diff options
Diffstat (limited to 'drivers/net/ethernet')
244 files changed, 12397 insertions, 4977 deletions
diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c index 084a6d58543a..be823c186517 100644 --- a/drivers/net/ethernet/3com/typhoon.c +++ b/drivers/net/ethernet/3com/typhoon.c @@ -283,7 +283,6 @@ struct typhoon { spinlock_t command_lock ____cacheline_aligned; struct basic_ring cmdRing; struct basic_ring respRing; - struct net_device_stats stats; struct net_device_stats stats_saved; struct typhoon_shared * shared; dma_addr_t shared_dma; @@ -898,7 +897,7 @@ typhoon_set_rx_mode(struct net_device *dev) static int typhoon_do_get_stats(struct typhoon *tp) { - struct net_device_stats *stats = &tp->stats; + struct net_device_stats *stats = &tp->dev->stats; struct net_device_stats *saved = &tp->stats_saved; struct cmd_desc xp_cmd; struct resp_desc xp_resp[7]; @@ -951,7 +950,7 @@ static struct net_device_stats * typhoon_get_stats(struct net_device *dev) { struct typhoon *tp = netdev_priv(dev); - struct net_device_stats *stats = &tp->stats; + struct net_device_stats *stats = &tp->dev->stats; struct net_device_stats *saved = &tp->stats_saved; smp_rmb(); @@ -1991,7 +1990,7 @@ typhoon_stop_runtime(struct typhoon *tp, int wait_type) tp->card_state = Sleeping; smp_wmb(); typhoon_do_get_stats(tp); - memcpy(&tp->stats_saved, &tp->stats, sizeof(struct net_device_stats)); + memcpy(&tp->stats_saved, &tp->dev->stats, sizeof(struct net_device_stats)); INIT_COMMAND_NO_RESPONSE(&xp_cmd, TYPHOON_CMD_HALT); typhoon_issue_command(tp, 1, &xp_cmd, 0, NULL); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 35f19430c84a..7c1214d78855 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -133,7 +133,7 @@ static int ena_init_rx_cpu_rmap(struct ena_adapter *adapter) int irq_idx = ENA_IO_IRQ_IDX(i); rc = irq_cpu_rmap_add(adapter->netdev->rx_cpu_rmap, - adapter->msix_entries[irq_idx].vector); + pci_irq_vector(adapter->pdev, irq_idx)); if (rc) { free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap); adapter->netdev->rx_cpu_rmap = NULL; @@ -1208,13 +1208,7 @@ static irqreturn_t ena_intr_msix_io(int irq, void *data) static int ena_enable_msix(struct ena_adapter *adapter, int num_queues) { - int i, msix_vecs, rc; - - if (test_bit(ENA_FLAG_MSIX_ENABLED, &adapter->flags)) { - netif_err(adapter, probe, adapter->netdev, - "Error, MSI-X is already enabled\n"); - return -EPERM; - } + int msix_vecs, rc; /* Reserved the max msix vectors we might need */ msix_vecs = ENA_MAX_MSIX_VEC(num_queues); @@ -1222,16 +1216,9 @@ static int ena_enable_msix(struct ena_adapter *adapter, int num_queues) netif_dbg(adapter, probe, adapter->netdev, "trying to enable MSI-X, vectors %d\n", msix_vecs); - adapter->msix_entries = vzalloc(msix_vecs * sizeof(struct msix_entry)); - - if (!adapter->msix_entries) - return -ENOMEM; - - for (i = 0; i < msix_vecs; i++) - adapter->msix_entries[i].entry = i; - - rc = pci_enable_msix(adapter->pdev, adapter->msix_entries, msix_vecs); - if (rc != 0) { + rc = pci_alloc_irq_vectors(adapter->pdev, msix_vecs, msix_vecs, + PCI_IRQ_MSIX); + if (rc < 0) { netif_err(adapter, probe, adapter->netdev, "Failed to enable MSI-X, vectors %d rc %d\n", msix_vecs, rc); @@ -1248,7 +1235,6 @@ static int ena_enable_msix(struct ena_adapter *adapter, int num_queues) } adapter->msix_vecs = msix_vecs; - set_bit(ENA_FLAG_MSIX_ENABLED, &adapter->flags); return 0; } @@ -1264,7 +1250,7 @@ static void ena_setup_mgmnt_intr(struct ena_adapter *adapter) ena_intr_msix_mgmnt; adapter->irq_tbl[ENA_MGMNT_IRQ_IDX].data = adapter; adapter->irq_tbl[ENA_MGMNT_IRQ_IDX].vector = - adapter->msix_entries[ENA_MGMNT_IRQ_IDX].vector; + pci_irq_vector(adapter->pdev, ENA_MGMNT_IRQ_IDX); cpu = cpumask_first(cpu_online_mask); adapter->irq_tbl[ENA_MGMNT_IRQ_IDX].cpu = cpu; cpumask_set_cpu(cpu, @@ -1287,7 +1273,7 @@ static void ena_setup_io_intr(struct ena_adapter *adapter) adapter->irq_tbl[irq_idx].handler = ena_intr_msix_io; adapter->irq_tbl[irq_idx].data = &adapter->ena_napi[i]; adapter->irq_tbl[irq_idx].vector = - adapter->msix_entries[irq_idx].vector; + pci_irq_vector(adapter->pdev, irq_idx); adapter->irq_tbl[irq_idx].cpu = cpu; cpumask_set_cpu(cpu, @@ -1325,12 +1311,6 @@ static int ena_request_io_irq(struct ena_adapter *adapter) struct ena_irq *irq; int rc = 0, i, k; - if (!test_bit(ENA_FLAG_MSIX_ENABLED, &adapter->flags)) { - netif_err(adapter, ifup, adapter->netdev, - "Failed to request I/O IRQ: MSI-X is not enabled\n"); - return -EINVAL; - } - for (i = ENA_IO_IRQ_FIRST_IDX; i < adapter->msix_vecs; i++) { irq = &adapter->irq_tbl[i]; rc = request_irq(irq->vector, irq->handler, flags, irq->name, @@ -1389,16 +1369,6 @@ static void ena_free_io_irq(struct ena_adapter *adapter) } } -static void ena_disable_msix(struct ena_adapter *adapter) -{ - if (test_and_clear_bit(ENA_FLAG_MSIX_ENABLED, &adapter->flags)) - pci_disable_msix(adapter->pdev); - - if (adapter->msix_entries) - vfree(adapter->msix_entries); - adapter->msix_entries = NULL; -} - static void ena_disable_io_intr_sync(struct ena_adapter *adapter) { int i; @@ -2479,8 +2449,7 @@ static int ena_enable_msix_and_set_admin_interrupts(struct ena_adapter *adapter, return 0; err_disable_msix: - ena_disable_msix(adapter); - + pci_free_irq_vectors(adapter->pdev); return rc; } @@ -2518,7 +2487,7 @@ static void ena_fw_reset_device(struct work_struct *work) ena_free_mgmnt_irq(adapter); - ena_disable_msix(adapter); + pci_free_irq_vectors(adapter->pdev); ena_com_abort_admin_commands(ena_dev); @@ -2569,7 +2538,7 @@ static void ena_fw_reset_device(struct work_struct *work) return; err_disable_msix: ena_free_mgmnt_irq(adapter); - ena_disable_msix(adapter); + pci_free_irq_vectors(adapter->pdev); err_device_destroy: ena_com_admin_destroy(ena_dev); err: @@ -3103,7 +3072,7 @@ err_rss: err_free_msix: ena_com_dev_reset(ena_dev); ena_free_mgmnt_irq(adapter); - ena_disable_msix(adapter); + pci_free_irq_vectors(adapter->pdev); err_worker_destroy: ena_com_destroy_interrupt_moderation(ena_dev); del_timer(&adapter->timer_service); @@ -3188,7 +3157,7 @@ static void ena_remove(struct pci_dev *pdev) ena_free_mgmnt_irq(adapter); - ena_disable_msix(adapter); + pci_free_irq_vectors(adapter->pdev); free_netdev(netdev); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index ed62d8e231a1..0e22bce6239d 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -248,7 +248,6 @@ enum ena_flags_t { ENA_FLAG_DEVICE_RUNNING, ENA_FLAG_DEV_UP, ENA_FLAG_LINK_UP, - ENA_FLAG_MSIX_ENABLED, ENA_FLAG_TRIGGER_RESET }; @@ -267,7 +266,6 @@ struct ena_adapter { int num_queues; - struct msix_entry *msix_entries; int msix_vecs; u32 tx_usecs, rx_usecs; /* interrupt moderation */ diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c index b556c926557a..9c152d85840d 100644 --- a/drivers/net/ethernet/amd/nmclan_cs.c +++ b/drivers/net/ethernet/amd/nmclan_cs.c @@ -359,7 +359,6 @@ typedef struct _mace_statistics { typedef struct _mace_private { struct pcmcia_device *p_dev; - struct net_device_stats linux_stats; /* Linux statistics counters */ mace_statistics mace_stats; /* MACE chip statistics counters */ /* restore_multicast_list() state variables */ @@ -879,7 +878,7 @@ static netdev_tx_t mace_start_xmit(struct sk_buff *skb, service a transmit interrupt while we are in here. */ - lp->linux_stats.tx_bytes += skb->len; + dev->stats.tx_bytes += skb->len; lp->tx_free_frames--; /* WARNING: Write the _exact_ number of bytes written in the header! */ @@ -967,7 +966,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id) fifofc = inb(ioaddr + AM2150_MACE_BASE + MACE_FIFOFC); if ((fifofc & MACE_FIFOFC_XMTFC)==0) { - lp->linux_stats.tx_errors++; + dev->stats.tx_errors++; outb(0xFF, ioaddr + AM2150_XMT_SKIP); } @@ -1016,7 +1015,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id) } /* if (xmtfs & MACE_XMTFS_XMTSV) */ - lp->linux_stats.tx_packets++; + dev->stats.tx_packets++; lp->tx_free_frames++; netif_wake_queue(dev); } /* if (status & MACE_IR_XMTINT) */ @@ -1077,7 +1076,7 @@ static int mace_rx(struct net_device *dev, unsigned char RxCnt) " 0x%X.\n", dev->name, rx_framecnt, rx_status); if (rx_status & MACE_RCVFS_RCVSTS) { /* Error, update stats. */ - lp->linux_stats.rx_errors++; + dev->stats.rx_errors++; if (rx_status & MACE_RCVFS_OFLO) { lp->mace_stats.oflo++; } @@ -1114,14 +1113,14 @@ static int mace_rx(struct net_device *dev, unsigned char RxCnt) netif_rx(skb); /* Send the packet to the upper (protocol) layers. */ - lp->linux_stats.rx_packets++; - lp->linux_stats.rx_bytes += pkt_len; + dev->stats.rx_packets++; + dev->stats.rx_bytes += pkt_len; outb(0xFF, ioaddr + AM2150_RCV_NEXT); /* skip to next frame */ continue; } else { pr_debug("%s: couldn't allocate a sk_buff of size" " %d.\n", dev->name, pkt_len); - lp->linux_stats.rx_dropped++; + dev->stats.rx_dropped++; } } outb(0xFF, ioaddr + AM2150_RCV_NEXT); /* skip to next frame */ @@ -1231,13 +1230,13 @@ static void update_stats(unsigned int ioaddr, struct net_device *dev) lp->mace_stats.rntpc += mace_read(lp, ioaddr, MACE_RNTPC); lp->mace_stats.mpc += mace_read(lp, ioaddr, MACE_MPC); /* At this point, mace_stats is fully updated for this call. - We may now update the linux_stats. */ + We may now update the netdev stats. */ - /* The MACE has no equivalent for linux_stats field which are commented + /* The MACE has no equivalent for netdev stats field which are commented out. */ - /* lp->linux_stats.multicast; */ - lp->linux_stats.collisions = + /* dev->stats.multicast; */ + dev->stats.collisions = lp->mace_stats.rcvcco * 256 + lp->mace_stats.rcvcc; /* Collision: The MACE may retry sending a packet 15 times before giving up. The retry count is in XMTRC. @@ -1245,22 +1244,22 @@ static void update_stats(unsigned int ioaddr, struct net_device *dev) If so, why doesn't the RCVCC record these collisions? */ /* detailed rx_errors: */ - lp->linux_stats.rx_length_errors = + dev->stats.rx_length_errors = lp->mace_stats.rntpco * 256 + lp->mace_stats.rntpc; - /* lp->linux_stats.rx_over_errors */ - lp->linux_stats.rx_crc_errors = lp->mace_stats.fcs; - lp->linux_stats.rx_frame_errors = lp->mace_stats.fram; - lp->linux_stats.rx_fifo_errors = lp->mace_stats.oflo; - lp->linux_stats.rx_missed_errors = + /* dev->stats.rx_over_errors */ + dev->stats.rx_crc_errors = lp->mace_stats.fcs; + dev->stats.rx_frame_errors = lp->mace_stats.fram; + dev->stats.rx_fifo_errors = lp->mace_stats.oflo; + dev->stats.rx_missed_errors = lp->mace_stats.mpco * 256 + lp->mace_stats.mpc; /* detailed tx_errors */ - lp->linux_stats.tx_aborted_errors = lp->mace_stats.rtry; - lp->linux_stats.tx_carrier_errors = lp->mace_stats.lcar; + dev->stats.tx_aborted_errors = lp->mace_stats.rtry; + dev->stats.tx_carrier_errors = lp->mace_stats.lcar; /* LCAR usually results from bad cabling. */ - lp->linux_stats.tx_fifo_errors = lp->mace_stats.uflo; - lp->linux_stats.tx_heartbeat_errors = lp->mace_stats.cerr; - /* lp->linux_stats.tx_window_errors; */ + dev->stats.tx_fifo_errors = lp->mace_stats.uflo; + dev->stats.tx_heartbeat_errors = lp->mace_stats.cerr; + /* dev->stats.tx_window_errors; */ } /* update_stats */ /* ---------------------------------------------------------------------------- @@ -1274,10 +1273,10 @@ static struct net_device_stats *mace_get_stats(struct net_device *dev) update_stats(dev->base_addr, dev); pr_debug("%s: updating the statistics.\n", dev->name); - pr_linux_stats(&lp->linux_stats); + pr_linux_stats(&dev->stats); pr_mace_stats(&lp->mace_stats); - return &lp->linux_stats; + return &dev->stats; } /* net_device_stats */ /* ---------------------------------------------------------------------------- diff --git a/drivers/net/ethernet/apm/xgene-v2/ethtool.c b/drivers/net/ethernet/apm/xgene-v2/ethtool.c index 0c426f55ffdb..b6666e418e79 100644 --- a/drivers/net/ethernet/apm/xgene-v2/ethtool.c +++ b/drivers/net/ethernet/apm/xgene-v2/ethtool.c @@ -21,12 +21,13 @@ #include "main.h" -struct xge_gstrings_stats { - char name[ETH_GSTRING_LEN]; - int offset; -}; - #define XGE_STAT(m) { #m, offsetof(struct xge_pdata, stats.m) } +#define XGE_EXTD_STAT(m, n) \ + { \ + #m, \ + n, \ + 0 \ + } static const struct xge_gstrings_stats gstrings_stats[] = { XGE_STAT(rx_packets), @@ -36,7 +37,62 @@ static const struct xge_gstrings_stats gstrings_stats[] = { XGE_STAT(rx_errors) }; +static struct xge_gstrings_extd_stats gstrings_extd_stats[] = { + XGE_EXTD_STAT(tx_rx_64b_frame_cntr, TR64), + XGE_EXTD_STAT(tx_rx_127b_frame_cntr, TR127), + XGE_EXTD_STAT(tx_rx_255b_frame_cntr, TR255), + XGE_EXTD_STAT(tx_rx_511b_frame_cntr, TR511), + XGE_EXTD_STAT(tx_rx_1023b_frame_cntr, TR1K), + XGE_EXTD_STAT(tx_rx_1518b_frame_cntr, TRMAX), + XGE_EXTD_STAT(tx_rx_1522b_frame_cntr, TRMGV), + XGE_EXTD_STAT(rx_fcs_error_cntr, RFCS), + XGE_EXTD_STAT(rx_multicast_pkt_cntr, RMCA), + XGE_EXTD_STAT(rx_broadcast_pkt_cntr, RBCA), + XGE_EXTD_STAT(rx_ctrl_frame_pkt_cntr, RXCF), + XGE_EXTD_STAT(rx_pause_frame_pkt_cntr, RXPF), + XGE_EXTD_STAT(rx_unk_opcode_cntr, RXUO), + XGE_EXTD_STAT(rx_align_err_cntr, RALN), + XGE_EXTD_STAT(rx_frame_len_err_cntr, RFLR), + XGE_EXTD_STAT(rx_code_err_cntr, RCDE), + XGE_EXTD_STAT(rx_carrier_sense_err_cntr, RCSE), + XGE_EXTD_STAT(rx_undersize_pkt_cntr, RUND), + XGE_EXTD_STAT(rx_oversize_pkt_cntr, ROVR), + XGE_EXTD_STAT(rx_fragments_cntr, RFRG), + XGE_EXTD_STAT(rx_jabber_cntr, RJBR), + XGE_EXTD_STAT(rx_dropped_pkt_cntr, RDRP), + XGE_EXTD_STAT(tx_multicast_pkt_cntr, TMCA), + XGE_EXTD_STAT(tx_broadcast_pkt_cntr, TBCA), + XGE_EXTD_STAT(tx_pause_ctrl_frame_cntr, TXPF), + XGE_EXTD_STAT(tx_defer_pkt_cntr, TDFR), + XGE_EXTD_STAT(tx_excv_defer_pkt_cntr, TEDF), + XGE_EXTD_STAT(tx_single_col_pkt_cntr, TSCL), + XGE_EXTD_STAT(tx_multi_col_pkt_cntr, TMCL), + XGE_EXTD_STAT(tx_late_col_pkt_cntr, TLCL), + XGE_EXTD_STAT(tx_excv_col_pkt_cntr, TXCL), + XGE_EXTD_STAT(tx_total_col_cntr, TNCL), + XGE_EXTD_STAT(tx_pause_frames_hnrd_cntr, TPFH), + XGE_EXTD_STAT(tx_drop_frame_cntr, TDRP), + XGE_EXTD_STAT(tx_jabber_frame_cntr, TJBR), + XGE_EXTD_STAT(tx_fcs_error_cntr, TFCS), + XGE_EXTD_STAT(tx_ctrl_frame_cntr, TXCF), + XGE_EXTD_STAT(tx_oversize_frame_cntr, TOVR), + XGE_EXTD_STAT(tx_undersize_frame_cntr, TUND), + XGE_EXTD_STAT(tx_fragments_cntr, TFRG) +}; + #define XGE_STATS_LEN ARRAY_SIZE(gstrings_stats) +#define XGE_EXTD_STATS_LEN ARRAY_SIZE(gstrings_extd_stats) + +static void xge_mac_get_extd_stats(struct xge_pdata *pdata) +{ + u32 data; + int i; + + for (i = 0; i < XGE_EXTD_STATS_LEN; i++) { + data = xge_rd_csr(pdata, gstrings_extd_stats[i].addr); + gstrings_extd_stats[i].value += data; + } +} static void xge_get_drvinfo(struct net_device *ndev, struct ethtool_drvinfo *info) @@ -62,6 +118,11 @@ static void xge_get_strings(struct net_device *ndev, u32 stringset, u8 *data) memcpy(p, gstrings_stats[i].name, ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } + + for (i = 0; i < XGE_EXTD_STATS_LEN; i++) { + memcpy(p, gstrings_extd_stats[i].name, ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } } static int xge_get_sset_count(struct net_device *ndev, int sset) @@ -69,7 +130,7 @@ static int xge_get_sset_count(struct net_device *ndev, int sset) if (sset != ETH_SS_STATS) return -EINVAL; - return XGE_STATS_LEN; + return XGE_STATS_LEN + XGE_EXTD_STATS_LEN; } static void xge_get_ethtool_stats(struct net_device *ndev, @@ -81,6 +142,11 @@ static void xge_get_ethtool_stats(struct net_device *ndev, for (i = 0; i < XGE_STATS_LEN; i++) *data++ = *(u64 *)(pdata + gstrings_stats[i].offset); + + xge_mac_get_extd_stats(pdata); + + for (i = 0; i < XGE_EXTD_STATS_LEN; i++) + *data++ = gstrings_extd_stats[i].value; } static int xge_get_link_ksettings(struct net_device *ndev, diff --git a/drivers/net/ethernet/apm/xgene-v2/ethtool.h b/drivers/net/ethernet/apm/xgene-v2/ethtool.h new file mode 100644 index 000000000000..54b48d5561b8 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/ethtool.h @@ -0,0 +1,78 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian <isubramanian@apm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that 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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __XGENE_ENET_V2_ETHTOOL_H__ +#define __XGENE_ENET_V2_ETHTOOL_H__ + +struct xge_gstrings_stats { + char name[ETH_GSTRING_LEN]; + int offset; +}; + +struct xge_gstrings_extd_stats { + char name[ETH_GSTRING_LEN]; + u32 addr; + u32 value; +}; + +#define TR64 0xa080 +#define TR127 0xa084 +#define TR255 0xa088 +#define TR511 0xa08c +#define TR1K 0xa090 +#define TRMAX 0xa094 +#define TRMGV 0xa098 +#define RFCS 0xa0a4 +#define RMCA 0xa0a8 +#define RBCA 0xa0ac +#define RXCF 0xa0b0 +#define RXPF 0xa0b4 +#define RXUO 0xa0b8 +#define RALN 0xa0bc +#define RFLR 0xa0c0 +#define RCDE 0xa0c4 +#define RCSE 0xa0c8 +#define RUND 0xa0cc +#define ROVR 0xa0d0 +#define RFRG 0xa0d4 +#define RJBR 0xa0d8 +#define RDRP 0xa0dc +#define TMCA 0xa0e8 +#define TBCA 0xa0ec +#define TXPF 0xa0f0 +#define TDFR 0xa0f4 +#define TEDF 0xa0f8 +#define TSCL 0xa0fc +#define TMCL 0xa100 +#define TLCL 0xa104 +#define TXCL 0xa108 +#define TNCL 0xa10c +#define TPFH 0xa110 +#define TDRP 0xa114 +#define TJBR 0xa118 +#define TFCS 0xa11c +#define TXCF 0xa120 +#define TOVR 0xa124 +#define TUND 0xa128 +#define TFRG 0xa12c + +void xge_set_ethtool_ops(struct net_device *ndev); + +#endif /* __XGENE_ENET_V2_ETHTOOL_H__ */ diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.h b/drivers/net/ethernet/apm/xgene-v2/mac.h index 18a9c9d8a5e5..3c83fa617356 100644 --- a/drivers/net/ethernet/apm/xgene-v2/mac.h +++ b/drivers/net/ethernet/apm/xgene-v2/mac.h @@ -34,9 +34,6 @@ #define INTERFACE_CONTROL 0xa038 #define STATION_ADDR0 0xa040 #define STATION_ADDR1 0xa044 -#define RBYT 0xa09c -#define RPKT 0xa0a0 -#define RFCS 0xa0a4 #define RGMII_REG_0 0x27e0 #define ICM_CONFIG0_REG_0 0x2c00 diff --git a/drivers/net/ethernet/apm/xgene-v2/main.h b/drivers/net/ethernet/apm/xgene-v2/main.h index db1178e82a0a..969b258cb7de 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.h +++ b/drivers/net/ethernet/apm/xgene-v2/main.h @@ -38,6 +38,7 @@ #include "mac.h" #include "enet.h" #include "ring.h" +#include "ethtool.h" #define XGENE_ENET_V2_VERSION "v1.0" #define XGENE_ENET_STD_MTU 1536 @@ -75,6 +76,5 @@ struct xge_pdata { int xge_mdio_config(struct net_device *ndev); void xge_mdio_remove(struct net_device *ndev); -void xge_set_ethtool_ops(struct net_device *ndev); #endif /* __XGENE_ENET_V2_MAIN_H__ */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index d05fbfdce5e5..5d6c40d86775 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -100,11 +100,6 @@ static int aq_ndev_change_mtu(struct net_device *ndev, int new_mtu) goto err_exit; ndev->mtu = new_mtu; - if (netif_running(ndev)) { - aq_ndev_close(ndev); - aq_ndev_open(ndev); - } - err_exit: return err; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index ee78444bfb88..cdb02991f249 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -487,6 +487,9 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self, dx_buff->mss = skb_shinfo(skb)->gso_size; dx_buff->is_txc = 1U; + dx_buff->is_ipv6 = + (ip_hdr(skb)->version == 6) ? 1U : 0U; + dx = aq_ring_next_dx(ring, dx); dx_buff = &ring->buff_ring[dx]; ++ret; @@ -510,10 +513,22 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self, if (skb->ip_summed == CHECKSUM_PARTIAL) { dx_buff->is_ip_cso = (htons(ETH_P_IP) == skb->protocol) ? 1U : 0U; - dx_buff->is_tcp_cso = - (ip_hdr(skb)->protocol == IPPROTO_TCP) ? 1U : 0U; - dx_buff->is_udp_cso = - (ip_hdr(skb)->protocol == IPPROTO_UDP) ? 1U : 0U; + + if (ip_hdr(skb)->version == 4) { + dx_buff->is_tcp_cso = + (ip_hdr(skb)->protocol == IPPROTO_TCP) ? + 1U : 0U; + dx_buff->is_udp_cso = + (ip_hdr(skb)->protocol == IPPROTO_UDP) ? + 1U : 0U; + } else if (ip_hdr(skb)->version == 6) { + dx_buff->is_tcp_cso = + (ipv6_hdr(skb)->nexthdr == NEXTHDR_TCP) ? + 1U : 0U; + dx_buff->is_udp_cso = + (ipv6_hdr(skb)->nexthdr == NEXTHDR_UDP) ? + 1U : 0U; + } } for (; nr_frags--; ++frag_count) { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 0358e6072d45..3a8a4aa13687 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -101,6 +101,7 @@ int aq_ring_init(struct aq_ring_s *self) self->hw_head = 0; self->sw_head = 0; self->sw_tail = 0; + spin_lock_init(&self->header.lock); return 0; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index 257254645068..eecd6d1c4d73 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -58,7 +58,8 @@ struct __packed aq_ring_buff_s { u8 len_l2; u8 len_l3; u8 len_l4; - u8 rsvd2; + u8 is_ipv6:1; + u8 rsvd2:7; u32 len_pkt; }; }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index a2b746a2dd50..4ee15ff06a44 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -433,6 +433,9 @@ static int hw_atl_a0_hw_ring_tx_xmit(struct aq_hw_s *self, buff->len_l3 + buff->len_l2); is_gso = true; + + if (buff->is_ipv6) + txd->ctl |= HW_ATL_A0_TXD_CTL_CMD_IPV6; } else { buff_pa_len = buff->len; @@ -458,6 +461,7 @@ static int hw_atl_a0_hw_ring_tx_xmit(struct aq_hw_s *self, if (unlikely(buff->is_eop)) { txd->ctl |= HW_ATL_A0_TXD_CTL_EOP; txd->ctl |= HW_ATL_A0_TXD_CTL_CMD_WB; + is_gso = false; } } diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index cab2931dab9a..42150708191d 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -471,6 +471,9 @@ static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self, buff->len_l3 + buff->len_l2); is_gso = true; + + if (buff->is_ipv6) + txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_IPV6; } else { buff_pa_len = buff->len; @@ -496,6 +499,7 @@ static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self, if (unlikely(buff->is_eop)) { txd->ctl |= HW_ATL_B0_TXD_CTL_EOP; txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_WB; + is_gso = false; } } diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 23873395f100..68de2f2652f2 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -434,7 +434,7 @@ static int arc_emac_open(struct net_device *ndev) /* Enable EMAC */ arc_reg_or(priv, R_CTRL, EN_MASK); - phy_start_aneg(ndev->phydev); + phy_start(ndev->phydev); netif_start_queue(ndev); @@ -556,6 +556,8 @@ static int arc_emac_stop(struct net_device *ndev) napi_disable(&priv->napi); netif_stop_queue(ndev); + phy_stop(ndev->phydev); + /* Disable interrupts */ arc_reg_clr(priv, R_ENABLE, RXINT_MASK | TXINT_MASK | ERR_MASK); diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h index d4a409139ea2..78c5de467426 100644 --- a/drivers/net/ethernet/atheros/alx/alx.h +++ b/drivers/net/ethernet/atheros/alx/alx.h @@ -102,9 +102,6 @@ struct alx_napi { #define ALX_MAX_NAPIS 8 -#define ALX_FLAG_USING_MSIX BIT(0) -#define ALX_FLAG_USING_MSI BIT(1) - struct alx_priv { struct net_device *dev; @@ -112,7 +109,6 @@ struct alx_priv { /* msi-x vectors */ int num_vec; - struct msix_entry *msix_entries; /* all descriptor memory */ struct { @@ -139,8 +135,6 @@ struct alx_priv { u16 msg_enable; - int flags; - /* protects hw.stats */ spinlock_t stats_lock; }; diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 6a27c2662675..a8c2db881b75 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -314,7 +314,7 @@ static int alx_poll(struct napi_struct *napi, int budget) napi_complete_done(&np->napi, work); /* enable interrupt */ - if (alx->flags & ALX_FLAG_USING_MSIX) { + if (alx->hw.pdev->msix_enabled) { alx_mask_msix(hw, np->vec_idx, false); } else { spin_lock_irqsave(&alx->irq_lock, flags); @@ -811,7 +811,7 @@ static void alx_config_vector_mapping(struct alx_priv *alx) u32 tbl[2] = {0, 0}; int i, vector, idx, shift; - if (alx->flags & ALX_FLAG_USING_MSIX) { + if (alx->hw.pdev->msix_enabled) { /* tx mappings */ for (i = 0, vector = 1; i < alx->num_txq; i++, vector++) { idx = txq_vec_mapping_shift[i * 2]; @@ -828,29 +828,19 @@ static void alx_config_vector_mapping(struct alx_priv *alx) alx_write_mem32(hw, ALX_MSI_ID_MAP, 0); } -static bool alx_enable_msix(struct alx_priv *alx) +static int alx_enable_msix(struct alx_priv *alx) { - int i, err, num_vec, num_txq, num_rxq; + int err, num_vec, num_txq, num_rxq; num_txq = min_t(int, num_online_cpus(), ALX_MAX_TX_QUEUES); num_rxq = 1; num_vec = max_t(int, num_txq, num_rxq) + 1; - alx->msix_entries = kcalloc(num_vec, sizeof(struct msix_entry), - GFP_KERNEL); - if (!alx->msix_entries) { - netdev_warn(alx->dev, "Allocation of msix entries failed!\n"); - return false; - } - - for (i = 0; i < num_vec; i++) - alx->msix_entries[i].entry = i; - - err = pci_enable_msix(alx->hw.pdev, alx->msix_entries, num_vec); + err = pci_alloc_irq_vectors(alx->hw.pdev, num_vec, num_vec, + PCI_IRQ_MSIX); if (err) { - kfree(alx->msix_entries); netdev_warn(alx->dev, "Enabling MSI-X interrupts failed!\n"); - return false; + return err; } alx->num_vec = num_vec; @@ -858,7 +848,7 @@ static bool alx_enable_msix(struct alx_priv *alx) alx->num_txq = num_txq; alx->num_rxq = num_rxq; - return true; + return err; } static int alx_request_msix(struct alx_priv *alx) @@ -866,7 +856,7 @@ static int alx_request_msix(struct alx_priv *alx) struct net_device *netdev = alx->dev; int i, err, vector = 0, free_vector = 0; - err = request_irq(alx->msix_entries[0].vector, alx_intr_msix_misc, + err = request_irq(pci_irq_vector(alx->hw.pdev, 0), alx_intr_msix_misc, 0, netdev->name, alx); if (err) goto out_err; @@ -889,7 +879,7 @@ static int alx_request_msix(struct alx_priv *alx) sprintf(np->irq_lbl, "%s-unused", netdev->name); np->vec_idx = vector; - err = request_irq(alx->msix_entries[vector].vector, + err = request_irq(pci_irq_vector(alx->hw.pdev, vector), alx_intr_msix_ring, 0, np->irq_lbl, np); if (err) goto out_free; @@ -897,47 +887,31 @@ static int alx_request_msix(struct alx_priv *alx) return 0; out_free: - free_irq(alx->msix_entries[free_vector++].vector, alx); + free_irq(pci_irq_vector(alx->hw.pdev, free_vector++), alx); vector--; for (i = 0; i < vector; i++) - free_irq(alx->msix_entries[free_vector++].vector, + free_irq(pci_irq_vector(alx->hw.pdev,free_vector++), alx->qnapi[i]); out_err: return err; } -static void alx_init_intr(struct alx_priv *alx, bool msix) +static int alx_init_intr(struct alx_priv *alx) { - if (msix) { - if (alx_enable_msix(alx)) - alx->flags |= ALX_FLAG_USING_MSIX; - } + int ret; - if (!(alx->flags & ALX_FLAG_USING_MSIX)) { - alx->num_vec = 1; - alx->num_napi = 1; - alx->num_txq = 1; - alx->num_rxq = 1; - - if (!pci_enable_msi(alx->hw.pdev)) - alx->flags |= ALX_FLAG_USING_MSI; - } -} - -static void alx_disable_advanced_intr(struct alx_priv *alx) -{ - if (alx->flags & ALX_FLAG_USING_MSIX) { - kfree(alx->msix_entries); - pci_disable_msix(alx->hw.pdev); - alx->flags &= ~ALX_FLAG_USING_MSIX; - } + ret = pci_alloc_irq_vectors(alx->hw.pdev, 1, 1, + PCI_IRQ_MSI | PCI_IRQ_LEGACY); + if (ret) + return ret; - if (alx->flags & ALX_FLAG_USING_MSI) { - pci_disable_msi(alx->hw.pdev); - alx->flags &= ~ALX_FLAG_USING_MSI; - } + alx->num_vec = 1; + alx->num_napi = 1; + alx->num_txq = 1; + alx->num_rxq = 1; + return 0; } static void alx_irq_enable(struct alx_priv *alx) @@ -950,10 +924,11 @@ static void alx_irq_enable(struct alx_priv *alx) alx_write_mem32(hw, ALX_IMR, alx->int_mask); alx_post_write(hw); - if (alx->flags & ALX_FLAG_USING_MSIX) + if (alx->hw.pdev->msix_enabled) { /* enable all msix irqs */ for (i = 0; i < alx->num_vec; i++) alx_mask_msix(hw, i, false); + } } static void alx_irq_disable(struct alx_priv *alx) @@ -965,13 +940,13 @@ static void alx_irq_disable(struct alx_priv *alx) alx_write_mem32(hw, ALX_IMR, 0); alx_post_write(hw); - if (alx->flags & ALX_FLAG_USING_MSIX) { + if (alx->hw.pdev->msix_enabled) { for (i = 0; i < alx->num_vec; i++) { alx_mask_msix(hw, i, true); - synchronize_irq(alx->msix_entries[i].vector); + synchronize_irq(pci_irq_vector(alx->hw.pdev, i)); } } else { - synchronize_irq(alx->hw.pdev->irq); + synchronize_irq(pci_irq_vector(alx->hw.pdev, 0)); } } @@ -981,8 +956,11 @@ static int alx_realloc_resources(struct alx_priv *alx) alx_free_rings(alx); alx_free_napis(alx); - alx_disable_advanced_intr(alx); - alx_init_intr(alx, false); + pci_free_irq_vectors(alx->hw.pdev); + + err = alx_init_intr(alx); + if (err) + return err; err = alx_alloc_napis(alx); if (err) @@ -1004,7 +982,7 @@ static int alx_request_irq(struct alx_priv *alx) msi_ctrl = (hw->imt >> 1) << ALX_MSI_RETRANS_TM_SHIFT; - if (alx->flags & ALX_FLAG_USING_MSIX) { + if (alx->hw.pdev->msix_enabled) { alx_write_mem32(hw, ALX_MSI_RETRANS_TIMER, msi_ctrl); err = alx_request_msix(alx); if (!err) @@ -1016,20 +994,20 @@ static int alx_request_irq(struct alx_priv *alx) goto out; } - if (alx->flags & ALX_FLAG_USING_MSI) { + if (alx->hw.pdev->msi_enabled) { alx_write_mem32(hw, ALX_MSI_RETRANS_TIMER, msi_ctrl | ALX_MSI_MASK_SEL_LINE); - err = request_irq(pdev->irq, alx_intr_msi, 0, + err = request_irq(pci_irq_vector(pdev, 0), alx_intr_msi, 0, alx->dev->name, alx); if (!err) goto out; + /* fall back to legacy interrupt */ - alx->flags &= ~ALX_FLAG_USING_MSI; - pci_disable_msi(alx->hw.pdev); + pci_free_irq_vectors(alx->hw.pdev); } alx_write_mem32(hw, ALX_MSI_RETRANS_TIMER, 0); - err = request_irq(pdev->irq, alx_intr_legacy, IRQF_SHARED, + err = request_irq(pci_irq_vector(pdev, 0), alx_intr_legacy, IRQF_SHARED, alx->dev->name, alx); out: if (!err) @@ -1042,18 +1020,15 @@ out: static void alx_free_irq(struct alx_priv *alx) { struct pci_dev *pdev = alx->hw.pdev; - int i, vector = 0; + int i; - if (alx->flags & ALX_FLAG_USING_MSIX) { - free_irq(alx->msix_entries[vector++].vector, alx); + free_irq(pci_irq_vector(pdev, 0), alx); + if (alx->hw.pdev->msix_enabled) { for (i = 0; i < alx->num_napi; i++) - free_irq(alx->msix_entries[vector++].vector, - alx->qnapi[i]); - } else { - free_irq(pdev->irq, alx); + free_irq(pci_irq_vector(pdev, i + 1), alx->qnapi[i]); } - alx_disable_advanced_intr(alx); + pci_free_irq_vectors(pdev); } static int alx_identify_hw(struct alx_priv *alx) @@ -1221,7 +1196,12 @@ static int __alx_open(struct alx_priv *alx, bool resume) { int err; - alx_init_intr(alx, true); + err = alx_enable_msix(alx); + if (err < 0) { + err = alx_init_intr(alx); + if (err) + return err; + } if (!resume) netif_carrier_off(alx->dev); @@ -1264,7 +1244,7 @@ out_free_rings: alx_free_rings(alx); alx_free_napis(alx); out_disable_adv_intr: - alx_disable_advanced_intr(alx); + pci_free_irq_vectors(alx->hw.pdev); return err; } @@ -1637,11 +1617,11 @@ static void alx_poll_controller(struct net_device *netdev) struct alx_priv *alx = netdev_priv(netdev); int i; - if (alx->flags & ALX_FLAG_USING_MSIX) { + if (alx->hw.pdev->msix_enabled) { alx_intr_msix_misc(0, alx); for (i = 0; i < alx->num_txq; i++) alx_intr_msix_ring(0, alx->qnapi[i]); - } else if (alx->flags & ALX_FLAG_USING_MSI) + } else if (alx->hw.pdev->msi_enabled) alx_intr_msi(0, alx); else alx_intr_legacy(0, alx); @@ -1783,7 +1763,7 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->netdev_ops = &alx_netdev_ops; netdev->ethtool_ops = &alx_ethtool_ops; - netdev->irq = pdev->irq; + netdev->irq = pci_irq_vector(pdev, 0); netdev->watchdog_timeo = ALX_WATCHDOG_TIME; if (ent->driver_data & ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index 0a23034bbe3f..352beff796ae 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -2277,7 +2277,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id, GENERAL_ATTEN_OFFSET(LATCHED_ATTN_RBCP) | \ GENERAL_ATTEN_OFFSET(LATCHED_ATTN_RSVD_GRC)) -#define HW_INTERRUT_ASSERT_SET_0 \ +#define HW_INTERRUPT_ASSERT_SET_0 \ (AEU_INPUTS_ATTN_BITS_TSDM_HW_INTERRUPT | \ AEU_INPUTS_ATTN_BITS_TCM_HW_INTERRUPT | \ AEU_INPUTS_ATTN_BITS_TSEMI_HW_INTERRUPT | \ @@ -2290,7 +2290,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id, AEU_INPUTS_ATTN_BITS_TSEMI_PARITY_ERROR |\ AEU_INPUTS_ATTN_BITS_TCM_PARITY_ERROR |\ AEU_INPUTS_ATTN_BITS_PBCLIENT_PARITY_ERROR) -#define HW_INTERRUT_ASSERT_SET_1 \ +#define HW_INTERRUPT_ASSERT_SET_1 \ (AEU_INPUTS_ATTN_BITS_QM_HW_INTERRUPT | \ AEU_INPUTS_ATTN_BITS_TIMERS_HW_INTERRUPT | \ AEU_INPUTS_ATTN_BITS_XSDM_HW_INTERRUPT | \ @@ -2318,7 +2318,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id, AEU_INPUTS_ATTN_BITS_UPB_PARITY_ERROR | \ AEU_INPUTS_ATTN_BITS_CSDM_PARITY_ERROR |\ AEU_INPUTS_ATTN_BITS_CCM_PARITY_ERROR) -#define HW_INTERRUT_ASSERT_SET_2 \ +#define HW_INTERRUPT_ASSERT_SET_2 \ (AEU_INPUTS_ATTN_BITS_CSEMI_HW_INTERRUPT | \ AEU_INPUTS_ATTN_BITS_CDU_HW_INTERRUPT | \ AEU_INPUTS_ATTN_BITS_DMAE_HW_INTERRUPT | \ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index ac76fc251d26..a851f95c307a 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -4166,14 +4166,14 @@ static void bnx2x_attn_int_deasserted0(struct bnx2x *bp, u32 attn) bnx2x_release_phy_lock(bp); } - if (attn & HW_INTERRUT_ASSERT_SET_0) { + if (attn & HW_INTERRUPT_ASSERT_SET_0) { val = REG_RD(bp, reg_offset); - val &= ~(attn & HW_INTERRUT_ASSERT_SET_0); + val &= ~(attn & HW_INTERRUPT_ASSERT_SET_0); REG_WR(bp, reg_offset, val); BNX2X_ERR("FATAL HW block attention set0 0x%x\n", - (u32)(attn & HW_INTERRUT_ASSERT_SET_0)); + (u32)(attn & HW_INTERRUPT_ASSERT_SET_0)); bnx2x_panic(); } } @@ -4191,7 +4191,7 @@ static void bnx2x_attn_int_deasserted1(struct bnx2x *bp, u32 attn) BNX2X_ERR("FATAL error from DORQ\n"); } - if (attn & HW_INTERRUT_ASSERT_SET_1) { + if (attn & HW_INTERRUPT_ASSERT_SET_1) { int port = BP_PORT(bp); int reg_offset; @@ -4200,11 +4200,11 @@ static void bnx2x_attn_int_deasserted1(struct bnx2x *bp, u32 attn) MISC_REG_AEU_ENABLE1_FUNC_0_OUT_1); val = REG_RD(bp, reg_offset); - val &= ~(attn & HW_INTERRUT_ASSERT_SET_1); + val &= ~(attn & HW_INTERRUPT_ASSERT_SET_1); REG_WR(bp, reg_offset, val); BNX2X_ERR("FATAL HW block attention set1 0x%x\n", - (u32)(attn & HW_INTERRUT_ASSERT_SET_1)); + (u32)(attn & HW_INTERRUPT_ASSERT_SET_1)); bnx2x_panic(); } } @@ -4235,7 +4235,7 @@ static void bnx2x_attn_int_deasserted2(struct bnx2x *bp, u32 attn) } } - if (attn & HW_INTERRUT_ASSERT_SET_2) { + if (attn & HW_INTERRUPT_ASSERT_SET_2) { int port = BP_PORT(bp); int reg_offset; @@ -4244,11 +4244,11 @@ static void bnx2x_attn_int_deasserted2(struct bnx2x *bp, u32 attn) MISC_REG_AEU_ENABLE1_FUNC_0_OUT_2); val = REG_RD(bp, reg_offset); - val &= ~(attn & HW_INTERRUT_ASSERT_SET_2); + val &= ~(attn & HW_INTERRUPT_ASSERT_SET_2); REG_WR(bp, reg_offset, val); BNX2X_ERR("FATAL HW block attention set2 0x%x\n", - (u32)(attn & HW_INTERRUT_ASSERT_SET_2)); + (u32)(attn & HW_INTERRUPT_ASSERT_SET_2)); bnx2x_panic(); } } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 174ec8f84637..129b8101b932 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1983,20 +1983,25 @@ static void bnxt_free_rx_skbs(struct bnxt *bp) for (j = 0; j < max_idx; j++) { struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[j]; + dma_addr_t mapping = rx_buf->mapping; void *data = rx_buf->data; if (!data) continue; - dma_unmap_single(&pdev->dev, rx_buf->mapping, - bp->rx_buf_use_size, bp->rx_dir); - rx_buf->data = NULL; - if (BNXT_RX_PAGE_MODE(bp)) + if (BNXT_RX_PAGE_MODE(bp)) { + mapping -= bp->rx_dma_offset; + dma_unmap_page(&pdev->dev, mapping, + PAGE_SIZE, bp->rx_dir); __free_page(data); - else + } else { + dma_unmap_single(&pdev->dev, mapping, + bp->rx_buf_use_size, + bp->rx_dir); kfree(data); + } } for (j = 0; j < max_agg_idx; j++) { @@ -2455,6 +2460,18 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) return 0; } +static void bnxt_init_cp_rings(struct bnxt *bp) +{ + int i; + + for (i = 0; i < bp->cp_nr_rings; i++) { + struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring; + struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; + + ring->fw_ring_id = INVALID_HW_RING_ID; + } +} + static int bnxt_init_rx_rings(struct bnxt *bp) { int i, rc = 0; @@ -4532,6 +4549,9 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp) pf->max_tx_wm_flows = le32_to_cpu(resp->max_tx_wm_flows); pf->max_rx_em_flows = le32_to_cpu(resp->max_rx_em_flows); pf->max_rx_wm_flows = le32_to_cpu(resp->max_rx_wm_flows); + if (resp->flags & + cpu_to_le32(FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED)) + bp->flags |= BNXT_FLAG_WOL_CAP; } else { #ifdef CONFIG_BNXT_SRIOV struct bnxt_vf_info *vf = &bp->vf; @@ -4732,7 +4752,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa) rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags); if (rc) { netdev_err(bp->dev, "hwrm vnic set tpa failure rc for vnic %d: %x\n", - rc, i); + i, rc); return rc; } } @@ -5006,6 +5026,7 @@ static int bnxt_shutdown_nic(struct bnxt *bp, bool irq_re_init) static int bnxt_init_nic(struct bnxt *bp, bool irq_re_init) { + bnxt_init_cp_rings(bp); bnxt_init_rx_rings(bp); bnxt_init_tx_rings(bp); bnxt_init_ring_grps(bp, irq_re_init); @@ -5180,9 +5201,10 @@ static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp) { #if defined(CONFIG_BNXT_SRIOV) if (BNXT_VF(bp)) - return bp->vf.max_irqs; + return min_t(unsigned int, bp->vf.max_irqs, + bp->vf.max_cp_rings); #endif - return bp->pf.max_irqs; + return min_t(unsigned int, bp->pf.max_irqs, bp->pf.max_cp_rings); } void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs) @@ -5839,6 +5861,76 @@ static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp) return 0; } +int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp) +{ + struct hwrm_wol_filter_alloc_input req = {0}; + struct hwrm_wol_filter_alloc_output *resp = bp->hwrm_cmd_resp_addr; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_ALLOC, -1, -1); + req.port_id = cpu_to_le16(bp->pf.port_id); + req.wol_type = WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT; + req.enables = cpu_to_le32(WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS); + memcpy(req.mac_address, bp->dev->dev_addr, ETH_ALEN); + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc) + bp->wol_filter_id = resp->wol_filter_id; + mutex_unlock(&bp->hwrm_cmd_lock); + return rc; +} + +int bnxt_hwrm_free_wol_fltr(struct bnxt *bp) +{ + struct hwrm_wol_filter_free_input req = {0}; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_FREE, -1, -1); + req.port_id = cpu_to_le16(bp->pf.port_id); + req.enables = cpu_to_le32(WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID); + req.wol_filter_id = bp->wol_filter_id; + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + return rc; +} + +static u16 bnxt_hwrm_get_wol_fltrs(struct bnxt *bp, u16 handle) +{ + struct hwrm_wol_filter_qcfg_input req = {0}; + struct hwrm_wol_filter_qcfg_output *resp = bp->hwrm_cmd_resp_addr; + u16 next_handle = 0; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_QCFG, -1, -1); + req.port_id = cpu_to_le16(bp->pf.port_id); + req.handle = cpu_to_le16(handle); + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc) { + next_handle = le16_to_cpu(resp->next_handle); + if (next_handle != 0) { + if (resp->wol_type == + WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT) { + bp->wol = 1; + bp->wol_filter_id = resp->wol_filter_id; + } + } + } + mutex_unlock(&bp->hwrm_cmd_lock); + return next_handle; +} + +static void bnxt_get_wol_settings(struct bnxt *bp) +{ + u16 handle = 0; + + if (!BNXT_PF(bp) || !(bp->flags & BNXT_FLAG_WOL_CAP)) + return; + + do { + handle = bnxt_hwrm_get_wol_fltrs(bp, handle); + } while (handle && handle != 0xffff); +} + static bool bnxt_eee_config_ok(struct bnxt *bp) { struct ethtool_eee *eee = &bp->eee; @@ -6024,6 +6116,43 @@ int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) return rc; } +/* rtnl_lock held, open the NIC half way by allocating all resources, but + * NAPI, IRQ, and TX are not enabled. This is mainly used for offline + * self tests. + */ +int bnxt_half_open_nic(struct bnxt *bp) +{ + int rc = 0; + + rc = bnxt_alloc_mem(bp, false); + if (rc) { + netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc); + goto half_open_err; + } + rc = bnxt_init_nic(bp, false); + if (rc) { + netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc); + goto half_open_err; + } + return 0; + +half_open_err: + bnxt_free_skbs(bp); + bnxt_free_mem(bp, false); + dev_close(bp->dev); + return rc; +} + +/* rtnl_lock held, this call can only be made after a previous successful + * call to bnxt_half_open_nic(). + */ +void bnxt_half_close_nic(struct bnxt *bp) +{ + bnxt_hwrm_resource_free(bp, false, false); + bnxt_free_skbs(bp); + bnxt_free_mem(bp, false); +} + static int bnxt_open(struct net_device *dev) { struct bnxt *bp = netdev_priv(dev); @@ -7208,6 +7337,7 @@ static void bnxt_remove_one(struct pci_dev *pdev) bnxt_clear_int_mode(bp); bnxt_hwrm_func_drv_unrgtr(bp); bnxt_free_hwrm_resources(bp); + bnxt_ethtool_free(bp); bnxt_dcb_free(bp); kfree(bp->edev); bp->edev = NULL; @@ -7530,6 +7660,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) bnxt_hwrm_func_qcfg(bp); bnxt_hwrm_port_led_qcaps(bp); + bnxt_ethtool_init(bp); bnxt_set_rx_skb_mode(bp, false); bnxt_set_tpa_flags(bp); @@ -7575,6 +7706,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto init_err_pci_clean; + bnxt_get_wol_settings(bp); + if (bp->flags & BNXT_FLAG_WOL_CAP) + device_set_wakeup_enable(&pdev->dev, bp->wol); + else + device_set_wakeup_capable(&pdev->dev, false); + rc = register_netdev(dev); if (rc) goto init_err_clr_int; @@ -7598,6 +7735,88 @@ init_err_free: return rc; } +static void bnxt_shutdown(struct pci_dev *pdev) +{ + struct net_device *dev = pci_get_drvdata(pdev); + struct bnxt *bp; + + if (!dev) + return; + + rtnl_lock(); + bp = netdev_priv(dev); + if (!bp) + goto shutdown_exit; + + if (netif_running(dev)) + dev_close(dev); + + if (system_state == SYSTEM_POWER_OFF) { + bnxt_clear_int_mode(bp); + pci_wake_from_d3(pdev, bp->wol); + pci_set_power_state(pdev, PCI_D3hot); + } + +shutdown_exit: + rtnl_unlock(); +} + +#ifdef CONFIG_PM_SLEEP +static int bnxt_suspend(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct net_device *dev = pci_get_drvdata(pdev); + struct bnxt *bp = netdev_priv(dev); + int rc = 0; + + rtnl_lock(); + if (netif_running(dev)) { + netif_device_detach(dev); + rc = bnxt_close(dev); + } + bnxt_hwrm_func_drv_unrgtr(bp); + rtnl_unlock(); + return rc; +} + +static int bnxt_resume(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct net_device *dev = pci_get_drvdata(pdev); + struct bnxt *bp = netdev_priv(dev); + int rc = 0; + + rtnl_lock(); + if (bnxt_hwrm_ver_get(bp) || bnxt_hwrm_func_drv_rgtr(bp)) { + rc = -ENODEV; + goto resume_exit; + } + rc = bnxt_hwrm_func_reset(bp); + if (rc) { + rc = -EBUSY; + goto resume_exit; + } + bnxt_get_wol_settings(bp); + if (netif_running(dev)) { + rc = bnxt_open(dev); + if (!rc) + netif_device_attach(dev); + } + +resume_exit: + rtnl_unlock(); + return rc; +} + +static SIMPLE_DEV_PM_OPS(bnxt_pm_ops, bnxt_suspend, bnxt_resume); +#define BNXT_PM_OPS (&bnxt_pm_ops) + +#else + +#define BNXT_PM_OPS NULL + +#endif /* CONFIG_PM_SLEEP */ + /** * bnxt_io_error_detected - called when PCI error is detected * @pdev: Pointer to PCI device @@ -7714,6 +7933,8 @@ static struct pci_driver bnxt_pci_driver = { .id_table = bnxt_pci_tbl, .probe = bnxt_init_one, .remove = bnxt_remove_one, + .shutdown = bnxt_shutdown, + .driver.pm = BNXT_PM_OPS, .err_handler = &bnxt_err_handler, #if defined(CONFIG_BNXT_SRIOV) .sriov_configure = bnxt_sriov_configure, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 3cb07778a690..c9a1688a65de 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -426,8 +426,6 @@ struct rx_tpa_end_cmp_ext { #define BNXT_MIN_PKT_SIZE 52 -#define BNXT_NUM_TESTS(bp) 0 - #define BNXT_DEFAULT_RX_RING_SIZE 511 #define BNXT_DEFAULT_TX_RING_SIZE 511 @@ -911,6 +909,14 @@ struct bnxt_led_info { __le16 led_color_caps; }; +#define BNXT_MAX_TEST 8 + +struct bnxt_test_info { + u8 offline_mask; + u16 timeout; + char string[BNXT_MAX_TEST][ETH_GSTRING_LEN]; +}; + #define BNXT_GRCPF_REG_WINDOW_BASE_OUT 0x400 #define BNXT_CAG_REG_LEGACY_INT_STATUS 0x4014 #define BNXT_CAG_REG_BASE 0x300000 @@ -989,6 +995,7 @@ struct bnxt { #define BNXT_FLAG_UDP_RSS_CAP 0x800 #define BNXT_FLAG_EEE_CAP 0x1000 #define BNXT_FLAG_NEW_RSS_CAP 0x2000 + #define BNXT_FLAG_WOL_CAP 0x4000 #define BNXT_FLAG_ROCEV1_CAP 0x8000 #define BNXT_FLAG_ROCEV2_CAP 0x10000 #define BNXT_FLAG_ROCE_CAP (BNXT_FLAG_ROCEV1_CAP | \ @@ -1180,6 +1187,12 @@ struct bnxt { u32 lpi_tmr_lo; u32 lpi_tmr_hi; + u8 num_tests; + struct bnxt_test_info *test_info; + + u8 wol_filter_id; + u8 wol; + u8 num_leds; struct bnxt_led_info leds[BNXT_MAX_LED]; @@ -1238,8 +1251,12 @@ void bnxt_tx_disable(struct bnxt *bp); void bnxt_tx_enable(struct bnxt *bp); int bnxt_hwrm_set_pause(struct bnxt *); int bnxt_hwrm_set_link_setting(struct bnxt *, bool, bool); +int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp); +int bnxt_hwrm_free_wol_fltr(struct bnxt *bp); int bnxt_hwrm_fw_set_time(struct bnxt *); int bnxt_open_nic(struct bnxt *, bool, bool); +int bnxt_half_open_nic(struct bnxt *bp); +void bnxt_half_close_nic(struct bnxt *bp); int bnxt_close_nic(struct bnxt *, bool, bool); int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, int tcs, int tx_xdp); int bnxt_setup_mq_tc(struct net_device *dev, u8 tc); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 6903a873f072..848ecf212b8f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -1,6 +1,7 @@ /* Broadcom NetXtreme-C/E network driver. * * Copyright (c) 2014-2016 Broadcom Corporation + * Copyright (c) 2016-2017 Broadcom Limited * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -17,6 +18,7 @@ #include <linux/firmware.h> #include "bnxt_hsi.h" #include "bnxt.h" +#include "bnxt_xdp.h" #include "bnxt_ethtool.h" #include "bnxt_nvm_defs.h" /* NVRAM content constant and structure defs */ #include "bnxt_fw_hdr.h" /* Firmware hdr constant and structure defs */ @@ -209,6 +211,10 @@ static int bnxt_get_sset_count(struct net_device *dev, int sset) return num_stats; } + case ETH_SS_TEST: + if (!bp->num_tests) + return -EOPNOTSUPP; + return bp->num_tests; default: return -EOPNOTSUPP; } @@ -306,6 +312,11 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf) } } break; + case ETH_SS_TEST: + if (bp->num_tests) + memcpy(buf, bp->test_info->string, + bp->num_tests * ETH_GSTRING_LEN); + break; default: netdev_err(bp->dev, "bnxt_get_strings invalid request %x\n", stringset); @@ -824,7 +835,7 @@ static void bnxt_get_drvinfo(struct net_device *dev, sizeof(info->fw_version)); strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info)); info->n_stats = BNXT_NUM_STATS * bp->cp_nr_rings; - info->testinfo_len = BNXT_NUM_TESTS(bp); + info->testinfo_len = bp->num_tests; /* TODO CHIMP_FW: eeprom dump details */ info->eedump_len = 0; /* TODO CHIMP FW: reg dump details */ @@ -832,6 +843,45 @@ static void bnxt_get_drvinfo(struct net_device *dev, kfree(pkglog); } +static void bnxt_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) +{ + struct bnxt *bp = netdev_priv(dev); + + wol->supported = 0; + wol->wolopts = 0; + memset(&wol->sopass, 0, sizeof(wol->sopass)); + if (bp->flags & BNXT_FLAG_WOL_CAP) { + wol->supported = WAKE_MAGIC; + if (bp->wol) + wol->wolopts = WAKE_MAGIC; + } +} + +static int bnxt_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) +{ + struct bnxt *bp = netdev_priv(dev); + + if (wol->wolopts & ~WAKE_MAGIC) + return -EINVAL; + + if (wol->wolopts & WAKE_MAGIC) { + if (!(bp->flags & BNXT_FLAG_WOL_CAP)) + return -EINVAL; + if (!bp->wol) { + if (bnxt_hwrm_alloc_wol_fltr(bp)) + return -EBUSY; + bp->wol = 1; + } + } else { + if (bp->wol) { + if (bnxt_hwrm_free_wol_fltr(bp)) + return -EBUSY; + bp->wol = 0; + } + } + return 0; +} + u32 _bnxt_fw_to_ethtool_adv_spds(u16 fw_speeds, u8 fw_pause) { u32 speed_mask = 0; @@ -2128,12 +2178,372 @@ static int bnxt_set_phys_id(struct net_device *dev, return rc; } +static int bnxt_hwrm_selftest_irq(struct bnxt *bp, u16 cmpl_ring) +{ + struct hwrm_selftest_irq_input req = {0}; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_IRQ, cmpl_ring, -1); + return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); +} + +static int bnxt_test_irq(struct bnxt *bp) +{ + int i; + + for (i = 0; i < bp->cp_nr_rings; i++) { + u16 cmpl_ring = bp->grp_info[i].cp_fw_ring_id; + int rc; + + rc = bnxt_hwrm_selftest_irq(bp, cmpl_ring); + if (rc) + return rc; + } + return 0; +} + +static int bnxt_hwrm_mac_loopback(struct bnxt *bp, bool enable) +{ + struct hwrm_port_mac_cfg_input req = {0}; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_MAC_CFG, -1, -1); + + req.enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_LPBK); + if (enable) + req.lpbk = PORT_MAC_CFG_REQ_LPBK_LOCAL; + else + req.lpbk = PORT_MAC_CFG_REQ_LPBK_NONE; + return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); +} + +static int bnxt_disable_an_for_lpbk(struct bnxt *bp, + struct hwrm_port_phy_cfg_input *req) +{ + struct bnxt_link_info *link_info = &bp->link_info; + u16 fw_advertising = link_info->advertising; + u16 fw_speed; + int rc; + + if (!link_info->autoneg) + return 0; + + fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB; + if (netif_carrier_ok(bp->dev)) + fw_speed = bp->link_info.link_speed; + else if (fw_advertising & BNXT_LINK_SPEED_MSK_10GB) + fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10GB; + else if (fw_advertising & BNXT_LINK_SPEED_MSK_25GB) + fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_25GB; + else if (fw_advertising & BNXT_LINK_SPEED_MSK_40GB) + fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB; + else if (fw_advertising & BNXT_LINK_SPEED_MSK_50GB) + fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB; + + req->force_link_speed = cpu_to_le16(fw_speed); + req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE | + PORT_PHY_CFG_REQ_FLAGS_RESET_PHY); + rc = hwrm_send_message(bp, req, sizeof(*req), HWRM_CMD_TIMEOUT); + req->flags = 0; + req->force_link_speed = cpu_to_le16(0); + return rc; +} + +static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable) +{ + struct hwrm_port_phy_cfg_input req = {0}; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_CFG, -1, -1); + + if (enable) { + bnxt_disable_an_for_lpbk(bp, &req); + req.lpbk = PORT_PHY_CFG_REQ_LPBK_LOCAL; + } else { + req.lpbk = PORT_PHY_CFG_REQ_LPBK_NONE; + } + req.enables = cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_LPBK); + return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); +} + +static int bnxt_rx_loopback(struct bnxt *bp, struct bnxt_napi *bnapi, + u32 raw_cons, int pkt_size) +{ + struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; + struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; + struct bnxt_sw_rx_bd *rx_buf; + struct rx_cmp *rxcmp; + u16 cp_cons, cons; + u8 *data; + u32 len; + int i; + + cp_cons = RING_CMP(raw_cons); + rxcmp = (struct rx_cmp *) + &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + cons = rxcmp->rx_cmp_opaque; + rx_buf = &rxr->rx_buf_ring[cons]; + data = rx_buf->data_ptr; + len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT; + if (len != pkt_size) + return -EIO; + i = ETH_ALEN; + if (!ether_addr_equal(data + i, bnapi->bp->dev->dev_addr)) + return -EIO; + i += ETH_ALEN; + for ( ; i < pkt_size; i++) { + if (data[i] != (u8)(i & 0xff)) + return -EIO; + } + return 0; +} + +static int bnxt_poll_loopback(struct bnxt *bp, int pkt_size) +{ + struct bnxt_napi *bnapi = bp->bnapi[0]; + struct bnxt_cp_ring_info *cpr; + struct tx_cmp *txcmp; + int rc = -EIO; + u32 raw_cons; + u32 cons; + int i; + + cpr = &bnapi->cp_ring; + raw_cons = cpr->cp_raw_cons; + for (i = 0; i < 200; i++) { + cons = RING_CMP(raw_cons); + txcmp = &cpr->cp_desc_ring[CP_RING(cons)][CP_IDX(cons)]; + + if (!TX_CMP_VALID(txcmp, raw_cons)) { + udelay(5); + continue; + } + + /* The valid test of the entry must be done first before + * reading any further. + */ + dma_rmb(); + if (TX_CMP_TYPE(txcmp) == CMP_TYPE_RX_L2_CMP) { + rc = bnxt_rx_loopback(bp, bnapi, raw_cons, pkt_size); + raw_cons = NEXT_RAW_CMP(raw_cons); + raw_cons = NEXT_RAW_CMP(raw_cons); + break; + } + raw_cons = NEXT_RAW_CMP(raw_cons); + } + cpr->cp_raw_cons = raw_cons; + return rc; +} + +static int bnxt_run_loopback(struct bnxt *bp) +{ + struct bnxt_tx_ring_info *txr = &bp->tx_ring[0]; + int pkt_size, i = 0; + struct sk_buff *skb; + dma_addr_t map; + u8 *data; + int rc; + + pkt_size = min(bp->dev->mtu + ETH_HLEN, bp->rx_copy_thresh); + skb = netdev_alloc_skb(bp->dev, pkt_size); + if (!skb) + return -ENOMEM; + data = skb_put(skb, pkt_size); + eth_broadcast_addr(data); + i += ETH_ALEN; + ether_addr_copy(&data[i], bp->dev->dev_addr); + i += ETH_ALEN; + for ( ; i < pkt_size; i++) + data[i] = (u8)(i & 0xff); + + map = dma_map_single(&bp->pdev->dev, skb->data, pkt_size, + PCI_DMA_TODEVICE); + if (dma_mapping_error(&bp->pdev->dev, map)) { + dev_kfree_skb(skb); + return -EIO; + } + bnxt_xmit_xdp(bp, txr, map, pkt_size, 0); + + /* Sync BD data before updating doorbell */ + wmb(); + + writel(DB_KEY_TX | txr->tx_prod, txr->tx_doorbell); + writel(DB_KEY_TX | txr->tx_prod, txr->tx_doorbell); + rc = bnxt_poll_loopback(bp, pkt_size); + + dma_unmap_single(&bp->pdev->dev, map, pkt_size, PCI_DMA_TODEVICE); + dev_kfree_skb(skb); + return rc; +} + +static int bnxt_run_fw_tests(struct bnxt *bp, u8 test_mask, u8 *test_results) +{ + struct hwrm_selftest_exec_output *resp = bp->hwrm_cmd_resp_addr; + struct hwrm_selftest_exec_input req = {0}; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_EXEC, -1, -1); + mutex_lock(&bp->hwrm_cmd_lock); + resp->test_success = 0; + req.flags = test_mask; + rc = _hwrm_send_message(bp, &req, sizeof(req), bp->test_info->timeout); + *test_results = resp->test_success; + mutex_unlock(&bp->hwrm_cmd_lock); + return rc; +} + +#define BNXT_DRV_TESTS 3 +#define BNXT_MACLPBK_TEST_IDX (bp->num_tests - BNXT_DRV_TESTS) +#define BNXT_PHYLPBK_TEST_IDX (BNXT_MACLPBK_TEST_IDX + 1) +#define BNXT_IRQ_TEST_IDX (BNXT_MACLPBK_TEST_IDX + 2) + +static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest, + u64 *buf) +{ + struct bnxt *bp = netdev_priv(dev); + bool offline = false; + u8 test_results = 0; + u8 test_mask = 0; + int rc, i; + + if (!bp->num_tests || !BNXT_SINGLE_PF(bp)) + return; + memset(buf, 0, sizeof(u64) * bp->num_tests); + if (!netif_running(dev)) { + etest->flags |= ETH_TEST_FL_FAILED; + return; + } + + if (etest->flags & ETH_TEST_FL_OFFLINE) { + if (bp->pf.active_vfs) { + etest->flags |= ETH_TEST_FL_FAILED; + netdev_warn(dev, "Offline tests cannot be run with active VFs\n"); + return; + } + offline = true; + } + + for (i = 0; i < bp->num_tests - BNXT_DRV_TESTS; i++) { + u8 bit_val = 1 << i; + + if (!(bp->test_info->offline_mask & bit_val)) + test_mask |= bit_val; + else if (offline) + test_mask |= bit_val; + } + if (!offline) { + bnxt_run_fw_tests(bp, test_mask, &test_results); + } else { + rc = bnxt_close_nic(bp, false, false); + if (rc) + return; + bnxt_run_fw_tests(bp, test_mask, &test_results); + + buf[BNXT_MACLPBK_TEST_IDX] = 1; + bnxt_hwrm_mac_loopback(bp, true); + msleep(250); + rc = bnxt_half_open_nic(bp); + if (rc) { + bnxt_hwrm_mac_loopback(bp, false); + etest->flags |= ETH_TEST_FL_FAILED; + return; + } + if (bnxt_run_loopback(bp)) + etest->flags |= ETH_TEST_FL_FAILED; + else + buf[BNXT_MACLPBK_TEST_IDX] = 0; + + bnxt_hwrm_mac_loopback(bp, false); + bnxt_hwrm_phy_loopback(bp, true); + msleep(1000); + if (bnxt_run_loopback(bp)) { + buf[BNXT_PHYLPBK_TEST_IDX] = 1; + etest->flags |= ETH_TEST_FL_FAILED; + } + bnxt_hwrm_phy_loopback(bp, false); + bnxt_half_close_nic(bp); + bnxt_open_nic(bp, false, true); + } + if (bnxt_test_irq(bp)) { + buf[BNXT_IRQ_TEST_IDX] = 1; + etest->flags |= ETH_TEST_FL_FAILED; + } + for (i = 0; i < bp->num_tests - BNXT_DRV_TESTS; i++) { + u8 bit_val = 1 << i; + + if ((test_mask & bit_val) && !(test_results & bit_val)) { + buf[i] = 1; + etest->flags |= ETH_TEST_FL_FAILED; + } + } +} + +void bnxt_ethtool_init(struct bnxt *bp) +{ + struct hwrm_selftest_qlist_output *resp = bp->hwrm_cmd_resp_addr; + struct hwrm_selftest_qlist_input req = {0}; + struct bnxt_test_info *test_info; + int i, rc; + + if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp)) + return; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_QLIST, -1, -1); + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + goto ethtool_init_exit; + + test_info = kzalloc(sizeof(*bp->test_info), GFP_KERNEL); + if (!test_info) + goto ethtool_init_exit; + + bp->test_info = test_info; + bp->num_tests = resp->num_tests + BNXT_DRV_TESTS; + if (bp->num_tests > BNXT_MAX_TEST) + bp->num_tests = BNXT_MAX_TEST; + + test_info->offline_mask = resp->offline_tests; + test_info->timeout = le16_to_cpu(resp->test_timeout); + if (!test_info->timeout) + test_info->timeout = HWRM_CMD_TIMEOUT; + for (i = 0; i < bp->num_tests; i++) { + char *str = test_info->string[i]; + char *fw_str = resp->test0_name + i * 32; + + if (i == BNXT_MACLPBK_TEST_IDX) { + strcpy(str, "Mac loopback test (offline)"); + } else if (i == BNXT_PHYLPBK_TEST_IDX) { + strcpy(str, "Phy loopback test (offline)"); + } else if (i == BNXT_IRQ_TEST_IDX) { + strcpy(str, "Interrupt_test (offline)"); + } else { + strlcpy(str, fw_str, ETH_GSTRING_LEN); + strncat(str, " test", ETH_GSTRING_LEN - strlen(str)); + if (test_info->offline_mask & (1 << i)) + strncat(str, " (offline)", + ETH_GSTRING_LEN - strlen(str)); + else + strncat(str, " (online)", + ETH_GSTRING_LEN - strlen(str)); + } + } + +ethtool_init_exit: + mutex_unlock(&bp->hwrm_cmd_lock); +} + +void bnxt_ethtool_free(struct bnxt *bp) +{ + kfree(bp->test_info); + bp->test_info = NULL; +} + const struct ethtool_ops bnxt_ethtool_ops = { .get_link_ksettings = bnxt_get_link_ksettings, .set_link_ksettings = bnxt_set_link_ksettings, .get_pauseparam = bnxt_get_pauseparam, .set_pauseparam = bnxt_set_pauseparam, .get_drvinfo = bnxt_get_drvinfo, + .get_wol = bnxt_get_wol, + .set_wol = bnxt_set_wol, .get_coalesce = bnxt_get_coalesce, .set_coalesce = bnxt_set_coalesce, .get_msglevel = bnxt_get_msglevel, @@ -2161,4 +2571,5 @@ const struct ethtool_ops bnxt_ethtool_ops = { .get_module_eeprom = bnxt_get_module_eeprom, .nway_reset = bnxt_nway_reset, .set_phys_id = bnxt_set_phys_id, + .self_test = bnxt_self_test, }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h index ed1e555292e9..f1bc90b6fb5b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h @@ -1,6 +1,7 @@ /* Broadcom NetXtreme-C/E network driver. * * Copyright (c) 2014-2016 Broadcom Corporation + * Copyright (c) 2016-2017 Broadcom Limited * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -38,5 +39,7 @@ extern const struct ethtool_ops bnxt_ethtool_ops; u32 _bnxt_fw_to_ethtool_adv_spds(u16, u8); u32 bnxt_fw_to_ethtool_speed(u16); u16 bnxt_get_fw_auto_link_speeds(u32); +void bnxt_ethtool_init(struct bnxt *bp); +void bnxt_ethtool_free(struct bnxt *bp); #endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 6e275c23d68b..7dc71bb95837 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -11,19 +11,21 @@ #ifndef BNXT_HSI_H #define BNXT_HSI_H -/* HSI and HWRM Specification 1.7.0 */ +/* HSI and HWRM Specification 1.7.6 */ #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 7 -#define HWRM_VERSION_UPDATE 0 +#define HWRM_VERSION_UPDATE 6 -#define HWRM_VERSION_STR "1.7.0" +#define HWRM_VERSION_RSVD 2 /* non-zero means beta version */ + +#define HWRM_VERSION_STR "1.7.6.2" /* * Following is the signature for HWRM message field that indicates not * applicable (All F's). Need to cast it the size of the field if needed. */ #define HWRM_NA_SIGNATURE ((__le32)(-1)) #define HWRM_MAX_REQ_LEN (128) /* hwrm_func_buf_rgtr */ -#define HWRM_MAX_RESP_LEN (176) /* hwrm_func_qstats */ +#define HWRM_MAX_RESP_LEN (248) /* hwrm_selftest_qlist */ #define HW_HASH_INDEX_SIZE 0x80 /* 7 bit indirection table index. */ #define HW_HASH_KEY_SIZE 40 #define HWRM_RESP_VALID_KEY 1 /* valid key for HWRM response */ @@ -571,9 +573,10 @@ struct hwrm_ver_get_output { __le16 max_req_win_len; __le16 max_resp_len; __le16 def_req_timeout; + u8 init_pending; + #define VER_GET_RESP_INIT_PENDING_DEV_NOT_RDY 0x1UL u8 unused_0; u8 unused_1; - u8 unused_2; u8 valid; }; @@ -809,6 +812,8 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_FLAGS_OOB_WOL_BMP_ENABLED 0x2UL #define FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED 0x4UL #define FUNC_QCFG_RESP_FLAGS_STD_TX_RING_MODE_ENABLED 0x8UL + #define FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED 0x10UL + #define FUNC_QCFG_RESP_FLAGS_MULTI_HOST 0x20UL u8 mac_address[6]; __le16 pci_id; __le16 alloc_rsscos_ctx; @@ -827,10 +832,12 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5 0x3UL #define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0 0x4UL #define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN 0xffUL - u8 unused_0; + u8 port_pf_cnt; + #define FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL 0x0UL __le16 dflt_vnic_id; - u8 unused_1; - u8 unused_2; + u8 host_cnt; + #define FUNC_QCFG_RESP_HOST_CNT_UNAVAIL 0x0UL + u8 unused_0; __le32 min_bw; #define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_MASK 0xfffffffUL #define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_SFT 0 @@ -867,12 +874,12 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_EVB_MODE_NO_EVB 0x0UL #define FUNC_QCFG_RESP_EVB_MODE_VEB 0x1UL #define FUNC_QCFG_RESP_EVB_MODE_VEPA 0x2UL - u8 unused_3; + u8 unused_1; __le16 alloc_vfs; __le32 alloc_mcast_filters; __le32 alloc_hw_ring_grps; __le16 alloc_sp_tx_rings; - u8 unused_4; + u8 unused_2; u8 valid; }; @@ -888,16 +895,13 @@ struct hwrm_func_cfg_input { u8 unused_0; u8 unused_1; __le32 flags; - #define FUNC_CFG_REQ_FLAGS_PROM_MODE 0x1UL - #define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK 0x2UL - #define FUNC_CFG_REQ_FLAGS_SRC_IP_ADDR_CHECK 0x4UL - #define FUNC_CFG_REQ_FLAGS_VLAN_PRI_MATCH 0x8UL - #define FUNC_CFG_REQ_FLAGS_DFLT_PRI_NOMATCH 0x10UL - #define FUNC_CFG_REQ_FLAGS_DISABLE_PAUSE 0x20UL - #define FUNC_CFG_REQ_FLAGS_DISABLE_STP 0x40UL - #define FUNC_CFG_REQ_FLAGS_DISABLE_LLDP 0x80UL - #define FUNC_CFG_REQ_FLAGS_DISABLE_PTPV2 0x100UL - #define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE 0x200UL + #define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE 0x1UL + #define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE 0x2UL + #define FUNC_CFG_REQ_FLAGS_RSVD_MASK 0x1fcUL + #define FUNC_CFG_REQ_FLAGS_RSVD_SFT 2 + #define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_ENABLE 0x200UL + #define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_DISABLE 0x400UL + #define FUNC_CFG_REQ_FLAGS_VIRT_MAC_PERSIST 0x800UL __le32 enables; #define FUNC_CFG_REQ_ENABLES_MTU 0x1UL #define FUNC_CFG_REQ_ENABLES_MRU 0x2UL @@ -1013,7 +1017,7 @@ struct hwrm_func_qstats_output { __le64 tx_ucast_pkts; __le64 tx_mcast_pkts; __le64 tx_bcast_pkts; - __le64 tx_err_pkts; + __le64 tx_discard_pkts; __le64 tx_drop_pkts; __le64 tx_ucast_bytes; __le64 tx_mcast_bytes; @@ -1021,7 +1025,7 @@ struct hwrm_func_qstats_output { __le64 rx_ucast_pkts; __le64 rx_mcast_pkts; __le64 rx_bcast_pkts; - __le64 rx_err_pkts; + __le64 rx_discard_pkts; __le64 rx_drop_pkts; __le64 rx_ucast_bytes; __le64 rx_mcast_bytes; @@ -4743,25 +4747,72 @@ struct hwrm_temp_monitor_query_output { u8 valid; }; -/* hwrm_nvm_read */ -/* Input (40 bytes) */ -struct hwrm_nvm_read_input { +/* hwrm_wol_filter_alloc */ +/* Input (64 bytes) */ +struct hwrm_wol_filter_alloc_input { __le16 req_type; __le16 cmpl_ring; __le16 seq_id; __le16 target_id; __le64 resp_addr; - __le64 host_dest_addr; - __le16 dir_idx; + __le32 flags; + __le32 enables; + #define WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS 0x1UL + #define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_OFFSET 0x2UL + #define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_SIZE 0x4UL + #define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_ADDR 0x8UL + #define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_ADDR 0x10UL + #define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_SIZE 0x20UL + __le16 port_id; + u8 wol_type; + #define WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT 0x0UL + #define WOL_FILTER_ALLOC_REQ_WOL_TYPE_BMP 0x1UL + #define WOL_FILTER_ALLOC_REQ_WOL_TYPE_INVALID 0xffUL u8 unused_0; - u8 unused_1; - __le32 offset; - __le32 len; + __le32 unused_1; + u8 mac_address[6]; + __le16 pattern_offset; + __le16 pattern_buf_size; + __le16 pattern_mask_size; __le32 unused_2; + __le64 pattern_buf_addr; + __le64 pattern_mask_addr; }; /* Output (16 bytes) */ -struct hwrm_nvm_read_output { +struct hwrm_wol_filter_alloc_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 wol_filter_id; + u8 unused_0; + __le16 unused_1; + u8 unused_2; + u8 unused_3; + u8 unused_4; + u8 valid; +}; + +/* hwrm_wol_filter_free */ +/* Input (32 bytes) */ +struct hwrm_wol_filter_free_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le32 flags; + #define WOL_FILTER_FREE_REQ_FLAGS_FREE_ALL_WOL_FILTERS 0x1UL + __le32 enables; + #define WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID 0x1UL + __le16 port_id; + u8 wol_filter_id; + u8 unused_0[5]; +}; + +/* Output (16 bytes) */ +struct hwrm_wol_filter_free_output { __le16 error_code; __le16 req_type; __le16 seq_id; @@ -4773,21 +4824,107 @@ struct hwrm_nvm_read_output { u8 valid; }; -/* hwrm_nvm_raw_dump */ -/* Input (32 bytes) */ -struct hwrm_nvm_raw_dump_input { +/* hwrm_wol_filter_qcfg */ +/* Input (56 bytes) */ +struct hwrm_wol_filter_qcfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 port_id; + __le16 handle; + __le32 unused_0; + __le64 pattern_buf_addr; + __le16 pattern_buf_size; + u8 unused_1; + u8 unused_2; + u8 unused_3[3]; + u8 unused_4; + __le64 pattern_mask_addr; + __le16 pattern_mask_size; + __le16 unused_5[3]; +}; + +/* Output (32 bytes) */ +struct hwrm_wol_filter_qcfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le16 next_handle; + u8 wol_filter_id; + u8 wol_type; + #define WOL_FILTER_QCFG_RESP_WOL_TYPE_MAGICPKT 0x0UL + #define WOL_FILTER_QCFG_RESP_WOL_TYPE_BMP 0x1UL + #define WOL_FILTER_QCFG_RESP_WOL_TYPE_INVALID 0xffUL + __le32 unused_0; + u8 mac_address[6]; + __le16 pattern_offset; + __le16 pattern_size; + __le16 pattern_mask_size; + u8 unused_1; + u8 unused_2; + u8 unused_3; + u8 valid; +}; + +/* hwrm_wol_reason_qcfg */ +/* Input (40 bytes) */ +struct hwrm_wol_reason_qcfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 port_id; + u8 unused_0; + u8 unused_1; + u8 unused_2[3]; + u8 unused_3; + __le64 wol_pkt_buf_addr; + __le16 wol_pkt_buf_size; + __le16 unused_4[3]; +}; + +/* Output (16 bytes) */ +struct hwrm_wol_reason_qcfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 wol_filter_id; + u8 wol_reason; + #define WOL_REASON_QCFG_RESP_WOL_REASON_MAGICPKT 0x0UL + #define WOL_REASON_QCFG_RESP_WOL_REASON_BMP 0x1UL + #define WOL_REASON_QCFG_RESP_WOL_REASON_INVALID 0xffUL + u8 wol_pkt_len; + u8 unused_0; + u8 unused_1; + u8 unused_2; + u8 unused_3; + u8 valid; +}; + +/* hwrm_nvm_read */ +/* Input (40 bytes) */ +struct hwrm_nvm_read_input { __le16 req_type; __le16 cmpl_ring; __le16 seq_id; __le16 target_id; __le64 resp_addr; __le64 host_dest_addr; + __le16 dir_idx; + u8 unused_0; + u8 unused_1; __le32 offset; __le32 len; + __le32 unused_2; }; /* Output (16 bytes) */ -struct hwrm_nvm_raw_dump_output { +struct hwrm_nvm_read_output { __le16 error_code; __le16 req_type; __le16 seq_id; @@ -4881,6 +5018,15 @@ struct hwrm_nvm_write_output { u8 valid; }; +/* Command specific Error Codes (8 bytes) */ +struct hwrm_nvm_write_cmd_err { + u8 code; + #define NVM_WRITE_CMD_ERR_CODE_UNKNOWN 0x0UL + #define NVM_WRITE_CMD_ERR_CODE_FRAG_ERR 0x1UL + #define NVM_WRITE_CMD_ERR_CODE_NO_SPACE 0x2UL + u8 unused_0[7]; +}; + /* hwrm_nvm_modify */ /* Input (40 bytes) */ struct hwrm_nvm_modify_input { @@ -5112,6 +5258,100 @@ struct hwrm_nvm_install_update_cmd_err { u8 unused_0[7]; }; +/* hwrm_selftest_qlist */ +/* Input (16 bytes) */ +struct hwrm_selftest_qlist_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; +}; + +/* Output (248 bytes) */ +struct hwrm_selftest_qlist_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 num_tests; + u8 available_tests; + #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_NVM_TEST 0x1UL + #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_LINK_TEST 0x2UL + #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_REGISTER_TEST 0x4UL + #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_MEMORY_TEST 0x8UL + u8 offline_tests; + #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_NVM_TEST 0x1UL + #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_LINK_TEST 0x2UL + #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_REGISTER_TEST 0x4UL + #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_MEMORY_TEST 0x8UL + u8 unused_0; + __le16 test_timeout; + u8 unused_1; + u8 unused_2; + char test0_name[32]; + char test1_name[32]; + char test2_name[32]; + char test3_name[32]; + char test4_name[32]; + char test5_name[32]; + char test6_name[32]; + char test7_name[32]; +}; + +/* hwrm_selftest_exec */ +/* Input (24 bytes) */ +struct hwrm_selftest_exec_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + u8 flags; + #define SELFTEST_EXEC_REQ_FLAGS_NVM_TEST 0x1UL + #define SELFTEST_EXEC_REQ_FLAGS_LINK_TEST 0x2UL + #define SELFTEST_EXEC_REQ_FLAGS_REGISTER_TEST 0x4UL + #define SELFTEST_EXEC_REQ_FLAGS_MEMORY_TEST 0x8UL + u8 unused_0[7]; +}; + +/* Output (16 bytes) */ +struct hwrm_selftest_exec_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 requested_tests; + #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_NVM_TEST 0x1UL + #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_LINK_TEST 0x2UL + #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_REGISTER_TEST 0x4UL + #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_MEMORY_TEST 0x8UL + u8 test_success; + #define SELFTEST_EXEC_RESP_TEST_SUCCESS_NVM_TEST 0x1UL + #define SELFTEST_EXEC_RESP_TEST_SUCCESS_LINK_TEST 0x2UL + #define SELFTEST_EXEC_RESP_TEST_SUCCESS_REGISTER_TEST 0x4UL + #define SELFTEST_EXEC_RESP_TEST_SUCCESS_MEMORY_TEST 0x8UL + __le16 unused_0[3]; +}; + +/* hwrm_selftest_irq */ +/* Input (16 bytes) */ +struct hwrm_selftest_irq_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; +}; + +/* Output (8 bytes) */ +struct hwrm_selftest_irq_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; +}; + /* Hardware Resource Manager Specification */ /* Input (16 bytes) */ struct input { @@ -5130,6 +5370,16 @@ struct output { __le16 resp_len; }; +/* Short Command Structure (16 bytes) */ +struct hwrm_short_input { + __le16 req_type; + __le16 signature; + #define SHORT_REQ_SIGNATURE_SHORT_CMD 0x4321UL + __le16 unused_0; + __le16 size; + __le64 req_addr; +}; + /* Command numbering (8 bytes) */ struct cmd_nums { __le16 req_type; @@ -5252,11 +5502,15 @@ struct cmd_nums { #define HWRM_CFA_FLOW_FLUSH (0x105UL) #define HWRM_CFA_FLOW_STATS (0x106UL) #define HWRM_CFA_FLOW_INFO (0x107UL) + #define HWRM_SELFTEST_QLIST (0x200UL) + #define HWRM_SELFTEST_EXEC (0x201UL) + #define HWRM_SELFTEST_IRQ (0x202UL) #define HWRM_DBG_READ_DIRECT (0xff10UL) #define HWRM_DBG_READ_INDIRECT (0xff11UL) #define HWRM_DBG_WRITE_DIRECT (0xff12UL) #define HWRM_DBG_WRITE_INDIRECT (0xff13UL) #define HWRM_DBG_DUMP (0xff14UL) + #define HWRM_NVM_FACTORY_DEFAULTS (0xffeeUL) #define HWRM_NVM_VALIDATE_OPTION (0xffefUL) #define HWRM_NVM_FLUSH (0xfff0UL) #define HWRM_NVM_GET_VARIABLE (0xfff1UL) @@ -5464,6 +5718,7 @@ struct hwrm_struct_hdr { #define STRUCT_HDR_STRUCT_ID_DCBX_FEATURE_STATE 0x422UL #define STRUCT_HDR_STRUCT_ID_LLDP_GENERIC 0x424UL #define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE 0x426UL + #define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE 0x1UL #define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION 0xaUL __le16 len; u8 version; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 0b8cd7443843..f89353175e6b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -1,6 +1,7 @@ /* Broadcom NetXtreme-C/E network driver. * * Copyright (c) 2014-2016 Broadcom Corporation + * Copyright (c) 2016-2017 Broadcom Limited * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -84,6 +85,9 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting) u32 func_flags; int rc; + if (bp->hwrm_spec_code < 0x10701) + return -ENOTSUPP; + rc = bnxt_vf_ndo_prep(bp, vf_id); if (rc) return rc; @@ -96,9 +100,9 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting) func_flags = vf->func_flags; if (setting) - func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK; + func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE; else - func_flags &= ~FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK; + func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE; /*TODO: if the driver supports VLAN filter on guest VLAN, * the spoof check should also include vlan anti-spoofing */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h index 1ab72e4820af..dbc8d977fc5a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h @@ -1,6 +1,7 @@ /* Broadcom NetXtreme-C/E network driver. * * Copyright (c) 2014-2016 Broadcom Corporation + * Copyright (c) 2016-2017 Broadcom Limited * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 899c30fb5188..9dae32756767 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -19,11 +19,10 @@ #include "bnxt.h" #include "bnxt_xdp.h" -static void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr, - dma_addr_t mapping, u32 len, u16 rx_prod) +void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr, + dma_addr_t mapping, u32 len, u16 rx_prod) { struct bnxt_sw_tx_bd *tx_buf; - struct tx_bd_ext *txbd1; struct tx_bd *txbd; u32 flags; u16 prod; @@ -33,23 +32,13 @@ static void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr, tx_buf->rx_prod = rx_prod; txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)]; - flags = (len << TX_BD_LEN_SHIFT) | TX_BD_TYPE_LONG_TX_BD | - (2 << TX_BD_FLAGS_BD_CNT_SHIFT) | TX_BD_FLAGS_COAL_NOW | + flags = (len << TX_BD_LEN_SHIFT) | (1 << TX_BD_FLAGS_BD_CNT_SHIFT) | TX_BD_FLAGS_PACKET_END | bnxt_lhint_arr[len >> 9]; txbd->tx_bd_len_flags_type = cpu_to_le32(flags); txbd->tx_bd_opaque = prod; txbd->tx_bd_haddr = cpu_to_le64(mapping); prod = NEXT_TX(prod); - txbd1 = (struct tx_bd_ext *) - &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)]; - - txbd1->tx_bd_hsize_lflags = cpu_to_le32(0); - txbd1->tx_bd_mss = cpu_to_le32(0); - txbd1->tx_bd_cfa_action = cpu_to_le32(0); - txbd1->tx_bd_cfa_meta = cpu_to_le32(0); - - prod = NEXT_TX(prod); txr->tx_prod = prod; } @@ -66,7 +55,6 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) for (i = 0; i < nr_pkts; i++) { last_tx_cons = tx_cons; tx_cons = NEXT_TX(tx_cons); - tx_cons = NEXT_TX(tx_cons); } txr->tx_cons = tx_cons; if (bnxt_tx_avail(bp, txr) == bp->tx_ring_size) { @@ -133,7 +121,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, return false; case XDP_TX: - if (tx_avail < 2) { + if (tx_avail < 1) { trace_xdp_exception(bp->dev, xdp_prog, act); bnxt_reuse_rx_data(rxr, cons, page); return true; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h index b529f2c5355b..12a5ad66b564 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h @@ -10,6 +10,8 @@ #ifndef BNXT_XDP_H #define BNXT_XDP_H +void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr, + dma_addr_t mapping, u32 len, u16 rx_prod); void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts); bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, struct page *page, u8 **data_ptr, unsigned int *len, diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c index 9e59663a6ead..0f6811860ad5 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c +++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c @@ -1930,13 +1930,13 @@ static void bfa_ioc_send_enable(struct bfa_ioc *ioc) { struct bfi_ioc_ctrl_req enable_req; - struct timeval tv; bfi_h2i_set(enable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_ENABLE_REQ, bfa_ioc_portid(ioc)); enable_req.clscode = htons(ioc->clscode); - do_gettimeofday(&tv); - enable_req.tv_sec = ntohl(tv.tv_sec); + enable_req.rsvd = htons(0); + /* overflow in 2106 */ + enable_req.tv_sec = ntohl(ktime_get_real_seconds()); bfa_ioc_mbox_send(ioc, &enable_req, sizeof(struct bfi_ioc_ctrl_req)); } @@ -1947,6 +1947,10 @@ bfa_ioc_send_disable(struct bfa_ioc *ioc) bfi_h2i_set(disable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_DISABLE_REQ, bfa_ioc_portid(ioc)); + disable_req.clscode = htons(ioc->clscode); + disable_req.rsvd = htons(0); + /* overflow in 2106 */ + disable_req.tv_sec = ntohl(ktime_get_real_seconds()); bfa_ioc_mbox_send(ioc, &disable_req, sizeof(struct bfi_ioc_ctrl_req)); } diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 30606b11b128..5cbd1e7a926a 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -684,8 +684,8 @@ static void macb_tx_error_task(struct work_struct *work) netdev_vdbg(bp->dev, "txerr skb %u (data %p) TX complete\n", macb_tx_ring_wrap(bp, tail), skb->data); - bp->stats.tx_packets++; - bp->stats.tx_bytes += skb->len; + bp->dev->stats.tx_packets++; + bp->dev->stats.tx_bytes += skb->len; } } else { /* "Buffers exhausted mid-frame" errors may only happen @@ -778,8 +778,8 @@ static void macb_tx_interrupt(struct macb_queue *queue) netdev_vdbg(bp->dev, "skb %u (data %p) TX complete\n", macb_tx_ring_wrap(bp, tail), skb->data); - bp->stats.tx_packets++; - bp->stats.tx_bytes += skb->len; + bp->dev->stats.tx_packets++; + bp->dev->stats.tx_bytes += skb->len; } /* Now we can safely release resources */ @@ -911,14 +911,14 @@ static int gem_rx(struct macb *bp, int budget) if (!(ctrl & MACB_BIT(RX_SOF) && ctrl & MACB_BIT(RX_EOF))) { netdev_err(bp->dev, "not whole frame pointed by descriptor\n"); - bp->stats.rx_dropped++; + bp->dev->stats.rx_dropped++; break; } skb = bp->rx_skbuff[entry]; if (unlikely(!skb)) { netdev_err(bp->dev, "inconsistent Rx descriptor chain\n"); - bp->stats.rx_dropped++; + bp->dev->stats.rx_dropped++; break; } /* now everything is ready for receiving packet */ @@ -938,8 +938,8 @@ static int gem_rx(struct macb *bp, int budget) GEM_BFEXT(RX_CSUM, ctrl) & GEM_RX_CSUM_CHECKED_MASK) skb->ip_summed = CHECKSUM_UNNECESSARY; - bp->stats.rx_packets++; - bp->stats.rx_bytes += skb->len; + bp->dev->stats.rx_packets++; + bp->dev->stats.rx_bytes += skb->len; #if defined(DEBUG) && defined(VERBOSE_DEBUG) netdev_vdbg(bp->dev, "received skb of length %u, csum: %08x\n", @@ -984,7 +984,7 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag, */ skb = netdev_alloc_skb(bp->dev, len + NET_IP_ALIGN); if (!skb) { - bp->stats.rx_dropped++; + bp->dev->stats.rx_dropped++; for (frag = first_frag; ; frag++) { desc = macb_rx_desc(bp, frag); desc->addr &= ~MACB_BIT(RX_USED); @@ -1030,8 +1030,8 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag, __skb_pull(skb, NET_IP_ALIGN); skb->protocol = eth_type_trans(skb, bp->dev); - bp->stats.rx_packets++; - bp->stats.rx_bytes += skb->len; + bp->dev->stats.rx_packets++; + bp->dev->stats.rx_bytes += skb->len; netdev_vdbg(bp->dev, "received skb of length %u, csum: %08x\n", skb->len, skb->csum); netif_receive_skb(skb); @@ -2210,7 +2210,7 @@ static void gem_update_stats(struct macb *bp) static struct net_device_stats *gem_get_stats(struct macb *bp) { struct gem_stats *hwstat = &bp->hw_stats.gem; - struct net_device_stats *nstat = &bp->stats; + struct net_device_stats *nstat = &bp->dev->stats; gem_update_stats(bp); @@ -2281,7 +2281,7 @@ static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p) static struct net_device_stats *macb_get_stats(struct net_device *dev) { struct macb *bp = netdev_priv(dev); - struct net_device_stats *nstat = &bp->stats; + struct net_device_stats *nstat = &bp->dev->stats; struct macb_stats *hwstat = &bp->hw_stats.macb; if (macb_is_gem(bp)) @@ -2993,15 +2993,15 @@ static void at91ether_rx(struct net_device *dev) memcpy(skb_put(skb, pktlen), p_recv, pktlen); skb->protocol = eth_type_trans(skb, dev); - lp->stats.rx_packets++; - lp->stats.rx_bytes += pktlen; + dev->stats.rx_packets++; + dev->stats.rx_bytes += pktlen; netif_rx(skb); } else { - lp->stats.rx_dropped++; + dev->stats.rx_dropped++; } if (desc->ctrl & MACB_BIT(RX_MHASH_MATCH)) - lp->stats.multicast++; + dev->stats.multicast++; /* reset ownership bit */ desc->addr &= ~MACB_BIT(RX_USED); @@ -3036,15 +3036,15 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id) if (intstatus & MACB_BIT(TCOMP)) { /* The TCOM bit is set even if the transmission failed */ if (intstatus & (MACB_BIT(ISR_TUND) | MACB_BIT(ISR_RLE))) - lp->stats.tx_errors++; + dev->stats.tx_errors++; if (lp->skb) { dev_kfree_skb_irq(lp->skb); lp->skb = NULL; dma_unmap_single(NULL, lp->skb_physaddr, lp->skb_length, DMA_TO_DEVICE); - lp->stats.tx_packets++; - lp->stats.tx_bytes += lp->skb_length; + dev->stats.tx_packets++; + dev->stats.tx_bytes += lp->skb_length; } netif_wake_queue(dev); } diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 234a49eaccfd..ec037b0fa2a4 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -919,7 +919,6 @@ struct macb { struct clk *rx_clk; struct net_device *dev; struct napi_struct napi; - struct net_device_stats stats; union { struct macb_stats macb; struct gem_stats gem; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index 08676df6cef0..796c2cbc11f6 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -127,6 +127,17 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr) struct octeon_device *oct = lio->oct_dev; u8 *mac; + if (nctrl->completion && nctrl->response_code) { + /* Signal whoever is interested that the response code from the + * firmware has arrived. + */ + WRITE_ONCE(*nctrl->response_code, nctrl->status); + complete(nctrl->completion); + } + + if (nctrl->status) + return; + switch (nctrl->ncmd.s.cmd) { case OCTNET_CMD_CHANGE_DEVFLAGS: case OCTNET_CMD_SET_MULTI_LIST: diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index fac02ed2c449..579dc7336f58 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -1323,8 +1323,6 @@ static void octnet_intrmod_callback(struct octeon_device *oct_dev, ctx->status = status; - oct_dev = lio_get_device(ctx->octeon_id); - WRITE_ONCE(ctx->cond, 1); /* This barrier is required to be sure that the response has been @@ -1359,7 +1357,7 @@ static int octnet_get_intrmod_cfg(struct lio *lio, memset(resp, 0, sizeof(struct oct_intrmod_resp)); ctx = (struct oct_intrmod_context *)sc->ctxptr; - memset(resp, 0, sizeof(struct oct_intrmod_context)); + memset(ctx, 0, sizeof(struct oct_intrmod_context)); WRITE_ONCE(ctx->cond, 0); ctx->octeon_id = lio_get_device_id(oct_dev); init_waitqueue_head(&ctx->wc); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index a8426d3d05d0..927617cbf6a9 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -173,6 +173,8 @@ static int liquidio_stop(struct net_device *netdev); static void liquidio_remove(struct pci_dev *pdev); static int liquidio_probe(struct pci_dev *pdev, const struct pci_device_id *ent); +static int liquidio_set_vf_link_state(struct net_device *netdev, int vfidx, + int linkstate); static struct handshake handshake[MAX_OCTEON_DEVICES]; static struct completion first_stage; @@ -1199,97 +1201,122 @@ static int octeon_setup_interrupt(struct octeon_device *oct) return 0; } +static struct octeon_device *get_other_octeon_device(struct octeon_device *oct) +{ + struct octeon_device *other_oct; + + other_oct = lio_get_device(oct->octeon_id + 1); + + if (other_oct && other_oct->pci_dev) { + int oct_busnum, other_oct_busnum; + + oct_busnum = oct->pci_dev->bus->number; + other_oct_busnum = other_oct->pci_dev->bus->number; + + if (oct_busnum == other_oct_busnum) { + int oct_slot, other_oct_slot; + + oct_slot = PCI_SLOT(oct->pci_dev->devfn); + other_oct_slot = PCI_SLOT(other_oct->pci_dev->devfn); + + if (oct_slot == other_oct_slot) + return other_oct; + } + } + + return NULL; +} + +static void disable_all_vf_links(struct octeon_device *oct) +{ + struct net_device *netdev; + int max_vfs, vf, i; + + if (!oct) + return; + + max_vfs = oct->sriov_info.max_vfs; + + for (i = 0; i < oct->ifcount; i++) { + netdev = oct->props[i].netdev; + if (!netdev) + continue; + + for (vf = 0; vf < max_vfs; vf++) + liquidio_set_vf_link_state(netdev, vf, + IFLA_VF_LINK_STATE_DISABLE); + } +} + static int liquidio_watchdog(void *param) { - u64 wdog; - u16 mask_of_stuck_cores = 0; - u16 mask_of_crashed_cores = 0; - int core_num; - u8 core_is_stuck[LIO_MAX_CORES]; - u8 core_crashed[LIO_MAX_CORES]; + bool err_msg_was_printed[LIO_MAX_CORES]; + u16 mask_of_crashed_or_stuck_cores = 0; + bool all_vf_links_are_disabled = false; struct octeon_device *oct = param; + struct octeon_device *other_oct; +#ifdef CONFIG_MODULE_UNLOAD + long refcount, vfs_referencing_pf; + u64 vfs_mask1, vfs_mask2; +#endif + int core; - memset(core_is_stuck, 0, sizeof(core_is_stuck)); - memset(core_crashed, 0, sizeof(core_crashed)); + memset(err_msg_was_printed, 0, sizeof(err_msg_was_printed)); while (!kthread_should_stop()) { - mask_of_crashed_cores = + /* sleep for a couple of seconds so that we don't hog the CPU */ + set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(msecs_to_jiffies(2000)); + + mask_of_crashed_or_stuck_cores = (u16)octeon_read_csr64(oct, CN23XX_SLI_SCRATCH2); - for (core_num = 0; core_num < LIO_MAX_CORES; core_num++) { - if (!core_is_stuck[core_num]) { - wdog = lio_pci_readq(oct, CIU3_WDOG(core_num)); - - /* look at watchdog state field */ - wdog &= CIU3_WDOG_MASK; - if (wdog) { - /* this watchdog timer has expired */ - core_is_stuck[core_num] = - LIO_MONITOR_WDOG_EXPIRE; - mask_of_stuck_cores |= (1 << core_num); - } - } + if (!mask_of_crashed_or_stuck_cores) + continue; - if (!core_crashed[core_num]) - core_crashed[core_num] = - (mask_of_crashed_cores >> core_num) & 1; - } + WRITE_ONCE(oct->cores_crashed, true); + other_oct = get_other_octeon_device(oct); + if (other_oct) + WRITE_ONCE(other_oct->cores_crashed, true); - if (mask_of_stuck_cores) { - for (core_num = 0; core_num < LIO_MAX_CORES; - core_num++) { - if (core_is_stuck[core_num] == 1) { - dev_err(&oct->pci_dev->dev, - "ERROR: Octeon core %d is stuck!\n", - core_num); - /* 2 means we have printk'd an error - * so no need to repeat the same printk - */ - core_is_stuck[core_num] = - LIO_MONITOR_CORE_STUCK_MSGD; - } - } - } + for (core = 0; core < LIO_MAX_CORES; core++) { + bool core_crashed_or_got_stuck; - if (mask_of_crashed_cores) { - for (core_num = 0; core_num < LIO_MAX_CORES; - core_num++) { - if (core_crashed[core_num] == 1) { - dev_err(&oct->pci_dev->dev, - "ERROR: Octeon core %d crashed! See oct-fwdump for details.\n", - core_num); - /* 2 means we have printk'd an error - * so no need to repeat the same printk - */ - core_crashed[core_num] = - LIO_MONITOR_CORE_STUCK_MSGD; - } + core_crashed_or_got_stuck = + (mask_of_crashed_or_stuck_cores + >> core) & 1; + + if (core_crashed_or_got_stuck && + !err_msg_was_printed[core]) { + dev_err(&oct->pci_dev->dev, + "ERROR: Octeon core %d crashed or got stuck! See oct-fwdump for details.\n", + core); + err_msg_was_printed[core] = true; } } + + if (all_vf_links_are_disabled) + continue; + + disable_all_vf_links(oct); + disable_all_vf_links(other_oct); + all_vf_links_are_disabled = true; + #ifdef CONFIG_MODULE_UNLOAD - if (mask_of_stuck_cores || mask_of_crashed_cores) { - /* make module refcount=0 so that rmmod will work */ - long refcount; + vfs_mask1 = READ_ONCE(oct->sriov_info.vf_drv_loaded_mask); + vfs_mask2 = READ_ONCE(other_oct->sriov_info.vf_drv_loaded_mask); - refcount = module_refcount(THIS_MODULE); + vfs_referencing_pf = hweight64(vfs_mask1); + vfs_referencing_pf += hweight64(vfs_mask2); - while (refcount > 0) { + refcount = module_refcount(THIS_MODULE); + if (refcount >= vfs_referencing_pf) { + while (vfs_referencing_pf) { module_put(THIS_MODULE); - refcount = module_refcount(THIS_MODULE); - } - - /* compensate for and withstand an unlikely (but still - * possible) race condition - */ - while (refcount < 0) { - try_module_get(THIS_MODULE); - refcount = module_refcount(THIS_MODULE); + vfs_referencing_pf--; } } #endif - /* sleep for two seconds */ - set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(2 * HZ); } return 0; @@ -3472,6 +3499,8 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command, struct octnic_ctrl_pkt nctrl; int ret = 0; + memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); + nctrl.ncmd.u64 = 0; nctrl.ncmd.s.cmd = command; nctrl.ncmd.s.param1 = rx_cmd; @@ -3505,6 +3534,8 @@ static int liquidio_vxlan_port_command(struct net_device *netdev, int command, struct octnic_ctrl_pkt nctrl; int ret = 0; + memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); + nctrl.ncmd.u64 = 0; nctrl.ncmd.s.cmd = command; nctrl.ncmd.s.more = vxlan_cmd_bit; @@ -4406,6 +4437,7 @@ octeon_recv_vf_drv_notice(struct octeon_recv_info *recv_info, void *buf) struct octeon_device *oct = (struct octeon_device *)buf; struct octeon_recv_pkt *recv_pkt = recv_info->recv_pkt; int i, notice, vf_idx; + bool cores_crashed; u64 *data, vf_num; notice = recv_pkt->rh.r.ossp; @@ -4416,19 +4448,23 @@ octeon_recv_vf_drv_notice(struct octeon_recv_info *recv_info, void *buf) octeon_swap_8B_data(&vf_num, 1); vf_idx = (int)vf_num - 1; + cores_crashed = READ_ONCE(oct->cores_crashed); + if (notice == VF_DRV_LOADED) { if (!(oct->sriov_info.vf_drv_loaded_mask & BIT_ULL(vf_idx))) { oct->sriov_info.vf_drv_loaded_mask |= BIT_ULL(vf_idx); dev_info(&oct->pci_dev->dev, "driver for VF%d was loaded\n", vf_idx); - try_module_get(THIS_MODULE); + if (!cores_crashed) + try_module_get(THIS_MODULE); } } else if (notice == VF_DRV_REMOVED) { if (oct->sriov_info.vf_drv_loaded_mask & BIT_ULL(vf_idx)) { oct->sriov_info.vf_drv_loaded_mask &= ~BIT_ULL(vf_idx); dev_info(&oct->pci_dev->dev, "driver for VF%d was removed\n", vf_idx); - module_put(THIS_MODULE); + if (!cores_crashed) + module_put(THIS_MODULE); } } else if (notice == VF_DRV_MACADDR_CHANGED) { u8 *b = (u8 *)&data[1]; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index 174d748b5928..34c77821fad9 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -2484,6 +2484,8 @@ liquidio_vlan_rx_add_vid(struct net_device *netdev, struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; struct octnic_ctrl_pkt nctrl; + struct completion compl; + u16 response_code; int ret = 0; memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); @@ -2495,14 +2497,25 @@ liquidio_vlan_rx_add_vid(struct net_device *netdev, nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; + init_completion(&compl); + nctrl.completion = &compl; + nctrl.response_code = &response_code; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); if (ret < 0) { dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n", ret); + return -EIO; } - return ret; + if (!wait_for_completion_timeout(&compl, + msecs_to_jiffies(nctrl.wait_time))) + return -EPERM; + + if (READ_ONCE(response_code)) + return -EPERM; + + return 0; } static int @@ -2547,6 +2560,8 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command, struct octnic_ctrl_pkt nctrl; int ret = 0; + memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); + nctrl.ncmd.u64 = 0; nctrl.ncmd.s.cmd = command; nctrl.ncmd.s.param1 = rx_cmd; @@ -2579,6 +2594,8 @@ static int liquidio_vxlan_port_command(struct net_device *netdev, int command, struct octnic_ctrl_pkt nctrl; int ret = 0; + memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); + nctrl.ncmd.u64 = 0; nctrl.ncmd.s.cmd = command; nctrl.ncmd.s.more = vxlan_cmd_bit; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h index dab35bfa4612..92f67de111aa 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h @@ -542,6 +542,8 @@ struct octeon_device { u32 rx_coalesce_usecs; u32 rx_max_coalesced_frames; u32 tx_max_coalesced_frames; + + bool cores_crashed; }; #define OCT_DRV_ONLINE 1 diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h index 454ec0ca56ab..bf483932ff25 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h @@ -141,10 +141,6 @@ struct lio { #define LIO_SIZE (sizeof(struct lio)) #define GET_LIO(netdev) ((struct lio *)netdev_priv(netdev)) -#define CIU3_WDOG(c) (0x1010000020000ULL + ((c) << 3)) -#define CIU3_WDOG_MASK 12ULL -#define LIO_MONITOR_WDOG_EXPIRE 1 -#define LIO_MONITOR_CORE_STUCK_MSGD 2 #define LIO_MAX_CORES 12 /** diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c index 0243be8dd56f..b457cf23fce6 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c @@ -100,14 +100,16 @@ static void octnet_link_ctrl_callback(struct octeon_device *oct, nctrl = (struct octnic_ctrl_pkt *)sc->ctxptr; - /* Call the callback function if status is OK. - * Status is OK only if a response was expected and core returned - * success. + /* Call the callback function if status is zero (meaning OK) or status + * contains a firmware status code bigger than zero (meaning the + * firmware is reporting an error). * If no response was expected, status is OK if the command was posted * successfully. */ - if (!status && nctrl->cb_fn) + if ((!status || status > FIRMWARE_STATUS_CODE(0)) && nctrl->cb_fn) { + nctrl->status = status; nctrl->cb_fn(nctrl); + } octeon_free_soft_command(oct, sc); } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h index 0c7a5c9b2932..6480ef863441 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h @@ -62,6 +62,10 @@ struct octnic_ctrl_pkt { /** Callback function called when the command has been fetched */ octnic_ctrl_pkt_cb_fn_t cb_fn; + + u32 status; + u16 *response_code; + struct completion *completion; }; #define MAX_UDD_SIZE(nctrl) (sizeof((nctrl)->udd)) diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index 2269ff562d95..6fb44218bf55 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -319,9 +319,7 @@ struct nicvf { struct bgx_stats bgx_stats; /* MSI-X */ - bool msix_enabled; u8 num_vec; - struct msix_entry msix_entries[NIC_VF_MSIX_VECTORS]; char irq_name[NIC_VF_MSIX_VECTORS][IFNAMSIZ + 15]; bool irq_allocated[NIC_VF_MSIX_VECTORS]; cpumask_var_t affinity_mask[NIC_VF_MSIX_VECTORS]; diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 767234e2e8f9..fb770b0182d3 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -65,9 +65,7 @@ struct nicpf { bool mbx_lock[MAX_NUM_VFS_SUPPORTED]; /* MSI-X */ - bool msix_enabled; u8 num_vec; - struct msix_entry *msix_entries; bool irq_allocated[NIC_PF_MSIX_VECTORS]; char irq_name[NIC_PF_MSIX_VECTORS][20]; }; @@ -1088,7 +1086,7 @@ static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq) u64 intr; u8 vf, vf_per_mbx_reg = 64; - if (irq == nic->msix_entries[NIC_PF_INTR_ID_MBOX0].vector) + if (irq == pci_irq_vector(nic->pdev, NIC_PF_INTR_ID_MBOX0)) mbx = 0; else mbx = 1; @@ -1107,51 +1105,13 @@ static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq) return IRQ_HANDLED; } -static int nic_enable_msix(struct nicpf *nic) -{ - int i, ret; - - nic->num_vec = pci_msix_vec_count(nic->pdev); - - nic->msix_entries = kmalloc_array(nic->num_vec, - sizeof(struct msix_entry), - GFP_KERNEL); - if (!nic->msix_entries) - return -ENOMEM; - - for (i = 0; i < nic->num_vec; i++) - nic->msix_entries[i].entry = i; - - ret = pci_enable_msix(nic->pdev, nic->msix_entries, nic->num_vec); - if (ret) { - dev_err(&nic->pdev->dev, - "Request for #%d msix vectors failed, returned %d\n", - nic->num_vec, ret); - kfree(nic->msix_entries); - return ret; - } - - nic->msix_enabled = 1; - return 0; -} - -static void nic_disable_msix(struct nicpf *nic) -{ - if (nic->msix_enabled) { - pci_disable_msix(nic->pdev); - kfree(nic->msix_entries); - nic->msix_enabled = 0; - nic->num_vec = 0; - } -} - static void nic_free_all_interrupts(struct nicpf *nic) { int irq; for (irq = 0; irq < nic->num_vec; irq++) { if (nic->irq_allocated[irq]) - free_irq(nic->msix_entries[irq].vector, nic); + free_irq(pci_irq_vector(nic->pdev, irq), nic); nic->irq_allocated[irq] = false; } } @@ -1159,18 +1119,24 @@ static void nic_free_all_interrupts(struct nicpf *nic) static int nic_register_interrupts(struct nicpf *nic) { int i, ret; + nic->num_vec = pci_msix_vec_count(nic->pdev); /* Enable MSI-X */ - ret = nic_enable_msix(nic); - if (ret) - return ret; + ret = pci_alloc_irq_vectors(nic->pdev, nic->num_vec, nic->num_vec, + PCI_IRQ_MSIX); + if (ret < 0) { + dev_err(&nic->pdev->dev, + "Request for #%d msix vectors failed, returned %d\n", + nic->num_vec, ret); + return 1; + } /* Register mailbox interrupt handler */ for (i = NIC_PF_INTR_ID_MBOX0; i < nic->num_vec; i++) { sprintf(nic->irq_name[i], "NICPF Mbox%d", (i - NIC_PF_INTR_ID_MBOX0)); - ret = request_irq(nic->msix_entries[i].vector, + ret = request_irq(pci_irq_vector(nic->pdev, i), nic_mbx_intr_handler, 0, nic->irq_name[i], nic); if (ret) @@ -1186,14 +1152,16 @@ static int nic_register_interrupts(struct nicpf *nic) fail: dev_err(&nic->pdev->dev, "Request irq failed\n"); nic_free_all_interrupts(nic); - nic_disable_msix(nic); + pci_free_irq_vectors(nic->pdev); + nic->num_vec = 0; return ret; } static void nic_unregister_interrupts(struct nicpf *nic) { nic_free_all_interrupts(nic); - nic_disable_msix(nic); + pci_free_irq_vectors(nic->pdev); + nic->num_vec = 0; } static int nic_num_sqs_en(struct nicpf *nic, int vf_en) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 24017588f531..81a2fcb3cb1b 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -882,38 +882,9 @@ static irqreturn_t nicvf_qs_err_intr_handler(int irq, void *nicvf_irq) return IRQ_HANDLED; } -static int nicvf_enable_msix(struct nicvf *nic) -{ - int ret, vec; - - nic->num_vec = NIC_VF_MSIX_VECTORS; - - for (vec = 0; vec < nic->num_vec; vec++) - nic->msix_entries[vec].entry = vec; - - ret = pci_enable_msix(nic->pdev, nic->msix_entries, nic->num_vec); - if (ret) { - netdev_err(nic->netdev, - "Req for #%d msix vectors failed\n", nic->num_vec); - return 0; - } - nic->msix_enabled = 1; - return 1; -} - -static void nicvf_disable_msix(struct nicvf *nic) -{ - if (nic->msix_enabled) { - pci_disable_msix(nic->pdev); - nic->msix_enabled = 0; - nic->num_vec = 0; - } -} - static void nicvf_set_irq_affinity(struct nicvf *nic) { int vec, cpu; - int irqnum; for (vec = 0; vec < nic->num_vec; vec++) { if (!nic->irq_allocated[vec]) @@ -930,15 +901,14 @@ static void nicvf_set_irq_affinity(struct nicvf *nic) cpumask_set_cpu(cpumask_local_spread(cpu, nic->node), nic->affinity_mask[vec]); - irqnum = nic->msix_entries[vec].vector; - irq_set_affinity_hint(irqnum, nic->affinity_mask[vec]); + irq_set_affinity_hint(pci_irq_vector(nic->pdev, vec), + nic->affinity_mask[vec]); } } static int nicvf_register_interrupts(struct nicvf *nic) { int irq, ret = 0; - int vector; for_each_cq_irq(irq) sprintf(nic->irq_name[irq], "%s-rxtx-%d", @@ -957,8 +927,8 @@ static int nicvf_register_interrupts(struct nicvf *nic) /* Register CQ interrupts */ for (irq = 0; irq < nic->qs->cq_cnt; irq++) { - vector = nic->msix_entries[irq].vector; - ret = request_irq(vector, nicvf_intr_handler, + ret = request_irq(pci_irq_vector(nic->pdev, irq), + nicvf_intr_handler, 0, nic->irq_name[irq], nic->napi[irq]); if (ret) goto err; @@ -968,8 +938,8 @@ static int nicvf_register_interrupts(struct nicvf *nic) /* Register RBDR interrupt */ for (irq = NICVF_INTR_ID_RBDR; irq < (NICVF_INTR_ID_RBDR + nic->qs->rbdr_cnt); irq++) { - vector = nic->msix_entries[irq].vector; - ret = request_irq(vector, nicvf_rbdr_intr_handler, + ret = request_irq(pci_irq_vector(nic->pdev, irq), + nicvf_rbdr_intr_handler, 0, nic->irq_name[irq], nic); if (ret) goto err; @@ -981,7 +951,7 @@ static int nicvf_register_interrupts(struct nicvf *nic) nic->pnicvf->netdev->name, nic->sqs_mode ? (nic->sqs_id + 1) : 0); irq = NICVF_INTR_ID_QS_ERR; - ret = request_irq(nic->msix_entries[irq].vector, + ret = request_irq(pci_irq_vector(nic->pdev, irq), nicvf_qs_err_intr_handler, 0, nic->irq_name[irq], nic); if (ret) @@ -1001,6 +971,7 @@ err: static void nicvf_unregister_interrupts(struct nicvf *nic) { + struct pci_dev *pdev = nic->pdev; int irq; /* Free registered interrupts */ @@ -1008,19 +979,20 @@ static void nicvf_unregister_interrupts(struct nicvf *nic) if (!nic->irq_allocated[irq]) continue; - irq_set_affinity_hint(nic->msix_entries[irq].vector, NULL); + irq_set_affinity_hint(pci_irq_vector(pdev, irq), NULL); free_cpumask_var(nic->affinity_mask[irq]); if (irq < NICVF_INTR_ID_SQ) - free_irq(nic->msix_entries[irq].vector, nic->napi[irq]); + free_irq(pci_irq_vector(pdev, irq), nic->napi[irq]); else - free_irq(nic->msix_entries[irq].vector, nic); + free_irq(pci_irq_vector(pdev, irq), nic); nic->irq_allocated[irq] = false; } /* Disable MSI-X */ - nicvf_disable_msix(nic); + pci_free_irq_vectors(pdev); + nic->num_vec = 0; } /* Initialize MSIX vectors and register MISC interrupt. @@ -1032,16 +1004,22 @@ static int nicvf_register_misc_interrupt(struct nicvf *nic) int irq = NICVF_INTR_ID_MISC; /* Return if mailbox interrupt is already registered */ - if (nic->msix_enabled) + if (nic->pdev->msix_enabled) return 0; /* Enable MSI-X */ - if (!nicvf_enable_msix(nic)) + nic->num_vec = pci_msix_vec_count(nic->pdev); + ret = pci_alloc_irq_vectors(nic->pdev, nic->num_vec, nic->num_vec, + PCI_IRQ_MSIX); + if (ret < 0) { + netdev_err(nic->netdev, + "Req for #%d msix vectors failed\n", nic->num_vec); return 1; + } sprintf(nic->irq_name[irq], "%s Mbox", "NICVF"); /* Register Misc interrupt */ - ret = request_irq(nic->msix_entries[irq].vector, + ret = request_irq(pci_irq_vector(nic->pdev, irq), nicvf_misc_intr_handler, 0, nic->irq_name[irq], nic); if (ret) @@ -1164,7 +1142,7 @@ int nicvf_stop(struct net_device *netdev) /* Wait for pending IRQ handlers to finish */ for (irq = 0; irq < nic->num_vec; irq++) - synchronize_irq(nic->msix_entries[irq].vector); + synchronize_irq(pci_irq_vector(nic->pdev, irq)); tasklet_kill(&nic->rbdr_task); tasklet_kill(&nic->qs_err_task); @@ -1365,7 +1343,7 @@ static int nicvf_set_mac_address(struct net_device *netdev, void *p) memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); - if (nic->msix_enabled) { + if (nic->pdev->msix_enabled) { if (nicvf_hw_set_mac_addr(nic, netdev)) return -EBUSY; } else { @@ -1665,8 +1643,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_unregister_interrupts; - netdev->hw_features = (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_SG | - NETIF_F_TSO | NETIF_F_GRO | + netdev->hw_features = (NETIF_F_RXCSUM | NETIF_F_SG | + NETIF_F_TSO | NETIF_F_GRO | NETIF_F_TSO6 | + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_HW_VLAN_CTAG_RX); netdev->hw_features |= NETIF_F_RXHASH; @@ -1674,7 +1653,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->features |= netdev->hw_features; netdev->hw_features |= NETIF_F_LOOPBACK; - netdev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; + netdev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6; netdev->netdev_ops = &nicvf_netdev_ops; netdev->watchdog_timeo = NICVF_TX_TIMEOUT; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index f13289f0d238..7b0fd8d871cc 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -1094,7 +1094,13 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry, { int proto; struct sq_hdr_subdesc *hdr; + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } ip; + ip.hdr = skb_network_header(skb); hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry); memset(hdr, 0, SND_QUEUE_DESC_SIZE); hdr->subdesc_type = SQ_DESC_TYPE_HEADER; @@ -1119,7 +1125,9 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry, hdr->l3_offset = skb_network_offset(skb); hdr->l4_offset = skb_transport_offset(skb); - proto = ip_hdr(skb)->protocol; + proto = (ip.v4->version == 4) ? ip.v4->protocol : + ip.v6->nexthdr; + switch (proto) { case IPPROTO_TCP: hdr->csum_l4 = SEND_L4_CSUM_TCP; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 64a1095e4d14..a0ca68ce3fbb 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -134,6 +134,7 @@ static void set_max_bgx_per_node(struct pci_dev *pdev) pci_read_config_word(pdev, PCI_SUBSYSTEM_ID, &sdevid); switch (sdevid) { case PCI_SUBSYS_DEVID_81XX_BGX: + case PCI_SUBSYS_DEVID_81XX_RGX: max_bgx_per_node = MAX_BGX_PER_CN81XX; break; case PCI_SUBSYS_DEVID_83XX_BGX: diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index c5080f2cead5..6b7fe6fdd13b 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -16,6 +16,7 @@ /* Subsystem device IDs */ #define PCI_SUBSYS_DEVID_88XX_BGX 0xA126 #define PCI_SUBSYS_DEVID_81XX_BGX 0xA226 +#define PCI_SUBSYS_DEVID_81XX_RGX 0xA254 #define PCI_SUBSYS_DEVID_83XX_BGX 0xA326 #define MAX_BGX_THUNDER 8 /* Max 2 nodes, 4 per node */ diff --git a/drivers/net/ethernet/chelsio/cxgb/common.h b/drivers/net/ethernet/chelsio/cxgb/common.h index 6916c62f2487..94b9482f14a5 100644 --- a/drivers/net/ethernet/chelsio/cxgb/common.h +++ b/drivers/net/ethernet/chelsio/cxgb/common.h @@ -223,7 +223,6 @@ struct port_info { struct cmac *mac; struct cphy *phy; struct link_config link_config; - struct net_device_stats netstats; }; struct sge; diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c index d8aff7a4b3c7..8623be13bf86 100644 --- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c +++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c @@ -296,7 +296,7 @@ static struct net_device_stats *t1_get_stats(struct net_device *dev) { struct adapter *adapter = dev->ml_priv; struct port_info *p = &adapter->port[dev->if_port]; - struct net_device_stats *ns = &p->netstats; + struct net_device_stats *ns = &dev->stats; const struct cmac_statistics *pstats; /* Do a full update of the MAC stats */ diff --git a/drivers/net/ethernet/chelsio/cxgb3/adapter.h b/drivers/net/ethernet/chelsio/cxgb3/adapter.h index 8b395b537330..087ff0ffb597 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/adapter.h +++ b/drivers/net/ethernet/chelsio/cxgb3/adapter.h @@ -72,7 +72,6 @@ struct port_info { struct cphy phy; struct cmac mac; struct link_config link_config; - struct net_device_stats netstats; int activity; __be32 iscsi_ipv4addr; struct iscsi_config iscsic; diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index d76491676b51..2ff6bd139c96 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -1489,7 +1489,7 @@ static struct net_device_stats *cxgb_get_stats(struct net_device *dev) { struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; - struct net_device_stats *ns = &pi->netstats; + struct net_device_stats *ns = &dev->stats; const struct mac_stats *pstats; spin_lock(&adapter->stats_lock); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index afb0967d2ce6..aa7101953e64 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2338,6 +2338,10 @@ int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid, f->locked = 1; f->fs.rpttid = 1; + /* Save the actual tid. We need this to get the corresponding + * filter entry structure in filter_rpl. + */ + f->tid = stid + adap->tids.ftid_base; ret = set_filter_wr(adap, stid); if (ret) { clear_filter(adap, f); diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index 3647b28e8de0..47384f7323ac 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -1896,7 +1896,7 @@ static int cs89x0_platform_remove(struct platform_device *pdev) return 0; } -static const struct __maybe_unused of_device_id cs89x0_match[] = { +static const struct of_device_id __maybe_unused cs89x0_match[] = { { .compatible = "cirrus,cs8900", }, { .compatible = "cirrus,cs8920", }, { }, diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index 127ce9707378..91b8f6f5a765 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -312,8 +312,6 @@ struct de_private { u32 msg_enable; - struct net_device_stats net_stats; - struct pci_dev *pdev; u16 setup_frame[DE_SETUP_FRAME_WORDS]; @@ -388,14 +386,14 @@ static void de_rx_err_acct (struct de_private *de, unsigned rx_tail, netif_warn(de, rx_err, de->dev, "Oversized Ethernet frame spanned multiple buffers, status %08x!\n", status); - de->net_stats.rx_length_errors++; + de->dev->stats.rx_length_errors++; } } else if (status & RxError) { /* There was a fatal error. */ - de->net_stats.rx_errors++; /* end of a packet.*/ - if (status & 0x0890) de->net_stats.rx_length_errors++; - if (status & RxErrCRC) de->net_stats.rx_crc_errors++; - if (status & RxErrFIFO) de->net_stats.rx_fifo_errors++; + de->dev->stats.rx_errors++; /* end of a packet.*/ + if (status & 0x0890) de->dev->stats.rx_length_errors++; + if (status & RxErrCRC) de->dev->stats.rx_crc_errors++; + if (status & RxErrFIFO) de->dev->stats.rx_fifo_errors++; } } @@ -423,7 +421,7 @@ static void de_rx (struct de_private *de) mapping = de->rx_skb[rx_tail].mapping; if (unlikely(drop)) { - de->net_stats.rx_dropped++; + de->dev->stats.rx_dropped++; goto rx_next; } @@ -441,7 +439,7 @@ static void de_rx (struct de_private *de) buflen = copying_skb ? (len + RX_OFFSET) : de->rx_buf_sz; copy_skb = netdev_alloc_skb(de->dev, buflen); if (unlikely(!copy_skb)) { - de->net_stats.rx_dropped++; + de->dev->stats.rx_dropped++; drop = 1; rx_work = 100; goto rx_next; @@ -470,8 +468,8 @@ static void de_rx (struct de_private *de) skb->protocol = eth_type_trans (skb, de->dev); - de->net_stats.rx_packets++; - de->net_stats.rx_bytes += skb->len; + de->dev->stats.rx_packets++; + de->dev->stats.rx_bytes += skb->len; rc = netif_rx (skb); if (rc == NET_RX_DROP) drop = 1; @@ -572,18 +570,18 @@ static void de_tx (struct de_private *de) netif_dbg(de, tx_err, de->dev, "tx err, status 0x%x\n", status); - de->net_stats.tx_errors++; + de->dev->stats.tx_errors++; if (status & TxOWC) - de->net_stats.tx_window_errors++; + de->dev->stats.tx_window_errors++; if (status & TxMaxCol) - de->net_stats.tx_aborted_errors++; + de->dev->stats.tx_aborted_errors++; if (status & TxLinkFail) - de->net_stats.tx_carrier_errors++; + de->dev->stats.tx_carrier_errors++; if (status & TxFIFOUnder) - de->net_stats.tx_fifo_errors++; + de->dev->stats.tx_fifo_errors++; } else { - de->net_stats.tx_packets++; - de->net_stats.tx_bytes += skb->len; + de->dev->stats.tx_packets++; + de->dev->stats.tx_bytes += skb->len; netif_dbg(de, tx_done, de->dev, "tx done, slot %d\n", tx_tail); } @@ -814,9 +812,9 @@ static void de_set_rx_mode (struct net_device *dev) static inline void de_rx_missed(struct de_private *de, u32 rx_missed) { if (unlikely(rx_missed & RxMissedOver)) - de->net_stats.rx_missed_errors += RxMissedMask; + de->dev->stats.rx_missed_errors += RxMissedMask; else - de->net_stats.rx_missed_errors += (rx_missed & RxMissedMask); + de->dev->stats.rx_missed_errors += (rx_missed & RxMissedMask); } static void __de_get_stats(struct de_private *de) @@ -836,7 +834,7 @@ static struct net_device_stats *de_get_stats(struct net_device *dev) __de_get_stats(de); spin_unlock_irq(&de->lock); - return &de->net_stats; + return &dev->stats; } static inline int de_is_running (struct de_private *de) @@ -1348,7 +1346,7 @@ static void de_clean_rings (struct de_private *de) struct sk_buff *skb = de->tx_skb[i].skb; if ((skb) && (skb != DE_DUMMY_SKB)) { if (skb != DE_SETUP_SKB) { - de->net_stats.tx_dropped++; + de->dev->stats.tx_dropped++; pci_unmap_single(de->pdev, de->tx_skb[i].mapping, skb->len, PCI_DMA_TODEVICE); diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index 1e350135f11d..778f974e2928 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -878,10 +878,10 @@ tx_error (struct net_device *dev, int tx_status) frame_id = (tx_status & 0xffff0000); printk (KERN_ERR "%s: Transmit error, TxStatus %4.4x, FrameId %d.\n", dev->name, tx_status, frame_id); - np->stats.tx_errors++; + dev->stats.tx_errors++; /* Ttransmit Underrun */ if (tx_status & 0x10) { - np->stats.tx_fifo_errors++; + dev->stats.tx_fifo_errors++; dw16(TxStartThresh, dr16(TxStartThresh) + 0x10); /* Transmit Underrun need to set TxReset, DMARest, FIFOReset */ dw16(ASICCtrl + 2, @@ -903,7 +903,7 @@ tx_error (struct net_device *dev, int tx_status) } /* Late Collision */ if (tx_status & 0x04) { - np->stats.tx_fifo_errors++; + dev->stats.tx_fifo_errors++; /* TxReset and clear FIFO */ dw16(ASICCtrl + 2, TxReset | FIFOReset); /* Wait reset done */ @@ -916,13 +916,8 @@ tx_error (struct net_device *dev, int tx_status) /* Let TxStartThresh stay default value */ } /* Maximum Collisions */ -#ifdef ETHER_STATS if (tx_status & 0x08) - np->stats.collisions16++; -#else - if (tx_status & 0x08) - np->stats.collisions++; -#endif + dev->stats.collisions++; /* Restart the Tx */ dw32(MACCtrl, dr16(MACCtrl) | TxEnable); } @@ -952,15 +947,15 @@ receive_packet (struct net_device *dev) break; /* Update rx error statistics, drop packet. */ if (frame_status & RFS_Errors) { - np->stats.rx_errors++; + dev->stats.rx_errors++; if (frame_status & (RxRuntFrame | RxLengthError)) - np->stats.rx_length_errors++; + dev->stats.rx_length_errors++; if (frame_status & RxFCSError) - np->stats.rx_crc_errors++; + dev->stats.rx_crc_errors++; if (frame_status & RxAlignmentError && np->speed != 1000) - np->stats.rx_frame_errors++; + dev->stats.rx_frame_errors++; if (frame_status & RxFIFOOverrun) - np->stats.rx_fifo_errors++; + dev->stats.rx_fifo_errors++; } else { struct sk_buff *skb; @@ -1096,23 +1091,23 @@ get_stats (struct net_device *dev) /* All statistics registers need to be acknowledged, else statistic overflow could cause problems */ - np->stats.rx_packets += dr32(FramesRcvOk); - np->stats.tx_packets += dr32(FramesXmtOk); - np->stats.rx_bytes += dr32(OctetRcvOk); - np->stats.tx_bytes += dr32(OctetXmtOk); + dev->stats.rx_packets += dr32(FramesRcvOk); + dev->stats.tx_packets += dr32(FramesXmtOk); + dev->stats.rx_bytes += dr32(OctetRcvOk); + dev->stats.tx_bytes += dr32(OctetXmtOk); - np->stats.multicast = dr32(McstFramesRcvdOk); - np->stats.collisions += dr32(SingleColFrames) + dev->stats.multicast = dr32(McstFramesRcvdOk); + dev->stats.collisions += dr32(SingleColFrames) + dr32(MultiColFrames); /* detailed tx errors */ stat_reg = dr16(FramesAbortXSColls); - np->stats.tx_aborted_errors += stat_reg; - np->stats.tx_errors += stat_reg; + dev->stats.tx_aborted_errors += stat_reg; + dev->stats.tx_errors += stat_reg; stat_reg = dr16(CarrierSenseErrors); - np->stats.tx_carrier_errors += stat_reg; - np->stats.tx_errors += stat_reg; + dev->stats.tx_carrier_errors += stat_reg; + dev->stats.tx_errors += stat_reg; /* Clear all other statistic register. */ dr32(McstOctetXmtOk); @@ -1142,7 +1137,7 @@ get_stats (struct net_device *dev) dr16(TCPCheckSumErrors); dr16(UDPCheckSumErrors); dr16(IPCheckSumErrors); - return &np->stats; + return &dev->stats; } static int diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h index 5d8ae5320242..10e98ba33ebf 100644 --- a/drivers/net/ethernet/dlink/dl2k.h +++ b/drivers/net/ethernet/dlink/dl2k.h @@ -377,7 +377,6 @@ struct netdev_private { void __iomem *eeprom_addr; spinlock_t tx_lock; spinlock_t rx_lock; - struct net_device_stats stats; unsigned int rx_buf_sz; /* Based on MTU+slack. */ unsigned int speed; /* Operating speed */ unsigned int vlan; /* VLAN Id */ diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index d49528ad7821..50566243e6fa 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -567,6 +567,12 @@ struct be_error_recovery { /* Ethtool priv_flags */ #define BE_DISABLE_TPE_RECOVERY 0x1 +struct be_vxlan_port { + struct list_head list; + __be16 port; /* VxLAN UDP dst port */ + int port_aliases; /* alias count */ +}; + struct be_adapter { struct pci_dev *pdev; struct net_device *netdev; @@ -671,9 +677,9 @@ struct be_adapter { u32 sli_family; u8 hba_port_num; u16 pvid; - __be16 vxlan_port; - int vxlan_port_count; - int vxlan_port_aliases; + __be16 vxlan_port; /* offloaded vxlan port num */ + int vxlan_port_count; /* active vxlan port count */ + struct list_head vxlan_port_list; /* vxlan port list */ struct phy_info phy; u8 wol_cap; bool wol_en; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 30e855004c57..02dd5246dfae 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -4939,8 +4939,9 @@ static int __be_cmd_set_logical_link_config(struct be_adapter *adapter, int link_state, int version, u8 domain) { - struct be_mcc_wrb *wrb; struct be_cmd_req_set_ll_link *req; + struct be_mcc_wrb *wrb; + u32 link_config = 0; int status; mutex_lock(&adapter->mcc_lock); @@ -4962,10 +4963,12 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter, if (link_state == IFLA_VF_LINK_STATE_ENABLE || link_state == IFLA_VF_LINK_STATE_AUTO) - req->link_config |= PLINK_ENABLE; + link_config |= PLINK_ENABLE; if (link_state == IFLA_VF_LINK_STATE_AUTO) - req->link_config |= PLINK_TRACK; + link_config |= PLINK_TRACK; + + req->link_config = cpu_to_le32(link_config); status = be_mcc_notify_wait(adapter); err: diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 6be3b9aba8ed..8702661b99c0 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -3857,6 +3857,44 @@ static void be_cancel_err_detection(struct be_adapter *adapter) } } +static int be_enable_vxlan_offloads(struct be_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct device *dev = &adapter->pdev->dev; + struct be_vxlan_port *vxlan_port; + __be16 port; + int status; + + vxlan_port = list_first_entry(&adapter->vxlan_port_list, + struct be_vxlan_port, list); + port = vxlan_port->port; + + status = be_cmd_manage_iface(adapter, adapter->if_handle, + OP_CONVERT_NORMAL_TO_TUNNEL); + if (status) { + dev_warn(dev, "Failed to convert normal interface to tunnel\n"); + return status; + } + adapter->flags |= BE_FLAGS_VXLAN_OFFLOADS; + + status = be_cmd_set_vxlan_port(adapter, port); + if (status) { + dev_warn(dev, "Failed to add VxLAN port\n"); + return status; + } + adapter->vxlan_port = port; + + netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_TUNNEL; + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + netdev->features |= NETIF_F_GSO_UDP_TUNNEL; + + dev_info(dev, "Enabled VxLAN offloads for UDP port %d\n", + be16_to_cpu(port)); + return 0; +} + static void be_disable_vxlan_offloads(struct be_adapter *adapter) { struct net_device *netdev = adapter->netdev; @@ -4903,63 +4941,59 @@ static struct be_cmd_work *be_alloc_work(struct be_adapter *adapter, * those other tunnels are unexported on the fly through ndo_features_check(). * * Skyhawk supports VxLAN offloads only for one UDP dport. So, if the stack - * adds more than one port, disable offloads and don't re-enable them again - * until after all the tunnels are removed. + * adds more than one port, disable offloads and re-enable them again when + * there's only one port left. We maintain a list of ports for this purpose. */ static void be_work_add_vxlan_port(struct work_struct *work) { struct be_cmd_work *cmd_work = container_of(work, struct be_cmd_work, work); struct be_adapter *adapter = cmd_work->adapter; - struct net_device *netdev = adapter->netdev; struct device *dev = &adapter->pdev->dev; __be16 port = cmd_work->info.vxlan_port; + struct be_vxlan_port *vxlan_port; int status; - if (adapter->vxlan_port == port && adapter->vxlan_port_count) { - adapter->vxlan_port_aliases++; - goto done; + /* Bump up the alias count if it is an existing port */ + list_for_each_entry(vxlan_port, &adapter->vxlan_port_list, list) { + if (vxlan_port->port == port) { + vxlan_port->port_aliases++; + goto done; + } } + /* Add a new port to our list. We don't need a lock here since port + * add/delete are done only in the context of a single-threaded work + * queue (be_wq). + */ + vxlan_port = kzalloc(sizeof(*vxlan_port), GFP_KERNEL); + if (!vxlan_port) + goto done; + + vxlan_port->port = port; + INIT_LIST_HEAD(&vxlan_port->list); + list_add_tail(&vxlan_port->list, &adapter->vxlan_port_list); + adapter->vxlan_port_count++; + if (adapter->flags & BE_FLAGS_VXLAN_OFFLOADS) { dev_info(dev, "Only one UDP port supported for VxLAN offloads\n"); dev_info(dev, "Disabling VxLAN offloads\n"); - adapter->vxlan_port_count++; goto err; } - if (adapter->vxlan_port_count++ >= 1) + if (adapter->vxlan_port_count > 1) goto done; - status = be_cmd_manage_iface(adapter, adapter->if_handle, - OP_CONVERT_NORMAL_TO_TUNNEL); - if (status) { - dev_warn(dev, "Failed to convert normal interface to tunnel\n"); - goto err; - } - - status = be_cmd_set_vxlan_port(adapter, port); - if (status) { - dev_warn(dev, "Failed to add VxLAN port\n"); - goto err; - } - adapter->flags |= BE_FLAGS_VXLAN_OFFLOADS; - adapter->vxlan_port = port; - - netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_TSO | NETIF_F_TSO6 | - NETIF_F_GSO_UDP_TUNNEL; - netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; - netdev->features |= NETIF_F_GSO_UDP_TUNNEL; + status = be_enable_vxlan_offloads(adapter); + if (!status) + goto done; - dev_info(dev, "Enabled VxLAN offloads for UDP port %d\n", - be16_to_cpu(port)); - goto done; err: be_disable_vxlan_offloads(adapter); done: kfree(cmd_work); + return; } static void be_work_del_vxlan_port(struct work_struct *work) @@ -4968,23 +5002,40 @@ static void be_work_del_vxlan_port(struct work_struct *work) container_of(work, struct be_cmd_work, work); struct be_adapter *adapter = cmd_work->adapter; __be16 port = cmd_work->info.vxlan_port; + struct be_vxlan_port *vxlan_port; - if (adapter->vxlan_port != port) - goto done; + /* Nothing to be done if a port alias is being deleted */ + list_for_each_entry(vxlan_port, &adapter->vxlan_port_list, list) { + if (vxlan_port->port == port) { + if (vxlan_port->port_aliases) { + vxlan_port->port_aliases--; + goto done; + } + break; + } + } + + /* No port aliases left; delete the port from the list */ + list_del(&vxlan_port->list); + adapter->vxlan_port_count--; - if (adapter->vxlan_port_aliases) { - adapter->vxlan_port_aliases--; + /* Disable VxLAN offload if this is the offloaded port */ + if (adapter->vxlan_port == vxlan_port->port) { + WARN_ON(adapter->vxlan_port_count); + be_disable_vxlan_offloads(adapter); + dev_info(&adapter->pdev->dev, + "Disabled VxLAN offloads for UDP port %d\n", + be16_to_cpu(port)); goto out; } - be_disable_vxlan_offloads(adapter); + /* If only 1 port is left, re-enable VxLAN offload */ + if (adapter->vxlan_port_count == 1) + be_enable_vxlan_offloads(adapter); - dev_info(&adapter->pdev->dev, - "Disabled VxLAN offloads for UDP port %d\n", - be16_to_cpu(port)); -done: - adapter->vxlan_port_count--; out: + kfree(vxlan_port); +done: kfree(cmd_work); } @@ -5626,6 +5677,7 @@ static int be_drv_init(struct be_adapter *adapter) /* Must be a power of 2 or else MODULO will BUG_ON */ adapter->be_get_temp_freq = 64; + INIT_LIST_HEAD(&adapter->vxlan_port_list); return 0; free_rx_filter: diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c index 70165fcbff9c..659f1ad37e96 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.c +++ b/drivers/net/ethernet/ezchip/nps_enet.c @@ -190,11 +190,9 @@ static int nps_enet_poll(struct napi_struct *napi, int budget) nps_enet_tx_handler(ndev); work_done = nps_enet_rx_handler(ndev); - if (work_done < budget) { + if ((work_done < budget) && napi_complete_done(napi, work_done)) { u32 buf_int_enable_value = 0; - napi_complete_done(napi, work_done); - /* set tx_done and rx_rdy bits */ buf_int_enable_value |= NPS_ENET_ENABLE << RX_RDY_SHIFT; buf_int_enable_value |= NPS_ENET_ENABLE << TX_DONE_SHIFT; diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 928b0df2b8e0..95bf5e89cfd1 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -28,8 +28,13 @@ #include <linux/io.h> #include <linux/module.h> #include <linux/netdevice.h> +#include <linux/of.h> #include <linux/phy.h> #include <linux/platform_device.h> +#include <linux/property.h> +#include <linux/crc32.h> +#include <linux/if_vlan.h> +#include <linux/of_net.h> #include <net/ip.h> #include <net/ncsi.h> @@ -38,103 +43,137 @@ #define DRV_NAME "ftgmac100" #define DRV_VERSION "0.7" -#define RX_QUEUE_ENTRIES 256 /* must be power of 2 */ -#define TX_QUEUE_ENTRIES 512 /* must be power of 2 */ +/* Arbitrary values, I am not sure the HW has limits */ +#define MAX_RX_QUEUE_ENTRIES 1024 +#define MAX_TX_QUEUE_ENTRIES 1024 +#define MIN_RX_QUEUE_ENTRIES 32 +#define MIN_TX_QUEUE_ENTRIES 32 -#define MAX_PKT_SIZE 1518 -#define RX_BUF_SIZE PAGE_SIZE /* must be smaller than 0x3fff */ +/* Defaults */ +#define DEF_RX_QUEUE_ENTRIES 128 +#define DEF_TX_QUEUE_ENTRIES 128 -/****************************************************************************** - * private data - *****************************************************************************/ -struct ftgmac100_descs { - struct ftgmac100_rxdes rxdes[RX_QUEUE_ENTRIES]; - struct ftgmac100_txdes txdes[TX_QUEUE_ENTRIES]; -}; +#define MAX_PKT_SIZE 1536 +#define RX_BUF_SIZE MAX_PKT_SIZE /* must be smaller than 0x3fff */ + +/* Min number of tx ring entries before stopping queue */ +#define TX_THRESHOLD (MAX_SKB_FRAGS + 1) struct ftgmac100 { + /* Registers */ struct resource *res; void __iomem *base; - int irq; - - struct ftgmac100_descs *descs; - dma_addr_t descs_dma_addr; - - struct page *rx_pages[RX_QUEUE_ENTRIES]; + /* Rx ring */ + unsigned int rx_q_entries; + struct ftgmac100_rxdes *rxdes; + dma_addr_t rxdes_dma; + struct sk_buff **rx_skbs; unsigned int rx_pointer; + u32 rxdes0_edorr_mask; + + /* Tx ring */ + unsigned int tx_q_entries; + struct ftgmac100_txdes *txdes; + dma_addr_t txdes_dma; + struct sk_buff **tx_skbs; unsigned int tx_clean_pointer; unsigned int tx_pointer; - unsigned int tx_pending; + u32 txdes0_edotr_mask; + + /* Used to signal the reset task of ring change request */ + unsigned int new_rx_q_entries; + unsigned int new_tx_q_entries; - spinlock_t tx_lock; + /* Scratch page to use when rx skb alloc fails */ + void *rx_scratch; + dma_addr_t rx_scratch_dma; + /* Component structures */ struct net_device *netdev; struct device *dev; struct ncsi_dev *ndev; struct napi_struct napi; - + struct work_struct reset_task; struct mii_bus *mii_bus; - int old_speed; - int int_mask_all; - bool use_ncsi; - bool enabled; - - u32 rxdes0_edorr_mask; - u32 txdes0_edotr_mask; -}; -static int ftgmac100_alloc_rx_page(struct ftgmac100 *priv, - struct ftgmac100_rxdes *rxdes, gfp_t gfp); - -/****************************************************************************** - * internal functions (hardware register access) - *****************************************************************************/ -static void ftgmac100_set_rx_ring_base(struct ftgmac100 *priv, dma_addr_t addr) -{ - iowrite32(addr, priv->base + FTGMAC100_OFFSET_RXR_BADR); -} + /* Link management */ + int cur_speed; + int cur_duplex; + bool use_ncsi; -static void ftgmac100_set_rx_buffer_size(struct ftgmac100 *priv, - unsigned int size) -{ - size = FTGMAC100_RBSR_SIZE(size); - iowrite32(size, priv->base + FTGMAC100_OFFSET_RBSR); -} + /* Multicast filter settings */ + u32 maht0; + u32 maht1; -static void ftgmac100_set_normal_prio_tx_ring_base(struct ftgmac100 *priv, - dma_addr_t addr) -{ - iowrite32(addr, priv->base + FTGMAC100_OFFSET_NPTXR_BADR); -} + /* Flow control settings */ + bool tx_pause; + bool rx_pause; + bool aneg_pause; -static void ftgmac100_txdma_normal_prio_start_polling(struct ftgmac100 *priv) -{ - iowrite32(1, priv->base + FTGMAC100_OFFSET_NPTXPD); -} + /* Misc */ + bool need_mac_restart; + bool is_aspeed; +}; -static int ftgmac100_reset_hw(struct ftgmac100 *priv) +static int ftgmac100_reset_mac(struct ftgmac100 *priv, u32 maccr) { struct net_device *netdev = priv->netdev; int i; /* NOTE: reset clears all registers */ - iowrite32(FTGMAC100_MACCR_SW_RST, priv->base + FTGMAC100_OFFSET_MACCR); - for (i = 0; i < 5; i++) { + iowrite32(maccr, priv->base + FTGMAC100_OFFSET_MACCR); + iowrite32(maccr | FTGMAC100_MACCR_SW_RST, + priv->base + FTGMAC100_OFFSET_MACCR); + for (i = 0; i < 50; i++) { unsigned int maccr; maccr = ioread32(priv->base + FTGMAC100_OFFSET_MACCR); if (!(maccr & FTGMAC100_MACCR_SW_RST)) return 0; - udelay(1000); + udelay(1); } - netdev_err(netdev, "software reset failed\n"); + netdev_err(netdev, "Hardware reset failed\n"); return -EIO; } -static void ftgmac100_set_mac(struct ftgmac100 *priv, const unsigned char *mac) +static int ftgmac100_reset_and_config_mac(struct ftgmac100 *priv) +{ + u32 maccr = 0; + + switch (priv->cur_speed) { + case SPEED_10: + case 0: /* no link */ + break; + + case SPEED_100: + maccr |= FTGMAC100_MACCR_FAST_MODE; + break; + + case SPEED_1000: + maccr |= FTGMAC100_MACCR_GIGA_MODE; + break; + default: + netdev_err(priv->netdev, "Unknown speed %d !\n", + priv->cur_speed); + break; + } + + /* (Re)initialize the queue pointers */ + priv->rx_pointer = 0; + priv->tx_clean_pointer = 0; + priv->tx_pointer = 0; + + /* The doc says reset twice with 10us interval */ + if (ftgmac100_reset_mac(priv, maccr)) + return -EIO; + usleep_range(10, 1000); + return ftgmac100_reset_mac(priv, maccr); +} + +static void ftgmac100_write_mac_addr(struct ftgmac100 *priv, const u8 *mac) { unsigned int maddr = mac[0] << 8 | mac[1]; unsigned int laddr = mac[2] << 24 | mac[3] << 16 | mac[4] << 8 | mac[5]; @@ -143,7 +182,7 @@ static void ftgmac100_set_mac(struct ftgmac100 *priv, const unsigned char *mac) iowrite32(laddr, priv->base + FTGMAC100_OFFSET_MAC_LADR); } -static void ftgmac100_setup_mac(struct ftgmac100 *priv) +static void ftgmac100_initial_mac(struct ftgmac100 *priv) { u8 mac[ETH_ALEN]; unsigned int m; @@ -187,716 +226,833 @@ static int ftgmac100_set_mac_addr(struct net_device *dev, void *p) return ret; eth_commit_mac_addr_change(dev, p); - ftgmac100_set_mac(netdev_priv(dev), dev->dev_addr); + ftgmac100_write_mac_addr(netdev_priv(dev), dev->dev_addr); return 0; } -static void ftgmac100_init_hw(struct ftgmac100 *priv) -{ - /* setup ring buffer base registers */ - ftgmac100_set_rx_ring_base(priv, - priv->descs_dma_addr + - offsetof(struct ftgmac100_descs, rxdes)); - ftgmac100_set_normal_prio_tx_ring_base(priv, - priv->descs_dma_addr + - offsetof(struct ftgmac100_descs, txdes)); - - ftgmac100_set_rx_buffer_size(priv, RX_BUF_SIZE); - - iowrite32(FTGMAC100_APTC_RXPOLL_CNT(1), priv->base + FTGMAC100_OFFSET_APTC); - - ftgmac100_set_mac(priv, priv->netdev->dev_addr); -} - -#define MACCR_ENABLE_ALL (FTGMAC100_MACCR_TXDMA_EN | \ - FTGMAC100_MACCR_RXDMA_EN | \ - FTGMAC100_MACCR_TXMAC_EN | \ - FTGMAC100_MACCR_RXMAC_EN | \ - FTGMAC100_MACCR_FULLDUP | \ - FTGMAC100_MACCR_CRC_APD | \ - FTGMAC100_MACCR_RX_RUNT | \ - FTGMAC100_MACCR_RX_BROADPKT) - -static void ftgmac100_start_hw(struct ftgmac100 *priv, int speed) +static void ftgmac100_config_pause(struct ftgmac100 *priv) { - int maccr = MACCR_ENABLE_ALL; + u32 fcr = FTGMAC100_FCR_PAUSE_TIME(16); - switch (speed) { - default: - case 10: - break; - - case 100: - maccr |= FTGMAC100_MACCR_FAST_MODE; - break; + /* Throttle tx queue when receiving pause frames */ + if (priv->rx_pause) + fcr |= FTGMAC100_FCR_FC_EN; - case 1000: - maccr |= FTGMAC100_MACCR_GIGA_MODE; - break; - } + /* Enables sending pause frames when the RX queue is past a + * certain threshold. + */ + if (priv->tx_pause) + fcr |= FTGMAC100_FCR_FCTHR_EN; - iowrite32(maccr, priv->base + FTGMAC100_OFFSET_MACCR); + iowrite32(fcr, priv->base + FTGMAC100_OFFSET_FCR); } -static void ftgmac100_stop_hw(struct ftgmac100 *priv) +static void ftgmac100_init_hw(struct ftgmac100 *priv) { - iowrite32(0, priv->base + FTGMAC100_OFFSET_MACCR); -} + u32 reg, rfifo_sz, tfifo_sz; -/****************************************************************************** - * internal functions (receive descriptor) - *****************************************************************************/ -static bool ftgmac100_rxdes_first_segment(struct ftgmac100_rxdes *rxdes) -{ - return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_FRS); -} + /* Clear stale interrupts */ + reg = ioread32(priv->base + FTGMAC100_OFFSET_ISR); + iowrite32(reg, priv->base + FTGMAC100_OFFSET_ISR); -static bool ftgmac100_rxdes_last_segment(struct ftgmac100_rxdes *rxdes) -{ - return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_LRS); -} + /* Setup RX ring buffer base */ + iowrite32(priv->rxdes_dma, priv->base + FTGMAC100_OFFSET_RXR_BADR); -static bool ftgmac100_rxdes_packet_ready(struct ftgmac100_rxdes *rxdes) -{ - return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RXPKT_RDY); -} + /* Setup TX ring buffer base */ + iowrite32(priv->txdes_dma, priv->base + FTGMAC100_OFFSET_NPTXR_BADR); -static void ftgmac100_rxdes_set_dma_own(const struct ftgmac100 *priv, - struct ftgmac100_rxdes *rxdes) -{ - /* clear status bits */ - rxdes->rxdes0 &= cpu_to_le32(priv->rxdes0_edorr_mask); -} + /* Configure RX buffer size */ + iowrite32(FTGMAC100_RBSR_SIZE(RX_BUF_SIZE), + priv->base + FTGMAC100_OFFSET_RBSR); -static bool ftgmac100_rxdes_rx_error(struct ftgmac100_rxdes *rxdes) -{ - return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RX_ERR); -} + /* Set RX descriptor autopoll */ + iowrite32(FTGMAC100_APTC_RXPOLL_CNT(1), + priv->base + FTGMAC100_OFFSET_APTC); -static bool ftgmac100_rxdes_crc_error(struct ftgmac100_rxdes *rxdes) -{ - return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_CRC_ERR); -} + /* Write MAC address */ + ftgmac100_write_mac_addr(priv, priv->netdev->dev_addr); -static bool ftgmac100_rxdes_frame_too_long(struct ftgmac100_rxdes *rxdes) -{ - return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_FTL); -} + /* Write multicast filter */ + iowrite32(priv->maht0, priv->base + FTGMAC100_OFFSET_MAHT0); + iowrite32(priv->maht1, priv->base + FTGMAC100_OFFSET_MAHT1); -static bool ftgmac100_rxdes_runt(struct ftgmac100_rxdes *rxdes) -{ - return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RUNT); + /* Configure descriptor sizes and increase burst sizes according + * to values in Aspeed SDK. The FIFO arbitration is enabled and + * the thresholds set based on the recommended values in the + * AST2400 specification. + */ + iowrite32(FTGMAC100_DBLAC_RXDES_SIZE(2) | /* 2*8 bytes RX descs */ + FTGMAC100_DBLAC_TXDES_SIZE(2) | /* 2*8 bytes TX descs */ + FTGMAC100_DBLAC_RXBURST_SIZE(3) | /* 512 bytes max RX bursts */ + FTGMAC100_DBLAC_TXBURST_SIZE(3) | /* 512 bytes max TX bursts */ + FTGMAC100_DBLAC_RX_THR_EN | /* Enable fifo threshold arb */ + FTGMAC100_DBLAC_RXFIFO_HTHR(6) | /* 6/8 of FIFO high threshold */ + FTGMAC100_DBLAC_RXFIFO_LTHR(2), /* 2/8 of FIFO low threshold */ + priv->base + FTGMAC100_OFFSET_DBLAC); + + /* Interrupt mitigation configured for 1 interrupt/packet. HW interrupt + * mitigation doesn't seem to provide any benefit with NAPI so leave + * it at that. + */ + iowrite32(FTGMAC100_ITC_RXINT_THR(1) | + FTGMAC100_ITC_TXINT_THR(1), + priv->base + FTGMAC100_OFFSET_ITC); + + /* Configure FIFO sizes in the TPAFCR register */ + reg = ioread32(priv->base + FTGMAC100_OFFSET_FEAR); + rfifo_sz = reg & 0x00000007; + tfifo_sz = (reg >> 3) & 0x00000007; + reg = ioread32(priv->base + FTGMAC100_OFFSET_TPAFCR); + reg &= ~0x3f000000; + reg |= (tfifo_sz << 27); + reg |= (rfifo_sz << 24); + iowrite32(reg, priv->base + FTGMAC100_OFFSET_TPAFCR); +} + +static void ftgmac100_start_hw(struct ftgmac100 *priv) +{ + u32 maccr = ioread32(priv->base + FTGMAC100_OFFSET_MACCR); + + /* Keep the original GMAC and FAST bits */ + maccr &= (FTGMAC100_MACCR_FAST_MODE | FTGMAC100_MACCR_GIGA_MODE); + + /* Add all the main enable bits */ + maccr |= FTGMAC100_MACCR_TXDMA_EN | + FTGMAC100_MACCR_RXDMA_EN | + FTGMAC100_MACCR_TXMAC_EN | + FTGMAC100_MACCR_RXMAC_EN | + FTGMAC100_MACCR_CRC_APD | + FTGMAC100_MACCR_PHY_LINK_LEVEL | + FTGMAC100_MACCR_RX_RUNT | + FTGMAC100_MACCR_RX_BROADPKT; + + /* Add other bits as needed */ + if (priv->cur_duplex == DUPLEX_FULL) + maccr |= FTGMAC100_MACCR_FULLDUP; + if (priv->netdev->flags & IFF_PROMISC) + maccr |= FTGMAC100_MACCR_RX_ALL; + if (priv->netdev->flags & IFF_ALLMULTI) + maccr |= FTGMAC100_MACCR_RX_MULTIPKT; + else if (netdev_mc_count(priv->netdev)) + maccr |= FTGMAC100_MACCR_HT_MULTI_EN; + + /* Vlan filtering enabled */ + if (priv->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) + maccr |= FTGMAC100_MACCR_RM_VLAN; + + /* Hit the HW */ + iowrite32(maccr, priv->base + FTGMAC100_OFFSET_MACCR); } -static bool ftgmac100_rxdes_odd_nibble(struct ftgmac100_rxdes *rxdes) +static void ftgmac100_stop_hw(struct ftgmac100 *priv) { - return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RX_ODD_NB); + iowrite32(0, priv->base + FTGMAC100_OFFSET_MACCR); } -static unsigned int ftgmac100_rxdes_data_length(struct ftgmac100_rxdes *rxdes) +static void ftgmac100_calc_mc_hash(struct ftgmac100 *priv) { - return le32_to_cpu(rxdes->rxdes0) & FTGMAC100_RXDES0_VDBC; -} + struct netdev_hw_addr *ha; -static bool ftgmac100_rxdes_multicast(struct ftgmac100_rxdes *rxdes) -{ - return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_MULTICAST); -} + priv->maht1 = 0; + priv->maht0 = 0; + netdev_for_each_mc_addr(ha, priv->netdev) { + u32 crc_val = ether_crc_le(ETH_ALEN, ha->addr); -static void ftgmac100_rxdes_set_end_of_ring(const struct ftgmac100 *priv, - struct ftgmac100_rxdes *rxdes) -{ - rxdes->rxdes0 |= cpu_to_le32(priv->rxdes0_edorr_mask); + crc_val = (~(crc_val >> 2)) & 0x3f; + if (crc_val >= 32) + priv->maht1 |= 1ul << (crc_val - 32); + else + priv->maht0 |= 1ul << (crc_val); + } } -static void ftgmac100_rxdes_set_dma_addr(struct ftgmac100_rxdes *rxdes, - dma_addr_t addr) +static void ftgmac100_set_rx_mode(struct net_device *netdev) { - rxdes->rxdes3 = cpu_to_le32(addr); -} + struct ftgmac100 *priv = netdev_priv(netdev); -static dma_addr_t ftgmac100_rxdes_get_dma_addr(struct ftgmac100_rxdes *rxdes) -{ - return le32_to_cpu(rxdes->rxdes3); -} + /* Setup the hash filter */ + ftgmac100_calc_mc_hash(priv); -static bool ftgmac100_rxdes_is_tcp(struct ftgmac100_rxdes *rxdes) -{ - return (rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_PROT_MASK)) == - cpu_to_le32(FTGMAC100_RXDES1_PROT_TCPIP); -} + /* Interface down ? that's all there is to do */ + if (!netif_running(netdev)) + return; -static bool ftgmac100_rxdes_is_udp(struct ftgmac100_rxdes *rxdes) -{ - return (rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_PROT_MASK)) == - cpu_to_le32(FTGMAC100_RXDES1_PROT_UDPIP); -} + /* Update the HW */ + iowrite32(priv->maht0, priv->base + FTGMAC100_OFFSET_MAHT0); + iowrite32(priv->maht1, priv->base + FTGMAC100_OFFSET_MAHT1); -static bool ftgmac100_rxdes_tcpcs_err(struct ftgmac100_rxdes *rxdes) -{ - return rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_TCP_CHKSUM_ERR); + /* Reconfigure MACCR */ + ftgmac100_start_hw(priv); } -static bool ftgmac100_rxdes_udpcs_err(struct ftgmac100_rxdes *rxdes) +static int ftgmac100_alloc_rx_buf(struct ftgmac100 *priv, unsigned int entry, + struct ftgmac100_rxdes *rxdes, gfp_t gfp) { - return rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_UDP_CHKSUM_ERR); -} + struct net_device *netdev = priv->netdev; + struct sk_buff *skb; + dma_addr_t map; + int err; -static bool ftgmac100_rxdes_ipcs_err(struct ftgmac100_rxdes *rxdes) -{ - return rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_IP_CHKSUM_ERR); -} + skb = netdev_alloc_skb_ip_align(netdev, RX_BUF_SIZE); + if (unlikely(!skb)) { + if (net_ratelimit()) + netdev_warn(netdev, "failed to allocate rx skb\n"); + err = -ENOMEM; + map = priv->rx_scratch_dma; + } else { + map = dma_map_single(priv->dev, skb->data, RX_BUF_SIZE, + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(priv->dev, map))) { + if (net_ratelimit()) + netdev_err(netdev, "failed to map rx page\n"); + dev_kfree_skb_any(skb); + map = priv->rx_scratch_dma; + skb = NULL; + err = -ENOMEM; + } + } -static inline struct page **ftgmac100_rxdes_page_slot(struct ftgmac100 *priv, - struct ftgmac100_rxdes *rxdes) -{ - return &priv->rx_pages[rxdes - priv->descs->rxdes]; -} + /* Store skb */ + priv->rx_skbs[entry] = skb; -/* - * rxdes2 is not used by hardware. We use it to keep track of page. - * Since hardware does not touch it, we can skip cpu_to_le32()/le32_to_cpu(). - */ -static void ftgmac100_rxdes_set_page(struct ftgmac100 *priv, - struct ftgmac100_rxdes *rxdes, - struct page *page) -{ - *ftgmac100_rxdes_page_slot(priv, rxdes) = page; -} + /* Store DMA address into RX desc */ + rxdes->rxdes3 = cpu_to_le32(map); -static struct page *ftgmac100_rxdes_get_page(struct ftgmac100 *priv, - struct ftgmac100_rxdes *rxdes) -{ - return *ftgmac100_rxdes_page_slot(priv, rxdes); -} + /* Ensure the above is ordered vs clearing the OWN bit */ + dma_wmb(); -/****************************************************************************** - * internal functions (receive) - *****************************************************************************/ -static int ftgmac100_next_rx_pointer(int pointer) -{ - return (pointer + 1) & (RX_QUEUE_ENTRIES - 1); -} + /* Clean status (which resets own bit) */ + if (entry == (priv->rx_q_entries - 1)) + rxdes->rxdes0 = cpu_to_le32(priv->rxdes0_edorr_mask); + else + rxdes->rxdes0 = 0; -static void ftgmac100_rx_pointer_advance(struct ftgmac100 *priv) -{ - priv->rx_pointer = ftgmac100_next_rx_pointer(priv->rx_pointer); -} - -static struct ftgmac100_rxdes *ftgmac100_current_rxdes(struct ftgmac100 *priv) -{ - return &priv->descs->rxdes[priv->rx_pointer]; + return 0; } -static struct ftgmac100_rxdes * -ftgmac100_rx_locate_first_segment(struct ftgmac100 *priv) +static unsigned int ftgmac100_next_rx_pointer(struct ftgmac100 *priv, + unsigned int pointer) { - struct ftgmac100_rxdes *rxdes = ftgmac100_current_rxdes(priv); - - while (ftgmac100_rxdes_packet_ready(rxdes)) { - if (ftgmac100_rxdes_first_segment(rxdes)) - return rxdes; - - ftgmac100_rxdes_set_dma_own(priv, rxdes); - ftgmac100_rx_pointer_advance(priv); - rxdes = ftgmac100_current_rxdes(priv); - } - - return NULL; + return (pointer + 1) & (priv->rx_q_entries - 1); } -static bool ftgmac100_rx_packet_error(struct ftgmac100 *priv, - struct ftgmac100_rxdes *rxdes) +static void ftgmac100_rx_packet_error(struct ftgmac100 *priv, u32 status) { struct net_device *netdev = priv->netdev; - bool error = false; - - if (unlikely(ftgmac100_rxdes_rx_error(rxdes))) { - if (net_ratelimit()) - netdev_info(netdev, "rx err\n"); + if (status & FTGMAC100_RXDES0_RX_ERR) netdev->stats.rx_errors++; - error = true; - } - - if (unlikely(ftgmac100_rxdes_crc_error(rxdes))) { - if (net_ratelimit()) - netdev_info(netdev, "rx crc err\n"); + if (status & FTGMAC100_RXDES0_CRC_ERR) netdev->stats.rx_crc_errors++; - error = true; - } else if (unlikely(ftgmac100_rxdes_ipcs_err(rxdes))) { - if (net_ratelimit()) - netdev_info(netdev, "rx IP checksum err\n"); - - error = true; - } - - if (unlikely(ftgmac100_rxdes_frame_too_long(rxdes))) { - if (net_ratelimit()) - netdev_info(netdev, "rx frame too long\n"); - - netdev->stats.rx_length_errors++; - error = true; - } else if (unlikely(ftgmac100_rxdes_runt(rxdes))) { - if (net_ratelimit()) - netdev_info(netdev, "rx runt\n"); - - netdev->stats.rx_length_errors++; - error = true; - } else if (unlikely(ftgmac100_rxdes_odd_nibble(rxdes))) { - if (net_ratelimit()) - netdev_info(netdev, "rx odd nibble\n"); + if (status & (FTGMAC100_RXDES0_FTL | + FTGMAC100_RXDES0_RUNT | + FTGMAC100_RXDES0_RX_ODD_NB)) netdev->stats.rx_length_errors++; - error = true; - } - - return error; } -static void ftgmac100_rx_drop_packet(struct ftgmac100 *priv) +static bool ftgmac100_rx_packet(struct ftgmac100 *priv, int *processed) { struct net_device *netdev = priv->netdev; - struct ftgmac100_rxdes *rxdes = ftgmac100_current_rxdes(priv); - bool done = false; + struct ftgmac100_rxdes *rxdes; + struct sk_buff *skb; + unsigned int pointer, size; + u32 status, csum_vlan; + dma_addr_t map; - if (net_ratelimit()) - netdev_dbg(netdev, "drop packet %p\n", rxdes); + /* Grab next RX descriptor */ + pointer = priv->rx_pointer; + rxdes = &priv->rxdes[pointer]; - do { - if (ftgmac100_rxdes_last_segment(rxdes)) - done = true; + /* Grab descriptor status */ + status = le32_to_cpu(rxdes->rxdes0); - ftgmac100_rxdes_set_dma_own(priv, rxdes); - ftgmac100_rx_pointer_advance(priv); - rxdes = ftgmac100_current_rxdes(priv); - } while (!done && ftgmac100_rxdes_packet_ready(rxdes)); + /* Do we have a packet ? */ + if (!(status & FTGMAC100_RXDES0_RXPKT_RDY)) + return false; - netdev->stats.rx_dropped++; -} + /* Order subsequent reads with the test for the ready bit */ + dma_rmb(); -static bool ftgmac100_rx_packet(struct ftgmac100 *priv, int *processed) -{ - struct net_device *netdev = priv->netdev; - struct ftgmac100_rxdes *rxdes; - struct sk_buff *skb; - bool done = false; + /* We don't cope with fragmented RX packets */ + if (unlikely(!(status & FTGMAC100_RXDES0_FRS) || + !(status & FTGMAC100_RXDES0_LRS))) + goto drop; - rxdes = ftgmac100_rx_locate_first_segment(priv); - if (!rxdes) - return false; + /* Grab received size and csum vlan field in the descriptor */ + size = status & FTGMAC100_RXDES0_VDBC; + csum_vlan = le32_to_cpu(rxdes->rxdes1); - if (unlikely(ftgmac100_rx_packet_error(priv, rxdes))) { - ftgmac100_rx_drop_packet(priv); - return true; + /* Any error (other than csum offload) flagged ? */ + if (unlikely(status & RXDES0_ANY_ERROR)) { + /* Correct for incorrect flagging of runt packets + * with vlan tags... Just accept a runt packet that + * has been flagged as vlan and whose size is at + * least 60 bytes. + */ + if ((status & FTGMAC100_RXDES0_RUNT) && + (csum_vlan & FTGMAC100_RXDES1_VLANTAG_AVAIL) && + (size >= 60)) + status &= ~FTGMAC100_RXDES0_RUNT; + + /* Any error still in there ? */ + if (status & RXDES0_ANY_ERROR) { + ftgmac100_rx_packet_error(priv, status); + goto drop; + } } - /* start processing */ - skb = netdev_alloc_skb_ip_align(netdev, 128); - if (unlikely(!skb)) { - if (net_ratelimit()) - netdev_err(netdev, "rx skb alloc failed\n"); - - ftgmac100_rx_drop_packet(priv); - return true; + /* If the packet had no skb (failed to allocate earlier) + * then try to allocate one and skip + */ + skb = priv->rx_skbs[pointer]; + if (!unlikely(skb)) { + ftgmac100_alloc_rx_buf(priv, pointer, rxdes, GFP_ATOMIC); + goto drop; } - if (unlikely(ftgmac100_rxdes_multicast(rxdes))) + if (unlikely(status & FTGMAC100_RXDES0_MULTICAST)) netdev->stats.multicast++; - /* - * It seems that HW does checksum incorrectly with fragmented packets, - * so we are conservative here - if HW checksum error, let software do - * the checksum again. + /* If the HW found checksum errors, bounce it to software. + * + * If we didn't, we need to see if the packet was recognized + * by HW as one of the supported checksummed protocols before + * we accept the HW test results. */ - if ((ftgmac100_rxdes_is_tcp(rxdes) && !ftgmac100_rxdes_tcpcs_err(rxdes)) || - (ftgmac100_rxdes_is_udp(rxdes) && !ftgmac100_rxdes_udpcs_err(rxdes))) - skb->ip_summed = CHECKSUM_UNNECESSARY; - - do { - dma_addr_t map = ftgmac100_rxdes_get_dma_addr(rxdes); - struct page *page = ftgmac100_rxdes_get_page(priv, rxdes); - unsigned int size; + if (netdev->features & NETIF_F_RXCSUM) { + u32 err_bits = FTGMAC100_RXDES1_TCP_CHKSUM_ERR | + FTGMAC100_RXDES1_UDP_CHKSUM_ERR | + FTGMAC100_RXDES1_IP_CHKSUM_ERR; + if ((csum_vlan & err_bits) || + !(csum_vlan & FTGMAC100_RXDES1_PROT_MASK)) + skb->ip_summed = CHECKSUM_NONE; + else + skb->ip_summed = CHECKSUM_UNNECESSARY; + } - dma_unmap_page(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE); + /* Transfer received size to skb */ + skb_put(skb, size); - size = ftgmac100_rxdes_data_length(rxdes); - skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, page, 0, size); + /* Extract vlan tag */ + if ((netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && + (csum_vlan & FTGMAC100_RXDES1_VLANTAG_AVAIL)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + csum_vlan & 0xffff); - skb->len += size; - skb->data_len += size; - skb->truesize += PAGE_SIZE; + /* Tear down DMA mapping, do necessary cache management */ + map = le32_to_cpu(rxdes->rxdes3); - if (ftgmac100_rxdes_last_segment(rxdes)) - done = true; +#if defined(CONFIG_ARM) && !defined(CONFIG_ARM_DMA_USE_IOMMU) + /* When we don't have an iommu, we can save cycles by not + * invalidating the cache for the part of the packet that + * wasn't received. + */ + dma_unmap_single(priv->dev, map, size, DMA_FROM_DEVICE); +#else + dma_unmap_single(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE); +#endif - ftgmac100_alloc_rx_page(priv, rxdes, GFP_ATOMIC); - ftgmac100_rx_pointer_advance(priv); - rxdes = ftgmac100_current_rxdes(priv); - } while (!done); + /* Resplenish rx ring */ + ftgmac100_alloc_rx_buf(priv, pointer, rxdes, GFP_ATOMIC); + priv->rx_pointer = ftgmac100_next_rx_pointer(priv, pointer); - /* Small frames are copied into linear part of skb to free one page */ - if (skb->len <= 128) { - skb->truesize -= PAGE_SIZE; - __pskb_pull_tail(skb, skb->len); - } else { - /* We pull the minimum amount into linear part */ - __pskb_pull_tail(skb, ETH_HLEN); - } skb->protocol = eth_type_trans(skb, netdev); netdev->stats.rx_packets++; - netdev->stats.rx_bytes += skb->len; + netdev->stats.rx_bytes += size; /* push packet to protocol stack */ - napi_gro_receive(&priv->napi, skb); + if (skb->ip_summed == CHECKSUM_NONE) + netif_receive_skb(skb); + else + napi_gro_receive(&priv->napi, skb); (*processed)++; return true; + + drop: + /* Clean rxdes0 (which resets own bit) */ + rxdes->rxdes0 = cpu_to_le32(status & priv->rxdes0_edorr_mask); + priv->rx_pointer = ftgmac100_next_rx_pointer(priv, pointer); + netdev->stats.rx_dropped++; + return true; } -/****************************************************************************** - * internal functions (transmit descriptor) - *****************************************************************************/ -static void ftgmac100_txdes_reset(const struct ftgmac100 *priv, - struct ftgmac100_txdes *txdes) +static u32 ftgmac100_base_tx_ctlstat(struct ftgmac100 *priv, + unsigned int index) { - /* clear all except end of ring bit */ - txdes->txdes0 &= cpu_to_le32(priv->txdes0_edotr_mask); - txdes->txdes1 = 0; - txdes->txdes2 = 0; - txdes->txdes3 = 0; + if (index == (priv->tx_q_entries - 1)) + return priv->txdes0_edotr_mask; + else + return 0; } -static bool ftgmac100_txdes_owned_by_dma(struct ftgmac100_txdes *txdes) +static unsigned int ftgmac100_next_tx_pointer(struct ftgmac100 *priv, + unsigned int pointer) { - return txdes->txdes0 & cpu_to_le32(FTGMAC100_TXDES0_TXDMA_OWN); + return (pointer + 1) & (priv->tx_q_entries - 1); } -static void ftgmac100_txdes_set_dma_own(struct ftgmac100_txdes *txdes) +static u32 ftgmac100_tx_buf_avail(struct ftgmac100 *priv) { - /* - * Make sure dma own bit will not be set before any other - * descriptor fields. + /* Returns the number of available slots in the TX queue + * + * This always leaves one free slot so we don't have to + * worry about empty vs. full, and this simplifies the + * test for ftgmac100_tx_buf_cleanable() below */ - wmb(); - txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_TXDMA_OWN); + return (priv->tx_clean_pointer - priv->tx_pointer - 1) & + (priv->tx_q_entries - 1); } -static void ftgmac100_txdes_set_end_of_ring(const struct ftgmac100 *priv, - struct ftgmac100_txdes *txdes) +static bool ftgmac100_tx_buf_cleanable(struct ftgmac100 *priv) { - txdes->txdes0 |= cpu_to_le32(priv->txdes0_edotr_mask); + return priv->tx_pointer != priv->tx_clean_pointer; } -static void ftgmac100_txdes_set_first_segment(struct ftgmac100_txdes *txdes) +static void ftgmac100_free_tx_packet(struct ftgmac100 *priv, + unsigned int pointer, + struct sk_buff *skb, + struct ftgmac100_txdes *txdes, + u32 ctl_stat) { - txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_FTS); -} + dma_addr_t map = le32_to_cpu(txdes->txdes3); + size_t len; -static void ftgmac100_txdes_set_last_segment(struct ftgmac100_txdes *txdes) -{ - txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_LTS); -} + if (ctl_stat & FTGMAC100_TXDES0_FTS) { + len = skb_headlen(skb); + dma_unmap_single(priv->dev, map, len, DMA_TO_DEVICE); + } else { + len = FTGMAC100_TXDES0_TXBUF_SIZE(ctl_stat); + dma_unmap_page(priv->dev, map, len, DMA_TO_DEVICE); + } -static void ftgmac100_txdes_set_buffer_size(struct ftgmac100_txdes *txdes, - unsigned int len) -{ - txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_TXBUF_SIZE(len)); + /* Free SKB on last segment */ + if (ctl_stat & FTGMAC100_TXDES0_LTS) + dev_kfree_skb(skb); + priv->tx_skbs[pointer] = NULL; } -static void ftgmac100_txdes_set_txint(struct ftgmac100_txdes *txdes) +static bool ftgmac100_tx_complete_packet(struct ftgmac100 *priv) { - txdes->txdes1 |= cpu_to_le32(FTGMAC100_TXDES1_TXIC); -} + struct net_device *netdev = priv->netdev; + struct ftgmac100_txdes *txdes; + struct sk_buff *skb; + unsigned int pointer; + u32 ctl_stat; -static void ftgmac100_txdes_set_tcpcs(struct ftgmac100_txdes *txdes) -{ - txdes->txdes1 |= cpu_to_le32(FTGMAC100_TXDES1_TCP_CHKSUM); -} + pointer = priv->tx_clean_pointer; + txdes = &priv->txdes[pointer]; -static void ftgmac100_txdes_set_udpcs(struct ftgmac100_txdes *txdes) -{ - txdes->txdes1 |= cpu_to_le32(FTGMAC100_TXDES1_UDP_CHKSUM); -} + ctl_stat = le32_to_cpu(txdes->txdes0); + if (ctl_stat & FTGMAC100_TXDES0_TXDMA_OWN) + return false; -static void ftgmac100_txdes_set_ipcs(struct ftgmac100_txdes *txdes) -{ - txdes->txdes1 |= cpu_to_le32(FTGMAC100_TXDES1_IP_CHKSUM); -} + skb = priv->tx_skbs[pointer]; + netdev->stats.tx_packets++; + netdev->stats.tx_bytes += skb->len; + ftgmac100_free_tx_packet(priv, pointer, skb, txdes, ctl_stat); + txdes->txdes0 = cpu_to_le32(ctl_stat & priv->txdes0_edotr_mask); -static void ftgmac100_txdes_set_dma_addr(struct ftgmac100_txdes *txdes, - dma_addr_t addr) -{ - txdes->txdes3 = cpu_to_le32(addr); -} + priv->tx_clean_pointer = ftgmac100_next_tx_pointer(priv, pointer); -static dma_addr_t ftgmac100_txdes_get_dma_addr(struct ftgmac100_txdes *txdes) -{ - return le32_to_cpu(txdes->txdes3); + return true; } -/* - * txdes2 is not used by hardware. We use it to keep track of socket buffer. - * Since hardware does not touch it, we can skip cpu_to_le32()/le32_to_cpu(). - */ -static void ftgmac100_txdes_set_skb(struct ftgmac100_txdes *txdes, - struct sk_buff *skb) +static void ftgmac100_tx_complete(struct ftgmac100 *priv) { - txdes->txdes2 = (unsigned int)skb; -} + struct net_device *netdev = priv->netdev; -static struct sk_buff *ftgmac100_txdes_get_skb(struct ftgmac100_txdes *txdes) -{ - return (struct sk_buff *)txdes->txdes2; -} + /* Process all completed packets */ + while (ftgmac100_tx_buf_cleanable(priv) && + ftgmac100_tx_complete_packet(priv)) + ; -/****************************************************************************** - * internal functions (transmit) - *****************************************************************************/ -static int ftgmac100_next_tx_pointer(int pointer) -{ - return (pointer + 1) & (TX_QUEUE_ENTRIES - 1); + /* Restart queue if needed */ + smp_mb(); + if (unlikely(netif_queue_stopped(netdev) && + ftgmac100_tx_buf_avail(priv) >= TX_THRESHOLD)) { + struct netdev_queue *txq; + + txq = netdev_get_tx_queue(netdev, 0); + __netif_tx_lock(txq, smp_processor_id()); + if (netif_queue_stopped(netdev) && + ftgmac100_tx_buf_avail(priv) >= TX_THRESHOLD) + netif_wake_queue(netdev); + __netif_tx_unlock(txq); + } } -static void ftgmac100_tx_pointer_advance(struct ftgmac100 *priv) +static bool ftgmac100_prep_tx_csum(struct sk_buff *skb, u32 *csum_vlan) { - priv->tx_pointer = ftgmac100_next_tx_pointer(priv->tx_pointer); -} + if (skb->protocol == cpu_to_be16(ETH_P_IP)) { + u8 ip_proto = ip_hdr(skb)->protocol; -static void ftgmac100_tx_clean_pointer_advance(struct ftgmac100 *priv) -{ - priv->tx_clean_pointer = ftgmac100_next_tx_pointer(priv->tx_clean_pointer); + *csum_vlan |= FTGMAC100_TXDES1_IP_CHKSUM; + switch(ip_proto) { + case IPPROTO_TCP: + *csum_vlan |= FTGMAC100_TXDES1_TCP_CHKSUM; + return true; + case IPPROTO_UDP: + *csum_vlan |= FTGMAC100_TXDES1_UDP_CHKSUM; + return true; + case IPPROTO_IP: + return true; + } + } + return skb_checksum_help(skb) == 0; } -static struct ftgmac100_txdes *ftgmac100_current_txdes(struct ftgmac100 *priv) +static int ftgmac100_hard_start_xmit(struct sk_buff *skb, + struct net_device *netdev) { - return &priv->descs->txdes[priv->tx_pointer]; -} + struct ftgmac100 *priv = netdev_priv(netdev); + struct ftgmac100_txdes *txdes, *first; + unsigned int pointer, nfrags, len, i, j; + u32 f_ctl_stat, ctl_stat, csum_vlan; + dma_addr_t map; -static struct ftgmac100_txdes * -ftgmac100_current_clean_txdes(struct ftgmac100 *priv) -{ - return &priv->descs->txdes[priv->tx_clean_pointer]; -} + /* The HW doesn't pad small frames */ + if (eth_skb_pad(skb)) { + netdev->stats.tx_dropped++; + return NETDEV_TX_OK; + } -static bool ftgmac100_tx_complete_packet(struct ftgmac100 *priv) -{ - struct net_device *netdev = priv->netdev; - struct ftgmac100_txdes *txdes; - struct sk_buff *skb; - dma_addr_t map; + /* Reject oversize packets */ + if (unlikely(skb->len > MAX_PKT_SIZE)) { + if (net_ratelimit()) + netdev_dbg(netdev, "tx packet too big\n"); + goto drop; + } - if (priv->tx_pending == 0) - return false; + /* Do we have a limit on #fragments ? I yet have to get a reply + * from Aspeed. If there's one I haven't hit it. + */ + nfrags = skb_shinfo(skb)->nr_frags; - txdes = ftgmac100_current_clean_txdes(priv); + /* Get header len */ + len = skb_headlen(skb); - if (ftgmac100_txdes_owned_by_dma(txdes)) - return false; + /* Map the packet head */ + map = dma_map_single(priv->dev, skb->data, len, DMA_TO_DEVICE); + if (dma_mapping_error(priv->dev, map)) { + if (net_ratelimit()) + netdev_err(netdev, "map tx packet head failed\n"); + goto drop; + } - skb = ftgmac100_txdes_get_skb(txdes); - map = ftgmac100_txdes_get_dma_addr(txdes); + /* Grab the next free tx descriptor */ + pointer = priv->tx_pointer; + txdes = first = &priv->txdes[pointer]; - netdev->stats.tx_packets++; - netdev->stats.tx_bytes += skb->len; + /* Setup it up with the packet head. Don't write the head to the + * ring just yet + */ + priv->tx_skbs[pointer] = skb; + f_ctl_stat = ftgmac100_base_tx_ctlstat(priv, pointer); + f_ctl_stat |= FTGMAC100_TXDES0_TXDMA_OWN; + f_ctl_stat |= FTGMAC100_TXDES0_TXBUF_SIZE(len); + f_ctl_stat |= FTGMAC100_TXDES0_FTS; + if (nfrags == 0) + f_ctl_stat |= FTGMAC100_TXDES0_LTS; + txdes->txdes3 = cpu_to_le32(map); + + /* Setup HW checksumming */ + csum_vlan = 0; + if (skb->ip_summed == CHECKSUM_PARTIAL && + !ftgmac100_prep_tx_csum(skb, &csum_vlan)) + goto drop; + + /* Add VLAN tag */ + if (skb_vlan_tag_present(skb)) { + csum_vlan |= FTGMAC100_TXDES1_INS_VLANTAG; + csum_vlan |= skb_vlan_tag_get(skb) & 0xffff; + } - dma_unmap_single(priv->dev, map, skb_headlen(skb), DMA_TO_DEVICE); + txdes->txdes1 = cpu_to_le32(csum_vlan); + + /* Next descriptor */ + pointer = ftgmac100_next_tx_pointer(priv, pointer); + + /* Add the fragments */ + for (i = 0; i < nfrags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + len = frag->size; + + /* Map it */ + map = skb_frag_dma_map(priv->dev, frag, 0, len, + DMA_TO_DEVICE); + if (dma_mapping_error(priv->dev, map)) + goto dma_err; + + /* Setup descriptor */ + priv->tx_skbs[pointer] = skb; + txdes = &priv->txdes[pointer]; + ctl_stat = ftgmac100_base_tx_ctlstat(priv, pointer); + ctl_stat |= FTGMAC100_TXDES0_TXDMA_OWN; + ctl_stat |= FTGMAC100_TXDES0_TXBUF_SIZE(len); + if (i == (nfrags - 1)) + ctl_stat |= FTGMAC100_TXDES0_LTS; + txdes->txdes0 = cpu_to_le32(ctl_stat); + txdes->txdes1 = 0; + txdes->txdes3 = cpu_to_le32(map); + + /* Next one */ + pointer = ftgmac100_next_tx_pointer(priv, pointer); + } - dev_kfree_skb(skb); + /* Order the previous packet and descriptor udpates + * before setting the OWN bit on the first descriptor. + */ + dma_wmb(); + first->txdes0 = cpu_to_le32(f_ctl_stat); - ftgmac100_txdes_reset(priv, txdes); + /* Update next TX pointer */ + priv->tx_pointer = pointer; - ftgmac100_tx_clean_pointer_advance(priv); + /* If there isn't enough room for all the fragments of a new packet + * in the TX ring, stop the queue. The sequence below is race free + * vs. a concurrent restart in ftgmac100_poll() + */ + if (unlikely(ftgmac100_tx_buf_avail(priv) < TX_THRESHOLD)) { + netif_stop_queue(netdev); + /* Order the queue stop with the test below */ + smp_mb(); + if (ftgmac100_tx_buf_avail(priv) >= TX_THRESHOLD) + netif_wake_queue(netdev); + } - spin_lock(&priv->tx_lock); - priv->tx_pending--; - spin_unlock(&priv->tx_lock); - netif_wake_queue(netdev); + /* Poke transmitter to read the updated TX descriptors */ + iowrite32(1, priv->base + FTGMAC100_OFFSET_NPTXPD); - return true; -} + return NETDEV_TX_OK; -static void ftgmac100_tx_complete(struct ftgmac100 *priv) -{ - while (ftgmac100_tx_complete_packet(priv)) - ; + dma_err: + if (net_ratelimit()) + netdev_err(netdev, "map tx fragment failed\n"); + + /* Free head */ + pointer = priv->tx_pointer; + ftgmac100_free_tx_packet(priv, pointer, skb, first, f_ctl_stat); + first->txdes0 = cpu_to_le32(f_ctl_stat & priv->txdes0_edotr_mask); + + /* Then all fragments */ + for (j = 0; j < i; j++) { + pointer = ftgmac100_next_tx_pointer(priv, pointer); + txdes = &priv->txdes[pointer]; + ctl_stat = le32_to_cpu(txdes->txdes0); + ftgmac100_free_tx_packet(priv, pointer, skb, txdes, ctl_stat); + txdes->txdes0 = cpu_to_le32(ctl_stat & priv->txdes0_edotr_mask); + } + + /* This cannot be reached if we successfully mapped the + * last fragment, so we know ftgmac100_free_tx_packet() + * hasn't freed the skb yet. + */ + drop: + /* Drop the packet */ + dev_kfree_skb_any(skb); + netdev->stats.tx_dropped++; + + return NETDEV_TX_OK; } -static int ftgmac100_xmit(struct ftgmac100 *priv, struct sk_buff *skb, - dma_addr_t map) +static void ftgmac100_free_buffers(struct ftgmac100 *priv) { - struct net_device *netdev = priv->netdev; - struct ftgmac100_txdes *txdes; - unsigned int len = (skb->len < ETH_ZLEN) ? ETH_ZLEN : skb->len; - - txdes = ftgmac100_current_txdes(priv); - ftgmac100_tx_pointer_advance(priv); - - /* setup TX descriptor */ - ftgmac100_txdes_set_skb(txdes, skb); - ftgmac100_txdes_set_dma_addr(txdes, map); - ftgmac100_txdes_set_buffer_size(txdes, len); - - ftgmac100_txdes_set_first_segment(txdes); - ftgmac100_txdes_set_last_segment(txdes); - ftgmac100_txdes_set_txint(txdes); - if (skb->ip_summed == CHECKSUM_PARTIAL) { - __be16 protocol = skb->protocol; - - if (protocol == cpu_to_be16(ETH_P_IP)) { - u8 ip_proto = ip_hdr(skb)->protocol; - - ftgmac100_txdes_set_ipcs(txdes); - if (ip_proto == IPPROTO_TCP) - ftgmac100_txdes_set_tcpcs(txdes); - else if (ip_proto == IPPROTO_UDP) - ftgmac100_txdes_set_udpcs(txdes); - } + int i; + + /* Free all RX buffers */ + for (i = 0; i < priv->rx_q_entries; i++) { + struct ftgmac100_rxdes *rxdes = &priv->rxdes[i]; + struct sk_buff *skb = priv->rx_skbs[i]; + dma_addr_t map = le32_to_cpu(rxdes->rxdes3); + + if (!skb) + continue; + + priv->rx_skbs[i] = NULL; + dma_unmap_single(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE); + dev_kfree_skb_any(skb); } - spin_lock(&priv->tx_lock); - priv->tx_pending++; - if (priv->tx_pending == TX_QUEUE_ENTRIES) - netif_stop_queue(netdev); + /* Free all TX buffers */ + for (i = 0; i < priv->tx_q_entries; i++) { + struct ftgmac100_txdes *txdes = &priv->txdes[i]; + struct sk_buff *skb = priv->tx_skbs[i]; + + if (!skb) + continue; + ftgmac100_free_tx_packet(priv, i, skb, txdes, + le32_to_cpu(txdes->txdes0)); + } +} - /* start transmit */ - ftgmac100_txdes_set_dma_own(txdes); - spin_unlock(&priv->tx_lock); +static void ftgmac100_free_rings(struct ftgmac100 *priv) +{ + /* Free skb arrays */ + kfree(priv->rx_skbs); + kfree(priv->tx_skbs); - ftgmac100_txdma_normal_prio_start_polling(priv); + /* Free descriptors */ + if (priv->rxdes) + dma_free_coherent(priv->dev, MAX_RX_QUEUE_ENTRIES * + sizeof(struct ftgmac100_rxdes), + priv->rxdes, priv->rxdes_dma); + priv->rxdes = NULL; - return NETDEV_TX_OK; + if (priv->txdes) + dma_free_coherent(priv->dev, MAX_TX_QUEUE_ENTRIES * + sizeof(struct ftgmac100_txdes), + priv->txdes, priv->txdes_dma); + priv->txdes = NULL; + + /* Free scratch packet buffer */ + if (priv->rx_scratch) + dma_free_coherent(priv->dev, RX_BUF_SIZE, + priv->rx_scratch, priv->rx_scratch_dma); } -/****************************************************************************** - * internal functions (buffer) - *****************************************************************************/ -static int ftgmac100_alloc_rx_page(struct ftgmac100 *priv, - struct ftgmac100_rxdes *rxdes, gfp_t gfp) +static int ftgmac100_alloc_rings(struct ftgmac100 *priv) { - struct net_device *netdev = priv->netdev; - struct page *page; - dma_addr_t map; + /* Allocate skb arrays */ + priv->rx_skbs = kcalloc(MAX_RX_QUEUE_ENTRIES, sizeof(void *), + GFP_KERNEL); + if (!priv->rx_skbs) + return -ENOMEM; + priv->tx_skbs = kcalloc(MAX_TX_QUEUE_ENTRIES, sizeof(void *), + GFP_KERNEL); + if (!priv->tx_skbs) + return -ENOMEM; - page = alloc_page(gfp); - if (!page) { - if (net_ratelimit()) - netdev_err(netdev, "failed to allocate rx page\n"); + /* Allocate descriptors */ + priv->rxdes = dma_zalloc_coherent(priv->dev, + MAX_RX_QUEUE_ENTRIES * + sizeof(struct ftgmac100_rxdes), + &priv->rxdes_dma, GFP_KERNEL); + if (!priv->rxdes) + return -ENOMEM; + priv->txdes = dma_zalloc_coherent(priv->dev, + MAX_TX_QUEUE_ENTRIES * + sizeof(struct ftgmac100_txdes), + &priv->txdes_dma, GFP_KERNEL); + if (!priv->txdes) return -ENOMEM; - } - map = dma_map_page(priv->dev, page, 0, RX_BUF_SIZE, DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(priv->dev, map))) { - if (net_ratelimit()) - netdev_err(netdev, "failed to map rx page\n"); - __free_page(page); + /* Allocate scratch packet buffer */ + priv->rx_scratch = dma_alloc_coherent(priv->dev, + RX_BUF_SIZE, + &priv->rx_scratch_dma, + GFP_KERNEL); + if (!priv->rx_scratch) return -ENOMEM; - } - ftgmac100_rxdes_set_page(priv, rxdes, page); - ftgmac100_rxdes_set_dma_addr(rxdes, map); - ftgmac100_rxdes_set_dma_own(priv, rxdes); return 0; } -static void ftgmac100_free_buffers(struct ftgmac100 *priv) +static void ftgmac100_init_rings(struct ftgmac100 *priv) { + struct ftgmac100_rxdes *rxdes = NULL; + struct ftgmac100_txdes *txdes = NULL; int i; - for (i = 0; i < RX_QUEUE_ENTRIES; i++) { - struct ftgmac100_rxdes *rxdes = &priv->descs->rxdes[i]; - struct page *page = ftgmac100_rxdes_get_page(priv, rxdes); - dma_addr_t map = ftgmac100_rxdes_get_dma_addr(rxdes); + /* Update entries counts */ + priv->rx_q_entries = priv->new_rx_q_entries; + priv->tx_q_entries = priv->new_tx_q_entries; - if (!page) - continue; + if (WARN_ON(priv->rx_q_entries < MIN_RX_QUEUE_ENTRIES)) + return; - dma_unmap_page(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE); - __free_page(page); + /* Initialize RX ring */ + for (i = 0; i < priv->rx_q_entries; i++) { + rxdes = &priv->rxdes[i]; + rxdes->rxdes0 = 0; + rxdes->rxdes3 = cpu_to_le32(priv->rx_scratch_dma); } + /* Mark the end of the ring */ + rxdes->rxdes0 |= cpu_to_le32(priv->rxdes0_edorr_mask); - for (i = 0; i < TX_QUEUE_ENTRIES; i++) { - struct ftgmac100_txdes *txdes = &priv->descs->txdes[i]; - struct sk_buff *skb = ftgmac100_txdes_get_skb(txdes); - dma_addr_t map = ftgmac100_txdes_get_dma_addr(txdes); - - if (!skb) - continue; + if (WARN_ON(priv->tx_q_entries < MIN_RX_QUEUE_ENTRIES)) + return; - dma_unmap_single(priv->dev, map, skb_headlen(skb), DMA_TO_DEVICE); - kfree_skb(skb); + /* Initialize TX ring */ + for (i = 0; i < priv->tx_q_entries; i++) { + txdes = &priv->txdes[i]; + txdes->txdes0 = 0; } - - dma_free_coherent(priv->dev, sizeof(struct ftgmac100_descs), - priv->descs, priv->descs_dma_addr); + txdes->txdes0 |= cpu_to_le32(priv->txdes0_edotr_mask); } -static int ftgmac100_alloc_buffers(struct ftgmac100 *priv) +static int ftgmac100_alloc_rx_buffers(struct ftgmac100 *priv) { int i; - priv->descs = dma_zalloc_coherent(priv->dev, - sizeof(struct ftgmac100_descs), - &priv->descs_dma_addr, GFP_KERNEL); - if (!priv->descs) - return -ENOMEM; - - /* initialize RX ring */ - ftgmac100_rxdes_set_end_of_ring(priv, - &priv->descs->rxdes[RX_QUEUE_ENTRIES - 1]); - - for (i = 0; i < RX_QUEUE_ENTRIES; i++) { - struct ftgmac100_rxdes *rxdes = &priv->descs->rxdes[i]; + for (i = 0; i < priv->rx_q_entries; i++) { + struct ftgmac100_rxdes *rxdes = &priv->rxdes[i]; - if (ftgmac100_alloc_rx_page(priv, rxdes, GFP_KERNEL)) - goto err; + if (ftgmac100_alloc_rx_buf(priv, i, rxdes, GFP_KERNEL)) + return -ENOMEM; } - - /* initialize TX ring */ - ftgmac100_txdes_set_end_of_ring(priv, - &priv->descs->txdes[TX_QUEUE_ENTRIES - 1]); return 0; - -err: - ftgmac100_free_buffers(priv); - return -ENOMEM; } -/****************************************************************************** - * internal functions (mdio) - *****************************************************************************/ static void ftgmac100_adjust_link(struct net_device *netdev) { struct ftgmac100 *priv = netdev_priv(netdev); struct phy_device *phydev = netdev->phydev; - int ier; + bool tx_pause, rx_pause; + int new_speed; + + /* We store "no link" as speed 0 */ + if (!phydev->link) + new_speed = 0; + else + new_speed = phydev->speed; + + /* Grab pause settings from PHY if configured to do so */ + if (priv->aneg_pause) { + rx_pause = tx_pause = phydev->pause; + if (phydev->asym_pause) + tx_pause = !rx_pause; + } else { + rx_pause = priv->rx_pause; + tx_pause = priv->tx_pause; + } - if (phydev->speed == priv->old_speed) + /* Link hasn't changed, do nothing */ + if (phydev->speed == priv->cur_speed && + phydev->duplex == priv->cur_duplex && + rx_pause == priv->rx_pause && + tx_pause == priv->tx_pause) return; - priv->old_speed = phydev->speed; - - ier = ioread32(priv->base + FTGMAC100_OFFSET_IER); + /* Print status if we have a link or we had one and just lost it, + * don't print otherwise. + */ + if (new_speed || priv->cur_speed) + phy_print_status(phydev); - /* disable all interrupts */ - iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); + priv->cur_speed = new_speed; + priv->cur_duplex = phydev->duplex; + priv->rx_pause = rx_pause; + priv->tx_pause = tx_pause; - netif_stop_queue(netdev); - ftgmac100_stop_hw(priv); + /* Link is down, do nothing else */ + if (!new_speed) + return; - netif_start_queue(netdev); - ftgmac100_init_hw(priv); - ftgmac100_start_hw(priv, phydev->speed); + /* Disable all interrupts */ + iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); - /* re-enable interrupts */ - iowrite32(ier, priv->base + FTGMAC100_OFFSET_IER); + /* Reset the adapter asynchronously */ + schedule_work(&priv->reset_task); } -static int ftgmac100_mii_probe(struct ftgmac100 *priv) +static int ftgmac100_mii_probe(struct ftgmac100 *priv, phy_interface_t intf) { struct net_device *netdev = priv->netdev; struct phy_device *phydev; @@ -908,19 +1064,25 @@ static int ftgmac100_mii_probe(struct ftgmac100 *priv) } phydev = phy_connect(netdev, phydev_name(phydev), - &ftgmac100_adjust_link, PHY_INTERFACE_MODE_GMII); + &ftgmac100_adjust_link, intf); if (IS_ERR(phydev)) { netdev_err(netdev, "%s: Could not attach to PHY\n", netdev->name); return PTR_ERR(phydev); } + /* Indicate that we support PAUSE frames (see comment in + * Documentation/networking/phy.txt) + */ + phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + phydev->advertising = phydev->supported; + + /* Display what we found */ + phy_attached_info(phydev); + return 0; } -/****************************************************************************** - * struct mii_bus functions - *****************************************************************************/ static int ftgmac100_mdiobus_read(struct mii_bus *bus, int phy_addr, int regnum) { struct net_device *netdev = bus->priv; @@ -992,9 +1154,6 @@ static int ftgmac100_mdiobus_write(struct mii_bus *bus, int phy_addr, return -EIO; } -/****************************************************************************** - * struct ethtool_ops functions - *****************************************************************************/ static void ftgmac100_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info) { @@ -1003,175 +1162,365 @@ static void ftgmac100_get_drvinfo(struct net_device *netdev, strlcpy(info->bus_info, dev_name(&netdev->dev), sizeof(info->bus_info)); } +static void ftgmac100_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ering) +{ + struct ftgmac100 *priv = netdev_priv(netdev); + + memset(ering, 0, sizeof(*ering)); + ering->rx_max_pending = MAX_RX_QUEUE_ENTRIES; + ering->tx_max_pending = MAX_TX_QUEUE_ENTRIES; + ering->rx_pending = priv->rx_q_entries; + ering->tx_pending = priv->tx_q_entries; +} + +static int ftgmac100_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ering) +{ + struct ftgmac100 *priv = netdev_priv(netdev); + + if (ering->rx_pending > MAX_RX_QUEUE_ENTRIES || + ering->tx_pending > MAX_TX_QUEUE_ENTRIES || + ering->rx_pending < MIN_RX_QUEUE_ENTRIES || + ering->tx_pending < MIN_TX_QUEUE_ENTRIES || + !is_power_of_2(ering->rx_pending) || + !is_power_of_2(ering->tx_pending)) + return -EINVAL; + + priv->new_rx_q_entries = ering->rx_pending; + priv->new_tx_q_entries = ering->tx_pending; + if (netif_running(netdev)) + schedule_work(&priv->reset_task); + + return 0; +} + +static void ftgmac100_get_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct ftgmac100 *priv = netdev_priv(netdev); + + pause->autoneg = priv->aneg_pause; + pause->tx_pause = priv->tx_pause; + pause->rx_pause = priv->rx_pause; +} + +static int ftgmac100_set_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct ftgmac100 *priv = netdev_priv(netdev); + struct phy_device *phydev = netdev->phydev; + + priv->aneg_pause = pause->autoneg; + priv->tx_pause = pause->tx_pause; + priv->rx_pause = pause->rx_pause; + + if (phydev) { + phydev->advertising &= ~ADVERTISED_Pause; + phydev->advertising &= ~ADVERTISED_Asym_Pause; + + if (pause->rx_pause) { + phydev->advertising |= ADVERTISED_Pause; + phydev->advertising |= ADVERTISED_Asym_Pause; + } + + if (pause->tx_pause) + phydev->advertising ^= ADVERTISED_Asym_Pause; + } + if (netif_running(netdev)) { + if (phydev && priv->aneg_pause) + phy_start_aneg(phydev); + else + ftgmac100_config_pause(priv); + } + + return 0; +} + static const struct ethtool_ops ftgmac100_ethtool_ops = { .get_drvinfo = ftgmac100_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, + .nway_reset = phy_ethtool_nway_reset, + .get_ringparam = ftgmac100_get_ringparam, + .set_ringparam = ftgmac100_set_ringparam, + .get_pauseparam = ftgmac100_get_pauseparam, + .set_pauseparam = ftgmac100_set_pauseparam, }; -/****************************************************************************** - * interrupt handler - *****************************************************************************/ static irqreturn_t ftgmac100_interrupt(int irq, void *dev_id) { struct net_device *netdev = dev_id; struct ftgmac100 *priv = netdev_priv(netdev); + unsigned int status, new_mask = FTGMAC100_INT_BAD; - /* When running in NCSI mode, the interface should be ready for - * receiving or transmitting NCSI packets before it's opened. - */ - if (likely(priv->use_ncsi || netif_running(netdev))) { - /* Disable interrupts for polling */ - iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); - napi_schedule(&priv->napi); + /* Fetch and clear interrupt bits, process abnormal ones */ + status = ioread32(priv->base + FTGMAC100_OFFSET_ISR); + iowrite32(status, priv->base + FTGMAC100_OFFSET_ISR); + if (unlikely(status & FTGMAC100_INT_BAD)) { + + /* RX buffer unavailable */ + if (status & FTGMAC100_INT_NO_RXBUF) + netdev->stats.rx_over_errors++; + + /* received packet lost due to RX FIFO full */ + if (status & FTGMAC100_INT_RPKT_LOST) + netdev->stats.rx_fifo_errors++; + + /* sent packet lost due to excessive TX collision */ + if (status & FTGMAC100_INT_XPKT_LOST) + netdev->stats.tx_fifo_errors++; + + /* AHB error -> Reset the chip */ + if (status & FTGMAC100_INT_AHB_ERR) { + if (net_ratelimit()) + netdev_warn(netdev, + "AHB bus error ! Resetting chip.\n"); + iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); + schedule_work(&priv->reset_task); + return IRQ_HANDLED; + } + + /* We may need to restart the MAC after such errors, delay + * this until after we have freed some Rx buffers though + */ + priv->need_mac_restart = true; + + /* Disable those errors until we restart */ + new_mask &= ~status; } + /* Only enable "bad" interrupts while NAPI is on */ + iowrite32(new_mask, priv->base + FTGMAC100_OFFSET_IER); + + /* Schedule NAPI bh */ + napi_schedule_irqoff(&priv->napi); + return IRQ_HANDLED; } -/****************************************************************************** - * struct napi_struct functions - *****************************************************************************/ +static bool ftgmac100_check_rx(struct ftgmac100 *priv) +{ + struct ftgmac100_rxdes *rxdes = &priv->rxdes[priv->rx_pointer]; + + /* Do we have a packet ? */ + return !!(rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RXPKT_RDY)); +} + static int ftgmac100_poll(struct napi_struct *napi, int budget) { struct ftgmac100 *priv = container_of(napi, struct ftgmac100, napi); - struct net_device *netdev = priv->netdev; - unsigned int status; - bool completed = true; - int rx = 0; + int work_done = 0; + bool more; - status = ioread32(priv->base + FTGMAC100_OFFSET_ISR); - iowrite32(status, priv->base + FTGMAC100_OFFSET_ISR); + /* Handle TX completions */ + if (ftgmac100_tx_buf_cleanable(priv)) + ftgmac100_tx_complete(priv); - if (status & (FTGMAC100_INT_RPKT_BUF | FTGMAC100_INT_NO_RXBUF)) { - /* - * FTGMAC100_INT_RPKT_BUF: - * RX DMA has received packets into RX buffer successfully - * - * FTGMAC100_INT_NO_RXBUF: - * RX buffer unavailable - */ - bool retry; + /* Handle RX packets */ + do { + more = ftgmac100_rx_packet(priv, &work_done); + } while (more && work_done < budget); - do { - retry = ftgmac100_rx_packet(priv, &rx); - } while (retry && rx < budget); - if (retry && rx == budget) - completed = false; - } + /* The interrupt is telling us to kick the MAC back to life + * after an RX overflow + */ + if (unlikely(priv->need_mac_restart)) { + ftgmac100_start_hw(priv); - if (status & (FTGMAC100_INT_XPKT_ETH | FTGMAC100_INT_XPKT_LOST)) { - /* - * FTGMAC100_INT_XPKT_ETH: - * packet transmitted to ethernet successfully - * - * FTGMAC100_INT_XPKT_LOST: - * packet transmitted to ethernet lost due to late - * collision or excessive collision - */ - ftgmac100_tx_complete(priv); + /* Re-enable "bad" interrupts */ + iowrite32(FTGMAC100_INT_BAD, + priv->base + FTGMAC100_OFFSET_IER); } - if (status & priv->int_mask_all & (FTGMAC100_INT_NO_RXBUF | - FTGMAC100_INT_RPKT_LOST | FTGMAC100_INT_AHB_ERR)) { - if (net_ratelimit()) - netdev_info(netdev, "[ISR] = 0x%x: %s%s%s\n", status, - status & FTGMAC100_INT_NO_RXBUF ? "NO_RXBUF " : "", - status & FTGMAC100_INT_RPKT_LOST ? "RPKT_LOST " : "", - status & FTGMAC100_INT_AHB_ERR ? "AHB_ERR " : ""); + /* As long as we are waiting for transmit packets to be + * completed we keep NAPI going + */ + if (ftgmac100_tx_buf_cleanable(priv)) + work_done = budget; + + if (work_done < budget) { + /* We are about to re-enable all interrupts. However + * the HW has been latching RX/TX packet interrupts while + * they were masked. So we clear them first, then we need + * to re-check if there's something to process + */ + iowrite32(FTGMAC100_INT_RXTX, + priv->base + FTGMAC100_OFFSET_ISR); - if (status & FTGMAC100_INT_NO_RXBUF) { - /* RX buffer unavailable */ - netdev->stats.rx_over_errors++; - } + /* Push the above (and provides a barrier vs. subsequent + * reads of the descriptor). + */ + ioread32(priv->base + FTGMAC100_OFFSET_ISR); - if (status & FTGMAC100_INT_RPKT_LOST) { - /* received packet lost due to RX FIFO full */ - netdev->stats.rx_fifo_errors++; - } - } + /* Check RX and TX descriptors for more work to do */ + if (ftgmac100_check_rx(priv) || + ftgmac100_tx_buf_cleanable(priv)) + return budget; - if (completed) { + /* deschedule NAPI */ napi_complete(napi); /* enable all interrupts */ - iowrite32(priv->int_mask_all, + iowrite32(FTGMAC100_INT_ALL, priv->base + FTGMAC100_OFFSET_IER); } - return rx; + return work_done; } -/****************************************************************************** - * struct net_device_ops functions - *****************************************************************************/ -static int ftgmac100_open(struct net_device *netdev) +static int ftgmac100_init_all(struct ftgmac100 *priv, bool ignore_alloc_err) { - struct ftgmac100 *priv = netdev_priv(netdev); - unsigned int status; + int err = 0; + + /* Re-init descriptors (adjust queue sizes) */ + ftgmac100_init_rings(priv); + + /* Realloc rx descriptors */ + err = ftgmac100_alloc_rx_buffers(priv); + if (err && !ignore_alloc_err) + return err; + + /* Reinit and restart HW */ + ftgmac100_init_hw(priv); + ftgmac100_config_pause(priv); + ftgmac100_start_hw(priv); + + /* Re-enable the device */ + napi_enable(&priv->napi); + netif_start_queue(priv->netdev); + + /* Enable all interrupts */ + iowrite32(FTGMAC100_INT_ALL, priv->base + FTGMAC100_OFFSET_IER); + + return err; +} + +static void ftgmac100_reset_task(struct work_struct *work) +{ + struct ftgmac100 *priv = container_of(work, struct ftgmac100, + reset_task); + struct net_device *netdev = priv->netdev; int err; - err = ftgmac100_alloc_buffers(priv); + netdev_dbg(netdev, "Resetting NIC...\n"); + + /* Lock the world */ + rtnl_lock(); + if (netdev->phydev) + mutex_lock(&netdev->phydev->lock); + if (priv->mii_bus) + mutex_lock(&priv->mii_bus->mdio_lock); + + + /* Check if the interface is still up */ + if (!netif_running(netdev)) + goto bail; + + /* Stop the network stack */ + netif_trans_update(netdev); + napi_disable(&priv->napi); + netif_tx_disable(netdev); + + /* Stop and reset the MAC */ + ftgmac100_stop_hw(priv); + err = ftgmac100_reset_and_config_mac(priv); if (err) { - netdev_err(netdev, "failed to allocate buffers\n"); - goto err_alloc; + /* Not much we can do ... it might come back... */ + netdev_err(netdev, "attempting to continue...\n"); } - err = request_irq(priv->irq, ftgmac100_interrupt, 0, netdev->name, netdev); + /* Free all rx and tx buffers */ + ftgmac100_free_buffers(priv); + + /* Setup everything again and restart chip */ + ftgmac100_init_all(priv, true); + + netdev_dbg(netdev, "Reset done !\n"); + bail: + if (priv->mii_bus) + mutex_unlock(&priv->mii_bus->mdio_lock); + if (netdev->phydev) + mutex_unlock(&netdev->phydev->lock); + rtnl_unlock(); +} + +static int ftgmac100_open(struct net_device *netdev) +{ + struct ftgmac100 *priv = netdev_priv(netdev); + int err; + + /* Allocate ring buffers */ + err = ftgmac100_alloc_rings(priv); if (err) { - netdev_err(netdev, "failed to request irq %d\n", priv->irq); - goto err_irq; + netdev_err(netdev, "Failed to allocate descriptors\n"); + return err; } - priv->rx_pointer = 0; - priv->tx_clean_pointer = 0; - priv->tx_pointer = 0; - priv->tx_pending = 0; + /* When using NC-SI we force the speed to 100Mbit/s full duplex, + * + * Otherwise we leave it set to 0 (no link), the link + * message from the PHY layer will handle setting it up to + * something else if needed. + */ + if (priv->use_ncsi) { + priv->cur_duplex = DUPLEX_FULL; + priv->cur_speed = SPEED_100; + } else { + priv->cur_duplex = 0; + priv->cur_speed = 0; + } - err = ftgmac100_reset_hw(priv); + /* Reset the hardware */ + err = ftgmac100_reset_and_config_mac(priv); if (err) goto err_hw; - ftgmac100_init_hw(priv); - ftgmac100_start_hw(priv, priv->use_ncsi ? 100 : 10); + /* Initialize NAPI */ + netif_napi_add(netdev, &priv->napi, ftgmac100_poll, 64); - /* Clear stale interrupts */ - status = ioread32(priv->base + FTGMAC100_OFFSET_ISR); - iowrite32(status, priv->base + FTGMAC100_OFFSET_ISR); + /* Grab our interrupt */ + err = request_irq(netdev->irq, ftgmac100_interrupt, 0, netdev->name, netdev); + if (err) { + netdev_err(netdev, "failed to request irq %d\n", netdev->irq); + goto err_irq; + } - if (netdev->phydev) + /* Start things up */ + err = ftgmac100_init_all(priv, false); + if (err) { + netdev_err(netdev, "Failed to allocate packet buffers\n"); + goto err_alloc; + } + + if (netdev->phydev) { + /* If we have a PHY, start polling */ phy_start(netdev->phydev); - else if (priv->use_ncsi) + } else if (priv->use_ncsi) { + /* If using NC-SI, set our carrier on and start the stack */ netif_carrier_on(netdev); - napi_enable(&priv->napi); - netif_start_queue(netdev); - - /* enable all interrupts */ - iowrite32(priv->int_mask_all, priv->base + FTGMAC100_OFFSET_IER); - - /* Start the NCSI device */ - if (priv->use_ncsi) { + /* Start the NCSI device */ err = ncsi_start_dev(priv->ndev); if (err) goto err_ncsi; } - priv->enabled = true; - return 0; -err_ncsi: + err_ncsi: napi_disable(&priv->napi); netif_stop_queue(netdev); - iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); -err_hw: - free_irq(priv->irq, netdev); -err_irq: + err_alloc: ftgmac100_free_buffers(priv); -err_alloc: + free_irq(netdev->irq, netdev); + err_irq: + netif_napi_del(&priv->napi); + err_hw: + iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); + ftgmac100_free_rings(priv); return err; } @@ -1179,64 +1528,87 @@ static int ftgmac100_stop(struct net_device *netdev) { struct ftgmac100 *priv = netdev_priv(netdev); - if (!priv->enabled) - return 0; + /* Note about the reset task: We are called with the rtnl lock + * held, so we are synchronized against the core of the reset + * task. We must not try to synchronously cancel it otherwise + * we can deadlock. But since it will test for netif_running() + * which has already been cleared by the net core, we don't + * anything special to do. + */ /* disable all interrupts */ - priv->enabled = false; iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); netif_stop_queue(netdev); napi_disable(&priv->napi); + netif_napi_del(&priv->napi); if (netdev->phydev) phy_stop(netdev->phydev); else if (priv->use_ncsi) ncsi_stop_dev(priv->ndev); ftgmac100_stop_hw(priv); - free_irq(priv->irq, netdev); + free_irq(netdev->irq, netdev); ftgmac100_free_buffers(priv); + ftgmac100_free_rings(priv); return 0; } -static int ftgmac100_hard_start_xmit(struct sk_buff *skb, - struct net_device *netdev) +/* optional */ +static int ftgmac100_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +{ + if (!netdev->phydev) + return -ENXIO; + + return phy_mii_ioctl(netdev->phydev, ifr, cmd); +} + +static void ftgmac100_tx_timeout(struct net_device *netdev) { struct ftgmac100 *priv = netdev_priv(netdev); - dma_addr_t map; - if (unlikely(skb->len > MAX_PKT_SIZE)) { - if (net_ratelimit()) - netdev_dbg(netdev, "tx packet too big\n"); + /* Disable all interrupts */ + iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); - netdev->stats.tx_dropped++; - kfree_skb(skb); - return NETDEV_TX_OK; - } + /* Do the reset outside of interrupt context */ + schedule_work(&priv->reset_task); +} - map = dma_map_single(priv->dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(priv->dev, map))) { - /* drop packet */ - if (net_ratelimit()) - netdev_err(netdev, "map socket buffer failed\n"); +static int ftgmac100_set_features(struct net_device *netdev, + netdev_features_t features) +{ + struct ftgmac100 *priv = netdev_priv(netdev); + netdev_features_t changed = netdev->features ^ features; - netdev->stats.tx_dropped++; - kfree_skb(skb); - return NETDEV_TX_OK; + if (!netif_running(netdev)) + return 0; + + /* Update the vlan filtering bit */ + if (changed & NETIF_F_HW_VLAN_CTAG_RX) { + u32 maccr; + + maccr = ioread32(priv->base + FTGMAC100_OFFSET_MACCR); + if (priv->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) + maccr |= FTGMAC100_MACCR_RM_VLAN; + else + maccr &= ~FTGMAC100_MACCR_RM_VLAN; + iowrite32(maccr, priv->base + FTGMAC100_OFFSET_MACCR); } - return ftgmac100_xmit(priv, skb, map); + return 0; } -/* optional */ -static int ftgmac100_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +#ifdef CONFIG_NET_POLL_CONTROLLER +static void ftgmac100_poll_controller(struct net_device *netdev) { - if (!netdev->phydev) - return -ENXIO; + unsigned long flags; - return phy_mii_ioctl(netdev->phydev, ifr, cmd); + local_irq_save(flags); + ftgmac100_interrupt(netdev->irq, netdev); + local_irq_restore(flags); } +#endif static const struct net_device_ops ftgmac100_netdev_ops = { .ndo_open = ftgmac100_open, @@ -1245,12 +1617,20 @@ static const struct net_device_ops ftgmac100_netdev_ops = { .ndo_set_mac_address = ftgmac100_set_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_do_ioctl = ftgmac100_do_ioctl, + .ndo_tx_timeout = ftgmac100_tx_timeout, + .ndo_set_rx_mode = ftgmac100_set_rx_mode, + .ndo_set_features = ftgmac100_set_features, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = ftgmac100_poll_controller, +#endif }; static int ftgmac100_setup_mdio(struct net_device *netdev) { struct ftgmac100 *priv = netdev_priv(netdev); struct platform_device *pdev = to_platform_device(priv->dev); + int phy_intf = PHY_INTERFACE_MODE_RGMII; + struct device_node *np = pdev->dev.of_node; int i, err = 0; u32 reg; @@ -1259,14 +1639,46 @@ static int ftgmac100_setup_mdio(struct net_device *netdev) if (!priv->mii_bus) return -EIO; - if (of_machine_is_compatible("aspeed,ast2400") || - of_machine_is_compatible("aspeed,ast2500")) { + if (priv->is_aspeed) { /* This driver supports the old MDIO interface */ reg = ioread32(priv->base + FTGMAC100_OFFSET_REVR); reg &= ~FTGMAC100_REVR_NEW_MDIO_INTERFACE; iowrite32(reg, priv->base + FTGMAC100_OFFSET_REVR); }; + /* Get PHY mode from device-tree */ + if (np) { + /* Default to RGMII. It's a gigabit part after all */ + phy_intf = of_get_phy_mode(np); + if (phy_intf < 0) + phy_intf = PHY_INTERFACE_MODE_RGMII; + + /* Aspeed only supports these. I don't know about other IP + * block vendors so I'm going to just let them through for + * now. Note that this is only a warning if for some obscure + * reason the DT really means to lie about it or it's a newer + * part we don't know about. + * + * On the Aspeed SoC there are additionally straps and SCU + * control bits that could tell us what the interface is + * (or allow us to configure it while the IP block is held + * in reset). For now I chose to keep this driver away from + * those SoC specific bits and assume the device-tree is + * right and the SCU has been configured properly by pinmux + * or the firmware. + */ + if (priv->is_aspeed && + phy_intf != PHY_INTERFACE_MODE_RMII && + phy_intf != PHY_INTERFACE_MODE_RGMII && + phy_intf != PHY_INTERFACE_MODE_RGMII_ID && + phy_intf != PHY_INTERFACE_MODE_RGMII_RXID && + phy_intf != PHY_INTERFACE_MODE_RGMII_TXID) { + netdev_warn(netdev, + "Unsupported PHY mode %s !\n", + phy_modes(phy_intf)); + } + } + priv->mii_bus->name = "ftgmac100_mdio"; snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%d", pdev->name, pdev->id); @@ -1283,7 +1695,7 @@ static int ftgmac100_setup_mdio(struct net_device *netdev) goto err_register_mdiobus; } - err = ftgmac100_mii_probe(priv); + err = ftgmac100_mii_probe(priv, phy_intf); if (err) { dev_err(priv->dev, "MII Probe failed!\n"); goto err_mii_probe; @@ -1319,15 +1731,13 @@ static void ftgmac100_ncsi_handler(struct ncsi_dev *nd) nd->link_up ? "up" : "down"); } -/****************************************************************************** - * struct platform_driver functions - *****************************************************************************/ static int ftgmac100_probe(struct platform_device *pdev) { struct resource *res; int irq; struct net_device *netdev; struct ftgmac100 *priv; + struct device_node *np; int err = 0; if (!pdev) @@ -1352,6 +1762,7 @@ static int ftgmac100_probe(struct platform_device *pdev) netdev->ethtool_ops = &ftgmac100_ethtool_ops; netdev->netdev_ops = &ftgmac100_netdev_ops; + netdev->watchdog_timeo = 5 * HZ; platform_set_drvdata(pdev, netdev); @@ -1359,11 +1770,7 @@ static int ftgmac100_probe(struct platform_device *pdev) priv = netdev_priv(netdev); priv->netdev = netdev; priv->dev = &pdev->dev; - - spin_lock_init(&priv->tx_lock); - - /* initialize NAPI */ - netif_napi_add(netdev, &priv->napi, ftgmac100_poll, 64); + INIT_WORK(&priv->reset_task, ftgmac100_reset_task); /* map io memory */ priv->res = request_mem_region(res->start, resource_size(res), @@ -1381,29 +1788,28 @@ static int ftgmac100_probe(struct platform_device *pdev) goto err_ioremap; } - priv->irq = irq; + netdev->irq = irq; - /* MAC address from chip or random one */ - ftgmac100_setup_mac(priv); + /* Enable pause */ + priv->tx_pause = true; + priv->rx_pause = true; + priv->aneg_pause = true; - priv->int_mask_all = (FTGMAC100_INT_RPKT_LOST | - FTGMAC100_INT_XPKT_ETH | - FTGMAC100_INT_XPKT_LOST | - FTGMAC100_INT_AHB_ERR | - FTGMAC100_INT_RPKT_BUF | - FTGMAC100_INT_NO_RXBUF); + /* MAC address from chip or random one */ + ftgmac100_initial_mac(priv); - if (of_machine_is_compatible("aspeed,ast2400") || - of_machine_is_compatible("aspeed,ast2500")) { + np = pdev->dev.of_node; + if (np && (of_device_is_compatible(np, "aspeed,ast2400-mac") || + of_device_is_compatible(np, "aspeed,ast2500-mac"))) { priv->rxdes0_edorr_mask = BIT(30); priv->txdes0_edotr_mask = BIT(30); + priv->is_aspeed = true; } else { priv->rxdes0_edorr_mask = BIT(15); priv->txdes0_edotr_mask = BIT(15); } - if (pdev->dev.of_node && - of_get_property(pdev->dev.of_node, "use-ncsi", NULL)) { + if (np && of_get_property(np, "use-ncsi", NULL)) { if (!IS_ENABLED(CONFIG_NET_NCSI)) { dev_err(&pdev->dev, "NCSI stack not enabled\n"); goto err_ncsi_dev; @@ -1421,15 +1827,21 @@ static int ftgmac100_probe(struct platform_device *pdev) goto err_setup_mdio; } - /* We have to disable on-chip IP checksum functionality - * when NCSI is enabled on the interface. It doesn't work - * in that case. - */ - netdev->features = NETIF_F_IP_CSUM | NETIF_F_GRO; - if (priv->use_ncsi && - of_get_property(pdev->dev.of_node, "no-hw-checksum", NULL)) - netdev->features &= ~NETIF_F_IP_CSUM; + /* Default ring sizes */ + priv->rx_q_entries = priv->new_rx_q_entries = DEF_RX_QUEUE_ENTRIES; + priv->tx_q_entries = priv->new_tx_q_entries = DEF_TX_QUEUE_ENTRIES; + /* Base feature set */ + netdev->hw_features = NETIF_F_RXCSUM | NETIF_F_HW_CSUM | + NETIF_F_GRO | NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX; + + /* AST2400 doesn't have working HW checksum generation */ + if (np && (of_device_is_compatible(np, "aspeed,ast2400-mac"))) + netdev->hw_features &= ~NETIF_F_HW_CSUM; + if (np && of_get_property(np, "no-hw-checksum", NULL)) + netdev->hw_features &= ~(NETIF_F_HW_CSUM | NETIF_F_RXCSUM); + netdev->features |= netdev->hw_features; /* register network device */ err = register_netdev(netdev); @@ -1438,7 +1850,7 @@ static int ftgmac100_probe(struct platform_device *pdev) goto err_register_netdev; } - netdev_info(netdev, "irq %d, mapped at %p\n", priv->irq, priv->base); + netdev_info(netdev, "irq %d, mapped at %p\n", netdev->irq, priv->base); return 0; @@ -1465,6 +1877,12 @@ static int ftgmac100_remove(struct platform_device *pdev) priv = netdev_priv(netdev); unregister_netdev(netdev); + + /* There's a small chance the reset task will have been re-queued, + * during stop, make sure it's gone before we free the structure. + */ + cancel_work_sync(&priv->reset_task); + ftgmac100_destroy_mdio(netdev); iounmap(priv->base); diff --git a/drivers/net/ethernet/faraday/ftgmac100.h b/drivers/net/ethernet/faraday/ftgmac100.h index a7ce0ac8858a..0653d8176e6a 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.h +++ b/drivers/net/ethernet/faraday/ftgmac100.h @@ -86,6 +86,20 @@ #define FTGMAC100_INT_PHYSTS_CHG (1 << 9) #define FTGMAC100_INT_NO_HPTXBUF (1 << 10) +/* Interrupts we care about in NAPI mode */ +#define FTGMAC100_INT_BAD (FTGMAC100_INT_RPKT_LOST | \ + FTGMAC100_INT_XPKT_LOST | \ + FTGMAC100_INT_AHB_ERR | \ + FTGMAC100_INT_NO_RXBUF) + +/* Normal RX/TX interrupts, enabled when NAPI off */ +#define FTGMAC100_INT_RXTX (FTGMAC100_INT_XPKT_ETH | \ + FTGMAC100_INT_RPKT_BUF) + +/* All the interrupts we care about */ +#define FTGMAC100_INT_ALL (FTGMAC100_INT_RPKT_BUF | \ + FTGMAC100_INT_BAD) + /* * Interrupt timer control register */ @@ -185,13 +199,20 @@ #define FTGMAC100_PHYDATA_MIIRDATA(phydata) (((phydata) >> 16) & 0xffff) /* + * Flow control register + */ +#define FTGMAC100_FCR_FC_EN (1 << 0) +#define FTGMAC100_FCR_FCTHR_EN (1 << 2) +#define FTGMAC100_FCR_PAUSE_TIME(x) (((x) & 0xffff) << 16) + +/* * Transmit descriptor, aligned to 16 bytes */ struct ftgmac100_txdes { - unsigned int txdes0; - unsigned int txdes1; - unsigned int txdes2; /* not used by HW */ - unsigned int txdes3; /* TXBUF_BADR */ + __le32 txdes0; /* Control & status bits */ + __le32 txdes1; /* Irq, checksum and vlan control */ + __le32 txdes2; /* Reserved */ + __le32 txdes3; /* DMA buffer address */ } __attribute__ ((aligned(16))); #define FTGMAC100_TXDES0_TXBUF_SIZE(x) ((x) & 0x3fff) @@ -213,10 +234,10 @@ struct ftgmac100_txdes { * Receive descriptor, aligned to 16 bytes */ struct ftgmac100_rxdes { - unsigned int rxdes0; - unsigned int rxdes1; - unsigned int rxdes2; /* not used by HW */ - unsigned int rxdes3; /* RXBUF_BADR */ + __le32 rxdes0; /* Control & status bits */ + __le32 rxdes1; /* Checksum and vlan status */ + __le32 rxdes2; /* length/type on AST2500 */ + __le32 rxdes3; /* DMA buffer address */ } __attribute__ ((aligned(16))); #define FTGMAC100_RXDES0_VDBC 0x3fff @@ -234,6 +255,14 @@ struct ftgmac100_rxdes { #define FTGMAC100_RXDES0_FRS (1 << 29) #define FTGMAC100_RXDES0_RXPKT_RDY (1 << 31) +/* Errors we care about for dropping packets */ +#define RXDES0_ANY_ERROR ( \ + FTGMAC100_RXDES0_RX_ERR | \ + FTGMAC100_RXDES0_CRC_ERR | \ + FTGMAC100_RXDES0_FTL | \ + FTGMAC100_RXDES0_RUNT | \ + FTGMAC100_RXDES0_RX_ODD_NB) + #define FTGMAC100_RXDES1_VLANTAG_CI 0xffff #define FTGMAC100_RXDES1_PROT_MASK (0x3 << 20) #define FTGMAC100_RXDES1_PROT_NONIP (0x0 << 20) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 91a16641e851..a92bf94f8e94 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -117,8 +117,9 @@ static struct platform_device_id fec_devtype[] = { .name = "imx6ul-fec", .driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT | FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | - FEC_QUIRK_HAS_VLAN | FEC_QUIRK_BUG_CAPTURE | - FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE, + FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 | + FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC | + FEC_QUIRK_HAS_COALESCE, }, { /* sentinel */ } @@ -235,14 +236,14 @@ static struct bufdesc *fec_enet_get_nextdesc(struct bufdesc *bdp, struct bufdesc_prop *bd) { return (bdp >= bd->last) ? bd->base - : (struct bufdesc *)(((unsigned)bdp) + bd->dsize); + : (struct bufdesc *)(((void *)bdp) + bd->dsize); } static struct bufdesc *fec_enet_get_prevdesc(struct bufdesc *bdp, struct bufdesc_prop *bd) { return (bdp <= bd->base) ? bd->last - : (struct bufdesc *)(((unsigned)bdp) - bd->dsize); + : (struct bufdesc *)(((void *)bdp) - bd->dsize); } static int fec_enet_get_bd_index(struct bufdesc *bdp, @@ -1266,7 +1267,7 @@ skb_done: } } - /* ERR006538: Keep the transmitter going */ + /* ERR006358: Keep the transmitter going */ if (bdp != txq->bd.cur && readl(txq->bd.reg_desc_active) == 0) writel(0, txq->bd.reg_desc_active); @@ -2651,7 +2652,7 @@ static void fec_enet_free_queue(struct net_device *ndev) for (i = 0; i < fep->num_tx_queues; i++) if (fep->tx_queue[i] && fep->tx_queue[i]->tso_hdrs) { txq = fep->tx_queue[i]; - dma_free_coherent(NULL, + dma_free_coherent(&fep->pdev->dev, txq->bd.ring_size * TSO_HEADER_SIZE, txq->tso_hdrs, txq->tso_hdrs_dma); @@ -2685,7 +2686,7 @@ static int fec_enet_alloc_queue(struct net_device *ndev) txq->tx_wake_threshold = (txq->bd.ring_size - txq->tx_stop_threshold) / 2; - txq->tso_hdrs = dma_alloc_coherent(NULL, + txq->tso_hdrs = dma_alloc_coherent(&fep->pdev->dev, txq->bd.ring_size * TSO_HEADER_SIZE, &txq->tso_hdrs_dma, GFP_KERNEL); @@ -3187,7 +3188,7 @@ static int fec_enet_init(struct net_device *ndev) } #ifdef CONFIG_OF -static void fec_reset_phy(struct platform_device *pdev) +static int fec_reset_phy(struct platform_device *pdev) { int err, phy_reset; bool active_high = false; @@ -3195,16 +3196,18 @@ static void fec_reset_phy(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; if (!np) - return; + return 0; - of_property_read_u32(np, "phy-reset-duration", &msec); + err = of_property_read_u32(np, "phy-reset-duration", &msec); /* A sane reset duration should not be longer than 1s */ - if (msec > 1000) + if (!err && msec > 1000) msec = 1; phy_reset = of_get_named_gpio(np, "phy-reset-gpios", 0); - if (!gpio_is_valid(phy_reset)) - return; + if (phy_reset == -EPROBE_DEFER) + return phy_reset; + else if (!gpio_is_valid(phy_reset)) + return 0; active_high = of_property_read_bool(np, "phy-reset-active-high"); @@ -3213,7 +3216,7 @@ static void fec_reset_phy(struct platform_device *pdev) "phy-reset"); if (err) { dev_err(&pdev->dev, "failed to get phy-reset-gpios: %d\n", err); - return; + return err; } if (msec > 20) @@ -3222,14 +3225,17 @@ static void fec_reset_phy(struct platform_device *pdev) usleep_range(msec * 1000, msec * 1000 + 1000); gpio_set_value_cansleep(phy_reset, !active_high); + + return 0; } #else /* CONFIG_OF */ -static void fec_reset_phy(struct platform_device *pdev) +static int fec_reset_phy(struct platform_device *pdev) { /* * In case of platform probe, the reset has been done * by machine code. */ + return 0; } #endif /* CONFIG_OF */ @@ -3400,6 +3406,7 @@ fec_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "Failed to enable phy regulator: %d\n", ret); + clk_disable_unprepare(fep->clk_ipg); goto failed_regulator; } } else { @@ -3412,7 +3419,9 @@ fec_probe(struct platform_device *pdev) pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); - fec_reset_phy(pdev); + ret = fec_reset_phy(pdev); + if (ret) + goto failed_reset; if (fep->bufdesc_ex) fec_ptp_init(pdev); @@ -3473,8 +3482,10 @@ failed_init: fec_ptp_stop(pdev); if (fep->reg_phy) regulator_disable(fep->reg_phy); +failed_reset: + pm_runtime_put(&pdev->dev); + pm_runtime_disable(&pdev->dev); failed_regulator: - clk_disable_unprepare(fep->clk_ipg); failed_clk_ipg: fec_enet_clk_enable(ndev, false); failed_clk: diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 120427a40883..9d9b6e6dd988 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -57,11 +57,15 @@ static int hnae_alloc_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb) static void hnae_free_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb) { + if (unlikely(!cb->priv)) + return; + if (cb->type == DESC_TYPE_SKB) dev_kfree_skb_any((struct sk_buff *)cb->priv); else if (unlikely(is_rx_ring(ring))) put_page((struct page *)cb->priv); - memset(cb, 0, sizeof(*cb)); + + cb->priv = NULL; } static int hnae_map_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb) @@ -197,6 +201,7 @@ hnae_init_ring(struct hnae_queue *q, struct hnae_ring *ring, int flags) ring->q = q; ring->flags = flags; + spin_lock_init(&ring->lock); assert(!ring->desc && !ring->desc_cb && !ring->desc_dma_addr); /* not matter for tx or rx ring, the ntc and ntc start from 0 */ diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index 8016854796fb..04211ac73b36 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -67,6 +67,8 @@ do { \ #define AE_IS_VER1(ver) ((ver) == AE_VERSION_1) #define AE_NAME_SIZE 16 +#define BD_SIZE_2048_MAX_MTU 6000 + /* some said the RX and TX RCB format should not be the same in the future. But * it is the same now... */ @@ -101,7 +103,6 @@ enum hnae_led_state { #define HNS_RX_FLAG_L4ID_TCP 0x1 #define HNS_RX_FLAG_L4ID_SCTP 0x3 - #define HNS_TXD_ASID_S 0 #define HNS_TXD_ASID_M (0xff << HNS_TXD_ASID_S) #define HNS_TXD_BUFNUM_S 8 @@ -273,6 +274,9 @@ struct hnae_ring { /* statistic */ struct ring_stats stats; + /* ring lock for poll one */ + spinlock_t lock; + dma_addr_t desc_dma_addr; u32 buf_size; /* size for hnae_desc->addr, preset by AE */ u16 desc_num; /* total number of desc */ @@ -483,11 +487,11 @@ struct hnae_ae_ops { u32 auto_neg, u32 rx_en, u32 tx_en); void (*get_coalesce_usecs)(struct hnae_handle *handle, u32 *tx_usecs, u32 *rx_usecs); - void (*get_rx_max_coalesced_frames)(struct hnae_handle *handle, - u32 *tx_frames, u32 *rx_frames); + void (*get_max_coalesced_frames)(struct hnae_handle *handle, + u32 *tx_frames, u32 *rx_frames); int (*set_coalesce_usecs)(struct hnae_handle *handle, u32 timeout); int (*set_coalesce_frames)(struct hnae_handle *handle, - u32 coalesce_frames); + u32 tx_frames, u32 rx_frames); void (*get_coalesce_range)(struct hnae_handle *handle, u32 *tx_frames_low, u32 *rx_frames_low, u32 *tx_frames_high, u32 *rx_frames_high, @@ -646,6 +650,41 @@ static inline void hnae_reuse_buffer(struct hnae_ring *ring, int i) ring->desc[i].rx.ipoff_bnum_pid_flag = 0; } +/* when reinit buffer size, we should reinit buffer description */ +static inline void hnae_reinit_all_ring_desc(struct hnae_handle *h) +{ + int i, j; + struct hnae_ring *ring; + + for (i = 0; i < h->q_num; i++) { + ring = &h->qs[i]->rx_ring; + for (j = 0; j < ring->desc_num; j++) + ring->desc[j].addr = cpu_to_le64(ring->desc_cb[j].dma); + } + + wmb(); /* commit all data before submit */ +} + +/* when reinit buffer size, we should reinit page offset */ +static inline void hnae_reinit_all_ring_page_off(struct hnae_handle *h) +{ + int i, j; + struct hnae_ring *ring; + + for (i = 0; i < h->q_num; i++) { + ring = &h->qs[i]->rx_ring; + for (j = 0; j < ring->desc_num; j++) { + ring->desc_cb[j].page_offset = 0; + if (ring->desc[j].addr != + cpu_to_le64(ring->desc_cb[j].dma)) + ring->desc[j].addr = + cpu_to_le64(ring->desc_cb[j].dma); + } + } + + wmb(); /* commit all data before submit */ +} + #define hnae_set_field(origin, mask, shift, val) \ do { \ (origin) &= (~(mask)); \ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index 0a9cdf00b31a..ff864a187d5a 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -267,8 +267,32 @@ static int hns_ae_clr_multicast(struct hnae_handle *handle) static int hns_ae_set_mtu(struct hnae_handle *handle, int new_mtu) { struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); + struct hnae_queue *q; + u32 rx_buf_size; + int i, ret; + + /* when buf_size is 2048, max mtu is 6K for rx ring max bd num is 3. */ + if (!AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver)) { + if (new_mtu <= BD_SIZE_2048_MAX_MTU) + rx_buf_size = 2048; + else + rx_buf_size = 4096; + } else { + rx_buf_size = mac_cb->dsaf_dev->buf_size; + } + + ret = hns_mac_set_mtu(mac_cb, new_mtu, rx_buf_size); - return hns_mac_set_mtu(mac_cb, new_mtu); + if (!ret) { + /* reinit ring buf_size */ + for (i = 0; i < handle->q_num; i++) { + q = handle->qs[i]; + q->rx_ring.buf_size = rx_buf_size; + hns_rcb_set_rx_ring_bs(q, rx_buf_size); + } + } + + return ret; } static void hns_ae_set_tso_stats(struct hnae_handle *handle, int enable) @@ -463,15 +487,21 @@ static void hns_ae_get_coalesce_usecs(struct hnae_handle *handle, ring_pair->port_id_in_comm); } -static void hns_ae_get_rx_max_coalesced_frames(struct hnae_handle *handle, - u32 *tx_frames, u32 *rx_frames) +static void hns_ae_get_max_coalesced_frames(struct hnae_handle *handle, + u32 *tx_frames, u32 *rx_frames) { struct ring_pair_cb *ring_pair = container_of(handle->qs[0], struct ring_pair_cb, q); + struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev); - *tx_frames = hns_rcb_get_coalesced_frames(ring_pair->rcb_common, - ring_pair->port_id_in_comm); - *rx_frames = hns_rcb_get_coalesced_frames(ring_pair->rcb_common, + if (AE_IS_VER1(dsaf_dev->dsaf_ver) || + handle->port_type == HNAE_PORT_DEBUG) + *tx_frames = hns_rcb_get_rx_coalesced_frames( + ring_pair->rcb_common, ring_pair->port_id_in_comm); + else + *tx_frames = hns_rcb_get_tx_coalesced_frames( + ring_pair->rcb_common, ring_pair->port_id_in_comm); + *rx_frames = hns_rcb_get_rx_coalesced_frames(ring_pair->rcb_common, ring_pair->port_id_in_comm); } @@ -485,15 +515,34 @@ static int hns_ae_set_coalesce_usecs(struct hnae_handle *handle, ring_pair->rcb_common, ring_pair->port_id_in_comm, timeout); } -static int hns_ae_set_coalesce_frames(struct hnae_handle *handle, - u32 coalesce_frames) +static int hns_ae_set_coalesce_frames(struct hnae_handle *handle, + u32 tx_frames, u32 rx_frames) { + int ret; struct ring_pair_cb *ring_pair = container_of(handle->qs[0], struct ring_pair_cb, q); + struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev); - return hns_rcb_set_coalesced_frames( - ring_pair->rcb_common, - ring_pair->port_id_in_comm, coalesce_frames); + if (AE_IS_VER1(dsaf_dev->dsaf_ver) || + handle->port_type == HNAE_PORT_DEBUG) { + if (tx_frames != rx_frames) + return -EINVAL; + return hns_rcb_set_rx_coalesced_frames( + ring_pair->rcb_common, + ring_pair->port_id_in_comm, rx_frames); + } else { + if (tx_frames != 1) + return -EINVAL; + ret = hns_rcb_set_tx_coalesced_frames( + ring_pair->rcb_common, + ring_pair->port_id_in_comm, tx_frames); + if (ret) + return ret; + + return hns_rcb_set_rx_coalesced_frames( + ring_pair->rcb_common, + ring_pair->port_id_in_comm, rx_frames); + } } static void hns_ae_get_coalesce_range(struct hnae_handle *handle, @@ -504,20 +553,27 @@ static void hns_ae_get_coalesce_range(struct hnae_handle *handle, { struct dsaf_device *dsaf_dev; + assert(handle); + dsaf_dev = hns_ae_get_dsaf_dev(handle->dev); - *tx_frames_low = HNS_RCB_MIN_COALESCED_FRAMES; - *rx_frames_low = HNS_RCB_MIN_COALESCED_FRAMES; - *tx_frames_high = - (dsaf_dev->desc_num - 1 > HNS_RCB_MAX_COALESCED_FRAMES) ? - HNS_RCB_MAX_COALESCED_FRAMES : dsaf_dev->desc_num - 1; - *rx_frames_high = - (dsaf_dev->desc_num - 1 > HNS_RCB_MAX_COALESCED_FRAMES) ? - HNS_RCB_MAX_COALESCED_FRAMES : dsaf_dev->desc_num - 1; - *tx_usecs_low = 0; - *rx_usecs_low = 0; - *tx_usecs_high = HNS_RCB_MAX_COALESCED_USECS; - *rx_usecs_high = HNS_RCB_MAX_COALESCED_USECS; + *tx_frames_low = HNS_RCB_TX_FRAMES_LOW; + *rx_frames_low = HNS_RCB_RX_FRAMES_LOW; + + if (AE_IS_VER1(dsaf_dev->dsaf_ver) || + handle->port_type == HNAE_PORT_DEBUG) + *tx_frames_high = + (dsaf_dev->desc_num - 1 > HNS_RCB_TX_FRAMES_HIGH) ? + HNS_RCB_TX_FRAMES_HIGH : dsaf_dev->desc_num - 1; + else + *tx_frames_high = 1; + + *rx_frames_high = (dsaf_dev->desc_num - 1 > HNS_RCB_RX_FRAMES_HIGH) ? + HNS_RCB_RX_FRAMES_HIGH : dsaf_dev->desc_num - 1; + *tx_usecs_low = HNS_RCB_TX_USECS_LOW; + *rx_usecs_low = HNS_RCB_RX_USECS_LOW; + *tx_usecs_high = HNS_RCB_TX_USECS_HIGH; + *rx_usecs_high = HNS_RCB_RX_USECS_HIGH; } void hns_ae_update_stats(struct hnae_handle *handle, @@ -802,8 +858,9 @@ static int hns_ae_get_rss(struct hnae_handle *handle, u32 *indir, u8 *key, memcpy(key, ppe_cb->rss_key, HNS_PPEV2_RSS_KEY_SIZE); /* update the current hash->queue mappings from the shadow RSS table */ - memcpy(indir, ppe_cb->rss_indir_table, - HNS_PPEV2_RSS_IND_TBL_SIZE * sizeof(*indir)); + if (indir) + memcpy(indir, ppe_cb->rss_indir_table, + HNS_PPEV2_RSS_IND_TBL_SIZE * sizeof(*indir)); return 0; } @@ -814,15 +871,19 @@ static int hns_ae_set_rss(struct hnae_handle *handle, const u32 *indir, struct hns_ppe_cb *ppe_cb = hns_get_ppe_cb(handle); /* set the RSS Hash Key if specififed by the user */ - if (key) - hns_ppe_set_rss_key(ppe_cb, (u32 *)key); + if (key) { + memcpy(ppe_cb->rss_key, key, HNS_PPEV2_RSS_KEY_SIZE); + hns_ppe_set_rss_key(ppe_cb, ppe_cb->rss_key); + } - /* update the shadow RSS table with user specified qids */ - memcpy(ppe_cb->rss_indir_table, indir, - HNS_PPEV2_RSS_IND_TBL_SIZE * sizeof(*indir)); + if (indir) { + /* update the shadow RSS table with user specified qids */ + memcpy(ppe_cb->rss_indir_table, indir, + HNS_PPEV2_RSS_IND_TBL_SIZE * sizeof(*indir)); - /* now update the hardware */ - hns_ppe_set_indir_table(ppe_cb, ppe_cb->rss_indir_table); + /* now update the hardware */ + hns_ppe_set_indir_table(ppe_cb, ppe_cb->rss_indir_table); + } return 0; } @@ -846,7 +907,7 @@ static struct hnae_ae_ops hns_dsaf_ops = { .get_autoneg = hns_ae_get_autoneg, .set_pauseparam = hns_ae_set_pauseparam, .get_coalesce_usecs = hns_ae_get_coalesce_usecs, - .get_rx_max_coalesced_frames = hns_ae_get_rx_max_coalesced_frames, + .get_max_coalesced_frames = hns_ae_get_max_coalesced_frames, .set_coalesce_usecs = hns_ae_set_coalesce_usecs, .set_coalesce_frames = hns_ae_set_coalesce_frames, .get_coalesce_range = hns_ae_get_coalesce_range, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index 3382441fe7b5..74bd260ca02a 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -86,12 +86,11 @@ static void hns_gmac_disable(void *mac_drv, enum mac_commom_mode mode) dsaf_set_dev_bit(drv, GMAC_PORT_EN_REG, GMAC_PORT_RX_EN_B, 0); } -/** -*hns_gmac_get_en - get port enable -*@mac_drv:mac device -*@rx:rx enable -*@tx:tx enable -*/ +/* hns_gmac_get_en - get port enable + * @mac_drv:mac device + * @rx:rx enable + * @tx:tx enable + */ static void hns_gmac_get_en(void *mac_drv, u32 *rx, u32 *tx) { struct mac_driver *drv = (struct mac_driver *)mac_drv; @@ -148,6 +147,17 @@ static void hns_gmac_config_max_frame_length(void *mac_drv, u16 newval) GMAC_MAX_FRM_SIZE_S, newval); } +static void hns_gmac_config_pad_and_crc(void *mac_drv, u8 newval) +{ + u32 tx_ctrl; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG); + dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, !!newval); + dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, !!newval); + dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl); +} + static void hns_gmac_config_an_mode(void *mac_drv, u8 newval) { struct mac_driver *drv = (struct mac_driver *)mac_drv; @@ -250,7 +260,6 @@ static void hns_gmac_get_pausefrm_cfg(void *mac_drv, u32 *rx_pause_en, static int hns_gmac_adjust_link(void *mac_drv, enum mac_speed speed, u32 full_duplex) { - u32 tx_ctrl; struct mac_driver *drv = (struct mac_driver *)mac_drv; dsaf_set_dev_bit(drv, GMAC_DUPLEX_TYPE_REG, @@ -279,14 +288,6 @@ static int hns_gmac_adjust_link(void *mac_drv, enum mac_speed speed, return -EINVAL; } - tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG); - dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, 1); - dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, 1); - dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl); - - dsaf_set_dev_bit(drv, GMAC_MODE_CHANGE_EN_REG, - GMAC_MODE_CHANGE_EB_B, 1); - return 0; } @@ -325,6 +326,17 @@ static void hns_gmac_init(void *mac_drv) hns_gmac_tx_loop_pkt_dis(mac_drv); if (drv->mac_cb->mac_type == HNAE_PORT_DEBUG) hns_gmac_set_uc_match(mac_drv, 0); + + hns_gmac_config_pad_and_crc(mac_drv, 1); + + dsaf_set_dev_bit(drv, GMAC_MODE_CHANGE_EN_REG, + GMAC_MODE_CHANGE_EB_B, 1); + + /* reduce gmac tx water line to avoid gmac hang-up + * in speed 100M and duplex half. + */ + dsaf_set_dev_field(drv, GMAC_TX_WATER_LINE_REG, GMAC_TX_WATER_LINE_MASK, + GMAC_TX_WATER_LINE_SHIFT, 8); } void hns_gmac_update_stats(void *mac_drv) @@ -453,24 +465,6 @@ static int hns_gmac_config_loopback(void *mac_drv, enum hnae_loop loop_mode, return 0; } -static void hns_gmac_config_pad_and_crc(void *mac_drv, u8 newval) -{ - u32 tx_ctrl; - struct mac_driver *drv = (struct mac_driver *)mac_drv; - - tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG); - dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, !!newval); - dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, !!newval); - dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl); -} - -static void hns_gmac_get_id(void *mac_drv, u8 *mac_id) -{ - struct mac_driver *drv = (struct mac_driver *)mac_drv; - - *mac_id = drv->mac_id; -} - static void hns_gmac_get_info(void *mac_drv, struct mac_info *mac_info) { enum hns_gmac_duplex_mdoe duplex; @@ -712,7 +706,6 @@ void *hns_gmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param) mac_drv->config_pad_and_crc = hns_gmac_config_pad_and_crc; mac_drv->config_half_duplex = hns_gmac_set_duplex_type; mac_drv->set_rx_ignore_pause_frames = hns_gmac_set_rx_auto_pause_frames; - mac_drv->mac_get_id = hns_gmac_get_id; mac_drv->get_info = hns_gmac_get_info; mac_drv->autoneg_stat = hns_gmac_autoneg_stat; mac_drv->get_pause_enable = hns_gmac_get_pausefrm_cfg; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 3239d27143b9..0c1f56e58074 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -82,9 +82,12 @@ void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status) else *link_status = 0; - ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb, &sfp_prsnt); - if (!ret) - *link_status = *link_status && sfp_prsnt; + if (mac_cb->media_type == HNAE_MEDIA_TYPE_FIBER) { + ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb, + &sfp_prsnt); + if (!ret) + *link_status = *link_status && sfp_prsnt; + } mac_cb->link = *link_status; } @@ -332,44 +335,6 @@ int hns_mac_set_multi(struct hns_mac_cb *mac_cb, return 0; } -/** - *hns_mac_del_mac - delete mac address into dsaf table,can't delete the same - * address twice - *@net_dev: net device - *@vfn : vf lan - *@mac : mac address - *return status - */ -int hns_mac_del_mac(struct hns_mac_cb *mac_cb, u32 vfn, char *mac) -{ - struct mac_entry_idx *old_mac; - struct dsaf_device *dsaf_dev; - u32 ret; - - dsaf_dev = mac_cb->dsaf_dev; - - if (vfn < DSAF_MAX_VM_NUM) { - old_mac = &mac_cb->addr_entry_idx[vfn]; - } else { - dev_err(mac_cb->dev, - "vf queue is too large, %s mac%d queue = %#x!\n", - mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id, vfn); - return -EINVAL; - } - - if (dsaf_dev) { - ret = hns_dsaf_del_mac_entry(dsaf_dev, old_mac->vlan_id, - mac_cb->mac_id, old_mac->addr); - if (ret) - return ret; - - if (memcmp(old_mac->addr, mac, sizeof(old_mac->addr)) == 0) - old_mac->valid = 0; - } - - return 0; -} - int hns_mac_clr_multicast(struct hns_mac_cb *mac_cb, int vfn) { struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev; @@ -491,10 +456,9 @@ void hns_mac_reset(struct hns_mac_cb *mac_cb) } } -int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu) +int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu, u32 buf_size) { struct mac_driver *drv = hns_mac_get_drv(mac_cb); - u32 buf_size = mac_cb->dsaf_dev->buf_size; u32 new_frm = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; u32 max_frm = AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver) ? MAC_MAX_MTU : MAC_MAX_MTU_V2; @@ -855,7 +819,7 @@ static int hns_mac_get_info(struct hns_mac_cb *mac_cb) of_node_put(np); np = of_parse_phandle(to_of_node(mac_cb->fw_port), - "serdes-syscon", 0); + "serdes-syscon", 0); syscon = syscon_node_to_regmap(np); of_node_put(np); if (IS_ERR_OR_NULL(syscon)) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h index 2bb3d1e93c64..24dfba53a0f2 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h @@ -373,8 +373,6 @@ struct mac_driver { void (*set_rx_ignore_pause_frames)(void *mac_drv, u32 enable); /* config rx mode for promiscuous*/ void (*set_promiscuous)(void *mac_drv, u8 enable); - /* get mac id */ - void (*mac_get_id)(void *mac_drv, u8 *mac_id); void (*mac_pausefrm_cfg)(void *mac_drv, u32 rx_en, u32 tx_en); void (*autoneg_stat)(void *mac_drv, u32 *enable); @@ -436,7 +434,6 @@ int hns_mac_set_multi(struct hns_mac_cb *mac_cb, int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vm, bool enable); void hns_mac_start(struct hns_mac_cb *mac_cb); void hns_mac_stop(struct hns_mac_cb *mac_cb); -int hns_mac_del_mac(struct hns_mac_cb *mac_cb, u32 vfn, char *mac); void hns_mac_uninit(struct dsaf_device *dsaf_dev); void hns_mac_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex); void hns_mac_reset(struct hns_mac_cb *mac_cb); @@ -444,7 +441,7 @@ void hns_mac_get_autoneg(struct hns_mac_cb *mac_cb, u32 *auto_neg); void hns_mac_get_pauseparam(struct hns_mac_cb *mac_cb, u32 *rx_en, u32 *tx_en); int hns_mac_set_autoneg(struct hns_mac_cb *mac_cb, u8 enable); int hns_mac_set_pauseparam(struct hns_mac_cb *mac_cb, u32 rx_en, u32 tx_en); -int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu); +int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu, u32 buf_size); int hns_mac_get_port_info(struct hns_mac_cb *mac_cb, u8 *auto_neg, u16 *speed, u8 *duplex); int hns_mac_config_mac_loopback(struct hns_mac_cb *mac_cb, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 90dbda792614..e0bc79ea3d88 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -510,10 +510,10 @@ static void hns_dsafv2_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev) o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg); dsaf_set_field(o_sbm_bp_cfg, DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_M, - DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 48); + DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 55); dsaf_set_field(o_sbm_bp_cfg, DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_M, - DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 80); + DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 110); dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg); /* for no enable pfc mode */ @@ -521,10 +521,10 @@ static void hns_dsafv2_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev) o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg); dsaf_set_field(o_sbm_bp_cfg, DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_M, - DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_S, 192); + DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_S, 128); dsaf_set_field(o_sbm_bp_cfg, DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_M, - DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S, 240); + DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S, 192); dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg); } @@ -1519,6 +1519,7 @@ static void hns_dsaf_set_mac_key( mac_key->high.bits.mac_3 = addr[3]; mac_key->low.bits.mac_4 = addr[4]; mac_key->low.bits.mac_5 = addr[5]; + mac_key->low.bits.port_vlan = 0; dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_VLAN_M, DSAF_TBL_TCAM_KEY_VLAN_S, vlan_id); dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M, @@ -1647,87 +1648,6 @@ int hns_dsaf_rm_mac_addr( mac_entry->addr); } -/** - * hns_dsaf_set_mac_mc_entry - set mac mc-entry - * @dsaf_dev: dsa fabric device struct pointer - * @mac_entry: mc-mac entry - */ -int hns_dsaf_set_mac_mc_entry( - struct dsaf_device *dsaf_dev, - struct dsaf_drv_mac_multi_dest_entry *mac_entry) -{ - u16 entry_index = DSAF_INVALID_ENTRY_IDX; - struct dsaf_drv_tbl_tcam_key mac_key; - struct dsaf_tbl_tcam_mcast_cfg mac_data; - struct dsaf_drv_priv *priv = - (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev); - struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl; - struct dsaf_drv_tbl_tcam_key tmp_mac_key; - struct dsaf_tbl_tcam_data tcam_data; - - /* mac addr check */ - if (MAC_IS_ALL_ZEROS(mac_entry->addr)) { - dev_err(dsaf_dev->dev, "set uc %s Mac %pM err!\n", - dsaf_dev->ae_dev.name, mac_entry->addr); - return -EINVAL; - } - - /*config key */ - hns_dsaf_set_mac_key(dsaf_dev, &mac_key, - mac_entry->in_vlan_id, - mac_entry->in_port_num, mac_entry->addr); - - /* entry ie exist? */ - entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); - if (entry_index == DSAF_INVALID_ENTRY_IDX) { - /*if hasnot, find enpty entry*/ - entry_index = hns_dsaf_find_empty_mac_entry(dsaf_dev); - if (entry_index == DSAF_INVALID_ENTRY_IDX) { - /*if hasnot empty, error*/ - dev_err(dsaf_dev->dev, - "set_uc_entry failed, %s Mac key(%#x:%#x)\n", - dsaf_dev->ae_dev.name, - mac_key.high.val, mac_key.low.val); - return -EINVAL; - } - - /* config hardware entry */ - memset(mac_data.tbl_mcast_port_msk, - 0, sizeof(mac_data.tbl_mcast_port_msk)); - } else { - /* config hardware entry */ - hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, - &mac_data); - - tmp_mac_key.high.val = - le32_to_cpu(tcam_data.tbl_tcam_data_high); - tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low); - } - mac_data.tbl_mcast_old_en = 0; - mac_data.tbl_mcast_item_vld = 1; - dsaf_set_field(mac_data.tbl_mcast_port_msk[0], - 0x3F, 0, mac_entry->port_mask[0]); - - dev_dbg(dsaf_dev->dev, - "set_uc_entry, %s key(%#x:%#x) entry_index%d\n", - dsaf_dev->ae_dev.name, mac_key.high.val, - mac_key.low.val, entry_index); - - tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val); - tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val); - - hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, &tcam_data, NULL, - &mac_data); - - /* config software entry */ - soft_mac_entry += entry_index; - soft_mac_entry->index = entry_index; - soft_mac_entry->tcam_key.high.val = mac_key.high.val; - soft_mac_entry->tcam_key.low.val = mac_key.low.val; - - return 0; -} - static void hns_dsaf_mc_mask_bit_clear(char *dst, const char *src) { u16 *a = (u16 *)dst; @@ -2089,166 +2009,6 @@ int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev, u8 mac_id, return ret; } -/** - * hns_dsaf_get_mac_uc_entry - get mac uc entry - * @dsaf_dev: dsa fabric device struct pointer - * @mac_entry: mac entry - */ -int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev, - struct dsaf_drv_mac_single_dest_entry *mac_entry) -{ - u16 entry_index = DSAF_INVALID_ENTRY_IDX; - struct dsaf_drv_tbl_tcam_key mac_key; - - struct dsaf_tbl_tcam_ucast_cfg mac_data; - struct dsaf_tbl_tcam_data tcam_data; - - /* check macaddr */ - if (MAC_IS_ALL_ZEROS(mac_entry->addr) || - MAC_IS_BROADCAST(mac_entry->addr)) { - dev_err(dsaf_dev->dev, "get_entry failed,addr %pM\n", - mac_entry->addr); - return -EINVAL; - } - - /*config key */ - hns_dsaf_set_mac_key(dsaf_dev, &mac_key, mac_entry->in_vlan_id, - mac_entry->in_port_num, mac_entry->addr); - - /*check exist? */ - entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); - if (entry_index == DSAF_INVALID_ENTRY_IDX) { - /*find none, error */ - dev_err(dsaf_dev->dev, - "get_uc_entry failed, %s Mac key(%#x:%#x)\n", - dsaf_dev->ae_dev.name, - mac_key.high.val, mac_key.low.val); - return -EINVAL; - } - dev_dbg(dsaf_dev->dev, - "get_uc_entry, %s Mac key(%#x:%#x) entry_index%d\n", - dsaf_dev->ae_dev.name, mac_key.high.val, - mac_key.low.val, entry_index); - - /* read entry */ - hns_dsaf_tcam_uc_get(dsaf_dev, entry_index, &tcam_data, &mac_data); - - mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high); - mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low); - - mac_entry->port_num = mac_data.tbl_ucast_out_port; - - return 0; -} - -/** - * hns_dsaf_get_mac_mc_entry - get mac mc entry - * @dsaf_dev: dsa fabric device struct pointer - * @mac_entry: mac entry - */ -int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev, - struct dsaf_drv_mac_multi_dest_entry *mac_entry) -{ - u16 entry_index = DSAF_INVALID_ENTRY_IDX; - struct dsaf_drv_tbl_tcam_key mac_key; - - struct dsaf_tbl_tcam_mcast_cfg mac_data; - struct dsaf_tbl_tcam_data tcam_data; - - /*check mac addr */ - if (MAC_IS_ALL_ZEROS(mac_entry->addr) || - MAC_IS_BROADCAST(mac_entry->addr)) { - dev_err(dsaf_dev->dev, "get_entry failed,addr %pM\n", - mac_entry->addr); - return -EINVAL; - } - - /*config key */ - hns_dsaf_set_mac_key(dsaf_dev, &mac_key, mac_entry->in_vlan_id, - mac_entry->in_port_num, mac_entry->addr); - - /*check exist? */ - entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); - if (entry_index == DSAF_INVALID_ENTRY_IDX) { - /* find none, error */ - dev_err(dsaf_dev->dev, - "get_mac_uc_entry failed, %s Mac key(%#x:%#x)\n", - dsaf_dev->ae_dev.name, mac_key.high.val, - mac_key.low.val); - return -EINVAL; - } - dev_dbg(dsaf_dev->dev, - "get_mac_uc_entry, %s Mac key(%#x:%#x) entry_index%d\n", - dsaf_dev->ae_dev.name, mac_key.high.val, - mac_key.low.val, entry_index); - - /*read entry */ - hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data); - - mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high); - mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low); - - mac_entry->port_mask[0] = mac_data.tbl_mcast_port_msk[0] & 0x3F; - return 0; -} - -/** - * hns_dsaf_get_mac_entry_by_index - get mac entry by tab index - * @dsaf_dev: dsa fabric device struct pointer - * @entry_index: tab entry index - * @mac_entry: mac entry - */ -int hns_dsaf_get_mac_entry_by_index( - struct dsaf_device *dsaf_dev, - u16 entry_index, struct dsaf_drv_mac_multi_dest_entry *mac_entry) -{ - struct dsaf_drv_tbl_tcam_key mac_key; - - struct dsaf_tbl_tcam_mcast_cfg mac_data; - struct dsaf_tbl_tcam_ucast_cfg mac_uc_data; - struct dsaf_tbl_tcam_data tcam_data; - char mac_addr[ETH_ALEN] = {0}; - - if (entry_index >= dsaf_dev->tcam_max_num) { - /* find none, del error */ - dev_err(dsaf_dev->dev, "get_uc_entry failed, %s\n", - dsaf_dev->ae_dev.name); - return -EINVAL; - } - - /* mc entry, do read opt */ - hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data); - - mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high); - mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low); - - mac_entry->port_mask[0] = mac_data.tbl_mcast_port_msk[0] & 0x3F; - - /***get mac addr*/ - mac_addr[0] = mac_key.high.bits.mac_0; - mac_addr[1] = mac_key.high.bits.mac_1; - mac_addr[2] = mac_key.high.bits.mac_2; - mac_addr[3] = mac_key.high.bits.mac_3; - mac_addr[4] = mac_key.low.bits.mac_4; - mac_addr[5] = mac_key.low.bits.mac_5; - /**is mc or uc*/ - if (MAC_IS_MULTICAST((u8 *)mac_addr) || - MAC_IS_L3_MULTICAST((u8 *)mac_addr)) { - /**mc donot do*/ - } else { - /*is not mc, just uc... */ - hns_dsaf_tcam_uc_get(dsaf_dev, entry_index, &tcam_data, - &mac_uc_data); - - mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high); - mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low); - - mac_entry->port_mask[0] = (1 << mac_uc_data.tbl_ucast_out_port); - } - - return 0; -} - static struct dsaf_device *hns_dsaf_alloc_dev(struct device *dev, size_t sizeof_priv) { @@ -2924,10 +2684,11 @@ void hns_dsaf_set_promisc_tcam(struct dsaf_device *dsaf_dev, /* find the tcam entry index for promisc */ entry_index = dsaf_promisc_tcam_entry(port); + memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data)); + memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask)); + /* config key mask */ if (enable) { - memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data)); - memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask)); dsaf_set_field(tbl_tcam_data.low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M, DSAF_TBL_TCAM_KEY_PORT_S, port); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index cef6bf46ae93..4507e8222683 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -68,7 +68,7 @@ enum dsaf_roce_qos_sl { }; #define DSAF_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset)))) -#define HNS_DSAF_IS_DEBUG(dev) (dev->dsaf_mode == DSAF_MODE_DISABLE_SP) +#define HNS_DSAF_IS_DEBUG(dev) ((dev)->dsaf_mode == DSAF_MODE_DISABLE_SP) enum hal_dsaf_mode { HRD_DSAF_NO_DSAF_MODE = 0x0, @@ -429,23 +429,12 @@ static inline struct hnae_vf_cb *hns_ae_get_vf_cb( int hns_dsaf_set_mac_uc_entry(struct dsaf_device *dsaf_dev, struct dsaf_drv_mac_single_dest_entry *mac_entry); -int hns_dsaf_set_mac_mc_entry(struct dsaf_device *dsaf_dev, - struct dsaf_drv_mac_multi_dest_entry *mac_entry); int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev, struct dsaf_drv_mac_single_dest_entry *mac_entry); int hns_dsaf_del_mac_entry(struct dsaf_device *dsaf_dev, u16 vlan_id, u8 in_port_num, u8 *addr); int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev, struct dsaf_drv_mac_single_dest_entry *mac_entry); -int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev, - struct dsaf_drv_mac_single_dest_entry *mac_entry); -int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev, - struct dsaf_drv_mac_multi_dest_entry *mac_entry); -int hns_dsaf_get_mac_entry_by_index( - struct dsaf_device *dsaf_dev, - u16 entry_index, - struct dsaf_drv_mac_multi_dest_entry *mac_entry); - void hns_dsaf_fix_mac_mode(struct hns_mac_cb *mac_cb); int hns_dsaf_ae_init(struct dsaf_device *dsaf_dev); @@ -475,5 +464,4 @@ int hns_dsaf_rm_mac_addr( int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev, u8 mac_id, u8 port_num); - #endif /* __HNS_DSAF_MAIN_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index a2c22d084ce9..e13aa064a8e9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -461,6 +461,32 @@ int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt) return 0; } +int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt) +{ + union acpi_object *obj; + union acpi_object obj_args, argv4; + + obj_args.integer.type = ACPI_TYPE_INTEGER; + obj_args.integer.value = mac_cb->mac_id; + + argv4.type = ACPI_TYPE_PACKAGE, + argv4.package.count = 1, + argv4.package.elements = &obj_args, + + obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev), + hns_dsaf_acpi_dsm_uuid, 0, + HNS_OP_GET_SFP_STAT_FUNC, &argv4); + + if (!obj || obj->type != ACPI_TYPE_INTEGER) + return -ENODEV; + + *sfp_prsnt = obj->integer.value; + + ACPI_FREE(obj); + + return 0; +} + /** * hns_mac_config_sds_loopback - set loop back for serdes * @mac_cb: mac control block @@ -592,7 +618,7 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev) misc_op->hns_dsaf_roce_srst = hns_dsaf_roce_srst_acpi; misc_op->get_phy_if = hns_mac_get_phy_if_acpi; - misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt; + misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt_acpi; misc_op->cfg_serdes_loopback = hns_mac_config_sds_loopback_acpi; } else { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c index 6ea872287307..eba406bea52f 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c @@ -496,17 +496,17 @@ void hns_ppe_get_stats(struct hns_ppe_cb *ppe_cb, u64 *data) */ int hns_ppe_init(struct dsaf_device *dsaf_dev) { - int i, k; int ret; + int i; for (i = 0; i < HNS_PPE_COM_NUM; i++) { ret = hns_ppe_common_get_cfg(dsaf_dev, i); if (ret) - goto get_ppe_cfg_fail; + goto get_cfg_fail; ret = hns_rcb_common_get_cfg(dsaf_dev, i); if (ret) - goto get_rcb_cfg_fail; + goto get_cfg_fail; hns_ppe_get_cfg(dsaf_dev->ppe_common[i]); @@ -518,13 +518,12 @@ int hns_ppe_init(struct dsaf_device *dsaf_dev) return 0; -get_rcb_cfg_fail: - hns_ppe_common_free_cfg(dsaf_dev, i); -get_ppe_cfg_fail: - for (k = i - 1; k >= 0; k--) { - hns_rcb_common_free_cfg(dsaf_dev, k); - hns_ppe_common_free_cfg(dsaf_dev, k); +get_cfg_fail: + for (i = 0; i < HNS_PPE_COM_NUM; i++) { + hns_rcb_common_free_cfg(dsaf_dev, i); + hns_ppe_common_free_cfg(dsaf_dev, i); } + return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c index f0ed80d6ef9c..c20a0f4f8f02 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -32,6 +32,9 @@ #define RCB_RESET_WAIT_TIMES 30 #define RCB_RESET_TRY_TIMES 10 +/* Because default mtu is 1500, rcb buffer size is set to 2048 enough */ +#define RCB_DEFAULT_BUFFER_SIZE 2048 + /** *hns_rcb_wait_fbd_clean - clean fbd *@qs: ring struct pointer array @@ -192,6 +195,30 @@ void hns_rcb_common_init_commit_hw(struct rcb_common_cb *rcb_common) wmb(); /* Sync point after breakpoint */ } +/* hns_rcb_set_tx_ring_bs - init rcb ring buf size regester + *@q: hnae_queue + *@buf_size: buffer size set to hw + */ +void hns_rcb_set_tx_ring_bs(struct hnae_queue *q, u32 buf_size) +{ + u32 bd_size_type = hns_rcb_buf_size2type(buf_size); + + dsaf_write_dev(q, RCB_RING_TX_RING_BD_LEN_REG, + bd_size_type); +} + +/* hns_rcb_set_rx_ring_bs - init rcb ring buf size regester + *@q: hnae_queue + *@buf_size: buffer size set to hw + */ +void hns_rcb_set_rx_ring_bs(struct hnae_queue *q, u32 buf_size) +{ + u32 bd_size_type = hns_rcb_buf_size2type(buf_size); + + dsaf_write_dev(q, RCB_RING_RX_RING_BD_LEN_REG, + bd_size_type); +} + /** *hns_rcb_ring_init - init rcb ring *@ring_pair: ring pair control block @@ -200,8 +227,6 @@ void hns_rcb_common_init_commit_hw(struct rcb_common_cb *rcb_common) static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type) { struct hnae_queue *q = &ring_pair->q; - struct rcb_common_cb *rcb_common = ring_pair->rcb_common; - u32 bd_size_type = rcb_common->dsaf_dev->buf_size_type; struct hnae_ring *ring = (ring_type == RX_RING) ? &q->rx_ring : &q->tx_ring; dma_addr_t dma = ring->desc_dma_addr; @@ -212,8 +237,8 @@ static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type) dsaf_write_dev(q, RCB_RING_RX_RING_BASEADDR_H_REG, (u32)((dma >> 31) >> 1)); - dsaf_write_dev(q, RCB_RING_RX_RING_BD_LEN_REG, - bd_size_type); + hns_rcb_set_rx_ring_bs(q, ring->buf_size); + dsaf_write_dev(q, RCB_RING_RX_RING_BD_NUM_REG, ring_pair->port_id_in_comm); dsaf_write_dev(q, RCB_RING_RX_RING_PKTLINE_REG, @@ -224,12 +249,12 @@ static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type) dsaf_write_dev(q, RCB_RING_TX_RING_BASEADDR_H_REG, (u32)((dma >> 31) >> 1)); - dsaf_write_dev(q, RCB_RING_TX_RING_BD_LEN_REG, - bd_size_type); + hns_rcb_set_tx_ring_bs(q, ring->buf_size); + dsaf_write_dev(q, RCB_RING_TX_RING_BD_NUM_REG, ring_pair->port_id_in_comm); dsaf_write_dev(q, RCB_RING_TX_RING_PKTLINE_REG, - ring_pair->port_id_in_comm); + ring_pair->port_id_in_comm + HNS_RCB_TX_PKTLINE_OFFSET); } } @@ -259,13 +284,27 @@ static void hns_rcb_set_port_desc_cnt(struct rcb_common_cb *rcb_common, static void hns_rcb_set_port_timeout( struct rcb_common_cb *rcb_common, u32 port_idx, u32 timeout) { - if (AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) + if (AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) { dsaf_write_dev(rcb_common, RCB_CFG_OVERTIME_REG, timeout * HNS_RCB_CLK_FREQ_MHZ); - else + } else if (!HNS_DSAF_IS_DEBUG(rcb_common->dsaf_dev)) { + if (timeout > HNS_RCB_DEF_GAP_TIME_USECS) + dsaf_write_dev(rcb_common, + RCB_PORT_INT_GAPTIME_REG + port_idx * 4, + HNS_RCB_DEF_GAP_TIME_USECS); + else + dsaf_write_dev(rcb_common, + RCB_PORT_INT_GAPTIME_REG + port_idx * 4, + timeout); + + dsaf_write_dev(rcb_common, + RCB_PORT_CFG_OVERTIME_REG + port_idx * 4, + timeout); + } else { dsaf_write_dev(rcb_common, RCB_PORT_CFG_OVERTIME_REG + port_idx * 4, timeout); + } } static int hns_rcb_common_get_port_num(struct rcb_common_cb *rcb_common) @@ -327,8 +366,12 @@ int hns_rcb_common_init_hw(struct rcb_common_cb *rcb_common) for (i = 0; i < port_num; i++) { hns_rcb_set_port_desc_cnt(rcb_common, i, rcb_common->desc_num); - (void)hns_rcb_set_coalesced_frames( - rcb_common, i, HNS_RCB_DEF_COALESCED_FRAMES); + hns_rcb_set_rx_coalesced_frames( + rcb_common, i, HNS_RCB_DEF_RX_COALESCED_FRAMES); + if (!AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver) && + !HNS_DSAF_IS_DEBUG(rcb_common->dsaf_dev)) + hns_rcb_set_tx_coalesced_frames( + rcb_common, i, HNS_RCB_DEF_TX_COALESCED_FRAMES); hns_rcb_set_port_timeout( rcb_common, i, HNS_RCB_DEF_COALESCED_USECS); } @@ -380,7 +423,6 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type) struct hnae_ring *ring; struct rcb_common_cb *rcb_common; struct ring_pair_cb *ring_pair_cb; - u32 buf_size; u16 desc_num, mdnum_ppkt; bool irq_idx, is_ver1; @@ -401,7 +443,6 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type) } rcb_common = ring_pair_cb->rcb_common; - buf_size = rcb_common->dsaf_dev->buf_size; desc_num = rcb_common->dsaf_dev->desc_num; ring->desc = NULL; @@ -410,7 +451,7 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type) ring->irq = ring_pair_cb->virq[irq_idx]; ring->desc_dma_addr = 0; - ring->buf_size = buf_size; + ring->buf_size = RCB_DEFAULT_BUFFER_SIZE; ring->desc_num = desc_num; ring->max_desc_num_per_pkt = mdnum_ppkt; ring->max_raw_data_sz_per_desc = HNS_RCB_MAX_PKT_SIZE; @@ -430,7 +471,6 @@ static void hns_rcb_ring_pair_get_cfg(struct ring_pair_cb *ring_pair_cb) static int hns_rcb_get_port_in_comm( struct rcb_common_cb *rcb_common, int ring_idx) { - return ring_idx / (rcb_common->max_q_per_vf * rcb_common->max_vfn); } @@ -484,19 +524,35 @@ void hns_rcb_get_cfg(struct rcb_common_cb *rcb_common) } /** - *hns_rcb_get_coalesced_frames - get rcb port coalesced frames + *hns_rcb_get_rx_coalesced_frames - get rcb port rx coalesced frames *@rcb_common: rcb_common device *@port_idx:port id in comm * *Returns: coalesced_frames */ -u32 hns_rcb_get_coalesced_frames( +u32 hns_rcb_get_rx_coalesced_frames( struct rcb_common_cb *rcb_common, u32 port_idx) { return dsaf_read_dev(rcb_common, RCB_CFG_PKTLINE_REG + port_idx * 4); } /** + *hns_rcb_get_tx_coalesced_frames - get rcb port tx coalesced frames + *@rcb_common: rcb_common device + *@port_idx:port id in comm + * + *Returns: coalesced_frames + */ +u32 hns_rcb_get_tx_coalesced_frames( + struct rcb_common_cb *rcb_common, u32 port_idx) +{ + u64 reg; + + reg = RCB_CFG_PKTLINE_REG + (port_idx + HNS_RCB_TX_PKTLINE_OFFSET) * 4; + return dsaf_read_dev(rcb_common, reg); +} + +/** *hns_rcb_get_coalesce_usecs - get rcb port coalesced time_out *@rcb_common: rcb_common device *@port_idx:port id in comm @@ -538,33 +594,47 @@ int hns_rcb_set_coalesce_usecs( return -EINVAL; } } - if (timeout > HNS_RCB_MAX_COALESCED_USECS) { + if (timeout > HNS_RCB_MAX_COALESCED_USECS || timeout == 0) { dev_err(rcb_common->dsaf_dev->dev, - "error: coalesce_usecs setting supports 0~1023us\n"); + "error: coalesce_usecs setting supports 1~1023us\n"); return -EINVAL; } + hns_rcb_set_port_timeout(rcb_common, port_idx, timeout); + return 0; +} - if (!AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) { - if (timeout == 0) - /* set timeout to 0, Disable gap time */ - dsaf_set_reg_field(rcb_common->io_base, - RCB_INT_GAP_TIME_REG + port_idx * 4, - PPE_INT_GAPTIME_M, PPE_INT_GAPTIME_B, - 0); - else - /* set timeout non 0, restore gap time to 1 */ - dsaf_set_reg_field(rcb_common->io_base, - RCB_INT_GAP_TIME_REG + port_idx * 4, - PPE_INT_GAPTIME_M, PPE_INT_GAPTIME_B, - 1); +/** + *hns_rcb_set_tx_coalesced_frames - set rcb coalesced frames + *@rcb_common: rcb_common device + *@port_idx:port id in comm + *@coalesced_frames:tx/rx BD num for coalesced frames + * + * Returns: + * Zero for success, or an error code in case of failure + */ +int hns_rcb_set_tx_coalesced_frames( + struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames) +{ + u32 old_waterline = + hns_rcb_get_tx_coalesced_frames(rcb_common, port_idx); + u64 reg; + + if (coalesced_frames == old_waterline) + return 0; + + if (coalesced_frames != 1) { + dev_err(rcb_common->dsaf_dev->dev, + "error: not support tx coalesce_frames setting!\n"); + return -EINVAL; } - hns_rcb_set_port_timeout(rcb_common, port_idx, timeout); + reg = RCB_CFG_PKTLINE_REG + (port_idx + HNS_RCB_TX_PKTLINE_OFFSET) * 4; + dsaf_write_dev(rcb_common, reg, coalesced_frames); return 0; } /** - *hns_rcb_set_coalesced_frames - set rcb coalesced frames + *hns_rcb_set_rx_coalesced_frames - set rcb rx coalesced frames *@rcb_common: rcb_common device *@port_idx:port id in comm *@coalesced_frames:tx/rx BD num for coalesced frames @@ -572,10 +642,11 @@ int hns_rcb_set_coalesce_usecs( * Returns: * Zero for success, or an error code in case of failure */ -int hns_rcb_set_coalesced_frames( +int hns_rcb_set_rx_coalesced_frames( struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames) { - u32 old_waterline = hns_rcb_get_coalesced_frames(rcb_common, port_idx); + u32 old_waterline = + hns_rcb_get_rx_coalesced_frames(rcb_common, port_idx); if (coalesced_frames == old_waterline) return 0; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h index 99b4e1ba0a94..a664ee88ab45 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h @@ -35,12 +35,23 @@ struct rcb_common_cb; #define HNS_RCB_REG_OFFSET 0x10000 +#define HNS_RCB_TX_FRAMES_LOW 1 +#define HNS_RCB_RX_FRAMES_LOW 1 +#define HNS_RCB_TX_FRAMES_HIGH 1023 +#define HNS_RCB_RX_FRAMES_HIGH 1023 +#define HNS_RCB_TX_USECS_LOW 1 +#define HNS_RCB_RX_USECS_LOW 1 +#define HNS_RCB_TX_USECS_HIGH 1023 +#define HNS_RCB_RX_USECS_HIGH 1023 #define HNS_RCB_MAX_COALESCED_FRAMES 1023 #define HNS_RCB_MIN_COALESCED_FRAMES 1 -#define HNS_RCB_DEF_COALESCED_FRAMES 50 +#define HNS_RCB_DEF_RX_COALESCED_FRAMES 50 +#define HNS_RCB_DEF_TX_COALESCED_FRAMES 1 #define HNS_RCB_CLK_FREQ_MHZ 350 #define HNS_RCB_MAX_COALESCED_USECS 0x3ff -#define HNS_RCB_DEF_COALESCED_USECS 50 +#define HNS_RCB_DEF_COALESCED_USECS 30 +#define HNS_RCB_DEF_GAP_TIME_USECS 20 +#define HNS_RCB_TX_PKTLINE_OFFSET 8 #define HNS_RCB_COMMON_ENDIAN 1 @@ -125,13 +136,17 @@ void hns_rcbv2_int_clr_hw(struct hnae_queue *q, u32 flag); void hns_rcb_init_hw(struct ring_pair_cb *ring); void hns_rcb_reset_ring_hw(struct hnae_queue *q); void hns_rcb_wait_fbd_clean(struct hnae_queue **qs, int q_num, u32 flag); -u32 hns_rcb_get_coalesced_frames( +u32 hns_rcb_get_rx_coalesced_frames( + struct rcb_common_cb *rcb_common, u32 port_idx); +u32 hns_rcb_get_tx_coalesced_frames( struct rcb_common_cb *rcb_common, u32 port_idx); u32 hns_rcb_get_coalesce_usecs( struct rcb_common_cb *rcb_common, u32 port_idx); int hns_rcb_set_coalesce_usecs( struct rcb_common_cb *rcb_common, u32 port_idx, u32 timeout); -int hns_rcb_set_coalesced_frames( +int hns_rcb_set_rx_coalesced_frames( + struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames); +int hns_rcb_set_tx_coalesced_frames( struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames); void hns_rcb_update_stats(struct hnae_queue *queue); @@ -146,4 +161,7 @@ int hns_rcb_get_ring_regs_count(void); void hns_rcb_get_ring_regs(struct hnae_queue *queue, void *data); void hns_rcb_get_strings(int stringset, u8 *data, int index); +void hns_rcb_set_rx_ring_bs(struct hnae_queue *q, u32 buf_size); +void hns_rcb_set_tx_ring_bs(struct hnae_queue *q, u32 buf_size); + #endif /* _HNS_DSAF_RCB_H */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index 8fa18fc17cd2..46a52d9bb196 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -421,7 +421,7 @@ #define RCB_CFG_OVERTIME_REG 0x9300 #define RCB_CFG_PKTLINE_INT_NUM_REG 0x9304 #define RCB_CFG_OVERTIME_INT_NUM_REG 0x9308 -#define RCB_INT_GAP_TIME_REG 0x9400 +#define RCB_PORT_INT_GAPTIME_REG 0x9400 #define RCB_PORT_CFG_OVERTIME_REG 0x9430 #define RCB_RING_RX_RING_BASEADDR_L_REG 0x00000 @@ -466,6 +466,7 @@ #define GMAC_DUPLEX_TYPE_REG 0x0008UL #define GMAC_FD_FC_TYPE_REG 0x000CUL +#define GMAC_TX_WATER_LINE_REG 0x0010UL #define GMAC_FC_TX_TIMER_REG 0x001CUL #define GMAC_FD_FC_ADDR_LOW_REG 0x0020UL #define GMAC_FD_FC_ADDR_HIGH_REG 0x0024UL @@ -912,6 +913,9 @@ #define GMAC_DUPLEX_TYPE_B 0 +#define GMAC_TX_WATER_LINE_MASK ((1UL << 8) - 1) +#define GMAC_TX_WATER_LINE_SHIFT 0 + #define GMAC_FC_TX_TIMER_S 0 #define GMAC_FC_TX_TIMER_M 0xffff diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c index aae830a93050..37a2fc35148f 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c @@ -300,18 +300,6 @@ static void hns_xgmac_set_tx_auto_pause_frames(void *mac_drv, u16 enable) } /** - *hns_xgmac_get_id - get xgmac port id - *@mac_drv: mac driver - *@newval:xgmac max frame length - */ -static void hns_xgmac_get_id(void *mac_drv, u8 *mac_id) -{ - struct mac_driver *drv = (struct mac_driver *)mac_drv; - - *mac_id = drv->mac_id; -} - -/** *hns_xgmac_config_max_frame_length - set xgmac max frame length *@mac_drv: mac driver *@newval:xgmac max frame length @@ -833,7 +821,6 @@ void *hns_xgmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param) mac_drv->config_half_duplex = NULL; mac_drv->set_rx_ignore_pause_frames = hns_xgmac_set_rx_ignore_pause_frames; - mac_drv->mac_get_id = hns_xgmac_get_id; mac_drv->mac_free = hns_xgmac_free; mac_drv->adjust_link = NULL; mac_drv->set_tx_auto_pause_frames = hns_xgmac_set_tx_auto_pause_frames; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index fca37e2c7f01..c6700b91a2df 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -512,7 +512,8 @@ static void hns_nic_reuse_page(struct sk_buff *skb, int i, int last_offset; bool twobufs; - twobufs = ((PAGE_SIZE < 8192) && hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048); + twobufs = ((PAGE_SIZE < 8192) && + hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048); desc = &ring->desc[ring->next_to_clean]; size = le16_to_cpu(desc->rx.size); @@ -859,7 +860,7 @@ out: return recv_pkts; } -static void hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data) +static bool hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data) { struct hnae_ring *ring = ring_data->ring; int num = 0; @@ -873,22 +874,23 @@ static void hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data) ring_data->ring->q->handle->dev->ops->toggle_ring_irq( ring_data->ring, 1); - napi_schedule(&ring_data->napi); + return false; + } else { + return true; } } -static void hns_nic_rx_fini_pro_v2(struct hns_nic_ring_data *ring_data) +static bool hns_nic_rx_fini_pro_v2(struct hns_nic_ring_data *ring_data) { struct hnae_ring *ring = ring_data->ring; - int num = 0; + int num; num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM); - if (num == 0) - ring_data->ring->q->handle->dev->ops->toggle_ring_irq( - ring, 0); + if (!num) + return true; else - napi_schedule(&ring_data->napi); + return false; } static inline void hns_nic_reclaim_one_desc(struct hnae_ring *ring, @@ -921,12 +923,13 @@ static int is_valid_clean_head(struct hnae_ring *ring, int h) /* netif_tx_lock will turn down the performance, set only when necessary */ #ifdef CONFIG_NET_POLL_CONTROLLER -#define NETIF_TX_LOCK(ndev) netif_tx_lock(ndev) -#define NETIF_TX_UNLOCK(ndev) netif_tx_unlock(ndev) +#define NETIF_TX_LOCK(ring) spin_lock(&(ring)->lock) +#define NETIF_TX_UNLOCK(ring) spin_unlock(&(ring)->lock) #else -#define NETIF_TX_LOCK(ndev) -#define NETIF_TX_UNLOCK(ndev) +#define NETIF_TX_LOCK(ring) +#define NETIF_TX_UNLOCK(ring) #endif + /* reclaim all desc in one budget * return error or number of desc left */ @@ -940,13 +943,13 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, int head; int bytes, pkts; - NETIF_TX_LOCK(ndev); + NETIF_TX_LOCK(ring); head = readl_relaxed(ring->io_base + RCB_REG_HEAD); rmb(); /* make sure head is ready before touch any data */ if (is_ring_empty(ring) || head == ring->next_to_clean) { - NETIF_TX_UNLOCK(ndev); + NETIF_TX_UNLOCK(ring); return 0; /* no data to poll */ } @@ -954,7 +957,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, netdev_err(ndev, "wrong head (%d, %d-%d)\n", head, ring->next_to_use, ring->next_to_clean); ring->stats.io_err_cnt++; - NETIF_TX_UNLOCK(ndev); + NETIF_TX_UNLOCK(ring); return -EIO; } @@ -966,7 +969,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, prefetch(&ring->desc_cb[ring->next_to_clean]); } - NETIF_TX_UNLOCK(ndev); + NETIF_TX_UNLOCK(ring); dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index); netdev_tx_completed_queue(dev_queue, pkts, bytes); @@ -989,7 +992,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, return 0; } -static void hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data) +static bool hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data) { struct hnae_ring *ring = ring_data->ring; int head; @@ -1002,20 +1005,21 @@ static void hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data) ring_data->ring->q->handle->dev->ops->toggle_ring_irq( ring_data->ring, 1); - napi_schedule(&ring_data->napi); + return false; + } else { + return true; } } -static void hns_nic_tx_fini_pro_v2(struct hns_nic_ring_data *ring_data) +static bool hns_nic_tx_fini_pro_v2(struct hns_nic_ring_data *ring_data) { struct hnae_ring *ring = ring_data->ring; int head = readl_relaxed(ring->io_base + RCB_REG_HEAD); if (head == ring->next_to_clean) - ring_data->ring->q->handle->dev->ops->toggle_ring_irq( - ring, 0); + return true; else - napi_schedule(&ring_data->napi); + return false; } static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data) @@ -1026,7 +1030,7 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data) int head; int bytes, pkts; - NETIF_TX_LOCK(ndev); + NETIF_TX_LOCK(ring); head = ring->next_to_use; /* ntu :soft setted ring position*/ bytes = 0; @@ -1034,7 +1038,7 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data) while (head != ring->next_to_clean) hns_nic_reclaim_one_desc(ring, &bytes, &pkts); - NETIF_TX_UNLOCK(ndev); + NETIF_TX_UNLOCK(ring); dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index); netdev_tx_reset_queue(dev_queue); @@ -1042,15 +1046,23 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data) static int hns_nic_common_poll(struct napi_struct *napi, int budget) { + int clean_complete = 0; struct hns_nic_ring_data *ring_data = container_of(napi, struct hns_nic_ring_data, napi); - int clean_complete = ring_data->poll_one( - ring_data, budget, ring_data->ex_process); + struct hnae_ring *ring = ring_data->ring; - if (clean_complete >= 0 && clean_complete < budget) { - napi_complete(napi); - ring_data->fini_process(ring_data); - return 0; +try_again: + clean_complete += ring_data->poll_one( + ring_data, budget - clean_complete, + ring_data->ex_process); + + if (clean_complete < budget) { + if (ring_data->fini_process(ring_data)) { + napi_complete(napi); + ring->q->handle->dev->ops->toggle_ring_irq(ring, 0); + } else { + goto try_again; + } } return clean_complete; @@ -1196,54 +1208,31 @@ static void hns_nic_ring_close(struct net_device *netdev, int idx) napi_disable(&priv->ring_data[idx].napi); } -static void hns_set_irq_affinity(struct hns_nic_priv *priv) +static int hns_nic_init_affinity_mask(int q_num, int ring_idx, + struct hnae_ring *ring, cpumask_t *mask) { - struct hnae_handle *h = priv->ae_handle; - struct hns_nic_ring_data *rd; - int i; int cpu; - cpumask_var_t mask; - - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) - return; - /*diffrent irq banlance for 16core and 32core*/ - if (h->q_num == num_possible_cpus()) { - for (i = 0; i < h->q_num * 2; i++) { - rd = &priv->ring_data[i]; - if (cpu_online(rd->queue_index)) { - cpumask_clear(mask); - cpu = rd->queue_index; - cpumask_set_cpu(cpu, mask); - (void)irq_set_affinity_hint(rd->ring->irq, - mask); - } - } + /* Diffrent irq banlance between 16core and 32core. + * The cpu mask set by ring index according to the ring flag + * which indicate the ring is tx or rx. + */ + if (q_num == num_possible_cpus()) { + if (is_tx_ring(ring)) + cpu = ring_idx; + else + cpu = ring_idx - q_num; } else { - for (i = 0; i < h->q_num; i++) { - rd = &priv->ring_data[i]; - if (cpu_online(rd->queue_index * 2)) { - cpumask_clear(mask); - cpu = rd->queue_index * 2; - cpumask_set_cpu(cpu, mask); - (void)irq_set_affinity_hint(rd->ring->irq, - mask); - } - } - - for (i = h->q_num; i < h->q_num * 2; i++) { - rd = &priv->ring_data[i]; - if (cpu_online(rd->queue_index * 2 + 1)) { - cpumask_clear(mask); - cpu = rd->queue_index * 2 + 1; - cpumask_set_cpu(cpu, mask); - (void)irq_set_affinity_hint(rd->ring->irq, - mask); - } - } + if (is_tx_ring(ring)) + cpu = ring_idx * 2; + else + cpu = (ring_idx - q_num) * 2 + 1; } - free_cpumask_var(mask); + cpumask_clear(mask); + cpumask_set_cpu(cpu, mask); + + return cpu; } static int hns_nic_init_irq(struct hns_nic_priv *priv) @@ -1252,6 +1241,7 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv) struct hns_nic_ring_data *rd; int i; int ret; + int cpu; for (i = 0; i < h->q_num * 2; i++) { rd = &priv->ring_data[i]; @@ -1261,7 +1251,7 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv) snprintf(rd->ring->ring_name, RCB_RING_NAME_LEN, "%s-%s%d", priv->netdev->name, - (i < h->q_num ? "tx" : "rx"), rd->queue_index); + (is_tx_ring(rd->ring) ? "tx" : "rx"), rd->queue_index); rd->ring->ring_name[RCB_RING_NAME_LEN - 1] = '\0'; @@ -1273,12 +1263,17 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv) return ret; } disable_irq(rd->ring->irq); + + cpu = hns_nic_init_affinity_mask(h->q_num, i, + rd->ring, &rd->mask); + + if (cpu_online(cpu)) + irq_set_affinity_hint(rd->ring->irq, + &rd->mask); + rd->ring->irq_init_flag = RCB_IRQ_INITED; } - /*set cpu affinity*/ - hns_set_irq_affinity(priv); - return 0; } @@ -1487,32 +1482,259 @@ static netdev_tx_t hns_nic_net_xmit(struct sk_buff *skb, return (netdev_tx_t)ret; } +static void hns_nic_drop_rx_fetch(struct hns_nic_ring_data *ring_data, + struct sk_buff *skb) +{ + dev_kfree_skb_any(skb); +} + +#define HNS_LB_TX_RING 0 +static struct sk_buff *hns_assemble_skb(struct net_device *ndev) +{ + struct sk_buff *skb; + struct ethhdr *ethhdr; + int frame_len; + + /* allocate test skb */ + skb = alloc_skb(64, GFP_KERNEL); + if (!skb) + return NULL; + + skb_put(skb, 64); + skb->dev = ndev; + memset(skb->data, 0xFF, skb->len); + + /* must be tcp/ip package */ + ethhdr = (struct ethhdr *)skb->data; + ethhdr->h_proto = htons(ETH_P_IP); + + frame_len = skb->len & (~1ul); + memset(&skb->data[frame_len / 2], 0xAA, + frame_len / 2 - 1); + + skb->queue_mapping = HNS_LB_TX_RING; + + return skb; +} + +static int hns_enable_serdes_lb(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + struct hnae_ae_ops *ops = h->dev->ops; + int speed, duplex; + int ret; + + ret = ops->set_loopback(h, MAC_INTERNALLOOP_SERDES, 1); + if (ret) + return ret; + + ret = ops->start ? ops->start(h) : 0; + if (ret) + return ret; + + /* link adjust duplex*/ + if (h->phy_if != PHY_INTERFACE_MODE_XGMII) + speed = 1000; + else + speed = 10000; + duplex = 1; + + ops->adjust_link(h, speed, duplex); + + /* wait h/w ready */ + mdelay(300); + + return 0; +} + +static void hns_disable_serdes_lb(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + struct hnae_ae_ops *ops = h->dev->ops; + + ops->stop(h); + ops->set_loopback(h, MAC_INTERNALLOOP_SERDES, 0); +} + +/** + *hns_nic_clear_all_rx_fetch - clear the chip fetched descriptions. The + *function as follows: + * 1. if one rx ring has found the page_offset is not equal 0 between head + * and tail, it means that the chip fetched the wrong descs for the ring + * which buffer size is 4096. + * 2. we set the chip serdes loopback and set rss indirection to the ring. + * 3. construct 64-bytes ip broadcast packages, wait the associated rx ring + * recieving all packages and it will fetch new descriptions. + * 4. recover to the original state. + * + *@ndev: net device + */ +static int hns_nic_clear_all_rx_fetch(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + struct hnae_ae_ops *ops = h->dev->ops; + struct hns_nic_ring_data *rd; + struct hnae_ring *ring; + struct sk_buff *skb; + u32 *org_indir; + u32 *cur_indir; + int indir_size; + int head, tail; + int fetch_num; + int i, j; + bool found; + int retry_times; + int ret = 0; + + /* alloc indir memory */ + indir_size = ops->get_rss_indir_size(h) * sizeof(*org_indir); + org_indir = kzalloc(indir_size, GFP_KERNEL); + if (!org_indir) + return -ENOMEM; + + /* store the orginal indirection */ + ops->get_rss(h, org_indir, NULL, NULL); + + cur_indir = kzalloc(indir_size, GFP_KERNEL); + if (!cur_indir) { + ret = -ENOMEM; + goto cur_indir_alloc_err; + } + + /* set loopback */ + if (hns_enable_serdes_lb(ndev)) { + ret = -EINVAL; + goto enable_serdes_lb_err; + } + + /* foreach every rx ring to clear fetch desc */ + for (i = 0; i < h->q_num; i++) { + ring = &h->qs[i]->rx_ring; + head = readl_relaxed(ring->io_base + RCB_REG_HEAD); + tail = readl_relaxed(ring->io_base + RCB_REG_TAIL); + found = false; + fetch_num = ring_dist(ring, head, tail); + + while (head != tail) { + if (ring->desc_cb[head].page_offset != 0) { + found = true; + break; + } + + head++; + if (head == ring->desc_num) + head = 0; + } + + if (found) { + for (j = 0; j < indir_size / sizeof(*org_indir); j++) + cur_indir[j] = i; + ops->set_rss(h, cur_indir, NULL, 0); + + for (j = 0; j < fetch_num; j++) { + /* alloc one skb and init */ + skb = hns_assemble_skb(ndev); + if (!skb) + goto out; + rd = &tx_ring_data(priv, skb->queue_mapping); + hns_nic_net_xmit_hw(ndev, skb, rd); + + retry_times = 0; + while (retry_times++ < 10) { + mdelay(10); + /* clean rx */ + rd = &rx_ring_data(priv, i); + if (rd->poll_one(rd, fetch_num, + hns_nic_drop_rx_fetch)) + break; + } + + retry_times = 0; + while (retry_times++ < 10) { + mdelay(10); + /* clean tx ring 0 send package */ + rd = &tx_ring_data(priv, + HNS_LB_TX_RING); + if (rd->poll_one(rd, fetch_num, NULL)) + break; + } + } + } + } + +out: + /* restore everything */ + ops->set_rss(h, org_indir, NULL, 0); + hns_disable_serdes_lb(ndev); +enable_serdes_lb_err: + kfree(cur_indir); +cur_indir_alloc_err: + kfree(org_indir); + + return ret; +} + static int hns_nic_change_mtu(struct net_device *ndev, int new_mtu) { struct hns_nic_priv *priv = netdev_priv(ndev); struct hnae_handle *h = priv->ae_handle; + bool if_running = netif_running(ndev); int ret; + /* MTU < 68 is an error and causes problems on some kernels */ + if (new_mtu < 68) + return -EINVAL; + + /* MTU no change */ + if (new_mtu == ndev->mtu) + return 0; + if (!h->dev->ops->set_mtu) return -ENOTSUPP; - if (netif_running(ndev)) { + if (if_running) { (void)hns_nic_net_stop(ndev); msleep(100); + } - ret = h->dev->ops->set_mtu(h, new_mtu); - if (ret) - netdev_err(ndev, "set mtu fail, return value %d\n", - ret); + if (priv->enet_ver != AE_VERSION_1 && + ndev->mtu <= BD_SIZE_2048_MAX_MTU && + new_mtu > BD_SIZE_2048_MAX_MTU) { + /* update desc */ + hnae_reinit_all_ring_desc(h); - if (hns_nic_net_open(ndev)) - netdev_err(ndev, "hns net open fail\n"); - } else { - ret = h->dev->ops->set_mtu(h, new_mtu); + /* clear the package which the chip has fetched */ + ret = hns_nic_clear_all_rx_fetch(ndev); + + /* the page offset must be consist with desc */ + hnae_reinit_all_ring_page_off(h); + + if (ret) { + netdev_err(ndev, "clear the fetched desc fail\n"); + goto out; + } + } + + ret = h->dev->ops->set_mtu(h, new_mtu); + if (ret) { + netdev_err(ndev, "set mtu fail, return value %d\n", + ret); + goto out; } - if (!ret) - ndev->mtu = new_mtu; + /* finally, set new mtu to netdevice */ + ndev->mtu = new_mtu; + +out: + if (if_running) { + if (hns_nic_net_open(ndev)) { + netdev_err(ndev, "hns net open fail\n"); + ret = -EINVAL; + } + } return ret; } @@ -1791,7 +2013,7 @@ static void hns_nic_reset_subtask(struct hns_nic_priv *priv) static void hns_nic_service_event_complete(struct hns_nic_priv *priv) { WARN_ON(!test_bit(NIC_STATE_SERVICE_SCHED, &priv->state)); - + /* make sure to commit the things */ smp_mb__before_atomic(); clear_bit(NIC_STATE_SERVICE_SCHED, &priv->state); } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h index 5b412de350aa..1b83232082b2 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h @@ -37,10 +37,11 @@ enum hns_nic_state { struct hns_nic_ring_data { struct hnae_ring *ring; struct napi_struct napi; + cpumask_t mask; /* affinity mask */ int queue_index; int (*poll_one)(struct hns_nic_ring_data *, int, void *); void (*ex_process)(struct hns_nic_ring_data *, struct sk_buff *); - void (*fini_process)(struct hns_nic_ring_data *); + bool (*fini_process)(struct hns_nic_ring_data *); }; /* compatible the difference between two versions */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 3ac2183dbd21..b8fab149690f 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -146,7 +146,7 @@ static int hns_nic_get_link_ksettings(struct net_device *net_dev, /* When there is no phy, autoneg is off. */ cmd->base.autoneg = false; - cmd->base.cmd = speed; + cmd->base.speed = speed; cmd->base.duplex = duplex; if (net_dev->phydev) @@ -764,14 +764,14 @@ static int hns_get_coalesce(struct net_device *net_dev, ec->use_adaptive_tx_coalesce = 1; if ((!ops->get_coalesce_usecs) || - (!ops->get_rx_max_coalesced_frames)) + (!ops->get_max_coalesced_frames)) return -ESRCH; ops->get_coalesce_usecs(priv->ae_handle, &ec->tx_coalesce_usecs, &ec->rx_coalesce_usecs); - ops->get_rx_max_coalesced_frames( + ops->get_max_coalesced_frames( priv->ae_handle, &ec->tx_max_coalesced_frames, &ec->rx_max_coalesced_frames); @@ -801,30 +801,28 @@ static int hns_set_coalesce(struct net_device *net_dev, { struct hns_nic_priv *priv = netdev_priv(net_dev); struct hnae_ae_ops *ops; - int ret; + int rc1, rc2; ops = priv->ae_handle->dev->ops; if (ec->tx_coalesce_usecs != ec->rx_coalesce_usecs) return -EINVAL; - if (ec->rx_max_coalesced_frames != ec->tx_max_coalesced_frames) - return -EINVAL; - if ((!ops->set_coalesce_usecs) || (!ops->set_coalesce_frames)) return -ESRCH; - ret = ops->set_coalesce_usecs(priv->ae_handle, + rc1 = ops->set_coalesce_usecs(priv->ae_handle, ec->rx_coalesce_usecs); - if (ret) - return ret; - ret = ops->set_coalesce_frames( - priv->ae_handle, - ec->rx_max_coalesced_frames); + rc2 = ops->set_coalesce_frames(priv->ae_handle, + ec->tx_max_coalesced_frames, + ec->rx_max_coalesced_frames); - return ret; + if (rc1 || rc2) + return -EINVAL; + + return 0; } /** @@ -1253,12 +1251,10 @@ hns_set_rss(struct net_device *netdev, const u32 *indir, const u8 *key, ops = priv->ae_handle->dev->ops; - /* currently hfunc can only be Toeplitz hash */ - if (key || - (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)) + if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) { + netdev_err(netdev, "Invalid hfunc!\n"); return -EOPNOTSUPP; - if (!indir) - return 0; + } return ops->set_rss(priv->ae_handle, indir, key, hfunc); } diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index 501eb2090ca6..e5221d95afe1 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -23,17 +23,9 @@ #include <linux/phy.h> #include <linux/platform_device.h> #include <linux/regmap.h> -#include <linux/spinlock_types.h> #define MDIO_DRV_NAME "Hi-HNS_MDIO" #define MDIO_BUS_NAME "Hisilicon MII Bus" -#define MDIO_DRV_VERSION "1.3.0" -#define MDIO_COPYRIGHT "Copyright(c) 2015 Huawei Corporation." -#define MDIO_DRV_STRING MDIO_BUS_NAME -#define MDIO_DEFAULT_DEVICE_DESCR MDIO_BUS_NAME - -#define MDIO_CTL_DEV_ADDR(x) (x & 0x1f) -#define MDIO_CTL_PORT_ADDR(x) ((x & 0x1f) << 5) #define MDIO_TIMEOUT 1000000 @@ -64,9 +56,7 @@ struct hns_mdio_device { #define MDIO_CMD_DEVAD_S 0 #define MDIO_CMD_PRTAD_M 0x1f #define MDIO_CMD_PRTAD_S 5 -#define MDIO_CMD_OP_M 0x3 #define MDIO_CMD_OP_S 10 -#define MDIO_CMD_ST_M 0x3 #define MDIO_CMD_ST_S 12 #define MDIO_CMD_START_B 14 @@ -185,18 +175,20 @@ static int mdio_sc_cfg_reg_write(struct hns_mdio_device *mdio_dev, static int hns_mdio_wait_ready(struct mii_bus *bus) { struct hns_mdio_device *mdio_dev = bus->priv; + u32 cmd_reg_value; int i; - u32 cmd_reg_value = 1; /* waitting for MDIO_COMMAND_REG 's mdio_start==0 */ /* after that can do read or write*/ - for (i = 0; cmd_reg_value; i++) { + for (i = 0; i < MDIO_TIMEOUT; i++) { cmd_reg_value = MDIO_GET_REG_BIT(mdio_dev, MDIO_COMMAND_REG, MDIO_CMD_START_B); - if (i == MDIO_TIMEOUT) - return -ETIMEDOUT; + if (!cmd_reg_value) + break; } + if ((i == MDIO_TIMEOUT) && cmd_reg_value) + return -ETIMEDOUT; return 0; } diff --git a/drivers/net/ethernet/ibm/emac/Makefile b/drivers/net/ethernet/ibm/emac/Makefile index eba21835d90d..98768ba0955a 100644 --- a/drivers/net/ethernet/ibm/emac/Makefile +++ b/drivers/net/ethernet/ibm/emac/Makefile @@ -8,4 +8,3 @@ ibm_emac-y := mal.o core.o phy.o ibm_emac-$(CONFIG_IBM_EMAC_ZMII) += zmii.o ibm_emac-$(CONFIG_IBM_EMAC_RGMII) += rgmii.o ibm_emac-$(CONFIG_IBM_EMAC_TAH) += tah.o -ibm_emac-$(CONFIG_IBM_EMAC_DEBUG) += debug.o diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index c44036d5761a..508923f39ccf 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -1929,7 +1929,7 @@ static struct net_device_stats *emac_stats(struct net_device *ndev) struct emac_instance *dev = netdev_priv(ndev); struct emac_stats *st = &dev->stats; struct emac_error_stats *est = &dev->estats; - struct net_device_stats *nst = &dev->nstats; + struct net_device_stats *nst = &ndev->stats; unsigned long flags; DBG2(dev, "stats" NL); @@ -3173,8 +3173,6 @@ static int emac_probe(struct platform_device *ofdev) printk("%s: found %s PHY (0x%02x)\n", ndev->name, dev->phy.def->name, dev->phy.address); - emac_dbg_register(dev); - /* Life is good */ return 0; @@ -3243,7 +3241,6 @@ static int emac_remove(struct platform_device *ofdev) mal_unregister_commac(dev->mal, &dev->commac); emac_put_deps(dev); - emac_dbg_unregister(dev); iounmap(dev->emacp); if (dev->wol_irq) @@ -3326,9 +3323,6 @@ static int __init emac_init(void) printk(KERN_INFO DRV_DESC ", version " DRV_VERSION "\n"); - /* Init debug stuff */ - emac_init_debug(); - /* Build EMAC boot list */ emac_make_bootlist(); @@ -3373,7 +3367,6 @@ static void __exit emac_exit(void) rgmii_exit(); zmii_exit(); mal_exit(); - emac_fini_debug(); /* Destroy EMAC boot list */ for (i = 0; i < EMAC_BOOT_LIST_SIZE; i++) diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h index 0710a6685489..f10e156641d5 100644 --- a/drivers/net/ethernet/ibm/emac/core.h +++ b/drivers/net/ethernet/ibm/emac/core.h @@ -265,7 +265,6 @@ struct emac_instance { /* Stats */ struct emac_error_stats estats; - struct net_device_stats nstats; struct emac_stats stats; /* Misc diff --git a/drivers/net/ethernet/ibm/emac/debug.c b/drivers/net/ethernet/ibm/emac/debug.c deleted file mode 100644 index a559f326bf63..000000000000 --- a/drivers/net/ethernet/ibm/emac/debug.c +++ /dev/null @@ -1,270 +0,0 @@ -/* - * drivers/net/ethernet/ibm/emac/debug.c - * - * Driver for PowerPC 4xx on-chip ethernet controller, debug print routines. - * - * Copyright 2007 Benjamin Herrenschmidt, IBM Corp. - * <benh@kernel.crashing.org> - * - * Based on the arch/ppc version of the driver: - * - * Copyright (c) 2004, 2005 Zultys Technologies - * Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - */ -#include <linux/init.h> -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/netdevice.h> -#include <linux/sysrq.h> -#include <asm/io.h> - -#include "core.h" - -static DEFINE_SPINLOCK(emac_dbg_lock); - -static void emac_desc_dump(struct emac_instance *p) -{ - int i; - printk("** EMAC %s TX BDs **\n" - " tx_cnt = %d tx_slot = %d ack_slot = %d\n", - p->ofdev->dev.of_node->full_name, - p->tx_cnt, p->tx_slot, p->ack_slot); - for (i = 0; i < NUM_TX_BUFF / 2; ++i) - printk - ("bd[%2d] 0x%08x %c 0x%04x %4u - bd[%2d] 0x%08x %c 0x%04x %4u\n", - i, p->tx_desc[i].data_ptr, p->tx_skb[i] ? 'V' : ' ', - p->tx_desc[i].ctrl, p->tx_desc[i].data_len, - NUM_TX_BUFF / 2 + i, - p->tx_desc[NUM_TX_BUFF / 2 + i].data_ptr, - p->tx_skb[NUM_TX_BUFF / 2 + i] ? 'V' : ' ', - p->tx_desc[NUM_TX_BUFF / 2 + i].ctrl, - p->tx_desc[NUM_TX_BUFF / 2 + i].data_len); - - printk("** EMAC %s RX BDs **\n" - " rx_slot = %d flags = 0x%lx rx_skb_size = %d rx_sync_size = %d\n" - " rx_sg_skb = 0x%p\n", - p->ofdev->dev.of_node->full_name, - p->rx_slot, p->commac.flags, p->rx_skb_size, - p->rx_sync_size, p->rx_sg_skb); - for (i = 0; i < NUM_RX_BUFF / 2; ++i) - printk - ("bd[%2d] 0x%08x %c 0x%04x %4u - bd[%2d] 0x%08x %c 0x%04x %4u\n", - i, p->rx_desc[i].data_ptr, p->rx_skb[i] ? 'V' : ' ', - p->rx_desc[i].ctrl, p->rx_desc[i].data_len, - NUM_RX_BUFF / 2 + i, - p->rx_desc[NUM_RX_BUFF / 2 + i].data_ptr, - p->rx_skb[NUM_RX_BUFF / 2 + i] ? 'V' : ' ', - p->rx_desc[NUM_RX_BUFF / 2 + i].ctrl, - p->rx_desc[NUM_RX_BUFF / 2 + i].data_len); -} - -static void emac_mac_dump(struct emac_instance *dev) -{ - struct emac_regs __iomem *p = dev->emacp; - const int xaht_regs = EMAC_XAHT_REGS(dev); - u32 *gaht_base = emac_gaht_base(dev); - u32 *iaht_base = emac_iaht_base(dev); - int emac4sync = emac_has_feature(dev, EMAC_FTR_EMAC4SYNC); - int n; - - printk("** EMAC %s registers **\n" - "MR0 = 0x%08x MR1 = 0x%08x TMR0 = 0x%08x TMR1 = 0x%08x\n" - "RMR = 0x%08x ISR = 0x%08x ISER = 0x%08x\n" - "IAR = %04x%08x VTPID = 0x%04x VTCI = 0x%04x\n", - dev->ofdev->dev.of_node->full_name, - in_be32(&p->mr0), in_be32(&p->mr1), - in_be32(&p->tmr0), in_be32(&p->tmr1), - in_be32(&p->rmr), in_be32(&p->isr), in_be32(&p->iser), - in_be32(&p->iahr), in_be32(&p->ialr), in_be32(&p->vtpid), - in_be32(&p->vtci) - ); - - if (emac4sync) - printk("MAR = %04x%08x MMAR = %04x%08x\n", - in_be32(&p->u0.emac4sync.mahr), - in_be32(&p->u0.emac4sync.malr), - in_be32(&p->u0.emac4sync.mmahr), - in_be32(&p->u0.emac4sync.mmalr) - ); - - for (n = 0; n < xaht_regs; n++) - printk("IAHT%02d = 0x%08x\n", n + 1, in_be32(iaht_base + n)); - - for (n = 0; n < xaht_regs; n++) - printk("GAHT%02d = 0x%08x\n", n + 1, in_be32(gaht_base + n)); - - printk("LSA = %04x%08x IPGVR = 0x%04x\n" - "STACR = 0x%08x TRTR = 0x%08x RWMR = 0x%08x\n" - "OCTX = 0x%08x OCRX = 0x%08x\n", - in_be32(&p->lsah), in_be32(&p->lsal), in_be32(&p->ipgvr), - in_be32(&p->stacr), in_be32(&p->trtr), in_be32(&p->rwmr), - in_be32(&p->octx), in_be32(&p->ocrx) - ); - - if (!emac4sync) { - printk("IPCR = 0x%08x\n", - in_be32(&p->u1.emac4.ipcr) - ); - } else { - printk("REVID = 0x%08x TPC = 0x%08x\n", - in_be32(&p->u1.emac4sync.revid), - in_be32(&p->u1.emac4sync.tpc) - ); - } - - emac_desc_dump(dev); -} - -static void emac_mal_dump(struct mal_instance *mal) -{ - int i; - - printk("** MAL %s Registers **\n" - "CFG = 0x%08x ESR = 0x%08x IER = 0x%08x\n" - "TX|CASR = 0x%08x CARR = 0x%08x EOBISR = 0x%08x DEIR = 0x%08x\n" - "RX|CASR = 0x%08x CARR = 0x%08x EOBISR = 0x%08x DEIR = 0x%08x\n", - mal->ofdev->dev.of_node->full_name, - get_mal_dcrn(mal, MAL_CFG), get_mal_dcrn(mal, MAL_ESR), - get_mal_dcrn(mal, MAL_IER), - get_mal_dcrn(mal, MAL_TXCASR), get_mal_dcrn(mal, MAL_TXCARR), - get_mal_dcrn(mal, MAL_TXEOBISR), get_mal_dcrn(mal, MAL_TXDEIR), - get_mal_dcrn(mal, MAL_RXCASR), get_mal_dcrn(mal, MAL_RXCARR), - get_mal_dcrn(mal, MAL_RXEOBISR), get_mal_dcrn(mal, MAL_RXDEIR) - ); - - printk("TX|"); - for (i = 0; i < mal->num_tx_chans; ++i) { - if (i && !(i % 4)) - printk("\n "); - printk("CTP%d = 0x%08x ", i, get_mal_dcrn(mal, MAL_TXCTPR(i))); - } - printk("\nRX|"); - for (i = 0; i < mal->num_rx_chans; ++i) { - if (i && !(i % 4)) - printk("\n "); - printk("CTP%d = 0x%08x ", i, get_mal_dcrn(mal, MAL_RXCTPR(i))); - } - printk("\n "); - for (i = 0; i < mal->num_rx_chans; ++i) { - u32 r = get_mal_dcrn(mal, MAL_RCBS(i)); - if (i && !(i % 3)) - printk("\n "); - printk("RCBS%d = 0x%08x (%d) ", i, r, r * 16); - } - printk("\n"); -} - -static struct emac_instance *__emacs[4]; -static struct mal_instance *__mals[1]; - -void emac_dbg_register(struct emac_instance *dev) -{ - unsigned long flags; - int i; - - spin_lock_irqsave(&emac_dbg_lock, flags); - for (i = 0; i < ARRAY_SIZE(__emacs); i++) - if (__emacs[i] == NULL) { - __emacs[i] = dev; - break; - } - spin_unlock_irqrestore(&emac_dbg_lock, flags); -} - -void emac_dbg_unregister(struct emac_instance *dev) -{ - unsigned long flags; - int i; - - spin_lock_irqsave(&emac_dbg_lock, flags); - for (i = 0; i < ARRAY_SIZE(__emacs); i++) - if (__emacs[i] == dev) { - __emacs[i] = NULL; - break; - } - spin_unlock_irqrestore(&emac_dbg_lock, flags); -} - -void mal_dbg_register(struct mal_instance *mal) -{ - unsigned long flags; - int i; - - spin_lock_irqsave(&emac_dbg_lock, flags); - for (i = 0; i < ARRAY_SIZE(__mals); i++) - if (__mals[i] == NULL) { - __mals[i] = mal; - break; - } - spin_unlock_irqrestore(&emac_dbg_lock, flags); -} - -void mal_dbg_unregister(struct mal_instance *mal) -{ - unsigned long flags; - int i; - - spin_lock_irqsave(&emac_dbg_lock, flags); - for (i = 0; i < ARRAY_SIZE(__mals); i++) - if (__mals[i] == mal) { - __mals[i] = NULL; - break; - } - spin_unlock_irqrestore(&emac_dbg_lock, flags); -} - -void emac_dbg_dump_all(void) -{ - unsigned int i; - unsigned long flags; - - spin_lock_irqsave(&emac_dbg_lock, flags); - - for (i = 0; i < ARRAY_SIZE(__mals); ++i) - if (__mals[i]) - emac_mal_dump(__mals[i]); - - for (i = 0; i < ARRAY_SIZE(__emacs); ++i) - if (__emacs[i]) - emac_mac_dump(__emacs[i]); - - spin_unlock_irqrestore(&emac_dbg_lock, flags); -} - -#if defined(CONFIG_MAGIC_SYSRQ) -static void emac_sysrq_handler(int key) -{ - emac_dbg_dump_all(); -} - -static struct sysrq_key_op emac_sysrq_op = { - .handler = emac_sysrq_handler, - .help_msg = "emac(c)", - .action_msg = "Show EMAC(s) status", -}; - -int __init emac_init_debug(void) -{ - return register_sysrq_key('c', &emac_sysrq_op); -} - -void __exit emac_fini_debug(void) -{ - unregister_sysrq_key('c', &emac_sysrq_op); -} - -#else -int __init emac_init_debug(void) -{ - return 0; -} -void __exit emac_fini_debug(void) -{ -} -#endif /* CONFIG_MAGIC_SYSRQ */ diff --git a/drivers/net/ethernet/ibm/emac/debug.h b/drivers/net/ethernet/ibm/emac/debug.h index 9c45efe4c8fe..5bdfc174a07e 100644 --- a/drivers/net/ethernet/ibm/emac/debug.h +++ b/drivers/net/ethernet/ibm/emac/debug.h @@ -25,32 +25,9 @@ #include "core.h" #if defined(CONFIG_IBM_EMAC_DEBUG) - -struct emac_instance; -struct mal_instance; - -void emac_dbg_register(struct emac_instance *dev); -void emac_dbg_unregister(struct emac_instance *dev); -void mal_dbg_register(struct mal_instance *mal); -void mal_dbg_unregister(struct mal_instance *mal); -int emac_init_debug(void) __init; -void emac_fini_debug(void) __exit; -void emac_dbg_dump_all(void); - # define DBG_LEVEL 1 - #else - -# define emac_dbg_register(x) do { } while(0) -# define emac_dbg_unregister(x) do { } while(0) -# define mal_dbg_register(x) do { } while(0) -# define mal_dbg_unregister(x) do { } while(0) -# define emac_init_debug() do { } while(0) -# define emac_fini_debug() do { } while(0) -# define emac_dbg_dump_all() do { } while(0) - # define DBG_LEVEL 0 - #endif #define EMAC_DBG(d, name, fmt, arg...) \ diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c index cd3227b088b7..91b1a558f37d 100644 --- a/drivers/net/ethernet/ibm/emac/mal.c +++ b/drivers/net/ethernet/ibm/emac/mal.c @@ -695,8 +695,6 @@ static int mal_probe(struct platform_device *ofdev) wmb(); platform_set_drvdata(ofdev, mal); - mal_dbg_register(mal); - return 0; fail6: @@ -740,8 +738,6 @@ static int mal_remove(struct platform_device *ofdev) mal_reset(mal); - mal_dbg_unregister(mal); - dma_free_coherent(&ofdev->dev, sizeof(struct mal_descriptor) * (NUM_TX_BUFF * mal->num_tx_chans + diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 7ba43cfadf3a..e8c72abfd7ac 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -193,9 +193,9 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter, if (!ltb->buff) return; - dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr); if (!adapter->failover) send_request_unmap(adapter, ltb->map_id); + dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr); } static void replenish_rx_pool(struct ibmvnic_adapter *adapter, @@ -502,48 +502,21 @@ static int init_tx_pools(struct net_device *netdev) return 0; } -static void release_bounce_buffer(struct ibmvnic_adapter *adapter) -{ - struct device *dev = &adapter->vdev->dev; - - if (!adapter->bounce_buffer) - return; - - if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) { - dma_unmap_single(dev, adapter->bounce_buffer_dma, - adapter->bounce_buffer_size, - DMA_BIDIRECTIONAL); - adapter->bounce_buffer_dma = DMA_ERROR_CODE; - } - - kfree(adapter->bounce_buffer); - adapter->bounce_buffer = NULL; -} - -static int init_bounce_buffer(struct net_device *netdev) +static void release_error_buffers(struct ibmvnic_adapter *adapter) { - struct ibmvnic_adapter *adapter = netdev_priv(netdev); struct device *dev = &adapter->vdev->dev; - char *buf; - int buf_sz; - dma_addr_t map_addr; - - buf_sz = (netdev->mtu + ETH_HLEN - 1) / PAGE_SIZE + 1; - buf = kmalloc(adapter->bounce_buffer_size, GFP_KERNEL); - if (!buf) - return -1; + struct ibmvnic_error_buff *error_buff, *tmp; + unsigned long flags; - map_addr = dma_map_single(dev, buf, buf_sz, DMA_TO_DEVICE); - if (dma_mapping_error(dev, map_addr)) { - dev_err(dev, "Couldn't map bounce buffer\n"); - kfree(buf); - return -1; + spin_lock_irqsave(&adapter->error_list_lock, flags); + list_for_each_entry_safe(error_buff, tmp, &adapter->errors, list) { + list_del(&error_buff->list); + dma_unmap_single(dev, error_buff->dma, error_buff->len, + DMA_FROM_DEVICE); + kfree(error_buff->buff); + kfree(error_buff); } - - adapter->bounce_buffer = buf; - adapter->bounce_buffer_size = buf_sz; - adapter->bounce_buffer_dma = map_addr; - return 0; + spin_unlock_irqrestore(&adapter->error_list_lock, flags); } static int ibmvnic_login(struct net_device *netdev) @@ -580,14 +553,11 @@ static int ibmvnic_login(struct net_device *netdev) static void release_resources(struct ibmvnic_adapter *adapter) { - release_bounce_buffer(adapter); release_tx_pools(adapter); release_rx_pools(adapter); - release_sub_crqs(adapter); - release_crq_queue(adapter); - release_stats_token(adapter); + release_error_buffers(adapter); } static int ibmvnic_open(struct net_device *netdev) @@ -641,10 +611,6 @@ static int ibmvnic_open(struct net_device *netdev) if (rc) goto ibmvnic_open_fail; - rc = init_bounce_buffer(netdev); - if (rc) - goto ibmvnic_open_fail; - replenish_pools(adapter); /* We're ready to receive frames, enable the sub-crq interrupts and @@ -674,6 +640,23 @@ ibmvnic_open_fail: return -ENOMEM; } +static void disable_sub_crqs(struct ibmvnic_adapter *adapter) +{ + int i; + + if (adapter->tx_scrq) { + for (i = 0; i < adapter->req_tx_queues; i++) + if (adapter->tx_scrq[i]) + disable_irq(adapter->tx_scrq[i]->irq); + } + + if (adapter->rx_scrq) { + for (i = 0; i < adapter->req_rx_queues; i++) + if (adapter->rx_scrq[i]) + disable_irq(adapter->rx_scrq[i]->irq); + } +} + static int ibmvnic_close(struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); @@ -681,6 +664,7 @@ static int ibmvnic_close(struct net_device *netdev) int i; adapter->closing = true; + disable_sub_crqs(adapter); for (i = 0; i < adapter->req_rx_queues; i++) napi_disable(&adapter->napi[i]); @@ -847,7 +831,6 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) unsigned int tx_bytes = 0; dma_addr_t data_dma_addr; struct netdev_queue *txq; - bool used_bounce = false; unsigned long lpar_rc; union sub_crq tx_crq; unsigned int offset; @@ -888,7 +871,6 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_buff->index = index; tx_buff->pool_index = queue_num; tx_buff->last_frag = true; - tx_buff->used_bounce = used_bounce; memset(&tx_crq, 0, sizeof(tx_crq)); tx_crq.v1.first = IBMVNIC_CRQ_CMD; @@ -962,9 +944,8 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) goto out; } - atomic_inc(&tx_scrq->used); - - if (atomic_read(&tx_scrq->used) >= adapter->req_tx_entries_per_subcrq) { + if (atomic_inc_return(&tx_scrq->used) + >= adapter->req_tx_entries_per_subcrq) { netdev_info(netdev, "Stopping queue %d\n", queue_num); netif_stop_subqueue(netdev, queue_num); } @@ -1309,6 +1290,12 @@ static void release_sub_crq_queue(struct ibmvnic_adapter *adapter, scrq->crq_num); } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); + if (rc) { + netdev_err(adapter->netdev, + "Failed to release sub-CRQ %16lx, rc = %ld\n", + scrq->crq_num, rc); + } + dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE, DMA_BIDIRECTIONAL); free_pages((unsigned long)scrq->msgs, 2); @@ -1322,12 +1309,12 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter struct ibmvnic_sub_crq_queue *scrq; int rc; - scrq = kmalloc(sizeof(*scrq), GFP_ATOMIC); + scrq = kzalloc(sizeof(*scrq), GFP_ATOMIC); if (!scrq) return NULL; - scrq->msgs = (union sub_crq *)__get_free_pages(GFP_ATOMIC, 2); - memset(scrq->msgs, 0, 4 * PAGE_SIZE); + scrq->msgs = + (union sub_crq *)__get_free_pages(GFP_ATOMIC | __GFP_ZERO, 2); if (!scrq->msgs) { dev_warn(dev, "Couldn't allocate crq queue messages page\n"); goto zero_page_failed; @@ -1355,9 +1342,6 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter scrq->adapter = adapter; scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs); - scrq->cur = 0; - atomic_set(&scrq->used, 0); - scrq->rx_skb_top = NULL; spin_lock_init(&scrq->lock); netdev_dbg(adapter->netdev, @@ -1482,7 +1466,6 @@ restart_loop: continue; txbuff->data_dma[j] = 0; - txbuff->used_bounce = false; } /* if sub_crq was sent indirectly */ first = txbuff->indir_arr[0].generic.first; @@ -1493,9 +1476,8 @@ restart_loop: } if (txbuff->last_frag) { - atomic_dec(&scrq->used); - - if (atomic_read(&scrq->used) <= + if (atomic_sub_return(next->tx_comp.num_comps, + &scrq->used) <= (adapter->req_tx_entries_per_subcrq / 2) && netif_subqueue_stopped(adapter->netdev, txbuff->skb)) { @@ -1953,13 +1935,11 @@ static void send_login(struct ibmvnic_adapter *adapter) { struct ibmvnic_login_rsp_buffer *login_rsp_buffer; struct ibmvnic_login_buffer *login_buffer; - struct ibmvnic_inflight_cmd *inflight_cmd; struct device *dev = &adapter->vdev->dev; dma_addr_t rsp_buffer_token; dma_addr_t buffer_token; size_t rsp_buffer_size; union ibmvnic_crq crq; - unsigned long flags; size_t buffer_size; __be64 *tx_list_p; __be64 *rx_list_p; @@ -1996,11 +1976,7 @@ static void send_login(struct ibmvnic_adapter *adapter) dev_err(dev, "Couldn't map login rsp buffer\n"); goto buf_rsp_map_failed; } - inflight_cmd = kmalloc(sizeof(*inflight_cmd), GFP_ATOMIC); - if (!inflight_cmd) { - dev_err(dev, "Couldn't allocate inflight_cmd\n"); - goto inflight_alloc_failed; - } + adapter->login_buf = login_buffer; adapter->login_buf_token = buffer_token; adapter->login_buf_sz = buffer_size; @@ -2051,20 +2027,10 @@ static void send_login(struct ibmvnic_adapter *adapter) crq.login.cmd = LOGIN; crq.login.ioba = cpu_to_be32(buffer_token); crq.login.len = cpu_to_be32(buffer_size); - - memcpy(&inflight_cmd->crq, &crq, sizeof(crq)); - - spin_lock_irqsave(&adapter->inflight_lock, flags); - list_add_tail(&inflight_cmd->list, &adapter->inflight); - spin_unlock_irqrestore(&adapter->inflight_lock, flags); - ibmvnic_send_crq(adapter, &crq); return; -inflight_alloc_failed: - dma_unmap_single(dev, rsp_buffer_token, rsp_buffer_size, - DMA_FROM_DEVICE); buf_rsp_map_failed: kfree(login_rsp_buffer); buf_rsp_alloc_failed: @@ -2370,7 +2336,6 @@ static void handle_error_indication(union ibmvnic_crq *crq, struct ibmvnic_adapter *adapter) { int detail_len = be32_to_cpu(crq->error_indication.detail_error_sz); - struct ibmvnic_inflight_cmd *inflight_cmd; struct device *dev = &adapter->vdev->dev; struct ibmvnic_error_buff *error_buff; union ibmvnic_crq new_crq; @@ -2402,15 +2367,6 @@ static void handle_error_indication(union ibmvnic_crq *crq, return; } - inflight_cmd = kmalloc(sizeof(*inflight_cmd), GFP_ATOMIC); - if (!inflight_cmd) { - dma_unmap_single(dev, error_buff->dma, detail_len, - DMA_FROM_DEVICE); - kfree(error_buff->buff); - kfree(error_buff); - return; - } - error_buff->len = detail_len; error_buff->error_id = crq->error_indication.error_id; @@ -2424,13 +2380,6 @@ static void handle_error_indication(union ibmvnic_crq *crq, new_crq.request_error_info.ioba = cpu_to_be32(error_buff->dma); new_crq.request_error_info.len = cpu_to_be32(detail_len); new_crq.request_error_info.error_id = crq->error_indication.error_id; - - memcpy(&inflight_cmd->crq, &crq, sizeof(crq)); - - spin_lock_irqsave(&adapter->inflight_lock, flags); - list_add_tail(&inflight_cmd->list, &adapter->inflight); - spin_unlock_irqrestore(&adapter->inflight_lock, flags); - ibmvnic_send_crq(adapter, &new_crq); } @@ -2815,48 +2764,6 @@ out: } } -static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter) -{ - struct ibmvnic_inflight_cmd *inflight_cmd, *tmp1; - struct device *dev = &adapter->vdev->dev; - struct ibmvnic_error_buff *error_buff, *tmp2; - unsigned long flags; - unsigned long flags2; - - spin_lock_irqsave(&adapter->inflight_lock, flags); - list_for_each_entry_safe(inflight_cmd, tmp1, &adapter->inflight, list) { - switch (inflight_cmd->crq.generic.cmd) { - case LOGIN: - dma_unmap_single(dev, adapter->login_buf_token, - adapter->login_buf_sz, - DMA_BIDIRECTIONAL); - dma_unmap_single(dev, adapter->login_rsp_buf_token, - adapter->login_rsp_buf_sz, - DMA_BIDIRECTIONAL); - kfree(adapter->login_rsp_buf); - kfree(adapter->login_buf); - break; - case REQUEST_ERROR_INFO: - spin_lock_irqsave(&adapter->error_list_lock, flags2); - list_for_each_entry_safe(error_buff, tmp2, - &adapter->errors, list) { - dma_unmap_single(dev, error_buff->dma, - error_buff->len, - DMA_FROM_DEVICE); - kfree(error_buff->buff); - list_del(&error_buff->list); - kfree(error_buff); - } - spin_unlock_irqrestore(&adapter->error_list_lock, - flags2); - break; - } - list_del(&inflight_cmd->list); - kfree(inflight_cmd); - } - spin_unlock_irqrestore(&adapter->inflight_lock, flags); -} - static void ibmvnic_xport_event(struct work_struct *work) { struct ibmvnic_adapter *adapter = container_of(work, @@ -2865,7 +2772,6 @@ static void ibmvnic_xport_event(struct work_struct *work) struct device *dev = &adapter->vdev->dev; long rc; - ibmvnic_free_inflight(adapter); release_sub_crqs(adapter); if (adapter->migrated) { rc = ibmvnic_reenable_crq_queue(adapter); @@ -2884,11 +2790,12 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, struct ibmvnic_generic_crq *gen_crq = &crq->generic; struct net_device *netdev = adapter->netdev; struct device *dev = &adapter->vdev->dev; + u64 *u64_crq = (u64 *)crq; long rc; netdev_dbg(netdev, "Handling CRQ: %016lx %016lx\n", - ((unsigned long int *)crq)[0], - ((unsigned long int *)crq)[1]); + (unsigned long int)cpu_to_be64(u64_crq[0]), + (unsigned long int)cpu_to_be64(u64_crq[1])); switch (gen_crq->first) { case IBMVNIC_CRQ_INIT_RSP: switch (gen_crq->cmd) { @@ -3022,12 +2929,8 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, static irqreturn_t ibmvnic_interrupt(int irq, void *instance) { struct ibmvnic_adapter *adapter = instance; - unsigned long flags; - spin_lock_irqsave(&adapter->crq.lock, flags); - vio_disable_interrupts(adapter->vdev); tasklet_schedule(&adapter->tasklet); - spin_unlock_irqrestore(&adapter->crq.lock, flags); return IRQ_HANDLED; } @@ -3035,32 +2938,23 @@ static void ibmvnic_tasklet(void *data) { struct ibmvnic_adapter *adapter = data; struct ibmvnic_crq_queue *queue = &adapter->crq; - struct vio_dev *vdev = adapter->vdev; union ibmvnic_crq *crq; unsigned long flags; bool done = false; spin_lock_irqsave(&queue->lock, flags); - vio_disable_interrupts(vdev); while (!done) { /* Pull all the valid messages off the CRQ */ while ((crq = ibmvnic_next_crq(adapter)) != NULL) { ibmvnic_handle_crq(crq, adapter); crq->generic.first = 0; } - vio_enable_interrupts(vdev); - crq = ibmvnic_next_crq(adapter); - if (crq) { - vio_disable_interrupts(vdev); - ibmvnic_handle_crq(crq, adapter); - crq->generic.first = 0; - } else { - /* remain in tasklet until all - * capabilities responses are received - */ - if (!adapter->wait_capability) - done = true; - } + + /* remain in tasklet until all + * capabilities responses are received + */ + if (!adapter->wait_capability) + done = true; } /* if capabilities CRQ's were sent in this tasklet, the following * tasklet must wait until all responses are received @@ -3341,9 +3235,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) spin_lock_init(&adapter->stats_lock); INIT_LIST_HEAD(&adapter->errors); - INIT_LIST_HEAD(&adapter->inflight); spin_lock_init(&adapter->error_list_lock); - spin_lock_init(&adapter->inflight_lock); rc = ibmvnic_init(adapter); if (rc) { @@ -3368,8 +3260,14 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) static int ibmvnic_remove(struct vio_dev *dev) { struct net_device *netdev = dev_get_drvdata(&dev->dev); + struct ibmvnic_adapter *adapter = netdev_priv(netdev); unregister_netdev(netdev); + + release_resources(adapter); + release_sub_crqs(adapter); + release_crq_queue(adapter); + free_netdev(netdev); dev_set_drvdata(&dev->dev, NULL); @@ -3393,7 +3291,6 @@ static unsigned long ibmvnic_get_desired_dma(struct vio_dev *vdev) adapter = netdev_priv(netdev); ret += PAGE_SIZE; /* the crq message queue */ - ret += adapter->bounce_buffer_size; ret += IOMMU_PAGE_ALIGN(sizeof(struct ibmvnic_statistics), tbl); for (i = 0; i < adapter->req_tx_queues + adapter->req_rx_queues; i++) diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index b0d0b890d033..355225cf6d30 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -518,8 +518,8 @@ struct ibmvnic_change_mac_addr { u8 first; u8 cmd; u8 mac_addr[6]; - struct ibmvnic_rc rc; u8 reserved[4]; + struct ibmvnic_rc rc; } __packed __aligned(8); struct ibmvnic_multicast_ctrl { @@ -868,7 +868,6 @@ struct ibmvnic_tx_buff { int index; int pool_index; bool last_frag; - bool used_bounce; union sub_crq indir_arr[6]; u8 hdr_data[140]; dma_addr_t indir_dma; @@ -913,11 +912,6 @@ struct ibmvnic_error_buff { __be32 error_id; }; -struct ibmvnic_inflight_cmd { - union ibmvnic_crq crq; - struct list_head list; -}; - struct ibmvnic_adapter { struct vio_dev *vdev; struct net_device *netdev; @@ -929,9 +923,6 @@ struct ibmvnic_adapter { dma_addr_t ip_offload_ctrl_tok; bool migrated; u32 msg_enable; - void *bounce_buffer; - int bounce_buffer_size; - dma_addr_t bounce_buffer_dma; /* Statistics */ struct ibmvnic_statistics stats; @@ -978,10 +969,6 @@ struct ibmvnic_adapter { struct completion fw_done; - /* in-flight commands that allocate and/or map memory*/ - struct list_head inflight; - spinlock_t inflight_lock; - /* partner capabilities */ u64 min_tx_queues; u64 min_rx_queues; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 2175cced402f..e9af89ad039c 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6274,8 +6274,8 @@ static int e1000e_pm_freeze(struct device *dev) /* Quiesce the device without resetting the hardware */ e1000e_down(adapter, false); e1000_free_irq(adapter); - e1000e_reset_interrupt_capability(adapter); } + e1000e_reset_interrupt_capability(adapter); /* Allow time for pending master requests to run */ e1000e_disable_pcie_master(&adapter->hw); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 52b979443cde..689c413b7782 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * 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, @@ -65,14 +65,16 @@ enum fm10k_ring_state_t { __FM10K_TX_DETECT_HANG, __FM10K_HANG_CHECK_ARMED, __FM10K_TX_XPS_INIT_DONE, + /* This must be last and is used to calculate BITMAP size */ + __FM10K_TX_STATE_SIZE__, }; #define check_for_tx_hang(ring) \ - test_bit(__FM10K_TX_DETECT_HANG, &(ring)->state) + test_bit(__FM10K_TX_DETECT_HANG, (ring)->state) #define set_check_for_tx_hang(ring) \ - set_bit(__FM10K_TX_DETECT_HANG, &(ring)->state) + set_bit(__FM10K_TX_DETECT_HANG, (ring)->state) #define clear_check_for_tx_hang(ring) \ - clear_bit(__FM10K_TX_DETECT_HANG, &(ring)->state) + clear_bit(__FM10K_TX_DETECT_HANG, (ring)->state) struct fm10k_tx_buffer { struct fm10k_tx_desc *next_to_watch; @@ -126,7 +128,7 @@ struct fm10k_ring { struct fm10k_rx_buffer *rx_buffer; }; u32 __iomem *tail; - unsigned long state; + DECLARE_BITMAP(state, __FM10K_TX_STATE_SIZE__); dma_addr_t dma; /* phys. address of descriptor ring */ unsigned int size; /* length in bytes */ @@ -249,18 +251,46 @@ struct fm10k_udp_port { /* one work queue for entire driver */ extern struct workqueue_struct *fm10k_workqueue; +/* The following enumeration contains flags which indicate or enable modified + * driver behaviors. To avoid race conditions, the flags are stored in + * a BITMAP in the fm10k_intfc structure. The BITMAP should be accessed using + * atomic *_bit() operations. + */ +enum fm10k_flags_t { + FM10K_FLAG_RESET_REQUESTED, + FM10K_FLAG_RSS_FIELD_IPV4_UDP, + FM10K_FLAG_RSS_FIELD_IPV6_UDP, + FM10K_FLAG_SWPRI_CONFIG, + /* __FM10K_FLAGS_SIZE__ is used to calculate the size of + * interface->flags and must be the last value in this + * enumeration. + */ + __FM10K_FLAGS_SIZE__ +}; + +enum fm10k_state_t { + __FM10K_RESETTING, + __FM10K_DOWN, + __FM10K_SERVICE_SCHED, + __FM10K_SERVICE_REQUEST, + __FM10K_SERVICE_DISABLE, + __FM10K_MBX_LOCK, + __FM10K_LINK_DOWN, + __FM10K_UPDATING_STATS, + /* This value must be last and determines the BITMAP size */ + __FM10K_STATE_SIZE__, +}; + struct fm10k_intfc { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; struct net_device *netdev; struct fm10k_l2_accel *l2_accel; /* pointer to L2 acceleration list */ struct pci_dev *pdev; - unsigned long state; + DECLARE_BITMAP(state, __FM10K_STATE_SIZE__); + + /* Access flag values using atomic *_bit() operations */ + DECLARE_BITMAP(flags, __FM10K_FLAGS_SIZE__); - u32 flags; -#define FM10K_FLAG_RESET_REQUESTED (u32)(BIT(0)) -#define FM10K_FLAG_RSS_FIELD_IPV4_UDP (u32)(BIT(1)) -#define FM10K_FLAG_RSS_FIELD_IPV6_UDP (u32)(BIT(2)) -#define FM10K_FLAG_SWPRI_CONFIG (u32)(BIT(3)) int xcast_mode; /* Tx fast path data */ @@ -352,22 +382,12 @@ struct fm10k_intfc { u16 vid; }; -enum fm10k_state_t { - __FM10K_RESETTING, - __FM10K_DOWN, - __FM10K_SERVICE_SCHED, - __FM10K_SERVICE_DISABLE, - __FM10K_MBX_LOCK, - __FM10K_LINK_DOWN, - __FM10K_UPDATING_STATS, -}; - static inline void fm10k_mbx_lock(struct fm10k_intfc *interface) { /* busy loop if we cannot obtain the lock as some calls * such as ndo_set_rx_mode may be made in atomic context */ - while (test_and_set_bit(__FM10K_MBX_LOCK, &interface->state)) + while (test_and_set_bit(__FM10K_MBX_LOCK, interface->state)) udelay(20); } @@ -375,12 +395,12 @@ static inline void fm10k_mbx_unlock(struct fm10k_intfc *interface) { /* flush memory to make sure state is correct */ smp_mb__before_atomic(); - clear_bit(__FM10K_MBX_LOCK, &interface->state); + clear_bit(__FM10K_MBX_LOCK, interface->state); } static inline int fm10k_mbx_trylock(struct fm10k_intfc *interface) { - return !test_and_set_bit(__FM10K_MBX_LOCK, &interface->state); + return !test_and_set_bit(__FM10K_MBX_LOCK, interface->state); } /* fm10k_test_staterr - test bits in Rx descriptor status and error fields */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 0c84fef750f4..c7234f35f8ff 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * 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, @@ -562,7 +562,7 @@ static int fm10k_set_ringparam(struct net_device *netdev, return 0; } - while (test_and_set_bit(__FM10K_RESETTING, &interface->state)) + while (test_and_set_bit(__FM10K_RESETTING, interface->state)) usleep_range(1000, 2000); if (!netif_running(interface->netdev)) { @@ -648,7 +648,7 @@ err_setup: fm10k_up(interface); vfree(temp_ring); clear_reset: - clear_bit(__FM10K_RESETTING, &interface->state); + clear_bit(__FM10K_RESETTING, interface->state); return err; } @@ -716,7 +716,8 @@ static int fm10k_get_rss_hash_opts(struct fm10k_intfc *interface, cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; /* fall through */ case UDP_V4_FLOW: - if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV4_UDP) + if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, + interface->flags)) cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; /* fall through */ case SCTP_V4_FLOW: @@ -732,7 +733,8 @@ static int fm10k_get_rss_hash_opts(struct fm10k_intfc *interface, cmd->data |= RXH_IP_SRC | RXH_IP_DST; break; case UDP_V6_FLOW: - if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV6_UDP) + if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, + interface->flags)) cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; cmd->data |= RXH_IP_SRC | RXH_IP_DST; break; @@ -764,12 +766,13 @@ static int fm10k_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, return ret; } -#define UDP_RSS_FLAGS (FM10K_FLAG_RSS_FIELD_IPV4_UDP | \ - FM10K_FLAG_RSS_FIELD_IPV6_UDP) static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface, struct ethtool_rxnfc *nfc) { - u32 flags = interface->flags; + int rss_ipv4_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, + interface->flags); + int rss_ipv6_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, + interface->flags); /* RSS does not support anything other than hashing * to queues on src and dst IPs and ports @@ -793,10 +796,12 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface, return -EINVAL; switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { case 0: - flags &= ~FM10K_FLAG_RSS_FIELD_IPV4_UDP; + clear_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, + interface->flags); break; case (RXH_L4_B_0_1 | RXH_L4_B_2_3): - flags |= FM10K_FLAG_RSS_FIELD_IPV4_UDP; + set_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, + interface->flags); break; default: return -EINVAL; @@ -808,10 +813,12 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface, return -EINVAL; switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { case 0: - flags &= ~FM10K_FLAG_RSS_FIELD_IPV6_UDP; + clear_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, + interface->flags); break; case (RXH_L4_B_0_1 | RXH_L4_B_2_3): - flags |= FM10K_FLAG_RSS_FIELD_IPV6_UDP; + set_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, + interface->flags); break; default: return -EINVAL; @@ -835,28 +842,41 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface, return -EINVAL; } - /* if we changed something we need to update flags */ - if (flags != interface->flags) { + /* If something changed we need to update the MRQC register. Note that + * test_bit() is guaranteed to return strictly 0 or 1, so testing for + * equality is safe. + */ + if ((rss_ipv4_udp != test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, + interface->flags)) || + (rss_ipv6_udp != test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, + interface->flags))) { struct fm10k_hw *hw = &interface->hw; + bool warn = false; u32 mrqc; - if ((flags & UDP_RSS_FLAGS) && - !(interface->flags & UDP_RSS_FLAGS)) - netif_warn(interface, drv, interface->netdev, - "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n"); - - interface->flags = flags; - /* Perform hash on these packet types */ mrqc = FM10K_MRQC_IPV4 | FM10K_MRQC_TCP_IPV4 | FM10K_MRQC_IPV6 | FM10K_MRQC_TCP_IPV6; - if (flags & FM10K_FLAG_RSS_FIELD_IPV4_UDP) + if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, + interface->flags)) { mrqc |= FM10K_MRQC_UDP_IPV4; - if (flags & FM10K_FLAG_RSS_FIELD_IPV6_UDP) + warn = true; + } + if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, + interface->flags)) { mrqc |= FM10K_MRQC_UDP_IPV6; + warn = true; + } + + /* If we enable UDP RSS display a warning that this may cause + * fragmented UDP packets to arrive out of order. + */ + if (warn) + netif_warn(interface, drv, interface->netdev, + "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n"); fm10k_write_reg(hw, FM10K_MRQC(0), mrqc); } @@ -939,7 +959,7 @@ static void fm10k_self_test(struct net_device *dev, memset(data, 0, sizeof(*data) * FM10K_TEST_LEN); - if (FM10K_REMOVED(hw)) { + if (FM10K_REMOVED(hw->hw_addr)) { netif_err(interface, drv, dev, "Interface removed - test blocked\n"); eth_test->flags |= ETH_TEST_FL_FAILED; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 5bb233a9614c..9dffaba85ae6 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * 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, @@ -34,7 +34,7 @@ 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 - 2016 Intel Corporation."; + "Copyright(c) 2013 - 2017 Intel Corporation."; MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); @@ -1175,13 +1175,13 @@ bool fm10k_check_tx_hang(struct fm10k_ring *tx_ring) /* update completed stats and continue */ tx_ring->tx_stats.tx_done_old = tx_done; /* reset the countdown */ - clear_bit(__FM10K_HANG_CHECK_ARMED, &tx_ring->state); + clear_bit(__FM10K_HANG_CHECK_ARMED, tx_ring->state); return false; } /* make sure it is true for two checks in a row */ - return test_and_set_bit(__FM10K_HANG_CHECK_ARMED, &tx_ring->state); + return test_and_set_bit(__FM10K_HANG_CHECK_ARMED, tx_ring->state); } /** @@ -1191,9 +1191,9 @@ bool fm10k_check_tx_hang(struct fm10k_ring *tx_ring) void fm10k_tx_timeout_reset(struct fm10k_intfc *interface) { /* Do the reset outside of interrupt context */ - if (!test_bit(__FM10K_DOWN, &interface->state)) { + if (!test_bit(__FM10K_DOWN, interface->state)) { interface->tx_timeout_count++; - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); fm10k_service_event_schedule(interface); } } @@ -1214,7 +1214,7 @@ static bool fm10k_clean_tx_irq(struct fm10k_q_vector *q_vector, unsigned int budget = q_vector->tx.work_limit; unsigned int i = tx_ring->next_to_clean; - if (test_bit(__FM10K_DOWN, &interface->state)) + if (test_bit(__FM10K_DOWN, interface->state)) return true; tx_buffer = &tx_ring->tx_buffer[i]; @@ -1344,7 +1344,7 @@ static bool fm10k_clean_tx_irq(struct fm10k_q_vector *q_vector, smp_mb(); if (__netif_subqueue_stopped(tx_ring->netdev, tx_ring->queue_index) && - !test_bit(__FM10K_DOWN, &interface->state)) { + !test_bit(__FM10K_DOWN, interface->state)) { netif_wake_subqueue(tx_ring->netdev, tx_ring->queue_index); ++tx_ring->tx_stats.restart_queue; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 72481670478c..24f2f6f86f5a 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * 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, @@ -737,6 +737,23 @@ static void fm10k_tx_timeout(struct net_device *netdev) } } +/** + * fm10k_host_mbx_ready - Check PF interface's mailbox readiness + * @interface: board private structure + * + * This function checks if the PF interface's mailbox is ready before queueing + * mailbox messages for transmission. This will prevent filling the TX mailbox + * queue when the receiver is not ready. VF interfaces are exempt from this + * check since it will block all PF-VF mailbox messages from being sent from + * the VF to the PF at initialization. + **/ +static bool fm10k_host_mbx_ready(struct fm10k_intfc *interface) +{ + struct fm10k_hw *hw = &interface->hw; + + return (hw->mac.type == fm10k_mac_vf || interface->host_ready); +} + static int fm10k_uc_vlan_unsync(struct net_device *netdev, const unsigned char *uc_addr) { @@ -745,12 +762,15 @@ static int fm10k_uc_vlan_unsync(struct net_device *netdev, u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); - int err; + int err = -EHOSTDOWN; /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; - err = hw->mac.ops.update_uc_addr(hw, glort, uc_addr, vid, set, 0); + if (fm10k_host_mbx_ready(interface)) + err = hw->mac.ops.update_uc_addr(hw, glort, uc_addr, + vid, set, 0); + if (err) return err; @@ -766,12 +786,14 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev, u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); - int err; + int err = -EHOSTDOWN; /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; - err = hw->mac.ops.update_mc_addr(hw, glort, mc_addr, vid, set); + if (fm10k_host_mbx_ready(interface)) + err = hw->mac.ops.update_mc_addr(hw, glort, mc_addr, vid, set); + if (err) return err; @@ -822,7 +844,7 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) /* Do not throw an error if the interface is down. We will sync once * we come up */ - if (test_bit(__FM10K_DOWN, &interface->state)) + if (test_bit(__FM10K_DOWN, interface->state)) return 0; fm10k_mbx_lock(interface); @@ -834,9 +856,13 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) goto err_out; } - /* update our base MAC address */ - err = hw->mac.ops.update_uc_addr(hw, interface->glort, hw->mac.addr, - vid, set, 0); + /* update our base MAC address if host's mailbox is ready */ + if (fm10k_host_mbx_ready(interface)) + err = hw->mac.ops.update_uc_addr(hw, interface->glort, + hw->mac.addr, vid, set, 0); + else + err = -EHOSTDOWN; + if (err) goto err_out; @@ -907,12 +933,15 @@ static int __fm10k_uc_sync(struct net_device *dev, if (!is_valid_ether_addr(addr)) return -EADDRNOTAVAIL; - /* update table with current entries */ + /* update table with current entries if host's mailbox is ready */ + if (!fm10k_host_mbx_ready(interface)) + return -EHOSTDOWN; + for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { err = hw->mac.ops.update_uc_addr(hw, glort, addr, - vid, sync, 0); + vid, sync, 0); if (err) return err; } @@ -970,7 +999,10 @@ static int __fm10k_mc_sync(struct net_device *dev, struct fm10k_hw *hw = &interface->hw; u16 vid, glort = interface->glort; - /* update table with current entries */ + /* update table with current entries if host's mailbox is ready */ + if (!fm10k_host_mbx_ready(interface)) + return 0; + for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { @@ -1018,8 +1050,10 @@ static void fm10k_set_rx_mode(struct net_device *dev) if (interface->xcast_mode == FM10K_XCAST_MODE_PROMISC) fm10k_clear_unused_vlans(interface); - /* update xcast mode */ - hw->mac.ops.update_xcast_mode(hw, interface->glort, xcast_mode); + /* update xcast mode if host's mailbox is ready */ + if (fm10k_host_mbx_ready(interface)) + hw->mac.ops.update_xcast_mode(hw, interface->glort, + xcast_mode); /* record updated xcast mode state */ interface->xcast_mode = xcast_mode; @@ -1054,8 +1088,10 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) fm10k_mbx_lock(interface); - /* Enable logical port */ - hw->mac.ops.update_lport_state(hw, glort, interface->glort_count, true); + /* Enable logical port if host's mailbox is ready */ + if (fm10k_host_mbx_ready(interface)) + hw->mac.ops.update_lport_state(hw, glort, + interface->glort_count, true); /* update VLAN table */ hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, 0, @@ -1069,12 +1105,18 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { hw->mac.ops.update_vlan(hw, vid, 0, true); - hw->mac.ops.update_uc_addr(hw, glort, hw->mac.addr, - vid, true, 0); + + /* Update unicast entries if host's mailbox is ready */ + if (fm10k_host_mbx_ready(interface)) + hw->mac.ops.update_uc_addr(hw, glort, hw->mac.addr, + vid, true, 0); } - /* update xcast mode before synchronizing addresses */ - hw->mac.ops.update_xcast_mode(hw, glort, xcast_mode); + /* update xcast mode before synchronizing addresses if host's mailbox + * is ready + */ + if (fm10k_host_mbx_ready(interface)) + hw->mac.ops.update_xcast_mode(hw, glort, xcast_mode); /* synchronize all of the addresses */ __dev_uc_sync(netdev, fm10k_uc_sync, fm10k_uc_unsync); @@ -1096,9 +1138,12 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface) fm10k_mbx_lock(interface); - /* clear the logical port state on lower device */ - hw->mac.ops.update_lport_state(hw, interface->glort, - interface->glort_count, false); + /* clear the logical port state on lower device if host's mailbox is + * ready + */ + if (fm10k_host_mbx_ready(interface)) + hw->mac.ops.update_lport_state(hw, interface->glort, + interface->glort_count, false); fm10k_mbx_unlock(interface); @@ -1115,8 +1160,8 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface) * @netdev: network interface device structure * @stats: storage space for 64bit statistics * - * Returns 64bit statistics, for use in the ndo_get_stats64 callback. This - * function replaces fm10k_get_stats for kernels which support it. + * Obtain 64bit statistics in a way that is safe for both 32bit and 64bit + * architectures. */ static void fm10k_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) @@ -1207,7 +1252,7 @@ int fm10k_setup_tc(struct net_device *dev, u8 tc) goto err_open; /* flag to indicate SWPRI has yet to be updated */ - interface->flags |= FM10K_FLAG_SWPRI_CONFIG; + set_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags); return 0; err_open: @@ -1319,8 +1364,13 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, fm10k_mbx_lock(interface); glort = l2_accel->dglort + 1 + i; - hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_MULTI); - hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, 0, true, 0); + + if (fm10k_host_mbx_ready(interface)) { + hw->mac.ops.update_xcast_mode(hw, glort, + FM10K_XCAST_MODE_MULTI); + hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, + 0, true, 0); + } fm10k_mbx_unlock(interface); @@ -1354,8 +1404,13 @@ static void fm10k_dfwd_del_station(struct net_device *dev, void *priv) fm10k_mbx_lock(interface); glort = l2_accel->dglort + 1 + i; - hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_NONE); - hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, 0, false, 0); + + if (fm10k_host_mbx_ready(interface)) { + hw->mac.ops.update_xcast_mode(hw, glort, + FM10K_XCAST_MODE_NONE); + hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, + 0, false, 0); + } fm10k_mbx_unlock(interface); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 60d9b6aaf63a..3e26d27ad213 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * 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, @@ -93,18 +93,29 @@ static int fm10k_hw_ready(struct fm10k_intfc *interface) void fm10k_service_event_schedule(struct fm10k_intfc *interface) { - if (!test_bit(__FM10K_SERVICE_DISABLE, &interface->state) && - !test_and_set_bit(__FM10K_SERVICE_SCHED, &interface->state)) + if (!test_bit(__FM10K_SERVICE_DISABLE, interface->state) && + !test_and_set_bit(__FM10K_SERVICE_SCHED, interface->state)) { + clear_bit(__FM10K_SERVICE_REQUEST, interface->state); queue_work(fm10k_workqueue, &interface->service_task); + } else { + set_bit(__FM10K_SERVICE_REQUEST, interface->state); + } } static void fm10k_service_event_complete(struct fm10k_intfc *interface) { - WARN_ON(!test_bit(__FM10K_SERVICE_SCHED, &interface->state)); + WARN_ON(!test_bit(__FM10K_SERVICE_SCHED, interface->state)); /* flush memory to make sure state is correct before next watchog */ smp_mb__before_atomic(); - clear_bit(__FM10K_SERVICE_SCHED, &interface->state); + clear_bit(__FM10K_SERVICE_SCHED, interface->state); + + /* If a service event was requested since we started, immediately + * re-schedule now. This ensures we don't drop a request until the + * next timer event. + */ + if (test_bit(__FM10K_SERVICE_REQUEST, interface->state)) + fm10k_service_event_schedule(interface); } /** @@ -137,7 +148,7 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface) if (~value) { interface->hw.hw_addr = interface->uc_addr; netif_device_attach(netdev); - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); netdev_warn(netdev, "PCIe link restored, device now attached\n"); return; } @@ -159,7 +170,7 @@ static void fm10k_prepare_for_reset(struct fm10k_intfc *interface) /* put off any impending NetWatchDogTimeout */ netif_trans_update(netdev); - while (test_and_set_bit(__FM10K_RESETTING, &interface->state)) + while (test_and_set_bit(__FM10K_RESETTING, interface->state)) usleep_range(1000, 2000); rtnl_lock(); @@ -242,7 +253,7 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface) rtnl_unlock(); - clear_bit(__FM10K_RESETTING, &interface->state); + clear_bit(__FM10K_RESETTING, interface->state); return err; err_open: @@ -254,7 +265,7 @@ reinit_err: rtnl_unlock(); - clear_bit(__FM10K_RESETTING, &interface->state); + clear_bit(__FM10K_RESETTING, interface->state); return err; } @@ -273,11 +284,10 @@ static void fm10k_reinit(struct fm10k_intfc *interface) static void fm10k_reset_subtask(struct fm10k_intfc *interface) { - if (!(interface->flags & FM10K_FLAG_RESET_REQUESTED)) + if (!test_and_clear_bit(FM10K_FLAG_RESET_REQUESTED, + interface->flags)) return; - interface->flags &= ~FM10K_FLAG_RESET_REQUESTED; - netdev_err(interface->netdev, "Reset interface\n"); fm10k_reinit(interface); @@ -296,7 +306,7 @@ static void fm10k_configure_swpri_map(struct fm10k_intfc *interface) int i; /* clear flag indicating update is needed */ - interface->flags &= ~FM10K_FLAG_SWPRI_CONFIG; + clear_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags); /* these registers are only available on the PF */ if (hw->mac.type != fm10k_mac_pf) @@ -317,14 +327,14 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface) struct fm10k_hw *hw = &interface->hw; s32 err; - if (test_bit(__FM10K_LINK_DOWN, &interface->state)) { + if (test_bit(__FM10K_LINK_DOWN, interface->state)) { interface->host_ready = false; if (time_is_after_jiffies(interface->link_down_event)) return; - clear_bit(__FM10K_LINK_DOWN, &interface->state); + clear_bit(__FM10K_LINK_DOWN, interface->state); } - if (interface->flags & FM10K_FLAG_SWPRI_CONFIG) { + if (test_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags)) { if (rtnl_trylock()) { fm10k_configure_swpri_map(interface); rtnl_unlock(); @@ -336,7 +346,7 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface) err = hw->mac.ops.get_host_state(hw, &interface->host_ready); if (err && time_is_before_jiffies(interface->last_reset)) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); /* free the lock */ fm10k_mbx_unlock(interface); @@ -412,7 +422,7 @@ void fm10k_update_stats(struct fm10k_intfc *interface) int i; /* ensure only one thread updates stats at a time */ - if (test_and_set_bit(__FM10K_UPDATING_STATS, &interface->state)) + if (test_and_set_bit(__FM10K_UPDATING_STATS, interface->state)) return; /* do not allow stats update via service task for next second */ @@ -493,7 +503,7 @@ void fm10k_update_stats(struct fm10k_intfc *interface) net_stats->rx_errors = rx_errors; net_stats->rx_dropped = interface->stats.nodesc_drop.count; - clear_bit(__FM10K_UPDATING_STATS, &interface->state); + clear_bit(__FM10K_UPDATING_STATS, interface->state); } /** @@ -523,7 +533,7 @@ static void fm10k_watchdog_flush_tx(struct fm10k_intfc *interface) * controller to flush Tx. */ if (some_tx_pending) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); } /** @@ -533,8 +543,8 @@ static void fm10k_watchdog_flush_tx(struct fm10k_intfc *interface) static void fm10k_watchdog_subtask(struct fm10k_intfc *interface) { /* if interface is down do nothing */ - if (test_bit(__FM10K_DOWN, &interface->state) || - test_bit(__FM10K_RESETTING, &interface->state)) + if (test_bit(__FM10K_DOWN, interface->state) || + test_bit(__FM10K_RESETTING, interface->state)) return; if (interface->host_ready) @@ -564,8 +574,8 @@ static void fm10k_check_hang_subtask(struct fm10k_intfc *interface) int i; /* If we're down or resetting, just bail */ - if (test_bit(__FM10K_DOWN, &interface->state) || - test_bit(__FM10K_RESETTING, &interface->state)) + if (test_bit(__FM10K_DOWN, interface->state) || + test_bit(__FM10K_RESETTING, interface->state)) return; /* rate limit tx hang checks to only once every 2 seconds */ @@ -664,7 +674,7 @@ static void fm10k_configure_tx_ring(struct fm10k_intfc *interface, FM10K_PFVTCTL_FTAG_DESC_ENABLE); /* Initialize XPS */ - if (!test_and_set_bit(__FM10K_TX_XPS_INIT_DONE, &ring->state) && + if (!test_and_set_bit(__FM10K_TX_XPS_INIT_DONE, ring->state) && ring->q_vector) netif_set_xps_queue(ring->netdev, &ring->q_vector->affinity_mask, @@ -744,6 +754,7 @@ static void fm10k_configure_rx_ring(struct fm10k_intfc *interface, /* disable queue to avoid issues while updating state */ rxqctl = fm10k_read_reg(hw, FM10K_RXQCTL(reg_idx)); rxqctl &= ~FM10K_RXQCTL_ENABLE; + fm10k_write_reg(hw, FM10K_RXQCTL(reg_idx), rxqctl); fm10k_write_flush(hw); /* possible poll here to verify ring resources have been cleaned */ @@ -864,9 +875,9 @@ static void fm10k_configure_dglort(struct fm10k_intfc *interface) FM10K_MRQC_IPV6 | FM10K_MRQC_TCP_IPV6; - if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV4_UDP) + if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, interface->flags)) mrqc |= FM10K_MRQC_UDP_IPV4; - if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV6_UDP) + if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, interface->flags)) mrqc |= FM10K_MRQC_UDP_IPV6; fm10k_write_reg(hw, FM10K_MRQC(0), mrqc); @@ -981,7 +992,7 @@ void fm10k_netpoll(struct net_device *netdev) int i; /* if interface is down do nothing */ - if (test_bit(__FM10K_DOWN, &interface->state)) + if (test_bit(__FM10K_DOWN, interface->state)) return; for (i = 0; i < interface->num_q_vectors; i++) @@ -1168,13 +1179,13 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data) } if (err == FM10K_ERR_RESET_REQUESTED) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); /* if switch toggled state we should reset GLORTs */ if (eicr & FM10K_EICR_SWITCHNOTREADY) { /* force link down for at least 4 seconds */ interface->link_down_event = jiffies + (4 * HZ); - set_bit(__FM10K_LINK_DOWN, &interface->state); + set_bit(__FM10K_LINK_DOWN, interface->state); /* reset dglort_map back to no config */ hw->mac.dglort_map = FM10K_DGLORTMAP_NONE; @@ -1247,12 +1258,12 @@ static s32 fm10k_mbx_mac_addr(struct fm10k_hw *hw, u32 **results, /* MAC was changed so we need reset */ if (is_valid_ether_addr(hw->mac.perm_addr) && !ether_addr_equal(hw->mac.perm_addr, hw->mac.addr)) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); /* VLAN override was changed, or default VLAN changed */ if ((vlan_override != hw->mac.vlan_override) || (default_vid != hw->mac.default_vid)) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); return 0; } @@ -1326,7 +1337,7 @@ static s32 fm10k_lport_map(struct fm10k_hw *hw, u32 **results, if (!err && hw->swapi.status) { /* force link down for a reasonable delay */ interface->link_down_event = jiffies + (2 * HZ); - set_bit(__FM10K_LINK_DOWN, &interface->state); + set_bit(__FM10K_LINK_DOWN, interface->state); /* reset dglort_map back to no config */ hw->mac.dglort_map = FM10K_DGLORTMAP_NONE; @@ -1357,7 +1368,7 @@ static s32 fm10k_lport_map(struct fm10k_hw *hw, u32 **results, /* we need to reset if port count was just updated */ if (dglort_map != hw->mac.dglort_map) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); return 0; } @@ -1396,7 +1407,7 @@ static s32 fm10k_update_pvid(struct fm10k_hw *hw, u32 **results, /* we need to reset if default VLAN was just updated */ if (pvid != hw->mac.default_vid) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); hw->mac.default_vid = pvid; @@ -1624,10 +1635,10 @@ void fm10k_up(struct fm10k_intfc *interface) hw->mac.ops.update_int_moderator(hw); /* enable statistics capture again */ - clear_bit(__FM10K_UPDATING_STATS, &interface->state); + clear_bit(__FM10K_UPDATING_STATS, interface->state); /* clear down bit to indicate we are ready to go */ - clear_bit(__FM10K_DOWN, &interface->state); + clear_bit(__FM10K_DOWN, interface->state); /* enable polling cleanups */ fm10k_napi_enable_all(interface); @@ -1661,7 +1672,7 @@ void fm10k_down(struct fm10k_intfc *interface) int err, i = 0, count = 0; /* signal that we are down to the interrupt handler and service task */ - if (test_and_set_bit(__FM10K_DOWN, &interface->state)) + if (test_and_set_bit(__FM10K_DOWN, interface->state)) return; /* call carrier off first to avoid false dev_watchdog timeouts */ @@ -1681,7 +1692,7 @@ void fm10k_down(struct fm10k_intfc *interface) fm10k_update_stats(interface); /* prevent updating statistics while we're down */ - while (test_and_set_bit(__FM10K_UPDATING_STATS, &interface->state)) + while (test_and_set_bit(__FM10K_UPDATING_STATS, interface->state)) usleep_range(1000, 2000); /* skip waiting for TX DMA if we lost PCIe link */ @@ -1850,8 +1861,8 @@ static int fm10k_sw_init(struct fm10k_intfc *interface, memcpy(interface->rssrk, rss_key, sizeof(rss_key)); /* Start off interface as being down */ - set_bit(__FM10K_DOWN, &interface->state); - set_bit(__FM10K_UPDATING_STATS, &interface->state); + set_bit(__FM10K_DOWN, interface->state); + set_bit(__FM10K_UPDATING_STATS, interface->state); return 0; } @@ -2028,7 +2039,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * must ensure it is disabled since we haven't yet requested the timer * or work item. */ - set_bit(__FM10K_SERVICE_DISABLE, &interface->state); + set_bit(__FM10K_SERVICE_DISABLE, interface->state); err = fm10k_mbx_request_irq(interface); if (err) @@ -2069,7 +2080,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) fm10k_iov_configure(pdev, 0); /* clear the service task disable bit to allow service task to start */ - clear_bit(__FM10K_SERVICE_DISABLE, &interface->state); + clear_bit(__FM10K_SERVICE_DISABLE, interface->state); return 0; @@ -2107,7 +2118,7 @@ static void fm10k_remove(struct pci_dev *pdev) del_timer_sync(&interface->service_timer); - set_bit(__FM10K_SERVICE_DISABLE, &interface->state); + set_bit(__FM10K_SERVICE_DISABLE, interface->state); cancel_work_sync(&interface->service_task); /* free netdev, this may bounce the interrupts due to setup_tc */ @@ -2146,7 +2157,7 @@ static void fm10k_prepare_suspend(struct fm10k_intfc *interface) * stopped. We stop the watchdog task until after we resume software * activity. */ - set_bit(__FM10K_SERVICE_DISABLE, &interface->state); + set_bit(__FM10K_SERVICE_DISABLE, interface->state); cancel_work_sync(&interface->service_task); fm10k_prepare_for_reset(interface); @@ -2172,10 +2183,10 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) /* force link to stay down for a second to prevent link flutter */ interface->link_down_event = jiffies + (HZ); - set_bit(__FM10K_LINK_DOWN, &interface->state); + set_bit(__FM10K_LINK_DOWN, interface->state); /* clear the service task disable bit to allow service task to start */ - clear_bit(__FM10K_SERVICE_DISABLE, &interface->state); + clear_bit(__FM10K_SERVICE_DISABLE, interface->state); fm10k_service_event_schedule(interface); return err; diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile index 4f454d364d0d..3da482c3d68d 100644 --- a/drivers/net/ethernet/intel/i40e/Makefile +++ b/drivers/net/ethernet/intel/i40e/Makefile @@ -28,6 +28,9 @@ # Makefile for the Intel(R) Ethernet Connection XL710 (i40e.ko) driver # +ccflags-y += -I$(src) +subdir-ccflags-y += -I$(src) + obj-$(CONFIG_I40E) += i40e.o i40e-objs := i40e_main.o \ diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 421ea57128d3..70f9458f7a01 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -145,7 +145,7 @@ enum i40e_state_t { __I40E_DOWN_REQUESTED, __I40E_FD_FLUSH_REQUESTED, __I40E_RESET_FAILED, - __I40E_PORT_TX_SUSPENDED, + __I40E_PORT_SUSPENDED, __I40E_VF_DISABLE, }; @@ -389,13 +389,9 @@ struct i40e_pf { #define I40E_FLAG_MSIX_ENABLED BIT_ULL(3) #define I40E_FLAG_RSS_ENABLED BIT_ULL(6) #define I40E_FLAG_VMDQ_ENABLED BIT_ULL(7) -#define I40E_FLAG_NEED_LINK_UPDATE BIT_ULL(9) #define I40E_FLAG_IWARP_ENABLED BIT_ULL(10) -#define I40E_FLAG_CLEAN_ADMINQ BIT_ULL(14) #define I40E_FLAG_FILTER_SYNC BIT_ULL(15) #define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT_ULL(16) -#define I40E_FLAG_PROCESS_MDD_EVENT BIT_ULL(17) -#define I40E_FLAG_PROCESS_VFLR_EVENT BIT_ULL(18) #define I40E_FLAG_SRIOV_ENABLED BIT_ULL(19) #define I40E_FLAG_DCB_ENABLED BIT_ULL(20) #define I40E_FLAG_FD_SB_ENABLED BIT_ULL(21) @@ -617,7 +613,6 @@ struct i40e_vsi { u32 tx_busy; u64 tx_linearize; u64 tx_force_wb; - u64 tx_lost_interrupt; u32 rx_buf_failed; u32 rx_page_failed; @@ -703,9 +698,6 @@ struct i40e_q_vector { u8 num_ringpairs; /* total number of ring pairs in vector */ -#define I40E_Q_VECTOR_HUNG_DETECT 0 /* Bit Index for hung detection logic */ - unsigned long hung_detected; /* Set/Reset for hung_detection logic */ - cpumask_t affinity_mask; struct irq_affinity_notify affinity_notify; @@ -771,21 +763,6 @@ static inline void i40e_vsi_setup_irqhandler(struct i40e_vsi *vsi, } /** - * i40e_rx_is_programming_status - check for programming status descriptor - * @qw: the first quad word of the program status descriptor - * - * 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) -{ - return I40E_RX_PROG_STATUS_DESC_LENGTH == - (qw >> I40E_RX_PROG_STATUS_DESC_LENGTH_SHIFT); -} - -/** * i40e_get_fd_cnt_all - get the total FD filter space available * @pf: pointer to the PF struct **/ @@ -837,7 +814,7 @@ void i40e_down(struct i40e_vsi *vsi); extern const char i40e_driver_name[]; extern const char i40e_driver_version_str[]; void i40e_do_reset_safe(struct i40e_pf *pf, u32 reset_flags); -void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags); +void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired); int i40e_config_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); int i40e_get_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); void i40e_fill_rss_lut(struct i40e_pf *pf, u8 *lut, @@ -891,6 +868,8 @@ void i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, int i40e_vsi_start_rings(struct i40e_vsi *vsi); void i40e_vsi_stop_rings(struct i40e_vsi *vsi); +void i40e_vsi_stop_rings_no_wait(struct i40e_vsi *vsi); +int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi); int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count); struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags, u16 uplink_seid, u16 downlink_seid, u8 enabled_tc); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 56fb27298936..ba04988e0598 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -850,8 +850,8 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw, */ if (i40e_asq_done(hw)) break; - usleep_range(1000, 2000); - total_delay++; + udelay(50); + total_delay += 50; } while (total_delay < hw->aq.asq_cmd_timeout); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h index d92aad38afdc..2349fbe04bd2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h @@ -151,7 +151,7 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc) /* general information */ #define I40E_AQ_LARGE_BUF 512 -#define I40E_ASQ_CMD_TIMEOUT 250 /* msecs */ +#define I40E_ASQ_CMD_TIMEOUT 250000 /* usecs */ void i40e_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 251074c677c4..5eb04114e13f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -190,6 +190,10 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_add_mirror_rule = 0x0260, i40e_aqc_opc_delete_mirror_rule = 0x0261, + /* Pipeline Personalization Profile */ + i40e_aqc_opc_write_personalization_profile = 0x0270, + i40e_aqc_opc_get_personalization_profile_list = 0x0271, + /* DCB commands */ i40e_aqc_opc_dcb_ignore_pfc = 0x0301, i40e_aqc_opc_dcb_updated = 0x0302, @@ -1431,6 +1435,36 @@ struct i40e_aqc_add_delete_mirror_rule_completion { I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule_completion); +/* Pipeline Personalization Profile */ +struct i40e_aqc_write_personalization_profile { + u8 flags; + u8 reserved[3]; + __le32 profile_track_id; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_write_personalization_profile); + +struct i40e_aqc_write_ppp_resp { + __le32 error_offset; + __le32 error_info; + __le32 addr_high; + __le32 addr_low; +}; + +struct i40e_aqc_get_applied_profiles { + u8 flags; +#define I40E_AQC_GET_PPP_GET_CONF 0x1 +#define I40E_AQC_GET_PPP_GET_RDPU_CONF 0x2 + u8 rsv[3]; + __le32 reserved; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_applied_profiles); + /* DCB 0x03xx*/ /* PFC Ignore (direct 0x0301) diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index 191028b1489b..eb2896fd52a6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -436,6 +436,12 @@ int i40e_lan_add_device(struct i40e_pf *pf) pf->hw.pf_id, pf->hw.bus.bus_id, pf->hw.bus.device, pf->hw.bus.func); + /* If a client has already been registered, we need to add an instance + * of it to our new LAN device. + */ + if (registered_client) + i40e_client_add_instance(pf); + /* Since in some cases register may have happened before a device gets * added, we can schedule a subtask to go initiate the clients if * they can be launched at probe time. @@ -459,6 +465,9 @@ int i40e_lan_del_device(struct i40e_pf *pf) struct i40e_device *ldev, *tmp; int ret = -ENODEV; + /* First, remove any client instance. */ + i40e_client_del_instance(pf); + mutex_lock(&i40e_device_mutex); list_for_each_entry_safe(ldev, tmp, &i40e_devices, list) { if (ldev->pf == pf) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index f9db95aa3a20..24f020655291 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -5042,3 +5042,215 @@ do_retry: if (status || use_register) wr32(hw, reg_addr, reg_val); } + +/** + * i40e_aq_write_ppp - Write pipeline personalization profile (ppp) + * @hw: pointer to the hw struct + * @buff: command buffer (size in bytes = buff_size) + * @buff_size: buffer size in bytes + * @track_id: package tracking id + * @error_offset: returns error offset + * @error_info: returns error information + * @cmd_details: pointer to command details structure or NULL + **/ +enum +i40e_status_code i40e_aq_write_ppp(struct i40e_hw *hw, void *buff, + u16 buff_size, u32 track_id, + u32 *error_offset, u32 *error_info, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_write_personalization_profile *cmd = + (struct i40e_aqc_write_personalization_profile *) + &desc.params.raw; + struct i40e_aqc_write_ppp_resp *resp; + i40e_status status; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_write_personalization_profile); + + desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD); + if (buff_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + + desc.datalen = cpu_to_le16(buff_size); + + cmd->profile_track_id = cpu_to_le32(track_id); + + status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details); + if (!status) { + resp = (struct i40e_aqc_write_ppp_resp *)&desc.params.raw; + if (error_offset) + *error_offset = le32_to_cpu(resp->error_offset); + if (error_info) + *error_info = le32_to_cpu(resp->error_info); + } + + return status; +} + +/** + * i40e_aq_get_ppp_list - Read pipeline personalization profile (ppp) + * @hw: pointer to the hw struct + * @buff: command buffer (size in bytes = buff_size) + * @buff_size: buffer size in bytes + * @cmd_details: pointer to command details structure or NULL + **/ +enum +i40e_status_code i40e_aq_get_ppp_list(struct i40e_hw *hw, void *buff, + u16 buff_size, u8 flags, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_get_applied_profiles *cmd = + (struct i40e_aqc_get_applied_profiles *)&desc.params.raw; + i40e_status status; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_personalization_profile_list); + + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + if (buff_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + desc.datalen = cpu_to_le16(buff_size); + + cmd->flags = flags; + + status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details); + + return status; +} + +/** + * i40e_find_segment_in_package + * @segment_type: the segment type to search for (i.e., SEGMENT_TYPE_I40E) + * @pkg_hdr: pointer to the package header to be searched + * + * This function searches a package file for a particular segment type. On + * success it returns a pointer to the segment header, otherwise it will + * return NULL. + **/ +struct i40e_generic_seg_header * +i40e_find_segment_in_package(u32 segment_type, + struct i40e_package_header *pkg_hdr) +{ + struct i40e_generic_seg_header *segment; + u32 i; + + /* Search all package segments for the requested segment type */ + for (i = 0; i < pkg_hdr->segment_count; i++) { + segment = + (struct i40e_generic_seg_header *)((u8 *)pkg_hdr + + pkg_hdr->segment_offset[i]); + + if (segment->type == segment_type) + return segment; + } + + return NULL; +} + +/** + * i40e_write_profile + * @hw: pointer to the hardware structure + * @profile: pointer to the profile segment of the package to be downloaded + * @track_id: package tracking id + * + * Handles the download of a complete package. + */ +enum i40e_status_code +i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, + u32 track_id) +{ + i40e_status status = 0; + struct i40e_section_table *sec_tbl; + struct i40e_profile_section_header *sec = NULL; + u32 dev_cnt; + u32 vendor_dev_id; + u32 *nvm; + u32 section_size = 0; + u32 offset = 0, info = 0; + u32 i; + + if (!track_id) { + i40e_debug(hw, I40E_DEBUG_PACKAGE, "Track_id can't be 0."); + return I40E_NOT_SUPPORTED; + } + + dev_cnt = profile->device_table_count; + + for (i = 0; i < dev_cnt; i++) { + vendor_dev_id = profile->device_table[i].vendor_dev_id; + if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL) + if (hw->device_id == (vendor_dev_id & 0xFFFF)) + break; + } + if (i == dev_cnt) { + i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support PPP"); + return I40E_ERR_DEVICE_NOT_SUPPORTED; + } + + nvm = (u32 *)&profile->device_table[dev_cnt]; + sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1]; + + for (i = 0; i < sec_tbl->section_count; i++) { + sec = (struct i40e_profile_section_header *)((u8 *)profile + + sec_tbl->section_offset[i]); + + /* Skip 'AQ', 'note' and 'name' sections */ + if (sec->section.type != SECTION_TYPE_MMIO) + continue; + + section_size = sec->section.size + + sizeof(struct i40e_profile_section_header); + + /* Write profile */ + status = i40e_aq_write_ppp(hw, (void *)sec, (u16)section_size, + track_id, &offset, &info, NULL); + if (status) { + i40e_debug(hw, I40E_DEBUG_PACKAGE, + "Failed to write profile: offset %d, info %d", + offset, info); + break; + } + } + return status; +} + +/** + * i40e_add_pinfo_to_list + * @hw: pointer to the hardware structure + * @profile: pointer to the profile segment of the package + * @profile_info_sec: buffer for information section + * @track_id: package tracking id + * + * Register a profile to the list of loaded profiles. + */ +enum i40e_status_code +i40e_add_pinfo_to_list(struct i40e_hw *hw, + struct i40e_profile_segment *profile, + u8 *profile_info_sec, u32 track_id) +{ + i40e_status status = 0; + struct i40e_profile_section_header *sec = NULL; + struct i40e_profile_info *pinfo; + u32 offset = 0, info = 0; + + sec = (struct i40e_profile_section_header *)profile_info_sec; + sec->tbl_size = 1; + sec->data_end = sizeof(struct i40e_profile_section_header) + + sizeof(struct i40e_profile_info); + sec->section.type = SECTION_TYPE_INFO; + sec->section.offset = sizeof(struct i40e_profile_section_header); + sec->section.size = sizeof(struct i40e_profile_info); + pinfo = (struct i40e_profile_info *)(profile_info_sec + + sec->section.offset); + pinfo->track_id = track_id; + pinfo->version = profile->version; + pinfo->op = I40E_PPP_ADD_TRACKID; + memcpy(pinfo->name, profile->name, I40E_PPP_NAME_SIZE); + + status = i40e_aq_write_ppp(hw, (void *)sec, sec->data_end, + track_id, &offset, &info, NULL); + return status; +} diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index c5f68cc1edcd..a3d7ec62b76c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -384,6 +384,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) " base_queue = %d, num_queue_pairs = %d, num_desc = %d\n", vsi->base_queue, vsi->num_queue_pairs, vsi->num_desc); dev_info(&pf->pdev->dev, " type = %i\n", vsi->type); + if (vsi->type == I40E_VSI_SRIOV) + dev_info(&pf->pdev->dev, " VF ID = %i\n", vsi->vf_id); dev_info(&pf->pdev->dev, " info: valid_sections = 0x%04x, switch_id = 0x%04x\n", vsi->info.valid_sections, vsi->info.switch_id); @@ -694,6 +696,47 @@ static void i40e_dbg_dump_veb_all(struct i40e_pf *pf) } } +/** + * i40e_dbg_dump_vf - dump VF info + * @pf: the i40e_pf created in command write + * @vf_id: the vf_id from the user + **/ +static void i40e_dbg_dump_vf(struct i40e_pf *pf, int vf_id) +{ + struct i40e_vf *vf; + struct i40e_vsi *vsi; + + if (!pf->num_alloc_vfs) { + dev_info(&pf->pdev->dev, "no VFs allocated\n"); + } else if ((vf_id >= 0) && (vf_id < pf->num_alloc_vfs)) { + vf = &pf->vf[vf_id]; + vsi = pf->vsi[vf->lan_vsi_idx]; + dev_info(&pf->pdev->dev, "vf %2d: VSI id=%d, seid=%d, qps=%d\n", + vf_id, vf->lan_vsi_id, vsi->seid, vf->num_queue_pairs); + dev_info(&pf->pdev->dev, " num MDD=%lld, invalid msg=%lld, valid msg=%lld\n", + vf->num_mdd_events, + vf->num_invalid_msgs, + vf->num_valid_msgs); + } else { + dev_info(&pf->pdev->dev, "invalid VF id %d\n", vf_id); + } +} + +/** + * i40e_dbg_dump_vf_all - dump VF info for all VFs + * @pf: the i40e_pf created in command write + **/ +static void i40e_dbg_dump_vf_all(struct i40e_pf *pf) +{ + int i; + + if (!pf->num_alloc_vfs) + dev_info(&pf->pdev->dev, "no VFs enabled!\n"); + else + for (i = 0; i < pf->num_alloc_vfs; i++) + i40e_dbg_dump_vf(pf, i); +} + #define I40E_MAX_DEBUG_OUT_BUFFER (4096*4) /** * i40e_dbg_command_write - write into command datum @@ -712,6 +755,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, struct i40e_vsi *vsi; int vsi_seid; int veb_seid; + int vf_id; int cnt; /* don't allow partial writes */ @@ -914,6 +958,12 @@ static ssize_t i40e_dbg_command_write(struct file *filp, i40e_dbg_dump_veb_seid(pf, vsi_seid); else i40e_dbg_dump_veb_all(pf); + } else if (strncmp(&cmd_buf[5], "vf", 2) == 0) { + cnt = sscanf(&cmd_buf[7], "%i", &vf_id); + if (cnt > 0) + i40e_dbg_dump_vf(pf, vf_id); + else + i40e_dbg_dump_vf_all(pf); } else if (strncmp(&cmd_buf[5], "desc", 4) == 0) { int ring_id, desc_n; if (strncmp(&cmd_buf[10], "rx", 2) == 0) { @@ -1109,6 +1159,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, dev_info(&pf->pdev->dev, "dump vsi [seid]\n"); dev_info(&pf->pdev->dev, "dump reset stats\n"); dev_info(&pf->pdev->dev, "dump port\n"); + dev_info(&pf->pdev->dev, "dump vf [vf_id]\n"); dev_info(&pf->pdev->dev, "dump debug fwdata <cluster_id> <table_id> <index>\n"); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index c0c1a0cdaa5b..08035c4389cd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -89,7 +89,6 @@ static const struct i40e_stats i40e_gstrings_misc_stats[] = { I40E_VSI_STAT("rx_unknown_protocol", eth_stats.rx_unknown_protocol), I40E_VSI_STAT("tx_linearize", tx_linearize), I40E_VSI_STAT("tx_force_wb", tx_force_wb), - I40E_VSI_STAT("tx_lost_interrupt", tx_lost_interrupt), I40E_VSI_STAT("rx_alloc_fail", rx_buf_failed), I40E_VSI_STAT("rx_pg_alloc_fail", rx_page_failed), }; @@ -699,6 +698,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings copy_cmd; i40e_status status = 0; bool change = false; + int timeout = 50; int err = 0; u32 autoneg; u32 advertise; @@ -757,14 +757,20 @@ static int i40e_set_link_ksettings(struct net_device *netdev, if (memcmp(©_cmd, &safe_cmd, sizeof(struct ethtool_link_ksettings))) return -EOPNOTSUPP; - while (test_bit(__I40E_CONFIG_BUSY, &vsi->state)) + while (test_and_set_bit(__I40E_CONFIG_BUSY, &pf->state)) { + timeout--; + if (!timeout) + return -EBUSY; usleep_range(1000, 2000); + } /* Get the current phy config */ status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities, NULL); - if (status) - return -EAGAIN; + if (status) { + err = -EAGAIN; + goto done; + } /* Copy abilities to config in case autoneg is not * set below @@ -780,7 +786,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev, if (!ethtool_link_ksettings_test_link_mode( &safe_cmd, supported, Autoneg)) { netdev_info(netdev, "Autoneg not supported on this phy\n"); - return -EINVAL; + err = -EINVAL; + goto done; } /* Autoneg is allowed to change */ config.abilities = abilities.abilities | @@ -798,7 +805,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev, hw->phy.link_info.phy_type != I40E_PHY_TYPE_10GBASE_T) { netdev_info(netdev, "Autoneg cannot be disabled on this phy\n"); - return -EINVAL; + err = -EINVAL; + goto done; } /* Autoneg is allowed to change */ config.abilities = abilities.abilities & @@ -809,8 +817,10 @@ static int i40e_set_link_ksettings(struct net_device *netdev, ethtool_convert_link_mode_to_legacy_u32(&tmp, safe_cmd.link_modes.supported); - if (advertise & ~tmp) - return -EINVAL; + if (advertise & ~tmp) { + err = -EINVAL; + goto done; + } if (advertise & ADVERTISED_100baseT_Full) config.link_speed |= I40E_LINK_SPEED_100MB; @@ -866,7 +876,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev, netdev_info(netdev, "Set phy config failed, err %s aq_err %s\n", i40e_stat_str(hw, status), i40e_aq_str(hw, hw->aq.asq_last_status)); - return -EAGAIN; + err = -EAGAIN; + goto done; } status = i40e_update_link_info(hw); @@ -879,6 +890,9 @@ static int i40e_set_link_ksettings(struct net_device *netdev, netdev_info(netdev, "Nothing changed, exiting without setting anything.\n"); } +done: + clear_bit(__I40E_CONFIG_BUSY, &pf->state); + return err; } @@ -1293,6 +1307,7 @@ static int i40e_set_ringparam(struct net_device *netdev, struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; u32 new_rx_count, new_tx_count; + int timeout = 50; int i, err = 0; if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) @@ -1317,8 +1332,12 @@ static int i40e_set_ringparam(struct net_device *netdev, (new_rx_count == vsi->rx_rings[0]->count)) return 0; - while (test_and_set_bit(__I40E_CONFIG_BUSY, &pf->state)) + while (test_and_set_bit(__I40E_CONFIG_BUSY, &pf->state)) { + timeout--; + if (!timeout) + return -EBUSY; usleep_range(1000, 2000); + } if (!netif_running(vsi->netdev)) { /* simple case - set for the next time the netdev is started */ @@ -1852,7 +1871,7 @@ static void i40e_diag_test(struct net_device *netdev, * link then the following link test would have * to be moved to before the reset */ - i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true); if (i40e_link_test(netdev, &data[I40E_ETH_TEST_LINK])) eth_test->flags |= ETH_TEST_FL_FAILED; @@ -1868,7 +1887,7 @@ static void i40e_diag_test(struct net_device *netdev, eth_test->flags |= ETH_TEST_FL_FAILED; clear_bit(__I40E_TESTING, &pf->state); - i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true); if (if_running) i40e_open(netdev); @@ -4099,7 +4118,7 @@ flags_complete: */ if ((changed_flags & I40E_FLAG_VEB_STATS_ENABLED) || ((changed_flags & I40E_FLAG_LEGACY_RX) && netif_running(dev))) - i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true); return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index a0506e28d167..c001562f19b2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -32,6 +32,12 @@ #include "i40e.h" #include "i40e_diag.h" #include <net/udp_tunnel.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 + */ +#define CREATE_TRACE_POINTS +#include "i40e_trace.h" const char i40e_driver_name[] = "i40e"; static const char i40e_driver_string[] = @@ -50,13 +56,16 @@ static const char i40e_copyright[] = "Copyright (c) 2013 - 2014 Intel Corporatio /* a bit of forward declarations */ static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi); -static void i40e_handle_reset_warning(struct i40e_pf *pf); +static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired); static int i40e_add_vsi(struct i40e_vsi *vsi); static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi); static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit); static int i40e_setup_misc_vector(struct i40e_pf *pf); static void i40e_determine_queue_usage(struct i40e_pf *pf); static int i40e_setup_pf_filter_control(struct i40e_pf *pf); +static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired); +static int i40e_reset(struct i40e_pf *pf); +static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired); static void i40e_fdir_sb_setup(struct i40e_pf *pf); static int i40e_veb_get_bw_info(struct i40e_veb *veb); @@ -734,7 +743,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) struct i40e_eth_stats *oes; struct i40e_eth_stats *es; /* device's eth stats */ u32 tx_restart, tx_busy; - u64 tx_lost_interrupt; struct i40e_ring *p; u32 rx_page, rx_buf; u64 bytes, packets; @@ -760,7 +768,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) rx_b = rx_p = 0; tx_b = tx_p = 0; tx_restart = tx_busy = tx_linearize = tx_force_wb = 0; - tx_lost_interrupt = 0; rx_page = 0; rx_buf = 0; rcu_read_lock(); @@ -779,7 +786,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) tx_busy += p->tx_stats.tx_busy; tx_linearize += p->tx_stats.tx_linearize; tx_force_wb += p->tx_stats.tx_force_wb; - tx_lost_interrupt += p->tx_stats.tx_lost_interrupt; /* Rx queue is part of the same block as Tx queue */ p = &p[1]; @@ -798,7 +804,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) vsi->tx_busy = tx_busy; vsi->tx_linearize = tx_linearize; vsi->tx_force_wb = tx_force_wb; - vsi->tx_lost_interrupt = tx_lost_interrupt; vsi->rx_page_failed = rx_page; vsi->rx_buf_failed = rx_buf; @@ -3039,6 +3044,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) return -ENOMEM; } + /* configure Rx buffer alignment */ + if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) + clear_ring_build_skb_enabled(ring); + else + set_ring_build_skb_enabled(ring); + /* cache tail for quicker writes, and clear the reg before use */ ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q); writel(0, ring->tail); @@ -3080,13 +3091,15 @@ static int i40e_vsi_configure_rx(struct i40e_vsi *vsi) vsi->max_frame = I40E_MAX_RXBUFFER; vsi->rx_buf_len = I40E_RXBUFFER_2048; #if (PAGE_SIZE < 8192) - } else if (vsi->netdev->mtu <= ETH_DATA_LEN) { + } else if (!I40E_2K_TOO_SMALL_WITH_PADDING && + (vsi->netdev->mtu <= ETH_DATA_LEN)) { vsi->max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN; vsi->rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN; #endif } else { vsi->max_frame = I40E_MAX_RXBUFFER; - vsi->rx_buf_len = I40E_RXBUFFER_2048; + vsi->rx_buf_len = (PAGE_SIZE < 8192) ? I40E_RXBUFFER_3072 : + I40E_RXBUFFER_2048; } /* set up individual rings */ @@ -3906,6 +3919,8 @@ static void i40e_netpoll(struct net_device *netdev) } #endif +#define I40E_QTX_ENA_WAIT_COUNT 50 + /** * i40e_pf_txq_wait - Wait for a PF's Tx queue to be enabled or disabled * @pf: the PF being configured @@ -3936,6 +3951,50 @@ static int i40e_pf_txq_wait(struct i40e_pf *pf, int pf_q, bool enable) } /** + * i40e_control_tx_q - Start or stop a particular Tx queue + * @pf: the PF structure + * @pf_q: the PF queue to configure + * @enable: start or stop the queue + * + * This function enables or disables a single queue. Note that any delay + * required after the operation is expected to be handled by the caller of + * this function. + **/ +static void i40e_control_tx_q(struct i40e_pf *pf, int pf_q, bool enable) +{ + struct i40e_hw *hw = &pf->hw; + u32 tx_reg; + int i; + + /* warn the TX unit of coming changes */ + i40e_pre_tx_queue_cfg(&pf->hw, pf_q, enable); + if (!enable) + usleep_range(10, 20); + + for (i = 0; i < I40E_QTX_ENA_WAIT_COUNT; i++) { + tx_reg = rd32(hw, I40E_QTX_ENA(pf_q)); + if (((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT) & 1) == + ((tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT) & 1)) + break; + usleep_range(1000, 2000); + } + + /* Skip if the queue is already in the requested state */ + if (enable == !!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK)) + return; + + /* turn on/off the queue */ + if (enable) { + wr32(hw, I40E_QTX_HEAD(pf_q), 0); + tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK; + } else { + tx_reg &= ~I40E_QTX_ENA_QENA_REQ_MASK; + } + + wr32(hw, I40E_QTX_ENA(pf_q), tx_reg); +} + +/** * i40e_vsi_control_tx - Start or stop a VSI's rings * @vsi: the VSI being configured * @enable: start or stop the rings @@ -3943,41 +4002,11 @@ static int i40e_pf_txq_wait(struct i40e_pf *pf, int pf_q, bool enable) static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) { struct i40e_pf *pf = vsi->back; - struct i40e_hw *hw = &pf->hw; - int i, j, pf_q, ret = 0; - u32 tx_reg; + int i, pf_q, ret = 0; pf_q = vsi->base_queue; for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - - /* warn the TX unit of coming changes */ - i40e_pre_tx_queue_cfg(&pf->hw, pf_q, enable); - if (!enable) - usleep_range(10, 20); - - for (j = 0; j < 50; j++) { - tx_reg = rd32(hw, I40E_QTX_ENA(pf_q)); - if (((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT) & 1) == - ((tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT) & 1)) - break; - usleep_range(1000, 2000); - } - /* Skip if the queue is already in the requested state */ - if (enable == !!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK)) - continue; - - /* turn on/off the queue */ - if (enable) { - wr32(hw, I40E_QTX_HEAD(pf_q), 0); - tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK; - } else { - tx_reg &= ~I40E_QTX_ENA_QENA_REQ_MASK; - } - - wr32(hw, I40E_QTX_ENA(pf_q), tx_reg); - /* No waiting for the Tx queue to disable */ - if (!enable && test_bit(__I40E_PORT_TX_SUSPENDED, &pf->state)) - continue; + i40e_control_tx_q(pf, pf_q, enable); /* wait for the change to finish */ ret = i40e_pf_txq_wait(pf, pf_q, enable); @@ -4022,6 +4051,43 @@ static int i40e_pf_rxq_wait(struct i40e_pf *pf, int pf_q, bool enable) } /** + * i40e_control_rx_q - Start or stop a particular Rx queue + * @pf: the PF structure + * @pf_q: the PF queue to configure + * @enable: start or stop the queue + * + * This function enables or disables a single queue. Note that any delay + * required after the operation is expected to be handled by the caller of + * this function. + **/ +static void i40e_control_rx_q(struct i40e_pf *pf, int pf_q, bool enable) +{ + struct i40e_hw *hw = &pf->hw; + u32 rx_reg; + int i; + + for (i = 0; i < I40E_QTX_ENA_WAIT_COUNT; i++) { + rx_reg = rd32(hw, I40E_QRX_ENA(pf_q)); + if (((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT) & 1) == + ((rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT) & 1)) + break; + usleep_range(1000, 2000); + } + + /* Skip if the queue is already in the requested state */ + if (enable == !!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK)) + return; + + /* turn on/off the queue */ + if (enable) + rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK; + else + rx_reg &= ~I40E_QRX_ENA_QENA_REQ_MASK; + + wr32(hw, I40E_QRX_ENA(pf_q), rx_reg); +} + +/** * i40e_vsi_control_rx - Start or stop a VSI's rings * @vsi: the VSI being configured * @enable: start or stop the rings @@ -4029,33 +4095,11 @@ static int i40e_pf_rxq_wait(struct i40e_pf *pf, int pf_q, bool enable) static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable) { struct i40e_pf *pf = vsi->back; - struct i40e_hw *hw = &pf->hw; - int i, j, pf_q, ret = 0; - u32 rx_reg; + int i, pf_q, ret = 0; pf_q = vsi->base_queue; for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - for (j = 0; j < 50; j++) { - rx_reg = rd32(hw, I40E_QRX_ENA(pf_q)); - if (((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT) & 1) == - ((rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT) & 1)) - break; - usleep_range(1000, 2000); - } - - /* Skip if the queue is already in the requested state */ - if (enable == !!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK)) - continue; - - /* turn on/off the queue */ - if (enable) - rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK; - else - rx_reg &= ~I40E_QRX_ENA_QENA_REQ_MASK; - wr32(hw, I40E_QRX_ENA(pf_q), rx_reg); - /* No waiting for the Tx queue to disable */ - if (!enable && test_bit(__I40E_PORT_TX_SUSPENDED, &pf->state)) - continue; + i40e_control_rx_q(pf, pf_q, enable); /* wait for the change to finish */ ret = i40e_pf_rxq_wait(pf, pf_q, enable); @@ -4099,6 +4143,10 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi) **/ void i40e_vsi_stop_rings(struct i40e_vsi *vsi) { + /* When port TX is suspended, don't wait */ + if (test_bit(__I40E_PORT_SUSPENDED, &vsi->back->state)) + return i40e_vsi_stop_rings_no_wait(vsi); + /* do rx first for enable and last for disable * Ignore return value, we need to shutdown whatever we can */ @@ -4107,6 +4155,29 @@ void i40e_vsi_stop_rings(struct i40e_vsi *vsi) } /** + * i40e_vsi_stop_rings_no_wait - Stop a VSI's rings and do not delay + * @vsi: the VSI being shutdown + * + * This function stops all the rings for a VSI but does not delay to verify + * that rings have been disabled. It is expected that the caller is shutting + * down multiple VSIs at once and will delay together for all the VSIs after + * initiating the shutdown. This is particularly useful for shutting down lots + * of VFs together. Otherwise, a large delay can be incurred while configuring + * each VSI in serial. + **/ +void i40e_vsi_stop_rings_no_wait(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + int i, pf_q; + + pf_q = vsi->base_queue; + for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { + i40e_control_tx_q(pf, pf_q, false); + i40e_control_rx_q(pf, pf_q, false); + } +} + +/** * i40e_vsi_free_irq - Free the irq association with the OS * @vsi: the VSI being configured **/ @@ -4331,8 +4402,12 @@ static void i40e_napi_enable_all(struct i40e_vsi *vsi) if (!vsi->netdev) return; - for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) - napi_enable(&vsi->q_vectors[q_idx]->napi); + for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) { + struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx]; + + if (q_vector->rx.ring || q_vector->tx.ring) + napi_enable(&q_vector->napi); + } } /** @@ -4346,8 +4421,12 @@ static void i40e_napi_disable_all(struct i40e_vsi *vsi) if (!vsi->netdev) return; - for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) - napi_disable(&vsi->q_vectors[q_idx]->napi); + for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) { + struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx]; + + if (q_vector->rx.ring || q_vector->tx.ring) + napi_disable(&q_vector->napi); + } } /** @@ -4428,21 +4507,20 @@ static void i40e_pf_unquiesce_all_vsi(struct i40e_pf *pf) } } -#ifdef CONFIG_I40E_DCB /** * i40e_vsi_wait_queues_disabled - Wait for VSI's queues to be disabled * @vsi: the VSI being configured * - * This function waits for the given VSI's queues to be disabled. + * Wait until all queues on a given VSI have been disabled. **/ -static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi) +int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; int i, pf_q, ret; pf_q = vsi->base_queue; for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - /* Check and wait for the disable status of the queue */ + /* Check and wait for the Tx queue */ ret = i40e_pf_txq_wait(pf, pf_q, false); if (ret) { dev_info(&pf->pdev->dev, @@ -4450,11 +4528,7 @@ static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi) vsi->seid, pf_q); return ret; } - } - - pf_q = vsi->base_queue; - for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - /* Check and wait for the disable status of the queue */ + /* Check and wait for the Tx queue */ ret = i40e_pf_rxq_wait(pf, pf_q, false); if (ret) { dev_info(&pf->pdev->dev, @@ -4467,6 +4541,7 @@ static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi) return 0; } +#ifdef CONFIG_I40E_DCB /** * i40e_pf_wait_queues_disabled - Wait for all queues of PF VSIs to be disabled * @pf: the PF @@ -4497,16 +4572,15 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf) * @vsi: Pointer to VSI struct * * This function checks specified queue for given VSI. Detects hung condition. - * Sets hung bit since it is two step process. Before next run of service task - * if napi_poll runs, it reset 'hung' bit for respective q_vector. If not, - * hung condition remain unchanged and during subsequent run, this function - * issues SW interrupt to recover from hung condition. + * We proactively detect hung TX queues by checking if interrupts are disabled + * but there are pending descriptors. If it appears hung, attempt to recover + * by triggering a SW interrupt. **/ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi) { struct i40e_ring *tx_ring = NULL; struct i40e_pf *pf; - u32 head, val, tx_pending_hw; + u32 val, tx_pending; int i; pf = vsi->back; @@ -4532,47 +4606,15 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi) else val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0); - head = i40e_get_head(tx_ring); - - tx_pending_hw = i40e_get_tx_pending(tx_ring, false); - - /* HW is done executing descriptors, updated HEAD write back, - * but SW hasn't processed those descriptors. If interrupt is - * not generated from this point ON, it could result into - * dev_watchdog detecting timeout on those netdev_queue, - * hence proactively trigger SW interrupt. - */ - if (tx_pending_hw && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) { - /* NAPI Poll didn't run and clear since it was set */ - if (test_and_clear_bit(I40E_Q_VECTOR_HUNG_DETECT, - &tx_ring->q_vector->hung_detected)) { - netdev_info(vsi->netdev, "VSI_seid %d, Hung TX queue %d, tx_pending_hw: %d, NTC:0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x\n", - vsi->seid, q_idx, tx_pending_hw, - tx_ring->next_to_clean, head, - tx_ring->next_to_use, - readl(tx_ring->tail)); - netdev_info(vsi->netdev, "VSI_seid %d, Issuing force_wb for TX queue %d, Interrupt Reg: 0x%x\n", - vsi->seid, q_idx, val); - i40e_force_wb(vsi, tx_ring->q_vector); - } else { - /* First Chance - detected possible hung */ - set_bit(I40E_Q_VECTOR_HUNG_DETECT, - &tx_ring->q_vector->hung_detected); - } - } + tx_pending = i40e_get_tx_pending(tx_ring); - /* This is the case where we have interrupts missing, - * so the tx_pending in HW will most likely be 0, but we - * will have tx_pending in SW since the WB happened but the - * interrupt got lost. + /* Interrupts are disabled and TX pending is non-zero, + * trigger the SW interrupt (don't wait). Worst case + * there will be one extra interrupt which may result + * into not cleaning any queues because queues are cleaned. */ - if ((!tx_pending_hw) && i40e_get_tx_pending(tx_ring, true) && - (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) { - local_bh_disable(); - if (napi_reschedule(&tx_ring->q_vector->napi)) - tx_ring->tx_stats.tx_lost_interrupt++; - local_bh_enable(); - } + if (tx_pending && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) + i40e_force_wb(vsi, tx_ring->q_vector); } /** @@ -5529,6 +5571,8 @@ int i40e_open(struct net_device *netdev) * Finish initialization of the VSI. * * Returns 0 on success, negative value on failure + * + * Note: expects to be called while under rtnl_lock() **/ int i40e_vsi_open(struct i40e_vsi *vsi) { @@ -5592,7 +5636,7 @@ err_setup_rx: err_setup_tx: i40e_vsi_free_tx_resources(vsi); if (vsi == pf->vsi[pf->lan_vsi]) - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true); return err; } @@ -5678,12 +5722,14 @@ int i40e_close(struct net_device *netdev) * i40e_do_reset - Start a PF or Core Reset sequence * @pf: board private structure * @reset_flags: which reset is requested + * @lock_acquired: indicates whether or not the lock has been acquired + * before this function was called. * * The essential difference in resets is that the PF Reset * doesn't clear the packet buffers, doesn't reset the PE * firmware, and doesn't bother the other PFs on the chip. **/ -void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags) +void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) { u32 val; @@ -5729,7 +5775,7 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags) * for the Core Reset. */ dev_dbg(&pf->pdev->dev, "PFR requested\n"); - i40e_handle_reset_warning(pf); + i40e_handle_reset_warning(pf, lock_acquired); } else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) { int v; @@ -5898,7 +5944,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf, else pf->flags &= ~I40E_FLAG_DCB_ENABLED; - set_bit(__I40E_PORT_TX_SUSPENDED, &pf->state); + set_bit(__I40E_PORT_SUSPENDED, &pf->state); /* Reconfiguration needed quiesce all VSIs */ i40e_pf_quiesce_all_vsi(pf); @@ -5907,7 +5953,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf, ret = i40e_resume_port_tx(pf); - clear_bit(__I40E_PORT_TX_SUSPENDED, &pf->state); + clear_bit(__I40E_PORT_SUSPENDED, &pf->state); /* In case of error no point in resuming VSIs */ if (ret) goto exit; @@ -5938,7 +5984,7 @@ exit: void i40e_do_reset_safe(struct i40e_pf *pf, u32 reset_flags) { rtnl_lock(); - i40e_do_reset(pf, reset_flags); + i40e_do_reset(pf, reset_flags, true); rtnl_unlock(); } @@ -6340,7 +6386,6 @@ static void i40e_reset_subtask(struct i40e_pf *pf) { u32 reset_flags = 0; - rtnl_lock(); if (test_bit(__I40E_REINIT_REQUESTED, &pf->state)) { reset_flags |= BIT(__I40E_REINIT_REQUESTED); clear_bit(__I40E_REINIT_REQUESTED, &pf->state); @@ -6366,18 +6411,19 @@ static void i40e_reset_subtask(struct i40e_pf *pf) * precedence before starting a new reset sequence. */ if (test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state)) { - i40e_handle_reset_warning(pf); - goto unlock; + i40e_prep_for_reset(pf, false); + i40e_reset(pf); + i40e_rebuild(pf, false, false); } /* If we're already down or resetting, just bail */ if (reset_flags && !test_bit(__I40E_DOWN, &pf->state) && - !test_bit(__I40E_CONFIG_BUSY, &pf->state)) - i40e_do_reset(pf, reset_flags); - -unlock: - rtnl_unlock(); + !test_bit(__I40E_CONFIG_BUSY, &pf->state)) { + rtnl_lock(); + i40e_do_reset(pf, reset_flags, true); + rtnl_unlock(); + } } /** @@ -6865,10 +6911,12 @@ static void i40e_fdir_teardown(struct i40e_pf *pf) /** * i40e_prep_for_reset - prep for the core to reset * @pf: board private structure + * @lock_acquired: indicates whether or not the lock has been acquired + * before this function was called. * * Close up the VFs and other things in prep for PF Reset. **/ -static void i40e_prep_for_reset(struct i40e_pf *pf) +static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired) { struct i40e_hw *hw = &pf->hw; i40e_status ret = 0; @@ -6883,7 +6931,12 @@ static void i40e_prep_for_reset(struct i40e_pf *pf) dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n"); /* quiesce the VSIs and their queues that are not already DOWN */ + /* pf_quiesce_all_vsi modifies netdev structures -rtnl_lock needed */ + if (!lock_acquired) + rtnl_lock(); i40e_pf_quiesce_all_vsi(pf); + if (!lock_acquired) + rtnl_unlock(); for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v]) @@ -6918,29 +6971,39 @@ static void i40e_send_version(struct i40e_pf *pf) } /** - * i40e_reset_and_rebuild - reset and rebuild using a saved config + * i40e_reset - wait for core reset to finish reset, reset pf if corer not seen * @pf: board private structure - * @reinit: if the Main VSI needs to re-initialized. **/ -static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) +static int i40e_reset(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; - u8 set_fc_aq_fail = 0; i40e_status ret; - u32 val; - u32 v; - /* Now we wait for GRST to settle out. - * We don't have to delete the VEBs or VSIs from the hw switch - * because the reset will make them disappear. - */ ret = i40e_pf_reset(hw); if (ret) { dev_info(&pf->pdev->dev, "PF reset failed, %d\n", ret); set_bit(__I40E_RESET_FAILED, &pf->state); - goto clear_recovery; + clear_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state); + } else { + pf->pfr_count++; } - pf->pfr_count++; + return ret; +} + +/** + * i40e_rebuild - rebuild using a saved config + * @pf: board private structure + * @reinit: if the Main VSI needs to re-initialized. + * @lock_acquired: indicates whether or not the lock has been acquired + * before this function was called. + **/ +static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) +{ + struct i40e_hw *hw = &pf->hw; + u8 set_fc_aq_fail = 0; + i40e_status ret; + u32 val; + int v; if (test_bit(__I40E_DOWN, &pf->state)) goto clear_recovery; @@ -6985,9 +7048,11 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) } #endif /* CONFIG_I40E_DCB */ /* do basic switch setup */ + if (!lock_acquired) + rtnl_lock(); ret = i40e_setup_pf_switch(pf, reinit); if (ret) - goto end_core_reset; + goto end_unlock; /* The driver only wants link up/down and module qualification * reports from firmware. Note the negative logic. @@ -7058,7 +7123,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) if (ret) { dev_info(&pf->pdev->dev, "rebuild of Main VSI failed: %d\n", ret); - goto end_core_reset; + goto end_unlock; } } @@ -7101,14 +7166,21 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) /* restart the VSIs that were rebuilt and running before the reset */ i40e_pf_unquiesce_all_vsi(pf); - if (pf->num_alloc_vfs) { - for (v = 0; v < pf->num_alloc_vfs; v++) - i40e_reset_vf(&pf->vf[v], true); - } + /* Release the RTNL lock before we start resetting VFs */ + if (!lock_acquired) + rtnl_unlock(); + + i40e_reset_all_vfs(pf, true); /* tell the firmware that we're starting */ i40e_send_version(pf); + /* We've already released the lock, so don't do it again */ + goto end_core_reset; + +end_unlock: + if (!lock_acquired) + rtnl_unlock(); end_core_reset: clear_bit(__I40E_RESET_FAILED, &pf->state); clear_recovery: @@ -7116,16 +7188,38 @@ clear_recovery: } /** + * i40e_reset_and_rebuild - reset and rebuild using a saved config + * @pf: board private structure + * @reinit: if the Main VSI needs to re-initialized. + * @lock_acquired: indicates whether or not the lock has been acquired + * before this function was called. + **/ +static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit, + bool lock_acquired) +{ + int ret; + /* Now we wait for GRST to settle out. + * We don't have to delete the VEBs or VSIs from the hw switch + * because the reset will make them disappear. + */ + ret = i40e_reset(pf); + if (!ret) + i40e_rebuild(pf, reinit, lock_acquired); +} + +/** * i40e_handle_reset_warning - prep for the PF to reset, reset and rebuild * @pf: board private structure * * Close up the VFs and other things in prep for a Core Reset, * then get ready to rebuild the world. + * @lock_acquired: indicates whether or not the lock has been acquired + * before this function was called. **/ -static void i40e_handle_reset_warning(struct i40e_pf *pf) +static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired) { - i40e_prep_for_reset(pf); - i40e_reset_and_rebuild(pf, false); + i40e_prep_for_reset(pf, lock_acquired); + i40e_reset_and_rebuild(pf, false, lock_acquired); } /** @@ -8422,6 +8516,7 @@ static int i40e_pf_config_rss(struct i40e_pf *pf) * * returns 0 if rss is not enabled, if enabled returns the final rss queue * count which may be different from the requested queue count. + * Note: expects to be called while under rtnl_lock() **/ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count) { @@ -8437,11 +8532,11 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count) u16 qcount; vsi->req_queue_pairs = queue_count; - i40e_prep_for_reset(pf); + i40e_prep_for_reset(pf, true); pf->alloc_rss_size = new_rss_size; - i40e_reset_and_rebuild(pf, true); + i40e_reset_and_rebuild(pf, true, true); /* Discard the user configured hash keys and lut, if less * queues are enabled. @@ -8817,6 +8912,7 @@ static void i40e_clear_rss_lut(struct i40e_vsi *vsi) * i40e_set_features - set the netdev feature flags * @netdev: ptr to the netdev being adjusted * @features: the feature set that the stack is suggesting + * Note: expects to be called while under rtnl_lock() **/ static int i40e_set_features(struct net_device *netdev, netdev_features_t features) @@ -8840,7 +8936,7 @@ static int i40e_set_features(struct net_device *netdev, need_reset = i40e_set_ntuple(pf, features); if (need_reset) - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true); return 0; } @@ -9035,6 +9131,8 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], * is to change the mode then that requires a PF reset to * allow rebuild of the components with required hardware * bridge mode enabled. + * + * Note: expects to be called while under rtnl_lock() **/ static int i40e_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, @@ -9090,7 +9188,8 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; else pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), + true); break; } } @@ -9245,6 +9344,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) u8 broadcast[ETH_ALEN]; u8 mac_addr[ETH_ALEN]; int etherdev_size; + netdev_features_t hw_enc_features; + netdev_features_t hw_features; etherdev_size = sizeof(struct i40e_netdev_priv); netdev = alloc_etherdev_mq(etherdev_size, vsi->alloc_queue_pairs); @@ -9255,52 +9356,57 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) np = netdev_priv(netdev); np->vsi = vsi; - netdev->hw_enc_features |= NETIF_F_SG | - NETIF_F_IP_CSUM | - NETIF_F_IPV6_CSUM | - NETIF_F_HIGHDMA | - NETIF_F_SOFT_FEATURES | - NETIF_F_TSO | - NETIF_F_TSO_ECN | - NETIF_F_TSO6 | - NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM | - NETIF_F_GSO_IPXIP4 | - NETIF_F_GSO_IPXIP6 | - NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_GSO_PARTIAL | - NETIF_F_SCTP_CRC | - NETIF_F_RXHASH | - NETIF_F_RXCSUM | - 0; + hw_enc_features = NETIF_F_SG | + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_HIGHDMA | + NETIF_F_SOFT_FEATURES | + NETIF_F_TSO | + NETIF_F_TSO_ECN | + NETIF_F_TSO6 | + NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | + NETIF_F_GSO_PARTIAL | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_SCTP_CRC | + NETIF_F_RXHASH | + NETIF_F_RXCSUM | + 0; if (!(pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE)) netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; + netdev->hw_enc_features |= hw_enc_features; + /* record features VLANs can make use of */ - netdev->vlan_features |= netdev->hw_enc_features | - NETIF_F_TSO_MANGLEID; + netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID; if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) netdev->hw_features |= NETIF_F_NTUPLE; + hw_features = hw_enc_features | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX; - netdev->hw_features |= netdev->hw_enc_features | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX; + netdev->hw_features |= hw_features; - netdev->features |= netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; + netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; if (vsi->type == I40E_VSI_MAIN) { SET_NETDEV_DEV(netdev, &pf->pdev->dev); ether_addr_copy(mac_addr, hw->mac.perm_addr); - /* The following steps are necessary to properly keep track of - * MAC-VLAN filters loaded into firmware - first we remove - * filter that is automatically generated by firmware and then - * add new filter both to the driver hash table and firmware. + /* The following steps are necessary for two reasons. First, + * some older NVM configurations load a default MAC-VLAN + * filter that will accept any tagged packet, and we want to + * replace this with a normal filter. Additionally, it is + * possible our MAC address was provided by the platform using + * Open Firmware or similar. + * + * Thus, we need to remove the default filter and install one + * specific to the MAC address. */ i40e_rm_default_mac_filter(vsi, mac_addr); spin_lock_bh(&vsi->mac_filter_hash_lock); @@ -10805,20 +10911,18 @@ static void i40e_print_features(struct i40e_pf *pf) /** * i40e_get_platform_mac_addr - get platform-specific MAC address - * * @pdev: PCI device information struct * @pf: board private structure * - * Look up the MAC address in Open Firmware on systems that support it, - * and use IDPROM on SPARC if no OF address is found. On return, the - * I40E_FLAG_PF_MAC will be wset in pf->flags if a platform-specific value - * has been selected. + * Look up the MAC address for the device. First we'll try + * eth_platform_get_mac_address, which will check Open Firmware, or arch + * specific fallback. Otherwise, we'll default to the stored value in + * firmware. **/ static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf) { - pf->flags &= ~I40E_FLAG_PF_MAC; - if (!eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr)) - pf->flags |= I40E_FLAG_PF_MAC; + if (eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr)) + i40e_get_mac_addr(&pf->hw, pf->hw.mac.addr); } /** @@ -11032,9 +11136,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i40e_aq_stop_lldp(hw, true, NULL); } - i40e_get_mac_addr(hw, hw->mac.addr); /* allow a platform config to override the HW addr */ i40e_get_platform_mac_addr(pdev, pf); + if (!is_valid_ether_addr(hw->mac.addr)) { dev_info(&pdev->dev, "invalid MAC address %pM\n", hw->mac.addr); err = -EIO; @@ -11063,7 +11167,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&pf->service_task, i40e_service_task); clear_bit(__I40E_SERVICE_SCHED, &pf->state); - pf->flags |= I40E_FLAG_NEED_LINK_UPDATE; /* NVM bit on means WoL disabled for the port */ i40e_read_nvm_word(hw, I40E_SR_NVM_WAKE_ON_LAN, &wol_nvm_bits); @@ -11235,10 +11338,12 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) round_jiffies(jiffies + pf->service_timer_period)); /* add this PF to client device list and launch a client service task */ - err = i40e_lan_add_device(pf); - if (err) - dev_info(&pdev->dev, "Failed to add PF to client API service list: %d\n", - err); + if (pf->flags & I40E_FLAG_IWARP_ENABLED) { + err = i40e_lan_add_device(pf); + if (err) + dev_info(&pdev->dev, "Failed to add PF to client API service list: %d\n", + err); + } #define PCI_SPEED_SIZE 8 #define PCI_WIDTH_SIZE 8 @@ -11385,6 +11490,11 @@ static void i40e_remove(struct pci_dev *pdev) if (pf->service_task.func) cancel_work_sync(&pf->service_task); + /* Client close must be called explicitly here because the timer + * has been stopped. + */ + i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false); + if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { i40e_free_vfs(pf); pf->flags &= ~I40E_FLAG_SRIOV_ENABLED; @@ -11411,10 +11521,11 @@ static void i40e_remove(struct pci_dev *pdev) i40e_vsi_release(pf->vsi[pf->lan_vsi]); /* remove attached clients */ - ret_code = i40e_lan_del_device(pf); - if (ret_code) { - dev_warn(&pdev->dev, "Failed to delete client device: %d\n", - ret_code); + if (pf->flags & I40E_FLAG_IWARP_ENABLED) { + ret_code = i40e_lan_del_device(pf); + if (ret_code) + dev_warn(&pdev->dev, "Failed to delete client device: %d\n", + ret_code); } /* shutdown and destroy the HMC */ @@ -11483,7 +11594,7 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev, /* shutdown all operations */ if (!test_bit(__I40E_SUSPENDED, &pf->state)) { rtnl_lock(); - i40e_prep_for_reset(pf); + i40e_prep_for_reset(pf, true); rtnl_unlock(); } @@ -11552,7 +11663,7 @@ static void i40e_pci_error_resume(struct pci_dev *pdev) return; rtnl_lock(); - i40e_handle_reset_warning(pf); + i40e_handle_reset_warning(pf, true); rtnl_unlock(); } @@ -11615,7 +11726,7 @@ static void i40e_shutdown(struct pci_dev *pdev) set_bit(__I40E_SUSPENDED, &pf->state); set_bit(__I40E_DOWN, &pf->state); rtnl_lock(); - i40e_prep_for_reset(pf); + i40e_prep_for_reset(pf, true); rtnl_unlock(); wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); @@ -11625,11 +11736,16 @@ static void i40e_shutdown(struct pci_dev *pdev) cancel_work_sync(&pf->service_task); i40e_fdir_teardown(pf); + /* Client close must be called explicitly here because the timer + * has been stopped. + */ + i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false); + if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE)) i40e_enable_mc_magic_wake(pf); rtnl_lock(); - i40e_prep_for_reset(pf); + i40e_prep_for_reset(pf, true); rtnl_unlock(); wr32(hw, I40E_PFPM_APM, @@ -11663,7 +11779,7 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state) i40e_enable_mc_magic_wake(pf); rtnl_lock(); - i40e_prep_for_reset(pf); + i40e_prep_for_reset(pf, true); rtnl_unlock(); wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); @@ -11711,7 +11827,7 @@ static int i40e_resume(struct pci_dev *pdev) if (test_and_clear_bit(__I40E_SUSPENDED, &pf->state)) { clear_bit(__I40E_DOWN, &pf->state); rtnl_lock(); - i40e_reset_and_rebuild(pf, false); + i40e_reset_and_rebuild(pf, false, true); rtnl_unlock(); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index dfc5e5901be5..c56d976cf85a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -377,4 +377,21 @@ i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num); i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, u32 time, u32 interval); +i40e_status i40e_aq_write_ppp(struct i40e_hw *hw, void *buff, + u16 buff_size, u32 track_id, + u32 *error_offset, u32 *error_info, + struct i40e_asq_cmd_details *cmd_details); +i40e_status i40e_aq_get_ppp_list(struct i40e_hw *hw, void *buff, + u16 buff_size, u8 flags, + struct i40e_asq_cmd_details *cmd_details); +struct i40e_generic_seg_header * +i40e_find_segment_in_package(u32 segment_type, + struct i40e_package_header *pkg_header); +enum i40e_status_code +i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg, + u32 track_id); +enum i40e_status_code +i40e_add_pinfo_to_list(struct i40e_hw *hw, + struct i40e_profile_segment *profile, + u8 *profile_info_sec, u32 track_id); #endif /* _I40E_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h new file mode 100644 index 000000000000..d3e55f54a05e --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h @@ -0,0 +1,229 @@ +/******************************************************************************* + * + * Intel(R) 40-10 Gigabit Ethernet Connection Network 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 + * + ******************************************************************************/ + +/* Modeled on trace-events-sample.h */ + +/* The trace subsystem name for i40e will be "i40e". + * + * This file is named i40e_trace.h. + * + * Since this include file's name is different from the trace + * subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end + * of this file. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM i40e + +/* See trace-events-sample.h for a detailed description of why this + * guard clause is different from most normal include files. + */ +#if !defined(_I40E_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _I40E_TRACE_H_ + +#include <linux/tracepoint.h> + +/** + * i40e_trace() macro enables shared code to refer to trace points + * like: + * + * trace_i40e{,vf}_example(args...) + * + * ... as: + * + * i40e_trace(example, args...) + * + * ... to resolve to the PF or VF version of the tracepoint without + * ifdefs, and to allow tracepoints to be disabled entirely at build + * time. + * + * Trace point should always be referred to in the driver via this + * macro. + * + * Similarly, i40e_trace_enabled(trace_name) wraps references to + * trace_i40e{,vf}_<trace_name>_enabled() functions. + */ +#define _I40E_TRACE_NAME(trace_name) (trace_ ## i40e ## _ ## trace_name) +#define I40E_TRACE_NAME(trace_name) _I40E_TRACE_NAME(trace_name) + +#define i40e_trace(trace_name, args...) I40E_TRACE_NAME(trace_name)(args) + +#define i40e_trace_enabled(trace_name) I40E_TRACE_NAME(trace_name##_enabled)() + +/* Events common to PF and VF. Corresponding versions will be defined + * for both, named trace_i40e_* and trace_i40evf_*. The i40e_trace() + * macro above will select the right trace point name for the driver + * being built from shared code. + */ + +/* Events related to a vsi & ring */ +DECLARE_EVENT_CLASS( + i40e_tx_template, + + TP_PROTO(struct i40e_ring *ring, + struct i40e_tx_desc *desc, + struct i40e_tx_buffer *buf), + + TP_ARGS(ring, desc, buf), + + /* The convention here is to make the first fields in the + * TP_STRUCT match the TP_PROTO exactly. This enables the use + * of the args struct generated by the tplist tool (from the + * bcc-tools package) to be used for those fields. To access + * fields other than the tracepoint args will require the + * tplist output to be adjusted. + */ + TP_STRUCT__entry( + __field(void*, ring) + __field(void*, desc) + __field(void*, buf) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->ring = ring; + __entry->desc = desc; + __entry->buf = buf; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s ring: %p desc: %p buf %p", + __get_str(devname), __entry->ring, + __entry->desc, __entry->buf) +); + +DEFINE_EVENT( + i40e_tx_template, i40e_clean_tx_irq, + TP_PROTO(struct i40e_ring *ring, + struct i40e_tx_desc *desc, + struct i40e_tx_buffer *buf), + + TP_ARGS(ring, desc, buf)); + +DEFINE_EVENT( + i40e_tx_template, i40e_clean_tx_irq_unmap, + TP_PROTO(struct i40e_ring *ring, + struct i40e_tx_desc *desc, + struct i40e_tx_buffer *buf), + + TP_ARGS(ring, desc, buf)); + +DECLARE_EVENT_CLASS( + i40e_rx_template, + + TP_PROTO(struct i40e_ring *ring, + union i40e_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb), + + TP_STRUCT__entry( + __field(void*, ring) + __field(void*, desc) + __field(void*, skb) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->ring = ring; + __entry->desc = desc; + __entry->skb = skb; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s ring: %p desc: %p skb %p", + __get_str(devname), __entry->ring, + __entry->desc, __entry->skb) +); + +DEFINE_EVENT( + i40e_rx_template, i40e_clean_rx_irq, + TP_PROTO(struct i40e_ring *ring, + union i40e_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb)); + +DEFINE_EVENT( + i40e_rx_template, i40e_clean_rx_irq_rx, + TP_PROTO(struct i40e_ring *ring, + union i40e_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb)); + +DECLARE_EVENT_CLASS( + i40e_xmit_template, + + TP_PROTO(struct sk_buff *skb, + struct i40e_ring *ring), + + TP_ARGS(skb, ring), + + TP_STRUCT__entry( + __field(void*, skb) + __field(void*, ring) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->skb = skb; + __entry->ring = ring; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s skb: %p ring: %p", + __get_str(devname), __entry->skb, + __entry->ring) +); + +DEFINE_EVENT( + i40e_xmit_template, i40e_xmit_frame_ring, + TP_PROTO(struct sk_buff *skb, + struct i40e_ring *ring), + + TP_ARGS(skb, ring)); + +DEFINE_EVENT( + i40e_xmit_template, i40e_xmit_frame_ring_drop, + TP_PROTO(struct sk_buff *skb, + struct i40e_ring *ring), + + TP_ARGS(skb, ring)); + +/* Events unique to the PF. */ + +#endif /* _I40E_TRACE_H_ */ +/* This must be outside ifdef _I40E_TRACE_H */ + +/* This trace include file is not located in the .../include/trace + * with the kernel tracepoint definitions, because we're a loadable + * module. + */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE i40e_trace +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index ebffca0cefac..1531a0f9fcc6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -27,6 +27,7 @@ #include <linux/prefetch.h> #include <net/busy_poll.h> #include "i40e.h" +#include "i40e_trace.h" #include "i40e_prototype.h" static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, @@ -533,14 +534,15 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi, break; default: /* We cannot support masking based on protocol */ - goto unsupported_flow; + dev_info(&pf->pdev->dev, "Unsupported IPv4 protocol 0x%02x\n", + input->ip4_proto); + return -EINVAL; } break; default: -unsupported_flow: - dev_info(&pf->pdev->dev, "Could not specify spec type %d\n", + dev_info(&pf->pdev->dev, "Unsupported flow type 0x%02x\n", input->flow_type); - ret = -EINVAL; + return -EINVAL; } /* The buffer allocated here will be normally be freed by @@ -710,19 +712,15 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring) /** * i40e_get_tx_pending - how many tx descriptors not processed * @tx_ring: the ring of descriptors - * @in_sw: is tx_pending being checked in SW or HW * * Since there is no access to the ring head register * in XL710, we need to use our local copies **/ -u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw) +u32 i40e_get_tx_pending(struct i40e_ring *ring) { u32 head, tail; - if (!in_sw) - head = i40e_get_head(ring); - else - head = ring->next_to_clean; + head = i40e_get_head(ring); tail = readl(ring->tail); if (head != tail) @@ -768,6 +766,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* prevent any other reads prior to eop_desc */ read_barrier_depends(); + i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); /* we have caught up to head, no work left to do */ if (tx_head == tx_desc) break; @@ -794,6 +793,8 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* unmap remaining buffers */ while (tx_desc != eop_desc) { + i40e_trace(clean_tx_irq_unmap, + tx_ring, tx_desc, tx_buf); tx_buf++; tx_desc++; @@ -845,7 +846,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, * them to be written back in case we stay in NAPI. * In this mode on X722 we do not enable Interrupt. */ - unsigned int j = i40e_get_tx_pending(tx_ring, false); + unsigned int j = i40e_get_tx_pending(tx_ring); if (budget && ((j / WB_STRIDE) == 0) && (j > 0) && @@ -1041,9 +1042,29 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) } /** + * 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 - 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 * * Flow director should handle FD_FILTER_STATUS to check its filter programming * status being successful or not and take actions accordingly. FCoE should @@ -1051,12 +1072,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) * **/ static void i40e_clean_programming_status(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc) + union i40e_rx_desc *rx_desc, + u64 qw) { - u64 qw; + u32 ntc = rx_ring->next_to_clean + 1; u8 id; - qw = le64_to_cpu(rx_desc->wb.qword1.status_error_len); + /* fetch, update, and store next to clean */ + 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) >> I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT; @@ -1141,14 +1168,15 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) dma_sync_single_range_for_cpu(rx_ring->dev, rx_bi->dma, rx_bi->page_offset, - I40E_RXBUFFER_2048, + rx_ring->rx_buf_len, DMA_FROM_DEVICE); /* free resources associated with mapping */ dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, - PAGE_SIZE, + i40e_rx_pg_size(rx_ring), DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); + __page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias); rx_bi->page = NULL; @@ -1250,6 +1278,17 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) } /** + * i40e_rx_offset - Return expected offset into page to access data + * @rx_ring: Ring we are requesting offset of + * + * Returns the offset value for ring into the data buffer. + */ +static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0; +} + +/** * i40e_alloc_mapped_page - recycle or make a new page * @rx_ring: ring to use * @bi: rx_buffer struct to modify @@ -1270,7 +1309,7 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /* alloc new page for storage */ - page = dev_alloc_page(); + page = dev_alloc_pages(i40e_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_page_failed++; return false; @@ -1278,7 +1317,7 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, /* map page for use */ dma = dma_map_page_attrs(rx_ring->dev, page, 0, - PAGE_SIZE, + i40e_rx_pg_size(rx_ring), DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); @@ -1286,14 +1325,14 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_pages(page, 0); + __free_pages(page, i40e_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_page_failed++; return false; } bi->dma = dma; bi->page = page; - bi->page_offset = 0; + bi->page_offset = i40e_rx_offset(rx_ring); /* initialize pagecnt_bias to 1 representing we fully own page */ bi->pagecnt_bias = 1; @@ -1346,7 +1385,7 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, bi->page_offset, - I40E_RXBUFFER_2048, + rx_ring->rx_buf_len, DMA_FROM_DEVICE); /* Refresh the desc even if buffer_addrs didn't change @@ -1648,9 +1687,6 @@ static inline bool i40e_page_is_reusable(struct page *page) **/ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) { -#if (PAGE_SIZE >= 8192) - unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048; -#endif unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -1663,7 +1699,9 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) if (unlikely((page_count(page) - pagecnt_bias) > 1)) return false; #else - if (rx_buffer->page_offset > last_offset) +#define I40E_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048) + if (rx_buffer->page_offset > I40E_LAST_OFFSET) return false; #endif @@ -1697,9 +1735,9 @@ static void i40e_add_rx_frag(struct i40e_ring *rx_ring, unsigned int size) { #if (PAGE_SIZE < 8192) - unsigned int truesize = I40E_RXBUFFER_2048; + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = SKB_DATA_ALIGN(size); + unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring)); #endif skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, @@ -1758,7 +1796,7 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, { void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = I40E_RXBUFFER_2048; + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(size); #endif @@ -1808,6 +1846,51 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, } /** + * i40e_build_skb - Build skb around an existing buffer + * @rx_ring: Rx descriptor ring to transact packets on + * @rx_buffer: Rx buffer to pull data from + * @size: size of buffer to add to skb + * + * This function builds an skb around an existing Rx buffer, taking care + * to set up the skb correctly and avoid any memcpy overhead. + */ +static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *rx_buffer, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size); +#endif + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + /* build an skb around the page buffer */ + skb = build_skb(va - I40E_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; + + /* update pointers within the skb to store the data */ + skb_reserve(skb, I40E_SKB_PAD); + __skb_put(skb, size); + + /* buffer is used by skb, update page_offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + + return skb; +} + +/** * i40e_put_rx_buffer - Clean up used buffer and either recycle or free * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: rx buffer to pull data from @@ -1824,7 +1907,8 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + i40e_rx_pg_size(rx_ring), DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); __page_frag_cache_drain(rx_buffer->page, rx_buffer->pagecnt_bias); @@ -1857,11 +1941,6 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, prefetch(I40E_RX_DESC(rx_ring, ntc)); -#define staterrlen rx_desc->wb.qword1.status_error_len - if (unlikely(i40e_rx_is_programming_status(le64_to_cpu(staterrlen)))) { - i40e_clean_programming_status(rx_ring, rx_desc); - return true; - } /* if we are the last buffer then there is nothing else to do */ #define I40E_RXD_EOF BIT(I40E_RX_DESC_STATUS_EOF_SHIFT) if (likely(i40e_test_staterr(rx_desc, I40E_RXD_EOF))) @@ -1914,10 +1993,6 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) * hardware wrote DD then the length will be non-zero */ qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> - I40E_RXD_QW1_LENGTH_PBUF_SHIFT; - if (!size) - break; /* This memory barrier is needed to keep us from reading * any other fields out of the rx_desc until we have @@ -1925,11 +2000,23 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ dma_rmb(); + if (unlikely(i40e_rx_is_programming_status(qword))) { + i40e_clean_programming_status(rx_ring, rx_desc, qword); + continue; + } + size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> + I40E_RXD_QW1_LENGTH_PBUF_SHIFT; + if (!size) + break; + + i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb); rx_buffer = i40e_get_rx_buffer(rx_ring, size); /* retrieve a buffer from the ring */ if (skb) i40e_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = i40e_build_skb(rx_ring, rx_buffer, size); else skb = i40e_construct_skb(rx_ring, rx_buffer, size); @@ -1975,6 +2062,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; + i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); i40e_receive_skb(rx_ring, skb, vlan_tag); skb = NULL; @@ -2125,8 +2213,6 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) return 0; } - /* Clear hung_detected bit */ - clear_bit(I40E_Q_VECTOR_HUNG_DETECT, &q_vector->hung_detected); /* Since the actual Tx work is minimal, we can give the Tx a larger * budget and be more aggressive about cleaning up the Tx descriptors. */ @@ -2262,8 +2348,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, /* Due to lack of space, no more new filters can be programmed */ if (th->syn && (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED)) return; - if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) && - (!(pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) { + if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) { /* HW ATR eviction will take care of removing filters on FIN * and RST packets. */ @@ -2325,8 +2410,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) & I40E_TXD_FLTR_QW1_CNTINDEX_MASK; - if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) && - (!(pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) + if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK; fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype); @@ -3060,6 +3144,8 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, /* prefetch the data, we'll need it later */ prefetch(skb->data); + i40e_trace(xmit_frame_ring, skb, tx_ring); + count = i40e_xmit_descriptor_count(skb); if (i40e_chk_linearize(skb, count)) { if (__skb_linearize(skb)) { @@ -3138,6 +3224,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_OK; out_drop: + i40e_trace(xmit_frame_ring_drop, first->skb, tx_ring); dev_kfree_skb_any(first->skb); first->skb = NULL; return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index d6609deace57..f5de51124cae 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -119,6 +119,7 @@ enum i40e_dyn_idx_t { #define I40E_RXBUFFER_256 256 #define I40E_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ #define I40E_RXBUFFER_2048 2048 +#define I40E_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ #define I40E_MAX_RXBUFFER 9728 /* largest size for single descriptor */ /* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we @@ -134,6 +135,58 @@ enum i40e_dyn_idx_t { #define I40E_RX_DMA_ATTR \ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) +/* Attempt to maximize the headroom available for incoming frames. We + * use a 2K buffer for receives and need 1536/1534 to store the data for + * the frame. This leaves us with 512 bytes of room. From that we need + * to deduct the space needed for the shared info and the padding needed + * to IP align the frame. + * + * Note: For cache line sizes 256 or larger this value is going to end + * up negative. In these cases we should fall back to the legacy + * receive path. + */ +#if (PAGE_SIZE < 8192) +#define I40E_2K_TOO_SMALL_WITH_PADDING \ +((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048)) + +static inline int i40e_compute_pad(int rx_buf_len) +{ + int page_size, pad_size; + + page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); + pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len; + + return pad_size; +} + +static inline int i40e_skb_pad(void) +{ + int rx_buf_len; + + /* If a 2K buffer cannot handle a standard Ethernet frame then + * optimize padding for a 3K buffer instead of a 1.5K buffer. + * + * For a 3K buffer we need to add enough padding to allow for + * tailroom due to NET_IP_ALIGN possibly shifting us out of + * cache-line alignment. + */ + if (I40E_2K_TOO_SMALL_WITH_PADDING) + rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); + else + rx_buf_len = I40E_RXBUFFER_1536; + + /* if needed make room for NET_IP_ALIGN */ + rx_buf_len -= NET_IP_ALIGN; + + return i40e_compute_pad(rx_buf_len); +} + +#define I40E_SKB_PAD i40e_skb_pad() +#else +#define I40E_2K_TOO_SMALL_WITH_PADDING false +#define I40E_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#endif + /** * i40e_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format) @@ -275,7 +328,6 @@ struct i40e_tx_queue_stats { u64 tx_done_old; u64 tx_linearize; u64 tx_force_wb; - u64 tx_lost_interrupt; }; struct i40e_rx_queue_stats { @@ -341,7 +393,8 @@ struct i40e_ring { u8 packet_stride; u16 flags; -#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) +#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) +#define I40E_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) /* stats structs */ struct i40e_queue_stats stats; @@ -369,6 +422,21 @@ struct i40e_ring { */ } ____cacheline_internodealigned_in_smp; +static inline bool ring_uses_build_skb(struct i40e_ring *ring) +{ + return !!(ring->flags & I40E_RXR_FLAGS_BUILD_SKB_ENABLED); +} + +static inline void set_ring_build_skb_enabled(struct i40e_ring *ring) +{ + ring->flags |= I40E_RXR_FLAGS_BUILD_SKB_ENABLED; +} + +static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring) +{ + ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED; +} + enum i40e_latency_range { I40E_LOWEST_LATENCY = 0, I40E_LOW_LATENCY = 1, @@ -390,6 +458,17 @@ struct i40e_ring_container { #define i40e_for_each_ring(pos, head) \ for (pos = (head).ring; pos != NULL; pos = pos->next) +static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring->rx_buf_len > (PAGE_SIZE / 2)) + return 1; +#endif + return 0; +} + +#define i40e_rx_pg_size(_ring) (PAGE_SIZE << i40e_rx_pg_order(_ring)) + bool i40e_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count); netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev); void i40e_clean_tx_ring(struct i40e_ring *tx_ring); @@ -400,7 +479,7 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring); void i40e_free_rx_resources(struct i40e_ring *rx_ring); int i40e_napi_poll(struct napi_struct *napi, int budget); void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector); -u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw); +u32 i40e_get_tx_pending(struct i40e_ring *ring); int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 9200f2d9c752..3a18ed13edc4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -78,6 +78,7 @@ enum i40e_debug_mask { I40E_DEBUG_DCB = 0x00000400, I40E_DEBUG_DIAG = 0x00000800, I40E_DEBUG_FD = 0x00001000, + I40E_DEBUG_PACKAGE = 0x00002000, I40E_DEBUG_IWARP = 0x00F00000, I40E_DEBUG_AQ_MESSAGE = 0x01000000, I40E_DEBUG_AQ_DESCRIPTOR = 0x02000000, @@ -1462,4 +1463,83 @@ struct i40e_lldp_variables { #define I40E_FLEX_56_MASK (0x1ULL << I40E_FLEX_56_SHIFT) #define I40E_FLEX_57_SHIFT 6 #define I40E_FLEX_57_MASK (0x1ULL << I40E_FLEX_57_SHIFT) + +/* Version format for PPP */ +struct i40e_ppp_version { + u8 major; + u8 minor; + u8 update; + u8 draft; +}; + +#define I40E_PPP_NAME_SIZE 32 + +/* Package header */ +struct i40e_package_header { + struct i40e_ppp_version version; + u32 segment_count; + u32 segment_offset[1]; +}; + +/* Generic segment header */ +struct i40e_generic_seg_header { +#define SEGMENT_TYPE_METADATA 0x00000001 +#define SEGMENT_TYPE_NOTES 0x00000002 +#define SEGMENT_TYPE_I40E 0x00000011 +#define SEGMENT_TYPE_X722 0x00000012 + u32 type; + struct i40e_ppp_version version; + u32 size; + char name[I40E_PPP_NAME_SIZE]; +}; + +struct i40e_metadata_segment { + struct i40e_generic_seg_header header; + struct i40e_ppp_version version; + u32 track_id; + char name[I40E_PPP_NAME_SIZE]; +}; + +struct i40e_device_id_entry { + u32 vendor_dev_id; + u32 sub_vendor_dev_id; +}; + +struct i40e_profile_segment { + struct i40e_generic_seg_header header; + struct i40e_ppp_version version; + char name[I40E_PPP_NAME_SIZE]; + u32 device_table_count; + struct i40e_device_id_entry device_table[1]; +}; + +struct i40e_section_table { + u32 section_count; + u32 section_offset[1]; +}; + +struct i40e_profile_section_header { + u16 tbl_size; + u16 data_end; + struct { +#define SECTION_TYPE_INFO 0x00000010 +#define SECTION_TYPE_MMIO 0x00000800 +#define SECTION_TYPE_AQ 0x00000801 +#define SECTION_TYPE_NOTE 0x80000000 +#define SECTION_TYPE_NAME 0x80000001 + u32 type; + u32 offset; + u32 size; + } section; +}; + +struct i40e_profile_info { + u32 track_id; + struct i40e_ppp_version version; + u8 op; +#define I40E_PPP_ADD_TRACKID 0x01 +#define I40E_PPP_REMOVE_TRACKID 0x02 + u8 reserved[7]; + u8 name[I40E_PPP_NAME_SIZE]; +}; #endif /* _I40E_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h index 974ba2baf6ea..8552192a5bde 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h @@ -163,7 +163,8 @@ struct i40e_virtchnl_vsi_resource { #define I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF 0X00080000 -#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00100000 +#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP 0X00100000 +#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000 #define I40E_VF_BASE_MODE_OFFLOADS (I40E_VIRTCHNL_VF_OFFLOAD_L2 | \ I40E_VIRTCHNL_VF_OFFLOAD_VLAN | \ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index d526940ff951..350cba70490c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -923,22 +923,19 @@ static int i40e_quiesce_vf_pci(struct i40e_vf *vf) } /** - * i40e_reset_vf + * i40e_trigger_vf_reset * @vf: pointer to the VF structure * @flr: VFLR was issued or not * - * reset the VF + * Trigger hardware to start a reset for a particular VF. Expects the caller + * to wait the proper amount of time to allow hardware to reset the VF before + * it cleans up and restores VF functionality. **/ -void i40e_reset_vf(struct i40e_vf *vf, bool flr) +static void i40e_trigger_vf_reset(struct i40e_vf *vf, bool flr) { struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; u32 reg, reg_idx, bit_idx; - bool rsd = false; - int i; - - if (test_and_set_bit(__I40E_VF_DISABLE, &pf->state)) - return; /* warn the VF */ clear_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states); @@ -970,37 +967,22 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) if (i40e_quiesce_vf_pci(vf)) dev_err(&pf->pdev->dev, "VF %d PCI transactions stuck\n", vf->vf_id); +} - /* poll VPGEN_VFRSTAT reg to make sure - * that reset is complete - */ - for (i = 0; i < 10; i++) { - /* VF reset requires driver to first reset the VF and then - * poll the status register to make sure that the reset - * completed successfully. Due to internal HW FIFO flushes, - * we must wait 10ms before the register will be valid. - */ - usleep_range(10000, 20000); - reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); - if (reg & I40E_VPGEN_VFRSTAT_VFRD_MASK) { - rsd = true; - break; - } - } - - if (flr) - usleep_range(10000, 20000); - - if (!rsd) - dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n", - vf->vf_id); - - /* On initial reset, we won't have any queues */ - if (vf->lan_vsi_idx == 0) - goto complete_reset; +/** + * i40e_cleanup_reset_vf + * @vf: pointer to the VF structure + * + * Cleanup a VF after the hardware reset is finished. Expects the caller to + * have verified whether the reset is finished properly, and ensure the + * minimum amount of wait time has passed. + **/ +static void i40e_cleanup_reset_vf(struct i40e_vf *vf) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_hw *hw = &pf->hw; + u32 reg; - i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]); -complete_reset: /* free VF resources to begin resetting the VSI state */ i40e_free_vf_res(vf); @@ -1035,6 +1017,159 @@ complete_reset: * request resources immediately after setting this flag. */ wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE); +} + +/** + * i40e_reset_vf + * @vf: pointer to the VF structure + * @flr: VFLR was issued or not + * + * reset the VF + **/ +void i40e_reset_vf(struct i40e_vf *vf, bool flr) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_hw *hw = &pf->hw; + bool rsd = false; + u32 reg; + int i; + + /* If VFs have been disabled, there is no need to reset */ + if (test_and_set_bit(__I40E_VF_DISABLE, &pf->state)) + return; + + i40e_trigger_vf_reset(vf, flr); + + /* poll VPGEN_VFRSTAT reg to make sure + * that reset is complete + */ + for (i = 0; i < 10; i++) { + /* VF reset requires driver to first reset the VF and then + * poll the status register to make sure that the reset + * completed successfully. Due to internal HW FIFO flushes, + * we must wait 10ms before the register will be valid. + */ + usleep_range(10000, 20000); + reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); + if (reg & I40E_VPGEN_VFRSTAT_VFRD_MASK) { + rsd = true; + break; + } + } + + if (flr) + usleep_range(10000, 20000); + + if (!rsd) + dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n", + vf->vf_id); + usleep_range(10000, 20000); + + /* On initial reset, we don't have any queues to disable */ + if (vf->lan_vsi_idx != 0) + i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]); + + i40e_cleanup_reset_vf(vf); + + i40e_flush(hw); + clear_bit(__I40E_VF_DISABLE, &pf->state); +} + +/** + * i40e_reset_all_vfs + * @pf: pointer to the PF structure + * @flr: VFLR was issued or not + * + * Reset all allocated VFs in one go. First, tell the hardware to reset each + * VF, then do all the waiting in one chunk, and finally finish restoring each + * VF after the wait. This is useful during PF routines which need to reset + * all VFs, as otherwise it must perform these resets in a serialized fashion. + **/ +void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) +{ + struct i40e_hw *hw = &pf->hw; + struct i40e_vf *vf; + int i, v; + u32 reg; + + /* If we don't have any VFs, then there is nothing to reset */ + if (!pf->num_alloc_vfs) + return; + + /* If VFs have been disabled, there is no need to reset */ + if (test_and_set_bit(__I40E_VF_DISABLE, &pf->state)) + return; + + /* Begin reset on all VFs at once */ + for (v = 0; v < pf->num_alloc_vfs; v++) + i40e_trigger_vf_reset(&pf->vf[v], flr); + + /* HW requires some time to make sure it can flush the FIFO for a VF + * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in + * sequence to make sure that it has completed. We'll keep track of + * the VFs using a simple iterator that increments once that VF has + * finished resetting. + */ + for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { + usleep_range(10000, 20000); + + /* Check each VF in sequence, beginning with the VF to fail + * the previous check. + */ + while (v < pf->num_alloc_vfs) { + vf = &pf->vf[v]; + reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); + if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK)) + break; + + /* If the current VF has finished resetting, move on + * to the next VF in sequence. + */ + v++; + } + } + + if (flr) + usleep_range(10000, 20000); + + /* Display a warning if at least one VF didn't manage to reset in + * time, but continue on with the operation. + */ + if (v < pf->num_alloc_vfs) + dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n", + pf->vf[v].vf_id); + usleep_range(10000, 20000); + + /* Begin disabling all the rings associated with VFs, but do not wait + * between each VF. + */ + for (v = 0; v < pf->num_alloc_vfs; v++) { + /* On initial reset, we don't have any queues to disable */ + if (pf->vf[v].lan_vsi_idx == 0) + continue; + + i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]); + } + + /* Now that we've notified HW to disable all of the VF rings, wait + * until they finish. + */ + for (v = 0; v < pf->num_alloc_vfs; v++) { + /* On initial reset, we don't have any queues to disable */ + if (pf->vf[v].lan_vsi_idx == 0) + continue; + + i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]); + } + + /* Hw may need up to 50ms to finish disabling the RX queues. We + * minimize the wait by delaying only once for all VFs. + */ + mdelay(50); + + /* Finish the reset on each VF */ + for (v = 0; v < pf->num_alloc_vfs; v++) + i40e_cleanup_reset_vf(&pf->vf[v]); i40e_flush(hw); clear_bit(__I40E_VF_DISABLE, &pf->state); @@ -1408,6 +1543,13 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; } + if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_ENCAP) + vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_ENCAP; + + if ((pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE) && + (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM)) + vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; + if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING) { if (pf->flags & I40E_FLAG_MFP_ENABLED) { dev_err(&pf->pdev->dev, diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 37af437daa5d..9495f1422122 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -124,6 +124,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen); int i40e_vc_process_vflr_event(struct i40e_pf *pf); void i40e_reset_vf(struct i40e_vf *vf, bool flr); +void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr); void i40e_vc_notify_vf_reset(struct i40e_vf *vf); /* VF configuration related iplink handlers */ diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile index 827c7a6ed0ba..a393f4a07f06 100644 --- a/drivers/net/ethernet/intel/i40evf/Makefile +++ b/drivers/net/ethernet/intel/i40evf/Makefile @@ -29,6 +29,9 @@ # # +ccflags-y += -I$(src) +subdir-ccflags-y += -I$(src) + obj-$(CONFIG_I40EVF) += i40evf.o i40evf-objs := i40evf_main.o i40evf_ethtool.o i40evf_virtchnl.o \ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index 96385156b824..8b0d4b255dea 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -797,8 +797,8 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, */ if (i40evf_asq_done(hw)) break; - usleep_range(1000, 2000); - total_delay++; + udelay(50); + total_delay += 50; } while (total_delay < hw->aq.asq_cmd_timeout); } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h index 1f9b3b5d946d..e0bfaa3d4a21 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h @@ -151,7 +151,7 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc) /* general information */ #define I40E_AQ_LARGE_BUF 512 -#define I40E_ASQ_CMD_TIMEOUT 250 /* msecs */ +#define I40E_ASQ_CMD_TIMEOUT 250000 /* usecs */ void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index c28cb8f27243..91d8786d386d 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -190,6 +190,10 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_add_mirror_rule = 0x0260, i40e_aqc_opc_delete_mirror_rule = 0x0261, + /* Pipeline Personalization Profile */ + i40e_aqc_opc_write_personalization_profile = 0x0270, + i40e_aqc_opc_get_personalization_profile_list = 0x0271, + /* DCB commands */ i40e_aqc_opc_dcb_ignore_pfc = 0x0301, i40e_aqc_opc_dcb_updated = 0x0302, @@ -1426,6 +1430,36 @@ struct i40e_aqc_add_delete_mirror_rule_completion { I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule_completion); +/* Pipeline Personalization Profile */ +struct i40e_aqc_write_personalization_profile { + u8 flags; + u8 reserved[3]; + __le32 profile_track_id; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_write_personalization_profile); + +struct i40e_aqc_write_ppp_resp { + __le32 error_offset; + __le32 error_info; + __le32 addr_high; + __le32 addr_low; +}; + +struct i40e_aqc_get_applied_profiles { + u8 flags; +#define I40E_AQC_GET_PPP_GET_CONF 0x1 +#define I40E_AQC_GET_PPP_GET_RDPU_CONF 0x2 + u8 rsv[3]; + __le32 reserved; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_applied_profiles); + /* DCB 0x03xx*/ /* PFC Ignore (direct 0x0301) diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index 626fbf1ead4d..43f10761f4ba 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -1131,3 +1131,215 @@ i40e_status i40e_vf_reset(struct i40e_hw *hw) return i40e_aq_send_msg_to_pf(hw, I40E_VIRTCHNL_OP_RESET_VF, 0, NULL, 0, NULL); } + +/** + * i40evf_aq_write_ppp - Write pipeline personalization profile (ppp) + * @hw: pointer to the hw struct + * @buff: command buffer (size in bytes = buff_size) + * @buff_size: buffer size in bytes + * @track_id: package tracking id + * @error_offset: returns error offset + * @error_info: returns error information + * @cmd_details: pointer to command details structure or NULL + **/ +enum +i40e_status_code i40evf_aq_write_ppp(struct i40e_hw *hw, void *buff, + u16 buff_size, u32 track_id, + u32 *error_offset, u32 *error_info, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_write_personalization_profile *cmd = + (struct i40e_aqc_write_personalization_profile *) + &desc.params.raw; + struct i40e_aqc_write_ppp_resp *resp; + i40e_status status; + + i40evf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_write_personalization_profile); + + desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD); + if (buff_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + + desc.datalen = cpu_to_le16(buff_size); + + cmd->profile_track_id = cpu_to_le32(track_id); + + status = i40evf_asq_send_command(hw, &desc, buff, buff_size, cmd_details); + if (!status) { + resp = (struct i40e_aqc_write_ppp_resp *)&desc.params.raw; + if (error_offset) + *error_offset = le32_to_cpu(resp->error_offset); + if (error_info) + *error_info = le32_to_cpu(resp->error_info); + } + + return status; +} + +/** + * i40evf_aq_get_ppp_list - Read pipeline personalization profile (ppp) + * @hw: pointer to the hw struct + * @buff: command buffer (size in bytes = buff_size) + * @buff_size: buffer size in bytes + * @cmd_details: pointer to command details structure or NULL + **/ +enum +i40e_status_code i40evf_aq_get_ppp_list(struct i40e_hw *hw, void *buff, + u16 buff_size, u8 flags, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_get_applied_profiles *cmd = + (struct i40e_aqc_get_applied_profiles *)&desc.params.raw; + i40e_status status; + + i40evf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_personalization_profile_list); + + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + if (buff_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + desc.datalen = cpu_to_le16(buff_size); + + cmd->flags = flags; + + status = i40evf_asq_send_command(hw, &desc, buff, buff_size, cmd_details); + + return status; +} + +/** + * i40evf_find_segment_in_package + * @segment_type: the segment type to search for (i.e., SEGMENT_TYPE_I40E) + * @pkg_hdr: pointer to the package header to be searched + * + * This function searches a package file for a particular segment type. On + * success it returns a pointer to the segment header, otherwise it will + * return NULL. + **/ +struct i40e_generic_seg_header * +i40evf_find_segment_in_package(u32 segment_type, + struct i40e_package_header *pkg_hdr) +{ + struct i40e_generic_seg_header *segment; + u32 i; + + /* Search all package segments for the requested segment type */ + for (i = 0; i < pkg_hdr->segment_count; i++) { + segment = + (struct i40e_generic_seg_header *)((u8 *)pkg_hdr + + pkg_hdr->segment_offset[i]); + + if (segment->type == segment_type) + return segment; + } + + return NULL; +} + +/** + * i40evf_write_profile + * @hw: pointer to the hardware structure + * @profile: pointer to the profile segment of the package to be downloaded + * @track_id: package tracking id + * + * Handles the download of a complete package. + */ +enum i40e_status_code +i40evf_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, + u32 track_id) +{ + i40e_status status = 0; + struct i40e_section_table *sec_tbl; + struct i40e_profile_section_header *sec = NULL; + u32 dev_cnt; + u32 vendor_dev_id; + u32 *nvm; + u32 section_size = 0; + u32 offset = 0, info = 0; + u32 i; + + if (!track_id) { + i40e_debug(hw, I40E_DEBUG_PACKAGE, "Track_id can't be 0."); + return I40E_NOT_SUPPORTED; + } + + dev_cnt = profile->device_table_count; + + for (i = 0; i < dev_cnt; i++) { + vendor_dev_id = profile->device_table[i].vendor_dev_id; + if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL) + if (hw->device_id == (vendor_dev_id & 0xFFFF)) + break; + } + if (i == dev_cnt) { + i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support PPP"); + return I40E_ERR_DEVICE_NOT_SUPPORTED; + } + + nvm = (u32 *)&profile->device_table[dev_cnt]; + sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1]; + + for (i = 0; i < sec_tbl->section_count; i++) { + sec = (struct i40e_profile_section_header *)((u8 *)profile + + sec_tbl->section_offset[i]); + + /* Skip 'AQ', 'note' and 'name' sections */ + if (sec->section.type != SECTION_TYPE_MMIO) + continue; + + section_size = sec->section.size + + sizeof(struct i40e_profile_section_header); + + /* Write profile */ + status = i40evf_aq_write_ppp(hw, (void *)sec, (u16)section_size, + track_id, &offset, &info, NULL); + if (status) { + i40e_debug(hw, I40E_DEBUG_PACKAGE, + "Failed to write profile: offset %d, info %d", + offset, info); + break; + } + } + return status; +} + +/** + * i40evf_add_pinfo_to_list + * @hw: pointer to the hardware structure + * @profile: pointer to the profile segment of the package + * @profile_info_sec: buffer for information section + * @track_id: package tracking id + * + * Register a profile to the list of loaded profiles. + */ +enum i40e_status_code +i40evf_add_pinfo_to_list(struct i40e_hw *hw, + struct i40e_profile_segment *profile, + u8 *profile_info_sec, u32 track_id) +{ + i40e_status status = 0; + struct i40e_profile_section_header *sec = NULL; + struct i40e_profile_info *pinfo; + u32 offset = 0, info = 0; + + sec = (struct i40e_profile_section_header *)profile_info_sec; + sec->tbl_size = 1; + sec->data_end = sizeof(struct i40e_profile_section_header) + + sizeof(struct i40e_profile_info); + sec->section.type = SECTION_TYPE_INFO; + sec->section.offset = sizeof(struct i40e_profile_section_header); + sec->section.size = sizeof(struct i40e_profile_info); + pinfo = (struct i40e_profile_info *)(profile_info_sec + + sec->section.offset); + pinfo->track_id = track_id; + pinfo->version = profile->version; + pinfo->op = I40E_PPP_ADD_TRACKID; + memcpy(pinfo->name, profile->name, I40E_PPP_NAME_SIZE); + + status = i40evf_aq_write_ppp(hw, (void *)sec, sec->data_end, + track_id, &offset, &info, NULL); + return status; +} diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h index ba6c6bda0e22..741223d5d809 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h @@ -122,4 +122,21 @@ i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num); i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, u32 time, u32 interval); +i40e_status i40evf_aq_write_ppp(struct i40e_hw *hw, void *buff, + u16 buff_size, u32 track_id, + u32 *error_offset, u32 *error_info, + struct i40e_asq_cmd_details *cmd_details); +i40e_status i40evf_aq_get_ppp_list(struct i40e_hw *hw, void *buff, + u16 buff_size, u8 flags, + struct i40e_asq_cmd_details *cmd_details); +struct i40e_generic_seg_header * +i40evf_find_segment_in_package(u32 segment_type, + struct i40e_package_header *pkg_header); +enum i40e_status_code +i40evf_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg, + u32 track_id); +enum i40e_status_code +i40evf_add_pinfo_to_list(struct i40e_hw *hw, + struct i40e_profile_segment *profile, + u8 *profile_info_sec, u32 track_id); #endif /* _I40E_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_trace.h b/drivers/net/ethernet/intel/i40evf/i40e_trace.h new file mode 100644 index 000000000000..9a5100b2b7c7 --- /dev/null +++ b/drivers/net/ethernet/intel/i40evf/i40e_trace.h @@ -0,0 +1,229 @@ +/******************************************************************************* + * + * Intel(R) 40-10 Gigabit Ethernet Virtual Function 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 + * + ******************************************************************************/ + +/* Modeled on trace-events-sample.h */ + +/* The trace subsystem name for i40evf will be "i40evf". + * + * This file is named i40e_trace.h. + * + * Since this include file's name is different from the trace + * subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end + * of this file. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM i40evf + +/* See trace-events-sample.h for a detailed description of why this + * guard clause is different from most normal include files. + */ +#if !defined(_I40E_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _I40E_TRACE_H_ + +#include <linux/tracepoint.h> + +/** + * i40e_trace() macro enables shared code to refer to trace points + * like: + * + * trace_i40e{,vf}_example(args...) + * + * ... as: + * + * i40e_trace(example, args...) + * + * ... to resolve to the PF or VF version of the tracepoint without + * ifdefs, and to allow tracepoints to be disabled entirely at build + * time. + * + * Trace point should always be referred to in the driver via this + * macro. + * + * Similarly, i40e_trace_enabled(trace_name) wraps references to + * trace_i40e{,vf}_<trace_name>_enabled() functions. + */ +#define _I40E_TRACE_NAME(trace_name) (trace_ ## i40evf ## _ ## trace_name) +#define I40E_TRACE_NAME(trace_name) _I40E_TRACE_NAME(trace_name) + +#define i40e_trace(trace_name, args...) I40E_TRACE_NAME(trace_name)(args) + +#define i40e_trace_enabled(trace_name) I40E_TRACE_NAME(trace_name##_enabled)() + +/* Events common to PF and VF. Corresponding versions will be defined + * for both, named trace_i40e_* and trace_i40evf_*. The i40e_trace() + * macro above will select the right trace point name for the driver + * being built from shared code. + */ + +/* Events related to a vsi & ring */ +DECLARE_EVENT_CLASS( + i40evf_tx_template, + + TP_PROTO(struct i40e_ring *ring, + struct i40e_tx_desc *desc, + struct i40e_tx_buffer *buf), + + TP_ARGS(ring, desc, buf), + + /* The convention here is to make the first fields in the + * TP_STRUCT match the TP_PROTO exactly. This enables the use + * of the args struct generated by the tplist tool (from the + * bcc-tools package) to be used for those fields. To access + * fields other than the tracepoint args will require the + * tplist output to be adjusted. + */ + TP_STRUCT__entry( + __field(void*, ring) + __field(void*, desc) + __field(void*, buf) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->ring = ring; + __entry->desc = desc; + __entry->buf = buf; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s ring: %p desc: %p buf %p", + __get_str(devname), __entry->ring, + __entry->desc, __entry->buf) +); + +DEFINE_EVENT( + i40evf_tx_template, i40evf_clean_tx_irq, + TP_PROTO(struct i40e_ring *ring, + struct i40e_tx_desc *desc, + struct i40e_tx_buffer *buf), + + TP_ARGS(ring, desc, buf)); + +DEFINE_EVENT( + i40evf_tx_template, i40evf_clean_tx_irq_unmap, + TP_PROTO(struct i40e_ring *ring, + struct i40e_tx_desc *desc, + struct i40e_tx_buffer *buf), + + TP_ARGS(ring, desc, buf)); + +DECLARE_EVENT_CLASS( + i40evf_rx_template, + + TP_PROTO(struct i40e_ring *ring, + union i40e_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb), + + TP_STRUCT__entry( + __field(void*, ring) + __field(void*, desc) + __field(void*, skb) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->ring = ring; + __entry->desc = desc; + __entry->skb = skb; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s ring: %p desc: %p skb %p", + __get_str(devname), __entry->ring, + __entry->desc, __entry->skb) +); + +DEFINE_EVENT( + i40evf_rx_template, i40evf_clean_rx_irq, + TP_PROTO(struct i40e_ring *ring, + union i40e_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb)); + +DEFINE_EVENT( + i40evf_rx_template, i40evf_clean_rx_irq_rx, + TP_PROTO(struct i40e_ring *ring, + union i40e_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb)); + +DECLARE_EVENT_CLASS( + i40evf_xmit_template, + + TP_PROTO(struct sk_buff *skb, + struct i40e_ring *ring), + + TP_ARGS(skb, ring), + + TP_STRUCT__entry( + __field(void*, skb) + __field(void*, ring) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->skb = skb; + __entry->ring = ring; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s skb: %p ring: %p", + __get_str(devname), __entry->skb, + __entry->ring) +); + +DEFINE_EVENT( + i40evf_xmit_template, i40evf_xmit_frame_ring, + TP_PROTO(struct sk_buff *skb, + struct i40e_ring *ring), + + TP_ARGS(skb, ring)); + +DEFINE_EVENT( + i40evf_xmit_template, i40evf_xmit_frame_ring_drop, + TP_PROTO(struct sk_buff *skb, + struct i40e_ring *ring), + + TP_ARGS(skb, ring)); + +/* Events unique to the VF. */ + +#endif /* _I40E_TRACE_H_ */ +/* This must be outside ifdef _I40E_TRACE_H */ + +/* This trace include file is not located in the .../include/trace + * with the kernel tracepoint definitions, because we're a loadable + * module. + */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE i40e_trace +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 95e383af41c4..34e96d98251a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -28,6 +28,7 @@ #include <net/busy_poll.h> #include "i40evf.h" +#include "i40e_trace.h" #include "i40e_prototype.h" static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, @@ -180,6 +181,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* prevent any other reads prior to eop_desc */ read_barrier_depends(); + i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); /* if the descriptor isn't done, no work yet to do */ if (!(eop_desc->cmd_type_offset_bsz & cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE))) @@ -207,6 +209,8 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* unmap remaining buffers */ while (tx_desc != eop_desc) { + i40e_trace(clean_tx_irq_unmap, + tx_ring, tx_desc, tx_buf); tx_buf++; tx_desc++; @@ -509,14 +513,15 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) dma_sync_single_range_for_cpu(rx_ring->dev, rx_bi->dma, rx_bi->page_offset, - I40E_RXBUFFER_2048, + rx_ring->rx_buf_len, DMA_FROM_DEVICE); /* free resources associated with mapping */ dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, - PAGE_SIZE, + i40e_rx_pg_size(rx_ring), DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); + __page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias); rx_bi->page = NULL; @@ -618,6 +623,17 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) } /** + * i40e_rx_offset - Return expected offset into page to access data + * @rx_ring: Ring we are requesting offset of + * + * Returns the offset value for ring into the data buffer. + */ +static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0; +} + +/** * i40e_alloc_mapped_page - recycle or make a new page * @rx_ring: ring to use * @bi: rx_buffer struct to modify @@ -638,7 +654,7 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /* alloc new page for storage */ - page = dev_alloc_page(); + page = dev_alloc_pages(i40e_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_page_failed++; return false; @@ -646,7 +662,7 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, /* map page for use */ dma = dma_map_page_attrs(rx_ring->dev, page, 0, - PAGE_SIZE, + i40e_rx_pg_size(rx_ring), DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); @@ -654,14 +670,14 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_pages(page, 0); + __free_pages(page, i40e_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_page_failed++; return false; } bi->dma = dma; bi->page = page; - bi->page_offset = 0; + bi->page_offset = i40e_rx_offset(rx_ring); /* initialize pagecnt_bias to 1 representing we fully own page */ bi->pagecnt_bias = 1; @@ -714,7 +730,7 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, bi->page_offset, - I40E_RXBUFFER_2048, + rx_ring->rx_buf_len, DMA_FROM_DEVICE); /* Refresh the desc even if buffer_addrs didn't change @@ -819,13 +835,6 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT)) return; - /* If there is an outer header present that might contain a checksum - * we need to bump the checksum level by 1 to reflect the fact that - * we are indicating we validated the inner checksum. - */ - if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT) - skb->csum_level = 1; - /* Only report checksum unnecessary for TCP, UDP, or SCTP */ switch (decoded.inner_prot) { case I40E_RX_PTYPE_INNER_PROT_TCP: @@ -1006,9 +1015,6 @@ static inline bool i40e_page_is_reusable(struct page *page) **/ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) { -#if (PAGE_SIZE >= 8192) - unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048; -#endif unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -1021,7 +1027,9 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) if (unlikely((page_count(page) - pagecnt_bias) > 1)) return false; #else - if (rx_buffer->page_offset > last_offset) +#define I40E_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048) + if (rx_buffer->page_offset > I40E_LAST_OFFSET) return false; #endif @@ -1055,9 +1063,9 @@ static void i40e_add_rx_frag(struct i40e_ring *rx_ring, unsigned int size) { #if (PAGE_SIZE < 8192) - unsigned int truesize = I40E_RXBUFFER_2048; + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = SKB_DATA_ALIGN(size); + unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring)); #endif skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, @@ -1116,7 +1124,7 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, { void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = I40E_RXBUFFER_2048; + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(size); #endif @@ -1166,6 +1174,51 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, } /** + * i40e_build_skb - Build skb around an existing buffer + * @rx_ring: Rx descriptor ring to transact packets on + * @rx_buffer: Rx buffer to pull data from + * @size: size of buffer to add to skb + * + * This function builds an skb around an existing Rx buffer, taking care + * to set up the skb correctly and avoid any memcpy overhead. + */ +static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *rx_buffer, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size); +#endif + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + /* build an skb around the page buffer */ + skb = build_skb(va - I40E_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; + + /* update pointers within the skb to store the data */ + skb_reserve(skb, I40E_SKB_PAD); + __skb_put(skb, size); + + /* buffer is used by skb, update page_offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + + return skb; +} + +/** * i40e_put_rx_buffer - Clean up used buffer and either recycle or free * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: rx buffer to pull data from @@ -1182,7 +1235,8 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + i40e_rx_pg_size(rx_ring), DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); __page_frag_cache_drain(rx_buffer->page, rx_buffer->pagecnt_bias); @@ -1267,10 +1321,6 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) * hardware wrote DD then the length will be non-zero */ qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> - I40E_RXD_QW1_LENGTH_PBUF_SHIFT; - if (!size) - break; /* This memory barrier is needed to keep us from reading * any other fields out of the rx_desc until we have @@ -1278,11 +1328,19 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ dma_rmb(); + size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> + I40E_RXD_QW1_LENGTH_PBUF_SHIFT; + if (!size) + break; + + i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb); rx_buffer = i40e_get_rx_buffer(rx_ring, size); /* retrieve a buffer from the ring */ if (skb) i40e_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = i40e_build_skb(rx_ring, rx_buffer, size); else skb = i40e_construct_skb(rx_ring, rx_buffer, size); @@ -1329,6 +1387,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; + i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); i40e_receive_skb(rx_ring, skb, vlan_tag); skb = NULL; @@ -2170,6 +2229,8 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, /* prefetch the data, we'll need it later */ prefetch(skb->data); + i40e_trace(xmit_frame_ring, skb, tx_ring); + count = i40e_xmit_descriptor_count(skb); if (i40e_chk_linearize(skb, count)) { if (__skb_linearize(skb)) { @@ -2237,6 +2298,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_OK; out_drop: + i40e_trace(xmit_frame_ring_drop, first->skb, tx_ring); dev_kfree_skb_any(first->skb); first->skb = NULL; return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 3bb4d732e467..901282c87cf6 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -106,6 +106,7 @@ enum i40e_dyn_idx_t { #define I40E_RXBUFFER_256 256 #define I40E_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ #define I40E_RXBUFFER_2048 2048 +#define I40E_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ #define I40E_MAX_RXBUFFER 9728 /* largest size for single descriptor */ /* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we @@ -121,6 +122,58 @@ enum i40e_dyn_idx_t { #define I40E_RX_DMA_ATTR \ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) +/* Attempt to maximize the headroom available for incoming frames. We + * use a 2K buffer for receives and need 1536/1534 to store the data for + * the frame. This leaves us with 512 bytes of room. From that we need + * to deduct the space needed for the shared info and the padding needed + * to IP align the frame. + * + * Note: For cache line sizes 256 or larger this value is going to end + * up negative. In these cases we should fall back to the legacy + * receive path. + */ +#if (PAGE_SIZE < 8192) +#define I40E_2K_TOO_SMALL_WITH_PADDING \ +((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048)) + +static inline int i40e_compute_pad(int rx_buf_len) +{ + int page_size, pad_size; + + page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); + pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len; + + return pad_size; +} + +static inline int i40e_skb_pad(void) +{ + int rx_buf_len; + + /* If a 2K buffer cannot handle a standard Ethernet frame then + * optimize padding for a 3K buffer instead of a 1.5K buffer. + * + * For a 3K buffer we need to add enough padding to allow for + * tailroom due to NET_IP_ALIGN possibly shifting us out of + * cache-line alignment. + */ + if (I40E_2K_TOO_SMALL_WITH_PADDING) + rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); + else + rx_buf_len = I40E_RXBUFFER_1536; + + /* if needed make room for NET_IP_ALIGN */ + rx_buf_len -= NET_IP_ALIGN; + + return i40e_compute_pad(rx_buf_len); +} + +#define I40E_SKB_PAD i40e_skb_pad() +#else +#define I40E_2K_TOO_SMALL_WITH_PADDING false +#define I40E_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#endif + /** * i40e_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format) @@ -327,7 +380,8 @@ struct i40e_ring { u8 packet_stride; u16 flags; -#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) +#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) +#define I40E_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) /* stats structs */ struct i40e_queue_stats stats; @@ -355,6 +409,21 @@ struct i40e_ring { */ } ____cacheline_internodealigned_in_smp; +static inline bool ring_uses_build_skb(struct i40e_ring *ring) +{ + return !!(ring->flags & I40E_RXR_FLAGS_BUILD_SKB_ENABLED); +} + +static inline void set_ring_build_skb_enabled(struct i40e_ring *ring) +{ + ring->flags |= I40E_RXR_FLAGS_BUILD_SKB_ENABLED; +} + +static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring) +{ + ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED; +} + enum i40e_latency_range { I40E_LOWEST_LATENCY = 0, I40E_LOW_LATENCY = 1, @@ -376,6 +445,17 @@ struct i40e_ring_container { #define i40e_for_each_ring(pos, head) \ for (pos = (head).ring; pos != NULL; pos = pos->next) +static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring->rx_buf_len > (PAGE_SIZE / 2)) + return 1; +#endif + return 0; +} + +#define i40e_rx_pg_size(_ring) (PAGE_SIZE << i40e_rx_pg_order(_ring)) + bool i40evf_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count); netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev); void i40evf_clean_tx_ring(struct i40e_ring *tx_ring); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 16bb88084bb9..bde7f24af1c6 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -78,6 +78,7 @@ enum i40e_debug_mask { I40E_DEBUG_DCB = 0x00000400, I40E_DEBUG_DIAG = 0x00000800, I40E_DEBUG_FD = 0x00001000, + I40E_DEBUG_PACKAGE = 0x00002000, I40E_DEBUG_AQ_MESSAGE = 0x01000000, I40E_DEBUG_AQ_DESCRIPTOR = 0x02000000, @@ -1396,4 +1397,83 @@ enum i40e_reset_type { #define I40E_FD_INSET_FLEX_WORD57_SHIFT 10 #define I40E_FD_INSET_FLEX_WORD57_MASK (0x1ULL << \ I40E_FD_INSET_FLEX_WORD57_SHIFT) + +/* Version format for PPP */ +struct i40e_ppp_version { + u8 major; + u8 minor; + u8 update; + u8 draft; +}; + +#define I40E_PPP_NAME_SIZE 32 + +/* Package header */ +struct i40e_package_header { + struct i40e_ppp_version version; + u32 segment_count; + u32 segment_offset[1]; +}; + +/* Generic segment header */ +struct i40e_generic_seg_header { +#define SEGMENT_TYPE_METADATA 0x00000001 +#define SEGMENT_TYPE_NOTES 0x00000002 +#define SEGMENT_TYPE_I40E 0x00000011 +#define SEGMENT_TYPE_X722 0x00000012 + u32 type; + struct i40e_ppp_version version; + u32 size; + char name[I40E_PPP_NAME_SIZE]; +}; + +struct i40e_metadata_segment { + struct i40e_generic_seg_header header; + struct i40e_ppp_version version; + u32 track_id; + char name[I40E_PPP_NAME_SIZE]; +}; + +struct i40e_device_id_entry { + u32 vendor_dev_id; + u32 sub_vendor_dev_id; +}; + +struct i40e_profile_segment { + struct i40e_generic_seg_header header; + struct i40e_ppp_version version; + char name[I40E_PPP_NAME_SIZE]; + u32 device_table_count; + struct i40e_device_id_entry device_table[1]; +}; + +struct i40e_section_table { + u32 section_count; + u32 section_offset[1]; +}; + +struct i40e_profile_section_header { + u16 tbl_size; + u16 data_end; + struct { +#define SECTION_TYPE_INFO 0x00000010 +#define SECTION_TYPE_MMIO 0x00000800 +#define SECTION_TYPE_AQ 0x00000801 +#define SECTION_TYPE_NOTE 0x80000000 +#define SECTION_TYPE_NAME 0x80000001 + u32 type; + u32 offset; + u32 size; + } section; +}; + +struct i40e_profile_info { + u32 track_id; + struct i40e_ppp_version version; + u8 op; +#define I40E_PPP_ADD_TRACKID 0x01 +#define I40E_PPP_REMOVE_TRACKID 0x02 + u8 reserved[7]; + u8 name[I40E_PPP_NAME_SIZE]; +}; #endif /* _I40E_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h index f431fbc4a3e7..c5ad0388c3d5 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h @@ -163,7 +163,8 @@ struct i40e_virtchnl_vsi_resource { #define I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF 0X00080000 -#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00100000 +#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP 0X00100000 +#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000 #define I40E_VF_BASE_MODE_OFFLOADS (I40E_VIRTCHNL_VF_OFFLOAD_L2 | \ I40E_VIRTCHNL_VF_OFFLOAD_VLAN | \ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index d61ecf655091..40f56e2335df 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -202,10 +202,8 @@ struct i40evf_adapter { u32 flags; #define I40EVF_FLAG_RX_CSUM_ENABLED BIT(0) -#define I40EVF_FLAG_IN_NETPOLL BIT(4) #define I40EVF_FLAG_IMIR_ENABLED BIT(5) #define I40EVF_FLAG_MQ_CAPABLE BIT(6) -#define I40EVF_FLAG_NEED_LINK_UPDATE BIT(7) #define I40EVF_FLAG_PF_COMMS_FAILED BIT(8) #define I40EVF_FLAG_RESET_PENDING BIT(9) #define I40EVF_FLAG_RESET_NEEDED BIT(10) @@ -222,7 +220,6 @@ struct i40evf_adapter { /* duplicates for common code */ #define I40E_FLAG_FDIR_ATR_ENABLED 0 #define I40E_FLAG_DCB_ENABLED 0 -#define I40E_FLAG_IN_NETPOLL I40EVF_FLAG_IN_NETPOLL #define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED #define I40E_FLAG_WB_ON_ITR_CAPABLE I40EVF_FLAG_WB_ON_ITR_CAPABLE #define I40E_FLAG_OUTER_UDP_CSUM_CAPABLE I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE @@ -253,7 +250,6 @@ struct i40evf_adapter { /* OS defined structs */ struct net_device *netdev; struct pci_dev *pdev; - struct net_device_stats net_stats; struct i40e_hw hw; /* defined in i40e_type.h */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index fb2811c23024..5915273c372f 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -27,6 +27,13 @@ #include "i40evf.h" #include "i40e_prototype.h" #include "i40evf_client.h" +/* All i40evf tracepoints are defined by the include below, which must + * be included exactly once across the whole kernel with + * CREATE_TRACE_POINTS defined + */ +#define CREATE_TRACE_POINTS +#include "i40e_trace.h" + static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter); static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter); static int i40evf_close(struct net_device *netdev); @@ -694,11 +701,18 @@ static void i40evf_configure_rx(struct i40evf_adapter *adapter) /* Legacy Rx will always default to a 2048 buffer size. */ #if (PAGE_SIZE < 8192) if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX)) { + /* For jumbo frames on systems with 4K pages we have to use + * an order 1 page, so we might as well increase the size + * of our Rx buffer to make better use of the available space + */ + rx_buf_len = I40E_RXBUFFER_3072; + /* We use a 1536 buffer size for configurations with * standard Ethernet mtu. On x86 this gives us enough room * for shared info and 192 bytes of padding. */ - if (netdev->mtu <= ETH_DATA_LEN) + if (!I40E_2K_TOO_SMALL_WITH_PADDING && + (netdev->mtu <= ETH_DATA_LEN)) rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN; } #endif @@ -706,6 +720,11 @@ static void i40evf_configure_rx(struct i40evf_adapter *adapter) for (i = 0; i < adapter->num_active_queues; i++) { adapter->rx_rings[i].tail = hw->hw_addr + I40E_QRX_TAIL1(i); adapter->rx_rings[i].rx_buf_len = rx_buf_len; + + if (adapter->flags & I40EVF_FLAG_LEGACY_RX) + clear_ring_build_skb_enabled(&adapter->rx_rings[i]); + else + set_ring_build_skb_enabled(&adapter->rx_rings[i]); } } @@ -2231,21 +2250,6 @@ static int i40evf_close(struct net_device *netdev) } /** - * i40evf_get_stats - Get System Network Statistics - * @netdev: network interface device structure - * - * Returns the address of the device statistics structure. - * The statistics are actually updated from the timer callback. - **/ -static struct net_device_stats *i40evf_get_stats(struct net_device *netdev) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - /* only return the current stats */ - return &adapter->net_stats; -} - -/** * i40evf_change_mtu - Change the Maximum Transfer Unit * @netdev: network interface device structure * @new_mtu: new value for maximum frame size @@ -2351,7 +2355,6 @@ static const struct net_device_ops i40evf_netdev_ops = { .ndo_open = i40evf_open, .ndo_stop = i40evf_close, .ndo_start_xmit = i40evf_xmit_frame, - .ndo_get_stats = i40evf_get_stats, .ndo_set_rx_mode = i40evf_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = i40evf_set_mac, @@ -2401,6 +2404,8 @@ int i40evf_process_config(struct i40evf_adapter *adapter) struct net_device *netdev = adapter->netdev; struct i40e_vsi *vsi = &adapter->vsi; int i; + netdev_features_t hw_enc_features; + netdev_features_t hw_features; /* got VF config message back from PF, now we can parse it */ for (i = 0; i < vfres->num_vsis; i++) { @@ -2412,46 +2417,52 @@ int i40evf_process_config(struct i40evf_adapter *adapter) return -ENODEV; } - netdev->hw_enc_features |= NETIF_F_SG | - NETIF_F_IP_CSUM | - NETIF_F_IPV6_CSUM | - NETIF_F_HIGHDMA | - NETIF_F_SOFT_FEATURES | - NETIF_F_TSO | - NETIF_F_TSO_ECN | - NETIF_F_TSO6 | + hw_enc_features = NETIF_F_SG | + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_HIGHDMA | + NETIF_F_SOFT_FEATURES | + NETIF_F_TSO | + NETIF_F_TSO_ECN | + NETIF_F_TSO6 | + NETIF_F_SCTP_CRC | + NETIF_F_RXHASH | + NETIF_F_RXCSUM | + 0; + + /* advertise to stack only if offloads for encapsulated packets is + * supported + */ + if (vfres->vf_offload_flags & I40E_VIRTCHNL_VF_OFFLOAD_ENCAP) { + hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_IPXIP4 | NETIF_F_GSO_IPXIP6 | - NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_PARTIAL | - NETIF_F_SCTP_CRC | - NETIF_F_RXHASH | - NETIF_F_RXCSUM | 0; - if (!(adapter->flags & I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE)) - netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; - - netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; + if (!(vfres->vf_offload_flags & + I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM)) + netdev->gso_partial_features |= + NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; + netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; + netdev->hw_enc_features |= hw_enc_features; + } /* record features VLANs can make use of */ - netdev->vlan_features |= netdev->hw_enc_features | - NETIF_F_TSO_MANGLEID; + netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID; /* Write features and hw_features separately to avoid polluting - * with, or dropping, features that are set when we registgered. + * with, or dropping, features that are set when we registered. */ - netdev->hw_features |= netdev->hw_enc_features; + hw_features = hw_enc_features; - netdev->features |= netdev->hw_enc_features | I40EVF_VLAN_FEATURES; - netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; + netdev->hw_features |= hw_features; - /* disable VLAN features if not supported */ - if (!(vfres->vf_offload_flags & I40E_VIRTCHNL_VF_OFFLOAD_VLAN)) - netdev->features ^= I40EVF_VLAN_FEATURES; + netdev->features |= hw_features | I40EVF_VLAN_FEATURES; adapter->vsi.id = adapter->vsi_res->vsi_id; @@ -2592,9 +2603,6 @@ static void i40evf_init_task(struct work_struct *work) goto err_alloc; } - if (hw->mac.type == I40E_MAC_X722_VF) - adapter->flags |= I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE; - if (i40evf_process_config(adapter)) goto err_alloc; adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 032be8d3928a..deb2cb8dac6b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -159,7 +159,9 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) I40E_VIRTCHNL_VF_OFFLOAD_RSS_REG | I40E_VIRTCHNL_VF_OFFLOAD_VLAN | I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR | - I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; + I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | + I40E_VIRTCHNL_VF_OFFLOAD_ENCAP | + I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; adapter->current_op = I40E_VIRTCHNL_OP_GET_VF_RESOURCES; adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG; @@ -958,17 +960,17 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, case I40E_VIRTCHNL_OP_GET_STATS: { struct i40e_eth_stats *stats = (struct i40e_eth_stats *)msg; - adapter->net_stats.rx_packets = stats->rx_unicast + - stats->rx_multicast + - stats->rx_broadcast; - adapter->net_stats.tx_packets = stats->tx_unicast + - stats->tx_multicast + - stats->tx_broadcast; - adapter->net_stats.rx_bytes = stats->rx_bytes; - adapter->net_stats.tx_bytes = stats->tx_bytes; - adapter->net_stats.tx_errors = stats->tx_errors; - adapter->net_stats.rx_dropped = stats->rx_discards; - adapter->net_stats.tx_dropped = stats->tx_discards; + netdev->stats.rx_packets = stats->rx_unicast + + stats->rx_multicast + + stats->rx_broadcast; + netdev->stats.tx_packets = stats->tx_unicast + + stats->tx_multicast + + stats->tx_broadcast; + netdev->stats.rx_bytes = stats->rx_bytes; + netdev->stats.tx_bytes = stats->tx_bytes; + netdev->stats.tx_errors = stats->tx_errors; + netdev->stats.rx_dropped = stats->rx_discards; + netdev->stats.tx_dropped = stats->tx_discards; adapter->current_stats = *stats; } break; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index b1ecc2627a5a..656ca8f69768 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -86,17 +86,62 @@ /* Supported Rx Buffer Sizes */ #define IXGBE_RXBUFFER_256 256 /* Used for skb receive header */ +#define IXGBE_RXBUFFER_1536 1536 #define IXGBE_RXBUFFER_2K 2048 #define IXGBE_RXBUFFER_3K 3072 #define IXGBE_RXBUFFER_4K 4096 #define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */ -#define IXGBE_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +/* Attempt to maximize the headroom available for incoming frames. We + * use a 2K buffer for receives and need 1536/1534 to store the data for + * the frame. This leaves us with 512 bytes of room. From that we need + * to deduct the space needed for the shared info and the padding needed + * to IP align the frame. + * + * Note: For cache line sizes 256 or larger this value is going to end + * up negative. In these cases we should fall back to the 3K + * buffers. + */ #if (PAGE_SIZE < 8192) -#define IXGBE_MAX_FRAME_BUILD_SKB \ - (SKB_WITH_OVERHEAD(IXGBE_RXBUFFER_2K) - IXGBE_SKB_PAD) +#define IXGBE_MAX_2K_FRAME_BUILD_SKB (IXGBE_RXBUFFER_1536 - NET_IP_ALIGN) +#define IXGBE_2K_TOO_SMALL_WITH_PADDING \ +((NET_SKB_PAD + IXGBE_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IXGBE_RXBUFFER_2K)) + +static inline int ixgbe_compute_pad(int rx_buf_len) +{ + int page_size, pad_size; + + page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); + pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len; + + return pad_size; +} + +static inline int ixgbe_skb_pad(void) +{ + int rx_buf_len; + + /* If a 2K buffer cannot handle a standard Ethernet frame then + * optimize padding for a 3K buffer instead of a 1.5K buffer. + * + * For a 3K buffer we need to add enough padding to allow for + * tailroom due to NET_IP_ALIGN possibly shifting us out of + * cache-line alignment. + */ + if (IXGBE_2K_TOO_SMALL_WITH_PADDING) + rx_buf_len = IXGBE_RXBUFFER_3K + SKB_DATA_ALIGN(NET_IP_ALIGN); + else + rx_buf_len = IXGBE_RXBUFFER_1536; + + /* if needed make room for NET_IP_ALIGN */ + rx_buf_len -= NET_IP_ALIGN; + + return ixgbe_compute_pad(rx_buf_len); +} + +#define IXGBE_SKB_PAD ixgbe_skb_pad() #else -#define IXGBE_MAX_FRAME_BUILD_SKB IXGBE_RXBUFFER_2K +#define IXGBE_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) #endif /* @@ -361,7 +406,7 @@ static inline unsigned int ixgbe_rx_bufsz(struct ixgbe_ring *ring) return IXGBE_RXBUFFER_3K; #if (PAGE_SIZE < 8192) if (ring_uses_build_skb(ring)) - return IXGBE_MAX_FRAME_BUILD_SKB; + return IXGBE_MAX_2K_FRAME_BUILD_SKB; #endif return IXGBE_RXBUFFER_2K; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 0da0752fedef..59730ede4746 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -179,6 +179,7 @@ static u32 ixgbe_get_supported_10gtypes(struct ixgbe_hw *hw) case IXGBE_DEV_ID_82598_BX: case IXGBE_DEV_ID_82599_KR: case IXGBE_DEV_ID_X550EM_X_KR: + case IXGBE_DEV_ID_X550EM_X_XFI: return SUPPORTED_10000baseKR_Full; default: return SUPPORTED_10000baseKX4_Full | diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 852a2e7e25ed..afff2ca7f8c0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -131,6 +131,7 @@ static const struct pci_device_id ixgbe_pci_tbl[] = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T), board_X550}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T1), board_X550}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KX4), board_X550EM_x}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_XFI), board_X550EM_x}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KR), board_X550EM_x}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_10G_T), board_X550EM_x}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_SFP), board_X550EM_x}, @@ -508,7 +509,7 @@ static const struct ixgbe_reg_info ixgbe_reg_info_tbl[] = { */ static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo) { - int i = 0, j = 0; + int i; char rname[16]; u32 regs[64]; @@ -570,17 +571,21 @@ static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo) regs[i] = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i)); break; default: - pr_info("%-15s %08x\n", reginfo->name, - IXGBE_READ_REG(hw, reginfo->ofs)); + pr_info("%-15s %08x\n", + reginfo->name, IXGBE_READ_REG(hw, reginfo->ofs)); return; } - for (i = 0; i < 8; i++) { - snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i*8, i*8+7); - pr_err("%-15s", rname); + i = 0; + while (i < 64) { + int j; + char buf[9 * 8 + 1]; + char *p = buf; + + snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i, i + 7); for (j = 0; j < 8; j++) - pr_cont(" %08x", regs[i*8+j]); - pr_cont("\n"); + p += sprintf(p, " %08x", regs[i++]); + pr_err("%-15s%s\n", rname, buf); } } @@ -601,7 +606,6 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) struct ixgbe_ring *rx_ring; union ixgbe_adv_rx_desc *rx_desc; struct ixgbe_rx_buffer *rx_buffer_info; - u32 staterr; int i = 0; if (!netif_msg_hw(adapter)) @@ -701,7 +705,18 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) tx_buffer = &tx_ring->tx_buffer_info[i]; u0 = (struct my_u0 *)tx_desc; if (dma_unmap_len(tx_buffer, len) > 0) { - pr_info("T [0x%03X] %016llX %016llX %016llX %08X %p %016llX %p", + const char *ring_desc; + + if (i == tx_ring->next_to_use && + i == tx_ring->next_to_clean) + ring_desc = " NTC/U"; + else if (i == tx_ring->next_to_use) + ring_desc = " NTU"; + else if (i == tx_ring->next_to_clean) + ring_desc = " NTC"; + else + ring_desc = ""; + pr_info("T [0x%03X] %016llX %016llX %016llX %08X %p %016llX %p%s", i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), @@ -709,16 +724,8 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) dma_unmap_len(tx_buffer, len), tx_buffer->next_to_watch, (u64)tx_buffer->time_stamp, - tx_buffer->skb); - if (i == tx_ring->next_to_use && - i == tx_ring->next_to_clean) - pr_cont(" NTC/U\n"); - else if (i == tx_ring->next_to_use) - pr_cont(" NTU\n"); - else if (i == tx_ring->next_to_clean) - pr_cont(" NTC\n"); - else - pr_cont("\n"); + tx_buffer->skb, + ring_desc); if (netif_msg_pktdata(adapter) && tx_buffer->skb) @@ -797,34 +804,44 @@ rx_ring_summary: pr_info("------------------------------------\n"); pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index); pr_info("------------------------------------\n"); - pr_info("%s%s%s", + pr_info("%s%s%s\n", "R [desc] [ PktBuf A0] ", "[ HeadBuf DD] [bi->dma ] [bi->skb ] ", - "<-- Adv Rx Read format\n"); - pr_info("%s%s%s", + "<-- Adv Rx Read format"); + pr_info("%s%s%s\n", "RWB[desc] [PcsmIpSHl PtRs] ", "[vl er S cks ln] ---------------- [bi->skb ] ", - "<-- Adv Rx Write-Back format\n"); + "<-- Adv Rx Write-Back format"); for (i = 0; i < rx_ring->count; i++) { + const char *ring_desc; + + if (i == rx_ring->next_to_use) + ring_desc = " NTU"; + else if (i == rx_ring->next_to_clean) + ring_desc = " NTC"; + else + ring_desc = ""; + rx_buffer_info = &rx_ring->rx_buffer_info[i]; rx_desc = IXGBE_RX_DESC(rx_ring, i); u0 = (struct my_u0 *)rx_desc; - staterr = le32_to_cpu(rx_desc->wb.upper.status_error); - if (staterr & IXGBE_RXD_STAT_DD) { + if (rx_desc->wb.upper.length) { /* Descriptor Done */ - pr_info("RWB[0x%03X] %016llX " - "%016llX ---------------- %p", i, + pr_info("RWB[0x%03X] %016llX %016llX ---------------- %p%s\n", + i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), - rx_buffer_info->skb); + rx_buffer_info->skb, + ring_desc); } else { - pr_info("R [0x%03X] %016llX " - "%016llX %016llX %p", i, + pr_info("R [0x%03X] %016llX %016llX %016llX %p%s\n", + i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), (u64)rx_buffer_info->dma, - rx_buffer_info->skb); + rx_buffer_info->skb, + ring_desc); if (netif_msg_pktdata(adapter) && rx_buffer_info->dma) { @@ -835,14 +852,6 @@ rx_ring_summary: ixgbe_rx_bufsz(rx_ring), true); } } - - if (i == rx_ring->next_to_use) - pr_cont(" NTU\n"); - else if (i == rx_ring->next_to_clean) - pr_cont(" NTC\n"); - else - pr_cont("\n"); - } } } @@ -3802,7 +3811,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, /* Limit the maximum frame size so we don't overrun the skb */ if (ring_uses_build_skb(ring) && !test_bit(__IXGBE_RX_3K_BUFFER, &ring->state)) - rxdctl |= IXGBE_MAX_FRAME_BUILD_SKB | + rxdctl |= IXGBE_MAX_2K_FRAME_BUILD_SKB | IXGBE_RXDCTL_RLPML_EN; #endif } @@ -3972,8 +3981,8 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter) if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); - if ((max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)) || - (max_frame > IXGBE_MAX_FRAME_BUILD_SKB)) + if (IXGBE_2K_TOO_SMALL_WITH_PADDING || + (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN))) set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); #endif } @@ -5944,10 +5953,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, /* assign number of SR-IOV VFs */ if (hw->mac.type != ixgbe_mac_82598EB) { if (max_vfs > IXGBE_MAX_VFS_DRV_LIMIT) { - adapter->num_vfs = 0; + max_vfs = 0; e_dev_warn("max_vfs parameter out of range. Not assigning any SR-IOV VFs\n"); - } else { - adapter->num_vfs = max_vfs; } } #endif /* CONFIG_PCI_IOV */ @@ -9810,7 +9817,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ixgbe_init_mbx_params_pf(hw); hw->mbx.ops = ii->mbx_ops; pci_sriov_set_totalvfs(pdev, IXGBE_MAX_VFS_DRV_LIMIT); - ixgbe_enable_sriov(adapter); + ixgbe_enable_sriov(adapter, max_vfs); skip_sriov: #endif diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index e55b2602f371..654a402f0e9e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -792,7 +792,8 @@ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw, hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_10_FULL; /* Setup link based on the new speed settings */ - hw->phy.ops.setup_link(hw); + if (hw->phy.ops.setup_link) + hw->phy.ops.setup_link(hw); return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 044cb44747cf..102ca937ddb4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -46,88 +46,96 @@ #include "ixgbe_sriov.h" #ifdef CONFIG_PCI_IOV -static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter) +static inline void ixgbe_alloc_vf_macvlans(struct ixgbe_adapter *adapter, + unsigned int num_vfs) { struct ixgbe_hw *hw = &adapter->hw; - int num_vf_macvlans, i; struct vf_macvlans *mv_list; - - adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED; - e_info(probe, "SR-IOV enabled with %d VFs\n", adapter->num_vfs); - - /* Enable VMDq flag so device will be set in VM mode */ - adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED; - if (!adapter->ring_feature[RING_F_VMDQ].limit) - adapter->ring_feature[RING_F_VMDQ].limit = 1; - adapter->ring_feature[RING_F_VMDQ].offset = adapter->num_vfs; + int num_vf_macvlans, i; num_vf_macvlans = hw->mac.num_rar_entries - - (IXGBE_MAX_PF_MACVLANS + 1 + adapter->num_vfs); + (IXGBE_MAX_PF_MACVLANS + 1 + num_vfs); + if (!num_vf_macvlans) + return; - adapter->mv_list = mv_list = kcalloc(num_vf_macvlans, - sizeof(struct vf_macvlans), - GFP_KERNEL); + mv_list = kcalloc(num_vf_macvlans, sizeof(struct vf_macvlans), + GFP_KERNEL); if (mv_list) { /* Initialize list of VF macvlans */ INIT_LIST_HEAD(&adapter->vf_mvs.l); for (i = 0; i < num_vf_macvlans; i++) { - mv_list->vf = -1; - mv_list->free = true; - list_add(&mv_list->l, &adapter->vf_mvs.l); - mv_list++; + mv_list[i].vf = -1; + mv_list[i].free = true; + list_add(&mv_list[i].l, &adapter->vf_mvs.l); } + adapter->mv_list = mv_list; } +} + +static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter, + unsigned int num_vfs) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + + adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED; + + /* Enable VMDq flag so device will be set in VM mode */ + adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED; + if (!adapter->ring_feature[RING_F_VMDQ].limit) + adapter->ring_feature[RING_F_VMDQ].limit = 1; + + /* Allocate memory for per VF control structures */ + adapter->vfinfo = kcalloc(num_vfs, sizeof(struct vf_data_storage), + GFP_KERNEL); + if (!adapter->vfinfo) + return -ENOMEM; + + adapter->num_vfs = num_vfs; + + ixgbe_alloc_vf_macvlans(adapter, num_vfs); + adapter->ring_feature[RING_F_VMDQ].offset = num_vfs; /* Initialize default switching mode VEB */ IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN); adapter->bridge_mode = BRIDGE_MODE_VEB; - /* If call to enable VFs succeeded then allocate memory - * for per VF control structures. - */ - adapter->vfinfo = - kcalloc(adapter->num_vfs, - sizeof(struct vf_data_storage), GFP_KERNEL); - if (adapter->vfinfo) { - /* limit trafffic classes based on VFs enabled */ - if ((adapter->hw.mac.type == ixgbe_mac_82599EB) && - (adapter->num_vfs < 16)) { - adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS; - adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS; - } else if (adapter->num_vfs < 32) { - adapter->dcb_cfg.num_tcs.pg_tcs = 4; - adapter->dcb_cfg.num_tcs.pfc_tcs = 4; - } else { - adapter->dcb_cfg.num_tcs.pg_tcs = 1; - adapter->dcb_cfg.num_tcs.pfc_tcs = 1; - } - - /* Disable RSC when in SR-IOV mode */ - adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE | - IXGBE_FLAG2_RSC_ENABLED); + /* limit trafffic classes based on VFs enabled */ + if ((adapter->hw.mac.type == ixgbe_mac_82599EB) && (num_vfs < 16)) { + adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS; + adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS; + } else if (num_vfs < 32) { + adapter->dcb_cfg.num_tcs.pg_tcs = 4; + adapter->dcb_cfg.num_tcs.pfc_tcs = 4; + } else { + adapter->dcb_cfg.num_tcs.pg_tcs = 1; + adapter->dcb_cfg.num_tcs.pfc_tcs = 1; + } - for (i = 0; i < adapter->num_vfs; i++) { - /* enable spoof checking for all VFs */ - adapter->vfinfo[i].spoofchk_enabled = true; + /* Disable RSC when in SR-IOV mode */ + adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE | + IXGBE_FLAG2_RSC_ENABLED); - /* We support VF RSS querying only for 82599 and x540 - * devices at the moment. These devices share RSS - * indirection table and RSS hash key with PF therefore - * we want to disable the querying by default. - */ - adapter->vfinfo[i].rss_query_enabled = 0; + for (i = 0; i < num_vfs; i++) { + /* enable spoof checking for all VFs */ + adapter->vfinfo[i].spoofchk_enabled = true; - /* Untrust all VFs */ - adapter->vfinfo[i].trusted = false; + /* We support VF RSS querying only for 82599 and x540 + * devices at the moment. These devices share RSS + * indirection table and RSS hash key with PF therefore + * we want to disable the querying by default. + */ + adapter->vfinfo[i].rss_query_enabled = 0; - /* set the default xcast mode */ - adapter->vfinfo[i].xcast_mode = IXGBEVF_XCAST_MODE_NONE; - } + /* Untrust all VFs */ + adapter->vfinfo[i].trusted = false; - return 0; + /* set the default xcast mode */ + adapter->vfinfo[i].xcast_mode = IXGBEVF_XCAST_MODE_NONE; } - return -ENOMEM; + e_info(probe, "SR-IOV enabled with %d VFs\n", num_vfs); + return 0; } /** @@ -165,12 +173,13 @@ static void ixgbe_get_vfs(struct ixgbe_adapter *adapter) /* Note this function is called when the user wants to enable SR-IOV * VFs using the now deprecated module parameter */ -void ixgbe_enable_sriov(struct ixgbe_adapter *adapter) +void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, unsigned int max_vfs) { int pre_existing_vfs = 0; + unsigned int num_vfs; pre_existing_vfs = pci_num_vf(adapter->pdev); - if (!pre_existing_vfs && !adapter->num_vfs) + if (!pre_existing_vfs && !max_vfs) return; /* If there are pre-existing VFs then we have to force @@ -180,7 +189,7 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter) * have been created via the new PCI SR-IOV sysfs interface. */ if (pre_existing_vfs) { - adapter->num_vfs = pre_existing_vfs; + num_vfs = pre_existing_vfs; dev_warn(&adapter->pdev->dev, "Virtual Functions already enabled for this device - Please reload all VF drivers to avoid spoofed packet errors\n"); } else { @@ -192,17 +201,16 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter) * physical function. If the user requests greater than * 63 VFs then it is an error - reset to default of zero. */ - adapter->num_vfs = min_t(unsigned int, adapter->num_vfs, IXGBE_MAX_VFS_DRV_LIMIT); + num_vfs = min_t(unsigned int, max_vfs, IXGBE_MAX_VFS_DRV_LIMIT); - err = pci_enable_sriov(adapter->pdev, adapter->num_vfs); + err = pci_enable_sriov(adapter->pdev, num_vfs); if (err) { e_err(probe, "Failed to enable PCI sriov: %d\n", err); - adapter->num_vfs = 0; return; } } - if (!__ixgbe_enable_sriov(adapter)) { + if (!__ixgbe_enable_sriov(adapter, num_vfs)) { ixgbe_get_vfs(adapter); return; } @@ -298,6 +306,7 @@ static int ixgbe_pci_sriov_enable(struct pci_dev *dev, int num_vfs) #ifdef CONFIG_PCI_IOV struct ixgbe_adapter *adapter = pci_get_drvdata(dev); int err = 0; + u8 num_tc; int i; int pre_existing_vfs = pci_num_vf(dev); @@ -310,23 +319,41 @@ static int ixgbe_pci_sriov_enable(struct pci_dev *dev, int num_vfs) return err; /* While the SR-IOV capability structure reports total VFs to be 64, - * we have to limit the actual number allocated based on two factors. + * we limit the actual number allocated as below based on two factors. + * Num_TCs MAX_VFs + * 1 63 + * <=4 31 + * >4 15 * First, we reserve some transmit/receive resources for the PF. * Second, VMDQ also uses the same pools that SR-IOV does. We need to * account for this, so that we don't accidentally allocate more VFs * than we have available pools. The PCI bus driver already checks for * other values out of range. */ - if ((num_vfs + adapter->num_rx_pools) > IXGBE_MAX_VF_FUNCTIONS) - return -EPERM; + num_tc = netdev_get_num_tc(adapter->netdev); - adapter->num_vfs = num_vfs; + if (num_tc > 4) { + if ((num_vfs + adapter->num_rx_pools) > IXGBE_MAX_VFS_8TC) { + e_dev_err("Currently the device is configured with %d TCs, Creating more than %d VFs is not allowed\n", num_tc, IXGBE_MAX_VFS_8TC); + return -EPERM; + } + } else if ((num_tc > 1) && (num_tc <= 4)) { + if ((num_vfs + adapter->num_rx_pools) > IXGBE_MAX_VFS_4TC) { + e_dev_err("Currently the device is configured with %d TCs, Creating more than %d VFs is not allowed\n", num_tc, IXGBE_MAX_VFS_4TC); + return -EPERM; + } + } else { + if ((num_vfs + adapter->num_rx_pools) > IXGBE_MAX_VFS_1TC) { + e_dev_err("Currently the device is configured with %d TCs, Creating more than %d VFs is not allowed\n", num_tc, IXGBE_MAX_VFS_1TC); + return -EPERM; + } + } - err = __ixgbe_enable_sriov(adapter); + err = __ixgbe_enable_sriov(adapter, num_vfs); if (err) return err; - for (i = 0; i < adapter->num_vfs; i++) + for (i = 0; i < num_vfs; i++) ixgbe_vf_configuration(dev, (i | 0x10000000)); /* reset before enabling SRIOV to avoid mailbox issues */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h index 0c7977d27b71..cf67b9b18ed7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h @@ -33,6 +33,9 @@ * 63 (IXGBE_MAX_VF_FUNCTIONS - 1) */ #define IXGBE_MAX_VFS_DRV_LIMIT (IXGBE_MAX_VF_FUNCTIONS - 1) +#define IXGBE_MAX_VFS_1TC IXGBE_MAX_VF_FUNCTIONS +#define IXGBE_MAX_VFS_4TC 32 +#define IXGBE_MAX_VFS_8TC 16 #ifdef CONFIG_PCI_IOV void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter); @@ -56,7 +59,7 @@ int ixgbe_ndo_get_vf_config(struct net_device *netdev, void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter); int ixgbe_disable_sriov(struct ixgbe_adapter *adapter); #ifdef CONFIG_PCI_IOV -void ixgbe_enable_sriov(struct ixgbe_adapter *adapter); +void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, unsigned int max_vfs); #endif int ixgbe_pci_sriov_configure(struct pci_dev *dev, int num_vfs); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 1d07f2ead914..2f06e4d9208d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -85,6 +85,7 @@ #define IXGBE_DEV_ID_X550EM_X_SFP 0x15AC #define IXGBE_DEV_ID_X550EM_X_10G_T 0x15AD #define IXGBE_DEV_ID_X550EM_X_1G_T 0x15AE +#define IXGBE_DEV_ID_X550EM_X_XFI 0x15B0 #define IXGBE_DEV_ID_X550EM_A_KR 0x15C2 #define IXGBE_DEV_ID_X550EM_A_KR_L 0x15C3 #define IXGBE_DEV_ID_X550EM_A_SFP_N 0x15C4 @@ -1387,9 +1388,6 @@ struct ixgbe_thermal_sensor_data { #define ATH_PHY_ID 0x03429050 #define AQ_FW_REV 0x20 -/* PHY Types */ -#define IXGBE_M88E1145_E_PHY_ID 0x01410CD0 - /* Special PHY Init Routine */ #define IXGBE_PHY_INIT_OFFSET_NL 0x002B #define IXGBE_PHY_INIT_END_NL 0xFFFF @@ -3128,6 +3126,7 @@ enum ixgbe_phy_type { ixgbe_phy_aq, ixgbe_phy_x550em_kr, ixgbe_phy_x550em_kx4, + ixgbe_phy_x550em_xfi, ixgbe_phy_x550em_ext_t, ixgbe_phy_cu_unknown, ixgbe_phy_qt, @@ -3754,15 +3753,6 @@ struct ixgbe_info { #define IXGBE_KRM_TX_COEFF_CTRL_1_CZERO_EN BIT(3) #define IXGBE_KRM_TX_COEFF_CTRL_1_OVRRD_EN BIT(31) -#define IXGBE_KX4_LINK_CNTL_1 0x4C -#define IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX BIT(16) -#define IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX4 BIT(17) -#define IXGBE_KX4_LINK_CNTL_1_TETH_EEE_CAP_KX BIT(24) -#define IXGBE_KX4_LINK_CNTL_1_TETH_EEE_CAP_KX4 BIT(25) -#define IXGBE_KX4_LINK_CNTL_1_TETH_AN_ENABLE BIT(29) -#define IXGBE_KX4_LINK_CNTL_1_TETH_FORCE_LINK_UP BIT(30) -#define IXGBE_KX4_LINK_CNTL_1_TETH_AN_RESTART BIT(31) - #define IXGBE_SB_IOSF_INDIRECT_CTRL 0x00011144 #define IXGBE_SB_IOSF_INDIRECT_DATA 0x00011148 @@ -3779,12 +3769,14 @@ struct ixgbe_info { #define IXGBE_SB_IOSF_CTRL_BUSY_SHIFT 31 #define IXGBE_SB_IOSF_CTRL_BUSY BIT(IXGBE_SB_IOSF_CTRL_BUSY_SHIFT) #define IXGBE_SB_IOSF_TARGET_KR_PHY 0 -#define IXGBE_SB_IOSF_TARGET_KX4_UNIPHY 1 -#define IXGBE_SB_IOSF_TARGET_KX4_PCS0 2 -#define IXGBE_SB_IOSF_TARGET_KX4_PCS1 3 #define IXGBE_NW_MNG_IF_SEL 0x00011178 #define IXGBE_NW_MNG_IF_SEL_MDIO_ACT BIT(1) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_10M BIT(17) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_100M BIT(18) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_1G BIT(19) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_2_5G BIT(20) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_10G BIT(21) #define IXGBE_NW_MNG_IF_SEL_ENABLE_10_100M BIT(23) #define IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE BIT(24) #define IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT 3 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 200f847fd8f3..2658394599e4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -320,6 +320,9 @@ static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw) case IXGBE_DEV_ID_X550EM_X_KX4: hw->phy.type = ixgbe_phy_x550em_kx4; break; + case IXGBE_DEV_ID_X550EM_X_XFI: + hw->phy.type = ixgbe_phy_x550em_xfi; + break; case IXGBE_DEV_ID_X550EM_X_KR: case IXGBE_DEV_ID_X550EM_A_KR: case IXGBE_DEV_ID_X550EM_A_KR_L: @@ -334,6 +337,16 @@ static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw) case IXGBE_DEV_ID_X550EM_X_1G_T: case IXGBE_DEV_ID_X550EM_X_10G_T: return ixgbe_identify_phy_generic(hw); + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + hw->phy.type = ixgbe_phy_fw; + hw->phy.ops.read_reg = NULL; + hw->phy.ops.write_reg = NULL; + if (hw->bus.lan_id) + hw->phy.phy_semaphore_mask |= IXGBE_GSSR_PHY1_SM; + else + hw->phy.phy_semaphore_mask |= IXGBE_GSSR_PHY0_SM; + break; default: break; } @@ -2215,8 +2228,38 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw, else *speed = IXGBE_LINK_SPEED_10GB_FULL; } else { - *speed = IXGBE_LINK_SPEED_10GB_FULL | - IXGBE_LINK_SPEED_1GB_FULL; + switch (hw->phy.type) { + case ixgbe_phy_x550em_kx4: + *speed = IXGBE_LINK_SPEED_1GB_FULL | + IXGBE_LINK_SPEED_2_5GB_FULL | + IXGBE_LINK_SPEED_10GB_FULL; + break; + case ixgbe_phy_x550em_xfi: + *speed = IXGBE_LINK_SPEED_1GB_FULL | + IXGBE_LINK_SPEED_10GB_FULL; + break; + case ixgbe_phy_sgmii: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + case ixgbe_phy_x550em_kr: + if (hw->mac.type == ixgbe_mac_x550em_a) { + /* check different backplane modes */ + if (hw->phy.nw_mng_if_sel & + IXGBE_NW_MNG_IF_SEL_PHY_SPEED_2_5G) { + *speed = IXGBE_LINK_SPEED_2_5GB_FULL; + break; + } else if (hw->device_id == + IXGBE_DEV_ID_X550EM_A_KR_L) { + *speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + } + } + /* fall through */ + default: + *speed = IXGBE_LINK_SPEED_10GB_FULL | + IXGBE_LINK_SPEED_1GB_FULL; + break; + } *autoneg = true; } return 0; @@ -2473,44 +2516,6 @@ static s32 ixgbe_setup_kr_speed_x550em(struct ixgbe_hw *hw, return ixgbe_restart_an_internal_phy_x550em(hw); } -/** ixgbe_setup_kx4_x550em - Configure the KX4 PHY. - * @hw: pointer to hardware structure - * - * Configures the integrated KX4 PHY. - **/ -static s32 ixgbe_setup_kx4_x550em(struct ixgbe_hw *hw) -{ - s32 status; - u32 reg_val; - - status = hw->mac.ops.read_iosf_sb_reg(hw, IXGBE_KX4_LINK_CNTL_1, - IXGBE_SB_IOSF_TARGET_KX4_PCS0 + - hw->bus.lan_id, ®_val); - if (status) - return status; - - reg_val &= ~(IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX4 | - IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX); - - reg_val |= IXGBE_KX4_LINK_CNTL_1_TETH_AN_ENABLE; - - /* Advertise 10G support. */ - if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) - reg_val |= IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX4; - - /* Advertise 1G support. */ - if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) - reg_val |= IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX; - - /* Restart auto-negotiation. */ - reg_val |= IXGBE_KX4_LINK_CNTL_1_TETH_AN_RESTART; - status = hw->mac.ops.write_iosf_sb_reg(hw, IXGBE_KX4_LINK_CNTL_1, - IXGBE_SB_IOSF_TARGET_KX4_PCS0 + - hw->bus.lan_id, reg_val); - - return status; -} - /** * ixgbe_setup_kr_x550em - Configure the KR PHY * @hw: pointer to hardware structure @@ -2521,6 +2526,9 @@ static s32 ixgbe_setup_kr_x550em(struct ixgbe_hw *hw) if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_2_5GB_FULL) return 0; + if (ixgbe_check_reset_blocked(hw)) + return 0; + return ixgbe_setup_kr_speed_x550em(hw, hw->phy.autoneg_advertised); } @@ -3134,7 +3142,7 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) /* Set functions pointers based on phy type */ switch (hw->phy.type) { case ixgbe_phy_x550em_kx4: - phy->ops.setup_link = ixgbe_setup_kx4_x550em; + phy->ops.setup_link = NULL; phy->ops.read_reg = ixgbe_read_phy_reg_x550em; phy->ops.write_reg = ixgbe_write_phy_reg_x550em; break; @@ -3143,6 +3151,12 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) phy->ops.read_reg = ixgbe_read_phy_reg_x550em; phy->ops.write_reg = ixgbe_write_phy_reg_x550em; break; + case ixgbe_phy_x550em_xfi: + /* link is managed by HW */ + phy->ops.setup_link = NULL; + phy->ops.read_reg = ixgbe_read_phy_reg_x550em; + phy->ops.write_reg = ixgbe_write_phy_reg_x550em; + break; case ixgbe_phy_x550em_ext_t: /* Save NW management interface connected on board. This is used * to determine internal PHY mode @@ -3164,6 +3178,9 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) phy->ops.handle_lasi = ixgbe_handle_lasi_ext_t_x550em; phy->ops.reset = ixgbe_reset_phy_t_X550em; break; + case ixgbe_phy_sgmii: + phy->ops.setup_link = NULL; + break; case ixgbe_phy_fw: phy->ops.setup_link = ixgbe_setup_fw_link; phy->ops.reset = ixgbe_reset_phy_fw; @@ -3193,6 +3210,7 @@ static enum ixgbe_media_type ixgbe_get_media_type_X550em(struct ixgbe_hw *hw) /* Fallthrough */ case IXGBE_DEV_ID_X550EM_X_KR: case IXGBE_DEV_ID_X550EM_X_KX4: + case IXGBE_DEV_ID_X550EM_X_XFI: case IXGBE_DEV_ID_X550EM_A_KR: case IXGBE_DEV_ID_X550EM_A_KR_L: media_type = ixgbe_media_type_backplane; @@ -3780,7 +3798,7 @@ static struct ixgbe_mac_operations mac_ops_x550em_a = { .get_media_type = ixgbe_get_media_type_X550em, .get_san_mac_addr = NULL, .get_wwn_prefix = NULL, - .setup_link = NULL, /* defined later */ + .setup_link = &ixgbe_setup_mac_link_X540, .get_link_capabilities = ixgbe_get_link_capabilities_X550em, .get_bus_info = ixgbe_get_bus_info_X550em, .setup_sfp = ixgbe_setup_sfp_modules_X550em, diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index 1f6c0ecd50bb..6bf740945260 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -91,18 +91,18 @@ static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = { #define IXGBEVF_TEST_LEN (sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN) -static int ixgbevf_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int ixgbevf_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 link_speed = 0; bool link_up; - ecmd->supported = SUPPORTED_10000baseT_Full; - ecmd->autoneg = AUTONEG_DISABLE; - ecmd->transceiver = XCVR_DUMMY1; - ecmd->port = -1; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full); + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = -1; hw->mac.get_link_status = 1; hw->mac.ops.check_link(hw, &link_speed, &link_up, false); @@ -122,11 +122,11 @@ static int ixgbevf_get_settings(struct net_device *netdev, break; } - ethtool_cmd_speed_set(ecmd, speed); - ecmd->duplex = DUPLEX_FULL; + cmd->base.speed = speed; + cmd->base.duplex = DUPLEX_FULL; } else { - ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); - ecmd->duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } return 0; @@ -885,7 +885,6 @@ static int ixgbevf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, } static const struct ethtool_ops ixgbevf_ethtool_ops = { - .get_settings = ixgbevf_get_settings, .get_drvinfo = ixgbevf_get_drvinfo, .get_regs_len = ixgbevf_get_regs_len, .get_regs = ixgbevf_get_regs, @@ -905,6 +904,7 @@ static const struct ethtool_ops ixgbevf_ethtool_ops = { .get_rxfh_indir_size = ixgbevf_get_rxfh_indir_size, .get_rxfh_key_size = ixgbevf_get_rxfh_key_size, .get_rxfh = ixgbevf_get_rxfh, + .get_link_ksettings = ixgbevf_get_link_ksettings, }; void ixgbevf_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index a0d1b084ecec..90a60b98c28e 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -53,7 +53,7 @@ struct orion_mdio_dev { struct mutex lock; void __iomem *regs; - struct clk *clk; + struct clk *clk[3]; /* * If we have access to the error interrupt pin (which is * somewhat misnamed as it not only reflects internal errors @@ -187,7 +187,7 @@ static int orion_mdio_probe(struct platform_device *pdev) struct resource *r; struct mii_bus *bus; struct orion_mdio_dev *dev; - int ret; + int i, ret; r = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!r) { @@ -216,11 +216,20 @@ static int orion_mdio_probe(struct platform_device *pdev) init_waitqueue_head(&dev->smi_busy_wait); - dev->clk = devm_clk_get(&pdev->dev, NULL); - if (!IS_ERR(dev->clk)) - clk_prepare_enable(dev->clk); + for (i = 0; i < ARRAY_SIZE(dev->clk); i++) { + dev->clk[i] = of_clk_get(pdev->dev.of_node, i); + if (IS_ERR(dev->clk[i])) + break; + clk_prepare_enable(dev->clk[i]); + } dev->err_interrupt = platform_get_irq(pdev, 0); + if (dev->err_interrupt > 0 && + resource_size(r) < MVMDIO_ERR_INT_MASK + 4) { + dev_err(&pdev->dev, + "disabling interrupt, resource size is too small\n"); + dev->err_interrupt = 0; + } if (dev->err_interrupt > 0) { ret = devm_request_irq(&pdev->dev, dev->err_interrupt, orion_mdio_err_irq, @@ -251,8 +260,16 @@ static int orion_mdio_probe(struct platform_device *pdev) return 0; out_mdio: - if (!IS_ERR(dev->clk)) - clk_disable_unprepare(dev->clk); + if (dev->err_interrupt > 0) + writel(0, dev->regs + MVMDIO_ERR_INT_MASK); + + for (i = 0; i < ARRAY_SIZE(dev->clk); i++) { + if (IS_ERR(dev->clk[i])) + break; + clk_disable_unprepare(dev->clk[i]); + clk_put(dev->clk[i]); + } + return ret; } @@ -260,11 +277,18 @@ static int orion_mdio_remove(struct platform_device *pdev) { struct mii_bus *bus = platform_get_drvdata(pdev); struct orion_mdio_dev *dev = bus->priv; + int i; - writel(0, dev->regs + MVMDIO_ERR_INT_MASK); + if (dev->err_interrupt > 0) + writel(0, dev->regs + MVMDIO_ERR_INT_MASK); mdiobus_unregister(bus); - if (!IS_ERR(dev->clk)) - clk_disable_unprepare(dev->clk); + + for (i = 0; i < ARRAY_SIZE(dev->clk); i++) { + if (IS_ERR(dev->clk[i])) + break; + clk_disable_unprepare(dev->clk[i]); + clk_put(dev->clk[i]); + } return 0; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 34a3686d2ce6..d297011b535d 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1107,7 +1107,7 @@ static void mvneta_port_up(struct mvneta_port *pp) q_map = 0; for (queue = 0; queue < txq_number; queue++) { struct mvneta_tx_queue *txq = &pp->txqs[queue]; - if (txq->descs != NULL) + if (txq->descs) q_map |= (1 << queue); } mvreg_write(pp, MVNETA_TXQ_CMD, q_map); @@ -1116,7 +1116,7 @@ static void mvneta_port_up(struct mvneta_port *pp) for (queue = 0; queue < rxq_number; queue++) { struct mvneta_rx_queue *rxq = &pp->rxqs[queue]; - if (rxq->descs != NULL) + if (rxq->descs) q_map |= (1 << queue); } mvreg_write(pp, MVNETA_RXQ_CMD, q_map); @@ -2850,7 +2850,7 @@ static int mvneta_rxq_init(struct mvneta_port *pp, rxq->descs = dma_alloc_coherent(pp->dev->dev.parent, rxq->size * MVNETA_DESC_ALIGNED_SIZE, &rxq->descs_phys, GFP_KERNEL); - if (rxq->descs == NULL) + if (!rxq->descs) return -ENOMEM; rxq->last_desc = rxq->size - 1; @@ -2920,7 +2920,7 @@ static int mvneta_txq_init(struct mvneta_port *pp, txq->descs = dma_alloc_coherent(pp->dev->dev.parent, txq->size * MVNETA_DESC_ALIGNED_SIZE, &txq->descs_phys, GFP_KERNEL); - if (txq->descs == NULL) + if (!txq->descs) return -ENOMEM; txq->last_desc = txq->size - 1; @@ -2933,8 +2933,9 @@ static int mvneta_txq_init(struct mvneta_port *pp, mvreg_write(pp, MVNETA_TXQ_BASE_ADDR_REG(txq->id), txq->descs_phys); mvreg_write(pp, MVNETA_TXQ_SIZE_REG(txq->id), txq->size); - txq->tx_skb = kmalloc(txq->size * sizeof(*txq->tx_skb), GFP_KERNEL); - if (txq->tx_skb == NULL) { + txq->tx_skb = kmalloc_array(txq->size, sizeof(*txq->tx_skb), + GFP_KERNEL); + if (!txq->tx_skb) { dma_free_coherent(pp->dev->dev.parent, txq->size * MVNETA_DESC_ALIGNED_SIZE, txq->descs, txq->descs_phys); @@ -2945,7 +2946,7 @@ static int mvneta_txq_init(struct mvneta_port *pp, txq->tso_hdrs = dma_alloc_coherent(pp->dev->dev.parent, txq->size * TSO_HEADER_SIZE, &txq->tso_hdrs_phys, GFP_KERNEL); - if (txq->tso_hdrs == NULL) { + if (!txq->tso_hdrs) { kfree(txq->tx_skb); dma_free_coherent(pp->dev->dev.parent, txq->size * MVNETA_DESC_ALIGNED_SIZE, @@ -3318,6 +3319,7 @@ static void mvneta_adjust_link(struct net_device *ndev) static int mvneta_mdio_probe(struct mvneta_port *pp) { struct phy_device *phy_dev; + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; phy_dev = of_phy_connect(pp->dev, pp->phy_node, mvneta_adjust_link, 0, pp->phy_interface); @@ -3326,6 +3328,9 @@ static int mvneta_mdio_probe(struct mvneta_port *pp) return -ENODEV; } + phy_ethtool_get_wol(phy_dev, &wol); + device_set_wakeup_capable(&pp->dev->dev, !!wol.supported); + phy_dev->supported &= PHY_GBIT_FEATURES; phy_dev->advertising = phy_dev->supported; @@ -3942,10 +3947,16 @@ static void mvneta_ethtool_get_wol(struct net_device *dev, static int mvneta_ethtool_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { + int ret; + if (!dev->phydev) return -EOPNOTSUPP; - return phy_ethtool_set_wol(dev->phydev, wol); + ret = phy_ethtool_set_wol(dev->phydev, wol); + if (!ret) + device_set_wakeup_enable(&dev->dev, !!wol->wolopts); + + return ret; } static const struct net_device_ops mvneta_netdev_ops = { @@ -3992,8 +4003,7 @@ static int mvneta_init(struct device *dev, struct mvneta_port *pp) /* Set port default values */ mvneta_defaults_set(pp); - pp->txqs = devm_kcalloc(dev, txq_number, sizeof(struct mvneta_tx_queue), - GFP_KERNEL); + pp->txqs = devm_kcalloc(dev, txq_number, sizeof(*pp->txqs), GFP_KERNEL); if (!pp->txqs) return -ENOMEM; @@ -4005,8 +4015,7 @@ static int mvneta_init(struct device *dev, struct mvneta_port *pp) txq->done_pkts_coal = MVNETA_TXDONE_COAL_PKTS; } - pp->rxqs = devm_kcalloc(dev, rxq_number, sizeof(struct mvneta_rx_queue), - GFP_KERNEL); + pp->rxqs = devm_kcalloc(dev, rxq_number, sizeof(*pp->rxqs), GFP_KERNEL); if (!pp->rxqs) return -ENOMEM; @@ -4017,9 +4026,11 @@ static int mvneta_init(struct device *dev, struct mvneta_port *pp) rxq->size = pp->rx_ring_size; rxq->pkts_coal = MVNETA_RX_COAL_PKTS; rxq->time_coal = MVNETA_RX_COAL_USEC; - rxq->buf_virt_addr = devm_kmalloc(pp->dev->dev.parent, - rxq->size * sizeof(void *), - GFP_KERNEL); + rxq->buf_virt_addr + = devm_kmalloc_array(pp->dev->dev.parent, + rxq->size, + sizeof(*rxq->buf_virt_addr), + GFP_KERNEL); if (!rxq->buf_virt_addr) return -ENOMEM; } diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index af5bfa13d976..9b875d776b29 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -1689,7 +1689,7 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add) mvpp2_prs_hw_read(priv, &pe); } else { /* Entry doesn't exist - create new */ - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC); pe.index = MVPP2_PE_DROP_ALL; @@ -1726,7 +1726,7 @@ static void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port, bool add) mvpp2_prs_hw_read(priv, &pe); } else { /* Entry doesn't exist - create new */ - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC); pe.index = MVPP2_PE_MAC_PROMISCUOUS; @@ -1772,7 +1772,7 @@ static void mvpp2_prs_mac_multi_set(struct mvpp2 *priv, int port, int index, mvpp2_prs_hw_read(priv, &pe); } else { /* Entry doesn't exist - create new */ - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC); pe.index = index; @@ -1824,7 +1824,7 @@ static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add, mvpp2_prs_hw_read(priv, &pe); } else { /* Entry doesn't exist - create new */ - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_DSA); pe.index = tid; @@ -1887,7 +1887,7 @@ static void mvpp2_prs_dsa_tag_ethertype_set(struct mvpp2 *priv, int port, mvpp2_prs_hw_read(priv, &pe); } else { /* Entry doesn't exist - create new */ - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_DSA); pe.index = tid; @@ -2021,10 +2021,10 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai, if (tid <= tid_aux) { ret = -EINVAL; - goto error; + goto free_pe; } - memset(pe, 0 , sizeof(struct mvpp2_prs_entry)); + memset(pe, 0, sizeof(*pe)); mvpp2_prs_tcam_lu_set(pe, MVPP2_PRS_LU_VLAN); pe->index = tid; @@ -2053,8 +2053,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai, mvpp2_prs_tcam_port_map_set(pe, port_map); mvpp2_prs_hw_write(priv, pe); - -error: +free_pe: kfree(pe); return ret; @@ -2139,7 +2138,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1, ai = mvpp2_prs_double_vlan_ai_free_get(priv); if (ai < 0) { ret = ai; - goto error; + goto free_pe; } /* Get first single/triple vlan tid */ @@ -2162,10 +2161,10 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1, if (tid >= tid_aux) { ret = -ERANGE; - goto error; + goto free_pe; } - memset(pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(pe, 0, sizeof(*pe)); mvpp2_prs_tcam_lu_set(pe, MVPP2_PRS_LU_VLAN); pe->index = tid; @@ -2189,8 +2188,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1, /* Update ports' mask */ mvpp2_prs_tcam_port_map_set(pe, port_map); mvpp2_prs_hw_write(priv, pe); - -error: +free_pe: kfree(pe); return ret; } @@ -2212,7 +2210,7 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto, if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP4); pe.index = tid; @@ -2270,7 +2268,7 @@ static int mvpp2_prs_ip4_cast(struct mvpp2 *priv, unsigned short l3_cast) if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP4); pe.index = tid; @@ -2326,7 +2324,7 @@ static int mvpp2_prs_ip6_proto(struct mvpp2 *priv, unsigned short proto, if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP6); pe.index = tid; @@ -2365,7 +2363,7 @@ static int mvpp2_prs_ip6_cast(struct mvpp2 *priv, unsigned short l3_cast) if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP6); pe.index = tid; @@ -2425,7 +2423,7 @@ static void mvpp2_prs_def_flow_init(struct mvpp2 *priv) int port; for (port = 0; port < MVPP2_MAX_PORTS; port++) { - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_FLOWS); pe.index = MVPP2_PE_FIRST_DEFAULT_FLOW - port; @@ -2447,7 +2445,7 @@ static void mvpp2_prs_mh_init(struct mvpp2 *priv) { struct mvpp2_prs_entry pe; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); pe.index = MVPP2_PE_MH_DEFAULT; mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MH); @@ -2470,7 +2468,7 @@ static void mvpp2_prs_mac_init(struct mvpp2 *priv) { struct mvpp2_prs_entry pe; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); /* Non-promiscuous mode for all ports - DROP unknown packets */ pe.index = MVPP2_PE_MAC_NON_PROMISCUOUS; @@ -2531,7 +2529,7 @@ static void mvpp2_prs_dsa_init(struct mvpp2 *priv) MVPP2_PRS_TAGGED, MVPP2_PRS_DSA); /* Set default entry, in case DSA or EDSA tag not found */ - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_DSA); pe.index = MVPP2_PE_DSA_DEFAULT; mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_VLAN); @@ -2561,7 +2559,7 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv) if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_L2); pe.index = tid; @@ -2587,7 +2585,7 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv) if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_L2); pe.index = tid; @@ -2617,7 +2615,7 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv) if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_L2); pe.index = tid; @@ -2651,7 +2649,7 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv) if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_L2); pe.index = tid; @@ -2716,7 +2714,7 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv) if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_L2); pe.index = tid; @@ -2813,7 +2811,7 @@ static int mvpp2_prs_vlan_init(struct platform_device *pdev, struct mvpp2 *priv) return err; /* Set default double vlan entry */ - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VLAN); pe.index = MVPP2_PE_VLAN_DBL; @@ -2833,7 +2831,7 @@ static int mvpp2_prs_vlan_init(struct platform_device *pdev, struct mvpp2 *priv) mvpp2_prs_hw_write(priv, &pe); /* Set default vlan none entry */ - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VLAN); pe.index = MVPP2_PE_VLAN_NONE; @@ -2863,7 +2861,7 @@ static int mvpp2_prs_pppoe_init(struct mvpp2 *priv) if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_PPPOE); pe.index = tid; @@ -2913,7 +2911,7 @@ static int mvpp2_prs_pppoe_init(struct mvpp2 *priv) if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_PPPOE); pe.index = tid; @@ -2940,7 +2938,7 @@ static int mvpp2_prs_pppoe_init(struct mvpp2 *priv) if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_PPPOE); pe.index = tid; @@ -2998,7 +2996,7 @@ static int mvpp2_prs_ip4_init(struct mvpp2 *priv) return err; /* Default IPv4 entry for unknown protocols */ - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP4); pe.index = MVPP2_PE_IP4_PROTO_UN; @@ -3023,7 +3021,7 @@ static int mvpp2_prs_ip4_init(struct mvpp2 *priv) mvpp2_prs_hw_write(priv, &pe); /* Default IPv4 entry for unicast address */ - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP4); pe.index = MVPP2_PE_IP4_ADDR_UN; @@ -3091,7 +3089,7 @@ static int mvpp2_prs_ip6_init(struct mvpp2 *priv) if (tid < 0) return tid; - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP6); pe.index = tid; @@ -3112,7 +3110,7 @@ static int mvpp2_prs_ip6_init(struct mvpp2 *priv) mvpp2_prs_hw_write(priv, &pe); /* Default IPv6 entry for unknown protocols */ - memset(&pe, 0, sizeof(struct mvpp2_prs_entry)); + memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP6); pe.index = MVPP2_PE_IP6_PROTO_UN; @@ -3205,7 +3203,7 @@ static int mvpp2_prs_default_init(struct platform_device *pdev, mvpp2_prs_hw_inv(priv, index); priv->prs_shadow = devm_kcalloc(&pdev->dev, MVPP2_PRS_TCAM_SRAM_SIZE, - sizeof(struct mvpp2_prs_shadow), + sizeof(*priv->prs_shadow), GFP_KERNEL); if (!priv->prs_shadow) return -ENOMEM; @@ -3833,7 +3831,7 @@ static int mvpp2_bm_init(struct platform_device *pdev, struct mvpp2 *priv) /* Allocate and initialize BM pools */ priv->bm_pools = devm_kcalloc(&pdev->dev, MVPP2_BM_POOLS_NUM, - sizeof(struct mvpp2_bm_pool), GFP_KERNEL); + sizeof(*priv->bm_pools), GFP_KERNEL); if (!priv->bm_pools) return -ENOMEM; @@ -4417,7 +4415,7 @@ static void mvpp2_egress_enable(struct mvpp2_port *port) for (queue = 0; queue < txq_number; queue++) { struct mvpp2_tx_queue *txq = port->txqs[queue]; - if (txq->descs != NULL) + if (txq->descs) qmap |= (1 << queue); } @@ -5083,11 +5081,11 @@ static int mvpp2_txq_init(struct mvpp2_port *port, for_each_present_cpu(cpu) { txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); txq_pcpu->size = txq->size; - txq_pcpu->buffs = kmalloc(txq_pcpu->size * - sizeof(struct mvpp2_txq_pcpu_buf), - GFP_KERNEL); + txq_pcpu->buffs = kmalloc_array(txq_pcpu->size, + sizeof(*txq_pcpu->buffs), + GFP_KERNEL); if (!txq_pcpu->buffs) - goto error; + goto cleanup; txq_pcpu->count = 0; txq_pcpu->reserved_num = 0; @@ -5096,8 +5094,7 @@ static int mvpp2_txq_init(struct mvpp2_port *port, } return 0; - -error: +cleanup: for_each_present_cpu(cpu) { txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); kfree(txq_pcpu->buffs); @@ -5515,7 +5512,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, * comprised by the RX descriptor. */ if (rx_status & MVPP2_RXD_ERR_SUMMARY) { - err_drop_frame: +err_drop_frame: dev->stats.rx_errors++; mvpp2_rx_error(port, rx_desc); /* Return the buffer to the pool */ @@ -5606,7 +5603,7 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, DMA_TO_DEVICE); if (dma_mapping_error(port->dev->dev.parent, buf_dma_addr)) { mvpp2_txq_desc_put(txq); - goto error; + goto cleanup; } mvpp2_txdesc_offset_set(port, tx_desc, @@ -5627,8 +5624,7 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, } return 0; - -error: +cleanup: /* Release all descriptors that were used to map fragments of * this packet, as well as the corresponding DMA mappings */ @@ -6065,7 +6061,7 @@ static int mvpp2_set_mac_address(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) { err = -EADDRNOTAVAIL; - goto error; + goto log_error; } if (!netif_running(dev)) { @@ -6075,7 +6071,7 @@ static int mvpp2_set_mac_address(struct net_device *dev, void *p) /* Reconfigure parser to accept the original MAC address */ err = mvpp2_prs_update_mac_da(dev, dev->dev_addr); if (err) - goto error; + goto log_error; } mvpp2_stop_dev(port); @@ -6087,15 +6083,14 @@ static int mvpp2_set_mac_address(struct net_device *dev, void *p) /* Reconfigure parser accept the original MAC address */ err = mvpp2_prs_update_mac_da(dev, dev->dev_addr); if (err) - goto error; + goto log_error; out_start: mvpp2_start_dev(port); mvpp2_egress_enable(port); mvpp2_ingress_enable(port); return 0; - -error: - netdev_err(dev, "fail to change MAC address\n"); +log_error: + netdev_err(dev, "failed to change MAC address\n"); return err; } @@ -6120,7 +6115,7 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu) /* Reconfigure BM to the original MTU */ err = mvpp2_bm_update_mtu(dev, dev->mtu); if (err) - goto error; + goto log_error; } mvpp2_stop_dev(port); @@ -6134,7 +6129,7 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu) /* Reconfigure BM to the original MTU */ err = mvpp2_bm_update_mtu(dev, dev->mtu); if (err) - goto error; + goto log_error; out_start: mvpp2_start_dev(port); @@ -6142,9 +6137,8 @@ out_start: mvpp2_ingress_enable(port); return 0; - -error: - netdev_err(dev, "fail to change MTU\n"); +log_error: + netdev_err(dev, "failed to change MTU\n"); return err; } @@ -6313,7 +6307,7 @@ static int mvpp2_ethtool_set_ringparam(struct net_device *dev, err_clean_rxqs: mvpp2_cleanup_rxqs(port); err_out: - netdev_err(dev, "fail to change ring parameters"); + netdev_err(dev, "failed to change ring parameters"); return err; } @@ -6487,8 +6481,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, int phy_mode; int err, i, cpu; - dev = alloc_etherdev_mqs(sizeof(struct mvpp2_port), txq_number, - rxq_number); + dev = alloc_etherdev_mqs(sizeof(*port), txq_number, rxq_number); if (!dev) return -ENOMEM; @@ -6806,7 +6799,7 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) /* Allocate and initialize aggregated TXQs */ priv->aggr_txqs = devm_kcalloc(&pdev->dev, num_present_cpus(), - sizeof(struct mvpp2_tx_queue), + sizeof(*priv->aggr_txqs), GFP_KERNEL); if (!priv->aggr_txqs) return -ENOMEM; @@ -6873,7 +6866,7 @@ static int mvpp2_probe(struct platform_device *pdev) int port_count, cpu; int err; - priv = devm_kzalloc(&pdev->dev, sizeof(struct mvpp2), GFP_KERNEL); + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; @@ -6970,8 +6963,8 @@ static int mvpp2_probe(struct platform_device *pdev) } priv->port_list = devm_kcalloc(&pdev->dev, port_count, - sizeof(struct mvpp2_port *), - GFP_KERNEL); + sizeof(*priv->port_list), + GFP_KERNEL); if (!priv->port_list) { err = -ENOMEM; goto err_mg_clk; diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index 28cb36d9e50a..993724959a7c 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -556,11 +556,11 @@ static int init_hash_table(struct pxa168_eth_private *pep) * function.Driver can dynamically switch to them if the 1/2kB hash * table is full. */ - if (pep->htpr == NULL) { + if (!pep->htpr) { pep->htpr = dma_zalloc_coherent(pep->dev->dev.parent, HASH_ADDR_TABLE_SIZE, &pep->htpr_dma, GFP_KERNEL); - if (pep->htpr == NULL) + if (!pep->htpr) return -ENOMEM; } else { memset(pep->htpr, 0, HASH_ADDR_TABLE_SIZE); @@ -1036,8 +1036,7 @@ static int rxq_init(struct net_device *dev) int rx_desc_num = pep->rx_ring_size; /* Allocate RX skb rings */ - pep->rx_skb = kzalloc(sizeof(*pep->rx_skb) * pep->rx_ring_size, - GFP_KERNEL); + pep->rx_skb = kcalloc(rx_desc_num, sizeof(*pep->rx_skb), GFP_KERNEL); if (!pep->rx_skb) return -ENOMEM; @@ -1096,8 +1095,7 @@ static int txq_init(struct net_device *dev) int size = 0, i = 0; int tx_desc_num = pep->tx_ring_size; - pep->tx_skb = kzalloc(sizeof(*pep->tx_skb) * pep->tx_ring_size, - GFP_KERNEL); + pep->tx_skb = kcalloc(tx_desc_num, sizeof(*pep->tx_skb), GFP_KERNEL); if (!pep->tx_skb) return -ENOMEM; @@ -1358,7 +1356,7 @@ static int pxa168_smi_write(struct mii_bus *bus, int phy_addr, int regnum, static int pxa168_eth_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { - if (dev->phydev != NULL) + if (dev->phydev) return phy_mii_ioctl(dev->phydev, ifr, cmd); return -EOPNOTSUPP; @@ -1503,7 +1501,7 @@ static int pxa168_eth_probe(struct platform_device *pdev) pep->timeout.data = (unsigned long)pep; pep->smi_bus = mdiobus_alloc(); - if (pep->smi_bus == NULL) { + if (!pep->smi_bus) { err = -ENOMEM; goto err_netdev; } diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index edb95271a4f2..5d7d94de4e00 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -2657,7 +2657,7 @@ static int skge_down(struct net_device *dev) struct skge_hw *hw = skge->hw; int port = skge->port; - if (skge->mem == NULL) + if (!skge->mem) return 0; netif_info(skge, ifdown, skge->netdev, "disabling interface\n"); @@ -3718,7 +3718,7 @@ static int skge_debug_show(struct seq_file *seq, void *v) t->csum_offs, t->csum_write, t->csum_start); } - seq_printf(seq, "\nRx Ring:\n"); + seq_puts(seq, "\nRx Ring:\n"); for (e = skge->rx_ring.to_clean; ; e = e->next) { const struct skge_rx_desc *r = e->desc; diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 2b2cc3f3ca10..1145cde2274a 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4544,7 +4544,7 @@ static int sky2_debug_show(struct seq_file *seq, void *v) sky2_read32(hw, B0_Y2_SP_ICR)); if (!netif_running(dev)) { - seq_printf(seq, "network not running\n"); + seq_puts(seq, "network not running\n"); return 0; } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index bf6317eca2f6..16f97552ae98 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -613,7 +613,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; struct mtk_tx_dma *itxd, *txd; - struct mtk_tx_buf *tx_buf; + struct mtk_tx_buf *itx_buf, *tx_buf; dma_addr_t mapped_addr; unsigned int nr_frags; int i, n_desc = 1; @@ -627,8 +627,8 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, fport = (mac->id + 1) << TX_DMA_FPORT_SHIFT; txd4 |= fport; - tx_buf = mtk_desc_to_tx_buf(ring, itxd); - memset(tx_buf, 0, sizeof(*tx_buf)); + itx_buf = mtk_desc_to_tx_buf(ring, itxd); + memset(itx_buf, 0, sizeof(*itx_buf)); if (gso) txd4 |= TX_DMA_TSO; @@ -647,9 +647,11 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, return -ENOMEM; WRITE_ONCE(itxd->txd1, mapped_addr); - tx_buf->flags |= MTK_TX_FLAGS_SINGLE0; - dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); - dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb)); + itx_buf->flags |= MTK_TX_FLAGS_SINGLE0; + itx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 : + MTK_TX_FLAGS_FPORT1; + dma_unmap_addr_set(itx_buf, dma_addr0, mapped_addr); + dma_unmap_len_set(itx_buf, dma_len0, skb_headlen(skb)); /* TX SG offload */ txd = itxd; @@ -685,11 +687,13 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, last_frag * TX_DMA_LS0)); WRITE_ONCE(txd->txd4, fport); - tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC; tx_buf = mtk_desc_to_tx_buf(ring, txd); memset(tx_buf, 0, sizeof(*tx_buf)); - + tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC; tx_buf->flags |= MTK_TX_FLAGS_PAGE0; + tx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 : + MTK_TX_FLAGS_FPORT1; + dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); dma_unmap_len_set(tx_buf, dma_len0, frag_map_size); frag_size -= frag_map_size; @@ -698,7 +702,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, } /* store skb to cleanup */ - tx_buf->skb = skb; + itx_buf->skb = skb; WRITE_ONCE(itxd->txd4, txd4); WRITE_ONCE(itxd->txd3, (TX_DMA_SWC | TX_DMA_PLEN0(skb_headlen(skb)) | @@ -1012,17 +1016,16 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget) while ((cpu != dma) && budget) { u32 next_cpu = desc->txd2; - int mac; + int mac = 0; desc = mtk_qdma_phys_to_virt(ring, desc->txd2); if ((desc->txd3 & TX_DMA_OWNER_CPU) == 0) break; - mac = (desc->txd4 >> TX_DMA_FPORT_SHIFT) & - TX_DMA_FPORT_MASK; - mac--; - tx_buf = mtk_desc_to_tx_buf(ring, desc); + if (tx_buf->flags & MTK_TX_FLAGS_FPORT1) + mac = 1; + skb = tx_buf->skb; if (!skb) { condition = 1; @@ -1846,6 +1849,12 @@ static int mtk_hw_init(struct mtk_eth *eth) /* GE2, Force 1000M/FD, FC ON */ mtk_w32(eth, MAC_MCR_FIXED_LINK, MTK_MAC_MCR(1)); + /* Indicates CDM to parse the MTK special tag from CPU + * which also is working out for untag packets. + */ + val = mtk_r32(eth, MTK_CDMQ_IG_CTRL); + mtk_w32(eth, val | MTK_CDMQ_STAG_EN, MTK_CDMQ_IG_CTRL); + /* Enable RX VLan Offloading */ mtk_w32(eth, 1, MTK_CDMP_EG_CTRL); @@ -2316,6 +2325,8 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) eth->netdev[id]->ethtool_ops = &mtk_ethtool_ops; eth->netdev[id]->irq = eth->irq[0]; + eth->netdev[id]->dev.of_node = np; + return 0; free_netdev: diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 99b1c8e9f16f..3c46a3b613b9 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -70,6 +70,10 @@ /* Frame Engine Interrupt Grouping Register */ #define MTK_FE_INT_GRP 0x20 +/* CDMP Ingress Control Register */ +#define MTK_CDMQ_IG_CTRL 0x1400 +#define MTK_CDMQ_STAG_EN BIT(0) + /* CDMP Exgress Control Register */ #define MTK_CDMP_EG_CTRL 0x404 @@ -406,12 +410,18 @@ struct mtk_hw_stats { struct u64_stats_sync syncp; }; -/* PDMA descriptor can point at 1-2 segments. This enum allows us to track how - * memory was allocated so that it can be freed properly - */ enum mtk_tx_flags { + /* PDMA descriptor can point at 1-2 segments. This enum allows us to + * track how memory was allocated so that it can be freed properly. + */ MTK_TX_FLAGS_SINGLE0 = 0x01, MTK_TX_FLAGS_PAGE0 = 0x02, + + /* MTK_TX_FLAGS_FPORTx allows tracking which port the transmitted + * SKB out instead of looking up through hardware TX descriptor. + */ + MTK_TX_FLAGS_FPORT0 = 0x04, + MTK_TX_FLAGS_FPORT1 = 0x08, }; /* This enum allows us to identify how the clock is defined on the array of the diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index e0c5ffb3e3a6..3ba89bc43d74 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -978,8 +978,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) ring->tso_packets++; - i = ((skb->len - lso_header_size) / shinfo->gso_size) + - !!((skb->len - lso_header_size) % shinfo->gso_size); + i = shinfo->gso_segs; tx_info->nr_bytes = skb->len + (i - 1) * lso_header_size; ring->packets += i; } else { diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index d8d5d161b8c7..4aa29ee93013 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2749,7 +2749,7 @@ int mlx4_SW2HW_MPT_wrapper(struct mlx4_dev *dev, int slave, int err; int index = vhcr->in_modifier; struct res_mtt *mtt; - struct res_mpt *mpt; + struct res_mpt *mpt = NULL; int mtt_base = mr_get_mtt_addr(inbox->buf) / dev->caps.mtt_entry_sz; int phys; int id; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 117170014e88..a84b652f9b54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -31,3 +31,10 @@ config MLX5_CORE_EN_DCB This flag is depended on the kernel's DCB support. If unsure, set to Y + +config MLX5_CORE_IPOIB + bool "Mellanox Technologies ConnectX-4 IPoIB offloads support" + depends on MLX5_CORE_EN + default y + ---help--- + MLX5 IPoIB offloads & acceleration support. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 9f43beb86250..9e644615f07a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -11,3 +11,5 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o eswitch_offloads.o \ en_tc.o en_arfs.o en_rep.o en_fs_ethtool.o en_selftest.o mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o + +mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 150fb52a0737..0881325fba04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -37,6 +37,7 @@ #include <linux/timecounter.h> #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> +#include <linux/crash_dump.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/qp.h> #include <linux/mlx5/cq.h> @@ -153,6 +154,14 @@ static inline int mlx5_max_log_rq_size(int wq_type) } } +static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) +{ + return is_kdump_kernel() ? + MLX5E_MIN_NUM_CHANNELS : + min_t(int, mdev->priv.eq_table.num_comp_vectors, + MLX5E_MAX_NUM_CHANNELS); +} + struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_eth_seg eth; @@ -221,6 +230,7 @@ struct mlx5e_params { u8 toeplitz_hash_key[40]; u32 indirection_rqt[MLX5E_INDIR_RQT_SIZE]; bool vlan_strip_disable; + bool scatter_fcs_en; bool rx_am_enabled; u32 lro_timeout; u32 pflags; @@ -294,6 +304,7 @@ struct mlx5e_cq { } ____cacheline_aligned_in_smp; struct mlx5e_tx_wqe_info { + struct sk_buff *skb; u32 num_bytes; u8 num_wqebbs; u8 num_dma; @@ -335,7 +346,6 @@ struct mlx5e_txqsq { /* write@xmit, read@completion */ struct { - struct sk_buff **skb; struct mlx5e_sq_dma *dma_fifo; struct mlx5e_tx_wqe_info *wqe_info; } db; @@ -769,6 +779,10 @@ struct mlx5e_profile { void (*disable)(struct mlx5e_priv *priv); void (*update_stats)(struct mlx5e_priv *priv); int (*max_nch)(struct mlx5_core_dev *mdev); + struct { + mlx5e_fp_handle_rx_cqe handle_rx_cqe; + mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe; + } rx_handlers; int max_tc; }; @@ -842,8 +856,6 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto, void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv); -int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd); - struct mlx5e_redirect_rqt_param { bool is_rss; union { @@ -875,6 +887,8 @@ typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv); void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, struct mlx5e_channels *new_chs, mlx5e_fp_hw_modify hw_modify); +void mlx5e_activate_priv_channels(struct mlx5e_priv *priv); +void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv); void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev, u32 *indirection_rqt, int len, @@ -991,21 +1005,30 @@ int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr); void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); void mlx5e_update_hw_rep_counters(struct mlx5e_priv *priv); +/* common netdev helpers */ +int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv); + +int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv); +void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv); + int mlx5e_create_direct_rqts(struct mlx5e_priv *priv); -void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt); +void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv); int mlx5e_create_direct_tirs(struct mlx5e_priv *priv); void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv); +void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt); + +int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn); +void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv); + +int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc, + u32 underlay_qpn, u32 *tisn); +void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn); + int mlx5e_create_tises(struct mlx5e_priv *priv); void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv); int mlx5e_close(struct net_device *netdev); int mlx5e_open(struct net_device *netdev); void mlx5e_update_stats_work(struct work_struct *work); -struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev, - const struct mlx5e_profile *profile, - void *ppriv); -void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv); -int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev); -void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev); u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout); int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev, @@ -1013,5 +1036,16 @@ int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev, bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id); bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv); -bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv); + +/* mlx5e generic netdev management API */ +struct net_device* +mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile, + void *ppriv); +int mlx5e_attach_netdev(struct mlx5e_priv *priv); +void mlx5e_detach_netdev(struct mlx5e_priv *priv); +void mlx5e_destroy_netdev(struct mlx5e_priv *priv); +void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + u16 max_channels); + #endif /* __MLX5_EN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index c4e9cc79f5c7..c8a005326e30 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -321,10 +321,16 @@ static int arfs_create_table(struct mlx5e_priv *priv, { struct mlx5e_arfs_tables *arfs = &priv->fs.arfs; struct mlx5e_flow_table *ft = &arfs->arfs_tables[type].ft; + struct mlx5_flow_table_attr ft_attr = {}; int err; - ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO, - MLX5E_ARFS_TABLE_SIZE, MLX5E_ARFS_FT_LEVEL, 0); + ft->num_groups = 0; + + ft_attr.max_fte = MLX5E_ARFS_TABLE_SIZE; + ft_attr.level = MLX5E_ARFS_FT_LEVEL; + ft_attr.prio = MLX5E_NIC_PRIO; + + ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr); if (IS_ERR(ft->t)) { err = PTR_ERR(ft->t); ft->t = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 40912937d211..ce7b09d72ff6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -42,8 +42,9 @@ static void mlx5e_get_drvinfo(struct net_device *dev, strlcpy(drvinfo->version, DRIVER_VERSION " (" DRIVER_RELDATE ")", sizeof(drvinfo->version)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), - "%d.%d.%d", - fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev)); + "%d.%d.%04d (%.16s)", + fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev), + mdev->board_id); strlcpy(drvinfo->bus_info, pci_name(mdev->pdev), sizeof(drvinfo->bus_info)); } @@ -1064,8 +1065,12 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, u32 rqtn = priv->indir_rqt.rqtn; struct mlx5e_redirect_rqt_param rrp = { .is_rss = true, - .rss.hfunc = priv->channels.params.rss_hfunc, - .rss.channels = &priv->channels + { + .rss = { + .hfunc = priv->channels.params.rss_hfunc, + .channels = &priv->channels, + }, + }, }; mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 5376d69a6b1a..576d6787b484 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -792,7 +792,7 @@ err: return err; } -static void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv) +void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv) { struct mlx5e_ttc_table *ttc = &priv->fs.ttc; @@ -800,14 +800,19 @@ static void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv) mlx5e_destroy_flow_table(&ttc->ft); } -static int mlx5e_create_ttc_table(struct mlx5e_priv *priv) +int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn) { struct mlx5e_ttc_table *ttc = &priv->fs.ttc; + struct mlx5_flow_table_attr ft_attr = {}; struct mlx5e_flow_table *ft = &ttc->ft; int err; - ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO, - MLX5E_TTC_TABLE_SIZE, MLX5E_TTC_FT_LEVEL, 0); + ft_attr.max_fte = MLX5E_TTC_TABLE_SIZE; + ft_attr.level = MLX5E_TTC_FT_LEVEL; + ft_attr.prio = MLX5E_NIC_PRIO; + ft_attr.underlay_qpn = underlay_qpn; + + ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr); if (IS_ERR(ft->t)) { err = PTR_ERR(ft->t); ft->t = NULL; @@ -973,12 +978,16 @@ static int mlx5e_create_l2_table(struct mlx5e_priv *priv) { struct mlx5e_l2_table *l2_table = &priv->fs.l2; struct mlx5e_flow_table *ft = &l2_table->ft; + struct mlx5_flow_table_attr ft_attr = {}; int err; ft->num_groups = 0; - ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO, - MLX5E_L2_TABLE_SIZE, MLX5E_L2_FT_LEVEL, 0); + ft_attr.max_fte = MLX5E_L2_TABLE_SIZE; + ft_attr.level = MLX5E_L2_FT_LEVEL; + ft_attr.prio = MLX5E_NIC_PRIO; + + ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr); if (IS_ERR(ft->t)) { err = PTR_ERR(ft->t); ft->t = NULL; @@ -1076,11 +1085,16 @@ static int mlx5e_create_vlan_table_groups(struct mlx5e_flow_table *ft) static int mlx5e_create_vlan_table(struct mlx5e_priv *priv) { struct mlx5e_flow_table *ft = &priv->fs.vlan.ft; + struct mlx5_flow_table_attr ft_attr = {}; int err; ft->num_groups = 0; - ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO, - MLX5E_VLAN_TABLE_SIZE, MLX5E_VLAN_FT_LEVEL, 0); + + ft_attr.max_fte = MLX5E_VLAN_TABLE_SIZE; + ft_attr.level = MLX5E_VLAN_FT_LEVEL; + ft_attr.prio = MLX5E_NIC_PRIO; + + ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr); if (IS_ERR(ft->t)) { err = PTR_ERR(ft->t); @@ -1133,7 +1147,7 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv) priv->netdev->hw_features &= ~NETIF_F_NTUPLE; } - err = mlx5e_create_ttc_table(priv); + err = mlx5e_create_ttc_table(priv, 0); if (err) { netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 68d6c3c58ba7..061b20c73071 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -31,7 +31,6 @@ */ #include <net/tc_act/tc_gact.h> -#include <linux/crash_dump.h> #include <net/pkt_cls.h> #include <linux/mlx5/fs.h> #include <net/vxlan.h> @@ -586,15 +585,17 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - if (mlx5e_is_vf_vport_rep(c->priv)) { - err = -EINVAL; - goto err_rq_wq_destroy; - } - rq->handle_rx_cqe = mlx5e_handle_rx_cqe_mpwrq; rq->alloc_wqe = mlx5e_alloc_rx_mpwqe; rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; + rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe_mpwqe; + if (!rq->handle_rx_cqe) { + err = -EINVAL; + netdev_err(c->netdev, "RX handler of MPWQE RQ is not set, err %d\n", err); + goto err_rq_wq_destroy; + } + rq->mpwqe_stride_sz = BIT(params->mpwqe_log_stride_sz); rq->mpwqe_num_strides = BIT(params->mpwqe_log_num_strides); @@ -617,15 +618,17 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = -ENOMEM; goto err_rq_wq_destroy; } - - if (mlx5e_is_vf_vport_rep(c->priv)) - rq->handle_rx_cqe = mlx5e_handle_rx_cqe_rep; - else - rq->handle_rx_cqe = mlx5e_handle_rx_cqe; - rq->alloc_wqe = mlx5e_alloc_rx_wqe; rq->dealloc_wqe = mlx5e_dealloc_rx_wqe; + rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe; + if (!rq->handle_rx_cqe) { + kfree(rq->dma_info); + err = -EINVAL; + netdev_err(c->netdev, "RX handler of RQ is not set, err %d\n", err); + goto err_rq_wq_destroy; + } + rq->buff.wqe_sz = params->lro_en ? params->lro_wqe_sz : MLX5E_SW2HW_MTU(c->netdev->mtu); @@ -760,6 +763,37 @@ static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, return err; } +static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable) +{ + struct mlx5e_channel *c = rq->channel; + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + + void *in; + void *rqc; + int inlen; + int err; + + inlen = MLX5_ST_SZ_BYTES(modify_rq_in); + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx); + + MLX5_SET(modify_rq_in, in, rq_state, MLX5_RQC_STATE_RDY); + MLX5_SET64(modify_rq_in, in, modify_bitmask, + MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS); + MLX5_SET(rqc, rqc, scatter_fcs, enable); + MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY); + + err = mlx5_core_modify_rq(mdev, rq->rqn, in, inlen); + + kvfree(in); + + return err; +} + static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd) { struct mlx5e_channel *c = rq->channel; @@ -1012,7 +1046,6 @@ static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq) { kfree(sq->db.wqe_info); kfree(sq->db.dma_fifo); - kfree(sq->db.skb); } static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) @@ -1020,13 +1053,11 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) int wq_sz = mlx5_wq_cyc_get_size(&sq->wq); int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS; - sq->db.skb = kzalloc_node(wq_sz * sizeof(*sq->db.skb), - GFP_KERNEL, numa); sq->db.dma_fifo = kzalloc_node(df_sz * sizeof(*sq->db.dma_fifo), GFP_KERNEL, numa); sq->db.wqe_info = kzalloc_node(wq_sz * sizeof(*sq->db.wqe_info), GFP_KERNEL, numa); - if (!sq->db.skb || !sq->db.dma_fifo || !sq->db.wqe_info) { + if (!sq->db.dma_fifo || !sq->db.wqe_info) { mlx5e_free_txqsq_db(sq); return -ENOMEM; } @@ -1265,7 +1296,7 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) if (mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1)) { struct mlx5e_tx_wqe *nop; - sq->db.skb[(sq->pc & sq->wq.sz_m1)] = NULL; + sq->db.wqe_info[(sq->pc & sq->wq.sz_m1)].skb = NULL; nop = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc); mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nop->ctrl); } @@ -1388,21 +1419,16 @@ static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq) mlx5e_free_xdpsq(sq); } -static int mlx5e_alloc_cq(struct mlx5e_channel *c, - struct mlx5e_cq_param *param, - struct mlx5e_cq *cq) +static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev, + struct mlx5e_cq_param *param, + struct mlx5e_cq *cq) { - struct mlx5_core_dev *mdev = c->mdev; struct mlx5_core_cq *mcq = &cq->mcq; int eqn_not_used; unsigned int irqn; int err; u32 i; - param->wq.buf_numa_node = cpu_to_node(c->cpu); - param->wq.db_numa_node = cpu_to_node(c->cpu); - param->eq_ix = c->ix; - err = mlx5_cqwq_create(mdev, ¶m->wq, param->cqc, &cq->wq, &cq->wq_ctrl); if (err) @@ -1410,8 +1436,6 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c, mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn); - cq->napi = &c->napi; - mcq->cqe_sz = 64; mcq->set_ci_db = cq->wq_ctrl.db.db; mcq->arm_db = cq->wq_ctrl.db.db + 1; @@ -1428,12 +1452,30 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c, cqe->op_own = 0xf1; } - cq->channel = c; cq->mdev = mdev; return 0; } +static int mlx5e_alloc_cq(struct mlx5e_channel *c, + struct mlx5e_cq_param *param, + struct mlx5e_cq *cq) +{ + struct mlx5_core_dev *mdev = c->priv->mdev; + int err; + + param->wq.buf_numa_node = cpu_to_node(c->cpu); + param->wq.db_numa_node = cpu_to_node(c->cpu); + param->eq_ix = c->ix; + + err = mlx5e_alloc_cq_common(mdev, param, cq); + + cq->napi = &c->napi; + cq->channel = c; + + return err; +} + static void mlx5e_free_cq(struct mlx5e_cq *cq) { mlx5_cqwq_destroy(&cq->wq_ctrl); @@ -1668,14 +1710,6 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate) return err; } -static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) -{ - return is_kdump_kernel() ? - MLX5E_MIN_NUM_CHANNELS : - min_t(int, mdev->priv.eq_table.num_comp_vectors, - MLX5E_MAX_NUM_CHANNELS); -} - static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct mlx5e_params *params, struct mlx5e_channel_param *cparam, @@ -1834,6 +1868,7 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv, MLX5_SET(wq, wq, pd, priv->mdev->mlx5e_res.pdn); MLX5_SET(rqc, rqc, counter_set_id, priv->q_counter); MLX5_SET(rqc, rqc, vsd, params->vlan_strip_disable); + MLX5_SET(rqc, rqc, scatter_fcs, params->scatter_fcs_en); param->wq.buf_numa_node = dev_to_node(&priv->mdev->pdev->dev); param->wq.linear = 1; @@ -1901,10 +1936,6 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv, } mlx5e_build_common_cq_param(priv, param); - - if (params->rx_am_enabled) - params->rx_cq_moderation = - mlx5e_am_get_def_profile(params->rx_cq_period_mode); } static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv, @@ -2085,11 +2116,15 @@ void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt) mlx5_core_destroy_rqt(priv->mdev, rqt->rqtn); } -static int mlx5e_create_indirect_rqts(struct mlx5e_priv *priv) +int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv) { struct mlx5e_rqt *rqt = &priv->indir_rqt; + int err; - return mlx5e_create_rqt(priv, MLX5E_INDIR_RQT_SIZE, rqt); + err = mlx5e_create_rqt(priv, MLX5E_INDIR_RQT_SIZE, rqt); + if (err) + mlx5_core_warn(priv->mdev, "create indirect rqts failed, %d\n", err); + return err; } int mlx5e_create_direct_rqts(struct mlx5e_priv *priv) @@ -2108,12 +2143,21 @@ int mlx5e_create_direct_rqts(struct mlx5e_priv *priv) return 0; err_destroy_rqts: + mlx5_core_warn(priv->mdev, "create direct rqts failed, %d\n", err); for (ix--; ix >= 0; ix--) mlx5e_destroy_rqt(priv, &priv->direct_tir[ix].rqt); return err; } +void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv) +{ + int i; + + for (i = 0; i < priv->profile->max_nch(priv->mdev); i++) + mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt); +} + static int mlx5e_rx_hash_fn(int hfunc) { return (hfunc == ETH_RSS_HASH_TOP) ? @@ -2207,7 +2251,9 @@ static void mlx5e_redirect_rqts(struct mlx5e_priv *priv, for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) { struct mlx5e_redirect_rqt_param direct_rrp = { .is_rss = false, - .rqn = mlx5e_get_direct_rqn(priv, ix, rrp) + { + .rqn = mlx5e_get_direct_rqn(priv, ix, rrp) + }, }; /* Direct RQ Tables */ @@ -2224,8 +2270,12 @@ static void mlx5e_redirect_rqts_to_channels(struct mlx5e_priv *priv, { struct mlx5e_redirect_rqt_param rrp = { .is_rss = true, - .rss.channels = chs, - .rss.hfunc = chs->params.rss_hfunc + { + .rss = { + .channels = chs, + .hfunc = chs->params.rss_hfunc, + } + }, }; mlx5e_redirect_rqts(priv, rrp); @@ -2235,7 +2285,9 @@ static void mlx5e_redirect_rqts_to_drop(struct mlx5e_priv *priv) { struct mlx5e_redirect_rqt_param drop_rrp = { .is_rss = false, - .rqn = priv->drop_rq.rqn + { + .rqn = priv->drop_rq.rqn, + }, }; mlx5e_redirect_rqts(priv, drop_rrp); @@ -2496,33 +2548,37 @@ static void mlx5e_build_channels_tx_maps(struct mlx5e_priv *priv) } } -static void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) +static bool mlx5e_is_eswitch_vport_mngr(struct mlx5_core_dev *mdev) +{ + return (MLX5_CAP_GEN(mdev, vport_group_manager) && + MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH); +} + +void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) { int num_txqs = priv->channels.num * priv->channels.params.num_tc; struct net_device *netdev = priv->netdev; mlx5e_netdev_set_tcs(netdev); - if (netdev->real_num_tx_queues != num_txqs) - netif_set_real_num_tx_queues(netdev, num_txqs); - if (netdev->real_num_rx_queues != priv->channels.num) - netif_set_real_num_rx_queues(netdev, priv->channels.num); + netif_set_real_num_tx_queues(netdev, num_txqs); + netif_set_real_num_rx_queues(netdev, priv->channels.num); mlx5e_build_channels_tx_maps(priv); mlx5e_activate_channels(&priv->channels); netif_tx_start_all_queues(priv->netdev); - if (MLX5_CAP_GEN(priv->mdev, vport_group_manager)) + if (mlx5e_is_eswitch_vport_mngr(priv->mdev)) mlx5e_add_sqs_fwd_rules(priv); mlx5e_wait_channels_min_rx_wqes(&priv->channels); mlx5e_redirect_rqts_to_channels(priv, &priv->channels); } -static void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) +void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) { mlx5e_redirect_rqts_to_drop(priv); - if (MLX5_CAP_GEN(priv->mdev, vport_group_manager)) + if (mlx5e_is_eswitch_vport_mngr(priv->mdev)) mlx5e_remove_sqs_fwd_rules(priv); /* FIXME: This is a W/A only for tx timeout watch dog false alarm when @@ -2659,31 +2715,7 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev, struct mlx5e_cq *cq, struct mlx5e_cq_param *param) { - struct mlx5_core_cq *mcq = &cq->mcq; - int eqn_not_used; - unsigned int irqn; - int err; - - err = mlx5_cqwq_create(mdev, ¶m->wq, param->cqc, &cq->wq, - &cq->wq_ctrl); - if (err) - return err; - - mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn); - - mcq->cqe_sz = 64; - mcq->set_ci_db = cq->wq_ctrl.db.db; - mcq->arm_db = cq->wq_ctrl.db.db + 1; - *mcq->set_ci_db = 0; - *mcq->arm_db = 0; - mcq->vector = param->eq_ix; - mcq->comp = mlx5e_completion_event; - mcq->event = mlx5e_cq_error_event; - mcq->irqn = irqn; - - cq->mdev = mdev; - - return 0; + return mlx5e_alloc_cq_common(mdev, param, cq); } static int mlx5e_open_drop_rq(struct mlx5_core_dev *mdev, @@ -2734,24 +2766,25 @@ static void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq) mlx5e_free_cq(&drop_rq->cq); } -static int mlx5e_create_tis(struct mlx5e_priv *priv, int tc) +int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc, + u32 underlay_qpn, u32 *tisn) { - struct mlx5_core_dev *mdev = priv->mdev; u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {0}; void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx); MLX5_SET(tisc, tisc, prio, tc << 1); + MLX5_SET(tisc, tisc, underlay_qpn, underlay_qpn); MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.td.tdn); if (mlx5_lag_is_lacp_owner(mdev)) MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1); - return mlx5_core_create_tis(mdev, in, sizeof(in), &priv->tisn[tc]); + return mlx5_core_create_tis(mdev, in, sizeof(in), tisn); } -static void mlx5e_destroy_tis(struct mlx5e_priv *priv, int tc) +void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn) { - mlx5_core_destroy_tis(priv->mdev, priv->tisn[tc]); + mlx5_core_destroy_tis(mdev, tisn); } int mlx5e_create_tises(struct mlx5e_priv *priv) @@ -2760,7 +2793,7 @@ int mlx5e_create_tises(struct mlx5e_priv *priv) int tc; for (tc = 0; tc < priv->profile->max_tc; tc++) { - err = mlx5e_create_tis(priv, tc); + err = mlx5e_create_tis(priv->mdev, tc, 0, &priv->tisn[tc]); if (err) goto err_close_tises; } @@ -2769,7 +2802,7 @@ int mlx5e_create_tises(struct mlx5e_priv *priv) err_close_tises: for (tc--; tc >= 0; tc--) - mlx5e_destroy_tis(priv, tc); + mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); return err; } @@ -2779,7 +2812,7 @@ void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) int tc; for (tc = 0; tc < priv->profile->max_tc; tc++) - mlx5e_destroy_tis(priv, tc); + mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); } static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, @@ -2806,7 +2839,7 @@ static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *t MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8); } -static int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv) +int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv) { struct mlx5e_tir *tir; void *tirc; @@ -2835,6 +2868,7 @@ static int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv) return 0; err_destroy_tirs: + mlx5_core_warn(priv->mdev, "create indirect tirs failed, %d\n", err); for (tt--; tt >= 0; tt--) mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[tt]); @@ -2873,6 +2907,7 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv) return 0; err_destroy_ch_tirs: + mlx5_core_warn(priv->mdev, "create direct tirs failed, %d\n", err); for (ix--; ix >= 0; ix--) mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[ix]); @@ -2881,7 +2916,7 @@ err_destroy_ch_tirs: return err; } -static void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv) +void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv) { int i; @@ -2898,7 +2933,21 @@ void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv) mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[i]); } -int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) +static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable) +{ + int err = 0; + int i; + + for (i = 0; i < chs->num; i++) { + err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable); + if (err) + return err; + } + + return 0; +} + +static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) { int err = 0; int i; @@ -3115,6 +3164,23 @@ static int set_feature_rx_all(struct net_device *netdev, bool enable) return mlx5_set_port_fcs(mdev, !enable); } +static int set_feature_rx_fcs(struct net_device *netdev, bool enable) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + int err; + + mutex_lock(&priv->state_lock); + + priv->channels.params.scatter_fcs_en = enable; + err = mlx5e_modify_channels_scatter_fcs(&priv->channels, enable); + if (err) + priv->channels.params.scatter_fcs_en = !enable; + + mutex_unlock(&priv->state_lock); + + return err; +} + static int set_feature_rx_vlan(struct net_device *netdev, bool enable) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -3188,6 +3254,8 @@ static int mlx5e_set_features(struct net_device *netdev, set_feature_tc_num_filters); err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXALL, set_feature_rx_all); + err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXFCS, + set_feature_rx_fcs); err |= mlx5e_handle_feature(netdev, features, NETIF_F_HW_VLAN_CTAG_RX, set_feature_rx_vlan); #ifdef CONFIG_RFS_ACCEL @@ -3729,6 +3797,10 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) params->rx_cq_moderation.usec = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE; + if (params->rx_am_enabled) + params->rx_cq_moderation = + mlx5e_am_get_def_profile(params->rx_cq_period_mode); + MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER, params->rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE); } @@ -3745,9 +3817,9 @@ u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]); } -static void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, - struct mlx5e_params *params, - u16 max_channels) +void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + u16 max_channels) { u8 cq_period_mode = 0; u32 link_speed = 0; @@ -3777,6 +3849,7 @@ static void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, mlx5e_set_rq_params(mdev, params); /* HW LRO */ + /* TODO: && MLX5_CAP_ETH(mdev, lro_cap) */ if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) params->lro_en = true; params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); @@ -3902,6 +3975,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) if (fcs_supported) netdev->hw_features |= NETIF_F_RXALL; + if (MLX5_CAP_ETH(mdev, scatter_fcs)) + netdev->hw_features |= NETIF_F_RXFCS; + netdev->features = netdev->hw_features; if (!priv->channels.params.lro_en) netdev->features &= ~NETIF_F_LRO; @@ -3909,6 +3985,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) if (fcs_enabled) netdev->features &= ~NETIF_F_RXALL; + if (!priv->channels.params.scatter_fcs_en) + netdev->features &= ~NETIF_F_RXFCS; + #define FT_CAP(f) MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.f) if (FT_CAP(flow_modify_en) && FT_CAP(modify_root) && @@ -3976,31 +4055,22 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; int err; - int i; - err = mlx5e_create_indirect_rqts(priv); - if (err) { - mlx5_core_warn(mdev, "create indirect rqts failed, %d\n", err); + err = mlx5e_create_indirect_rqt(priv); + if (err) return err; - } err = mlx5e_create_direct_rqts(priv); - if (err) { - mlx5_core_warn(mdev, "create direct rqts failed, %d\n", err); + if (err) goto err_destroy_indirect_rqts; - } err = mlx5e_create_indirect_tirs(priv); - if (err) { - mlx5_core_warn(mdev, "create indirect tirs failed, %d\n", err); + if (err) goto err_destroy_direct_rqts; - } err = mlx5e_create_direct_tirs(priv); - if (err) { - mlx5_core_warn(mdev, "create direct tirs failed, %d\n", err); + if (err) goto err_destroy_indirect_tirs; - } err = mlx5e_create_flow_steering(priv); if (err) { @@ -4021,8 +4091,7 @@ err_destroy_direct_tirs: err_destroy_indirect_tirs: mlx5e_destroy_indirect_tirs(priv); err_destroy_direct_rqts: - for (i = 0; i < priv->profile->max_nch(mdev); i++) - mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt); + mlx5e_destroy_direct_rqts(priv); err_destroy_indirect_rqts: mlx5e_destroy_rqt(priv, &priv->indir_rqt); return err; @@ -4030,14 +4099,11 @@ err_destroy_indirect_rqts: static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv) { - int i; - mlx5e_tc_cleanup(priv); mlx5e_destroy_flow_steering(priv); mlx5e_destroy_direct_tirs(priv); mlx5e_destroy_indirect_tirs(priv); - for (i = 0; i < priv->profile->max_nch(priv->mdev); i++) - mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt); + mlx5e_destroy_direct_rqts(priv); mlx5e_destroy_rqt(priv, &priv->indir_rqt); } @@ -4057,12 +4123,57 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv) return 0; } +static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev) +{ + struct mlx5_eswitch *esw = mdev->priv.eswitch; + int total_vfs = MLX5_TOTAL_VPORTS(mdev); + int vport; + u8 mac[ETH_ALEN]; + + if (!MLX5_CAP_GEN(mdev, vport_group_manager)) + return; + + mlx5_query_nic_vport_mac_address(mdev, 0, mac); + + for (vport = 1; vport < total_vfs; vport++) { + struct mlx5_eswitch_rep rep; + + rep.load = mlx5e_vport_rep_load; + rep.unload = mlx5e_vport_rep_unload; + rep.vport = vport; + ether_addr_copy(rep.hw_id, mac); + mlx5_eswitch_register_vport_rep(esw, vport, &rep); + } +} + +static void mlx5e_unregister_vport_rep(struct mlx5_core_dev *mdev) +{ + struct mlx5_eswitch *esw = mdev->priv.eswitch; + int total_vfs = MLX5_TOTAL_VPORTS(mdev); + int vport; + + if (!MLX5_CAP_GEN(mdev, vport_group_manager)) + return; + + for (vport = 1; vport < total_vfs; vport++) + mlx5_eswitch_unregister_vport_rep(esw, vport); +} + static void mlx5e_nic_enable(struct mlx5e_priv *priv) { struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_eswitch *esw = mdev->priv.eswitch; struct mlx5_eswitch_rep rep; + u16 max_mtu; + + mlx5e_init_l2_addr(priv); + + /* MTU range: 68 - hw-specific max */ + netdev->min_mtu = ETH_MIN_MTU; + mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1); + netdev->max_mtu = MLX5E_HW2SW_MTU(max_mtu); + mlx5e_set_dev_port_mtu(priv); mlx5_lag_add(mdev, netdev); @@ -4077,6 +4188,8 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) mlx5_eswitch_register_vport_rep(esw, 0, &rep); } + mlx5e_register_vport_rep(mdev); + if (netdev->reg_state != NETREG_REGISTERED) return; @@ -4088,6 +4201,12 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) } queue_work(priv->wq, &priv->set_rx_mode_work); + + rtnl_lock(); + if (netif_running(netdev)) + mlx5e_open(netdev); + netif_device_attach(netdev); + rtnl_unlock(); } static void mlx5e_nic_disable(struct mlx5e_priv *priv) @@ -4095,7 +4214,14 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_eswitch *esw = mdev->priv.eswitch; + rtnl_lock(); + if (netif_running(priv->netdev)) + mlx5e_close(priv->netdev); + netif_device_detach(priv->netdev); + rtnl_unlock(); + queue_work(priv->wq, &priv->set_rx_mode_work); + mlx5e_unregister_vport_rep(mdev); if (MLX5_CAP_GEN(mdev, vport_group_manager)) mlx5_eswitch_unregister_vport_rep(esw, 0); mlx5e_disable_async_events(priv); @@ -4113,9 +4239,13 @@ static const struct mlx5e_profile mlx5e_nic_profile = { .disable = mlx5e_nic_disable, .update_stats = mlx5e_update_stats, .max_nch = mlx5e_get_max_num_channels, + .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe, + .rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq, .max_tc = MLX5E_MAX_NUM_TC, }; +/* mlx5e generic netdev management API (move to en_common.c) */ + struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile, void *ppriv) @@ -4155,14 +4285,12 @@ err_cleanup_nic: return NULL; } -int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev) +int mlx5e_attach_netdev(struct mlx5e_priv *priv) { + struct mlx5_core_dev *mdev = priv->mdev; const struct mlx5e_profile *profile; - struct mlx5e_priv *priv; - u16 max_mtu; int err; - priv = netdev_priv(netdev); profile = priv->profile; clear_bit(MLX5E_STATE_DESTROYING, &priv->state); @@ -4182,24 +4310,9 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev) mlx5e_create_q_counter(priv); - mlx5e_init_l2_addr(priv); - - /* MTU range: 68 - hw-specific max */ - netdev->min_mtu = ETH_MIN_MTU; - mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1); - netdev->max_mtu = MLX5E_HW2SW_MTU(max_mtu); - - mlx5e_set_dev_port_mtu(priv); - if (profile->enable) profile->enable(priv); - rtnl_lock(); - if (netif_running(netdev)) - mlx5e_open(netdev); - netif_device_attach(netdev); - rtnl_unlock(); - return 0; err_close_drop_rq: @@ -4212,55 +4325,12 @@ out: return err; } -static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev) -{ - struct mlx5_eswitch *esw = mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(mdev); - int vport; - u8 mac[ETH_ALEN]; - - if (!MLX5_CAP_GEN(mdev, vport_group_manager)) - return; - - mlx5_query_nic_vport_mac_address(mdev, 0, mac); - - for (vport = 1; vport < total_vfs; vport++) { - struct mlx5_eswitch_rep rep; - - rep.load = mlx5e_vport_rep_load; - rep.unload = mlx5e_vport_rep_unload; - rep.vport = vport; - ether_addr_copy(rep.hw_id, mac); - mlx5_eswitch_register_vport_rep(esw, vport, &rep); - } -} - -static void mlx5e_unregister_vport_rep(struct mlx5_core_dev *mdev) +void mlx5e_detach_netdev(struct mlx5e_priv *priv) { - struct mlx5_eswitch *esw = mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(mdev); - int vport; - - if (!MLX5_CAP_GEN(mdev, vport_group_manager)) - return; - - for (vport = 1; vport < total_vfs; vport++) - mlx5_eswitch_unregister_vport_rep(esw, vport); -} - -void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev) -{ - struct mlx5e_priv *priv = netdev_priv(netdev); const struct mlx5e_profile *profile = priv->profile; set_bit(MLX5E_STATE_DESTROYING, &priv->state); - rtnl_lock(); - if (netif_running(netdev)) - mlx5e_close(netdev); - netif_device_detach(netdev); - rtnl_unlock(); - if (profile->disable) profile->disable(priv); flush_workqueue(priv->wq); @@ -4272,6 +4342,17 @@ void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev) cancel_delayed_work_sync(&priv->update_stats_work); } +void mlx5e_destroy_netdev(struct mlx5e_priv *priv) +{ + const struct mlx5e_profile *profile = priv->profile; + struct net_device *netdev = priv->netdev; + + destroy_workqueue(priv->wq); + if (profile->cleanup) + profile->cleanup(priv); + free_netdev(netdev); +} + /* mlx5e_attach and mlx5e_detach scope should be only creating/destroying * hardware contexts and to connect it to the current netdev. */ @@ -4288,13 +4369,12 @@ static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv) if (err) return err; - err = mlx5e_attach_netdev(mdev, netdev); + err = mlx5e_attach_netdev(priv); if (err) { mlx5e_destroy_mdev_resources(mdev); return err; } - mlx5e_register_vport_rep(mdev); return 0; } @@ -4306,8 +4386,7 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) if (!netif_device_present(netdev)) return; - mlx5e_unregister_vport_rep(mdev); - mlx5e_detach_netdev(mdev, netdev); + mlx5e_detach_netdev(priv); mlx5e_destroy_mdev_resources(mdev); } @@ -4354,7 +4433,7 @@ err_detach: mlx5e_detach(mdev, priv); err_destroy_netdev: - mlx5e_destroy_netdev(mdev, priv); + mlx5e_destroy_netdev(priv); err_unregister_reps: for (vport = 1; vport < total_vfs; vport++) @@ -4363,24 +4442,13 @@ err_unregister_reps: return NULL; } -void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv) -{ - const struct mlx5e_profile *profile = priv->profile; - struct net_device *netdev = priv->netdev; - - destroy_workqueue(priv->wq); - if (profile->cleanup) - profile->cleanup(priv); - free_netdev(netdev); -} - static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv) { struct mlx5e_priv *priv = vpriv; unregister_netdev(priv->netdev); mlx5e_detach(mdev, vpriv); - mlx5e_destroy_netdev(mdev, priv); + mlx5e_destroy_netdev(priv); } static void *mlx5e_get_netdev(void *vpriv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 53db5ec2c122..16b683e8226d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -329,7 +329,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) return false; } -bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv) +static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv) { struct mlx5_eswitch_rep *rep = (struct mlx5_eswitch_rep *)priv->ppriv; @@ -465,22 +465,18 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_eswitch_rep *rep = priv->ppriv; - struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_flow_handle *flow_rule; int err; - int i; + + mlx5e_init_l2_addr(priv); err = mlx5e_create_direct_rqts(priv); - if (err) { - mlx5_core_warn(mdev, "create direct rqts failed, %d\n", err); + if (err) return err; - } err = mlx5e_create_direct_tirs(priv); - if (err) { - mlx5_core_warn(mdev, "create direct tirs failed, %d\n", err); + if (err) goto err_destroy_direct_rqts; - } flow_rule = mlx5_eswitch_create_vport_rx_rule(esw, rep->vport, @@ -502,21 +498,18 @@ err_del_flow_rule: err_destroy_direct_tirs: mlx5e_destroy_direct_tirs(priv); err_destroy_direct_rqts: - for (i = 0; i < priv->channels.params.num_channels; i++) - mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt); + mlx5e_destroy_direct_rqts(priv); return err; } static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) { struct mlx5_eswitch_rep *rep = priv->ppriv; - int i; mlx5e_tc_cleanup(priv); mlx5_del_flow_rules(rep->vport_rx_rule); mlx5e_destroy_direct_tirs(priv); - for (i = 0; i < priv->channels.params.num_channels; i++) - mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt); + mlx5e_destroy_direct_rqts(priv); } static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) @@ -545,6 +538,8 @@ static struct mlx5e_profile mlx5e_rep_profile = { .cleanup_tx = mlx5e_cleanup_nic_tx, .update_stats = mlx5e_rep_update_stats, .max_nch = mlx5e_get_rep_max_num_channels, + .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep, + .rx_handlers.handle_rx_cqe_mpwqe = NULL /* Not supported */, .max_tc = 1, }; @@ -563,7 +558,7 @@ int mlx5e_vport_rep_load(struct mlx5_eswitch *esw, rep->netdev = netdev; - err = mlx5e_attach_netdev(esw->dev, netdev); + err = mlx5e_attach_netdev(netdev_priv(netdev)); if (err) { pr_warn("Failed to attach representor netdev for vport %d\n", rep->vport); @@ -580,10 +575,10 @@ int mlx5e_vport_rep_load(struct mlx5_eswitch *esw, return 0; err_detach_netdev: - mlx5e_detach_netdev(esw->dev, netdev); + mlx5e_detach_netdev(netdev_priv(netdev)); err_destroy_netdev: - mlx5e_destroy_netdev(esw->dev, netdev_priv(netdev)); + mlx5e_destroy_netdev(netdev_priv(netdev)); return err; @@ -595,6 +590,6 @@ void mlx5e_vport_rep_unload(struct mlx5_eswitch *esw, struct net_device *netdev = rep->netdev; unregister_netdev(netdev); - mlx5e_detach_netdev(esw->dev, netdev); - mlx5e_destroy_netdev(esw->dev, netdev_priv(netdev)); + mlx5e_detach_netdev(netdev_priv(netdev)); + mlx5e_destroy_netdev(netdev_priv(netdev)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 1a9532b31635..43308243f519 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1031,3 +1031,81 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) mlx5e_page_release(rq, di, false); } } + +#ifdef CONFIG_MLX5_CORE_IPOIB + +#define MLX5_IB_GRH_DGID_OFFSET 24 +#define MLX5_IB_GRH_BYTES 40 +#define MLX5_IPOIB_ENCAP_LEN 4 +#define MLX5_GID_SIZE 16 + +static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, + struct mlx5_cqe64 *cqe, + u32 cqe_bcnt, + struct sk_buff *skb) +{ + struct net_device *netdev = rq->netdev; + u8 *dgid; + u8 g; + + g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3; + dgid = skb->data + MLX5_IB_GRH_DGID_OFFSET; + if ((!g) || dgid[0] != 0xff) + skb->pkt_type = PACKET_HOST; + else if (memcmp(dgid, netdev->broadcast + 4, MLX5_GID_SIZE) == 0) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + + /* TODO: IB/ipoib: Allow mcast packets from other VFs + * 68996a6e760e5c74654723eeb57bf65628ae87f4 + */ + + skb_pull(skb, MLX5_IB_GRH_BYTES); + + skb->protocol = *((__be16 *)(skb->data)); + + skb->ip_summed = CHECKSUM_COMPLETE; + skb->csum = csum_unfold((__force __sum16)cqe->check_sum); + + skb_record_rx_queue(skb, rq->ix); + + if (likely(netdev->features & NETIF_F_RXHASH)) + mlx5e_skb_set_hash(cqe, skb); + + skb_reset_mac_header(skb); + skb_pull(skb, MLX5_IPOIB_ENCAP_LEN); + + skb->dev = netdev; + + rq->stats.csum_complete++; + rq->stats.packets++; + rq->stats.bytes += cqe_bcnt; +} + +void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) +{ + struct mlx5e_rx_wqe *wqe; + __be16 wqe_counter_be; + struct sk_buff *skb; + u16 wqe_counter; + u32 cqe_bcnt; + + wqe_counter_be = cqe->wqe_counter; + wqe_counter = be16_to_cpu(wqe_counter_be); + wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter); + cqe_bcnt = be32_to_cpu(cqe->byte_cnt); + + skb = skb_from_cqe(rq, cqe, wqe_counter, cqe_bcnt); + if (!skb) + goto wq_ll_pop; + + mlx5i_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); + napi_gro_receive(rq->cq.napi, skb); + +wq_ll_pop: + mlx5_wq_ll_pop(&rq->wq, wqe_counter_be, + &wqe->next.next_wqe_index); +} + +#endif /* CONFIG_MLX5_CORE_IPOIB */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 5bbc313e70c5..dda7db503043 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -177,30 +177,9 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs, mlx5e_tx_skb_pull_inline(skb_data, skb_len, cpy2_sz); } -static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb) +static inline void +mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) { - struct mlx5_wq_cyc *wq = &sq->wq; - - u16 pi = sq->pc & wq->sz_m1; - struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); - struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi]; - - struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; - struct mlx5_wqe_eth_seg *eseg = &wqe->eth; - struct mlx5_wqe_data_seg *dseg; - - unsigned char *skb_data = skb->data; - unsigned int skb_len = skb->len; - u8 opcode = MLX5_OPCODE_SEND; - dma_addr_t dma_addr = 0; - unsigned int num_bytes; - u16 headlen; - u16 ds_cnt; - u16 ihs; - int i; - - memset(wqe, 0, sizeof(*wqe)); - if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; if (skb->encapsulation) { @@ -212,66 +191,51 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb) } } else sq->stats.csum_none++; +} - if (skb_is_gso(skb)) { - eseg->mss = cpu_to_be16(skb_shinfo(skb)->gso_size); - opcode = MLX5_OPCODE_LSO; +static inline u16 +mlx5e_txwqe_build_eseg_gso(struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5_wqe_eth_seg *eseg, unsigned int *num_bytes) +{ + u16 ihs; - if (skb->encapsulation) { - ihs = skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb); - sq->stats.tso_inner_packets++; - sq->stats.tso_inner_bytes += skb->len - ihs; - } else { - ihs = skb_transport_offset(skb) + tcp_hdrlen(skb); - sq->stats.tso_packets++; - sq->stats.tso_bytes += skb->len - ihs; - } + eseg->mss = cpu_to_be16(skb_shinfo(skb)->gso_size); - sq->stats.packets += skb_shinfo(skb)->gso_segs; - num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; + if (skb->encapsulation) { + ihs = skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb); + sq->stats.tso_inner_packets++; + sq->stats.tso_inner_bytes += skb->len - ihs; } else { - ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb); - sq->stats.packets++; - num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); + ihs = skb_transport_offset(skb) + tcp_hdrlen(skb); + sq->stats.tso_packets++; + sq->stats.tso_bytes += skb->len - ihs; } - sq->stats.bytes += num_bytes; - wi->num_bytes = num_bytes; - - ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS; - if (ihs) { - if (skb_vlan_tag_present(skb)) { - mlx5e_insert_vlan(eseg->inline_hdr.start, skb, ihs, &skb_data, &skb_len); - ihs += VLAN_HLEN; - } else { - memcpy(eseg->inline_hdr.start, skb_data, ihs); - mlx5e_tx_skb_pull_inline(&skb_data, &skb_len, ihs); - } - eseg->inline_hdr.sz = cpu_to_be16(ihs); - ds_cnt += DIV_ROUND_UP(ihs - sizeof(eseg->inline_hdr.start), MLX5_SEND_WQE_DS); - } else if (skb_vlan_tag_present(skb)) { - eseg->insert.type = cpu_to_be16(MLX5_ETH_WQE_INSERT_VLAN); - eseg->insert.vlan_tci = cpu_to_be16(skb_vlan_tag_get(skb)); - } - - dseg = (struct mlx5_wqe_data_seg *)cseg + ds_cnt; + *num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; + return ihs; +} - wi->num_dma = 0; +static inline int +mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb, + unsigned char *skb_data, u16 headlen, + struct mlx5_wqe_data_seg *dseg) +{ + dma_addr_t dma_addr = 0; + u8 num_dma = 0; + int i; - headlen = skb_len - skb->data_len; if (headlen) { dma_addr = dma_map_single(sq->pdev, skb_data, headlen, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(sq->pdev, dma_addr))) - goto dma_unmap_wqe_err; + return -ENOMEM; dseg->addr = cpu_to_be64(dma_addr); dseg->lkey = sq->mkey_be; dseg->byte_count = cpu_to_be32(headlen); mlx5e_dma_push(sq, dma_addr, headlen, MLX5E_DMA_MAP_SINGLE); - wi->num_dma++; - + num_dma++; dseg++; } @@ -280,51 +244,120 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb) int fsz = skb_frag_size(frag); dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz, - DMA_TO_DEVICE); + DMA_TO_DEVICE); if (unlikely(dma_mapping_error(sq->pdev, dma_addr))) - goto dma_unmap_wqe_err; + return -ENOMEM; dseg->addr = cpu_to_be64(dma_addr); dseg->lkey = sq->mkey_be; dseg->byte_count = cpu_to_be32(fsz); mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE); - wi->num_dma++; - + num_dma++; dseg++; } - ds_cnt += wi->num_dma; - - cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode); - cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt); + return num_dma; +} - sq->db.skb[pi] = skb; +static inline void +mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, + u8 opcode, u16 ds_cnt, u32 num_bytes, u8 num_dma, + struct mlx5e_tx_wqe_info *wi, struct mlx5_wqe_ctrl_seg *cseg) +{ + struct mlx5_wq_cyc *wq = &sq->wq; + u16 pi; + wi->num_bytes = num_bytes; + wi->num_dma = num_dma; wi->num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS); - sq->pc += wi->num_wqebbs; + wi->skb = skb; - netdev_tx_sent_queue(sq->txq, wi->num_bytes); + cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode); + cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt); + + netdev_tx_sent_queue(sq->txq, num_bytes); if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, - MLX5E_SQ_STOP_ROOM))) { + sq->pc += wi->num_wqebbs; + if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, MLX5E_SQ_STOP_ROOM))) { netif_tx_stop_queue(sq->txq); sq->stats.stopped++; } - sq->stats.xmit_more += skb->xmit_more; if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg); /* fill sq edge with nops to avoid wqe wrap around */ while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) { - sq->db.skb[pi] = NULL; - mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc); + sq->db.wqe_info[pi].skb = NULL; + mlx5e_post_nop(wq, sq->sqn, &sq->pc); sq->stats.nop++; } +} + +static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb) +{ + struct mlx5_wq_cyc *wq = &sq->wq; + + u16 pi = sq->pc & wq->sz_m1; + struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); + struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi]; + + struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; + struct mlx5_wqe_eth_seg *eseg = &wqe->eth; + + unsigned char *skb_data = skb->data; + unsigned int skb_len = skb->len; + u8 opcode = MLX5_OPCODE_SEND; + unsigned int num_bytes; + int num_dma; + u16 headlen; + u16 ds_cnt; + u16 ihs; + + memset(wqe, 0, sizeof(*wqe)); + + mlx5e_txwqe_build_eseg_csum(sq, skb, eseg); + + if (skb_is_gso(skb)) { + opcode = MLX5_OPCODE_LSO; + ihs = mlx5e_txwqe_build_eseg_gso(sq, skb, eseg, &num_bytes); + sq->stats.packets += skb_shinfo(skb)->gso_segs; + } else { + ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb); + num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); + sq->stats.packets++; + } + sq->stats.bytes += num_bytes; + sq->stats.xmit_more += skb->xmit_more; + + ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS; + if (ihs) { + if (skb_vlan_tag_present(skb)) { + mlx5e_insert_vlan(eseg->inline_hdr.start, skb, ihs, &skb_data, &skb_len); + ihs += VLAN_HLEN; + } else { + memcpy(eseg->inline_hdr.start, skb_data, ihs); + mlx5e_tx_skb_pull_inline(&skb_data, &skb_len, ihs); + } + eseg->inline_hdr.sz = cpu_to_be16(ihs); + ds_cnt += DIV_ROUND_UP(ihs - sizeof(eseg->inline_hdr.start), MLX5_SEND_WQE_DS); + } else if (skb_vlan_tag_present(skb)) { + eseg->insert.type = cpu_to_be16(MLX5_ETH_WQE_INSERT_VLAN); + eseg->insert.vlan_tci = cpu_to_be16(skb_vlan_tag_get(skb)); + } + + headlen = skb_len - skb->data_len; + num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen, + (struct mlx5_wqe_data_seg *)cseg + ds_cnt); + if (unlikely(num_dma < 0)) + goto dma_unmap_wqe_err; + + mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma, + num_bytes, num_dma, wi, cseg); return NETDEV_TX_OK; @@ -392,8 +425,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) last_wqe = (sqcc == wqe_counter); ci = sqcc & sq->wq.sz_m1; - skb = sq->db.skb[ci]; wi = &sq->db.wqe_info[ci]; + skb = wi->skb; if (unlikely(!skb)) { /* nop */ sqcc++; @@ -451,8 +484,8 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq) while (sq->cc != sq->pc) { ci = sq->cc & sq->wq.sz_m1; - skb = sq->db.skb[ci]; wi = &sq->db.wqe_info[ci]; + skb = wi->skb; if (!skb) { /* nop */ sq->cc++; @@ -470,3 +503,90 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq) sq->cc += wi->num_wqebbs; } } + +#ifdef CONFIG_MLX5_CORE_IPOIB + +struct mlx5_wqe_eth_pad { + u8 rsvd0[16]; +}; + +struct mlx5i_tx_wqe { + struct mlx5_wqe_ctrl_seg ctrl; + struct mlx5_wqe_datagram_seg datagram; + struct mlx5_wqe_eth_pad pad; + struct mlx5_wqe_eth_seg eth; +}; + +static inline void +mlx5i_txwqe_build_datagram(struct mlx5_av *av, u32 dqpn, u32 dqkey, + struct mlx5_wqe_datagram_seg *dseg) +{ + memcpy(&dseg->av, av, sizeof(struct mlx5_av)); + dseg->av.dqp_dct = cpu_to_be32(dqpn | MLX5_EXTENDED_UD_AV); + dseg->av.key.qkey.qkey = cpu_to_be32(dqkey); +} + +netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5_av *av, u32 dqpn, u32 dqkey) +{ + struct mlx5_wq_cyc *wq = &sq->wq; + u16 pi = sq->pc & wq->sz_m1; + struct mlx5i_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); + struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi]; + + struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; + struct mlx5_wqe_datagram_seg *datagram = &wqe->datagram; + struct mlx5_wqe_eth_seg *eseg = &wqe->eth; + + unsigned char *skb_data = skb->data; + unsigned int skb_len = skb->len; + u8 opcode = MLX5_OPCODE_SEND; + unsigned int num_bytes; + int num_dma; + u16 headlen; + u16 ds_cnt; + u16 ihs; + + memset(wqe, 0, sizeof(*wqe)); + + mlx5i_txwqe_build_datagram(av, dqpn, dqkey, datagram); + + mlx5e_txwqe_build_eseg_csum(sq, skb, eseg); + + if (skb_is_gso(skb)) { + opcode = MLX5_OPCODE_LSO; + ihs = mlx5e_txwqe_build_eseg_gso(sq, skb, eseg, &num_bytes); + } else { + ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb); + num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); + } + + ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS; + if (ihs) { + memcpy(eseg->inline_hdr.start, skb_data, ihs); + mlx5e_tx_skb_pull_inline(&skb_data, &skb_len, ihs); + eseg->inline_hdr.sz = cpu_to_be16(ihs); + ds_cnt += DIV_ROUND_UP(ihs - sizeof(eseg->inline_hdr.start), MLX5_SEND_WQE_DS); + } + + headlen = skb_len - skb->data_len; + num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen, + (struct mlx5_wqe_data_seg *)cseg + ds_cnt); + if (unlikely(num_dma < 0)) + goto dma_unmap_wqe_err; + + mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma, + num_bytes, num_dma, wi, cseg); + + return NETDEV_TX_OK; + +dma_unmap_wqe_err: + sq->stats.dropped++; + mlx5e_dma_unmap_wqe_err(sq, wi->num_dma); + + dev_kfree_skb_any(skb); + + return NETDEV_TX_OK; +} + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index fcd5bc7e31db..b3281d1118b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -337,6 +337,7 @@ esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport) static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_core_dev *dev = esw->dev; struct mlx5_flow_namespace *root_ns; struct mlx5_flow_table *fdb; @@ -362,7 +363,9 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports) memset(flow_group_in, 0, inlen); table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size)); - fdb = mlx5_create_flow_table(root_ns, 0, table_size, 0, 0); + + ft_attr.max_fte = table_size; + fdb = mlx5_create_flow_table(root_ns, &ft_attr); if (IS_ERR(fdb)) { err = PTR_ERR(fdb); esw_warn(dev, "Failed to create FDB Table err %d\n", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index fff962dac8e3..992b380d36be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -432,6 +432,7 @@ out: static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_table_attr ft_attr = {}; int table_size, ix, esw_size, err = 0; struct mlx5_core_dev *dev = esw->dev; struct mlx5_flow_namespace *root_ns; @@ -475,7 +476,11 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports) esw->fdb_table.fdb = fdb; table_size = nvports + MAX_PF_SQ + 1; - fdb = mlx5_create_flow_table(root_ns, FDB_SLOW_PATH, table_size, 0, 0); + + ft_attr.max_fte = table_size; + ft_attr.prio = FDB_SLOW_PATH; + + fdb = mlx5_create_flow_table(root_ns, &ft_attr); if (IS_ERR(fdb)) { err = PTR_ERR(fdb); esw_warn(dev, "Failed to create slow path FDB Table err %d\n", err); @@ -556,9 +561,10 @@ static void esw_destroy_offloads_fdb_table(struct mlx5_eswitch *esw) static int esw_create_offloads_table(struct mlx5_eswitch *esw) { - struct mlx5_flow_namespace *ns; - struct mlx5_flow_table *ft_offloads; + struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_table *ft_offloads; + struct mlx5_flow_namespace *ns; int err = 0; ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_OFFLOADS); @@ -567,7 +573,9 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw) return -EOPNOTSUPP; } - ft_offloads = mlx5_create_flow_table(ns, 0, dev->priv.sriov.num_vfs + 2, 0, 0); + ft_attr.max_fte = dev->priv.sriov.num_vfs + 2; + + ft_offloads = mlx5_create_flow_table(ns, &ft_attr); if (IS_ERR(ft_offloads)) { err = PTR_ERR(ft_offloads); esw_warn(esw->dev, "Failed to create offloads table, err %d\n", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index c6178ea1a461..19e3d2fc2099 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -45,6 +45,10 @@ int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {0}; u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {0}; + if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) && + ft->underlay_qpn == 0) + return 0; + MLX5_SET(set_flow_table_root_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ROOT); MLX5_SET(set_flow_table_root_in, in, table_type, ft->type); @@ -54,6 +58,10 @@ int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, MLX5_SET(set_flow_table_root_in, in, other_vport, 1); } + if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) && + ft->underlay_qpn != 0) + MLX5_SET(set_flow_table_root_in, in, underlay_qpn, ft->underlay_qpn); + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 27ff815600f7..b8a176503d38 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -778,18 +778,16 @@ static void list_add_flow_table(struct mlx5_flow_table *ft, } static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespace *ns, + struct mlx5_flow_table_attr *ft_attr, enum fs_flow_table_op_mod op_mod, - u16 vport, int prio, - int max_fte, u32 level, - u32 flags) + u16 vport) { + struct mlx5_flow_root_namespace *root = find_root(&ns->node); struct mlx5_flow_table *next_ft = NULL; + struct fs_prio *fs_prio = NULL; struct mlx5_flow_table *ft; - int err; int log_table_sz; - struct mlx5_flow_root_namespace *root = - find_root(&ns->node); - struct fs_prio *fs_prio = NULL; + int err; if (!root) { pr_err("mlx5: flow steering failed to find root of namespace\n"); @@ -797,29 +795,31 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa } mutex_lock(&root->chain_lock); - fs_prio = find_prio(ns, prio); + fs_prio = find_prio(ns, ft_attr->prio); if (!fs_prio) { err = -EINVAL; goto unlock_root; } - if (level >= fs_prio->num_levels) { + if (ft_attr->level >= fs_prio->num_levels) { err = -ENOSPC; goto unlock_root; } /* The level is related to the * priority level range. */ - level += fs_prio->start_level; - ft = alloc_flow_table(level, + ft_attr->level += fs_prio->start_level; + ft = alloc_flow_table(ft_attr->level, vport, - max_fte ? roundup_pow_of_two(max_fte) : 0, + ft_attr->max_fte ? roundup_pow_of_two(ft_attr->max_fte) : 0, root->table_type, - op_mod, flags); + op_mod, ft_attr->flags); if (!ft) { err = -ENOMEM; goto unlock_root; } + ft->underlay_qpn = ft_attr->underlay_qpn; + tree_init_node(&ft->node, 1, del_flow_table); log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0; next_ft = find_next_chained_ft(fs_prio); @@ -849,44 +849,56 @@ unlock_root: } struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns, - int prio, int max_fte, - u32 level, - u32 flags) + struct mlx5_flow_table_attr *ft_attr) { - return __mlx5_create_flow_table(ns, FS_FT_OP_MOD_NORMAL, 0, prio, - max_fte, level, flags); + return __mlx5_create_flow_table(ns, ft_attr, FS_FT_OP_MOD_NORMAL, 0); } struct mlx5_flow_table *mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns, int prio, int max_fte, u32 level, u16 vport) { - return __mlx5_create_flow_table(ns, FS_FT_OP_MOD_NORMAL, vport, prio, - max_fte, level, 0); + struct mlx5_flow_table_attr ft_attr = {}; + + ft_attr.max_fte = max_fte; + ft_attr.level = level; + ft_attr.prio = prio; + + return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_NORMAL, 0); } -struct mlx5_flow_table *mlx5_create_lag_demux_flow_table( - struct mlx5_flow_namespace *ns, - int prio, u32 level) +struct mlx5_flow_table* +mlx5_create_lag_demux_flow_table(struct mlx5_flow_namespace *ns, + int prio, u32 level) { - return __mlx5_create_flow_table(ns, FS_FT_OP_MOD_LAG_DEMUX, 0, prio, 0, - level, 0); + struct mlx5_flow_table_attr ft_attr = {}; + + ft_attr.level = level; + ft_attr.prio = prio; + return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_LAG_DEMUX, 0); } EXPORT_SYMBOL(mlx5_create_lag_demux_flow_table); -struct mlx5_flow_table *mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, - int prio, - int num_flow_table_entries, - int max_num_groups, - u32 level, - u32 flags) +struct mlx5_flow_table* +mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, + int prio, + int num_flow_table_entries, + int max_num_groups, + u32 level, + u32 flags) { + struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_flow_table *ft; if (max_num_groups > num_flow_table_entries) return ERR_PTR(-EINVAL); - ft = mlx5_create_flow_table(ns, prio, num_flow_table_entries, level, flags); + ft_attr.max_fte = num_flow_table_entries; + ft_attr.prio = prio; + ft_attr.level = level; + ft_attr.flags = flags; + + ft = mlx5_create_flow_table(ns, &ft_attr); if (IS_ERR(ft)) return ft; @@ -1828,12 +1840,18 @@ static void set_prio_attrs(struct mlx5_flow_root_namespace *root_ns) static int create_anchor_flow_table(struct mlx5_flow_steering *steering) { struct mlx5_flow_namespace *ns = NULL; + struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_flow_table *ft; ns = mlx5_get_flow_namespace(steering->dev, MLX5_FLOW_NAMESPACE_ANCHOR); if (WARN_ON(!ns)) return -EINVAL; - ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE, ANCHOR_LEVEL, 0); + + ft_attr.max_fte = ANCHOR_SIZE; + ft_attr.level = ANCHOR_LEVEL; + ft_attr.prio = ANCHOR_PRIO; + + ft = mlx5_create_flow_table(ns, &ft_attr); if (IS_ERR(ft)) { mlx5_core_err(steering->dev, "Failed to create last anchor flow table"); return PTR_ERR(ft); @@ -1887,9 +1905,6 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev) { struct mlx5_flow_steering *steering = dev->priv.steering; - if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) - return; - cleanup_root_ns(steering->root_ns); cleanup_root_ns(steering->esw_egress_root_ns); cleanup_root_ns(steering->esw_ingress_root_ns); @@ -1992,9 +2007,6 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) struct mlx5_flow_steering *steering; int err = 0; - if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) - return 0; - err = mlx5_init_fc_stats(dev); if (err) return err; @@ -2005,7 +2017,10 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) steering->dev = dev; dev->priv.steering = steering; - if (MLX5_CAP_GEN(dev, nic_flow_table) && + if ((((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && + (MLX5_CAP_GEN(dev, nic_flow_table))) || + ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) && + MLX5_CAP_GEN(dev, ipoib_enhanced_offloads))) && MLX5_CAP_FLOWTABLE_NIC_RX(dev, ft_support)) { err = init_root_ns(steering); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 03af2e7989f3..577d056bf3df 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -118,6 +118,7 @@ struct mlx5_flow_table { /* FWD rules that point on this flow table */ struct list_head fwd_rules; u32 flags; + u32 underlay_qpn; }; struct mlx5_fc_cache { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index d0bbefa08af7..1bc14d0fded8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -137,7 +137,8 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } - if (MLX5_CAP_GEN(dev, nic_flow_table)) { + if (MLX5_CAP_GEN(dev, nic_flow_table) || + MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) { err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c new file mode 100644 index 000000000000..ec78e637840f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c @@ -0,0 +1,496 @@ +/* + * Copyright (c) 2017, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/mlx5/fs.h> +#include "en.h" +#include "ipoib.h" + +#define IB_DEFAULT_Q_KEY 0xb1b + +static int mlx5i_open(struct net_device *netdev); +static int mlx5i_close(struct net_device *netdev); +static int mlx5i_dev_init(struct net_device *dev); +static void mlx5i_dev_cleanup(struct net_device *dev); + +static const struct net_device_ops mlx5i_netdev_ops = { + .ndo_open = mlx5i_open, + .ndo_stop = mlx5i_close, + .ndo_init = mlx5i_dev_init, + .ndo_uninit = mlx5i_dev_cleanup, +}; + +/* IPoIB mlx5 netdev profile */ + +/* Called directly after IPoIB netdevice was created to initialize SW structs */ +static void mlx5i_init(struct mlx5_core_dev *mdev, + struct net_device *netdev, + const struct mlx5e_profile *profile, + void *ppriv) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + + priv->mdev = mdev; + priv->netdev = netdev; + priv->profile = profile; + priv->ppriv = ppriv; + + mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev)); + + mutex_init(&priv->state_lock); + + netdev->hw_features |= NETIF_F_SG; + netdev->hw_features |= NETIF_F_IP_CSUM; + netdev->hw_features |= NETIF_F_IPV6_CSUM; + netdev->hw_features |= NETIF_F_GRO; + netdev->hw_features |= NETIF_F_TSO; + netdev->hw_features |= NETIF_F_TSO6; + netdev->hw_features |= NETIF_F_RXCSUM; + netdev->hw_features |= NETIF_F_RXHASH; + + netdev->netdev_ops = &mlx5i_netdev_ops; +} + +/* Called directly before IPoIB netdevice is destroyed to cleanup SW structs */ +static void mlx5i_cleanup(struct mlx5e_priv *priv) +{ + /* Do nothing .. */ +} + +#define MLX5_QP_ENHANCED_ULP_STATELESS_MODE 2 + +static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) +{ + struct mlx5_qp_context *context = NULL; + u32 *in = NULL; + void *addr_path; + int ret = 0; + int inlen; + void *qpc; + + inlen = MLX5_ST_SZ_BYTES(create_qp_in); + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); + MLX5_SET(qpc, qpc, st, MLX5_QP_ST_UD); + MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED); + MLX5_SET(qpc, qpc, ulp_stateless_offload_mode, + MLX5_QP_ENHANCED_ULP_STATELESS_MODE); + + addr_path = MLX5_ADDR_OF(qpc, qpc, primary_address_path); + MLX5_SET(ads, addr_path, port, 1); + MLX5_SET(ads, addr_path, grh, 1); + + ret = mlx5_core_create_qp(mdev, qp, in, inlen); + if (ret) { + mlx5_core_err(mdev, "Failed creating IPoIB QP err : %d\n", ret); + goto out; + } + + /* QP states */ + context = kzalloc(sizeof(*context), GFP_KERNEL); + if (!context) { + ret = -ENOMEM; + goto out; + } + + context->flags = cpu_to_be32(MLX5_QP_PM_MIGRATED << 11); + context->pri_path.port = 1; + context->qkey = cpu_to_be32(IB_DEFAULT_Q_KEY); + + ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, context, qp); + if (ret) { + mlx5_core_err(mdev, "Failed to modify qp RST2INIT, err: %d\n", ret); + goto out; + } + memset(context, 0, sizeof(*context)); + + ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, context, qp); + if (ret) { + mlx5_core_err(mdev, "Failed to modify qp INIT2RTR, err: %d\n", ret); + goto out; + } + + ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, context, qp); + if (ret) { + mlx5_core_err(mdev, "Failed to modify qp RTR2RTS, err: %d\n", ret); + goto out; + } + +out: + kfree(context); + kvfree(in); + return ret; +} + +static void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) +{ + mlx5_core_destroy_qp(mdev, qp); +} + +static int mlx5i_init_tx(struct mlx5e_priv *priv) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + int err; + + err = mlx5i_create_underlay_qp(priv->mdev, &ipriv->qp); + if (err) { + mlx5_core_warn(priv->mdev, "create underlay QP failed, %d\n", err); + return err; + } + + err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]); + if (err) { + mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err); + return err; + } + + return 0; +} + +void mlx5i_cleanup_tx(struct mlx5e_priv *priv) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + + mlx5e_destroy_tis(priv->mdev, priv->tisn[0]); + mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp); +} + +static int mlx5i_create_flow_steering(struct mlx5e_priv *priv) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + int err; + + priv->fs.ns = mlx5_get_flow_namespace(priv->mdev, + MLX5_FLOW_NAMESPACE_KERNEL); + + if (!priv->fs.ns) + return -EINVAL; + + err = mlx5e_arfs_create_tables(priv); + if (err) { + netdev_err(priv->netdev, "Failed to create arfs tables, err=%d\n", + err); + priv->netdev->hw_features &= ~NETIF_F_NTUPLE; + } + + err = mlx5e_create_ttc_table(priv, ipriv->qp.qpn); + if (err) { + netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n", + err); + goto err_destroy_arfs_tables; + } + + return 0; + +err_destroy_arfs_tables: + mlx5e_arfs_destroy_tables(priv); + + return err; +} + +static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) +{ + mlx5e_destroy_ttc_table(priv); + mlx5e_arfs_destroy_tables(priv); +} + +static int mlx5i_init_rx(struct mlx5e_priv *priv) +{ + int err; + + err = mlx5e_create_indirect_rqt(priv); + if (err) + return err; + + err = mlx5e_create_direct_rqts(priv); + if (err) + goto err_destroy_indirect_rqts; + + err = mlx5e_create_indirect_tirs(priv); + if (err) + goto err_destroy_direct_rqts; + + err = mlx5e_create_direct_tirs(priv); + if (err) + goto err_destroy_indirect_tirs; + + err = mlx5i_create_flow_steering(priv); + if (err) + goto err_destroy_direct_tirs; + + return 0; + +err_destroy_direct_tirs: + mlx5e_destroy_direct_tirs(priv); +err_destroy_indirect_tirs: + mlx5e_destroy_indirect_tirs(priv); +err_destroy_direct_rqts: + mlx5e_destroy_direct_rqts(priv); +err_destroy_indirect_rqts: + mlx5e_destroy_rqt(priv, &priv->indir_rqt); + return err; +} + +static void mlx5i_cleanup_rx(struct mlx5e_priv *priv) +{ + mlx5i_destroy_flow_steering(priv); + mlx5e_destroy_direct_tirs(priv); + mlx5e_destroy_indirect_tirs(priv); + mlx5e_destroy_direct_rqts(priv); + mlx5e_destroy_rqt(priv, &priv->indir_rqt); +} + +static const struct mlx5e_profile mlx5i_nic_profile = { + .init = mlx5i_init, + .cleanup = mlx5i_cleanup, + .init_tx = mlx5i_init_tx, + .cleanup_tx = mlx5i_cleanup_tx, + .init_rx = mlx5i_init_rx, + .cleanup_rx = mlx5i_cleanup_rx, + .enable = NULL, /* mlx5i_enable */ + .disable = NULL, /* mlx5i_disable */ + .update_stats = NULL, /* mlx5i_update_stats */ + .max_nch = mlx5e_get_max_num_channels, + .rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe, + .rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */ + .max_tc = MLX5I_MAX_NUM_TC, +}; + +/* mlx5i netdev NDos */ + +static int mlx5i_dev_init(struct net_device *dev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + struct mlx5i_priv *ipriv = priv->ppriv; + + /* Set dev address using underlay QP */ + dev->dev_addr[1] = (ipriv->qp.qpn >> 16) & 0xff; + dev->dev_addr[2] = (ipriv->qp.qpn >> 8) & 0xff; + dev->dev_addr[3] = (ipriv->qp.qpn) & 0xff; + + return 0; +} + +static void mlx5i_dev_cleanup(struct net_device *dev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5i_priv *ipriv = priv->ppriv; + struct mlx5_qp_context context; + + /* detach qp from flow-steering by reset it */ + mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2RST_QP, 0, &context, &ipriv->qp); +} + +static int mlx5i_open(struct net_device *netdev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + int err; + + mutex_lock(&priv->state_lock); + + set_bit(MLX5E_STATE_OPENED, &priv->state); + + err = mlx5e_open_channels(priv, &priv->channels); + if (err) + goto err_clear_state_opened_flag; + + mlx5e_refresh_tirs(priv, false); + mlx5e_activate_priv_channels(priv); + mutex_unlock(&priv->state_lock); + return 0; + +err_clear_state_opened_flag: + clear_bit(MLX5E_STATE_OPENED, &priv->state); + mutex_unlock(&priv->state_lock); + return err; +} + +static int mlx5i_close(struct net_device *netdev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + + /* May already be CLOSED in case a previous configuration operation + * (e.g RX/TX queue size change) that involves close&open failed. + */ + mutex_lock(&priv->state_lock); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto unlock; + + clear_bit(MLX5E_STATE_OPENED, &priv->state); + + netif_carrier_off(priv->netdev); + mlx5e_deactivate_priv_channels(priv); + mlx5e_close_channels(&priv->channels); +unlock: + mutex_unlock(&priv->state_lock); + return 0; +} + +/* IPoIB RDMA netdev callbacks */ +int mlx5i_attach_mcast(struct net_device *netdev, struct ib_device *hca, + union ib_gid *gid, u16 lid, int set_qkey) +{ + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5_core_dev *mdev = epriv->mdev; + struct mlx5i_priv *ipriv = epriv->ppriv; + int err; + + mlx5_core_dbg(mdev, "attaching QPN 0x%x, MGID %pI6\n", ipriv->qp.qpn, gid->raw); + err = mlx5_core_attach_mcg(mdev, gid, ipriv->qp.qpn); + if (err) + mlx5_core_warn(mdev, "failed attaching QPN 0x%x, MGID %pI6\n", + ipriv->qp.qpn, gid->raw); + + return err; +} + +int mlx5i_detach_mcast(struct net_device *netdev, struct ib_device *hca, + union ib_gid *gid, u16 lid) +{ + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5_core_dev *mdev = epriv->mdev; + struct mlx5i_priv *ipriv = epriv->ppriv; + int err; + + mlx5_core_dbg(mdev, "detaching QPN 0x%x, MGID %pI6\n", ipriv->qp.qpn, gid->raw); + + err = mlx5_core_detach_mcg(mdev, gid, ipriv->qp.qpn); + if (err) + mlx5_core_dbg(mdev, "failed dettaching QPN 0x%x, MGID %pI6\n", + ipriv->qp.qpn, gid->raw); + + return err; +} + +int mlx5i_xmit(struct net_device *dev, struct sk_buff *skb, + struct ib_ah *address, u32 dqpn, u32 dqkey) +{ + struct mlx5e_priv *epriv = mlx5i_epriv(dev); + struct mlx5e_txqsq *sq = epriv->txq2sq[skb_get_queue_mapping(skb)]; + struct mlx5_ib_ah *mah = to_mah(address); + + return mlx5i_sq_xmit(sq, skb, &mah->av, dqpn, dqkey); +} + +static int mlx5i_check_required_hca_cap(struct mlx5_core_dev *mdev) +{ + if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_IB) + return -EOPNOTSUPP; + + if (!MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads)) { + mlx5_core_warn(mdev, "IPoIB enhanced offloads are not supported\n"); + return -ENOTSUPP; + } + + return 0; +} + +struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, + struct ib_device *ibdev, + const char *name, + void (*setup)(struct net_device *)) +{ + const struct mlx5e_profile *profile = &mlx5i_nic_profile; + int nch = profile->max_nch(mdev); + struct net_device *netdev; + struct mlx5i_priv *ipriv; + struct mlx5e_priv *epriv; + int err; + + if (mlx5i_check_required_hca_cap(mdev)) { + mlx5_core_warn(mdev, "Accelerated mode is not supported\n"); + return ERR_PTR(-EOPNOTSUPP); + } + + /* This function should only be called once per mdev */ + err = mlx5e_create_mdev_resources(mdev); + if (err) + return NULL; + + netdev = alloc_netdev_mqs(sizeof(struct mlx5i_priv) + sizeof(struct mlx5e_priv), + name, NET_NAME_UNKNOWN, + setup, + nch * MLX5E_MAX_NUM_TC, + nch); + if (!netdev) { + mlx5_core_warn(mdev, "alloc_netdev_mqs failed\n"); + goto free_mdev_resources; + } + + ipriv = netdev_priv(netdev); + epriv = mlx5i_epriv(netdev); + + epriv->wq = create_singlethread_workqueue("mlx5i"); + if (!epriv->wq) + goto err_free_netdev; + + profile->init(mdev, netdev, profile, ipriv); + + mlx5e_attach_netdev(epriv); + netif_carrier_off(netdev); + + /* TODO: set rdma_netdev func pointers + * rn = &ipriv->rn; + * rn->hca = ibdev; + * rn->send = mlx5i_xmit; + * rn->attach_mcast = mlx5i_attach_mcast; + * rn->detach_mcast = mlx5i_detach_mcast; + */ + return netdev; + +err_free_netdev: + free_netdev(netdev); +free_mdev_resources: + mlx5e_destroy_mdev_resources(mdev); + + return NULL; +} +EXPORT_SYMBOL(mlx5_rdma_netdev_alloc); + +void mlx5_rdma_netdev_free(struct net_device *netdev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + const struct mlx5e_profile *profile = priv->profile; + + mlx5e_detach_netdev(priv); + profile->cleanup(priv); + destroy_workqueue(priv->wq); + free_netdev(netdev); + + mlx5e_destroy_mdev_resources(priv->mdev); +} +EXPORT_SYMBOL(mlx5_rdma_netdev_free); + diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.h new file mode 100644 index 000000000000..bae0a5cbc8ad --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.h @@ -0,0 +1,54 @@ +/* + * Copyright (c) 2017, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __MLX5E_IPOB_H__ +#define __MLX5E_IPOB_H__ + +#include <linux/mlx5/fs.h> +#include "en.h" + +#define MLX5I_MAX_NUM_TC 1 + +/* ipoib rdma netdev's private data structure */ +struct mlx5i_priv { + struct mlx5_core_qp qp; + char *mlx5e_priv[0]; +}; + +/* Extract mlx5e_priv from IPoIB netdev */ +#define mlx5i_epriv(netdev) ((void *)(((struct mlx5i_priv *)netdev_priv(netdev))->mlx5e_priv)) + +netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5_av *av, u32 dqpn, u32 dqkey); +void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); + +#endif /* __MLX5E_IPOB_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 55957246c0e8..b5d5519542e8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -294,7 +294,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, struct netdev_notifier_changeupper_info *info) { struct net_device *upper = info->upper_dev, *ndev_tmp; - struct netdev_lag_upper_info *lag_upper_info; + struct netdev_lag_upper_info *lag_upper_info = NULL; bool is_bonded; int bond_status = 0; int num_slaves = 0; @@ -303,7 +303,8 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, if (!netif_is_lag_master(upper)) return 0; - lag_upper_info = info->upper_info; + if (info->linking) + lag_upper_info = info->upper_info; /* The event may still be of interest if the slave does not belong to * us, but is enslaved to a master which has one or more of our netdevs diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 60154a175bd3..9c2bec732af9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1514,8 +1514,10 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1016), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4LX VF */ { PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5, PCIe 3.0 */ { PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 VF */ - { PCI_VDEVICE(MELLANOX, 0x1019) }, /* ConnectX-5, PCIe 4.0 */ - { PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5, PCIe 4.0 VF */ + { PCI_VDEVICE(MELLANOX, 0x1019) }, /* ConnectX-5 Ex */ + { PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 Ex VF */ + { PCI_VDEVICE(MELLANOX, 0x101b) }, /* ConnectX-6 */ + { PCI_VDEVICE(MELLANOX, 0x101c), MLX5_PCI_DEV_IS_VF}, /* ConnectX-6 VF */ { 0, } }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index a984c361926c..46304ffb9449 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -811,3 +811,47 @@ int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block, return 0; } EXPORT_SYMBOL(mlxsw_afa_block_append_counter); + +/* Virtual Router and Forwarding Domain Action + * ------------------------------------------- + * Virtual Switch action is used for manipulate the Virtual Router (VR), + * MPLS label space and the Forwarding Identifier (FID). + */ + +#define MLXSW_AFA_VIRFWD_CODE 0x0E +#define MLXSW_AFA_VIRFWD_SIZE 1 + +enum mlxsw_afa_virfwd_fid_cmd { + /* Do nothing */ + MLXSW_AFA_VIRFWD_FID_CMD_NOOP, + /* Set the Forwarding Identifier (FID) to fid */ + MLXSW_AFA_VIRFWD_FID_CMD_SET, +}; + +/* afa_virfwd_fid_cmd */ +MLXSW_ITEM32(afa, virfwd, fid_cmd, 0x08, 29, 3); + +/* afa_virfwd_fid + * The FID value. + */ +MLXSW_ITEM32(afa, virfwd, fid, 0x08, 0, 16); + +static inline void mlxsw_afa_virfwd_pack(char *payload, + enum mlxsw_afa_virfwd_fid_cmd fid_cmd, + u16 fid) +{ + mlxsw_afa_virfwd_fid_cmd_set(payload, fid_cmd); + mlxsw_afa_virfwd_fid_set(payload, fid); +} + +int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid) +{ + char *act = mlxsw_afa_block_append_action(block, + MLXSW_AFA_VIRFWD_CODE, + MLXSW_AFA_VIRFWD_SIZE); + if (!act) + return -ENOBUFS; + mlxsw_afa_virfwd_pack(act, MLXSW_AFA_VIRFWD_FID_CMD_SET, fid); + return 0; +} +EXPORT_SYMBOL(mlxsw_afa_block_append_fid_set); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index a03362c1ef32..bd8b91d02880 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -66,5 +66,6 @@ int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block, u16 vid, u8 pcp, u8 et); int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block, u32 counter_index); +int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index eaa3e3bf5a2b..23f7d828cf67 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -136,7 +136,6 @@ struct mlxsw_pci { u8 __iomem *hw_addr; struct mlxsw_pci_queue_type_group queues[MLXSW_PCI_QUEUE_TYPE_COUNT]; u32 doorbell_offset; - struct msix_entry msix_entry; struct mlxsw_core *core; struct { struct mlxsw_pci_mem_item *items; @@ -1409,7 +1408,7 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, if (err) goto err_aqs_init; - err = request_irq(mlxsw_pci->msix_entry.vector, + err = request_irq(pci_irq_vector(pdev, 0), mlxsw_pci_eq_irq_handler, 0, mlxsw_pci->bus_info.device_kind, mlxsw_pci); if (err) { @@ -1442,7 +1441,7 @@ static void mlxsw_pci_fini(void *bus_priv) { struct mlxsw_pci *mlxsw_pci = bus_priv; - free_irq(mlxsw_pci->msix_entry.vector, mlxsw_pci); + free_irq(pci_irq_vector(mlxsw_pci->pdev, 0), mlxsw_pci); mlxsw_pci_aqs_fini(mlxsw_pci); mlxsw_pci_fw_area_fini(mlxsw_pci); mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox); @@ -1717,8 +1716,8 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_sw_reset; } - err = pci_enable_msix_exact(pdev, &mlxsw_pci->msix_entry, 1); - if (err) { + err = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSIX); + if (err < 0) { dev_err(&pdev->dev, "MSI-X init failed\n"); goto err_msix_init; } @@ -1737,7 +1736,7 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; err_bus_device_register: - pci_disable_msix(mlxsw_pci->pdev); + pci_free_irq_vectors(mlxsw_pci->pdev); err_msix_init: err_sw_reset: iounmap(mlxsw_pci->hw_addr); @@ -1757,7 +1756,7 @@ static void mlxsw_pci_remove(struct pci_dev *pdev) struct mlxsw_pci *mlxsw_pci = pci_get_drvdata(pdev); mlxsw_core_bus_device_unregister(mlxsw_pci->core); - pci_disable_msix(mlxsw_pci->pdev); + pci_free_irq_vectors(mlxsw_pci->pdev); iounmap(mlxsw_pci->hw_addr); pci_release_regions(mlxsw_pci->pdev); pci_disable_device(mlxsw_pci->pdev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index b031f09bf4e6..20c1b6c2dba0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1061,8 +1061,9 @@ mlxsw_sp_port_get_stats64(struct net_device *dev, memcpy(stats, mlxsw_sp_port->hw_stats.cache, sizeof(*stats)); } -int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin, - u16 vid_end, bool is_member, bool untagged) +static int __mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, + u16 vid_begin, u16 vid_end, + bool is_member, bool untagged) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char *spvm_pl; @@ -1079,6 +1080,26 @@ int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin, return err; } +int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin, + u16 vid_end, bool is_member, bool untagged) +{ + u16 vid, vid_e; + int err; + + for (vid = vid_begin; vid <= vid_end; + vid += MLXSW_REG_SPVM_REC_MAX_COUNT) { + vid_e = min((u16) (vid + MLXSW_REG_SPVM_REC_MAX_COUNT - 1), + vid_end); + + err = __mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid_e, + is_member, untagged); + if (err) + return err; + } + + return 0; +} + static int mlxsw_sp_port_vp_mode_trans(struct mlxsw_sp_port *mlxsw_sp_port) { enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID; @@ -2987,6 +3008,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_NO_MARK(IGMP_V3_REPORT, TRAP_TO_CPU, IGMP, false), MLXSW_SP_RXL_MARK(ARPBC, MIRROR_TO_CPU, ARP, false), MLXSW_SP_RXL_MARK(ARPUC, MIRROR_TO_CPU, ARP, false), + MLXSW_SP_RXL_NO_MARK(FID_MISS, TRAP_TO_CPU, IP2ME, false), /* L3 traps */ MLXSW_SP_RXL_NO_MARK(MTUERROR, TRAP_TO_CPU, ROUTER_EXP, false), MLXSW_SP_RXL_NO_MARK(TTLERROR, TRAP_TO_CPU, ROUTER_EXP, false), @@ -3268,6 +3290,18 @@ static int mlxsw_sp_basic_trap_groups_set(struct mlxsw_core *mlxsw_core) return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); } +static int mlxsw_sp_vfid_op(struct mlxsw_sp *mlxsw_sp, u16 fid, bool create); + +static int mlxsw_sp_dummy_fid_init(struct mlxsw_sp *mlxsw_sp) +{ + return mlxsw_sp_vfid_op(mlxsw_sp, MLXSW_SP_DUMMY_FID, true); +} + +static void mlxsw_sp_dummy_fid_fini(struct mlxsw_sp *mlxsw_sp) +{ + mlxsw_sp_vfid_op(mlxsw_sp, MLXSW_SP_DUMMY_FID, false); +} + static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, const struct mlxsw_bus_info *mlxsw_bus_info) { @@ -3346,6 +3380,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_dpipe_init; } + err = mlxsw_sp_dummy_fid_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to init dummy FID\n"); + goto err_dummy_fid_init; + } + err = mlxsw_sp_ports_create(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n"); @@ -3355,6 +3395,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, return 0; err_ports_create: + mlxsw_sp_dummy_fid_fini(mlxsw_sp); +err_dummy_fid_init: mlxsw_sp_dpipe_fini(mlxsw_sp); err_dpipe_init: mlxsw_sp_counter_pool_fini(mlxsw_sp); @@ -3381,6 +3423,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); mlxsw_sp_ports_remove(mlxsw_sp); + mlxsw_sp_dummy_fid_fini(mlxsw_sp); mlxsw_sp_dpipe_fini(mlxsw_sp); mlxsw_sp_counter_pool_fini(mlxsw_sp); mlxsw_sp_acl_fini(mlxsw_sp); @@ -3994,6 +4037,56 @@ static void mlxsw_sp_port_vlan_unlink(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_vport->dev = mlxsw_sp_port->dev; } +static int mlxsw_sp_port_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, + bool enable) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + enum mlxsw_reg_spms_state spms_state; + char *spms_pl; + u16 vid; + int err; + + spms_state = enable ? MLXSW_REG_SPMS_STATE_FORWARDING : + MLXSW_REG_SPMS_STATE_DISCARDING; + + spms_pl = kmalloc(MLXSW_REG_SPMS_LEN, GFP_KERNEL); + if (!spms_pl) + return -ENOMEM; + mlxsw_reg_spms_pack(spms_pl, mlxsw_sp_port->local_port); + + for (vid = 0; vid < VLAN_N_VID; vid++) + mlxsw_reg_spms_vid_pack(spms_pl, vid, spms_state); + + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spms), spms_pl); + kfree(spms_pl); + return err; +} + +static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port) +{ + int err; + + err = mlxsw_sp_port_stp_set(mlxsw_sp_port, true); + if (err) + return err; + err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1, + true, false); + if (err) + goto err_port_vlan_set; + return 0; + +err_port_vlan_set: + mlxsw_sp_port_stp_set(mlxsw_sp_port, false); + return err; +} + +static void mlxsw_sp_port_ovs_leave(struct mlxsw_sp_port *mlxsw_sp_port) +{ + mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1, + false, false); + mlxsw_sp_port_stp_set(mlxsw_sp_port, false); +} + static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, unsigned long event, void *ptr) { @@ -4013,7 +4106,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, if (!is_vlan_dev(upper_dev) && !netif_is_lag_master(upper_dev) && !netif_is_bridge_master(upper_dev) && - !netif_is_l3_master(upper_dev)) + !netif_is_l3_master(upper_dev) && + !netif_is_ovs_master(upper_dev)) return -EINVAL; if (!info->linking) break; @@ -4030,6 +4124,10 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) && !netif_is_lag_master(vlan_dev_real_dev(upper_dev))) return -EINVAL; + if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev)) + return -EINVAL; + if (netif_is_ovs_port(dev) && is_vlan_dev(upper_dev)) + return -EINVAL; break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; @@ -4038,8 +4136,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, err = mlxsw_sp_port_vlan_link(mlxsw_sp_port, upper_dev); else - mlxsw_sp_port_vlan_unlink(mlxsw_sp_port, - upper_dev); + mlxsw_sp_port_vlan_unlink(mlxsw_sp_port, + upper_dev); } else if (netif_is_bridge_master(upper_dev)) { if (info->linking) err = mlxsw_sp_port_bridge_join(mlxsw_sp_port, @@ -4058,6 +4156,11 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, err = mlxsw_sp_port_vrf_join(mlxsw_sp_port); else mlxsw_sp_port_vrf_leave(mlxsw_sp_port); + } else if (netif_is_ovs_master(upper_dev)) { + if (info->linking) + err = mlxsw_sp_port_ovs_join(mlxsw_sp_port); + else + mlxsw_sp_port_ovs_leave(mlxsw_sp_port); } else { err = -EINVAL; WARN_ON(1); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index c245e4c3d9ad..0af6e1abe0a7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -57,6 +57,8 @@ #define MLXSW_SP_VFID_BASE VLAN_N_VID #define MLXSW_SP_VFID_MAX 1024 /* Bridged VLAN interfaces */ +#define MLXSW_SP_DUMMY_FID 15359 + #define MLXSW_SP_RFID_BASE 15360 #define MLXSW_SP_MID_MAX 7000 @@ -105,7 +107,7 @@ static inline u16 mlxsw_sp_fid_to_vfid(u16 fid) static inline bool mlxsw_sp_fid_is_vfid(u16 fid) { - return fid >= MLXSW_SP_VFID_BASE && fid < MLXSW_SP_RFID_BASE; + return fid >= MLXSW_SP_VFID_BASE && fid < MLXSW_SP_DUMMY_FID; } struct mlxsw_sp_sb_pr { @@ -661,6 +663,9 @@ int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp, u32 action, u16 vid, u16 proto, u8 prio); int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei); +int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei, + u16 fid); struct mlxsw_sp_acl_rule; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index d3b791f69f5b..317f7b14627f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -403,6 +403,13 @@ int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp, rulei->counter_index); } +int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei, + u16 fid) +{ + return mlxsw_afa_block_append_fid_set(rulei->act_block, fid); +} + struct mlxsw_sp_acl_rule * mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_ruleset *ruleset, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 3e7a0bcbba72..7d87e23578a3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -71,6 +71,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, int ifindex = tcf_mirred_ifindex(a); struct net_device *out_dev; + err = mlxsw_sp_acl_rulei_act_fid_set(mlxsw_sp, rulei, + MLXSW_SP_DUMMY_FID); + if (err) + return err; + out_dev = __dev_get_by_index(dev_net(dev), ifindex); if (out_dev == dev) out_dev = NULL; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index c70c59181014..146f8c7d1120 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -3098,7 +3098,9 @@ static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev, static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev, unsigned long event) { - if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev)) + if (netif_is_bridge_port(port_dev) || + netif_is_lag_port(port_dev) || + netif_is_ovs_port(port_dev)) return 0; return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 05eaa15ad9d5..0d8411f1f954 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -745,27 +745,6 @@ err_port_allow_untagged_set: return err; } -static int __mlxsw_sp_port_vlans_set(struct mlxsw_sp_port *mlxsw_sp_port, - u16 vid_begin, u16 vid_end, bool is_member, - bool untagged) -{ - u16 vid, vid_e; - int err; - - for (vid = vid_begin; vid <= vid_end; - vid += MLXSW_REG_SPVM_REC_MAX_COUNT) { - vid_e = min((u16) (vid + MLXSW_REG_SPVM_REC_MAX_COUNT - 1), - vid_end); - - err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid_e, - is_member, untagged); - if (err) - return err; - } - - return 0; -} - static int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin, u16 vid_end, bool learn_enable) @@ -804,8 +783,8 @@ static int __mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port, return err; } - err = __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end, - true, flag_untagged); + err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid_begin, vid_end, + true, flag_untagged); if (err) { netdev_err(dev, "Unable to add VIDs %d-%d\n", vid_begin, vid_end); @@ -863,8 +842,8 @@ err_port_vid_learning_set: if (old_pvid != mlxsw_sp_port->pvid) mlxsw_sp_port_pvid_set(mlxsw_sp_port, old_pvid); err_port_pvid_set: - __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end, false, - false); + mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid_begin, vid_end, + false, false); err_port_vlans_set: mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end); return err; @@ -1171,8 +1150,8 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, if (pvid >= vid_begin && pvid <= vid_end) mlxsw_sp_port_pvid_set(mlxsw_sp_port, 0); - __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end, false, - false); + mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid_begin, vid_end, + false, false); mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end); diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 02ea48b15eb5..e008fdbed20f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -55,6 +55,7 @@ enum { MLXSW_TRAP_ID_IGMP_V2_LEAVE = 0x33, MLXSW_TRAP_ID_IGMP_V3_REPORT = 0x34, MLXSW_TRAP_ID_PKT_SAMPLE = 0x38, + MLXSW_TRAP_ID_FID_MISS = 0x3D, MLXSW_TRAP_ID_ARPBC = 0x50, MLXSW_TRAP_ID_ARPUC = 0x51, MLXSW_TRAP_ID_MTUERROR = 0x52, diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 06c9f4100cb9..c0d7d5eec7e7 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -25,6 +25,7 @@ #include <linux/of_irq.h> #include <linux/crc32.h> #include <linux/crc32c.h> +#include <linux/circ_buf.h> #include "moxart_ether.h" @@ -227,8 +228,8 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) if (desc0 & (RX_DESC0_ERR | RX_DESC0_CRC_ERR | RX_DESC0_FTL | RX_DESC0_RUNT | RX_DESC0_ODD_NB)) { net_dbg_ratelimited("packet error\n"); - priv->stats.rx_dropped++; - priv->stats.rx_errors++; + ndev->stats.rx_dropped++; + ndev->stats.rx_errors++; goto rx_next; } @@ -244,8 +245,8 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) if (unlikely(!skb)) { net_dbg_ratelimited("netdev_alloc_skb_ip_align failed\n"); - priv->stats.rx_dropped++; - priv->stats.rx_errors++; + ndev->stats.rx_dropped++; + ndev->stats.rx_errors++; goto rx_next; } @@ -255,10 +256,10 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) napi_gro_receive(&priv->napi, skb); rx++; - priv->stats.rx_packets++; - priv->stats.rx_bytes += len; + ndev->stats.rx_packets++; + ndev->stats.rx_bytes += len; if (desc0 & RX_DESC0_MULTICAST) - priv->stats.multicast++; + ndev->stats.multicast++; rx_next: wmb(); /* prevent setting ownership back too early */ @@ -278,6 +279,13 @@ rx_next: return rx; } +static int moxart_tx_queue_space(struct net_device *ndev) +{ + struct moxart_mac_priv_t *priv = netdev_priv(ndev); + + return CIRC_SPACE(priv->tx_head, priv->tx_tail, TX_DESC_NUM); +} + static void moxart_tx_finished(struct net_device *ndev) { struct moxart_mac_priv_t *priv = netdev_priv(ndev); @@ -288,8 +296,8 @@ static void moxart_tx_finished(struct net_device *ndev) dma_unmap_single(&ndev->dev, priv->tx_mapping[tx_tail], priv->tx_len[tx_tail], DMA_TO_DEVICE); - priv->stats.tx_packets++; - priv->stats.tx_bytes += priv->tx_skb[tx_tail]->len; + ndev->stats.tx_packets++; + ndev->stats.tx_bytes += priv->tx_skb[tx_tail]->len; dev_kfree_skb_irq(priv->tx_skb[tx_tail]); priv->tx_skb[tx_tail] = NULL; @@ -297,6 +305,9 @@ static void moxart_tx_finished(struct net_device *ndev) tx_tail = TX_NEXT(tx_tail); } priv->tx_tail = tx_tail; + if (netif_queue_stopped(ndev) && + moxart_tx_queue_space(ndev) >= TX_WAKE_THRESHOLD) + netif_wake_queue(ndev); } static irqreturn_t moxart_mac_interrupt(int irq, void *dev_id) @@ -324,16 +335,21 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct moxart_mac_priv_t *priv = netdev_priv(ndev); void *desc; unsigned int len; - unsigned int tx_head = priv->tx_head; + unsigned int tx_head; u32 txdes1; int ret = NETDEV_TX_BUSY; + spin_lock_irq(&priv->txlock); + + tx_head = priv->tx_head; desc = priv->tx_desc_base + (TX_REG_DESC_SIZE * tx_head); - spin_lock_irq(&priv->txlock); + if (moxart_tx_queue_space(ndev) == 1) + netif_stop_queue(ndev); + if (moxart_desc_read(desc + TX_REG_OFFSET_DESC0) & TX_DESC0_DMA_OWN) { net_dbg_ratelimited("no TX space for packet\n"); - priv->stats.tx_dropped++; + ndev->stats.tx_dropped++; goto out_unlock; } rmb(); /* ensure data is only read that had TX_DESC0_DMA_OWN cleared */ @@ -384,13 +400,6 @@ out_unlock: return ret; } -static struct net_device_stats *moxart_mac_get_stats(struct net_device *ndev) -{ - struct moxart_mac_priv_t *priv = netdev_priv(ndev); - - return &priv->stats; -} - static void moxart_mac_setmulticast(struct net_device *ndev) { struct moxart_mac_priv_t *priv = netdev_priv(ndev); @@ -440,7 +449,6 @@ static const struct net_device_ops moxart_netdev_ops = { .ndo_open = moxart_mac_open, .ndo_stop = moxart_mac_stop, .ndo_start_xmit = moxart_mac_start_xmit, - .ndo_get_stats = moxart_mac_get_stats, .ndo_set_rx_mode = moxart_mac_set_rx_mode, .ndo_set_mac_address = moxart_set_mac_address, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/moxa/moxart_ether.h b/drivers/net/ethernet/moxa/moxart_ether.h index 93a9563ac7c6..686b8957d5cf 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.h +++ b/drivers/net/ethernet/moxa/moxart_ether.h @@ -59,6 +59,7 @@ #define TX_NEXT(N) (((N) + 1) & (TX_DESC_NUM_MASK)) #define TX_BUF_SIZE 1600 #define TX_BUF_SIZE_MAX (TX_DESC1_BUF_SIZE_MASK+1) +#define TX_WAKE_THRESHOLD 16 #define RX_DESC_NUM 64 #define RX_DESC_NUM_MASK (RX_DESC_NUM-1) @@ -292,7 +293,6 @@ struct moxart_mac_priv_t { void __iomem *base; - struct net_device_stats stats; unsigned int reg_maccr; unsigned int reg_imr; struct napi_struct napi; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index dedac720fb29..bea2a1a6c211 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -48,7 +48,7 @@ #include "nfpcore/nfp.h" #include "nfpcore/nfp_cpp.h" #include "nfpcore/nfp_nffw.h" -#include "nfpcore/nfp_nsp_eth.h" +#include "nfpcore/nfp_nsp.h" #include "nfpcore/nfp6000_pcie.h" @@ -385,8 +385,7 @@ static void nfp_pci_remove(struct pci_dev *pdev) { struct nfp_pf *pf = pci_get_drvdata(pdev); - if (!list_empty(&pf->ports)) - nfp_net_pci_remove(pf); + nfp_net_pci_remove(pf); nfp_pcie_sriov_disable(pdev); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h index 39105d0435e9..b57de047b002 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h @@ -42,7 +42,9 @@ #include <linux/list.h> #include <linux/types.h> #include <linux/msi.h> +#include <linux/mutex.h> #include <linux/pci.h> +#include <linux/workqueue.h> struct dentry; struct pci_dev; @@ -64,8 +66,11 @@ struct nfp_eth_table; * @fw_loaded: Is the firmware loaded? * @eth_tbl: NSP ETH table * @ddir: Per-device debugfs directory - * @num_ports: Number of adapter ports + * @num_ports: Number of adapter ports app firmware supports + * @num_netdevs: Number of netdevs spawned * @ports: Linked list of port structures (struct nfp_net) + * @port_lock: Protects @ports, @num_ports, @num_netdevs + * @port_refresh_work: Work entry for taking netdevs out */ struct nfp_pf { struct pci_dev *pdev; @@ -88,7 +93,11 @@ struct nfp_pf { struct dentry *ddir; unsigned int num_ports; + unsigned int num_netdevs; + struct list_head ports; + struct work_struct port_refresh_work; + struct mutex port_lock; }; extern struct pci_driver nfp_netvf_pci_driver; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 8e04aa0e6e87..052db9208fbb 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -523,7 +523,8 @@ struct nfp_net_dp { * @reconfig_sync_present: Some thread is performing synchronous reconfig * @reconfig_timer: Timer for async reading of reconfig results * @link_up: Is the link up? - * @link_status_lock: Protects @link_up and ensures atomicity with BAR reading + * @link_changed: Has link state changes since last port refresh? + * @link_status_lock: Protects @link_* and ensures atomicity with BAR reading * @rx_coalesce_usecs: RX interrupt moderation usecs delay parameter * @rx_coalesce_max_frames: RX interrupt moderation frame count parameter * @tx_coalesce_usecs: TX interrupt moderation usecs delay parameter @@ -580,6 +581,7 @@ struct nfp_net { u32 me_freq_mhz; bool link_up; + bool link_changed; spinlock_t link_status_lock; spinlock_t reconfig_lock; @@ -810,6 +812,9 @@ nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries, struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn); int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *new); +bool nfp_net_link_changed_read_clear(struct nfp_net *nn); +void nfp_net_refresh_port_config(struct nfp_net *nn); + #ifdef CONFIG_NFP_DEBUG void nfp_net_debugfs_create(void); void nfp_net_debugfs_destroy(void); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 8f2da128ce0f..e2197160e4dc 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -67,7 +67,7 @@ #include <net/pkt_cls.h> #include <net/vxlan.h> -#include "nfpcore/nfp_nsp_eth.h" +#include "nfpcore/nfp_nsp.h" #include "nfp_net_ctrl.h" #include "nfp_net.h" @@ -376,6 +376,19 @@ static irqreturn_t nfp_net_irq_rxtx(int irq, void *data) return IRQ_HANDLED; } +bool nfp_net_link_changed_read_clear(struct nfp_net *nn) +{ + unsigned long flags; + bool ret; + + spin_lock_irqsave(&nn->link_status_lock, flags); + ret = nn->link_changed; + nn->link_changed = false; + spin_unlock_irqrestore(&nn->link_status_lock, flags); + + return ret; +} + /** * nfp_net_read_link_status() - Reread link status from control BAR * @nn: NFP Network structure @@ -395,6 +408,7 @@ static void nfp_net_read_link_status(struct nfp_net *nn) goto out; nn->link_up = link_up; + nn->link_changed = true; if (nn->link_up) { netif_carrier_on(nn->dp.netdev); @@ -3281,9 +3295,10 @@ void nfp_net_netdev_clean(struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); + unregister_netdev(nn->dp.netdev); + if (nn->dp.xdp_prog) bpf_prog_put(nn->dp.xdp_prog); if (nn->dp.bpf_offload_xdp) nfp_net_xdp_offload(nn, NULL); - unregister_netdev(nn->dp.netdev); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index 71d86171b4ee..d04ccc9f6116 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -177,6 +177,19 @@ #define NFP_NET_CFG_VERSION_MINOR(x) (((x) & 0xff) << 0) #define NFP_NET_CFG_STS 0x0034 #define NFP_NET_CFG_STS_LINK (0x1 << 0) /* Link up or down */ +/* Link rate */ +#define NFP_NET_CFG_STS_LINK_RATE_SHIFT 1 +#define NFP_NET_CFG_STS_LINK_RATE_MASK 0xF +#define NFP_NET_CFG_STS_LINK_RATE \ + (NFP_NET_CFG_STS_LINK_RATE_MASK << NFP_NET_CFG_STS_LINK_RATE_SHIFT) +#define NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED 0 +#define NFP_NET_CFG_STS_LINK_RATE_UNKNOWN 1 +#define NFP_NET_CFG_STS_LINK_RATE_1G 2 +#define NFP_NET_CFG_STS_LINK_RATE_10G 3 +#define NFP_NET_CFG_STS_LINK_RATE_25G 4 +#define NFP_NET_CFG_STS_LINK_RATE_40G 5 +#define NFP_NET_CFG_STS_LINK_RATE_50G 6 +#define NFP_NET_CFG_STS_LINK_RATE_100G 7 #define NFP_NET_CFG_CAP 0x0038 #define NFP_NET_CFG_MAX_TXRINGS 0x003c #define NFP_NET_CFG_MAX_RXRINGS 0x0040 diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index ed22a813e579..3328041ec290 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -49,6 +49,7 @@ #include <linux/ethtool.h> #include "nfpcore/nfp.h" +#include "nfpcore/nfp_nsp.h" #include "nfp_net_ctrl.h" #include "nfp_net.h" @@ -173,6 +174,114 @@ static void nfp_net_get_drvinfo(struct net_device *netdev, drvinfo->regdump_len = NFP_NET_CFG_BAR_SZ; } +/** + * nfp_net_get_link_ksettings - Get Link Speed settings + * @netdev: network interface device structure + * @cmd: ethtool command + * + * Reports speed settings based on info in the BAR provided by the fw. + */ +static int +nfp_net_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + static const u32 ls_to_ethtool[] = { + [NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED] = 0, + [NFP_NET_CFG_STS_LINK_RATE_UNKNOWN] = SPEED_UNKNOWN, + [NFP_NET_CFG_STS_LINK_RATE_1G] = SPEED_1000, + [NFP_NET_CFG_STS_LINK_RATE_10G] = SPEED_10000, + [NFP_NET_CFG_STS_LINK_RATE_25G] = SPEED_25000, + [NFP_NET_CFG_STS_LINK_RATE_40G] = SPEED_40000, + [NFP_NET_CFG_STS_LINK_RATE_50G] = SPEED_50000, + [NFP_NET_CFG_STS_LINK_RATE_100G] = SPEED_100000, + }; + struct nfp_net *nn = netdev_priv(netdev); + u32 sts, ls; + + ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); + cmd->base.port = PORT_OTHER; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + + if (nn->eth_port) + cmd->base.autoneg = nn->eth_port->aneg != NFP_ANEG_DISABLED ? + AUTONEG_ENABLE : AUTONEG_DISABLE; + + if (!netif_carrier_ok(netdev)) + return 0; + + /* Use link speed from ETH table if available, otherwise try the BAR */ + if (nn->eth_port && nfp_net_link_changed_read_clear(nn)) + nfp_net_refresh_port_config(nn); + /* Separate if - on FW error the port could've disappeared from table */ + if (nn->eth_port) { + cmd->base.port = nn->eth_port->port_type; + cmd->base.speed = nn->eth_port->speed; + cmd->base.duplex = DUPLEX_FULL; + return 0; + } + + sts = nn_readl(nn, NFP_NET_CFG_STS); + + ls = FIELD_GET(NFP_NET_CFG_STS_LINK_RATE, sts); + if (ls == NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED) + return -EOPNOTSUPP; + + if (ls == NFP_NET_CFG_STS_LINK_RATE_UNKNOWN || + ls >= ARRAY_SIZE(ls_to_ethtool)) + return 0; + + cmd->base.speed = ls_to_ethtool[sts]; + cmd->base.duplex = DUPLEX_FULL; + + return 0; +} + +static int +nfp_net_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) +{ + struct nfp_net *nn = netdev_priv(netdev); + struct nfp_nsp *nsp; + int err; + + if (!nn->eth_port) + return -EOPNOTSUPP; + + if (netif_running(netdev)) { + nn_warn(nn, "Changing settings not allowed on an active interface. It may cause the port to be disabled until reboot.\n"); + return -EBUSY; + } + + nsp = nfp_eth_config_start(nn->cpp, nn->eth_port->index); + if (IS_ERR(nsp)) + return PTR_ERR(nsp); + + err = __nfp_eth_set_aneg(nsp, cmd->base.autoneg == AUTONEG_ENABLE ? + NFP_ANEG_AUTO : NFP_ANEG_DISABLED); + if (err) + goto err_bad_set; + if (cmd->base.speed != SPEED_UNKNOWN) { + u32 speed = cmd->base.speed / nn->eth_port->lanes; + + err = __nfp_eth_set_speed(nsp, speed); + if (err) + goto err_bad_set; + } + + err = nfp_eth_config_commit_end(nsp); + if (err > 0) + return 0; /* no change */ + + nfp_net_refresh_port_config(nn); + + return err; + +err_bad_set: + nfp_eth_config_cleanup_end(nsp); + return err; +} + static void nfp_net_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) { @@ -814,6 +923,8 @@ static const struct ethtool_ops nfp_net_ethtool_ops = { .set_coalesce = nfp_net_set_coalesce, .get_channels = nfp_net_get_channels, .set_channels = nfp_net_set_channels, + .get_link_ksettings = nfp_net_get_link_ksettings, + .set_link_ksettings = nfp_net_set_link_ksettings, }; void nfp_net_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 2025cb7c6d90..4c6863a072d3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -47,11 +47,12 @@ #include <linux/pci_regs.h> #include <linux/msi.h> #include <linux/random.h> +#include <linux/rtnetlink.h> #include "nfpcore/nfp.h" #include "nfpcore/nfp_cpp.h" #include "nfpcore/nfp_nffw.h" -#include "nfpcore/nfp_nsp_eth.h" +#include "nfpcore/nfp_nsp.h" #include "nfpcore/nfp6000_pcie.h" #include "nfp_net_ctrl.h" @@ -129,14 +130,29 @@ err_area: return (u8 __iomem *)ERR_PTR(err); } +/** + * nfp_net_get_mac_addr() - Get the MAC address. + * @nn: NFP Network structure + * @cpp: NFP CPP handle + * @id: NFP port id + * + * First try to get the MAC address from NSP ETH table. If that + * fails try HWInfo. As a last resort generate a random address. + */ static void -nfp_net_get_mac_addr_hwinfo(struct nfp_net_dp *dp, struct nfp_cpp *cpp, - unsigned int id) +nfp_net_get_mac_addr(struct nfp_net *nn, struct nfp_cpp *cpp, unsigned int id) { + struct nfp_net_dp *dp = &nn->dp; u8 mac_addr[ETH_ALEN]; const char *mac_str; char name[32]; + if (nn->eth_port) { + ether_addr_copy(dp->netdev->dev_addr, nn->eth_port->mac_addr); + ether_addr_copy(dp->netdev->perm_addr, nn->eth_port->mac_addr); + return; + } + snprintf(name, sizeof(name), "eth%d.mac", id); mac_str = nfp_hwinfo_lookup(cpp, name); @@ -159,32 +175,16 @@ nfp_net_get_mac_addr_hwinfo(struct nfp_net_dp *dp, struct nfp_cpp *cpp, ether_addr_copy(dp->netdev->perm_addr, mac_addr); } -/** - * nfp_net_get_mac_addr() - Get the MAC address. - * @nn: NFP Network structure - * @pf: NFP PF device structure - * @id: NFP port id - * - * First try to get the MAC address from NSP ETH table. If that - * fails try HWInfo. As a last resort generate a random address. - */ -static void -nfp_net_get_mac_addr(struct nfp_net *nn, struct nfp_pf *pf, unsigned int id) +static struct nfp_eth_table_port * +nfp_net_find_port(struct nfp_pf *pf, unsigned int id) { int i; for (i = 0; pf->eth_tbl && i < pf->eth_tbl->count; i++) - if (pf->eth_tbl->ports[i].eth_index == id) { - const u8 *mac_addr = pf->eth_tbl->ports[i].mac_addr; - - nn->eth_port = &pf->eth_tbl->ports[i]; + if (pf->eth_tbl->ports[i].eth_index == id) + return &pf->eth_tbl->ports[i]; - ether_addr_copy(nn->dp.netdev->dev_addr, mac_addr); - ether_addr_copy(nn->dp.netdev->perm_addr, mac_addr); - return; - } - - nfp_net_get_mac_addr_hwinfo(&nn->dp, pf->cpp, id); + return NULL; } static unsigned int nfp_net_pf_get_num_ports(struct nfp_pf *pf) @@ -283,6 +283,7 @@ static void nfp_net_pf_free_netdevs(struct nfp_pf *pf) while (!list_empty(&pf->ports)) { nn = list_first_entry(&pf->ports, struct nfp_net, port_list); list_del(&nn->port_list); + pf->num_netdevs--; nfp_net_netdev_free(nn); } @@ -291,7 +292,8 @@ static void nfp_net_pf_free_netdevs(struct nfp_pf *pf) static struct nfp_net * nfp_net_pf_alloc_port_netdev(struct nfp_pf *pf, void __iomem *ctrl_bar, void __iomem *tx_bar, void __iomem *rx_bar, - int stride, struct nfp_net_fw_version *fw_ver) + int stride, struct nfp_net_fw_version *fw_ver, + struct nfp_eth_table_port *eth_port) { u32 n_tx_rings, n_rx_rings; struct nfp_net *nn; @@ -312,6 +314,7 @@ nfp_net_pf_alloc_port_netdev(struct nfp_pf *pf, void __iomem *ctrl_bar, nn->dp.is_vf = 0; nn->stride_rx = stride; nn->stride_tx = stride; + nn->eth_port = eth_port; return nn; } @@ -323,7 +326,7 @@ nfp_net_pf_init_port_netdev(struct nfp_pf *pf, struct nfp_net *nn, int err; /* Get MAC address */ - nfp_net_get_mac_addr(nn, pf, id); + nfp_net_get_mac_addr(nn, pf->cpp, id); /* Get ME clock frequency from ctrl BAR * XXX for now frequency is hardcoded until we figure out how @@ -348,6 +351,7 @@ nfp_net_pf_alloc_netdevs(struct nfp_pf *pf, void __iomem *ctrl_bar, int stride, struct nfp_net_fw_version *fw_ver) { u32 prev_tx_base, prev_rx_base, tgt_tx_base, tgt_rx_base; + struct nfp_eth_table_port *eth_port; struct nfp_net *nn; unsigned int i; int err; @@ -363,17 +367,27 @@ nfp_net_pf_alloc_netdevs(struct nfp_pf *pf, void __iomem *ctrl_bar, prev_tx_base = tgt_tx_base; prev_rx_base = tgt_rx_base; - nn = nfp_net_pf_alloc_port_netdev(pf, ctrl_bar, tx_bar, rx_bar, - stride, fw_ver); - if (IS_ERR(nn)) { - err = PTR_ERR(nn); - goto err_free_prev; + eth_port = nfp_net_find_port(pf, i); + if (eth_port && eth_port->override_changed) { + nfp_warn(pf->cpp, "Config changed for port #%d, reboot required before port will be operational\n", i); + } else { + nn = nfp_net_pf_alloc_port_netdev(pf, ctrl_bar, tx_bar, + rx_bar, stride, + fw_ver, eth_port); + if (IS_ERR(nn)) { + err = PTR_ERR(nn); + goto err_free_prev; + } + list_add_tail(&nn->port_list, &pf->ports); + pf->num_netdevs++; } - list_add_tail(&nn->port_list, &pf->ports); ctrl_bar += NFP_PF_CSR_SLICE_SIZE; } + if (list_empty(&pf->ports)) + return -ENODEV; + return 0; err_free_prev: @@ -409,7 +423,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf, } num_irqs = nfp_net_irqs_alloc(pf->pdev, pf->irq_entries, - NFP_NET_MIN_PORT_IRQS * pf->num_ports, + NFP_NET_MIN_PORT_IRQS * pf->num_netdevs, wanted_irqs); if (!num_irqs) { nn_warn(nn, "Unable to allocate MSI-X Vectors. Exiting\n"); @@ -419,7 +433,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf, /* Distribute IRQs to ports */ irqs_left = num_irqs; - ports_left = pf->num_ports; + ports_left = pf->num_netdevs; list_for_each_entry(nn, &pf->ports, port_list) { unsigned int n; @@ -455,6 +469,81 @@ err_nn_free: return err; } +static void nfp_net_pci_remove_finish(struct nfp_pf *pf) +{ + nfp_net_debugfs_dir_clean(&pf->ddir); + + nfp_net_irqs_disable(pf->pdev); + kfree(pf->irq_entries); + + nfp_cpp_area_release_free(pf->rx_area); + nfp_cpp_area_release_free(pf->tx_area); + nfp_cpp_area_release_free(pf->ctrl_area); +} + +static void nfp_net_refresh_netdevs(struct work_struct *work) +{ + struct nfp_pf *pf = container_of(work, struct nfp_pf, + port_refresh_work); + struct nfp_net *nn, *next; + + mutex_lock(&pf->port_lock); + + /* Check for nfp_net_pci_remove() racing against us */ + if (list_empty(&pf->ports)) + goto out; + + list_for_each_entry_safe(nn, next, &pf->ports, port_list) { + if (!nn->eth_port) { + nfp_warn(pf->cpp, "Warning: port not present after reconfig\n"); + continue; + } + if (!nn->eth_port->override_changed) + continue; + + nn_warn(nn, "Port config changed, unregistering. Reboot required before port will be operational again.\n"); + + nfp_net_debugfs_dir_clean(&nn->debugfs_dir); + nfp_net_netdev_clean(nn->dp.netdev); + + list_del(&nn->port_list); + pf->num_netdevs--; + nfp_net_netdev_free(nn); + } + + if (list_empty(&pf->ports)) + nfp_net_pci_remove_finish(pf); +out: + mutex_unlock(&pf->port_lock); +} + +void nfp_net_refresh_port_config(struct nfp_net *nn) +{ + struct nfp_pf *pf = pci_get_drvdata(nn->pdev); + struct nfp_eth_table *old_table; + + ASSERT_RTNL(); + + old_table = pf->eth_tbl; + + list_for_each_entry(nn, &pf->ports, port_list) + nfp_net_link_changed_read_clear(nn); + + pf->eth_tbl = nfp_eth_read_ports(pf->cpp); + if (!pf->eth_tbl) { + pf->eth_tbl = old_table; + nfp_err(pf->cpp, "Error refreshing port config!\n"); + return; + } + + list_for_each_entry(nn, &pf->ports, port_list) + nn->eth_port = nfp_net_find_port(pf, nn->eth_port->eth_index); + + kfree(old_table); + + schedule_work(&pf->port_refresh_work); +} + /* * PCI device functions */ @@ -468,17 +557,23 @@ int nfp_net_pci_probe(struct nfp_pf *pf) int stride; int err; + INIT_WORK(&pf->port_refresh_work, nfp_net_refresh_netdevs); + mutex_init(&pf->port_lock); + /* Verify that the board has completed initialization */ if (!nfp_is_ready(pf->cpp)) { nfp_err(pf->cpp, "NFP is not ready for NIC operation.\n"); return -EINVAL; } + mutex_lock(&pf->port_lock); pf->num_ports = nfp_net_pf_get_num_ports(pf); ctrl_bar = nfp_net_pf_map_ctrl_bar(pf); - if (!ctrl_bar) - return pf->fw_loaded ? -EINVAL : -EPROBE_DEFER; + if (!ctrl_bar) { + err = pf->fw_loaded ? -EINVAL : -EPROBE_DEFER; + goto err_unlock; + } nfp_net_get_fw_version(&fw_ver, ctrl_bar); if (fw_ver.resv || fw_ver.class != NFP_NET_CFG_VERSION_CLASS_GENERIC) { @@ -552,6 +647,8 @@ int nfp_net_pci_probe(struct nfp_pf *pf) if (err) goto err_clean_ddir; + mutex_unlock(&pf->port_lock); + return 0; err_clean_ddir: @@ -561,6 +658,8 @@ err_unmap_tx: nfp_cpp_area_release_free(pf->tx_area); err_ctrl_unmap: nfp_cpp_area_release_free(pf->ctrl_area); +err_unlock: + mutex_unlock(&pf->port_lock); return err; } @@ -568,6 +667,10 @@ void nfp_net_pci_remove(struct nfp_pf *pf) { struct nfp_net *nn; + mutex_lock(&pf->port_lock); + if (list_empty(&pf->ports)) + goto out; + list_for_each_entry(nn, &pf->ports, port_list) { nfp_net_debugfs_dir_clean(&nn->debugfs_dir); @@ -576,12 +679,9 @@ void nfp_net_pci_remove(struct nfp_pf *pf) nfp_net_pf_free_netdevs(pf); - nfp_net_debugfs_dir_clean(&pf->ddir); + nfp_net_pci_remove_finish(pf); +out: + mutex_unlock(&pf->port_lock); - nfp_net_irqs_disable(pf->pdev); - kfree(pf->irq_entries); - - nfp_cpp_area_release_free(pf->rx_area); - nfp_cpp_area_release_free(pf->tx_area); - nfp_cpp_area_release_free(pf->ctrl_area); + cancel_work_sync(&pf->port_refresh_work); } diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h index f7ca8e374923..8afef7593f13 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h @@ -48,18 +48,18 @@ const char *nfp_hwinfo_lookup(struct nfp_cpp *cpp, const char *lookup); -/* Implemented in nfp_nsp.c */ +/* Implemented in nfp_nsp.c, low level functions */ struct nfp_nsp; -struct firmware; - -struct nfp_nsp *nfp_nsp_open(struct nfp_cpp *cpp); -void nfp_nsp_close(struct nfp_nsp *state); -u16 nfp_nsp_get_abi_ver_major(struct nfp_nsp *state); -u16 nfp_nsp_get_abi_ver_minor(struct nfp_nsp *state); -int nfp_nsp_wait(struct nfp_nsp *state); -int nfp_nsp_device_soft_reset(struct nfp_nsp *state); -int nfp_nsp_load_fw(struct nfp_nsp *state, const struct firmware *fw); + +struct nfp_cpp *nfp_nsp_cpp(struct nfp_nsp *state); +bool nfp_nsp_config_modified(struct nfp_nsp *state); +void nfp_nsp_config_set_modified(struct nfp_nsp *state, bool modified); +void *nfp_nsp_config_entries(struct nfp_nsp *state); +unsigned int nfp_nsp_config_idx(struct nfp_nsp *state); +void nfp_nsp_config_set_state(struct nfp_nsp *state, void *entries, + unsigned int idx); +void nfp_nsp_config_clear_state(struct nfp_nsp *state); int nfp_nsp_read_eth_table(struct nfp_nsp *state, void *buf, unsigned int size); int nfp_nsp_write_eth_table(struct nfp_nsp *state, const void *buf, unsigned int size); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c index 17822ae4a17f..4635f42e15b0 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c @@ -49,6 +49,7 @@ #include "nfp.h" #include "nfp_cpp.h" +#include "nfp_nsp.h" /* Offsets relative to the CSR base */ #define NSP_STATUS 0x00 @@ -96,6 +97,17 @@ enum nfp_nsp_cmd { __MAX_SPCODE, }; +static const struct { + int code; + const char *msg; +} nsp_errors[] = { + { 6010, "could not map to phy for port" }, + { 6011, "not an allowed rate/lanes for port" }, + { 6012, "not an allowed rate/lanes for port" }, + { 6013, "high/low error, change other port first" }, + { 6014, "config not found in flash" }, +}; + struct nfp_nsp { struct nfp_cpp *cpp; struct nfp_resource *res; @@ -103,8 +115,63 @@ struct nfp_nsp { u16 major; u16 minor; } ver; + + /* Eth table config state */ + bool modified; + unsigned int idx; + void *entries; }; +struct nfp_cpp *nfp_nsp_cpp(struct nfp_nsp *state) +{ + return state->cpp; +} + +bool nfp_nsp_config_modified(struct nfp_nsp *state) +{ + return state->modified; +} + +void nfp_nsp_config_set_modified(struct nfp_nsp *state, bool modified) +{ + state->modified = modified; +} + +void *nfp_nsp_config_entries(struct nfp_nsp *state) +{ + return state->entries; +} + +unsigned int nfp_nsp_config_idx(struct nfp_nsp *state) +{ + return state->idx; +} + +void +nfp_nsp_config_set_state(struct nfp_nsp *state, void *entries, unsigned int idx) +{ + state->entries = entries; + state->idx = idx; +} + +void nfp_nsp_config_clear_state(struct nfp_nsp *state) +{ + state->entries = NULL; + state->idx = 0; +} + +static void nfp_nsp_print_extended_error(struct nfp_nsp *state, u32 ret_val) +{ + int i; + + if (!ret_val) + return; + + for (i = 0; i < ARRAY_SIZE(nsp_errors); i++) + if (ret_val == nsp_errors[i].code) + nfp_err(state->cpp, "err msg: %s\n", nsp_errors[i].msg); +} + static int nfp_nsp_check(struct nfp_nsp *state) { struct nfp_cpp *cpp = state->cpp; @@ -238,7 +305,7 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg, static int nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option, u32 buff_cpp, u64 buff_addr) { - u64 reg, nsp_base, nsp_buffer, nsp_status, nsp_command; + u64 reg, ret_val, nsp_base, nsp_buffer, nsp_status, nsp_command; struct nfp_cpp *cpp = state->cpp; u32 nsp_cpp; int err; @@ -291,18 +358,20 @@ static int nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option, return err; } + err = nfp_cpp_readq(cpp, nsp_cpp, nsp_command, &ret_val); + if (err < 0) + return err; + ret_val = FIELD_GET(NSP_COMMAND_OPTION, ret_val); + err = FIELD_GET(NSP_STATUS_RESULT, reg); if (err) { - nfp_warn(cpp, "Result (error) code set: %d command: %d\n", - -err, code); + nfp_warn(cpp, "Result (error) code set: %d (%d) command: %d\n", + -err, (int)ret_val, code); + nfp_nsp_print_extended_error(state, ret_val); return -err; } - err = nfp_cpp_readq(cpp, nsp_cpp, nsp_command, ®); - if (err < 0) - return err; - - return FIELD_GET(NSP_COMMAND_OPTION, reg); + return ret_val; } static int nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option, diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h index 325e841ca90a..7d34ff145fd7 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h @@ -31,12 +31,48 @@ * SOFTWARE. */ -#ifndef NSP_NSP_ETH_H -#define NSP_NSP_ETH_H 1 +#ifndef NSP_NSP_H +#define NSP_NSP_H 1 #include <linux/types.h> #include <linux/if_ether.h> +struct firmware; +struct nfp_cpp; +struct nfp_nsp; + +struct nfp_nsp *nfp_nsp_open(struct nfp_cpp *cpp); +void nfp_nsp_close(struct nfp_nsp *state); +u16 nfp_nsp_get_abi_ver_major(struct nfp_nsp *state); +u16 nfp_nsp_get_abi_ver_minor(struct nfp_nsp *state); +int nfp_nsp_wait(struct nfp_nsp *state); +int nfp_nsp_device_soft_reset(struct nfp_nsp *state); +int nfp_nsp_load_fw(struct nfp_nsp *state, const struct firmware *fw); + +enum nfp_eth_interface { + NFP_INTERFACE_NONE = 0, + NFP_INTERFACE_SFP = 1, + NFP_INTERFACE_SFPP = 10, + NFP_INTERFACE_SFP28 = 28, + NFP_INTERFACE_QSFP = 40, + NFP_INTERFACE_CXP = 100, + NFP_INTERFACE_QSFP28 = 112, +}; + +enum nfp_eth_media { + NFP_MEDIA_DAC_PASSIVE = 0, + NFP_MEDIA_DAC_ACTIVE, + NFP_MEDIA_FIBRE, +}; + +enum nfp_eth_aneg { + NFP_ANEG_AUTO = 0, + NFP_ANEG_SEARCH, + NFP_ANEG_25G_CONSORTIUM, + NFP_ANEG_25G_IEEE, + NFP_ANEG_DISABLED, +}; + /** * struct nfp_eth_table - ETH table information * @count: number of table entries @@ -48,13 +84,18 @@ * @base: first channel index (within NBI) * @lanes: number of channels * @speed: interface speed (in Mbps) + * @interface: interface (module) plugged in + * @media: media type of the @interface + * @aneg: auto negotiation mode * @mac_addr: interface MAC address * @label_port: port id * @label_subport: id of interface within port (for split ports) * @enabled: is enabled? * @tx_enabled: is TX enabled? * @rx_enabled: is RX enabled? + * @override_changed: is media reconfig pending? * + * @port_type: one of %PORT_* defines for ethtool * @is_split: is interface part of a split port */ struct nfp_eth_table { @@ -67,6 +108,11 @@ struct nfp_eth_table { unsigned int lanes; unsigned int speed; + unsigned int interface; + enum nfp_eth_media media; + + enum nfp_eth_aneg aneg; + u8 mac_addr[ETH_ALEN]; u8 label_port; @@ -76,17 +122,29 @@ struct nfp_eth_table { bool tx_enabled; bool rx_enabled; + bool override_changed; + /* Computed fields */ + u8 port_type; + bool is_split; } ports[0]; }; -struct nfp_cpp; -struct nfp_nsp; - struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp); struct nfp_eth_table * __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp); + int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable); +int nfp_eth_set_configured(struct nfp_cpp *cpp, unsigned int idx, + bool configed); + +struct nfp_nsp *nfp_eth_config_start(struct nfp_cpp *cpp, unsigned int idx); +int nfp_eth_config_commit_end(struct nfp_nsp *nsp); +void nfp_eth_config_cleanup_end(struct nfp_nsp *nsp); + +int __nfp_eth_set_aneg(struct nfp_nsp *nsp, enum nfp_eth_aneg mode); +int __nfp_eth_set_speed(struct nfp_nsp *nsp, unsigned int speed); +int __nfp_eth_set_split(struct nfp_nsp *nsp, unsigned int lanes); #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c index 38bd80077e33..639438d8313a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c @@ -43,13 +43,13 @@ #include <linux/module.h> #include "nfp.h" -#include "nfp_nsp_eth.h" +#include "nfp_nsp.h" #include "nfp6000/nfp6000.h" #define NSP_ETH_NBI_PORT_COUNT 24 #define NSP_ETH_MAX_COUNT (2 * NSP_ETH_NBI_PORT_COUNT) #define NSP_ETH_TABLE_SIZE (NSP_ETH_MAX_COUNT * \ - sizeof(struct eth_table_entry)) + sizeof(union eth_table_entry)) #define NSP_ETH_PORT_LANES GENMASK_ULL(3, 0) #define NSP_ETH_PORT_INDEX GENMASK_ULL(15, 8) @@ -58,14 +58,32 @@ #define NSP_ETH_PORT_LANES_MASK cpu_to_le64(NSP_ETH_PORT_LANES) +#define NSP_ETH_STATE_CONFIGURED BIT_ULL(0) #define NSP_ETH_STATE_ENABLED BIT_ULL(1) #define NSP_ETH_STATE_TX_ENABLED BIT_ULL(2) #define NSP_ETH_STATE_RX_ENABLED BIT_ULL(3) #define NSP_ETH_STATE_RATE GENMASK_ULL(11, 8) +#define NSP_ETH_STATE_INTERFACE GENMASK_ULL(19, 12) +#define NSP_ETH_STATE_MEDIA GENMASK_ULL(21, 20) +#define NSP_ETH_STATE_OVRD_CHNG BIT_ULL(22) +#define NSP_ETH_STATE_ANEG GENMASK_ULL(25, 23) +#define NSP_ETH_CTRL_CONFIGURED BIT_ULL(0) #define NSP_ETH_CTRL_ENABLED BIT_ULL(1) #define NSP_ETH_CTRL_TX_ENABLED BIT_ULL(2) #define NSP_ETH_CTRL_RX_ENABLED BIT_ULL(3) +#define NSP_ETH_CTRL_SET_RATE BIT_ULL(4) +#define NSP_ETH_CTRL_SET_LANES BIT_ULL(5) +#define NSP_ETH_CTRL_SET_ANEG BIT_ULL(6) + +enum nfp_eth_raw { + NSP_ETH_RAW_PORT = 0, + NSP_ETH_RAW_STATE, + NSP_ETH_RAW_MAC, + NSP_ETH_RAW_CONTROL, + + NSP_ETH_NUM_RAW +}; enum nfp_eth_rate { RATE_INVALID = 0, @@ -76,29 +94,49 @@ enum nfp_eth_rate { RATE_25G, }; -struct eth_table_entry { - __le64 port; - __le64 state; - u8 mac_addr[6]; - u8 resv[2]; - __le64 control; +union eth_table_entry { + struct { + __le64 port; + __le64 state; + u8 mac_addr[6]; + u8 resv[2]; + __le64 control; + }; + __le64 raw[NSP_ETH_NUM_RAW]; +}; + +static const struct { + enum nfp_eth_rate rate; + unsigned int speed; +} nsp_eth_rate_tbl[] = { + { RATE_INVALID, 0, }, + { RATE_10M, SPEED_10, }, + { RATE_100M, SPEED_100, }, + { RATE_1G, SPEED_1000, }, + { RATE_10G, SPEED_10000, }, + { RATE_25G, SPEED_25000, }, }; -static unsigned int nfp_eth_rate(enum nfp_eth_rate rate) +static unsigned int nfp_eth_rate2speed(enum nfp_eth_rate rate) { - unsigned int rate_xlate[] = { - [RATE_INVALID] = 0, - [RATE_10M] = SPEED_10, - [RATE_100M] = SPEED_100, - [RATE_1G] = SPEED_1000, - [RATE_10G] = SPEED_10000, - [RATE_25G] = SPEED_25000, - }; + int i; - if (rate >= ARRAY_SIZE(rate_xlate)) - return 0; + for (i = 0; i < ARRAY_SIZE(nsp_eth_rate_tbl); i++) + if (nsp_eth_rate_tbl[i].rate == rate) + return nsp_eth_rate_tbl[i].speed; - return rate_xlate[rate]; + return 0; +} + +static unsigned int nfp_eth_speed2rate(unsigned int speed) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(nsp_eth_rate_tbl); i++) + if (nsp_eth_rate_tbl[i].speed == speed) + return nsp_eth_rate_tbl[i].rate; + + return RATE_INVALID; } static void nfp_eth_copy_mac_reverse(u8 *dst, const u8 *src) @@ -110,8 +148,8 @@ static void nfp_eth_copy_mac_reverse(u8 *dst, const u8 *src) } static void -nfp_eth_port_translate(const struct eth_table_entry *src, unsigned int index, - struct nfp_eth_table_port *dst) +nfp_eth_port_translate(struct nfp_nsp *nsp, const union eth_table_entry *src, + unsigned int index, struct nfp_eth_table_port *dst) { unsigned int rate; u64 port, state; @@ -129,13 +167,22 @@ nfp_eth_port_translate(const struct eth_table_entry *src, unsigned int index, dst->tx_enabled = FIELD_GET(NSP_ETH_STATE_TX_ENABLED, state); dst->rx_enabled = FIELD_GET(NSP_ETH_STATE_RX_ENABLED, state); - rate = nfp_eth_rate(FIELD_GET(NSP_ETH_STATE_RATE, state)); + rate = nfp_eth_rate2speed(FIELD_GET(NSP_ETH_STATE_RATE, state)); dst->speed = dst->lanes * rate; + dst->interface = FIELD_GET(NSP_ETH_STATE_INTERFACE, state); + dst->media = FIELD_GET(NSP_ETH_STATE_MEDIA, state); + nfp_eth_copy_mac_reverse(dst->mac_addr, src->mac_addr); dst->label_port = FIELD_GET(NSP_ETH_PORT_PHYLABEL, port); dst->label_subport = FIELD_GET(NSP_ETH_PORT_LABEL, port); + + if (nfp_nsp_get_abi_ver_minor(nsp) < 17) + return; + + dst->override_changed = FIELD_GET(NSP_ETH_STATE_OVRD_CHNG, state); + dst->aneg = FIELD_GET(NSP_ETH_STATE_ANEG, state); } static void @@ -162,6 +209,20 @@ nfp_eth_mark_split_ports(struct nfp_cpp *cpp, struct nfp_eth_table *table) } } +static void +nfp_eth_calc_port_type(struct nfp_cpp *cpp, struct nfp_eth_table_port *entry) +{ + if (entry->interface == NFP_INTERFACE_NONE) { + entry->port_type = PORT_NONE; + return; + } + + if (entry->media == NFP_MEDIA_FIBRE) + entry->port_type = PORT_FIBRE; + else + entry->port_type = PORT_DA; +} + /** * nfp_eth_read_ports() - retrieve port information * @cpp: NFP CPP handle @@ -189,7 +250,7 @@ struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp) struct nfp_eth_table * __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp) { - struct eth_table_entry *entries; + union eth_table_entry *entries; struct nfp_eth_table *table; int i, j, ret, cnt = 0; @@ -225,10 +286,12 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp) table->count = cnt; for (i = 0, j = 0; i < NSP_ETH_MAX_COUNT; i++) if (entries[i].port & NSP_ETH_PORT_LANES_MASK) - nfp_eth_port_translate(&entries[i], i, + nfp_eth_port_translate(nsp, &entries[i], i, &table->ports[j++]); nfp_eth_mark_split_ports(cpp, table); + for (i = 0; i < table->count; i++) + nfp_eth_calc_port_type(cpp, &table->ports[i]); kfree(entries); @@ -239,63 +302,247 @@ err: return NULL; } -/** - * nfp_eth_set_mod_enable() - set PHY module enable control bit - * @cpp: NFP CPP handle - * @idx: NFP chip-wide port index - * @enable: Desired state - * - * Enable or disable PHY module (this usually means setting the TX lanes - * disable bits). - * - * Return: 0 or -ERRNO. - */ -int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable) +struct nfp_nsp *nfp_eth_config_start(struct nfp_cpp *cpp, unsigned int idx) { - struct eth_table_entry *entries; + union eth_table_entry *entries; struct nfp_nsp *nsp; - u64 reg; int ret; entries = kzalloc(NSP_ETH_TABLE_SIZE, GFP_KERNEL); if (!entries) - return -ENOMEM; + return ERR_PTR(-ENOMEM); nsp = nfp_nsp_open(cpp); if (IS_ERR(nsp)) { kfree(entries); - return PTR_ERR(nsp); + return nsp; } ret = nfp_nsp_read_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE); if (ret < 0) { nfp_err(cpp, "reading port table failed %d\n", ret); - goto exit_close_nsp; + goto err; } if (!(entries[idx].port & NSP_ETH_PORT_LANES_MASK)) { nfp_warn(cpp, "trying to set port state on disabled port %d\n", idx); - ret = -EINVAL; - goto exit_close_nsp; + goto err; + } + + nfp_nsp_config_set_state(nsp, entries, idx); + return nsp; + +err: + nfp_nsp_close(nsp); + kfree(entries); + return ERR_PTR(-EIO); +} + +void nfp_eth_config_cleanup_end(struct nfp_nsp *nsp) +{ + union eth_table_entry *entries = nfp_nsp_config_entries(nsp); + + nfp_nsp_config_set_modified(nsp, false); + nfp_nsp_config_clear_state(nsp); + nfp_nsp_close(nsp); + kfree(entries); +} + +/** + * nfp_eth_config_commit_end() - perform recorded configuration changes + * @nsp: NFP NSP handle returned from nfp_eth_config_start() + * + * Perform the configuration which was requested with __nfp_eth_set_*() + * helpers and recorded in @nsp state. If device was already configured + * as requested or no __nfp_eth_set_*() operations were made no NSP command + * will be performed. + * + * Return: + * 0 - configuration successful; + * 1 - no changes were needed; + * -ERRNO - configuration failed. + */ +int nfp_eth_config_commit_end(struct nfp_nsp *nsp) +{ + union eth_table_entry *entries = nfp_nsp_config_entries(nsp); + int ret = 1; + + if (nfp_nsp_config_modified(nsp)) { + ret = nfp_nsp_write_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE); + ret = ret < 0 ? ret : 0; + } + + nfp_eth_config_cleanup_end(nsp); + + return ret; +} + +/** + * nfp_eth_set_mod_enable() - set PHY module enable control bit + * @cpp: NFP CPP handle + * @idx: NFP chip-wide port index + * @enable: Desired state + * + * Enable or disable PHY module (this usually means setting the TX lanes + * disable bits). + * + * Return: 0 or -ERRNO. + */ +int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable) +{ + union eth_table_entry *entries; + struct nfp_nsp *nsp; + u64 reg; + + nsp = nfp_eth_config_start(cpp, idx); + if (IS_ERR(nsp)) + return PTR_ERR(nsp); + + entries = nfp_nsp_config_entries(nsp); + + /* Check if we are already in requested state */ + reg = le64_to_cpu(entries[idx].state); + if (enable != FIELD_GET(NSP_ETH_CTRL_ENABLED, reg)) { + reg = le64_to_cpu(entries[idx].control); + reg &= ~NSP_ETH_CTRL_ENABLED; + reg |= FIELD_PREP(NSP_ETH_CTRL_ENABLED, enable); + entries[idx].control = cpu_to_le64(reg); + + nfp_nsp_config_set_modified(nsp, true); } + return nfp_eth_config_commit_end(nsp); +} + +/** + * nfp_eth_set_configured() - set PHY module configured control bit + * @cpp: NFP CPP handle + * @idx: NFP chip-wide port index + * @configed: Desired state + * + * Set the ifup/ifdown state on the PHY. + * + * Return: 0 or -ERRNO. + */ +int nfp_eth_set_configured(struct nfp_cpp *cpp, unsigned int idx, bool configed) +{ + union eth_table_entry *entries; + struct nfp_nsp *nsp; + u64 reg; + + nsp = nfp_eth_config_start(cpp, idx); + if (IS_ERR(nsp)) + return PTR_ERR(nsp); + + entries = nfp_nsp_config_entries(nsp); + /* Check if we are already in requested state */ reg = le64_to_cpu(entries[idx].state); - if (enable == FIELD_GET(NSP_ETH_CTRL_ENABLED, reg)) { - ret = 0; - goto exit_close_nsp; + if (configed != FIELD_GET(NSP_ETH_STATE_CONFIGURED, reg)) { + reg = le64_to_cpu(entries[idx].control); + reg &= ~NSP_ETH_CTRL_CONFIGURED; + reg |= FIELD_PREP(NSP_ETH_CTRL_CONFIGURED, configed); + entries[idx].control = cpu_to_le64(reg); + + nfp_nsp_config_set_modified(nsp, true); } - reg = le64_to_cpu(entries[idx].control); - reg &= ~NSP_ETH_CTRL_ENABLED; - reg |= FIELD_PREP(NSP_ETH_CTRL_ENABLED, enable); - entries[idx].control = cpu_to_le64(reg); + return nfp_eth_config_commit_end(nsp); +} - ret = nfp_nsp_write_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE); -exit_close_nsp: - nfp_nsp_close(nsp); - kfree(entries); +/* Force inline, FIELD_* macroes require masks to be compilation-time known */ +static __always_inline int +nfp_eth_set_bit_config(struct nfp_nsp *nsp, unsigned int raw_idx, + const u64 mask, unsigned int val, const u64 ctrl_bit) +{ + union eth_table_entry *entries = nfp_nsp_config_entries(nsp); + unsigned int idx = nfp_nsp_config_idx(nsp); + u64 reg; + + /* Note: set features were added in ABI 0.14 but the error + * codes were initially not populated correctly. + */ + if (nfp_nsp_get_abi_ver_minor(nsp) < 17) { + nfp_err(nfp_nsp_cpp(nsp), + "set operations not supported, please update flash\n"); + return -EOPNOTSUPP; + } + + /* Check if we are already in requested state */ + reg = le64_to_cpu(entries[idx].raw[raw_idx]); + if (val == FIELD_GET(mask, reg)) + return 0; + + reg &= ~mask; + reg |= FIELD_PREP(mask, val); + entries[idx].raw[raw_idx] = cpu_to_le64(reg); + + entries[idx].control |= cpu_to_le64(ctrl_bit); - return ret < 0 ? ret : 0; + nfp_nsp_config_set_modified(nsp, true); + + return 0; +} + +/** + * __nfp_eth_set_aneg() - set PHY autonegotiation control bit + * @nsp: NFP NSP handle returned from nfp_eth_config_start() + * @mode: Desired autonegotiation mode + * + * Allow/disallow PHY module to advertise/perform autonegotiation. + * Will write to hwinfo overrides in the flash (persistent config). + * + * Return: 0 or -ERRNO. + */ +int __nfp_eth_set_aneg(struct nfp_nsp *nsp, enum nfp_eth_aneg mode) +{ + return nfp_eth_set_bit_config(nsp, NSP_ETH_RAW_STATE, + NSP_ETH_STATE_ANEG, mode, + NSP_ETH_CTRL_SET_ANEG); +} + +/** + * __nfp_eth_set_speed() - set interface speed/rate + * @nsp: NFP NSP handle returned from nfp_eth_config_start() + * @speed: Desired speed (per lane) + * + * Set lane speed. Provided @speed value should be subport speed divided + * by number of lanes this subport is spanning (i.e. 10000 for 40G, 25000 for + * 50G, etc.) + * Will write to hwinfo overrides in the flash (persistent config). + * + * Return: 0 or -ERRNO. + */ +int __nfp_eth_set_speed(struct nfp_nsp *nsp, unsigned int speed) +{ + enum nfp_eth_rate rate; + + rate = nfp_eth_speed2rate(speed); + if (rate == RATE_INVALID) { + nfp_warn(nfp_nsp_cpp(nsp), + "could not find matching lane rate for speed %u\n", + speed); + return -EINVAL; + } + + return nfp_eth_set_bit_config(nsp, NSP_ETH_RAW_STATE, + NSP_ETH_STATE_RATE, rate, + NSP_ETH_CTRL_SET_RATE); +} + +/** + * __nfp_eth_set_split() - set interface lane split + * @nsp: NFP NSP handle returned from nfp_eth_config_start() + * @lanes: Desired lanes per port + * + * Set number of lanes in the port. + * Will write to hwinfo overrides in the flash (persistent config). + * + * Return: 0 or -ERRNO. + */ +int __nfp_eth_set_split(struct nfp_nsp *nsp, unsigned int lanes) +{ + return nfp_eth_set_bit_config(nsp, NSP_ETH_RAW_PORT, NSP_ETH_PORT_LANES, + lanes, NSP_ETH_CTRL_SET_LANES); } diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c index 9709c8ca0774..159564d8dcdb 100644 --- a/drivers/net/ethernet/nuvoton/w90p910_ether.c +++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c @@ -152,7 +152,6 @@ struct w90p910_ether { struct tran_pdesc *tdesc; dma_addr_t rdesc_phys; dma_addr_t tdesc_phys; - struct net_device_stats stats; struct platform_device *pdev; struct resource *res; struct sk_buff *skb; @@ -584,15 +583,6 @@ static int w90p910_ether_close(struct net_device *dev) return 0; } -static struct net_device_stats *w90p910_ether_stats(struct net_device *dev) -{ - struct w90p910_ether *ether; - - ether = netdev_priv(dev); - - return ðer->stats; -} - static int w90p910_send_frame(struct net_device *dev, unsigned char *data, int length) { @@ -671,10 +661,10 @@ static irqreturn_t w90p910_tx_interrupt(int irq, void *dev_id) ether->finish_tx = 0; if (txbd->sl & TXDS_TXCP) { - ether->stats.tx_packets++; - ether->stats.tx_bytes += txbd->sl & 0xFFFF; + dev->stats.tx_packets++; + dev->stats.tx_bytes += txbd->sl & 0xFFFF; } else { - ether->stats.tx_errors++; + dev->stats.tx_errors++; } txbd->sl = 0x0; @@ -730,7 +720,7 @@ static void netdev_rx(struct net_device *dev) data = ether->rdesc->recv_buf[ether->cur_rx]; skb = netdev_alloc_skb(dev, length + 2); if (!skb) { - ether->stats.rx_dropped++; + dev->stats.rx_dropped++; return; } @@ -738,24 +728,24 @@ static void netdev_rx(struct net_device *dev) skb_put(skb, length); skb_copy_to_linear_data(skb, data, length); skb->protocol = eth_type_trans(skb, dev); - ether->stats.rx_packets++; - ether->stats.rx_bytes += length; + dev->stats.rx_packets++; + dev->stats.rx_bytes += length; netif_rx(skb); } else { - ether->stats.rx_errors++; + dev->stats.rx_errors++; if (status & RXDS_RP) { dev_err(&pdev->dev, "rx runt err\n"); - ether->stats.rx_length_errors++; + dev->stats.rx_length_errors++; } else if (status & RXDS_CRCE) { dev_err(&pdev->dev, "rx crc err\n"); - ether->stats.rx_crc_errors++; + dev->stats.rx_crc_errors++; } else if (status & RXDS_ALIE) { dev_err(&pdev->dev, "rx alignment err\n"); - ether->stats.rx_frame_errors++; + dev->stats.rx_frame_errors++; } else if (status & RXDS_PTLE) { dev_err(&pdev->dev, "rx longer err\n"); - ether->stats.rx_over_errors++; + dev->stats.rx_over_errors++; } } @@ -912,7 +902,6 @@ static const struct net_device_ops w90p910_ether_netdev_ops = { .ndo_open = w90p910_ether_open, .ndo_stop = w90p910_ether_close, .ndo_start_xmit = w90p910_ether_start_xmit, - .ndo_get_stats = w90p910_ether_stats, .ndo_set_rx_mode = w90p910_ether_set_multicast_list, .ndo_set_mac_address = w90p910_set_mac_address, .ndo_do_ioctl = w90p910_ether_ioctl, diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 8c85fd2f3949..c539ba138db9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -225,8 +225,9 @@ enum QED_FEATURE { QED_PF_L2_QUE, QED_VF, QED_RDMA_CNQ, - QED_VF_L2_QUE, + QED_ISCSI_CQ, QED_FCOE_CQ, + QED_VF_L2_QUE, QED_MAX_FEATURES, }; @@ -271,9 +272,14 @@ struct qed_hw_info { RESC_NUM(_p_hwfn, resc)) #define FEAT_NUM(_p_hwfn, resc) ((_p_hwfn)->hw_info.feat_num[resc]) - u8 num_tc; + /* Amount of traffic classes HW supports */ + u8 num_hw_tc; + + /* Amount of TCs which should be active according to DCBx or upper + * layer driver configuration. + */ + u8 num_active_tc; u8 offload_tc; - u8 non_offload_tc; u32 concrete_fid; u16 opaque_fid; @@ -336,15 +342,19 @@ struct qed_qm_info { struct init_qm_port_params *qm_port_params; u16 start_pq; u8 start_vport; - u8 pure_lb_pq; - u8 offload_pq; - u8 pure_ack_pq; - u8 ooo_pq; - u8 vf_queues_offset; + u16 pure_lb_pq; + u16 offload_pq; + u16 low_latency_pq; + u16 pure_ack_pq; + u16 ooo_pq; + u16 first_vf_pq; + u16 first_mcos_pq; + u16 first_rl_pq; u16 num_pqs; u16 num_vf_pqs; u8 num_vports; u8 max_phys_tcs_per_port; + u8 ooo_tc; bool pf_rl_en; bool pf_wfq_en; bool vport_rl_en; @@ -494,6 +504,8 @@ struct qed_hwfn { u8 dcbx_no_edpm; u8 db_bar_no_edpm; + struct qed_ptt *p_arfs_ptt; + /* p_ptp_ptt is valid for leading HWFN only */ struct qed_ptt *p_ptp_ptt; struct qed_simd_fp_handler simd_proto_handler[64]; @@ -729,9 +741,27 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev, u32 min_pf_rate); void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); -#define QED_LEADING_HWFN(dev) (&dev->hwfns[0]) int qed_device_num_engines(struct qed_dev *cdev); +#define QED_LEADING_HWFN(dev) (&dev->hwfns[0]) + +/* Flags for indication of required queues */ +#define PQ_FLAGS_RLS (BIT(0)) +#define PQ_FLAGS_MCOS (BIT(1)) +#define PQ_FLAGS_LB (BIT(2)) +#define PQ_FLAGS_OOO (BIT(3)) +#define PQ_FLAGS_ACK (BIT(4)) +#define PQ_FLAGS_OFLD (BIT(5)) +#define PQ_FLAGS_VFS (BIT(6)) +#define PQ_FLAGS_LLT (BIT(7)) + +/* physical queue index for cm context intialization */ +u16 qed_get_cm_pq_idx(struct qed_hwfn *p_hwfn, u32 pq_flags); +u16 qed_get_cm_pq_idx_mcos(struct qed_hwfn *p_hwfn, u8 tc); +u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf); + +#define QED_LEADING_HWFN(dev) (&dev->hwfns[0]) + /* Other Linux specific common definitions */ #define DP_NAME(cdev) ((cdev)->name) diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 9ff62cc5723d..b3aaa985956e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -219,9 +219,6 @@ struct qed_cxt_mngr { */ u32 vf_count; - /* total number of SRQ's for this hwfn */ - u32 srq_count; - /* Acquired CIDs */ struct qed_cid_acquired_map acquired[MAX_CONN_TYPES]; @@ -237,12 +234,17 @@ struct qed_cxt_mngr { u32 t2_num_pages; u64 first_free; u64 last_free; + + /* total number of SRQ's for this hwfn */ + u32 srq_count; + + /* Maximal number of L2 steering filters */ + u32 arfs_count; }; static bool src_proto(enum protocol_type type) { return type == PROTOCOLID_ISCSI || - type == PROTOCOLID_FCOE || - type == PROTOCOLID_ROCE; + type == PROTOCOLID_FCOE; } static bool tm_cid_proto(enum protocol_type type) @@ -292,6 +294,9 @@ static void qed_cxt_src_iids(struct qed_cxt_mngr *p_mngr, iids->pf_cids += p_mngr->conn_cfg[i].cid_count; iids->per_vf_cids += p_mngr->conn_cfg[i].cids_per_vf; } + + /* Add L2 filtering filters in addition */ + iids->pf_cids += p_mngr->arfs_count; } /* counts the iids for the Timers block configuration */ @@ -303,16 +308,34 @@ struct qed_tm_iids { u32 per_vf_tids; }; -static void qed_cxt_tm_iids(struct qed_cxt_mngr *p_mngr, +static void qed_cxt_tm_iids(struct qed_hwfn *p_hwfn, + struct qed_cxt_mngr *p_mngr, struct qed_tm_iids *iids) { - u32 i, j; - - for (i = 0; i < MAX_CONN_TYPES; i++) { + bool tm_vf_required = false; + bool tm_required = false; + int i, j; + + /* Timers is a special case -> we don't count how many cids require + * timers but what's the max cid that will be used by the timer block. + * therefore we traverse in reverse order, and once we hit a protocol + * that requires the timers memory, we'll sum all the protocols up + * to that one. + */ + for (i = MAX_CONN_TYPES - 1; i >= 0; i--) { struct qed_conn_type_cfg *p_cfg = &p_mngr->conn_cfg[i]; - if (tm_cid_proto(i)) { + if (tm_cid_proto(i) || tm_required) { + if (p_cfg->cid_count) + tm_required = true; + iids->pf_cids += p_cfg->cid_count; + } + + if (tm_cid_proto(i) || tm_vf_required) { + if (p_cfg->cids_per_vf) + tm_vf_required = true; + iids->per_vf_cids += p_cfg->cids_per_vf; } @@ -526,7 +549,22 @@ static u32 qed_ilt_get_dynamic_line_cnt(struct qed_hwfn *p_hwfn, return lines_to_skip; } -int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) +static struct qed_ilt_client_cfg *qed_cxt_set_cli(struct qed_ilt_client_cfg + *p_cli) +{ + p_cli->active = false; + p_cli->first.val = 0; + p_cli->last.val = 0; + return p_cli; +} + +static struct qed_ilt_cli_blk *qed_cxt_set_blk(struct qed_ilt_cli_blk *p_blk) +{ + p_blk->total_size = 0; + return p_blk; +} + +int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count) { struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr; u32 curr_line, total, i, task_size, line; @@ -550,7 +588,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) p_hwfn->my_id, p_hwfn->p_cxt_mngr->pf_start_line); /* CDUC */ - p_cli = &p_mngr->clients[ILT_CLI_CDUC]; + p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_CDUC]); + curr_line = p_mngr->pf_start_line; /* CDUC PF */ @@ -559,7 +598,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) /* get the counters for the CDUC and QM clients */ qed_cxt_cdu_iids(p_mngr, &cdu_iids); - p_blk = &p_cli->pf_blks[CDUC_BLK]; + p_blk = qed_cxt_set_blk(&p_cli->pf_blks[CDUC_BLK]); total = cdu_iids.pf_cids * CONN_CXT_SIZE(p_hwfn); @@ -573,7 +612,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) ILT_CLI_CDUC); /* CDUC VF */ - p_blk = &p_cli->vf_blks[CDUC_BLK]; + p_blk = qed_cxt_set_blk(&p_cli->vf_blks[CDUC_BLK]); total = cdu_iids.per_vf_cids * CONN_CXT_SIZE(p_hwfn); qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line, @@ -587,7 +626,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) ILT_CLI_CDUC); /* CDUT PF */ - p_cli = &p_mngr->clients[ILT_CLI_CDUT]; + p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_CDUT]); p_cli->first.val = curr_line; /* first the 'working' task memory */ @@ -596,7 +635,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) if (!p_seg || p_seg->count == 0) continue; - p_blk = &p_cli->pf_blks[CDUT_SEG_BLK(i)]; + p_blk = qed_cxt_set_blk(&p_cli->pf_blks[CDUT_SEG_BLK(i)]); total = p_seg->count * p_mngr->task_type_size[p_seg->type]; qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line, total, p_mngr->task_type_size[p_seg->type]); @@ -611,7 +650,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) if (!p_seg || p_seg->count == 0) continue; - p_blk = &p_cli->pf_blks[CDUT_FL_SEG_BLK(i, PF)]; + p_blk = + qed_cxt_set_blk(&p_cli->pf_blks[CDUT_FL_SEG_BLK(i, PF)]); if (!p_seg->has_fl_mem) { /* The segment is active (total size pf 'working' @@ -656,7 +696,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) /* 'working' memory */ total = p_seg->count * p_mngr->task_type_size[p_seg->type]; - p_blk = &p_cli->vf_blks[CDUT_SEG_BLK(0)]; + p_blk = qed_cxt_set_blk(&p_cli->vf_blks[CDUT_SEG_BLK(0)]); qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line, total, p_mngr->task_type_size[p_seg->type]); @@ -665,7 +705,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) ILT_CLI_CDUT); /* 'init' memory */ - p_blk = &p_cli->vf_blks[CDUT_FL_SEG_BLK(0, VF)]; + p_blk = + qed_cxt_set_blk(&p_cli->vf_blks[CDUT_FL_SEG_BLK(0, VF)]); if (!p_seg->has_fl_mem) { /* see comment above */ line = p_cli->vf_blks[CDUT_SEG_BLK(0)].start_line; @@ -693,8 +734,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) } /* QM */ - p_cli = &p_mngr->clients[ILT_CLI_QM]; - p_blk = &p_cli->pf_blks[0]; + p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_QM]); + p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]); qed_cxt_qm_iids(p_hwfn, &qm_iids); total = qed_qm_pf_mem_size(p_hwfn->rel_pf_id, qm_iids.cids, @@ -718,7 +759,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) p_cli->pf_total_lines = curr_line - p_blk->start_line; /* SRC */ - p_cli = &p_mngr->clients[ILT_CLI_SRC]; + p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_SRC]); qed_cxt_src_iids(p_mngr, &src_iids); /* Both the PF and VFs searcher connections are stored in the per PF @@ -732,7 +773,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) total = roundup_pow_of_two(local_max); - p_blk = &p_cli->pf_blks[0]; + p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]); qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line, total * sizeof(struct src_ent), sizeof(struct src_ent)); @@ -743,11 +784,11 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) } /* TM PF */ - p_cli = &p_mngr->clients[ILT_CLI_TM]; - qed_cxt_tm_iids(p_mngr, &tm_iids); + p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_TM]); + qed_cxt_tm_iids(p_hwfn, p_mngr, &tm_iids); total = tm_iids.pf_cids + tm_iids.pf_tids_total; if (total) { - p_blk = &p_cli->pf_blks[0]; + p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]); qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line, total * TM_ELEM_SIZE, TM_ELEM_SIZE); @@ -759,14 +800,14 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) /* TM VF */ total = tm_iids.per_vf_cids + tm_iids.per_vf_tids; if (total) { - p_blk = &p_cli->vf_blks[0]; + p_blk = qed_cxt_set_blk(&p_cli->vf_blks[0]); qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line, total * TM_ELEM_SIZE, TM_ELEM_SIZE); qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line, ILT_CLI_TM); - p_cli->pf_total_lines = curr_line - p_blk->start_line; + p_cli->vf_total_lines = curr_line - p_blk->start_line; for (i = 1; i < p_mngr->vf_count; i++) qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line, ILT_CLI_TM); @@ -776,8 +817,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) total = qed_cxt_get_srq_count(p_hwfn); if (total) { - p_cli = &p_mngr->clients[ILT_CLI_TSDM]; - p_blk = &p_cli->pf_blks[SRQ_BLK]; + p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_TSDM]); + p_blk = qed_cxt_set_blk(&p_cli->pf_blks[SRQ_BLK]); qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line, total * SRQ_CXT_SIZE, SRQ_CXT_SIZE); @@ -786,13 +827,50 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn) p_cli->pf_total_lines = curr_line - p_blk->start_line; } + *line_count = curr_line - p_hwfn->p_cxt_mngr->pf_start_line; + if (curr_line - p_hwfn->p_cxt_mngr->pf_start_line > - RESC_NUM(p_hwfn, QED_ILT)) { - DP_ERR(p_hwfn, "too many ilt lines...#lines=%d\n", - curr_line - p_hwfn->p_cxt_mngr->pf_start_line); + RESC_NUM(p_hwfn, QED_ILT)) return -EINVAL; + + return 0; +} + +u32 qed_cxt_cfg_ilt_compute_excess(struct qed_hwfn *p_hwfn, u32 used_lines) +{ + struct qed_ilt_client_cfg *p_cli; + u32 excess_lines, available_lines; + struct qed_cxt_mngr *p_mngr; + u32 ilt_page_size, elem_size; + struct qed_tid_seg *p_seg; + int i; + + available_lines = RESC_NUM(p_hwfn, QED_ILT); + excess_lines = used_lines - available_lines; + + if (!excess_lines) + return 0; + + if (p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE) + return 0; + + p_mngr = p_hwfn->p_cxt_mngr; + p_cli = &p_mngr->clients[ILT_CLI_CDUT]; + ilt_page_size = ILT_PAGE_IN_BYTES(p_cli->p_size.val); + + for (i = 0; i < NUM_TASK_PF_SEGMENTS; i++) { + p_seg = qed_cxt_tid_seg_info(p_hwfn, i); + if (!p_seg || p_seg->count == 0) + continue; + + elem_size = p_mngr->task_type_size[p_seg->type]; + if (!elem_size) + continue; + + return (ilt_page_size / elem_size) * excess_lines; } + DP_NOTICE(p_hwfn, "failed computing excess ILT lines\n"); return 0; } @@ -1366,7 +1444,7 @@ static void qed_cdu_init_pf(struct qed_hwfn *p_hwfn) } } -void qed_qm_init_pf(struct qed_hwfn *p_hwfn) +void qed_qm_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { struct qed_qm_pf_rt_init_params params; struct qed_qm_info *qm_info = &p_hwfn->qm_info; @@ -1392,22 +1470,15 @@ void qed_qm_init_pf(struct qed_hwfn *p_hwfn) params.pq_params = qm_info->qm_pq_params; params.vport_params = qm_info->qm_vport_params; - qed_qm_pf_rt_init(p_hwfn, p_hwfn->p_main_ptt, ¶ms); + qed_qm_pf_rt_init(p_hwfn, p_ptt, ¶ms); } /* CM PF */ -static int qed_cm_init_pf(struct qed_hwfn *p_hwfn) +void qed_cm_init_pf(struct qed_hwfn *p_hwfn) { - union qed_qm_pq_params pq_params; - u16 pq; - /* XCM pure-LB queue */ - memset(&pq_params, 0, sizeof(pq_params)); - pq_params.core.tc = LB_TC; - pq = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params); - STORE_RT_REG(p_hwfn, XCM_REG_CON_PHY_Q3_RT_OFFSET, pq); - - return 0; + STORE_RT_REG(p_hwfn, XCM_REG_CON_PHY_Q3_RT_OFFSET, + qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB)); } /* DQ PF */ @@ -1639,7 +1710,7 @@ static void qed_tm_init_pf(struct qed_hwfn *p_hwfn) u8 i; memset(&tm_iids, 0, sizeof(tm_iids)); - qed_cxt_tm_iids(p_mngr, &tm_iids); + qed_cxt_tm_iids(p_hwfn, p_mngr, &tm_iids); /* @@@TBD No pre-scan for now */ @@ -1757,9 +1828,9 @@ void qed_cxt_hw_init_common(struct qed_hwfn *p_hwfn) qed_prs_init_common(p_hwfn); } -void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn) +void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { - qed_qm_init_pf(p_hwfn); + qed_qm_init_pf(p_hwfn, p_ptt); qed_cm_init_pf(p_hwfn); qed_dq_init_pf(p_hwfn); qed_cdu_init_pf(p_hwfn); @@ -1883,13 +1954,12 @@ int qed_cxt_get_cid_info(struct qed_hwfn *p_hwfn, struct qed_cxt_info *p_info) } static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn, - struct qed_rdma_pf_params *p_params) + struct qed_rdma_pf_params *p_params, + u32 num_tasks) { - u32 num_cons, num_tasks, num_qps, num_mrs, num_srqs; + u32 num_cons, num_qps, num_srqs; enum protocol_type proto; - num_mrs = min_t(u32, RDMA_MAX_TIDS, p_params->num_mrs); - num_tasks = num_mrs; /* each mr uses a single task id */ num_srqs = min_t(u32, 32 * 1024, p_params->num_srqs); switch (p_hwfn->hw_info.personality) { @@ -1918,7 +1988,7 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn, } } -int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn) +int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks) { /* Set the number of required CORE connections */ u32 core_cids = 1; /* SPQ */ @@ -1930,9 +2000,10 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn) switch (p_hwfn->hw_info.personality) { case QED_PCI_ETH_ROCE: { - qed_rdma_set_pf_params(p_hwfn, - &p_hwfn-> - pf_params.rdma_pf_params); + qed_rdma_set_pf_params(p_hwfn, + &p_hwfn-> + pf_params.rdma_pf_params, + rdma_tasks); /* no need for break since RoCE coexist with Ethernet */ } case QED_PCI_ETH: @@ -1942,6 +2013,7 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn) qed_cxt_set_proto_cid_count(p_hwfn, PROTOCOLID_ETH, p_params->num_cons, 1); + p_hwfn->p_cxt_mngr->arfs_count = p_params->num_arfs_filters; break; } case QED_PCI_FCOE: diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h index 8b010324268a..53ad532dc212 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h @@ -105,19 +105,28 @@ u32 qed_cxt_get_proto_cid_count(struct qed_hwfn *p_hwfn, * @brief qed_cxt_set_pf_params - Set the PF params for cxt init * * @param p_hwfn - * + * @param rdma_tasks - requested maximum * @return int */ -int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn); +int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks); /** * @brief qed_cxt_cfg_ilt_compute - compute ILT init parameters * * @param p_hwfn + * @param last_line * * @return int */ -int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn); +int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *last_line); + +/** + * @brief qed_cxt_cfg_ilt_compute_excess - how many lines can be decreased + * + * @param p_hwfn + * @param used_lines + */ +u32 qed_cxt_cfg_ilt_compute_excess(struct qed_hwfn *p_hwfn, u32 used_lines); /** * @brief qed_cxt_mngr_alloc - Allocate and init the context manager struct @@ -163,19 +172,18 @@ void qed_cxt_hw_init_common(struct qed_hwfn *p_hwfn); /** * @brief qed_cxt_hw_init_pf - Initailze ILT and DQ, PF phase, per path. * - * - * * @param p_hwfn + * @param p_ptt */ -void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn); +void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** * @brief qed_qm_init_pf - Initailze the QM PF phase, per path * * @param p_hwfn + * @param p_ptt */ - -void qed_qm_init_pf(struct qed_hwfn *p_hwfn); +void qed_qm_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** * @brief Reconfigures QM pf on the fly diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 5bd36a4a8fcd..2fc1fde824bd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -183,7 +183,7 @@ qed_dcbx_dp_protocol(struct qed_hwfn *p_hwfn, struct qed_dcbx_results *p_data) "%s info: update %d, enable %d, prio %d, tc %d, num_tc %d\n", qed_dcbx_app_update[i].name, p_data->arr[id].update, p_data->arr[id].enable, p_data->arr[id].priority, - p_data->arr[id].tc, p_hwfn->hw_info.num_tc); + p_data->arr[id].tc, p_hwfn->hw_info.num_active_tc); } } @@ -204,12 +204,8 @@ qed_dcbx_set_params(struct qed_dcbx_results *p_data, p_data->arr[type].tc = tc; /* QM reconf data */ - if (p_info->personality == personality) { - if (personality == QED_PCI_ETH) - p_info->non_offload_tc = tc; - else - p_info->offload_tc = tc; - } + if (p_info->personality == personality) + p_info->offload_tc = tc; } /* Update app protocol data and hw_info fields with the TLV info */ @@ -376,7 +372,9 @@ static int qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn) if (rc) return rc; - p_info->num_tc = QED_MFW_GET_FIELD(p_ets->flags, DCBX_ETS_MAX_TCS); + p_info->num_active_tc = QED_MFW_GET_FIELD(p_ets->flags, + DCBX_ETS_MAX_TCS); + p_hwfn->qm_info.ooo_tc = QED_MFW_GET_FIELD(p_ets->flags, DCBX_OOO_TC); data.pf_id = p_hwfn->rel_pf_id; data.dcbx_enabled = !!dcbx_version; diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index e75c83351d34..fad73195010d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -75,7 +75,8 @@ enum BAR_ID { BAR_ID_1 /* Used for doorbells */ }; -static u32 qed_hw_bar_size(struct qed_hwfn *p_hwfn, enum BAR_ID bar_id) +static u32 qed_hw_bar_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, enum BAR_ID bar_id) { u32 bar_reg = (bar_id == BAR_ID_0 ? PGLUE_B_REG_PF_BAR0_SIZE : PGLUE_B_REG_PF_BAR1_SIZE); @@ -84,7 +85,7 @@ static u32 qed_hw_bar_size(struct qed_hwfn *p_hwfn, enum BAR_ID bar_id) if (IS_VF(p_hwfn->cdev)) return 1 << 17; - val = qed_rd(p_hwfn, p_hwfn->p_main_ptt, bar_reg); + val = qed_rd(p_hwfn, p_ptt, bar_reg); if (val) return 1 << (val + 15); @@ -186,195 +187,569 @@ void qed_resc_free(struct qed_dev *cdev) } } -static int qed_init_qm_info(struct qed_hwfn *p_hwfn, bool b_sleepable) +/******************** QM initialization *******************/ +#define ACTIVE_TCS_BMAP 0x9f +#define ACTIVE_TCS_BMAP_4PORT_K2 0xf + +/* determines the physical queue flags for a given PF. */ +static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn) { - u8 num_vports, vf_offset = 0, i, vport_id, num_ports, curr_queue = 0; - struct qed_qm_info *qm_info = &p_hwfn->qm_info; - struct init_qm_port_params *p_qm_port; - bool init_rdma_offload_pq = false; - bool init_pure_ack_pq = false; - bool init_ooo_pq = false; - u16 num_pqs, multi_cos_tcs = 1; - u8 pf_wfq = qm_info->pf_wfq; - u32 pf_rl = qm_info->pf_rl; - u16 num_pf_rls = 0; - u16 num_vfs = 0; - -#ifdef CONFIG_QED_SRIOV - if (p_hwfn->cdev->p_iov_info) - num_vfs = p_hwfn->cdev->p_iov_info->total_vfs; -#endif - memset(qm_info, 0, sizeof(*qm_info)); + u32 flags; - num_pqs = multi_cos_tcs + num_vfs + 1; /* The '1' is for pure-LB */ - num_vports = (u8)RESC_NUM(p_hwfn, QED_VPORT); + /* common flags */ + flags = PQ_FLAGS_LB; - if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) { - num_pqs++; /* for RoCE queue */ - init_rdma_offload_pq = true; - /* we subtract num_vfs because each require a rate limiter, - * and one default rate limiter - */ - if (p_hwfn->pf_params.rdma_pf_params.enable_dcqcn) - num_pf_rls = RESC_NUM(p_hwfn, QED_RL) - num_vfs - 1; + /* feature flags */ + if (IS_QED_SRIOV(p_hwfn->cdev)) + flags |= PQ_FLAGS_VFS; - num_pqs += num_pf_rls; - qm_info->num_pf_rls = (u8) num_pf_rls; + /* protocol flags */ + switch (p_hwfn->hw_info.personality) { + case QED_PCI_ETH: + flags |= PQ_FLAGS_MCOS; + break; + case QED_PCI_FCOE: + flags |= PQ_FLAGS_OFLD; + break; + case QED_PCI_ISCSI: + flags |= PQ_FLAGS_ACK | PQ_FLAGS_OOO | PQ_FLAGS_OFLD; + break; + case QED_PCI_ETH_ROCE: + flags |= PQ_FLAGS_MCOS | PQ_FLAGS_OFLD | PQ_FLAGS_LLT; + break; + default: + DP_ERR(p_hwfn, + "unknown personality %d\n", p_hwfn->hw_info.personality); + return 0; } - if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) { - num_pqs += 2; /* for iSCSI pure-ACK / OOO queue */ - init_pure_ack_pq = true; - init_ooo_pq = true; - } + return flags; +} - /* Sanity checking that setup requires legal number of resources */ - if (num_pqs > RESC_NUM(p_hwfn, QED_PQ)) { - DP_ERR(p_hwfn, - "Need too many Physical queues - 0x%04x when only %04x are available\n", - num_pqs, RESC_NUM(p_hwfn, QED_PQ)); - return -EINVAL; - } +/* Getters for resource amounts necessary for qm initialization */ +u8 qed_init_qm_get_num_tcs(struct qed_hwfn *p_hwfn) +{ + return p_hwfn->hw_info.num_hw_tc; +} - /* PQs will be arranged as follows: First per-TC PQ then pure-LB quete. - */ - qm_info->qm_pq_params = kcalloc(num_pqs, - sizeof(struct init_qm_pq_params), - b_sleepable ? GFP_KERNEL : GFP_ATOMIC); - if (!qm_info->qm_pq_params) - goto alloc_err; +u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn) +{ + return IS_QED_SRIOV(p_hwfn->cdev) ? + p_hwfn->cdev->p_iov_info->total_vfs : 0; +} - qm_info->qm_vport_params = kcalloc(num_vports, - sizeof(struct init_qm_vport_params), - b_sleepable ? GFP_KERNEL - : GFP_ATOMIC); - if (!qm_info->qm_vport_params) - goto alloc_err; +#define NUM_DEFAULT_RLS 1 - qm_info->qm_port_params = kcalloc(MAX_NUM_PORTS, - sizeof(struct init_qm_port_params), - b_sleepable ? GFP_KERNEL - : GFP_ATOMIC); - if (!qm_info->qm_port_params) - goto alloc_err; +u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn) +{ + u16 num_pf_rls, num_vfs = qed_init_qm_get_num_vfs(p_hwfn); - qm_info->wfq_data = kcalloc(num_vports, sizeof(struct qed_wfq_data), - b_sleepable ? GFP_KERNEL : GFP_ATOMIC); - if (!qm_info->wfq_data) - goto alloc_err; + /* num RLs can't exceed resource amount of rls or vports */ + num_pf_rls = (u16) min_t(u32, RESC_NUM(p_hwfn, QED_RL), + RESC_NUM(p_hwfn, QED_VPORT)); - vport_id = (u8)RESC_START(p_hwfn, QED_VPORT); + /* Make sure after we reserve there's something left */ + if (num_pf_rls < num_vfs + NUM_DEFAULT_RLS) + return 0; - /* First init rate limited queues */ - for (curr_queue = 0; curr_queue < num_pf_rls; curr_queue++) { - qm_info->qm_pq_params[curr_queue].vport_id = vport_id++; - qm_info->qm_pq_params[curr_queue].tc_id = - p_hwfn->hw_info.non_offload_tc; - qm_info->qm_pq_params[curr_queue].wrr_group = 1; - qm_info->qm_pq_params[curr_queue].rl_valid = 1; - } + /* subtract rls necessary for VFs and one default one for the PF */ + num_pf_rls -= num_vfs + NUM_DEFAULT_RLS; - /* First init per-TC PQs */ - for (i = 0; i < multi_cos_tcs; i++) { - struct init_qm_pq_params *params = - &qm_info->qm_pq_params[curr_queue++]; + return num_pf_rls; +} - if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE || - p_hwfn->hw_info.personality == QED_PCI_ETH) { - params->vport_id = vport_id; - params->tc_id = p_hwfn->hw_info.non_offload_tc; - params->wrr_group = 1; - } else { - params->vport_id = vport_id; - params->tc_id = p_hwfn->hw_info.offload_tc; - params->wrr_group = 1; - } - } +u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn) +{ + u32 pq_flags = qed_get_pq_flags(p_hwfn); + + /* all pqs share the same vport, except for vfs and pf_rl pqs */ + return (!!(PQ_FLAGS_RLS & pq_flags)) * + qed_init_qm_get_num_pf_rls(p_hwfn) + + (!!(PQ_FLAGS_VFS & pq_flags)) * + qed_init_qm_get_num_vfs(p_hwfn) + 1; +} - /* Then init pure-LB PQ */ - qm_info->pure_lb_pq = curr_queue; - qm_info->qm_pq_params[curr_queue].vport_id = - (u8) RESC_START(p_hwfn, QED_VPORT); - qm_info->qm_pq_params[curr_queue].tc_id = PURE_LB_TC; - qm_info->qm_pq_params[curr_queue].wrr_group = 1; - curr_queue++; - - qm_info->offload_pq = 0; - if (init_rdma_offload_pq) { - qm_info->offload_pq = curr_queue; - qm_info->qm_pq_params[curr_queue].vport_id = vport_id; - qm_info->qm_pq_params[curr_queue].tc_id = - p_hwfn->hw_info.offload_tc; - qm_info->qm_pq_params[curr_queue].wrr_group = 1; - curr_queue++; - } - - if (init_pure_ack_pq) { - qm_info->pure_ack_pq = curr_queue; - qm_info->qm_pq_params[curr_queue].vport_id = vport_id; - qm_info->qm_pq_params[curr_queue].tc_id = - p_hwfn->hw_info.offload_tc; - qm_info->qm_pq_params[curr_queue].wrr_group = 1; - curr_queue++; - } - - if (init_ooo_pq) { - qm_info->ooo_pq = curr_queue; - qm_info->qm_pq_params[curr_queue].vport_id = vport_id; - qm_info->qm_pq_params[curr_queue].tc_id = DCBX_ISCSI_OOO_TC; - qm_info->qm_pq_params[curr_queue].wrr_group = 1; - curr_queue++; - } - - /* Then init per-VF PQs */ - vf_offset = curr_queue; - for (i = 0; i < num_vfs; i++) { - /* First vport is used by the PF */ - qm_info->qm_pq_params[curr_queue].vport_id = vport_id + i + 1; - qm_info->qm_pq_params[curr_queue].tc_id = - p_hwfn->hw_info.non_offload_tc; - qm_info->qm_pq_params[curr_queue].wrr_group = 1; - qm_info->qm_pq_params[curr_queue].rl_valid = 1; - curr_queue++; - } - - qm_info->vf_queues_offset = vf_offset; - qm_info->num_pqs = num_pqs; - qm_info->num_vports = num_vports; +/* calc amount of PQs according to the requested flags */ +u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn) +{ + u32 pq_flags = qed_get_pq_flags(p_hwfn); + + return (!!(PQ_FLAGS_RLS & pq_flags)) * + qed_init_qm_get_num_pf_rls(p_hwfn) + + (!!(PQ_FLAGS_MCOS & pq_flags)) * + qed_init_qm_get_num_tcs(p_hwfn) + + (!!(PQ_FLAGS_LB & pq_flags)) + (!!(PQ_FLAGS_OOO & pq_flags)) + + (!!(PQ_FLAGS_ACK & pq_flags)) + (!!(PQ_FLAGS_OFLD & pq_flags)) + + (!!(PQ_FLAGS_LLT & pq_flags)) + + (!!(PQ_FLAGS_VFS & pq_flags)) * qed_init_qm_get_num_vfs(p_hwfn); +} + +/* initialize the top level QM params */ +static void qed_init_qm_params(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + bool four_port; + + /* pq and vport bases for this PF */ + qm_info->start_pq = (u16) RESC_START(p_hwfn, QED_PQ); + qm_info->start_vport = (u8) RESC_START(p_hwfn, QED_VPORT); + + /* rate limiting and weighted fair queueing are always enabled */ + qm_info->vport_rl_en = 1; + qm_info->vport_wfq_en = 1; + + /* TC config is different for AH 4 port */ + four_port = p_hwfn->cdev->num_ports_in_engines == MAX_NUM_PORTS_K2; + + /* in AH 4 port we have fewer TCs per port */ + qm_info->max_phys_tcs_per_port = four_port ? NUM_PHYS_TCS_4PORT_K2 : + NUM_OF_PHYS_TCS; + + /* unless MFW indicated otherwise, ooo_tc == 3 for + * AH 4-port and 4 otherwise. + */ + if (!qm_info->ooo_tc) + qm_info->ooo_tc = four_port ? DCBX_TCP_OOO_K2_4PORT_TC : + DCBX_TCP_OOO_TC; +} + +/* initialize qm vport params */ +static void qed_init_qm_vport_params(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + u8 i; + /* all vports participate in weighted fair queueing */ + for (i = 0; i < qed_init_qm_get_num_vports(p_hwfn); i++) + qm_info->qm_vport_params[i].vport_wfq = 1; +} + +/* initialize qm port params */ +static void qed_init_qm_port_params(struct qed_hwfn *p_hwfn) +{ /* Initialize qm port parameters */ - num_ports = p_hwfn->cdev->num_ports_in_engines; + u8 i, active_phys_tcs, num_ports = p_hwfn->cdev->num_ports_in_engines; + + /* indicate how ooo and high pri traffic is dealt with */ + active_phys_tcs = num_ports == MAX_NUM_PORTS_K2 ? + ACTIVE_TCS_BMAP_4PORT_K2 : + ACTIVE_TCS_BMAP; + for (i = 0; i < num_ports; i++) { - p_qm_port = &qm_info->qm_port_params[i]; + struct init_qm_port_params *p_qm_port = + &p_hwfn->qm_info.qm_port_params[i]; + p_qm_port->active = 1; - if (num_ports == 4) - p_qm_port->active_phys_tcs = 0x7; - else - p_qm_port->active_phys_tcs = 0x9f; + p_qm_port->active_phys_tcs = active_phys_tcs; p_qm_port->num_pbf_cmd_lines = PBF_MAX_CMD_LINES / num_ports; p_qm_port->num_btb_blocks = BTB_MAX_BLOCKS / num_ports; } +} + +/* Reset the params which must be reset for qm init. QM init may be called as + * a result of flows other than driver load (e.g. dcbx renegotiation). Other + * params may be affected by the init but would simply recalculate to the same + * values. The allocations made for QM init, ports, vports, pqs and vfqs are not + * affected as these amounts stay the same. + */ +static void qed_init_qm_reset_params(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + + qm_info->num_pqs = 0; + qm_info->num_vports = 0; + qm_info->num_pf_rls = 0; + qm_info->num_vf_pqs = 0; + qm_info->first_vf_pq = 0; + qm_info->first_mcos_pq = 0; + qm_info->first_rl_pq = 0; +} + +static void qed_init_qm_advance_vport(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + + qm_info->num_vports++; + + if (qm_info->num_vports > qed_init_qm_get_num_vports(p_hwfn)) + DP_ERR(p_hwfn, + "vport overflow! qm_info->num_vports %d, qm_init_get_num_vports() %d\n", + qm_info->num_vports, qed_init_qm_get_num_vports(p_hwfn)); +} + +/* initialize a single pq and manage qm_info resources accounting. + * The pq_init_flags param determines whether the PQ is rate limited + * (for VF or PF) and whether a new vport is allocated to the pq or not + * (i.e. vport will be shared). + */ + +/* flags for pq init */ +#define PQ_INIT_SHARE_VPORT (1 << 0) +#define PQ_INIT_PF_RL (1 << 1) +#define PQ_INIT_VF_RL (1 << 2) + +/* defines for pq init */ +#define PQ_INIT_DEFAULT_WRR_GROUP 1 +#define PQ_INIT_DEFAULT_TC 0 +#define PQ_INIT_OFLD_TC (p_hwfn->hw_info.offload_tc) + +static void qed_init_qm_pq(struct qed_hwfn *p_hwfn, + struct qed_qm_info *qm_info, + u8 tc, u32 pq_init_flags) +{ + u16 pq_idx = qm_info->num_pqs, max_pq = qed_init_qm_get_num_pqs(p_hwfn); + + if (pq_idx > max_pq) + DP_ERR(p_hwfn, + "pq overflow! pq %d, max pq %d\n", pq_idx, max_pq); + + /* init pq params */ + qm_info->qm_pq_params[pq_idx].vport_id = qm_info->start_vport + + qm_info->num_vports; + qm_info->qm_pq_params[pq_idx].tc_id = tc; + qm_info->qm_pq_params[pq_idx].wrr_group = PQ_INIT_DEFAULT_WRR_GROUP; + qm_info->qm_pq_params[pq_idx].rl_valid = + (pq_init_flags & PQ_INIT_PF_RL || pq_init_flags & PQ_INIT_VF_RL); + + /* qm params accounting */ + qm_info->num_pqs++; + if (!(pq_init_flags & PQ_INIT_SHARE_VPORT)) + qm_info->num_vports++; + + if (pq_init_flags & PQ_INIT_PF_RL) + qm_info->num_pf_rls++; + + if (qm_info->num_vports > qed_init_qm_get_num_vports(p_hwfn)) + DP_ERR(p_hwfn, + "vport overflow! qm_info->num_vports %d, qm_init_get_num_vports() %d\n", + qm_info->num_vports, qed_init_qm_get_num_vports(p_hwfn)); + + if (qm_info->num_pf_rls > qed_init_qm_get_num_pf_rls(p_hwfn)) + DP_ERR(p_hwfn, + "rl overflow! qm_info->num_pf_rls %d, qm_init_get_num_pf_rls() %d\n", + qm_info->num_pf_rls, qed_init_qm_get_num_pf_rls(p_hwfn)); +} + +/* get pq index according to PQ_FLAGS */ +static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn, + u32 pq_flags) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + + /* Can't have multiple flags set here */ + if (bitmap_weight((unsigned long *)&pq_flags, sizeof(pq_flags)) > 1) + goto err; + + switch (pq_flags) { + case PQ_FLAGS_RLS: + return &qm_info->first_rl_pq; + case PQ_FLAGS_MCOS: + return &qm_info->first_mcos_pq; + case PQ_FLAGS_LB: + return &qm_info->pure_lb_pq; + case PQ_FLAGS_OOO: + return &qm_info->ooo_pq; + case PQ_FLAGS_ACK: + return &qm_info->pure_ack_pq; + case PQ_FLAGS_OFLD: + return &qm_info->offload_pq; + case PQ_FLAGS_LLT: + return &qm_info->low_latency_pq; + case PQ_FLAGS_VFS: + return &qm_info->first_vf_pq; + default: + goto err; + } + +err: + DP_ERR(p_hwfn, "BAD pq flags %d\n", pq_flags); + return NULL; +} + +/* save pq index in qm info */ +static void qed_init_qm_set_idx(struct qed_hwfn *p_hwfn, + u32 pq_flags, u16 pq_val) +{ + u16 *base_pq_idx = qed_init_qm_get_idx_from_flags(p_hwfn, pq_flags); + + *base_pq_idx = p_hwfn->qm_info.start_pq + pq_val; +} + +/* get tx pq index, with the PQ TX base already set (ready for context init) */ +u16 qed_get_cm_pq_idx(struct qed_hwfn *p_hwfn, u32 pq_flags) +{ + u16 *base_pq_idx = qed_init_qm_get_idx_from_flags(p_hwfn, pq_flags); + + return *base_pq_idx + CM_TX_PQ_BASE; +} + +u16 qed_get_cm_pq_idx_mcos(struct qed_hwfn *p_hwfn, u8 tc) +{ + u8 max_tc = qed_init_qm_get_num_tcs(p_hwfn); + + if (tc > max_tc) + DP_ERR(p_hwfn, "tc %d must be smaller than %d\n", tc, max_tc); + + return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_MCOS) + tc; +} + +u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf) +{ + u16 max_vf = qed_init_qm_get_num_vfs(p_hwfn); + + if (vf > max_vf) + DP_ERR(p_hwfn, "vf %d must be smaller than %d\n", vf, max_vf); + + return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_VFS) + vf; +} + +u16 qed_get_cm_pq_idx_rl(struct qed_hwfn *p_hwfn, u8 rl) +{ + u16 max_rl = qed_init_qm_get_num_pf_rls(p_hwfn); + + if (rl > max_rl) + DP_ERR(p_hwfn, "rl %d must be smaller than %d\n", rl, max_rl); + + return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_RLS) + rl; +} + +/* Functions for creating specific types of pqs */ +static void qed_init_qm_lb_pq(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + + if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_LB)) + return; + + qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LB, qm_info->num_pqs); + qed_init_qm_pq(p_hwfn, qm_info, PURE_LB_TC, PQ_INIT_SHARE_VPORT); +} + +static void qed_init_qm_ooo_pq(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + + if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_OOO)) + return; + + qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OOO, qm_info->num_pqs); + qed_init_qm_pq(p_hwfn, qm_info, qm_info->ooo_tc, PQ_INIT_SHARE_VPORT); +} + +static void qed_init_qm_pure_ack_pq(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + + if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_ACK)) + return; + + qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_ACK, qm_info->num_pqs); + qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT); +} + +static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + + if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_OFLD)) + return; + + qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OFLD, qm_info->num_pqs); + qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT); +} - qm_info->max_phys_tcs_per_port = NUM_OF_PHYS_TCS; +static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + + if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_LLT)) + return; + + qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LLT, qm_info->num_pqs); + qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT); +} + +static void qed_init_qm_mcos_pqs(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + u8 tc_idx; + + if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_MCOS)) + return; + + qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_MCOS, qm_info->num_pqs); + for (tc_idx = 0; tc_idx < qed_init_qm_get_num_tcs(p_hwfn); tc_idx++) + qed_init_qm_pq(p_hwfn, qm_info, tc_idx, PQ_INIT_SHARE_VPORT); +} + +static void qed_init_qm_vf_pqs(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + u16 vf_idx, num_vfs = qed_init_qm_get_num_vfs(p_hwfn); - qm_info->start_pq = (u16)RESC_START(p_hwfn, QED_PQ); + if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_VFS)) + return; + qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_VFS, qm_info->num_pqs); qm_info->num_vf_pqs = num_vfs; - qm_info->start_vport = (u8) RESC_START(p_hwfn, QED_VPORT); + for (vf_idx = 0; vf_idx < num_vfs; vf_idx++) + qed_init_qm_pq(p_hwfn, + qm_info, PQ_INIT_DEFAULT_TC, PQ_INIT_VF_RL); +} - for (i = 0; i < qm_info->num_vports; i++) - qm_info->qm_vport_params[i].vport_wfq = 1; +static void qed_init_qm_rl_pqs(struct qed_hwfn *p_hwfn) +{ + u16 pf_rls_idx, num_pf_rls = qed_init_qm_get_num_pf_rls(p_hwfn); + struct qed_qm_info *qm_info = &p_hwfn->qm_info; - qm_info->vport_rl_en = 1; - qm_info->vport_wfq_en = 1; - qm_info->pf_rl = pf_rl; - qm_info->pf_wfq = pf_wfq; + if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_RLS)) + return; + + qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_RLS, qm_info->num_pqs); + for (pf_rls_idx = 0; pf_rls_idx < num_pf_rls; pf_rls_idx++) + qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_PF_RL); +} + +static void qed_init_qm_pq_params(struct qed_hwfn *p_hwfn) +{ + /* rate limited pqs, must come first (FW assumption) */ + qed_init_qm_rl_pqs(p_hwfn); + + /* pqs for multi cos */ + qed_init_qm_mcos_pqs(p_hwfn); + + /* pure loopback pq */ + qed_init_qm_lb_pq(p_hwfn); + + /* out of order pq */ + qed_init_qm_ooo_pq(p_hwfn); + + /* pure ack pq */ + qed_init_qm_pure_ack_pq(p_hwfn); + + /* pq for offloaded protocol */ + qed_init_qm_offload_pq(p_hwfn); + + /* low latency pq */ + qed_init_qm_low_latency_pq(p_hwfn); + + /* done sharing vports */ + qed_init_qm_advance_vport(p_hwfn); + + /* pqs for vfs */ + qed_init_qm_vf_pqs(p_hwfn); +} + +/* compare values of getters against resources amounts */ +static int qed_init_qm_sanity(struct qed_hwfn *p_hwfn) +{ + if (qed_init_qm_get_num_vports(p_hwfn) > RESC_NUM(p_hwfn, QED_VPORT)) { + DP_ERR(p_hwfn, "requested amount of vports exceeds resource\n"); + return -EINVAL; + } + + if (qed_init_qm_get_num_pqs(p_hwfn) > RESC_NUM(p_hwfn, QED_PQ)) { + DP_ERR(p_hwfn, "requested amount of pqs exceeds resource\n"); + return -EINVAL; + } return 0; +} -alloc_err: - qed_qm_info_free(p_hwfn); - return -ENOMEM; +static void qed_dp_init_qm_params(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + struct init_qm_vport_params *vport; + struct init_qm_port_params *port; + struct init_qm_pq_params *pq; + int i, tc; + + /* top level params */ + DP_VERBOSE(p_hwfn, + NETIF_MSG_HW, + "qm init top level params: start_pq %d, start_vport %d, pure_lb_pq %d, offload_pq %d, pure_ack_pq %d\n", + qm_info->start_pq, + qm_info->start_vport, + qm_info->pure_lb_pq, + qm_info->offload_pq, qm_info->pure_ack_pq); + DP_VERBOSE(p_hwfn, + NETIF_MSG_HW, + "ooo_pq %d, first_vf_pq %d, num_pqs %d, num_vf_pqs %d, num_vports %d, max_phys_tcs_per_port %d\n", + qm_info->ooo_pq, + qm_info->first_vf_pq, + qm_info->num_pqs, + qm_info->num_vf_pqs, + qm_info->num_vports, qm_info->max_phys_tcs_per_port); + DP_VERBOSE(p_hwfn, + NETIF_MSG_HW, + "pf_rl_en %d, pf_wfq_en %d, vport_rl_en %d, vport_wfq_en %d, pf_wfq %d, pf_rl %d, num_pf_rls %d, pq_flags %x\n", + qm_info->pf_rl_en, + qm_info->pf_wfq_en, + qm_info->vport_rl_en, + qm_info->vport_wfq_en, + qm_info->pf_wfq, + qm_info->pf_rl, + qm_info->num_pf_rls, qed_get_pq_flags(p_hwfn)); + + /* port table */ + for (i = 0; i < p_hwfn->cdev->num_ports_in_engines; i++) { + port = &(qm_info->qm_port_params[i]); + DP_VERBOSE(p_hwfn, + NETIF_MSG_HW, + "port idx %d, active %d, active_phys_tcs %d, num_pbf_cmd_lines %d, num_btb_blocks %d, reserved %d\n", + i, + port->active, + port->active_phys_tcs, + port->num_pbf_cmd_lines, + port->num_btb_blocks, port->reserved); + } + + /* vport table */ + for (i = 0; i < qm_info->num_vports; i++) { + vport = &(qm_info->qm_vport_params[i]); + DP_VERBOSE(p_hwfn, + NETIF_MSG_HW, + "vport idx %d, vport_rl %d, wfq %d, first_tx_pq_id [ ", + qm_info->start_vport + i, + vport->vport_rl, vport->vport_wfq); + for (tc = 0; tc < NUM_OF_TCS; tc++) + DP_VERBOSE(p_hwfn, + NETIF_MSG_HW, + "%d ", vport->first_tx_pq_id[tc]); + DP_VERBOSE(p_hwfn, NETIF_MSG_HW, "]\n"); + } + + /* pq table */ + for (i = 0; i < qm_info->num_pqs; i++) { + pq = &(qm_info->qm_pq_params[i]); + DP_VERBOSE(p_hwfn, + NETIF_MSG_HW, + "pq idx %d, vport_id %d, tc %d, wrr_grp %d, rl_valid %d\n", + qm_info->start_pq + i, + pq->vport_id, + pq->tc_id, pq->wrr_group, pq->rl_valid); + } +} + +static void qed_init_qm_info(struct qed_hwfn *p_hwfn) +{ + /* reset params required for init run */ + qed_init_qm_reset_params(p_hwfn); + + /* init QM top level params */ + qed_init_qm_params(p_hwfn); + + /* init QM port params */ + qed_init_qm_port_params(p_hwfn); + + /* init QM vport params */ + qed_init_qm_vport_params(p_hwfn); + + /* init QM physical queue params */ + qed_init_qm_pq_params(p_hwfn); + + /* display all that init */ + qed_dp_init_qm_params(p_hwfn); } /* This function reconfigures the QM pf on the fly. @@ -391,17 +766,8 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) bool b_rc; int rc; - /* qm_info is allocated in qed_init_qm_info() which is already called - * from qed_resc_alloc() or previous call of qed_qm_reconf(). - * The allocated size may change each init, so we free it before next - * allocation. - */ - qed_qm_info_free(p_hwfn); - /* initialize qed's qm data structure */ - rc = qed_init_qm_info(p_hwfn, false); - if (rc) - return rc; + qed_init_qm_info(p_hwfn); /* stop PF's qm queues */ spin_lock_bh(&qm_lock); @@ -415,7 +781,7 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) qed_init_clear_rt_data(p_hwfn); /* prepare QM portion of runtime array */ - qed_qm_init_pf(p_hwfn); + qed_qm_init_pf(p_hwfn, p_ptt); /* activate init tool on runtime array */ rc = qed_init_run(p_hwfn, p_ptt, PHASE_QM_PF, p_hwfn->rel_pf_id, @@ -434,6 +800,47 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) return 0; } +static int qed_alloc_qm_data(struct qed_hwfn *p_hwfn) +{ + struct qed_qm_info *qm_info = &p_hwfn->qm_info; + int rc; + + rc = qed_init_qm_sanity(p_hwfn); + if (rc) + goto alloc_err; + + qm_info->qm_pq_params = kzalloc(sizeof(*qm_info->qm_pq_params) * + qed_init_qm_get_num_pqs(p_hwfn), + GFP_KERNEL); + if (!qm_info->qm_pq_params) + goto alloc_err; + + qm_info->qm_vport_params = kzalloc(sizeof(*qm_info->qm_vport_params) * + qed_init_qm_get_num_vports(p_hwfn), + GFP_KERNEL); + if (!qm_info->qm_vport_params) + goto alloc_err; + + qm_info->qm_port_params = kzalloc(sizeof(qm_info->qm_port_params) * + p_hwfn->cdev->num_ports_in_engines, + GFP_KERNEL); + if (!qm_info->qm_port_params) + goto alloc_err; + + qm_info->wfq_data = kzalloc(sizeof(*qm_info->wfq_data) * + qed_init_qm_get_num_vports(p_hwfn), + GFP_KERNEL); + if (!qm_info->wfq_data) + goto alloc_err; + + return 0; + +alloc_err: + DP_NOTICE(p_hwfn, "Failed to allocate memory for QM params\n"); + qed_qm_info_free(p_hwfn); + return -ENOMEM; +} + int qed_resc_alloc(struct qed_dev *cdev) { struct qed_iscsi_info *p_iscsi_info; @@ -442,8 +849,10 @@ int qed_resc_alloc(struct qed_dev *cdev) #ifdef CONFIG_QED_LL2 struct qed_ll2_info *p_ll2_info; #endif + u32 rdma_tasks, excess_tasks; struct qed_consq *p_consq; struct qed_eq *p_eq; + u32 line_count; int i, rc = 0; if (IS_VF(cdev)) @@ -465,19 +874,44 @@ int qed_resc_alloc(struct qed_dev *cdev) /* Set the HW cid/tid numbers (in the contest manager) * Must be done prior to any further computations. */ - rc = qed_cxt_set_pf_params(p_hwfn); + rc = qed_cxt_set_pf_params(p_hwfn, RDMA_MAX_TIDS); if (rc) goto alloc_err; - /* Prepare and process QM requirements */ - rc = qed_init_qm_info(p_hwfn, true); + rc = qed_alloc_qm_data(p_hwfn); if (rc) goto alloc_err; + /* init qm info */ + qed_init_qm_info(p_hwfn); + /* Compute the ILT client partition */ - rc = qed_cxt_cfg_ilt_compute(p_hwfn); - if (rc) - goto alloc_err; + rc = qed_cxt_cfg_ilt_compute(p_hwfn, &line_count); + if (rc) { + DP_NOTICE(p_hwfn, + "too many ILT lines; re-computing with less lines\n"); + /* In case there are not enough ILT lines we reduce the + * number of RDMA tasks and re-compute. + */ + excess_tasks = + qed_cxt_cfg_ilt_compute_excess(p_hwfn, line_count); + if (!excess_tasks) + goto alloc_err; + + rdma_tasks = RDMA_MAX_TIDS - excess_tasks; + rc = qed_cxt_set_pf_params(p_hwfn, rdma_tasks); + if (rc) + goto alloc_err; + + rc = qed_cxt_cfg_ilt_compute(p_hwfn, &line_count); + if (rc) { + DP_ERR(p_hwfn, + "failed ILT compute. Requested too many lines: %u\n", + line_count); + + goto alloc_err; + } + } /* CID map / ILT shadow table / T2 * The talbes sizes are determined by the computations above @@ -758,6 +1192,57 @@ static void qed_init_cau_rt_data(struct qed_dev *cdev) } } +static void qed_init_cache_line_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) +{ + u32 val, wr_mbs, cache_line_size; + + val = qed_rd(p_hwfn, p_ptt, PSWRQ2_REG_WR_MBS0); + switch (val) { + case 0: + wr_mbs = 128; + break; + case 1: + wr_mbs = 256; + break; + case 2: + wr_mbs = 512; + break; + default: + DP_INFO(p_hwfn, + "Unexpected value of PSWRQ2_REG_WR_MBS0 [0x%x]. Avoid configuring PGLUE_B_REG_CACHE_LINE_SIZE.\n", + val); + return; + } + + cache_line_size = min_t(u32, L1_CACHE_BYTES, wr_mbs); + switch (cache_line_size) { + case 32: + val = 0; + break; + case 64: + val = 1; + break; + case 128: + val = 2; + break; + case 256: + val = 3; + break; + default: + DP_INFO(p_hwfn, + "Unexpected value of cache line size [0x%x]. Avoid configuring PGLUE_B_REG_CACHE_LINE_SIZE.\n", + cache_line_size); + } + + if (L1_CACHE_BYTES > wr_mbs) + DP_INFO(p_hwfn, + "The cache line size for padding is suboptimal for performance [OS cache line size 0x%x, wr mbs 0x%x]\n", + L1_CACHE_BYTES, wr_mbs); + + STORE_RT_REG(p_hwfn, PGLUE_REG_B_CACHE_LINE_SIZE_RT_OFFSET, val); +} + static int qed_hw_init_common(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, int hw_mode) { @@ -794,17 +1279,7 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn, qed_cxt_hw_init_common(p_hwfn); - /* Close gate from NIG to BRB/Storm; By default they are open, but - * we close them to prevent NIG from passing data to reset blocks. - * Should have been done in the ENGINE phase, but init-tool lacks - * proper port-pretend capabilities. - */ - qed_wr(p_hwfn, p_ptt, NIG_REG_RX_BRB_OUT_EN, 0); - qed_wr(p_hwfn, p_ptt, NIG_REG_STORM_OUT_EN, 0); - qed_port_pretend(p_hwfn, p_ptt, p_hwfn->port_id ^ 1); - qed_wr(p_hwfn, p_ptt, NIG_REG_RX_BRB_OUT_EN, 0); - qed_wr(p_hwfn, p_ptt, NIG_REG_STORM_OUT_EN, 0); - qed_port_unpretend(p_hwfn, p_ptt); + qed_init_cache_line_size(p_hwfn, p_ptt); rc = qed_init_run(p_hwfn, p_ptt, PHASE_ENGINE, ANY_PHASE_ID, hw_mode); if (rc) @@ -887,7 +1362,7 @@ qed_hw_init_pf_doorbell_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) int rc = 0; u8 cond; - db_bar_size = qed_hw_bar_size(p_hwfn, BAR_ID_1); + db_bar_size = qed_hw_bar_size(p_hwfn, p_ptt, BAR_ID_1); if (p_hwfn->cdev->num_hwfns > 1) db_bar_size /= 2; @@ -998,7 +1473,7 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn, p_hwfn->qm_info.pf_rl = 100000; } - qed_cxt_hw_init_pf(p_hwfn); + qed_cxt_hw_init_pf(p_hwfn, p_ptt); qed_int_igu_init_rt(p_hwfn); @@ -1419,18 +1894,21 @@ int qed_hw_stop(struct qed_dev *cdev) return rc2; } -void qed_hw_stop_fastpath(struct qed_dev *cdev) +int qed_hw_stop_fastpath(struct qed_dev *cdev) { int j; for_each_hwfn(cdev, j) { struct qed_hwfn *p_hwfn = &cdev->hwfns[j]; - struct qed_ptt *p_ptt = p_hwfn->p_main_ptt; + struct qed_ptt *p_ptt; if (IS_VF(cdev)) { qed_vf_pf_int_cleanup(p_hwfn); continue; } + p_ptt = qed_ptt_acquire(p_hwfn); + if (!p_ptt) + return -EAGAIN; DP_VERBOSE(p_hwfn, NETIF_MSG_IFDOWN, "Shutting down the fastpath\n"); @@ -1448,17 +1926,28 @@ void qed_hw_stop_fastpath(struct qed_dev *cdev) /* Need to wait 1ms to guarantee SBs are cleared */ usleep_range(1000, 2000); + qed_ptt_release(p_hwfn, p_ptt); } + + return 0; } -void qed_hw_start_fastpath(struct qed_hwfn *p_hwfn) +int qed_hw_start_fastpath(struct qed_hwfn *p_hwfn) { + struct qed_ptt *p_ptt; + if (IS_VF(p_hwfn->cdev)) - return; + return 0; + + p_ptt = qed_ptt_acquire(p_hwfn); + if (!p_ptt) + return -EAGAIN; /* Re-open incoming traffic */ - qed_wr(p_hwfn, p_hwfn->p_main_ptt, - NIG_REG_RX_LLH_BRB_GATE_DNTFWD_PERPF, 0x0); + qed_wr(p_hwfn, p_ptt, NIG_REG_RX_LLH_BRB_GATE_DNTFWD_PERPF, 0x0); + qed_ptt_release(p_hwfn, p_ptt); + + return 0; } /* Free hwfn memory and resources acquired in hw_hwfn_prepare */ @@ -1556,12 +2045,17 @@ static void qed_hw_set_feat(struct qed_hwfn *p_hwfn) QED_VF_L2_QUE)); } + if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) + feat_num[QED_ISCSI_CQ] = min_t(u32, RESC_NUM(p_hwfn, QED_SB), + RESC_NUM(p_hwfn, + QED_CMDQS_CQS)); DP_VERBOSE(p_hwfn, NETIF_MSG_PROBE, - "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d #SBS=%d\n", + "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d ISCSI_CQ=%d #SBS=%d\n", (int)FEAT_NUM(p_hwfn, QED_PF_L2_QUE), (int)FEAT_NUM(p_hwfn, QED_VF_L2_QUE), (int)FEAT_NUM(p_hwfn, QED_RDMA_CNQ), + (int)FEAT_NUM(p_hwfn, QED_ISCSI_CQ), RESC_NUM(p_hwfn, QED_SB)); } @@ -2253,6 +2747,9 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn, p_hwfn->hw_info.personality = protocol; } + p_hwfn->hw_info.num_hw_tc = NUM_PHYS_TCS_4PORT_K2; + p_hwfn->hw_info.num_active_tc = 1; + qed_get_num_funcs(p_hwfn, p_ptt); if (qed_mcp_is_init(p_hwfn)) @@ -2261,9 +2758,9 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn, return qed_hw_get_resc(p_hwfn, p_ptt); } -static int qed_get_dev_info(struct qed_dev *cdev) +static int qed_get_dev_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { - struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); + struct qed_dev *cdev = p_hwfn->cdev; u16 device_id_mask; u32 tmp; @@ -2285,15 +2782,13 @@ static int qed_get_dev_info(struct qed_dev *cdev) return -EBUSY; } - cdev->chip_num = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt, - MISCS_REG_CHIP_NUM); - cdev->chip_rev = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt, - MISCS_REG_CHIP_REV); + cdev->chip_num = (u16)qed_rd(p_hwfn, p_ptt, MISCS_REG_CHIP_NUM); + cdev->chip_rev = (u16)qed_rd(p_hwfn, p_ptt, MISCS_REG_CHIP_REV); + MASK_FIELD(CHIP_REV, cdev->chip_rev); /* Learn number of HW-functions */ - tmp = qed_rd(p_hwfn, p_hwfn->p_main_ptt, - MISCS_REG_CMT_ENABLED_FOR_PAIR); + tmp = qed_rd(p_hwfn, p_ptt, MISCS_REG_CMT_ENABLED_FOR_PAIR); if (tmp & (1 << p_hwfn->rel_pf_id)) { DP_NOTICE(cdev->hwfns, "device in CMT mode\n"); @@ -2302,11 +2797,10 @@ static int qed_get_dev_info(struct qed_dev *cdev) cdev->num_hwfns = 1; } - cdev->chip_bond_id = qed_rd(p_hwfn, p_hwfn->p_main_ptt, + cdev->chip_bond_id = qed_rd(p_hwfn, p_ptt, MISCS_REG_CHIP_TEST_REG) >> 4; MASK_FIELD(CHIP_BOND_ID, cdev->chip_bond_id); - cdev->chip_metal = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt, - MISCS_REG_CHIP_METAL); + cdev->chip_metal = (u16)qed_rd(p_hwfn, p_ptt, MISCS_REG_CHIP_METAL); MASK_FIELD(CHIP_METAL, cdev->chip_metal); DP_INFO(cdev->hwfns, @@ -2359,7 +2853,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn, /* First hwfn learns basic information, e.g., number of hwfns */ if (!p_hwfn->my_id) { - rc = qed_get_dev_info(p_hwfn->cdev); + rc = qed_get_dev_info(p_hwfn, p_hwfn->p_main_ptt); if (rc) goto err1; } @@ -2430,11 +2924,14 @@ int qed_hw_prepare(struct qed_dev *cdev, u8 __iomem *addr; /* adjust bar offset for second engine */ - addr = cdev->regview + qed_hw_bar_size(p_hwfn, BAR_ID_0) / 2; + addr = cdev->regview + + qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt, + BAR_ID_0) / 2; p_regview = addr; - /* adjust doorbell bar offset for second engine */ - addr = cdev->doorbells + qed_hw_bar_size(p_hwfn, BAR_ID_1) / 2; + addr = cdev->doorbells + + qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt, + BAR_ID_1) / 2; p_doorbell = addr; /* prepare second hw function */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h index 2c6637fd7ef6..341636da9964 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h +++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h @@ -165,17 +165,19 @@ int qed_hw_stop(struct qed_dev *cdev); * * @param cdev * + * @return int */ -void qed_hw_stop_fastpath(struct qed_dev *cdev); +int qed_hw_stop_fastpath(struct qed_dev *cdev); /** * @brief qed_hw_start_fastpath -restart fastpath traffic, * only if hw_stop_fastpath was called * - * @param cdev + * @param p_hwfn * + * @return int */ -void qed_hw_start_fastpath(struct qed_hwfn *p_hwfn); +int qed_hw_start_fastpath(struct qed_hwfn *p_hwfn); /** diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c index 60921b72c995..21a58fffd02b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c +++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c @@ -241,7 +241,7 @@ qed_sp_fcoe_conn_offload(struct qed_hwfn *p_hwfn, struct fcoe_conn_offload_ramrod_data *p_data; struct qed_spq_entry *p_ent = NULL; struct qed_sp_init_data init_data; - u16 pq_id = 0, tmp; + u16 physical_q0, tmp; int rc; /* Get SPQ entry */ @@ -261,9 +261,9 @@ qed_sp_fcoe_conn_offload(struct qed_hwfn *p_hwfn, p_data = &p_ramrod->offload_ramrod_data; /* Transmission PQ is the first of the PF */ - pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_FCOE, NULL); - p_conn->physical_q0 = cpu_to_le16(pq_id); - p_data->physical_q0 = cpu_to_le16(pq_id); + physical_q0 = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD); + p_conn->physical_q0 = cpu_to_le16(physical_q0); + p_data->physical_q0 = cpu_to_le16(physical_q0); p_data->conn_id = cpu_to_le16(p_conn->conn_id); DMA_REGPAIR_LE(p_data->sq_pbl_addr, p_conn->sq_pbl_addr); @@ -340,10 +340,10 @@ qed_sp_fcoe_conn_destroy(struct qed_hwfn *p_hwfn, static int qed_sp_fcoe_func_stop(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, enum spq_mode comp_mode, struct qed_spq_comp_cb *p_comp_addr) { - struct qed_ptt *p_ptt = p_hwfn->p_main_ptt; struct qed_spq_entry *p_ent = NULL; struct qed_sp_init_data init_data; u32 active_segs = 0; @@ -765,6 +765,7 @@ static struct qed_hash_fcoe_con *qed_fcoe_get_hash(struct qed_dev *cdev, static int qed_fcoe_stop(struct qed_dev *cdev) { + struct qed_ptt *p_ptt; int rc; if (!(cdev->flags & QED_FLAG_STORAGE_STARTED)) { @@ -778,10 +779,15 @@ static int qed_fcoe_stop(struct qed_dev *cdev) return -EINVAL; } + p_ptt = qed_ptt_acquire(QED_LEADING_HWFN(cdev)); + if (!p_ptt) + return -EAGAIN; + /* Stop the fcoe */ - rc = qed_sp_fcoe_func_stop(QED_LEADING_HWFN(cdev), + rc = qed_sp_fcoe_func_stop(QED_LEADING_HWFN(cdev), p_ptt, QED_SPQ_MODE_EBLOCK, NULL); cdev->flags &= ~QED_FLAG_STORAGE_STARTED; + qed_ptt_release(QED_LEADING_HWFN(cdev), p_ptt); return rc; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index c6b9a3fd4f46..858a57a73589 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -3473,6 +3473,11 @@ void qed_set_geneve_dest_port(struct qed_hwfn *p_hwfn, void qed_set_geneve_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool eth_geneve_enable, bool ip_geneve_enable); +void qed_set_rfs_mode_disable(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u16 pf_id); +void qed_set_rfs_mode_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u16 pf_id, bool tcp, bool udp, + bool ipv4, bool ipv6); #define YSTORM_FLOW_CONTROL_MODE_OFFSET (IRO[0].base) #define YSTORM_FLOW_CONTROL_MODE_SIZE (IRO[0].size) @@ -4862,6 +4867,18 @@ struct eth_vport_tx_mode { __le16 reserved2[3]; }; +enum gft_filter_update_action { + GFT_ADD_FILTER, + GFT_DELETE_FILTER, + MAX_GFT_FILTER_UPDATE_ACTION +}; + +enum gft_logic_filter_type { + GFT_FILTER_TYPE, + RFS_FILTER_TYPE, + MAX_GFT_LOGIC_FILTER_TYPE +}; + /* Ramrod data for rx queue start ramrod */ struct rx_queue_start_ramrod_data { __le16 rx_queue_id; @@ -4932,6 +4949,16 @@ struct rx_udp_filter_data { __le32 tenant_id; }; +struct rx_update_gft_filter_data { + struct regpair pkt_hdr_addr; + __le16 pkt_hdr_length; + __le16 rx_qid_or_action_icid; + u8 vport_id; + u8 filter_type; + u8 filter_action; + u8 reserved; +}; + /* Ramrod data for rx queue start ramrod */ struct tx_queue_start_ramrod_data { __le16 sb_id; @@ -5075,6 +5102,166 @@ struct vport_update_ramrod_data { struct eth_vport_rss_config rss_config; }; +struct gft_cam_line { + __le32 camline; +#define GFT_CAM_LINE_VALID_MASK 0x1 +#define GFT_CAM_LINE_VALID_SHIFT 0 +#define GFT_CAM_LINE_DATA_MASK 0x3FFF +#define GFT_CAM_LINE_DATA_SHIFT 1 +#define GFT_CAM_LINE_MASK_BITS_MASK 0x3FFF +#define GFT_CAM_LINE_MASK_BITS_SHIFT 15 +#define GFT_CAM_LINE_RESERVED1_MASK 0x7 +#define GFT_CAM_LINE_RESERVED1_SHIFT 29 +}; + +struct gft_cam_line_mapped { + __le32 camline; +#define GFT_CAM_LINE_MAPPED_VALID_MASK 0x1 +#define GFT_CAM_LINE_MAPPED_VALID_SHIFT 0 +#define GFT_CAM_LINE_MAPPED_IP_VERSION_MASK 0x1 +#define GFT_CAM_LINE_MAPPED_IP_VERSION_SHIFT 1 +#define GFT_CAM_LINE_MAPPED_TUNNEL_IP_VERSION_MASK 0x1 +#define GFT_CAM_LINE_MAPPED_TUNNEL_IP_VERSION_SHIFT 2 +#define GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE_MASK 0xF +#define GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE_SHIFT 3 +#define GFT_CAM_LINE_MAPPED_TUNNEL_TYPE_MASK 0xF +#define GFT_CAM_LINE_MAPPED_TUNNEL_TYPE_SHIFT 7 +#define GFT_CAM_LINE_MAPPED_PF_ID_MASK 0xF +#define GFT_CAM_LINE_MAPPED_PF_ID_SHIFT 11 +#define GFT_CAM_LINE_MAPPED_IP_VERSION_MASK_MASK 0x1 +#define GFT_CAM_LINE_MAPPED_IP_VERSION_MASK_SHIFT 15 +#define GFT_CAM_LINE_MAPPED_TUNNEL_IP_VERSION_MASK_MASK 0x1 +#define GFT_CAM_LINE_MAPPED_TUNNEL_IP_VERSION_MASK_SHIFT 16 +#define GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE_MASK_MASK 0xF +#define GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE_MASK_SHIFT 17 +#define GFT_CAM_LINE_MAPPED_TUNNEL_TYPE_MASK_MASK 0xF +#define GFT_CAM_LINE_MAPPED_TUNNEL_TYPE_MASK_SHIFT 21 +#define GFT_CAM_LINE_MAPPED_PF_ID_MASK_MASK 0xF +#define GFT_CAM_LINE_MAPPED_PF_ID_MASK_SHIFT 25 +#define GFT_CAM_LINE_MAPPED_RESERVED1_MASK 0x7 +#define GFT_CAM_LINE_MAPPED_RESERVED1_SHIFT 29 +}; + +union gft_cam_line_union { + struct gft_cam_line cam_line; + struct gft_cam_line_mapped cam_line_mapped; +}; + +enum gft_profile_ip_version { + GFT_PROFILE_IPV4 = 0, + GFT_PROFILE_IPV6 = 1, + MAX_GFT_PROFILE_IP_VERSION +}; + +enum gft_profile_upper_protocol_type { + GFT_PROFILE_ROCE_PROTOCOL = 0, + GFT_PROFILE_RROCE_PROTOCOL = 1, + GFT_PROFILE_FCOE_PROTOCOL = 2, + GFT_PROFILE_ICMP_PROTOCOL = 3, + GFT_PROFILE_ARP_PROTOCOL = 4, + GFT_PROFILE_USER_TCP_SRC_PORT_1_INNER = 5, + GFT_PROFILE_USER_TCP_DST_PORT_1_INNER = 6, + GFT_PROFILE_TCP_PROTOCOL = 7, + GFT_PROFILE_USER_UDP_DST_PORT_1_INNER = 8, + GFT_PROFILE_USER_UDP_DST_PORT_2_OUTER = 9, + GFT_PROFILE_UDP_PROTOCOL = 10, + GFT_PROFILE_USER_IP_1_INNER = 11, + GFT_PROFILE_USER_IP_2_OUTER = 12, + GFT_PROFILE_USER_ETH_1_INNER = 13, + GFT_PROFILE_USER_ETH_2_OUTER = 14, + GFT_PROFILE_RAW = 15, + MAX_GFT_PROFILE_UPPER_PROTOCOL_TYPE +}; + +struct gft_ram_line { + __le32 low32bits; +#define GFT_RAM_LINE_VLAN_SELECT_MASK 0x3 +#define GFT_RAM_LINE_VLAN_SELECT_SHIFT 0 +#define GFT_RAM_LINE_TUNNEL_ENTROPHY_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_ENTROPHY_SHIFT 2 +#define GFT_RAM_LINE_TUNNEL_TTL_EQUAL_ONE_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_TTL_EQUAL_ONE_SHIFT 3 +#define GFT_RAM_LINE_TUNNEL_TTL_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_TTL_SHIFT 4 +#define GFT_RAM_LINE_TUNNEL_ETHERTYPE_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_ETHERTYPE_SHIFT 5 +#define GFT_RAM_LINE_TUNNEL_DST_PORT_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_DST_PORT_SHIFT 6 +#define GFT_RAM_LINE_TUNNEL_SRC_PORT_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_SRC_PORT_SHIFT 7 +#define GFT_RAM_LINE_TUNNEL_DSCP_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_DSCP_SHIFT 8 +#define GFT_RAM_LINE_TUNNEL_OVER_IP_PROTOCOL_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_OVER_IP_PROTOCOL_SHIFT 9 +#define GFT_RAM_LINE_TUNNEL_DST_IP_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_DST_IP_SHIFT 10 +#define GFT_RAM_LINE_TUNNEL_SRC_IP_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_SRC_IP_SHIFT 11 +#define GFT_RAM_LINE_TUNNEL_PRIORITY_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_PRIORITY_SHIFT 12 +#define GFT_RAM_LINE_TUNNEL_PROVIDER_VLAN_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_PROVIDER_VLAN_SHIFT 13 +#define GFT_RAM_LINE_TUNNEL_VLAN_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_VLAN_SHIFT 14 +#define GFT_RAM_LINE_TUNNEL_DST_MAC_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_DST_MAC_SHIFT 15 +#define GFT_RAM_LINE_TUNNEL_SRC_MAC_MASK 0x1 +#define GFT_RAM_LINE_TUNNEL_SRC_MAC_SHIFT 16 +#define GFT_RAM_LINE_TTL_EQUAL_ONE_MASK 0x1 +#define GFT_RAM_LINE_TTL_EQUAL_ONE_SHIFT 17 +#define GFT_RAM_LINE_TTL_MASK 0x1 +#define GFT_RAM_LINE_TTL_SHIFT 18 +#define GFT_RAM_LINE_ETHERTYPE_MASK 0x1 +#define GFT_RAM_LINE_ETHERTYPE_SHIFT 19 +#define GFT_RAM_LINE_RESERVED0_MASK 0x1 +#define GFT_RAM_LINE_RESERVED0_SHIFT 20 +#define GFT_RAM_LINE_TCP_FLAG_FIN_MASK 0x1 +#define GFT_RAM_LINE_TCP_FLAG_FIN_SHIFT 21 +#define GFT_RAM_LINE_TCP_FLAG_SYN_MASK 0x1 +#define GFT_RAM_LINE_TCP_FLAG_SYN_SHIFT 22 +#define GFT_RAM_LINE_TCP_FLAG_RST_MASK 0x1 +#define GFT_RAM_LINE_TCP_FLAG_RST_SHIFT 23 +#define GFT_RAM_LINE_TCP_FLAG_PSH_MASK 0x1 +#define GFT_RAM_LINE_TCP_FLAG_PSH_SHIFT 24 +#define GFT_RAM_LINE_TCP_FLAG_ACK_MASK 0x1 +#define GFT_RAM_LINE_TCP_FLAG_ACK_SHIFT 25 +#define GFT_RAM_LINE_TCP_FLAG_URG_MASK 0x1 +#define GFT_RAM_LINE_TCP_FLAG_URG_SHIFT 26 +#define GFT_RAM_LINE_TCP_FLAG_ECE_MASK 0x1 +#define GFT_RAM_LINE_TCP_FLAG_ECE_SHIFT 27 +#define GFT_RAM_LINE_TCP_FLAG_CWR_MASK 0x1 +#define GFT_RAM_LINE_TCP_FLAG_CWR_SHIFT 28 +#define GFT_RAM_LINE_TCP_FLAG_NS_MASK 0x1 +#define GFT_RAM_LINE_TCP_FLAG_NS_SHIFT 29 +#define GFT_RAM_LINE_DST_PORT_MASK 0x1 +#define GFT_RAM_LINE_DST_PORT_SHIFT 30 +#define GFT_RAM_LINE_SRC_PORT_MASK 0x1 +#define GFT_RAM_LINE_SRC_PORT_SHIFT 31 + __le32 high32bits; +#define GFT_RAM_LINE_DSCP_MASK 0x1 +#define GFT_RAM_LINE_DSCP_SHIFT 0 +#define GFT_RAM_LINE_OVER_IP_PROTOCOL_MASK 0x1 +#define GFT_RAM_LINE_OVER_IP_PROTOCOL_SHIFT 1 +#define GFT_RAM_LINE_DST_IP_MASK 0x1 +#define GFT_RAM_LINE_DST_IP_SHIFT 2 +#define GFT_RAM_LINE_SRC_IP_MASK 0x1 +#define GFT_RAM_LINE_SRC_IP_SHIFT 3 +#define GFT_RAM_LINE_PRIORITY_MASK 0x1 +#define GFT_RAM_LINE_PRIORITY_SHIFT 4 +#define GFT_RAM_LINE_PROVIDER_VLAN_MASK 0x1 +#define GFT_RAM_LINE_PROVIDER_VLAN_SHIFT 5 +#define GFT_RAM_LINE_VLAN_MASK 0x1 +#define GFT_RAM_LINE_VLAN_SHIFT 6 +#define GFT_RAM_LINE_DST_MAC_MASK 0x1 +#define GFT_RAM_LINE_DST_MAC_SHIFT 7 +#define GFT_RAM_LINE_SRC_MAC_MASK 0x1 +#define GFT_RAM_LINE_SRC_MAC_SHIFT 8 +#define GFT_RAM_LINE_TENANT_ID_MASK 0x1 +#define GFT_RAM_LINE_TENANT_ID_SHIFT 9 +#define GFT_RAM_LINE_RESERVED1_MASK 0x3FFFFF +#define GFT_RAM_LINE_RESERVED1_SHIFT 10 +}; + struct mstorm_eth_conn_ag_ctx { u8 byte0; u8 byte1; @@ -9578,12 +9765,12 @@ struct dcbx_ets_feature { #define DCBX_ETS_CBS_SHIFT 3 #define DCBX_ETS_MAX_TCS_MASK 0x000000f0 #define DCBX_ETS_MAX_TCS_SHIFT 4 -#define DCBX_ISCSI_OOO_TC_MASK 0x00000f00 -#define DCBX_ISCSI_OOO_TC_SHIFT 8 +#define DCBX_OOO_TC_MASK 0x00000f00 +#define DCBX_OOO_TC_SHIFT 8 u32 pri_tc_tbl[1]; -#define DCBX_ISCSI_OOO_TC (4) +#define DCBX_TCP_OOO_TC (4) -#define NIG_ETS_ISCSI_OOO_CLIENT_OFFSET (DCBX_ISCSI_OOO_TC + 1) +#define NIG_ETS_ISCSI_OOO_CLIENT_OFFSET (DCBX_TCP_OOO_TC + 1) #define DCBX_CEE_STRICT_PRIORITY 0xf u32 tc_bw_tbl[2]; u32 tc_tsa_tbl[2]; @@ -9592,6 +9779,9 @@ struct dcbx_ets_feature { #define DCBX_ETS_TSA_ETS 2 }; +#define DCBX_TCP_OOO_TC (4) +#define DCBX_TCP_OOO_K2_4PORT_TC (3) + struct dcbx_app_priority_entry { u32 entry; #define DCBX_APP_PRI_MAP_MASK 0x000000ff diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c index 899cad7f97ea..a05feb38c6ee 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hw.c +++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c @@ -58,6 +58,7 @@ struct qed_ptt { struct list_head list_entry; unsigned int idx; struct pxp_ptt_entry pxp; + u8 hwfn_id; }; struct qed_ptt_pool { @@ -79,6 +80,7 @@ int qed_ptt_pool_alloc(struct qed_hwfn *p_hwfn) p_pool->ptts[i].idx = i; p_pool->ptts[i].pxp.offset = QED_BAR_INVALID_OFFSET; p_pool->ptts[i].pxp.pretend.control = 0; + p_pool->ptts[i].hwfn_id = p_hwfn->my_id; if (i >= RESERVED_PTT_MAX) list_add(&p_pool->ptts[i].list_entry, &p_pool->free_list); @@ -193,6 +195,11 @@ static u32 qed_set_ptt(struct qed_hwfn *p_hwfn, offset = hw_addr - win_hw_addr; + if (p_ptt->hwfn_id != p_hwfn->my_id) + DP_NOTICE(p_hwfn, + "ptt[%d] of hwfn[%02x] is used by hwfn[%02x]!\n", + p_ptt->idx, p_ptt->hwfn_id, p_hwfn->my_id); + /* Verify the address is within the window */ if (hw_addr < win_hw_addr || offset >= PXP_EXTERNAL_BAR_PF_WINDOW_SINGLE_SIZE) { @@ -800,55 +807,3 @@ int qed_dmae_host2host(struct qed_hwfn *p_hwfn, return rc; } -u16 qed_get_qm_pq(struct qed_hwfn *p_hwfn, - enum protocol_type proto, union qed_qm_pq_params *p_params) -{ - u16 pq_id = 0; - - if ((proto == PROTOCOLID_CORE || - proto == PROTOCOLID_ETH || - proto == PROTOCOLID_ISCSI || - proto == PROTOCOLID_ROCE) && !p_params) { - DP_NOTICE(p_hwfn, - "Protocol %d received NULL PQ params\n", proto); - return 0; - } - - switch (proto) { - case PROTOCOLID_CORE: - if (p_params->core.tc == LB_TC) - pq_id = p_hwfn->qm_info.pure_lb_pq; - else if (p_params->core.tc == OOO_LB_TC) - pq_id = p_hwfn->qm_info.ooo_pq; - else - pq_id = p_hwfn->qm_info.offload_pq; - break; - case PROTOCOLID_ETH: - pq_id = p_params->eth.tc; - if (p_params->eth.is_vf) - pq_id += p_hwfn->qm_info.vf_queues_offset + - p_params->eth.vf_id; - break; - case PROTOCOLID_ISCSI: - if (p_params->iscsi.q_idx == 1) - pq_id = p_hwfn->qm_info.pure_ack_pq; - break; - case PROTOCOLID_ROCE: - if (p_params->roce.dcqcn) - pq_id = p_params->roce.qpid; - else - pq_id = p_hwfn->qm_info.offload_pq; - if (pq_id > p_hwfn->qm_info.num_pf_rls) - pq_id = p_hwfn->qm_info.offload_pq; - break; - case PROTOCOLID_FCOE: - pq_id = p_hwfn->qm_info.offload_pq; - break; - default: - pq_id = 0; - } - - pq_id = CM_TX_PQ_BASE + pq_id + RESC_START(p_hwfn, QED_PQ); - - return pq_id; -} diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.h b/drivers/net/ethernet/qlogic/qed/qed_hw.h index 9277264d2e65..f2505c691c26 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hw.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hw.h @@ -297,9 +297,6 @@ union qed_qm_pq_params { } roce; }; -u16 qed_get_qm_pq(struct qed_hwfn *p_hwfn, - enum protocol_type proto, union qed_qm_pq_params *params); - int qed_init_fw_data(struct qed_dev *cdev, const u8 *fw_data); #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c index 2a50e2b7568f..67200c5498ab 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c @@ -961,3 +961,132 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn, qed_wr(p_hwfn, p_ptt, DORQ_REG_L2_EDPM_TUNNEL_NGE_IP_EN, ip_geneve_enable ? 1 : 0); } + +#define T_ETH_PACKET_MATCH_RFS_EVENTID 25 +#define PARSER_ETH_CONN_CM_HDR (0x0) +#define CAM_LINE_SIZE sizeof(u32) +#define RAM_LINE_SIZE sizeof(u64) +#define REG_SIZE sizeof(u32) + +void qed_set_rfs_mode_disable(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u16 pf_id) +{ + union gft_cam_line_union camline; + struct gft_ram_line ramline; + u32 *p_ramline, i; + + p_ramline = (u32 *)&ramline; + + /*stop using gft logic */ + qed_wr(p_hwfn, p_ptt, PRS_REG_SEARCH_GFT, 0); + qed_wr(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT, 0x0); + memset(&camline, 0, sizeof(union gft_cam_line_union)); + qed_wr(p_hwfn, p_ptt, PRS_REG_GFT_CAM + CAM_LINE_SIZE * pf_id, + camline.cam_line_mapped.camline); + memset(&ramline, 0, sizeof(union gft_cam_line_union)); + + for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++) { + u32 hw_addr = PRS_REG_GFT_PROFILE_MASK_RAM; + + hw_addr += (RAM_LINE_SIZE * pf_id + i * REG_SIZE); + + qed_wr(p_hwfn, p_ptt, hw_addr, *(p_ramline + i)); + } +} + +void qed_set_rfs_mode_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u16 pf_id, bool tcp, bool udp, + bool ipv4, bool ipv6) +{ + u32 rfs_cm_hdr_event_id, *p_ramline; + union gft_cam_line_union camline; + struct gft_ram_line ramline; + int i; + + rfs_cm_hdr_event_id = qed_rd(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT); + p_ramline = (u32 *)&ramline; + + if (!ipv6 && !ipv4) + DP_NOTICE(p_hwfn, + "set_rfs_mode_enable: must accept at least on of - ipv4 or ipv6"); + if (!tcp && !udp) + DP_NOTICE(p_hwfn, + "set_rfs_mode_enable: must accept at least on of - udp or tcp"); + + rfs_cm_hdr_event_id |= T_ETH_PACKET_MATCH_RFS_EVENTID << + PRS_REG_CM_HDR_GFT_EVENT_ID_SHIFT; + rfs_cm_hdr_event_id |= PARSER_ETH_CONN_CM_HDR << + PRS_REG_CM_HDR_GFT_CM_HDR_SHIFT; + qed_wr(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT, rfs_cm_hdr_event_id); + + /* Configure Registers for RFS mode */ + qed_wr(p_hwfn, p_ptt, PRS_REG_SEARCH_GFT, 1); + qed_wr(p_hwfn, p_ptt, PRS_REG_LOAD_L2_FILTER, 0); + camline.cam_line_mapped.camline = 0; + + /* cam line is now valid!! */ + SET_FIELD(camline.cam_line_mapped.camline, + GFT_CAM_LINE_MAPPED_VALID, 1); + + /* filters are per PF!! */ + SET_FIELD(camline.cam_line_mapped.camline, + GFT_CAM_LINE_MAPPED_PF_ID_MASK, 1); + SET_FIELD(camline.cam_line_mapped.camline, + GFT_CAM_LINE_MAPPED_PF_ID, pf_id); + if (!(tcp && udp)) { + SET_FIELD(camline.cam_line_mapped.camline, + GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE_MASK, 1); + if (tcp) + SET_FIELD(camline.cam_line_mapped.camline, + GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE, + GFT_PROFILE_TCP_PROTOCOL); + else + SET_FIELD(camline.cam_line_mapped.camline, + GFT_CAM_LINE_MAPPED_UPPER_PROTOCOL_TYPE, + GFT_PROFILE_UDP_PROTOCOL); + } + + if (!(ipv4 && ipv6)) { + SET_FIELD(camline.cam_line_mapped.camline, + GFT_CAM_LINE_MAPPED_IP_VERSION_MASK, 1); + if (ipv4) + SET_FIELD(camline.cam_line_mapped.camline, + GFT_CAM_LINE_MAPPED_IP_VERSION, + GFT_PROFILE_IPV4); + else + SET_FIELD(camline.cam_line_mapped.camline, + GFT_CAM_LINE_MAPPED_IP_VERSION, + GFT_PROFILE_IPV6); + } + + /* write characteristics to cam */ + qed_wr(p_hwfn, p_ptt, PRS_REG_GFT_CAM + CAM_LINE_SIZE * pf_id, + camline.cam_line_mapped.camline); + camline.cam_line_mapped.camline = qed_rd(p_hwfn, p_ptt, + PRS_REG_GFT_CAM + + CAM_LINE_SIZE * pf_id); + + /* write line to RAM - compare to filter 4 tuple */ + ramline.low32bits = 0; + ramline.high32bits = 0; + SET_FIELD(ramline.high32bits, GFT_RAM_LINE_DST_IP, 1); + SET_FIELD(ramline.high32bits, GFT_RAM_LINE_SRC_IP, 1); + SET_FIELD(ramline.low32bits, GFT_RAM_LINE_SRC_PORT, 1); + SET_FIELD(ramline.low32bits, GFT_RAM_LINE_DST_PORT, 1); + + /* each iteration write to reg */ + for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++) + qed_wr(p_hwfn, p_ptt, + PRS_REG_GFT_PROFILE_MASK_RAM + RAM_LINE_SIZE * pf_id + + i * REG_SIZE, *(p_ramline + i)); + + /* set default profile so that no filter match will happen */ + ramline.low32bits = 0xffff; + ramline.high32bits = 0xffff; + + for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++) + qed_wr(p_hwfn, p_ptt, + PRS_REG_GFT_PROFILE_MASK_RAM + RAM_LINE_SIZE * + PRS_GFT_CAM_LINES_NO_MATCH + i * REG_SIZE, + *(p_ramline + i)); +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index 84310b60849b..0ed24d6e6c65 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -2500,8 +2500,9 @@ void qed_int_cau_conf_sb(struct qed_hwfn *p_hwfn, /* Configure pi coalescing if set */ if (p_hwfn->cdev->int_coalescing_mode == QED_COAL_MODE_ENABLE) { + u8 num_tc = p_hwfn->hw_info.num_hw_tc; u8 timeset, timer_res; - u8 num_tc = 1, i; + u8 i; /* timeset = (coalesce >> timer-res), timeset is 7bit wide */ if (p_hwfn->cdev->rx_coalesce_usecs <= 0x7F) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c index 2f8ac75ebd84..339c91dfa658 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c @@ -181,6 +181,15 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn, p_params = &p_hwfn->pf_params.iscsi_pf_params; p_queue = &p_init->q_params; + /* Sanity */ + if (p_params->num_queues > p_hwfn->hw_info.feat_num[QED_ISCSI_CQ]) { + DP_ERR(p_hwfn, + "Cannot satisfy CQ amount. Queues requested %d, CQs available %d. Aborting function start\n", + p_params->num_queues, + p_hwfn->hw_info.resc_num[QED_ISCSI_CQ]); + return -EINVAL; + } + SET_FIELD(p_init->hdr.flags, ISCSI_SLOW_PATH_HDR_LAYER_CODE, ISCSI_SLOW_PATH_LAYER_CODE); p_init->hdr.op_code = ISCSI_RAMROD_CMD_ID_INIT_FUNC; @@ -270,11 +279,10 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn, struct tcp_offload_params *p_tcp = NULL; struct qed_spq_entry *p_ent = NULL; struct qed_sp_init_data init_data; - union qed_qm_pq_params pq_params; - u16 pq0_id = 0, pq1_id = 0; dma_addr_t r2tq_pbl_addr; dma_addr_t xhq_pbl_addr; dma_addr_t uhq_pbl_addr; + u16 physical_q; int rc = 0; u32 dval; u16 wval; @@ -297,16 +305,14 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn, p_ramrod = &p_ent->ramrod.iscsi_conn_offload; /* Transmission PQ is the first of the PF */ - memset(&pq_params, 0, sizeof(pq_params)); - pq0_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_ISCSI, &pq_params); - p_conn->physical_q0 = cpu_to_le16(pq0_id); - p_ramrod->iscsi.physical_q0 = cpu_to_le16(pq0_id); + physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD); + p_conn->physical_q0 = cpu_to_le16(physical_q); + p_ramrod->iscsi.physical_q0 = cpu_to_le16(physical_q); /* iSCSI Pure-ACK PQ */ - pq_params.iscsi.q_idx = 1; - pq1_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_ISCSI, &pq_params); - p_conn->physical_q1 = cpu_to_le16(pq1_id); - p_ramrod->iscsi.physical_q1 = cpu_to_le16(pq1_id); + physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_ACK); + p_conn->physical_q1 = cpu_to_le16(physical_q); + p_ramrod->iscsi.physical_q1 = cpu_to_le16(physical_q); p_ramrod->hdr.op_code = ISCSI_RAMROD_CMD_ID_OFFLOAD_CONN; SET_FIELD(p_ramrod->hdr.flags, ISCSI_SLOW_PATH_HDR_LAYER_CODE, @@ -867,6 +873,8 @@ static void _qed_iscsi_get_tstats(struct qed_hwfn *p_hwfn, HILO_64_REGPAIR(tstats.iscsi_rx_bytes_cnt); p_stats->iscsi_rx_packet_cnt = HILO_64_REGPAIR(tstats.iscsi_rx_packet_cnt); + p_stats->iscsi_rx_new_ooo_isle_events_cnt = + HILO_64_REGPAIR(tstats.iscsi_rx_new_ooo_isle_events_cnt); p_stats->iscsi_cmdq_threshold_cnt = le32_to_cpu(tstats.iscsi_cmdq_threshold_cnt); p_stats->iscsi_rq_threshold_cnt = @@ -1013,6 +1021,8 @@ static int qed_fill_iscsi_dev_info(struct qed_dev *cdev, info->secondary_bdq_rq_addr = qed_iscsi_get_secondary_bdq_prod(hwfn, BDQ_ID_RQ); + info->num_cqs = FEAT_NUM(hwfn, QED_ISCSI_CQ); + return rc; } @@ -1314,6 +1324,26 @@ static int qed_iscsi_stats(struct qed_dev *cdev, struct qed_iscsi_stats *stats) return qed_iscsi_get_stats(QED_LEADING_HWFN(cdev), stats); } +void qed_get_protocol_stats_iscsi(struct qed_dev *cdev, + struct qed_mcp_iscsi_stats *stats) +{ + struct qed_iscsi_stats proto_stats; + + /* Retrieve FW statistics */ + memset(&proto_stats, 0, sizeof(proto_stats)); + if (qed_iscsi_stats(cdev, &proto_stats)) { + DP_VERBOSE(cdev, QED_MSG_STORAGE, + "Failed to collect ISCSI statistics\n"); + return; + } + + /* Translate FW statistics into struct */ + stats->rx_pdus = proto_stats.iscsi_rx_total_pdu_cnt; + stats->tx_pdus = proto_stats.iscsi_tx_total_pdu_cnt; + stats->rx_bytes = proto_stats.iscsi_rx_bytes_cnt; + stats->tx_bytes = proto_stats.iscsi_tx_bytes_cnt; +} + static const struct qed_iscsi_ops qed_iscsi_ops_pass = { .common = &qed_common_ops_pass, .ll2 = &qed_ll2_ops_pass, diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h index 20c187f4ed0b..ae98f772cbc0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h @@ -64,13 +64,25 @@ void qed_iscsi_setup(struct qed_hwfn *p_hwfn, void qed_iscsi_free(struct qed_hwfn *p_hwfn, struct qed_iscsi_info *p_iscsi_info); + +/** + * @brief - Fills provided statistics struct with statistics. + * + * @param cdev + * @param stats - points to struct that will be filled with statistics. + */ +void qed_get_protocol_stats_iscsi(struct qed_dev *cdev, + struct qed_mcp_iscsi_stats *stats); #else /* IS_ENABLED(CONFIG_QED_ISCSI) */ static inline struct qed_iscsi_info *qed_iscsi_alloc( struct qed_hwfn *p_hwfn) { return NULL; } static inline void qed_iscsi_setup(struct qed_hwfn *p_hwfn, struct qed_iscsi_info *p_iscsi_info) {} static inline void qed_iscsi_free(struct qed_hwfn *p_hwfn, - struct qed_iscsi_info *p_iscsi_info) {} + struct qed_iscsi_info *p_iscsi_info) {} +static inline void +qed_get_protocol_stats_iscsi(struct qed_dev *cdev, + struct qed_mcp_iscsi_stats *stats) {} #endif /* IS_ENABLED(CONFIG_QED_ISCSI) */ #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 4385ccbb5efb..eb5e280eb104 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -938,15 +938,12 @@ qed_eth_pf_tx_queue_start(struct qed_hwfn *p_hwfn, dma_addr_t pbl_addr, u16 pbl_size, void __iomem **pp_doorbell) { - union qed_qm_pq_params pq_params; int rc; - memset(&pq_params, 0, sizeof(pq_params)); rc = qed_eth_txq_start_ramrod(p_hwfn, p_cid, pbl_addr, pbl_size, - qed_get_qm_pq(p_hwfn, PROTOCOLID_ETH, - &pq_params)); + qed_get_cm_pq_idx_mcos(p_hwfn, tc)); if (rc) return rc; @@ -1802,6 +1799,84 @@ void qed_reset_vport_stats(struct qed_dev *cdev) _qed_get_vport_stats(cdev, cdev->reset_stats); } +static void +qed_arfs_mode_configure(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_arfs_config_params *p_cfg_params) +{ + if (p_cfg_params->arfs_enable) { + qed_set_rfs_mode_enable(p_hwfn, p_ptt, p_hwfn->rel_pf_id, + p_cfg_params->tcp, p_cfg_params->udp, + p_cfg_params->ipv4, p_cfg_params->ipv6); + DP_VERBOSE(p_hwfn, QED_MSG_SP, + "tcp = %s, udp = %s, ipv4 = %s, ipv6 =%s\n", + p_cfg_params->tcp ? "Enable" : "Disable", + p_cfg_params->udp ? "Enable" : "Disable", + p_cfg_params->ipv4 ? "Enable" : "Disable", + p_cfg_params->ipv6 ? "Enable" : "Disable"); + } else { + qed_set_rfs_mode_disable(p_hwfn, p_ptt, p_hwfn->rel_pf_id); + } + + DP_VERBOSE(p_hwfn, QED_MSG_SP, "Configured ARFS mode : %s\n", + p_cfg_params->arfs_enable ? "Enable" : "Disable"); +} + +static int +qed_configure_rfs_ntuple_filter(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_spq_comp_cb *p_cb, + dma_addr_t p_addr, u16 length, u16 qid, + u8 vport_id, bool b_is_add) +{ + struct rx_update_gft_filter_data *p_ramrod = NULL; + struct qed_spq_entry *p_ent = NULL; + struct qed_sp_init_data init_data; + u16 abs_rx_q_id = 0; + u8 abs_vport_id = 0; + int rc = -EINVAL; + + rc = qed_fw_vport(p_hwfn, vport_id, &abs_vport_id); + if (rc) + return rc; + + rc = qed_fw_l2_queue(p_hwfn, qid, &abs_rx_q_id); + if (rc) + return rc; + + /* Get SPQ entry */ + memset(&init_data, 0, sizeof(init_data)); + init_data.cid = qed_spq_get_cid(p_hwfn); + + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + + if (p_cb) { + init_data.comp_mode = QED_SPQ_MODE_CB; + init_data.p_comp_data = p_cb; + } else { + init_data.comp_mode = QED_SPQ_MODE_EBLOCK; + } + + rc = qed_sp_init_request(p_hwfn, &p_ent, + ETH_RAMROD_GFT_UPDATE_FILTER, + PROTOCOLID_ETH, &init_data); + if (rc) + return rc; + + p_ramrod = &p_ent->ramrod.rx_update_gft; + DMA_REGPAIR_LE(p_ramrod->pkt_hdr_addr, p_addr); + p_ramrod->pkt_hdr_length = cpu_to_le16(length); + p_ramrod->rx_qid_or_action_icid = cpu_to_le16(abs_rx_q_id); + p_ramrod->vport_id = abs_vport_id; + p_ramrod->filter_type = RFS_FILTER_TYPE; + p_ramrod->filter_action = b_is_add ? GFT_ADD_FILTER : GFT_DELETE_FILTER; + + DP_VERBOSE(p_hwfn, QED_MSG_SP, + "V[%0x], Q[%04x] - %s filter from 0x%llx [length %04xb]\n", + abs_vport_id, abs_rx_q_id, + b_is_add ? "Adding" : "Removing", (u64)p_addr, length); + + return qed_spq_post(p_hwfn, p_ent, NULL); +} + static int qed_fill_eth_dev_info(struct qed_dev *cdev, struct qed_dev_eth_info *info) { @@ -1932,7 +2007,11 @@ static int qed_start_vport(struct qed_dev *cdev, return rc; } - qed_hw_start_fastpath(p_hwfn); + rc = qed_hw_start_fastpath(p_hwfn); + if (rc) { + DP_ERR(cdev, "Failed to start VPORT fastpath\n"); + return rc; + } DP_VERBOSE(cdev, (QED_MSG_SPQ | NETIF_MSG_IFUP), "Started V-PORT %d with MTU %d\n", @@ -2175,7 +2254,13 @@ static int qed_start_txq(struct qed_dev *cdev, #define QED_HW_STOP_RETRY_LIMIT (10) static int qed_fastpath_stop(struct qed_dev *cdev) { - qed_hw_stop_fastpath(cdev); + int rc; + + rc = qed_hw_stop_fastpath(cdev); + if (rc) { + DP_ERR(cdev, "Failed to stop Fastpath\n"); + return rc; + } return 0; } @@ -2349,6 +2434,59 @@ static int qed_configure_filter(struct qed_dev *cdev, } } +static int qed_configure_arfs_searcher(struct qed_dev *cdev, bool en_searcher) +{ + struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); + struct qed_arfs_config_params arfs_config_params; + + memset(&arfs_config_params, 0, sizeof(arfs_config_params)); + arfs_config_params.tcp = true; + arfs_config_params.udp = true; + arfs_config_params.ipv4 = true; + arfs_config_params.ipv6 = true; + arfs_config_params.arfs_enable = en_searcher; + + qed_arfs_mode_configure(p_hwfn, p_hwfn->p_arfs_ptt, + &arfs_config_params); + return 0; +} + +static void +qed_arfs_sp_response_handler(struct qed_hwfn *p_hwfn, + void *cookie, union event_ring_data *data, + u8 fw_return_code) +{ + struct qed_common_cb_ops *op = p_hwfn->cdev->protocol_ops.common; + void *dev = p_hwfn->cdev->ops_cookie; + + op->arfs_filter_op(dev, cookie, fw_return_code); +} + +static int qed_ntuple_arfs_filter_config(struct qed_dev *cdev, void *cookie, + dma_addr_t mapping, u16 length, + u16 vport_id, u16 rx_queue_id, + bool add_filter) +{ + struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); + struct qed_spq_comp_cb cb; + int rc = -EINVAL; + + cb.function = qed_arfs_sp_response_handler; + cb.cookie = cookie; + + rc = qed_configure_rfs_ntuple_filter(p_hwfn, p_hwfn->p_arfs_ptt, + &cb, mapping, length, rx_queue_id, + vport_id, add_filter); + if (rc) + DP_NOTICE(p_hwfn, + "Failed to issue a-RFS filter configuration\n"); + else + DP_VERBOSE(p_hwfn, NETIF_MSG_DRV, + "Successfully issued a-RFS filter configuration\n"); + + return rc; +} + static int qed_fp_cqe_completion(struct qed_dev *dev, u8 rss_id, struct eth_slow_path_rx_cqe *cqe) { @@ -2390,6 +2528,8 @@ static const struct qed_eth_ops qed_eth_ops_pass = { .eth_cqe_completion = &qed_fp_cqe_completion, .get_vport_stats = &qed_get_vport_stats, .tunn_config = &qed_tunn_configure, + .ntuple_filter_config = &qed_ntuple_arfs_filter_config, + .configure_arfs_searcher = &qed_configure_arfs_searcher, }; const struct qed_eth_ops *qed_get_eth_ops(void) diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index e763abd334f6..6f44229899eb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -185,6 +185,14 @@ struct qed_filter_accept_flags { #define QED_ACCEPT_BCAST 0x20 }; +struct qed_arfs_config_params { + bool tcp; + bool udp; + bool ipv4; + bool ipv6; + bool arfs_enable; +}; + struct qed_sp_vport_update_params { u16 opaque_fid; u8 vport_id; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 178650aa0c6c..09c86411918c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -1090,7 +1090,6 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, struct core_tx_start_ramrod_data *p_ramrod = NULL; struct qed_spq_entry *p_ent = NULL; struct qed_sp_init_data init_data; - union qed_qm_pq_params pq_params; u16 pq_id = 0, pbl_size; int rc = -EINVAL; @@ -1127,9 +1126,18 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, pbl_size = qed_chain_get_page_cnt(&p_tx->txq_chain); p_ramrod->pbl_size = cpu_to_le16(pbl_size); - memset(&pq_params, 0, sizeof(pq_params)); - pq_params.core.tc = p_ll2_conn->conn.tx_tc; - pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params); + switch (p_ll2_conn->conn.tx_tc) { + case LB_TC: + pq_id = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB); + break; + case OOO_LB_TC: + pq_id = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OOO); + break; + default: + pq_id = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD); + break; + } + p_ramrod->qm_pq_id = cpu_to_le16(pq_id); switch (conn_type) { @@ -1400,13 +1408,21 @@ int qed_ll2_establish_connection(struct qed_hwfn *p_hwfn, u8 connection_handle) struct qed_ll2_info *p_ll2_conn; struct qed_ll2_rx_queue *p_rx; struct qed_ll2_tx_queue *p_tx; + struct qed_ptt *p_ptt; int rc = -EINVAL; u32 i, capacity; u8 qid; + p_ptt = qed_ptt_acquire(p_hwfn); + if (!p_ptt) + return -EAGAIN; + p_ll2_conn = qed_ll2_handle_sanity_lock(p_hwfn, connection_handle); - if (!p_ll2_conn) - return -EINVAL; + if (!p_ll2_conn) { + rc = -EINVAL; + goto out; + } + p_rx = &p_ll2_conn->rx_queue; p_tx = &p_ll2_conn->tx_queue; @@ -1439,7 +1455,9 @@ int qed_ll2_establish_connection(struct qed_hwfn *p_hwfn, u8 connection_handle) p_tx->cur_completing_frag_num = 0; *p_tx->p_fw_cons = 0; - qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_CORE, &p_ll2_conn->cid); + rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_CORE, &p_ll2_conn->cid); + if (rc) + goto out; qid = p_hwfn->hw_info.resc_start[QED_LL2_QUEUE] + connection_handle; p_ll2_conn->queue_id = qid; @@ -1453,26 +1471,28 @@ int qed_ll2_establish_connection(struct qed_hwfn *p_hwfn, u8 connection_handle) rc = qed_ll2_establish_connection_rx(p_hwfn, p_ll2_conn); if (rc) - return rc; + goto out; rc = qed_sp_ll2_tx_queue_start(p_hwfn, p_ll2_conn); if (rc) - return rc; + goto out; if (p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE) - qed_wr(p_hwfn, p_hwfn->p_main_ptt, PRS_REG_USE_LIGHT_L2, 1); + qed_wr(p_hwfn, p_ptt, PRS_REG_USE_LIGHT_L2, 1); qed_ll2_establish_connection_ooo(p_hwfn, p_ll2_conn); if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_FCOE) { - qed_llh_add_protocol_filter(p_hwfn, p_hwfn->p_main_ptt, + qed_llh_add_protocol_filter(p_hwfn, p_ptt, 0x8906, 0, QED_LLH_FILTER_ETHERTYPE); - qed_llh_add_protocol_filter(p_hwfn, p_hwfn->p_main_ptt, + qed_llh_add_protocol_filter(p_hwfn, p_ptt, 0x8914, 0, QED_LLH_FILTER_ETHERTYPE); } +out: + qed_ptt_release(p_hwfn, p_ptt); return rc; } @@ -1823,23 +1843,30 @@ int qed_ll2_terminate_connection(struct qed_hwfn *p_hwfn, u8 connection_handle) { struct qed_ll2_info *p_ll2_conn = NULL; int rc = -EINVAL; + struct qed_ptt *p_ptt; + + p_ptt = qed_ptt_acquire(p_hwfn); + if (!p_ptt) + return -EAGAIN; p_ll2_conn = qed_ll2_handle_sanity_lock(p_hwfn, connection_handle); - if (!p_ll2_conn) - return -EINVAL; + if (!p_ll2_conn) { + rc = -EINVAL; + goto out; + } /* Stop Tx & Rx of connection, if needed */ if (QED_LL2_TX_REGISTERED(p_ll2_conn)) { rc = qed_sp_ll2_tx_queue_stop(p_hwfn, p_ll2_conn); if (rc) - return rc; + goto out; qed_ll2_txq_flush(p_hwfn, connection_handle); } if (QED_LL2_RX_REGISTERED(p_ll2_conn)) { rc = qed_sp_ll2_rx_queue_stop(p_hwfn, p_ll2_conn); if (rc) - return rc; + goto out; qed_ll2_rxq_flush(p_hwfn, connection_handle); } @@ -1847,14 +1874,16 @@ int qed_ll2_terminate_connection(struct qed_hwfn *p_hwfn, u8 connection_handle) qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info); if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_FCOE) { - qed_llh_remove_protocol_filter(p_hwfn, p_hwfn->p_main_ptt, + qed_llh_remove_protocol_filter(p_hwfn, p_ptt, 0x8906, 0, QED_LLH_FILTER_ETHERTYPE); - qed_llh_remove_protocol_filter(p_hwfn, p_hwfn->p_main_ptt, + qed_llh_remove_protocol_filter(p_hwfn, p_ptt, 0x8914, 0, QED_LLH_FILTER_ETHERTYPE); } +out: + qed_ptt_release(p_hwfn, p_ptt); return rc; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index d4edb993b1b0..da562cf8a965 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -55,6 +55,8 @@ #include "qed_dev_api.h" #include "qed_ll2.h" #include "qed_fcoe.h" +#include "qed_iscsi.h" + #include "qed_mcp.h" #include "qed_hw.h" #include "qed_selftest.h" @@ -745,7 +747,8 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev, cdev->int_params.fp_msix_cnt = cdev->int_params.out.num_vectors - cdev->num_hwfns; - if (!IS_ENABLED(CONFIG_QED_RDMA)) + if (!IS_ENABLED(CONFIG_QED_RDMA) || + QED_LEADING_HWFN(cdev)->hw_info.personality != QED_PCI_ETH_ROCE) return 0; for_each_hwfn(cdev, i) @@ -877,10 +880,12 @@ static void qed_update_pf_params(struct qed_dev *cdev, params->rdma_pf_params.num_qps = QED_ROCE_QPS; params->rdma_pf_params.min_dpis = QED_ROCE_DPIS; /* divide by 3 the MRs to avoid MF ILT overflow */ - params->rdma_pf_params.num_mrs = RDMA_MAX_TIDS; params->rdma_pf_params.gl_pi = QED_ROCE_PROTOCOL_INDEX; } + if (cdev->num_hwfns > 1 || IS_VF(cdev)) + params->eth_pf_params.num_arfs_filters = 0; + /* In case we might support RDMA, don't allow qede to be greedy * with the L2 contexts. Allow for 64 queues [rx, tx, xdp] per hwfn. */ @@ -924,6 +929,18 @@ static int qed_slowpath_start(struct qed_dev *cdev, goto err; } +#ifdef CONFIG_RFS_ACCEL + if (cdev->num_hwfns == 1) { + p_ptt = qed_ptt_acquire(QED_LEADING_HWFN(cdev)); + if (p_ptt) { + QED_LEADING_HWFN(cdev)->p_arfs_ptt = p_ptt; + } else { + DP_NOTICE(cdev, + "Failed to acquire PTT for aRFS\n"); + goto err; + } + } +#endif p_ptt = qed_ptt_acquire(QED_LEADING_HWFN(cdev)); if (p_ptt) { QED_LEADING_HWFN(cdev)->p_ptp_ptt = p_ptt; @@ -1030,6 +1047,12 @@ err: if (IS_PF(cdev)) release_firmware(cdev->firmware); +#ifdef CONFIG_RFS_ACCEL + if (IS_PF(cdev) && (cdev->num_hwfns == 1) && + QED_LEADING_HWFN(cdev)->p_arfs_ptt) + qed_ptt_release(QED_LEADING_HWFN(cdev), + QED_LEADING_HWFN(cdev)->p_arfs_ptt); +#endif if (IS_PF(cdev) && QED_LEADING_HWFN(cdev)->p_ptp_ptt) qed_ptt_release(QED_LEADING_HWFN(cdev), QED_LEADING_HWFN(cdev)->p_ptp_ptt); @@ -1047,6 +1070,11 @@ static int qed_slowpath_stop(struct qed_dev *cdev) qed_ll2_dealloc_if(cdev); if (IS_PF(cdev)) { +#ifdef CONFIG_RFS_ACCEL + if (cdev->num_hwfns == 1) + qed_ptt_release(QED_LEADING_HWFN(cdev), + QED_LEADING_HWFN(cdev)->p_arfs_ptt); +#endif qed_ptt_release(QED_LEADING_HWFN(cdev), QED_LEADING_HWFN(cdev)->p_ptp_ptt); qed_free_stream_mem(cdev); @@ -1679,6 +1707,9 @@ void qed_get_protocol_stats(struct qed_dev *cdev, case QED_MCP_FCOE_STATS: qed_get_protocol_stats_fcoe(cdev, &stats->fcoe_stats); break; + case QED_MCP_ISCSI_STATS: + qed_get_protocol_stats_iscsi(cdev, &stats->iscsi_stats); + break; default: DP_ERR(cdev, "Invalid protocol type = %d\n", type); return; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 619eac845028..ff6080df2246 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -455,8 +455,10 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, qed_mcp_reread_offsets(p_hwfn, p_ptt); seq_num = ++p_hwfn->mcp_info->drv_mb_seq; p_cmd_elem = qed_mcp_cmd_add_elem(p_hwfn, p_mb_params, seq_num); - if (!p_cmd_elem) + if (!p_cmd_elem) { + rc = -ENOMEM; goto err; + } __qed_mcp_cmd_and_union(p_hwfn, p_ptt, p_mb_params, seq_num); spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c index 378afce58b3f..db96670192c7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c @@ -41,6 +41,7 @@ #include "qed_iscsi.h" #include "qed_ll2.h" #include "qed_ooo.h" +#include "qed_cxt.h" static struct qed_ooo_archipelago *qed_ooo_seek_archipelago(struct qed_hwfn *p_hwfn, @@ -48,15 +49,18 @@ static struct qed_ooo_archipelago *p_ooo_info, u32 cid) { - struct qed_ooo_archipelago *p_archipelago = NULL; + u32 idx = (cid & 0xffff) - p_ooo_info->cid_base; + struct qed_ooo_archipelago *p_archipelago; - list_for_each_entry(p_archipelago, - &p_ooo_info->archipelagos_list, list_entry) { - if (p_archipelago->cid == cid) - return p_archipelago; - } + if (idx >= p_ooo_info->max_num_archipelagos) + return NULL; - return NULL; + p_archipelago = &p_ooo_info->p_archipelagos_mem[idx]; + + if (list_empty(&p_archipelago->isles_list)) + return NULL; + + return p_archipelago; } static struct qed_ooo_isle *qed_ooo_seek_isle(struct qed_hwfn *p_hwfn, @@ -97,8 +101,8 @@ void qed_ooo_save_history_entry(struct qed_hwfn *p_hwfn, struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn) { + u16 max_num_archipelagos = 0, cid_base; struct qed_ooo_info *p_ooo_info; - u16 max_num_archipelagos = 0; u16 max_num_isles = 0; u32 i; @@ -110,6 +114,7 @@ struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn) max_num_archipelagos = p_hwfn->pf_params.iscsi_pf_params.num_cons; max_num_isles = QED_MAX_NUM_ISLES + max_num_archipelagos; + cid_base = (u16)qed_cxt_get_proto_cid_start(p_hwfn, PROTOCOLID_ISCSI); if (!max_num_archipelagos) { DP_NOTICE(p_hwfn, @@ -121,11 +126,12 @@ struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn) if (!p_ooo_info) return NULL; + p_ooo_info->cid_base = cid_base; + p_ooo_info->max_num_archipelagos = max_num_archipelagos; + INIT_LIST_HEAD(&p_ooo_info->free_buffers_list); INIT_LIST_HEAD(&p_ooo_info->ready_buffers_list); INIT_LIST_HEAD(&p_ooo_info->free_isles_list); - INIT_LIST_HEAD(&p_ooo_info->free_archipelagos_list); - INIT_LIST_HEAD(&p_ooo_info->archipelagos_list); p_ooo_info->p_isles_mem = kcalloc(max_num_isles, sizeof(struct qed_ooo_isle), @@ -146,11 +152,8 @@ struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn) if (!p_ooo_info->p_archipelagos_mem) goto no_archipelagos_mem; - for (i = 0; i < max_num_archipelagos; i++) { + for (i = 0; i < max_num_archipelagos; i++) INIT_LIST_HEAD(&p_ooo_info->p_archipelagos_mem[i].isles_list); - list_add_tail(&p_ooo_info->p_archipelagos_mem[i].list_entry, - &p_ooo_info->free_archipelagos_list); - } p_ooo_info->ooo_history.p_cqes = kcalloc(QED_MAX_NUM_OOO_HISTORY_ENTRIES, @@ -178,21 +181,9 @@ void qed_ooo_release_connection_isles(struct qed_hwfn *p_hwfn, struct qed_ooo_archipelago *p_archipelago; struct qed_ooo_buffer *p_buffer; struct qed_ooo_isle *p_isle; - bool b_found = false; - - if (list_empty(&p_ooo_info->archipelagos_list)) - return; - list_for_each_entry(p_archipelago, - &p_ooo_info->archipelagos_list, list_entry) { - if (p_archipelago->cid == cid) { - list_del(&p_archipelago->list_entry); - b_found = true; - break; - } - } - - if (!b_found) + p_archipelago = qed_ooo_seek_archipelago(p_hwfn, p_ooo_info, cid); + if (!p_archipelago) return; while (!list_empty(&p_archipelago->isles_list)) { @@ -216,27 +207,21 @@ void qed_ooo_release_connection_isles(struct qed_hwfn *p_hwfn, list_add_tail(&p_isle->list_entry, &p_ooo_info->free_isles_list); } - - list_add_tail(&p_archipelago->list_entry, - &p_ooo_info->free_archipelagos_list); } void qed_ooo_release_all_isles(struct qed_hwfn *p_hwfn, struct qed_ooo_info *p_ooo_info) { - struct qed_ooo_archipelago *p_arch; + struct qed_ooo_archipelago *p_archipelago; struct qed_ooo_buffer *p_buffer; struct qed_ooo_isle *p_isle; + u32 i; - while (!list_empty(&p_ooo_info->archipelagos_list)) { - p_arch = list_first_entry(&p_ooo_info->archipelagos_list, - struct qed_ooo_archipelago, - list_entry); - - list_del(&p_arch->list_entry); + for (i = 0; i < p_ooo_info->max_num_archipelagos; i++) { + p_archipelago = &(p_ooo_info->p_archipelagos_mem[i]); - while (!list_empty(&p_arch->isles_list)) { - p_isle = list_first_entry(&p_arch->isles_list, + while (!list_empty(&p_archipelago->isles_list)) { + p_isle = list_first_entry(&p_archipelago->isles_list, struct qed_ooo_isle, list_entry); @@ -258,8 +243,6 @@ void qed_ooo_release_all_isles(struct qed_hwfn *p_hwfn, list_add_tail(&p_isle->list_entry, &p_ooo_info->free_isles_list); } - list_add_tail(&p_arch->list_entry, - &p_ooo_info->free_archipelagos_list); } if (!list_empty(&p_ooo_info->ready_buffers_list)) list_splice_tail_init(&p_ooo_info->ready_buffers_list, @@ -378,12 +361,6 @@ void qed_ooo_delete_isles(struct qed_hwfn *p_hwfn, p_ooo_info->cur_isles_number--; list_add(&p_isle->list_entry, &p_ooo_info->free_isles_list); } - - if (list_empty(&p_archipelago->isles_list)) { - list_del(&p_archipelago->list_entry); - list_add(&p_archipelago->list_entry, - &p_ooo_info->free_archipelagos_list); - } } void qed_ooo_add_new_isle(struct qed_hwfn *p_hwfn, @@ -426,28 +403,10 @@ void qed_ooo_add_new_isle(struct qed_hwfn *p_hwfn, return; } - if (!p_archipelago && - !list_empty(&p_ooo_info->free_archipelagos_list)) { - p_archipelago = - list_first_entry(&p_ooo_info->free_archipelagos_list, - struct qed_ooo_archipelago, list_entry); + if (!p_archipelago) { + u32 idx = (cid & 0xffff) - p_ooo_info->cid_base; - list_del(&p_archipelago->list_entry); - if (!list_empty(&p_archipelago->isles_list)) { - DP_NOTICE(p_hwfn, - "Free OOO connection is not empty\n"); - INIT_LIST_HEAD(&p_archipelago->isles_list); - } - p_archipelago->cid = cid; - list_add(&p_archipelago->list_entry, - &p_ooo_info->archipelagos_list); - } else if (!p_archipelago) { - DP_NOTICE(p_hwfn, "No more free OOO connections\n"); - list_add(&p_isle->list_entry, - &p_ooo_info->free_isles_list); - list_add(&p_buffer->list_entry, - &p_ooo_info->free_buffers_list); - return; + p_archipelago = &p_ooo_info->p_archipelagos_mem[idx]; } list_add(&p_buffer->list_entry, &p_isle->buffers_list); @@ -517,11 +476,6 @@ void qed_ooo_join_isles(struct qed_hwfn *p_hwfn, } else { list_splice_tail_init(&p_right_isle->buffers_list, &p_ooo_info->ready_buffers_list); - if (list_empty(&p_archipelago->isles_list)) { - list_del(&p_archipelago->list_entry); - list_add(&p_archipelago->list_entry, - &p_ooo_info->free_archipelagos_list); - } } list_add_tail(&p_right_isle->list_entry, &p_ooo_info->free_isles_list); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.h b/drivers/net/ethernet/qlogic/qed/qed_ooo.h index 4f138fb5f533..791ad0f8b759 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ooo.h +++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.h @@ -60,9 +60,7 @@ struct qed_ooo_isle { }; struct qed_ooo_archipelago { - struct list_head list_entry; struct list_head isles_list; - u32 cid; }; struct qed_ooo_history { @@ -75,14 +73,14 @@ struct qed_ooo_info { struct list_head free_buffers_list; struct list_head ready_buffers_list; struct list_head free_isles_list; - struct list_head free_archipelagos_list; - struct list_head archipelagos_list; struct qed_ooo_archipelago *p_archipelagos_mem; struct qed_ooo_isle *p_isles_mem; struct qed_ooo_history ooo_history; u32 cur_isles_number; u32 max_isles_number; u32 gen_isles_number; + u16 max_num_archipelagos; + u16 cid_base; }; #if IS_ENABLED(CONFIG_QED_ISCSI) diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index 6d4ac7e2ee83..1ae73b2d6d1e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -1551,6 +1551,7 @@ #define NIG_REG_TSGEN_FREE_CNT_VALUE_LSB 0x5088a8UL #define NIG_REG_TSGEN_FREE_CNT_VALUE_MSB 0x5088acUL #define NIG_REG_PTP_LATCH_OSTS_PKT_TIME 0x509040UL +#define PSWRQ2_REG_WR_MBS0 0x240400UL #define PGLUE_B_REG_PGL_ADDR_E8_F0_K2 0x2aaf98UL #define PGLUE_B_REG_PGL_ADDR_EC_F0_K2 0x2aaf9cUL @@ -1559,4 +1560,12 @@ #define NIG_REG_TSGEN_FREECNT_UPDATE_K2 0x509008UL #define CNIG_REG_NIG_PORT0_CONF_K2 0x218200UL +#define PRS_REG_SEARCH_GFT 0x1f11bcUL +#define PRS_REG_CM_HDR_GFT 0x1f11c8UL +#define PRS_REG_GFT_CAM 0x1f1100UL +#define PRS_REG_GFT_PROFILE_MASK_RAM 0x1f1000UL +#define PRS_REG_CM_HDR_GFT_EVENT_ID_SHIFT 0 +#define PRS_REG_CM_HDR_GFT_CM_HDR_SHIFT 8 +#define PRS_REG_LOAD_L2_FILTER 0x1f0198UL + #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index 4bef5c59627c..b8c811f95205 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -1224,7 +1224,6 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn, { struct roce_create_qp_resp_ramrod_data *p_ramrod; struct qed_sp_init_data init_data; - union qed_qm_pq_params qm_params; enum roce_flavor roce_flavor; struct qed_spq_entry *p_ent; u16 regular_latency_queue; @@ -1313,10 +1312,7 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn, p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->rq_cq_id); - memset(&qm_params, 0, sizeof(qm_params)); - qm_params.roce.qpid = qp->icid >> 1; - regular_latency_queue = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, - &qm_params); + regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD); p_ramrod->regular_latency_phy_queue = cpu_to_le16(regular_latency_queue); @@ -1368,7 +1364,6 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn, { struct roce_create_qp_req_ramrod_data *p_ramrod; struct qed_sp_init_data init_data; - union qed_qm_pq_params qm_params; enum roce_flavor roce_flavor; struct qed_spq_entry *p_ent; u16 regular_latency_queue; @@ -1446,10 +1441,7 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn, p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->sq_cq_id); - memset(&qm_params, 0, sizeof(qm_params)); - qm_params.roce.qpid = qp->icid >> 1; - regular_latency_queue = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, - &qm_params); + regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD); p_ramrod->regular_latency_phy_queue = cpu_to_le16(regular_latency_queue); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 30393ffaa8e5..583c8d38c8d7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -84,6 +84,7 @@ union ramrod_data { struct tx_queue_stop_ramrod_data tx_queue_stop; struct vport_start_ramrod_data vport_start; struct vport_stop_ramrod_data vport_stop; + struct rx_update_gft_filter_data rx_update_gft; struct vport_update_ramrod_data vport_update; struct core_rx_start_ramrod_data core_rx_queue_start; struct core_rx_stop_ramrod_data core_rx_queue_stop; diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 54fbe3789cf3..f6423a139ca0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -119,6 +119,7 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn, u8 *p_fw_ret, bool skip_quick_poll) { struct qed_spq_comp_done *comp_done; + struct qed_ptt *p_ptt; int rc; /* A relatively short polling period w/o sleeping, to allow the FW to @@ -135,8 +136,14 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn, if (!rc) return 0; + p_ptt = qed_ptt_acquire(p_hwfn); + if (!p_ptt) { + DP_NOTICE(p_hwfn, "ptt, failed to acquire\n"); + return -EAGAIN; + } + DP_INFO(p_hwfn, "Ramrod is stuck, requesting MCP drain\n"); - rc = qed_mcp_drain(p_hwfn, p_hwfn->p_main_ptt); + rc = qed_mcp_drain(p_hwfn, p_ptt); if (rc) { DP_NOTICE(p_hwfn, "MCP drain failed\n"); goto err; @@ -145,15 +152,18 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn, /* Retry after drain */ rc = __qed_spq_block(p_hwfn, p_ent, p_fw_ret, true); if (!rc) - return 0; + goto out; comp_done = (struct qed_spq_comp_done *)p_ent->comp_cb.cookie; - if (comp_done->done == 1) { + if (comp_done->done == 1) if (p_fw_ret) *p_fw_ret = comp_done->fw_return_code; - return 0; - } +out: + qed_ptt_release(p_hwfn, p_ptt); + return 0; + err: + qed_ptt_release(p_hwfn, p_ptt); DP_NOTICE(p_hwfn, "Ramrod is stuck [CID %08x cmd %02x protocol %02x echo %04x]\n", le32_to_cpu(p_ent->elem.hdr.cid), @@ -205,11 +215,10 @@ static int qed_spq_fill_entry(struct qed_hwfn *p_hwfn, static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn, struct qed_spq *p_spq) { - u16 pq; - struct qed_cxt_info cxt_info; - struct core_conn_context *p_cxt; - union qed_qm_pq_params pq_params; - int rc; + struct core_conn_context *p_cxt; + struct qed_cxt_info cxt_info; + u16 physical_q; + int rc; cxt_info.iid = p_spq->cid; @@ -231,10 +240,8 @@ static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn, XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_EN, 1); /* QM physical queue */ - memset(&pq_params, 0, sizeof(pq_params)); - pq_params.core.tc = LB_TC; - pq = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params); - p_cxt->xstorm_ag_context.physical_q0 = cpu_to_le16(pq); + physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB); + p_cxt->xstorm_ag_context.physical_q0 = cpu_to_le16(physical_q); p_cxt->xstorm_st_context.spq_base_lo = DMA_LO_LE(p_spq->chain.p_phys_addr); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 18fc6e62ca41..92a3ee1715d9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -2066,17 +2066,11 @@ static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn, struct qed_queue_start_common_params params; struct qed_iov_vf_mbx *mbx = &vf->vf_mbx; u8 status = PFVF_STATUS_NO_RESOURCE; - union qed_qm_pq_params pq_params; struct vfpf_start_txq_tlv *req; struct qed_vf_q_info *p_queue; int rc; u16 pq; - /* Prepare the parameters which would choose the right PQ */ - memset(&pq_params, 0, sizeof(pq_params)); - pq_params.eth.is_vf = 1; - pq_params.eth.vf_id = vf->relative_vf_id; - memset(¶ms, 0, sizeof(params)); req = &mbx->req_virt->start_txq; @@ -2101,7 +2095,7 @@ static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn, if (!p_queue->p_tx_cid) goto out; - pq = qed_get_qm_pq(p_hwfn, PROTOCOLID_ETH, &pq_params); + pq = qed_get_cm_pq_idx_vf(p_hwfn, vf->relative_vf_id); rc = qed_eth_txq_start_ramrod(p_hwfn, p_queue->p_tx_cid, req->pbl_addr, req->pbl_size, pq); if (rc) { diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index e73a4a5165ee..7e18ae6dec51 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -41,6 +41,9 @@ #include <linux/mutex.h> #include <linux/bpf.h> #include <linux/io.h> +#ifdef CONFIG_RFS_ACCEL +#include <linux/cpu_rmap.h> +#endif #include <linux/qed/common_hsi.h> #include <linux/qed/eth_common.h> #include <linux/qed/qed_if.h> @@ -237,7 +240,10 @@ struct qede_dev { u16 vxlan_dst_port; u16 geneve_dst_port; - bool wol_enabled; +#ifdef CONFIG_RFS_ACCEL + struct qede_arfs *arfs; +#endif + bool wol_enabled; struct qede_rdma_dev rdma_info; @@ -313,21 +319,24 @@ struct qede_rx_queue { u8 data_direction; u8 rxq_id; + /* Used once per each NAPI run */ + u16 num_rx_buffers; + + u16 rx_headroom; + u32 rx_buf_size; u32 rx_buf_seg_size; - u64 rcv_pkts; - struct sw_rx_data *sw_rx_ring; struct qed_chain rx_bd_ring; struct qed_chain rx_comp_ring ____cacheline_aligned; - /* Used once per each NAPI run */ - u16 num_rx_buffers; - /* GRO */ struct qede_agg_info tpa_info[ETH_TPA_MAX_AGGS_NUM]; + /* Used once per each NAPI run */ + u64 rcv_pkts; + u64 rx_hw_errors; u64 rx_alloc_errors; u64 rx_ip_frags; @@ -349,6 +358,11 @@ struct sw_tx_bd { #define QEDE_TSO_SPLIT_BD BIT(0) }; +struct sw_tx_xdp { + struct page *page; + dma_addr_t mapping; +}; + struct qede_tx_queue { u8 is_xdp; bool is_legacy; @@ -372,11 +386,11 @@ struct qede_tx_queue { #define QEDE_TXQ_IDX_TO_XDP(edev, idx) ((idx) + QEDE_MAX_TSS_CNT(edev)) /* Regular Tx requires skb + metadata for release purpose, - * while XDP requires only the pages themselves. + * while XDP requires the pages and the mapped address. */ union { struct sw_tx_bd *skbs; - struct page **pages; + struct sw_tx_xdp *xdp; } sw_tx_ring; struct qed_chain tx_pbl; @@ -431,6 +445,20 @@ struct qede_fastpath { #define QEDE_SP_VXLAN_PORT_CONFIG 2 #define QEDE_SP_GENEVE_PORT_CONFIG 3 +#ifdef CONFIG_RFS_ACCEL +int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, + u16 rxq_index, u32 flow_id); +void qede_process_arfs_filters(struct qede_dev *edev, bool free_fltr); +void qede_poll_for_freeing_arfs_filters(struct qede_dev *edev); +void qede_arfs_filter_op(void *dev, void *filter, u8 fw_rc); +void qede_free_arfs(struct qede_dev *edev); +int qede_alloc_arfs(struct qede_dev *edev); + +#define QEDE_SP_ARFS_CONFIG 4 +#define QEDE_SP_TASK_POLL_DELAY (5 * HZ) +#define QEDE_RFS_MAX_FLTR 256 +#endif + struct qede_reload_args { void (*func)(struct qede_dev *edev, struct qede_reload_args *args); union { diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index 107c3fda4792..34473fbac798 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -38,6 +38,448 @@ #include <linux/qed/qed_if.h> #include "qede.h" +#ifdef CONFIG_RFS_ACCEL +struct qede_arfs_tuple { + union { + __be32 src_ipv4; + struct in6_addr src_ipv6; + }; + union { + __be32 dst_ipv4; + struct in6_addr dst_ipv6; + }; + __be16 src_port; + __be16 dst_port; + __be16 eth_proto; + u8 ip_proto; +}; + +struct qede_arfs_fltr_node { +#define QEDE_FLTR_VALID 0 + unsigned long state; + + /* pointer to aRFS packet buffer */ + void *data; + + /* dma map address of aRFS packet buffer */ + dma_addr_t mapping; + + /* length of aRFS packet buffer */ + int buf_len; + + /* tuples to hold from aRFS packet buffer */ + struct qede_arfs_tuple tuple; + + u32 flow_id; + u16 sw_id; + u16 rxq_id; + u16 next_rxq_id; + bool filter_op; + bool used; + struct hlist_node node; +}; + +struct qede_arfs { +#define QEDE_ARFS_POLL_COUNT 100 +#define QEDE_RFS_FLW_BITSHIFT (4) +#define QEDE_RFS_FLW_MASK ((1 << QEDE_RFS_FLW_BITSHIFT) - 1) + struct hlist_head arfs_hl_head[1 << QEDE_RFS_FLW_BITSHIFT]; + + /* lock for filter list access */ + spinlock_t arfs_list_lock; + unsigned long *arfs_fltr_bmap; + int filter_count; + bool enable; +}; + +static void qede_configure_arfs_fltr(struct qede_dev *edev, + struct qede_arfs_fltr_node *n, + u16 rxq_id, bool add_fltr) +{ + const struct qed_eth_ops *op = edev->ops; + + if (n->used) + return; + + DP_VERBOSE(edev, NETIF_MSG_RX_STATUS, + "%s arfs filter flow_id=%d, sw_id=%d, src_port=%d, dst_port=%d, rxq=%d\n", + add_fltr ? "Adding" : "Deleting", + n->flow_id, n->sw_id, ntohs(n->tuple.src_port), + ntohs(n->tuple.dst_port), rxq_id); + + n->used = true; + n->filter_op = add_fltr; + op->ntuple_filter_config(edev->cdev, n, n->mapping, n->buf_len, 0, + rxq_id, add_fltr); +} + +static void +qede_free_arfs_filter(struct qede_dev *edev, struct qede_arfs_fltr_node *fltr) +{ + kfree(fltr->data); + clear_bit(fltr->sw_id, edev->arfs->arfs_fltr_bmap); + kfree(fltr); +} + +void qede_arfs_filter_op(void *dev, void *filter, u8 fw_rc) +{ + struct qede_arfs_fltr_node *fltr = filter; + struct qede_dev *edev = dev; + + if (fw_rc) { + DP_NOTICE(edev, + "Failed arfs filter configuration fw_rc=%d, flow_id=%d, sw_id=%d, src_port=%d, dst_port=%d, rxq=%d\n", + fw_rc, fltr->flow_id, fltr->sw_id, + ntohs(fltr->tuple.src_port), + ntohs(fltr->tuple.dst_port), fltr->rxq_id); + + spin_lock_bh(&edev->arfs->arfs_list_lock); + + fltr->used = false; + clear_bit(QEDE_FLTR_VALID, &fltr->state); + + spin_unlock_bh(&edev->arfs->arfs_list_lock); + return; + } + + spin_lock_bh(&edev->arfs->arfs_list_lock); + + fltr->used = false; + + if (fltr->filter_op) { + set_bit(QEDE_FLTR_VALID, &fltr->state); + if (fltr->rxq_id != fltr->next_rxq_id) + qede_configure_arfs_fltr(edev, fltr, fltr->rxq_id, + false); + } else { + clear_bit(QEDE_FLTR_VALID, &fltr->state); + if (fltr->rxq_id != fltr->next_rxq_id) { + fltr->rxq_id = fltr->next_rxq_id; + qede_configure_arfs_fltr(edev, fltr, + fltr->rxq_id, true); + } + } + + spin_unlock_bh(&edev->arfs->arfs_list_lock); +} + +/* Should be called while qede_lock is held */ +void qede_process_arfs_filters(struct qede_dev *edev, bool free_fltr) +{ + int i; + + for (i = 0; i <= QEDE_RFS_FLW_MASK; i++) { + struct hlist_node *temp; + struct hlist_head *head; + struct qede_arfs_fltr_node *fltr; + + head = &edev->arfs->arfs_hl_head[i]; + + hlist_for_each_entry_safe(fltr, temp, head, node) { + bool del = false; + + if (edev->state != QEDE_STATE_OPEN) + del = true; + + spin_lock_bh(&edev->arfs->arfs_list_lock); + + if ((!test_bit(QEDE_FLTR_VALID, &fltr->state) && + !fltr->used) || free_fltr) { + hlist_del(&fltr->node); + dma_unmap_single(&edev->pdev->dev, + fltr->mapping, + fltr->buf_len, DMA_TO_DEVICE); + qede_free_arfs_filter(edev, fltr); + edev->arfs->filter_count--; + } else { + if ((rps_may_expire_flow(edev->ndev, + fltr->rxq_id, + fltr->flow_id, + fltr->sw_id) || del) && + !free_fltr) + qede_configure_arfs_fltr(edev, fltr, + fltr->rxq_id, + false); + } + + spin_unlock_bh(&edev->arfs->arfs_list_lock); + } + } + + spin_lock_bh(&edev->arfs->arfs_list_lock); + + if (!edev->arfs->filter_count) { + if (edev->arfs->enable) { + edev->arfs->enable = false; + edev->ops->configure_arfs_searcher(edev->cdev, false); + } + } else { + set_bit(QEDE_SP_ARFS_CONFIG, &edev->sp_flags); + schedule_delayed_work(&edev->sp_task, + QEDE_SP_TASK_POLL_DELAY); + } + + spin_unlock_bh(&edev->arfs->arfs_list_lock); +} + +/* This function waits until all aRFS filters get deleted and freed. + * On timeout it frees all filters forcefully. + */ +void qede_poll_for_freeing_arfs_filters(struct qede_dev *edev) +{ + int count = QEDE_ARFS_POLL_COUNT; + + while (count) { + qede_process_arfs_filters(edev, false); + + if (!edev->arfs->filter_count) + break; + + msleep(100); + count--; + } + + if (!count) { + DP_NOTICE(edev, "Timeout in polling for arfs filter free\n"); + + /* Something is terribly wrong, free forcefully */ + qede_process_arfs_filters(edev, true); + } +} + +int qede_alloc_arfs(struct qede_dev *edev) +{ + int i; + + edev->arfs = vzalloc(sizeof(*edev->arfs)); + if (!edev->arfs) + return -ENOMEM; + + spin_lock_init(&edev->arfs->arfs_list_lock); + + for (i = 0; i <= QEDE_RFS_FLW_MASK; i++) + INIT_HLIST_HEAD(&edev->arfs->arfs_hl_head[i]); + + edev->ndev->rx_cpu_rmap = alloc_irq_cpu_rmap(QEDE_RSS_COUNT(edev)); + if (!edev->ndev->rx_cpu_rmap) { + vfree(edev->arfs); + edev->arfs = NULL; + return -ENOMEM; + } + + edev->arfs->arfs_fltr_bmap = vzalloc(BITS_TO_LONGS(QEDE_RFS_MAX_FLTR) * + sizeof(long)); + if (!edev->arfs->arfs_fltr_bmap) { + free_irq_cpu_rmap(edev->ndev->rx_cpu_rmap); + edev->ndev->rx_cpu_rmap = NULL; + vfree(edev->arfs); + edev->arfs = NULL; + return -ENOMEM; + } + + return 0; +} + +void qede_free_arfs(struct qede_dev *edev) +{ + if (!edev->arfs) + return; + + if (edev->ndev->rx_cpu_rmap) + free_irq_cpu_rmap(edev->ndev->rx_cpu_rmap); + + edev->ndev->rx_cpu_rmap = NULL; + vfree(edev->arfs->arfs_fltr_bmap); + edev->arfs->arfs_fltr_bmap = NULL; + vfree(edev->arfs); + edev->arfs = NULL; +} + +static bool qede_compare_ip_addr(struct qede_arfs_fltr_node *tpos, + const struct sk_buff *skb) +{ + if (skb->protocol == htons(ETH_P_IP)) { + if (tpos->tuple.src_ipv4 == ip_hdr(skb)->saddr && + tpos->tuple.dst_ipv4 == ip_hdr(skb)->daddr) + return true; + else + return false; + } else { + struct in6_addr *src = &tpos->tuple.src_ipv6; + u8 size = sizeof(struct in6_addr); + + if (!memcmp(src, &ipv6_hdr(skb)->saddr, size) && + !memcmp(&tpos->tuple.dst_ipv6, &ipv6_hdr(skb)->daddr, size)) + return true; + else + return false; + } +} + +static struct qede_arfs_fltr_node * +qede_arfs_htbl_key_search(struct hlist_head *h, const struct sk_buff *skb, + __be16 src_port, __be16 dst_port, u8 ip_proto) +{ + struct qede_arfs_fltr_node *tpos; + + hlist_for_each_entry(tpos, h, node) + if (tpos->tuple.ip_proto == ip_proto && + tpos->tuple.eth_proto == skb->protocol && + qede_compare_ip_addr(tpos, skb) && + tpos->tuple.src_port == src_port && + tpos->tuple.dst_port == dst_port) + return tpos; + + return NULL; +} + +static struct qede_arfs_fltr_node * +qede_alloc_filter(struct qede_dev *edev, int min_hlen) +{ + struct qede_arfs_fltr_node *n; + int bit_id; + + bit_id = find_first_zero_bit(edev->arfs->arfs_fltr_bmap, + QEDE_RFS_MAX_FLTR); + + if (bit_id >= QEDE_RFS_MAX_FLTR) + return NULL; + + n = kzalloc(sizeof(*n), GFP_ATOMIC); + if (!n) + return NULL; + + n->data = kzalloc(min_hlen, GFP_ATOMIC); + if (!n->data) { + kfree(n); + return NULL; + } + + n->sw_id = (u16)bit_id; + set_bit(bit_id, edev->arfs->arfs_fltr_bmap); + return n; +} + +int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, + u16 rxq_index, u32 flow_id) +{ + struct qede_dev *edev = netdev_priv(dev); + struct qede_arfs_fltr_node *n; + int min_hlen, rc, tp_offset; + struct ethhdr *eth; + __be16 *ports; + u16 tbl_idx; + u8 ip_proto; + + if (skb->encapsulation) + return -EPROTONOSUPPORT; + + if (skb->protocol != htons(ETH_P_IP) && + skb->protocol != htons(ETH_P_IPV6)) + return -EPROTONOSUPPORT; + + if (skb->protocol == htons(ETH_P_IP)) { + ip_proto = ip_hdr(skb)->protocol; + tp_offset = sizeof(struct iphdr); + } else { + ip_proto = ipv6_hdr(skb)->nexthdr; + tp_offset = sizeof(struct ipv6hdr); + } + + if (ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) + return -EPROTONOSUPPORT; + + ports = (__be16 *)(skb->data + tp_offset); + tbl_idx = skb_get_hash_raw(skb) & QEDE_RFS_FLW_MASK; + + spin_lock_bh(&edev->arfs->arfs_list_lock); + + n = qede_arfs_htbl_key_search(&edev->arfs->arfs_hl_head[tbl_idx], + skb, ports[0], ports[1], ip_proto); + + if (n) { + /* Filter match */ + n->next_rxq_id = rxq_index; + + if (test_bit(QEDE_FLTR_VALID, &n->state)) { + if (n->rxq_id != rxq_index) + qede_configure_arfs_fltr(edev, n, n->rxq_id, + false); + } else { + if (!n->used) { + n->rxq_id = rxq_index; + qede_configure_arfs_fltr(edev, n, n->rxq_id, + true); + } + } + + rc = n->sw_id; + goto ret_unlock; + } + + min_hlen = ETH_HLEN + skb_headlen(skb); + + n = qede_alloc_filter(edev, min_hlen); + if (!n) { + rc = -ENOMEM; + goto ret_unlock; + } + + n->buf_len = min_hlen; + n->rxq_id = rxq_index; + n->next_rxq_id = rxq_index; + n->tuple.src_port = ports[0]; + n->tuple.dst_port = ports[1]; + n->flow_id = flow_id; + + if (skb->protocol == htons(ETH_P_IP)) { + n->tuple.src_ipv4 = ip_hdr(skb)->saddr; + n->tuple.dst_ipv4 = ip_hdr(skb)->daddr; + } else { + memcpy(&n->tuple.src_ipv6, &ipv6_hdr(skb)->saddr, + sizeof(struct in6_addr)); + memcpy(&n->tuple.dst_ipv6, &ipv6_hdr(skb)->daddr, + sizeof(struct in6_addr)); + } + + eth = (struct ethhdr *)n->data; + eth->h_proto = skb->protocol; + n->tuple.eth_proto = skb->protocol; + n->tuple.ip_proto = ip_proto; + memcpy(n->data + ETH_HLEN, skb->data, skb_headlen(skb)); + + n->mapping = dma_map_single(&edev->pdev->dev, n->data, + n->buf_len, DMA_TO_DEVICE); + if (dma_mapping_error(&edev->pdev->dev, n->mapping)) { + DP_NOTICE(edev, "Failed to map DMA memory for arfs\n"); + qede_free_arfs_filter(edev, n); + rc = -ENOMEM; + goto ret_unlock; + } + + INIT_HLIST_NODE(&n->node); + hlist_add_head(&n->node, &edev->arfs->arfs_hl_head[tbl_idx]); + edev->arfs->filter_count++; + + if (edev->arfs->filter_count == 1 && !edev->arfs->enable) { + edev->ops->configure_arfs_searcher(edev->cdev, true); + edev->arfs->enable = true; + } + + qede_configure_arfs_fltr(edev, n, n->rxq_id, true); + + spin_unlock_bh(&edev->arfs->arfs_list_lock); + + set_bit(QEDE_SP_ARFS_CONFIG, &edev->sp_flags); + schedule_delayed_work(&edev->sp_task, 0); + return n->sw_id; + +ret_unlock: + spin_unlock_bh(&edev->arfs->arfs_list_lock); + return rc; +} +#endif + void qede_force_mac(void *dev, u8 *mac, bool forced) { struct qede_dev *edev = dev; @@ -520,11 +962,6 @@ static int qede_xdp_set(struct qede_dev *edev, struct bpf_prog *prog) { struct qede_reload_args args; - if (prog && prog->xdp_adjust_head) { - DP_ERR(edev, "Does not support bpf_xdp_adjust_head()\n"); - return -EOPNOTSUPP; - } - /* If we're called, there was already a bpf reference increment */ args.func = &qede_xdp_reload_func; args.u.new_prog = prog; @@ -537,6 +974,11 @@ int qede_xdp(struct net_device *dev, struct netdev_xdp *xdp) { struct qede_dev *edev = netdev_priv(dev); + if (IS_VF(edev)) { + DP_NOTICE(edev, "VFs don't support XDP\n"); + return -EOPNOTSUPP; + } + switch (xdp->command) { case XDP_SETUP_PROG: return qede_xdp_set(edev, xdp->prog); diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 1e65038c8fc0..961b1d36b9eb 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -87,7 +87,8 @@ int qede_alloc_rx_buffer(struct qede_rx_queue *rxq, bool allow_lazy) rx_bd = (struct eth_rx_bd *)qed_chain_produce(&rxq->rx_bd_ring); WARN_ON(!rx_bd); rx_bd->addr.hi = cpu_to_le32(upper_32_bits(mapping)); - rx_bd->addr.lo = cpu_to_le32(lower_32_bits(mapping)); + rx_bd->addr.lo = cpu_to_le32(lower_32_bits(mapping) + + rxq->rx_headroom); rxq->sw_rx_prod++; rxq->filled_buffers++; @@ -360,7 +361,8 @@ static int qede_xdp_xmit(struct qede_dev *edev, struct qede_fastpath *fp, metadata->mapping + padding, length, PCI_DMA_TODEVICE); - txq->sw_tx_ring.pages[idx] = metadata->data; + txq->sw_tx_ring.xdp[idx].page = metadata->data; + txq->sw_tx_ring.xdp[idx].mapping = metadata->mapping; txq->sw_tx_prod++; /* Mark the fastpath for future XDP doorbell */ @@ -384,19 +386,19 @@ int qede_txq_has_work(struct qede_tx_queue *txq) static void qede_xdp_tx_int(struct qede_dev *edev, struct qede_tx_queue *txq) { - struct eth_tx_1st_bd *bd; - u16 hw_bd_cons; + u16 hw_bd_cons, idx; hw_bd_cons = le16_to_cpu(*txq->hw_cons_ptr); barrier(); while (hw_bd_cons != qed_chain_get_cons_idx(&txq->tx_pbl)) { - bd = (struct eth_tx_1st_bd *)qed_chain_consume(&txq->tx_pbl); + qed_chain_consume(&txq->tx_pbl); + idx = txq->sw_tx_cons & NUM_TX_BDS_MAX; - dma_unmap_single(&edev->pdev->dev, BD_UNMAP_ADDR(bd), - PAGE_SIZE, DMA_BIDIRECTIONAL); - __free_page(txq->sw_tx_ring.pages[txq->sw_tx_cons & - NUM_TX_BDS_MAX]); + dma_unmap_page(&edev->pdev->dev, + txq->sw_tx_ring.xdp[idx].mapping, + PAGE_SIZE, DMA_BIDIRECTIONAL); + __free_page(txq->sw_tx_ring.xdp[idx].page); txq->sw_tx_cons++; txq->xmit_pkts++; @@ -508,7 +510,8 @@ static inline void qede_reuse_page(struct qede_rx_queue *rxq, new_mapping = curr_prod->mapping + curr_prod->page_offset; rx_bd_prod->addr.hi = cpu_to_le32(upper_32_bits(new_mapping)); - rx_bd_prod->addr.lo = cpu_to_le32(lower_32_bits(new_mapping)); + rx_bd_prod->addr.lo = cpu_to_le32(lower_32_bits(new_mapping) + + rxq->rx_headroom); rxq->sw_rx_prod++; curr_cons->data = NULL; @@ -624,7 +627,6 @@ static inline void qede_skb_receive(struct qede_dev *edev, __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); napi_gro_receive(&fp->napi, skb); - rxq->rcv_pkts++; } static void qede_set_gro_params(struct qede_dev *edev, @@ -884,9 +886,9 @@ static inline void qede_tpa_cont(struct qede_dev *edev, "Strange - TPA cont with more than a single len_list entry\n"); } -static void qede_tpa_end(struct qede_dev *edev, - struct qede_fastpath *fp, - struct eth_fast_path_rx_tpa_end_cqe *cqe) +static int qede_tpa_end(struct qede_dev *edev, + struct qede_fastpath *fp, + struct eth_fast_path_rx_tpa_end_cqe *cqe) { struct qede_rx_queue *rxq = fp->rxq; struct qede_agg_info *tpa_info; @@ -934,11 +936,12 @@ static void qede_tpa_end(struct qede_dev *edev, tpa_info->state = QEDE_AGG_STATE_NONE; - return; + return 1; err: tpa_info->state = QEDE_AGG_STATE_NONE; dev_kfree_skb_any(tpa_info->skb); tpa_info->skb = NULL; + return 0; } static u8 qede_check_notunn_csum(u16 flag) @@ -990,14 +993,15 @@ static bool qede_rx_xdp(struct qede_dev *edev, struct qede_rx_queue *rxq, struct bpf_prog *prog, struct sw_rx_data *bd, - struct eth_fast_path_rx_reg_cqe *cqe) + struct eth_fast_path_rx_reg_cqe *cqe, + u16 *data_offset, u16 *len) { - u16 len = le16_to_cpu(cqe->len_on_first_bd); struct xdp_buff xdp; enum xdp_action act; - xdp.data = page_address(bd->data) + cqe->placement_offset; - xdp.data_end = xdp.data + len; + xdp.data_hard_start = page_address(bd->data); + xdp.data = xdp.data_hard_start + *data_offset; + xdp.data_end = xdp.data + *len; /* Queues always have a full reset currently, so for the time * being until there's atomic program replace just mark read @@ -1007,6 +1011,10 @@ static bool qede_rx_xdp(struct qede_dev *edev, act = bpf_prog_run_xdp(prog, &xdp); rcu_read_unlock(); + /* Recalculate, as XDP might have changed the headers */ + *data_offset = xdp.data - xdp.data_hard_start; + *len = xdp.data_end - xdp.data; + if (act == XDP_PASS) return true; @@ -1025,7 +1033,7 @@ static bool qede_rx_xdp(struct qede_dev *edev, /* Now if there's a transmission problem, we'd still have to * throw current buffer, as replacement was already allocated. */ - if (qede_xdp_xmit(edev, fp, bd, cqe->placement_offset, len)) { + if (qede_xdp_xmit(edev, fp, bd, *data_offset, *len)) { dma_unmap_page(rxq->dev, bd->mapping, PAGE_SIZE, DMA_BIDIRECTIONAL); __free_page(bd->data); @@ -1052,7 +1060,7 @@ static struct sk_buff *qede_rx_allocate_skb(struct qede_dev *edev, struct sw_rx_data *bd, u16 len, u16 pad) { - unsigned int offset = bd->page_offset; + unsigned int offset = bd->page_offset + pad; struct skb_frag_struct *frag; struct page *page = bd->data; unsigned int pull_len; @@ -1069,7 +1077,7 @@ static struct sk_buff *qede_rx_allocate_skb(struct qede_dev *edev, */ if (len + pad <= edev->rx_copybreak) { memcpy(skb_put(skb, len), - page_address(page) + pad + offset, len); + page_address(page) + offset, len); qede_reuse_page(rxq, bd); goto out; } @@ -1077,7 +1085,7 @@ static struct sk_buff *qede_rx_allocate_skb(struct qede_dev *edev, frag = &skb_shinfo(skb)->frags[0]; skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, - page, pad + offset, len, rxq->rx_buf_seg_size); + page, offset, len, rxq->rx_buf_seg_size); va = skb_frag_address(frag); pull_len = eth_get_headlen(va, QEDE_RX_HDR_SIZE); @@ -1178,8 +1186,7 @@ static int qede_rx_process_tpa_cqe(struct qede_dev *edev, qede_tpa_cont(edev, rxq, &cqe->fast_path_tpa_cont); return 0; case ETH_RX_CQE_TYPE_TPA_END: - qede_tpa_end(edev, fp, &cqe->fast_path_tpa_end); - return 1; + return qede_tpa_end(edev, fp, &cqe->fast_path_tpa_end); default: return 0; } @@ -1224,12 +1231,13 @@ static int qede_rx_process_cqe(struct qede_dev *edev, fp_cqe = &cqe->fast_path_regular; len = le16_to_cpu(fp_cqe->len_on_first_bd); - pad = fp_cqe->placement_offset; + pad = fp_cqe->placement_offset + rxq->rx_headroom; /* Run eBPF program if one is attached */ if (xdp_prog) - if (!qede_rx_xdp(edev, fp, rxq, xdp_prog, bd, fp_cqe)) - return 1; + if (!qede_rx_xdp(edev, fp, rxq, xdp_prog, bd, fp_cqe, + &pad, &len)) + return 0; /* If this is an error packet then drop it */ flags = cqe->fast_path_regular.pars_flags.flags; @@ -1290,8 +1298,8 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget) { struct qede_rx_queue *rxq = fp->rxq; struct qede_dev *edev = fp->edev; + int work_done = 0, rcv_pkts = 0; u16 hw_comp_cons, sw_comp_cons; - int work_done = 0; hw_comp_cons = le16_to_cpu(*rxq->hw_cons_ptr); sw_comp_cons = qed_chain_get_cons_idx(&rxq->rx_comp_ring); @@ -1305,12 +1313,14 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget) /* Loop to complete all indicated BDs */ while ((sw_comp_cons != hw_comp_cons) && (work_done < budget)) { - qede_rx_process_cqe(edev, fp, rxq); + rcv_pkts += qede_rx_process_cqe(edev, fp, rxq); qed_chain_recycle_consumed(&rxq->rx_comp_ring); sw_comp_cons = qed_chain_get_cons_idx(&rxq->rx_comp_ring); work_done++; } + rxq->rcv_pkts += rcv_pkts; + /* Allocate replacement buffers */ while (rxq->num_rx_buffers - rxq->filled_buffers) if (qede_alloc_rx_buffer(rxq, false)) diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index abd99109e532..02b305c19f38 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -225,6 +225,9 @@ static struct pci_driver qede_pci_driver = { static struct qed_eth_cb_ops qede_ll_ops = { { +#ifdef CONFIG_RFS_ACCEL + .arfs_filter_op = qede_arfs_filter_op, +#endif .link_update = qede_link_update, }, .force_mac = qede_force_mac, @@ -554,6 +557,9 @@ static const struct net_device_ops qede_netdev_ops = { .ndo_udp_tunnel_del = qede_udp_tunnel_del, .ndo_features_check = qede_features_check, .ndo_xdp = qede_xdp, +#ifdef CONFIG_RFS_ACCEL + .ndo_rx_flow_steer = qede_rx_flow_steer, +#endif }; /* ------------------------------------------------------------------------- @@ -603,7 +609,7 @@ static void qede_init_ndev(struct qede_dev *edev) { struct net_device *ndev = edev->ndev; struct pci_dev *pdev = edev->pdev; - u32 hw_features; + netdev_features_t hw_features; pci_set_drvdata(pdev, ndev); @@ -629,6 +635,10 @@ static void qede_init_ndev(struct qede_dev *edev) hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_TSO_ECN | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM; + + if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) + hw_features |= NETIF_F_NTUPLE; + ndev->hw_enc_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GSO_GRE | @@ -798,6 +808,12 @@ static void qede_sp_task(struct work_struct *work) qed_ops->tunn_config(cdev, &tunn_params); } +#ifdef CONFIG_RFS_ACCEL + if (test_and_clear_bit(QEDE_SP_ARFS_CONFIG, &edev->sp_flags)) { + if (edev->state == QEDE_STATE_OPEN) + qede_process_arfs_filters(edev, false); + } +#endif __qede_unlock(edev); } @@ -808,6 +824,9 @@ static void qede_update_pf_params(struct qed_dev *cdev) /* 64 rx + 64 tx + 64 XDP */ memset(&pf_params, 0, sizeof(struct qed_pf_params)); pf_params.eth_pf_params.num_cons = (MAX_SB_PER_PF_MIMD - 1) * 3; +#ifdef CONFIG_RFS_ACCEL + pf_params.eth_pf_params.num_arfs_filters = QEDE_RFS_MAX_FLTR; +#endif qed_ops->common->update_pf_params(cdev, &pf_params); } @@ -962,9 +981,8 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) DP_INFO(edev, "Starting qede_remove\n"); - cancel_delayed_work_sync(&edev->sp_task); - unregister_netdev(ndev); + cancel_delayed_work_sync(&edev->sp_task); qede_ptp_remove(edev); @@ -1187,9 +1205,11 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq) rxq->num_rx_buffers = edev->q_num_rx_buffers; rxq->rx_buf_size = NET_IP_ALIGN + ETH_OVERHEAD + edev->ndev->mtu; + rxq->rx_headroom = edev->xdp_prog ? XDP_PACKET_HEADROOM : 0; - if (rxq->rx_buf_size > PAGE_SIZE) - rxq->rx_buf_size = PAGE_SIZE; + /* Make sure that the headroom and payload fit in a single page */ + if (rxq->rx_buf_size + rxq->rx_headroom > PAGE_SIZE) + rxq->rx_buf_size = PAGE_SIZE - rxq->rx_headroom; /* Segment size to spilt a page in multiple equal parts, * unless XDP is used in which case we'd use the entire page. @@ -1251,7 +1271,7 @@ static void qede_free_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq) { /* Free the parallel SW ring */ if (txq->is_xdp) - kfree(txq->sw_tx_ring.pages); + kfree(txq->sw_tx_ring.xdp); else kfree(txq->sw_tx_ring.skbs); @@ -1269,9 +1289,9 @@ static int qede_alloc_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq) /* Allocate the parallel driver ring for Tx buffers */ if (txq->is_xdp) { - size = sizeof(*txq->sw_tx_ring.pages) * TX_RING_SIZE; - txq->sw_tx_ring.pages = kzalloc(size, GFP_KERNEL); - if (!txq->sw_tx_ring.pages) + size = sizeof(*txq->sw_tx_ring.xdp) * TX_RING_SIZE; + txq->sw_tx_ring.xdp = kzalloc(size, GFP_KERNEL); + if (!txq->sw_tx_ring.xdp) goto err; } else { size = sizeof(*txq->sw_tx_ring.skbs) * TX_RING_SIZE; @@ -1488,6 +1508,18 @@ static int qede_req_msix_irqs(struct qede_dev *edev) } for (i = 0; i < QEDE_QUEUE_CNT(edev); i++) { +#ifdef CONFIG_RFS_ACCEL + struct qede_fastpath *fp = &edev->fp_array[i]; + + if (edev->ndev->rx_cpu_rmap && (fp->type & QEDE_FASTPATH_RX)) { + rc = irq_cpu_rmap_add(edev->ndev->rx_cpu_rmap, + edev->int_info.msix[i].vector); + if (rc) { + DP_ERR(edev, "Failed to add CPU rmap\n"); + qede_free_arfs(edev); + } + } +#endif rc = request_irq(edev->int_info.msix[i].vector, qede_msix_fp_int, 0, edev->fp_array[i].name, &edev->fp_array[i]); @@ -1869,7 +1901,12 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode, qede_vlan_mark_nonconfigured(edev); edev->ops->fastpath_stop(edev->cdev); - +#ifdef CONFIG_RFS_ACCEL + if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) { + qede_poll_for_freeing_arfs_filters(edev); + qede_free_arfs(edev); + } +#endif /* Release the interrupts */ qede_sync_free_irqs(edev); edev->ops->common->set_fp_int(edev->cdev, 0); @@ -1921,6 +1958,13 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode, if (rc) goto err2; +#ifdef CONFIG_RFS_ACCEL + if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) { + rc = qede_alloc_arfs(edev); + if (rc) + DP_NOTICE(edev, "aRFS memory allocation failed\n"); + } +#endif qede_napi_add_enable(edev); DP_INFO(edev, "Napi added and enabled\n"); diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index e9e647072596..1188d420fe53 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -4686,7 +4686,8 @@ static int ql_init_device(struct pci_dev *pdev, struct net_device *ndev, /* * Set up the operating parameters. */ - qdev->workqueue = alloc_ordered_workqueue(ndev->name, WQ_MEM_RECLAIM); + qdev->workqueue = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, + ndev->name); INIT_DELAYED_WORK(&qdev->asic_reset_work, ql_asic_reset_work); INIT_DELAYED_WORK(&qdev->mpi_reset_work, ql_mpi_reset_work); INIT_DELAYED_WORK(&qdev->mpi_work, ql_mpi_work); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 54248775f227..f68c4db656ed 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1127,12 +1127,70 @@ static struct mdiobb_ops bb_ops = { .get_mdio_data = sh_get_mdio, }; +/* free Tx skb function */ +static int sh_eth_tx_free(struct net_device *ndev, bool sent_only) +{ + struct sh_eth_private *mdp = netdev_priv(ndev); + struct sh_eth_txdesc *txdesc; + int free_num = 0; + int entry; + bool sent; + + for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) { + entry = mdp->dirty_tx % mdp->num_tx_ring; + txdesc = &mdp->tx_ring[entry]; + sent = !(txdesc->status & cpu_to_le32(TD_TACT)); + if (sent_only && !sent) + break; + /* TACT bit must be checked before all the following reads */ + dma_rmb(); + netif_info(mdp, tx_done, ndev, + "tx entry %d status 0x%08x\n", + entry, le32_to_cpu(txdesc->status)); + /* Free the original skb. */ + if (mdp->tx_skbuff[entry]) { + dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr), + le32_to_cpu(txdesc->len) >> 16, + DMA_TO_DEVICE); + dev_kfree_skb_irq(mdp->tx_skbuff[entry]); + mdp->tx_skbuff[entry] = NULL; + free_num++; + } + txdesc->status = cpu_to_le32(TD_TFP); + if (entry >= mdp->num_tx_ring - 1) + txdesc->status |= cpu_to_le32(TD_TDLE); + + if (sent) { + ndev->stats.tx_packets++; + ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16; + } + } + return free_num; +} + /* free skb and descriptor buffer */ static void sh_eth_ring_free(struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); int ringsize, i; + if (mdp->rx_ring) { + for (i = 0; i < mdp->num_rx_ring; i++) { + if (mdp->rx_skbuff[i]) { + struct sh_eth_rxdesc *rxdesc = &mdp->rx_ring[i]; + + dma_unmap_single(&ndev->dev, + le32_to_cpu(rxdesc->addr), + ALIGN(mdp->rx_buf_sz, 32), + DMA_FROM_DEVICE); + } + } + ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring; + dma_free_coherent(NULL, ringsize, mdp->rx_ring, + mdp->rx_desc_dma); + mdp->rx_ring = NULL; + } + /* Free Rx skb ringbuffer */ if (mdp->rx_skbuff) { for (i = 0; i < mdp->num_rx_ring; i++) @@ -1141,27 +1199,18 @@ static void sh_eth_ring_free(struct net_device *ndev) kfree(mdp->rx_skbuff); mdp->rx_skbuff = NULL; - /* Free Tx skb ringbuffer */ - if (mdp->tx_skbuff) { - for (i = 0; i < mdp->num_tx_ring; i++) - dev_kfree_skb(mdp->tx_skbuff[i]); - } - kfree(mdp->tx_skbuff); - mdp->tx_skbuff = NULL; - - if (mdp->rx_ring) { - ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring; - dma_free_coherent(NULL, ringsize, mdp->rx_ring, - mdp->rx_desc_dma); - mdp->rx_ring = NULL; - } - if (mdp->tx_ring) { + sh_eth_tx_free(ndev, false); + ringsize = sizeof(struct sh_eth_txdesc) * mdp->num_tx_ring; dma_free_coherent(NULL, ringsize, mdp->tx_ring, mdp->tx_desc_dma); mdp->tx_ring = NULL; } + + /* Free Tx skb ringbuffer */ + kfree(mdp->tx_skbuff); + mdp->tx_skbuff = NULL; } /* format skb and descriptor buffer */ @@ -1409,43 +1458,6 @@ static void sh_eth_dev_exit(struct net_device *ndev) update_mac_address(ndev); } -/* free Tx skb function */ -static int sh_eth_txfree(struct net_device *ndev) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - struct sh_eth_txdesc *txdesc; - int free_num = 0; - int entry; - - for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) { - entry = mdp->dirty_tx % mdp->num_tx_ring; - txdesc = &mdp->tx_ring[entry]; - if (txdesc->status & cpu_to_le32(TD_TACT)) - break; - /* TACT bit must be checked before all the following reads */ - dma_rmb(); - netif_info(mdp, tx_done, ndev, - "tx entry %d status 0x%08x\n", - entry, le32_to_cpu(txdesc->status)); - /* Free the original skb. */ - if (mdp->tx_skbuff[entry]) { - dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr), - le32_to_cpu(txdesc->len) >> 16, - DMA_TO_DEVICE); - dev_kfree_skb_irq(mdp->tx_skbuff[entry]); - mdp->tx_skbuff[entry] = NULL; - free_num++; - } - txdesc->status = cpu_to_le32(TD_TFP); - if (entry >= mdp->num_tx_ring - 1) - txdesc->status |= cpu_to_le32(TD_TDLE); - - ndev->stats.tx_packets++; - ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16; - } - return free_num; -} - /* Packet receive function */ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) { @@ -1690,7 +1702,7 @@ static void sh_eth_error(struct net_device *ndev, u32 intr_status) intr_status, mdp->cur_tx, mdp->dirty_tx, (u32)ndev->state, edtrr); /* dirty buffer free */ - sh_eth_txfree(ndev); + sh_eth_tx_free(ndev, true); /* SH7712 BUG */ if (edtrr ^ sh_eth_get_edtrr_trns(mdp)) { @@ -1751,7 +1763,7 @@ static irqreturn_t sh_eth_interrupt(int irq, void *netdev) /* Clear Tx interrupts */ sh_eth_write(ndev, intr_status & cd->tx_check, EESR); - sh_eth_txfree(ndev); + sh_eth_tx_free(ndev, true); netif_wake_queue(ndev); } @@ -2412,7 +2424,7 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev) spin_lock_irqsave(&mdp->lock, flags); if ((mdp->cur_tx - mdp->dirty_tx) >= (mdp->num_tx_ring - 4)) { - if (!sh_eth_txfree(ndev)) { + if (!sh_eth_tx_free(ndev, true)) { netif_warn(mdp, tx_queued, ndev, "TxFD exhausted.\n"); netif_stop_queue(ndev); spin_unlock_irqrestore(&mdp->lock, flags); diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 7cd76b6b5cb9..2ae852454780 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -2216,18 +2216,15 @@ static int ofdpa_port_stp_update(struct ofdpa_port *ofdpa_port, { bool want[OFDPA_CTRL_MAX] = { 0, }; bool prev_ctrls[OFDPA_CTRL_MAX]; - u8 uninitialized_var(prev_state); + u8 prev_state; int err; int i; - if (switchdev_trans_ph_prepare(trans)) { - memcpy(prev_ctrls, ofdpa_port->ctrls, sizeof(prev_ctrls)); - prev_state = ofdpa_port->stp_state; - } - - if (ofdpa_port->stp_state == state) + prev_state = ofdpa_port->stp_state; + if (prev_state == state) return 0; + memcpy(prev_ctrls, ofdpa_port->ctrls, sizeof(prev_ctrls)); ofdpa_port->stp_state = state; switch (state) { diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index c60c2d4c646a..78efb2822b86 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -119,6 +119,7 @@ struct efx_ef10_filter_table { bool mc_promisc; /* Whether in multicast promiscuous mode when last changed */ bool mc_promisc_last; + bool mc_overflow; /* Too many MC addrs; should always imply mc_promisc */ bool vlan_filter; struct list_head vlan_list; }; @@ -5058,6 +5059,7 @@ static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx) struct netdev_hw_addr *mc; unsigned int i, addr_count; + table->mc_overflow = false; table->mc_promisc = !!(net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI)); addr_count = netdev_mc_count(net_dev); @@ -5065,6 +5067,7 @@ static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx) netdev_for_each_mc_addr(mc, net_dev) { if (i >= EFX_EF10_FILTER_DEV_MC_MAX) { table->mc_promisc = true; + table->mc_overflow = true; break; } ether_addr_copy(table->dev_mc_list[i].addr, mc->addr); @@ -5469,12 +5472,15 @@ static void efx_ef10_filter_vlan_sync_rx_mode(struct efx_nic *efx, } } else { /* If we failed to insert promiscuous filters, don't - * rollback. Regardless, also insert the mc_list + * rollback. Regardless, also insert the mc_list, + * unless it's incomplete due to overflow */ efx_ef10_filter_insert_def(efx, vlan, EFX_ENCAP_TYPE_NONE, true, false); - efx_ef10_filter_insert_addr_list(efx, vlan, true, false); + if (!table->mc_overflow) + efx_ef10_filter_insert_addr_list(efx, vlan, + true, false); } } else { /* If any filters failed to insert, rollback and fall back to diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 50d28261b6b9..b9cb697b2818 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1371,6 +1371,13 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx) free_cpumask_var(thread_mask); } + if (count > EFX_MAX_RX_QUEUES) { + netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn, + "Reducing number of rx queues from %u to %u.\n", + count, EFX_MAX_RX_QUEUES); + count = EFX_MAX_RX_QUEUES; + } + /* If RSS is requested for the PF *and* VFs then we can't write RSS * table entries that are inaccessible to VFs */ diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index f5e5cd1659a1..29614da91cbf 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -1354,6 +1354,13 @@ static unsigned int ef4_wanted_parallelism(struct ef4_nic *efx) free_cpumask_var(thread_mask); } + if (count > EF4_MAX_RX_QUEUES) { + netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn, + "Reducing number of rx queues from %u to %u.\n", + count, EF4_MAX_RX_QUEUES); + count = EF4_MAX_RX_QUEUES; + } + return count; } diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c index 01a8c020d6db..e93c40b4631e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c @@ -26,12 +26,15 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) { - struct stmmac_priv *priv = (struct stmmac_priv *)p; - unsigned int entry = priv->cur_tx; - struct dma_desc *desc = priv->dma_tx + entry; + struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)p; unsigned int nopaged_len = skb_headlen(skb); + struct stmmac_priv *priv = tx_q->priv_data; + unsigned int entry = tx_q->cur_tx; unsigned int bmax, des2; unsigned int i = 1, len; + struct dma_desc *desc; + + desc = tx_q->dma_tx + entry; if (priv->plat->enh_desc) bmax = BUF_SIZE_8KiB; @@ -45,16 +48,16 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des2 = cpu_to_le32(des2); if (dma_mapping_error(priv->device, des2)) return -1; - priv->tx_skbuff_dma[entry].buf = des2; - priv->tx_skbuff_dma[entry].len = bmax; + tx_q->tx_skbuff_dma[entry].buf = des2; + tx_q->tx_skbuff_dma[entry].len = bmax; /* do not close the descriptor and do not set own bit */ priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE, - 0, false); + 0, false, skb->len); while (len != 0) { - priv->tx_skbuff[entry] = NULL; + tx_q->tx_skbuff[entry] = NULL; entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); - desc = priv->dma_tx + entry; + desc = tx_q->dma_tx + entry; if (len > bmax) { des2 = dma_map_single(priv->device, @@ -63,11 +66,11 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des2 = cpu_to_le32(des2); if (dma_mapping_error(priv->device, des2)) return -1; - priv->tx_skbuff_dma[entry].buf = des2; - priv->tx_skbuff_dma[entry].len = bmax; + tx_q->tx_skbuff_dma[entry].buf = des2; + tx_q->tx_skbuff_dma[entry].len = bmax; priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum, STMMAC_CHAIN_MODE, 1, - false); + false, skb->len); len -= bmax; i++; } else { @@ -77,17 +80,17 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des2 = cpu_to_le32(des2); if (dma_mapping_error(priv->device, des2)) return -1; - priv->tx_skbuff_dma[entry].buf = des2; - priv->tx_skbuff_dma[entry].len = len; + tx_q->tx_skbuff_dma[entry].buf = des2; + tx_q->tx_skbuff_dma[entry].len = len; /* last descriptor can be set now */ priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, STMMAC_CHAIN_MODE, 1, - true); + true, skb->len); len = 0; } } - priv->cur_tx = entry; + tx_q->cur_tx = entry; return entry; } @@ -136,32 +139,34 @@ static void stmmac_init_dma_chain(void *des, dma_addr_t phy_addr, static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p) { - struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr; + struct stmmac_rx_queue *rx_q = (struct stmmac_rx_queue *)priv_ptr; + struct stmmac_priv *priv = rx_q->priv_data; if (priv->hwts_rx_en && !priv->extend_desc) /* NOTE: Device will overwrite des3 with timestamp value if * 1588-2002 time stamping is enabled, hence reinitialize it * to keep explicit chaining in the descriptor. */ - p->des3 = cpu_to_le32((unsigned int)(priv->dma_rx_phy + - (((priv->dirty_rx) + 1) % + p->des3 = cpu_to_le32((unsigned int)(rx_q->dma_rx_phy + + (((rx_q->dirty_rx) + 1) % DMA_RX_SIZE) * sizeof(struct dma_desc))); } static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p) { - struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr; - unsigned int entry = priv->dirty_tx; + struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)priv_ptr; + struct stmmac_priv *priv = tx_q->priv_data; + unsigned int entry = tx_q->dirty_tx; - if (priv->tx_skbuff_dma[entry].last_segment && !priv->extend_desc && + if (tx_q->tx_skbuff_dma[entry].last_segment && !priv->extend_desc && priv->hwts_tx_en) /* NOTE: Device will overwrite des3 with timestamp value if * 1588-2002 time stamping is enabled, hence reinitialize it * to keep explicit chaining in the descriptor. */ - p->des3 = cpu_to_le32((unsigned int)((priv->dma_tx_phy + - ((priv->dirty_tx + 1) % DMA_TX_SIZE)) + p->des3 = cpu_to_le32((unsigned int)((tx_q->dma_tx_phy + + ((tx_q->dirty_tx + 1) % DMA_TX_SIZE)) * sizeof(struct dma_desc))); } diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 90d28bcad880..b7ce3fbb5375 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -373,7 +373,7 @@ struct stmmac_desc_ops { /* Invoked by the xmit function to prepare the tx descriptor */ void (*prepare_tx_desc) (struct dma_desc *p, int is_fs, int len, bool csum_flag, int mode, bool tx_own, - bool ls); + bool ls, unsigned int tot_pkt_len); void (*prepare_tso_tx_desc)(struct dma_desc *p, int is_fs, int len1, int len2, bool tx_own, bool ls, unsigned int tcphdrlen, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index 843ec69222ea..aa6476439aee 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -304,12 +304,13 @@ static void dwmac4_rd_init_tx_desc(struct dma_desc *p, int mode, int end) static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, bool csum_flag, int mode, bool tx_own, - bool ls) + bool ls, unsigned int tot_pkt_len) { unsigned int tdes3 = le32_to_cpu(p->des3); p->des2 |= cpu_to_le32(len & TDES2_BUFFER1_SIZE_MASK); + tdes3 |= tot_pkt_len & TDES3_PACKET_SIZE_MASK; if (is_fs) tdes3 |= TDES3_FIRST_DESCRIPTOR; else diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c index 323b59ec74a3..7546b3664113 100644 --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c @@ -315,7 +315,7 @@ static void enh_desc_release_tx_desc(struct dma_desc *p, int mode) static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, bool csum_flag, int mode, bool tx_own, - bool ls) + bool ls, unsigned int tot_pkt_len) { unsigned int tdes0 = le32_to_cpu(p->des0); diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c index efb818ebd55e..f817f8f36569 100644 --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c @@ -191,7 +191,7 @@ static void ndesc_release_tx_desc(struct dma_desc *p, int mode) static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, bool csum_flag, int mode, bool tx_own, - bool ls) + bool ls, unsigned int tot_pkt_len) { unsigned int tdes1 = le32_to_cpu(p->des1); diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index 452f256ff03f..28e4b5d50ce6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -26,16 +26,17 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) { - struct stmmac_priv *priv = (struct stmmac_priv *)p; - unsigned int entry = priv->cur_tx; - struct dma_desc *desc; + struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)p; unsigned int nopaged_len = skb_headlen(skb); + struct stmmac_priv *priv = tx_q->priv_data; + unsigned int entry = tx_q->cur_tx; unsigned int bmax, len, des2; + struct dma_desc *desc; if (priv->extend_desc) - desc = (struct dma_desc *)(priv->dma_etx + entry); + desc = (struct dma_desc *)(tx_q->dma_etx + entry); else - desc = priv->dma_tx + entry; + desc = tx_q->dma_tx + entry; if (priv->plat->enh_desc) bmax = BUF_SIZE_8KiB; @@ -52,48 +53,51 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) if (dma_mapping_error(priv->device, des2)) return -1; - priv->tx_skbuff_dma[entry].buf = des2; - priv->tx_skbuff_dma[entry].len = bmax; - priv->tx_skbuff_dma[entry].is_jumbo = true; + tx_q->tx_skbuff_dma[entry].buf = des2; + tx_q->tx_skbuff_dma[entry].len = bmax; + tx_q->tx_skbuff_dma[entry].is_jumbo = true; desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, - STMMAC_RING_MODE, 0, false); - priv->tx_skbuff[entry] = NULL; + STMMAC_RING_MODE, 0, + false, skb->len); + tx_q->tx_skbuff[entry] = NULL; entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); if (priv->extend_desc) - desc = (struct dma_desc *)(priv->dma_etx + entry); + desc = (struct dma_desc *)(tx_q->dma_etx + entry); else - desc = priv->dma_tx + entry; + desc = tx_q->dma_tx + entry; des2 = dma_map_single(priv->device, skb->data + bmax, len, DMA_TO_DEVICE); desc->des2 = cpu_to_le32(des2); if (dma_mapping_error(priv->device, des2)) return -1; - priv->tx_skbuff_dma[entry].buf = des2; - priv->tx_skbuff_dma[entry].len = len; - priv->tx_skbuff_dma[entry].is_jumbo = true; + tx_q->tx_skbuff_dma[entry].buf = des2; + tx_q->tx_skbuff_dma[entry].len = len; + tx_q->tx_skbuff_dma[entry].is_jumbo = true; desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, - STMMAC_RING_MODE, 1, true); + STMMAC_RING_MODE, 1, + true, skb->len); } else { des2 = dma_map_single(priv->device, skb->data, nopaged_len, DMA_TO_DEVICE); desc->des2 = cpu_to_le32(des2); if (dma_mapping_error(priv->device, des2)) return -1; - priv->tx_skbuff_dma[entry].buf = des2; - priv->tx_skbuff_dma[entry].len = nopaged_len; - priv->tx_skbuff_dma[entry].is_jumbo = true; + tx_q->tx_skbuff_dma[entry].buf = des2; + tx_q->tx_skbuff_dma[entry].len = nopaged_len; + tx_q->tx_skbuff_dma[entry].is_jumbo = true; desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum, - STMMAC_RING_MODE, 0, true); + STMMAC_RING_MODE, 0, + true, skb->len); } - priv->cur_tx = entry; + tx_q->cur_tx = entry; return entry; } @@ -125,12 +129,13 @@ static void stmmac_init_desc3(struct dma_desc *p) static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p) { - struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr; - unsigned int entry = priv->dirty_tx; + struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)priv_ptr; + struct stmmac_priv *priv = tx_q->priv_data; + unsigned int entry = tx_q->dirty_tx; /* des3 is only used for jumbo frames tx or time stamping */ - if (unlikely(priv->tx_skbuff_dma[entry].is_jumbo || - (priv->tx_skbuff_dma[entry].last_segment && + if (unlikely(tx_q->tx_skbuff_dma[entry].is_jumbo || + (tx_q->tx_skbuff_dma[entry].last_segment && !priv->extend_desc && priv->hwts_tx_en))) p->des3 = 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index cd8fb619b1e9..33efe7038cab 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -46,38 +46,51 @@ struct stmmac_tx_info { bool is_jumbo; }; -struct stmmac_priv { - /* Frequently used values are kept adjacent for cache effect */ +/* Frequently used values are kept adjacent for cache effect */ +struct stmmac_tx_queue { + u32 queue_index; + struct stmmac_priv *priv_data; struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp; struct dma_desc *dma_tx; struct sk_buff **tx_skbuff; + struct stmmac_tx_info *tx_skbuff_dma; unsigned int cur_tx; unsigned int dirty_tx; + dma_addr_t dma_tx_phy; + u32 tx_tail_addr; +}; + +struct stmmac_rx_queue { + u32 queue_index; + struct stmmac_priv *priv_data; + struct dma_extended_desc *dma_erx; + struct dma_desc *dma_rx ____cacheline_aligned_in_smp; + struct sk_buff **rx_skbuff; + dma_addr_t *rx_skbuff_dma; + unsigned int cur_rx; + unsigned int dirty_rx; + u32 rx_zeroc_thresh; + dma_addr_t dma_rx_phy; + u32 rx_tail_addr; + struct napi_struct napi ____cacheline_aligned_in_smp; +}; + +struct stmmac_priv { + /* Frequently used values are kept adjacent for cache effect */ u32 tx_count_frames; u32 tx_coal_frames; u32 tx_coal_timer; - struct stmmac_tx_info *tx_skbuff_dma; - dma_addr_t dma_tx_phy; + int tx_coalesce; int hwts_tx_en; bool tx_path_in_lpi_mode; struct timer_list txtimer; bool tso; - struct dma_desc *dma_rx ____cacheline_aligned_in_smp; - struct dma_extended_desc *dma_erx; - struct sk_buff **rx_skbuff; - unsigned int cur_rx; - unsigned int dirty_rx; unsigned int dma_buf_sz; unsigned int rx_copybreak; - unsigned int rx_zeroc_thresh; u32 rx_riwt; int hwts_rx_en; - dma_addr_t *rx_skbuff_dma; - dma_addr_t dma_rx_phy; - - struct napi_struct napi ____cacheline_aligned_in_smp; void __iomem *ioaddr; struct net_device *dev; @@ -85,6 +98,12 @@ struct stmmac_priv { struct mac_device_info *hw; spinlock_t lock; + /* RX Queue */ + struct stmmac_rx_queue rx_queue[MTL_MAX_RX_QUEUES]; + + /* TX Queue */ + struct stmmac_tx_queue tx_queue[MTL_MAX_TX_QUEUES]; + int oldlink; int speed; int oldduplex; @@ -119,8 +138,6 @@ struct stmmac_priv { spinlock_t ptp_lock; void __iomem *mmcaddr; void __iomem *ptpaddr; - u32 rx_tail_addr; - u32 tx_tail_addr; u32 mss; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 43361f324229..cd8c60132390 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -139,6 +139,64 @@ static void stmmac_verify_args(void) } /** + * stmmac_disable_all_queues - Disable all queues + * @priv: driver private structure + */ +static void stmmac_disable_all_queues(struct stmmac_priv *priv) +{ + u32 rx_queues_cnt = priv->plat->rx_queues_to_use; + u32 queue; + + for (queue = 0; queue < rx_queues_cnt; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + napi_disable(&rx_q->napi); + } +} + +/** + * stmmac_enable_all_queues - Enable all queues + * @priv: driver private structure + */ +static void stmmac_enable_all_queues(struct stmmac_priv *priv) +{ + u32 rx_queues_cnt = priv->plat->rx_queues_to_use; + u32 queue; + + for (queue = 0; queue < rx_queues_cnt; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + napi_enable(&rx_q->napi); + } +} + +/** + * stmmac_stop_all_queues - Stop all queues + * @priv: driver private structure + */ +static void stmmac_stop_all_queues(struct stmmac_priv *priv) +{ + u32 tx_queues_cnt = priv->plat->tx_queues_to_use; + u32 queue; + + for (queue = 0; queue < tx_queues_cnt; queue++) + netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); +} + +/** + * stmmac_start_all_queues - Start all queues + * @priv: driver private structure + */ +static void stmmac_start_all_queues(struct stmmac_priv *priv) +{ + u32 tx_queues_cnt = priv->plat->tx_queues_to_use; + u32 queue; + + for (queue = 0; queue < tx_queues_cnt; queue++) + netif_tx_start_queue(netdev_get_tx_queue(priv->dev, queue)); +} + +/** * stmmac_clk_csr_set - dynamically set the MDC clock * @priv: driver private structure * Description: this is to dynamically set the MDC clock according to the csr @@ -185,26 +243,33 @@ static void print_pkt(unsigned char *buf, int len) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, buf, len); } -static inline u32 stmmac_tx_avail(struct stmmac_priv *priv) +static inline u32 stmmac_tx_avail(struct stmmac_priv *priv, u32 queue) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; u32 avail; - if (priv->dirty_tx > priv->cur_tx) - avail = priv->dirty_tx - priv->cur_tx - 1; + if (tx_q->dirty_tx > tx_q->cur_tx) + avail = tx_q->dirty_tx - tx_q->cur_tx - 1; else - avail = DMA_TX_SIZE - priv->cur_tx + priv->dirty_tx - 1; + avail = DMA_TX_SIZE - tx_q->cur_tx + tx_q->dirty_tx - 1; return avail; } -static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv) +/** + * stmmac_rx_dirty - Get RX queue dirty + * @priv: driver private structure + * @queue: RX queue index + */ +static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv, u32 queue) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; u32 dirty; - if (priv->dirty_rx <= priv->cur_rx) - dirty = priv->cur_rx - priv->dirty_rx; + if (rx_q->dirty_rx <= rx_q->cur_rx) + dirty = rx_q->cur_rx - rx_q->dirty_rx; else - dirty = DMA_RX_SIZE - priv->dirty_rx + priv->cur_rx; + dirty = DMA_RX_SIZE - rx_q->dirty_rx + rx_q->cur_rx; return dirty; } @@ -232,9 +297,19 @@ static inline void stmmac_hw_fix_mac_speed(struct stmmac_priv *priv) */ static void stmmac_enable_eee_mode(struct stmmac_priv *priv) { + u32 tx_cnt = priv->plat->tx_queues_to_use; + u32 queue; + + /* check if all TX queues have the work finished */ + for (queue = 0; queue < tx_cnt; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + if (tx_q->dirty_tx != tx_q->cur_tx) + return; /* still unfinished work */ + } + /* Check and enter in LPI mode */ - if ((priv->dirty_tx == priv->cur_tx) && - (priv->tx_path_in_lpi_mode == false)) + if (!priv->tx_path_in_lpi_mode) priv->hw->mac->set_eee_mode(priv->hw, priv->plat->en_tx_lpi_clockgating); } @@ -889,22 +964,56 @@ static int stmmac_init_phy(struct net_device *dev) return 0; } -static void stmmac_display_rings(struct stmmac_priv *priv) +static void stmmac_display_rx_rings(struct stmmac_priv *priv) { - void *head_rx, *head_tx; + u32 rx_cnt = priv->plat->rx_queues_to_use; + void *head_rx; + u32 queue; - if (priv->extend_desc) { - head_rx = (void *)priv->dma_erx; - head_tx = (void *)priv->dma_etx; - } else { - head_rx = (void *)priv->dma_rx; - head_tx = (void *)priv->dma_tx; + /* Display RX rings */ + for (queue = 0; queue < rx_cnt; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + pr_info("\tRX Queue %u rings\n", queue); + + if (priv->extend_desc) + head_rx = (void *)rx_q->dma_erx; + else + head_rx = (void *)rx_q->dma_rx; + + /* Display RX ring */ + priv->hw->desc->display_ring(head_rx, DMA_RX_SIZE, true); } +} - /* Display Rx ring */ - priv->hw->desc->display_ring(head_rx, DMA_RX_SIZE, true); - /* Display Tx ring */ - priv->hw->desc->display_ring(head_tx, DMA_TX_SIZE, false); +static void stmmac_display_tx_rings(struct stmmac_priv *priv) +{ + u32 tx_cnt = priv->plat->tx_queues_to_use; + void *head_tx; + u32 queue; + + /* Display TX rings */ + for (queue = 0; queue < tx_cnt; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + pr_info("\tTX Queue %d rings\n", queue); + + if (priv->extend_desc) + head_tx = (void *)tx_q->dma_etx; + else + head_tx = (void *)tx_q->dma_tx; + + priv->hw->desc->display_ring(head_tx, DMA_TX_SIZE, false); + } +} + +static void stmmac_display_rings(struct stmmac_priv *priv) +{ + /* Display RX ring */ + stmmac_display_rx_rings(priv); + + /* Display TX ring */ + stmmac_display_tx_rings(priv); } static int stmmac_set_bfsize(int mtu, int bufsize) @@ -924,48 +1033,88 @@ static int stmmac_set_bfsize(int mtu, int bufsize) } /** - * stmmac_clear_descriptors - clear descriptors + * stmmac_clear_rx_descriptors - clear RX descriptors * @priv: driver private structure - * Description: this function is called to clear the tx and rx descriptors + * @queue: RX queue index + * Description: this function is called to clear the RX descriptors * in case of both basic and extended descriptors are used. */ -static void stmmac_clear_descriptors(struct stmmac_priv *priv) +static void stmmac_clear_rx_descriptors(struct stmmac_priv *priv, u32 queue) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; int i; - /* Clear the Rx/Tx descriptors */ + /* Clear the RX descriptors */ for (i = 0; i < DMA_RX_SIZE; i++) if (priv->extend_desc) - priv->hw->desc->init_rx_desc(&priv->dma_erx[i].basic, + priv->hw->desc->init_rx_desc(&rx_q->dma_erx[i].basic, priv->use_riwt, priv->mode, (i == DMA_RX_SIZE - 1)); else - priv->hw->desc->init_rx_desc(&priv->dma_rx[i], + priv->hw->desc->init_rx_desc(&rx_q->dma_rx[i], priv->use_riwt, priv->mode, (i == DMA_RX_SIZE - 1)); +} + +/** + * stmmac_clear_tx_descriptors - clear tx descriptors + * @priv: driver private structure + * @queue: TX queue index. + * Description: this function is called to clear the TX descriptors + * in case of both basic and extended descriptors are used. + */ +static void stmmac_clear_tx_descriptors(struct stmmac_priv *priv, u32 queue) +{ + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + int i; + + /* Clear the TX descriptors */ for (i = 0; i < DMA_TX_SIZE; i++) if (priv->extend_desc) - priv->hw->desc->init_tx_desc(&priv->dma_etx[i].basic, + priv->hw->desc->init_tx_desc(&tx_q->dma_etx[i].basic, priv->mode, (i == DMA_TX_SIZE - 1)); else - priv->hw->desc->init_tx_desc(&priv->dma_tx[i], + priv->hw->desc->init_tx_desc(&tx_q->dma_tx[i], priv->mode, (i == DMA_TX_SIZE - 1)); } /** + * stmmac_clear_descriptors - clear descriptors + * @priv: driver private structure + * Description: this function is called to clear the TX and RX descriptors + * in case of both basic and extended descriptors are used. + */ +static void stmmac_clear_descriptors(struct stmmac_priv *priv) +{ + u32 rx_queue_cnt = priv->plat->rx_queues_to_use; + u32 tx_queue_cnt = priv->plat->tx_queues_to_use; + u32 queue; + + /* Clear the RX descriptors */ + for (queue = 0; queue < rx_queue_cnt; queue++) + stmmac_clear_rx_descriptors(priv, queue); + + /* Clear the TX descriptors */ + for (queue = 0; queue < tx_queue_cnt; queue++) + stmmac_clear_tx_descriptors(priv, queue); +} + +/** * stmmac_init_rx_buffers - init the RX descriptor buffer. * @priv: driver private structure * @p: descriptor pointer * @i: descriptor index - * @flags: gfp flag. + * @flags: gfp flag + * @queue: RX queue index * Description: this function is called to allocate a receive buffer, perform * the DMA mapping and init the descriptor. */ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p, - int i, gfp_t flags) + int i, gfp_t flags, u32 queue) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; struct sk_buff *skb; skb = __netdev_alloc_skb_ip_align(priv->dev, priv->dma_buf_sz, flags); @@ -974,20 +1123,20 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p, "%s: Rx init fails; skb is NULL\n", __func__); return -ENOMEM; } - priv->rx_skbuff[i] = skb; - priv->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data, + rx_q->rx_skbuff[i] = skb; + rx_q->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data, priv->dma_buf_sz, DMA_FROM_DEVICE); - if (dma_mapping_error(priv->device, priv->rx_skbuff_dma[i])) { + if (dma_mapping_error(priv->device, rx_q->rx_skbuff_dma[i])) { netdev_err(priv->dev, "%s: DMA mapping error\n", __func__); dev_kfree_skb_any(skb); return -EINVAL; } if (priv->synopsys_id >= DWMAC_CORE_4_00) - p->des0 = cpu_to_le32(priv->rx_skbuff_dma[i]); + p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[i]); else - p->des2 = cpu_to_le32(priv->rx_skbuff_dma[i]); + p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[i]); if ((priv->hw->mode->init_desc3) && (priv->dma_buf_sz == BUF_SIZE_16KiB)) @@ -996,30 +1145,71 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p, return 0; } -static void stmmac_free_rx_buffers(struct stmmac_priv *priv, int i) +/** + * stmmac_free_rx_buffer - free RX dma buffers + * @priv: private structure + * @queue: RX queue index + * @i: buffer index. + */ +static void stmmac_free_rx_buffer(struct stmmac_priv *priv, u32 queue, int i) { - if (priv->rx_skbuff[i]) { - dma_unmap_single(priv->device, priv->rx_skbuff_dma[i], + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + if (rx_q->rx_skbuff[i]) { + dma_unmap_single(priv->device, rx_q->rx_skbuff_dma[i], priv->dma_buf_sz, DMA_FROM_DEVICE); - dev_kfree_skb_any(priv->rx_skbuff[i]); + dev_kfree_skb_any(rx_q->rx_skbuff[i]); } - priv->rx_skbuff[i] = NULL; + rx_q->rx_skbuff[i] = NULL; } /** - * init_dma_desc_rings - init the RX/TX descriptor rings + * stmmac_free_tx_buffer - free RX dma buffers + * @priv: private structure + * @queue: RX queue index + * @i: buffer index. + */ +static void stmmac_free_tx_buffer(struct stmmac_priv *priv, u32 queue, int i) +{ + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + if (tx_q->tx_skbuff_dma[i].buf) { + if (tx_q->tx_skbuff_dma[i].map_as_page) + dma_unmap_page(priv->device, + tx_q->tx_skbuff_dma[i].buf, + tx_q->tx_skbuff_dma[i].len, + DMA_TO_DEVICE); + else + dma_unmap_single(priv->device, + tx_q->tx_skbuff_dma[i].buf, + tx_q->tx_skbuff_dma[i].len, + DMA_TO_DEVICE); + } + + if (tx_q->tx_skbuff[i]) { + dev_kfree_skb_any(tx_q->tx_skbuff[i]); + tx_q->tx_skbuff[i] = NULL; + tx_q->tx_skbuff_dma[i].buf = 0; + tx_q->tx_skbuff_dma[i].map_as_page = false; + } +} + +/** + * init_dma_rx_desc_rings - init the RX descriptor rings * @dev: net device structure * @flags: gfp flag. - * Description: this function initializes the DMA RX/TX descriptors + * Description: this function initializes the DMA RX descriptors * and allocates the socket buffers. It supports the chained and ring * modes. */ -static int init_dma_desc_rings(struct net_device *dev, gfp_t flags) +static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags) { - int i; struct stmmac_priv *priv = netdev_priv(dev); + u32 rx_count = priv->plat->rx_queues_to_use; unsigned int bfsize = 0; int ret = -ENOMEM; + u32 queue; + int i; if (priv->hw->mode->set_16kib_bfsize) bfsize = priv->hw->mode->set_16kib_bfsize(dev->mtu); @@ -1029,235 +1219,409 @@ static int init_dma_desc_rings(struct net_device *dev, gfp_t flags) priv->dma_buf_sz = bfsize; - netif_dbg(priv, probe, priv->dev, - "(%s) dma_rx_phy=0x%08x dma_tx_phy=0x%08x\n", - __func__, (u32)priv->dma_rx_phy, (u32)priv->dma_tx_phy); - /* RX INITIALIZATION */ netif_dbg(priv, probe, priv->dev, "SKB addresses:\nskb\t\tskb data\tdma data\n"); - for (i = 0; i < DMA_RX_SIZE; i++) { - struct dma_desc *p; - if (priv->extend_desc) - p = &((priv->dma_erx + i)->basic); - else - p = priv->dma_rx + i; + for (queue = 0; queue < rx_count; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + netif_dbg(priv, probe, priv->dev, + "(%s) dma_rx_phy=0x%08x\n", __func__, + (u32)rx_q->dma_rx_phy); + + for (i = 0; i < DMA_RX_SIZE; i++) { + struct dma_desc *p; - ret = stmmac_init_rx_buffers(priv, p, i, flags); - if (ret) - goto err_init_rx_buffers; + if (priv->extend_desc) + p = &((rx_q->dma_erx + i)->basic); + else + p = rx_q->dma_rx + i; + + ret = stmmac_init_rx_buffers(priv, p, i, flags, + queue); + if (ret) + goto err_init_rx_buffers; - netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n", - priv->rx_skbuff[i], priv->rx_skbuff[i]->data, - (unsigned int)priv->rx_skbuff_dma[i]); + netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n", + rx_q->rx_skbuff[i], rx_q->rx_skbuff[i]->data, + (unsigned int)rx_q->rx_skbuff_dma[i]); + } + + rx_q->cur_rx = 0; + rx_q->dirty_rx = (unsigned int)(i - DMA_RX_SIZE); + + stmmac_clear_rx_descriptors(priv, queue); + + /* Setup the chained descriptor addresses */ + if (priv->mode == STMMAC_CHAIN_MODE) { + if (priv->extend_desc) + priv->hw->mode->init(rx_q->dma_erx, + rx_q->dma_rx_phy, + DMA_RX_SIZE, 1); + else + priv->hw->mode->init(rx_q->dma_rx, + rx_q->dma_rx_phy, + DMA_RX_SIZE, 0); + } } - priv->cur_rx = 0; - priv->dirty_rx = (unsigned int)(i - DMA_RX_SIZE); + buf_sz = bfsize; - /* Setup the chained descriptor addresses */ - if (priv->mode == STMMAC_CHAIN_MODE) { - if (priv->extend_desc) { - priv->hw->mode->init(priv->dma_erx, priv->dma_rx_phy, - DMA_RX_SIZE, 1); - priv->hw->mode->init(priv->dma_etx, priv->dma_tx_phy, - DMA_TX_SIZE, 1); - } else { - priv->hw->mode->init(priv->dma_rx, priv->dma_rx_phy, - DMA_RX_SIZE, 0); - priv->hw->mode->init(priv->dma_tx, priv->dma_tx_phy, - DMA_TX_SIZE, 0); - } + return 0; + +err_init_rx_buffers: + while (queue >= 0) { + while (--i >= 0) + stmmac_free_rx_buffer(priv, queue, i); + + if (queue == 0) + break; + + i = DMA_RX_SIZE; + queue--; } - /* TX INITIALIZATION */ - for (i = 0; i < DMA_TX_SIZE; i++) { - struct dma_desc *p; - if (priv->extend_desc) - p = &((priv->dma_etx + i)->basic); - else - p = priv->dma_tx + i; + return ret; +} - if (priv->synopsys_id >= DWMAC_CORE_4_00) { - p->des0 = 0; - p->des1 = 0; - p->des2 = 0; - p->des3 = 0; - } else { - p->des2 = 0; +/** + * init_dma_tx_desc_rings - init the TX descriptor rings + * @dev: net device structure. + * Description: this function initializes the DMA TX descriptors + * and allocates the socket buffers. It supports the chained and ring + * modes. + */ +static int init_dma_tx_desc_rings(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + u32 tx_queue_cnt = priv->plat->tx_queues_to_use; + u32 queue; + int i; + + for (queue = 0; queue < tx_queue_cnt; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + netif_dbg(priv, probe, priv->dev, + "(%s) dma_tx_phy=0x%08x\n", __func__, + (u32)tx_q->dma_tx_phy); + + /* Setup the chained descriptor addresses */ + if (priv->mode == STMMAC_CHAIN_MODE) { + if (priv->extend_desc) + priv->hw->mode->init(tx_q->dma_etx, + tx_q->dma_tx_phy, + DMA_TX_SIZE, 1); + else + priv->hw->mode->init(tx_q->dma_tx, + tx_q->dma_tx_phy, + DMA_TX_SIZE, 0); } - priv->tx_skbuff_dma[i].buf = 0; - priv->tx_skbuff_dma[i].map_as_page = false; - priv->tx_skbuff_dma[i].len = 0; - priv->tx_skbuff_dma[i].last_segment = false; - priv->tx_skbuff[i] = NULL; + for (i = 0; i < DMA_TX_SIZE; i++) { + struct dma_desc *p; + if (priv->extend_desc) + p = &((tx_q->dma_etx + i)->basic); + else + p = tx_q->dma_tx + i; + + if (priv->synopsys_id >= DWMAC_CORE_4_00) { + p->des0 = 0; + p->des1 = 0; + p->des2 = 0; + p->des3 = 0; + } else { + p->des2 = 0; + } + + tx_q->tx_skbuff_dma[i].buf = 0; + tx_q->tx_skbuff_dma[i].map_as_page = false; + tx_q->tx_skbuff_dma[i].len = 0; + tx_q->tx_skbuff_dma[i].last_segment = false; + tx_q->tx_skbuff[i] = NULL; + } + + tx_q->dirty_tx = 0; + tx_q->cur_tx = 0; + + netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, queue)); } - priv->dirty_tx = 0; - priv->cur_tx = 0; - netdev_reset_queue(priv->dev); + return 0; +} + +/** + * init_dma_desc_rings - init the RX/TX descriptor rings + * @dev: net device structure + * @flags: gfp flag. + * Description: this function initializes the DMA RX/TX descriptors + * and allocates the socket buffers. It supports the chained and ring + * modes. + */ +static int init_dma_desc_rings(struct net_device *dev, gfp_t flags) +{ + struct stmmac_priv *priv = netdev_priv(dev); + int ret; + + ret = init_dma_rx_desc_rings(dev, flags); + if (ret) + return ret; + + ret = init_dma_tx_desc_rings(dev); stmmac_clear_descriptors(priv); if (netif_msg_hw(priv)) stmmac_display_rings(priv); - return 0; -err_init_rx_buffers: - while (--i >= 0) - stmmac_free_rx_buffers(priv, i); return ret; } -static void dma_free_rx_skbufs(struct stmmac_priv *priv) +/** + * dma_free_rx_skbufs - free RX dma buffers + * @priv: private structure + * @queue: RX queue index + */ +static void dma_free_rx_skbufs(struct stmmac_priv *priv, u32 queue) { int i; for (i = 0; i < DMA_RX_SIZE; i++) - stmmac_free_rx_buffers(priv, i); + stmmac_free_rx_buffer(priv, queue, i); } -static void dma_free_tx_skbufs(struct stmmac_priv *priv) +/** + * dma_free_tx_skbufs - free TX dma buffers + * @priv: private structure + * @queue: TX queue index + */ +static void dma_free_tx_skbufs(struct stmmac_priv *priv, u32 queue) { int i; - for (i = 0; i < DMA_TX_SIZE; i++) { - if (priv->tx_skbuff_dma[i].buf) { - if (priv->tx_skbuff_dma[i].map_as_page) - dma_unmap_page(priv->device, - priv->tx_skbuff_dma[i].buf, - priv->tx_skbuff_dma[i].len, - DMA_TO_DEVICE); - else - dma_unmap_single(priv->device, - priv->tx_skbuff_dma[i].buf, - priv->tx_skbuff_dma[i].len, - DMA_TO_DEVICE); - } + for (i = 0; i < DMA_TX_SIZE; i++) + stmmac_free_tx_buffer(priv, queue, i); +} - if (priv->tx_skbuff[i]) { - dev_kfree_skb_any(priv->tx_skbuff[i]); - priv->tx_skbuff[i] = NULL; - priv->tx_skbuff_dma[i].buf = 0; - priv->tx_skbuff_dma[i].map_as_page = false; - } +/** + * free_dma_rx_desc_resources - free RX dma desc resources + * @priv: private structure + */ +static void free_dma_rx_desc_resources(struct stmmac_priv *priv) +{ + u32 rx_count = priv->plat->rx_queues_to_use; + u32 queue; + + /* Free RX queue resources */ + for (queue = 0; queue < rx_count; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + /* Release the DMA RX socket buffers */ + dma_free_rx_skbufs(priv, queue); + + /* Free DMA regions of consistent memory previously allocated */ + if (!priv->extend_desc) + dma_free_coherent(priv->device, + DMA_RX_SIZE * sizeof(struct dma_desc), + rx_q->dma_rx, rx_q->dma_rx_phy); + else + dma_free_coherent(priv->device, DMA_RX_SIZE * + sizeof(struct dma_extended_desc), + rx_q->dma_erx, rx_q->dma_rx_phy); + + kfree(rx_q->rx_skbuff_dma); + kfree(rx_q->rx_skbuff); } } /** - * alloc_dma_desc_resources - alloc TX/RX resources. + * free_dma_tx_desc_resources - free TX dma desc resources + * @priv: private structure + */ +static void free_dma_tx_desc_resources(struct stmmac_priv *priv) +{ + u32 tx_count = priv->plat->tx_queues_to_use; + u32 queue = 0; + + /* Free TX queue resources */ + for (queue = 0; queue < tx_count; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + /* Release the DMA TX socket buffers */ + dma_free_tx_skbufs(priv, queue); + + /* Free DMA regions of consistent memory previously allocated */ + if (!priv->extend_desc) + dma_free_coherent(priv->device, + DMA_TX_SIZE * sizeof(struct dma_desc), + tx_q->dma_tx, tx_q->dma_tx_phy); + else + dma_free_coherent(priv->device, DMA_TX_SIZE * + sizeof(struct dma_extended_desc), + tx_q->dma_etx, tx_q->dma_tx_phy); + + kfree(tx_q->tx_skbuff_dma); + kfree(tx_q->tx_skbuff); + } +} + +/** + * alloc_dma_rx_desc_resources - alloc RX resources. * @priv: private structure * Description: according to which descriptor can be used (extend or basic) * this function allocates the resources for TX and RX paths. In case of * reception, for example, it pre-allocated the RX socket buffer in order to * allow zero-copy mechanism. */ -static int alloc_dma_desc_resources(struct stmmac_priv *priv) +static int alloc_dma_rx_desc_resources(struct stmmac_priv *priv) { + u32 rx_count = priv->plat->rx_queues_to_use; int ret = -ENOMEM; + u32 queue; - priv->rx_skbuff_dma = kmalloc_array(DMA_RX_SIZE, sizeof(dma_addr_t), - GFP_KERNEL); - if (!priv->rx_skbuff_dma) - return -ENOMEM; + /* RX queues buffers and DMA */ + for (queue = 0; queue < rx_count; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; - priv->rx_skbuff = kmalloc_array(DMA_RX_SIZE, sizeof(struct sk_buff *), - GFP_KERNEL); - if (!priv->rx_skbuff) - goto err_rx_skbuff; - - priv->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE, - sizeof(*priv->tx_skbuff_dma), - GFP_KERNEL); - if (!priv->tx_skbuff_dma) - goto err_tx_skbuff_dma; - - priv->tx_skbuff = kmalloc_array(DMA_TX_SIZE, sizeof(struct sk_buff *), - GFP_KERNEL); - if (!priv->tx_skbuff) - goto err_tx_skbuff; - - if (priv->extend_desc) { - priv->dma_erx = dma_zalloc_coherent(priv->device, DMA_RX_SIZE * - sizeof(struct - dma_extended_desc), - &priv->dma_rx_phy, - GFP_KERNEL); - if (!priv->dma_erx) - goto err_dma; + rx_q->queue_index = queue; + rx_q->priv_data = priv; - priv->dma_etx = dma_zalloc_coherent(priv->device, DMA_TX_SIZE * - sizeof(struct - dma_extended_desc), - &priv->dma_tx_phy, + rx_q->rx_skbuff_dma = kmalloc_array(DMA_RX_SIZE, + sizeof(dma_addr_t), GFP_KERNEL); - if (!priv->dma_etx) { - dma_free_coherent(priv->device, DMA_RX_SIZE * - sizeof(struct dma_extended_desc), - priv->dma_erx, priv->dma_rx_phy); - goto err_dma; - } - } else { - priv->dma_rx = dma_zalloc_coherent(priv->device, DMA_RX_SIZE * - sizeof(struct dma_desc), - &priv->dma_rx_phy, - GFP_KERNEL); - if (!priv->dma_rx) - goto err_dma; + if (!rx_q->rx_skbuff_dma) + return -ENOMEM; - priv->dma_tx = dma_zalloc_coherent(priv->device, DMA_TX_SIZE * - sizeof(struct dma_desc), - &priv->dma_tx_phy, - GFP_KERNEL); - if (!priv->dma_tx) { - dma_free_coherent(priv->device, DMA_RX_SIZE * - sizeof(struct dma_desc), - priv->dma_rx, priv->dma_rx_phy); + rx_q->rx_skbuff = kmalloc_array(DMA_RX_SIZE, + sizeof(struct sk_buff *), + GFP_KERNEL); + if (!rx_q->rx_skbuff) goto err_dma; + + if (priv->extend_desc) { + rx_q->dma_erx = dma_zalloc_coherent(priv->device, + DMA_RX_SIZE * + sizeof(struct + dma_extended_desc), + &rx_q->dma_rx_phy, + GFP_KERNEL); + if (!rx_q->dma_erx) + goto err_dma; + + } else { + rx_q->dma_rx = dma_zalloc_coherent(priv->device, + DMA_RX_SIZE * + sizeof(struct + dma_desc), + &rx_q->dma_rx_phy, + GFP_KERNEL); + if (!rx_q->dma_rx) + goto err_dma; } } return 0; err_dma: - kfree(priv->tx_skbuff); -err_tx_skbuff: - kfree(priv->tx_skbuff_dma); -err_tx_skbuff_dma: - kfree(priv->rx_skbuff); -err_rx_skbuff: - kfree(priv->rx_skbuff_dma); + free_dma_rx_desc_resources(priv); + return ret; } -static void free_dma_desc_resources(struct stmmac_priv *priv) +/** + * alloc_dma_tx_desc_resources - alloc TX resources. + * @priv: private structure + * Description: according to which descriptor can be used (extend or basic) + * this function allocates the resources for TX and RX paths. In case of + * reception, for example, it pre-allocated the RX socket buffer in order to + * allow zero-copy mechanism. + */ +static int alloc_dma_tx_desc_resources(struct stmmac_priv *priv) { - /* Release the DMA TX/RX socket buffers */ - dma_free_rx_skbufs(priv); - dma_free_tx_skbufs(priv); - - /* Free DMA regions of consistent memory previously allocated */ - if (!priv->extend_desc) { - dma_free_coherent(priv->device, - DMA_TX_SIZE * sizeof(struct dma_desc), - priv->dma_tx, priv->dma_tx_phy); - dma_free_coherent(priv->device, - DMA_RX_SIZE * sizeof(struct dma_desc), - priv->dma_rx, priv->dma_rx_phy); - } else { - dma_free_coherent(priv->device, DMA_TX_SIZE * - sizeof(struct dma_extended_desc), - priv->dma_etx, priv->dma_tx_phy); - dma_free_coherent(priv->device, DMA_RX_SIZE * - sizeof(struct dma_extended_desc), - priv->dma_erx, priv->dma_rx_phy); + u32 tx_count = priv->plat->tx_queues_to_use; + int ret = -ENOMEM; + u32 queue; + + /* TX queues buffers and DMA */ + for (queue = 0; queue < tx_count; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + tx_q->queue_index = queue; + tx_q->priv_data = priv; + + tx_q->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE, + sizeof(*tx_q->tx_skbuff_dma), + GFP_KERNEL); + if (!tx_q->tx_skbuff_dma) + return -ENOMEM; + + tx_q->tx_skbuff = kmalloc_array(DMA_TX_SIZE, + sizeof(struct sk_buff *), + GFP_KERNEL); + if (!tx_q->tx_skbuff) + goto err_dma_buffers; + + if (priv->extend_desc) { + tx_q->dma_etx = dma_zalloc_coherent(priv->device, + DMA_TX_SIZE * + sizeof(struct + dma_extended_desc), + &tx_q->dma_tx_phy, + GFP_KERNEL); + if (!tx_q->dma_etx) + goto err_dma_buffers; + } else { + tx_q->dma_tx = dma_zalloc_coherent(priv->device, + DMA_TX_SIZE * + sizeof(struct + dma_desc), + &tx_q->dma_tx_phy, + GFP_KERNEL); + if (!tx_q->dma_tx) + goto err_dma_buffers; + } } - kfree(priv->rx_skbuff_dma); - kfree(priv->rx_skbuff); - kfree(priv->tx_skbuff_dma); - kfree(priv->tx_skbuff); + + return 0; + +err_dma_buffers: + free_dma_tx_desc_resources(priv); + + return ret; +} + +/** + * alloc_dma_desc_resources - alloc TX/RX resources. + * @priv: private structure + * Description: according to which descriptor can be used (extend or basic) + * this function allocates the resources for TX and RX paths. In case of + * reception, for example, it pre-allocated the RX socket buffer in order to + * allow zero-copy mechanism. + */ +static int alloc_dma_desc_resources(struct stmmac_priv *priv) +{ + /* RX Allocation */ + int ret = alloc_dma_rx_desc_resources(priv); + + if (ret) + return ret; + + ret = alloc_dma_tx_desc_resources(priv); + + return ret; +} + +/** + * free_dma_desc_resources - free dma desc resources + * @priv: private structure + */ +static void free_dma_desc_resources(struct stmmac_priv *priv) +{ + /* Release the DMA RX socket buffers */ + free_dma_rx_desc_resources(priv); + + /* Release the DMA TX socket buffers */ + free_dma_tx_desc_resources(priv); } /** @@ -1421,26 +1785,28 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) /** * stmmac_tx_clean - to manage the transmission completion * @priv: driver private structure + * @queue: TX queue index * Description: it reclaims the transmit resources after transmission completes. */ -static void stmmac_tx_clean(struct stmmac_priv *priv) +static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; unsigned int bytes_compl = 0, pkts_compl = 0; - unsigned int entry = priv->dirty_tx; + unsigned int entry = tx_q->dirty_tx; netif_tx_lock(priv->dev); priv->xstats.tx_clean++; - while (entry != priv->cur_tx) { - struct sk_buff *skb = priv->tx_skbuff[entry]; + while (entry != tx_q->cur_tx) { + struct sk_buff *skb = tx_q->tx_skbuff[entry]; struct dma_desc *p; int status; if (priv->extend_desc) - p = (struct dma_desc *)(priv->dma_etx + entry); + p = (struct dma_desc *)(tx_q->dma_etx + entry); else - p = priv->dma_tx + entry; + p = tx_q->dma_tx + entry; status = priv->hw->desc->tx_status(&priv->dev->stats, &priv->xstats, p, @@ -1461,48 +1827,51 @@ static void stmmac_tx_clean(struct stmmac_priv *priv) stmmac_get_tx_hwtstamp(priv, p, skb); } - if (likely(priv->tx_skbuff_dma[entry].buf)) { - if (priv->tx_skbuff_dma[entry].map_as_page) + if (likely(tx_q->tx_skbuff_dma[entry].buf)) { + if (tx_q->tx_skbuff_dma[entry].map_as_page) dma_unmap_page(priv->device, - priv->tx_skbuff_dma[entry].buf, - priv->tx_skbuff_dma[entry].len, + tx_q->tx_skbuff_dma[entry].buf, + tx_q->tx_skbuff_dma[entry].len, DMA_TO_DEVICE); else dma_unmap_single(priv->device, - priv->tx_skbuff_dma[entry].buf, - priv->tx_skbuff_dma[entry].len, + tx_q->tx_skbuff_dma[entry].buf, + tx_q->tx_skbuff_dma[entry].len, DMA_TO_DEVICE); - priv->tx_skbuff_dma[entry].buf = 0; - priv->tx_skbuff_dma[entry].len = 0; - priv->tx_skbuff_dma[entry].map_as_page = false; + tx_q->tx_skbuff_dma[entry].buf = 0; + tx_q->tx_skbuff_dma[entry].len = 0; + tx_q->tx_skbuff_dma[entry].map_as_page = false; } if (priv->hw->mode->clean_desc3) - priv->hw->mode->clean_desc3(priv, p); + priv->hw->mode->clean_desc3(tx_q, p); - priv->tx_skbuff_dma[entry].last_segment = false; - priv->tx_skbuff_dma[entry].is_jumbo = false; + tx_q->tx_skbuff_dma[entry].last_segment = false; + tx_q->tx_skbuff_dma[entry].is_jumbo = false; if (likely(skb != NULL)) { pkts_compl++; bytes_compl += skb->len; dev_consume_skb_any(skb); - priv->tx_skbuff[entry] = NULL; + tx_q->tx_skbuff[entry] = NULL; } priv->hw->desc->release_tx_desc(p, priv->mode); entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); } - priv->dirty_tx = entry; + tx_q->dirty_tx = entry; + + netdev_tx_completed_queue(netdev_get_tx_queue(priv->dev, queue), + pkts_compl, bytes_compl); - netdev_completed_queue(priv->dev, pkts_compl, bytes_compl); + if (unlikely(netif_tx_queue_stopped(netdev_get_tx_queue(priv->dev, + queue))) && + stmmac_tx_avail(priv, queue) > STMMAC_TX_THRESH) { - if (unlikely(netif_queue_stopped(priv->dev) && - stmmac_tx_avail(priv) > STMMAC_TX_THRESH)) { netif_dbg(priv, tx_done, priv->dev, "%s: restart transmit\n", __func__); - netif_wake_queue(priv->dev); + netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, queue)); } if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) { @@ -1531,27 +1900,29 @@ static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv, u32 chan) */ static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan]; int i; - netif_stop_queue(priv->dev); + + netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, chan)); stmmac_stop_tx_dma(priv, chan); - dma_free_tx_skbufs(priv); + dma_free_tx_skbufs(priv, chan); for (i = 0; i < DMA_TX_SIZE; i++) if (priv->extend_desc) - priv->hw->desc->init_tx_desc(&priv->dma_etx[i].basic, + priv->hw->desc->init_tx_desc(&tx_q->dma_etx[i].basic, priv->mode, (i == DMA_TX_SIZE - 1)); else - priv->hw->desc->init_tx_desc(&priv->dma_tx[i], + priv->hw->desc->init_tx_desc(&tx_q->dma_tx[i], priv->mode, (i == DMA_TX_SIZE - 1)); - priv->dirty_tx = 0; - priv->cur_tx = 0; - netdev_reset_queue(priv->dev); + tx_q->dirty_tx = 0; + tx_q->cur_tx = 0; + netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, chan)); stmmac_start_tx_dma(priv, chan); priv->dev->stats.tx_errors++; - netif_wake_queue(priv->dev); + netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, chan)); } /** @@ -1596,12 +1967,14 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) u32 chan; for (chan = 0; chan < tx_channel_count; chan++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan]; + status = priv->hw->dma->dma_interrupt(priv->ioaddr, &priv->xstats, chan); if (likely((status & handle_rx)) || (status & handle_tx)) { - if (likely(napi_schedule_prep(&priv->napi))) { + if (likely(napi_schedule_prep(&rx_q->napi))) { stmmac_disable_dma_irq(priv, chan); - __napi_schedule(&priv->napi); + __napi_schedule(&rx_q->napi); } } @@ -1734,6 +2107,8 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) { u32 rx_channels_count = priv->plat->rx_queues_to_use; u32 tx_channels_count = priv->plat->tx_queues_to_use; + struct stmmac_rx_queue *rx_q; + struct stmmac_tx_queue *tx_q; u32 dummy_dma_rx_phy = 0; u32 dummy_dma_tx_phy = 0; u32 chan = 0; @@ -1761,36 +2136,42 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) /* DMA RX Channel Configuration */ for (chan = 0; chan < rx_channels_count; chan++) { + rx_q = &priv->rx_queue[chan]; + priv->hw->dma->init_rx_chan(priv->ioaddr, priv->plat->dma_cfg, - priv->dma_rx_phy, chan); + rx_q->dma_rx_phy, chan); - priv->rx_tail_addr = priv->dma_rx_phy + + rx_q->rx_tail_addr = rx_q->dma_rx_phy + (DMA_RX_SIZE * sizeof(struct dma_desc)); priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, - priv->rx_tail_addr, + rx_q->rx_tail_addr, chan); } /* DMA TX Channel Configuration */ for (chan = 0; chan < tx_channels_count; chan++) { + tx_q = &priv->tx_queue[chan]; + priv->hw->dma->init_chan(priv->ioaddr, - priv->plat->dma_cfg, - chan); + priv->plat->dma_cfg, + chan); priv->hw->dma->init_tx_chan(priv->ioaddr, priv->plat->dma_cfg, - priv->dma_tx_phy, chan); + tx_q->dma_tx_phy, chan); - priv->tx_tail_addr = priv->dma_tx_phy + + tx_q->tx_tail_addr = tx_q->dma_tx_phy + (DMA_TX_SIZE * sizeof(struct dma_desc)); priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, - priv->tx_tail_addr, + tx_q->tx_tail_addr, chan); } } else { + rx_q = &priv->rx_queue[chan]; + tx_q = &priv->tx_queue[chan]; priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg, - priv->dma_tx_phy, priv->dma_rx_phy, atds); + tx_q->dma_tx_phy, rx_q->dma_rx_phy, atds); } if (priv->plat->axi && priv->hw->dma->axi) @@ -1808,8 +2189,12 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) static void stmmac_tx_timer(unsigned long data) { struct stmmac_priv *priv = (struct stmmac_priv *)data; + u32 tx_queues_count = priv->plat->tx_queues_to_use; + u32 queue; - stmmac_tx_clean(priv); + /* let's scan all the tx queues */ + for (queue = 0; queue < tx_queues_count; queue++) + stmmac_tx_clean(priv, queue); } /** @@ -1880,7 +2265,8 @@ static void stmmac_configure_cbs(struct stmmac_priv *priv) u32 mode_to_use; u32 queue; - for (queue = 0; queue < tx_queues_count; queue++) { + /* queue 0 is reserved for legacy traffic */ + for (queue = 1; queue < tx_queues_count; queue++) { mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use; if (mode_to_use == MTL_QUEUE_DCB) continue; @@ -2000,7 +2386,7 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) stmmac_configure_cbs(priv); /* Map RX MTL to DMA channels */ - if (rx_queues_count > 1 && priv->hw->mac->map_mtl_to_dma) + if (priv->hw->mac->map_mtl_to_dma) stmmac_rx_queue_dma_chan_map(priv); /* Enable MAC RX Queues */ @@ -2230,8 +2616,8 @@ static int stmmac_open(struct net_device *dev) } } - napi_enable(&priv->napi); - netif_start_queue(dev); + stmmac_enable_all_queues(priv); + stmmac_start_all_queues(priv); return 0; @@ -2274,9 +2660,9 @@ static int stmmac_release(struct net_device *dev) phy_disconnect(dev->phydev); } - netif_stop_queue(dev); + stmmac_stop_all_queues(priv); - napi_disable(&priv->napi); + stmmac_disable_all_queues(priv); del_timer_sync(&priv->txtimer); @@ -2313,22 +2699,24 @@ static int stmmac_release(struct net_device *dev) * @des: buffer start address * @total_len: total length to fill in descriptors * @last_segmant: condition for the last descriptor + * @queue: TX queue index * Description: * This function fills descriptor and request new descriptors according to * buffer length to fill */ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des, - int total_len, bool last_segment) + int total_len, bool last_segment, u32 queue) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; struct dma_desc *desc; - int tmp_len; u32 buff_size; + int tmp_len; tmp_len = total_len; while (tmp_len > 0) { - priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE); - desc = priv->dma_tx + priv->cur_tx; + tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); + desc = tx_q->dma_tx + tx_q->cur_tx; desc->des0 = cpu_to_le32(des + (total_len - tmp_len)); buff_size = tmp_len >= TSO_MAX_BUFF_SIZE ? @@ -2372,23 +2760,28 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des, */ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) { - u32 pay_len, mss; - int tmp_pay_len = 0; + struct dma_desc *desc, *first, *mss_desc = NULL; struct stmmac_priv *priv = netdev_priv(dev); int nfrags = skb_shinfo(skb)->nr_frags; + u32 queue = skb_get_queue_mapping(skb); unsigned int first_entry, des; - struct dma_desc *desc, *first, *mss_desc = NULL; + struct stmmac_tx_queue *tx_q; + int tmp_pay_len = 0; + u32 pay_len, mss; u8 proto_hdr_len; int i; + tx_q = &priv->tx_queue[queue]; + /* Compute header lengths */ proto_hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); /* Desc availability based on threshold should be enough safe */ - if (unlikely(stmmac_tx_avail(priv) < + if (unlikely(stmmac_tx_avail(priv, queue) < (((skb->len - proto_hdr_len) / TSO_MAX_BUFF_SIZE + 1)))) { - if (!netif_queue_stopped(dev)) { - netif_stop_queue(dev); + if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) { + netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, + queue)); /* This is a hard error, log it. */ netdev_err(priv->dev, "%s: Tx Ring full when queue awake\n", @@ -2403,10 +2796,10 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) /* set new MSS value if needed */ if (mss != priv->mss) { - mss_desc = priv->dma_tx + priv->cur_tx; + mss_desc = tx_q->dma_tx + tx_q->cur_tx; priv->hw->desc->set_mss(mss_desc, mss); priv->mss = mss; - priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE); + tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); } if (netif_msg_tx_queued(priv)) { @@ -2416,9 +2809,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) skb->data_len); } - first_entry = priv->cur_tx; + first_entry = tx_q->cur_tx; - desc = priv->dma_tx + first_entry; + desc = tx_q->dma_tx + first_entry; first = desc; /* first descriptor: fill Headers on Buf1 */ @@ -2427,9 +2820,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) if (dma_mapping_error(priv->device, des)) goto dma_map_err; - priv->tx_skbuff_dma[first_entry].buf = des; - priv->tx_skbuff_dma[first_entry].len = skb_headlen(skb); - priv->tx_skbuff[first_entry] = skb; + tx_q->tx_skbuff_dma[first_entry].buf = des; + tx_q->tx_skbuff_dma[first_entry].len = skb_headlen(skb); + tx_q->tx_skbuff[first_entry] = skb; first->des0 = cpu_to_le32(des); @@ -2440,7 +2833,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) /* If needed take extra descriptors to fill the remaining payload */ tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE; - stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0)); + stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue); /* Prepare fragments */ for (i = 0; i < nfrags; i++) { @@ -2453,22 +2846,22 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) goto dma_map_err; stmmac_tso_allocator(priv, des, skb_frag_size(frag), - (i == nfrags - 1)); + (i == nfrags - 1), queue); - priv->tx_skbuff_dma[priv->cur_tx].buf = des; - priv->tx_skbuff_dma[priv->cur_tx].len = skb_frag_size(frag); - priv->tx_skbuff[priv->cur_tx] = NULL; - priv->tx_skbuff_dma[priv->cur_tx].map_as_page = true; + tx_q->tx_skbuff_dma[tx_q->cur_tx].buf = des; + tx_q->tx_skbuff_dma[tx_q->cur_tx].len = skb_frag_size(frag); + tx_q->tx_skbuff[tx_q->cur_tx] = NULL; + tx_q->tx_skbuff_dma[tx_q->cur_tx].map_as_page = true; } - priv->tx_skbuff_dma[priv->cur_tx].last_segment = true; + tx_q->tx_skbuff_dma[tx_q->cur_tx].last_segment = true; - priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE); + tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); - if (unlikely(stmmac_tx_avail(priv) <= (MAX_SKB_FRAGS + 1))) { + if (unlikely(stmmac_tx_avail(priv, queue) <= (MAX_SKB_FRAGS + 1))) { netif_dbg(priv, hw, priv->dev, "%s: stop transmitted packets\n", __func__); - netif_stop_queue(dev); + netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); } dev->stats.tx_bytes += skb->len; @@ -2500,7 +2893,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) priv->hw->desc->prepare_tso_tx_desc(first, 1, proto_hdr_len, pay_len, - 1, priv->tx_skbuff_dma[first_entry].last_segment, + 1, tx_q->tx_skbuff_dma[first_entry].last_segment, tcp_hdrlen(skb) / 4, (skb->len - proto_hdr_len)); /* If context desc is used to change MSS */ @@ -2515,20 +2908,20 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) if (netif_msg_pktdata(priv)) { pr_info("%s: curr=%d dirty=%d f=%d, e=%d, f_p=%p, nfrags %d\n", - __func__, priv->cur_tx, priv->dirty_tx, first_entry, - priv->cur_tx, first, nfrags); + __func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry, + tx_q->cur_tx, first, nfrags); - priv->hw->desc->display_ring((void *)priv->dma_tx, DMA_TX_SIZE, + priv->hw->desc->display_ring((void *)tx_q->dma_tx, DMA_TX_SIZE, 0); pr_info(">>> frame to be transmitted: "); print_pkt(skb->data, skb_headlen(skb)); } - netdev_sent_queue(dev, skb->len); + netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); - priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr, - STMMAC_CHAN0); + priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, tx_q->tx_tail_addr, + queue); return NETDEV_TX_OK; @@ -2552,21 +2945,26 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) struct stmmac_priv *priv = netdev_priv(dev); unsigned int nopaged_len = skb_headlen(skb); int i, csum_insertion = 0, is_jumbo = 0; + u32 queue = skb_get_queue_mapping(skb); int nfrags = skb_shinfo(skb)->nr_frags; unsigned int entry, first_entry; struct dma_desc *desc, *first; + struct stmmac_tx_queue *tx_q; unsigned int enh_desc; unsigned int des; + tx_q = &priv->tx_queue[queue]; + /* Manage oversized TCP frames for GMAC4 device */ if (skb_is_gso(skb) && priv->tso) { if (ip_hdr(skb)->protocol == IPPROTO_TCP) return stmmac_tso_xmit(skb, dev); } - if (unlikely(stmmac_tx_avail(priv) < nfrags + 1)) { - if (!netif_queue_stopped(dev)) { - netif_stop_queue(dev); + if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) { + if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) { + netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, + queue)); /* This is a hard error, log it. */ netdev_err(priv->dev, "%s: Tx Ring full when queue awake\n", @@ -2578,19 +2976,19 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) if (priv->tx_path_in_lpi_mode) stmmac_disable_eee_mode(priv); - entry = priv->cur_tx; + entry = tx_q->cur_tx; first_entry = entry; csum_insertion = (skb->ip_summed == CHECKSUM_PARTIAL); if (likely(priv->extend_desc)) - desc = (struct dma_desc *)(priv->dma_etx + entry); + desc = (struct dma_desc *)(tx_q->dma_etx + entry); else - desc = priv->dma_tx + entry; + desc = tx_q->dma_tx + entry; first = desc; - priv->tx_skbuff[first_entry] = skb; + tx_q->tx_skbuff[first_entry] = skb; enh_desc = priv->plat->enh_desc; /* To program the descriptors according to the size of the frame */ @@ -2599,7 +2997,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(is_jumbo) && likely(priv->synopsys_id < DWMAC_CORE_4_00)) { - entry = priv->hw->mode->jumbo_frm(priv, skb, csum_insertion); + entry = priv->hw->mode->jumbo_frm(tx_q, skb, csum_insertion); if (unlikely(entry < 0)) goto dma_map_err; } @@ -2612,48 +3010,49 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); if (likely(priv->extend_desc)) - desc = (struct dma_desc *)(priv->dma_etx + entry); + desc = (struct dma_desc *)(tx_q->dma_etx + entry); else - desc = priv->dma_tx + entry; + desc = tx_q->dma_tx + entry; des = skb_frag_dma_map(priv->device, frag, 0, len, DMA_TO_DEVICE); if (dma_mapping_error(priv->device, des)) goto dma_map_err; /* should reuse desc w/o issues */ - priv->tx_skbuff[entry] = NULL; + tx_q->tx_skbuff[entry] = NULL; - priv->tx_skbuff_dma[entry].buf = des; + tx_q->tx_skbuff_dma[entry].buf = des; if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) desc->des0 = cpu_to_le32(des); else desc->des2 = cpu_to_le32(des); - priv->tx_skbuff_dma[entry].map_as_page = true; - priv->tx_skbuff_dma[entry].len = len; - priv->tx_skbuff_dma[entry].last_segment = last_segment; + tx_q->tx_skbuff_dma[entry].map_as_page = true; + tx_q->tx_skbuff_dma[entry].len = len; + tx_q->tx_skbuff_dma[entry].last_segment = last_segment; /* Prepare the descriptor and set the own bit too */ priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion, - priv->mode, 1, last_segment); + priv->mode, 1, last_segment, + skb->len); } entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); - priv->cur_tx = entry; + tx_q->cur_tx = entry; if (netif_msg_pktdata(priv)) { void *tx_head; netdev_dbg(priv->dev, "%s: curr=%d dirty=%d f=%d, e=%d, first=%p, nfrags=%d", - __func__, priv->cur_tx, priv->dirty_tx, first_entry, + __func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry, entry, first, nfrags); if (priv->extend_desc) - tx_head = (void *)priv->dma_etx; + tx_head = (void *)tx_q->dma_etx; else - tx_head = (void *)priv->dma_tx; + tx_head = (void *)tx_q->dma_tx; priv->hw->desc->display_ring(tx_head, DMA_TX_SIZE, false); @@ -2661,10 +3060,10 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) print_pkt(skb->data, skb->len); } - if (unlikely(stmmac_tx_avail(priv) <= (MAX_SKB_FRAGS + 1))) { + if (unlikely(stmmac_tx_avail(priv, queue) <= (MAX_SKB_FRAGS + 1))) { netif_dbg(priv, hw, priv->dev, "%s: stop transmitted packets\n", __func__); - netif_stop_queue(dev); + netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); } dev->stats.tx_bytes += skb->len; @@ -2699,14 +3098,14 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) if (dma_mapping_error(priv->device, des)) goto dma_map_err; - priv->tx_skbuff_dma[first_entry].buf = des; + tx_q->tx_skbuff_dma[first_entry].buf = des; if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) first->des0 = cpu_to_le32(des); else first->des2 = cpu_to_le32(des); - priv->tx_skbuff_dma[first_entry].len = nopaged_len; - priv->tx_skbuff_dma[first_entry].last_segment = last_segment; + tx_q->tx_skbuff_dma[first_entry].len = nopaged_len; + tx_q->tx_skbuff_dma[first_entry].last_segment = last_segment; if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && priv->hwts_tx_en)) { @@ -2718,7 +3117,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* Prepare the first descriptor setting the OWN bit too */ priv->hw->desc->prepare_tx_desc(first, 1, nopaged_len, csum_insertion, priv->mode, 1, - last_segment); + last_segment, skb->len); /* The own bit must be the latest setting done when prepare the * descriptor and then barrier is needed to make sure that @@ -2727,13 +3126,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) dma_wmb(); } - netdev_sent_queue(dev, skb->len); + netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); if (priv->synopsys_id < DWMAC_CORE_4_00) priv->hw->dma->enable_dma_transmission(priv->ioaddr); else - priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr, - STMMAC_CHAN0); + priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, tx_q->tx_tail_addr, + queue); return NETDEV_TX_OK; @@ -2761,9 +3160,9 @@ static void stmmac_rx_vlan(struct net_device *dev, struct sk_buff *skb) } -static inline int stmmac_rx_threshold_count(struct stmmac_priv *priv) +static inline int stmmac_rx_threshold_count(struct stmmac_rx_queue *rx_q) { - if (priv->rx_zeroc_thresh < STMMAC_RX_THRESH) + if (rx_q->rx_zeroc_thresh < STMMAC_RX_THRESH) return 0; return 1; @@ -2772,30 +3171,33 @@ static inline int stmmac_rx_threshold_count(struct stmmac_priv *priv) /** * stmmac_rx_refill - refill used skb preallocated buffers * @priv: driver private structure + * @queue: RX queue index * Description : this is to reallocate the skb for the reception process * that is based on zero-copy. */ -static inline void stmmac_rx_refill(struct stmmac_priv *priv) +static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + int dirty = stmmac_rx_dirty(priv, queue); + unsigned int entry = rx_q->dirty_rx; + int bfsize = priv->dma_buf_sz; - unsigned int entry = priv->dirty_rx; - int dirty = stmmac_rx_dirty(priv); while (dirty-- > 0) { struct dma_desc *p; if (priv->extend_desc) - p = (struct dma_desc *)(priv->dma_erx + entry); + p = (struct dma_desc *)(rx_q->dma_erx + entry); else - p = priv->dma_rx + entry; + p = rx_q->dma_rx + entry; - if (likely(priv->rx_skbuff[entry] == NULL)) { + if (likely(!rx_q->rx_skbuff[entry])) { struct sk_buff *skb; skb = netdev_alloc_skb_ip_align(priv->dev, bfsize); if (unlikely(!skb)) { /* so for a while no zero-copy! */ - priv->rx_zeroc_thresh = STMMAC_RX_THRESH; + rx_q->rx_zeroc_thresh = STMMAC_RX_THRESH; if (unlikely(net_ratelimit())) dev_err(priv->device, "fail to alloc skb entry %d\n", @@ -2803,28 +3205,28 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv) break; } - priv->rx_skbuff[entry] = skb; - priv->rx_skbuff_dma[entry] = + rx_q->rx_skbuff[entry] = skb; + rx_q->rx_skbuff_dma[entry] = dma_map_single(priv->device, skb->data, bfsize, DMA_FROM_DEVICE); if (dma_mapping_error(priv->device, - priv->rx_skbuff_dma[entry])) { + rx_q->rx_skbuff_dma[entry])) { netdev_err(priv->dev, "Rx DMA map failed\n"); dev_kfree_skb(skb); break; } if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) { - p->des0 = cpu_to_le32(priv->rx_skbuff_dma[entry]); + p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]); p->des1 = 0; } else { - p->des2 = cpu_to_le32(priv->rx_skbuff_dma[entry]); + p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]); } if (priv->hw->mode->refill_desc3) - priv->hw->mode->refill_desc3(priv, p); + priv->hw->mode->refill_desc3(rx_q, p); - if (priv->rx_zeroc_thresh > 0) - priv->rx_zeroc_thresh--; + if (rx_q->rx_zeroc_thresh > 0) + rx_q->rx_zeroc_thresh--; netif_dbg(priv, rx_status, priv->dev, "refill entry #%d\n", entry); @@ -2840,31 +3242,33 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv) entry = STMMAC_GET_ENTRY(entry, DMA_RX_SIZE); } - priv->dirty_rx = entry; + rx_q->dirty_rx = entry; } /** * stmmac_rx - manage the receive process * @priv: driver private structure - * @limit: napi bugget. + * @limit: napi bugget + * @queue: RX queue index. * Description : this the function called by the napi poll method. * It gets all the frames inside the ring. */ -static int stmmac_rx(struct stmmac_priv *priv, int limit) +static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) { - unsigned int entry = priv->cur_rx; + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + unsigned int entry = rx_q->cur_rx; + int coe = priv->hw->rx_csum; unsigned int next_entry; unsigned int count = 0; - int coe = priv->hw->rx_csum; if (netif_msg_rx_status(priv)) { void *rx_head; netdev_dbg(priv->dev, "%s: descriptor ring:\n", __func__); if (priv->extend_desc) - rx_head = (void *)priv->dma_erx; + rx_head = (void *)rx_q->dma_erx; else - rx_head = (void *)priv->dma_rx; + rx_head = (void *)rx_q->dma_rx; priv->hw->desc->display_ring(rx_head, DMA_RX_SIZE, true); } @@ -2874,9 +3278,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) struct dma_desc *np; if (priv->extend_desc) - p = (struct dma_desc *)(priv->dma_erx + entry); + p = (struct dma_desc *)(rx_q->dma_erx + entry); else - p = priv->dma_rx + entry; + p = rx_q->dma_rx + entry; /* read the status of the incoming frame */ status = priv->hw->desc->rx_status(&priv->dev->stats, @@ -2887,20 +3291,20 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) count++; - priv->cur_rx = STMMAC_GET_ENTRY(priv->cur_rx, DMA_RX_SIZE); - next_entry = priv->cur_rx; + rx_q->cur_rx = STMMAC_GET_ENTRY(rx_q->cur_rx, DMA_RX_SIZE); + next_entry = rx_q->cur_rx; if (priv->extend_desc) - np = (struct dma_desc *)(priv->dma_erx + next_entry); + np = (struct dma_desc *)(rx_q->dma_erx + next_entry); else - np = priv->dma_rx + next_entry; + np = rx_q->dma_rx + next_entry; prefetch(np); if ((priv->extend_desc) && (priv->hw->desc->rx_extended_status)) priv->hw->desc->rx_extended_status(&priv->dev->stats, &priv->xstats, - priv->dma_erx + + rx_q->dma_erx + entry); if (unlikely(status == discard_frame)) { priv->dev->stats.rx_errors++; @@ -2910,9 +3314,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) * them in stmmac_rx_refill() function so that * device can reuse it. */ - priv->rx_skbuff[entry] = NULL; + rx_q->rx_skbuff[entry] = NULL; dma_unmap_single(priv->device, - priv->rx_skbuff_dma[entry], + rx_q->rx_skbuff_dma[entry], priv->dma_buf_sz, DMA_FROM_DEVICE); } @@ -2960,7 +3364,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) */ if (unlikely(!priv->plat->has_gmac4 && ((frame_len < priv->rx_copybreak) || - stmmac_rx_threshold_count(priv)))) { + stmmac_rx_threshold_count(rx_q)))) { skb = netdev_alloc_skb_ip_align(priv->dev, frame_len); if (unlikely(!skb)) { @@ -2972,21 +3376,21 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) } dma_sync_single_for_cpu(priv->device, - priv->rx_skbuff_dma + rx_q->rx_skbuff_dma [entry], frame_len, DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, - priv-> + rx_q-> rx_skbuff[entry]->data, frame_len); skb_put(skb, frame_len); dma_sync_single_for_device(priv->device, - priv->rx_skbuff_dma + rx_q->rx_skbuff_dma [entry], frame_len, DMA_FROM_DEVICE); } else { - skb = priv->rx_skbuff[entry]; + skb = rx_q->rx_skbuff[entry]; if (unlikely(!skb)) { netdev_err(priv->dev, "%s: Inconsistent Rx chain\n", @@ -2995,12 +3399,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) break; } prefetch(skb->data - NET_IP_ALIGN); - priv->rx_skbuff[entry] = NULL; - priv->rx_zeroc_thresh++; + rx_q->rx_skbuff[entry] = NULL; + rx_q->rx_zeroc_thresh++; skb_put(skb, frame_len); dma_unmap_single(priv->device, - priv->rx_skbuff_dma[entry], + rx_q->rx_skbuff_dma[entry], priv->dma_buf_sz, DMA_FROM_DEVICE); } @@ -3022,7 +3426,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) else skb->ip_summed = CHECKSUM_UNNECESSARY; - napi_gro_receive(&priv->napi, skb); + napi_gro_receive(&rx_q->napi, skb); priv->dev->stats.rx_packets++; priv->dev->stats.rx_bytes += frame_len; @@ -3030,7 +3434,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) entry = next_entry; } - stmmac_rx_refill(priv); + stmmac_rx_refill(priv, queue); priv->xstats.rx_pkt_n += count; @@ -3047,14 +3451,21 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) */ static int stmmac_poll(struct napi_struct *napi, int budget) { - struct stmmac_priv *priv = container_of(napi, struct stmmac_priv, napi); + struct stmmac_rx_queue *rx_q = + container_of(napi, struct stmmac_rx_queue, napi); + struct stmmac_priv *priv = rx_q->priv_data; + u32 tx_count = priv->plat->tx_queues_to_use; + u32 chan = rx_q->queue_index; int work_done = 0; - u32 chan = STMMAC_CHAN0; + u32 queue; priv->xstats.napi_poll++; - stmmac_tx_clean(priv); - work_done = stmmac_rx(priv, budget); + /* check all the queues */ + for (queue = 0; queue < tx_count; queue++) + stmmac_tx_clean(priv, queue); + + work_done = stmmac_rx(priv, budget, rx_q->queue_index); if (work_done < budget) { napi_complete_done(napi, work_done); stmmac_enable_dma_irq(priv, chan); @@ -3073,10 +3484,12 @@ static int stmmac_poll(struct napi_struct *napi, int budget) static void stmmac_tx_timeout(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); - u32 chan = STMMAC_CHAN0; + u32 tx_count = priv->plat->tx_queues_to_use; + u32 chan; /* Clear Tx resources and restart transmitting again */ - stmmac_tx_err(priv, chan); + for (chan = 0; chan < tx_count; chan++) + stmmac_tx_err(priv, chan); } /** @@ -3215,6 +3628,9 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) if (priv->synopsys_id >= DWMAC_CORE_4_00) { for (queue = 0; queue < queues_count; queue++) { + struct stmmac_rx_queue *rx_q = + &priv->rx_queue[queue]; + status |= priv->hw->mac->host_mtl_irq_status(priv->hw, queue); @@ -3222,7 +3638,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr) priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, - priv->rx_tail_addr, + rx_q->rx_tail_addr, queue); } } @@ -3322,17 +3738,40 @@ static int stmmac_sysfs_ring_read(struct seq_file *seq, void *v) { struct net_device *dev = seq->private; struct stmmac_priv *priv = netdev_priv(dev); + u32 rx_count = priv->plat->rx_queues_to_use; + u32 tx_count = priv->plat->tx_queues_to_use; + u32 queue; - if (priv->extend_desc) { - seq_printf(seq, "Extended RX descriptor ring:\n"); - sysfs_display_ring((void *)priv->dma_erx, DMA_RX_SIZE, 1, seq); - seq_printf(seq, "Extended TX descriptor ring:\n"); - sysfs_display_ring((void *)priv->dma_etx, DMA_TX_SIZE, 1, seq); - } else { - seq_printf(seq, "RX descriptor ring:\n"); - sysfs_display_ring((void *)priv->dma_rx, DMA_RX_SIZE, 0, seq); - seq_printf(seq, "TX descriptor ring:\n"); - sysfs_display_ring((void *)priv->dma_tx, DMA_TX_SIZE, 0, seq); + for (queue = 0; queue < rx_count; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + seq_printf(seq, "RX Queue %d:\n", queue); + + if (priv->extend_desc) { + seq_printf(seq, "Extended descriptor ring:\n"); + sysfs_display_ring((void *)rx_q->dma_erx, + DMA_RX_SIZE, 1, seq); + } else { + seq_printf(seq, "Descriptor ring:\n"); + sysfs_display_ring((void *)rx_q->dma_rx, + DMA_RX_SIZE, 0, seq); + } + } + + for (queue = 0; queue < tx_count; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + seq_printf(seq, "TX Queue %d:\n", queue); + + if (priv->extend_desc) { + seq_printf(seq, "Extended descriptor ring:\n"); + sysfs_display_ring((void *)tx_q->dma_etx, + DMA_TX_SIZE, 1, seq); + } else { + seq_printf(seq, "Descriptor ring:\n"); + sysfs_display_ring((void *)tx_q->dma_tx, + DMA_TX_SIZE, 0, seq); + } } return 0; @@ -3615,11 +4054,14 @@ int stmmac_dvr_probe(struct device *device, struct plat_stmmacenet_data *plat_dat, struct stmmac_resources *res) { - int ret = 0; struct net_device *ndev = NULL; struct stmmac_priv *priv; + int ret = 0; + u32 queue; - ndev = alloc_etherdev(sizeof(struct stmmac_priv)); + ndev = alloc_etherdev_mqs(sizeof(struct stmmac_priv), + MTL_MAX_TX_QUEUES, + MTL_MAX_RX_QUEUES); if (!ndev) return -ENOMEM; @@ -3661,6 +4103,10 @@ int stmmac_dvr_probe(struct device *device, if (ret) goto error_hw_init; + /* Configure real RX and TX queues */ + netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use); + netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use); + ndev->netdev_ops = &stmmac_netdev_ops; ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | @@ -3710,7 +4156,12 @@ int stmmac_dvr_probe(struct device *device, "Enable RX Mitigation via HW Watchdog Timer\n"); } - netif_napi_add(ndev, &priv->napi, stmmac_poll, 64); + for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + netif_napi_add(ndev, &rx_q->napi, stmmac_poll, + (8 * priv->plat->rx_queues_to_use)); + } spin_lock_init(&priv->lock); @@ -3755,7 +4206,11 @@ error_netdev_register: priv->hw->pcs != STMMAC_PCS_RTBI) stmmac_mdio_unregister(ndev); error_mdio_register: - netif_napi_del(&priv->napi); + for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + netif_napi_del(&rx_q->napi); + } error_hw_init: free_netdev(ndev); @@ -3817,9 +4272,9 @@ int stmmac_suspend(struct device *dev) spin_lock_irqsave(&priv->lock, flags); netif_device_detach(ndev); - netif_stop_queue(ndev); + stmmac_stop_all_queues(priv); - napi_disable(&priv->napi); + stmmac_disable_all_queues(priv); /* Stop TX/RX DMA */ stmmac_stop_all_dma(priv); @@ -3845,6 +4300,31 @@ int stmmac_suspend(struct device *dev) EXPORT_SYMBOL_GPL(stmmac_suspend); /** + * stmmac_reset_queues_param - reset queue parameters + * @dev: device pointer + */ +static void stmmac_reset_queues_param(struct stmmac_priv *priv) +{ + u32 rx_cnt = priv->plat->rx_queues_to_use; + u32 tx_cnt = priv->plat->tx_queues_to_use; + u32 queue; + + for (queue = 0; queue < rx_cnt; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + rx_q->cur_rx = 0; + rx_q->dirty_rx = 0; + } + + for (queue = 0; queue < tx_cnt; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + tx_q->cur_tx = 0; + tx_q->dirty_tx = 0; + } +} + +/** * stmmac_resume - resume callback * @dev: device pointer * Description: when resume this function is invoked to setup the DMA and CORE @@ -3884,10 +4364,8 @@ int stmmac_resume(struct device *dev) spin_lock_irqsave(&priv->lock, flags); - priv->cur_rx = 0; - priv->dirty_rx = 0; - priv->dirty_tx = 0; - priv->cur_tx = 0; + stmmac_reset_queues_param(priv); + /* reset private mss value to force mss context settings at * next tso xmit (only used for gmac4). */ @@ -3899,9 +4377,9 @@ int stmmac_resume(struct device *dev) stmmac_init_tx_coalesce(priv); stmmac_set_rx_mode(ndev); - napi_enable(&priv->napi); + stmmac_enable_all_queues(priv); - netif_start_queue(ndev); + stmmac_start_all_queues(priv); spin_unlock_irqrestore(&priv->lock, flags); diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index c4caf486cbef..3189722110c2 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -169,7 +169,7 @@ static void bigmac_stop(struct bigmac *bp) static void bigmac_get_counters(struct bigmac *bp, void __iomem *bregs) { - struct net_device_stats *stats = &bp->enet_stats; + struct net_device_stats *stats = &bp->dev->stats; stats->rx_crc_errors += sbus_readl(bregs + BMAC_RCRCECTR); sbus_writel(0, bregs + BMAC_RCRCECTR); @@ -774,8 +774,8 @@ static void bigmac_tx(struct bigmac *bp) if (this->tx_flags & TXD_OWN) break; skb = bp->tx_skbs[elem]; - bp->enet_stats.tx_packets++; - bp->enet_stats.tx_bytes += skb->len; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; dma_unmap_single(&bp->bigmac_op->dev, this->tx_addr, skb->len, DMA_TO_DEVICE); @@ -811,12 +811,12 @@ static void bigmac_rx(struct bigmac *bp) /* Check for errors. */ if (len < ETH_ZLEN) { - bp->enet_stats.rx_errors++; - bp->enet_stats.rx_length_errors++; + bp->dev->stats.rx_errors++; + bp->dev->stats.rx_length_errors++; drop_it: /* Return it to the BigMAC. */ - bp->enet_stats.rx_dropped++; + bp->dev->stats.rx_dropped++; this->rx_flags = (RXD_OWN | ((RX_BUF_ALLOC_SIZE - 34) & RXD_LENGTH)); goto next; @@ -875,8 +875,8 @@ static void bigmac_rx(struct bigmac *bp) /* No checksums done by the BigMAC ;-( */ skb->protocol = eth_type_trans(skb, bp->dev); netif_rx(skb); - bp->enet_stats.rx_packets++; - bp->enet_stats.rx_bytes += len; + bp->dev->stats.rx_packets++; + bp->dev->stats.rx_bytes += len; next: elem = NEXT_RX(elem); this = &rxbase[elem]; @@ -987,7 +987,7 @@ static struct net_device_stats *bigmac_get_stats(struct net_device *dev) struct bigmac *bp = netdev_priv(dev); bigmac_get_counters(bp, bp->bregs); - return &bp->enet_stats; + return &dev->stats; } static void bigmac_set_multicast(struct net_device *dev) diff --git a/drivers/net/ethernet/sun/sunbmac.h b/drivers/net/ethernet/sun/sunbmac.h index 532fc56830cf..ee56930475a8 100644 --- a/drivers/net/ethernet/sun/sunbmac.h +++ b/drivers/net/ethernet/sun/sunbmac.h @@ -311,7 +311,6 @@ struct bigmac { enum bigmac_timer_state timer_state; unsigned int timer_ticks; - struct net_device_stats enet_stats; struct platform_device *qec_op; struct platform_device *bigmac_op; struct net_device *dev; diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 53ff66ef53ac..a6cc9a2d41c1 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -933,7 +933,7 @@ static void happy_meal_stop(struct happy_meal *hp, void __iomem *gregs) /* hp->happy_lock must be held */ static void happy_meal_get_counters(struct happy_meal *hp, void __iomem *bregs) { - struct net_device_stats *stats = &hp->net_stats; + struct net_device_stats *stats = &hp->dev->stats; stats->rx_crc_errors += hme_read32(hp, bregs + BMAC_RCRCECTR); hme_write32(hp, bregs + BMAC_RCRCECTR, 0); @@ -1947,7 +1947,7 @@ static void happy_meal_tx(struct happy_meal *hp) break; } hp->tx_skbs[elem] = NULL; - hp->net_stats.tx_bytes += skb->len; + dev->stats.tx_bytes += skb->len; for (frag = 0; frag <= skb_shinfo(skb)->nr_frags; frag++) { dma_addr = hme_read_desc32(hp, &this->tx_addr); @@ -1964,7 +1964,7 @@ static void happy_meal_tx(struct happy_meal *hp) } dev_kfree_skb_irq(skb); - hp->net_stats.tx_packets++; + dev->stats.tx_packets++; } hp->tx_old = elem; TXD((">")); @@ -2009,17 +2009,17 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev) /* Check for errors. */ if ((len < ETH_ZLEN) || (flags & RXFLAG_OVERFLOW)) { RXD(("ERR(%08x)]", flags)); - hp->net_stats.rx_errors++; + dev->stats.rx_errors++; if (len < ETH_ZLEN) - hp->net_stats.rx_length_errors++; + dev->stats.rx_length_errors++; if (len & (RXFLAG_OVERFLOW >> 16)) { - hp->net_stats.rx_over_errors++; - hp->net_stats.rx_fifo_errors++; + dev->stats.rx_over_errors++; + dev->stats.rx_fifo_errors++; } /* Return it to the Happy meal. */ drop_it: - hp->net_stats.rx_dropped++; + dev->stats.rx_dropped++; hme_write_rxd(hp, this, (RXFLAG_OWN|((RX_BUF_ALLOC_SIZE-RX_OFFSET)<<16)), dma_addr); @@ -2084,8 +2084,8 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev) skb->protocol = eth_type_trans(skb, dev); netif_rx(skb); - hp->net_stats.rx_packets++; - hp->net_stats.rx_bytes += len; + dev->stats.rx_packets++; + dev->stats.rx_bytes += len; next: elem = NEXT_RX(elem); this = &rxbase[elem]; @@ -2396,7 +2396,7 @@ static struct net_device_stats *happy_meal_get_stats(struct net_device *dev) happy_meal_get_counters(hp, hp->bigmacregs); spin_unlock_irq(&hp->happy_lock); - return &hp->net_stats; + return &dev->stats; } static void happy_meal_set_multicast(struct net_device *dev) diff --git a/drivers/net/ethernet/sun/sunhme.h b/drivers/net/ethernet/sun/sunhme.h index 4a8d5b18dfd5..3af540adb3c5 100644 --- a/drivers/net/ethernet/sun/sunhme.h +++ b/drivers/net/ethernet/sun/sunhme.h @@ -418,8 +418,6 @@ struct happy_meal { int rx_new, tx_new, rx_old, tx_old; - struct net_device_stats net_stats; /* Statistical counters */ - #if defined(CONFIG_SBUS) && defined(CONFIG_PCI) u32 (*read32)(void __iomem *); void (*write32)(void __iomem *, u32); diff --git a/drivers/net/ethernet/synopsys/Makefile b/drivers/net/ethernet/synopsys/Makefile index c06e2eb3be90..0ad01916f11e 100644 --- a/drivers/net/ethernet/synopsys/Makefile +++ b/drivers/net/ethernet/synopsys/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_DWC_XLGMAC) += dwc-xlgmac.o dwc-xlgmac-objs := dwc-xlgmac-net.o dwc-xlgmac-desc.o \ - dwc-xlgmac-hw.o dwc-xlgmac-common.o + dwc-xlgmac-hw.o dwc-xlgmac-common.o \ + dwc-xlgmac-ethtool.o dwc-xlgmac-$(CONFIG_DWC_XLGMAC_PCI) += dwc-xlgmac-pci.o diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c index 07def2beabfa..d655a4261e98 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c @@ -175,6 +175,7 @@ static int xlgmac_init(struct xlgmac_pdata *pdata) /* Set device operations */ netdev->netdev_ops = xlgmac_get_netdev_ops(); + netdev->ethtool_ops = xlgmac_get_ethtool_ops(); /* Set device features */ if (pdata->hw_feat.tso) { diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c new file mode 100644 index 000000000000..fde722136869 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c @@ -0,0 +1,275 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is dual-licensed; you may select either version 2 of + * the GNU General Public License ("GPL") or BSD license ("BSD"). + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#include <linux/ethtool.h> +#include <linux/kernel.h> +#include <linux/netdevice.h> + +#include "dwc-xlgmac.h" +#include "dwc-xlgmac-reg.h" + +struct xlgmac_stats_desc { + char stat_string[ETH_GSTRING_LEN]; + int stat_offset; +}; + +#define XLGMAC_STAT(str, var) \ + { \ + str, \ + offsetof(struct xlgmac_pdata, stats.var), \ + } + +static const struct xlgmac_stats_desc xlgmac_gstring_stats[] = { + /* MMC TX counters */ + XLGMAC_STAT("tx_bytes", txoctetcount_gb), + XLGMAC_STAT("tx_bytes_good", txoctetcount_g), + XLGMAC_STAT("tx_packets", txframecount_gb), + XLGMAC_STAT("tx_packets_good", txframecount_g), + XLGMAC_STAT("tx_unicast_packets", txunicastframes_gb), + XLGMAC_STAT("tx_broadcast_packets", txbroadcastframes_gb), + XLGMAC_STAT("tx_broadcast_packets_good", txbroadcastframes_g), + XLGMAC_STAT("tx_multicast_packets", txmulticastframes_gb), + XLGMAC_STAT("tx_multicast_packets_good", txmulticastframes_g), + XLGMAC_STAT("tx_vlan_packets_good", txvlanframes_g), + XLGMAC_STAT("tx_64_byte_packets", tx64octets_gb), + XLGMAC_STAT("tx_65_to_127_byte_packets", tx65to127octets_gb), + XLGMAC_STAT("tx_128_to_255_byte_packets", tx128to255octets_gb), + XLGMAC_STAT("tx_256_to_511_byte_packets", tx256to511octets_gb), + XLGMAC_STAT("tx_512_to_1023_byte_packets", tx512to1023octets_gb), + XLGMAC_STAT("tx_1024_to_max_byte_packets", tx1024tomaxoctets_gb), + XLGMAC_STAT("tx_underflow_errors", txunderflowerror), + XLGMAC_STAT("tx_pause_frames", txpauseframes), + + /* MMC RX counters */ + XLGMAC_STAT("rx_bytes", rxoctetcount_gb), + XLGMAC_STAT("rx_bytes_good", rxoctetcount_g), + XLGMAC_STAT("rx_packets", rxframecount_gb), + XLGMAC_STAT("rx_unicast_packets_good", rxunicastframes_g), + XLGMAC_STAT("rx_broadcast_packets_good", rxbroadcastframes_g), + XLGMAC_STAT("rx_multicast_packets_good", rxmulticastframes_g), + XLGMAC_STAT("rx_vlan_packets", rxvlanframes_gb), + XLGMAC_STAT("rx_64_byte_packets", rx64octets_gb), + XLGMAC_STAT("rx_65_to_127_byte_packets", rx65to127octets_gb), + XLGMAC_STAT("rx_128_to_255_byte_packets", rx128to255octets_gb), + XLGMAC_STAT("rx_256_to_511_byte_packets", rx256to511octets_gb), + XLGMAC_STAT("rx_512_to_1023_byte_packets", rx512to1023octets_gb), + XLGMAC_STAT("rx_1024_to_max_byte_packets", rx1024tomaxoctets_gb), + XLGMAC_STAT("rx_undersize_packets_good", rxundersize_g), + XLGMAC_STAT("rx_oversize_packets_good", rxoversize_g), + XLGMAC_STAT("rx_crc_errors", rxcrcerror), + XLGMAC_STAT("rx_crc_errors_small_packets", rxrunterror), + XLGMAC_STAT("rx_crc_errors_giant_packets", rxjabbererror), + XLGMAC_STAT("rx_length_errors", rxlengtherror), + XLGMAC_STAT("rx_out_of_range_errors", rxoutofrangetype), + XLGMAC_STAT("rx_fifo_overflow_errors", rxfifooverflow), + XLGMAC_STAT("rx_watchdog_errors", rxwatchdogerror), + XLGMAC_STAT("rx_pause_frames", rxpauseframes), + + /* Extra counters */ + XLGMAC_STAT("tx_tso_packets", tx_tso_packets), + XLGMAC_STAT("rx_split_header_packets", rx_split_header_packets), + XLGMAC_STAT("tx_process_stopped", tx_process_stopped), + XLGMAC_STAT("rx_process_stopped", rx_process_stopped), + XLGMAC_STAT("tx_buffer_unavailable", tx_buffer_unavailable), + XLGMAC_STAT("rx_buffer_unavailable", rx_buffer_unavailable), + XLGMAC_STAT("fatal_bus_error", fatal_bus_error), + XLGMAC_STAT("tx_vlan_packets", tx_vlan_packets), + XLGMAC_STAT("rx_vlan_packets", rx_vlan_packets), + XLGMAC_STAT("napi_poll_isr", napi_poll_isr), + XLGMAC_STAT("napi_poll_txtimer", napi_poll_txtimer), +}; + +#define XLGMAC_STATS_COUNT ARRAY_SIZE(xlgmac_gstring_stats) + +static void xlgmac_ethtool_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + u32 ver = pdata->hw_feat.version; + u32 snpsver, devid, userver; + + strlcpy(drvinfo->driver, pdata->drv_name, sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, pdata->drv_ver, sizeof(drvinfo->version)); + strlcpy(drvinfo->bus_info, dev_name(pdata->dev), + sizeof(drvinfo->bus_info)); + /* S|SNPSVER: Synopsys-defined Version + * D|DEVID: Indicates the Device family + * U|USERVER: User-defined Version + */ + snpsver = XLGMAC_GET_REG_BITS(ver, MAC_VR_SNPSVER_POS, + MAC_VR_SNPSVER_LEN); + devid = XLGMAC_GET_REG_BITS(ver, MAC_VR_DEVID_POS, + MAC_VR_DEVID_LEN); + userver = XLGMAC_GET_REG_BITS(ver, MAC_VR_USERVER_POS, + MAC_VR_USERVER_LEN); + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "S.D.U: %x.%x.%x", snpsver, devid, userver); +} + +static u32 xlgmac_ethtool_get_msglevel(struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + + return pdata->msg_enable; +} + +static void xlgmac_ethtool_set_msglevel(struct net_device *netdev, + u32 msglevel) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + + pdata->msg_enable = msglevel; +} + +static void xlgmac_ethtool_get_channels(struct net_device *netdev, + struct ethtool_channels *channel) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + + channel->max_rx = XLGMAC_MAX_DMA_CHANNELS; + channel->max_tx = XLGMAC_MAX_DMA_CHANNELS; + channel->rx_count = pdata->rx_q_count; + channel->tx_count = pdata->tx_q_count; +} + +static int xlgmac_ethtool_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + + memset(ec, 0, sizeof(struct ethtool_coalesce)); + ec->rx_coalesce_usecs = pdata->rx_usecs; + ec->rx_max_coalesced_frames = pdata->rx_frames; + ec->tx_max_coalesced_frames = pdata->tx_frames; + + return 0; +} + +static int xlgmac_ethtool_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + unsigned int rx_frames, rx_riwt, rx_usecs; + unsigned int tx_frames; + + /* Check for not supported parameters */ + if ((ec->rx_coalesce_usecs_irq) || (ec->rx_max_coalesced_frames_irq) || + (ec->tx_coalesce_usecs) || (ec->tx_coalesce_usecs_high) || + (ec->tx_max_coalesced_frames_irq) || (ec->tx_coalesce_usecs_irq) || + (ec->stats_block_coalesce_usecs) || (ec->pkt_rate_low) || + (ec->use_adaptive_rx_coalesce) || (ec->use_adaptive_tx_coalesce) || + (ec->rx_max_coalesced_frames_low) || (ec->rx_coalesce_usecs_low) || + (ec->tx_coalesce_usecs_low) || (ec->tx_max_coalesced_frames_low) || + (ec->pkt_rate_high) || (ec->rx_coalesce_usecs_high) || + (ec->rx_max_coalesced_frames_high) || + (ec->tx_max_coalesced_frames_high) || + (ec->rate_sample_interval)) + return -EOPNOTSUPP; + + rx_usecs = ec->rx_coalesce_usecs; + rx_riwt = hw_ops->usec_to_riwt(pdata, rx_usecs); + rx_frames = ec->rx_max_coalesced_frames; + tx_frames = ec->tx_max_coalesced_frames; + + if ((rx_riwt > XLGMAC_MAX_DMA_RIWT) || + (rx_riwt < XLGMAC_MIN_DMA_RIWT) || + (rx_frames > pdata->rx_desc_count)) + return -EINVAL; + + if (tx_frames > pdata->tx_desc_count) + return -EINVAL; + + pdata->rx_riwt = rx_riwt; + pdata->rx_usecs = rx_usecs; + pdata->rx_frames = rx_frames; + hw_ops->config_rx_coalesce(pdata); + + pdata->tx_frames = tx_frames; + hw_ops->config_tx_coalesce(pdata); + + return 0; +} + +static void xlgmac_ethtool_get_strings(struct net_device *netdev, + u32 stringset, u8 *data) +{ + int i; + + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < XLGMAC_STATS_COUNT; i++) { + memcpy(data, xlgmac_gstring_stats[i].stat_string, + ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } + break; + default: + WARN_ON(1); + break; + } +} + +static int xlgmac_ethtool_get_sset_count(struct net_device *netdev, + int stringset) +{ + int ret; + + switch (stringset) { + case ETH_SS_STATS: + ret = XLGMAC_STATS_COUNT; + break; + + default: + ret = -EOPNOTSUPP; + } + + return ret; +} + +static void xlgmac_ethtool_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, + u64 *data) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + u8 *stat; + int i; + + pdata->hw_ops.read_mmc_stats(pdata); + for (i = 0; i < XLGMAC_STATS_COUNT; i++) { + stat = (u8 *)pdata + xlgmac_gstring_stats[i].stat_offset; + *data++ = *(u64 *)stat; + } +} + +static const struct ethtool_ops xlgmac_ethtool_ops = { + .get_drvinfo = xlgmac_ethtool_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_msglevel = xlgmac_ethtool_get_msglevel, + .set_msglevel = xlgmac_ethtool_set_msglevel, + .get_channels = xlgmac_ethtool_get_channels, + .get_coalesce = xlgmac_ethtool_get_coalesce, + .set_coalesce = xlgmac_ethtool_set_coalesce, + .get_strings = xlgmac_ethtool_get_strings, + .get_sset_count = xlgmac_ethtool_get_sset_count, + .get_ethtool_stats = xlgmac_ethtool_get_ethtool_stats, +}; + +const struct ethtool_ops *xlgmac_get_ethtool_ops(void) +{ + return &xlgmac_ethtool_ops; +} diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c index 0dec1dcf8457..458a7844260a 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c @@ -835,12 +835,14 @@ static void xlgmac_dev_xmit(struct xlgmac_channel *channel) desc_data->skb_dma_len); /* VLAN tag insertion check */ - if (vlan) + if (vlan) { dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( dma_desc->desc2, TX_NORMAL_DESC2_VTIR_POS, TX_NORMAL_DESC2_VTIR_LEN, TX_NORMAL_DESC2_VLAN_INSERT); + pdata->stats.tx_vlan_packets++; + } /* Timestamp enablement check */ if (XLGMAC_GET_REG_BITS(pkt_info->attributes, diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c index 6acf86ced61d..3b91257683bc 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c @@ -290,19 +290,34 @@ static irqreturn_t xlgmac_isr(int irq, void *data) /* Disable Tx and Rx interrupts */ xlgmac_disable_rx_tx_ints(pdata); + pdata->stats.napi_poll_isr++; /* Turn on polling */ __napi_schedule_irqoff(&pdata->napi); } } + if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_TPS_POS, + DMA_CH_SR_TPS_LEN)) + pdata->stats.tx_process_stopped++; + + if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RPS_POS, + DMA_CH_SR_RPS_LEN)) + pdata->stats.rx_process_stopped++; + + if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_TBU_POS, + DMA_CH_SR_TBU_LEN)) + pdata->stats.tx_buffer_unavailable++; + if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RBU_POS, DMA_CH_SR_RBU_LEN)) pdata->stats.rx_buffer_unavailable++; /* Restart the device on a Fatal Bus Error */ if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_FBE_POS, - DMA_CH_SR_FBE_LEN)) + DMA_CH_SR_FBE_LEN)) { + pdata->stats.fatal_bus_error++; schedule_work(&pdata->restart_work); + } /* Clear all interrupt signals */ writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_SR)); @@ -357,6 +372,7 @@ static void xlgmac_tx_timer(unsigned long data) else xlgmac_disable_rx_tx_ints(pdata); + pdata->stats.napi_poll_txtimer++; /* Turn on polling */ __napi_schedule(napi); } @@ -1225,9 +1241,11 @@ read_again: if (XLGMAC_GET_REG_BITS(pkt_info->attributes, RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS, - RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN)) + RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN)) { __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), pkt_info->vlan_ctag); + pdata->stats.rx_vlan_packets++; + } if (XLGMAC_GET_REG_BITS(pkt_info->attributes, RX_PACKET_ATTRIBUTES_RSS_HASH_POS, diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac.h b/drivers/net/ethernet/synopsys/dwc-xlgmac.h index 676b2fb8dfcc..cab3e40a86b9 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac.h +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac.h @@ -67,6 +67,8 @@ #define XLGMAC_INIT_DMA_TX_FRAMES 25 #define XLGMAC_INIT_DMA_RX_USECS 30 #define XLGMAC_INIT_DMA_RX_FRAMES 25 +#define XLGMAC_MAX_DMA_RIWT 0xff +#define XLGMAC_MIN_DMA_RIWT 0x01 /* Flow control queue count */ #define XLGMAC_MAX_FLOW_CONTROL_QUEUES 8 @@ -190,7 +192,15 @@ struct xlgmac_stats { /* Extra counters */ u64 tx_tso_packets; u64 rx_split_header_packets; + u64 tx_process_stopped; + u64 rx_process_stopped; + u64 tx_buffer_unavailable; u64 rx_buffer_unavailable; + u64 fatal_bus_error; + u64 tx_vlan_packets; + u64 rx_vlan_packets; + u64 napi_poll_isr; + u64 napi_poll_txtimer; }; struct xlgmac_ring_buf { @@ -622,6 +632,7 @@ struct xlgmac_pdata { void xlgmac_init_desc_ops(struct xlgmac_desc_ops *desc_ops); void xlgmac_init_hw_ops(struct xlgmac_hw_ops *hw_ops); const struct net_device_ops *xlgmac_get_netdev_ops(void); +const struct ethtool_ops *xlgmac_get_ethtool_ops(void); void xlgmac_dump_tx_desc(struct xlgmac_pdata *pdata, struct xlgmac_ring *ring, unsigned int idx, diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 9f3d9c67e3fe..fa674a8bda0c 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1267,6 +1267,7 @@ static void soft_reset_slave(struct cpsw_slave *slave) static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) { u32 slave_port; + struct phy_device *phy; struct cpsw_common *cpsw = priv->cpsw; soft_reset_slave(slave); @@ -1300,27 +1301,28 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) 1 << slave_port, 0, 0, ALE_MCAST_FWD_2); if (slave->data->phy_node) { - slave->phy = of_phy_connect(priv->ndev, slave->data->phy_node, + phy = of_phy_connect(priv->ndev, slave->data->phy_node, &cpsw_adjust_link, 0, slave->data->phy_if); - if (!slave->phy) { + if (!phy) { dev_err(priv->dev, "phy \"%s\" not found on slave %d\n", slave->data->phy_node->full_name, slave->slave_num); return; } } else { - slave->phy = phy_connect(priv->ndev, slave->data->phy_id, + phy = phy_connect(priv->ndev, slave->data->phy_id, &cpsw_adjust_link, slave->data->phy_if); - if (IS_ERR(slave->phy)) { + if (IS_ERR(phy)) { dev_err(priv->dev, "phy \"%s\" not found on slave %d, err %ld\n", slave->data->phy_id, slave->slave_num, - PTR_ERR(slave->phy)); - slave->phy = NULL; + PTR_ERR(phy)); return; } } + slave->phy = phy; + phy_attached_info(slave->phy); phy_start(slave->phy); @@ -1817,6 +1819,8 @@ static void cpsw_ndo_tx_timeout(struct net_device *ndev) } cpsw_intr_enable(cpsw); + netif_trans_update(ndev); + netif_tx_wake_all_queues(ndev); } static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p) diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c index f90267f0519f..2bdfb39215e9 100644 --- a/drivers/net/ethernet/wiznet/w5100.c +++ b/drivers/net/ethernet/wiznet/w5100.c @@ -1152,7 +1152,8 @@ int w5100_probe(struct device *dev, const struct w5100_ops *ops, if (err < 0) goto err_register; - priv->xfer_wq = alloc_workqueue(netdev_name(ndev), WQ_MEM_RECLAIM, 0); + priv->xfer_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, + netdev_name(ndev)); if (!priv->xfer_wq) { err = -ENOMEM; goto err_wq; |