From d678cbd2f867a564a3c5b276c454e873f43f02f8 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Tue, 7 Jun 2022 16:22:00 +0200 Subject: [PATCH] xsk: Fix handling of invalid descriptors in XSK TX batching API xdpxceiver run on a AF_XDP ZC enabled driver revealed a problem with XSK Tx batching API. There is a test that checks how invalid Tx descriptors are handled by AF_XDP. Each valid descriptor is followed by invalid one on Tx side whereas the Rx side expects only to receive a set of valid descriptors. In current xsk_tx_peek_release_desc_batch() function, the amount of available descriptors is hidden inside xskq_cons_peek_desc_batch(). This can be problematic in cases where invalid descriptors are present due to the fact that xskq_cons_peek_desc_batch() returns only a count of valid descriptors. This means that it is impossible to properly update XSK ring state when calling xskq_cons_release_n(). To address this issue, pull out the contents of xskq_cons_peek_desc_batch() so that callers (currently only xsk_tx_peek_release_desc_batch()) will always be able to update the state of ring properly, as total count of entries is now available and use this value as an argument in xskq_cons_release_n(). By doing so, xskq_cons_peek_desc_batch() can be dropped altogether. Fixes: 9349eb3a9d2a ("xsk: Introduce batched Tx descriptor interfaces") Signed-off-by: Maciej Fijalkowski Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Link: https://lore.kernel.org/bpf/20220607142200.576735-1-maciej.fijalkowski@intel.com --- net/xdp/xsk.c | 5 +++-- net/xdp/xsk_queue.h | 8 -------- 2 files changed, 3 insertions(+), 10 deletions(-) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index e0a4526ab66b..19ac872a6624 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -373,7 +373,8 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries) goto out; } - nb_pkts = xskq_cons_peek_desc_batch(xs->tx, pool, max_entries); + max_entries = xskq_cons_nb_entries(xs->tx, max_entries); + nb_pkts = xskq_cons_read_desc_batch(xs->tx, pool, max_entries); if (!nb_pkts) { xs->tx->queue_empty_descs++; goto out; @@ -389,7 +390,7 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries) if (!nb_pkts) goto out; - xskq_cons_release_n(xs->tx, nb_pkts); + xskq_cons_release_n(xs->tx, max_entries); __xskq_cons_release(xs->tx); xs->sk.sk_write_space(&xs->sk); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index a794410989cc..fb20bf7207cf 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -282,14 +282,6 @@ static inline bool xskq_cons_peek_desc(struct xsk_queue *q, return xskq_cons_read_desc(q, desc, pool); } -static inline u32 xskq_cons_peek_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool, - u32 max) -{ - u32 entries = xskq_cons_nb_entries(q, max); - - return xskq_cons_read_desc_batch(q, pool, entries); -} - /* To improve performance in the xskq_cons_release functions, only update local state here. * Reflect this to global state when we get new entries from the ring in * xskq_cons_get_entries() and whenever Rx or Tx processing are completed in the NAPI loop.