diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 874fad0a5cf8..0489c1c2e7dd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -56,6 +56,7 @@ #include #include #include +#include #include "bnxt_hsi.h" #include "bnxt.h" @@ -738,7 +739,6 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping, page_pool_recycle_direct(rxr->page_pool, page); return NULL; } - *mapping += bp->rx_dma_offset; return page; } @@ -780,6 +780,7 @@ int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, if (!page) return -ENOMEM; + mapping += bp->rx_dma_offset; rx_buf->data = page; rx_buf->data_ptr = page_address(page) + bp->rx_offset; } else { @@ -840,33 +841,41 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp, u16 sw_prod = rxr->rx_sw_agg_prod; unsigned int offset = 0; - if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) { - page = rxr->rx_page; - if (!page) { + if (BNXT_RX_PAGE_MODE(bp)) { + page = __bnxt_alloc_rx_page(bp, &mapping, rxr, gfp); + + if (!page) + return -ENOMEM; + + } else { + if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) { + page = rxr->rx_page; + if (!page) { + page = alloc_page(gfp); + if (!page) + return -ENOMEM; + rxr->rx_page = page; + rxr->rx_page_offset = 0; + } + offset = rxr->rx_page_offset; + rxr->rx_page_offset += BNXT_RX_PAGE_SIZE; + if (rxr->rx_page_offset == PAGE_SIZE) + rxr->rx_page = NULL; + else + get_page(page); + } else { page = alloc_page(gfp); if (!page) return -ENOMEM; - rxr->rx_page = page; - rxr->rx_page_offset = 0; } - offset = rxr->rx_page_offset; - rxr->rx_page_offset += BNXT_RX_PAGE_SIZE; - if (rxr->rx_page_offset == PAGE_SIZE) - rxr->rx_page = NULL; - else - get_page(page); - } else { - page = alloc_page(gfp); - if (!page) - return -ENOMEM; - } - mapping = dma_map_page_attrs(&pdev->dev, page, offset, - BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE, - DMA_ATTR_WEAK_ORDERING); - if (dma_mapping_error(&pdev->dev, mapping)) { - __free_page(page); - return -EIO; + mapping = dma_map_page_attrs(&pdev->dev, page, offset, + BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE, + DMA_ATTR_WEAK_ORDERING); + if (dma_mapping_error(&pdev->dev, mapping)) { + __free_page(page); + return -EIO; + } } if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap))) @@ -962,6 +971,39 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx, rxr->rx_sw_agg_prod = sw_prod; } +static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr, + u16 cons, void *data, u8 *data_ptr, + dma_addr_t dma_addr, + unsigned int offset_and_len) +{ + unsigned int len = offset_and_len & 0xffff; + struct page *page = data; + u16 prod = rxr->rx_prod; + struct sk_buff *skb; + int err; + + err = bnxt_alloc_rx_data(bp, rxr, prod, GFP_ATOMIC); + if (unlikely(err)) { + bnxt_reuse_rx_data(rxr, cons, data); + return NULL; + } + dma_addr -= bp->rx_dma_offset; + dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir, + DMA_ATTR_WEAK_ORDERING); + skb = build_skb(page_address(page), BNXT_PAGE_MODE_BUF_SIZE + + bp->rx_dma_offset); + if (!skb) { + __free_page(page); + return NULL; + } + skb_mark_for_recycle(skb); + skb_reserve(skb, bp->rx_dma_offset); + __skb_put(skb, len); + + return skb; +} + static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, void *data, u8 *data_ptr, @@ -984,7 +1026,6 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, dma_addr -= bp->rx_dma_offset; dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir, DMA_ATTR_WEAK_ORDERING); - page_pool_release_page(rxr->page_pool, page); if (unlikely(!payload)) payload = eth_get_headlen(bp->dev, data_ptr, len); @@ -995,6 +1036,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, return NULL; } + skb_mark_for_recycle(skb); off = (void *)data_ptr - page_address(page); skb_add_rx_frag(skb, 0, page, off, len, PAGE_SIZE); memcpy(skb->data - NET_IP_ALIGN, data_ptr - NET_IP_ALIGN, @@ -1038,22 +1080,24 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp, return skb; } -static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, - struct bnxt_cp_ring_info *cpr, - struct sk_buff *skb, u16 idx, - u32 agg_bufs, bool tpa) +static u32 __bnxt_rx_agg_pages(struct bnxt *bp, + struct bnxt_cp_ring_info *cpr, + struct skb_shared_info *shinfo, + u16 idx, u32 agg_bufs, bool tpa, + struct xdp_buff *xdp) { struct bnxt_napi *bnapi = cpr->bnapi; struct pci_dev *pdev = bp->pdev; struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; u16 prod = rxr->rx_agg_prod; + u32 i, total_frag_len = 0; bool p5_tpa = false; - u32 i; if ((bp->flags & BNXT_FLAG_CHIP_P5) && tpa) p5_tpa = true; for (i = 0; i < agg_bufs; i++) { + skb_frag_t *frag = &shinfo->frags[i]; u16 cons, frag_len; struct rx_agg_cmp *agg; struct bnxt_sw_rx_agg_bd *cons_rx_buf; @@ -1069,8 +1113,10 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT; cons_rx_buf = &rxr->rx_agg_ring[cons]; - skb_fill_page_desc(skb, i, cons_rx_buf->page, - cons_rx_buf->offset, frag_len); + skb_frag_off_set(frag, cons_rx_buf->offset); + skb_frag_size_set(frag, frag_len); + __skb_frag_set_page(frag, cons_rx_buf->page); + shinfo->nr_frags = i + 1; __clear_bit(cons, rxr->rx_agg_bmap); /* It is possible for bnxt_alloc_rx_page() to allocate @@ -1081,16 +1127,14 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, page = cons_rx_buf->page; cons_rx_buf->page = NULL; + if (xdp && page_is_pfmemalloc(page)) + xdp_buff_set_frag_pfmemalloc(xdp); + if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_ATOMIC) != 0) { - struct skb_shared_info *shinfo; unsigned int nr_frags; - shinfo = skb_shinfo(skb); nr_frags = --shinfo->nr_frags; __skb_frag_set_page(&shinfo->frags[nr_frags], NULL); - - dev_kfree_skb(skb); - cons_rx_buf->page = page; /* Update prod since possibly some pages have been @@ -1098,23 +1142,62 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, */ rxr->rx_agg_prod = prod; bnxt_reuse_rx_agg_bufs(cpr, idx, i, agg_bufs - i, tpa); - return NULL; + return 0; } dma_unmap_page_attrs(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE, - DMA_FROM_DEVICE, + bp->rx_dir, DMA_ATTR_WEAK_ORDERING); - skb->data_len += frag_len; - skb->len += frag_len; - skb->truesize += PAGE_SIZE; - + total_frag_len += frag_len; prod = NEXT_RX_AGG(prod); } rxr->rx_agg_prod = prod; + return total_frag_len; +} + +static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp, + struct bnxt_cp_ring_info *cpr, + struct sk_buff *skb, u16 idx, + u32 agg_bufs, bool tpa) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + u32 total_frag_len = 0; + + total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo, idx, + agg_bufs, tpa, NULL); + if (!total_frag_len) { + dev_kfree_skb(skb); + return NULL; + } + + skb->data_len += total_frag_len; + skb->len += total_frag_len; + skb->truesize += PAGE_SIZE * agg_bufs; return skb; } +static u32 bnxt_rx_agg_pages_xdp(struct bnxt *bp, + struct bnxt_cp_ring_info *cpr, + struct xdp_buff *xdp, u16 idx, + u32 agg_bufs, bool tpa) +{ + struct skb_shared_info *shinfo = xdp_get_shared_info_from_buff(xdp); + u32 total_frag_len = 0; + + if (!xdp_buff_has_frags(xdp)) + shinfo->nr_frags = 0; + + total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo, + idx, agg_bufs, tpa, xdp); + if (total_frag_len) { + xdp_buff_set_frags_flag(xdp); + shinfo->nr_frags = agg_bufs; + shinfo->xdp_frags_size = total_frag_len; + } + return total_frag_len; +} + static int bnxt_agg_bufs_valid(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, u8 agg_bufs, u32 *raw_cons) { @@ -1644,7 +1727,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, } if (agg_bufs) { - skb = bnxt_rx_pages(bp, cpr, skb, idx, agg_bufs, true); + skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, idx, agg_bufs, true); if (!skb) { /* Page reuse already handled by bnxt_rx_pages(). */ cpr->sw_stats.rx.rx_oom_discards += 1; @@ -1729,8 +1812,10 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, struct bnxt_sw_rx_bd *rx_buf; unsigned int len; u8 *data_ptr, agg_bufs, cmp_type; + bool xdp_active = false; dma_addr_t dma_addr; struct sk_buff *skb; + struct xdp_buff xdp; u32 flags, misc; void *data; int rc = 0; @@ -1839,18 +1924,39 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, len = flags >> RX_CMP_LEN_SHIFT; dma_addr = rx_buf->mapping; - if (bnxt_rx_xdp(bp, rxr, cons, data, &data_ptr, &len, event)) { - rc = 1; - goto next_rx; + if (bnxt_xdp_attached(bp, rxr)) { + bnxt_xdp_buff_init(bp, rxr, cons, &data_ptr, &len, &xdp); + if (agg_bufs) { + u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp, + cp_cons, agg_bufs, + false); + if (!frag_len) { + cpr->sw_stats.rx.rx_oom_discards += 1; + rc = -ENOMEM; + goto next_rx; + } + } + xdp_active = true; + } + + if (xdp_active) { + if (bnxt_rx_xdp(bp, rxr, cons, xdp, data, &len, event)) { + rc = 1; + goto next_rx; + } } if (len <= bp->rx_copy_thresh) { skb = bnxt_copy_skb(bnapi, data_ptr, len, dma_addr); bnxt_reuse_rx_data(rxr, cons, data); if (!skb) { - if (agg_bufs) - bnxt_reuse_rx_agg_bufs(cpr, cp_cons, 0, - agg_bufs, false); + if (agg_bufs) { + if (!xdp_active) + bnxt_reuse_rx_agg_bufs(cpr, cp_cons, 0, + agg_bufs, false); + else + bnxt_xdp_buff_frags_free(rxr, &xdp); + } cpr->sw_stats.rx.rx_oom_discards += 1; rc = -ENOMEM; goto next_rx; @@ -1872,11 +1978,22 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } if (agg_bufs) { - skb = bnxt_rx_pages(bp, cpr, skb, cp_cons, agg_bufs, false); - if (!skb) { - cpr->sw_stats.rx.rx_oom_discards += 1; - rc = -ENOMEM; - goto next_rx; + if (!xdp_active) { + skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, cp_cons, agg_bufs, false); + if (!skb) { + cpr->sw_stats.rx.rx_oom_discards += 1; + rc = -ENOMEM; + goto next_rx; + } + } else { + skb = bnxt_xdp_build_skb(bp, skb, agg_bufs, rxr->page_pool, &xdp, rxcmp1); + if (!skb) { + /* we should be able to free the old skb here */ + bnxt_xdp_buff_frags_free(rxr, &xdp); + cpr->sw_stats.rx.rx_oom_discards += 1; + rc = -ENOMEM; + goto next_rx; + } } } @@ -2492,10 +2609,13 @@ static void __bnxt_poll_work_done(struct bnxt *bp, struct bnxt_napi *bnapi) if ((bnapi->events & BNXT_RX_EVENT) && !(bnapi->in_reset)) { struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; - if (bnapi->events & BNXT_AGG_EVENT) - bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod); } + if (bnapi->events & BNXT_AGG_EVENT) { + struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; + + bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); + } bnapi->events = 0; } @@ -2872,14 +2992,23 @@ skip_rx_buf_free: if (!page) continue; - dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping, - BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE, - DMA_ATTR_WEAK_ORDERING); + if (BNXT_RX_PAGE_MODE(bp)) { + dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping, + BNXT_RX_PAGE_SIZE, bp->rx_dir, + DMA_ATTR_WEAK_ORDERING); + rx_agg_buf->page = NULL; + __clear_bit(i, rxr->rx_agg_bmap); - rx_agg_buf->page = NULL; - __clear_bit(i, rxr->rx_agg_bmap); + page_pool_recycle_direct(rxr->page_pool, page); + } else { + dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping, + BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE, + DMA_ATTR_WEAK_ORDERING); + rx_agg_buf->page = NULL; + __clear_bit(i, rxr->rx_agg_bmap); - __free_page(page); + __free_page(page); + } } skip_rx_agg_free: @@ -3793,7 +3922,7 @@ void bnxt_set_ring_params(struct bnxt *bp) /* 8 for CRC and VLAN */ rx_size = SKB_DATA_ALIGN(bp->dev->mtu + ETH_HLEN + NET_IP_ALIGN + 8); - rx_space = rx_size + NET_SKB_PAD + + rx_space = rx_size + ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); bp->rx_copy_thresh = BNXT_RX_COPY_THRESH; @@ -3834,9 +3963,15 @@ void bnxt_set_ring_params(struct bnxt *bp) } bp->rx_agg_ring_size = agg_ring_size; bp->rx_agg_ring_mask = (bp->rx_agg_nr_pages * RX_DESC_CNT) - 1; - rx_size = SKB_DATA_ALIGN(BNXT_RX_COPY_THRESH + NET_IP_ALIGN); - rx_space = rx_size + NET_SKB_PAD + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + if (BNXT_RX_PAGE_MODE(bp)) { + rx_space = BNXT_PAGE_MODE_BUF_SIZE; + rx_size = BNXT_MAX_PAGE_MODE_MTU; + } else { + rx_size = SKB_DATA_ALIGN(BNXT_RX_COPY_THRESH + NET_IP_ALIGN); + rx_space = rx_size + NET_SKB_PAD + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + } } bp->rx_buf_use_size = rx_size; @@ -3877,14 +4012,21 @@ void bnxt_set_ring_params(struct bnxt *bp) int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) { if (page_mode) { - if (bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) - return -EOPNOTSUPP; - bp->dev->max_mtu = - min_t(u16, bp->max_mtu, BNXT_MAX_PAGE_MODE_MTU); bp->flags &= ~BNXT_FLAG_AGG_RINGS; - bp->flags |= BNXT_FLAG_NO_AGG_RINGS | BNXT_FLAG_RX_PAGE_MODE; + bp->flags |= BNXT_FLAG_RX_PAGE_MODE; + + if (bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) { + bp->flags |= BNXT_FLAG_JUMBO; + bp->rx_skb_func = bnxt_rx_multi_page_skb; + bp->dev->max_mtu = + min_t(u16, bp->max_mtu, BNXT_MAX_MTU); + } else { + bp->flags |= BNXT_FLAG_NO_AGG_RINGS; + bp->rx_skb_func = bnxt_rx_page_skb; + bp->dev->max_mtu = + min_t(u16, bp->max_mtu, BNXT_MAX_PAGE_MODE_MTU); + } bp->rx_dir = DMA_BIDIRECTIONAL; - bp->rx_skb_func = bnxt_rx_page_skb; /* Disable LRO or GRO_HW */ netdev_update_features(bp->dev); } else { @@ -5226,12 +5368,15 @@ static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, u16 vnic_id) if (rc) return rc; - req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT | - VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 | - VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6); - req->enables = - cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID | - VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID); + req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT); + req->enables = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID); + + if (BNXT_RX_PAGE_MODE(bp) && !BNXT_RX_JUMBO_MODE(bp)) { + req->flags |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 | + VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6); + req->enables |= + cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID); + } /* thresholds not implemented in firmware yet */ req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh); req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh); @@ -11031,6 +11176,9 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev, if (bp->flags & BNXT_FLAG_NO_AGG_RINGS) features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW); + if (!(bp->flags & BNXT_FLAG_TPA)) + features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW); + if (!(features & NETIF_F_GRO)) features &= ~NETIF_F_GRO_HW; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 98453a78cbd0..a498ee297946 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -591,10 +591,12 @@ struct nqe_cn { #define BNXT_RX_PAGE_SIZE (1 << BNXT_RX_PAGE_SHIFT) #define BNXT_MAX_MTU 9500 -#define BNXT_MAX_PAGE_MODE_MTU \ +#define BNXT_PAGE_MODE_BUF_SIZE \ ((unsigned int)PAGE_SIZE - VLAN_ETH_HLEN - NET_IP_ALIGN - \ - XDP_PACKET_HEADROOM - \ - SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info))) + XDP_PACKET_HEADROOM) +#define BNXT_MAX_PAGE_MODE_MTU \ + BNXT_PAGE_MODE_BUF_SIZE - \ + SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info)) #define BNXT_MIN_PKT_SIZE 52 @@ -699,13 +701,12 @@ struct bnxt_sw_tx_bd { }; DEFINE_DMA_UNMAP_ADDR(mapping); DEFINE_DMA_UNMAP_LEN(len); + struct page *page; u8 is_gso; u8 is_push; u8 action; - union { - unsigned short nr_frags; - u16 rx_prod; - }; + unsigned short nr_frags; + u16 rx_prod; }; struct bnxt_sw_rx_bd { @@ -1817,6 +1818,7 @@ struct bnxt { #define BNXT_SUPPORTS_TPA(bp) (!BNXT_CHIP_TYPE_NITRO_A0(bp) && \ (!((bp)->flags & BNXT_FLAG_CHIP_P5) || \ (bp)->max_tpa_v2) && !is_kdump_kernel()) +#define BNXT_RX_JUMBO_MODE(bp) ((bp)->flags & BNXT_FLAG_JUMBO) #define BNXT_CHIP_SR2(bp) \ ((bp)->chip_num == CHIP_NUM_58818) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 22e965e18fbc..b3a48d6675fe 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -3491,7 +3491,7 @@ static int bnxt_run_loopback(struct bnxt *bp) dev_kfree_skb(skb); return -EIO; } - bnxt_xmit_bd(bp, txr, map, pkt_size); + bnxt_xmit_bd(bp, txr, map, pkt_size, NULL); /* Sync BD data before updating doorbell */ wmb(); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 03b1d6c04504..f02fe906dedb 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -24,36 +24,91 @@ DEFINE_STATIC_KEY_FALSE(bnxt_xdp_locking_key); struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, struct bnxt_tx_ring_info *txr, - dma_addr_t mapping, u32 len) + dma_addr_t mapping, u32 len, + struct xdp_buff *xdp) { - struct bnxt_sw_tx_bd *tx_buf; + struct skb_shared_info *sinfo; + struct bnxt_sw_tx_bd *tx_buf, *first_buf; struct tx_bd *txbd; + int num_frags = 0; u32 flags; u16 prod; + int i; + if (xdp && xdp_buff_has_frags(xdp)) { + sinfo = xdp_get_shared_info_from_buff(xdp); + num_frags = sinfo->nr_frags; + } + + /* fill up the first buffer */ prod = txr->tx_prod; tx_buf = &txr->tx_buf_ring[prod]; + first_buf = tx_buf; + tx_buf->nr_frags = num_frags; + if (xdp) + tx_buf->page = virt_to_head_page(xdp->data); txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)]; - flags = (len << TX_BD_LEN_SHIFT) | (1 << TX_BD_FLAGS_BD_CNT_SHIFT) | - TX_BD_FLAGS_PACKET_END | bnxt_lhint_arr[len >> 9]; + flags = ((len) << TX_BD_LEN_SHIFT) | ((num_frags + 1) << TX_BD_FLAGS_BD_CNT_SHIFT); txbd->tx_bd_len_flags_type = cpu_to_le32(flags); txbd->tx_bd_opaque = prod; txbd->tx_bd_haddr = cpu_to_le64(mapping); + /* now let us fill up the frags into the next buffers */ + for (i = 0; i < num_frags ; i++) { + skb_frag_t *frag = &sinfo->frags[i]; + struct bnxt_sw_tx_bd *frag_tx_buf; + struct pci_dev *pdev = bp->pdev; + dma_addr_t frag_mapping; + int frag_len; + + prod = NEXT_TX(prod); + txr->tx_prod = prod; + + /* first fill up the first buffer */ + frag_tx_buf = &txr->tx_buf_ring[prod]; + frag_tx_buf->page = skb_frag_page(frag); + + txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)]; + + frag_len = skb_frag_size(frag); + frag_mapping = skb_frag_dma_map(&pdev->dev, frag, 0, + frag_len, DMA_TO_DEVICE); + + if (unlikely(dma_mapping_error(&pdev->dev, frag_mapping))) + return NULL; + + dma_unmap_addr_set(frag_tx_buf, mapping, frag_mapping); + + flags = frag_len << TX_BD_LEN_SHIFT; + txbd->tx_bd_len_flags_type = cpu_to_le32(flags); + txbd->tx_bd_opaque = prod; + txbd->tx_bd_haddr = cpu_to_le64(frag_mapping); + + len = frag_len; + } + + flags &= ~TX_BD_LEN; + txbd->tx_bd_len_flags_type = cpu_to_le32(((len) << TX_BD_LEN_SHIFT) | flags | + TX_BD_FLAGS_PACKET_END); + /* Sync TX BD */ + wmb(); prod = NEXT_TX(prod); txr->tx_prod = prod; - return tx_buf; + + return first_buf; } static void __bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr, - dma_addr_t mapping, u32 len, u16 rx_prod) + dma_addr_t mapping, u32 len, u16 rx_prod, + struct xdp_buff *xdp) { struct bnxt_sw_tx_bd *tx_buf; - tx_buf = bnxt_xmit_bd(bp, txr, mapping, len); + tx_buf = bnxt_xmit_bd(bp, txr, mapping, len, xdp); tx_buf->rx_prod = rx_prod; tx_buf->action = XDP_TX; + } static void __bnxt_xmit_xdp_redirect(struct bnxt *bp, @@ -63,7 +118,7 @@ static void __bnxt_xmit_xdp_redirect(struct bnxt *bp, { struct bnxt_sw_tx_bd *tx_buf; - tx_buf = bnxt_xmit_bd(bp, txr, mapping, len); + tx_buf = bnxt_xmit_bd(bp, txr, mapping, len, NULL); tx_buf->action = XDP_REDIRECT; tx_buf->xdpf = xdpf; dma_unmap_addr_set(tx_buf, mapping, mapping); @@ -78,7 +133,7 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) struct bnxt_sw_tx_bd *tx_buf; u16 tx_cons = txr->tx_cons; u16 last_tx_cons = tx_cons; - int i; + int i, j, frags; for (i = 0; i < nr_pkts; i++) { tx_buf = &txr->tx_buf_ring[tx_cons]; @@ -96,6 +151,13 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) } else if (tx_buf->action == XDP_TX) { rx_doorbell_needed = true; last_tx_cons = tx_cons; + + frags = tx_buf->nr_frags; + for (j = 0; j < frags; j++) { + tx_cons = NEXT_TX(tx_cons); + tx_buf = &txr->tx_buf_ring[tx_cons]; + page_pool_recycle_direct(rxr->page_pool, tx_buf->page); + } } tx_cons = NEXT_TX(tx_cons); } @@ -103,22 +165,67 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) if (rx_doorbell_needed) { tx_buf = &txr->tx_buf_ring[last_tx_cons]; bnxt_db_write(bp, &rxr->rx_db, tx_buf->rx_prod); + } } +bool bnxt_xdp_attached(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) +{ + struct bpf_prog *xdp_prog = READ_ONCE(rxr->xdp_prog); + + return !!xdp_prog; +} + +void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, + u16 cons, u8 **data_ptr, unsigned int *len, + struct xdp_buff *xdp) +{ + struct bnxt_sw_rx_bd *rx_buf; + struct pci_dev *pdev; + dma_addr_t mapping; + u32 offset; + + pdev = bp->pdev; + rx_buf = &rxr->rx_buf_ring[cons]; + offset = bp->rx_offset; + + mapping = rx_buf->mapping - bp->rx_dma_offset; + dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir); + + xdp_init_buff(xdp, BNXT_PAGE_MODE_BUF_SIZE + offset, &rxr->xdp_rxq); + xdp_prepare_buff(xdp, *data_ptr - offset, offset, *len, false); +} + +void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr, + struct xdp_buff *xdp) +{ + struct skb_shared_info *shinfo; + int i; + + if (!xdp || !xdp_buff_has_frags(xdp)) + return; + shinfo = xdp_get_shared_info_from_buff(xdp); + for (i = 0; i < shinfo->nr_frags; i++) { + struct page *page = skb_frag_page(&shinfo->frags[i]); + + page_pool_recycle_direct(rxr->page_pool, page); + } + shinfo->nr_frags = 0; +} + /* returns the following: * true - packet consumed by XDP and new buffer is allocated. * false - packet should be passed to the stack. */ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, - struct page *page, u8 **data_ptr, unsigned int *len, u8 *event) + struct xdp_buff xdp, struct page *page, unsigned int *len, u8 *event) { struct bpf_prog *xdp_prog = READ_ONCE(rxr->xdp_prog); struct bnxt_tx_ring_info *txr; struct bnxt_sw_rx_bd *rx_buf; struct pci_dev *pdev; - struct xdp_buff xdp; dma_addr_t mapping; + u32 tx_needed = 1; void *orig_data; u32 tx_avail; u32 offset; @@ -128,16 +235,10 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, return false; pdev = bp->pdev; - rx_buf = &rxr->rx_buf_ring[cons]; offset = bp->rx_offset; - mapping = rx_buf->mapping - bp->rx_dma_offset; - dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir); - txr = rxr->bnapi->tx_ring; /* BNXT_RX_PAGE_MODE(bp) when XDP enabled */ - xdp_init_buff(&xdp, PAGE_SIZE, &rxr->xdp_rxq); - xdp_prepare_buff(&xdp, *data_ptr - offset, offset, *len, false); orig_data = xdp.data; act = bpf_prog_run_xdp(xdp_prog, &xdp); @@ -150,26 +251,38 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, *event &= ~BNXT_RX_EVENT; *len = xdp.data_end - xdp.data; - if (orig_data != xdp.data) { + if (orig_data != xdp.data) offset = xdp.data - xdp.data_hard_start; - *data_ptr = xdp.data_hard_start + offset; - } + switch (act) { case XDP_PASS: return false; case XDP_TX: - if (tx_avail < 1) { + rx_buf = &rxr->rx_buf_ring[cons]; + mapping = rx_buf->mapping - bp->rx_dma_offset; + *event = 0; + + if (unlikely(xdp_buff_has_frags(&xdp))) { + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(&xdp); + + tx_needed += sinfo->nr_frags; + *event = BNXT_AGG_EVENT; + } + + if (tx_avail < tx_needed) { trace_xdp_exception(bp->dev, xdp_prog, act); + bnxt_xdp_buff_frags_free(rxr, &xdp); bnxt_reuse_rx_data(rxr, cons, page); return true; } - *event = BNXT_TX_EVENT; dma_sync_single_for_device(&pdev->dev, mapping + offset, *len, bp->rx_dir); + + *event |= BNXT_TX_EVENT; __bnxt_xmit_xdp(bp, txr, mapping + offset, *len, - NEXT_RX(rxr->rx_prod)); + NEXT_RX(rxr->rx_prod), &xdp); bnxt_reuse_rx_data(rxr, cons, page); return true; case XDP_REDIRECT: @@ -177,6 +290,8 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, * redirect is coming from a frame received by the * bnxt_en driver. */ + rx_buf = &rxr->rx_buf_ring[cons]; + mapping = rx_buf->mapping - bp->rx_dma_offset; dma_unmap_page_attrs(&pdev->dev, mapping, PAGE_SIZE, bp->rx_dir, DMA_ATTR_WEAK_ORDERING); @@ -184,6 +299,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, /* if we are unable to allocate a new buffer, abort and reuse */ if (bnxt_alloc_rx_data(bp, rxr, rxr->rx_prod, GFP_ATOMIC)) { trace_xdp_exception(bp->dev, xdp_prog, act); + bnxt_xdp_buff_frags_free(rxr, &xdp); bnxt_reuse_rx_data(rxr, cons, page); return true; } @@ -203,6 +319,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, trace_xdp_exception(bp->dev, xdp_prog, act); fallthrough; case XDP_DROP: + bnxt_xdp_buff_frags_free(rxr, &xdp); bnxt_reuse_rx_data(rxr, cons, page); break; } @@ -270,8 +387,9 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog) int tx_xdp = 0, rc, tc; struct bpf_prog *old; - if (prog && bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) { - netdev_warn(dev, "MTU %d larger than largest XDP supported MTU %d.\n", + if (prog && !prog->aux->xdp_has_frags && + bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) { + netdev_warn(dev, "MTU %d larger than %d without XDP frag support.\n", bp->dev->mtu, BNXT_MAX_PAGE_MODE_MTU); return -EOPNOTSUPP; } @@ -337,3 +455,26 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp) } return rc; } + +struct sk_buff * +bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags, + struct page_pool *pool, struct xdp_buff *xdp, + struct rx_cmp_ext *rxcmp1) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + + if (!skb) + return NULL; + skb_checksum_none_assert(skb); + if (RX_CMP_L4_CS_OK(rxcmp1)) { + if (bp->dev->features & NETIF_F_RXCSUM) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->csum_level = RX_CMP_ENCAP(rxcmp1); + } + } + xdp_update_skb_shared_info(skb, num_frags, + sinfo->xdp_frags_size, + PAGE_SIZE * sinfo->nr_frags, + xdp_buff_is_frag_pfmemalloc(xdp)); + return skb; +} diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h index 067bb5e821f5..505911ae095d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h @@ -14,13 +14,25 @@ DECLARE_STATIC_KEY_FALSE(bnxt_xdp_locking_key); struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, struct bnxt_tx_ring_info *txr, - dma_addr_t mapping, u32 len); + dma_addr_t mapping, u32 len, + struct xdp_buff *xdp); void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts); bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, - struct page *page, u8 **data_ptr, unsigned int *len, + struct xdp_buff xdp, struct page *page, unsigned int *len, u8 *event); int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp); int bnxt_xdp_xmit(struct net_device *dev, int num_frames, struct xdp_frame **frames, u32 flags); +bool bnxt_xdp_attached(struct bnxt *bp, struct bnxt_rx_ring_info *rxr); + +void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, + u16 cons, u8 **data_ptr, unsigned int *len, + struct xdp_buff *xdp); +void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr, + struct xdp_buff *xdp); +struct sk_buff *bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, + u8 num_frags, struct page_pool *pool, + struct xdp_buff *xdp, + struct rx_cmp_ext *rxcmp1); #endif