Commit 2543a600 authored Nov 24, 2020 by Eric Dumazet Committed by Jakub Kicinski Nov 25, 2020

gro_cells: reduce number of synchronize_net() calls



After cited commit, gro_cells_destroy() became damn slow
on hosts with a lot of cores.

This is because we have one additional synchronize_net() per cpu as
stated in the changelog.

gro_cells_init() is setting NAPI_STATE_NO_BUSY_POLL, and this was enough
to not have one synchronize_net() call per netif_napi_del()

We can factorize all the synchronize_net() to a single one,
right before freeing per-cpu memory.

Fixes: 5198d545 ("net: remove napi_hash_del() from driver-facing API")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20201124203822.1360107-1-eric.dumazet@gmail.com


Signed-off-by: Jakub Kicinski <kuba@kernel.org>

parent 12a8fe56

net/core/gro_cells.c

+6 −1

Original line number	Diff line number	Diff line
		@@ -99,9 +99,14 @@ void gro_cells_destroy(struct gro_cells *gcells)
		struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);

		napi_disable(&cell->napi);
		netif_napi_del(&cell->napi);
		__netif_napi_del(&cell->napi);
		__skb_queue_purge(&cell->napi_skbs);
		}
		/* This barrier is needed because netpoll could access dev->napi_list
		* under rcu protection.
		*/
		synchronize_net();

		free_percpu(gcells->cells);
		gcells->cells = NULL;
		}

Admin message