost_test_misc);
+
+MODULE_VERSION("0.0.1");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Michael S. Tsirkin");
+MODULE_DESCRIPTION("Host kernel side for virtio simulator");

linux-7.2.3/drivers/vhost/test.h

@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_VHOST_TEST_H
+#define LINUX_VHOST_TEST_H
+
+/* Start a given test on the virtio null device. 0 stops all tests. */
+#define VHOST_TEST_RUN _IOW(VHOST_VIRTIO, 0x31, int)
+#define VHOST_TEST_SET_BACKEND _IOW(VHOST_VIRTIO, 0x32, int)
+
+#endif

linux-7.2.3/drivers/vhost/vhost.h

@@ -0,0 +1,404 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _VHOST_H
+#define _VHOST_H
+
+#include <linux/eventfd.h>
+#include <linux/vhost.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/poll.h>
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+#include <linux/atomic.h>
+#include <linux/vhost_iotlb.h>
+#include <linux/irqbypass.h>
+#include <linux/unroll.h>
+
+struct vhost_work;
+struct vhost_task;
+typedef void (*vhost_work_fn_t)(struct vhost_work *work);
+
+#define VHOST_WORK_QUEUED 1
+struct vhost_work {
+	struct llist_node	node;
+	vhost_work_fn_t		fn;
+	unsigned long		flags;
+};
+
+struct vhost_worker;
+struct vhost_dev;
+
+struct vhost_worker_ops {
+	int (*create)(struct vhost_worker *worker, struct vhost_dev *dev,
+		      const char *name);
+	void (*stop)(struct vhost_worker *worker);
+	void (*wakeup)(struct vhost_worker *worker);
+};
+
+struct vhost_worker {
+	struct task_struct *kthread_task;
+	struct vhost_task	*vtsk;
+	struct vhost_dev	*dev;
+	/* Used to serialize device wide flushing with worker swapping. */
+	struct mutex		mutex;
+	struct llist_head	work_list;
+	struct kcov_common_handle_id kcov_handle;
+	u32			id;
+	int			attachment_cnt;
+	bool			killed;
+	const struct vhost_worker_ops *ops;
+};
+
+/* Poll a file (eventfd or socket) */
+/* Note: there's nothing vhost specific about this structure. */
+struct vhost_poll {
+	poll_table		table;
+	wait_queue_head_t	*wqh;
+	wait_queue_entry_t	wait;
+	struct vhost_work	work;
+	__poll_t		mask;
+	struct vhost_dev	*dev;
+	struct vhost_virtqueue	*vq;
+};
+
+void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
+		     __poll_t mask, struct vhost_dev *dev,
+		     struct vhost_virtqueue *vq);
+int vhost_poll_start(struct vhost_poll *poll, struct file *file);
+void vhost_poll_stop(struct vhost_poll *poll);
+void vhost_poll_queue(struct vhost_poll *poll);
+
+void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn);
+void vhost_dev_flush(struct vhost_dev *dev);
+
+struct vhost_log {
+	u64 addr;
+	u64 len;
+};
+
+enum vhost_uaddr_type {
+	VHOST_ADDR_DESC = 0,
+	VHOST_ADDR_AVAIL = 1,
+	VHOST_ADDR_USED = 2,
+	VHOST_NUM_ADDRS = 3,
+};
+
+struct vhost_vring_call {
+	struct eventfd_ctx *ctx;
+	struct irq_bypass_producer producer;
+};
+
+/* The virtqueue structure describes a queue attached to a device. */
+struct vhost_virtqueue {
+	struct vhost_dev *dev;
+	struct vhost_worker __rcu *worker;
+
+	/* The actual ring of buffers. */
+	struct mutex mutex;
+	unsigned int num;
+	vring_desc_t __user *desc;
+	vring_avail_t __user *avail;
+	vring_used_t __user *used;
+	const struct vhost_iotlb_map *meta_iotlb[VHOST_NUM_ADDRS];
+	struct file *kick;
+	struct vhost_vring_call call_ctx;
+	struct eventfd_ctx *error_ctx;
+	struct eventfd_ctx *log_ctx;
+
+	struct vhost_poll poll;
+
+	/* The routine to call when the Guest pings us, or timeout. */
+	vhost_work_fn_t handle_kick;
+
+	/* Last available index we saw.
+	 * Values are limited to 0x7fff, and the high bit is used as
+	 * a wrap counter when using VIRTIO_F_RING_PACKED. */
+	u16 last_avail_idx;
+	/* Next avail ring head when VIRTIO_F_IN_ORDER is negoitated */
+	u16 next_avail_head;
+
+	/* Caches available index value from user. */
+	u16 avail_idx;
+
+	/* Last index we used.
+	 * Values are limited to 0x7fff, and the high bit is used as
+	 * a wrap counter when using VIRTIO_F_RING_PACKED. */
+	u16 last_used_idx;
+
+	/* Used flags */
+	u16 used_flags;
+
+	/* Last used index value we have signalled on */
+	u16 signalled_used;
+
+	/* Last used index value we have signalled on */
+	bool signalled_used_valid;
+
+	/* Log writes to used structure. */
+	bool log_used;
+	u64 log_addr;
+
+	struct iovec iov[UIO_MAXIOV];
+	struct iovec iotlb_iov[64];
+	struct iovec *indirect;
+	struct vring_used_elem *heads;
+	u16 *nheads;
+	/* Protected by virtqueue mutex. */
+	struct vhost_iotlb *umem;
+	struct vhost_iotlb *iotlb;
+	void *private_data;
+	VIRTIO_DECLARE_FEATURES(acked_features);
+	u64 acked_backend_features;
+	/* Log write descriptors */
+	void __user *log_base;
+	struct vhost_log *log;
+	struct iovec log_iov[64];
+
+	/* Ring endianness. Defaults to legacy native endianness.
+	 * Set to true when starting a modern virtio device. */
+	bool is_le;
+#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
+	/* Ring endianness requested by userspace for cross-endian support. */
+	bool user_be;
+#endif
+	u32 busyloop_timeout;
+};
+
+struct vhost_msg_node {
+  union {
+	  struct vhost_msg msg;
+	  struct vhost_msg_v2 msg_v2;
+  };
+  struct vhost_virtqueue *vq;
+  struct list_head node;
+};
+
+struct vhost_dev {
+	struct mm_struct *mm;
+	struct mutex mutex;
+	struct vhost_virtqueue **vqs;
+	int nvqs;
+	struct eventfd_ctx *log_ctx;
+	struct vhost_iotlb *umem;
+	struct vhost_iotlb *iotlb;
+	spinlock_t iotlb_lock;
+	struct list_head read_list;
+	struct list_head pending_list;
+	wait_queue_head_t wait;
+	int iov_limit;
+	int weight;
+	int byte_weight;
+	struct xarray worker_xa;
+	bool use_worker;
+	/*
+	 * If fork_owner is true we use vhost_tasks to create
+	 * the worker so all settings/limits like cgroups, NPROC,
+	 * scheduler, etc are inherited from the owner. If false,
+	 * we use kthreads and only attach to the same cgroups
+	 * as the owner for compat with older kernels.
+	 * here we use true as default value.
+	 * The default value is set by fork_from_owner_default
+	 */
+	bool fork_owner;
+	int (*msg_handler)(struct vhost_dev *dev, u32 asid,
+			   struct vhost_iotlb_msg *msg);
+};
+
+bool vhost_exceeds_weight(struct vhost_virtqueue *vq, int pkts, int total_len);
+void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs,
+		    int nvqs, int iov_limit, int weight, int byte_weight,
+		    bool use_worker,
+		    int (*msg_handler)(struct vhost_dev *dev, u32 asid,
+				       struct vhost_iotlb_msg *msg));
+long vhost_dev_set_owner(struct vhost_dev *dev);
+bool vhost_dev_has_owner(struct vhost_dev *dev);
+long vhost_dev_check_owner(struct vhost_dev *);
+struct vhost_iotlb *vhost_dev_reset_owner_prepare(void);
+void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_iotlb *iotlb);
+void vhost_dev_cleanup(struct vhost_dev *);
+void vhost_dev_stop(struct vhost_dev *);
+long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp);
+long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp);
+long vhost_worker_ioctl(struct vhost_dev *dev, unsigned int ioctl,
+			void __user *argp);
+bool vhost_vq_access_ok(struct vhost_virtqueue *vq);
+bool vhost_log_access_ok(struct vhost_dev *);
+void vhost_clear_msg(struct vhost_dev *dev);
+
+int vhost_get_vq_desc(struct vhost_virtqueue *,
+		      struct iovec iov[], unsigned int iov_size,
+		      unsigned int *out_num, unsigned int *in_num,
+		      struct vhost_log *log, unsigned int *log_num);
+
+int vhost_get_vq_desc_n(struct vhost_virtqueue *vq,
+			struct iovec iov[], unsigned int iov_size,
+			unsigned int *out_num, unsigned int *in_num,
+			struct vhost_log *log, unsigned int *log_num,
+			unsigned int *ndesc);
+
+void vhost_discard_vq_desc(struct vhost_virtqueue *, int nbuf,
+			   unsigned int ndesc);
+
+bool vhost_vq_work_queue(struct vhost_virtqueue *vq, struct vhost_work *work);
+bool vhost_vq_has_work(struct vhost_virtqueue *vq);
+bool vhost_vq_is_setup(struct vhost_virtqueue *vq);
+int vhost_vq_init_access(struct vhost_virtqueue *);
+int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);
+int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads,
+		     u16 *nheads, unsigned count);
+void vhost_add_used_and_signal(struct vhost_dev *, struct vhost_virtqueue *,
+			       unsigned int id, int len);
+void vhost_add_used_and_signal_n(struct vhost_dev *, struct vhost_virtqueue *,
+				 struct vring_used_elem *heads, u16 *nheads,
+				 unsigned count);
+void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
+void vhost_disable_notify(struct vhost_dev *, struct vhost_virtqueue *);
+bool vhost_vq_avail_empty(struct vhost_dev *, struct vhost_virtqueue *);
+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_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,
+		       struct list_head *head,
+		       struct vhost_msg_node *node);
+struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev,
+					 struct list_head *head);
+void vhost_set_backend_features(struct vhost_dev *dev, u64 features);
+
+__poll_t vhost_chr_poll(struct file *file, struct vhost_dev *dev,
+			    poll_table *wait);
+ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
+			    int noblock);
+ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
+			     struct iov_iter *from);
+int vhost_init_device_iotlb(struct vhost_dev *d);
+
+void vhost_iotlb_map_free(struct vhost_iotlb *iotlb,
+			  struct vhost_iotlb_map *map);
+
+#define vq_err(vq, fmt, ...) do {                                  \
+		pr_debug(pr_fmt(fmt), ##__VA_ARGS__);       \
+		if ((vq)->error_ctx)                               \
+				eventfd_signal((vq)->error_ctx);\
+	} while (0)
+
+#define VHOST_FEATURES \
+	VIRTIO_F_NOTIFY_ON_EMPTY, \
+	VIRTIO_RING_F_INDIRECT_DESC, \
+	VIRTIO_RING_F_EVENT_IDX, \
+	VHOST_F_LOG_ALL, \
+	VIRTIO_F_ANY_LAYOUT, \
+	VIRTIO_F_VERSION_1
+
+static inline u64 vhost_features_u64(const int *features, int size, int idx)
+{
+	u64 res = 0;
+
+	unrolled_count(VIRTIO_FEATURES_BITS)
+	for (int i = 0; i < size; ++i) {
+		int bit = features[i];
+
+		if (virtio_features_chk_bit(bit) && VIRTIO_U64(bit) == idx)
+			res |= VIRTIO_BIT(bit);
+	}
+	return res;
+}
+
+#define VHOST_FEATURES_U64(features, idx) \
+	vhost_features_u64(features, ARRAY_SIZE(features), idx)
+
+#define DEFINE_VHOST_FEATURES_ARRAY_ENTRY(idx, features) \
+	[idx] = VHOST_FEATURES_U64(features, idx),
+
+#define DEFINE_VHOST_FEATURES_ARRAY(array, features) \
+	u64 array[VIRTIO_FEATURES_U64S] = { \
+		UNROLL(VIRTIO_FEATURES_U64S, \
+		       DEFINE_VHOST_FEATURES_ARRAY_ENTRY, features) \
+	}
+
+/**
+ * vhost_vq_set_backend - Set backend.
+ *
+ * @vq            Virtqueue.
+ * @private_data  The private data.
+ *
+ * Context: Need to call with vq->mutex acquired.
+ */
+static inline void vhost_vq_set_backend(struct vhost_virtqueue *vq,
+					void *private_data)
+{
+	vq->private_data = private_data;
+}
+
+/**
+ * vhost_vq_get_backend - Get backend.
+ *
+ * @vq            Virtqueue.
+ *
+ * Context: Need to call with vq->mutex acquired.
+ * Return: Private data previously set with vhost_vq_set_backend.
+ */
+static inline void *vhost_vq_get_backend(struct vhost_virtqueue *vq)
+{
+	return vq->private_data;
+}
+
+static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit)
+{
+	return virtio_features_test_bit(vq->acked_features_array, bit);
+}
+
+static inline bool vhost_backend_has_feature(struct vhost_virtqueue *vq, int bit)
+{
+	return vq->acked_backend_features & (1ULL << bit);
+}
+
+#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
+static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq)
+{
+	return vq->is_le;
+}
+#else
+static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq)
+{
+	return virtio_legacy_is_little_endian() || vq->is_le;
+}
+#endif
+
+/* Memory accessors */
+static inline u16 vhost16_to_cpu(struct vhost_virtqueue *vq, __virtio16 val)
+{
+	return __virtio16_to_cpu(vhost_is_little_endian(vq), val);
+}
+
+static inline __virtio16 cpu_to_vhost16(struct vhost_virtqueue *vq, u16 val)
+{
+	return __cpu_to_virtio16(vhost_is_little_endian(vq), val);
+}
+
+static inline u32 vhost32_to_cpu(struct vhost_virtqueue *vq, __virtio32 val)
+{
+	return __virtio32_to_cpu(vhost_is_little_endian(vq), val);
+}
+
+static inline __virtio32 cpu_to_vhost32(struct vhost_virtqueue *vq, u32 val)
+{
+	return __cpu_to_virtio32(vhost_is_little_endian(vq), val);
+}
+
+static inline u64 vhost64_to_cpu(struct vhost_virtqueue *vq, __virtio64 val)
+{
+	return __virtio64_to_cpu(vhost_is_little_endian(vq), val);
+}
+
+static inline __virtio64 cpu_to_vhost64(struct vhost_virtqueue *vq, u64 val)
+{
+	return __cpu_to_virtio64(vhost_is_little_endian(vq), val);
+}
+#endif