Re: [PATCH v2 net 7/7] virtio_net: Differentiate sk_buff and xdp_frame on freeing
On Tue, Jan 29, 2019 at 09:45:59AM +0900, Toshiaki Makita wrote:
> We do not reset or free up unused buffers when enabling/disabling XDP,
> so it can happen that xdp_frames are freed after disabling XDP or
> sk_buffs are freed after enabling XDP on xdp tx queues.
> Thus we need to handle both forms (xdp_frames and sk_buffs) regardless
> of XDP setting.
> One way to trigger this problem is to disable XDP when napi_tx is
> enabled. In that case, virtnet_xdp_set() calls virtnet_napi_enable()
> which kicks NAPI. The NAPI handler will call virtnet_poll_cleantx()
> which invokes free_old_xmit_skbs() for queues which have been used by
> XDP.
>
> Note that even with this change we need to keep skipping
> free_old_xmit_skbs() from NAPI handlers when XDP is enabled, because XDP
> tx queues do not aquire queue locks.
>
> - v2: Use napi_consume_skb() instead of dev_consume_skb_any()
>
> Fixes: 4941d472bf95 ("virtio-net: do not reset during XDP set")
> Signed-off-by: Toshiaki Makita
Acked-by: Michael S. Tsirkin
> ---
> NOTE: Dropped Acked-by because of the v2 change.
>
> drivers/net/virtio_net.c | 54
> +---
> 1 file changed, 42 insertions(+), 12 deletions(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 1d454ce..2594481 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -57,6 +57,8 @@
> #define VIRTIO_XDP_TXBIT(0)
> #define VIRTIO_XDP_REDIR BIT(1)
>
> +#define VIRTIO_XDP_FLAG BIT(0)
> +
> /* RX packet size EWMA. The average packet size is used to determine the
> packet
> * buffer size when refilling RX rings. As the entire RX ring may be refilled
> * at once, the weight is chosen so that the EWMA will be insensitive to
> short-
> @@ -252,6 +254,21 @@ struct padded_vnet_hdr {
> char padding[4];
> };
>
> +static bool is_xdp_frame(void *ptr)
> +{
> + return (unsigned long)ptr & VIRTIO_XDP_FLAG;
> +}
> +
> +static void *xdp_to_ptr(struct xdp_frame *ptr)
> +{
> + return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG);
> +}
> +
> +static struct xdp_frame *ptr_to_xdp(void *ptr)
> +{
> + return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG);
> +}
> +
> /* Converting between virtqueue no. and kernel tx/rx queue no.
> * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq
> */
> @@ -462,7 +479,8 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
>
> sg_init_one(sq->sg, xdpf->data, xdpf->len);
>
> - err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdpf, GFP_ATOMIC);
> + err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp_to_ptr(xdpf),
> +GFP_ATOMIC);
> if (unlikely(err))
> return -ENOSPC; /* Caller handle free/refcnt */
>
> @@ -482,13 +500,13 @@ static int virtnet_xdp_xmit(struct net_device *dev,
> {
> struct virtnet_info *vi = netdev_priv(dev);
> struct receive_queue *rq = vi->rq;
> - struct xdp_frame *xdpf_sent;
> struct bpf_prog *xdp_prog;
> struct send_queue *sq;
> unsigned int len;
> int drops = 0;
> int kicks = 0;
> int ret, err;
> + void *ptr;
> int i;
>
> /* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this
> @@ -507,8 +525,12 @@ static int virtnet_xdp_xmit(struct net_device *dev,
> }
>
> /* Free up any pending old buffers before queueing new ones. */
> - while ((xdpf_sent = virtqueue_get_buf(sq->vq, )) != NULL)
> - xdp_return_frame(xdpf_sent);
> + while ((ptr = virtqueue_get_buf(sq->vq, )) != NULL) {
> + if (likely(is_xdp_frame(ptr)))
> + xdp_return_frame(ptr_to_xdp(ptr));
> + else
> + napi_consume_skb(ptr, false);
> + }
>
> for (i = 0; i < n; i++) {
> struct xdp_frame *xdpf = frames[i];
> @@ -1329,18 +1351,26 @@ static int virtnet_receive(struct receive_queue *rq,
> int budget,
>
> static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
> {
> - struct sk_buff *skb;
> unsigned int len;
> unsigned int packets = 0;
> unsigned int bytes = 0;
> + void *ptr;
>
> - while ((skb = virtqueue_get_buf(sq->vq, )) != NULL) {
> - pr_debug("Sent skb %p\n", skb);
> + while ((ptr = virtqueue_get_buf(sq->vq, )) != NULL) {
> + if (likely(!is_xdp_frame(ptr))) {
> + struct sk_buff *skb = ptr;
>
> - bytes += skb->len;
> - packets++;
> + pr_debug("Sent skb %p\n", skb);
>
> - napi_consume_skb(skb, in_napi);
> + bytes += skb->len;
> + napi_consume_skb(skb, in_napi);
> + } else {
> + struct xdp_frame *frame = ptr_to_xdp(ptr);
> +
> + bytes += frame->len;
> + xdp_return_frame(frame);
> + }
> +
Re: [PATCH v2 net 7/7] virtio_net: Differentiate sk_buff and xdp_frame on freeing
On 2019/01/29 11:23, Jason Wang wrote:
> On 2019/1/29 上午8:45, Toshiaki Makita wrote:
...
>> @@ -2666,10 +2696,10 @@ static void free_unused_bufs(struct
>> virtnet_info *vi)
>> for (i = 0; i < vi->max_queue_pairs; i++) {
>> struct virtqueue *vq = vi->sq[i].vq;
>> while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
>> - if (!is_xdp_raw_buffer_queue(vi, i))
>> + if (!is_xdp_frame(buf))
>
>
> I believe this is the last user of is_xdp_raw_buffer_queue(), maybe you
> can sent a patch on top to remove it.
Actually patch2 added new users of it ;)
>
>
>> dev_kfree_skb(buf);
>> else
>> - xdp_return_frame(buf);
>> + xdp_return_frame(ptr_to_xdp(buf));
>> }
>> }
>>
>
>
> Acked-by: Jason Wang
>
Thanks!
--
Toshiaki Makita
___
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH v2 net 7/7] virtio_net: Differentiate sk_buff and xdp_frame on freeing
On 2019/1/29 上午10:35, Toshiaki Makita wrote:
On 2019/01/29 11:23, Jason Wang wrote:
On 2019/1/29 上午8:45, Toshiaki Makita wrote:
...
@@ -2666,10 +2696,10 @@ static void free_unused_bufs(struct
virtnet_info *vi)
for (i = 0; i < vi->max_queue_pairs; i++) {
struct virtqueue *vq = vi->sq[i].vq;
while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
- if (!is_xdp_raw_buffer_queue(vi, i))
+ if (!is_xdp_frame(buf))
I believe this is the last user of is_xdp_raw_buffer_queue(), maybe you
can sent a patch on top to remove it.
Actually patch2 added new users of it ;)
Right, I missed that.
Thanks
dev_kfree_skb(buf);
else
- xdp_return_frame(buf);
+ xdp_return_frame(ptr_to_xdp(buf));
}
}
Acked-by: Jason Wang
Thanks!
___
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH v2 net 7/7] virtio_net: Differentiate sk_buff and xdp_frame on freeing
On 2019/1/29 上午8:45, Toshiaki Makita wrote:
We do not reset or free up unused buffers when enabling/disabling XDP,
so it can happen that xdp_frames are freed after disabling XDP or
sk_buffs are freed after enabling XDP on xdp tx queues.
Thus we need to handle both forms (xdp_frames and sk_buffs) regardless
of XDP setting.
One way to trigger this problem is to disable XDP when napi_tx is
enabled. In that case, virtnet_xdp_set() calls virtnet_napi_enable()
which kicks NAPI. The NAPI handler will call virtnet_poll_cleantx()
which invokes free_old_xmit_skbs() for queues which have been used by
XDP.
Note that even with this change we need to keep skipping
free_old_xmit_skbs() from NAPI handlers when XDP is enabled, because XDP
tx queues do not aquire queue locks.
- v2: Use napi_consume_skb() instead of dev_consume_skb_any()
Fixes: 4941d472bf95 ("virtio-net: do not reset during XDP set")
Signed-off-by: Toshiaki Makita
---
NOTE: Dropped Acked-by because of the v2 change.
drivers/net/virtio_net.c | 54 +---
1 file changed, 42 insertions(+), 12 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 1d454ce..2594481 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -57,6 +57,8 @@
#define VIRTIO_XDP_TX BIT(0)
#define VIRTIO_XDP_REDIR BIT(1)
+#define VIRTIO_XDP_FLAG BIT(0)
+
/* RX packet size EWMA. The average packet size is used to determine the
packet
* buffer size when refilling RX rings. As the entire RX ring may be refilled
* at once, the weight is chosen so that the EWMA will be insensitive to
short-
@@ -252,6 +254,21 @@ struct padded_vnet_hdr {
char padding[4];
};
+static bool is_xdp_frame(void *ptr)
+{
+ return (unsigned long)ptr & VIRTIO_XDP_FLAG;
+}
+
+static void *xdp_to_ptr(struct xdp_frame *ptr)
+{
+ return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG);
+}
+
+static struct xdp_frame *ptr_to_xdp(void *ptr)
+{
+ return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG);
+}
+
/* Converting between virtqueue no. and kernel tx/rx queue no.
* 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq
*/
@@ -462,7 +479,8 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
sg_init_one(sq->sg, xdpf->data, xdpf->len);
- err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdpf, GFP_ATOMIC);
+ err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp_to_ptr(xdpf),
+ GFP_ATOMIC);
if (unlikely(err))
return -ENOSPC; /* Caller handle free/refcnt */
@@ -482,13 +500,13 @@ static int virtnet_xdp_xmit(struct net_device *dev,
{
struct virtnet_info *vi = netdev_priv(dev);
struct receive_queue *rq = vi->rq;
- struct xdp_frame *xdpf_sent;
struct bpf_prog *xdp_prog;
struct send_queue *sq;
unsigned int len;
int drops = 0;
int kicks = 0;
int ret, err;
+ void *ptr;
int i;
/* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this
@@ -507,8 +525,12 @@ static int virtnet_xdp_xmit(struct net_device *dev,
}
/* Free up any pending old buffers before queueing new ones. */
- while ((xdpf_sent = virtqueue_get_buf(sq->vq, )) != NULL)
- xdp_return_frame(xdpf_sent);
+ while ((ptr = virtqueue_get_buf(sq->vq, )) != NULL) {
+ if (likely(is_xdp_frame(ptr)))
+ xdp_return_frame(ptr_to_xdp(ptr));
+ else
+ napi_consume_skb(ptr, false);
+ }
for (i = 0; i < n; i++) {
struct xdp_frame *xdpf = frames[i];
@@ -1329,18 +1351,26 @@ static int virtnet_receive(struct receive_queue *rq,
int budget,
static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
{
- struct sk_buff *skb;
unsigned int len;
unsigned int packets = 0;
unsigned int bytes = 0;
+ void *ptr;
- while ((skb = virtqueue_get_buf(sq->vq, )) != NULL) {
- pr_debug("Sent skb %p\n", skb);
+ while ((ptr = virtqueue_get_buf(sq->vq, )) != NULL) {
+ if (likely(!is_xdp_frame(ptr))) {
+ struct sk_buff *skb = ptr;
- bytes += skb->len;
- packets++;
+ pr_debug("Sent skb %p\n", skb);
- napi_consume_skb(skb, in_napi);
+ bytes += skb->len;
+ napi_consume_skb(skb, in_napi);
+ } else {
+ struct xdp_frame *frame = ptr_to_xdp(ptr);
+
+ bytes += frame->len;
+ xdp_return_frame(frame);
+ }
+ packets++;
}
/* Avoid overhead when no packets have been processed
@@ -2666,10 +2696,10 @@ static void free_unused_bufs(struct virtnet_info *vi)
for (i = 0; i < vi->max_queue_pairs; i++) {
struct virtqueue
