From mboxrd@z Thu Jan 1 00:00:00 1970 From: Brenden Blanco Subject: [PATCH v6 06/12] net/mlx4_en: add page recycle to prepare rx ring for tx support Date: Thu, 7 Jul 2016 19:15:18 -0700 Message-ID: <1467944124-14891-7-git-send-email-bblanco@plumgrid.com> References: <1467944124-14891-1-git-send-email-bblanco@plumgrid.com> Cc: Brenden Blanco , Martin KaFai Lau , Jesper Dangaard Brouer , Ari Saha , Alexei Starovoitov , Or Gerlitz , john.fastabend@gmail.com, hannes@stressinduktion.org, Thomas Graf , Tom Herbert , Daniel Borkmann To: davem@davemloft.net, netdev@vger.kernel.org Return-path: Received: from mail-pa0-f43.google.com ([209.85.220.43]:35273 "EHLO mail-pa0-f43.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753953AbcGHCPn (ORCPT ); Thu, 7 Jul 2016 22:15:43 -0400 Received: by mail-pa0-f43.google.com with SMTP id dx3so10985178pab.2 for ; Thu, 07 Jul 2016 19:15:43 -0700 (PDT) In-Reply-To: <1467944124-14891-1-git-send-email-bblanco@plumgrid.com> Sender: netdev-owner@vger.kernel.org List-ID: The mlx4 driver by default allocates order-3 pages for the ring to consume in multiple fragments. When the device has an xdp program, this behavior will prevent tx actions since the page must be re-mapped in TODEVICE mode, which cannot be done if the page is still shared. Start by making the allocator configurable based on whether xdp is running, such that order-0 pages are always used and never shared. Since this will stress the page allocator, add a simple page cache to each rx ring. Pages in the cache are left dma-mapped, and in drop-only stress tests the page allocator is eliminated from the perf report. Note that setting an xdp program will now require the rings to be reconfigured. Before: 26.91% ksoftirqd/0 [mlx4_en] [k] mlx4_en_process_rx_cq 17.88% ksoftirqd/0 [mlx4_en] [k] mlx4_en_alloc_frags 6.00% ksoftirqd/0 [mlx4_en] [k] mlx4_en_free_frag 4.49% ksoftirqd/0 [kernel.vmlinux] [k] get_page_from_freelist 3.21% swapper [kernel.vmlinux] [k] intel_idle 2.73% ksoftirqd/0 [kernel.vmlinux] [k] bpf_map_lookup_elem 2.57% swapper [mlx4_en] [k] mlx4_en_process_rx_cq After: 31.72% swapper [kernel.vmlinux] [k] intel_idle 8.79% swapper [mlx4_en] [k] mlx4_en_process_rx_cq 7.54% swapper [kernel.vmlinux] [k] poll_idle 6.36% swapper [mlx4_core] [k] mlx4_eq_int 4.21% swapper [kernel.vmlinux] [k] tasklet_action 4.03% swapper [kernel.vmlinux] [k] cpuidle_enter_state 3.43% swapper [mlx4_en] [k] mlx4_en_prepare_rx_desc 2.18% swapper [kernel.vmlinux] [k] native_irq_return_iret 1.37% swapper [kernel.vmlinux] [k] menu_select 1.09% swapper [kernel.vmlinux] [k] bpf_map_lookup_elem Signed-off-by: Brenden Blanco --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 46 +++++++++++++++-- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 69 ++++++++++++++++++++++--- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 12 ++++- 4 files changed, 115 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 51a2e82..d3d51fa 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -47,7 +47,7 @@ #define EN_ETHTOOL_SHORT_MASK cpu_to_be16(0xffff) #define EN_ETHTOOL_WORD_MASK cpu_to_be32(0xffffffff) -static int mlx4_en_moderation_update(struct mlx4_en_priv *priv) +int mlx4_en_moderation_update(struct mlx4_en_priv *priv) { int i; int err = 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 5c6b1a0c..2883315 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2532,19 +2532,57 @@ static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 m static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) { struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = priv->mdev; struct bpf_prog *old_prog; + int port_up = 0; + int err; + + /* No need to reconfigure buffers when simply swapping the + * program for a new one. + */ + if (READ_ONCE(priv->prog) && prog) { + /* This xchg is paired with READ_ONCE in the fast path, but is + * also protected from itself via rtnl lock + */ + old_prog = xchg(&priv->prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + return 0; + } if (priv->num_frags > 1) return -EOPNOTSUPP; - /* This xchg is paired with READ_ONCE in the fast path, but is - * also protected from itself via rtnl lock - */ + mutex_lock(&mdev->state_lock); + if (priv->port_up) { + port_up = 1; + mlx4_en_stop_port(dev, 1); + } + + mlx4_en_free_resources(priv); + old_prog = xchg(&priv->prog, prog); if (old_prog) bpf_prog_put(old_prog); - return 0; + err = mlx4_en_alloc_resources(priv); + if (err) { + en_err(priv, "Failed reallocating port resources\n"); + goto out; + } + if (port_up) { + err = mlx4_en_start_port(dev); + if (err) + en_err(priv, "Failed starting port\n"); + } + + err = mlx4_en_moderation_update(priv); + +out: + if (err) + priv->prog = NULL; + mutex_unlock(&mdev->state_lock); + return err; } static bool mlx4_xdp_attached(struct net_device *dev) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 2bf3d62..02d63a0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -57,7 +57,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv, struct page *page; dma_addr_t dma; - for (order = MLX4_EN_ALLOC_PREFER_ORDER; ;) { + for (order = frag_info->order; ;) { gfp_t gfp = _gfp; if (order) @@ -70,7 +70,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv, return -ENOMEM; } dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE << order, - PCI_DMA_FROMDEVICE); + frag_info->dma_dir); if (dma_mapping_error(priv->ddev, dma)) { put_page(page); return -ENOMEM; @@ -124,7 +124,8 @@ out: while (i--) { if (page_alloc[i].page != ring_alloc[i].page) { dma_unmap_page(priv->ddev, page_alloc[i].dma, - page_alloc[i].page_size, PCI_DMA_FROMDEVICE); + page_alloc[i].page_size, + priv->frag_info[i].dma_dir); page = page_alloc[i].page; /* Revert changes done by mlx4_alloc_pages */ page_ref_sub(page, page_alloc[i].page_size / @@ -145,7 +146,7 @@ static void mlx4_en_free_frag(struct mlx4_en_priv *priv, if (next_frag_end > frags[i].page_size) dma_unmap_page(priv->ddev, frags[i].dma, frags[i].page_size, - PCI_DMA_FROMDEVICE); + frag_info->dma_dir); if (frags[i].page) put_page(frags[i].page); @@ -176,7 +177,8 @@ out: page_alloc = &ring->page_alloc[i]; dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->page_size, PCI_DMA_FROMDEVICE); + page_alloc->page_size, + priv->frag_info[i].dma_dir); page = page_alloc->page; /* Revert changes done by mlx4_alloc_pages */ page_ref_sub(page, page_alloc->page_size / @@ -201,7 +203,7 @@ static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv, i, page_count(page_alloc->page)); dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->page_size, PCI_DMA_FROMDEVICE); + page_alloc->page_size, frag_info->dma_dir); while (page_alloc->page_offset + frag_info->frag_stride < page_alloc->page_size) { put_page(page_alloc->page); @@ -244,6 +246,12 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, struct mlx4_en_rx_alloc *frags = ring->rx_info + (index << priv->log_rx_info); + if (ring->page_cache.index > 0) { + frags[0] = ring->page_cache.buf[--ring->page_cache.index]; + rx_desc->data[0].addr = cpu_to_be64(frags[0].dma); + return 0; + } + return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp); } @@ -502,12 +510,39 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv) } } +/* When the rx ring is running in page-per-packet mode, a released frame can go + * directly into a small cache, to avoid unmapping or touching the page + * allocator. In bpf prog performance scenarios, buffers are either forwarded + * or dropped, never converted to skbs, so every page can come directly from + * this cache when it is sized to be a multiple of the napi budget. + */ +bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring, + struct mlx4_en_rx_alloc *frame) +{ + struct mlx4_en_page_cache *cache = &ring->page_cache; + + if (cache->index >= MLX4_EN_CACHE_SIZE) + return false; + + cache->buf[cache->index++] = *frame; + return true; +} + void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv, struct mlx4_en_rx_ring **pring, u32 size, u16 stride) { struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_en_rx_ring *ring = *pring; + int i; + + for (i = 0; i < ring->page_cache.index; i++) { + struct mlx4_en_rx_alloc *frame = &ring->page_cache.buf[i]; + + dma_unmap_page(priv->ddev, frame->dma, frame->page_size, + priv->frag_info[0].dma_dir); + put_page(frame->page); + } mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE); vfree(ring->rx_info); @@ -862,6 +897,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud default: bpf_warn_invalid_xdp_action(act); case XDP_DROP: + if (mlx4_en_rx_recycle(ring, frags)) + goto consumed; goto next; } } @@ -1017,6 +1054,7 @@ next: for (nr = 0; nr < priv->num_frags; nr++) mlx4_en_free_frag(priv, frags, nr); +consumed: ++cq->mcq.cons_index; index = (cq->mcq.cons_index) & ring->size_mask; cqe = mlx4_en_get_cqe(cq->buf, index, priv->cqe_size) + factor; @@ -1092,19 +1130,34 @@ static const int frag_sizes[] = { void mlx4_en_calc_rx_buf(struct net_device *dev) { + enum dma_data_direction dma_dir = PCI_DMA_FROMDEVICE; struct mlx4_en_priv *priv = netdev_priv(dev); int eff_mtu = MLX4_EN_EFF_MTU(dev->mtu); + int order = MLX4_EN_ALLOC_PREFER_ORDER; + u32 align = SMP_CACHE_BYTES; int buf_size = 0; int i = 0; + /* bpf requires buffers to be set up as 1 packet per page. + * This only works when num_frags == 1. + */ + if (priv->prog) { + /* This will gain efficient xdp frame recycling at the expense + * of more costly truesize accounting + */ + align = PAGE_SIZE; + order = 0; + } + while (buf_size < eff_mtu) { + priv->frag_info[i].order = order; priv->frag_info[i].frag_size = (eff_mtu > buf_size + frag_sizes[i]) ? frag_sizes[i] : eff_mtu - buf_size; priv->frag_info[i].frag_prefix_size = buf_size; priv->frag_info[i].frag_stride = - ALIGN(priv->frag_info[i].frag_size, - SMP_CACHE_BYTES); + ALIGN(priv->frag_info[i].frag_size, align); + priv->frag_info[i].dma_dir = dma_dir; buf_size += priv->frag_info[i].frag_size; i++; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 35ecfa2..0e0ecd1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -259,6 +259,12 @@ struct mlx4_en_rx_alloc { u32 page_size; }; +#define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT) +struct mlx4_en_page_cache { + u32 index; + struct mlx4_en_rx_alloc buf[MLX4_EN_CACHE_SIZE]; +}; + struct mlx4_en_tx_ring { /* cache line used and dirtied in tx completion * (mlx4_en_free_tx_buf()) @@ -323,6 +329,7 @@ struct mlx4_en_rx_ring { u8 fcs_del; void *buf; void *rx_info; + struct mlx4_en_page_cache page_cache; unsigned long bytes; unsigned long packets; unsigned long csum_ok; @@ -442,7 +449,9 @@ struct mlx4_en_mc_list { struct mlx4_en_frag_info { u16 frag_size; u16 frag_prefix_size; - u16 frag_stride; + u32 frag_stride; + enum dma_data_direction dma_dir; + int order; }; #ifdef CONFIG_MLX4_EN_DCB @@ -654,6 +663,7 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev, void mlx4_en_free_resources(struct mlx4_en_priv *priv); int mlx4_en_alloc_resources(struct mlx4_en_priv *priv); +int mlx4_en_moderation_update(struct mlx4_en_priv *priv); int mlx4_en_create_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq, int entries, int ring, enum cq_type mode, int node); -- 2.8.2