diff options
25 files changed, 245 insertions, 117 deletions
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 9abfaae1c6f7d8..a4e4e15f574df2 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -745,6 +745,19 @@ const struct bond_option *bond_opt_get(unsigned int option) return &bond_opts[option]; } +static void bond_set_xfrm_features(struct net_device *bond_dev, u64 mode) +{ + if (!IS_ENABLED(CONFIG_XFRM_OFFLOAD)) + return; + + if (mode == BOND_MODE_ACTIVEBACKUP) + bond_dev->wanted_features |= BOND_XFRM_FEATURES; + else + bond_dev->wanted_features &= ~BOND_XFRM_FEATURES; + + netdev_update_features(bond_dev); +} + static int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval) { @@ -767,13 +780,8 @@ static int bond_option_mode_set(struct bonding *bond, if (newval->value == BOND_MODE_ALB) bond->params.tlb_dynamic_lb = 1; -#ifdef CONFIG_XFRM_OFFLOAD - if (newval->value == BOND_MODE_ACTIVEBACKUP) - bond->dev->wanted_features |= BOND_XFRM_FEATURES; - else - bond->dev->wanted_features &= ~BOND_XFRM_FEATURES; - netdev_change_features(bond->dev); -#endif /* CONFIG_XFRM_OFFLOAD */ + if (bond->dev->reg_state == NETREG_REGISTERED) + bond_set_xfrm_features(bond->dev, newval->value); /* don't cache arp_validate between modes */ bond->params.arp_validate = BOND_ARP_VALIDATE_NONE; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index b30f00891c0372..128ab6898070e0 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6475,13 +6475,13 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter) /* Ungate PGCB clock */ mac_data = er32(FEXTNVM9); - mac_data |= BIT(28); + mac_data &= ~BIT(28); ew32(FEXTNVM9, mac_data); /* Enable K1 off to enable mPHY Power Gating */ mac_data = er32(FEXTNVM6); mac_data |= BIT(31); - ew32(FEXTNVM12, mac_data); + ew32(FEXTNVM6, mac_data); /* Enable mPHY power gating for any link and speed */ mac_data = er32(FEXTNVM8); @@ -6525,11 +6525,11 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) /* Disable K1 off */ mac_data = er32(FEXTNVM6); mac_data &= ~BIT(31); - ew32(FEXTNVM12, mac_data); + ew32(FEXTNVM6, mac_data); /* Disable Ungate PGCB clock */ mac_data = er32(FEXTNVM9); - mac_data &= ~BIT(28); + mac_data |= BIT(28); ew32(FEXTNVM9, mac_data); /* Cancel not waking from dynamic diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index d43ce13a93c9f0..3f5825fa67c99c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1850,6 +1850,7 @@ static inline bool i40e_page_is_reusable(struct page *page) * the adapter for another receive * * @rx_buffer: buffer containing the page + * @rx_buffer_pgcnt: buffer page refcount pre xdp_do_redirect() call * * If page is reusable, rx_buffer->page_offset is adjusted to point to * an unused region in the page. @@ -1872,7 +1873,8 @@ static inline bool i40e_page_is_reusable(struct page *page) * * In either case, if the page is reusable its refcount is increased. **/ -static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) +static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -1883,7 +1885,7 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) return false; #else #define I40E_LAST_OFFSET \ @@ -1942,16 +1944,24 @@ static void i40e_add_rx_frag(struct i40e_ring *rx_ring, * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use * @rx_ring: rx descriptor ring to transact packets on * @size: size of buffer to add to skb + * @rx_buffer_pgcnt: buffer page refcount * * This function will pull an Rx buffer from the ring and synchronize it * for use by the CPU. */ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, - const unsigned int size) + const unsigned int size, + int *rx_buffer_pgcnt) { struct i40e_rx_buffer *rx_buffer; rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); + *rx_buffer_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif prefetch_page_address(rx_buffer->page); /* we are reusing so sync this buffer for CPU use */ @@ -2102,14 +2112,16 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * 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 + * @rx_buffer_pgcnt: rx buffer page refcount pre xdp_do_redirect() call * * This function will clean up the contents of the rx_buffer. It will * either recycle the buffer or unmap it and free the associated resources. */ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer) + struct i40e_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) { - if (i40e_can_reuse_rx_page(rx_buffer)) { + if (i40e_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { /* hand second half of page back to the ring */ i40e_reuse_rx_page(rx_ring, rx_buffer); } else { @@ -2336,6 +2348,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) while (likely(total_rx_packets < (unsigned int)budget)) { struct i40e_rx_buffer *rx_buffer; union i40e_rx_desc *rx_desc; + int rx_buffer_pgcnt; unsigned int size; u64 qword; @@ -2378,7 +2391,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) break; i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb); - rx_buffer = i40e_get_rx_buffer(rx_ring, size); + rx_buffer = i40e_get_rx_buffer(rx_ring, size, &rx_buffer_pgcnt); /* retrieve a buffer from the ring */ if (!skb) { @@ -2421,7 +2434,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) break; } - i40e_put_rx_buffer(rx_ring, rx_buffer); + i40e_put_rx_buffer(rx_ring, rx_buffer, rx_buffer_pgcnt); cleaned_count++; if (i40e_is_non_eop(rx_ring, rx_desc, skb)) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index eae75260fe20b0..23eca2f0a03b1c 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -762,13 +762,15 @@ ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size) /** * ice_can_reuse_rx_page - Determine if page can be reused for another Rx * @rx_buf: buffer containing the page + * @rx_buf_pgcnt: rx_buf page refcount pre xdp_do_redirect() call * * If page is reusable, we have a green light for calling ice_reuse_rx_page, * which will assign the current buffer to the buffer that next_to_alloc is * pointing to; otherwise, the DMA mapping needs to be destroyed and * page freed */ -static bool ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) +static bool +ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf, int rx_buf_pgcnt) { unsigned int pagecnt_bias = rx_buf->pagecnt_bias; struct page *page = rx_buf->page; @@ -779,7 +781,7 @@ static bool ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1)) return false; #else #define ICE_LAST_OFFSET \ @@ -864,17 +866,24 @@ ice_reuse_rx_page(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf) * @rx_ring: Rx descriptor ring to transact packets on * @skb: skb to be used * @size: size of buffer to add to skb + * @rx_buf_pgcnt: rx_buf page refcount * * This function will pull an Rx buffer from the ring and synchronize it * for use by the CPU. */ static struct ice_rx_buf * ice_get_rx_buf(struct ice_ring *rx_ring, struct sk_buff **skb, - const unsigned int size) + const unsigned int size, int *rx_buf_pgcnt) { struct ice_rx_buf *rx_buf; rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean]; + *rx_buf_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buf->page); +#else + 0; +#endif prefetchw(rx_buf->page); *skb = rx_buf->skb; @@ -1006,12 +1015,15 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * ice_put_rx_buf - Clean up used buffer and either recycle or free * @rx_ring: Rx descriptor ring to transact packets on * @rx_buf: Rx buffer to pull data from + * @rx_buf_pgcnt: Rx buffer page count pre xdp_do_redirect() * * This function will update next_to_clean and then clean up the contents * of the rx_buf. It will either recycle the buffer or unmap it and free * the associated resources. */ -static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) +static void +ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, + int rx_buf_pgcnt) { u16 ntc = rx_ring->next_to_clean + 1; @@ -1022,7 +1034,7 @@ static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) if (!rx_buf) return; - if (ice_can_reuse_rx_page(rx_buf)) { + if (ice_can_reuse_rx_page(rx_buf, rx_buf_pgcnt)) { /* hand second half of page back to the ring */ ice_reuse_rx_page(rx_ring, rx_buf); } else { @@ -1097,6 +1109,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) struct sk_buff *skb; unsigned int size; u16 stat_err_bits; + int rx_buf_pgcnt; u16 vlan_tag = 0; u8 rx_ptype; @@ -1119,7 +1132,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) dma_rmb(); if (rx_desc->wb.rxdid == FDIR_DESC_RXDID || !rx_ring->netdev) { - ice_put_rx_buf(rx_ring, NULL); + ice_put_rx_buf(rx_ring, NULL, 0); cleaned_count++; continue; } @@ -1128,7 +1141,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) ICE_RX_FLX_DESC_PKT_LEN_M; /* retrieve a buffer from the ring */ - rx_buf = ice_get_rx_buf(rx_ring, &skb, size); + rx_buf = ice_get_rx_buf(rx_ring, &skb, size, &rx_buf_pgcnt); if (!size) { xdp.data = NULL; @@ -1168,7 +1181,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) total_rx_pkts++; cleaned_count++; - ice_put_rx_buf(rx_ring, rx_buf); + ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt); continue; construct_skb: if (skb) { @@ -1187,7 +1200,7 @@ construct_skb: break; } - ice_put_rx_buf(rx_ring, rx_buf); + ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt); cleaned_count++; /* skip if it is NOP desc */ diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 0286d2fceee4d3..aaa954aae57448 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -138,6 +138,8 @@ struct vf_mac_filter { /* this is the size past which hardware will drop packets when setting LPE=0 */ #define MAXIMUM_ETHERNET_VLAN_SIZE 1522 +#define IGB_ETH_PKT_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) + /* Supported Rx Buffer Sizes */ #define IGB_RXBUFFER_256 256 #define IGB_RXBUFFER_1536 1536 @@ -247,6 +249,9 @@ enum igb_tx_flags { #define IGB_SFF_ADDRESSING_MODE 0x4 #define IGB_SFF_8472_UNSUP 0x00 +/* TX resources are shared between XDP and netstack + * and we need to tag the buffer type to distinguish them + */ enum igb_tx_buf_type { IGB_TYPE_SKB = 0, IGB_TYPE_XDP, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 5fc2c381da55de..0d343d05097392 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2824,20 +2824,25 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, } } -static int igb_xdp_setup(struct net_device *dev, struct bpf_prog *prog) +static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf) { - int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + int i, frame_size = dev->mtu + IGB_ETH_PKT_HDR_PAD; struct igb_adapter *adapter = netdev_priv(dev); + struct bpf_prog *prog = bpf->prog, *old_prog; bool running = netif_running(dev); - struct bpf_prog *old_prog; bool need_reset; /* verify igb ring attributes are sufficient for XDP */ for (i = 0; i < adapter->num_rx_queues; i++) { struct igb_ring *ring = adapter->rx_ring[i]; - if (frame_size > igb_rx_bufsz(ring)) + if (frame_size > igb_rx_bufsz(ring)) { + NL_SET_ERR_MSG_MOD(bpf->extack, + "The RX buffer size is too small for the frame size"); + netdev_warn(dev, "XDP RX buffer size %d is too small for the frame size %d\n", + igb_rx_bufsz(ring), frame_size); return -EINVAL; + } } old_prog = xchg(&adapter->xdp_prog, prog); @@ -2869,7 +2874,7 @@ static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: - return igb_xdp_setup(dev, xdp->prog); + return igb_xdp_setup(dev, xdp); default: return -EINVAL; } @@ -2910,10 +2915,12 @@ static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) */ tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; if (unlikely(!tx_ring)) - return -ENXIO; + return IGB_XDP_CONSUMED; nq = txring_txq(tx_ring); __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + nq->trans_start = jiffies; ret = igb_xmit_xdp_ring(adapter, tx_ring, xdpf); __netif_tx_unlock(nq); @@ -2946,6 +2953,9 @@ static int igb_xdp_xmit(struct net_device *dev, int n, nq = txring_txq(tx_ring); __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + nq->trans_start = jiffies; + for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; int err; @@ -3950,8 +3960,7 @@ static int igb_sw_init(struct igb_adapter *adapter) /* set default work limits */ adapter->tx_work_limit = IGB_DEFAULT_TX_WORK; - adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + - VLAN_HLEN; + adapter->max_frame_size = netdev->mtu + IGB_ETH_PKT_HDR_PAD; adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; spin_lock_init(&adapter->nfc_lock); @@ -6491,7 +6500,7 @@ static void igb_get_stats64(struct net_device *netdev, static int igb_change_mtu(struct net_device *netdev, int new_mtu) { struct igb_adapter *adapter = netdev_priv(netdev); - int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + int max_frame = new_mtu + IGB_ETH_PKT_HDR_PAD; if (adapter->xdp_prog) { int i; @@ -6500,7 +6509,9 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu) struct igb_ring *ring = adapter->rx_ring[i]; if (max_frame > igb_rx_bufsz(ring)) { - netdev_warn(adapter->netdev, "Requested MTU size is not supported with XDP\n"); + netdev_warn(adapter->netdev, + "Requested MTU size is not supported with XDP. Max frame size is %d\n", + max_frame); return -EINVAL; } } @@ -8351,6 +8362,7 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, SKB_DATA_ALIGN(xdp->data_end - xdp->data_hard_start); #endif + unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; /* prefetch first cache line of first page */ @@ -8365,6 +8377,9 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, skb_reserve(skb, xdp->data - xdp->data_hard_start); __skb_put(skb, xdp->data_end - xdp->data); + if (metasize) + skb_metadata_set(skb, metasize); + /* pull timestamp out of packet data */ if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb); @@ -8771,7 +8786,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) rx_ring->skb = skb; if (xdp_xmit & IGB_XDP_REDIR) - xdp_do_flush_map(); + xdp_do_flush(); if (xdp_xmit & IGB_XDP_TX) { struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 45ae33e1530384..f3f449f53920f3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1945,7 +1945,8 @@ static inline bool ixgbe_page_is_reserved(struct page *page) return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } -static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer) +static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -1956,7 +1957,7 @@ static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) return false; #else /* The last offset is a bit aggressive in that we assume the @@ -2021,11 +2022,18 @@ static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, static struct ixgbe_rx_buffer *ixgbe_get_rx_buffer(struct ixgbe_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff **skb, - const unsigned int size) + const unsigned int size, + int *rx_buffer_pgcnt) { struct ixgbe_rx_buffer *rx_buffer; rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + *rx_buffer_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif prefetchw(rx_buffer->page); *skb = rx_buffer->skb; @@ -2055,9 +2063,10 @@ skip_sync: static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *rx_buffer, - struct sk_buff *skb) + struct sk_buff *skb, + int rx_buffer_pgcnt) { - if (ixgbe_can_reuse_rx_page(rx_buffer)) { + if (ixgbe_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { /* hand second half of page back to the ring */ ixgbe_reuse_rx_page(rx_ring, rx_buffer); } else { @@ -2303,6 +2312,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, union ixgbe_adv_rx_desc *rx_desc; struct ixgbe_rx_buffer *rx_buffer; struct sk_buff *skb; + int rx_buffer_pgcnt; unsigned int size; /* return some buffers to hardware, one at a time is too slow */ @@ -2322,7 +2332,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, */ dma_rmb(); - rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size); + rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size, &rx_buffer_pgcnt); /* retrieve a buffer from the ring */ if (!skb) { @@ -2367,7 +2377,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, break; } - ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb); + ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb, rx_buffer_pgcnt); cleaned_count++; /* place incomplete frames back on ring for completion */ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 106513f772c383..6f290319b61787 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1378,8 +1378,10 @@ static void mlx4_en_tx_timeout(struct net_device *dev, unsigned int txqueue) tx_ring->cons, tx_ring->prod); priv->port_stats.tx_timeout++; - en_dbg(DRV, priv, "Scheduling watchdog\n"); - queue_work(mdev->workqueue, &priv->watchdog_task); + if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) { + en_dbg(DRV, priv, "Scheduling port restart\n"); + queue_work(mdev->workqueue, &priv->restart_task); + } } @@ -1733,6 +1735,7 @@ int mlx4_en_start_port(struct net_device *dev) mlx4_en_deactivate_cq(priv, cq); goto tx_err; } + clear_bit(MLX4_EN_TX_RING_STATE_RECOVERING, &tx_ring->state); if (t != TX_XDP) { tx_ring->tx_queue = netdev_get_tx_queue(dev, i); tx_ring->recycle_ring = NULL; @@ -1829,6 +1832,7 @@ int mlx4_en_start_port(struct net_device *dev) local_bh_enable(); } + clear_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state); netif_tx_start_all_queues(dev); netif_device_attach(dev); @@ -1999,7 +2003,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach) static void mlx4_en_restart(struct work_struct *work) { struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, - watchdog_task); + restart_task); struct mlx4_en_dev *mdev = priv->mdev; struct net_device *dev = priv->dev; @@ -2377,7 +2381,7 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) if (netif_running(dev)) { mutex_lock(&mdev->state_lock); if (!mdev->device_up) { - /* NIC is probably restarting - let watchdog task reset + /* NIC is probably restarting - let restart task reset * the port */ en_dbg(DRV, priv, "Change MTU called with card down!?\n"); } else { @@ -2386,7 +2390,9 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) if (err) { en_err(priv, "Failed restarting port:%d\n", priv->port); - queue_work(mdev->workqueue, &priv->watchdog_task); + if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, + &priv->state)) + queue_work(mdev->workqueue, &priv->restart_task); } } mutex_unlock(&mdev->state_lock); @@ -2792,7 +2798,8 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) if (err) { en_err(priv, "Failed starting port %d for XDP change\n", priv->port); - queue_work(mdev->workqueue, &priv->watchdog_task); + if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) + queue_work(mdev->workqueue, &priv->restart_task); } } @@ -3165,7 +3172,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev); spin_lock_init(&priv->stats_lock); INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode); - INIT_WORK(&priv->watchdog_task, mlx4_en_restart); + INIT_WORK(&priv->restart_task, mlx4_en_restart); INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate); INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats); INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 3ddb7268e415f8..59b097cda32786 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -392,6 +392,35 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring) return cnt; } +static void mlx4_en_handle_err_cqe(struct mlx4_en_priv *priv, struct mlx4_err_cqe *err_cqe, + u16 cqe_index, struct mlx4_en_tx_ring *ring) +{ + struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_tx_info *tx_info; + struct mlx4_en_tx_desc *tx_desc; + u16 wqe_index; + int desc_size; + + en_err(priv, "CQE error - cqn 0x%x, ci 0x%x, vendor syndrome: 0x%x syndrome: 0x%x\n", + ring->sp_cqn, cqe_index, err_cqe->vendor_err_syndrome, err_cqe->syndrome); + print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, err_cqe, sizeof(*err_cqe), + false); + + wqe_index = be16_to_cpu(err_cqe->wqe_index) & ring->size_mask; + tx_info = &ring->tx_info[wqe_index]; + desc_size = tx_info->nr_txbb << LOG_TXBB_SIZE; + en_err(priv, "Related WQE - qpn 0x%x, wqe index 0x%x, wqe size 0x%x\n", ring->qpn, + wqe_index, desc_size); + tx_desc = ring->buf + (wqe_index << LOG_TXBB_SIZE); + print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, tx_desc, desc_size, false); + + if (test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) + return; + + en_err(priv, "Scheduling port restart\n"); + queue_work(mdev->workqueue, &priv->restart_task); +} + int mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int napi_budget) { @@ -438,13 +467,10 @@ int mlx4_en_process_tx_cq(struct net_device *dev, dma_rmb(); if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == - MLX4_CQE_OPCODE_ERROR)) { - struct mlx4_err_cqe *cqe_err = (struct mlx4_err_cqe *)cqe; - - en_err(priv, "CQE error - vendor syndrome: 0x%x syndrome: 0x%x\n", - cqe_err->vendor_err_syndrome, - cqe_err->syndrome); - } + MLX4_CQE_OPCODE_ERROR)) + if (!test_and_set_bit(MLX4_EN_TX_RING_STATE_RECOVERING, &ring->state)) + mlx4_en_handle_err_cqe(priv, (struct mlx4_err_cqe *)cqe, index, + ring); /* Skip over last polled CQE */ new_index = be16_to_cpu(cqe->wqe_index) & size_mask; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index a46efe37cfa90f..30378e4c90b5b1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -271,6 +271,10 @@ struct mlx4_en_page_cache { } buf[MLX4_EN_CACHE_SIZE]; }; +enum { + MLX4_EN_TX_RING_STATE_RECOVERING, +}; + struct mlx4_en_priv; struct mlx4_en_tx_ring { @@ -317,6 +321,7 @@ struct mlx4_en_tx_ring { * Only queue_stopped might be used if BQL is not properly working. */ unsigned long queue_stopped; + unsigned long state; struct mlx4_hwq_resources sp_wqres; struct mlx4_qp sp_qp; struct mlx4_qp_context sp_context; @@ -530,6 +535,10 @@ struct mlx4_en_stats_bitmap { struct mutex mutex; /* for mutual access to stats bitmap */ }; +enum { + MLX4_EN_STATE_FLAG_RESTARTING, +}; + struct mlx4_en_priv { struct mlx4_en_dev *mdev; struct mlx4_en_port_profile *prof; @@ -595,7 +604,7 @@ struct mlx4_en_priv { struct mlx4_en_cq *rx_cq[MAX_RX_RINGS]; struct mlx4_qp drop_qp; struct work_struct rx_mode_task; - struct work_struct watchdog_task; + struct work_struct restart_task; struct work_struct linkstate_task; struct delayed_work stats_task; struct delayed_work service_task; @@ -641,6 +650,7 @@ struct mlx4_en_priv { u32 pflags; u8 rss_key[MLX4_EN_RSS_KEY_SIZE]; u8 rss_hash_fn; + unsigned long state; }; enum mlx4_en_wol { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index efef5476a57710..223f69da7e95fc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -246,13 +246,7 @@ static int imx_dwmac_probe(struct platform_device *pdev) goto err_parse_dt; } - ret = dma_set_mask_and_coherent(&pdev->dev, - DMA_BIT_MASK(dwmac->ops->addr_width)); - if (ret) { - dev_err(&pdev->dev, "DMA mask set failed\n"); - goto err_dma_mask; - } - + plat_dat->addr64 = dwmac->ops->addr_width; plat_dat->init = imx_dwmac_init; plat_dat->exit = imx_dwmac_exit; plat_dat->fix_mac_speed = imx_dwmac_fix_speed; @@ -272,7 +266,6 @@ static int imx_dwmac_probe(struct platform_device *pdev) err_dwmac_init: err_drv_probe: imx_dwmac_exit(pdev, plat_dat->bsp_priv); -err_dma_mask: err_parse_dt: err_match_data: stmmac_remove_config_dt(pdev, plat_dat); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index 6e30d7eb4983d1..0b4ee2dbb691d3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -22,7 +22,7 @@ int dwmac4_dma_reset(void __iomem *ioaddr) return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value, !(value & DMA_BUS_MODE_SFT_RESET), - 10000, 100000); + 10000, 1000000); } void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ba45fe237512cb..c33db79cdd0ad1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1534,6 +1534,19 @@ static void dma_free_tx_skbufs(struct stmmac_priv *priv, u32 queue) } /** + * stmmac_free_tx_skbufs - free TX skb buffers + * @priv: private structure + */ +static void stmmac_free_tx_skbufs(struct stmmac_priv *priv) +{ + u32 tx_queue_cnt = priv->plat->tx_queues_to_use; + u32 queue; + + for (queue = 0; queue < tx_queue_cnt; queue++) + dma_free_tx_skbufs(priv, queue); +} + +/** * free_dma_rx_desc_resources - free RX dma desc resources * @priv: private structure */ @@ -2895,9 +2908,6 @@ static int stmmac_release(struct net_device *dev) struct stmmac_priv *priv = netdev_priv(dev); u32 chan; - if (priv->eee_enabled) - del_timer_sync(&priv->eee_ctrl_timer); - if (device_may_wakeup(priv->device)) phylink_speed_down(priv->phylink, false); /* Stop and disconnect the PHY */ @@ -2916,6 +2926,11 @@ static int stmmac_release(struct net_device *dev) if (priv->lpi_irq > 0) free_irq(priv->lpi_irq, dev); + if (priv->eee_enabled) { + priv->tx_path_in_lpi_mode = false; + del_timer_sync(&priv->eee_ctrl_timer); + } + /* Stop TX/RX DMA and clear the descriptors */ stmmac_stop_all_dma(priv); @@ -4930,6 +4945,14 @@ int stmmac_dvr_probe(struct device *device, dev_info(priv->device, "SPH feature enabled\n"); } + /* The current IP register MAC_HW_Feature1[ADDR64] only define + * 32/40/64 bit width, but some SOC support others like i.MX8MP + * support 34 bits but it map to 40 bits width in MAC_HW_Feature1[ADDR64]. + * So overwrite dma_cap.addr64 according to HW real design. + */ + if (priv->plat->addr64) + priv->dma_cap.addr64 = priv->plat->addr64; + if (priv->dma_cap.addr64) { ret = dma_set_mask_and_coherent(device, DMA_BIT_MASK(priv->dma_cap.addr64)); @@ -5142,6 +5165,11 @@ int stmmac_suspend(struct device *dev) for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++) del_timer_sync(&priv->tx_queue[chan].txtimer); + if (priv->eee_enabled) { + priv->tx_path_in_lpi_mode = false; + del_timer_sync(&priv->eee_ctrl_timer); + } + /* Stop TX/RX DMA */ stmmac_stop_all_dma(priv); @@ -5247,11 +5275,20 @@ int stmmac_resume(struct device *dev) return ret; } + if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { + rtnl_lock(); + phylink_start(priv->phylink); + /* We may have called phylink_speed_down before */ + phylink_speed_up(priv->phylink); + rtnl_unlock(); + } + rtnl_lock(); mutex_lock(&priv->lock); stmmac_reset_queues_param(priv); + stmmac_free_tx_skbufs(priv); stmmac_clear_descriptors(priv); stmmac_hw_setup(ndev, false); @@ -5265,14 +5302,6 @@ int stmmac_resume(struct device *dev) mutex_unlock(&priv->lock); rtnl_unlock(); - if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { - rtnl_lock(); - phylink_start(priv->phylink); - /* We may have called phylink_speed_down before */ - phylink_speed_up(priv->phylink); - rtnl_unlock(); - } - phylink_mac_change(priv->phylink, true); netif_device_attach(ndev); diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 60c199fcb91e5b..030185301014c3 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1351,7 +1351,6 @@ static int temac_probe(struct platform_device *pdev) struct device_node *temac_np = dev_of_node(&pdev->dev), *dma_np; struct temac_local *lp; struct net_device *ndev; - struct resource *res; const void *addr; __be32 *p; bool little_endian; @@ -1500,13 +1499,11 @@ static int temac_probe(struct platform_device *pdev) of_node_put(dma_np); } else if (pdata) { /* 2nd memory resource specifies DMA registers */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - lp->sdma_regs = devm_ioremap(&pdev->dev, res->start, - resource_size(res)); - if (!lp->sdma_regs) { + lp->sdma_regs = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(lp->sdma_regs)) { dev_err(&pdev->dev, "could not map DMA registers\n"); - return -ENOMEM; + return PTR_ERR(lp->sdma_regs); } if (pdata->dma_little_endian) { lp->dma_in = temac_dma_in32_le; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 8ae9ce2014a4a3..1426bfc009bc39 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -257,21 +257,11 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, skb_dst_set(skb, &tun_dst->dst); /* Ignore packet loops (and multicast echo) */ - if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) - goto rx_error; - - switch (skb_protocol(skb, true)) { - case htons(ETH_P_IP): - if (pskb_may_pull(skb, sizeof(struct iphdr))) - goto rx_error; - break; - case htons(ETH_P_IPV6): - if (pskb_may_pull(skb, sizeof(struct ipv6hdr))) - goto rx_error; - break; - default: - goto rx_error; + if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) { + geneve->dev->stats.rx_errors++; + goto drop; } + oiph = skb_network_header(skb); skb_reset_network_header(skb); @@ -308,8 +298,6 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, dev_sw_netstats_rx_add(geneve->dev, len); return; -rx_error: - geneve->dev->stats.rx_errors++; drop: /* Consume bad packet */ kfree_skb(skb); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 628e28903b8b81..15ca6b4167cc90 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -170,6 +170,7 @@ struct plat_stmmacenet_data { int unicast_filter_entries; int tx_fifo_size; int rx_fifo_size; + u32 addr64; u32 rx_queues_to_use; u32 tx_queues_to_use; u8 rx_sched_algorithm; diff --git a/include/net/bonding.h b/include/net/bonding.h index d9d0ff3b0ad327..adc3da77697002 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -86,10 +86,8 @@ #define bond_for_each_slave_rcu(bond, pos, iter) \ netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) -#ifdef CONFIG_XFRM_OFFLOAD #define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) -#endif /* CONFIG_XFRM_OFFLOAD */ #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; diff --git a/net/can/isotp.c b/net/can/isotp.c index d78ab13bd8be99..26bdc3c20b7e48 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1157,6 +1157,9 @@ static int isotp_setsockopt(struct socket *sock, int level, int optname, if (level != SOL_CAN_ISOTP) return -EINVAL; + if (so->bound) + return -EISCONN; + switch (optname) { case CAN_ISOTP_OPTS: if (optlen != sizeof(struct can_isotp_options)) diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index d4474c812b6420..715b67f6c62f31 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -381,10 +381,8 @@ static void __flow_block_indr_cleanup(void (*release)(void *cb_priv), list_for_each_entry_safe(this, next, &flow_block_indr_list, indr.list) { if (this->release == release && - this->indr.cb_priv == cb_priv) { + this->indr.cb_priv == cb_priv) list_move(&this->indr.list, cleanup_list); - return; - } } } diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index 1fb3603d92ad30..0515d6604b3b9d 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -628,6 +628,8 @@ int ethnl_parse_bitset(unsigned long *val, unsigned long *mask, return ret; change_bits = nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]); + if (change_bits > nbits) + change_bits = nbits; bitmap_from_arr32(val, nla_data(tb[ETHTOOL_A_BITSET_VALUE]), change_bits); if (change_bits < nbits) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 389d1b34024854..ef4bdb038a4bbb 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -510,7 +510,6 @@ static void tcp_init_buffer_space(struct sock *sk) if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) tcp_sndbuf_expand(sk); - tp->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss); tcp_mstamp_refresh(tp); tp->rcvq_space.time = tp->tcp_mstamp; tp->rcvq_space.seq = tp->copied_seq; @@ -534,6 +533,8 @@ static void tcp_init_buffer_space(struct sock *sk) tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp); tp->snd_cwnd_stamp = tcp_jiffies32; + tp->rcvq_space.space = min3(tp->rcv_ssthresh, tp->rcv_wnd, + (u32)TCP_INIT_CWND * tp->advmss); } /* 4. Recalculate window clamp after socket hit its memory bounds. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 8391aa29e7a41e..595dcc3afac5c1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -984,7 +984,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | + (inet_sk(sk)->tos & INET_ECN_MASK) : inet_sk(sk)->tos; if (!INET_ECN_is_capable(tos) && @@ -1541,7 +1542,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = prandom_u32(); - /* Set ToS of the new socket based upon the value of incoming SYN. */ + /* Set ToS of the new socket based upon the value of incoming SYN. + * ECT bits are set later in tcp_init_transfer(). + */ if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bf48cd73e96787..99011768c26402 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1880,7 +1880,8 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) * window, and remember whether we were cwnd-limited then. */ if (!before(tp->snd_una, tp->max_packets_seq) || - tp->packets_out > tp->max_packets_out) { + tp->packets_out > tp->max_packets_out || + is_cwnd_limited) { tp->max_packets_out = tp->packets_out; tp->max_packets_seq = tp->snd_nxt; tp->is_cwnd_limited = is_cwnd_limited; @@ -2702,6 +2703,10 @@ repair: else tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED); + is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); + if (likely(sent_pkts || is_cwnd_limited)) + tcp_cwnd_validate(sk, is_cwnd_limited); + if (likely(sent_pkts)) { if (tcp_in_cwnd_reduction(sk)) tp->prr_out += sent_pkts; @@ -2709,8 +2714,6 @@ repair: /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk, false); - is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); - tcp_cwnd_validate(sk, is_cwnd_limited); return false; } return !tp->packets_out && !tcp_write_queue_empty(sk); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 992cbf3eb9e38b..991dc36f95ff02 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -528,7 +528,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | + (np->tclass & INET_ECN_MASK) : np->tclass; if (!INET_ECN_is_capable(tclass) && @@ -1320,7 +1321,9 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * if (np->repflow) newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); - /* Set ToS of the new socket based upon the value of incoming SYN. */ + /* Set ToS of the new socket based upon the value of incoming SYN. + * ECT bits are set later in tcp_init_transfer(). + */ if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; diff --git a/net/tipc/node.c b/net/tipc/node.c index c95d037fde51ea..83978d5dae5941 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2181,9 +2181,11 @@ void tipc_node_apply_property(struct net *net, struct tipc_bearer *b, &xmitq); else if (prop == TIPC_NLA_PROP_MTU) tipc_link_set_mtu(e->link, b->mtu); + + /* Update MTU for node link entry */ + e->mtu = tipc_link_mss(e->link); } - /* Update MTU for node link entry */ - e->mtu = tipc_link_mss(e->link); + tipc_node_write_unlock(n); tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr, NULL); } |