diff mbox series

[bpf] xsk: fix poll/POLLIN premature returns

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

Commit Message

Björn Töpel July 23, 2018, 9:43 a.m. UTC 
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>
---
 net/xdp/xsk_queue.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Comments

Daniel Borkmann July 25, 2018, 5 p.m. UTC | #1 
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 mbox series

Patch

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);