diff options
Diffstat (limited to 'drivers/net/ethernet/microsoft/mana/mana_en.c')
| -rw-r--r-- | drivers/net/ethernet/microsoft/mana/mana_en.c | 1449 |
1 files changed, 1175 insertions, 274 deletions
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 4a16ebff3d1d..1ad154f9db1a 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -3,20 +3,25 @@ #include <uapi/linux/bpf.h> +#include <linux/debugfs.h> #include <linux/inetdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/mm.h> #include <linux/pci.h> +#include <linux/export.h> +#include <linux/skbuff.h> #include <net/checksum.h> #include <net/ip6_checksum.h> +#include <net/netdev_lock.h> #include <net/page_pool/helpers.h> #include <net/xdp.h> #include <net/mana/mana.h> #include <net/mana/mana_auxiliary.h> +#include <net/mana/hw_channel.h> static DEFINE_IDA(mana_adev_ida); @@ -30,25 +35,59 @@ static void mana_adev_idx_free(int idx) ida_free(&mana_adev_ida, idx); } +static ssize_t mana_dbg_q_read(struct file *filp, char __user *buf, size_t count, + loff_t *pos) +{ + struct gdma_queue *gdma_q = filp->private_data; + + return simple_read_from_buffer(buf, count, pos, gdma_q->queue_mem_ptr, + gdma_q->queue_size); +} + +static const struct file_operations mana_dbg_q_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = mana_dbg_q_read, +}; + +static bool mana_en_need_log(struct mana_port_context *apc, int err) +{ + if (apc && apc->ac && apc->ac->gdma_dev && + apc->ac->gdma_dev->gdma_context) + return mana_need_log(apc->ac->gdma_dev->gdma_context, err); + else + return true; +} + +static void mana_put_rx_page(struct mana_rxq *rxq, struct page *page, + bool from_pool) +{ + if (from_pool) + page_pool_put_full_page(rxq->page_pool, page, false); + else + put_page(page); +} + /* Microsoft Azure Network Adapter (MANA) functions */ static int mana_open(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); int err; - err = mana_alloc_queues(ndev); - if (err) + + if (err) { + netdev_err(ndev, "%s failed to allocate queues: %d\n", __func__, err); return err; + } apc->port_is_up = true; /* Ensure port state updated before txq state */ smp_wmb(); - netif_carrier_on(ndev); netif_tx_wake_all_queues(ndev); - + netdev_dbg(ndev, "%s successful\n", __func__); return 0; } @@ -62,6 +101,46 @@ static int mana_close(struct net_device *ndev) return mana_detach(ndev, true); } +static void mana_link_state_handle(struct work_struct *w) +{ + struct mana_context *ac; + struct net_device *ndev; + u32 link_event; + bool link_up; + int i; + + ac = container_of(w, struct mana_context, link_change_work); + + rtnl_lock(); + + link_event = READ_ONCE(ac->link_event); + + if (link_event == HWC_DATA_HW_LINK_CONNECT) + link_up = true; + else if (link_event == HWC_DATA_HW_LINK_DISCONNECT) + link_up = false; + else + goto out; + + /* Process all ports */ + for (i = 0; i < ac->num_ports; i++) { + ndev = ac->ports[i]; + if (!ndev) + continue; + + if (link_up) { + netif_carrier_on(ndev); + + __netdev_notify_peers(ndev); + } else { + netif_carrier_off(ndev); + } + } + +out: + rtnl_unlock(); +} + static bool mana_can_tx(struct gdma_queue *wq) { return mana_gd_wq_avail_space(wq) >= MAX_TX_WQE_SIZE; @@ -91,63 +170,140 @@ static unsigned int mana_checksum_info(struct sk_buff *skb) return 0; } +static void mana_add_sge(struct mana_tx_package *tp, struct mana_skb_head *ash, + int sg_i, dma_addr_t da, int sge_len, u32 gpa_mkey) +{ + ash->dma_handle[sg_i] = da; + ash->size[sg_i] = sge_len; + + tp->wqe_req.sgl[sg_i].address = da; + tp->wqe_req.sgl[sg_i].mem_key = gpa_mkey; + tp->wqe_req.sgl[sg_i].size = sge_len; +} + static int mana_map_skb(struct sk_buff *skb, struct mana_port_context *apc, - struct mana_tx_package *tp) + struct mana_tx_package *tp, int gso_hs) { struct mana_skb_head *ash = (struct mana_skb_head *)skb->head; + int hsg = 1; /* num of SGEs of linear part */ struct gdma_dev *gd = apc->ac->gdma_dev; + int skb_hlen = skb_headlen(skb); + int sge0_len, sge1_len = 0; struct gdma_context *gc; struct device *dev; skb_frag_t *frag; dma_addr_t da; + int sg_i; int i; gc = gd->gdma_context; dev = gc->dev; - da = dma_map_single(dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE); + if (gso_hs && gso_hs < skb_hlen) { + sge0_len = gso_hs; + sge1_len = skb_hlen - gso_hs; + } else { + sge0_len = skb_hlen; + } + + da = dma_map_single(dev, skb->data, sge0_len, DMA_TO_DEVICE); if (dma_mapping_error(dev, da)) return -ENOMEM; - ash->dma_handle[0] = da; - ash->size[0] = skb_headlen(skb); + mana_add_sge(tp, ash, 0, da, sge0_len, gd->gpa_mkey); + + if (sge1_len) { + sg_i = 1; + da = dma_map_single(dev, skb->data + sge0_len, sge1_len, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, da)) + goto frag_err; - tp->wqe_req.sgl[0].address = ash->dma_handle[0]; - tp->wqe_req.sgl[0].mem_key = gd->gpa_mkey; - tp->wqe_req.sgl[0].size = ash->size[0]; + mana_add_sge(tp, ash, sg_i, da, sge1_len, gd->gpa_mkey); + hsg = 2; + } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + sg_i = hsg + i; + frag = &skb_shinfo(skb)->frags[i]; da = skb_frag_dma_map(dev, frag, 0, skb_frag_size(frag), DMA_TO_DEVICE); - if (dma_mapping_error(dev, da)) goto frag_err; - ash->dma_handle[i + 1] = da; - ash->size[i + 1] = skb_frag_size(frag); - - tp->wqe_req.sgl[i + 1].address = ash->dma_handle[i + 1]; - tp->wqe_req.sgl[i + 1].mem_key = gd->gpa_mkey; - tp->wqe_req.sgl[i + 1].size = ash->size[i + 1]; + mana_add_sge(tp, ash, sg_i, da, skb_frag_size(frag), + gd->gpa_mkey); } return 0; frag_err: - for (i = i - 1; i >= 0; i--) - dma_unmap_page(dev, ash->dma_handle[i + 1], ash->size[i + 1], + if (net_ratelimit()) + netdev_err(apc->ndev, "Failed to map skb of size %u to DMA\n", + skb->len); + for (i = sg_i - 1; i >= hsg; i--) + dma_unmap_page(dev, ash->dma_handle[i], ash->size[i], DMA_TO_DEVICE); - dma_unmap_single(dev, ash->dma_handle[0], ash->size[0], DMA_TO_DEVICE); + for (i = hsg - 1; i >= 0; i--) + dma_unmap_single(dev, ash->dma_handle[i], ash->size[i], + DMA_TO_DEVICE); return -ENOMEM; } +/* Handle the case when GSO SKB linear length is too large. + * MANA NIC requires GSO packets to put only the packet header to SGE0. + * So, we need 2 SGEs for the skb linear part which contains more than the + * header. + * Return a positive value for the number of SGEs, or a negative value + * for an error. + */ +static int mana_fix_skb_head(struct net_device *ndev, struct sk_buff *skb, + int gso_hs) +{ + int num_sge = 1 + skb_shinfo(skb)->nr_frags; + int skb_hlen = skb_headlen(skb); + + if (gso_hs < skb_hlen) { + num_sge++; + } else if (gso_hs > skb_hlen) { + if (net_ratelimit()) + netdev_err(ndev, + "TX nonlinear head: hs:%d, skb_hlen:%d\n", + gso_hs, skb_hlen); + + return -EINVAL; + } + + return num_sge; +} + +/* Get the GSO packet's header size */ +static int mana_get_gso_hs(struct sk_buff *skb) +{ + int gso_hs; + + if (skb->encapsulation) { + gso_hs = skb_inner_tcp_all_headers(skb); + } else { + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { + gso_hs = skb_transport_offset(skb) + + sizeof(struct udphdr); + } else { + gso_hs = skb_tcp_all_headers(skb); + } + } + + return gso_hs; +} + netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) { enum mana_tx_pkt_format pkt_fmt = MANA_SHORT_PKT_FMT; struct mana_port_context *apc = netdev_priv(ndev); + int gso_hs = 0; /* zero for non-GSO pkts */ u16 txq_idx = skb_get_queue_mapping(skb); struct gdma_dev *gd = apc->ac->gdma_dev; bool ipv4 = false, ipv6 = false; @@ -155,11 +311,10 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct netdev_queue *net_txq; struct mana_stats_tx *tx_stats; struct gdma_queue *gdma_sq; + int err, len, num_gso_seg; unsigned int csum_type; struct mana_txq *txq; struct mana_cq *cq; - int err, len; - u16 ihs; if (unlikely(!apc->port_is_up)) goto tx_drop; @@ -167,11 +322,29 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (skb_cow_head(skb, MANA_HEADROOM)) goto tx_drop_count; + if (unlikely(ipv6_hopopt_jumbo_remove(skb))) + goto tx_drop_count; + txq = &apc->tx_qp[txq_idx].txq; gdma_sq = txq->gdma_sq; cq = &apc->tx_qp[txq_idx].tx_cq; tx_stats = &txq->stats; + BUILD_BUG_ON(MAX_TX_WQE_SGL_ENTRIES != MANA_MAX_TX_WQE_SGL_ENTRIES); + if (MAX_SKB_FRAGS + 2 > MAX_TX_WQE_SGL_ENTRIES && + skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) { + /* GSO skb with Hardware SGE limit exceeded is not expected here + * as they are handled in mana_features_check() callback + */ + if (skb_linearize(skb)) { + netdev_warn_once(ndev, "Failed to linearize skb with nr_frags=%d and is_gso=%d\n", + skb_shinfo(skb)->nr_frags, + skb_is_gso(skb)); + goto tx_drop_count; + } + apc->eth_stats.tx_linear_pkt_cnt++; + } + pkg.tx_oob.s_oob.vcq_num = cq->gdma_id; pkg.tx_oob.s_oob.vsq_frame = txq->vsq_frame; @@ -209,19 +382,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) pkg.wqe_req.client_data_unit = 0; pkg.wqe_req.num_sge = 1 + skb_shinfo(skb)->nr_frags; - WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES); - - if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) { - pkg.wqe_req.sgl = pkg.sgl_array; - } else { - pkg.sgl_ptr = kmalloc_array(pkg.wqe_req.num_sge, - sizeof(struct gdma_sge), - GFP_ATOMIC); - if (!pkg.sgl_ptr) - goto tx_drop_count; - - pkg.wqe_req.sgl = pkg.sgl_ptr; - } if (skb->protocol == htons(ETH_P_IP)) ipv4 = true; @@ -229,6 +389,26 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) ipv6 = true; if (skb_is_gso(skb)) { + int num_sge; + + gso_hs = mana_get_gso_hs(skb); + + num_sge = mana_fix_skb_head(ndev, skb, gso_hs); + if (num_sge > 0) + pkg.wqe_req.num_sge = num_sge; + else + goto tx_drop_count; + + u64_stats_update_begin(&tx_stats->syncp); + if (skb->encapsulation) { + tx_stats->tso_inner_packets++; + tx_stats->tso_inner_bytes += skb->len - gso_hs; + } else { + tx_stats->tso_packets++; + tx_stats->tso_bytes += skb->len - gso_hs; + } + u64_stats_update_end(&tx_stats->syncp); + pkg.tx_oob.s_oob.is_outer_ipv4 = ipv4; pkg.tx_oob.s_oob.is_outer_ipv6 = ipv6; @@ -252,28 +432,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) &ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); } - - if (skb->encapsulation) { - ihs = skb_inner_tcp_all_headers(skb); - u64_stats_update_begin(&tx_stats->syncp); - tx_stats->tso_inner_packets++; - tx_stats->tso_inner_bytes += skb->len - ihs; - u64_stats_update_end(&tx_stats->syncp); - } else { - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { - ihs = skb_transport_offset(skb) + sizeof(struct udphdr); - } else { - ihs = skb_tcp_all_headers(skb); - if (ipv6_has_hopopt_jumbo(skb)) - ihs -= sizeof(struct hop_jumbo_hdr); - } - - u64_stats_update_begin(&tx_stats->syncp); - tx_stats->tso_packets++; - tx_stats->tso_bytes += skb->len - ihs; - u64_stats_update_end(&tx_stats->syncp); - } - } else if (skb->ip_summed == CHECKSUM_PARTIAL) { csum_type = mana_checksum_info(skb); @@ -296,11 +454,23 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) } else { /* Can't do offload of this type of checksum */ if (skb_checksum_help(skb)) - goto free_sgl_ptr; + goto tx_drop_count; } } - if (mana_map_skb(skb, apc, &pkg)) { + if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) { + pkg.wqe_req.sgl = pkg.sgl_array; + } else { + pkg.sgl_ptr = kmalloc_array(pkg.wqe_req.num_sge, + sizeof(struct gdma_sge), + GFP_ATOMIC); + if (!pkg.sgl_ptr) + goto tx_drop_count; + + pkg.wqe_req.sgl = pkg.sgl_ptr; + } + + if (mana_map_skb(skb, apc, &pkg, gso_hs)) { u64_stats_update_begin(&tx_stats->syncp); tx_stats->mana_map_err++; u64_stats_update_end(&tx_stats->syncp); @@ -310,6 +480,7 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_queue_tail(&txq->pending_skbs, skb); len = skb->len; + num_gso_seg = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1; net_txq = netdev_get_tx_queue(ndev, txq_idx); err = mana_gd_post_work_request(gdma_sq, &pkg.wqe_req, @@ -321,9 +492,9 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (err) { (void)skb_dequeue_tail(&txq->pending_skbs); + mana_unmap_skb(skb, apc); netdev_warn(ndev, "Failed to post TX OOB: %d\n", err); - err = NETDEV_TX_BUSY; - goto tx_busy; + goto free_sgl_ptr; } err = NETDEV_TX_OK; @@ -334,13 +505,15 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) /* skb may be freed after mana_gd_post_work_request. Do not use it. */ skb = NULL; + /* Populated the packet and bytes counters based on post GSO packet + * calculations + */ tx_stats = &txq->stats; u64_stats_update_begin(&tx_stats->syncp); - tx_stats->packets++; - tx_stats->bytes += len; + tx_stats->packets += num_gso_seg; + tx_stats->bytes += len + ((num_gso_seg - 1) * gso_hs); u64_stats_update_end(&tx_stats->syncp); -tx_busy: if (netif_tx_queue_stopped(net_txq) && mana_can_tx(gdma_sq)) { netif_tx_wake_queue(net_txq); apc->eth_stats.wake_queue++; @@ -358,6 +531,25 @@ tx_drop: return NETDEV_TX_OK; } +#if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES) +static netdev_features_t mana_features_check(struct sk_buff *skb, + struct net_device *ndev, + netdev_features_t features) +{ + if (skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) { + /* Exceeds HW SGE limit. + * GSO case: + * Disable GSO so the stack will software-segment the skb + * into smaller skbs that fit the SGE budget. + * Non-GSO case: + * The xmit path will attempt skb_linearize() as a fallback. + */ + features &= ~NETIF_F_GSO_MASK; + } + return features; +} +#endif + static void mana_get_stats64(struct net_device *ndev, struct rtnl_link_stats64 *st) { @@ -374,6 +566,11 @@ static void mana_get_stats64(struct net_device *ndev, netdev_stats_to_stats64(st, &ndev->stats); + if (apc->ac->hwc_timeout_occurred) + netdev_warn_once(ndev, "HWC timeout occurred\n"); + + st->rx_missed_errors = apc->ac->hc_stats.hc_rx_discards_no_wqe; + for (q = 0; q < num_queues; q++) { rx_stats = &apc->rxqs[q]->stats; @@ -409,7 +606,7 @@ static int mana_get_tx_queue(struct net_device *ndev, struct sk_buff *skb, struct sock *sk = skb->sk; int txq; - txq = apc->indir_table[hash & MANA_INDIRECT_TABLE_MASK]; + txq = apc->indir_table[hash & (apc->indir_table_sz - 1)]; if (txq != old_q && sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) @@ -439,7 +636,7 @@ static u16 mana_select_queue(struct net_device *ndev, struct sk_buff *skb, } /* Release pre-allocated RX buffers */ -static void mana_pre_dealloc_rxbufs(struct mana_port_context *mpc) +void mana_pre_dealloc_rxbufs(struct mana_port_context *mpc) { struct device *dev; int i; @@ -519,20 +716,43 @@ static void *mana_get_rxbuf_pre(struct mana_rxq *rxq, dma_addr_t *da) } /* Get RX buffer's data size, alloc size, XDP headroom based on MTU */ -static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size, - u32 *headroom) +static void mana_get_rxbuf_cfg(struct mana_port_context *apc, + int mtu, u32 *datasize, u32 *alloc_size, + u32 *headroom, u32 *frag_count) { - if (mtu > MANA_XDP_MTU_MAX) - *headroom = 0; /* no support for XDP */ - else - *headroom = XDP_PACKET_HEADROOM; + u32 len, buf_size; + + /* Calculate datasize first (consistent across all cases) */ + *datasize = mtu + ETH_HLEN; + + /* For xdp and jumbo frames make sure only one packet fits per page */ + if (mtu + MANA_RXBUF_PAD > PAGE_SIZE / 2 || mana_xdp_get(apc)) { + if (mana_xdp_get(apc)) { + *headroom = XDP_PACKET_HEADROOM; + *alloc_size = PAGE_SIZE; + } else { + *headroom = 0; /* no support for XDP */ + *alloc_size = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD + + *headroom); + } + + *frag_count = 1; + return; + } + + /* Standard MTU case - optimize for multiple packets per page */ + *headroom = 0; - *alloc_size = mtu + MANA_RXBUF_PAD + *headroom; + /* Calculate base buffer size needed */ + len = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD + *headroom); + buf_size = ALIGN(len, MANA_RX_FRAG_ALIGNMENT); - *datasize = ALIGN(mtu + ETH_HLEN, MANA_RX_DATA_ALIGN); + /* Calculate how many packets can fit in a page */ + *frag_count = PAGE_SIZE / buf_size; + *alloc_size = buf_size; } -static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu) +int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_queues) { struct device *dev; struct page *page; @@ -541,12 +761,13 @@ static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu) void *va; int i; - mana_get_rxbuf_cfg(new_mtu, &mpc->rxbpre_datasize, - &mpc->rxbpre_alloc_size, &mpc->rxbpre_headroom); + mana_get_rxbuf_cfg(mpc, new_mtu, &mpc->rxbpre_datasize, + &mpc->rxbpre_alloc_size, &mpc->rxbpre_headroom, + &mpc->rxbpre_frag_count); dev = mpc->ac->gdma_dev->gdma_context->dev; - num_rxb = mpc->num_queues * RX_BUFFERS_PER_QUEUE; + num_rxb = num_queues * mpc->rx_queue_size; WARN(mpc->rxbufs_pre, "mana rxbufs_pre exists\n"); mpc->rxbufs_pre = kmalloc_array(num_rxb, sizeof(void *), GFP_KERNEL); @@ -560,30 +781,16 @@ static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu) mpc->rxbpre_total = 0; for (i = 0; i < num_rxb; i++) { - if (mpc->rxbpre_alloc_size > PAGE_SIZE) { - va = netdev_alloc_frag(mpc->rxbpre_alloc_size); - if (!va) - goto error; - - page = virt_to_head_page(va); - /* Check if the frag falls back to single page */ - if (compound_order(page) < - get_order(mpc->rxbpre_alloc_size)) { - put_page(page); - goto error; - } - } else { - page = dev_alloc_page(); - if (!page) - goto error; + page = dev_alloc_pages(get_order(mpc->rxbpre_alloc_size)); + if (!page) + goto error; - va = page_to_virt(page); - } + va = page_to_virt(page); da = dma_map_single(dev, va + mpc->rxbpre_headroom, mpc->rxbpre_datasize, DMA_FROM_DEVICE); if (dma_mapping_error(dev, da)) { - put_page(virt_to_head_page(va)); + put_page(page); goto error; } @@ -595,6 +802,7 @@ static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu) return 0; error: + netdev_err(mpc->ndev, "Failed to pre-allocate RX buffers for %d queues\n", num_queues); mana_pre_dealloc_rxbufs(mpc); return -ENOMEM; } @@ -606,7 +814,7 @@ static int mana_change_mtu(struct net_device *ndev, int new_mtu) int err; /* Pre-allocate buffers to prevent failure in mana_attach later */ - err = mana_pre_alloc_rxbufs(mpc, new_mtu); + err = mana_pre_alloc_rxbufs(mpc, new_mtu, mpc->num_queues); if (err) { netdev_err(ndev, "Insufficient memory for new MTU\n"); return err; @@ -618,12 +826,12 @@ static int mana_change_mtu(struct net_device *ndev, int new_mtu) goto out; } - ndev->mtu = new_mtu; + WRITE_ONCE(ndev->mtu, new_mtu); err = mana_attach(ndev); if (err) { netdev_err(ndev, "mana_attach failed: %d\n", err); - ndev->mtu = old_mtu; + WRITE_ONCE(ndev->mtu, old_mtu); } out: @@ -631,24 +839,113 @@ out: return err; } +static int mana_shaper_set(struct net_shaper_binding *binding, + const struct net_shaper *shaper, + struct netlink_ext_ack *extack) +{ + struct mana_port_context *apc = netdev_priv(binding->netdev); + u32 old_speed, rate; + int err; + + if (shaper->handle.scope != NET_SHAPER_SCOPE_NETDEV) { + NL_SET_ERR_MSG_MOD(extack, "net shaper scope should be netdev"); + return -EINVAL; + } + + if (apc->handle.id && shaper->handle.id != apc->handle.id) { + NL_SET_ERR_MSG_MOD(extack, "Cannot create multiple shapers"); + return -EOPNOTSUPP; + } + + if (!shaper->bw_max || (shaper->bw_max % 100000000)) { + NL_SET_ERR_MSG_MOD(extack, "Please use multiples of 100Mbps for bandwidth"); + return -EINVAL; + } + + rate = div_u64(shaper->bw_max, 1000); /* Convert bps to Kbps */ + rate = div_u64(rate, 1000); /* Convert Kbps to Mbps */ + + /* Get current speed */ + err = mana_query_link_cfg(apc); + old_speed = (err) ? SPEED_UNKNOWN : apc->speed; + + if (!err) { + err = mana_set_bw_clamp(apc, rate, TRI_STATE_TRUE); + apc->speed = (err) ? old_speed : rate; + apc->handle = (err) ? apc->handle : shaper->handle; + } + + return err; +} + +static int mana_shaper_del(struct net_shaper_binding *binding, + const struct net_shaper_handle *handle, + struct netlink_ext_ack *extack) +{ + struct mana_port_context *apc = netdev_priv(binding->netdev); + int err; + + err = mana_set_bw_clamp(apc, 0, TRI_STATE_FALSE); + + if (!err) { + /* Reset mana port context parameters */ + apc->handle.id = 0; + apc->handle.scope = NET_SHAPER_SCOPE_UNSPEC; + apc->speed = apc->max_speed; + } + + return err; +} + +static void mana_shaper_cap(struct net_shaper_binding *binding, + enum net_shaper_scope scope, + unsigned long *flags) +{ + *flags = BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MAX) | + BIT(NET_SHAPER_A_CAPS_SUPPORT_METRIC_BPS); +} + +static const struct net_shaper_ops mana_shaper_ops = { + .set = mana_shaper_set, + .delete = mana_shaper_del, + .capabilities = mana_shaper_cap, +}; + static const struct net_device_ops mana_devops = { .ndo_open = mana_open, .ndo_stop = mana_close, .ndo_select_queue = mana_select_queue, +#if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES) + .ndo_features_check = mana_features_check, +#endif .ndo_start_xmit = mana_start_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_get_stats64 = mana_get_stats64, .ndo_bpf = mana_bpf, .ndo_xdp_xmit = mana_xdp_xmit, .ndo_change_mtu = mana_change_mtu, + .net_shaper_ops = &mana_shaper_ops, }; static void mana_cleanup_port_context(struct mana_port_context *apc) { + /* + * make sure subsequent cleanup attempts don't end up removing already + * cleaned dentry pointer + */ + debugfs_remove(apc->mana_port_debugfs); + apc->mana_port_debugfs = NULL; kfree(apc->rxqs); apc->rxqs = NULL; } +static void mana_cleanup_indir_table(struct mana_port_context *apc) +{ + apc->indir_table_sz = 0; + kfree(apc->indir_table); + kfree(apc->rxobj_table); +} + static int mana_init_port_context(struct mana_port_context *apc) { apc->rxqs = kcalloc(apc->num_queues, sizeof(struct mana_rxq *), @@ -673,8 +970,13 @@ static int mana_send_request(struct mana_context *ac, void *in_buf, err = mana_gd_send_request(gc, in_len, in_buf, out_len, out_buf); if (err || resp->status) { - dev_err(dev, "Failed to send mana message: %d, 0x%x\n", - err, resp->status); + if (err == -EOPNOTSUPP) + return err; + + if (req->req.msg_type != MANA_QUERY_PHY_STAT && + mana_need_log(gc, err)) + dev_err(dev, "Failed to send mana message: %d, 0x%x\n", + err, resp->status); return err ? err : -EPROTO; } @@ -749,8 +1051,10 @@ static void mana_pf_deregister_hw_vport(struct mana_port_context *apc) err = mana_send_request(apc->ac, &req, sizeof(req), &resp, sizeof(resp)); if (err) { - netdev_err(apc->ndev, "Failed to unregister hw vPort: %d\n", - err); + if (mana_en_need_log(apc, err)) + netdev_err(apc->ndev, "Failed to unregister hw vPort: %d\n", + err); + return; } @@ -805,8 +1109,10 @@ static void mana_pf_deregister_filter(struct mana_port_context *apc) err = mana_send_request(apc->ac, &req, sizeof(req), &resp, sizeof(resp)); if (err) { - netdev_err(apc->ndev, "Failed to unregister filter: %d\n", - err); + if (mana_en_need_log(apc, err)) + netdev_err(apc->ndev, "Failed to unregister filter: %d\n", + err); + return; } @@ -820,7 +1126,7 @@ static void mana_pf_deregister_filter(struct mana_port_context *apc) static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver, u32 proto_minor_ver, u32 proto_micro_ver, - u16 *max_num_vports) + u16 *max_num_vports, u8 *bm_hostmode) { struct gdma_context *gc = ac->gdma_dev->gdma_context; struct mana_query_device_cfg_resp resp = {}; @@ -831,7 +1137,7 @@ static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver, mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_DEV_CONFIG, sizeof(req), sizeof(resp)); - req.hdr.resp.msg_version = GDMA_MESSAGE_V2; + req.hdr.resp.msg_version = GDMA_MESSAGE_V3; req.proto_major_ver = proto_major_ver; req.proto_minor_ver = proto_minor_ver; @@ -855,11 +1161,18 @@ static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver, *max_num_vports = resp.max_num_vports; - if (resp.hdr.response.msg_version == GDMA_MESSAGE_V2) + if (resp.hdr.response.msg_version >= GDMA_MESSAGE_V2) gc->adapter_mtu = resp.adapter_mtu; else gc->adapter_mtu = ETH_FRAME_LEN; + if (resp.hdr.response.msg_version >= GDMA_MESSAGE_V3) + *bm_hostmode = resp.bm_hostmode; + else + *bm_hostmode = 0; + + debugfs_create_u16("adapter-MTU", 0400, gc->mana_pci_debugfs, &gc->adapter_mtu); + return 0; } @@ -890,7 +1203,16 @@ static int mana_query_vport_cfg(struct mana_port_context *apc, u32 vport_index, *max_sq = resp.max_num_sq; *max_rq = resp.max_num_rq; - *num_indir_entry = resp.num_indirection_ent; + if (resp.num_indirection_ent > 0 && + resp.num_indirection_ent <= MANA_INDIRECT_TABLE_MAX_SIZE && + is_power_of_2(resp.num_indirection_ent)) { + *num_indir_entry = resp.num_indirection_ent; + } else { + netdev_warn(apc->ndev, + "Setting indirection table size to default %d for vPort %d\n", + MANA_INDIRECT_TABLE_DEF_SIZE, apc->port_idx); + *num_indir_entry = MANA_INDIRECT_TABLE_DEF_SIZE; + } apc->port_handle = resp.vport; ether_addr_copy(apc->mac_addr, resp.mac_addr); @@ -905,7 +1227,7 @@ void mana_uncfg_vport(struct mana_port_context *apc) WARN_ON(apc->vport_use_count < 0); mutex_unlock(&apc->vport_mutex); } -EXPORT_SYMBOL_NS(mana_uncfg_vport, NET_MANA); +EXPORT_SYMBOL_NS(mana_uncfg_vport, "NET_MANA"); int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, u32 doorbell_pg_id) @@ -975,22 +1297,20 @@ out: return err; } -EXPORT_SYMBOL_NS(mana_cfg_vport, NET_MANA); +EXPORT_SYMBOL_NS(mana_cfg_vport, "NET_MANA"); static int mana_cfg_vport_steering(struct mana_port_context *apc, enum TRI_STATE rx, bool update_default_rxobj, bool update_key, bool update_tab) { - u16 num_entries = MANA_INDIRECT_TABLE_SIZE; struct mana_cfg_rx_steer_req_v2 *req; struct mana_cfg_rx_steer_resp resp = {}; struct net_device *ndev = apc->ndev; - mana_handle_t *req_indir_tab; u32 req_buf_size; int err; - req_buf_size = sizeof(*req) + sizeof(mana_handle_t) * num_entries; + req_buf_size = struct_size(req, indir_tab, apc->indir_table_sz); req = kzalloc(req_buf_size, GFP_KERNEL); if (!req) return -ENOMEM; @@ -1001,8 +1321,9 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, req->hdr.req.msg_version = GDMA_MESSAGE_V2; req->vport = apc->port_handle; - req->num_indir_entries = num_entries; - req->indir_tab_offset = sizeof(*req); + req->num_indir_entries = apc->indir_table_sz; + req->indir_tab_offset = offsetof(struct mana_cfg_rx_steer_req_v2, + indir_tab); req->rx_enable = rx; req->rss_enable = apc->rss_state; req->update_default_rxobj = update_default_rxobj; @@ -1014,16 +1335,16 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, if (update_key) memcpy(&req->hashkey, apc->hashkey, MANA_HASH_KEY_SIZE); - if (update_tab) { - req_indir_tab = (mana_handle_t *)(req + 1); - memcpy(req_indir_tab, apc->rxobj_table, - req->num_indir_entries * sizeof(mana_handle_t)); - } + if (update_tab) + memcpy(req->indir_tab, apc->rxobj_table, + flex_array_size(req, indir_tab, req->num_indir_entries)); err = mana_send_request(apc->ac, req, req_buf_size, &resp, sizeof(resp)); if (err) { - netdev_err(ndev, "Failed to configure vPort RX: %d\n", err); + if (mana_en_need_log(apc, err)) + netdev_err(ndev, "Failed to configure vPort RX: %d\n", err); + goto out; } @@ -1041,12 +1362,101 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, } netdev_info(ndev, "Configured steering vPort %llu entries %u\n", - apc->port_handle, num_entries); + apc->port_handle, apc->indir_table_sz); out: kfree(req); return err; } +int mana_query_link_cfg(struct mana_port_context *apc) +{ + struct net_device *ndev = apc->ndev; + struct mana_query_link_config_resp resp = {}; + struct mana_query_link_config_req req = {}; + int err; + + mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_LINK_CONFIG, + sizeof(req), sizeof(resp)); + + req.vport = apc->port_handle; + req.hdr.resp.msg_version = GDMA_MESSAGE_V2; + + err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + sizeof(resp)); + + if (err) { + if (err == -EOPNOTSUPP) { + netdev_info_once(ndev, "MANA_QUERY_LINK_CONFIG not supported\n"); + return err; + } + netdev_err(ndev, "Failed to query link config: %d\n", err); + return err; + } + + err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_LINK_CONFIG, + sizeof(resp)); + + if (err || resp.hdr.status) { + netdev_err(ndev, "Failed to query link config: %d, 0x%x\n", err, + resp.hdr.status); + if (!err) + err = -EOPNOTSUPP; + return err; + } + + if (resp.qos_unconfigured) { + err = -EINVAL; + return err; + } + apc->speed = resp.link_speed_mbps; + apc->max_speed = resp.qos_speed_mbps; + return 0; +} + +int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed, + int enable_clamping) +{ + struct mana_set_bw_clamp_resp resp = {}; + struct mana_set_bw_clamp_req req = {}; + struct net_device *ndev = apc->ndev; + int err; + + mana_gd_init_req_hdr(&req.hdr, MANA_SET_BW_CLAMP, + sizeof(req), sizeof(resp)); + req.vport = apc->port_handle; + req.link_speed_mbps = speed; + req.enable_clamping = enable_clamping; + + err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + sizeof(resp)); + + if (err) { + if (err == -EOPNOTSUPP) { + netdev_info_once(ndev, "MANA_SET_BW_CLAMP not supported\n"); + return err; + } + netdev_err(ndev, "Failed to set bandwidth clamp for speed %u, err = %d", + speed, err); + return err; + } + + err = mana_verify_resp_hdr(&resp.hdr, MANA_SET_BW_CLAMP, + sizeof(resp)); + + if (err || resp.hdr.status) { + netdev_err(ndev, "Failed to set bandwidth clamp: %d, 0x%x\n", err, + resp.hdr.status); + if (!err) + err = -EOPNOTSUPP; + return err; + } + + if (resp.qos_unconfigured) + netdev_info(ndev, "QoS is unconfigured\n"); + + return 0; +} + int mana_create_wq_obj(struct mana_port_context *apc, mana_handle_t vport, u32 wq_type, struct mana_obj_spec *wq_spec, @@ -1100,7 +1510,7 @@ int mana_create_wq_obj(struct mana_port_context *apc, out: return err; } -EXPORT_SYMBOL_NS(mana_create_wq_obj, NET_MANA); +EXPORT_SYMBOL_NS(mana_create_wq_obj, "NET_MANA"); void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, mana_handle_t wq_obj) @@ -1118,7 +1528,9 @@ void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, err = mana_send_request(apc->ac, &req, sizeof(req), &resp, sizeof(resp)); if (err) { - netdev_err(ndev, "Failed to destroy WQ object: %d\n", err); + if (mana_en_need_log(apc, err)) + netdev_err(ndev, "Failed to destroy WQ object: %d\n", err); + return; } @@ -1128,7 +1540,7 @@ void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, netdev_err(ndev, "Failed to destroy WQ object: %d, 0x%x\n", err, resp.hdr.status); } -EXPORT_SYMBOL_NS(mana_destroy_wq_obj, NET_MANA); +EXPORT_SYMBOL_NS(mana_destroy_wq_obj, "NET_MANA"); static void mana_destroy_eq(struct mana_context *ac) { @@ -1139,6 +1551,9 @@ static void mana_destroy_eq(struct mana_context *ac) if (!ac->eqs) return; + debugfs_remove_recursive(ac->mana_eqs_debugfs); + ac->mana_eqs_debugfs = NULL; + for (i = 0; i < gc->max_num_queues; i++) { eq = ac->eqs[i].eq; if (!eq) @@ -1151,6 +1566,18 @@ static void mana_destroy_eq(struct mana_context *ac) ac->eqs = NULL; } +static void mana_create_eq_debugfs(struct mana_context *ac, int i) +{ + struct mana_eq eq = ac->eqs[i]; + char eqnum[32]; + + sprintf(eqnum, "eq%d", i); + eq.mana_eq_debugfs = debugfs_create_dir(eqnum, ac->mana_eqs_debugfs); + debugfs_create_u32("head", 0400, eq.mana_eq_debugfs, &eq.eq->head); + debugfs_create_u32("tail", 0400, eq.mana_eq_debugfs, &eq.eq->tail); + debugfs_create_file("eq_dump", 0400, eq.mana_eq_debugfs, eq.eq, &mana_dbg_q_fops); +} + static int mana_create_eq(struct mana_context *ac) { struct gdma_dev *gd = ac->gdma_dev; @@ -1171,10 +1598,16 @@ static int mana_create_eq(struct mana_context *ac) spec.eq.context = ac->eqs; spec.eq.log2_throttle_limit = LOG2_EQ_THROTTLE; + ac->mana_eqs_debugfs = debugfs_create_dir("EQs", gc->mana_pci_debugfs); + for (i = 0; i < gc->max_num_queues; i++) { + spec.eq.msix_index = (i + 1) % gc->num_msix_usable; err = mana_gd_create_mana_eq(gd, &spec, &ac->eqs[i].eq); - if (err) + if (err) { + dev_err(gc->dev, "Failed to create EQ %d : %d\n", i, err); goto out; + } + mana_create_eq_debugfs(ac, i); } return 0; @@ -1253,16 +1686,21 @@ static int mana_move_wq_tail(struct gdma_queue *wq, u32 num_units) return 0; } -static void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc) +void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc) { struct mana_skb_head *ash = (struct mana_skb_head *)skb->head; struct gdma_context *gc = apc->ac->gdma_dev->gdma_context; struct device *dev = gc->dev; - int i; + int hsg, i; + + /* Number of SGEs of linear part */ + hsg = (skb_is_gso(skb) && skb_headlen(skb) > ash->size[0]) ? 2 : 1; - dma_unmap_single(dev, ash->dma_handle[0], ash->size[0], DMA_TO_DEVICE); + for (i = 0; i < hsg; i++) + dma_unmap_single(dev, ash->dma_handle[i], ash->size[i], + DMA_TO_DEVICE); - for (i = 1; i < skb_shinfo(skb)->nr_frags + 1; i++) + for (i = hsg; i < skb_shinfo(skb)->nr_frags + hsg; i++) dma_unmap_page(dev, ash->dma_handle[i], ash->size[i], DMA_TO_DEVICE); } @@ -1317,19 +1755,23 @@ static void mana_poll_tx_cq(struct mana_cq *cq) case CQE_TX_VPORT_IDX_OUT_OF_RANGE: case CQE_TX_VPORT_DISABLED: case CQE_TX_VLAN_TAGGING_VIOLATION: - WARN_ONCE(1, "TX: CQE error %d: ignored.\n", - cqe_oob->cqe_hdr.cqe_type); + if (net_ratelimit()) + netdev_err(ndev, "TX: CQE error %d\n", + cqe_oob->cqe_hdr.cqe_type); + apc->eth_stats.tx_cqe_err++; break; default: - /* If the CQE type is unexpected, log an error, assert, - * and go through the error path. + /* If the CQE type is unknown, log an error, + * and still free the SKB, update tail, etc. */ - WARN_ONCE(1, "TX: Unexpected CQE type %d: HW BUG?\n", - cqe_oob->cqe_hdr.cqe_type); + if (net_ratelimit()) + netdev_err(ndev, "TX: unknown CQE type %d\n", + cqe_oob->cqe_hdr.cqe_type); + apc->eth_stats.tx_cqe_unknown_type++; - return; + break; } if (WARN_ON_ONCE(txq->gdma_txq_id != completions[i].wq_num)) @@ -1406,8 +1848,12 @@ static struct sk_buff *mana_build_skb(struct mana_rxq *rxq, void *buf_va, return NULL; if (xdp->data_hard_start) { + u32 metasize = xdp->data - xdp->data_meta; + skb_reserve(skb, xdp->data - xdp->data_hard_start); skb_put(skb, xdp->data_end - xdp->data); + if (metasize) + skb_metadata_set(skb, metasize); return skb; } @@ -1505,8 +1951,11 @@ drop_xdp: drop: if (from_pool) { - page_pool_recycle_direct(rxq->page_pool, - virt_to_head_page(buf_va)); + if (rxq->frag_count == 1) + page_pool_recycle_direct(rxq->page_pool, + virt_to_head_page(buf_va)); + else + page_pool_free_va(rxq->page_pool, buf_va, true); } else { WARN_ON_ONCE(rxq->xdp_save_va); /* Save for reuse */ @@ -1519,51 +1968,49 @@ drop: } static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, - dma_addr_t *da, bool *from_pool, bool is_napi) + dma_addr_t *da, bool *from_pool) { struct page *page; + u32 offset; void *va; - *from_pool = false; - /* Reuse XDP dropped page if available */ - if (rxq->xdp_save_va) { - va = rxq->xdp_save_va; - rxq->xdp_save_va = NULL; - } else if (rxq->alloc_size > PAGE_SIZE) { - if (is_napi) - va = napi_alloc_frag(rxq->alloc_size); - else - va = netdev_alloc_frag(rxq->alloc_size); + /* Don't use fragments for jumbo frames or XDP where it's 1 fragment + * per page. + */ + if (rxq->frag_count == 1) { + /* Reuse XDP dropped page if available */ + if (rxq->xdp_save_va) { + va = rxq->xdp_save_va; + page = virt_to_head_page(va); + rxq->xdp_save_va = NULL; + } else { + page = page_pool_dev_alloc_pages(rxq->page_pool); + if (!page) + return NULL; - if (!va) - return NULL; + *from_pool = true; + va = page_to_virt(page); + } - page = virt_to_head_page(va); - /* Check if the frag falls back to single page */ - if (compound_order(page) < get_order(rxq->alloc_size)) { - put_page(page); + *da = dma_map_single(dev, va + rxq->headroom, rxq->datasize, + DMA_FROM_DEVICE); + if (dma_mapping_error(dev, *da)) { + mana_put_rx_page(rxq, page, *from_pool); return NULL; } - } else { - page = page_pool_dev_alloc_pages(rxq->page_pool); - if (!page) - return NULL; - *from_pool = true; - va = page_to_virt(page); + return va; } - *da = dma_map_single(dev, va + rxq->headroom, rxq->datasize, - DMA_FROM_DEVICE); - if (dma_mapping_error(dev, *da)) { - if (*from_pool) - page_pool_put_full_page(rxq->page_pool, page, false); - else - put_page(virt_to_head_page(va)); - + page = page_pool_dev_alloc_frag(rxq->page_pool, &offset, + rxq->alloc_size); + if (!page) return NULL; - } + + va = page_to_virt(page) + offset; + *da = page_pool_get_dma_addr(page) + offset + rxq->headroom; + *from_pool = true; return va; } @@ -1577,12 +2024,12 @@ static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq, dma_addr_t da; void *va; - va = mana_get_rxfrag(rxq, dev, &da, &from_pool, true); + va = mana_get_rxfrag(rxq, dev, &da, &from_pool); if (!va) return; - - dma_unmap_single(dev, rxoob->sgl[0].address, rxq->datasize, - DMA_FROM_DEVICE); + if (!rxoob->from_pool || rxq->frag_count == 1) + dma_unmap_single(dev, rxoob->sgl[0].address, rxq->datasize, + DMA_FROM_DEVICE); *old_buf = rxoob->buf_va; *old_fp = rxoob->from_pool; @@ -1693,7 +2140,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) { struct mana_cq *cq = context; - u8 arm_bit; int w; WARN_ON_ONCE(cq->gdma_cq != gdma_queue); @@ -1704,16 +2150,23 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) mana_poll_tx_cq(cq); w = cq->work_done; - - if (w < cq->budget && - napi_complete_done(&cq->napi, w)) { - arm_bit = SET_ARM_BIT; - } else { - arm_bit = 0; + cq->work_done_since_doorbell += w; + + if (w < cq->budget) { + mana_gd_ring_cq(gdma_queue, SET_ARM_BIT); + cq->work_done_since_doorbell = 0; + napi_complete_done(&cq->napi, w); + } else if (cq->work_done_since_doorbell > + cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) { + /* MANA hardware requires at least one doorbell ring every 8 + * wraparounds of CQ even if there is no need to arm the CQ. + * This driver rings the doorbell as soon as we have exceeded + * 4 wraparounds. + */ + mana_gd_ring_cq(gdma_queue, 0); + cq->work_done_since_doorbell = 0; } - mana_gd_ring_cq(gdma_queue, arm_bit); - return w; } @@ -1766,11 +2219,16 @@ static void mana_destroy_txq(struct mana_port_context *apc) return; for (i = 0; i < apc->num_queues; i++) { - napi = &apc->tx_qp[i].tx_cq.napi; - napi_synchronize(napi); - napi_disable(napi); - netif_napi_del(napi); + debugfs_remove_recursive(apc->tx_qp[i].mana_tx_debugfs); + apc->tx_qp[i].mana_tx_debugfs = NULL; + napi = &apc->tx_qp[i].tx_cq.napi; + if (apc->tx_qp[i].txq.napi_initialized) { + napi_synchronize(napi); + napi_disable_locked(napi); + netif_napi_del_locked(napi); + apc->tx_qp[i].txq.napi_initialized = false; + } mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object); mana_deinit_cq(apc, &apc->tx_qp[i].tx_cq); @@ -1782,6 +2240,31 @@ static void mana_destroy_txq(struct mana_port_context *apc) apc->tx_qp = NULL; } +static void mana_create_txq_debugfs(struct mana_port_context *apc, int idx) +{ + struct mana_tx_qp *tx_qp = &apc->tx_qp[idx]; + char qnum[32]; + + sprintf(qnum, "TX-%d", idx); + tx_qp->mana_tx_debugfs = debugfs_create_dir(qnum, apc->mana_port_debugfs); + debugfs_create_u32("sq_head", 0400, tx_qp->mana_tx_debugfs, + &tx_qp->txq.gdma_sq->head); + debugfs_create_u32("sq_tail", 0400, tx_qp->mana_tx_debugfs, + &tx_qp->txq.gdma_sq->tail); + debugfs_create_u32("sq_pend_skb_qlen", 0400, tx_qp->mana_tx_debugfs, + &tx_qp->txq.pending_skbs.qlen); + debugfs_create_u32("cq_head", 0400, tx_qp->mana_tx_debugfs, + &tx_qp->tx_cq.gdma_cq->head); + debugfs_create_u32("cq_tail", 0400, tx_qp->mana_tx_debugfs, + &tx_qp->tx_cq.gdma_cq->tail); + debugfs_create_u32("cq_budget", 0400, tx_qp->mana_tx_debugfs, + &tx_qp->tx_cq.budget); + debugfs_create_file("txq_dump", 0400, tx_qp->mana_tx_debugfs, + tx_qp->txq.gdma_sq, &mana_dbg_q_fops); + debugfs_create_file("cq_dump", 0400, tx_qp->mana_tx_debugfs, + tx_qp->tx_cq.gdma_cq, &mana_dbg_q_fops); +} + static int mana_create_txq(struct mana_port_context *apc, struct net_device *net) { @@ -1804,15 +2287,17 @@ static int mana_create_txq(struct mana_port_context *apc, return -ENOMEM; /* The minimum size of the WQE is 32 bytes, hence - * MAX_SEND_BUFFERS_PER_QUEUE represents the maximum number of WQEs + * apc->tx_queue_size represents the maximum number of WQEs * the SQ can store. This value is then used to size other queues * to prevent overflow. + * Also note that the txq_size is always going to be MANA_PAGE_ALIGNED, + * as min val of apc->tx_queue_size is 128 and that would make + * txq_size 128*32 = 4096 and the other higher values of apc->tx_queue_size + * are always power of two */ - txq_size = MAX_SEND_BUFFERS_PER_QUEUE * 32; - BUILD_BUG_ON(!PAGE_ALIGNED(txq_size)); + txq_size = apc->tx_queue_size * 32; - cq_size = MAX_SEND_BUFFERS_PER_QUEUE * COMP_ENTRY_SIZE; - cq_size = PAGE_ALIGN(cq_size); + cq_size = apc->tx_queue_size * COMP_ENTRY_SIZE; gc = gd->gdma_context; @@ -1826,6 +2311,7 @@ static int mana_create_txq(struct mana_port_context *apc, txq->ndev = net; txq->net_txq = netdev_get_tx_queue(net, i); txq->vp_offset = apc->tx_vp_offset; + txq->napi_initialized = false; skb_queue_head_init(&txq->pending_skbs); memset(&spec, 0, sizeof(spec)); @@ -1890,20 +2376,26 @@ static int mana_create_txq(struct mana_port_context *apc, gc->cq_table[cq->gdma_id] = cq->gdma_cq; - netif_napi_add_tx(net, &cq->napi, mana_poll); - napi_enable(&cq->napi); + mana_create_txq_debugfs(apc, i); + + set_bit(NAPI_STATE_NO_BUSY_POLL, &cq->napi.state); + netif_napi_add_locked(net, &cq->napi, mana_poll); + napi_enable_locked(&cq->napi); + txq->napi_initialized = true; mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT); } return 0; out: + netdev_err(net, "Failed to create %d TX queues, %d\n", + apc->num_queues, err); mana_destroy_txq(apc); return err; } static void mana_destroy_rxq(struct mana_port_context *apc, - struct mana_rxq *rxq, bool validate_state) + struct mana_rxq *rxq, bool napi_initialized) { struct gdma_context *gc = apc->ac->gdma_dev->gdma_context; @@ -1916,17 +2408,19 @@ static void mana_destroy_rxq(struct mana_port_context *apc, if (!rxq) return; + debugfs_remove_recursive(rxq->mana_rx_debugfs); + rxq->mana_rx_debugfs = NULL; + napi = &rxq->rx_cq.napi; - if (validate_state) + if (napi_initialized) { napi_synchronize(napi); - napi_disable(napi); - + napi_disable_locked(napi); + netif_napi_del_locked(napi); + } xdp_rxq_info_unreg(&rxq->xdp_rxq); - netif_napi_del(napi); - mana_destroy_wq_obj(apc, GDMA_RQ, rxq->rxobj); mana_deinit_cq(apc, &rxq->rx_cq); @@ -1940,15 +2434,15 @@ static void mana_destroy_rxq(struct mana_port_context *apc, if (!rx_oob->buf_va) continue; - dma_unmap_single(dev, rx_oob->sgl[0].address, - rx_oob->sgl[0].size, DMA_FROM_DEVICE); - page = virt_to_head_page(rx_oob->buf_va); - if (rx_oob->from_pool) - page_pool_put_full_page(rxq->page_pool, page, false); - else - put_page(page); + if (rxq->frag_count == 1 || !rx_oob->from_pool) { + dma_unmap_single(dev, rx_oob->sgl[0].address, + rx_oob->sgl[0].size, DMA_FROM_DEVICE); + mana_put_rx_page(rxq, page, rx_oob->from_pool); + } else { + page_pool_free_va(rxq->page_pool, rx_oob->buf_va, true); + } rx_oob->buf_va = NULL; } @@ -1972,7 +2466,7 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key, if (mpc->rxbufs_pre) va = mana_get_rxbuf_pre(rxq, &da); else - va = mana_get_rxfrag(rxq, dev, &da, &from_pool, false); + va = mana_get_rxfrag(rxq, dev, &da, &from_pool); if (!va) return -ENOMEM; @@ -2050,12 +2544,26 @@ static int mana_push_wqe(struct mana_rxq *rxq) static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc) { + struct mana_port_context *mpc = netdev_priv(rxq->ndev); struct page_pool_params pprm = {}; int ret; - pprm.pool_size = RX_BUFFERS_PER_QUEUE; + pprm.pool_size = mpc->rx_queue_size / rxq->frag_count + 1; pprm.nid = gc->numa_node; pprm.napi = &rxq->rx_cq.napi; + pprm.netdev = rxq->ndev; + pprm.order = get_order(rxq->alloc_size); + pprm.queue_idx = rxq->rxq_idx; + pprm.dev = gc->dev; + + /* Let the page pool do the dma map when page sharing with multiple + * fragments enabled for rx buffers. + */ + if (rxq->frag_count > 1) { + pprm.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; + pprm.max_len = PAGE_SIZE; + pprm.dma_dir = DMA_FROM_DEVICE; + } rxq->page_pool = page_pool_create(&pprm); @@ -2084,19 +2592,18 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, gc = gd->gdma_context; - rxq = kzalloc(struct_size(rxq, rx_oobs, RX_BUFFERS_PER_QUEUE), + rxq = kzalloc(struct_size(rxq, rx_oobs, apc->rx_queue_size), GFP_KERNEL); if (!rxq) return NULL; rxq->ndev = ndev; - rxq->num_rx_buf = RX_BUFFERS_PER_QUEUE; + rxq->num_rx_buf = apc->rx_queue_size; rxq->rxq_idx = rxq_idx; rxq->rxobj = INVALID_MANA_HANDLE; - mana_get_rxbuf_cfg(ndev->mtu, &rxq->datasize, &rxq->alloc_size, - &rxq->headroom); - + mana_get_rxbuf_cfg(apc, ndev->mtu, &rxq->datasize, &rxq->alloc_size, + &rxq->headroom, &rxq->frag_count); /* Create page pool for RX queue */ err = mana_create_page_pool(rxq, gc); if (err) { @@ -2108,8 +2615,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, if (err) goto out; - rq_size = PAGE_ALIGN(rq_size); - cq_size = PAGE_ALIGN(cq_size); + rq_size = MANA_PAGE_ALIGN(rq_size); + cq_size = MANA_PAGE_ALIGN(cq_size); /* Create RQ */ memset(&spec, 0, sizeof(spec)); @@ -2171,14 +2678,14 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, gc->cq_table[cq->gdma_id] = cq->gdma_cq; - netif_napi_add_weight(ndev, &cq->napi, mana_poll, 1); + netif_napi_add_weight_locked(ndev, &cq->napi, mana_poll, 1); WARN_ON(xdp_rxq_info_reg(&rxq->xdp_rxq, ndev, rxq_idx, cq->napi.napi_id)); WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq, MEM_TYPE_PAGE_POOL, rxq->page_pool)); - napi_enable(&cq->napi); + napi_enable_locked(&cq->napi); mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT); out: @@ -2195,6 +2702,28 @@ out: return NULL; } +static void mana_create_rxq_debugfs(struct mana_port_context *apc, int idx) +{ + struct mana_rxq *rxq; + char qnum[32]; + + rxq = apc->rxqs[idx]; + + sprintf(qnum, "RX-%d", idx); + rxq->mana_rx_debugfs = debugfs_create_dir(qnum, apc->mana_port_debugfs); + debugfs_create_u32("rq_head", 0400, rxq->mana_rx_debugfs, &rxq->gdma_rq->head); + debugfs_create_u32("rq_tail", 0400, rxq->mana_rx_debugfs, &rxq->gdma_rq->tail); + debugfs_create_u32("rq_nbuf", 0400, rxq->mana_rx_debugfs, &rxq->num_rx_buf); + debugfs_create_u32("cq_head", 0400, rxq->mana_rx_debugfs, + &rxq->rx_cq.gdma_cq->head); + debugfs_create_u32("cq_tail", 0400, rxq->mana_rx_debugfs, + &rxq->rx_cq.gdma_cq->tail); + debugfs_create_u32("cq_budget", 0400, rxq->mana_rx_debugfs, &rxq->rx_cq.budget); + debugfs_create_file("rxq_dump", 0400, rxq->mana_rx_debugfs, rxq->gdma_rq, &mana_dbg_q_fops); + debugfs_create_file("cq_dump", 0400, rxq->mana_rx_debugfs, rxq->rx_cq.gdma_cq, + &mana_dbg_q_fops); +} + static int mana_add_rx_queues(struct mana_port_context *apc, struct net_device *ndev) { @@ -2207,12 +2736,15 @@ static int mana_add_rx_queues(struct mana_port_context *apc, rxq = mana_create_rxq(apc, i, &ac->eqs[i], ndev); if (!rxq) { err = -ENOMEM; + netdev_err(ndev, "Failed to create rxq %d : %d\n", i, err); goto out; } u64_stats_init(&rxq->stats.syncp); apc->rxqs[i] = rxq; + + mana_create_rxq_debugfs(apc, i); } apc->default_rxobj = apc->rxqs[0]->rxobj; @@ -2238,7 +2770,7 @@ static void mana_destroy_vport(struct mana_port_context *apc) mana_destroy_txq(apc); mana_uncfg_vport(apc); - if (gd->gdma_context->is_pf) + if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode) mana_pf_deregister_hw_vport(apc); } @@ -2250,7 +2782,7 @@ static int mana_create_vport(struct mana_port_context *apc, apc->default_rxobj = INVALID_MANA_HANDLE; - if (gd->gdma_context->is_pf) { + if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode) { err = mana_pf_register_hw_vport(apc); if (err) return err; @@ -2263,11 +2795,33 @@ static int mana_create_vport(struct mana_port_context *apc, return mana_create_txq(apc, net); } +static int mana_rss_table_alloc(struct mana_port_context *apc) +{ + if (!apc->indir_table_sz) { + netdev_err(apc->ndev, + "Indirection table size not set for vPort %d\n", + apc->port_idx); + return -EINVAL; + } + + apc->indir_table = kcalloc(apc->indir_table_sz, sizeof(u32), GFP_KERNEL); + if (!apc->indir_table) + return -ENOMEM; + + apc->rxobj_table = kcalloc(apc->indir_table_sz, sizeof(mana_handle_t), GFP_KERNEL); + if (!apc->rxobj_table) { + kfree(apc->indir_table); + return -ENOMEM; + } + + return 0; +} + static void mana_rss_table_init(struct mana_port_context *apc) { int i; - for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) + for (i = 0; i < apc->indir_table_sz; i++) apc->indir_table[i] = ethtool_rxfh_indir_default(i, apc->num_queues); } @@ -2280,7 +2834,7 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx, int i; if (update_tab) { - for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) { + for (i = 0; i < apc->indir_table_sz; i++) { queue_idx = apc->indir_table[i]; apc->rxobj_table[i] = apc->rxqs[queue_idx]->rxobj; } @@ -2295,60 +2849,195 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx, return 0; } -void mana_query_gf_stats(struct mana_port_context *apc) +int mana_query_gf_stats(struct mana_context *ac) { + struct gdma_context *gc = ac->gdma_dev->gdma_context; struct mana_query_gf_stat_resp resp = {}; struct mana_query_gf_stat_req req = {}; - struct net_device *ndev = apc->ndev; + struct device *dev = gc->dev; int err; mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_GF_STAT, sizeof(req), sizeof(resp)); - req.req_stats = STATISTICS_FLAGS_HC_TX_BYTES | + req.hdr.resp.msg_version = GDMA_MESSAGE_V2; + req.req_stats = STATISTICS_FLAGS_RX_DISCARDS_NO_WQE | + STATISTICS_FLAGS_RX_ERRORS_VPORT_DISABLED | + STATISTICS_FLAGS_HC_RX_BYTES | + STATISTICS_FLAGS_HC_RX_UCAST_PACKETS | + STATISTICS_FLAGS_HC_RX_UCAST_BYTES | + STATISTICS_FLAGS_HC_RX_MCAST_PACKETS | + STATISTICS_FLAGS_HC_RX_MCAST_BYTES | + STATISTICS_FLAGS_HC_RX_BCAST_PACKETS | + STATISTICS_FLAGS_HC_RX_BCAST_BYTES | + STATISTICS_FLAGS_TX_ERRORS_GF_DISABLED | + STATISTICS_FLAGS_TX_ERRORS_VPORT_DISABLED | + STATISTICS_FLAGS_TX_ERRORS_INVAL_VPORT_OFFSET_PACKETS | + STATISTICS_FLAGS_TX_ERRORS_VLAN_ENFORCEMENT | + STATISTICS_FLAGS_TX_ERRORS_ETH_TYPE_ENFORCEMENT | + STATISTICS_FLAGS_TX_ERRORS_SA_ENFORCEMENT | + STATISTICS_FLAGS_TX_ERRORS_SQPDID_ENFORCEMENT | + STATISTICS_FLAGS_TX_ERRORS_CQPDID_ENFORCEMENT | + STATISTICS_FLAGS_TX_ERRORS_MTU_VIOLATION | + STATISTICS_FLAGS_TX_ERRORS_INVALID_OOB | + STATISTICS_FLAGS_HC_TX_BYTES | STATISTICS_FLAGS_HC_TX_UCAST_PACKETS | STATISTICS_FLAGS_HC_TX_UCAST_BYTES | STATISTICS_FLAGS_HC_TX_MCAST_PACKETS | STATISTICS_FLAGS_HC_TX_MCAST_BYTES | STATISTICS_FLAGS_HC_TX_BCAST_PACKETS | - STATISTICS_FLAGS_HC_TX_BCAST_BYTES; + STATISTICS_FLAGS_HC_TX_BCAST_BYTES | + STATISTICS_FLAGS_TX_ERRORS_GDMA_ERROR; - err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + err = mana_send_request(ac, &req, sizeof(req), &resp, sizeof(resp)); if (err) { - netdev_err(ndev, "Failed to query GF stats: %d\n", err); - return; + dev_err(dev, "Failed to query GF stats: %d\n", err); + return err; } err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_GF_STAT, sizeof(resp)); if (err || resp.hdr.status) { - netdev_err(ndev, "Failed to query GF stats: %d, 0x%x\n", err, - resp.hdr.status); + dev_err(dev, "Failed to query GF stats: %d, 0x%x\n", err, + resp.hdr.status); + return err; + } + + ac->hc_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe; + ac->hc_stats.hc_rx_err_vport_disabled = resp.rx_err_vport_disabled; + ac->hc_stats.hc_rx_bytes = resp.hc_rx_bytes; + ac->hc_stats.hc_rx_ucast_pkts = resp.hc_rx_ucast_pkts; + ac->hc_stats.hc_rx_ucast_bytes = resp.hc_rx_ucast_bytes; + ac->hc_stats.hc_rx_bcast_pkts = resp.hc_rx_bcast_pkts; + ac->hc_stats.hc_rx_bcast_bytes = resp.hc_rx_bcast_bytes; + ac->hc_stats.hc_rx_mcast_pkts = resp.hc_rx_mcast_pkts; + ac->hc_stats.hc_rx_mcast_bytes = resp.hc_rx_mcast_bytes; + ac->hc_stats.hc_tx_err_gf_disabled = resp.tx_err_gf_disabled; + ac->hc_stats.hc_tx_err_vport_disabled = resp.tx_err_vport_disabled; + ac->hc_stats.hc_tx_err_inval_vportoffset_pkt = + resp.tx_err_inval_vport_offset_pkt; + ac->hc_stats.hc_tx_err_vlan_enforcement = + resp.tx_err_vlan_enforcement; + ac->hc_stats.hc_tx_err_eth_type_enforcement = + resp.tx_err_ethtype_enforcement; + ac->hc_stats.hc_tx_err_sa_enforcement = resp.tx_err_SA_enforcement; + ac->hc_stats.hc_tx_err_sqpdid_enforcement = + resp.tx_err_SQPDID_enforcement; + ac->hc_stats.hc_tx_err_cqpdid_enforcement = + resp.tx_err_CQPDID_enforcement; + ac->hc_stats.hc_tx_err_mtu_violation = resp.tx_err_mtu_violation; + ac->hc_stats.hc_tx_err_inval_oob = resp.tx_err_inval_oob; + ac->hc_stats.hc_tx_bytes = resp.hc_tx_bytes; + ac->hc_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts; + ac->hc_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes; + ac->hc_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts; + ac->hc_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes; + ac->hc_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts; + ac->hc_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes; + ac->hc_stats.hc_tx_err_gdma = resp.tx_err_gdma; + + return 0; +} + +void mana_query_phy_stats(struct mana_port_context *apc) +{ + struct mana_query_phy_stat_resp resp = {}; + struct mana_query_phy_stat_req req = {}; + struct net_device *ndev = apc->ndev; + int err; + + mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_PHY_STAT, + sizeof(req), sizeof(resp)); + err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + sizeof(resp)); + if (err) + return; + + err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_PHY_STAT, + sizeof(resp)); + if (err || resp.hdr.status) { + netdev_err(ndev, + "Failed to query PHY stats: %d, resp:0x%x\n", + err, resp.hdr.status); return; } - apc->eth_stats.hc_tx_bytes = resp.hc_tx_bytes; - apc->eth_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts; - apc->eth_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes; - apc->eth_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts; - apc->eth_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes; - apc->eth_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts; - apc->eth_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes; + /* Aggregate drop counters */ + apc->phy_stats.rx_pkt_drop_phy = resp.rx_pkt_drop_phy; + apc->phy_stats.tx_pkt_drop_phy = resp.tx_pkt_drop_phy; + + /* Per TC traffic Counters */ + apc->phy_stats.rx_pkt_tc0_phy = resp.rx_pkt_tc0_phy; + apc->phy_stats.tx_pkt_tc0_phy = resp.tx_pkt_tc0_phy; + apc->phy_stats.rx_pkt_tc1_phy = resp.rx_pkt_tc1_phy; + apc->phy_stats.tx_pkt_tc1_phy = resp.tx_pkt_tc1_phy; + apc->phy_stats.rx_pkt_tc2_phy = resp.rx_pkt_tc2_phy; + apc->phy_stats.tx_pkt_tc2_phy = resp.tx_pkt_tc2_phy; + apc->phy_stats.rx_pkt_tc3_phy = resp.rx_pkt_tc3_phy; + apc->phy_stats.tx_pkt_tc3_phy = resp.tx_pkt_tc3_phy; + apc->phy_stats.rx_pkt_tc4_phy = resp.rx_pkt_tc4_phy; + apc->phy_stats.tx_pkt_tc4_phy = resp.tx_pkt_tc4_phy; + apc->phy_stats.rx_pkt_tc5_phy = resp.rx_pkt_tc5_phy; + apc->phy_stats.tx_pkt_tc5_phy = resp.tx_pkt_tc5_phy; + apc->phy_stats.rx_pkt_tc6_phy = resp.rx_pkt_tc6_phy; + apc->phy_stats.tx_pkt_tc6_phy = resp.tx_pkt_tc6_phy; + apc->phy_stats.rx_pkt_tc7_phy = resp.rx_pkt_tc7_phy; + apc->phy_stats.tx_pkt_tc7_phy = resp.tx_pkt_tc7_phy; + + /* Per TC byte Counters */ + apc->phy_stats.rx_byte_tc0_phy = resp.rx_byte_tc0_phy; + apc->phy_stats.tx_byte_tc0_phy = resp.tx_byte_tc0_phy; + apc->phy_stats.rx_byte_tc1_phy = resp.rx_byte_tc1_phy; + apc->phy_stats.tx_byte_tc1_phy = resp.tx_byte_tc1_phy; + apc->phy_stats.rx_byte_tc2_phy = resp.rx_byte_tc2_phy; + apc->phy_stats.tx_byte_tc2_phy = resp.tx_byte_tc2_phy; + apc->phy_stats.rx_byte_tc3_phy = resp.rx_byte_tc3_phy; + apc->phy_stats.tx_byte_tc3_phy = resp.tx_byte_tc3_phy; + apc->phy_stats.rx_byte_tc4_phy = resp.rx_byte_tc4_phy; + apc->phy_stats.tx_byte_tc4_phy = resp.tx_byte_tc4_phy; + apc->phy_stats.rx_byte_tc5_phy = resp.rx_byte_tc5_phy; + apc->phy_stats.tx_byte_tc5_phy = resp.tx_byte_tc5_phy; + apc->phy_stats.rx_byte_tc6_phy = resp.rx_byte_tc6_phy; + apc->phy_stats.tx_byte_tc6_phy = resp.tx_byte_tc6_phy; + apc->phy_stats.rx_byte_tc7_phy = resp.rx_byte_tc7_phy; + apc->phy_stats.tx_byte_tc7_phy = resp.tx_byte_tc7_phy; + + /* Per TC pause Counters */ + apc->phy_stats.rx_pause_tc0_phy = resp.rx_pause_tc0_phy; + apc->phy_stats.tx_pause_tc0_phy = resp.tx_pause_tc0_phy; + apc->phy_stats.rx_pause_tc1_phy = resp.rx_pause_tc1_phy; + apc->phy_stats.tx_pause_tc1_phy = resp.tx_pause_tc1_phy; + apc->phy_stats.rx_pause_tc2_phy = resp.rx_pause_tc2_phy; + apc->phy_stats.tx_pause_tc2_phy = resp.tx_pause_tc2_phy; + apc->phy_stats.rx_pause_tc3_phy = resp.rx_pause_tc3_phy; + apc->phy_stats.tx_pause_tc3_phy = resp.tx_pause_tc3_phy; + apc->phy_stats.rx_pause_tc4_phy = resp.rx_pause_tc4_phy; + apc->phy_stats.tx_pause_tc4_phy = resp.tx_pause_tc4_phy; + apc->phy_stats.rx_pause_tc5_phy = resp.rx_pause_tc5_phy; + apc->phy_stats.tx_pause_tc5_phy = resp.tx_pause_tc5_phy; + apc->phy_stats.rx_pause_tc6_phy = resp.rx_pause_tc6_phy; + apc->phy_stats.tx_pause_tc6_phy = resp.tx_pause_tc6_phy; + apc->phy_stats.rx_pause_tc7_phy = resp.rx_pause_tc7_phy; + apc->phy_stats.tx_pause_tc7_phy = resp.tx_pause_tc7_phy; } static int mana_init_port(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); + struct gdma_dev *gd = apc->ac->gdma_dev; u32 max_txq, max_rxq, max_queues; int port_idx = apc->port_idx; - u32 num_indirect_entries; + struct gdma_context *gc; + char vport[32]; int err; err = mana_init_port_context(apc); if (err) return err; + gc = gd->gdma_context; + err = mana_query_vport_cfg(apc, port_idx, &max_txq, &max_rxq, - &num_indirect_entries); + &apc->indir_table_sz); if (err) { netdev_err(ndev, "Failed to query info for vPort %d\n", port_idx); @@ -2363,12 +3052,12 @@ static int mana_init_port(struct net_device *ndev) apc->num_queues = apc->max_queues; eth_hw_addr_set(ndev, apc->mac_addr); - + sprintf(vport, "vport%d", port_idx); + apc->mana_port_debugfs = debugfs_create_dir(vport, gc->mana_pci_debugfs); return 0; reset_apc: - kfree(apc->rxqs); - apc->rxqs = NULL; + mana_cleanup_port_context(apc); return err; } @@ -2379,12 +3068,18 @@ int mana_alloc_queues(struct net_device *ndev) int err; err = mana_create_vport(apc, ndev); - if (err) + if (err) { + netdev_err(ndev, "Failed to create vPort %u : %d\n", apc->port_idx, err); return err; + } err = netif_set_real_num_tx_queues(ndev, apc->num_queues); - if (err) + if (err) { + netdev_err(ndev, + "netif_set_real_num_tx_queues () failed for ndev with num_queues %u : %d\n", + apc->num_queues, err); goto destroy_vport; + } err = mana_add_rx_queues(apc, ndev); if (err) @@ -2393,16 +3088,22 @@ int mana_alloc_queues(struct net_device *ndev) apc->rss_state = apc->num_queues > 1 ? TRI_STATE_TRUE : TRI_STATE_FALSE; err = netif_set_real_num_rx_queues(ndev, apc->num_queues); - if (err) + if (err) { + netdev_err(ndev, + "netif_set_real_num_rx_queues () failed for ndev with num_queues %u : %d\n", + apc->num_queues, err); goto destroy_vport; + } mana_rss_table_init(apc); err = mana_config_rss(apc, TRI_STATE_TRUE, true, true); - if (err) + if (err) { + netdev_err(ndev, "Failed to configure RSS table: %d\n", err); goto destroy_vport; + } - if (gd->gdma_context->is_pf) { + if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode) { err = mana_pf_register_filter(apc); if (err) goto destroy_vport; @@ -2441,9 +3142,6 @@ int mana_attach(struct net_device *ndev) /* Ensure port state updated before txq state */ smp_wmb(); - if (apc->port_is_up) - netif_carrier_on(ndev); - netif_device_attach(ndev); return 0; @@ -2464,7 +3162,7 @@ static int mana_dealloc_queues(struct net_device *ndev) mana_chn_setxdp(apc, NULL); - if (gd->gdma_context->is_pf) + if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode) mana_pf_deregister_filter(apc); /* No packet can be transmitted now since apc->port_is_up is false. @@ -2513,11 +3211,10 @@ static int mana_dealloc_queues(struct net_device *ndev) apc->rss_state = TRI_STATE_FALSE; err = mana_config_rss(apc, TRI_STATE_FALSE, false, false); - if (err) { + if (err && mana_en_need_log(apc, err)) netdev_err(ndev, "Failed to disable vPort: %d\n", err); - return err; - } + /* Even in err case, still need to cleanup the vPort */ mana_destroy_vport(apc); return 0; @@ -2537,12 +3234,13 @@ int mana_detach(struct net_device *ndev, bool from_close) smp_wmb(); netif_tx_disable(ndev); - netif_carrier_off(ndev); if (apc->port_st_save) { err = mana_dealloc_queues(ndev); - if (err) + if (err) { + netdev_err(ndev, "%s failed to deallocate queues: %d\n", __func__, err); return err; + } } if (!from_close) { @@ -2573,6 +3271,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, apc->ndev = ndev; apc->max_queues = gc->max_num_queues; apc->num_queues = gc->max_num_queues; + apc->tx_queue_size = DEF_TX_BUFFERS_PER_QUEUE; + apc->rx_queue_size = DEF_RX_BUFFERS_PER_QUEUE; apc->port_handle = INVALID_MANA_HANDLE; apc->pf_filter_handle = INVALID_MANA_HANDLE; apc->port_idx = port_idx; @@ -2589,6 +3289,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, ndev->dev_port = port_idx; SET_NETDEV_DEV(ndev, gc->dev); + netif_set_tso_max_size(ndev, GSO_MAX_SIZE); + netif_carrier_off(ndev); netdev_rss_key_fill(apc->hashkey, MANA_HASH_KEY_SIZE); @@ -2597,6 +3299,10 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, if (err) goto free_net; + err = mana_rss_table_alloc(apc); + if (err) + goto reset_apc; + netdev_lockdep_set_classes(ndev); ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; @@ -2606,20 +3312,26 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, ndev->features = ndev->hw_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; ndev->vlan_features = ndev->features; - ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_NDO_XMIT; + xdp_set_features_flag(ndev, NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT); err = register_netdev(ndev); if (err) { netdev_err(ndev, "Unable to register netdev.\n"); - goto reset_apc; + goto free_indir; } + netif_carrier_on(ndev); + + debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs, &apc->speed); + return 0; +free_indir: + mana_cleanup_indir_table(apc); reset_apc: - kfree(apc->rxqs); - apc->rxqs = NULL; + mana_cleanup_port_context(apc); free_net: *ndev_storage = NULL; netdev_err(ndev, "Failed to probe vPort %d: %d\n", port_idx, err); @@ -2646,7 +3358,7 @@ static void remove_adev(struct gdma_dev *gd) gd->adev = NULL; } -static int add_adev(struct gdma_dev *gd) +static int add_adev(struct gdma_dev *gd, const char *name) { struct auxiliary_device *adev; struct mana_adev *madev; @@ -2662,7 +3374,7 @@ static int add_adev(struct gdma_dev *gd) goto idx_fail; adev->id = ret; - adev->name = "rdma"; + adev->name = name; adev->dev.parent = gd->gdma_context->dev; adev->dev.release = adev_release; madev->mdev = gd; @@ -2671,11 +3383,15 @@ static int add_adev(struct gdma_dev *gd) if (ret) goto init_fail; + /* madev is owned by the auxiliary device */ + madev = NULL; ret = auxiliary_device_add(adev); if (ret) goto add_fail; gd->adev = adev; + dev_dbg(gd->gdma_context->dev, + "Auxiliary device added successfully\n"); return 0; add_fail: @@ -2690,11 +3406,94 @@ idx_fail: return ret; } +static void mana_rdma_service_handle(struct work_struct *work) +{ + struct mana_service_work *serv_work = + container_of(work, struct mana_service_work, work); + struct gdma_dev *gd = serv_work->gdma_dev; + struct device *dev = gd->gdma_context->dev; + int ret; + + if (READ_ONCE(gd->rdma_teardown)) + goto out; + + switch (serv_work->event) { + case GDMA_SERVICE_TYPE_RDMA_SUSPEND: + if (!gd->adev || gd->is_suspended) + break; + + remove_adev(gd); + gd->is_suspended = true; + break; + + case GDMA_SERVICE_TYPE_RDMA_RESUME: + if (!gd->is_suspended) + break; + + ret = add_adev(gd, "rdma"); + if (ret) + dev_err(dev, "Failed to add adev on resume: %d\n", ret); + else + gd->is_suspended = false; + break; + + default: + dev_warn(dev, "unknown adev service event %u\n", + serv_work->event); + break; + } + +out: + kfree(serv_work); +} + +int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type event) +{ + struct gdma_dev *gd = &gc->mana_ib; + struct mana_service_work *serv_work; + + if (gd->dev_id.type != GDMA_DEVICE_MANA_IB) { + /* RDMA device is not detected on pci */ + return 0; + } + + serv_work = kzalloc(sizeof(*serv_work), GFP_ATOMIC); + if (!serv_work) + return -ENOMEM; + + serv_work->event = event; + serv_work->gdma_dev = gd; + + INIT_WORK(&serv_work->work, mana_rdma_service_handle); + queue_work(gc->service_wq, &serv_work->work); + + return 0; +} + +#define MANA_GF_STATS_PERIOD (2 * HZ) + +static void mana_gf_stats_work_handler(struct work_struct *work) +{ + struct mana_context *ac = + container_of(to_delayed_work(work), struct mana_context, gf_stats_work); + int err; + + err = mana_query_gf_stats(ac); + if (err == -ETIMEDOUT) { + /* HWC timeout detected - reset stats and stop rescheduling */ + ac->hwc_timeout_occurred = true; + memset(&ac->hc_stats, 0, sizeof(ac->hc_stats)); + return; + } + schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD); +} + int mana_probe(struct gdma_dev *gd, bool resuming) { struct gdma_context *gc = gd->gdma_context; struct mana_context *ac = gd->driver_data; struct device *dev = gc->dev; + u8 bm_hostmode = 0; u16 num_ports = 0; int err; int i; @@ -2717,16 +3516,22 @@ int mana_probe(struct gdma_dev *gd, bool resuming) } err = mana_create_eq(ac); - if (err) + if (err) { + dev_err(dev, "Failed to create EQs: %d\n", err); goto out; + } err = mana_query_device_cfg(ac, MANA_MAJOR_VERSION, MANA_MINOR_VERSION, - MANA_MICRO_VERSION, &num_ports); + MANA_MICRO_VERSION, &num_ports, &bm_hostmode); if (err) goto out; + ac->bm_hostmode = bm_hostmode; + if (!resuming) { ac->num_ports = num_ports; + + INIT_WORK(&ac->link_change_work, mana_link_state_handle); } else { if (ac->num_ports != num_ports) { dev_err(dev, "The number of vPorts changed: %d->%d\n", @@ -2734,6 +3539,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming) err = -EPROTO; goto out; } + + enable_work(&ac->link_change_work); } if (ac->num_ports == 0) @@ -2745,23 +3552,47 @@ int mana_probe(struct gdma_dev *gd, bool resuming) if (!resuming) { for (i = 0; i < ac->num_ports; i++) { err = mana_probe_port(ac, i, &ac->ports[i]); - if (err) + /* we log the port for which the probe failed and stop + * probes for subsequent ports. + * Note that we keep running ports, for which the probes + * were successful, unless add_adev fails too + */ + if (err) { + dev_err(dev, "Probe Failed for port %d\n", i); break; + } } } else { for (i = 0; i < ac->num_ports; i++) { rtnl_lock(); err = mana_attach(ac->ports[i]); rtnl_unlock(); - if (err) + /* we log the port for which the attach failed and stop + * attach for subsequent ports + * Note that we keep running ports, for which the attach + * were successful, unless add_adev fails too + */ + if (err) { + dev_err(dev, "Attach Failed for port %d\n", i); break; + } } } - err = add_adev(gd); + err = add_adev(gd, "eth"); + + INIT_DELAYED_WORK(&ac->gf_stats_work, mana_gf_stats_work_handler); + schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD); + out: - if (err) + if (err) { mana_remove(gd, false); + } else { + dev_dbg(dev, "gd=%p, id=%u, num_ports=%d, type=%u, instance=%u\n", + gd, gd->dev_id.as_uint32, ac->num_ports, + gd->dev_id.type, gd->dev_id.instance); + dev_dbg(dev, "%s succeeded\n", __func__); + } return err; } @@ -2770,17 +3601,22 @@ void mana_remove(struct gdma_dev *gd, bool suspending) { struct gdma_context *gc = gd->gdma_context; struct mana_context *ac = gd->driver_data; + struct mana_port_context *apc; struct device *dev = gc->dev; struct net_device *ndev; int err; int i; + disable_work_sync(&ac->link_change_work); + cancel_delayed_work_sync(&ac->gf_stats_work); + /* adev currently doesn't support suspending, always remove it */ if (gd->adev) remove_adev(gd); for (i = 0; i < ac->num_ports; i++) { ndev = ac->ports[i]; + apc = netdev_priv(ndev); if (!ndev) { if (i == 0) dev_err(dev, "No net device to remove\n"); @@ -2804,6 +3640,7 @@ void mana_remove(struct gdma_dev *gd, bool suspending) } unregister_netdevice(ndev); + mana_cleanup_indir_table(apc); rtnl_unlock(); @@ -2820,4 +3657,68 @@ out: gd->driver_data = NULL; gd->gdma_context = NULL; kfree(ac); + dev_dbg(dev, "%s succeeded\n", __func__); +} + +int mana_rdma_probe(struct gdma_dev *gd) +{ + int err = 0; + + if (gd->dev_id.type != GDMA_DEVICE_MANA_IB) { + /* RDMA device is not detected on pci */ + return err; + } + + err = mana_gd_register_device(gd); + if (err) + return err; + + err = add_adev(gd, "rdma"); + if (err) + mana_gd_deregister_device(gd); + + return err; +} + +void mana_rdma_remove(struct gdma_dev *gd) +{ + struct gdma_context *gc = gd->gdma_context; + + if (gd->dev_id.type != GDMA_DEVICE_MANA_IB) { + /* RDMA device is not detected on pci */ + return; + } + + WRITE_ONCE(gd->rdma_teardown, true); + flush_workqueue(gc->service_wq); + + if (gd->adev) + remove_adev(gd); + + mana_gd_deregister_device(gd); +} + +struct net_device *mana_get_primary_netdev(struct mana_context *ac, + u32 port_index, + netdevice_tracker *tracker) +{ + struct net_device *ndev; + + if (port_index >= ac->num_ports) + return NULL; + + rcu_read_lock(); + + /* If mana is used in netvsc, the upper netdevice should be returned. */ + ndev = netdev_master_upper_dev_get_rcu(ac->ports[port_index]); + + /* If there is no upper device, use the parent Ethernet device */ + if (!ndev) + ndev = ac->ports[port_index]; + + netdev_hold(ndev, tracker, GFP_ATOMIC); + rcu_read_unlock(); + + return ndev; } +EXPORT_SYMBOL_NS(mana_get_primary_netdev, "NET_MANA"); |