diff options
Diffstat (limited to 'drivers/net/ethernet/intel/fm10k/fm10k_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/fm10k/fm10k_main.c | 145 |
1 files changed, 57 insertions, 88 deletions
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 9dffaba85ae6..b8c15b837fda 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1,22 +1,5 @@ -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include <linux/types.h> #include <linux/module.h> @@ -28,18 +11,14 @@ #include "fm10k.h" -#define DRV_VERSION "0.21.7-k" #define DRV_SUMMARY "Intel(R) Ethernet Switch Host Interface Driver" -const char fm10k_driver_version[] = DRV_VERSION; char fm10k_driver_name[] = "fm10k"; static const char fm10k_driver_string[] = DRV_SUMMARY; static const char fm10k_copyright[] = - "Copyright(c) 2013 - 2017 Intel Corporation."; + "Copyright(c) 2013 - 2019 Intel Corporation."; -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); -MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); +MODULE_LICENSE("GPL v2"); /* single workqueue for entire fm10k driver */ struct workqueue_struct *fm10k_workqueue; @@ -52,16 +31,26 @@ struct workqueue_struct *fm10k_workqueue; **/ static int __init fm10k_init_module(void) { - pr_info("%s - version %s\n", fm10k_driver_string, fm10k_driver_version); + int ret; + + pr_info("%s\n", fm10k_driver_string); pr_info("%s\n", fm10k_copyright); /* create driver workqueue */ - fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, + fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM | WQ_PERCPU, 0, fm10k_driver_name); + if (!fm10k_workqueue) + return -ENOMEM; fm10k_dbg_init(); - return fm10k_register_pci_driver(); + ret = fm10k_register_pci_driver(); + if (ret) { + fm10k_dbg_exit(); + destroy_workqueue(fm10k_workqueue); + } + + return ret; } module_init(fm10k_init_module); @@ -212,17 +201,12 @@ static void fm10k_reuse_rx_page(struct fm10k_ring *rx_ring, DMA_FROM_DEVICE); } -static inline bool fm10k_page_is_reserved(struct page *page) -{ - return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); -} - static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer, struct page *page, unsigned int __maybe_unused truesize) { - /* avoid re-using remote pages */ - if (unlikely(fm10k_page_is_reserved(page))) + /* avoid re-using remote and pfmemalloc pages */ + if (!dev_page_is_reusable(page)) return false; #if (PAGE_SIZE < 8192) @@ -283,8 +267,8 @@ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer, if (likely(size <= FM10K_RX_HDR_LEN)) { memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - /* page is not reserved, we can reuse buffer as-is */ - if (likely(!fm10k_page_is_reserved(page))) + /* page is reusable, we can reuse buffer as-is */ + if (dev_page_is_reusable(page)) return true; /* this page cannot be reused so discard it */ @@ -295,7 +279,7 @@ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer, /* we need the header to contain the greater of either ETH_HLEN or * 60 bytes if the skb->len is less than 60 for skb_pad. */ - pull_len = eth_get_headlen(va, FM10K_RX_HDR_LEN); + pull_len = eth_get_headlen(skb->dev, va, FM10K_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); @@ -328,10 +312,7 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring, rx_buffer->page_offset; /* prefetch first cache line of first page */ - prefetch(page_addr); -#if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); -#endif + net_prefetch(page_addr); /* allocate a skb to store the frags */ skb = napi_alloc_skb(&rx_ring->q_vector->napi, @@ -444,15 +425,14 @@ static void fm10k_type_trans(struct fm10k_ring *rx_ring, l2_accel = NULL; } - skb->protocol = eth_type_trans(skb, dev); - + /* Record Rx queue, or update macvlan statistics */ if (!l2_accel) - return; + skb_record_rx_queue(skb, rx_ring->queue_index); + else + macvlan_count_rx(netdev_priv(dev), skb->len + ETH_HLEN, true, + false); - /* update MACVLAN statistics */ - macvlan_count_rx(netdev_priv(dev), skb->len + ETH_HLEN, 1, - !!(rx_desc->w.hdr_info & - cpu_to_le16(FM10K_RXD_HDR_INFO_XC_MASK))); + skb->protocol = eth_type_trans(skb, dev); } /** @@ -479,8 +459,6 @@ static unsigned int fm10k_process_skb_fields(struct fm10k_ring *rx_ring, FM10K_CB(skb)->fi.w.vlan = rx_desc->w.vlan; - skb_record_rx_queue(skb, rx_ring->queue_index); - FM10K_CB(skb)->fi.d.glort = rx_desc->d.glort; if (rx_desc->w.vlan) { @@ -656,15 +634,8 @@ static int fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector, static struct ethhdr *fm10k_port_is_vxlan(struct sk_buff *skb) { struct fm10k_intfc *interface = netdev_priv(skb->dev); - struct fm10k_udp_port *vxlan_port; - /* we can only offload a vxlan if we recognize it as such */ - vxlan_port = list_first_entry_or_null(&interface->vxlan_port, - struct fm10k_udp_port, list); - - if (!vxlan_port) - return NULL; - if (vxlan_port->port != udp_hdr(skb)->dest) + if (interface->vxlan_port != udp_hdr(skb)->dest) return NULL; /* return offset of udp_hdr plus 8 bytes for VXLAN header */ @@ -806,9 +777,10 @@ static int fm10k_tso(struct fm10k_ring *tx_ring, tx_desc->mss = cpu_to_le16(skb_shinfo(skb)->gso_size); return 1; + err_vxlan: tx_ring->netdev->features &= ~NETIF_F_GSO_UDP_TUNNEL; - if (!net_ratelimit()) + if (net_ratelimit()) netdev_err(tx_ring->netdev, "TSO requested for unsupported tunnel, disabling offload\n"); return -1; @@ -876,6 +848,7 @@ static void fm10k_tx_csum(struct fm10k_ring *tx_ring, case IPPROTO_GRE: if (skb->encapsulation) break; + fallthrough; default: if (unlikely(net_ratelimit())) { dev_warn(tx_ring->dev, @@ -962,7 +935,7 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring, struct sk_buff *skb = first->skb; struct fm10k_tx_buffer *tx_buffer; struct fm10k_tx_desc *tx_desc; - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned char *data; dma_addr_t dma; unsigned int data_len, size; @@ -1053,13 +1026,8 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring, fm10k_maybe_stop_tx(tx_ring, DESC_NEEDED); /* notify HW of packet */ - if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { writel(i, tx_ring->tail); - - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } return; @@ -1094,8 +1062,11 @@ netdev_tx_t fm10k_xmit_frame_ring(struct sk_buff *skb, * + 2 desc gap to keep tail from touching head * otherwise try next time */ - for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; + + count += TXD_USE_COUNT(skb_frag_size(frag)); + } if (fm10k_maybe_stop_tx(tx_ring, count + 3)) { tx_ring->tx_stats.tx_busy++; @@ -1229,7 +1200,7 @@ static bool fm10k_clean_tx_irq(struct fm10k_q_vector *q_vector, break; /* prevent any other reads prior to eop_desc */ - read_barrier_depends(); + smp_rmb(); /* if DD is not set pending work has not been completed */ if (!(eop_desc->flags & FM10K_TXD_FLAG_DONE)) @@ -1483,11 +1454,11 @@ static int fm10k_poll(struct napi_struct *napi, int budget) if (!clean_complete) return budget; - /* all work done, exit the polling mode */ - napi_complete_done(napi, work_done); - - /* re-enable the q_vector */ - fm10k_qv_enable(q_vector); + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) + fm10k_qv_enable(q_vector); return min(work_done, budget - 1); } @@ -1575,7 +1546,7 @@ static bool fm10k_set_rss_queues(struct fm10k_intfc *interface) * important, starting with the "most" number of features turned on at once, * and ending with the smallest set of features. This way large combinations * can be allocated if they're turned on, and smaller combinations are the - * fallthrough conditions. + * fall through conditions. * **/ static void fm10k_set_num_queues(struct fm10k_intfc *interface) @@ -1621,20 +1592,17 @@ static int fm10k_alloc_q_vector(struct fm10k_intfc *interface, { struct fm10k_q_vector *q_vector; struct fm10k_ring *ring; - int ring_count, size; + int ring_count; ring_count = txr_count + rxr_count; - size = sizeof(struct fm10k_q_vector) + - (sizeof(struct fm10k_ring) * ring_count); /* allocate q_vector and rings */ - q_vector = kzalloc(size, GFP_KERNEL); + q_vector = kzalloc(struct_size(q_vector, ring, ring_count), GFP_KERNEL); if (!q_vector) return -ENOMEM; /* initialize NAPI */ - netif_napi_add(interface->netdev, &q_vector->napi, - fm10k_poll, NAPI_POLL_WEIGHT); + netif_napi_add(interface->netdev, &q_vector->napi, fm10k_poll); /* tie q_vector and interface together */ interface->q_vector[v_idx] = q_vector; @@ -1812,7 +1780,7 @@ static void fm10k_free_q_vectors(struct fm10k_intfc *interface) } /** - * f10k_reset_msix_capability - reset MSI-X capability + * fm10k_reset_msix_capability - reset MSI-X capability * @interface: board private structure to initialize * * Reset the MSI-X capability back to its starting state @@ -1825,7 +1793,7 @@ static void fm10k_reset_msix_capability(struct fm10k_intfc *interface) } /** - * f10k_init_msix_capability - configure MSI-X capability + * fm10k_init_msix_capability - configure MSI-X capability * @interface: board private structure to initialize * * Attempt to configure the interrupts using the best available @@ -1846,7 +1814,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) v_budget = min_t(u16, v_budget, num_online_cpus()); /* account for vectors not related to queues */ - v_budget += NON_Q_VECTORS(hw); + v_budget += NON_Q_VECTORS; /* At the same time, hardware can only support a maximum of * hw.mac->max_msix_vectors vectors. With features @@ -1878,7 +1846,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) } /* record the number of queues available for q_vectors */ - interface->num_q_vectors = v_budget - NON_Q_VECTORS(hw); + interface->num_q_vectors = v_budget - NON_Q_VECTORS; return 0; } @@ -1892,7 +1860,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) static bool fm10k_cache_ring_qos(struct fm10k_intfc *interface) { struct net_device *dev = interface->netdev; - int pc, offset, rss_i, i, q_idx; + int pc, offset, rss_i, i; u16 pc_stride = interface->ring_feature[RING_F_QOS].mask + 1; u8 num_pcs = netdev_get_num_tc(dev); @@ -1902,7 +1870,8 @@ static bool fm10k_cache_ring_qos(struct fm10k_intfc *interface) rss_i = interface->ring_feature[RING_F_RSS].indices; for (pc = 0, offset = 0; pc < num_pcs; pc++, offset += rss_i) { - q_idx = pc; + int q_idx = pc; + for (i = 0; i < rss_i; i++) { interface->tx_ring[offset + i]->reg_idx = q_idx; interface->tx_ring[offset + i]->qos_pc = pc; |