From: Jason Wang <jasowang@redhat.com>
To: mst@redhat.com, jasowang@redhat.com,
linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
virtualization@lists.linux-foundation.org,
netdev@vger.kernel.org
Cc: tiwei.bie@intel.com, jgg@mellanox.com,
maxime.coquelin@redhat.com, cunming.liang@intel.com,
zhihong.wang@intel.com, rob.miller@broadcom.com,
xiao.w.wang@intel.com, haotian.wang@sifive.com,
lingshan.zhu@intel.com, eperezma@redhat.com, lulu@redhat.com,
parav@mellanox.com, kevin.tian@intel.com, stefanha@redhat.com,
rdunlap@infradead.org, hch@infradead.org, aadam@redhat.com,
jakub.kicinski@netronome.com, jiri@mellanox.com,
shahafs@mellanox.com, hanand@xilinx.com, mhabets@solarflare.com
Subject: [PATCH 4/5] virtio: introduce a vDPA based transport
Date: Thu, 16 Jan 2020 20:42:30 +0800 [thread overview]
Message-ID: <20200116124231.20253-5-jasowang@redhat.com> (raw)
In-Reply-To: <20200116124231.20253-1-jasowang@redhat.com>
This patch introduces a vDPA transport for virtio. This is used to
use kernel virtio driver to drive the mediated device that is capable
of populating virtqueue directly.
A new virtio-vdpa driver will be registered to the vDPA bus, when a
new virtio-vdpa device is probed, it will register the device with
vdpa based config ops. This means it is a software transport between
vDPA driver and vDPA device. The transport was implemented through
bus_ops of vDPA parent.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/virtio/Kconfig | 13 ++
drivers/virtio/Makefile | 1 +
drivers/virtio/virtio_vdpa.c | 400 +++++++++++++++++++++++++++++++++++
3 files changed, 414 insertions(+)
create mode 100644 drivers/virtio/virtio_vdpa.c
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 9c4fdb64d9ac..b4276999d17d 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -43,6 +43,19 @@ config VIRTIO_PCI_LEGACY
If unsure, say Y.
+config VIRTIO_VDPA
+ tristate "vDPA driver for virtio devices"
+ depends on VDPA && VIRTIO
+ default n
+ help
+ This driver provides support for virtio based paravirtual
+ device driver over vDPA bus. For this to be useful, you need
+ an appropriate vDPA device implementation that operates on a
+ physical device to allow the datapath of virtio to be
+ offloaded to hardware.
+
+ If unsure, say M.
+
config VIRTIO_PMEM
tristate "Support for virtio pmem driver"
depends on VIRTIO
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index fdf5eacd0d0a..3407ac03fe60 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -6,4 +6,5 @@ virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
+obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o
obj-$(CONFIG_VDPA) += vdpa/
diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
new file mode 100644
index 000000000000..86936e5e7ec3
--- /dev/null
+++ b/drivers/virtio/virtio_vdpa.c
@@ -0,0 +1,400 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VIRTIO based driver for vDPA device
+ *
+ * Copyright (c) 2020, Red Hat. All rights reserved.
+ * Author: Jason Wang <jasowang@redhat.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/uuid.h>
+#include <linux/virtio.h>
+#include <linux/vdpa.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+
+#define MOD_VERSION "0.1"
+#define MOD_AUTHOR "Jason Wang <jasowang@redhat.com>"
+#define MOD_DESC "vDPA bus driver for virtio devices"
+#define MOD_LICENSE "GPL v2"
+
+#define to_virtio_vdpa_device(dev) \
+ container_of(dev, struct virtio_vdpa_device, vdev)
+
+struct virtio_vdpa_device {
+ struct virtio_device vdev;
+ struct vdpa_device *vdpa;
+ u64 features;
+
+ /* The lock to protect virtqueue list */
+ spinlock_t lock;
+ /* List of virtio_vdpa_vq_info */
+ struct list_head virtqueues;
+};
+
+struct virtio_vdpa_vq_info {
+ /* the actual virtqueue */
+ struct virtqueue *vq;
+
+ /* the list node for the virtqueues list */
+ struct list_head node;
+};
+
+static struct vdpa_device *vd_get_vdpa(struct virtio_device *vdev)
+{
+ struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
+ struct vdpa_device *vdpa = vd_dev->vdpa;
+
+ return vdpa;
+}
+
+static void virtio_vdpa_get(struct virtio_device *vdev, unsigned offset,
+ void *buf, unsigned len)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ ops->get_config(vdpa, offset, buf, len);
+}
+
+static void virtio_vdpa_set(struct virtio_device *vdev, unsigned offset,
+ const void *buf, unsigned len)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ ops->set_config(vdpa, offset, buf, len);
+}
+
+static u32 virtio_vdpa_generation(struct virtio_device *vdev)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ if (ops->get_generation)
+ return ops->get_generation(vdpa);
+
+ return 0;
+}
+
+static u8 virtio_vdpa_get_status(struct virtio_device *vdev)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ return ops->get_status(vdpa);
+}
+
+static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ return ops->set_status(vdpa, status);
+}
+
+static void virtio_vdpa_reset(struct virtio_device *vdev)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ return ops->set_status(vdpa, 0);
+}
+
+static bool virtio_vdpa_notify(struct virtqueue *vq)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vq->vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ ops->kick_vq(vdpa, vq->index);
+
+ return true;
+}
+
+static irqreturn_t virtio_vdpa_config_cb(void *private)
+{
+ struct virtio_vdpa_device *vd_dev = private;
+
+ virtio_config_changed(&vd_dev->vdev);
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t virtio_vdpa_virtqueue_cb(void *private)
+{
+ struct virtio_vdpa_vq_info *info = private;
+
+ return vring_interrupt(0, info->vq);
+}
+
+static struct virtqueue *
+virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index,
+ void (*callback)(struct virtqueue *vq),
+ const char *name, bool ctx)
+{
+ struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+ struct virtio_vdpa_vq_info *info;
+ struct vdpa_callback cb;
+ struct virtqueue *vq;
+ u64 desc_addr, driver_addr, device_addr;
+ unsigned long flags;
+ u32 align, num;
+ int err;
+
+ if (!name)
+ return NULL;
+
+ /* Queue shouldn't already be set up. */
+ if (ops->get_vq_ready(vdpa, index))
+ return ERR_PTR(-ENOENT);
+
+ /* Allocate and fill out our active queue description */
+ info = kmalloc(sizeof(*info), GFP_KERNEL);
+ if (!info)
+ return ERR_PTR(-ENOMEM);
+
+ num = ops->get_vq_num_max(vdpa);
+ if (num == 0) {
+ err = -ENOENT;
+ goto error_new_virtqueue;
+ }
+
+ /* Create the vring */
+ align = ops->get_vq_align(vdpa);
+ vq = vring_create_virtqueue(index, num, align, vdev,
+ true, true, ctx,
+ virtio_vdpa_notify, callback, name);
+ if (!vq) {
+ err = -ENOMEM;
+ goto error_new_virtqueue;
+ }
+
+ /* Setup virtqueue callback */
+ cb.callback = virtio_vdpa_virtqueue_cb;
+ cb.private = info;
+ ops->set_vq_cb(vdpa, index, &cb);
+ ops->set_vq_num(vdpa, index, virtqueue_get_vring_size(vq));
+
+ desc_addr = virtqueue_get_desc_addr(vq);
+ driver_addr = virtqueue_get_avail_addr(vq);
+ device_addr = virtqueue_get_used_addr(vq);
+
+ if (ops->set_vq_address(vdpa, index,
+ desc_addr, driver_addr,
+ device_addr)) {
+ err = -EINVAL;
+ goto err_vq;
+ }
+
+ ops->set_vq_ready(vdpa, index, 1);
+
+ vq->priv = info;
+ info->vq = vq;
+
+ spin_lock_irqsave(&vd_dev->lock, flags);
+ list_add(&info->node, &vd_dev->virtqueues);
+ spin_unlock_irqrestore(&vd_dev->lock, flags);
+
+ return vq;
+
+err_vq:
+ vring_del_virtqueue(vq);
+error_new_virtqueue:
+ ops->set_vq_ready(vdpa, index, 0);
+ WARN_ON(ops->get_vq_ready(vdpa, index));
+ kfree(info);
+ return ERR_PTR(err);
+}
+
+static void virtio_vdpa_del_vq(struct virtqueue *vq)
+{
+ struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vq->vdev);
+ struct vdpa_device *vdpa = vd_dev->vdpa;
+ const struct vdpa_config_ops *ops = vdpa->config;
+ struct virtio_vdpa_vq_info *info = vq->priv;
+ unsigned int index = vq->index;
+ unsigned long flags;
+
+ spin_lock_irqsave(&vd_dev->lock, flags);
+ list_del(&info->node);
+ spin_unlock_irqrestore(&vd_dev->lock, flags);
+
+ /* Select and deactivate the queue */
+ ops->set_vq_ready(vdpa, index, 0);
+ WARN_ON(ops->get_vq_ready(vdpa, index));
+
+ vring_del_virtqueue(vq);
+
+ kfree(info);
+}
+
+static void virtio_vdpa_del_vqs(struct virtio_device *vdev)
+{
+ struct virtqueue *vq, *n;
+
+ list_for_each_entry_safe(vq, n, &vdev->vqs, list)
+ virtio_vdpa_del_vq(vq);
+}
+
+static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+ struct virtqueue *vqs[],
+ vq_callback_t *callbacks[],
+ const char * const names[],
+ const bool *ctx,
+ struct irq_affinity *desc)
+{
+ struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+ struct vdpa_callback cb;
+ int i, err, queue_idx = 0;
+
+ for (i = 0; i < nvqs; ++i) {
+ if (!names[i]) {
+ vqs[i] = NULL;
+ continue;
+ }
+
+ vqs[i] = virtio_vdpa_setup_vq(vdev, queue_idx++,
+ callbacks[i], names[i], ctx ?
+ ctx[i] : false);
+ if (IS_ERR(vqs[i])) {
+ err = PTR_ERR(vqs[i]);
+ goto err_setup_vq;
+ }
+ }
+
+ cb.callback = virtio_vdpa_config_cb;
+ cb.private = vd_dev;
+ ops->set_config_cb(vdpa, &cb);
+
+ return 0;
+
+err_setup_vq:
+ virtio_vdpa_del_vqs(vdev);
+ return err;
+}
+
+static u64 virtio_vdpa_get_features(struct virtio_device *vdev)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ return ops->get_features(vdpa);
+}
+
+static int virtio_vdpa_finalize_features(struct virtio_device *vdev)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ /* Give virtio_ring a chance to accept features. */
+ vring_transport_features(vdev);
+
+ return ops->set_features(vdpa, vdev->features);
+}
+
+static const char *virtio_vdpa_bus_name(struct virtio_device *vdev)
+{
+ struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
+ struct vdpa_device *vdpa = vd_dev->vdpa;
+
+ return dev_name(vdpa_to_dev(vdpa));
+}
+
+static const struct virtio_config_ops virtio_vdpa_config_ops = {
+ .get = virtio_vdpa_get,
+ .set = virtio_vdpa_set,
+ .generation = virtio_vdpa_generation,
+ .get_status = virtio_vdpa_get_status,
+ .set_status = virtio_vdpa_set_status,
+ .reset = virtio_vdpa_reset,
+ .find_vqs = virtio_vdpa_find_vqs,
+ .del_vqs = virtio_vdpa_del_vqs,
+ .get_features = virtio_vdpa_get_features,
+ .finalize_features = virtio_vdpa_finalize_features,
+ .bus_name = virtio_vdpa_bus_name,
+};
+
+static void virtio_vdpa_release_dev(struct device *_d)
+{
+ struct virtio_device *vdev =
+ container_of(_d, struct virtio_device, dev);
+ struct virtio_vdpa_device *vd_dev =
+ container_of(vdev, struct virtio_vdpa_device, vdev);
+ struct vdpa_device *vdpa = vd_dev->vdpa;
+
+ devm_kfree(&vdpa->dev, vd_dev);
+}
+
+static int virtio_vdpa_probe(struct device *dev)
+{
+ struct vdpa_device *vdpa = dev_to_vdpa(dev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+ struct virtio_vdpa_device *vd_dev;
+ int rc;
+
+ vd_dev = devm_kzalloc(dev, sizeof(*vd_dev), GFP_KERNEL);
+ if (!vd_dev)
+ return -ENOMEM;
+
+ vd_dev->vdev.dev.parent = &vdpa->dev;
+ vd_dev->vdev.dev.release = virtio_vdpa_release_dev;
+ vd_dev->vdev.config = &virtio_vdpa_config_ops;
+ vd_dev->vdpa = vdpa;
+ INIT_LIST_HEAD(&vd_dev->virtqueues);
+ spin_lock_init(&vd_dev->lock);
+
+ vd_dev->vdev.id.device = ops->get_device_id(vdpa);
+ if (vd_dev->vdev.id.device == 0)
+ return -ENODEV;
+
+ vd_dev->vdev.id.vendor = ops->get_vendor_id(vdpa);
+ rc = register_virtio_device(&vd_dev->vdev);
+ if (rc)
+ put_device(dev);
+ else
+ dev_set_drvdata(dev, vd_dev);
+
+ return rc;
+}
+
+static void virtio_vdpa_remove(struct device *dev)
+{
+ struct virtio_vdpa_device *vd_dev = dev_get_drvdata(dev);
+
+ unregister_virtio_device(&vd_dev->vdev);
+}
+
+static struct vdpa_driver virtio_vdpa_driver = {
+ .drv = {
+ .name = "virtio_vdpa",
+ },
+ .probe = virtio_vdpa_probe,
+ .remove = virtio_vdpa_remove,
+};
+
+static int __init virtio_vdpa_init(void)
+{
+ return register_vdpa_driver(&virtio_vdpa_driver);
+}
+
+static void __exit virtio_vdpa_exit(void)
+{
+ unregister_vdpa_driver(&virtio_vdpa_driver);
+}
+
+module_init(virtio_vdpa_init)
+module_exit(virtio_vdpa_exit)
+
+MODULE_VERSION(MOD_VERSION);
+MODULE_LICENSE(MOD_LICENSE);
+MODULE_AUTHOR(MOD_AUTHOR);
+MODULE_DESCRIPTION(MOD_DESC);
--
2.19.1
next prev parent reply other threads:[~2020-01-16 12:43 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-16 12:42 [PATCH 0/5] vDPA support Jason Wang
2020-01-16 12:42 ` [PATCH 1/5] vhost: factor out IOTLB Jason Wang
2020-01-17 4:14 ` Randy Dunlap
2020-01-17 9:34 ` Jason Wang
2020-01-18 0:01 ` kbuild test robot
2020-01-18 0:40 ` kbuild test robot
2020-01-16 12:42 ` [PATCH 2/5] vringh: IOTLB support Jason Wang
2020-01-17 21:54 ` kbuild test robot
2020-01-17 22:33 ` kbuild test robot
2020-01-16 12:42 ` [PATCH 3/5] vDPA: introduce vDPA bus Jason Wang
2020-01-16 15:22 ` Jason Gunthorpe
2020-01-17 3:03 ` Jason Wang
2020-01-17 13:54 ` Jason Gunthorpe
2020-01-20 7:50 ` Jason Wang
2020-01-20 12:17 ` Michael S. Tsirkin
2020-01-20 17:50 ` Jason Gunthorpe
2020-01-20 21:56 ` Michael S. Tsirkin
2020-01-21 14:12 ` Jason Gunthorpe
2020-01-21 14:15 ` Michael S. Tsirkin
2020-01-21 14:16 ` Jason Gunthorpe
2020-01-21 8:40 ` Tian, Kevin
2020-01-21 9:41 ` Jason Wang
2020-01-17 4:16 ` Randy Dunlap
2020-01-17 9:34 ` Jason Wang
2020-01-17 12:13 ` Michael S. Tsirkin
2020-01-17 13:52 ` Jason Wang
[not found] ` <CAJPjb1+fG9L3=iKbV4Vn13VwaeDZZdcfBPvarogF_Nzhk+FnKg@mail.gmail.com>
2020-01-19 9:07 ` Shahaf Shuler
2020-01-19 9:59 ` Michael S. Tsirkin
2020-01-20 8:44 ` Jason Wang
2020-01-20 12:09 ` Michael S. Tsirkin
2020-01-21 3:32 ` Jason Wang
2020-01-20 8:43 ` Jason Wang
2020-01-20 17:49 ` Jason Gunthorpe
2020-01-20 20:51 ` Shahaf Shuler
2020-01-20 21:25 ` Michael S. Tsirkin
2020-01-20 21:47 ` Shahaf Shuler
2020-01-20 21:59 ` Michael S. Tsirkin
2020-01-21 6:01 ` Shahaf Shuler
2020-01-21 7:57 ` Jason Wang
2020-01-21 14:07 ` Jason Gunthorpe
2020-01-21 14:16 ` Michael S. Tsirkin
2020-01-20 21:48 ` Michael S. Tsirkin
2020-01-21 4:00 ` Jason Wang
2020-01-21 5:47 ` Michael S. Tsirkin
2020-01-21 8:00 ` Jason Wang
2020-01-21 8:15 ` Michael S. Tsirkin
2020-01-21 8:35 ` Jason Wang
2020-01-21 11:09 ` Shahaf Shuler
2020-01-22 6:36 ` Jason Wang
2020-01-21 14:05 ` Jason Gunthorpe
2020-01-21 14:17 ` Michael S. Tsirkin
2020-01-22 6:18 ` Jason Wang
2020-01-20 8:19 ` Jason Wang
2020-01-16 12:42 ` Jason Wang [this message]
2020-01-16 15:38 ` [PATCH 4/5] virtio: introduce a vDPA based transport Jason Gunthorpe
2020-01-17 9:32 ` Jason Wang
2020-01-17 14:00 ` Jason Gunthorpe
2020-01-20 7:52 ` Jason Wang
2020-01-17 4:10 ` Randy Dunlap
2020-01-16 12:42 ` [PATCH 5/5] vdpasim: vDPA device simulator Jason Wang
2020-01-16 15:47 ` Jason Gunthorpe
2020-01-17 9:32 ` Jason Wang
2020-01-17 14:10 ` Jason Gunthorpe
2020-01-20 8:01 ` Jason Wang
2020-02-04 4:19 ` Jason Wang
2020-01-17 4:12 ` Randy Dunlap
2020-01-17 9:35 ` Jason Wang
2020-01-18 18:18 ` kbuild test robot
2020-01-28 3:32 ` Dan Carpenter
2020-02-04 4:07 ` Jason Wang
2020-02-04 8:21 ` Zhu Lingshan
2020-02-04 8:28 ` Jason Wang
2020-02-04 12:52 ` Jason Gunthorpe
2020-02-05 3:14 ` Jason Wang
2020-01-21 8:44 ` [PATCH 0/5] vDPA support Tian, Kevin
2020-01-21 9:39 ` Jason Wang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200116124231.20253-5-jasowang@redhat.com \
--to=jasowang@redhat.com \
--cc=aadam@redhat.com \
--cc=cunming.liang@intel.com \
--cc=eperezma@redhat.com \
--cc=hanand@xilinx.com \
--cc=haotian.wang@sifive.com \
--cc=hch@infradead.org \
--cc=jakub.kicinski@netronome.com \
--cc=jgg@mellanox.com \
--cc=jiri@mellanox.com \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=lingshan.zhu@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lulu@redhat.com \
--cc=maxime.coquelin@redhat.com \
--cc=mhabets@solarflare.com \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=parav@mellanox.com \
--cc=rdunlap@infradead.org \
--cc=rob.miller@broadcom.com \
--cc=shahafs@mellanox.com \
--cc=stefanha@redhat.com \
--cc=tiwei.bie@intel.com \
--cc=virtualization@lists.linux-foundation.org \
--cc=xiao.w.wang@intel.com \
--cc=zhihong.wang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).