patches for DPDK stable branches
 help / color / Atom feed
From: Tiwei Bie <tiwei.bie@intel.com>
To: Maxime Coquelin <maxime.coquelin@redhat.com>
Cc: zhihong.wang@intel.com, amorenoz@redhat.com,
	xiao.w.wang@intel.com, dev@dpdk.org, jfreimann@redhat.com,
	stable@dpdk.org
Subject: Re: [dpdk-stable] [PATCH 10/15] net/virtio: add vDPA op to configure and start the device
Date: Tue, 3 Sep 2019 13:30:06 +0800
Message-ID: <20190903053006.GA32701@___> (raw)
In-Reply-To: <20190829080000.20806-11-maxime.coquelin@redhat.com>

On Thu, Aug 29, 2019 at 09:59:55AM +0200, Maxime Coquelin wrote:
> In order to support multi-queue, we need to implement the control
> path. The problem is that both the Vhost-user master and slave use
> VAs in their processes address spaces as IOVAs, which creates
> collusions between the data rings IOVAs managed the master, and
> the Control ring IOVAs. The trick here is to remmap the Control
> ring memory to another range, after the slave is aware of master's
> ranges.
> 
> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> ---
>  drivers/net/virtio/virtio_vdpa.c | 255 +++++++++++++++++++++++++++++++
>  1 file changed, 255 insertions(+)
> 
> diff --git a/drivers/net/virtio/virtio_vdpa.c b/drivers/net/virtio/virtio_vdpa.c
> index fc52a8e92..13b4dd07d 100644
> --- a/drivers/net/virtio/virtio_vdpa.c
> +++ b/drivers/net/virtio/virtio_vdpa.c
> @@ -106,6 +106,127 @@ find_internal_resource_by_dev(struct rte_pci_device *pdev)
>  	return list;
>  }
>  
> +static int
> +virtio_vdpa_dma_map_ctrl_queue(struct virtio_vdpa_device *dev, int do_map,
> +		uint64_t iova)
> +{
> +	const struct rte_memzone *mz;
> +	int ret;
> +
> +	/*
> +	 * IOVAs are processes VAs. We cannot use them as the Data and Control
> +	 * paths are run in different processes, which may (does) lead to
> +	 * collusions. The trick here is to fixup Ctrl path IOVAs so that they
> +	 * start after the Data path ranges.
> +	 */
> +	if (do_map) {
> +		mz = dev->cvq->cq.mz;
> +		ret = rte_vfio_container_dma_map(dev->vfio_container_fd,
> +				(uint64_t)(uintptr_t)mz->addr,
> +				iova, mz->len);
> +		if (ret < 0) {
> +			DRV_LOG(ERR, "Failed to map ctrl ring (%d)", ret);
> +			return ret;
> +		}
> +
> +		dev->cvq->vq_ring_mem = iova;
> +		iova += mz->len;
> +
> +		mz = dev->cvq->cq.virtio_net_hdr_mz;
> +		ret = rte_vfio_container_dma_map(dev->vfio_container_fd,
> +				(uint64_t)(uintptr_t)mz->addr,
> +				iova, mz->len);
> +		if (ret < 0) {
> +			DRV_LOG(ERR, "Failed to map ctrl headers (%d)", ret);
> +			return ret;
> +		}

This will allow guest to access the cq.mz and cq.virtio_net_hdr_mz
via the device which may have potential risks.

Regards,
Tiwei

> +
> +		dev->cvq->cq.virtio_net_hdr_mem = iova;
> +	} else {
> +		mz = dev->cvq->cq.mz;
> +		ret = rte_vfio_container_dma_unmap(dev->vfio_container_fd,
> +				(uint64_t)(uintptr_t)mz->addr,
> +				iova, mz->len);
> +		if (ret < 0) {
> +			DRV_LOG(ERR, "Failed to unmap ctrl ring (%d)", ret);
> +			return ret;
> +		}
> +
> +		dev->cvq->vq_ring_mem = 0;
> +		iova += mz->len;
> +
> +		mz = dev->cvq->cq.virtio_net_hdr_mz;
> +		ret = rte_vfio_container_dma_unmap(dev->vfio_container_fd,
> +				(uint64_t)(uintptr_t)mz->addr,
> +				iova, mz->len);
> +		if (ret < 0) {
> +			DRV_LOG(ERR, "Failed to unmap ctrl headers (%d)", ret);
> +			return ret;
> +		}
> +
> +		dev->cvq->cq.virtio_net_hdr_mem = 0;
> +	}
> +
> +	return 0;
> +}
> +
> +static int
> +virtio_vdpa_dma_map(struct virtio_vdpa_device *dev, int do_map)
> +{
> +	uint32_t i;
> +	int ret;
> +	struct rte_vhost_memory *mem = NULL;
> +	int vfio_container_fd;
> +	uint64_t avail_iova = 0;
> +
> +	ret = rte_vhost_get_mem_table(dev->vid, &mem);
> +	if (ret < 0 || !mem) {
> +		DRV_LOG(ERR, "failed to get VM memory layout.");
> +		return ret;
> +	}
> +
> +	vfio_container_fd = dev->vfio_container_fd;
> +
> +	for (i = 0; i < mem->nregions; i++) {
> +		struct rte_vhost_mem_region *reg;
> +
> +		reg = &mem->regions[i];
> +		DRV_LOG(INFO, "%s, region %u: HVA 0x%" PRIx64 ", "
> +			"GPA 0x%" PRIx64 ", size 0x%" PRIx64 ".",
> +			do_map ? "DMA map" : "DMA unmap", i,
> +			reg->host_user_addr, reg->guest_phys_addr, reg->size);
> +
> +		if (reg->guest_phys_addr + reg->size > avail_iova)
> +			avail_iova = reg->guest_phys_addr + reg->size;
> +
> +		if (do_map) {
> +			ret = rte_vfio_container_dma_map(vfio_container_fd,
> +				reg->host_user_addr, reg->guest_phys_addr,
> +				reg->size);
> +			if (ret < 0) {
> +				DRV_LOG(ERR, "DMA map failed.");
> +				goto exit;
> +			}
> +		} else {
> +			ret = rte_vfio_container_dma_unmap(vfio_container_fd,
> +				reg->host_user_addr, reg->guest_phys_addr,
> +				reg->size);
> +			if (ret < 0) {
> +				DRV_LOG(ERR, "DMA unmap failed.");
> +				goto exit;
> +			}
> +		}
> +	}
> +
> +	if (dev->cvq)
> +		ret = virtio_vdpa_dma_map_ctrl_queue(dev, do_map, avail_iova);
> +
> +exit:
> +	free(mem);
> +
> +	return ret;
> +}
> +
>  static int
>  virtio_vdpa_vfio_setup(struct virtio_vdpa_device *dev)
>  {
> @@ -216,10 +337,144 @@ virtio_vdpa_get_protocol_features(int did __rte_unused, uint64_t *features)
>  	return 0;
>  }
>  
> +static uint64_t
> +hva_to_gpa(int vid, uint64_t hva)
> +{
> +	struct rte_vhost_memory *mem = NULL;
> +	struct rte_vhost_mem_region *reg;
> +	uint32_t i;
> +	uint64_t gpa = 0;
> +
> +	if (rte_vhost_get_mem_table(vid, &mem) < 0)
> +		goto exit;
> +
> +	for (i = 0; i < mem->nregions; i++) {
> +		reg = &mem->regions[i];
> +
> +		if (hva >= reg->host_user_addr &&
> +				hva < reg->host_user_addr + reg->size) {
> +			gpa = hva - reg->host_user_addr + reg->guest_phys_addr;
> +			break;
> +		}
> +	}
> +
> +exit:
> +	if (mem)
> +		free(mem);
> +	return gpa;
> +}
> +
> +static int
> +virtio_vdpa_start(struct virtio_vdpa_device *dev)
> +{
> +	struct virtio_hw *hw = &dev->hw;
> +	int i, vid, nr_vring, ret;
> +	struct rte_vhost_vring vr;
> +	struct virtio_pmd_ctrl ctrl;
> +	int dlen[1];
> +
> +	vid = dev->vid;
> +	nr_vring = rte_vhost_get_vring_num(vid);
> +
> +	if (dev->vqs)
> +		rte_free(dev->vqs);
> +
> +	dev->vqs = rte_zmalloc("virtio_vdpa", sizeof(*dev->vqs) * nr_vring, 0);
> +
> +	for (i = 0; i < nr_vring; i++) {
> +		struct virtqueue *vq = &dev->vqs[i];
> +
> +		rte_vhost_get_vhost_vring(vid, i, &vr);
> +
> +		vq->vq_queue_index = i;
> +		vq->vq_nentries = vr.size;
> +		vq->vq_ring_mem = hva_to_gpa(vid, (uint64_t)(uintptr_t)vr.desc);
> +		if (vq->vq_ring_mem  == 0) {
> +			DRV_LOG(ERR, "Fail to get GPA for descriptor ring.");
> +			ret = -1;
> +			goto out_free_vqs;
> +		}
> +
> +		ret = VTPCI_OPS(hw)->setup_queue(hw, vq);
> +		if (ret) {
> +			DRV_LOG(ERR, "Fail to setup queue.");
> +			goto out_free_vqs;
> +		}
> +	}
> +
> +	if (dev->cvq) {
> +		ret = VTPCI_OPS(hw)->setup_queue(hw, dev->cvq);
> +		if (ret) {
> +			DRV_LOG(ERR, "Fail to setup ctrl queue.");
> +			goto out_free_vqs;
> +		}
> +	}
> +
> +	vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_DRIVER_OK);
> +
> +	if (!dev->cvq)
> +		return 0;
> +
> +	ctrl.hdr.class = VIRTIO_NET_CTRL_MQ;
> +	ctrl.hdr.cmd = VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET;
> +	memcpy(ctrl.data, &dev->max_queue_pairs, sizeof(uint16_t));
> +
> +	dlen[0] = sizeof(uint16_t);
> +
> +	ret = virtio_send_command(hw->cvq, &ctrl, dlen, 1);
> +	if (ret) {
> +		DRV_LOG(ERR, "Multiqueue configured but send command "
> +			  "failed, this is too late now...");
> +		ret = -EINVAL;
> +		goto out_free_vqs;
> +	}
> +
> +	return 0;
> +out_free_vqs:
> +	rte_free(dev->vqs);
> +
> +	return ret;
> +}
> +
> +static int
> +virtio_vdpa_dev_config(int vid)
> +{
> +	int did, ret;
> +	struct internal_list *list;
> +	struct virtio_vdpa_device *dev;
> +
> +	did = rte_vhost_get_vdpa_device_id(vid);
> +	list = find_internal_resource_by_did(did);
> +	if (list == NULL) {
> +		DRV_LOG(ERR, "Invalid device id: %d", did);
> +		return -1;
> +	}
> +
> +	dev = list->dev;
> +	dev->vid = vid;
> +
> +	rte_spinlock_lock(&dev->lock);
> +
> +	ret = virtio_vdpa_dma_map(dev, 1);
> +	if (ret)
> +		goto out_unlock;
> +
> +	ret = virtio_vdpa_start(dev);
> +
> +	if (rte_vhost_host_notifier_ctrl(vid, true) != 0)
> +		DRV_LOG(NOTICE, "vDPA (%d): software relay is used.", did);
> +
> +out_unlock:
> +	rte_spinlock_unlock(&dev->lock);
> +
> +	return ret;
> +}
> +
>  static struct rte_vdpa_dev_ops virtio_vdpa_ops = {
>  	.get_queue_num = virtio_vdpa_get_queue_num,
>  	.get_features = virtio_vdpa_get_features,
>  	.get_protocol_features = virtio_vdpa_get_protocol_features,
> +	.dev_conf = virtio_vdpa_dev_config,
>  };
>  
>  static inline int
> -- 
> 2.21.0
> 

  reply index

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-29  7:59 [dpdk-stable] [PATCH 00/15] Introduce Virtio vDPA driver Maxime Coquelin
2019-08-29  7:59 ` [dpdk-stable] [PATCH 01/15] vhost: remove vhost kernel header inclusion Maxime Coquelin
2019-09-02  6:03   ` Tiwei Bie
2019-09-03  7:24     ` Maxime Coquelin
2019-08-29  7:59 ` [dpdk-stable] [PATCH 02/15] vhost: configure vDPA as soon as the device is ready Maxime Coquelin
2019-09-02  8:34   ` Ye Xiaolong
2019-09-02  9:02     ` Wang, Xiao W
2019-09-03  7:34       ` Maxime Coquelin
2019-09-03 10:58         ` Wang, Xiao W
2019-08-29  7:59 ` [dpdk-stable] [PATCH 03/15] net/virtio: move control path fonctions in virtqueue file Maxime Coquelin
2019-09-02  6:05   ` Tiwei Bie
2019-08-29  7:59 ` [dpdk-stable] [PATCH 04/15] net/virtio: add virtio PCI subsystem device ID declaration Maxime Coquelin
2019-09-02  6:14   ` Tiwei Bie
2019-09-03  7:25     ` Maxime Coquelin
2019-08-29  7:59 ` [dpdk-stable] [PATCH 05/15] net/virtio: save notify bar ID in virtio HW struct Maxime Coquelin
2019-09-02  6:17   ` Tiwei Bie
2019-08-29  7:59 ` [dpdk-stable] [PATCH 06/15] net/virtio: add skeleton for virtio vDPA driver Maxime Coquelin
2019-09-02  6:27   ` Tiwei Bie
2019-09-03  7:25     ` Maxime Coquelin
2019-08-29  7:59 ` [dpdk-stable] [PATCH 07/15] net/virtio: add vDPA ops to get number of queue Maxime Coquelin
2019-09-02  6:32   ` Tiwei Bie
2019-08-29  7:59 ` [dpdk-stable] [PATCH 08/15] net/virtio: add virtio vDPA op to get features Maxime Coquelin
2019-09-02  6:43   ` Tiwei Bie
2019-09-03  7:27     ` Maxime Coquelin
2019-08-29  7:59 ` [dpdk-stable] [PATCH 09/15] net/virtio: add virtio vDPA op to get protocol features Maxime Coquelin
2019-09-02  6:46   ` Tiwei Bie
2019-08-29  7:59 ` [dpdk-stable] [PATCH 10/15] net/virtio: add vDPA op to configure and start the device Maxime Coquelin
2019-09-03  5:30   ` Tiwei Bie [this message]
2019-09-03  7:40     ` Maxime Coquelin
2019-09-03  8:49       ` Tiwei Bie
2019-09-04  4:06         ` Jason Wang
2019-09-04  6:56           ` Maxime Coquelin
2019-09-05  2:57             ` Tiwei Bie
2019-08-29  7:59 ` [dpdk-stable] [PATCH 11/15] net/virtio: add vDPA op to stop and close " Maxime Coquelin
2019-09-02  7:07   ` Tiwei Bie
2019-09-03  7:30     ` Maxime Coquelin
2019-08-29  7:59 ` [dpdk-stable] [PATCH 12/15] net/virtio: add vDPA op to set features Maxime Coquelin
2019-08-29  7:59 ` [dpdk-stable] [PATCH 13/15] net/virtio: add vDPA ops to get VFIO FDs Maxime Coquelin
2019-09-03  4:47   ` Tiwei Bie
2019-08-29  7:59 ` [dpdk-stable] [PATCH 14/15] net/virtio: add vDPA op to get notification area Maxime Coquelin
2019-09-03  5:02   ` Tiwei Bie
2019-09-03  7:36     ` Maxime Coquelin
2019-09-03  8:40       ` Tiwei Bie
2019-08-29  8:00 ` [dpdk-stable] [PATCH 15/15] doc: add documentation for Virtio vDPA driver Maxime Coquelin
2019-09-09 11:55 ` [dpdk-stable] [dpdk-dev] [PATCH 00/15] Introduce " Shahaf Shuler
2019-09-10  7:46   ` Maxime Coquelin
2019-09-10 13:44     ` Shahaf Shuler
2019-09-10 13:56       ` Maxime Coquelin
2019-09-11  5:15         ` Shahaf Shuler
2019-09-11  7:15           ` Maxime Coquelin
2019-10-24  6:32 ` [dpdk-stable] " Maxime Coquelin

Reply instructions:

You may reply publically 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=20190903053006.GA32701@___ \
    --to=tiwei.bie@intel.com \
    --cc=amorenoz@redhat.com \
    --cc=dev@dpdk.org \
    --cc=jfreimann@redhat.com \
    --cc=maxime.coquelin@redhat.com \
    --cc=stable@dpdk.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

patches for DPDK stable branches

Archives are clonable:
	git clone --mirror http://inbox.dpdk.org/stable/0 stable/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 stable stable/ http://inbox.dpdk.org/stable \
		stable@dpdk.org
	public-inbox-index stable


Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.stable


AGPL code for this site: git clone https://public-inbox.org/ public-inbox