Even if skb is marked for zero copy, net core might still decide
to copy it later which is somewhat slower than a copy in user context:
besides copying the data we need to pin/unpin the pages.
Add a parameter reporting such cases through zero copy callback:
if this happens a lot, device can take this into account
and switch to copying in user context.
This patch updates all users but ignores the passed value for now:
it will be used by follow-up patches.
Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
---
drivers/vhost/vhost.c | 2 +-
drivers/vhost/vhost.h | 2 +-
include/linux/skbuff.h | 4 +++-
net/core/skbuff.c | 4 ++--
4 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 99ac2cb..92308b6 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1600,7 +1600,7 @@ void vhost_ubuf_put_and_wait(struct vhost_ubuf_ref *ubufs)
kfree(ubufs);
}
-void vhost_zerocopy_callback(struct ubuf_info *ubuf)
+void vhost_zerocopy_callback(struct ubuf_info *ubuf, int zerocopy_status)
{
struct vhost_ubuf_ref *ubufs = ubuf->ctx;
struct vhost_virtqueue *vq = ubufs->vq;
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 1125af3..eb7263c3 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -191,7 +191,7 @@ bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
unsigned int log_num, u64 len);
-void vhost_zerocopy_callback(struct ubuf_info *);
+void vhost_zerocopy_callback(struct ubuf_info *, int);
int vhost_zerocopy_signal_used(struct vhost_virtqueue *vq);
#define vq_err(vq, fmt, ...) do { \
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6a2c34e..8bac11b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -235,11 +235,13 @@ enum {
/*
* The callback notifies userspace to release buffers when skb DMA is done in
* lower device, the skb last reference should be 0 when calling this.
+ * The zerocopy_status argument is 0 if zero copy transmit occurred,
+ * 1 on successful data copy; < 0 on out of memory error.
* The ctx field is used to track device context.
* The desc field is used to track userspace buffer index.
*/
struct ubuf_info {
- void (*callback)(struct ubuf_info *);
+ void (*callback)(struct ubuf_info *, int zerocopy_status);
void *ctx;
unsigned long desc;
};
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6e04b1f..eb31f6e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -519,7 +519,7 @@ static void skb_release_data(struct sk_buff *skb)
uarg = skb_shinfo(skb)->destructor_arg;
if (uarg->callback)
- uarg->callback(uarg);
+ uarg->callback(uarg, 0);
}
if (skb_has_frag_list(skb))
@@ -797,7 +797,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
for (i = 0; i < num_frags; i++)
skb_frag_unref(skb, i);
- uarg->callback(uarg);
+ uarg->callback(uarg, 1);
/* skb frags point to kernel buffers */
for (i = num_frags - 1; i >= 0; i--) {
--
MST
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
