Message ID | 20180723094303.6632-1-bjorn.topel@gmail.com |
---|---|
State | Accepted, archived |
Delegated to: | BPF Maintainers |
Headers | show |
Series | [bpf] xsk: fix poll/POLLIN premature returns | expand |
On 07/23/2018 11:43 AM, Björn Töpel wrote: > From: Björn Töpel <bjorn.topel@intel.com> > > Polling for the ingress queues relies on reading the producer/consumer > pointers of the Rx queue. > > Prior this commit, a cached consumer pointer could be used, instead of > the actual consumer pointer and therefore report POLLIN prematurely. > > This patch makes sure that the non-cached consumer pointer is used > instead. > > Reported-by: Qi Zhang <qi.z.zhang@intel.com> > Tested-by: Qi Zhang <qi.z.zhang@intel.com> > Fixes: c497176cb2e4 ("xsk: add Rx receive functions and poll support") > Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Applied thanks, Björn!
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 52ecaf770642..8a64b150be54 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -250,7 +250,7 @@ static inline bool xskq_full_desc(struct xsk_queue *q) static inline bool xskq_empty_desc(struct xsk_queue *q) { - return xskq_nb_free(q, q->prod_tail, 1) == q->nentries; + return xskq_nb_free(q, q->prod_tail, q->nentries) == q->nentries; } void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props);