diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox')
31 files changed, 419 insertions, 247 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c index c7e939945259..53daa6ca5d83 100644 --- a/drivers/net/ethernet/mellanox/mlx4/catas.c +++ b/drivers/net/ethernet/mellanox/mlx4/catas.c @@ -158,7 +158,7 @@ static int mlx4_reset_slave(struct mlx4_dev *dev) return -ETIMEDOUT; } -static int mlx4_comm_internal_err(u32 slave_read) +int mlx4_comm_internal_err(u32 slave_read) { return (u32)COMM_CHAN_EVENT_INTERNAL_ERR == (slave_read & (u32)COMM_CHAN_EVENT_INTERNAL_ERR) ? 1 : 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index a849da92f857..6b8635378f1f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -101,13 +101,19 @@ void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn) { struct mlx4_cq *cq; + rcu_read_lock(); cq = radix_tree_lookup(&mlx4_priv(dev)->cq_table.tree, cqn & (dev->caps.num_cqs - 1)); + rcu_read_unlock(); + if (!cq) { mlx4_dbg(dev, "Completion event for bogus CQ %08x\n", cqn); return; } + /* Acessing the CQ outside of rcu_read_lock is safe, because + * the CQ is freed only after interrupt handling is completed. + */ ++cq->arm_sn; cq->comp(cq); @@ -118,23 +124,19 @@ void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type) struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table; struct mlx4_cq *cq; - spin_lock(&cq_table->lock); - + rcu_read_lock(); cq = radix_tree_lookup(&cq_table->tree, cqn & (dev->caps.num_cqs - 1)); - if (cq) - atomic_inc(&cq->refcount); - - spin_unlock(&cq_table->lock); + rcu_read_unlock(); if (!cq) { - mlx4_warn(dev, "Async event for bogus CQ %08x\n", cqn); + mlx4_dbg(dev, "Async event for bogus CQ %08x\n", cqn); return; } + /* Acessing the CQ outside of rcu_read_lock is safe, because + * the CQ is freed only after interrupt handling is completed. + */ cq->event(cq, event_type); - - if (atomic_dec_and_test(&cq->refcount)) - complete(&cq->free); } static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox, @@ -301,9 +303,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, if (err) return err; - spin_lock_irq(&cq_table->lock); + spin_lock(&cq_table->lock); err = radix_tree_insert(&cq_table->tree, cq->cqn, cq); - spin_unlock_irq(&cq_table->lock); + spin_unlock(&cq_table->lock); if (err) goto err_icm; @@ -349,9 +351,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, return 0; err_radix: - spin_lock_irq(&cq_table->lock); + spin_lock(&cq_table->lock); radix_tree_delete(&cq_table->tree, cq->cqn); - spin_unlock_irq(&cq_table->lock); + spin_unlock(&cq_table->lock); err_icm: mlx4_cq_free_icm(dev, cq->cqn); @@ -370,15 +372,15 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq) if (err) mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn); + spin_lock(&cq_table->lock); + radix_tree_delete(&cq_table->tree, cq->cqn); + spin_unlock(&cq_table->lock); + synchronize_irq(priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq); if (priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq != priv->eq_table.eq[MLX4_EQ_ASYNC].irq) synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq); - spin_lock_irq(&cq_table->lock); - radix_tree_delete(&cq_table->tree, cq->cqn); - spin_unlock_irq(&cq_table->lock); - if (atomic_dec_and_test(&cq->refcount)) complete(&cq->free); wait_for_completion(&cq->free); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c index a5fc46bbcbe2..d4d97ca12e83 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -88,10 +88,17 @@ void mlx4_en_remove_timestamp(struct mlx4_en_dev *mdev) } } +#define MLX4_EN_WRAP_AROUND_SEC 10UL +/* By scheduling the overflow check every 5 seconds, we have a reasonably + * good chance we wont miss a wrap around. + * TOTO: Use a timer instead of a work queue to increase the guarantee. + */ +#define MLX4_EN_OVERFLOW_PERIOD (MLX4_EN_WRAP_AROUND_SEC * HZ / 2) + void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev) { bool timeout = time_is_before_jiffies(mdev->last_overflow_check + - mdev->overflow_period); + MLX4_EN_OVERFLOW_PERIOD); unsigned long flags; if (timeout) { @@ -236,7 +243,6 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = { .enable = mlx4_en_phc_enable, }; -#define MLX4_EN_WRAP_AROUND_SEC 10ULL /* This function calculates the max shift that enables the user range * of MLX4_EN_WRAP_AROUND_SEC values in the cycles register. @@ -261,7 +267,6 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) { struct mlx4_dev *dev = mdev->dev; unsigned long flags; - u64 ns, zero = 0; /* mlx4_en_init_timestamp is called for each netdev. * mdev->ptp_clock is common for all ports, skip initialization if @@ -285,13 +290,6 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) ktime_to_ns(ktime_get_real())); write_unlock_irqrestore(&mdev->clock_lock, flags); - /* Calculate period in seconds to call the overflow watchdog - to make - * sure counter is checked at least once every wrap around. - */ - ns = cyclecounter_cyc2ns(&mdev->cycles, mdev->cycles.mask, zero, &zero); - do_div(ns, NSEC_PER_SEC / 2 / HZ); - mdev->overflow_period = ns; - /* Configure the PHC */ mdev->ptp_clock_info = mlx4_en_ptp_clock_info; snprintf(mdev->ptp_clock_info.name, 16, "mlx4 ptp"); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 4d3ddc2f7e43..bcbb80ff86a7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -444,8 +444,14 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv) ring->cqn = priv->rx_cq[ring_ind]->mcq.cqn; ring->stride = stride; - if (ring->stride <= TXBB_SIZE) + if (ring->stride <= TXBB_SIZE) { + /* Stamp first unused send wqe */ + __be32 *ptr = (__be32 *)ring->buf; + __be32 stamp = cpu_to_be32(1 << STAMP_SHIFT); + *ptr = stamp; + /* Move pointer to start of rx section */ ring->buf += TXBB_SIZE; + } ring->log_stride = ffs(ring->stride) - 1; ring->buf_size = ring->size * ring->stride; @@ -718,16 +724,21 @@ static inline __wsum get_fixed_vlan_csum(__wsum hw_checksum, * header, the HW adds it. To address that, we are subtracting the pseudo * header checksum from the checksum value provided by the HW. */ -static void get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb, - struct iphdr *iph) +static int get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb, + struct iphdr *iph) { __u16 length_for_csum = 0; __wsum csum_pseudo_header = 0; + __u8 ipproto = iph->protocol; + + if (unlikely(ipproto == IPPROTO_SCTP)) + return -1; length_for_csum = (be16_to_cpu(iph->tot_len) - (iph->ihl << 2)); csum_pseudo_header = csum_tcpudp_nofold(iph->saddr, iph->daddr, - length_for_csum, iph->protocol, 0); + length_for_csum, ipproto, 0); skb->csum = csum_sub(hw_checksum, csum_pseudo_header); + return 0; } #if IS_ENABLED(CONFIG_IPV6) @@ -738,17 +749,20 @@ static void get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb, static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb, struct ipv6hdr *ipv6h) { + __u8 nexthdr = ipv6h->nexthdr; __wsum csum_pseudo_hdr = 0; - if (unlikely(ipv6h->nexthdr == IPPROTO_FRAGMENT || - ipv6h->nexthdr == IPPROTO_HOPOPTS)) + if (unlikely(nexthdr == IPPROTO_FRAGMENT || + nexthdr == IPPROTO_HOPOPTS || + nexthdr == IPPROTO_SCTP)) return -1; - hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(ipv6h->nexthdr)); + hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(nexthdr)); csum_pseudo_hdr = csum_partial(&ipv6h->saddr, sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0); csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ipv6h->payload_len); - csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ntohs(ipv6h->nexthdr)); + csum_pseudo_hdr = csum_add(csum_pseudo_hdr, + (__force __wsum)htons(nexthdr)); skb->csum = csum_sub(hw_checksum, csum_pseudo_hdr); skb->csum = csum_add(skb->csum, csum_partial(ipv6h, sizeof(struct ipv6hdr), 0)); @@ -771,11 +785,10 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va, } if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4)) - get_fixed_ipv4_csum(hw_checksum, skb, hdr); + return get_fixed_ipv4_csum(hw_checksum, skb, hdr); #if IS_ENABLED(CONFIG_IPV6) - else if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6)) - if (unlikely(get_fixed_ipv6_csum(hw_checksum, skb, hdr))) - return -1; + if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6)) + return get_fixed_ipv6_csum(hw_checksum, skb, hdr); #endif return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index cd3638e6fe25..0509996957d9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -554,8 +554,9 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) break; case MLX4_EVENT_TYPE_SRQ_LIMIT: - mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT\n", - __func__); + mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT. srq_no=0x%x, eq 0x%x\n", + __func__, be32_to_cpu(eqe->event.srq.srqn), + eq->eqn); case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR: if (mlx4_is_master(dev)) { /* forward only to slave owning the SRQ */ @@ -570,15 +571,19 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) eq->eqn, eq->cons_index, ret); break; } - mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n", - __func__, slave, - be32_to_cpu(eqe->event.srq.srqn), - eqe->type, eqe->subtype); + if (eqe->type == + MLX4_EVENT_TYPE_SRQ_CATAS_ERROR) + mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n", + __func__, slave, + be32_to_cpu(eqe->event.srq.srqn), + eqe->type, eqe->subtype); if (!ret && slave != dev->caps.function) { - mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n", - __func__, eqe->type, - eqe->subtype, slave); + if (eqe->type == + MLX4_EVENT_TYPE_SRQ_CATAS_ERROR) + mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n", + __func__, eqe->type, + eqe->subtype, slave); mlx4_slave_event(dev, slave, eqe); break; } diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c index 2a9dd460a95f..e1f9e7cebf8f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/icm.c +++ b/drivers/net/ethernet/mellanox/mlx4/icm.c @@ -118,8 +118,13 @@ static int mlx4_alloc_icm_coherent(struct device *dev, struct scatterlist *mem, if (!buf) return -ENOMEM; + if (offset_in_page(buf)) { + dma_free_coherent(dev, PAGE_SIZE << order, + buf, sg_dma_address(mem)); + return -ENOMEM; + } + sg_set_buf(mem, buf, PAGE_SIZE << order); - BUG_ON(mem->offset); sg_dma_len(mem) = PAGE_SIZE << order; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index 0e8b7c44931f..8258d08acd8c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -222,6 +222,18 @@ void mlx4_unregister_device(struct mlx4_dev *dev) return; mlx4_stop_catas_poll(dev); + if (dev->persist->interface_state & MLX4_INTERFACE_STATE_DELETION && + mlx4_is_slave(dev)) { + /* In mlx4_remove_one on a VF */ + u32 slave_read = + swab32(readl(&mlx4_priv(dev)->mfunc.comm->slave_read)); + + if (mlx4_comm_internal_err(slave_read)) { + mlx4_dbg(dev, "%s: comm channel is down, entering error state.\n", + __func__); + mlx4_enter_error_state(dev->persist); + } + } mutex_lock(&intf_mutex); list_for_each_entry(intf, &intf_list, list) diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 75d07fa9d0b1..727122de7df0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -42,6 +42,7 @@ #include <linux/io-mapping.h> #include <linux/delay.h> #include <linux/kmod.h> +#include <linux/etherdevice.h> #include <net/devlink.h> #include <linux/mlx4/device.h> @@ -429,7 +430,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) /* Virtual PCI function needs to determine UAR page size from * firmware. Only master PCI function can set the uar page size */ - if (enable_4k_uar) + if (enable_4k_uar || !dev->persist->num_vfs) dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT; else dev->uar_page_shift = PAGE_SHIFT; @@ -782,6 +783,23 @@ int mlx4_is_slave_active(struct mlx4_dev *dev, int slave) } EXPORT_SYMBOL(mlx4_is_slave_active); +void mlx4_handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl, + struct _rule_hw *eth_header) +{ + if (is_multicast_ether_addr(eth_header->eth.dst_mac) || + is_broadcast_ether_addr(eth_header->eth.dst_mac)) { + struct mlx4_net_trans_rule_hw_eth *eth = + (struct mlx4_net_trans_rule_hw_eth *)eth_header; + struct _rule_hw *next_rule = (struct _rule_hw *)(eth + 1); + bool last_rule = next_rule->size == 0 && next_rule->id == 0 && + next_rule->rsvd == 0; + + if (last_rule) + ctrl->prio = cpu_to_be16(MLX4_DOMAIN_NIC); + } +} +EXPORT_SYMBOL(mlx4_handle_eth_header_mcast_prio); + static void slave_adjust_steering_mode(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap, struct mlx4_init_hca_param *hca_param) @@ -823,8 +841,6 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) return -ENOSYS; } - mlx4_log_num_mgm_entry_size = hca_param.log_mc_entry_sz; - dev->caps.hca_core_clock = hca_param.hca_core_clock; memset(&dev_cap, 0, sizeof(dev_cap)); @@ -2251,7 +2267,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev) dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1; - if (enable_4k_uar) { + if (enable_4k_uar || !dev->persist->num_vfs) { init_hca.log_uar_sz = ilog2(dev->caps.num_uars) + PAGE_SHIFT - DEFAULT_UAR_PAGE_SHIFT; init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12; @@ -4020,49 +4036,51 @@ int mlx4_restart_one(struct pci_dev *pdev) return err; } +#define MLX_SP(id) { PCI_VDEVICE(MELLANOX, id), MLX4_PCI_DEV_FORCE_SENSE_PORT } +#define MLX_VF(id) { PCI_VDEVICE(MELLANOX, id), MLX4_PCI_DEV_IS_VF } +#define MLX_GN(id) { PCI_VDEVICE(MELLANOX, id), 0 } + static const struct pci_device_id mlx4_pci_table[] = { - /* MT25408 "Hermon" SDR */ - { PCI_VDEVICE(MELLANOX, 0x6340), MLX4_PCI_DEV_FORCE_SENSE_PORT }, - /* MT25408 "Hermon" DDR */ - { PCI_VDEVICE(MELLANOX, 0x634a), MLX4_PCI_DEV_FORCE_SENSE_PORT }, - /* MT25408 "Hermon" QDR */ - { PCI_VDEVICE(MELLANOX, 0x6354), MLX4_PCI_DEV_FORCE_SENSE_PORT }, - /* MT25408 "Hermon" DDR PCIe gen2 */ - { PCI_VDEVICE(MELLANOX, 0x6732), MLX4_PCI_DEV_FORCE_SENSE_PORT }, - /* MT25408 "Hermon" QDR PCIe gen2 */ - { PCI_VDEVICE(MELLANOX, 0x673c), MLX4_PCI_DEV_FORCE_SENSE_PORT }, - /* MT25408 "Hermon" EN 10GigE */ - { PCI_VDEVICE(MELLANOX, 0x6368), MLX4_PCI_DEV_FORCE_SENSE_PORT }, - /* MT25408 "Hermon" EN 10GigE PCIe gen2 */ - { PCI_VDEVICE(MELLANOX, 0x6750), MLX4_PCI_DEV_FORCE_SENSE_PORT }, - /* MT25458 ConnectX EN 10GBASE-T 10GigE */ - { PCI_VDEVICE(MELLANOX, 0x6372), MLX4_PCI_DEV_FORCE_SENSE_PORT }, - /* MT25458 ConnectX EN 10GBASE-T+Gen2 10GigE */ - { PCI_VDEVICE(MELLANOX, 0x675a), MLX4_PCI_DEV_FORCE_SENSE_PORT }, - /* MT26468 ConnectX EN 10GigE PCIe gen2*/ - { PCI_VDEVICE(MELLANOX, 0x6764), MLX4_PCI_DEV_FORCE_SENSE_PORT }, - /* MT26438 ConnectX EN 40GigE PCIe gen2 5GT/s */ - { PCI_VDEVICE(MELLANOX, 0x6746), MLX4_PCI_DEV_FORCE_SENSE_PORT }, - /* MT26478 ConnectX2 40GigE PCIe gen2 */ - { PCI_VDEVICE(MELLANOX, 0x676e), MLX4_PCI_DEV_FORCE_SENSE_PORT }, - /* MT25400 Family [ConnectX-2 Virtual Function] */ - { PCI_VDEVICE(MELLANOX, 0x1002), MLX4_PCI_DEV_IS_VF }, + /* MT25408 "Hermon" */ + MLX_SP(PCI_DEVICE_ID_MELLANOX_HERMON_SDR), /* SDR */ + MLX_SP(PCI_DEVICE_ID_MELLANOX_HERMON_DDR), /* DDR */ + MLX_SP(PCI_DEVICE_ID_MELLANOX_HERMON_QDR), /* QDR */ + MLX_SP(PCI_DEVICE_ID_MELLANOX_HERMON_DDR_GEN2), /* DDR Gen2 */ + MLX_SP(PCI_DEVICE_ID_MELLANOX_HERMON_QDR_GEN2), /* QDR Gen2 */ + MLX_SP(PCI_DEVICE_ID_MELLANOX_HERMON_EN), /* EN 10GigE */ + MLX_SP(PCI_DEVICE_ID_MELLANOX_HERMON_EN_GEN2), /* EN 10GigE Gen2 */ + /* MT25458 ConnectX EN 10GBASE-T */ + MLX_SP(PCI_DEVICE_ID_MELLANOX_CONNECTX_EN), + MLX_SP(PCI_DEVICE_ID_MELLANOX_CONNECTX_EN_T_GEN2), /* Gen2 */ + /* MT26468 ConnectX EN 10GigE PCIe Gen2*/ + MLX_SP(PCI_DEVICE_ID_MELLANOX_CONNECTX_EN_GEN2), + /* MT26438 ConnectX EN 40GigE PCIe Gen2 5GT/s */ + MLX_SP(PCI_DEVICE_ID_MELLANOX_CONNECTX_EN_5_GEN2), + /* MT26478 ConnectX2 40GigE PCIe Gen2 */ + MLX_SP(PCI_DEVICE_ID_MELLANOX_CONNECTX2), + /* MT25400 Family [ConnectX-2] */ + MLX_VF(0x1002), /* Virtual Function */ /* MT27500 Family [ConnectX-3] */ - { PCI_VDEVICE(MELLANOX, 0x1003), 0 }, - /* MT27500 Family [ConnectX-3 Virtual Function] */ - { PCI_VDEVICE(MELLANOX, 0x1004), MLX4_PCI_DEV_IS_VF }, - { PCI_VDEVICE(MELLANOX, 0x1005), 0 }, /* MT27510 Family */ - { PCI_VDEVICE(MELLANOX, 0x1006), 0 }, /* MT27511 Family */ - { PCI_VDEVICE(MELLANOX, 0x1007), 0 }, /* MT27520 Family */ - { PCI_VDEVICE(MELLANOX, 0x1008), 0 }, /* MT27521 Family */ - { PCI_VDEVICE(MELLANOX, 0x1009), 0 }, /* MT27530 Family */ - { PCI_VDEVICE(MELLANOX, 0x100a), 0 }, /* MT27531 Family */ - { PCI_VDEVICE(MELLANOX, 0x100b), 0 }, /* MT27540 Family */ - { PCI_VDEVICE(MELLANOX, 0x100c), 0 }, /* MT27541 Family */ - { PCI_VDEVICE(MELLANOX, 0x100d), 0 }, /* MT27550 Family */ - { PCI_VDEVICE(MELLANOX, 0x100e), 0 }, /* MT27551 Family */ - { PCI_VDEVICE(MELLANOX, 0x100f), 0 }, /* MT27560 Family */ - { PCI_VDEVICE(MELLANOX, 0x1010), 0 }, /* MT27561 Family */ + MLX_GN(PCI_DEVICE_ID_MELLANOX_CONNECTX3), + MLX_VF(0x1004), /* Virtual Function */ + MLX_GN(0x1005), /* MT27510 Family */ + MLX_GN(0x1006), /* MT27511 Family */ + MLX_GN(PCI_DEVICE_ID_MELLANOX_CONNECTX3_PRO), /* MT27520 Family */ + MLX_GN(0x1008), /* MT27521 Family */ + MLX_GN(0x1009), /* MT27530 Family */ + MLX_GN(0x100a), /* MT27531 Family */ + MLX_GN(0x100b), /* MT27540 Family */ + MLX_GN(0x100c), /* MT27541 Family */ + MLX_GN(0x100d), /* MT27550 Family */ + MLX_GN(0x100e), /* MT27551 Family */ + MLX_GN(0x100f), /* MT27560 Family */ + MLX_GN(0x1010), /* MT27561 Family */ + + /* + * See the mellanox_check_broken_intx_masking() quirk when + * adding devices + */ + { 0, } }; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 88ee7d8a5923..086920b615af 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -1220,6 +1220,7 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type); void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type); void mlx4_enter_error_state(struct mlx4_dev_persistent *persist); +int mlx4_comm_internal_err(u32 slave_read); int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port, enum mlx4_port_type *type); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index a3528dd1e72e..df0f39611c5e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -419,7 +419,6 @@ struct mlx4_en_dev { struct cyclecounter cycles; struct timecounter clock; unsigned long last_overflow_check; - unsigned long overflow_period; struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_clock_info; struct notifier_block nb; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index c548beaaf910..1822382212ee 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2980,6 +2980,9 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, put_res(dev, slave, srqn, RES_SRQ); qp->srq = srq; } + + /* Save param3 for dynamic changes from VST back to VGT */ + qp->param3 = qpc->param3; put_res(dev, slave, rcqn, RES_CQ); put_res(dev, slave, mtt_base, RES_MTT); res_end_move(dev, slave, RES_QP, qpn); @@ -3772,7 +3775,6 @@ int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave, int qpn = vhcr->in_modifier & 0x7fffff; struct res_qp *qp; u8 orig_sched_queue; - __be32 orig_param3 = qpc->param3; u8 orig_vlan_control = qpc->pri_path.vlan_control; u8 orig_fvl_rx = qpc->pri_path.fvl_rx; u8 orig_pri_path_fl = qpc->pri_path.fl; @@ -3814,7 +3816,6 @@ out: */ if (!err) { qp->sched_queue = orig_sched_queue; - qp->param3 = orig_param3; qp->vlan_control = orig_vlan_control; qp->fvl_rx = orig_fvl_rx; qp->pri_path_fl = orig_pri_path_fl; @@ -4164,22 +4165,6 @@ static int validate_eth_header_mac(int slave, struct _rule_hw *eth_header, return 0; } -static void handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl, - struct _rule_hw *eth_header) -{ - if (is_multicast_ether_addr(eth_header->eth.dst_mac) || - is_broadcast_ether_addr(eth_header->eth.dst_mac)) { - struct mlx4_net_trans_rule_hw_eth *eth = - (struct mlx4_net_trans_rule_hw_eth *)eth_header; - struct _rule_hw *next_rule = (struct _rule_hw *)(eth + 1); - bool last_rule = next_rule->size == 0 && next_rule->id == 0 && - next_rule->rsvd == 0; - - if (last_rule) - ctrl->prio = cpu_to_be16(MLX4_DOMAIN_NIC); - } -} - /* * In case of missing eth header, append eth header with a MAC address * assigned to the VF. @@ -4363,10 +4348,7 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, header_id = map_hw_to_sw_id(be16_to_cpu(rule_header->id)); if (header_id == MLX4_NET_TRANS_RULE_ID_ETH) - handle_eth_header_mcast_prio(ctrl, rule_header); - - if (slave == dev->caps.function) - goto execute; + mlx4_handle_eth_header_mcast_prio(ctrl, rule_header); switch (header_id) { case MLX4_NET_TRANS_RULE_ID_ETH: @@ -4394,7 +4376,6 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, goto err_put_qp; } -execute: err = mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param, vhcr->in_modifier, 0, MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A, @@ -4473,6 +4454,7 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave, struct res_qp *rqp; struct res_fs_rule *rrule; u64 mirr_reg_id; + int qpn; if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED) @@ -4489,10 +4471,11 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave, } mirr_reg_id = rrule->mirr_rule_id; kfree(rrule->mirr_mbox); + qpn = rrule->qpn; /* Release the rule form busy state before removal */ put_res(dev, slave, vhcr->in_param, RES_FS_RULE); - err = get_res(dev, slave, rrule->qpn, RES_QP, &rqp); + err = get_res(dev, slave, qpn, RES_QP, &rqp); if (err) return err; @@ -4517,7 +4500,7 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave, if (!err) atomic_dec(&rqp->ref_count); out: - put_res(dev, slave, rrule->qpn, RES_QP); + put_res(dev, slave, qpn, RES_QP); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index bfe410e8a469..f7fabecc104f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -367,6 +367,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_QUERY_VPORT_COUNTER: case MLX5_CMD_OP_ALLOC_Q_COUNTER: case MLX5_CMD_OP_QUERY_Q_COUNTER: + case MLX5_CMD_OP_SET_RATE_LIMIT: + case MLX5_CMD_OP_QUERY_RATE_LIMIT: case MLX5_CMD_OP_ALLOC_PD: case MLX5_CMD_OP_ALLOC_UAR: case MLX5_CMD_OP_CONFIG_INT_MODERATION: @@ -500,6 +502,8 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER); MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER); MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER); + MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT); + MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT); MLX5_COMMAND_STR_CASE(ALLOC_PD); MLX5_COMMAND_STR_CASE(DEALLOC_PD); MLX5_COMMAND_STR_CASE(ALLOC_UAR); @@ -763,9 +767,13 @@ static void cb_timeout_handler(struct work_struct *work) mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n", mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); - mlx5_cmd_comp_handler(dev, 1UL << ent->idx); + mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); } +static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg); +static void mlx5_free_cmd_msg(struct mlx5_core_dev *dev, + struct mlx5_cmd_msg *msg); + static void cmd_work_handler(struct work_struct *work) { struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work); @@ -775,16 +783,27 @@ static void cmd_work_handler(struct work_struct *work) struct mlx5_cmd_layout *lay; struct semaphore *sem; unsigned long flags; + int alloc_ret; sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); if (!ent->page_queue) { - ent->idx = alloc_ent(cmd); - if (ent->idx < 0) { + alloc_ret = alloc_ent(cmd); + if (alloc_ret < 0) { + if (ent->callback) { + ent->callback(-EAGAIN, ent->context); + mlx5_free_cmd_msg(dev, ent->out); + free_msg(dev, ent->in); + free_cmd(ent); + } else { + ent->ret = -EAGAIN; + complete(&ent->done); + } mlx5_core_err(dev, "failed to allocate command entry\n"); up(sem); return; } + ent->idx = alloc_ret; } else { ent->idx = cmd->max_reg_cmds; spin_lock_irqsave(&cmd->alloc_lock, flags); @@ -793,6 +812,7 @@ static void cmd_work_handler(struct work_struct *work) } cmd->ent_arr[ent->idx] = ent; + set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); lay = get_inst(cmd, ent->idx); ent->lay = lay; memset(lay, 0, sizeof(*lay)); @@ -814,6 +834,20 @@ static void cmd_work_handler(struct work_struct *work) if (ent->callback) schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); + /* Skip sending command to fw if internal error */ + if (pci_channel_offline(dev->pdev) || + dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { + u8 status = 0; + u32 drv_synd; + + ent->ret = mlx5_internal_err_ret_value(dev, msg_to_opcode(ent->in), &drv_synd, &status); + MLX5_SET(mbox_out, ent->out, status, status); + MLX5_SET(mbox_out, ent->out, syndrome, drv_synd); + + mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + return; + } + /* ring doorbell after the descriptor is valid */ mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx); wmb(); @@ -824,7 +858,7 @@ static void cmd_work_handler(struct work_struct *work) poll_timeout(ent); /* make sure we read the descriptor after ownership is SW */ rmb(); - mlx5_cmd_comp_handler(dev, 1UL << ent->idx); + mlx5_cmd_comp_handler(dev, 1UL << ent->idx, (ent->ret == -ETIMEDOUT)); } } @@ -868,7 +902,7 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) wait_for_completion(&ent->done); } else if (!wait_for_completion_timeout(&ent->done, timeout)) { ent->ret = -ETIMEDOUT; - mlx5_cmd_comp_handler(dev, 1UL << ent->idx); + mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); } err = ent->ret; @@ -1365,7 +1399,7 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg) } } -void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec) +void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced) { struct mlx5_cmd *cmd = &dev->cmd; struct mlx5_cmd_work_ent *ent; @@ -1385,6 +1419,19 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec) struct semaphore *sem; ent = cmd->ent_arr[i]; + + /* if we already completed the command, ignore it */ + if (!test_and_clear_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, + &ent->state)) { + /* only real completion can free the cmd slot */ + if (!forced) { + mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n", + ent->idx); + free_ent(cmd, ent->idx); + } + continue; + } + if (ent->callback) cancel_delayed_work(&ent->cb_timeout_work); if (ent->page_queue) @@ -1407,7 +1454,10 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec) mlx5_core_dbg(dev, "command completed. ret 0x%x, delivery status %s(0x%x)\n", ent->ret, deliv_status_to_str(ent->status), ent->status); } - free_ent(cmd, ent->idx); + + /* only real completion will free the entry slot */ + if (!forced) + free_ent(cmd, ent->idx); if (ent->callback) { ds = ent->ts2 - ent->ts1; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 81d8e3bd01b6..6180ad45be18 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -82,7 +82,7 @@ #define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) <= U16_MAX) #define MLX5_UMR_ALIGN (2048) -#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (128) +#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (256) #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ (64 * 1024) #define MLX5E_DEFAULT_LRO_TIMEOUT 32 @@ -283,13 +283,15 @@ struct mlx5e_dma_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_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c index 13dc388667b6..1612ec0d9103 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c @@ -62,12 +62,14 @@ static void mlx5e_timestamp_overflow(struct work_struct *work) struct delayed_work *dwork = to_delayed_work(work); struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp, overflow_work); + struct mlx5e_priv *priv = container_of(tstamp, struct mlx5e_priv, tstamp); unsigned long flags; write_lock_irqsave(&tstamp->lock, flags); timecounter_read(&tstamp->clock); write_unlock_irqrestore(&tstamp->lock, flags); - schedule_delayed_work(&tstamp->overflow_work, tstamp->overflow_period); + queue_delayed_work(priv->wq, &tstamp->overflow_work, + msecs_to_jiffies(tstamp->overflow_period * 1000)); } int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr) @@ -263,7 +265,7 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv) INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow); if (tstamp->overflow_period) - schedule_delayed_work(&tstamp->overflow_work, 0); + queue_delayed_work(priv->wq, &tstamp->overflow_work, 0); else mlx5_core_warn(priv->mdev, "invalid overflow period, overflow_work is not scheduled\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 126cfeb7e0ec..da1d73fe1a81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -751,7 +751,6 @@ static void get_supported(u32 eth_proto_cap, ptys2ethtool_supported_port(link_ksettings, eth_proto_cap); ptys2ethtool_supported_link(supported, eth_proto_cap); ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause); - ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Asym_Pause); } static void get_advertising(u32 eth_proto_cap, u8 tx_pause, @@ -761,7 +760,7 @@ static void get_advertising(u32 eth_proto_cap, u8 tx_pause, unsigned long *advertising = link_ksettings->link_modes.advertising; ptys2ethtool_adver_link(advertising, eth_proto_cap); - if (tx_pause) + if (rx_pause) ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause); if (tx_pause ^ rx_pause) ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Asym_Pause); @@ -806,6 +805,8 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev, struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0}; + u32 rx_pause = 0; + u32 tx_pause = 0; u32 eth_proto_cap; u32 eth_proto_admin; u32 eth_proto_lp; @@ -828,11 +829,13 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev, an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); an_status = MLX5_GET(ptys_reg, out, an_status); + mlx5_query_port_pause(mdev, &rx_pause, &tx_pause); + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); get_supported(eth_proto_cap, link_ksettings); - get_advertising(eth_proto_admin, 0, 0, link_ksettings); + get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings); get_speed_duplex(netdev, eth_proto_oper, link_ksettings); eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; @@ -1180,11 +1183,11 @@ static int mlx5e_get_ts_info(struct net_device *dev, SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE; - info->tx_types = (BIT(1) << HWTSTAMP_TX_OFF) | - (BIT(1) << HWTSTAMP_TX_ON); + info->tx_types = BIT(HWTSTAMP_TX_OFF) | + BIT(HWTSTAMP_TX_ON); - info->rx_filters = (BIT(1) << HWTSTAMP_FILTER_NONE) | - (BIT(1) << HWTSTAMP_FILTER_ALL); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_ALL); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 36fbc6b21a33..8cd7227fbdfc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -1081,7 +1081,7 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv) MLX5_FLOW_NAMESPACE_KERNEL); if (!priv->fs.ns) - return -EINVAL; + return -EOPNOTSUPP; err = mlx5e_arfs_create_tables(priv); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 90e81ae9f3bc..cf070fc0fb6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -276,7 +276,7 @@ static void add_rule_to_list(struct mlx5e_priv *priv, static bool outer_header_zero(u32 *match_criteria) { - int size = MLX5_ST_SZ_BYTES(fte_match_param); + int size = MLX5_FLD_SZ_BYTES(fte_match_param, outer_headers); char *outer_headers_c = MLX5_ADDR_OF(fte_match_param, match_criteria, outer_headers); @@ -563,6 +563,7 @@ int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv, struct ethtool_rxnfc *i int idx = 0; int err = 0; + info->data = MAX_NUM_OF_ETHTOOL_RULES; while ((!err || err == -ENOENT) && idx < info->rule_cnt) { err = mlx5e_ethtool_get_flow(priv, info, location); if (!err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b30671376a3d..9d3722930c95 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -81,6 +81,7 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type) { priv->params.rq_wq_type = rq_type; + priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; switch (priv->params.rq_wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW; @@ -92,6 +93,10 @@ static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type) break; default: /* MLX5_WQ_TYPE_LINKED_LIST */ priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE; + + /* Extra room needed for build_skb */ + priv->params.lro_wqe_sz -= MLX5_RX_HEADROOM + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); } priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type, BIT(priv->params.log_rq_size)); @@ -2666,8 +2671,6 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) PPORT_802_3_GET(pstats, a_frame_check_sequence_errors); stats->rx_frame_errors = PPORT_802_3_GET(pstats, a_alignment_errors); stats->tx_aborted_errors = PPORT_2863_GET(pstats, if_out_discards); - stats->tx_carrier_errors = - PPORT_802_3_GET(pstats, a_symbol_error_during_carrier); stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors + stats->rx_frame_errors; stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors; @@ -3473,12 +3476,6 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev, mlx5e_build_default_indir_rqt(mdev, priv->params.indirection_rqt, MLX5E_INDIR_RQT_SIZE, profile->max_nch(mdev)); - priv->params.lro_wqe_sz = - MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - - /* Extra room needed for build_skb */ - MLX5_RX_HEADROOM - - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - /* Initialize pflags */ MLX5E_SET_PRIV_FLAG(priv, MLX5E_PFLAG_RX_CQE_BASED_MODER, priv->params.rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE); @@ -3847,7 +3844,8 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev, return netdev; err_cleanup_nic: - profile->cleanup(priv); + if (profile->cleanup) + profile->cleanup(priv); free_netdev(netdev); return NULL; @@ -3936,6 +3934,19 @@ static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev) } } +static void mlx5e_unregister_vport_rep(struct mlx5_core_dev *mdev) +{ + struct mlx5_eswitch *esw = mdev->priv.eswitch; + int total_vfs = MLX5_TOTAL_VPORTS(mdev); + int vport; + + if (!MLX5_CAP_GEN(mdev, vport_group_manager)) + return; + + for (vport = 1; vport < total_vfs; vport++) + mlx5_eswitch_unregister_vport_rep(esw, vport); +} + void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -3983,6 +3994,7 @@ static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv) return err; } + mlx5e_register_vport_rep(mdev); return 0; } @@ -3994,6 +4006,7 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) if (!netif_device_present(netdev)) return; + mlx5e_unregister_vport_rep(mdev); mlx5e_detach_netdev(mdev, netdev); mlx5e_destroy_mdev_resources(mdev); } @@ -4012,8 +4025,6 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) if (err) return NULL; - mlx5e_register_vport_rep(mdev); - if (MLX5_CAP_GEN(mdev, vport_group_manager)) ppriv = &esw->offloads.vport_reps[0]; @@ -4065,13 +4076,7 @@ void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv) static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv) { - struct mlx5_eswitch *esw = mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(mdev); struct mlx5e_priv *priv = vpriv; - int vport; - - for (vport = 1; vport < total_vfs; vport++) - mlx5_eswitch_unregister_vport_rep(esw, vport); unregister_netdev(priv->netdev); mlx5e_detach(mdev, vpriv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index e7b2158bb48a..7309ae3b8c7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -92,19 +92,18 @@ static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n) static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq, struct mlx5e_cq *cq, u32 cqcc) { - u16 wqe_cnt_step; - cq->title.byte_cnt = cq->mini_arr[cq->mini_arr_idx].byte_cnt; cq->title.check_sum = cq->mini_arr[cq->mini_arr_idx].checksum; cq->title.op_own &= 0xf0; cq->title.op_own |= 0x01 & (cqcc >> cq->wq.log_sz); cq->title.wqe_counter = cpu_to_be16(cq->decmprs_wqe_counter); - wqe_cnt_step = - rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ? - mpwrq_get_cqe_consumed_strides(&cq->title) : 1; - cq->decmprs_wqe_counter = - (cq->decmprs_wqe_counter + wqe_cnt_step) & rq->wq.sz_m1; + if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) + cq->decmprs_wqe_counter += + mpwrq_get_cqe_consumed_strides(&cq->title); + else + cq->decmprs_wqe_counter = + (cq->decmprs_wqe_counter + 1) & rq->wq.sz_m1; } static inline void mlx5e_decompress_cqe_no_hash(struct mlx5e_rq *rq, @@ -603,6 +602,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, if (lro_num_seg > 1) { mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt); skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg); + /* Subtract one since we already counted this as one + * "regular" packet in mlx5e_complete_rx_cqe() + */ + rq->stats.packets += lro_num_seg - 1; rq->stats.lro_packets++; rq->stats.lro_bytes += cqe_bcnt; } 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 cbfac06b7ffd..23ccec4cb7f5 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_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 6bb21b31cfeb..3fd471a41895 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -427,14 +427,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, } if (is_tcf_vlan(a)) { - if (tcf_vlan_action(a) == VLAN_F_POP) { + if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) { attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; - } else if (tcf_vlan_action(a) == VLAN_F_PUSH) { + } else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) { if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q)) return -EOPNOTSUPP; attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; attr->vlan = tcf_vlan_push_vid(a); + } else { /* action is TCA_VLAN_ACT_MODIFY */ + return -EOPNOTSUPP; } continue; } @@ -567,10 +569,14 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); + preempt_disable(); + tcf_exts_to_list(f->exts, &actions); list_for_each_entry(a, &actions, list) tcf_action_stats_update(a, bytes, packets, lastuse); + preempt_enable(); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index cfb68371c397..574311018e6f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -272,15 +272,18 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) sq->stats.tso_bytes += skb->len - ihs; } + sq->stats.packets += skb_shinfo(skb)->gso_segs; num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; } else { bf = sq->bf_budget && !skb->xmit_more && !skb_shinfo(skb)->nr_frags; ihs = mlx5e_get_inline_hdr_size(sq, skb, bf); + sq->stats.packets++; num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); } + sq->stats.bytes += num_bytes; wi->num_bytes = num_bytes; if (skb_vlan_tag_present(skb)) { @@ -377,8 +380,6 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) if (bf) sq->bf_budget--; - sq->stats.packets++; - sq->stats.bytes += num_bytes; return NETDEV_TX_OK; dma_unmap_wqe_err: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index aaca09002ca6..f86e9ff995be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -234,7 +234,7 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq) break; case MLX5_EVENT_TYPE_CMD: - mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector)); + mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false); break; case MLX5_EVENT_TYPE_PORT_CHANGE: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index c7011ef4e351..a8966e6dbe1b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -352,7 +352,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports) root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); if (!root_ns) { esw_warn(dev, "Failed to get FDB flow namespace\n"); - return -ENOMEM; + return -EOPNOTSUPP; } flow_group_in = mlx5_vzalloc(inlen); @@ -961,7 +961,7 @@ static int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw, root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS); if (!root_ns) { esw_warn(dev, "Failed to get E-Switch egress flow namespace\n"); - return -EIO; + return -EOPNOTSUPP; } flow_group_in = mlx5_vzalloc(inlen); @@ -1078,7 +1078,7 @@ static int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw, root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS); if (!root_ns) { esw_warn(dev, "Failed to get E-Switch ingress flow namespace\n"); - return -EIO; + return -EOPNOTSUPP; } flow_group_in = mlx5_vzalloc(inlen); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d239f5d0ea36..52a38106448e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -414,6 +414,7 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports) root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); if (!root_ns) { esw_warn(dev, "Failed to get FDB flow namespace\n"); + err = -EOPNOTSUPP; goto ns_err; } @@ -520,7 +521,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw) ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_OFFLOADS); if (!ns) { esw_warn(esw->dev, "Failed to get offloads flow namespace\n"); - return -ENOMEM; + return -EOPNOTSUPP; } ft_offloads = mlx5_create_flow_table(ns, 0, dev->priv.sriov.num_vfs + 2, 0); @@ -639,7 +640,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw) esw_warn(esw->dev, "Failed setting eswitch to offloads, err %d\n", err); err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY); if (err1) - esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err); + esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err1); } return err; } @@ -650,9 +651,14 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) int vport; int err; + /* disable PF RoCE so missed packets don't go through RoCE steering */ + mlx5_dev_list_lock(); + mlx5_remove_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); + mlx5_dev_list_unlock(); + err = esw_create_offloads_fdb_table(esw, nvports); if (err) - return err; + goto create_fdb_err; err = esw_create_offloads_table(esw); if (err) @@ -671,6 +677,7 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) if (err) goto err_reps; } + return 0; err_reps: @@ -687,6 +694,13 @@ create_fg_err: create_ft_err: esw_destroy_offloads_fdb_table(esw); + +create_fdb_err: + /* enable back PF RoCE */ + mlx5_dev_list_lock(); + mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); + mlx5_dev_list_unlock(); + return err; } @@ -703,6 +717,11 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw) esw_warn(esw->dev, "Failed setting eswitch back to offloads, err %d\n", err); } + /* enable back PF RoCE */ + mlx5_dev_list_lock(); + mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); + mlx5_dev_list_unlock(); + return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 7e20e4bc4cc7..4de3c28b0547 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1678,7 +1678,7 @@ static int create_anchor_flow_table(struct mlx5_flow_steering *steering) struct mlx5_flow_table *ft; ns = mlx5_get_flow_namespace(steering->dev, MLX5_FLOW_NAMESPACE_ANCHOR); - if (!ns) + if (WARN_ON(!ns)) return -EINVAL; ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE, ANCHOR_LEVEL); if (IS_ERR(ft)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 5bcf93422ee0..8beecd615a21 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -67,6 +67,7 @@ enum { enum { MLX5_DROP_NEW_HEALTH_WORK, + MLX5_DROP_NEW_RECOVERY_WORK, }; static u8 get_nic_state(struct mlx5_core_dev *dev) @@ -90,7 +91,7 @@ static void trigger_cmd_completions(struct mlx5_core_dev *dev) spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags); mlx5_core_dbg(dev, "vector 0x%llx\n", vector); - mlx5_cmd_comp_handler(dev, vector); + mlx5_cmd_comp_handler(dev, vector, true); return; no_trig: @@ -193,7 +194,7 @@ static void health_care(struct work_struct *work) mlx5_handle_bad_state(dev); spin_lock(&health->wq_lock); - if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) + if (!test_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags)) schedule_delayed_work(&health->recover_work, recover_delay); else dev_err(&dev->pdev->dev, @@ -328,6 +329,7 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) init_timer(&health->timer); health->sick = 0; clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + clear_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); health->health = &dev->iseg->health; health->health_counter = &dev->iseg->health_counter; @@ -350,11 +352,22 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev) spin_lock(&health->wq_lock); set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); spin_unlock(&health->wq_lock); cancel_delayed_work_sync(&health->recover_work); cancel_work_sync(&health->work); } +void mlx5_drain_health_recovery(struct mlx5_core_dev *dev) +{ + struct mlx5_core_health *health = &dev->priv.health; + + spin_lock(&health->wq_lock); + set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); + spin_unlock(&health->wq_lock); + cancel_delayed_work_sync(&dev->priv.health.recover_work); +} + void mlx5_health_cleanup(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 55957246c0e8..0ca4623bda6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -157,22 +157,17 @@ static bool mlx5_lag_is_bonded(struct mlx5_lag *ldev) static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker, u8 *port1, u8 *port2) { - if (tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) { - if (tracker->netdev_state[0].tx_enabled) { - *port1 = 1; - *port2 = 1; - } else { - *port1 = 2; - *port2 = 2; - } - } else { - *port1 = 1; - *port2 = 2; - if (!tracker->netdev_state[0].link_up) - *port1 = 2; - else if (!tracker->netdev_state[1].link_up) - *port2 = 1; + *port1 = 1; + *port2 = 2; + if (!tracker->netdev_state[0].tx_enabled || + !tracker->netdev_state[0].link_up) { + *port1 = 2; + return; } + + if (!tracker->netdev_state[1].tx_enabled || + !tracker->netdev_state[1].link_up) + *port2 = 1; } static void mlx5_activate_lag(struct mlx5_lag *ldev, @@ -294,7 +289,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, struct netdev_notifier_changeupper_info *info) { struct net_device *upper = info->upper_dev, *ndev_tmp; - struct netdev_lag_upper_info *lag_upper_info; + struct netdev_lag_upper_info *lag_upper_info = NULL; bool is_bonded; int bond_status = 0; int num_slaves = 0; @@ -303,7 +298,8 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, if (!netif_is_lag_master(upper)) return 0; - lag_upper_info = info->upper_info; + if (info->linking) + lag_upper_info = info->upper_info; /* The event may still be of interest if the slave does not belong to * us, but is enslaved to a master which has one or more of our netdevs diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 0c9ef8729ca7..b3309f2ed7dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -87,7 +87,7 @@ static struct mlx5_profile profile[] = { [2] = { .mask = MLX5_PROF_MASK_QP_SIZE | MLX5_PROF_MASK_MR_CACHE, - .log_max_qp = 17, + .log_max_qp = 18, .mr_cache[0] = { .size = 500, .limit = 250 @@ -155,8 +155,9 @@ static struct mlx5_profile profile[] = { }, }; -#define FW_INIT_TIMEOUT_MILI 2000 -#define FW_INIT_WAIT_MS 2 +#define FW_INIT_TIMEOUT_MILI 2000 +#define FW_INIT_WAIT_MS 2 +#define FW_PRE_INIT_TIMEOUT_MILI 10000 static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili) { @@ -956,6 +957,15 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, */ dev->state = MLX5_DEVICE_STATE_UP; + /* wait for firmware to accept initialization segments configurations + */ + err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI); + if (err) { + dev_err(&dev->pdev->dev, "Firmware over %d MS in pre-initializing state, aborting\n", + FW_PRE_INIT_TIMEOUT_MILI); + goto out; + } + err = mlx5_cmd_init(dev); if (err) { dev_err(&pdev->dev, "Failed initializing command interface, aborting\n"); @@ -966,7 +976,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, if (err) { dev_err(&dev->pdev->dev, "Firmware over %d MS in initializing state, aborting\n", FW_INIT_TIMEOUT_MILI); - goto out_err; + goto err_cmd_cleanup; } err = mlx5_core_enable_hca(dev, 0); @@ -1159,7 +1169,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, int err = 0; if (cleanup) - mlx5_drain_health_wq(dev); + mlx5_drain_health_recovery(dev); mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index f902c4d3de99..d50350c7adc4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -249,15 +249,14 @@ static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp *mlxsw_sp, } static struct mlxsw_sp_span_entry * -mlxsw_sp_span_entry_find(struct mlxsw_sp_port *port) +mlxsw_sp_span_entry_find(struct mlxsw_sp *mlxsw_sp, u8 local_port) { - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; int i; for (i = 0; i < mlxsw_sp->span.entries_count; i++) { struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; - if (curr->used && curr->local_port == port->local_port) + if (curr->used && curr->local_port == local_port) return curr; } return NULL; @@ -268,7 +267,8 @@ static struct mlxsw_sp_span_entry { struct mlxsw_sp_span_entry *span_entry; - span_entry = mlxsw_sp_span_entry_find(port); + span_entry = mlxsw_sp_span_entry_find(port->mlxsw_sp, + port->local_port); if (span_entry) { /* Already exists, just take a reference */ span_entry->ref_count++; @@ -453,12 +453,13 @@ err_port_bind: } static void mlxsw_sp_span_mirror_remove(struct mlxsw_sp_port *from, - struct mlxsw_sp_port *to, + u8 destination_port, enum mlxsw_sp_span_type type) { struct mlxsw_sp_span_entry *span_entry; - span_entry = mlxsw_sp_span_entry_find(to); + span_entry = mlxsw_sp_span_entry_find(from->mlxsw_sp, + destination_port); if (!span_entry) { netdev_err(from->dev, "no span entry found\n"); return; @@ -1255,10 +1256,8 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, static void mlxsw_sp_port_del_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_cls_matchall_offload *cls) { - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry; enum mlxsw_sp_span_type span_type; - struct mlxsw_sp_port *to_port; mall_tc_entry = mlxsw_sp_port_mirror_entry_find(mlxsw_sp_port, cls->cookie); @@ -1269,11 +1268,12 @@ static void mlxsw_sp_port_del_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, switch (mall_tc_entry->type) { case MLXSW_SP_PORT_MALL_MIRROR: - to_port = mlxsw_sp->ports[mall_tc_entry->mirror.to_local_port]; span_type = mall_tc_entry->mirror.ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; - mlxsw_sp_span_mirror_remove(mlxsw_sp_port, to_port, span_type); + mlxsw_sp_span_mirror_remove(mlxsw_sp_port, + mall_tc_entry->mirror.to_local_port, + span_type); break; default: WARN_ON(1); @@ -4172,6 +4172,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, return -EINVAL; if (!info->linking) break; + if (netdev_has_any_upper_dev(upper_dev)) + return -EINVAL; /* HW limitation forbids to put ports to multiple bridges. */ if (netif_is_bridge_master(upper_dev) && !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev)) @@ -4185,6 +4187,10 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) && !netif_is_lag_master(vlan_dev_real_dev(upper_dev))) return -EINVAL; + if (!info->linking) + break; + if (netdev_has_any_upper_dev(upper_dev)) + return -EINVAL; break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index e83072da6272..9e31a3390154 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -500,30 +500,40 @@ static int mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, struct mlxsw_sp_prefix_usage *req_prefix_usage) { - struct mlxsw_sp_lpm_tree *lpm_tree; + struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree; + struct mlxsw_sp_lpm_tree *new_tree; + int err; - if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, - &vr->lpm_tree->prefix_usage)) + if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, &lpm_tree->prefix_usage)) return 0; - lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage, + new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage, vr->proto, false); - if (IS_ERR(lpm_tree)) { + if (IS_ERR(new_tree)) { /* We failed to get a tree according to the required * prefix usage. However, the current tree might be still good * for us if our requirement is subset of the prefixes used * in the tree. */ if (mlxsw_sp_prefix_usage_subset(req_prefix_usage, - &vr->lpm_tree->prefix_usage)) + &lpm_tree->prefix_usage)) return 0; - return PTR_ERR(lpm_tree); + return PTR_ERR(new_tree); } - mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr); - mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree); + /* Prevent packet loss by overwriting existing binding */ + vr->lpm_tree = new_tree; + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); + if (err) + goto err_tree_bind; + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); + + return 0; + +err_tree_bind: vr->lpm_tree = lpm_tree; - return mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); + mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree); + return err; } static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, @@ -1168,7 +1178,8 @@ static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, static int mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop_group *nh_grp) + struct mlxsw_sp_nexthop_group *nh_grp, + bool reallocate) { u32 adj_index = nh_grp->adj_index; /* base */ struct mlxsw_sp_nexthop *nh; @@ -1183,7 +1194,7 @@ mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp, continue; } - if (nh->update) { + if (nh->update || reallocate) { err = mlxsw_sp_nexthop_mac_update(mlxsw_sp, adj_index, nh); if (err) @@ -1244,7 +1255,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, /* Nothing was added or removed, so no need to reallocate. Just * update MAC on existing adjacency indexes. */ - err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp); + err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, + false); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n"); goto set_trap; @@ -1272,7 +1284,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, nh_grp->adj_index_valid = 1; nh_grp->adj_index = adj_index; nh_grp->ecmp_size = ecmp_size; - err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp); + err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, true); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n"); goto set_trap; |