From 1f20a5769446a1acae67ac9e63d07a594829a789 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 7 May 2024 13:20:23 +0200 Subject: page_pool: make sure frag API fields don't span between cachelines After commit 5027ec19f104 ("net: page_pool: split the page_pool_params into fast and slow") that made &page_pool contain only "hot" params at the start, cacheline boundary chops frag API fields group in the middle again. To not bother with this each time fast params get expanded or shrunk, let's just align them to `4 * sizeof(long)`, the closest upper pow-2 to their actual size (2 longs + 1 int). This ensures 16-byte alignment for the 32-bit architectures and 32-byte alignment for the 64-bit ones, excluding unnecessary false-sharing. ::page_state_hold_cnt is used quite intensively on hotpath no matter if frag API is used, so move it to the newly created hole in the first cacheline. Signed-off-by: Alexander Lobakin Signed-off-by: Christoph Hellwig --- include/net/page_pool/types.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 5e43a08d3231..5460cbab5de0 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -130,12 +130,22 @@ struct page_pool { struct page_pool_params_fast p; int cpuid; + u32 pages_state_hold_cnt; bool has_init_callback; + /* The following block must stay within one cacheline. On 32-bit + * systems, sizeof(long) == sizeof(int), so that the block size is + * ``3 * sizeof(long)``. On 64-bit systems, the actual size is + * ``2 * sizeof(long) + sizeof(int)``. The closest pow-2 to both of + * them is ``4 * sizeof(long)``, so just use that one for simplicity. + * Having it aligned to a cacheline boundary may be excessive and + * doesn't bring any good. + */ + __cacheline_group_begin(frag) __aligned(4 * sizeof(long)); long frag_users; struct page *frag_page; unsigned int frag_offset; - u32 pages_state_hold_cnt; + __cacheline_group_end(frag); struct delayed_work release_dw; void (*disconnect)(void *pool); -- cgit v1.2.3 From 403f11ac9ab72fc3bee0b8c80c16e33212ea8cd9 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 7 May 2024 13:20:24 +0200 Subject: page_pool: don't use driver-set flags field directly page_pool::p is driver-defined params, copied directly from the structure passed to page_pool_create(). The structure isn't meant to be modified by the Page Pool core code and this even might look confusing[0][1]. In order to be able to alter some flags, let's define our own, internal fields the same way as the already existing one (::has_init_callback). They are defined as bits in the driver-set params, leave them so here as well, to not waste byte-per-bit or so. Almost 30 bits are still free for future extensions. We could've defined only new flags here or only the ones we may need to alter, but checking some flags in one place while others in another doesn't sound convenient or intuitive. ::flags passed by the driver can now go to the "slow" PP params. Suggested-by: Jakub Kicinski Link[0]: https://lore.kernel.org/netdev/20230703133207.4f0c54ce@kernel.org Suggested-by: Alexander Duyck Link[1]: https://lore.kernel.org/netdev/CAKgT0UfZCGnWgOH96E4GV3ZP6LLbROHM7SHE8NKwq+exX+Gk_Q@mail.gmail.com Signed-off-by: Alexander Lobakin Signed-off-by: Christoph Hellwig --- include/net/page_pool/types.h | 13 ++++++++++--- net/core/page_pool.c | 41 ++++++++++++++++++++++------------------- 2 files changed, 32 insertions(+), 22 deletions(-) (limited to 'include/net') diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 5460cbab5de0..8c6d9f16bf65 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -45,7 +45,6 @@ struct pp_alloc_cache { /** * struct page_pool_params - page pool parameters - * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV * @order: 2^order pages on allocation * @pool_size: size of the ptr_ring * @nid: NUMA node id to allocate from pages from @@ -55,10 +54,11 @@ struct pp_alloc_cache { * @dma_dir: DMA mapping direction * @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV + * @netdev: corresponding &net_device for Netlink introspection + * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL */ struct page_pool_params { struct_group_tagged(page_pool_params_fast, fast, - unsigned int flags; unsigned int order; unsigned int pool_size; int nid; @@ -70,6 +70,7 @@ struct page_pool_params { ); struct_group_tagged(page_pool_params_slow, slow, struct net_device *netdev; + unsigned int flags; /* private: used by test code only */ void (*init_callback)(struct page *page, void *arg); void *init_arg; @@ -131,7 +132,13 @@ struct page_pool { int cpuid; u32 pages_state_hold_cnt; - bool has_init_callback; + + bool has_init_callback:1; /* slow::init_callback is set */ + bool dma_map:1; /* Perform DMA mapping */ + bool dma_sync:1; /* Perform DMA sync */ +#ifdef CONFIG_PAGE_POOL_STATS + bool system:1; /* This is a global percpu pool */ +#endif /* The following block must stay within one cacheline. On 32-bit * systems, sizeof(long) == sizeof(int), so that the block size is diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 95eac12e8790..c2819ff03dd2 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -194,7 +194,7 @@ static int page_pool_init(struct page_pool *pool, pool->cpuid = cpuid; /* Validate only known flags were used */ - if (pool->p.flags & ~(PP_FLAG_ALL)) + if (pool->slow.flags & ~PP_FLAG_ALL) return -EINVAL; if (pool->p.pool_size) @@ -208,22 +208,26 @@ static int page_pool_init(struct page_pool *pool, * DMA_BIDIRECTIONAL is for allowing page used for DMA sending, * which is the XDP_TX use-case. */ - if (pool->p.flags & PP_FLAG_DMA_MAP) { + if (pool->slow.flags & PP_FLAG_DMA_MAP) { if ((pool->p.dma_dir != DMA_FROM_DEVICE) && (pool->p.dma_dir != DMA_BIDIRECTIONAL)) return -EINVAL; + + pool->dma_map = true; } - if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) { + if (pool->slow.flags & PP_FLAG_DMA_SYNC_DEV) { /* In order to request DMA-sync-for-device the page * needs to be mapped */ - if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + if (!(pool->slow.flags & PP_FLAG_DMA_MAP)) return -EINVAL; if (!pool->p.max_len) return -EINVAL; + pool->dma_sync = true; + /* pool->p.offset has to be set according to the address * offset used by the DMA engine to start copying rx data */ @@ -232,7 +236,7 @@ static int page_pool_init(struct page_pool *pool, pool->has_init_callback = !!pool->slow.init_callback; #ifdef CONFIG_PAGE_POOL_STATS - if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) { + if (!(pool->slow.flags & PP_FLAG_SYSTEM_POOL)) { pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats); if (!pool->recycle_stats) return -ENOMEM; @@ -242,12 +246,13 @@ static int page_pool_init(struct page_pool *pool, * (also percpu) page pool instance. */ pool->recycle_stats = &pp_system_recycle_stats; + pool->system = true; } #endif if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) { #ifdef CONFIG_PAGE_POOL_STATS - if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) + if (!pool->system) free_percpu(pool->recycle_stats); #endif return -ENOMEM; @@ -258,7 +263,7 @@ static int page_pool_init(struct page_pool *pool, /* Driver calling page_pool_create() also call page_pool_destroy() */ refcount_set(&pool->user_cnt, 1); - if (pool->p.flags & PP_FLAG_DMA_MAP) + if (pool->dma_map) get_device(pool->p.dev); return 0; @@ -268,11 +273,11 @@ static void page_pool_uninit(struct page_pool *pool) { ptr_ring_cleanup(&pool->ring, NULL); - if (pool->p.flags & PP_FLAG_DMA_MAP) + if (pool->dma_map) put_device(pool->p.dev); #ifdef CONFIG_PAGE_POOL_STATS - if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) + if (!pool->system) free_percpu(pool->recycle_stats); #endif } @@ -424,7 +429,7 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) if (page_pool_set_dma_addr(page, dma)) goto unmap_failed; - if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) + if (pool->dma_sync) page_pool_dma_sync_for_device(pool, page, pool->p.max_len); return true; @@ -470,8 +475,7 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool, if (unlikely(!page)) return NULL; - if ((pool->p.flags & PP_FLAG_DMA_MAP) && - unlikely(!page_pool_dma_map(pool, page))) { + if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page))) { put_page(page); return NULL; } @@ -491,8 +495,8 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, gfp_t gfp) { const int bulk = PP_ALLOC_CACHE_REFILL; - unsigned int pp_flags = pool->p.flags; unsigned int pp_order = pool->p.order; + bool dma_map = pool->dma_map; struct page *page; int i, nr_pages; @@ -517,8 +521,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, */ for (i = 0; i < nr_pages; i++) { page = pool->alloc.cache[i]; - if ((pp_flags & PP_FLAG_DMA_MAP) && - unlikely(!page_pool_dma_map(pool, page))) { + if (dma_map && unlikely(!page_pool_dma_map(pool, page))) { put_page(page); continue; } @@ -590,7 +593,7 @@ void __page_pool_release_page_dma(struct page_pool *pool, struct page *page) { dma_addr_t dma; - if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + if (!pool->dma_map) /* Always account for inflight pages, even if we didn't * map them */ @@ -673,7 +676,7 @@ static bool __page_pool_page_can_be_recycled(const struct page *page) } /* If the page refcnt == 1, this will try to recycle the page. - * if PP_FLAG_DMA_SYNC_DEV is set, we'll try to sync the DMA area for + * If pool->dma_sync is set, we'll try to sync the DMA area for * the configured size min(dma_sync_size, pool->max_len). * If the page refcnt != 1, then the page will be returned to memory * subsystem. @@ -696,7 +699,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, if (likely(__page_pool_page_can_be_recycled(page))) { /* Read barrier done in page_ref_count / READ_ONCE */ - if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) + if (pool->dma_sync) page_pool_dma_sync_for_device(pool, page, dma_sync_size); @@ -809,7 +812,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool, return NULL; if (__page_pool_page_can_be_recycled(page)) { - if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) + if (pool->dma_sync) page_pool_dma_sync_for_device(pool, page, -1); return page; -- cgit v1.2.3 From 163943ac00cb31ac1a88ce5f78a7e2ead37329ec Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 7 May 2024 13:20:26 +0200 Subject: xsk: use generic DMA sync shortcut instead of a custom one XSk infra's been using its own DMA sync shortcut to try avoiding redundant function calls. Now that there is a generic one, remove the custom implementation and rely on the generic helpers. xsk_buff_dma_sync_for_cpu() doesn't need the second argument anymore, remove it. Signed-off-by: Alexander Lobakin Signed-off-by: Christoph Hellwig --- drivers/net/ethernet/engleder/tsnep_main.c | 2 +- drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 2 +- drivers/net/ethernet/intel/ice/ice_xsk.c | 2 +- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 2 +- .../net/ethernet/mellanox/mlx5/core/en/xsk/rx.c | 4 +-- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +- drivers/net/ethernet/netronome/nfp/nfd3/xsk.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- include/net/xdp_sock_drv.h | 7 ++---- include/net/xsk_buff_pool.h | 14 +++-------- net/xdp/xsk_buff_pool.c | 29 +++------------------- 13 files changed, 21 insertions(+), 51 deletions(-) (limited to 'include/net') diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index 4b15af6b7122..44da335d66bd 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -1587,7 +1587,7 @@ static int tsnep_rx_poll_zc(struct tsnep_rx *rx, struct napi_struct *napi, length = __le32_to_cpu(entry->desc_wb->properties) & TSNEP_DESC_LENGTH_MASK; xsk_buff_set_size(entry->xdp, length - ETH_FCS_LEN); - xsk_buff_dma_sync_for_cpu(entry->xdp, rx->xsk_pool); + xsk_buff_dma_sync_for_cpu(entry->xdp); /* RX metadata with timestamps is in front of actual data, * subtract metadata size to get length of actual data and diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c index 051748b997f3..a466c2379146 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c @@ -55,7 +55,7 @@ static u32 dpaa2_xsk_run_xdp(struct dpaa2_eth_priv *priv, xdp_set_data_meta_invalid(xdp_buff); xdp_buff->rxq = &ch->xdp_rxq; - xsk_buff_dma_sync_for_cpu(xdp_buff, ch->xsk_pool); + xsk_buff_dma_sync_for_cpu(xdp_buff); xdp_act = bpf_prog_run_xdp(xdp_prog, xdp_buff); /* xdp.data pointer may have changed */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 11500003af0d..d20ce517426e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -483,7 +483,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) bi = *i40e_rx_bi(rx_ring, next_to_process); xsk_buff_set_size(bi, size); - xsk_buff_dma_sync_for_cpu(bi, rx_ring->xsk_pool); + xsk_buff_dma_sync_for_cpu(bi); if (!first) first = bi; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 1857220d27fe..cecd5b1e0757 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -879,7 +879,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) ICE_RX_FLX_DESC_PKT_LEN_M; xsk_buff_set_size(xdp, size); - xsk_buff_dma_sync_for_cpu(xdp, xsk_pool); + xsk_buff_dma_sync_for_cpu(xdp); if (!first) { first = xdp; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 4d975d620a8e..07692e2a7c64 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2813,7 +2813,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) } bi->xdp->data_end = bi->xdp->data + size; - xsk_buff_dma_sync_for_cpu(bi->xdp, ring->xsk_pool); + xsk_buff_dma_sync_for_cpu(bi->xdp); res = __igc_xdp_run_prog(adapter, prog, bi->xdp); switch (res) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index d34d715c59eb..ee2d0ec12b2d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -304,7 +304,7 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, } bi->xdp->data_end = bi->xdp->data + size; - xsk_buff_dma_sync_for_cpu(bi->xdp, rx_ring->xsk_pool); + xsk_buff_dma_sync_for_cpu(bi->xdp); xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, bi->xdp); if (likely(xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR))) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index b8dd74453655..1b7132fa70de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -270,7 +270,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, /* mxbuf->rq is set on allocation, but cqe is per-packet so set it here */ mxbuf->cqe = cqe; xsk_buff_set_size(&mxbuf->xdp, cqe_bcnt); - xsk_buff_dma_sync_for_cpu(&mxbuf->xdp, rq->xsk_pool); + xsk_buff_dma_sync_for_cpu(&mxbuf->xdp); net_prefetch(mxbuf->xdp.data); /* Possible flows: @@ -319,7 +319,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, /* mxbuf->rq is set on allocation, but cqe is per-packet so set it here */ mxbuf->cqe = cqe; xsk_buff_set_size(&mxbuf->xdp, cqe_bcnt); - xsk_buff_dma_sync_for_cpu(&mxbuf->xdp, rq->xsk_pool); + xsk_buff_dma_sync_for_cpu(&mxbuf->xdp); net_prefetch(mxbuf->xdp.data); prog = rcu_dereference(rq->xdp_prog); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index d601b5faaed5..b5333da20e8a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -917,7 +917,7 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) if (!rq->xsk_pool) { count = mlx5e_refill_rx_wqes(rq, head, wqe_bulk); - } else if (likely(!rq->xsk_pool->dma_need_sync)) { + } else if (likely(!dma_dev_need_sync(rq->pdev))) { mlx5e_xsk_free_rx_wqes(rq, head, wqe_bulk); count = mlx5e_xsk_alloc_rx_wqes_batched(rq, head, wqe_bulk); } else { diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/xsk.c b/drivers/net/ethernet/netronome/nfp/nfd3/xsk.c index 45be6954d5aa..01cfa9cc1b5e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfd3/xsk.c +++ b/drivers/net/ethernet/netronome/nfp/nfd3/xsk.c @@ -184,7 +184,7 @@ nfp_nfd3_xsk_rx(struct nfp_net_rx_ring *rx_ring, int budget, xrxbuf->xdp->data += meta_len; xrxbuf->xdp->data_end = xrxbuf->xdp->data + pkt_len; xdp_set_data_meta_invalid(xrxbuf->xdp); - xsk_buff_dma_sync_for_cpu(xrxbuf->xdp, r_vec->xsk_pool); + xsk_buff_dma_sync_for_cpu(xrxbuf->xdp); net_prefetch(xrxbuf->xdp->data); if (meta_len) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7c6fb14b5555..206cba44dd30 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5352,7 +5352,7 @@ read_again: /* RX buffer is good and fit into a XSK pool buffer */ buf->xdp->data_end = buf->xdp->data + buf1_len; - xsk_buff_dma_sync_for_cpu(buf->xdp, rx_q->xsk_pool); + xsk_buff_dma_sync_for_cpu(buf->xdp); prog = READ_ONCE(priv->xdp_prog); res = __stmmac_xdp_run_prog(priv, prog, buf->xdp); diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index c9aec9ab6191..0a5dca2b2b3f 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -219,13 +219,10 @@ static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool return meta; } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); - if (!pool->dma_need_sync) - return; - xp_dma_sync_for_cpu(xskb); } @@ -402,7 +399,7 @@ static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool return NULL; } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) { } diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 99dd7376df6a..bacb33f1e3e5 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -43,7 +43,6 @@ struct xsk_dma_map { refcount_t users; struct list_head list; /* Protected by the RTNL_LOCK */ u32 dma_pages_cnt; - bool dma_need_sync; }; struct xsk_buff_pool { @@ -82,7 +81,6 @@ struct xsk_buff_pool { u8 tx_metadata_len; /* inherited from umem */ u8 cached_need_wakeup; bool uses_need_wakeup; - bool dma_need_sync; bool unaligned; bool tx_sw_csum; void *addrs; @@ -155,21 +153,17 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb) return xskb->frame_dma; } -void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb); static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb) { - xp_dma_sync_for_cpu_slow(xskb); + dma_sync_single_for_cpu(xskb->pool->dev, xskb->dma, + xskb->pool->frame_len, + DMA_BIDIRECTIONAL); } -void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma, - size_t size); static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { - if (!pool->dma_need_sync) - return; - - xp_dma_sync_for_device_slow(pool, dma, size); + dma_sync_single_for_device(pool->dev, dma, size, DMA_BIDIRECTIONAL); } /* Masks for xdp_umem_page flags. diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index ce60ecd48a4d..c0e0204b9630 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -338,7 +338,6 @@ static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_devi dma_map->netdev = netdev; dma_map->dev = dev; - dma_map->dma_need_sync = false; dma_map->dma_pages_cnt = nr_pages; refcount_set(&dma_map->users, 1); list_add(&dma_map->list, &umem->xsk_dma_list); @@ -424,7 +423,6 @@ static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_ pool->dev = dma_map->dev; pool->dma_pages_cnt = dma_map->dma_pages_cnt; - pool->dma_need_sync = dma_map->dma_need_sync; memcpy(pool->dma_pages, dma_map->dma_pages, pool->dma_pages_cnt * sizeof(*pool->dma_pages)); @@ -460,8 +458,6 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, __xp_dma_unmap(dma_map, attrs); return -ENOMEM; } - if (dma_need_sync(dev, dma)) - dma_map->dma_need_sync = true; dma_map->dma_pages[i] = dma; } @@ -557,11 +553,9 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool) xskb->xdp.data_meta = xskb->xdp.data; xskb->xdp.flags = 0; - if (pool->dma_need_sync) { - dma_sync_single_range_for_device(pool->dev, xskb->dma, 0, - pool->frame_len, - DMA_BIDIRECTIONAL); - } + if (pool->dev) + xp_dma_sync_for_device(pool, xskb->dma, pool->frame_len); + return &xskb->xdp; } EXPORT_SYMBOL(xp_alloc); @@ -633,7 +627,7 @@ u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) { u32 nb_entries1 = 0, nb_entries2; - if (unlikely(pool->dma_need_sync)) { + if (unlikely(pool->dev && dma_dev_need_sync(pool->dev))) { struct xdp_buff *buff; /* Slow path */ @@ -693,18 +687,3 @@ dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr) (addr & ~PAGE_MASK); } EXPORT_SYMBOL(xp_raw_get_dma); - -void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb) -{ - dma_sync_single_range_for_cpu(xskb->pool->dev, xskb->dma, 0, - xskb->pool->frame_len, DMA_BIDIRECTIONAL); -} -EXPORT_SYMBOL(xp_dma_sync_for_cpu_slow); - -void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma, - size_t size) -{ - dma_sync_single_range_for_device(pool->dev, dma, 0, - size, DMA_BIDIRECTIONAL); -} -EXPORT_SYMBOL(xp_dma_sync_for_device_slow); -- cgit v1.2.3