diff options
Diffstat (limited to 'drivers')
27 files changed, 390 insertions, 1281 deletions
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2a037ec244b9..ea7395b391e5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11,7 +11,7 @@ #include "i40e_diag.h" #include "i40e_xsk.h" #include <net/udp_tunnel.h> -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> /* All i40e tracepoints are defined by the include below, which * must be included exactly once across the whole kernel with * CREATE_TRACE_POINTS defined @@ -3260,26 +3260,31 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) if (ring->vsi->type == I40E_VSI_MAIN) xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + kfree(ring->rx_bi); ring->xsk_umem = i40e_xsk_umem(ring); if (ring->xsk_umem) { - ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr - - XDP_PACKET_HEADROOM; + ret = i40e_alloc_rx_bi_zc(ring); + if (ret) + return ret; + ring->rx_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem); /* For AF_XDP ZC, we disallow packets to span on * multiple buffers, thus letting us skip that * handling in the fast-path. */ chain_len = 1; - ring->zca.free = i40e_zca_free; ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_ZERO_COPY, - &ring->zca); + MEM_TYPE_XSK_BUFF_POOL, + NULL); if (ret) return ret; dev_info(&vsi->back->pdev->dev, - "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n", + "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->queue_index); } else { + ret = i40e_alloc_rx_bi(ring); + if (ret) + return ret; ring->rx_buf_len = vsi->rx_buf_len; if (ring->vsi->type == I40E_VSI_MAIN) { ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, @@ -3344,9 +3349,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q); writel(0, ring->tail); - ok = ring->xsk_umem ? - i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) : - !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); + if (ring->xsk_umem) { + xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq); + ok = i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)); + } else { + ok = !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); + } if (!ok) { /* Log this in case the user has forgotten to give the kernel * any buffers, even later in the application. diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index a3772beffe02..f613782f2f56 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -521,28 +521,29 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi, /** * i40e_fd_handle_status - check the Programming Status for FD * @rx_ring: the Rx ring for this descriptor - * @rx_desc: the Rx descriptor for programming Status, not a packet descriptor. + * @qword0_raw: qword0 + * @qword1: qword1 after le_to_cpu * @prog_id: the id originally used for programming * * This is used to verify if the FD programming or invalidation * requested by SW to the HW is successful or not and take actions accordingly. **/ -void i40e_fd_handle_status(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, u8 prog_id) +static void i40e_fd_handle_status(struct i40e_ring *rx_ring, u64 qword0_raw, + u64 qword1, u8 prog_id) { struct i40e_pf *pf = rx_ring->vsi->back; struct pci_dev *pdev = pf->pdev; + struct i40e_32b_rx_wb_qw0 *qw0; u32 fcnt_prog, fcnt_avail; u32 error; - u64 qw; - qw = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - error = (qw & I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK) >> + qw0 = (struct i40e_32b_rx_wb_qw0 *)&qword0_raw; + error = (qword1 & I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK) >> I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT; if (error == BIT(I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT)) { - pf->fd_inv = le32_to_cpu(rx_desc->wb.qword0.hi_dword.fd_id); - if ((rx_desc->wb.qword0.hi_dword.fd_id != 0) || + pf->fd_inv = le32_to_cpu(qw0->hi_dword.fd_id); + if (qw0->hi_dword.fd_id != 0 || (I40E_DEBUG_FD & pf->hw.debug_mask)) dev_warn(&pdev->dev, "ntuple filter loc = %d, could not be added\n", pf->fd_inv); @@ -560,7 +561,7 @@ void i40e_fd_handle_status(struct i40e_ring *rx_ring, /* store the current atr filter count */ pf->fd_atr_cnt = i40e_get_current_atr_cnt(pf); - if ((rx_desc->wb.qword0.hi_dword.fd_id == 0) && + if (qw0->hi_dword.fd_id == 0 && test_bit(__I40E_FD_SB_AUTO_DISABLED, pf->state)) { /* These set_bit() calls aren't atomic with the * test_bit() here, but worse case we potentially @@ -589,7 +590,7 @@ void i40e_fd_handle_status(struct i40e_ring *rx_ring, } else if (error == BIT(I40E_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT)) { if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pdev->dev, "ntuple filter fd_id = %d, could not be removed\n", - rx_desc->wb.qword0.hi_dword.fd_id); + qw0->hi_dword.fd_id); } } @@ -1195,6 +1196,11 @@ clear_counts: rc->total_packets = 0; } +static struct i40e_rx_buffer *i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx) +{ + return &rx_ring->rx_bi[idx]; +} + /** * i40e_reuse_rx_page - page flip buffer and store it back on the ring * @rx_ring: rx descriptor ring to store buffers on @@ -1208,7 +1214,7 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, struct i40e_rx_buffer *new_buff; u16 nta = rx_ring->next_to_alloc; - new_buff = &rx_ring->rx_bi[nta]; + new_buff = i40e_rx_bi(rx_ring, nta); /* update, and store next to alloc */ nta++; @@ -1227,29 +1233,10 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, } /** - * i40e_rx_is_programming_status - check for programming status descriptor - * @qw: qword representing status_error_len in CPU ordering - * - * The value of in the descriptor length field indicate if this - * is a programming status descriptor for flow director or FCoE - * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise - * it is a packet descriptor. - **/ -static inline bool i40e_rx_is_programming_status(u64 qw) -{ - /* The Rx filter programming status and SPH bit occupy the same - * spot in the descriptor. Since we don't support packet split we - * can just reuse the bit as an indication that this is a - * programming status descriptor. - */ - return qw & I40E_RXD_QW1_LENGTH_SPH_MASK; -} - -/** - * i40e_clean_programming_status - try clean the programming status descriptor + * i40e_clean_programming_status - clean the programming status descriptor * @rx_ring: the rx ring that has this descriptor - * @rx_desc: the rx descriptor written back by HW - * @qw: qword representing status_error_len in CPU ordering + * @qword0_raw: qword0 + * @qword1: qword1 representing status_error_len in CPU ordering * * Flow director should handle FD_FILTER_STATUS to check its filter programming * status being successful or not and take actions accordingly. FCoE should @@ -1257,34 +1244,16 @@ static inline bool i40e_rx_is_programming_status(u64 qw) * * Returns an i40e_rx_buffer to reuse if the cleanup occurred, otherwise NULL. **/ -struct i40e_rx_buffer *i40e_clean_programming_status( - struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, - u64 qw) +void i40e_clean_programming_status(struct i40e_ring *rx_ring, u64 qword0_raw, + u64 qword1) { - struct i40e_rx_buffer *rx_buffer; - u32 ntc; u8 id; - if (!i40e_rx_is_programming_status(qw)) - return NULL; - - ntc = rx_ring->next_to_clean; - - /* fetch, update, and store next to clean */ - rx_buffer = &rx_ring->rx_bi[ntc++]; - ntc = (ntc < rx_ring->count) ? ntc : 0; - rx_ring->next_to_clean = ntc; - - prefetch(I40E_RX_DESC(rx_ring, ntc)); - - id = (qw & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >> + id = (qword1 & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >> I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT; if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS) - i40e_fd_handle_status(rx_ring, rx_desc, id); - - return rx_buffer; + i40e_fd_handle_status(rx_ring, qword0_raw, qword1, id); } /** @@ -1336,13 +1305,25 @@ err: return -ENOMEM; } +int i40e_alloc_rx_bi(struct i40e_ring *rx_ring) +{ + unsigned long sz = sizeof(*rx_ring->rx_bi) * rx_ring->count; + + rx_ring->rx_bi = kzalloc(sz, GFP_KERNEL); + return rx_ring->rx_bi ? 0 : -ENOMEM; +} + +static void i40e_clear_rx_bi(struct i40e_ring *rx_ring) +{ + memset(rx_ring->rx_bi, 0, sizeof(*rx_ring->rx_bi) * rx_ring->count); +} + /** * i40e_clean_rx_ring - Free Rx buffers * @rx_ring: ring to be cleaned **/ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) { - unsigned long bi_size; u16 i; /* ring already cleared, nothing to do */ @@ -1361,7 +1342,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) /* Free all the Rx ring sk_buffs */ for (i = 0; i < rx_ring->count; i++) { - struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; + struct i40e_rx_buffer *rx_bi = i40e_rx_bi(rx_ring, i); if (!rx_bi->page) continue; @@ -1388,8 +1369,10 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) } skip_free: - bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count; - memset(rx_ring->rx_bi, 0, bi_size); + if (rx_ring->xsk_umem) + i40e_clear_rx_bi_zc(rx_ring); + else + i40e_clear_rx_bi(rx_ring); /* Zero out the descriptor ring */ memset(rx_ring->desc, 0, rx_ring->size); @@ -1430,15 +1413,7 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring) int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) { struct device *dev = rx_ring->dev; - int err = -ENOMEM; - int bi_size; - - /* warn if we are about to overwrite the pointer */ - WARN_ON(rx_ring->rx_bi); - bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count; - rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL); - if (!rx_ring->rx_bi) - goto err; + int err; u64_stats_init(&rx_ring->syncp); @@ -1451,7 +1426,7 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) if (!rx_ring->desc) { dev_info(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n", rx_ring->size); - goto err; + return -ENOMEM; } rx_ring->next_to_alloc = 0; @@ -1463,16 +1438,12 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, rx_ring->queue_index); if (err < 0) - goto err; + return err; } rx_ring->xdp_prog = rx_ring->vsi->xdp_prog; return 0; -err: - kfree(rx_ring->rx_bi); - rx_ring->rx_bi = NULL; - return err; } /** @@ -1592,7 +1563,7 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) return false; rx_desc = I40E_RX_DESC(rx_ring, ntu); - bi = &rx_ring->rx_bi[ntu]; + bi = i40e_rx_bi(rx_ring, ntu); do { if (!i40e_alloc_mapped_page(rx_ring, bi)) @@ -1614,7 +1585,7 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) ntu++; if (unlikely(ntu == rx_ring->count)) { rx_desc = I40E_RX_DESC(rx_ring, 0); - bi = rx_ring->rx_bi; + bi = i40e_rx_bi(rx_ring, 0); ntu = 0; } @@ -1981,7 +1952,7 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, { struct i40e_rx_buffer *rx_buffer; - rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; + rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); prefetchw(rx_buffer->page); /* we are reusing so sync this buffer for CPU use */ @@ -2382,9 +2353,12 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ dma_rmb(); - rx_buffer = i40e_clean_programming_status(rx_ring, rx_desc, - qword); - if (unlikely(rx_buffer)) { + if (i40e_rx_is_programming_status(qword)) { + i40e_clean_programming_status(rx_ring, + rx_desc->raw.qword[0], + qword); + rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); + i40e_inc_ntc(rx_ring); i40e_reuse_rx_page(rx_ring, rx_buffer); cleaned_count++; continue; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 36d37f31a287..5c255977fd58 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -296,17 +296,9 @@ struct i40e_tx_buffer { struct i40e_rx_buffer { dma_addr_t dma; - union { - struct { - struct page *page; - __u32 page_offset; - __u16 pagecnt_bias; - }; - struct { - void *addr; - u64 handle; - }; - }; + struct page *page; + __u32 page_offset; + __u16 pagecnt_bias; }; struct i40e_queue_stats { @@ -358,6 +350,7 @@ struct i40e_ring { union { struct i40e_tx_buffer *tx_bi; struct i40e_rx_buffer *rx_bi; + struct xdp_buff **rx_bi_zc; }; DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS); u16 queue_index; /* Queue number of ring */ @@ -419,7 +412,6 @@ struct i40e_ring { struct i40e_channel *ch; struct xdp_rxq_info xdp_rxq; struct xdp_umem *xsk_umem; - struct zero_copy_allocator zca; /* ZC allocator anchor */ } ____cacheline_internodealigned_in_smp; static inline bool ring_uses_build_skb(struct i40e_ring *ring) @@ -495,6 +487,7 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); +int i40e_alloc_rx_bi(struct i40e_ring *rx_ring); /** * i40e_get_head - Retrieve head from head writeback diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h index 8af0e99c6c0d..667c4dc4b39f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h @@ -4,13 +4,9 @@ #ifndef I40E_TXRX_COMMON_ #define I40E_TXRX_COMMON_ -void i40e_fd_handle_status(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, u8 prog_id); int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring); -struct i40e_rx_buffer *i40e_clean_programming_status( - struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, - u64 qw); +void i40e_clean_programming_status(struct i40e_ring *rx_ring, u64 qword0_raw, + u64 qword1); void i40e_process_skb_fields(struct i40e_ring *rx_ring, union i40e_rx_desc *rx_desc, struct sk_buff *skb); void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring); @@ -84,6 +80,38 @@ static inline void i40e_arm_wb(struct i40e_ring *tx_ring, } } +/** + * i40e_rx_is_programming_status - check for programming status descriptor + * @qword1: qword1 representing status_error_len in CPU ordering + * + * The value of in the descriptor length field indicate if this + * is a programming status descriptor for flow director or FCoE + * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise + * it is a packet descriptor. + **/ +static inline bool i40e_rx_is_programming_status(u64 qword1) +{ + /* The Rx filter programming status and SPH bit occupy the same + * spot in the descriptor. Since we don't support packet split we + * can just reuse the bit as an indication that this is a + * programming status descriptor. + */ + return qword1 & I40E_RXD_QW1_LENGTH_SPH_MASK; +} + +/** + * i40e_inc_ntc: Advance the next_to_clean index + * @rx_ring: Rx ring + **/ +static inline void i40e_inc_ntc(struct i40e_ring *rx_ring) +{ + u32 ntc = rx_ring->next_to_clean + 1; + + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + prefetch(I40E_RX_DESC(rx_ring, ntc)); +} + void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring); void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring); bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi); diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 6ea2867ff60f..63e098f7cb63 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -689,7 +689,7 @@ union i40e_32byte_rx_desc { __le64 rsvd2; } read; struct { - struct { + struct i40e_32b_rx_wb_qw0 { struct { union { __le16 mirroring_status; @@ -727,6 +727,9 @@ union i40e_32byte_rx_desc { } hi_dword; } qword3; } wb; /* writeback */ + struct { + u64 qword[4]; + } raw; }; enum i40e_rx_desc_status_bits { diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 2b9184aead5f..f3953744c505 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -2,68 +2,30 @@ /* Copyright(c) 2018 Intel Corporation. */ #include <linux/bpf_trace.h> -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> #include <net/xdp.h> #include "i40e.h" #include "i40e_txrx_common.h" #include "i40e_xsk.h" -/** - * i40e_xsk_umem_dma_map - DMA maps all UMEM memory for the netdev - * @vsi: Current VSI - * @umem: UMEM to DMA map - * - * Returns 0 on success, <0 on failure - **/ -static int i40e_xsk_umem_dma_map(struct i40e_vsi *vsi, struct xdp_umem *umem) +int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring) { - struct i40e_pf *pf = vsi->back; - struct device *dev; - unsigned int i, j; - dma_addr_t dma; - - dev = &pf->pdev->dev; - for (i = 0; i < umem->npgs; i++) { - dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE, - DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR); - if (dma_mapping_error(dev, dma)) - goto out_unmap; + unsigned long sz = sizeof(*rx_ring->rx_bi_zc) * rx_ring->count; - umem->pages[i].dma = dma; - } - - return 0; - -out_unmap: - for (j = 0; j < i; j++) { - dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, - DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR); - umem->pages[i].dma = 0; - } - - return -1; + rx_ring->rx_bi_zc = kzalloc(sz, GFP_KERNEL); + return rx_ring->rx_bi_zc ? 0 : -ENOMEM; } -/** - * i40e_xsk_umem_dma_unmap - DMA unmaps all UMEM memory for the netdev - * @vsi: Current VSI - * @umem: UMEM to DMA map - **/ -static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem) +void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring) { - struct i40e_pf *pf = vsi->back; - struct device *dev; - unsigned int i; - - dev = &pf->pdev->dev; - - for (i = 0; i < umem->npgs; i++) { - dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, - DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR); + memset(rx_ring->rx_bi_zc, 0, + sizeof(*rx_ring->rx_bi_zc) * rx_ring->count); +} - umem->pages[i].dma = 0; - } +static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx) +{ + return &rx_ring->rx_bi_zc[idx]; } /** @@ -78,7 +40,6 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, u16 qid) { struct net_device *netdev = vsi->netdev; - struct xdp_umem_fq_reuse *reuseq; bool if_running; int err; @@ -92,13 +53,7 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, qid >= netdev->real_num_tx_queues) return -EINVAL; - reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count); - if (!reuseq) - return -ENOMEM; - - xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq)); - - err = i40e_xsk_umem_dma_map(vsi, umem); + err = xsk_buff_dma_map(umem, &vsi->back->pdev->dev, I40E_RX_DMA_ATTR); if (err) return err; @@ -151,7 +106,7 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) } clear_bit(qid, vsi->af_xdp_zc_qps); - i40e_xsk_umem_dma_unmap(vsi, umem); + xsk_buff_dma_unmap(umem, I40E_RX_DMA_ATTR); if (if_running) { err = i40e_queue_pair_enable(vsi, qid); @@ -190,11 +145,9 @@ int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, **/ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) { - struct xdp_umem *umem = rx_ring->xsk_umem; int err, result = I40E_XDP_PASS; struct i40e_ring *xdp_ring; struct bpf_prog *xdp_prog; - u64 offset; u32 act; rcu_read_lock(); @@ -203,9 +156,6 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) */ xdp_prog = READ_ONCE(rx_ring->xdp_prog); act = bpf_prog_run_xdp(xdp_prog, xdp); - offset = xdp->data - xdp->data_hard_start; - - xdp->handle = xsk_umem_adjust_offset(umem, xdp->handle, offset); switch (act) { case XDP_PASS: @@ -232,107 +182,26 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) return result; } -/** - * i40e_alloc_buffer_zc - Allocates an i40e_rx_buffer - * @rx_ring: Rx ring - * @bi: Rx buffer to populate - * - * This function allocates an Rx buffer. The buffer can come from fill - * queue, or via the recycle queue (next_to_alloc). - * - * Returns true for a successful allocation, false otherwise - **/ -static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *bi) -{ - struct xdp_umem *umem = rx_ring->xsk_umem; - void *addr = bi->addr; - u64 handle, hr; - - if (addr) { - rx_ring->rx_stats.page_reuse_count++; - return true; - } - - if (!xsk_umem_peek_addr(umem, &handle)) { - rx_ring->rx_stats.alloc_page_failed++; - return false; - } - - hr = umem->headroom + XDP_PACKET_HEADROOM; - - bi->dma = xdp_umem_get_dma(umem, handle); - bi->dma += hr; - - bi->addr = xdp_umem_get_data(umem, handle); - bi->addr += hr; - - bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom); - - xsk_umem_release_addr(umem); - return true; -} - -/** - * i40e_alloc_buffer_slow_zc - Allocates an i40e_rx_buffer - * @rx_ring: Rx ring - * @bi: Rx buffer to populate - * - * This function allocates an Rx buffer. The buffer can come from fill - * queue, or via the reuse queue. - * - * Returns true for a successful allocation, false otherwise - **/ -static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *bi) -{ - struct xdp_umem *umem = rx_ring->xsk_umem; - u64 handle, hr; - - if (!xsk_umem_peek_addr_rq(umem, &handle)) { - rx_ring->rx_stats.alloc_page_failed++; - return false; - } - - handle &= rx_ring->xsk_umem->chunk_mask; - - hr = umem->headroom + XDP_PACKET_HEADROOM; - - bi->dma = xdp_umem_get_dma(umem, handle); - bi->dma += hr; - - bi->addr = xdp_umem_get_data(umem, handle); - bi->addr += hr; - - bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom); - - xsk_umem_release_addr_rq(umem); - return true; -} - -static __always_inline bool -__i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count, - bool alloc(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *bi)) +bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) { u16 ntu = rx_ring->next_to_use; union i40e_rx_desc *rx_desc; - struct i40e_rx_buffer *bi; + struct xdp_buff **bi, *xdp; + dma_addr_t dma; bool ok = true; rx_desc = I40E_RX_DESC(rx_ring, ntu); - bi = &rx_ring->rx_bi[ntu]; + bi = i40e_rx_bi(rx_ring, ntu); do { - if (!alloc(rx_ring, bi)) { + xdp = xsk_buff_alloc(rx_ring->xsk_umem); + if (!xdp) { ok = false; goto no_buffers; } - - dma_sync_single_range_for_device(rx_ring->dev, bi->dma, 0, - rx_ring->rx_buf_len, - DMA_BIDIRECTIONAL); - - rx_desc->read.pkt_addr = cpu_to_le64(bi->dma); + *bi = xdp; + dma = xsk_buff_xdp_get_dma(xdp); + rx_desc->read.pkt_addr = cpu_to_le64(dma); + rx_desc->read.hdr_addr = 0; rx_desc++; bi++; @@ -340,11 +209,10 @@ __i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count, if (unlikely(ntu == rx_ring->count)) { rx_desc = I40E_RX_DESC(rx_ring, 0); - bi = rx_ring->rx_bi; + bi = i40e_rx_bi(rx_ring, 0); ntu = 0; } - rx_desc->wb.qword1.status_error_len = 0; count--; } while (count); @@ -356,127 +224,8 @@ no_buffers: } /** - * i40e_alloc_rx_buffers_zc - Allocates a number of Rx buffers - * @rx_ring: Rx ring - * @count: The number of buffers to allocate - * - * This function allocates a number of Rx buffers from the reuse queue - * or fill ring and places them on the Rx ring. - * - * Returns true for a successful allocation, false otherwise - **/ -bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) -{ - return __i40e_alloc_rx_buffers_zc(rx_ring, count, - i40e_alloc_buffer_slow_zc); -} - -/** - * i40e_alloc_rx_buffers_fast_zc - Allocates a number of Rx buffers - * @rx_ring: Rx ring - * @count: The number of buffers to allocate - * - * This function allocates a number of Rx buffers from the fill ring - * or the internal recycle mechanism and places them on the Rx ring. - * - * Returns true for a successful allocation, false otherwise - **/ -static bool i40e_alloc_rx_buffers_fast_zc(struct i40e_ring *rx_ring, u16 count) -{ - return __i40e_alloc_rx_buffers_zc(rx_ring, count, - i40e_alloc_buffer_zc); -} - -/** - * i40e_get_rx_buffer_zc - Return the current Rx buffer - * @rx_ring: Rx ring - * @size: The size of the rx buffer (read from descriptor) - * - * This function returns the current, received Rx buffer, and also - * does DMA synchronization. the Rx ring. - * - * Returns the received Rx buffer - **/ -static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring, - const unsigned int size) -{ - struct i40e_rx_buffer *bi; - - bi = &rx_ring->rx_bi[rx_ring->next_to_clean]; - - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - bi->dma, 0, - size, - DMA_BIDIRECTIONAL); - - return bi; -} - -/** - * i40e_reuse_rx_buffer_zc - Recycle an Rx buffer - * @rx_ring: Rx ring - * @old_bi: The Rx buffer to recycle - * - * This function recycles a finished Rx buffer, and places it on the - * recycle queue (next_to_alloc). - **/ -static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *old_bi) -{ - struct i40e_rx_buffer *new_bi = &rx_ring->rx_bi[rx_ring->next_to_alloc]; - u16 nta = rx_ring->next_to_alloc; - - /* update, and store next to alloc */ - nta++; - rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - - /* transfer page from old buffer to new buffer */ - new_bi->dma = old_bi->dma; - new_bi->addr = old_bi->addr; - new_bi->handle = old_bi->handle; - - old_bi->addr = NULL; -} - -/** - * i40e_zca_free - Free callback for MEM_TYPE_ZERO_COPY allocations - * @alloc: Zero-copy allocator - * @handle: Buffer handle - **/ -void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle) -{ - struct i40e_rx_buffer *bi; - struct i40e_ring *rx_ring; - u64 hr, mask; - u16 nta; - - rx_ring = container_of(alloc, struct i40e_ring, zca); - hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM; - mask = rx_ring->xsk_umem->chunk_mask; - - nta = rx_ring->next_to_alloc; - bi = &rx_ring->rx_bi[nta]; - - nta++; - rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - - handle &= mask; - - bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle); - bi->dma += hr; - - bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle); - bi->addr += hr; - - bi->handle = xsk_umem_adjust_offset(rx_ring->xsk_umem, (u64)handle, - rx_ring->xsk_umem->headroom); -} - -/** * i40e_construct_skb_zc - Create skbufff from zero-copy Rx buffer * @rx_ring: Rx ring - * @bi: Rx buffer * @xdp: xdp_buff * * This functions allocates a new skb from a zero-copy Rx buffer. @@ -484,7 +233,6 @@ void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle) * Returns the skb, or NULL on failure. **/ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *bi, struct xdp_buff *xdp) { unsigned int metasize = xdp->data - xdp->data_meta; @@ -503,24 +251,11 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring, if (metasize) skb_metadata_set(skb, metasize); - i40e_reuse_rx_buffer_zc(rx_ring, bi); + xsk_buff_free(xdp); return skb; } /** - * i40e_inc_ntc: Advance the next_to_clean index - * @rx_ring: Rx ring - **/ -static void i40e_inc_ntc(struct i40e_ring *rx_ring) -{ - u32 ntc = rx_ring->next_to_clean + 1; - - ntc = (ntc < rx_ring->count) ? ntc : 0; - rx_ring->next_to_clean = ntc; - prefetch(I40E_RX_DESC(rx_ring, ntc)); -} - -/** * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring * @rx_ring: Rx ring * @budget: NAPI budget @@ -531,25 +266,20 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); - struct xdp_umem *umem = rx_ring->xsk_umem; unsigned int xdp_res, xdp_xmit = 0; bool failure = false; struct sk_buff *skb; - struct xdp_buff xdp; - - xdp.rxq = &rx_ring->xdp_rxq; - xdp.frame_sz = xsk_umem_xdp_frame_sz(umem); while (likely(total_rx_packets < (unsigned int)budget)) { - struct i40e_rx_buffer *bi; union i40e_rx_desc *rx_desc; + struct xdp_buff **bi; unsigned int size; u64 qword; if (cleaned_count >= I40E_RX_BUFFER_WRITE) { failure = failure || - !i40e_alloc_rx_buffers_fast_zc(rx_ring, - cleaned_count); + !i40e_alloc_rx_buffers_zc(rx_ring, + cleaned_count); cleaned_count = 0; } @@ -562,35 +292,36 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) */ dma_rmb(); - bi = i40e_clean_programming_status(rx_ring, rx_desc, - qword); - if (unlikely(bi)) { - i40e_reuse_rx_buffer_zc(rx_ring, bi); + if (i40e_rx_is_programming_status(qword)) { + i40e_clean_programming_status(rx_ring, + rx_desc->raw.qword[0], + qword); + bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); + xsk_buff_free(*bi); + *bi = NULL; cleaned_count++; + i40e_inc_ntc(rx_ring); continue; } + bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> I40E_RXD_QW1_LENGTH_PBUF_SHIFT; if (!size) break; - bi = i40e_get_rx_buffer_zc(rx_ring, size); - xdp.data = bi->addr; - xdp.data_meta = xdp.data; - xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM; - xdp.data_end = xdp.data + size; - xdp.handle = bi->handle; + bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); + (*bi)->data_end = (*bi)->data + size; + xsk_buff_dma_sync_for_cpu(*bi); - xdp_res = i40e_run_xdp_zc(rx_ring, &xdp); + xdp_res = i40e_run_xdp_zc(rx_ring, *bi); if (xdp_res) { - if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) { + if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) xdp_xmit |= xdp_res; - bi->addr = NULL; - } else { - i40e_reuse_rx_buffer_zc(rx_ring, bi); - } + else + xsk_buff_free(*bi); + *bi = NULL; total_rx_bytes += size; total_rx_packets++; @@ -606,7 +337,8 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) * BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that * SBP is *not* set in PRT_SBPVSI (default not set). */ - skb = i40e_construct_skb_zc(rx_ring, bi, &xdp); + skb = i40e_construct_skb_zc(rx_ring, *bi); + *bi = NULL; if (!skb) { rx_ring->rx_stats.alloc_buff_failed++; break; @@ -664,10 +396,9 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc)) break; - dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr); - - dma_sync_single_for_device(xdp_ring->dev, dma, desc.len, - DMA_BIDIRECTIONAL); + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma, + desc.len); tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use]; tx_bi->bytecount = desc.len; @@ -826,13 +557,13 @@ void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring) u16 i; for (i = 0; i < rx_ring->count; i++) { - struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; + struct xdp_buff *rx_bi = *i40e_rx_bi(rx_ring, i); - if (!rx_bi->addr) + if (!rx_bi) continue; - xsk_umem_fq_reuse(rx_ring->xsk_umem, rx_bi->handle); - rx_bi->addr = NULL; + xsk_buff_free(rx_bi); + rx_bi = NULL; } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index 9ed59c14eb55..ea919a7d60ec 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -12,12 +12,13 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair); int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair); int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, u16 qid); -void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle); bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 cleaned_count); int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget); bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring, int napi_budget); int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); +int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring); +void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring); #endif /* _I40E_XSK_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 4c835c144907..f066befadd39 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019, Intel Corporation. */ +#include <net/xdp_sock_drv.h> #include "ice_base.h" #include "ice_dcb_lib.h" @@ -308,24 +309,23 @@ int ice_setup_rx_ctx(struct ice_ring *ring) if (ring->xsk_umem) { xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr - - XDP_PACKET_HEADROOM; + ring->rx_buf_len = + xsk_umem_get_rx_frame_size(ring->xsk_umem); /* For AF_XDP ZC, we disallow packets to span on * multiple buffers, thus letting us skip that * handling in the fast-path. */ chain_len = 1; - ring->zca.free = ice_zca_free; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_ZERO_COPY, - &ring->zca); + MEM_TYPE_XSK_BUFF_POOL, + NULL); if (err) return err; + xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq); - dev_info(ice_pf_to_dev(vsi->back), "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n", + dev_info(ice_pf_to_dev(vsi->back), "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->q_index); } else { - ring->zca.free = NULL; if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) /* coverity[check_return] */ xdp_rxq_info_reg(&ring->xdp_rxq, @@ -426,7 +426,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) writel(0, ring->tail); err = ring->xsk_umem ? - ice_alloc_rx_bufs_slow_zc(ring, ICE_DESC_UNUSED(ring)) : + ice_alloc_rx_bufs_zc(ring, ICE_DESC_UNUSED(ring)) : ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring)); if (err) dev_info(ice_pf_to_dev(vsi->back), "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n", diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 025dd642cf28..5f5a6ce2b7e5 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -158,17 +158,16 @@ struct ice_tx_offload_params { }; struct ice_rx_buf { - struct sk_buff *skb; - dma_addr_t dma; union { struct { + struct sk_buff *skb; + dma_addr_t dma; struct page *page; unsigned int page_offset; u16 pagecnt_bias; }; struct { - void *addr; - u64 handle; + struct xdp_buff *xdp; }; }; }; @@ -292,7 +291,6 @@ struct ice_ring { struct rcu_head rcu; /* to avoid race on free */ struct bpf_prog *xdp_prog; struct xdp_umem *xsk_umem; - struct zero_copy_allocator zca; /* CL3 - 3rd cacheline starts here */ struct xdp_rxq_info xdp_rxq; /* CLX - the below items are only accessed infrequently and should be diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 20ac54e3156d..b6f928c9e9c9 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -2,7 +2,7 @@ /* Copyright (c) 2019, Intel Corporation. */ #include <linux/bpf_trace.h> -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> #include <net/xdp.h> #include "ice.h" #include "ice_base.h" @@ -280,28 +280,6 @@ static int ice_xsk_alloc_umems(struct ice_vsi *vsi) } /** - * ice_xsk_add_umem - add a UMEM region for XDP sockets - * @vsi: VSI to which the UMEM will be added - * @umem: pointer to a requested UMEM region - * @qid: queue ID - * - * Returns 0 on success, negative on error - */ -static int ice_xsk_add_umem(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid) -{ - int err; - - err = ice_xsk_alloc_umems(vsi); - if (err) - return err; - - vsi->xsk_umems[qid] = umem; - vsi->num_xsk_umems_used++; - - return 0; -} - -/** * ice_xsk_remove_umem - Remove an UMEM for a certain ring/qid * @vsi: VSI from which the VSI will be removed * @qid: Ring/qid associated with the UMEM @@ -318,65 +296,6 @@ static void ice_xsk_remove_umem(struct ice_vsi *vsi, u16 qid) } } -/** - * ice_xsk_umem_dma_map - DMA map UMEM region for XDP sockets - * @vsi: VSI to map the UMEM region - * @umem: UMEM to map - * - * Returns 0 on success, negative on error - */ -static int ice_xsk_umem_dma_map(struct ice_vsi *vsi, struct xdp_umem *umem) -{ - struct ice_pf *pf = vsi->back; - struct device *dev; - unsigned int i; - - dev = ice_pf_to_dev(pf); - for (i = 0; i < umem->npgs; i++) { - dma_addr_t dma = dma_map_page_attrs(dev, umem->pgs[i], 0, - PAGE_SIZE, - DMA_BIDIRECTIONAL, - ICE_RX_DMA_ATTR); - if (dma_mapping_error(dev, dma)) { - dev_dbg(dev, "XSK UMEM DMA mapping error on page num %d\n", - i); - goto out_unmap; - } - - umem->pages[i].dma = dma; - } - - return 0; - -out_unmap: - for (; i > 0; i--) { - dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, - DMA_BIDIRECTIONAL, ICE_RX_DMA_ATTR); - umem->pages[i].dma = 0; - } - - return -EFAULT; -} - -/** - * ice_xsk_umem_dma_unmap - DMA unmap UMEM region for XDP sockets - * @vsi: VSI from which the UMEM will be unmapped - * @umem: UMEM to unmap - */ -static void ice_xsk_umem_dma_unmap(struct ice_vsi *vsi, struct xdp_umem *umem) -{ - struct ice_pf *pf = vsi->back; - struct device *dev; - unsigned int i; - - dev = ice_pf_to_dev(pf); - for (i = 0; i < umem->npgs; i++) { - dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, - DMA_BIDIRECTIONAL, ICE_RX_DMA_ATTR); - - umem->pages[i].dma = 0; - } -} /** * ice_xsk_umem_disable - disable a UMEM region @@ -391,7 +310,7 @@ static int ice_xsk_umem_disable(struct ice_vsi *vsi, u16 qid) !vsi->xsk_umems[qid]) return -EINVAL; - ice_xsk_umem_dma_unmap(vsi, vsi->xsk_umems[qid]); + xsk_buff_dma_unmap(vsi->xsk_umems[qid], ICE_RX_DMA_ATTR); ice_xsk_remove_umem(vsi, qid); return 0; @@ -408,7 +327,6 @@ static int ice_xsk_umem_disable(struct ice_vsi *vsi, u16 qid) static int ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid) { - struct xdp_umem_fq_reuse *reuseq; int err; if (vsi->type != ICE_VSI_PF) @@ -419,20 +337,18 @@ ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid) if (qid >= vsi->num_xsk_umems) return -EINVAL; + err = ice_xsk_alloc_umems(vsi); + if (err) + return err; + if (vsi->xsk_umems && vsi->xsk_umems[qid]) return -EBUSY; - reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count); - if (!reuseq) - return -ENOMEM; - - xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq)); - - err = ice_xsk_umem_dma_map(vsi, umem); - if (err) - return err; + vsi->xsk_umems[qid] = umem; + vsi->num_xsk_umems_used++; - err = ice_xsk_add_umem(vsi, umem, qid); + err = xsk_buff_dma_map(vsi->xsk_umems[qid], ice_pf_to_dev(vsi->back), + ICE_RX_DMA_ATTR); if (err) return err; @@ -484,137 +400,22 @@ xsk_umem_if_up: } /** - * ice_zca_free - Callback for MEM_TYPE_ZERO_COPY allocations - * @zca: zero-cpoy allocator - * @handle: Buffer handle - */ -void ice_zca_free(struct zero_copy_allocator *zca, unsigned long handle) -{ - struct ice_rx_buf *rx_buf; - struct ice_ring *rx_ring; - struct xdp_umem *umem; - u64 hr, mask; - u16 nta; - - rx_ring = container_of(zca, struct ice_ring, zca); - umem = rx_ring->xsk_umem; - hr = umem->headroom + XDP_PACKET_HEADROOM; - - mask = umem->chunk_mask; - - nta = rx_ring->next_to_alloc; - rx_buf = &rx_ring->rx_buf[nta]; - - nta++; - rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - - handle &= mask; - - rx_buf->dma = xdp_umem_get_dma(umem, handle); - rx_buf->dma += hr; - - rx_buf->addr = xdp_umem_get_data(umem, handle); - rx_buf->addr += hr; - - rx_buf->handle = (u64)handle + umem->headroom; -} - -/** - * ice_alloc_buf_fast_zc - Retrieve buffer address from XDP umem - * @rx_ring: ring with an xdp_umem bound to it - * @rx_buf: buffer to which xsk page address will be assigned - * - * This function allocates an Rx buffer in the hot path. - * The buffer can come from fill queue or recycle queue. - * - * Returns true if an assignment was successful, false if not. - */ -static __always_inline bool -ice_alloc_buf_fast_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) -{ - struct xdp_umem *umem = rx_ring->xsk_umem; - void *addr = rx_buf->addr; - u64 handle, hr; - - if (addr) { - rx_ring->rx_stats.page_reuse_count++; - return true; - } - - if (!xsk_umem_peek_addr(umem, &handle)) { - rx_ring->rx_stats.alloc_page_failed++; - return false; - } - - hr = umem->headroom + XDP_PACKET_HEADROOM; - - rx_buf->dma = xdp_umem_get_dma(umem, handle); - rx_buf->dma += hr; - - rx_buf->addr = xdp_umem_get_data(umem, handle); - rx_buf->addr += hr; - - rx_buf->handle = handle + umem->headroom; - - xsk_umem_release_addr(umem); - return true; -} - -/** - * ice_alloc_buf_slow_zc - Retrieve buffer address from XDP umem - * @rx_ring: ring with an xdp_umem bound to it - * @rx_buf: buffer to which xsk page address will be assigned - * - * This function allocates an Rx buffer in the slow path. - * The buffer can come from fill queue or recycle queue. - * - * Returns true if an assignment was successful, false if not. - */ -static __always_inline bool -ice_alloc_buf_slow_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) -{ - struct xdp_umem *umem = rx_ring->xsk_umem; - u64 handle, headroom; - - if (!xsk_umem_peek_addr_rq(umem, &handle)) { - rx_ring->rx_stats.alloc_page_failed++; - return false; - } - - handle &= umem->chunk_mask; - headroom = umem->headroom + XDP_PACKET_HEADROOM; - - rx_buf->dma = xdp_umem_get_dma(umem, handle); - rx_buf->dma += headroom; - - rx_buf->addr = xdp_umem_get_data(umem, handle); - rx_buf->addr += headroom; - - rx_buf->handle = handle + umem->headroom; - - xsk_umem_release_addr_rq(umem); - return true; -} - -/** * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers * @rx_ring: Rx ring * @count: The number of buffers to allocate - * @alloc: the function pointer to call for allocation * * This function allocates a number of Rx buffers from the fill ring * or the internal recycle mechanism and places them on the Rx ring. * * Returns false if all allocations were successful, true if any fail. */ -static bool -ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, int count, - bool (*alloc)(struct ice_ring *, struct ice_rx_buf *)) +bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) { union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; struct ice_rx_buf *rx_buf; bool ret = false; + dma_addr_t dma; if (!count) return false; @@ -623,16 +424,14 @@ ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, int count, rx_buf = &rx_ring->rx_buf[ntu]; do { - if (!alloc(rx_ring, rx_buf)) { + rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_umem); + if (!rx_buf->xdp) { ret = true; break; } - dma_sync_single_range_for_device(rx_ring->dev, rx_buf->dma, 0, - rx_ring->rx_buf_len, - DMA_BIDIRECTIONAL); - - rx_desc->read.pkt_addr = cpu_to_le64(rx_buf->dma); + dma = xsk_buff_xdp_get_dma(rx_buf->xdp); + rx_desc->read.pkt_addr = cpu_to_le64(dma); rx_desc->wb.status_error0 = 0; rx_desc++; @@ -653,32 +452,6 @@ ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, int count, } /** - * ice_alloc_rx_bufs_fast_zc - allocate zero copy bufs in the hot path - * @rx_ring: Rx ring - * @count: number of bufs to allocate - * - * Returns false on success, true on failure. - */ -static bool ice_alloc_rx_bufs_fast_zc(struct ice_ring *rx_ring, u16 count) -{ - return ice_alloc_rx_bufs_zc(rx_ring, count, - ice_alloc_buf_fast_zc); -} - -/** - * ice_alloc_rx_bufs_slow_zc - allocate zero copy bufs in the slow path - * @rx_ring: Rx ring - * @count: number of bufs to allocate - * - * Returns false on success, true on failure. - */ -bool ice_alloc_rx_bufs_slow_zc(struct ice_ring *rx_ring, u16 count) -{ - return ice_alloc_rx_bufs_zc(rx_ring, count, - ice_alloc_buf_slow_zc); -} - -/** * ice_bump_ntc - Bump the next_to_clean counter of an Rx ring * @rx_ring: Rx ring */ @@ -692,76 +465,21 @@ static void ice_bump_ntc(struct ice_ring *rx_ring) } /** - * ice_get_rx_buf_zc - Fetch the current Rx buffer - * @rx_ring: Rx ring - * @size: size of a buffer - * - * This function returns the current, received Rx buffer and does - * DMA synchronization. - * - * Returns a pointer to the received Rx buffer. - */ -static struct ice_rx_buf *ice_get_rx_buf_zc(struct ice_ring *rx_ring, int size) -{ - struct ice_rx_buf *rx_buf; - - rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean]; - - dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma, 0, - size, DMA_BIDIRECTIONAL); - - return rx_buf; -} - -/** - * ice_reuse_rx_buf_zc - reuse an Rx buffer - * @rx_ring: Rx ring - * @old_buf: The buffer to recycle - * - * This function recycles a finished Rx buffer, and places it on the recycle - * queue (next_to_alloc). - */ -static void -ice_reuse_rx_buf_zc(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf) -{ - unsigned long mask = (unsigned long)rx_ring->xsk_umem->chunk_mask; - u64 hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM; - u16 nta = rx_ring->next_to_alloc; - struct ice_rx_buf *new_buf; - - new_buf = &rx_ring->rx_buf[nta++]; - rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - - new_buf->dma = old_buf->dma & mask; - new_buf->dma += hr; - - new_buf->addr = (void *)((unsigned long)old_buf->addr & mask); - new_buf->addr += hr; - - new_buf->handle = old_buf->handle & mask; - new_buf->handle += rx_ring->xsk_umem->headroom; - - old_buf->addr = NULL; -} - -/** * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer * @rx_ring: Rx ring * @rx_buf: zero-copy Rx buffer - * @xdp: XDP buffer * * This function allocates a new skb from a zero-copy Rx buffer. * * Returns the skb on success, NULL on failure. */ static struct sk_buff * -ice_construct_skb_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, - struct xdp_buff *xdp) +ice_construct_skb_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) { - unsigned int metasize = xdp->data - xdp->data_meta; - unsigned int datasize = xdp->data_end - xdp->data; - unsigned int datasize_hard = xdp->data_end - - xdp->data_hard_start; + unsigned int metasize = rx_buf->xdp->data - rx_buf->xdp->data_meta; + unsigned int datasize = rx_buf->xdp->data_end - rx_buf->xdp->data; + unsigned int datasize_hard = rx_buf->xdp->data_end - + rx_buf->xdp->data_hard_start; struct sk_buff *skb; skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard, @@ -769,13 +487,13 @@ ice_construct_skb_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, if (unlikely(!skb)) return NULL; - skb_reserve(skb, xdp->data - xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), xdp->data, datasize); + skb_reserve(skb, rx_buf->xdp->data - rx_buf->xdp->data_hard_start); + memcpy(__skb_put(skb, datasize), rx_buf->xdp->data, datasize); if (metasize) skb_metadata_set(skb, metasize); - ice_reuse_rx_buf_zc(rx_ring, rx_buf); - + xsk_buff_free(rx_buf->xdp); + rx_buf->xdp = NULL; return skb; } @@ -802,7 +520,6 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) } act = bpf_prog_run_xdp(xdp_prog, xdp); - xdp->handle += xdp->data - xdp->data_hard_start; switch (act) { case XDP_PASS: break; @@ -840,13 +557,8 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; u16 cleaned_count = ICE_DESC_UNUSED(rx_ring); - struct xdp_umem *umem = rx_ring->xsk_umem; unsigned int xdp_xmit = 0; bool failure = false; - struct xdp_buff xdp; - - xdp.rxq = &rx_ring->xdp_rxq; - xdp.frame_sz = xsk_umem_xdp_frame_sz(umem); while (likely(total_rx_packets < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; @@ -858,8 +570,8 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) u8 rx_ptype; if (cleaned_count >= ICE_RX_BUF_WRITE) { - failure |= ice_alloc_rx_bufs_fast_zc(rx_ring, - cleaned_count); + failure |= ice_alloc_rx_bufs_zc(rx_ring, + cleaned_count); cleaned_count = 0; } @@ -880,25 +592,19 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) if (!size) break; - rx_buf = ice_get_rx_buf_zc(rx_ring, size); - if (!rx_buf->addr) - break; - xdp.data = rx_buf->addr; - xdp.data_meta = xdp.data; - xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM; - xdp.data_end = xdp.data + size; - xdp.handle = rx_buf->handle; + rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean]; + rx_buf->xdp->data_end = rx_buf->xdp->data + size; + xsk_buff_dma_sync_for_cpu(rx_buf->xdp); - xdp_res = ice_run_xdp_zc(rx_ring, &xdp); + xdp_res = ice_run_xdp_zc(rx_ring, rx_buf->xdp); if (xdp_res) { - if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) { + if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) xdp_xmit |= xdp_res; - rx_buf->addr = NULL; - } else { - ice_reuse_rx_buf_zc(rx_ring, rx_buf); - } + else + xsk_buff_free(rx_buf->xdp); + rx_buf->xdp = NULL; total_rx_bytes += size; total_rx_packets++; cleaned_count++; @@ -908,7 +614,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) } /* XDP_PASS path */ - skb = ice_construct_skb_zc(rx_ring, rx_buf, &xdp); + skb = ice_construct_skb_zc(rx_ring, rx_buf); if (!skb) { rx_ring->rx_stats.alloc_buf_failed++; break; @@ -979,10 +685,9 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc)) break; - dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr); - - dma_sync_single_for_device(xdp_ring->dev, dma, desc.len, - DMA_BIDIRECTIONAL); + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma, + desc.len); tx_buf->bytecount = desc.len; @@ -1165,11 +870,10 @@ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) for (i = 0; i < rx_ring->count; i++) { struct ice_rx_buf *rx_buf = &rx_ring->rx_buf[i]; - if (!rx_buf->addr) + if (!rx_buf->xdp) continue; - xsk_umem_fq_reuse(rx_ring->xsk_umem, rx_buf->handle); - rx_buf->addr = NULL; + rx_buf->xdp = NULL; } } diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 8a4ba7c6d549..fc1a06b4df36 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -10,11 +10,10 @@ struct ice_vsi; #ifdef CONFIG_XDP_SOCKETS int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid); -void ice_zca_free(struct zero_copy_allocator *zca, unsigned long handle); int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget); bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget); int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags); -bool ice_alloc_rx_bufs_slow_zc(struct ice_ring *rx_ring, u16 count); +bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count); bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi); void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring); void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring); @@ -27,12 +26,6 @@ ice_xsk_umem_setup(struct ice_vsi __always_unused *vsi, return -EOPNOTSUPP; } -static inline void -ice_zca_free(struct zero_copy_allocator __always_unused *zca, - unsigned long __always_unused handle) -{ -} - static inline int ice_clean_rx_irq_zc(struct ice_ring __always_unused *rx_ring, int __always_unused budget) @@ -48,8 +41,8 @@ ice_clean_tx_irq_zc(struct ice_ring __always_unused *xdp_ring, } static inline bool -ice_alloc_rx_bufs_slow_zc(struct ice_ring __always_unused *rx_ring, - u16 __always_unused count) +ice_alloc_rx_bufs_zc(struct ice_ring __always_unused *rx_ring, + u16 __always_unused count) { return false; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 2833e4f041ce..5ddfc83a1e46 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -224,17 +224,17 @@ struct ixgbe_tx_buffer { }; struct ixgbe_rx_buffer { - struct sk_buff *skb; - dma_addr_t dma; union { struct { + struct sk_buff *skb; + dma_addr_t dma; struct page *page; __u32 page_offset; __u16 pagecnt_bias; }; struct { - void *addr; - u64 handle; + bool discard; + struct xdp_buff *xdp; }; }; }; @@ -351,7 +351,6 @@ struct ixgbe_ring { }; struct xdp_rxq_info xdp_rxq; struct xdp_umem *xsk_umem; - struct zero_copy_allocator zca; /* ZC allocator anchor */ u16 ring_idx; /* {rx,tx,xdp}_ring back reference idx */ u16 rx_buf_len; } ____cacheline_internodealigned_in_smp; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index eab5934b04f5..45fc7ce1a543 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -35,7 +35,7 @@ #include <net/tc_act/tc_mirred.h> #include <net/vxlan.h> #include <net/mpls.h> -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> #include <net/xfrm.h> #include "ixgbe.h" @@ -3745,8 +3745,7 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, /* configure the packet buffer length */ if (rx_ring->xsk_umem) { - u32 xsk_buf_len = rx_ring->xsk_umem->chunk_size_nohr - - XDP_PACKET_HEADROOM; + u32 xsk_buf_len = xsk_umem_get_rx_frame_size(rx_ring->xsk_umem); /* If the MAC support setting RXDCTL.RLPML, the * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and @@ -4093,11 +4092,10 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); ring->xsk_umem = ixgbe_xsk_umem(adapter, ring); if (ring->xsk_umem) { - ring->zca.free = ixgbe_zca_free; WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_ZERO_COPY, - &ring->zca)); - + MEM_TYPE_XSK_BUFF_POOL, + NULL)); + xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq); } else { WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL)); @@ -4153,8 +4151,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, } if (ring->xsk_umem && hw->mac.type != ixgbe_mac_82599EB) { - u32 xsk_buf_len = ring->xsk_umem->chunk_size_nohr - - XDP_PACKET_HEADROOM; + u32 xsk_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem); rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | IXGBE_RXDCTL_RLPML_EN); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h index 6d01700b46bc..7887ae4aaf4f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h @@ -35,7 +35,7 @@ int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle); -void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count); +bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count); int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, struct ixgbe_ring *rx_ring, const int budget); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index a656ee9a1fae..86add9fbd36c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -2,7 +2,7 @@ /* Copyright(c) 2018 Intel Corporation. */ #include <linux/bpf_trace.h> -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> #include <net/xdp.h> #include "ixgbe.h" @@ -20,54 +20,11 @@ struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, return xdp_get_umem_from_qid(adapter->netdev, qid); } -static int ixgbe_xsk_umem_dma_map(struct ixgbe_adapter *adapter, - struct xdp_umem *umem) -{ - struct device *dev = &adapter->pdev->dev; - unsigned int i, j; - dma_addr_t dma; - - for (i = 0; i < umem->npgs; i++) { - dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE, - DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR); - if (dma_mapping_error(dev, dma)) - goto out_unmap; - - umem->pages[i].dma = dma; - } - - return 0; - -out_unmap: - for (j = 0; j < i; j++) { - dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, - DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR); - umem->pages[i].dma = 0; - } - - return -1; -} - -static void ixgbe_xsk_umem_dma_unmap(struct ixgbe_adapter *adapter, - struct xdp_umem *umem) -{ - struct device *dev = &adapter->pdev->dev; - unsigned int i; - - for (i = 0; i < umem->npgs; i++) { - dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, - DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR); - - umem->pages[i].dma = 0; - } -} - static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, struct xdp_umem *umem, u16 qid) { struct net_device *netdev = adapter->netdev; - struct xdp_umem_fq_reuse *reuseq; bool if_running; int err; @@ -78,13 +35,7 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, qid >= netdev->real_num_tx_queues) return -EINVAL; - reuseq = xsk_reuseq_prepare(adapter->rx_ring[0]->count); - if (!reuseq) - return -ENOMEM; - - xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq)); - - err = ixgbe_xsk_umem_dma_map(adapter, umem); + err = xsk_buff_dma_map(umem, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR); if (err) return err; @@ -124,7 +75,7 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) ixgbe_txrx_ring_disable(adapter, qid); clear_bit(qid, adapter->af_xdp_zc_qps); - ixgbe_xsk_umem_dma_unmap(adapter, umem); + xsk_buff_dma_unmap(umem, IXGBE_RX_DMA_ATTR); if (if_running) ixgbe_txrx_ring_enable(adapter, qid); @@ -143,19 +94,14 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, struct ixgbe_ring *rx_ring, struct xdp_buff *xdp) { - struct xdp_umem *umem = rx_ring->xsk_umem; int err, result = IXGBE_XDP_PASS; struct bpf_prog *xdp_prog; struct xdp_frame *xdpf; - u64 offset; u32 act; rcu_read_lock(); xdp_prog = READ_ONCE(rx_ring->xdp_prog); act = bpf_prog_run_xdp(xdp_prog, xdp); - offset = xdp->data - xdp->data_hard_start; - - xdp->handle = xsk_umem_adjust_offset(umem, xdp->handle, offset); switch (act) { case XDP_PASS: @@ -186,140 +132,16 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, return result; } -static struct -ixgbe_rx_buffer *ixgbe_get_rx_buffer_zc(struct ixgbe_ring *rx_ring, - unsigned int size) -{ - struct ixgbe_rx_buffer *bi; - - bi = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - bi->dma, 0, - size, - DMA_BIDIRECTIONAL); - - return bi; -} - -static void ixgbe_reuse_rx_buffer_zc(struct ixgbe_ring *rx_ring, - struct ixgbe_rx_buffer *obi) -{ - u16 nta = rx_ring->next_to_alloc; - struct ixgbe_rx_buffer *nbi; - - nbi = &rx_ring->rx_buffer_info[rx_ring->next_to_alloc]; - /* update, and store next to alloc */ - nta++; - rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - - /* transfer page from old buffer to new buffer */ - nbi->dma = obi->dma; - nbi->addr = obi->addr; - nbi->handle = obi->handle; - - obi->addr = NULL; - obi->skb = NULL; -} - -void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle) -{ - struct ixgbe_rx_buffer *bi; - struct ixgbe_ring *rx_ring; - u64 hr, mask; - u16 nta; - - rx_ring = container_of(alloc, struct ixgbe_ring, zca); - hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM; - mask = rx_ring->xsk_umem->chunk_mask; - - nta = rx_ring->next_to_alloc; - bi = rx_ring->rx_buffer_info; - - nta++; - rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - - handle &= mask; - - bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle); - bi->dma += hr; - - bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle); - bi->addr += hr; - - bi->handle = xsk_umem_adjust_offset(rx_ring->xsk_umem, (u64)handle, - rx_ring->xsk_umem->headroom); -} - -static bool ixgbe_alloc_buffer_zc(struct ixgbe_ring *rx_ring, - struct ixgbe_rx_buffer *bi) -{ - struct xdp_umem *umem = rx_ring->xsk_umem; - void *addr = bi->addr; - u64 handle, hr; - - if (addr) - return true; - - if (!xsk_umem_peek_addr(umem, &handle)) { - rx_ring->rx_stats.alloc_rx_page_failed++; - return false; - } - - hr = umem->headroom + XDP_PACKET_HEADROOM; - - bi->dma = xdp_umem_get_dma(umem, handle); - bi->dma += hr; - - bi->addr = xdp_umem_get_data(umem, handle); - bi->addr += hr; - - bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom); - - xsk_umem_release_addr(umem); - return true; -} - -static bool ixgbe_alloc_buffer_slow_zc(struct ixgbe_ring *rx_ring, - struct ixgbe_rx_buffer *bi) -{ - struct xdp_umem *umem = rx_ring->xsk_umem; - u64 handle, hr; - - if (!xsk_umem_peek_addr_rq(umem, &handle)) { - rx_ring->rx_stats.alloc_rx_page_failed++; - return false; - } - - handle &= rx_ring->xsk_umem->chunk_mask; - - hr = umem->headroom + XDP_PACKET_HEADROOM; - - bi->dma = xdp_umem_get_dma(umem, handle); - bi->dma += hr; - - bi->addr = xdp_umem_get_data(umem, handle); - bi->addr += hr; - - bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom); - - xsk_umem_release_addr_rq(umem); - return true; -} - -static __always_inline bool -__ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count, - bool alloc(struct ixgbe_ring *rx_ring, - struct ixgbe_rx_buffer *bi)) +bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count) { union ixgbe_adv_rx_desc *rx_desc; struct ixgbe_rx_buffer *bi; u16 i = rx_ring->next_to_use; + dma_addr_t dma; bool ok = true; /* nothing to do */ - if (!cleaned_count) + if (!count) return true; rx_desc = IXGBE_RX_DESC(rx_ring, i); @@ -327,21 +149,18 @@ __ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count, i -= rx_ring->count; do { - if (!alloc(rx_ring, bi)) { + bi->xdp = xsk_buff_alloc(rx_ring->xsk_umem); + if (!bi->xdp) { ok = false; break; } - /* sync the buffer for use by the device */ - dma_sync_single_range_for_device(rx_ring->dev, bi->dma, - bi->page_offset, - rx_ring->rx_buf_len, - DMA_BIDIRECTIONAL); + dma = xsk_buff_xdp_get_dma(bi->xdp); /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ - rx_desc->read.pkt_addr = cpu_to_le64(bi->dma); + rx_desc->read.pkt_addr = cpu_to_le64(dma); rx_desc++; bi++; @@ -355,17 +174,14 @@ __ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count, /* clear the length for the next_to_use descriptor */ rx_desc->wb.upper.length = 0; - cleaned_count--; - } while (cleaned_count); + count--; + } while (count); i += rx_ring->count; if (rx_ring->next_to_use != i) { rx_ring->next_to_use = i; - /* update next to alloc since we have filled the ring */ - rx_ring->next_to_alloc = i; - /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only * applicable for weak-ordered memory model archs, @@ -378,40 +194,27 @@ __ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count, return ok; } -void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count) -{ - __ixgbe_alloc_rx_buffers_zc(rx_ring, count, - ixgbe_alloc_buffer_slow_zc); -} - -static bool ixgbe_alloc_rx_buffers_fast_zc(struct ixgbe_ring *rx_ring, - u16 count) -{ - return __ixgbe_alloc_rx_buffers_zc(rx_ring, count, - ixgbe_alloc_buffer_zc); -} - static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring, - struct ixgbe_rx_buffer *bi, - struct xdp_buff *xdp) + struct ixgbe_rx_buffer *bi) { - unsigned int metasize = xdp->data - xdp->data_meta; - unsigned int datasize = xdp->data_end - xdp->data; + unsigned int metasize = bi->xdp->data - bi->xdp->data_meta; + unsigned int datasize = bi->xdp->data_end - bi->xdp->data; struct sk_buff *skb; /* allocate a skb to store the frags */ skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - xdp->data_end - xdp->data_hard_start, + bi->xdp->data_end - bi->xdp->data_hard_start, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; - skb_reserve(skb, xdp->data - xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), xdp->data, datasize); + skb_reserve(skb, bi->xdp->data - bi->xdp->data_hard_start); + memcpy(__skb_put(skb, datasize), bi->xdp->data, datasize); if (metasize) skb_metadata_set(skb, metasize); - ixgbe_reuse_rx_buffer_zc(rx_ring, bi); + xsk_buff_free(bi->xdp); + bi->xdp = NULL; return skb; } @@ -431,14 +234,9 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, unsigned int total_rx_bytes = 0, total_rx_packets = 0; struct ixgbe_adapter *adapter = q_vector->adapter; u16 cleaned_count = ixgbe_desc_unused(rx_ring); - struct xdp_umem *umem = rx_ring->xsk_umem; unsigned int xdp_res, xdp_xmit = 0; bool failure = false; struct sk_buff *skb; - struct xdp_buff xdp; - - xdp.rxq = &rx_ring->xdp_rxq; - xdp.frame_sz = xsk_umem_xdp_frame_sz(umem); while (likely(total_rx_packets < budget)) { union ixgbe_adv_rx_desc *rx_desc; @@ -448,8 +246,8 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) { failure = failure || - !ixgbe_alloc_rx_buffers_fast_zc(rx_ring, - cleaned_count); + !ixgbe_alloc_rx_buffers_zc(rx_ring, + cleaned_count); cleaned_count = 0; } @@ -464,42 +262,40 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, */ dma_rmb(); - bi = ixgbe_get_rx_buffer_zc(rx_ring, size); + bi = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; if (unlikely(!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))) { struct ixgbe_rx_buffer *next_bi; - ixgbe_reuse_rx_buffer_zc(rx_ring, bi); + xsk_buff_free(bi->xdp); + bi->xdp = NULL; ixgbe_inc_ntc(rx_ring); next_bi = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - next_bi->skb = ERR_PTR(-EINVAL); + next_bi->discard = true; continue; } - if (unlikely(bi->skb)) { - ixgbe_reuse_rx_buffer_zc(rx_ring, bi); + if (unlikely(bi->discard)) { + xsk_buff_free(bi->xdp); + bi->xdp = NULL; + bi->discard = false; ixgbe_inc_ntc(rx_ring); continue; } - xdp.data = bi->addr; - xdp.data_meta = xdp.data; - xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM; - xdp.data_end = xdp.data + size; - xdp.handle = bi->handle; - - xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, &xdp); + bi->xdp->data_end = bi->xdp->data + size; + xsk_buff_dma_sync_for_cpu(bi->xdp); + xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, bi->xdp); if (xdp_res) { - if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) { + if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) xdp_xmit |= xdp_res; - bi->addr = NULL; - bi->skb = NULL; - } else { - ixgbe_reuse_rx_buffer_zc(rx_ring, bi); - } + else + xsk_buff_free(bi->xdp); + + bi->xdp = NULL; total_rx_packets++; total_rx_bytes += size; @@ -509,7 +305,7 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, } /* XDP_PASS path */ - skb = ixgbe_construct_skb_zc(rx_ring, bi, &xdp); + skb = ixgbe_construct_skb_zc(rx_ring, bi); if (!skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; break; @@ -561,17 +357,17 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring) { - u16 i = rx_ring->next_to_clean; - struct ixgbe_rx_buffer *bi = &rx_ring->rx_buffer_info[i]; + struct ixgbe_rx_buffer *bi; + u16 i; - while (i != rx_ring->next_to_alloc) { - xsk_umem_fq_reuse(rx_ring->xsk_umem, bi->handle); - i++; - bi++; - if (i == rx_ring->count) { - i = 0; - bi = rx_ring->rx_buffer_info; - } + for (i = 0; i < rx_ring->count; i++) { + bi = &rx_ring->rx_buffer_info[i]; + + if (!bi->xdp) + continue; + + xsk_buff_free(bi->xdp); + bi->xdp = NULL; } } @@ -594,10 +390,9 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc)) break; - dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr); - - dma_sync_single_for_device(xdp_ring->dev, dma, desc.len, - DMA_BIDIRECTIONAL); + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma, + desc.len); tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use]; tx_bi->bytecount = desc.len; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 81fd53569463..4906aee6798d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -365,10 +365,7 @@ struct mlx5e_dma_info { dma_addr_t addr; union { struct page *page; - struct { - u64 handle; - void *data; - } xsk; + struct xdp_buff *xsk; }; }; @@ -581,7 +578,6 @@ struct mlx5e_rq { } mpwqe; }; struct { - u16 umem_headroom; u16 headroom; u32 frame0_sz; u8 map_dir; /* dma map direction */ @@ -614,7 +610,6 @@ struct mlx5e_rq { struct page_pool *page_pool; /* AF_XDP zero-copy */ - struct zero_copy_allocator zca; struct xdp_umem *umem; struct work_struct recover_work; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index eb2e1f2138e4..38e4f19d69f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -12,15 +12,16 @@ static inline bool mlx5e_rx_is_xdp(struct mlx5e_params *params, u16 mlx5e_get_linear_rq_headroom(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) { - u16 headroom = NET_IP_ALIGN; + u16 headroom; - if (mlx5e_rx_is_xdp(params, xsk)) { + if (xsk) + return xsk->headroom; + + headroom = NET_IP_ALIGN; + if (mlx5e_rx_is_xdp(params, xsk)) headroom += XDP_PACKET_HEADROOM; - if (xsk) - headroom += xsk->headroom; - } else { + else headroom += MLX5_RX_HEADROOM; - } return headroom; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 42202d19245c..3bea1d4be53b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -31,7 +31,7 @@ */ #include <linux/bpf_trace.h> -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> #include "en/xdp.h" #include "en/params.h" @@ -71,7 +71,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq, xdptxd.data = xdpf->data; xdptxd.len = xdpf->len; - if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) { + if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) { /* The xdp_buff was in the UMEM and was copied into a newly * allocated page. The UMEM page was returned via the ZCA, and * this new page has to be mapped at this point and has to be @@ -119,50 +119,33 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq, /* returns true if packet was consumed by xdp */ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, - void *va, u16 *rx_headroom, u32 *len, bool xsk) + u32 *len, struct xdp_buff *xdp) { struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); - struct xdp_umem *umem = rq->umem; - struct xdp_buff xdp; u32 act; int err; if (!prog) return false; - xdp.data = va + *rx_headroom; - xdp_set_data_meta_invalid(&xdp); - xdp.data_end = xdp.data + *len; - xdp.data_hard_start = va; - if (xsk) - xdp.handle = di->xsk.handle; - xdp.rxq = &rq->xdp_rxq; - xdp.frame_sz = rq->buff.frame0_sz; - - act = bpf_prog_run_xdp(prog, &xdp); - if (xsk) { - u64 off = xdp.data - xdp.data_hard_start; - - xdp.handle = xsk_umem_adjust_offset(umem, xdp.handle, off); - } + act = bpf_prog_run_xdp(prog, xdp); switch (act) { case XDP_PASS: - *rx_headroom = xdp.data - xdp.data_hard_start; - *len = xdp.data_end - xdp.data; + *len = xdp->data_end - xdp->data; return false; case XDP_TX: - if (unlikely(!mlx5e_xmit_xdp_buff(rq->xdpsq, rq, di, &xdp))) + if (unlikely(!mlx5e_xmit_xdp_buff(rq->xdpsq, rq, di, xdp))) goto xdp_abort; __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */ return true; case XDP_REDIRECT: /* When XDP enabled then page-refcnt==1 here */ - err = xdp_do_redirect(rq->netdev, &xdp, prog); + err = xdp_do_redirect(rq->netdev, xdp, prog); if (unlikely(err)) goto xdp_abort; __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); __set_bit(MLX5E_RQ_FLAG_XDP_REDIRECT, rq->flags); - if (!xsk) + if (xdp->rxq->mem.type != MEM_TYPE_XSK_BUFF_POOL) mlx5e_page_dma_unmap(rq, di); rq->stats->xdp_redirect++; return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index be64eb68f4e5..ca48c293151b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -61,7 +61,7 @@ struct mlx5e_xsk_param; int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, - void *va, u16 *rx_headroom, u32 *len, bool xsk); + u32 *len, struct xdp_buff *xdp); void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq); bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq); void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq); 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 62fc8a128a8d..a33a1f762c70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -3,71 +3,10 @@ #include "rx.h" #include "en/xdp.h" -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> /* RX data path */ -bool mlx5e_xsk_pages_enough_umem(struct mlx5e_rq *rq, int count) -{ - /* Check in advance that we have enough frames, instead of allocating - * one-by-one, failing and moving frames to the Reuse Ring. - */ - return xsk_umem_has_addrs_rq(rq->umem, count); -} - -int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq, - struct mlx5e_dma_info *dma_info) -{ - struct xdp_umem *umem = rq->umem; - u64 handle; - - if (!xsk_umem_peek_addr_rq(umem, &handle)) - return -ENOMEM; - - dma_info->xsk.handle = xsk_umem_adjust_offset(umem, handle, - rq->buff.umem_headroom); - dma_info->xsk.data = xdp_umem_get_data(umem, dma_info->xsk.handle); - - /* No need to add headroom to the DMA address. In striding RQ case, we - * just provide pages for UMR, and headroom is counted at the setup - * stage when creating a WQE. In non-striding RQ case, headroom is - * accounted in mlx5e_alloc_rx_wqe. - */ - dma_info->addr = xdp_umem_get_dma(umem, handle); - - xsk_umem_release_addr_rq(umem); - - dma_sync_single_for_device(rq->pdev, dma_info->addr, PAGE_SIZE, - DMA_BIDIRECTIONAL); - - return 0; -} - -static inline void mlx5e_xsk_recycle_frame(struct mlx5e_rq *rq, u64 handle) -{ - xsk_umem_fq_reuse(rq->umem, handle & rq->umem->chunk_mask); -} - -/* XSKRQ uses pages from UMEM, they must not be released. They are returned to - * the userspace if possible, and if not, this function is called to reuse them - * in the driver. - */ -void mlx5e_xsk_page_release(struct mlx5e_rq *rq, - struct mlx5e_dma_info *dma_info) -{ - mlx5e_xsk_recycle_frame(rq, dma_info->xsk.handle); -} - -/* Return a frame back to the hardware to fill in again. It is used by XDP when - * the XDP program returns XDP_TX or XDP_REDIRECT not to an XSKMAP. - */ -void mlx5e_xsk_zca_free(struct zero_copy_allocator *zca, unsigned long handle) -{ - struct mlx5e_rq *rq = container_of(zca, struct mlx5e_rq, zca); - - mlx5e_xsk_recycle_frame(rq, handle); -} - static struct sk_buff *mlx5e_xsk_construct_skb(struct mlx5e_rq *rq, void *data, u32 cqe_bcnt) { @@ -90,11 +29,8 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, u32 head_offset, u32 page_idx) { - struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx]; - u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom; + struct xdp_buff *xdp = wi->umr.dma_info[page_idx].xsk; u32 cqe_bcnt32 = cqe_bcnt; - void *va, *data; - u32 frag_size; bool consumed; /* Check packet size. Note LRO doesn't use linear SKB */ @@ -103,22 +39,20 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, return NULL; } - /* head_offset is not used in this function, because di->xsk.data and - * di->addr point directly to the necessary place. Furthermore, in the - * current implementation, UMR pages are mapped to XSK frames, so + /* head_offset is not used in this function, because xdp->data and the + * DMA address point directly to the necessary place. Furthermore, in + * the current implementation, UMR pages are mapped to XSK frames, so * head_offset should always be 0. */ WARN_ON_ONCE(head_offset); - va = di->xsk.data; - data = va + rx_headroom; - frag_size = rq->buff.headroom + cqe_bcnt32; - - dma_sync_single_for_cpu(rq->pdev, di->addr, frag_size, DMA_BIDIRECTIONAL); - prefetch(data); + xdp->data_end = xdp->data + cqe_bcnt32; + xdp_set_data_meta_invalid(xdp); + xsk_buff_dma_sync_for_cpu(xdp); + prefetch(xdp->data); rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32, true); + consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp); rcu_read_unlock(); /* Possible flows: @@ -145,7 +79,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, /* XDP_PASS: copy the data from the UMEM to a new SKB and reuse the * frame. On SKB allocation failure, NULL is returned. */ - return mlx5e_xsk_construct_skb(rq, data, cqe_bcnt32); + return mlx5e_xsk_construct_skb(rq, xdp->data, cqe_bcnt32); } struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, @@ -153,25 +87,20 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt) { - struct mlx5e_dma_info *di = wi->di; - u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom; - void *va, *data; + struct xdp_buff *xdp = wi->di->xsk; bool consumed; - u32 frag_size; - /* wi->offset is not used in this function, because di->xsk.data and - * di->addr point directly to the necessary place. Furthermore, in the - * current implementation, one page = one packet = one frame, so + /* wi->offset is not used in this function, because xdp->data and the + * DMA address point directly to the necessary place. Furthermore, the + * XSK allocator allocates frames per packet, instead of pages, so * wi->offset should always be 0. */ WARN_ON_ONCE(wi->offset); - va = di->xsk.data; - data = va + rx_headroom; - frag_size = rq->buff.headroom + cqe_bcnt; - - dma_sync_single_for_cpu(rq->pdev, di->addr, frag_size, DMA_BIDIRECTIONAL); - prefetch(data); + xdp->data_end = xdp->data + cqe_bcnt; + xdp_set_data_meta_invalid(xdp); + xsk_buff_dma_sync_for_cpu(xdp); + prefetch(xdp->data); if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) { rq->stats->wqe_err++; @@ -179,7 +108,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, } rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, true); + consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp); rcu_read_unlock(); if (likely(consumed)) @@ -189,5 +118,5 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, * will be handled by mlx5e_put_rx_frag. * On SKB allocation failure, NULL is returned. */ - return mlx5e_xsk_construct_skb(rq, data, cqe_bcnt); + return mlx5e_xsk_construct_skb(rq, xdp->data, cqe_bcnt); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h index cab0e93497ae..d147b2f13b54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h @@ -5,16 +5,10 @@ #define __MLX5_EN_XSK_RX_H__ #include "en.h" -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> /* RX data path */ -bool mlx5e_xsk_pages_enough_umem(struct mlx5e_rq *rq, int count); -int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq, - struct mlx5e_dma_info *dma_info); -void mlx5e_xsk_page_release(struct mlx5e_rq *rq, - struct mlx5e_dma_info *dma_info); -void mlx5e_xsk_zca_free(struct zero_copy_allocator *zca, unsigned long handle); struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, u16 cqe_bcnt, @@ -25,6 +19,23 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt); +static inline int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info) +{ + dma_info->xsk = xsk_buff_alloc(rq->umem); + if (!dma_info->xsk) + return -ENOMEM; + + /* Store the DMA address without headroom. In striding RQ case, we just + * provide pages for UMR, and headroom is counted at the setup stage + * when creating a WQE. In non-striding RQ case, headroom is accounted + * in mlx5e_alloc_rx_wqe. + */ + dma_info->addr = xsk_buff_xdp_get_frame_dma(dma_info->xsk); + + return 0; +} + static inline bool mlx5e_xsk_update_rx_wakeup(struct mlx5e_rq *rq, bool alloc_err) { if (!xsk_umem_uses_need_wakeup(rq->umem)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index 3bcdb5b2fc20..83dce9cdb8c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -5,7 +5,7 @@ #include "umem.h" #include "en/xdp.h" #include "en/params.h" -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { @@ -92,12 +92,11 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) break; } - xdptxd.dma_addr = xdp_umem_get_dma(umem, desc.addr); - xdptxd.data = xdp_umem_get_data(umem, desc.addr); + xdptxd.dma_addr = xsk_buff_raw_get_dma(umem, desc.addr); + xdptxd.data = xsk_buff_raw_get_data(umem, desc.addr); xdptxd.len = desc.len; - dma_sync_single_for_device(sq->pdev, xdptxd.dma_addr, - xdptxd.len, DMA_BIDIRECTIONAL); + xsk_buff_raw_dma_sync_for_device(umem, xdptxd.dma_addr, xdptxd.len); if (unlikely(!sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, check_result))) { if (sq->mpwqe.wqe) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h index 79b487d89757..39fa0a705856 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h @@ -5,7 +5,7 @@ #define __MLX5_EN_XSK_TX_H__ #include "en.h" -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> /* TX data path */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c index 4baaa5788320..7b17fcd0a56d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2019 Mellanox Technologies. */ -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> #include "umem.h" #include "setup.h" #include "en/params.h" @@ -10,40 +10,14 @@ static int mlx5e_xsk_map_umem(struct mlx5e_priv *priv, struct xdp_umem *umem) { struct device *dev = priv->mdev->device; - u32 i; - for (i = 0; i < umem->npgs; i++) { - dma_addr_t dma = dma_map_page(dev, umem->pgs[i], 0, PAGE_SIZE, - DMA_BIDIRECTIONAL); - - if (unlikely(dma_mapping_error(dev, dma))) - goto err_unmap; - umem->pages[i].dma = dma; - } - - return 0; - -err_unmap: - while (i--) { - dma_unmap_page(dev, umem->pages[i].dma, PAGE_SIZE, - DMA_BIDIRECTIONAL); - umem->pages[i].dma = 0; - } - - return -ENOMEM; + return xsk_buff_dma_map(umem, dev, 0); } static void mlx5e_xsk_unmap_umem(struct mlx5e_priv *priv, struct xdp_umem *umem) { - struct device *dev = priv->mdev->device; - u32 i; - - for (i = 0; i < umem->npgs; i++) { - dma_unmap_page(dev, umem->pages[i].dma, PAGE_SIZE, - DMA_BIDIRECTIONAL); - umem->pages[i].dma = 0; - } + return xsk_buff_dma_unmap(umem, 0); } static int mlx5e_xsk_get_umems(struct mlx5e_xsk *xsk) @@ -90,13 +64,14 @@ static void mlx5e_xsk_remove_umem(struct mlx5e_xsk *xsk, u16 ix) static bool mlx5e_xsk_is_umem_sane(struct xdp_umem *umem) { - return umem->headroom <= 0xffff && umem->chunk_size_nohr <= 0xffff; + return xsk_umem_get_headroom(umem) <= 0xffff && + xsk_umem_get_chunk_size(umem) <= 0xffff; } void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk) { - xsk->headroom = umem->headroom; - xsk->chunk_size = umem->chunk_size_nohr + umem->headroom; + xsk->headroom = xsk_umem_get_headroom(umem); + xsk->chunk_size = xsk_umem_get_chunk_size(umem); } static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv, @@ -241,18 +216,6 @@ int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid) mlx5e_xsk_disable_umem(priv, ix); } -int mlx5e_xsk_resize_reuseq(struct xdp_umem *umem, u32 nentries) -{ - struct xdp_umem_fq_reuse *reuseq; - - reuseq = xsk_reuseq_prepare(nentries); - if (unlikely(!reuseq)) - return -ENOMEM; - xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq)); - - return 0; -} - u16 mlx5e_xsk_first_unused_channel(struct mlx5e_params *params, struct mlx5e_xsk *xsk) { u16 res = xsk->refcnt ? params->num_channels : 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 07823abe5557..8b86c6ded302 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -38,7 +38,7 @@ #include <linux/bpf.h> #include <linux/if_bridge.h> #include <net/page_pool.h> -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> #include "eswitch.h" #include "en.h" #include "en/txrx.h" @@ -373,7 +373,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, struct mlx5_core_dev *mdev = c->mdev; void *rqc = rqp->rqc; void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq); - u32 num_xsk_frames = 0; u32 rq_xdp_ix; u32 pool_size; int wq_sz; @@ -413,7 +412,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk); - rq->buff.umem_headroom = xsk ? xsk->headroom : 0; pool_size = 1 << params->log_rq_mtu_frames; switch (rq->wq_type) { @@ -427,10 +425,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq); - if (xsk) - num_xsk_frames = wq_sz << - mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk); - pool_size = MLX5_MPWRQ_PAGES_PER_WQE << mlx5e_mpwqe_get_log_rq_size(params, xsk); @@ -482,9 +476,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, wq_sz = mlx5_wq_cyc_get_size(&rq->wqe.wq); - if (xsk) - num_xsk_frames = wq_sz << rq->wqe.info.log_num_frags; - rq->wqe.info = rqp->frags_info; rq->buff.frame0_sz = rq->wqe.info.arr[0].frag_stride; @@ -525,19 +516,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, } if (xsk) { - rq->buff.frame0_sz = xsk_umem_xdp_frame_sz(umem); - - err = mlx5e_xsk_resize_reuseq(umem, num_xsk_frames); - if (unlikely(err)) { - mlx5_core_err(mdev, "Unable to allocate the Reuse Ring for %u frames\n", - num_xsk_frames); - goto err_free; - } - - rq->zca.free = mlx5e_xsk_zca_free; err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, - MEM_TYPE_ZERO_COPY, - &rq->zca); + MEM_TYPE_XSK_BUFF_POOL, NULL); + xsk_buff_set_rxq_info(rq->umem, &rq->xdp_rxq); } else { /* Create a page_pool and register it with rxq */ pp_params.order = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index a514685fb560..fdba52136c5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -300,7 +300,7 @@ static inline void mlx5e_page_release(struct mlx5e_rq *rq, * put into the Reuse Ring, because there is no way to return * the page to the userspace when the interface goes down. */ - mlx5e_xsk_page_release(rq, dma_info); + xsk_buff_free(dma_info->xsk); else mlx5e_page_release_dynamic(rq, dma_info, recycle); } @@ -385,7 +385,11 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk) if (rq->umem) { int pages_desired = wqe_bulk << rq->wqe.info.log_num_frags; - if (unlikely(!mlx5e_xsk_pages_enough_umem(rq, pages_desired))) + /* Check in advance that we have enough frames, instead of + * allocating one-by-one, failing and moving frames to the + * Reuse Ring. + */ + if (unlikely(!xsk_buff_can_alloc(rq->umem, pages_desired))) return -ENOMEM; } @@ -480,8 +484,11 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) int err; int i; + /* Check in advance that we have enough frames, instead of allocating + * one-by-one, failing and moving frames to the Reuse Ring. + */ if (rq->umem && - unlikely(!mlx5e_xsk_pages_enough_umem(rq, MLX5_MPWRQ_PAGES_PER_WQE))) { + unlikely(!xsk_buff_can_alloc(rq->umem, MLX5_MPWRQ_PAGES_PER_WQE))) { err = -ENOMEM; goto err; } @@ -1044,12 +1051,24 @@ struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va, return skb; } +static void mlx5e_fill_xdp_buff(struct mlx5e_rq *rq, void *va, u16 headroom, + u32 len, struct xdp_buff *xdp) +{ + xdp->data_hard_start = va; + xdp_set_data_meta_invalid(xdp); + xdp->data = va + headroom; + xdp->data_end = xdp->data + len; + xdp->rxq = &rq->xdp_rxq; + xdp->frame_sz = rq->buff.frame0_sz; +} + struct sk_buff * mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt) { struct mlx5e_dma_info *di = wi->di; u16 rx_headroom = rq->buff.headroom; + struct xdp_buff xdp; struct sk_buff *skb; void *va, *data; bool consumed; @@ -1065,11 +1084,13 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, prefetch(data); rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, false); + mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt, &xdp); + consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp); rcu_read_unlock(); if (consumed) return NULL; /* page/packet was consumed by XDP */ + rx_headroom = xdp.data - xdp.data_hard_start; frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt); skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt); if (unlikely(!skb)) @@ -1343,6 +1364,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx]; u16 rx_headroom = rq->buff.headroom; u32 cqe_bcnt32 = cqe_bcnt; + struct xdp_buff xdp; struct sk_buff *skb; void *va, *data; u32 frag_size; @@ -1364,7 +1386,8 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, prefetch(data); rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32, false); + mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt32, &xdp); + consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp); rcu_read_unlock(); if (consumed) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) @@ -1372,6 +1395,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, return NULL; /* page/packet was consumed by XDP */ } + rx_headroom = xdp.data - xdp.data_hard_start; frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt32); skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt32); if (unlikely(!skb)) diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c index 1e0c024b0a93..8e4141552423 100644 --- a/drivers/net/hyperv/netvsc_bpf.c +++ b/drivers/net/hyperv/netvsc_bpf.c @@ -50,7 +50,6 @@ u32 netvsc_run_xdp(struct net_device *ndev, struct netvsc_channel *nvchan, xdp->data_end = xdp->data + len; xdp->rxq = &nvchan->xdp_rxq; xdp->frame_sz = PAGE_SIZE; - xdp->handle = 0; memcpy(xdp->data, data, len); |