Xuan Zhuo
2022-Mar-08 12:35 UTC
[PATCH v7 09/26] virtio_ring: split: implement virtqueue_reset_vring_split()
virtio ring supports reset.
Queue reset is divided into several stages.
1. notify device queue reset
2. vring release
3. attach new vring
4. notify device queue re-enable
After the first step is completed, the vring reset operation can be
performed. If the newly set vring num does not change, then just reset
the vq related value.
Otherwise, the vring will be released and the vring will be reallocated.
And the vring will be attached to the vq. If this process fails, the
function will exit, and the state of the vq will be the vring release
state. You can call this function again to reallocate the vring.
In addition, vring_align, may_reduce_num are necessary for reallocating
vring, so they are retained when creating vq.
Signed-off-by: Xuan Zhuo <xuanzhuo at linux.alibaba.com>
---
drivers/virtio/virtio_ring.c | 69 ++++++++++++++++++++++++++++++++++++
1 file changed, 69 insertions(+)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index e0422c04c903..148fb1fd3d5a 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -158,6 +158,12 @@ struct vring_virtqueue {
/* DMA address and size information */
dma_addr_t queue_dma_addr;
size_t queue_size_in_bytes;
+
+ /* The parameters for creating vrings are reserved for
+ * creating new vrings when enabling reset queue.
+ */
+ u32 vring_align;
+ bool may_reduce_num;
} split;
/* Available for packed ring */
@@ -217,6 +223,12 @@ struct vring_virtqueue {
#endif
};
+static void vring_free(struct virtqueue *vq);
+static void __vring_virtqueue_init_split(struct vring_virtqueue *vq,
+ struct virtio_device *vdev);
+static int __vring_virtqueue_attach_split(struct vring_virtqueue *vq,
+ struct virtio_device *vdev,
+ struct vring vring);
/*
* Helpers.
@@ -1012,6 +1024,8 @@ static struct virtqueue *vring_create_virtqueue_split(
return NULL;
}
+ to_vvq(vq)->split.vring_align = vring_align;
+ to_vvq(vq)->split.may_reduce_num = may_reduce_num;
to_vvq(vq)->split.queue_dma_addr = vring.dma_addr;
to_vvq(vq)->split.queue_size_in_bytes = vring.queue_size_in_bytes;
to_vvq(vq)->we_own_ring = true;
@@ -1019,6 +1033,59 @@ static struct virtqueue *vring_create_virtqueue_split(
return vq;
}
+static int virtqueue_reset_vring_split(struct virtqueue *_vq, u32 num)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ struct virtio_device *vdev = _vq->vdev;
+ struct vring_split vring;
+ int err;
+
+ if (num > _vq->num_max)
+ return -E2BIG;
+
+ switch (vq->vq.reset) {
+ case VIRTIO_VQ_RESET_STEP_NONE:
+ return -ENOENT;
+
+ case VIRTIO_VQ_RESET_STEP_VRING_ATTACH:
+ case VIRTIO_VQ_RESET_STEP_DEVICE:
+ if (vq->split.vring.num == num || !num)
+ break;
+
+ vring_free(_vq);
+
+ fallthrough;
+
+ case VIRTIO_VQ_RESET_STEP_VRING_RELEASE:
+ if (!num)
+ num = vq->split.vring.num;
+
+ err = vring_create_vring_split(&vring, vdev,
+ vq->split.vring_align,
+ vq->weak_barriers,
+ vq->split.may_reduce_num, num);
+ if (err)
+ return -ENOMEM;
+
+ err = __vring_virtqueue_attach_split(vq, vdev, vring.vring);
+ if (err) {
+ vring_free_queue(vdev, vring.queue_size_in_bytes,
+ vring.queue,
+ vring.dma_addr);
+ return -ENOMEM;
+ }
+
+ vq->split.queue_dma_addr = vring.dma_addr;
+ vq->split.queue_size_in_bytes = vring.queue_size_in_bytes;
+ }
+
+ __vring_virtqueue_init_split(vq, vdev);
+ vq->we_own_ring = true;
+ vq->vq.reset = VIRTIO_VQ_RESET_STEP_VRING_ATTACH;
+
+ return 0;
+}
+
/*
* Packed ring specific functions - *_packed().
@@ -2317,6 +2384,8 @@ static int __vring_virtqueue_attach_split(struct
vring_virtqueue *vq,
static void __vring_virtqueue_init_split(struct vring_virtqueue *vq,
struct virtio_device *vdev)
{
+ vq->vq.reset = VIRTIO_VQ_RESET_STEP_NONE;
+
vq->packed_ring = false;
vq->we_own_ring = false;
vq->broken = false;
--
2.31.0
Jason Wang
2022-Mar-09 07:55 UTC
[PATCH v7 09/26] virtio_ring: split: implement virtqueue_reset_vring_split()
? 2022/3/8 ??8:35, Xuan Zhuo ??:> virtio ring supports reset. > > Queue reset is divided into several stages. > > 1. notify device queue reset > 2. vring release > 3. attach new vring > 4. notify device queue re-enable > > After the first step is completed, the vring reset operation can be > performed. If the newly set vring num does not change, then just reset > the vq related value. > > Otherwise, the vring will be released and the vring will be reallocated. > And the vring will be attached to the vq. If this process fails, the > function will exit, and the state of the vq will be the vring release > state. You can call this function again to reallocate the vring. > > In addition, vring_align, may_reduce_num are necessary for reallocating > vring, so they are retained when creating vq. > > Signed-off-by: Xuan Zhuo <xuanzhuo at linux.alibaba.com> > --- > drivers/virtio/virtio_ring.c | 69 ++++++++++++++++++++++++++++++++++++ > 1 file changed, 69 insertions(+) > > diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c > index e0422c04c903..148fb1fd3d5a 100644 > --- a/drivers/virtio/virtio_ring.c > +++ b/drivers/virtio/virtio_ring.c > @@ -158,6 +158,12 @@ struct vring_virtqueue { > /* DMA address and size information */ > dma_addr_t queue_dma_addr; > size_t queue_size_in_bytes; > + > + /* The parameters for creating vrings are reserved for > + * creating new vrings when enabling reset queue. > + */ > + u32 vring_align; > + bool may_reduce_num; > } split; > > /* Available for packed ring */ > @@ -217,6 +223,12 @@ struct vring_virtqueue { > #endif > }; > > +static void vring_free(struct virtqueue *vq); > +static void __vring_virtqueue_init_split(struct vring_virtqueue *vq, > + struct virtio_device *vdev); > +static int __vring_virtqueue_attach_split(struct vring_virtqueue *vq, > + struct virtio_device *vdev, > + struct vring vring); > > /* > * Helpers. > @@ -1012,6 +1024,8 @@ static struct virtqueue *vring_create_virtqueue_split( > return NULL; > } > > + to_vvq(vq)->split.vring_align = vring_align; > + to_vvq(vq)->split.may_reduce_num = may_reduce_num; > to_vvq(vq)->split.queue_dma_addr = vring.dma_addr; > to_vvq(vq)->split.queue_size_in_bytes = vring.queue_size_in_bytes; > to_vvq(vq)->we_own_ring = true; > @@ -1019,6 +1033,59 @@ static struct virtqueue *vring_create_virtqueue_split( > return vq; > } > > +static int virtqueue_reset_vring_split(struct virtqueue *_vq, u32 num) > +{So what this function does is to resize the virtqueue actually, I suggest to rename it as virtqueue_resize_split().> + struct vring_virtqueue *vq = to_vvq(_vq); > + struct virtio_device *vdev = _vq->vdev; > + struct vring_split vring; > + int err; > + > + if (num > _vq->num_max) > + return -E2BIG; > + > + switch (vq->vq.reset) { > + case VIRTIO_VQ_RESET_STEP_NONE: > + return -ENOENT; > + > + case VIRTIO_VQ_RESET_STEP_VRING_ATTACH: > + case VIRTIO_VQ_RESET_STEP_DEVICE: > + if (vq->split.vring.num == num || !num) > + break; > + > + vring_free(_vq); > + > + fallthrough; > + > + case VIRTIO_VQ_RESET_STEP_VRING_RELEASE: > + if (!num) > + num = vq->split.vring.num; > + > + err = vring_create_vring_split(&vring, vdev, > + vq->split.vring_align, > + vq->weak_barriers, > + vq->split.may_reduce_num, num); > + if (err) > + return -ENOMEM;We'd better need a safe fallback here like: If we can't allocate new memory, we can keep using the current one. Otherwise an ethtool -G fail may make the device not usable. This could be done by not freeing the old vring and virtqueue states until new is allocated.> + > + err = __vring_virtqueue_attach_split(vq, vdev, vring.vring); > + if (err) { > + vring_free_queue(vdev, vring.queue_size_in_bytes, > + vring.queue, > + vring.dma_addr); > + return -ENOMEM; > + } > + > + vq->split.queue_dma_addr = vring.dma_addr; > + vq->split.queue_size_in_bytes = vring.queue_size_in_bytes; > + } > + > + __vring_virtqueue_init_split(vq, vdev); > + vq->we_own_ring = true;This seems wrong, we have the transport (rproc/mlxtbf) that allocate the vring by themselves. I think we need to fail the resize for we_own_ring == false. Thanks> + vq->vq.reset = VIRTIO_VQ_RESET_STEP_VRING_ATTACH; > + > + return 0; > +} > + > > /* > * Packed ring specific functions - *_packed(). > @@ -2317,6 +2384,8 @@ static int __vring_virtqueue_attach_split(struct vring_virtqueue *vq, > static void __vring_virtqueue_init_split(struct vring_virtqueue *vq, > struct virtio_device *vdev) > { > + vq->vq.reset = VIRTIO_VQ_RESET_STEP_NONE; > + > vq->packed_ring = false; > vq->we_own_ring = false; > vq->broken = false;
Michael S. Tsirkin
2022-Mar-10 07:00 UTC
[PATCH v7 09/26] virtio_ring: split: implement virtqueue_reset_vring_split()
On Tue, Mar 08, 2022 at 08:35:01PM +0800, Xuan Zhuo wrote:> virtio ring supports reset. > > Queue reset is divided into several stages. > > 1. notify device queue reset > 2. vring release > 3. attach new vring > 4. notify device queue re-enable > > After the first step is completed, the vring reset operation can be > performed. If the newly set vring num does not change, then just reset > the vq related value. > > Otherwise, the vring will be released and the vring will be reallocated. > And the vring will be attached to the vq. If this process fails, the > function will exit, and the state of the vq will be the vring release > state. You can call this function again to reallocate the vring. > > In addition, vring_align, may_reduce_num are necessary for reallocating > vring, so they are retained when creating vq. > > Signed-off-by: Xuan Zhuo <xuanzhuo at linux.alibaba.com> > --- > drivers/virtio/virtio_ring.c | 69 ++++++++++++++++++++++++++++++++++++ > 1 file changed, 69 insertions(+) > > diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c > index e0422c04c903..148fb1fd3d5a 100644 > --- a/drivers/virtio/virtio_ring.c > +++ b/drivers/virtio/virtio_ring.c > @@ -158,6 +158,12 @@ struct vring_virtqueue { > /* DMA address and size information */ > dma_addr_t queue_dma_addr; > size_t queue_size_in_bytes; > + > + /* The parameters for creating vrings are reserved for > + * creating new vrings when enabling reset queue. > + */ > + u32 vring_align; > + bool may_reduce_num; > } split; > > /* Available for packed ring */ > @@ -217,6 +223,12 @@ struct vring_virtqueue { > #endif > }; > > +static void vring_free(struct virtqueue *vq); > +static void __vring_virtqueue_init_split(struct vring_virtqueue *vq, > + struct virtio_device *vdev); > +static int __vring_virtqueue_attach_split(struct vring_virtqueue *vq, > + struct virtio_device *vdev, > + struct vring vring); > > /* > * Helpers. > @@ -1012,6 +1024,8 @@ static struct virtqueue *vring_create_virtqueue_split( > return NULL; > } > > + to_vvq(vq)->split.vring_align = vring_align; > + to_vvq(vq)->split.may_reduce_num = may_reduce_num; > to_vvq(vq)->split.queue_dma_addr = vring.dma_addr; > to_vvq(vq)->split.queue_size_in_bytes = vring.queue_size_in_bytes; > to_vvq(vq)->we_own_ring = true; > @@ -1019,6 +1033,59 @@ static struct virtqueue *vring_create_virtqueue_split( > return vq; > } > > +static int virtqueue_reset_vring_split(struct virtqueue *_vq, u32 num) > +{ > + struct vring_virtqueue *vq = to_vvq(_vq); > + struct virtio_device *vdev = _vq->vdev; > + struct vring_split vring; > + int err; > + > + if (num > _vq->num_max) > + return -E2BIG; > + > + switch (vq->vq.reset) { > + case VIRTIO_VQ_RESET_STEP_NONE: > + return -ENOENT; > + > + case VIRTIO_VQ_RESET_STEP_VRING_ATTACH: > + case VIRTIO_VQ_RESET_STEP_DEVICE: > + if (vq->split.vring.num == num || !num) > + break; > + > + vring_free(_vq); > + > + fallthrough; > + > + case VIRTIO_VQ_RESET_STEP_VRING_RELEASE: > + if (!num) > + num = vq->split.vring.num; > + > + err = vring_create_vring_split(&vring, vdev, > + vq->split.vring_align, > + vq->weak_barriers, > + vq->split.may_reduce_num, num); > + if (err) > + return -ENOMEM; > + > + err = __vring_virtqueue_attach_split(vq, vdev, vring.vring); > + if (err) { > + vring_free_queue(vdev, vring.queue_size_in_bytes, > + vring.queue, > + vring.dma_addr); > + return -ENOMEM; > + } > + > + vq->split.queue_dma_addr = vring.dma_addr; > + vq->split.queue_size_in_bytes = vring.queue_size_in_bytes; > + } > + > + __vring_virtqueue_init_split(vq, vdev); > + vq->we_own_ring = true; > + vq->vq.reset = VIRTIO_VQ_RESET_STEP_VRING_ATTACH; > + > + return 0; > +} > +I kind of dislike this state machine. Hacks like special-casing num = 0 to mean "reset" are especially confusing. And as Jason points out, when we want a resize then yes this currently implies reset but that is an implementation detail. There should be a way to just make these cases separate functions and then use them to compose consistent external APIs. If we additionally want to track state for debugging then bool flags seem more appropriate for this, though from experience that is not always worth the extra code.> /* > * Packed ring specific functions - *_packed(). > @@ -2317,6 +2384,8 @@ static int __vring_virtqueue_attach_split(struct vring_virtqueue *vq, > static void __vring_virtqueue_init_split(struct vring_virtqueue *vq, > struct virtio_device *vdev) > { > + vq->vq.reset = VIRTIO_VQ_RESET_STEP_NONE; > + > vq->packed_ring = false; > vq->we_own_ring = false; > vq->broken = false; > -- > 2.31.0