LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Jason Wang <jasowang@redhat.com>
To: Tiwei Bie <tiwei.bie@intel.com>,
	mst@redhat.com, virtualization@lists.linux-foundation.org,
	linux-kernel@vger.kernel.org, netdev@vger.kernel.org
Cc: wexu@redhat.com, jfreimann@redhat.com, Cornelia Huck <cohuck@redhat.com>
Subject: Re: [RFC v5 2/5] virtio_ring: support creating packed ring
Date: Tue, 29 May 2018 10:49:11 +0800	[thread overview]
Message-ID: <654feee2-3414-e304-0aec-2bb19a7e0c87@redhat.com> (raw)
In-Reply-To: <20180522081648.14768-3-tiwei.bie@intel.com>



On 2018年05月22日 16:16, Tiwei Bie wrote:
> This commit introduces the support for creating packed ring.
> All split ring specific functions are added _split suffix.
> Some necessary stubs for packed ring are also added.
>
> Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
> ---
>   drivers/virtio/virtio_ring.c | 801 +++++++++++++++++++++++------------
>   include/linux/virtio_ring.h  |   8 +-
>   2 files changed, 546 insertions(+), 263 deletions(-)
>
> diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
> index 71458f493cf8..f5ef5f42a7cf 100644
> --- a/drivers/virtio/virtio_ring.c
> +++ b/drivers/virtio/virtio_ring.c
> @@ -61,11 +61,15 @@ struct vring_desc_state {
>   	struct vring_desc *indir_desc;	/* Indirect descriptor, if any. */
>   };
>   
> +struct vring_desc_state_packed {
> +	int next;			/* The next desc state. */
> +};
> +
>   struct vring_virtqueue {
>   	struct virtqueue vq;
>   
> -	/* Actual memory layout for this queue */
> -	struct vring vring;
> +	/* Is this a packed ring? */
> +	bool packed;
>   
>   	/* Can we use weak barriers? */
>   	bool weak_barriers;
> @@ -87,11 +91,39 @@ struct vring_virtqueue {
>   	/* Last used index we've seen. */
>   	u16 last_used_idx;
>   
> -	/* Last written value to avail->flags */
> -	u16 avail_flags_shadow;
> +	union {
> +		/* Available for split ring */
> +		struct {
> +			/* Actual memory layout for this queue. */
> +			struct vring vring;
>   
> -	/* Last written value to avail->idx in guest byte order */
> -	u16 avail_idx_shadow;
> +			/* Last written value to avail->flags */
> +			u16 avail_flags_shadow;
> +
> +			/* Last written value to avail->idx in
> +			 * guest byte order. */
> +			u16 avail_idx_shadow;
> +		};
> +
> +		/* Available for packed ring */
> +		struct {
> +			/* Actual memory layout for this queue. */
> +			struct vring_packed vring_packed;
> +
> +			/* Driver ring wrap counter. */
> +			u8 avail_wrap_counter;
> +
> +			/* Device ring wrap counter. */
> +			u8 used_wrap_counter;

How about just use boolean?

> +
> +			/* Index of the next avail descriptor. */
> +			u16 next_avail_idx;
> +
> +			/* Last written value to driver->flags in
> +			 * guest byte order. */
> +			u16 event_flags_shadow;
> +		};
> +	};
>   
>   	/* How to notify other side. FIXME: commonalize hcalls! */
>   	bool (*notify)(struct virtqueue *vq);
> @@ -111,11 +143,24 @@ struct vring_virtqueue {
>   #endif
>   
>   	/* Per-descriptor state. */
> -	struct vring_desc_state desc_state[];
> +	union {
> +		struct vring_desc_state desc_state[1];
> +		struct vring_desc_state_packed desc_state_packed[1];
> +	};
>   };
>   
>   #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
>   
> +static inline bool virtqueue_use_indirect(struct virtqueue *_vq,
> +					  unsigned int total_sg)
> +{
> +	struct vring_virtqueue *vq = to_vvq(_vq);
> +
> +	/* If the host supports indirect descriptor tables, and we have multiple
> +	 * buffers, then go indirect. FIXME: tune this threshold */
> +	return (vq->indirect && total_sg > 1 && vq->vq.num_free);
> +}
> +
>   /*
>    * Modern virtio devices have feature bits to specify whether they need a
>    * quirk and bypass the IOMMU. If not there, just use the DMA API.
> @@ -201,8 +246,17 @@ static dma_addr_t vring_map_single(const struct vring_virtqueue *vq,
>   			      cpu_addr, size, direction);
>   }
>   
> -static void vring_unmap_one(const struct vring_virtqueue *vq,
> -			    struct vring_desc *desc)
> +static int vring_mapping_error(const struct vring_virtqueue *vq,
> +			       dma_addr_t addr)
> +{
> +	if (!vring_use_dma_api(vq->vq.vdev))
> +		return 0;
> +
> +	return dma_mapping_error(vring_dma_dev(vq), addr);
> +}
> +
> +static void vring_unmap_one_split(const struct vring_virtqueue *vq,
> +				  struct vring_desc *desc)
>   {
>   	u16 flags;
>   
> @@ -226,17 +280,9 @@ static void vring_unmap_one(const struct vring_virtqueue *vq,
>   	}
>   }
>   
> -static int vring_mapping_error(const struct vring_virtqueue *vq,
> -			       dma_addr_t addr)
> -{
> -	if (!vring_use_dma_api(vq->vq.vdev))
> -		return 0;
> -
> -	return dma_mapping_error(vring_dma_dev(vq), addr);
> -}

It looks to me if you keep vring_mapping_error behind 
vring_unmap_one_split(), lots of changes were unncessary.

> -
> -static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
> -					 unsigned int total_sg, gfp_t gfp)
> +static struct vring_desc *alloc_indirect_split(struct virtqueue *_vq,
> +					       unsigned int total_sg,
> +					       gfp_t gfp)
>   {
>   	struct vring_desc *desc;
>   	unsigned int i;
> @@ -257,14 +303,14 @@ static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
>   	return desc;
>   }
>   
> -static inline int virtqueue_add(struct virtqueue *_vq,
> -				struct scatterlist *sgs[],
> -				unsigned int total_sg,
> -				unsigned int out_sgs,
> -				unsigned int in_sgs,
> -				void *data,
> -				void *ctx,
> -				gfp_t gfp)
> +static inline int virtqueue_add_split(struct virtqueue *_vq,
> +				      struct scatterlist *sgs[],
> +				      unsigned int total_sg,
> +				      unsigned int out_sgs,
> +				      unsigned int in_sgs,
> +				      void *data,
> +				      void *ctx,
> +				      gfp_t gfp)
>   {
>   	struct vring_virtqueue *vq = to_vvq(_vq);
>   	struct scatterlist *sg;
> @@ -300,10 +346,8 @@ static inline int virtqueue_add(struct virtqueue *_vq,
>   
>   	head = vq->free_head;
>   
> -	/* If the host supports indirect descriptor tables, and we have multiple
> -	 * buffers, then go indirect. FIXME: tune this threshold */
> -	if (vq->indirect && total_sg > 1 && vq->vq.num_free)
> -		desc = alloc_indirect(_vq, total_sg, gfp);
> +	if (virtqueue_use_indirect(_vq, total_sg))
> +		desc = alloc_indirect_split(_vq, total_sg, gfp);
>   	else {
>   		desc = NULL;
>   		WARN_ON_ONCE(total_sg > vq->vring.num && !vq->indirect);
> @@ -424,7 +468,7 @@ static inline int virtqueue_add(struct virtqueue *_vq,
>   	for (n = 0; n < total_sg; n++) {
>   		if (i == err_idx)
>   			break;
> -		vring_unmap_one(vq, &desc[i]);
> +		vring_unmap_one_split(vq, &desc[i]);
>   		i = virtio16_to_cpu(_vq->vdev, vq->vring.desc[i].next);
>   	}
>   
> @@ -435,6 +479,355 @@ static inline int virtqueue_add(struct virtqueue *_vq,
>   	return -EIO;
>   }
>   
> +static bool virtqueue_kick_prepare_split(struct virtqueue *_vq)
> +{
> +	struct vring_virtqueue *vq = to_vvq(_vq);
> +	u16 new, old;
> +	bool needs_kick;
> +
> +	START_USE(vq);
> +	/* We need to expose available array entries before checking avail
> +	 * event. */
> +	virtio_mb(vq->weak_barriers);
> +
> +	old = vq->avail_idx_shadow - vq->num_added;
> +	new = vq->avail_idx_shadow;
> +	vq->num_added = 0;
> +
> +#ifdef DEBUG
> +	if (vq->last_add_time_valid) {
> +		WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
> +					      vq->last_add_time)) > 100);
> +	}
> +	vq->last_add_time_valid = false;
> +#endif
> +
> +	if (vq->event) {
> +		needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev, vring_avail_event(&vq->vring)),
> +					      new, old);
> +	} else {
> +		needs_kick = !(vq->vring.used->flags & cpu_to_virtio16(_vq->vdev, VRING_USED_F_NO_NOTIFY));
> +	}
> +	END_USE(vq);
> +	return needs_kick;
> +}
> +
> +static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
> +			     void **ctx)
> +{
> +	unsigned int i, j;
> +	__virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
> +
> +	/* Clear data ptr. */
> +	vq->desc_state[head].data = NULL;
> +
> +	/* Put back on free list: unmap first-level descriptors and find end */
> +	i = head;
> +
> +	while (vq->vring.desc[i].flags & nextflag) {
> +		vring_unmap_one_split(vq, &vq->vring.desc[i]);
> +		i = virtio16_to_cpu(vq->vq.vdev, vq->vring.desc[i].next);
> +		vq->vq.num_free++;
> +	}
> +
> +	vring_unmap_one_split(vq, &vq->vring.desc[i]);
> +	vq->vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev, vq->free_head);
> +	vq->free_head = head;
> +
> +	/* Plus final descriptor */
> +	vq->vq.num_free++;
> +
> +	if (vq->indirect) {
> +		struct vring_desc *indir_desc = vq->desc_state[head].indir_desc;
> +		u32 len;
> +
> +		/* Free the indirect table, if any, now that it's unmapped. */
> +		if (!indir_desc)
> +			return;
> +
> +		len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len);
> +
> +		BUG_ON(!(vq->vring.desc[head].flags &
> +			 cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
> +		BUG_ON(len == 0 || len % sizeof(struct vring_desc));
> +
> +		for (j = 0; j < len / sizeof(struct vring_desc); j++)
> +			vring_unmap_one_split(vq, &indir_desc[j]);
> +
> +		kfree(indir_desc);
> +		vq->desc_state[head].indir_desc = NULL;
> +	} else if (ctx) {
> +		*ctx = vq->desc_state[head].indir_desc;
> +	}
> +}
> +
> +static inline bool more_used_split(const struct vring_virtqueue *vq)
> +{
> +	return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->vring.used->idx);
> +}
> +
> +static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
> +					 unsigned int *len,
> +					 void **ctx)
> +{
> +	struct vring_virtqueue *vq = to_vvq(_vq);
> +	void *ret;
> +	unsigned int i;
> +	u16 last_used;
> +
> +	START_USE(vq);
> +
> +	if (unlikely(vq->broken)) {
> +		END_USE(vq);
> +		return NULL;
> +	}
> +
> +	if (!more_used_split(vq)) {
> +		pr_debug("No more buffers in queue\n");
> +		END_USE(vq);
> +		return NULL;
> +	}
> +
> +	/* Only get used array entries after they have been exposed by host. */
> +	virtio_rmb(vq->weak_barriers);
> +
> +	last_used = (vq->last_used_idx & (vq->vring.num - 1));
> +	i = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].id);
> +	*len = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].len);
> +
> +	if (unlikely(i >= vq->vring.num)) {
> +		BAD_RING(vq, "id %u out of range\n", i);
> +		return NULL;
> +	}
> +	if (unlikely(!vq->desc_state[i].data)) {
> +		BAD_RING(vq, "id %u is not a head!\n", i);
> +		return NULL;
> +	}
> +
> +	/* detach_buf_split clears data, so grab it now. */
> +	ret = vq->desc_state[i].data;
> +	detach_buf_split(vq, i, ctx);
> +	vq->last_used_idx++;
> +	/* If we expect an interrupt for the next entry, tell host
> +	 * by writing event index and flush out the write before
> +	 * the read in the next get_buf call. */
> +	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT))
> +		virtio_store_mb(vq->weak_barriers,
> +				&vring_used_event(&vq->vring),
> +				cpu_to_virtio16(_vq->vdev, vq->last_used_idx));
> +
> +#ifdef DEBUG
> +	vq->last_add_time_valid = false;
> +#endif
> +
> +	END_USE(vq);
> +	return ret;
> +}
> +
> +static void virtqueue_disable_cb_split(struct virtqueue *_vq)
> +{
> +	struct vring_virtqueue *vq = to_vvq(_vq);
> +
> +	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
> +		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
> +		if (!vq->event)
> +			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
> +	}
> +}
> +
> +static unsigned virtqueue_enable_cb_prepare_split(struct virtqueue *_vq)
> +{
> +	struct vring_virtqueue *vq = to_vvq(_vq);
> +	u16 last_used_idx;
> +
> +	START_USE(vq);
> +
> +	/* We optimistically turn back on interrupts, then check if there was
> +	 * more to do. */
> +	/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
> +	 * either clear the flags bit or point the event index at the next
> +	 * entry. Always do both to keep code simple. */
> +	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
> +		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
> +		if (!vq->event)
> +			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
> +	}
> +	vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
> +	END_USE(vq);
> +	return last_used_idx;
> +}
> +
> +static bool virtqueue_poll_split(struct virtqueue *_vq, unsigned last_used_idx)
> +{
> +	struct vring_virtqueue *vq = to_vvq(_vq);
> +
> +	virtio_mb(vq->weak_barriers);
> +	return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
> +}
> +
> +static bool virtqueue_enable_cb_delayed_split(struct virtqueue *_vq)
> +{
> +	struct vring_virtqueue *vq = to_vvq(_vq);
> +	u16 bufs;
> +
> +	START_USE(vq);
> +
> +	/* We optimistically turn back on interrupts, then check if there was
> +	 * more to do. */
> +	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
> +	 * either clear the flags bit or point the event index at the next
> +	 * entry. Always update the event index to keep code simple. */
> +	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
> +		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
> +		if (!vq->event)
> +			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
> +	}
> +	/* TODO: tune this threshold */
> +	bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
> +
> +	virtio_store_mb(vq->weak_barriers,
> +			&vring_used_event(&vq->vring),
> +			cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs));
> +
> +	if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
> +		END_USE(vq);
> +		return false;
> +	}
> +
> +	END_USE(vq);
> +	return true;
> +}
> +
> +static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq)
> +{
> +	struct vring_virtqueue *vq = to_vvq(_vq);
> +	unsigned int i;
> +	void *buf;
> +
> +	START_USE(vq);
> +
> +	for (i = 0; i < vq->vring.num; i++) {
> +		if (!vq->desc_state[i].data)
> +			continue;
> +		/* detach_buf clears data, so grab it now. */
> +		buf = vq->desc_state[i].data;
> +		detach_buf_split(vq, i, NULL);
> +		vq->avail_idx_shadow--;
> +		vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
> +		END_USE(vq);
> +		return buf;
> +	}
> +	/* That should have freed everything. */
> +	BUG_ON(vq->vq.num_free != vq->vring.num);
> +
> +	END_USE(vq);
> +	return NULL;
> +}

I think the those copy-and-paste hunks could be avoided and the diff 
should only contains renaming of the function. If yes, it would be very 
welcomed since it requires to compare the changes verbatim otherwise.

> +
> +/*
> + * The layout for the packed ring is a continuous chunk of memory
> + * which looks like this.
> + *
> + * struct vring_packed {
> + *	// The actual descriptors (16 bytes each)
> + *	struct vring_packed_desc desc[num];
> + *
> + *	// Padding to the next align boundary.
> + *	char pad[];
> + *
> + *	// Driver Event Suppression
> + *	struct vring_packed_desc_event driver;
> + *
> + *	// Device Event Suppression
> + *	struct vring_packed_desc_event device;
> + * };
> + */
> +static inline void vring_init_packed(struct vring_packed *vr, unsigned int num,
> +				     void *p, unsigned long align)
> +{
> +	vr->num = num;
> +	vr->desc = p;
> +	vr->driver = (void *)(((uintptr_t)p + sizeof(struct vring_packed_desc)
> +		* num + align - 1) & ~(align - 1));

If we choose not to go uapi, maybe we can use ALIGN() macro here?

> +	vr->device = vr->driver + 1;
> +}
> +
> +static inline unsigned vring_size_packed(unsigned int num, unsigned long align)
> +{
> +	return ((sizeof(struct vring_packed_desc) * num + align - 1)
> +		& ~(align - 1)) + sizeof(struct vring_packed_desc_event) * 2;
> +}
> +
> +static inline int virtqueue_add_packed(struct virtqueue *_vq,
> +				       struct scatterlist *sgs[],
> +				       unsigned int total_sg,
> +				       unsigned int out_sgs,
> +				       unsigned int in_sgs,
> +				       void *data,
> +				       void *ctx,
> +				       gfp_t gfp)
> +{
> +	return -EIO;
> +}
> +
> +static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
> +{
> +	return false;
> +}
> +
> +static inline bool more_used_packed(const struct vring_virtqueue *vq)
> +{
> +	return false;
> +}
> +
> +static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
> +					  unsigned int *len,
> +					  void **ctx)
> +{
> +	return NULL;
> +}
> +
> +static void virtqueue_disable_cb_packed(struct virtqueue *_vq)
> +{
> +}
> +
> +static unsigned virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq)
> +{
> +	return 0;
> +}
> +
> +static bool virtqueue_poll_packed(struct virtqueue *_vq, unsigned last_used_idx)
> +{
> +	return false;
> +}
> +
> +static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq)
> +{
> +	return false;
> +}
> +
> +static void *virtqueue_detach_unused_buf_packed(struct virtqueue *_vq)
> +{
> +	return NULL;
> +}
> +
> +static inline int virtqueue_add(struct virtqueue *_vq,
> +				struct scatterlist *sgs[],
> +				unsigned int total_sg,
> +				unsigned int out_sgs,
> +				unsigned int in_sgs,
> +				void *data,
> +				void *ctx,
> +				gfp_t gfp)
> +{
> +	struct vring_virtqueue *vq = to_vvq(_vq);
> +
> +	return vq->packed ? virtqueue_add_packed(_vq, sgs, total_sg, out_sgs,
> +						 in_sgs, data, ctx, gfp) :
> +			    virtqueue_add_split(_vq, sgs, total_sg, out_sgs,
> +						in_sgs, data, ctx, gfp);
> +}
> +
>   /**
>    * virtqueue_add_sgs - expose buffers to other end
>    * @vq: the struct virtqueue we're talking about.
> @@ -551,34 +944,9 @@ EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_ctx);
>   bool virtqueue_kick_prepare(struct virtqueue *_vq)
>   {
>   	struct vring_virtqueue *vq = to_vvq(_vq);
> -	u16 new, old;
> -	bool needs_kick;
>   
> -	START_USE(vq);
> -	/* We need to expose available array entries before checking avail
> -	 * event. */
> -	virtio_mb(vq->weak_barriers);
> -
> -	old = vq->avail_idx_shadow - vq->num_added;
> -	new = vq->avail_idx_shadow;
> -	vq->num_added = 0;
> -
> -#ifdef DEBUG
> -	if (vq->last_add_time_valid) {
> -		WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
> -					      vq->last_add_time)) > 100);
> -	}
> -	vq->last_add_time_valid = false;
> -#endif
> -
> -	if (vq->event) {
> -		needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev, vring_avail_event(&vq->vring)),
> -					      new, old);
> -	} else {
> -		needs_kick = !(vq->vring.used->flags & cpu_to_virtio16(_vq->vdev, VRING_USED_F_NO_NOTIFY));
> -	}
> -	END_USE(vq);
> -	return needs_kick;
> +	return vq->packed ? virtqueue_kick_prepare_packed(_vq) :
> +			    virtqueue_kick_prepare_split(_vq);
>   }
>   EXPORT_SYMBOL_GPL(virtqueue_kick_prepare);
>   
> @@ -626,58 +994,9 @@ bool virtqueue_kick(struct virtqueue *vq)
>   }
>   EXPORT_SYMBOL_GPL(virtqueue_kick);
>   
> -static void detach_buf(struct vring_virtqueue *vq, unsigned int head,
> -		       void **ctx)
> -{
> -	unsigned int i, j;
> -	__virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
> -
> -	/* Clear data ptr. */
> -	vq->desc_state[head].data = NULL;
> -
> -	/* Put back on free list: unmap first-level descriptors and find end */
> -	i = head;
> -
> -	while (vq->vring.desc[i].flags & nextflag) {
> -		vring_unmap_one(vq, &vq->vring.desc[i]);
> -		i = virtio16_to_cpu(vq->vq.vdev, vq->vring.desc[i].next);
> -		vq->vq.num_free++;
> -	}
> -
> -	vring_unmap_one(vq, &vq->vring.desc[i]);
> -	vq->vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev, vq->free_head);
> -	vq->free_head = head;
> -
> -	/* Plus final descriptor */
> -	vq->vq.num_free++;
> -
> -	if (vq->indirect) {
> -		struct vring_desc *indir_desc = vq->desc_state[head].indir_desc;
> -		u32 len;
> -
> -		/* Free the indirect table, if any, now that it's unmapped. */
> -		if (!indir_desc)
> -			return;
> -
> -		len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len);
> -
> -		BUG_ON(!(vq->vring.desc[head].flags &
> -			 cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
> -		BUG_ON(len == 0 || len % sizeof(struct vring_desc));
> -
> -		for (j = 0; j < len / sizeof(struct vring_desc); j++)
> -			vring_unmap_one(vq, &indir_desc[j]);
> -
> -		kfree(indir_desc);
> -		vq->desc_state[head].indir_desc = NULL;
> -	} else if (ctx) {
> -		*ctx = vq->desc_state[head].indir_desc;
> -	}
> -}
> -
>   static inline bool more_used(const struct vring_virtqueue *vq)
>   {
> -	return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->vring.used->idx);
> +	return vq->packed ? more_used_packed(vq) : more_used_split(vq);
>   }
>   
>   /**
> @@ -700,57 +1019,9 @@ void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
>   			    void **ctx)
>   {
>   	struct vring_virtqueue *vq = to_vvq(_vq);
> -	void *ret;
> -	unsigned int i;
> -	u16 last_used;
>   
> -	START_USE(vq);
> -
> -	if (unlikely(vq->broken)) {
> -		END_USE(vq);
> -		return NULL;
> -	}
> -
> -	if (!more_used(vq)) {
> -		pr_debug("No more buffers in queue\n");
> -		END_USE(vq);
> -		return NULL;
> -	}
> -
> -	/* Only get used array entries after they have been exposed by host. */
> -	virtio_rmb(vq->weak_barriers);
> -
> -	last_used = (vq->last_used_idx & (vq->vring.num - 1));
> -	i = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].id);
> -	*len = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].len);
> -
> -	if (unlikely(i >= vq->vring.num)) {
> -		BAD_RING(vq, "id %u out of range\n", i);
> -		return NULL;
> -	}
> -	if (unlikely(!vq->desc_state[i].data)) {
> -		BAD_RING(vq, "id %u is not a head!\n", i);
> -		return NULL;
> -	}
> -
> -	/* detach_buf clears data, so grab it now. */
> -	ret = vq->desc_state[i].data;
> -	detach_buf(vq, i, ctx);
> -	vq->last_used_idx++;
> -	/* If we expect an interrupt for the next entry, tell host
> -	 * by writing event index and flush out the write before
> -	 * the read in the next get_buf call. */
> -	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT))
> -		virtio_store_mb(vq->weak_barriers,
> -				&vring_used_event(&vq->vring),
> -				cpu_to_virtio16(_vq->vdev, vq->last_used_idx));
> -
> -#ifdef DEBUG
> -	vq->last_add_time_valid = false;
> -#endif
> -
> -	END_USE(vq);
> -	return ret;
> +	return vq->packed ? virtqueue_get_buf_ctx_packed(_vq, len, ctx) :
> +			    virtqueue_get_buf_ctx_split(_vq, len, ctx);
>   }
>   EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx);
>   
> @@ -772,12 +1043,10 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
>   {
>   	struct vring_virtqueue *vq = to_vvq(_vq);
>   
> -	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
> -		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
> -		if (!vq->event)
> -			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
> -	}
> -
> +	if (vq->packed)
> +		virtqueue_disable_cb_packed(_vq);
> +	else
> +		virtqueue_disable_cb_split(_vq);
>   }
>   EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
>   
> @@ -796,23 +1065,9 @@ EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
>   unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
>   {
>   	struct vring_virtqueue *vq = to_vvq(_vq);
> -	u16 last_used_idx;
>   
> -	START_USE(vq);
> -
> -	/* We optimistically turn back on interrupts, then check if there was
> -	 * more to do. */
> -	/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
> -	 * either clear the flags bit or point the event index at the next
> -	 * entry. Always do both to keep code simple. */
> -	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
> -		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
> -		if (!vq->event)
> -			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
> -	}
> -	vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
> -	END_USE(vq);
> -	return last_used_idx;
> +	return vq->packed ? virtqueue_enable_cb_prepare_packed(_vq) :
> +			    virtqueue_enable_cb_prepare_split(_vq);
>   }
>   EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare);
>   
> @@ -829,8 +1084,8 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
>   {
>   	struct vring_virtqueue *vq = to_vvq(_vq);
>   
> -	virtio_mb(vq->weak_barriers);
> -	return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
> +	return vq->packed ? virtqueue_poll_packed(_vq, last_used_idx) :
> +			    virtqueue_poll_split(_vq, last_used_idx);
>   }
>   EXPORT_SYMBOL_GPL(virtqueue_poll);
>   
> @@ -868,34 +1123,9 @@ EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
>   bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
>   {
>   	struct vring_virtqueue *vq = to_vvq(_vq);
> -	u16 bufs;
>   
> -	START_USE(vq);
> -
> -	/* We optimistically turn back on interrupts, then check if there was
> -	 * more to do. */
> -	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
> -	 * either clear the flags bit or point the event index at the next
> -	 * entry. Always update the event index to keep code simple. */
> -	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
> -		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
> -		if (!vq->event)
> -			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
> -	}
> -	/* TODO: tune this threshold */
> -	bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
> -
> -	virtio_store_mb(vq->weak_barriers,
> -			&vring_used_event(&vq->vring),
> -			cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs));
> -
> -	if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
> -		END_USE(vq);
> -		return false;
> -	}
> -
> -	END_USE(vq);
> -	return true;
> +	return vq->packed ? virtqueue_enable_cb_delayed_packed(_vq) :
> +			    virtqueue_enable_cb_delayed_split(_vq);
>   }
>   EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
>   
> @@ -910,27 +1140,9 @@ EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
>   void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
>   {
>   	struct vring_virtqueue *vq = to_vvq(_vq);
> -	unsigned int i;
> -	void *buf;
>   
> -	START_USE(vq);
> -
> -	for (i = 0; i < vq->vring.num; i++) {
> -		if (!vq->desc_state[i].data)
> -			continue;
> -		/* detach_buf clears data, so grab it now. */
> -		buf = vq->desc_state[i].data;
> -		detach_buf(vq, i, NULL);
> -		vq->avail_idx_shadow--;
> -		vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
> -		END_USE(vq);
> -		return buf;
> -	}
> -	/* That should have freed everything. */
> -	BUG_ON(vq->vq.num_free != vq->vring.num);
> -
> -	END_USE(vq);
> -	return NULL;
> +	return vq->packed ? virtqueue_detach_unused_buf_packed(_vq) :
> +			    virtqueue_detach_unused_buf_split(_vq);
>   }
>   EXPORT_SYMBOL_GPL(virtqueue_detach_unused_buf);
>   
> @@ -955,7 +1167,8 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
>   EXPORT_SYMBOL_GPL(vring_interrupt);
>   
>   struct virtqueue *__vring_new_virtqueue(unsigned int index,
> -					struct vring vring,
> +					union vring_union vring,
> +					bool packed,
>   					struct virtio_device *vdev,
>   					bool weak_barriers,
>   					bool context,
> @@ -963,19 +1176,22 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
>   					void (*callback)(struct virtqueue *),
>   					const char *name)
>   {
> -	unsigned int i;
>   	struct vring_virtqueue *vq;
> +	unsigned int num, i;
> +	size_t size;
>   
> -	vq = kmalloc(sizeof(*vq) + vring.num * sizeof(struct vring_desc_state),
> -		     GFP_KERNEL);
> +	num = packed ? vring.vring_packed.num : vring.vring_split.num;
> +	size = packed ? num * sizeof(struct vring_desc_state_packed) :
> +			num * sizeof(struct vring_desc_state);
> +
> +	vq = kmalloc(sizeof(*vq) + size, GFP_KERNEL);
>   	if (!vq)
>   		return NULL;
>   
> -	vq->vring = vring;
>   	vq->vq.callback = callback;
>   	vq->vq.vdev = vdev;
>   	vq->vq.name = name;
> -	vq->vq.num_free = vring.num;
> +	vq->vq.num_free = num;
>   	vq->vq.index = index;
>   	vq->we_own_ring = false;
>   	vq->queue_dma_addr = 0;
> @@ -984,9 +1200,8 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
>   	vq->weak_barriers = weak_barriers;
>   	vq->broken = false;
>   	vq->last_used_idx = 0;
> -	vq->avail_flags_shadow = 0;
> -	vq->avail_idx_shadow = 0;
>   	vq->num_added = 0;
> +	vq->packed = packed;
>   	list_add_tail(&vq->vq.list, &vdev->vqs);
>   #ifdef DEBUG
>   	vq->in_use = false;
> @@ -997,19 +1212,48 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
>   		!context;
>   	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
>   
> +	if (vq->packed) {
> +		vq->vring_packed = vring.vring_packed;
> +		vq->next_avail_idx = 0;
> +		vq->avail_wrap_counter = 1;
> +		vq->used_wrap_counter = 1;
> +		vq->event_flags_shadow = 0;
> +
> +		memset(vq->desc_state_packed, 0,
> +			num * sizeof(struct vring_desc_state_packed));
> +
> x
> +		vq->free_head = 0;
> +		for (i = 0; i < num-1; i++)
> +			vq->desc_state_packed[i].next = i + 1;
> +	} else {
> +		vq->vring = vring.vring_split;
> +		vq->avail_flags_shadow = 0;
> +		vq->avail_idx_shadow = 0;
> +
> +		/* Put everything in free lists. */
> +		vq->free_head = 0;
> +		for (i = 0; i < num-1; i++)
> +			vq->vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
> +
> +		memset(vq->desc_state, 0,
> +			num * sizeof(struct vring_desc_state));
> +	}
> +
>   	/* No callback?  Tell other side not to bother us. */
>   	if (!callback) {
> -		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
> -		if (!vq->event)
> -			vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
> +		if (packed) {
> +			vq->event_flags_shadow = VRING_EVENT_F_DISABLE;
> +			vq->vring_packed.driver->flags = cpu_to_virtio16(vdev,
> +						vq->event_flags_shadow);
> +		} else {
> +			vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
> +			if (!vq->event)
> +				vq->vring.avail->flags = cpu_to_virtio16(vdev,
> +						vq->avail_flags_shadow);
> +		}
>   	}
>   
> -	/* Put everything in free lists. */
> -	vq->free_head = 0;
> -	for (i = 0; i < vring.num-1; i++)
> -		vq->vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
> -	memset(vq->desc_state, 0, vring.num * sizeof(struct vring_desc_state));
> -
>   	return &vq->vq;
>   }
>   EXPORT_SYMBOL_GPL(__vring_new_virtqueue);
> @@ -1056,6 +1300,12 @@ static void vring_free_queue(struct virtio_device *vdev, size_t size,
>   	}
>   }
>   
> +static inline int
> +__vring_size(unsigned int num, unsigned long align, bool packed)
> +{
> +	return packed ? vring_size_packed(num, align) : vring_size(num, align);
> +}
> +
>   struct virtqueue *vring_create_virtqueue(
>   	unsigned int index,
>   	unsigned int num,
> @@ -1072,7 +1322,8 @@ struct virtqueue *vring_create_virtqueue(
>   	void *queue = NULL;
>   	dma_addr_t dma_addr;
>   	size_t queue_size_in_bytes;
> -	struct vring vring;
> +	union vring_union vring;
> +	bool packed;
>   
>   	/* We assume num is a power of 2. */
>   	if (num & (num - 1)) {
> @@ -1080,9 +1331,13 @@ struct virtqueue *vring_create_virtqueue(
>   		return NULL;
>   	}
>   
> +	packed = virtio_has_feature(vdev, VIRTIO_F_RING_PACKED);
> +
>   	/* TODO: allocate each queue chunk individually */
> -	for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) {
> -		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
> +	for (; num && __vring_size(num, vring_align, packed) > PAGE_SIZE;
> +			num /= 2) {
> +		queue = vring_alloc_queue(vdev, __vring_size(num, vring_align,
> +							     packed),
>   					  &dma_addr,
>   					  GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
>   		if (queue)
> @@ -1094,17 +1349,21 @@ struct virtqueue *vring_create_virtqueue(
>   
>   	if (!queue) {
>   		/* Try to get a single page. You are my only hope! */
> -		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
> +		queue = vring_alloc_queue(vdev, __vring_size(num, vring_align,
> +							     packed),
>   					  &dma_addr, GFP_KERNEL|__GFP_ZERO);
>   	}
>   	if (!queue)
>   		return NULL;
>   
> -	queue_size_in_bytes = vring_size(num, vring_align);
> -	vring_init(&vring, num, queue, vring_align);
> +	queue_size_in_bytes = __vring_size(num, vring_align, packed);
> +	if (packed)
> +		vring_init_packed(&vring.vring_packed, num, queue, vring_align);
> +	else
> +		vring_init(&vring.vring_split, num, queue, vring_align);
>   
> -	vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
> -				   notify, callback, name);
> +	vq = __vring_new_virtqueue(index, vring, packed, vdev, weak_barriers,
> +				   context, notify, callback, name);
>   	if (!vq) {
>   		vring_free_queue(vdev, queue_size_in_bytes, queue,
>   				 dma_addr);
> @@ -1130,10 +1389,17 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
>   				      void (*callback)(struct virtqueue *vq),
>   				      const char *name)
>   {
> -	struct vring vring;
> -	vring_init(&vring, num, pages, vring_align);
> -	return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
> -				     notify, callback, name);
> +	union vring_union vring;
> +	bool packed;
> +
> +	packed = virtio_has_feature(vdev, VIRTIO_F_RING_PACKED);
> +	if (packed)
> +		vring_init_packed(&vring.vring_packed, num, pages, vring_align);
> +	else
> +		vring_init(&vring.vring_split, num, pages, vring_align);
> +
> +	return __vring_new_virtqueue(index, vring, packed, vdev, weak_barriers,
> +				     context, notify, callback, name);
>   }
>   EXPORT_SYMBOL_GPL(vring_new_virtqueue);
>   
> @@ -1143,7 +1409,9 @@ void vring_del_virtqueue(struct virtqueue *_vq)
>   
>   	if (vq->we_own_ring) {
>   		vring_free_queue(vq->vq.vdev, vq->queue_size_in_bytes,
> -				 vq->vring.desc, vq->queue_dma_addr);
> +				 vq->packed ? (void *)vq->vring_packed.desc :
> +					      (void *)vq->vring.desc,
> +				 vq->queue_dma_addr);
>   	}
>   	list_del(&_vq->list);
>   	kfree(vq);
> @@ -1185,7 +1453,7 @@ unsigned int virtqueue_get_vring_size(struct virtqueue *_vq)
>   
>   	struct vring_virtqueue *vq = to_vvq(_vq);
>   
> -	return vq->vring.num;
> +	return vq->packed ? vq->vring_packed.num : vq->vring.num;
>   }
>   EXPORT_SYMBOL_GPL(virtqueue_get_vring_size);
>   
> @@ -1228,6 +1496,10 @@ dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq)
>   
>   	BUG_ON(!vq->we_own_ring);
>   
> +	if (vq->packed)
> +		return vq->queue_dma_addr + ((char *)vq->vring_packed.driver -
> +				(char *)vq->vring_packed.desc);
> +
>   	return vq->queue_dma_addr +
>   		((char *)vq->vring.avail - (char *)vq->vring.desc);
>   }
> @@ -1239,11 +1511,16 @@ dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq)
>   
>   	BUG_ON(!vq->we_own_ring);
>   
> +	if (vq->packed)
> +		return vq->queue_dma_addr + ((char *)vq->vring_packed.device -
> +				(char *)vq->vring_packed.desc);
> +
>   	return vq->queue_dma_addr +
>   		((char *)vq->vring.used - (char *)vq->vring.desc);
>   }
>   EXPORT_SYMBOL_GPL(virtqueue_get_used_addr);
>   
> +/* Only available for split ring */
>   const struct vring *virtqueue_get_vring(struct virtqueue *vq)
>   {

A possible issue with this is:

After commit d4674240f31f8c4289abba07d64291c6ddce51bc ("KVM: s390: 
virtio-ccw revision 1 SET_VQ"). CCW tries to use 
virtqueue_get_avail()/virtqueue_get_used(). Looks like a bug either here 
or ccw code.

Thanks

>   	return &to_vvq(vq)->vring;
> diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
> index bbf32524ab27..a0075894ad16 100644
> --- a/include/linux/virtio_ring.h
> +++ b/include/linux/virtio_ring.h
> @@ -60,6 +60,11 @@ static inline void virtio_store_mb(bool weak_barriers,
>   struct virtio_device;
>   struct virtqueue;
>   
> +union vring_union {
> +	struct vring vring_split;
> +	struct vring_packed vring_packed;
> +};
> +
>   /*
>    * Creates a virtqueue and allocates the descriptor ring.  If
>    * may_reduce_num is set, then this may allocate a smaller ring than
> @@ -79,7 +84,8 @@ struct virtqueue *vring_create_virtqueue(unsigned int index,
>   
>   /* Creates a virtqueue with a custom layout. */
>   struct virtqueue *__vring_new_virtqueue(unsigned int index,
> -					struct vring vring,
> +					union vring_union vring,
> +					bool packed,
>   					struct virtio_device *vdev,
>   					bool weak_barriers,
>   					bool ctx,

  reply	other threads:[~2018-05-29  2:50 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-22  8:16 [RFC v5 0/5] virtio: support " Tiwei Bie
2018-05-22  8:16 ` [RFC v5 1/5] virtio: add packed ring definitions Tiwei Bie
2018-05-22  8:16 ` [RFC v5 2/5] virtio_ring: support creating packed ring Tiwei Bie
2018-05-29  2:49   ` Jason Wang [this message]
2018-05-29  5:24     ` Tiwei Bie
2018-05-29  6:13       ` Jason Wang
2018-05-22  8:16 ` [RFC v5 3/5] virtio_ring: add packed ring support Tiwei Bie
2018-05-29  3:18   ` Jason Wang
2018-05-29  5:11     ` Tiwei Bie
2018-05-29  6:16       ` Jason Wang
2018-05-22  8:16 ` [RFC v5 4/5] virtio_ring: add event idx support in packed ring Tiwei Bie
2018-05-22  8:16 ` [RFC v5 5/5] virtio_ring: enable " Tiwei Bie
2018-05-25  2:31 ` [RFC v5 0/5] virtio: support " Jason Wang
2018-05-25  3:07   ` Tiwei Bie

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=654feee2-3414-e304-0aec-2bb19a7e0c87@redhat.com \
    --to=jasowang@redhat.com \
    --cc=cohuck@redhat.com \
    --cc=jfreimann@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=tiwei.bie@intel.com \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=wexu@redhat.com \
    --subject='Re: [RFC v5 2/5] virtio_ring: support creating packed ring' \
    /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

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).