From 4144a1059b47e821c82c3c82eb23a4c7312dce3a Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 11 Sep 2024 21:10:19 +0200 Subject: [PATCH] xsk: fix batch alloc API on non-coherent systems In cases when synchronizing DMA operations is necessary, xsk_buff_alloc_batch() returns a single buffer instead of the requested count. This puts the pressure on drivers that use batch API as they have to check for this corner case on their side and take care of allocations by themselves, which feels counter productive. Let us improve the core by looping over xp_alloc() @max times when slow path needs to be taken. Another issue with current interface, as spotted and fixed by Dries, was that when driver called xsk_buff_alloc_batch() with @max == 0, for slow path case it still allocated and returned a single buffer, which should not happen. By introducing the logic from first paragraph we kill two birds with one stone and address this problem as well. Fixes: 47e4075df300 ("xsk: Batched buffer allocation for the pool") Reported-and-tested-by: Dries De Winter Co-developed-by: Dries De Winter Signed-off-by: Dries De Winter Signed-off-by: Maciej Fijalkowski Acked-by: Magnus Karlsson Acked-by: Alexei Starovoitov Link: https://patch.msgid.link/20240911191019.296480-1-maciej.fijalkowski@intel.com Signed-off-by: Jakub Kicinski --- net/xdp/xsk_buff_pool.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index c0e0204b9630..b0f24ebd05f0 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -623,19 +623,30 @@ static u32 xp_alloc_reused(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u3 return nb_entries; } +static u32 xp_alloc_slow(struct xsk_buff_pool *pool, struct xdp_buff **xdp, + u32 max) +{ + int i; + + for (i = 0; i < max; i++) { + struct xdp_buff *buff; + + buff = xp_alloc(pool); + if (unlikely(!buff)) + return i; + *xdp = buff; + xdp++; + } + + return max; +} + u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) { u32 nb_entries1 = 0, nb_entries2; - if (unlikely(pool->dev && dma_dev_need_sync(pool->dev))) { - struct xdp_buff *buff; - - /* Slow path */ - buff = xp_alloc(pool); - if (buff) - *xdp = buff; - return !!buff; - } + if (unlikely(pool->dev && dma_dev_need_sync(pool->dev))) + return xp_alloc_slow(pool, xdp, max); if (unlikely(pool->free_list_cnt)) { nb_entries1 = xp_alloc_reused(pool, xdp, max);