@@ -924,7 +924,6 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
struct ice_rx_buf *rx_buf;
rx_buf = &rx_ring->rx_buf[ntc];
- rx_buf->pgcnt = page_count(rx_buf->page);
prefetchw(rx_buf->page);
if (!size)
@@ -940,6 +939,22 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
return rx_buf;
}
+static void ice_get_pgcnts(struct ice_rx_ring *rx_ring)
+{
+ u32 nr_frags = rx_ring->nr_frags + 1;
+ u32 idx = rx_ring->first_desc;
+ struct ice_rx_buf *rx_buf;
+ u32 cnt = rx_ring->count;
+
+ for (int i = 0; i < nr_frags; i++) {
+ rx_buf = &rx_ring->rx_buf[idx];
+ rx_buf->pgcnt = page_count(rx_buf->page);
+
+ if (++idx == cnt)
+ idx = 0;
+ }
+}
+
/**
* ice_build_skb - Build skb around an existing buffer
* @rx_ring: Rx descriptor ring to transact packets on
@@ -1229,6 +1244,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
if (ice_is_non_eop(rx_ring, rx_desc))
continue;
+ ice_get_pgcnts(rx_ring);
ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
if (rx_buf->act == ICE_XDP_PASS)
goto construct_skb;
Intel networking drivers have a page recycling scheme that is nicely explained by Bjorn Topel in commit 75aab4e10ae6 ("i40e: avoid premature Rx buffer reuse"). Please refer to it for better understanding what is described below. If we store the page count on a bunch of fragments while being in the middle of gathering the whole frame and we stumbled upon DD bit not being set, we terminate the NAPI Rx processing loop and come back later on. Then, on next NAPI execution, the page recycling algorithm will work on previously stored refcount of underlying page. Imagine that second half of page was used actively by networking stack and by the time we came back, stack is not busy with this page anymore and decremented the refcount. The page reuse logic in this case should be good to reuse the page but given the old refcount it will not do so and attempt to release the page via page_frag_cache_drain() with pagecnt_bias used as an arg. This in turn will result in negative refcount on struct page, which was initially observed by Xu Du. Therefore to fix this, move the page count storage from ice_get_rx_buf() to a place where we are sure that whole frame has been collected and processing of this frame will happen under current NAPI instance, but before calling XDP program as it internally can also change the page count of fragments belonging to xdp_buff. Fixes: ac0753391195 ("ice: Store page count inside ice_rx_buf") Reported-and-tested-by: Xu Du <xudu@redhat.com> Co-developed-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> --- drivers/net/ethernet/intel/ice/ice_txrx.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)