diff options
55 files changed, 516 insertions, 256 deletions
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index b44a6aeb346d..e5386ab706ec 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -90,10 +90,13 @@ enum ad_link_speed_type { AD_LINK_SPEED_100MBPS, AD_LINK_SPEED_1000MBPS, AD_LINK_SPEED_2500MBPS, + AD_LINK_SPEED_5000MBPS, AD_LINK_SPEED_10000MBPS, + AD_LINK_SPEED_14000MBPS, AD_LINK_SPEED_20000MBPS, AD_LINK_SPEED_25000MBPS, AD_LINK_SPEED_40000MBPS, + AD_LINK_SPEED_50000MBPS, AD_LINK_SPEED_56000MBPS, AD_LINK_SPEED_100000MBPS, }; @@ -259,10 +262,13 @@ static inline int __check_agg_selection_timer(struct port *port) * %AD_LINK_SPEED_100MBPS, * %AD_LINK_SPEED_1000MBPS, * %AD_LINK_SPEED_2500MBPS, + * %AD_LINK_SPEED_5000MBPS, * %AD_LINK_SPEED_10000MBPS + * %AD_LINK_SPEED_14000MBPS, * %AD_LINK_SPEED_20000MBPS * %AD_LINK_SPEED_25000MBPS * %AD_LINK_SPEED_40000MBPS + * %AD_LINK_SPEED_50000MBPS * %AD_LINK_SPEED_56000MBPS * %AD_LINK_SPEED_100000MBPS */ @@ -296,10 +302,18 @@ static u16 __get_link_speed(struct port *port) speed = AD_LINK_SPEED_2500MBPS; break; + case SPEED_5000: + speed = AD_LINK_SPEED_5000MBPS; + break; + case SPEED_10000: speed = AD_LINK_SPEED_10000MBPS; break; + case SPEED_14000: + speed = AD_LINK_SPEED_14000MBPS; + break; + case SPEED_20000: speed = AD_LINK_SPEED_20000MBPS; break; @@ -312,6 +326,10 @@ static u16 __get_link_speed(struct port *port) speed = AD_LINK_SPEED_40000MBPS; break; + case SPEED_50000: + speed = AD_LINK_SPEED_50000MBPS; + break; + case SPEED_56000: speed = AD_LINK_SPEED_56000MBPS; break; @@ -707,9 +725,15 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator) case AD_LINK_SPEED_2500MBPS: bandwidth = nports * 2500; break; + case AD_LINK_SPEED_5000MBPS: + bandwidth = nports * 5000; + break; case AD_LINK_SPEED_10000MBPS: bandwidth = nports * 10000; break; + case AD_LINK_SPEED_14000MBPS: + bandwidth = nports * 14000; + break; case AD_LINK_SPEED_20000MBPS: bandwidth = nports * 20000; break; @@ -719,6 +743,9 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator) case AD_LINK_SPEED_40000MBPS: bandwidth = nports * 40000; break; + case AD_LINK_SPEED_50000MBPS: + bandwidth = nports * 50000; + break; case AD_LINK_SPEED_56000MBPS: bandwidth = nports * 56000; break; diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 611d16a7061d..ae4ed03dc642 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -391,6 +391,9 @@ void can_change_state(struct net_device *dev, struct can_frame *cf, can_update_state_error_stats(dev, new_state); priv->state = new_state; + if (!cf) + return; + if (unlikely(new_state == CAN_STATE_BUS_OFF)) { cf->can_id |= CAN_ERR_BUSOFF; return; diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c index 0d57be5ea97b..85268be0c913 100644 --- a/drivers/net/can/peak_canfd/peak_canfd.c +++ b/drivers/net/can/peak_canfd/peak_canfd.c @@ -489,7 +489,7 @@ int peak_canfd_handle_msgs_list(struct peak_canfd_priv *priv, struct pucan_rx_msg *msg_list, int msg_count) { void *msg_ptr = msg_list; - int i, msg_size; + int i, msg_size = 0; for (i = 0; i < msg_count; i++) { msg_size = peak_canfd_handle_msg(priv, msg_ptr); diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index eecee7f8dfb7..afcc1312dbaf 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -265,6 +265,8 @@ static int gs_cmd_reset(struct gs_usb *gsusb, struct gs_can *gsdev) sizeof(*dm), 1000); + kfree(dm); + return rc; } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 57913dbbae0a..1ca76e03e965 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -908,8 +908,6 @@ static int peak_usb_probe(struct usb_interface *intf, const struct peak_usb_adapter *peak_usb_adapter = NULL; int i, err = -ENOMEM; - usb_dev = interface_to_usbdev(intf); - /* get corresponding PCAN-USB adapter */ for (i = 0; i < ARRAY_SIZE(peak_usb_adapters_list); i++) if (peak_usb_adapters_list[i]->device_id == usb_id_product) { @@ -920,7 +918,7 @@ static int peak_usb_probe(struct usb_interface *intf, if (!peak_usb_adapter) { /* should never come except device_id bad usage in this file */ pr_err("%s: didn't find device id. 0x%x in devices list\n", - PCAN_USB_DRIVER_NAME, usb_dev->descriptor.idProduct); + PCAN_USB_DRIVER_NAME, usb_id_product); return -ENODEV; } diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index 0eda1b308583..a8cb33264ff1 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -152,7 +152,7 @@ static const struct net_device_ops vcan_netdev_ops = { static void vcan_setup(struct net_device *dev) { dev->type = ARPHRD_CAN; - dev->mtu = CAN_MTU; + dev->mtu = CANFD_MTU; dev->hard_header_len = 0; dev->addr_len = 0; dev->tx_queue_len = 0; diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index 30cf2368becf..cfe889e8f172 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -150,7 +150,7 @@ static const struct net_device_ops vxcan_netdev_ops = { static void vxcan_setup(struct net_device *dev) { dev->type = ARPHRD_CAN; - dev->mtu = CAN_MTU; + dev->mtu = CANFD_MTU; dev->hard_header_len = 0; dev->addr_len = 0; dev->tx_queue_len = 0; diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 08d11cede9c9..f5b237e0bd60 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -61,6 +61,8 @@ #define ENA_MMIO_READ_TIMEOUT 0xFFFFFFFF +#define ENA_REGS_ADMIN_INTR_MASK 1 + /*****************************************************************************/ /*****************************************************************************/ /*****************************************************************************/ @@ -232,11 +234,9 @@ static struct ena_comp_ctx *__ena_com_submit_admin_cmd(struct ena_com_admin_queu tail_masked = admin_queue->sq.tail & queue_size_mask; /* In case of queue FULL */ - cnt = admin_queue->sq.tail - admin_queue->sq.head; + cnt = atomic_read(&admin_queue->outstanding_cmds); if (cnt >= admin_queue->q_depth) { - pr_debug("admin queue is FULL (tail %d head %d depth: %d)\n", - admin_queue->sq.tail, admin_queue->sq.head, - admin_queue->q_depth); + pr_debug("admin queue is full.\n"); admin_queue->stats.out_of_space++; return ERR_PTR(-ENOSPC); } @@ -508,15 +508,20 @@ static int ena_com_comp_status_to_errno(u8 comp_status) static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_ctx, struct ena_com_admin_queue *admin_queue) { - unsigned long flags; - u32 start_time; + unsigned long flags, timeout; int ret; - start_time = ((u32)jiffies_to_usecs(jiffies)); + timeout = jiffies + ADMIN_CMD_TIMEOUT_US; + + while (1) { + spin_lock_irqsave(&admin_queue->q_lock, flags); + ena_com_handle_admin_completion(admin_queue); + spin_unlock_irqrestore(&admin_queue->q_lock, flags); + + if (comp_ctx->status != ENA_CMD_SUBMITTED) + break; - while (comp_ctx->status == ENA_CMD_SUBMITTED) { - if ((((u32)jiffies_to_usecs(jiffies)) - start_time) > - ADMIN_CMD_TIMEOUT_US) { + if (time_is_before_jiffies(timeout)) { pr_err("Wait for completion (polling) timeout\n"); /* ENA didn't have any completion */ spin_lock_irqsave(&admin_queue->q_lock, flags); @@ -528,10 +533,6 @@ static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_c goto err; } - spin_lock_irqsave(&admin_queue->q_lock, flags); - ena_com_handle_admin_completion(admin_queue); - spin_unlock_irqrestore(&admin_queue->q_lock, flags); - msleep(100); } @@ -1455,6 +1456,12 @@ void ena_com_admin_destroy(struct ena_com_dev *ena_dev) void ena_com_set_admin_polling_mode(struct ena_com_dev *ena_dev, bool polling) { + u32 mask_value = 0; + + if (polling) + mask_value = ENA_REGS_ADMIN_INTR_MASK; + + writel(mask_value, ena_dev->reg_bar + ENA_REGS_INTR_MASK_OFF); ena_dev->admin_queue.polling = polling; } diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index 67b2338f8fb3..3ee55e2fd694 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -80,7 +80,6 @@ static const struct ena_stats ena_stats_tx_strings[] = { ENA_STAT_TX_ENTRY(tx_poll), ENA_STAT_TX_ENTRY(doorbells), ENA_STAT_TX_ENTRY(prepare_ctx_err), - ENA_STAT_TX_ENTRY(missing_tx_comp), ENA_STAT_TX_ENTRY(bad_req_id), }; @@ -94,6 +93,7 @@ static const struct ena_stats ena_stats_rx_strings[] = { ENA_STAT_RX_ENTRY(dma_mapping_err), ENA_STAT_RX_ENTRY(bad_desc_num), ENA_STAT_RX_ENTRY(rx_copybreak_pkt), + ENA_STAT_RX_ENTRY(empty_rx_ring), }; static const struct ena_stats ena_stats_ena_com_strings[] = { diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 7c1214d78855..4f16ed38bcf3 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -190,6 +190,7 @@ static void ena_init_io_rings(struct ena_adapter *adapter) rxr->sgl_size = adapter->max_rx_sgl_size; rxr->smoothed_interval = ena_com_get_nonadaptive_moderation_interval_rx(ena_dev); + rxr->empty_rx_queue = 0; } } @@ -1078,6 +1079,26 @@ inline void ena_adjust_intr_moderation(struct ena_ring *rx_ring, rx_ring->per_napi_bytes = 0; } +static inline void ena_unmask_interrupt(struct ena_ring *tx_ring, + struct ena_ring *rx_ring) +{ + struct ena_eth_io_intr_reg intr_reg; + + /* Update intr register: rx intr delay, + * tx intr delay and interrupt unmask + */ + ena_com_update_intr_reg(&intr_reg, + rx_ring->smoothed_interval, + tx_ring->smoothed_interval, + true); + + /* It is a shared MSI-X. + * Tx and Rx CQ have pointer to it. + * So we use one of them to reach the intr reg + */ + ena_com_unmask_intr(rx_ring->ena_com_io_cq, &intr_reg); +} + static inline void ena_update_ring_numa_node(struct ena_ring *tx_ring, struct ena_ring *rx_ring) { @@ -1108,7 +1129,6 @@ static int ena_io_poll(struct napi_struct *napi, int budget) { struct ena_napi *ena_napi = container_of(napi, struct ena_napi, napi); struct ena_ring *tx_ring, *rx_ring; - struct ena_eth_io_intr_reg intr_reg; u32 tx_work_done; u32 rx_work_done; @@ -1149,22 +1169,9 @@ static int ena_io_poll(struct napi_struct *napi, int budget) if (ena_com_get_adaptive_moderation_enabled(rx_ring->ena_dev)) ena_adjust_intr_moderation(rx_ring, tx_ring); - /* Update intr register: rx intr delay, - * tx intr delay and interrupt unmask - */ - ena_com_update_intr_reg(&intr_reg, - rx_ring->smoothed_interval, - tx_ring->smoothed_interval, - true); - - /* It is a shared MSI-X. - * Tx and Rx CQ have pointer to it. - * So we use one of them to reach the intr reg - */ - ena_com_unmask_intr(rx_ring->ena_com_io_cq, &intr_reg); + ena_unmask_interrupt(tx_ring, rx_ring); } - ena_update_ring_numa_node(tx_ring, rx_ring); ret = rx_work_done; @@ -1485,6 +1492,11 @@ static int ena_up_complete(struct ena_adapter *adapter) ena_napi_enable_all(adapter); + /* Enable completion queues interrupt */ + for (i = 0; i < adapter->num_queues; i++) + ena_unmask_interrupt(&adapter->tx_ring[i], + &adapter->rx_ring[i]); + /* schedule napi in case we had pending packets * from the last time we disable napi */ @@ -1532,6 +1544,7 @@ static int ena_create_io_tx_queue(struct ena_adapter *adapter, int qid) "Failed to get TX queue handlers. TX queue num %d rc: %d\n", qid, rc); ena_com_destroy_io_queue(ena_dev, ena_qid); + return rc; } ena_com_update_numa_node(tx_ring->ena_com_io_cq, ctx.numa_node); @@ -1596,6 +1609,7 @@ static int ena_create_io_rx_queue(struct ena_adapter *adapter, int qid) "Failed to get RX queue handlers. RX queue num %d rc: %d\n", qid, rc); ena_com_destroy_io_queue(ena_dev, ena_qid); + return rc; } ena_com_update_numa_node(rx_ring->ena_com_io_cq, ctx.numa_node); @@ -1981,6 +1995,7 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_info->tx_descs = nb_hw_desc; tx_info->last_jiffies = jiffies; + tx_info->print_once = 0; tx_ring->next_to_use = ENA_TX_RING_IDX_NEXT(next_to_use, tx_ring->ring_size); @@ -2550,13 +2565,44 @@ err: "Reset attempt failed. Can not reset the device\n"); } -static void check_for_missing_tx_completions(struct ena_adapter *adapter) +static int check_missing_comp_in_queue(struct ena_adapter *adapter, + struct ena_ring *tx_ring) { struct ena_tx_buffer *tx_buf; unsigned long last_jiffies; + u32 missed_tx = 0; + int i; + + for (i = 0; i < tx_ring->ring_size; i++) { + tx_buf = &tx_ring->tx_buffer_info[i]; + last_jiffies = tx_buf->last_jiffies; + if (unlikely(last_jiffies && + time_is_before_jiffies(last_jiffies + TX_TIMEOUT))) { + if (!tx_buf->print_once) + netif_notice(adapter, tx_err, adapter->netdev, + "Found a Tx that wasn't completed on time, qid %d, index %d.\n", + tx_ring->qid, i); + + tx_buf->print_once = 1; + missed_tx++; + + if (unlikely(missed_tx > MAX_NUM_OF_TIMEOUTED_PACKETS)) { + netif_err(adapter, tx_err, adapter->netdev, + "The number of lost tx completions is above the threshold (%d > %d). Reset the device\n", + missed_tx, MAX_NUM_OF_TIMEOUTED_PACKETS); + set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + return -EIO; + } + } + } + + return 0; +} + +static void check_for_missing_tx_completions(struct ena_adapter *adapter) +{ struct ena_ring *tx_ring; - int i, j, budget; - u32 missed_tx; + int i, budget, rc; /* Make sure the driver doesn't turn the device in other process */ smp_rmb(); @@ -2572,31 +2618,9 @@ static void check_for_missing_tx_completions(struct ena_adapter *adapter) for (i = adapter->last_monitored_tx_qid; i < adapter->num_queues; i++) { tx_ring = &adapter->tx_ring[i]; - for (j = 0; j < tx_ring->ring_size; j++) { - tx_buf = &tx_ring->tx_buffer_info[j]; - last_jiffies = tx_buf->last_jiffies; - if (unlikely(last_jiffies && time_is_before_jiffies(last_jiffies + TX_TIMEOUT))) { - netif_notice(adapter, tx_err, adapter->netdev, - "Found a Tx that wasn't completed on time, qid %d, index %d.\n", - tx_ring->qid, j); - - u64_stats_update_begin(&tx_ring->syncp); - missed_tx = tx_ring->tx_stats.missing_tx_comp++; - u64_stats_update_end(&tx_ring->syncp); - - /* Clear last jiffies so the lost buffer won't - * be counted twice. - */ - tx_buf->last_jiffies = 0; - - if (unlikely(missed_tx > MAX_NUM_OF_TIMEOUTED_PACKETS)) { - netif_err(adapter, tx_err, adapter->netdev, - "The number of lost tx completion is above the threshold (%d > %d). Reset the device\n", - missed_tx, MAX_NUM_OF_TIMEOUTED_PACKETS); - set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); - } - } - } + rc = check_missing_comp_in_queue(adapter, tx_ring); + if (unlikely(rc)) + return; budget--; if (!budget) @@ -2606,6 +2630,58 @@ static void check_for_missing_tx_completions(struct ena_adapter *adapter) adapter->last_monitored_tx_qid = i % adapter->num_queues; } +/* trigger napi schedule after 2 consecutive detections */ +#define EMPTY_RX_REFILL 2 +/* For the rare case where the device runs out of Rx descriptors and the + * napi handler failed to refill new Rx descriptors (due to a lack of memory + * for example). + * This case will lead to a deadlock: + * The device won't send interrupts since all the new Rx packets will be dropped + * The napi handler won't allocate new Rx descriptors so the device will be + * able to send new packets. + * + * This scenario can happen when the kernel's vm.min_free_kbytes is too small. + * It is recommended to have at least 512MB, with a minimum of 128MB for + * constrained environment). + * + * When such a situation is detected - Reschedule napi + */ +static void check_for_empty_rx_ring(struct ena_adapter *adapter) +{ + struct ena_ring *rx_ring; + int i, refill_required; + + if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags)) + return; + + if (test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags)) + return; + + for (i = 0; i < adapter->num_queues; i++) { + rx_ring = &adapter->rx_ring[i]; + + refill_required = + ena_com_sq_empty_space(rx_ring->ena_com_io_sq); + if (unlikely(refill_required == (rx_ring->ring_size - 1))) { + rx_ring->empty_rx_queue++; + + if (rx_ring->empty_rx_queue >= EMPTY_RX_REFILL) { + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->rx_stats.empty_rx_ring++; + u64_stats_update_end(&rx_ring->syncp); + + netif_err(adapter, drv, adapter->netdev, + "trigger refill for ring %d\n", i); + + napi_schedule(rx_ring->napi); + rx_ring->empty_rx_queue = 0; + } + } else { + rx_ring->empty_rx_queue = 0; + } + } +} + /* Check for keep alive expiration */ static void check_for_missing_keep_alive(struct ena_adapter *adapter) { @@ -2660,6 +2736,8 @@ static void ena_timer_service(unsigned long data) check_for_missing_tx_completions(adapter); + check_for_empty_rx_ring(adapter); + if (debug_area) ena_dump_stats_to_buf(adapter, debug_area); @@ -2840,6 +2918,11 @@ static void ena_release_bars(struct ena_com_dev *ena_dev, struct pci_dev *pdev) { int release_bars; + if (ena_dev->mem_bar) + devm_iounmap(&pdev->dev, ena_dev->mem_bar); + + devm_iounmap(&pdev->dev, ena_dev->reg_bar); + release_bars = pci_select_bars(pdev, IORESOURCE_MEM) & ENA_BAR_MASK; pci_release_selected_regions(pdev, release_bars); } @@ -2927,8 +3010,9 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_free_ena_dev; } - ena_dev->reg_bar = ioremap(pci_resource_start(pdev, ENA_REG_BAR), - pci_resource_len(pdev, ENA_REG_BAR)); + ena_dev->reg_bar = devm_ioremap(&pdev->dev, + pci_resource_start(pdev, ENA_REG_BAR), + pci_resource_len(pdev, ENA_REG_BAR)); if (!ena_dev->reg_bar) { dev_err(&pdev->dev, "failed to remap regs bar\n"); rc = -EFAULT; @@ -2948,8 +3032,9 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ena_set_push_mode(pdev, ena_dev, &get_feat_ctx); if (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) { - ena_dev->mem_bar = ioremap_wc(pci_resource_start(pdev, ENA_MEM_BAR), - pci_resource_len(pdev, ENA_MEM_BAR)); + ena_dev->mem_bar = devm_ioremap_wc(&pdev->dev, + pci_resource_start(pdev, ENA_MEM_BAR), + pci_resource_len(pdev, ENA_MEM_BAR)); if (!ena_dev->mem_bar) { rc = -EFAULT; goto err_device_destroy; diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index 0e22bce6239d..a4d3d5e21068 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -45,7 +45,7 @@ #define DRV_MODULE_VER_MAJOR 1 #define DRV_MODULE_VER_MINOR 1 -#define DRV_MODULE_VER_SUBMINOR 2 +#define DRV_MODULE_VER_SUBMINOR 7 #define DRV_MODULE_NAME "ena" #ifndef DRV_MODULE_VERSION @@ -146,7 +146,18 @@ struct ena_tx_buffer { u32 tx_descs; /* num of buffers used by this skb */ u32 num_of_bufs; - /* Save the last jiffies to detect missing tx packets */ + + /* Used for detect missing tx packets to limit the number of prints */ + u32 print_once; + /* Save the last jiffies to detect missing tx packets + * + * sets to non zero value on ena_start_xmit and set to zero on + * napi and timer_Service_routine. + * + * while this value is not protected by lock, + * a given packet is not expected to be handled by ena_start_xmit + * and by napi/timer_service at the same time. + */ unsigned long last_jiffies; struct ena_com_buf bufs[ENA_PKT_MAX_BUFS]; } ____cacheline_aligned; @@ -170,7 +181,6 @@ struct ena_stats_tx { u64 napi_comp; u64 tx_poll; u64 doorbells; - u64 missing_tx_comp; u64 bad_req_id; }; @@ -184,6 +194,7 @@ struct ena_stats_rx { u64 dma_mapping_err; u64 bad_desc_num; u64 rx_copybreak_pkt; + u64 empty_rx_ring; }; struct ena_ring { @@ -231,6 +242,7 @@ struct ena_ring { struct ena_stats_tx tx_stats; struct ena_stats_rx rx_stats; }; + int empty_rx_queue; } ____cacheline_aligned; struct ena_stats_dev { diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h index b8e3d88f0879..a66aee51ab5b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h @@ -193,9 +193,6 @@ int hw_atl_utils_hw_get_regs(struct aq_hw_s *self, struct aq_hw_caps_s *aq_hw_caps, u32 *regs_buff); -int hw_atl_utils_hw_get_settings(struct aq_hw_s *self, - struct ethtool_cmd *cmd); - int hw_atl_utils_hw_set_power(struct aq_hw_s *self, unsigned int power_state); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 5f49334dcad5..f619c4cac51f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3883,15 +3883,26 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) /* when transmitting in a vf, start bd must hold the ethertype * for fw to enforce it */ + u16 vlan_tci = 0; #ifndef BNX2X_STOP_ON_ERROR - if (IS_VF(bp)) + if (IS_VF(bp)) { #endif - tx_start_bd->vlan_or_ethertype = - cpu_to_le16(ntohs(eth->h_proto)); + /* Still need to consider inband vlan for enforced */ + if (__vlan_get_tag(skb, &vlan_tci)) { + tx_start_bd->vlan_or_ethertype = + cpu_to_le16(ntohs(eth->h_proto)); + } else { + tx_start_bd->bd_flags.as_bitfield |= + (X_ETH_INBAND_VLAN << + ETH_TX_BD_FLAGS_VLAN_MODE_SHIFT); + tx_start_bd->vlan_or_ethertype = + cpu_to_le16(vlan_tci); + } #ifndef BNX2X_STOP_ON_ERROR - else + } else { /* used by FW for packet accounting */ tx_start_bd->vlan_or_ethertype = cpu_to_le16(pkt_prod); + } #endif } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 870ea001a720..9ca994d0bab6 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -901,6 +901,8 @@ static void bnx2x_vf_flr(struct bnx2x *bp, struct bnx2x_virtf *vf) /* release VF resources */ bnx2x_vf_free_resc(bp, vf); + vf->malicious = false; + /* re-open the mailbox */ bnx2x_vf_enable_mbx(bp, vf->abs_vfid); return; @@ -1822,9 +1824,11 @@ get_vf: vf->abs_vfid, qidx); bnx2x_vf_handle_rss_update_eqe(bp, vf); case EVENT_RING_OPCODE_VF_FLR: - case EVENT_RING_OPCODE_MALICIOUS_VF: /* Do nothing for now */ return 0; + case EVENT_RING_OPCODE_MALICIOUS_VF: + vf->malicious = true; + return 0; } return 0; @@ -1905,6 +1909,13 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp) continue; } + if (vf->malicious) { + DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS), + "vf %d malicious so no stats for it\n", + vf->abs_vfid); + continue; + } + DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS), "add addresses for vf %d\n", vf->abs_vfid); for_each_vfq(vf, j) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index 888d0b6632e8..53466f6cebab 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -141,6 +141,7 @@ struct bnx2x_virtf { #define VF_RESET 3 /* VF FLR'd, pending cleanup */ bool flr_clnup_stage; /* true during flr cleanup */ + bool malicious; /* true if FW indicated so, until FLR */ /* dma */ dma_addr_t fw_stat_map; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index cdde3cc28fb5..44d9610f7a15 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -399,6 +399,7 @@ struct i40e_pf { #define I40E_FLAG_RX_CSUM_ENABLED BIT_ULL(1) #define I40E_FLAG_MSI_ENABLED BIT_ULL(2) #define I40E_FLAG_MSIX_ENABLED BIT_ULL(3) +#define I40E_FLAG_HW_ATR_EVICT_ENABLED BIT_ULL(4) #define I40E_FLAG_RSS_ENABLED BIT_ULL(6) #define I40E_FLAG_VMDQ_ENABLED BIT_ULL(7) #define I40E_FLAG_IWARP_ENABLED BIT_ULL(10) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 7a8eb486b9ea..894c8e57ba00 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -224,7 +224,7 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { I40E_PRIV_FLAG("LinkPolling", I40E_FLAG_LINK_POLLING_ENABLED, 0), I40E_PRIV_FLAG("flow-director-atr", I40E_FLAG_FD_ATR_ENABLED, 0), I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENABLED, 0), - I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_CAPABLE, 0), + I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_ENABLED, 0), I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0), }; @@ -4092,7 +4092,7 @@ flags_complete: /* Only allow ATR evict on hardware that is capable of handling it */ if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) - pf->flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE; + pf->flags &= ~I40E_FLAG_HW_ATR_EVICT_ENABLED; if (changed_flags & I40E_FLAG_TRUE_PROMISC_SUPPORT) { u16 sw_flags = 0, valid_flags = 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 150caf6ca2b4..a7a4b28b4144 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -8821,11 +8821,12 @@ static int i40e_sw_init(struct i40e_pf *pf) (pf->hw.aq.api_min_ver > 4))) { /* Supported in FW API version higher than 1.4 */ pf->flags |= I40E_FLAG_GENEVE_OFFLOAD_CAPABLE; - pf->flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; - } else { - pf->flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; } + /* Enable HW ATR eviction if possible */ + if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) + pf->flags |= I40E_FLAG_HW_ATR_EVICT_ENABLED; + pf->eeprom_version = 0xDEAD; pf->lan_veb = I40E_NO_VEB; pf->lan_vsi = I40E_NO_VSI; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index cd894f4023b1..77115c25d96f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2341,7 +2341,7 @@ 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->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED)) return; - if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) { + if (pf->flags & I40E_FLAG_HW_ATR_EVICT_ENABLED) { /* HW ATR eviction will take care of removing filters on FIN * and RST packets. */ @@ -2403,7 +2403,7 @@ 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) + if (pf->flags & I40E_FLAG_HW_ATR_EVICT_ENABLED) dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK; fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype); diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 70bca2a6fb02..33c901622ed5 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -3719,7 +3719,7 @@ static void mvpp2_bm_bufs_get_addrs(struct device *dev, struct mvpp2 *priv, dma_addr_t *dma_addr, phys_addr_t *phys_addr) { - int cpu = smp_processor_id(); + int cpu = get_cpu(); *dma_addr = mvpp2_percpu_read(priv, cpu, MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); @@ -3740,6 +3740,8 @@ static void mvpp2_bm_bufs_get_addrs(struct device *dev, struct mvpp2 *priv, if (sizeof(phys_addr_t) == 8) *phys_addr |= (u64)phys_addr_highbits << 32; } + + put_cpu(); } /* Free all buffers from the pool */ @@ -3920,18 +3922,12 @@ static inline u32 mvpp2_bm_cookie_pool_set(u32 cookie, int pool) return bm; } -/* Get pool number from a BM cookie */ -static inline int mvpp2_bm_cookie_pool_get(unsigned long cookie) -{ - return (cookie >> MVPP2_BM_COOKIE_POOL_OFFS) & 0xFF; -} - /* Release buffer to BM */ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, dma_addr_t buf_dma_addr, phys_addr_t buf_phys_addr) { - int cpu = smp_processor_id(); + int cpu = get_cpu(); if (port->priv->hw_version == MVPP22) { u32 val = 0; @@ -3958,15 +3954,15 @@ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, MVPP2_BM_VIRT_RLS_REG, buf_phys_addr); mvpp2_percpu_write(port->priv, cpu, MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr); + + put_cpu(); } /* Refill BM pool */ -static void mvpp2_pool_refill(struct mvpp2_port *port, u32 bm, +static void mvpp2_pool_refill(struct mvpp2_port *port, int pool, dma_addr_t dma_addr, phys_addr_t phys_addr) { - int pool = mvpp2_bm_cookie_pool_get(bm); - mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); } @@ -4513,21 +4509,6 @@ static void mvpp2_rxq_offset_set(struct mvpp2_port *port, mvpp2_write(port->priv, MVPP2_RXQ_CONFIG_REG(prxq), val); } -/* Obtain BM cookie information from descriptor */ -static u32 mvpp2_bm_cookie_build(struct mvpp2_port *port, - struct mvpp2_rx_desc *rx_desc) -{ - int cpu = smp_processor_id(); - int pool; - - pool = (mvpp2_rxdesc_status_get(port, rx_desc) & - MVPP2_RXD_BM_POOL_ID_MASK) >> - MVPP2_RXD_BM_POOL_ID_OFFS; - - return ((pool & 0xFF) << MVPP2_BM_COOKIE_POOL_OFFS) | - ((cpu & 0xFF) << MVPP2_BM_COOKIE_CPU_OFFS); -} - /* Tx descriptors helper methods */ /* Get pointer to next Tx descriptor to be processed (send) by HW */ @@ -4755,7 +4736,7 @@ static void mvpp2_txp_max_tx_size_set(struct mvpp2_port *port) static void mvpp2_rx_pkts_coal_set(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq) { - int cpu = smp_processor_id(); + int cpu = get_cpu(); if (rxq->pkts_coal > MVPP2_OCCUPIED_THRESH_MASK) rxq->pkts_coal = MVPP2_OCCUPIED_THRESH_MASK; @@ -4763,6 +4744,8 @@ static void mvpp2_rx_pkts_coal_set(struct mvpp2_port *port, mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id); mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_THRESH_REG, rxq->pkts_coal); + + put_cpu(); } static u32 mvpp2_usec_to_cycles(u32 usec, unsigned long clk_hz) @@ -4943,7 +4926,7 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0); /* Set Rx descriptors queue starting address - indirect access */ - cpu = smp_processor_id(); + cpu = get_cpu(); mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id); if (port->priv->hw_version == MVPP21) rxq_dma = rxq->descs_dma; @@ -4952,6 +4935,7 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, rxq_dma); mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, rxq->size); mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_INDEX_REG, 0); + put_cpu(); /* Set Offset */ mvpp2_rxq_offset_set(port, rxq->id, NET_SKB_PAD); @@ -4978,9 +4962,13 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port, for (i = 0; i < rx_received; i++) { struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq); - u32 bm = mvpp2_bm_cookie_build(port, rx_desc); + u32 status = mvpp2_rxdesc_status_get(port, rx_desc); + int pool; + + pool = (status & MVPP2_RXD_BM_POOL_ID_MASK) >> + MVPP2_RXD_BM_POOL_ID_OFFS; - mvpp2_pool_refill(port, bm, + mvpp2_pool_refill(port, pool, mvpp2_rxdesc_dma_addr_get(port, rx_desc), mvpp2_rxdesc_cookie_get(port, rx_desc)); } @@ -5010,10 +4998,11 @@ static void mvpp2_rxq_deinit(struct mvpp2_port *port, * free descriptor number */ mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0); - cpu = smp_processor_id(); + cpu = get_cpu(); mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id); mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, 0); mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, 0); + put_cpu(); } /* Create and initialize a Tx queue */ @@ -5036,7 +5025,7 @@ static int mvpp2_txq_init(struct mvpp2_port *port, txq->last_desc = txq->size - 1; /* Set Tx descriptors queue starting address - indirect access */ - cpu = smp_processor_id(); + cpu = get_cpu(); mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG, txq->descs_dma); @@ -5061,6 +5050,7 @@ static int mvpp2_txq_init(struct mvpp2_port *port, mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, MVPP2_PREF_BUF_PTR(desc) | MVPP2_PREF_BUF_SIZE_16 | MVPP2_PREF_BUF_THRESH(desc_per_txq / 2)); + put_cpu(); /* WRR / EJP configuration - indirect access */ tx_port_num = mvpp2_egress_port(port); @@ -5131,10 +5121,11 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port, mvpp2_write(port->priv, MVPP2_TXQ_SCHED_TOKEN_CNTR_REG(txq->id), 0); /* Set Tx descriptors queue starting address and size */ - cpu = smp_processor_id(); + cpu = get_cpu(); mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG, 0); mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG, 0); + put_cpu(); } /* Cleanup Tx ports */ @@ -5144,7 +5135,7 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) int delay, pending, cpu; u32 val; - cpu = smp_processor_id(); + cpu = get_cpu(); mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG); val |= MVPP2_TXQ_DRAIN_EN_MASK; @@ -5171,6 +5162,7 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) val &= ~MVPP2_TXQ_DRAIN_EN_MASK; mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val); + put_cpu(); for_each_present_cpu(cpu) { txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); @@ -5418,7 +5410,7 @@ static void mvpp2_rx_csum(struct mvpp2_port *port, u32 status, /* Reuse skb if possible, or allocate a new skb and add it to BM pool */ static int mvpp2_rx_refill(struct mvpp2_port *port, - struct mvpp2_bm_pool *bm_pool, u32 bm) + struct mvpp2_bm_pool *bm_pool, int pool) { dma_addr_t dma_addr; phys_addr_t phys_addr; @@ -5430,7 +5422,7 @@ static int mvpp2_rx_refill(struct mvpp2_port *port, if (!buf) return -ENOMEM; - mvpp2_pool_refill(port, bm, dma_addr, phys_addr); + mvpp2_pool_refill(port, pool, dma_addr, phys_addr); return 0; } @@ -5488,7 +5480,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, unsigned int frag_size; dma_addr_t dma_addr; phys_addr_t phys_addr; - u32 bm, rx_status; + u32 rx_status; int pool, rx_bytes, err; void *data; @@ -5500,8 +5492,8 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, phys_addr = mvpp2_rxdesc_cookie_get(port, rx_desc); data = (void *)phys_to_virt(phys_addr); - bm = mvpp2_bm_cookie_build(port, rx_desc); - pool = mvpp2_bm_cookie_pool_get(bm); + pool = (rx_status & MVPP2_RXD_BM_POOL_ID_MASK) >> + MVPP2_RXD_BM_POOL_ID_OFFS; bm_pool = &port->priv->bm_pools[pool]; /* In case of an error, release the requested buffer pointer @@ -5514,7 +5506,7 @@ err_drop_frame: dev->stats.rx_errors++; mvpp2_rx_error(port, rx_desc); /* Return the buffer to the pool */ - mvpp2_pool_refill(port, bm, dma_addr, phys_addr); + mvpp2_pool_refill(port, pool, dma_addr, phys_addr); continue; } @@ -5529,7 +5521,7 @@ err_drop_frame: goto err_drop_frame; } - err = mvpp2_rx_refill(port, bm_pool, bm); + err = mvpp2_rx_refill(port, bm_pool, pool); if (err) { netdev_err(port->dev, "failed to refill BM pools\n"); goto err_drop_frame; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 2fd044b23875..944fc1742464 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -458,13 +458,15 @@ struct mlx5e_mpw_info { struct mlx5e_rx_am_stats { int ppms; /* packets per msec */ + int bpms; /* bytes per msec */ int epms; /* events per msec */ }; struct mlx5e_rx_am_sample { - ktime_t time; - unsigned int pkt_ctr; - u16 event_ctr; + ktime_t time; + u32 pkt_ctr; + u32 byte_ctr; + u16 event_ctr; }; struct mlx5e_rx_am { /* Adaptive Moderation */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c index 02dd3a95ed8f..acf32fe952cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c @@ -183,28 +183,27 @@ static void mlx5e_am_exit_parking(struct mlx5e_rx_am *am) mlx5e_am_step(am); } +#define IS_SIGNIFICANT_DIFF(val, ref) \ + (((100 * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */ + static int mlx5e_am_stats_compare(struct mlx5e_rx_am_stats *curr, struct mlx5e_rx_am_stats *prev) { - int diff; - - if (!prev->ppms) - return curr->ppms ? MLX5E_AM_STATS_BETTER : + if (!prev->bpms) + return curr->bpms ? MLX5E_AM_STATS_BETTER : MLX5E_AM_STATS_SAME; - diff = curr->ppms - prev->ppms; - if (((100 * abs(diff)) / prev->ppms) > 10) /* more than 10% diff */ - return (diff > 0) ? MLX5E_AM_STATS_BETTER : - MLX5E_AM_STATS_WORSE; + if (IS_SIGNIFICANT_DIFF(curr->bpms, prev->bpms)) + return (curr->bpms > prev->bpms) ? MLX5E_AM_STATS_BETTER : + MLX5E_AM_STATS_WORSE; - if (!prev->epms) - return curr->epms ? MLX5E_AM_STATS_WORSE : - MLX5E_AM_STATS_SAME; + if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms)) + return (curr->ppms > prev->ppms) ? MLX5E_AM_STATS_BETTER : + MLX5E_AM_STATS_WORSE; - diff = curr->epms - prev->epms; - if (((100 * abs(diff)) / prev->epms) > 10) /* more than 10% diff */ - return (diff < 0) ? MLX5E_AM_STATS_BETTER : - MLX5E_AM_STATS_WORSE; + if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms)) + return (curr->epms < prev->epms) ? MLX5E_AM_STATS_BETTER : + MLX5E_AM_STATS_WORSE; return MLX5E_AM_STATS_SAME; } @@ -266,10 +265,13 @@ static void mlx5e_am_sample(struct mlx5e_rq *rq, { s->time = ktime_get(); s->pkt_ctr = rq->stats.packets; + s->byte_ctr = rq->stats.bytes; s->event_ctr = rq->cq.event_ctr; } #define MLX5E_AM_NEVENTS 64 +#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) +#define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) & (BIT_ULL(bits) - 1)) static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start, struct mlx5e_rx_am_sample *end, @@ -277,13 +279,17 @@ static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start, { /* u32 holds up to 71 minutes, should be enough */ u32 delta_us = ktime_us_delta(end->time, start->time); - unsigned int npkts = end->pkt_ctr - start->pkt_ctr; + u32 npkts = BIT_GAP(BITS_PER_TYPE(u32), end->pkt_ctr, start->pkt_ctr); + u32 nbytes = BIT_GAP(BITS_PER_TYPE(u32), end->byte_ctr, + start->byte_ctr); if (!delta_us) return; - curr_stats->ppms = (npkts * USEC_PER_MSEC) / delta_us; - curr_stats->epms = (MLX5E_AM_NEVENTS * USEC_PER_MSEC) / delta_us; + curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us); + curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us); + curr_stats->epms = DIV_ROUND_UP(MLX5E_AM_NEVENTS * USEC_PER_MSEC, + delta_us); } void mlx5e_rx_am_work(struct work_struct *work) @@ -308,7 +314,8 @@ void mlx5e_rx_am(struct mlx5e_rq *rq) switch (am->state) { case MLX5E_AM_MEASURE_IN_PROGRESS: - nevents = rq->cq.event_ctr - am->start_sample.event_ctr; + nevents = BIT_GAP(BITS_PER_TYPE(u16), rq->cq.event_ctr, + am->start_sample.event_ctr); if (nevents < MLX5E_AM_NEVENTS) break; mlx5e_am_sample(rq, &end_sample); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 53e4992d6511..f81c3aa60b46 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -417,20 +417,13 @@ struct mlx5e_stats { }; static const struct counter_desc mlx5e_pme_status_desc[] = { - { "module_plug", 0 }, { "module_unplug", 8 }, }; static const struct counter_desc mlx5e_pme_error_desc[] = { - { "module_pwr_budget_exd", 0 }, /* power budget exceed */ - { "module_long_range", 8 }, /* long range for non MLNX cable */ - { "module_bus_stuck", 16 }, /* bus stuck (I2C or data shorted) */ - { "module_no_eeprom", 24 }, /* no eeprom/retry time out */ - { "module_enforce_part", 32 }, /* enforce part number list */ - { "module_unknown_id", 40 }, /* unknown identifier */ - { "module_high_temp", 48 }, /* high temperature */ + { "module_bus_stuck", 16 }, /* bus stuck (I2C or data shorted) */ + { "module_high_temp", 48 }, /* high temperature */ { "module_bad_shorted", 56 }, /* bad or shorted cable/module */ - { "module_unknown_status", 64 }, }; #endif /* __MLX5_EN_STATS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 0e487e8ca634..8f5125ccd8d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -862,7 +862,7 @@ struct mlx5_flow_table *mlx5_create_vport_flow_table(struct mlx5_flow_namespace ft_attr.level = level; ft_attr.prio = prio; - return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_NORMAL, 0); + return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_NORMAL, vport); } struct mlx5_flow_table* diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 44f59b1d6f0f..f27f84ffbc85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -275,10 +275,8 @@ static void poll_health(unsigned long data) struct mlx5_core_health *health = &dev->priv.health; u32 count; - if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { - mod_timer(&health->timer, get_next_poll_jiffies()); - return; - } + if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + goto out; count = ioread32be(health->health_counter); if (count == health->prev) @@ -290,8 +288,6 @@ static void poll_health(unsigned long data) if (health->miss_counter == MAX_MISSES) { dev_err(&dev->pdev->dev, "device's health compromised - reached miss count\n"); print_health_info(dev); - } else { - mod_timer(&health->timer, get_next_poll_jiffies()); } if (in_fatal(dev) && !health->sick) { @@ -305,6 +301,9 @@ static void poll_health(unsigned long data) "new health works are not permitted at this stage\n"); spin_unlock(&health->wq_lock); } + +out: + mod_timer(&health->timer, get_next_poll_jiffies()); } void mlx5_start_health_poll(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index af945edfee19..4f577a5abf88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -537,8 +537,10 @@ static int handle_hca_cap(struct mlx5_core_dev *dev) /* disable cmdif checksum */ MLX5_SET(cmd_hca_cap, set_hca_cap, cmdif_checksum, 0); - /* If the HCA supports 4K UARs use it */ - if (MLX5_CAP_GEN_MAX(dev, uar_4k)) + /* Enable 4K UAR only when HCA supports it and page size is bigger + * than 4K. + */ + if (MLX5_CAP_GEN_MAX(dev, uar_4k) && PAGE_SIZE > 4096) MLX5_SET(cmd_hca_cap, set_hca_cap, uar_4k, 1); MLX5_SET(cmd_hca_cap, set_hca_cap, log_uar_page_sz, PAGE_SHIFT - 12); diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 483241b4b05d..a672f6a860dc 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -2956,7 +2956,7 @@ static u32 qed_grc_dump_ctx_data(struct qed_hwfn *p_hwfn, qed_wr(p_hwfn, p_ptt, s_storm_defs[storm_id].cm_ctx_wr_addr, - BIT(9) | lid); + (i << 9) | lid); *(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, rd_reg_addr); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index aa6476439aee..e0ef02f9503b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -214,13 +214,13 @@ static int dwmac4_wrback_get_tx_timestamp_status(struct dma_desc *p) { /* Context type from W/B descriptor must be zero */ if (le32_to_cpu(p->des3) & TDES3_CONTEXT_TYPE) - return -EINVAL; + return 0; /* Tx Timestamp Status is 1 so des0 and des1'll have valid values */ if (le32_to_cpu(p->des3) & TDES3_TIMESTAMP_STATUS) - return 0; + return 1; - return 1; + return 0; } static inline u64 dwmac4_get_timestamp(void *desc, u32 ats) @@ -282,7 +282,10 @@ static int dwmac4_wrback_get_rx_timestamp_status(void *desc, u32 ats) } } exit: - return ret; + if (likely(ret == 0)) + return 1; + + return 0; } static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 12236daf7bb6..d16d11bfc046 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -434,14 +434,14 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, return; /* check tx tstamp status */ - if (!priv->hw->desc->get_tx_timestamp_status(p)) { + if (priv->hw->desc->get_tx_timestamp_status(p)) { /* get the valid tstamp */ ns = priv->hw->desc->get_timestamp(p, priv->adv_ts); memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); shhwtstamp.hwtstamp = ns_to_ktime(ns); - netdev_info(priv->dev, "get valid TX hw timestamp %llu\n", ns); + netdev_dbg(priv->dev, "get valid TX hw timestamp %llu\n", ns); /* pass tstamp to stack */ skb_tstamp_tx(skb, &shhwtstamp); } @@ -468,19 +468,19 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, return; /* Check if timestamp is available */ - if (!priv->hw->desc->get_rx_timestamp_status(p, priv->adv_ts)) { + if (priv->hw->desc->get_rx_timestamp_status(p, priv->adv_ts)) { /* For GMAC4, the valid timestamp is from CTX next desc. */ if (priv->plat->has_gmac4) ns = priv->hw->desc->get_timestamp(np, priv->adv_ts); else ns = priv->hw->desc->get_timestamp(p, priv->adv_ts); - netdev_info(priv->dev, "get valid RX hw timestamp %llu\n", ns); + netdev_dbg(priv->dev, "get valid RX hw timestamp %llu\n", ns); shhwtstamp = skb_hwtstamps(skb); memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); shhwtstamp->hwtstamp = ns_to_ktime(ns); } else { - netdev_err(priv->dev, "cannot get RX hw timestamp\n"); + netdev_dbg(priv->dev, "cannot get RX hw timestamp\n"); } } @@ -546,7 +546,10 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) /* PTP v1, UDP, any kind of event packet */ config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; /* take time stamp for all event messages */ - snap_type_sel = PTP_TCR_SNAPTYPSEL_1; + if (priv->plat->has_gmac4) + snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1; + else + snap_type_sel = PTP_TCR_SNAPTYPSEL_1; ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA; ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA; @@ -578,7 +581,10 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; ptp_v2 = PTP_TCR_TSVER2ENA; /* take time stamp for all event messages */ - snap_type_sel = PTP_TCR_SNAPTYPSEL_1; + if (priv->plat->has_gmac4) + snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1; + else + snap_type_sel = PTP_TCR_SNAPTYPSEL_1; ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA; ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA; @@ -612,7 +618,10 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; ptp_v2 = PTP_TCR_TSVER2ENA; /* take time stamp for all event messages */ - snap_type_sel = PTP_TCR_SNAPTYPSEL_1; + if (priv->plat->has_gmac4) + snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1; + else + snap_type_sel = PTP_TCR_SNAPTYPSEL_1; ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA; ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h index 48fb72fc423c..f4b31d69f60e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h @@ -59,7 +59,8 @@ /* Enable Snapshot for Messages Relevant to Master */ #define PTP_TCR_TSMSTRENA BIT(15) /* Select PTP packets for Taking Snapshots */ -#define PTP_TCR_SNAPTYPSEL_1 GENMASK(17, 16) +#define PTP_TCR_SNAPTYPSEL_1 BIT(16) +#define PTP_GMAC4_TCR_SNAPTYPSEL_1 GENMASK(17, 16) /* Enable MAC address for PTP Frame Filtering */ #define PTP_TCR_TSENMACADDR BIT(18) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 06ee6395117f..0e27920c2b6b 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -358,7 +358,7 @@ static ssize_t enabled_store(struct config_item *item, if (err) goto out_unlock; - pr_info("netconsole: network logging started\n"); + pr_info("network logging started\n"); } else { /* false */ /* We need to disable the netconsole before cleaning it up * otherwise we might end up in write_msg() with diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index c360dd6ead22..3ab6c58d4be6 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -127,6 +127,7 @@ config MDIO_THUNDER tristate "ThunderX SOCs MDIO buses" depends on 64BIT depends on PCI + depends on !(MDIO_DEVICE=y && PHYLIB=m) select MDIO_CAVIUM help This driver supports the MDIO interfaces found on Cavium diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 7524caa0f29d..eebb0e1c70ff 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -54,6 +54,8 @@ static const char *phy_speed_to_str(int speed) return "5Gbps"; case SPEED_10000: return "10Gbps"; + case SPEED_14000: + return "14Gbps"; case SPEED_20000: return "20Gbps"; case SPEED_25000: diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 949671ce4039..32a22f4e8356 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1192,6 +1192,8 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9056, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9057, 8)}, {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ + {QMI_FIXED_INTF(0x1199, 0x9063, 8)}, /* Sierra Wireless EM7305 */ + {QMI_FIXED_INTF(0x1199, 0x9063, 10)}, /* Sierra Wireless EM7305 */ {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ @@ -1206,6 +1208,8 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)}, /* Telit LE920, LE920A4 */ + {QMI_FIXED_INTF(0x1c9e, 0x9801, 3)}, /* Telewell TW-3G HSPA+ */ + {QMI_FIXED_INTF(0x1c9e, 0x9803, 4)}, /* Telewell TW-3G HSPA+ */ {QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */ {QMI_FIXED_INTF(0x0b3c, 0xc000, 4)}, /* Olivetti Olicard 100 */ {QMI_FIXED_INTF(0x0b3c, 0xc001, 4)}, /* Olivetti Olicard 120 */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index ddc62cb69be8..1a419a45e2a2 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -4368,6 +4368,8 @@ static u8 rtl_get_version(struct usb_interface *intf) break; } + dev_dbg(&intf->dev, "Detected version 0x%04x\n", version); + return version; } diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index d38f11d833fe..022c0b5f9844 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -36,12 +36,14 @@ #include <net/addrconf.h> #include <net/l3mdev.h> #include <net/fib_rules.h> +#include <net/netns/generic.h> #define DRV_NAME "vrf" #define DRV_VERSION "1.0" #define FIB_RULE_PREF 1000 /* default preference for FIB rules */ -static bool add_fib_rules = true; + +static unsigned int vrf_net_id; struct net_vrf { struct rtable __rcu *rth; @@ -1394,6 +1396,8 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct net_vrf *vrf = netdev_priv(dev); + bool *add_fib_rules; + struct net *net; int err; if (!data || !data[IFLA_VRF_TABLE]) @@ -1409,13 +1413,15 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev, if (err) goto out; - if (add_fib_rules) { + net = dev_net(dev); + add_fib_rules = net_generic(net, vrf_net_id); + if (*add_fib_rules) { err = vrf_add_fib_rules(dev); if (err) { unregister_netdevice(dev); goto out; } - add_fib_rules = false; + *add_fib_rules = false; } out: @@ -1498,16 +1504,38 @@ static struct notifier_block vrf_notifier_block __read_mostly = { .notifier_call = vrf_device_event, }; +/* Initialize per network namespace state */ +static int __net_init vrf_netns_init(struct net *net) +{ + bool *add_fib_rules = net_generic(net, vrf_net_id); + + *add_fib_rules = true; + + return 0; +} + +static struct pernet_operations vrf_net_ops __net_initdata = { + .init = vrf_netns_init, + .id = &vrf_net_id, + .size = sizeof(bool), +}; + static int __init vrf_init_module(void) { int rc; register_netdevice_notifier(&vrf_notifier_block); - rc = rtnl_link_register(&vrf_link_ops); + rc = register_pernet_subsys(&vrf_net_ops); if (rc < 0) goto error; + rc = rtnl_link_register(&vrf_link_ops); + if (rc < 0) { + unregister_pernet_subsys(&vrf_net_ops); + goto error; + } + return 0; error: diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index d179d7767f51..7d4a594d5d58 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1486,8 +1486,10 @@ enum ethtool_link_mode_bit_indices { * it was forced up into this mode or autonegotiated. */ -/* The forced speed, in units of 1Mb. All values 0 to INT_MAX are legal. */ -/* Update drivers/net/phy/phy.c:phy_speed_to_str() when adding new values */ +/* The forced speed, in units of 1Mb. All values 0 to INT_MAX are legal. + * Update drivers/net/phy/phy.c:phy_speed_to_str() and + * drivers/net/bonding/bond_3ad.c:__get_link_speed() when adding new values. + */ #define SPEED_10 10 #define SPEED_100 100 #define SPEED_1000 1000 diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 61b7d36dfe34..156ee4cab82e 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -343,6 +343,7 @@ enum ovs_key_attr { #define OVS_KEY_ATTR_MAX (__OVS_KEY_ATTR_MAX - 1) enum ovs_tunnel_key_attr { + /* OVS_TUNNEL_KEY_ATTR_NONE, standard nl API requires this attribute! */ OVS_TUNNEL_KEY_ATTR_ID, /* be64 Tunnel ID */ OVS_TUNNEL_KEY_ATTR_IPV4_SRC, /* be32 src IP address. */ OVS_TUNNEL_KEY_ATTR_IPV4_DST, /* be32 dst IP address. */ diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c index 59ce1fcc220c..71b6ab240dea 100644 --- a/net/caif/cfpkt_skbuff.c +++ b/net/caif/cfpkt_skbuff.c @@ -81,11 +81,7 @@ static struct cfpkt *cfpkt_create_pfx(u16 len, u16 pfx) { struct sk_buff *skb; - if (likely(in_interrupt())) - skb = alloc_skb(len + pfx, GFP_ATOMIC); - else - skb = alloc_skb(len + pfx, GFP_KERNEL); - + skb = alloc_skb(len + pfx, GFP_ATOMIC); if (unlikely(skb == NULL)) return NULL; diff --git a/net/can/af_can.c b/net/can/af_can.c index b6406fe33c76..88edac0f3e36 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -872,8 +872,7 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg, static int can_pernet_init(struct net *net) { - net->can.can_rcvlists_lock = - __SPIN_LOCK_UNLOCKED(net->can.can_rcvlists_lock); + spin_lock_init(&net->can.can_rcvlists_lock); net->can.can_rx_alldev_list = kzalloc(sizeof(struct dev_rcv_lists), GFP_KERNEL); diff --git a/net/core/dev.c b/net/core/dev.c index 4c15466305c3..6d60149287a1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4949,6 +4949,19 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb) } EXPORT_SYMBOL(__skb_gro_checksum_complete); +static void net_rps_send_ipi(struct softnet_data *remsd) +{ +#ifdef CONFIG_RPS + while (remsd) { + struct softnet_data *next = remsd->rps_ipi_next; + + if (cpu_online(remsd->cpu)) + smp_call_function_single_async(remsd->cpu, &remsd->csd); + remsd = next; + } +#endif +} + /* * net_rps_action_and_irq_enable sends any pending IPI's for rps. * Note: called with local irq disabled, but exits with local irq enabled. @@ -4964,14 +4977,7 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd) local_irq_enable(); /* Send pending IPI's to kick RPS processing on remote cpus. */ - while (remsd) { - struct softnet_data *next = remsd->rps_ipi_next; - - if (cpu_online(remsd->cpu)) - smp_call_function_single_async(remsd->cpu, - &remsd->csd); - remsd = next; - } + net_rps_send_ipi(remsd); } else #endif local_irq_enable(); @@ -8197,7 +8203,7 @@ static int dev_cpu_dead(unsigned int oldcpu) struct sk_buff **list_skb; struct sk_buff *skb; unsigned int cpu; - struct softnet_data *sd, *oldsd; + struct softnet_data *sd, *oldsd, *remsd = NULL; local_irq_disable(); cpu = smp_processor_id(); @@ -8238,6 +8244,13 @@ static int dev_cpu_dead(unsigned int oldcpu) raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); +#ifdef CONFIG_RPS + remsd = oldsd->rps_ipi_list; + oldsd->rps_ipi_list = NULL; +#endif + /* send out pending IPI's on offline CPU */ + net_rps_send_ipi(remsd); + /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { netif_rx_ni(skb); diff --git a/net/core/dst.c b/net/core/dst.c index 6192f11beec9..13ba4a090c41 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -469,6 +469,20 @@ static int dst_dev_event(struct notifier_block *this, unsigned long event, spin_lock_bh(&dst_garbage.lock); dst = dst_garbage.list; dst_garbage.list = NULL; + /* The code in dst_ifdown places a hold on the loopback device. + * If the gc entry processing is set to expire after a lengthy + * interval, this hold can cause netdev_wait_allrefs() to hang + * out and wait for a long time -- until the the loopback + * interface is released. If we're really unlucky, it'll emit + * pr_emerg messages to console too. Reset the interval here, + * so dst cleanups occur in a more timely fashion. + */ + if (dst_garbage.timer_inc > DST_GC_INC) { + dst_garbage.timer_inc = DST_GC_INC; + dst_garbage.timer_expires = DST_GC_MIN; + mod_delayed_work(system_wq, &dst_gc_work, + dst_garbage.timer_expires); + } spin_unlock_bh(&dst_garbage.lock); if (last) diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 4ebe2aa3e7d3..04b5450c5a55 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -324,8 +324,7 @@ static int hsr_fill_frame_info(struct hsr_frame_info *frame, unsigned long irqflags; frame->is_supervision = is_supervision_frame(port->hsr, skb); - frame->node_src = hsr_get_node(&port->hsr->node_db, skb, - frame->is_supervision); + frame->node_src = hsr_get_node(port, skb, frame->is_supervision); if (frame->node_src == NULL) return -1; /* Unknown node and !is_supervision, or no mem */ diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 7ea925816f79..284a9b820df8 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -158,9 +158,10 @@ struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], /* Get the hsr_node from which 'skb' was sent. */ -struct hsr_node *hsr_get_node(struct list_head *node_db, struct sk_buff *skb, +struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, bool is_sup) { + struct list_head *node_db = &port->hsr->node_db; struct hsr_node *node; struct ethhdr *ethhdr; u16 seq_out; @@ -186,7 +187,11 @@ struct hsr_node *hsr_get_node(struct list_head *node_db, struct sk_buff *skb, */ seq_out = hsr_get_skb_sequence_nr(skb) - 1; } else { - WARN_ONCE(1, "%s: Non-HSR frame\n", __func__); + /* this is called also for frames from master port and + * so warn only for non master ports + */ + if (port->type != HSR_PT_MASTER) + WARN_ONCE(1, "%s: Non-HSR frame\n", __func__); seq_out = HSR_SEQNR_START; } diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 438b40f98f5a..4e04f0e868e9 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -18,7 +18,7 @@ struct hsr_node; struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], u16 seq_out); -struct hsr_node *hsr_get_node(struct list_head *node_db, struct sk_buff *skb, +struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, bool is_sup); void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, struct hsr_port *port); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 44fd86de2823..8f6b5bbcbf69 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2071,21 +2071,26 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, static void ip_mc_clear_src(struct ip_mc_list *pmc) { - struct ip_sf_list *psf, *nextpsf; + struct ip_sf_list *psf, *nextpsf, *tomb, *sources; - for (psf = pmc->tomb; psf; psf = nextpsf) { + spin_lock_bh(&pmc->lock); + tomb = pmc->tomb; + pmc->tomb = NULL; + sources = pmc->sources; + pmc->sources = NULL; + pmc->sfmode = MCAST_EXCLUDE; + pmc->sfcount[MCAST_INCLUDE] = 0; + pmc->sfcount[MCAST_EXCLUDE] = 1; + spin_unlock_bh(&pmc->lock); + + for (psf = tomb; psf; psf = nextpsf) { nextpsf = psf->sf_next; kfree(psf); } - pmc->tomb = NULL; - for (psf = pmc->sources; psf; psf = nextpsf) { + for (psf = sources; psf; psf = nextpsf) { nextpsf = psf->sf_next; kfree(psf); } - pmc->sources = NULL; - pmc->sfmode = MCAST_EXCLUDE; - pmc->sfcount[MCAST_INCLUDE] = 0; - pmc->sfcount[MCAST_EXCLUDE] = 1; } /* Join a multicast group diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b4f9622ee9f5..8ae425cad818 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -101,8 +101,8 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id); static void ipmr_free_table(struct mr_table *mrt); static void ip_mr_forward(struct net *net, struct mr_table *mrt, - struct sk_buff *skb, struct mfc_cache *cache, - int local); + struct net_device *dev, struct sk_buff *skb, + struct mfc_cache *cache, int local); static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, @@ -988,7 +988,7 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { - ip_mr_forward(net, mrt, skb, c, 0); + ip_mr_forward(net, mrt, skb->dev, skb, c, 0); } } } @@ -1073,7 +1073,7 @@ static int ipmr_cache_report(struct mr_table *mrt, /* Queue a packet for resolution. It gets locked cache entry! */ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, - struct sk_buff *skb) + struct sk_buff *skb, struct net_device *dev) { const struct iphdr *iph = ip_hdr(skb); struct mfc_cache *c; @@ -1130,6 +1130,10 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, kfree_skb(skb); err = -ENOBUFS; } else { + if (dev) { + skb->dev = dev; + skb->skb_iif = dev->ifindex; + } skb_queue_tail(&c->mfc_un.unres.unresolved, skb); err = 0; } @@ -1828,10 +1832,10 @@ static int ipmr_find_vif(struct mr_table *mrt, struct net_device *dev) /* "local" means that we should preserve one skb (for local delivery) */ static void ip_mr_forward(struct net *net, struct mr_table *mrt, - struct sk_buff *skb, struct mfc_cache *cache, - int local) + struct net_device *dev, struct sk_buff *skb, + struct mfc_cache *cache, int local) { - int true_vifi = ipmr_find_vif(mrt, skb->dev); + int true_vifi = ipmr_find_vif(mrt, dev); int psend = -1; int vif, ct; @@ -1853,13 +1857,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, } /* Wrong interface: drop packet and (maybe) send PIM assert. */ - if (mrt->vif_table[vif].dev != skb->dev) { - struct net_device *mdev; - - mdev = l3mdev_master_dev_rcu(mrt->vif_table[vif].dev); - if (mdev == skb->dev) - goto forward; - + if (mrt->vif_table[vif].dev != dev) { if (rt_is_output_route(skb_rtable(skb))) { /* It is our own packet, looped back. * Very complicated situation... @@ -2053,7 +2051,7 @@ int ip_mr_input(struct sk_buff *skb) read_lock(&mrt_lock); vif = ipmr_find_vif(mrt, dev); if (vif >= 0) { - int err2 = ipmr_cache_unresolved(mrt, vif, skb); + int err2 = ipmr_cache_unresolved(mrt, vif, skb, dev); read_unlock(&mrt_lock); return err2; @@ -2064,7 +2062,7 @@ int ip_mr_input(struct sk_buff *skb) } read_lock(&mrt_lock); - ip_mr_forward(net, mrt, skb, cache, local); + ip_mr_forward(net, mrt, dev, skb, cache, local); read_unlock(&mrt_lock); if (local) @@ -2238,7 +2236,7 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, iph->saddr = saddr; iph->daddr = daddr; iph->version = 0; - err = ipmr_cache_unresolved(mrt, vif, skb2); + err = ipmr_cache_unresolved(mrt, vif, skb2, dev); read_unlock(&mrt_lock); rcu_read_unlock(); return err; diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 2fd5ca151dcf..77f7f8c7d93d 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -62,6 +62,7 @@ static inline u32 ila_locator_hash(struct ila_locator loc) { u32 *v = (u32 *)loc.v32; + __ila_hash_secret_init(); return jhash_2words(v[0], v[1], hashrnd); } diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index cc8e3ae9ca73..e88bcb8ff0fd 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -219,7 +219,7 @@ static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu *mib, u64 buff64[SNMP_MIB_MAX]; int i; - memset(buff64, 0, sizeof(unsigned long) * SNMP_MIB_MAX); + memset(buff64, 0, sizeof(u64) * SNMP_MIB_MAX); snmp_get_cpu_field64_batch(buff64, itemlist, mib, syncpoff); for (i = 0; itemlist[i].name; i++) diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index f7c54ece3733..4de2ec94b08c 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -114,12 +114,13 @@ static void l2tp_eth_get_stats64(struct net_device *dev, { struct l2tp_eth *priv = netdev_priv(dev); - stats->tx_bytes = atomic_long_read(&priv->tx_bytes); - stats->tx_packets = atomic_long_read(&priv->tx_packets); - stats->tx_dropped = atomic_long_read(&priv->tx_dropped); - stats->rx_bytes = atomic_long_read(&priv->rx_bytes); - stats->rx_packets = atomic_long_read(&priv->rx_packets); - stats->rx_errors = atomic_long_read(&priv->rx_errors); + stats->tx_bytes = (unsigned long) atomic_long_read(&priv->tx_bytes); + stats->tx_packets = (unsigned long) atomic_long_read(&priv->tx_packets); + stats->tx_dropped = (unsigned long) atomic_long_read(&priv->tx_dropped); + stats->rx_bytes = (unsigned long) atomic_long_read(&priv->rx_bytes); + stats->rx_packets = (unsigned long) atomic_long_read(&priv->rx_packets); + stats->rx_errors = (unsigned long) atomic_long_read(&priv->rx_errors); + } static const struct net_device_ops l2tp_eth_netdev_ops = { diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 915d7e1b4545..f5f50150ba1c 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1816,6 +1816,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ret = dev_alloc_name(ndev, ndev->name); if (ret < 0) { ieee80211_if_free(ndev); + free_netdev(ndev); return ret; } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index f16c8d97b7f3..30aa0a529215 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4622,13 +4622,13 @@ int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), for (head = sctp_ep_hashtable; hash < sctp_ep_hashsize; hash++, head++) { - read_lock(&head->lock); + read_lock_bh(&head->lock); sctp_for_each_hentry(epb, &head->chain) { err = cb(sctp_ep(epb), p); if (err) break; } - read_unlock(&head->lock); + read_unlock_bh(&head->lock); } return err; diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 312ef7de57d7..ab3087687a32 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -508,7 +508,7 @@ bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err) } if (skb_cloned(_skb) && - pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_KERNEL)) + pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC)) goto exit; /* Now reverse the concerned fields */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 6a7fe7660551..1a0c961f4ffe 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -999,7 +999,8 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct path path = { }; err = -EINVAL; - if (sunaddr->sun_family != AF_UNIX) + if (addr_len < offsetofend(struct sockaddr_un, sun_family) || + sunaddr->sun_family != AF_UNIX) goto out; if (addr_len == sizeof(short)) { @@ -1110,6 +1111,10 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, unsigned int hash; int err; + err = -EINVAL; + if (alen < offsetofend(struct sockaddr, sa_family)) + goto out; + if (addr->sa_family != AF_UNSPEC) { err = unix_mkname(sunaddr, alen, &hash); if (err < 0) diff --git a/tools/testing/selftests/bpf/bpf_endian.h b/tools/testing/selftests/bpf/bpf_endian.h index 19d0604f8694..487cbfb89beb 100644 --- a/tools/testing/selftests/bpf/bpf_endian.h +++ b/tools/testing/selftests/bpf/bpf_endian.h @@ -1,23 +1,42 @@ #ifndef __BPF_ENDIAN__ #define __BPF_ENDIAN__ -#include <asm/byteorder.h> +#include <linux/swab.h> -#if __BYTE_ORDER == __LITTLE_ENDIAN -# define __bpf_ntohs(x) __builtin_bswap16(x) -# define __bpf_htons(x) __builtin_bswap16(x) -#elif __BYTE_ORDER == __BIG_ENDIAN -# define __bpf_ntohs(x) (x) -# define __bpf_htons(x) (x) +/* LLVM's BPF target selects the endianness of the CPU + * it compiles on, or the user specifies (bpfel/bpfeb), + * respectively. The used __BYTE_ORDER__ is defined by + * the compiler, we cannot rely on __BYTE_ORDER from + * libc headers, since it doesn't reflect the actual + * requested byte order. + * + * Note, LLVM's BPF target has different __builtin_bswapX() + * semantics. It does map to BPF_ALU | BPF_END | BPF_TO_BE + * in bpfel and bpfeb case, which means below, that we map + * to cpu_to_be16(). We could use it unconditionally in BPF + * case, but better not rely on it, so that this header here + * can be used from application and BPF program side, which + * use different targets. + */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +# define __bpf_ntohs(x) __builtin_bswap16(x) +# define __bpf_htons(x) __builtin_bswap16(x) +# define __bpf_constant_ntohs(x) ___constant_swab16(x) +# define __bpf_constant_htons(x) ___constant_swab16(x) +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +# define __bpf_ntohs(x) (x) +# define __bpf_htons(x) (x) +# define __bpf_constant_ntohs(x) (x) +# define __bpf_constant_htons(x) (x) #else -# error "Fix your __BYTE_ORDER?!" +# error "Fix your compiler's __BYTE_ORDER__?!" #endif #define bpf_htons(x) \ (__builtin_constant_p(x) ? \ - __constant_htons(x) : __bpf_htons(x)) + __bpf_constant_htons(x) : __bpf_htons(x)) #define bpf_ntohs(x) \ (__builtin_constant_p(x) ? \ - __constant_ntohs(x) : __bpf_ntohs(x)) + __bpf_constant_ntohs(x) : __bpf_ntohs(x)) -#endif +#endif /* __BPF_ENDIAN__ */ |