diff options
Diffstat (limited to 'drivers/net/ethernet/intel/igc/igc_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/igc/igc_main.c | 1055 |
1 files changed, 771 insertions, 284 deletions
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index bdeb36790d77..7aafa60ba0c8 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -12,6 +12,7 @@ #include <linux/bpf_trace.h> #include <net/xdp_sock_drv.h> #include <linux/pci.h> +#include <linux/mdio.h> #include <net/ipv6.h> @@ -31,7 +32,6 @@ static int debug = -1; -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); MODULE_LICENSE("GPL v2"); module_param(debug, int, 0); @@ -683,9 +683,9 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter, wr32(IGC_SRRCTL(reg_idx), srrctl); - rxdctl |= IGC_RX_PTHRESH; - rxdctl |= IGC_RX_HTHRESH << 8; - rxdctl |= IGC_RX_WTHRESH << 16; + rxdctl |= IGC_RXDCTL_PTHRESH; + rxdctl |= IGC_RXDCTL_HTHRESH << 8; + rxdctl |= IGC_RXDCTL_WTHRESH << 16; /* initialize rx_buffer_info */ memset(ring->rx_buffer_info, 0, @@ -749,11 +749,9 @@ static void igc_configure_tx_ring(struct igc_adapter *adapter, wr32(IGC_TDH(reg_idx), 0); writel(0, ring->tail); - txdctl |= IGC_TX_PTHRESH; - txdctl |= IGC_TX_HTHRESH << 8; - txdctl |= IGC_TX_WTHRESH << 16; + txdctl |= IGC_TXDCTL_PTHRESH(8) | IGC_TXDCTL_HTHRESH(1) | + IGC_TXDCTL_WTHRESH(16) | IGC_TXDCTL_QUEUE_ENABLE; - txdctl |= IGC_TXDCTL_QUEUE_ENABLE; wr32(IGC_TXDCTL(reg_idx), txdctl); } @@ -1092,10 +1090,12 @@ static int igc_init_empty_frame(struct igc_ring *ring, dma = dma_map_single(ring->dev, skb->data, size, DMA_TO_DEVICE); if (dma_mapping_error(ring->dev, dma)) { - netdev_err_once(ring->netdev, "Failed to map DMA for TX\n"); + net_err_ratelimited("%s: DMA mapping error for empty frame\n", + netdev_name(ring->netdev)); return -ENOMEM; } + buffer->type = IGC_TX_BUFFER_TYPE_SKB; buffer->skb = skb; buffer->protocol = 0; buffer->bytecount = skb->len; @@ -1107,20 +1107,12 @@ static int igc_init_empty_frame(struct igc_ring *ring, return 0; } -static int igc_init_tx_empty_descriptor(struct igc_ring *ring, - struct sk_buff *skb, - struct igc_tx_buffer *first) +static void igc_init_tx_empty_descriptor(struct igc_ring *ring, + struct sk_buff *skb, + struct igc_tx_buffer *first) { union igc_adv_tx_desc *desc; u32 cmd_type, olinfo_status; - int err; - - if (!igc_desc_unused(ring)) - return -EBUSY; - - err = igc_init_empty_frame(ring, first, skb); - if (err) - return err; cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | @@ -1139,8 +1131,6 @@ static int igc_init_tx_empty_descriptor(struct igc_ring *ring, ring->next_to_use++; if (ring->next_to_use == ring->count) ring->next_to_use = 0; - - return 0; } #define IGC_EMPTY_FRAME_SIZE 60 @@ -1271,10 +1261,21 @@ static u32 igc_tx_cmd_type(struct sk_buff *skb, u32 tx_flags) cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSO, (IGC_ADVTXD_DCMD_TSE)); - /* set timestamp bit if present */ + /* set timestamp bit if present, will select the register set + * based on the _TSTAMP(_X) bit. + */ cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP, (IGC_ADVTXD_MAC_TSTAMP)); + cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP_1, + (IGC_ADVTXD_TSTAMP_REG_1)); + + cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP_2, + (IGC_ADVTXD_TSTAMP_REG_2)); + + cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP_3, + (IGC_ADVTXD_TSTAMP_REG_3)); + /* insert frame checksum */ cmd_type ^= IGC_SET_FLAG(skb->no_fcs, 1, IGC_ADVTXD_DCMD_IFCS); @@ -1288,14 +1289,16 @@ static void igc_tx_olinfo_status(struct igc_ring *tx_ring, u32 olinfo_status = paylen << IGC_ADVTXD_PAYLEN_SHIFT; /* insert L4 checksum */ - olinfo_status |= (tx_flags & IGC_TX_FLAGS_CSUM) * - ((IGC_TXD_POPTS_TXSM << 8) / - IGC_TX_FLAGS_CSUM); + olinfo_status |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_CSUM, + (IGC_TXD_POPTS_TXSM << 8)); /* insert IPv4 checksum */ - olinfo_status |= (tx_flags & IGC_TX_FLAGS_IPV4) * - (((IGC_TXD_POPTS_IXSM << 8)) / - IGC_TX_FLAGS_IPV4); + olinfo_status |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_IPV4, + (IGC_TXD_POPTS_IXSM << 8)); + + /* Use the second timer (free running, in general) for the timestamp */ + olinfo_status |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP_TIMER_1, + IGC_TXD_PTP2_TIMER_1); tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); } @@ -1533,6 +1536,60 @@ static int igc_tso(struct igc_ring *tx_ring, return 1; } +static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *skb, u32 *flags) +{ + int i; + + for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) { + struct igc_tx_timestamp_request *tstamp = &adapter->tx_tstamp[i]; + + if (tstamp->skb) + continue; + + tstamp->skb = skb_get(skb); + tstamp->start = jiffies; + *flags = tstamp->flags; + + return true; + } + + return false; +} + +static int igc_insert_empty_frame(struct igc_ring *tx_ring) +{ + struct igc_tx_buffer *empty_info; + struct sk_buff *empty_skb; + void *data; + int ret; + + empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + empty_skb = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); + if (unlikely(!empty_skb)) { + net_err_ratelimited("%s: skb alloc error for empty frame\n", + netdev_name(tx_ring->netdev)); + return -ENOMEM; + } + + data = skb_put(empty_skb, IGC_EMPTY_FRAME_SIZE); + memset(data, 0, IGC_EMPTY_FRAME_SIZE); + + /* Prepare DMA mapping and Tx buffer information */ + ret = igc_init_empty_frame(tx_ring, empty_info, empty_skb); + if (unlikely(ret)) { + dev_kfree_skb_any(empty_skb); + return ret; + } + + /* Prepare advanced context descriptor for empty packet */ + igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); + + /* Prepare advanced data descriptor for empty packet */ + igc_init_tx_empty_descriptor(tx_ring, empty_skb, empty_info); + + return 0; +} + static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, struct igc_ring *tx_ring) { @@ -1552,6 +1609,7 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, * + 1 desc for skb_headlen/IGC_MAX_DATA_PER_TXD, * + 2 desc gap to keep tail from touching head, * + 1 desc for context descriptor, + * + 2 desc for inserting an empty packet for launch time, * otherwise try next time */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) @@ -1571,24 +1629,16 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, launch_time = igc_tx_launchtime(tx_ring, txtime, &first_flag, &insert_empty); if (insert_empty) { - struct igc_tx_buffer *empty_info; - struct sk_buff *empty; - void *data; - - empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; - empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); - if (!empty) - goto done; - - data = skb_put(empty, IGC_EMPTY_FRAME_SIZE); - memset(data, 0, IGC_EMPTY_FRAME_SIZE); - - igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); - - if (igc_init_tx_empty_descriptor(tx_ring, - empty, - empty_info) < 0) - dev_kfree_skb_any(empty); + /* Reset the launch time if the required empty frame fails to + * be inserted. However, this packet is not dropped, so it + * "dirties" the current Qbv cycle. This ensures that the + * upcoming packet, which is scheduled in the next Qbv cycle, + * does not require an empty frame. This way, the launch time + * continues to function correctly despite the current failure + * to insert the empty frame. + */ + if (igc_insert_empty_frame(tx_ring)) + launch_time = 0; } done: @@ -1609,19 +1659,16 @@ done: if (unlikely(test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags) && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { - /* FIXME: add support for retrieving timestamps from - * the other timer registers before skipping the - * timestamping request. - */ unsigned long flags; + u32 tstamp_flags; spin_lock_irqsave(&adapter->ptp_tx_lock, flags); - if (!adapter->ptp_tx_skb) { + if (igc_request_tx_tstamp(adapter, skb, &tstamp_flags)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - tx_flags |= IGC_TX_FLAGS_TSTAMP; - - adapter->ptp_tx_skb = skb_get(skb); - adapter->ptp_tx_start = jiffies; + tx_flags |= IGC_TX_FLAGS_TSTAMP | tstamp_flags; + if (skb->sk && + READ_ONCE(skb->sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC) + tx_flags |= IGC_TX_FLAGS_TSTAMP_TIMER_1; } else { adapter->tx_hwtstamp_skipped++; } @@ -1638,6 +1685,15 @@ done: first->tx_flags = tx_flags; first->protocol = protocol; + /* For preemptible queue, manually pad the skb so that HW includes + * padding bytes in mCRC calculation + */ + if (tx_ring->preemptible && skb->len < ETH_ZLEN) { + if (skb_padto(skb, ETH_ZLEN)) + goto out_drop; + skb_put(skb, ETH_ZLEN - skb->len); + } + tso = igc_tso(tx_ring, first, launch_time, first_flag, &hdr_len); if (tso < 0) goto out_drop; @@ -1934,9 +1990,9 @@ static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring, static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring, struct igc_rx_buffer *rx_buffer, - struct xdp_buff *xdp, - ktime_t timestamp) + struct igc_xdp_buff *ctx) { + struct xdp_buff *xdp = &ctx->xdp; unsigned int metasize = xdp->data - xdp->data_meta; unsigned int size = xdp->data_end - xdp->data; unsigned int truesize = igc_get_rx_frame_truesize(rx_ring, size); @@ -1953,8 +2009,10 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring, if (unlikely(!skb)) return NULL; - if (timestamp) - skb_hwtstamps(skb)->hwtstamp = timestamp; + if (ctx->rx_ts) { + skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP_NETDEV; + skb_hwtstamps(skb)->netdev_data = ctx->rx_ts; + } /* Determine available headroom for copy */ headlen = size; @@ -2092,10 +2150,6 @@ static bool igc_cleanup_headers(struct igc_ring *rx_ring, union igc_adv_rx_desc *rx_desc, struct sk_buff *skb) { - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - if (unlikely(igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_RXE))) { struct net_device *netdev = rx_ring->netdev; @@ -2160,6 +2214,7 @@ static bool igc_alloc_mapped_page(struct igc_ring *rx_ring, page = dev_alloc_pages(igc_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_failed++; + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); return false; } @@ -2176,6 +2231,7 @@ static bool igc_alloc_mapped_page(struct igc_ring *rx_ring, __free_page(page); rx_ring->rx_stats.alloc_failed++; + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); return false; } @@ -2415,8 +2471,7 @@ unmap: return -ENOMEM; } -static struct igc_ring *igc_xdp_get_tx_ring(struct igc_adapter *adapter, - int cpu) +struct igc_ring *igc_get_tx_ring(struct igc_adapter *adapter, int cpu) { int index = cpu; @@ -2440,7 +2495,7 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp) if (unlikely(!xdpf)) return -EFAULT; - ring = igc_xdp_get_tx_ring(adapter, cpu); + ring = igc_get_tx_ring(adapter, cpu); nq = txring_txq(ring); __netif_tx_lock(nq, cpu); @@ -2482,8 +2537,7 @@ out_failure: } } -static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, - struct xdp_buff *xdp) +static int igc_xdp_run_prog(struct igc_adapter *adapter, struct xdp_buff *xdp) { struct bpf_prog *prog; int res; @@ -2497,11 +2551,11 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, res = __igc_xdp_run_prog(adapter, prog, xdp); out: - return ERR_PTR(-res); + return res; } /* This function assumes __netif_tx_lock is held by the caller. */ -static void igc_flush_tx_descriptors(struct igc_ring *ring) +void igc_flush_tx_descriptors(struct igc_ring *ring) { /* Once tail pointer is updated, hardware can fetch the descriptors * any time so we issue a write membar here to ensure all memory @@ -2518,7 +2572,7 @@ static void igc_finalize_xdp(struct igc_adapter *adapter, int status) struct igc_ring *ring; if (status & IGC_XDP_TX) { - ring = igc_xdp_get_tx_ring(adapter, cpu); + ring = igc_get_tx_ring(adapter, cpu); nq = txring_txq(ring); __netif_tx_lock(nq, cpu); @@ -2552,13 +2606,13 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = igc_desc_unused(rx_ring); int xdp_status = 0, rx_buffer_pgcnt; + int xdp_res = 0; while (likely(total_packets < budget)) { - union igc_adv_rx_desc *rx_desc; + struct igc_xdp_buff ctx = { .rx_ts = NULL }; struct igc_rx_buffer *rx_buffer; + union igc_adv_rx_desc *rx_desc; unsigned int size, truesize; - struct igc_xdp_buff ctx; - ktime_t timestamp = 0; int pkt_offset = 0; void *pktbuf; @@ -2585,13 +2639,19 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) pktbuf = page_address(rx_buffer->page) + rx_buffer->page_offset; if (igc_test_staterr(rx_desc, IGC_RXDADV_STAT_TSIP)) { - timestamp = igc_ptp_rx_pktstamp(q_vector->adapter, - pktbuf); - ctx.rx_ts = timestamp; + ctx.rx_ts = pktbuf; pkt_offset = IGC_TS_HDR_LEN; size -= IGC_TS_HDR_LEN; } + if (igc_fpe_is_pmac_enabled(adapter) && + igc_fpe_handle_mpacket(adapter, rx_desc, size, pktbuf)) { + /* Advance the ring next-to-clean */ + igc_is_non_eop(rx_ring, rx_desc); + cleaned_count++; + continue; + } + if (!skb) { xdp_init_buff(&ctx.xdp, truesize, &rx_ring->xdp_rxq); xdp_prepare_buff(&ctx.xdp, pktbuf - igc_rx_offset(rx_ring), @@ -2600,12 +2660,10 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) xdp_buff_clear_frags_flag(&ctx.xdp); ctx.rx_desc = rx_desc; - skb = igc_xdp_run_prog(adapter, &ctx.xdp); + xdp_res = igc_xdp_run_prog(adapter, &ctx.xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { switch (xdp_res) { case IGC_XDP_CONSUMED: rx_buffer->pagecnt_bias++; @@ -2624,13 +2682,13 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) else if (ring_uses_build_skb(rx_ring)) skb = igc_build_skb(rx_ring, rx_buffer, &ctx.xdp); else - skb = igc_construct_skb(rx_ring, rx_buffer, &ctx.xdp, - timestamp); + skb = igc_construct_skb(rx_ring, rx_buffer, &ctx); /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_failed++; rx_buffer->pagecnt_bias++; + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); break; } @@ -2642,7 +2700,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) continue; /* verify the packet layout is correct */ - if (igc_cleanup_headers(rx_ring, rx_desc, skb)) { + if (xdp_res || igc_cleanup_headers(rx_ring, rx_desc, skb)) { skb = NULL; continue; } @@ -2677,16 +2735,16 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) } static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, - struct xdp_buff *xdp) + struct igc_xdp_buff *ctx) { + struct xdp_buff *xdp = &ctx->xdp; unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; net_prefetch(xdp->data_meta); - skb = __napi_alloc_skb(&ring->q_vector->napi, totalsize, - GFP_ATOMIC | __GFP_NOWARN); + skb = napi_alloc_skb(&ring->q_vector->napi, totalsize); if (unlikely(!skb)) return NULL; @@ -2698,26 +2756,28 @@ static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, __skb_pull(skb, metasize); } + if (ctx->rx_ts) { + skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP_NETDEV; + skb_hwtstamps(skb)->netdev_data = ctx->rx_ts; + } + return skb; } static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector, union igc_adv_rx_desc *desc, - struct xdp_buff *xdp, - ktime_t timestamp) + struct igc_xdp_buff *ctx) { struct igc_ring *ring = q_vector->rx.ring; struct sk_buff *skb; - skb = igc_construct_skb_zc(ring, xdp); + skb = igc_construct_skb_zc(ring, ctx); if (!skb) { ring->rx_stats.alloc_failed++; + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &ring->flags); return; } - if (timestamp) - skb_hwtstamps(skb)->hwtstamp = timestamp; - if (igc_cleanup_headers(ring, desc, skb)) return; @@ -2753,7 +2813,6 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) union igc_adv_rx_desc *desc; struct igc_rx_buffer *bi; struct igc_xdp_buff *ctx; - ktime_t timestamp = 0; unsigned int size; int res; @@ -2774,9 +2833,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) ctx->rx_desc = desc; if (igc_test_staterr(desc, IGC_RXDADV_STAT_TSIP)) { - timestamp = igc_ptp_rx_pktstamp(q_vector->adapter, - bi->xdp->data); - ctx->rx_ts = timestamp; + ctx->rx_ts = bi->xdp->data; bi->xdp->data += IGC_TS_HDR_LEN; @@ -2785,15 +2842,17 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) */ bi->xdp->data_meta += IGC_TS_HDR_LEN; size -= IGC_TS_HDR_LEN; + } else { + ctx->rx_ts = NULL; } bi->xdp->data_end = bi->xdp->data + size; - xsk_buff_dma_sync_for_cpu(bi->xdp, ring->xsk_pool); + xsk_buff_dma_sync_for_cpu(bi->xdp); res = __igc_xdp_run_prog(adapter, prog, bi->xdp); switch (res) { case IGC_XDP_PASS: - igc_dispatch_skb_zc(q_vector, desc, bi->xdp, timestamp); + igc_dispatch_skb_zc(q_vector, desc, ctx); fallthrough; case IGC_XDP_CONSUMED: xsk_buff_free(bi->xdp); @@ -2849,6 +2908,128 @@ static void igc_update_tx_stats(struct igc_q_vector *q_vector, q_vector->tx.total_packets += packets; } +static void igc_xsk_request_timestamp(void *_priv) +{ + struct igc_metadata_request *meta_req = _priv; + struct igc_ring *tx_ring = meta_req->tx_ring; + struct igc_tx_timestamp_request *tstamp; + u32 tx_flags = IGC_TX_FLAGS_TSTAMP; + struct igc_adapter *adapter; + unsigned long lock_flags; + bool found = false; + int i; + + if (test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags)) { + adapter = netdev_priv(tx_ring->netdev); + + spin_lock_irqsave(&adapter->ptp_tx_lock, lock_flags); + + /* Search for available tstamp regs */ + for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) { + tstamp = &adapter->tx_tstamp[i]; + + /* tstamp->skb and tstamp->xsk_tx_buffer are in union. + * When tstamp->skb is equal to NULL, + * tstamp->xsk_tx_buffer is equal to NULL as well. + * This condition means that the particular tstamp reg + * is not occupied by other packet. + */ + if (!tstamp->skb) { + found = true; + break; + } + } + + /* Return if no available tstamp regs */ + if (!found) { + adapter->tx_hwtstamp_skipped++; + spin_unlock_irqrestore(&adapter->ptp_tx_lock, + lock_flags); + return; + } + + tstamp->start = jiffies; + tstamp->xsk_queue_index = tx_ring->queue_index; + tstamp->xsk_tx_buffer = meta_req->tx_buffer; + tstamp->buffer_type = IGC_TX_BUFFER_TYPE_XSK; + + /* Hold the transmit completion until timestamp is ready */ + meta_req->tx_buffer->xsk_pending_ts = true; + + /* Keep the pointer to tx_timestamp, which is located in XDP + * metadata area. It is the location to store the value of + * tx hardware timestamp. + */ + xsk_tx_metadata_to_compl(meta_req->meta, &tstamp->xsk_meta); + + /* Set timestamp bit based on the _TSTAMP(_X) bit. */ + tx_flags |= tstamp->flags; + meta_req->cmd_type |= IGC_SET_FLAG(tx_flags, + IGC_TX_FLAGS_TSTAMP, + (IGC_ADVTXD_MAC_TSTAMP)); + meta_req->cmd_type |= IGC_SET_FLAG(tx_flags, + IGC_TX_FLAGS_TSTAMP_1, + (IGC_ADVTXD_TSTAMP_REG_1)); + meta_req->cmd_type |= IGC_SET_FLAG(tx_flags, + IGC_TX_FLAGS_TSTAMP_2, + (IGC_ADVTXD_TSTAMP_REG_2)); + meta_req->cmd_type |= IGC_SET_FLAG(tx_flags, + IGC_TX_FLAGS_TSTAMP_3, + (IGC_ADVTXD_TSTAMP_REG_3)); + + spin_unlock_irqrestore(&adapter->ptp_tx_lock, lock_flags); + } +} + +static u64 igc_xsk_fill_timestamp(void *_priv) +{ + return *(u64 *)_priv; +} + +static void igc_xsk_request_launch_time(u64 launch_time, void *_priv) +{ + struct igc_metadata_request *meta_req = _priv; + struct igc_ring *tx_ring = meta_req->tx_ring; + __le32 launch_time_offset; + bool insert_empty = false; + bool first_flag = false; + u16 used_desc = 0; + + if (!tx_ring->launchtime_enable) + return; + + launch_time_offset = igc_tx_launchtime(tx_ring, + ns_to_ktime(launch_time), + &first_flag, &insert_empty); + if (insert_empty) { + /* Disregard the launch time request if the required empty frame + * fails to be inserted. + */ + if (igc_insert_empty_frame(tx_ring)) + return; + + meta_req->tx_buffer = + &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + /* Inserting an empty packet requires two descriptors: + * one data descriptor and one context descriptor. + */ + used_desc += 2; + } + + /* Use one context descriptor to specify launch time and first flag. */ + igc_tx_ctxtdesc(tx_ring, launch_time_offset, first_flag, 0, 0, 0); + used_desc += 1; + + /* Update the number of used descriptors in this request */ + meta_req->used_desc += used_desc; +} + +const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops = { + .tmo_request_timestamp = igc_xsk_request_timestamp, + .tmo_fill_timestamp = igc_xsk_fill_timestamp, + .tmo_request_launch_time = igc_xsk_request_launch_time, +}; + static void igc_xdp_xmit_zc(struct igc_ring *ring) { struct xsk_buff_pool *pool = ring->xsk_pool; @@ -2869,25 +3050,51 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) ntu = ring->next_to_use; budget = igc_desc_unused(ring); - while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) { - u32 cmd_type, olinfo_status; + /* Packets with launch time require one data descriptor and one context + * descriptor. When the launch time falls into the next Qbv cycle, we + * may need to insert an empty packet, which requires two more + * descriptors. Therefore, to be safe, we always ensure we have at least + * 4 descriptors available. + */ + while (budget >= 4 && xsk_tx_peek_desc(pool, &xdp_desc)) { + struct igc_metadata_request meta_req; + struct xsk_tx_metadata *meta = NULL; struct igc_tx_buffer *bi; + u32 olinfo_status; dma_addr_t dma; - cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | - IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | - xdp_desc.len; + meta_req.cmd_type = IGC_ADVTXD_DTYP_DATA | + IGC_ADVTXD_DCMD_DEXT | + IGC_ADVTXD_DCMD_IFCS | + IGC_TXD_DCMD | xdp_desc.len; olinfo_status = xdp_desc.len << IGC_ADVTXD_PAYLEN_SHIFT; dma = xsk_buff_raw_get_dma(pool, xdp_desc.addr); + meta = xsk_buff_get_metadata(pool, xdp_desc.addr); xsk_buff_raw_dma_sync_for_device(pool, dma, xdp_desc.len); + bi = &ring->tx_buffer_info[ntu]; + + meta_req.tx_ring = ring; + meta_req.tx_buffer = bi; + meta_req.meta = meta; + meta_req.used_desc = 0; + xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops, + &meta_req); + + /* xsk_tx_metadata_request() may have updated next_to_use */ + ntu = ring->next_to_use; + + /* xsk_tx_metadata_request() may have updated Tx buffer info */ + bi = meta_req.tx_buffer; + + /* xsk_tx_metadata_request() may use a few descriptors */ + budget -= meta_req.used_desc; tx_desc = IGC_TX_DESC(ring, ntu); - tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.cmd_type_len = cpu_to_le32(meta_req.cmd_type); tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); tx_desc->read.buffer_addr = cpu_to_le64(dma); - bi = &ring->tx_buffer_info[ntu]; bi->type = IGC_TX_BUFFER_TYPE_XSK; bi->protocol = 0; bi->bytecount = xdp_desc.len; @@ -2900,9 +3107,11 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) ntu++; if (ntu == ring->count) ntu = 0; + + ring->next_to_use = ntu; + budget--; } - ring->next_to_use = ntu; if (tx_desc) { igc_flush_tx_descriptors(ring); xsk_tx_release(pool); @@ -2950,6 +3159,18 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) if (!(eop_desc->wb.status & cpu_to_le32(IGC_TXD_STAT_DD))) break; + if (igc_fpe_is_pmac_enabled(adapter) && + igc_fpe_transmitted_smd_v(tx_desc)) + ethtool_mmsv_event_handle(&adapter->fpe.mmsv, + ETHTOOL_MMSV_LD_SENT_VERIFY_MPACKET); + + /* Hold the completions while there's a pending tx hardware + * timestamp request from XDP Tx metadata. + */ + if (tx_buffer->type == IGC_TX_BUFFER_TYPE_XSK && + tx_buffer->xsk_pending_ts) + break; + /* clear next_to_watch to prevent false hangs */ tx_buffer->next_to_watch = NULL; @@ -3356,7 +3577,7 @@ static int igc_flex_filter_select(struct igc_adapter *adapter, u32 fhftsl; if (input->index >= MAX_FLEX_FILTER) { - dev_err(&adapter->pdev->dev, "Wrong Flex Filter index selected!\n"); + netdev_err(adapter->netdev, "Wrong Flex Filter index selected!\n"); return -EINVAL; } @@ -3391,7 +3612,6 @@ static int igc_flex_filter_select(struct igc_adapter *adapter, static int igc_write_flex_filter_ll(struct igc_adapter *adapter, struct igc_flex_filter *input) { - struct device *dev = &adapter->pdev->dev; struct igc_hw *hw = &adapter->hw; u8 *data = input->data; u8 *mask = input->mask; @@ -3405,7 +3625,7 @@ static int igc_write_flex_filter_ll(struct igc_adapter *adapter, * out early to avoid surprises later. */ if (input->length % 8 != 0) { - dev_err(dev, "The length of a flex filter has to be 8 byte aligned!\n"); + netdev_err(adapter->netdev, "The length of a flex filter has to be 8 byte aligned!\n"); return -EINVAL; } @@ -3423,8 +3643,8 @@ static int igc_write_flex_filter_ll(struct igc_adapter *adapter, /* Configure filter */ queuing = input->length & IGC_FHFT_LENGTH_MASK; - queuing |= (input->rx_queue << IGC_FHFT_QUEUE_SHIFT) & IGC_FHFT_QUEUE_MASK; - queuing |= (input->prio << IGC_FHFT_PRIO_SHIFT) & IGC_FHFT_PRIO_MASK; + queuing |= FIELD_PREP(IGC_FHFT_QUEUE_MASK, input->rx_queue); + queuing |= FIELD_PREP(IGC_FHFT_PRIO_MASK, input->prio); if (input->immediate_irq) queuing |= IGC_FHFT_IMM_INT; @@ -3475,8 +3695,8 @@ static int igc_write_flex_filter_ll(struct igc_adapter *adapter, } wr32(IGC_WUFC, wufc); - dev_dbg(&adapter->pdev->dev, "Added flex filter %u to HW.\n", - input->index); + netdev_dbg(adapter->netdev, "Added flex filter %u to HW.\n", + input->index); return 0; } @@ -3548,9 +3768,9 @@ static bool igc_flex_filter_in_use(struct igc_adapter *adapter) static int igc_add_flex_filter(struct igc_adapter *adapter, struct igc_nfc_rule *rule) { - struct igc_flex_filter flex = { }; struct igc_nfc_filter *filter = &rule->filter; unsigned int eth_offset, user_offset; + struct igc_flex_filter flex = { }; int ret, index; bool vlan; @@ -3586,10 +3806,12 @@ static int igc_add_flex_filter(struct igc_adapter *adapter, ETH_ALEN, NULL); /* Add VLAN etype */ - if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) - igc_flex_filter_add_field(&flex, &filter->vlan_etype, 12, - sizeof(filter->vlan_etype), - NULL); + if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) { + __be16 vlan_etype = cpu_to_be16(filter->vlan_etype); + + igc_flex_filter_add_field(&flex, &vlan_etype, 12, + sizeof(vlan_etype), NULL); + } /* Add VLAN TCI */ if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) @@ -3652,6 +3874,22 @@ static void igc_del_flex_filter(struct igc_adapter *adapter, wr32(IGC_WUFC, wufc); } +static void igc_set_default_queue_filter(struct igc_adapter *adapter, u32 queue) +{ + struct igc_hw *hw = &adapter->hw; + u32 mrqc = rd32(IGC_MRQC); + + mrqc &= ~IGC_MRQC_DEFAULT_QUEUE_MASK; + mrqc |= FIELD_PREP(IGC_MRQC_DEFAULT_QUEUE_MASK, queue); + wr32(IGC_MRQC, mrqc); +} + +static void igc_reset_default_queue_filter(struct igc_adapter *adapter) +{ + /* Reset the default queue to its default value which is Queue 0 */ + igc_set_default_queue_filter(adapter, 0); +} + static int igc_enable_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule) { @@ -3683,14 +3921,16 @@ static int igc_enable_nfc_rule(struct igc_adapter *adapter, } if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) { - int prio = (rule->filter.vlan_tci & VLAN_PRIO_MASK) >> - VLAN_PRIO_SHIFT; + int prio = FIELD_GET(VLAN_PRIO_MASK, rule->filter.vlan_tci); err = igc_add_vlan_prio_filter(adapter, prio, rule->action); if (err) return err; } + if (rule->filter.match_flags & IGC_FILTER_FLAG_DEFAULT_QUEUE) + igc_set_default_queue_filter(adapter, rule->action); + return 0; } @@ -3706,8 +3946,7 @@ static void igc_disable_nfc_rule(struct igc_adapter *adapter, igc_del_etype_filter(adapter, rule->filter.etype); if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) { - int prio = (rule->filter.vlan_tci & VLAN_PRIO_MASK) >> - VLAN_PRIO_SHIFT; + int prio = FIELD_GET(VLAN_PRIO_MASK, rule->filter.vlan_tci); igc_del_vlan_prio_filter(adapter, prio); } @@ -3719,6 +3958,9 @@ static void igc_disable_nfc_rule(struct igc_adapter *adapter, if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, rule->filter.dst_addr); + + if (rule->filter.match_flags & IGC_FILTER_FLAG_DEFAULT_QUEUE) + igc_reset_default_queue_filter(adapter); } /** @@ -3836,6 +4078,30 @@ static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr) } /** + * igc_enable_empty_addr_recv - Enable Rx of packets with all-zeroes MAC address + * @adapter: Pointer to the igc_adapter structure. + * + * Frame preemption verification requires that packets with the all-zeroes + * MAC address are allowed to be received by the driver. This function adds the + * all-zeroes destination address to the list of acceptable addresses. + * + * Return: 0 on success, negative value otherwise. + */ +int igc_enable_empty_addr_recv(struct igc_adapter *adapter) +{ + u8 empty[ETH_ALEN] = {}; + + return igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, empty, -1); +} + +void igc_disable_empty_addr_recv(struct igc_adapter *adapter) +{ + u8 empty[ETH_ALEN] = {}; + + igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, empty); +} + +/** * igc_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set * @netdev: network interface device structure * @@ -4801,6 +5067,7 @@ static int igc_sw_init(struct igc_adapter *adapter) adapter->nfc_rule_count = 0; spin_lock_init(&adapter->stats64_lock); + spin_lock_init(&adapter->qbv_tx_lock); /* Assume MSI-X interrupts, will be checked during IRQ allocation */ adapter->flags |= IGC_FLAG_HAS_MSIX; @@ -4820,6 +5087,22 @@ static int igc_sw_init(struct igc_adapter *adapter) return 0; } +static void igc_set_queue_napi(struct igc_adapter *adapter, int vector, + struct napi_struct *napi) +{ + struct igc_q_vector *q_vector = adapter->q_vector[vector]; + + if (q_vector->rx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->rx.ring->queue_index, + NETDEV_QUEUE_TYPE_RX, napi); + + if (q_vector->tx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->tx.ring->queue_index, + NETDEV_QUEUE_TYPE_TX, napi); +} + /** * igc_up - Open the interface and prepare it to handle traffic * @adapter: board private structure @@ -4827,6 +5110,7 @@ static int igc_sw_init(struct igc_adapter *adapter) void igc_up(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; + struct napi_struct *napi; int i = 0; /* hardware has been reset, we need to reload some things */ @@ -4834,8 +5118,11 @@ void igc_up(struct igc_adapter *adapter) clear_bit(__IGC_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&adapter->q_vector[i]->napi); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igc_set_queue_napi(adapter, i, napi); + } if (adapter->msix_entries) igc_configure_msix(adapter); @@ -5064,12 +5351,13 @@ void igc_down(struct igc_adapter *adapter) for (i = 0; i < adapter->num_q_vectors; i++) { if (adapter->q_vector[i]) { napi_synchronize(&adapter->q_vector[i]->napi); + igc_set_queue_napi(adapter, i, NULL); napi_disable(&adapter->q_vector[i]->napi); } } - del_timer_sync(&adapter->watchdog_timer); - del_timer_sync(&adapter->phy_info_timer); + timer_delete_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->phy_info_timer); /* record the stats before reset*/ spin_lock(&adapter->stats64_lock); @@ -5088,6 +5376,9 @@ void igc_down(struct igc_adapter *adapter) igc_disable_all_tx_rings_hw(adapter); igc_clean_all_tx_rings(adapter); igc_clean_all_rx_rings(adapter); + + if (adapter->fpe.mmsv.pmac_enabled) + ethtool_mmsv_stop(&adapter->fpe.mmsv); } void igc_reinit_locked(struct igc_adapter *adapter) @@ -5151,7 +5442,7 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu) igc_down(adapter); netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); - netdev->mtu = new_mtu; + WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) igc_up(adapter); @@ -5248,7 +5539,7 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev, unsigned int network_hdr_len, mac_hdr_len; /* Make certain the headers can be described by a context descriptor */ - mac_hdr_len = skb_network_header(skb) - skb->data; + mac_hdr_len = skb_network_offset(skb); if (unlikely(mac_hdr_len > IGC_MAX_MAC_HDR_LEN)) return features & ~(NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC | @@ -5274,25 +5565,22 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev, static void igc_tsync_interrupt(struct igc_adapter *adapter) { - u32 ack, tsauxc, sec, nsec, tsicr; struct igc_hw *hw = &adapter->hw; + u32 tsauxc, sec, nsec, tsicr; struct ptp_clock_event event; struct timespec64 ts; tsicr = rd32(IGC_TSICR); - ack = 0; if (tsicr & IGC_TSICR_SYS_WRAP) { event.type = PTP_CLOCK_PPS; if (adapter->ptp_caps.pps) ptp_clock_event(adapter->ptp_clock, &event); - ack |= IGC_TSICR_SYS_WRAP; } if (tsicr & IGC_TSICR_TXTS) { /* retrieve hardware timestamp */ igc_ptp_tx_tstamp_event(adapter); - ack |= IGC_TSICR_TXTS; } if (tsicr & IGC_TSICR_TT0) { @@ -5306,7 +5594,6 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) wr32(IGC_TSAUXC, tsauxc); adapter->perout[0].start = ts; spin_unlock(&adapter->tmreg_lock); - ack |= IGC_TSICR_TT0; } if (tsicr & IGC_TSICR_TT1) { @@ -5320,7 +5607,6 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) wr32(IGC_TSAUXC, tsauxc); adapter->perout[1].start = ts; spin_unlock(&adapter->tmreg_lock); - ack |= IGC_TSICR_TT1; } if (tsicr & IGC_TSICR_AUTT0) { @@ -5330,7 +5616,6 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) event.index = 0; event.timestamp = sec * NSEC_PER_SEC + nsec; ptp_clock_event(adapter->ptp_clock, &event); - ack |= IGC_TSICR_AUTT0; } if (tsicr & IGC_TSICR_AUTT1) { @@ -5340,11 +5625,7 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) event.index = 1; event.timestamp = sec * NSEC_PER_SEC + nsec; ptp_clock_event(adapter->ptp_clock, &event); - ack |= IGC_TSICR_AUTT1; } - - /* acknowledge the interrupts */ - wr32(IGC_TSICR, ack); } /** @@ -5458,6 +5739,9 @@ static int igc_request_msix(struct igc_adapter *adapter) q_vector); if (err) goto err_free; + + netif_napi_set_irq(&q_vector->napi, + adapter->msix_entries[vector].vector); } igc_configure_msix(adapter); @@ -5494,7 +5778,8 @@ static void igc_clear_interrupt_scheme(struct igc_adapter *adapter) */ static void igc_update_phy_info(struct timer_list *t) { - struct igc_adapter *adapter = from_timer(adapter, t, phy_info_timer); + struct igc_adapter *adapter = timer_container_of(adapter, t, + phy_info_timer); igc_get_phy_info(&adapter->hw); } @@ -5536,7 +5821,8 @@ bool igc_has_link(struct igc_adapter *adapter) */ static void igc_watchdog(struct timer_list *t) { - struct igc_adapter *adapter = from_timer(adapter, t, watchdog_timer); + struct igc_adapter *adapter = timer_container_of(adapter, t, + watchdog_timer); /* Do the rest outside of interrupt context */ schedule_work(&adapter->watchdog_task); } @@ -5619,6 +5905,10 @@ static void igc_watchdog_task(struct work_struct *work) */ igc_tsn_adjust_txtime_offset(adapter); + if (adapter->fpe.mmsv.pmac_enabled) + ethtool_mmsv_link_state_handle(&adapter->fpe.mmsv, + true); + if (adapter->link_speed != SPEED_1000) goto no_wait; @@ -5654,6 +5944,10 @@ no_wait: netdev_info(netdev, "NIC Link is Down\n"); netif_carrier_off(netdev); + if (adapter->fpe.mmsv.pmac_enabled) + ethtool_mmsv_link_state_handle(&adapter->fpe.mmsv, + false); + /* link state has changed, schedule phy info update */ if (!test_bit(__IGC_DOWN, &adapter->state)) mod_timer(&adapter->phy_info_timer, @@ -5693,11 +5987,29 @@ no_wait: if (adapter->flags & IGC_FLAG_HAS_MSIX) { u32 eics = 0; - for (i = 0; i < adapter->num_q_vectors; i++) - eics |= adapter->q_vector[i]->eims_value; - wr32(IGC_EICS, eics); + for (i = 0; i < adapter->num_q_vectors; i++) { + struct igc_q_vector *q_vector = adapter->q_vector[i]; + struct igc_ring *rx_ring; + + if (!q_vector->rx.ring) + continue; + + rx_ring = adapter->rx_ring[q_vector->rx.ring->queue_index]; + + if (test_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) { + eics |= q_vector->eims_value; + clear_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); + } + } + if (eics) + wr32(IGC_EICS, eics); } else { - wr32(IGC_ICS, IGC_ICS_RXDMT0); + struct igc_ring *rx_ring = adapter->rx_ring[0]; + + if (test_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) { + clear_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); + wr32(IGC_ICS, IGC_ICS_RXDMT0); + } } igc_ptp_tx_hang(adapter); @@ -5882,6 +6194,7 @@ static int __igc_open(struct net_device *netdev, bool resuming) struct igc_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = adapter->pdev; struct igc_hw *hw = &adapter->hw; + struct napi_struct *napi; int err = 0; int i = 0; @@ -5915,19 +6228,13 @@ static int __igc_open(struct net_device *netdev, bool resuming) if (err) goto err_req_irq; - /* Notify the stack of the actual queue counts. */ - err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues); - if (err) - goto err_set_queues; - - err = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues); - if (err) - goto err_set_queues; - clear_bit(__IGC_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&adapter->q_vector[i]->napi); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igc_set_queue_napi(adapter, i, napi); + } /* Clear any pending interrupts. */ rd32(IGC_ICR); @@ -5944,8 +6251,6 @@ static int __igc_open(struct net_device *netdev, bool resuming) return IGC_SUCCESS; -err_set_queues: - igc_free_irq(adapter); err_req_irq: igc_release_hw_control(adapter); igc_power_down_phy_copper_base(&adapter->hw); @@ -5962,6 +6267,17 @@ err_setup_tx: int igc_open(struct net_device *netdev) { + struct igc_adapter *adapter = netdev_priv(netdev); + int err; + + /* Notify the stack of the actual queue counts. */ + err = netif_set_real_num_queues(netdev, adapter->num_tx_queues, + adapter->num_rx_queues); + if (err) { + netdev_err(netdev, "error setting real queue count\n"); + return err; + } + return __igc_open(netdev, false); } @@ -6009,24 +6325,6 @@ int igc_close(struct net_device *netdev) return 0; } -/** - * igc_ioctl - Access the hwtstamp interface - * @netdev: network interface device structure - * @ifr: interface request data - * @cmd: ioctl command - **/ -static int igc_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) -{ - switch (cmd) { - case SIOCGHWTSTAMP: - return igc_ptp_get_ts_config(netdev, ifr); - case SIOCSHWTSTAMP: - return igc_ptp_set_ts_config(netdev, ifr); - default: - return -EOPNOTSUPP; - } -} - static int igc_save_launchtime_params(struct igc_adapter *adapter, int queue, bool enable) { @@ -6119,15 +6417,15 @@ static int igc_tsn_enable_launchtime(struct igc_adapter *adapter, return igc_tsn_offload_apply(adapter); } -static int igc_tsn_clear_schedule(struct igc_adapter *adapter) +static int igc_qbv_clear_schedule(struct igc_adapter *adapter) { + unsigned long flags; int i; adapter->base_time = 0; adapter->cycle_time = NSEC_PER_SEC; adapter->taprio_offload_enable = false; adapter->qbv_config_change_errors = 0; - adapter->qbv_transition = false; adapter->qbv_count = 0; for (i = 0; i < adapter->num_tx_queues; i++) { @@ -6136,13 +6434,52 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter) ring->start_time = 0; ring->end_time = NSEC_PER_SEC; ring->max_sdu = 0; + ring->preemptible = false; + } + + spin_lock_irqsave(&adapter->qbv_tx_lock, flags); + + adapter->qbv_transition = false; + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *ring = adapter->tx_ring[i]; + ring->oper_gate_closed = false; ring->admin_gate_closed = false; } + spin_unlock_irqrestore(&adapter->qbv_tx_lock, flags); + + return 0; +} + +static int igc_tsn_clear_schedule(struct igc_adapter *adapter) +{ + igc_qbv_clear_schedule(adapter); + return 0; } +static void igc_taprio_stats(struct net_device *dev, + struct tc_taprio_qopt_stats *stats) +{ + /* When Strict_End is enabled, the tx_overruns counter + * will always be zero. + */ + stats->tx_overruns = 0; +} + +static void igc_taprio_queue_stats(struct net_device *dev, + struct tc_taprio_qopt_queue_stats *queue_stats) +{ + struct tc_taprio_qopt_stats *stats = &queue_stats->stats; + + /* When Strict_End is enabled, the tx_overruns counter + * will always be zero. + */ + stats->tx_overruns = 0; +} + static int igc_save_qbv_schedule(struct igc_adapter *adapter, struct tc_taprio_qopt_offload *qopt) { @@ -6150,15 +6487,10 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, struct igc_hw *hw = &adapter->hw; u32 start_time = 0, end_time = 0; struct timespec64 now; + unsigned long flags; size_t n; int i; - if (qopt->cmd == TAPRIO_CMD_DESTROY) - return igc_tsn_clear_schedule(adapter); - - if (qopt->cmd != TAPRIO_CMD_REPLACE) - return -EOPNOTSUPP; - if (qopt->base_time < 0) return -ERANGE; @@ -6168,12 +6500,23 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, if (!validate_schedule(adapter, qopt)) return -EINVAL; + if (qopt->mqprio.preemptible_tcs && + !(adapter->flags & IGC_FLAG_TSN_REVERSE_TXQ_PRIO)) { + NL_SET_ERR_MSG_MOD(qopt->extack, + "reverse-tsn-txq-prio private flag must be enabled before setting preemptible tc"); + return -ENODEV; + } + + igc_ptp_read(adapter, &now); + + if (igc_tsn_is_taprio_activated_by_user(adapter) && + is_base_time_past(qopt->base_time, &now)) + adapter->qbv_config_change_errors++; + adapter->cycle_time = qopt->cycle_time; adapter->base_time = qopt->base_time; adapter->taprio_offload_enable = true; - igc_ptp_read(adapter, &now); - for (n = 0; n < qopt->num_entries; n++) { struct tc_taprio_sched_entry *e = &qopt->entries[n]; @@ -6217,6 +6560,8 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, start_time += e->interval; } + spin_lock_irqsave(&adapter->qbv_tx_lock, flags); + /* Check whether a queue gets configured. * If not, set the start and end time to be end time. */ @@ -6241,6 +6586,8 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, } } + spin_unlock_irqrestore(&adapter->qbv_tx_lock, flags); + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; struct net_device *dev = adapter->netdev; @@ -6251,6 +6598,8 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, ring->max_sdu = 0; } + igc_fpe_save_preempt_queue(adapter, &qopt->mqprio); + return 0; } @@ -6263,7 +6612,23 @@ static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter, if (hw->mac.type != igc_i225) return -EOPNOTSUPP; - err = igc_save_qbv_schedule(adapter, qopt); + switch (qopt->cmd) { + case TAPRIO_CMD_REPLACE: + err = igc_save_qbv_schedule(adapter, qopt); + break; + case TAPRIO_CMD_DESTROY: + err = igc_tsn_clear_schedule(adapter); + break; + case TAPRIO_CMD_STATS: + igc_taprio_stats(adapter->netdev, &qopt->stats); + return 0; + case TAPRIO_CMD_QUEUE_STATS: + igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats); + return 0; + default: + return -EOPNOTSUPP; + } + if (err) return err; @@ -6344,10 +6709,18 @@ static int igc_tc_query_caps(struct igc_adapter *adapter, struct igc_hw *hw = &adapter->hw; switch (base->type) { + case TC_SETUP_QDISC_MQPRIO: { + struct tc_mqprio_caps *caps = base->caps; + + caps->validate_queue_counts = true; + + return 0; + } case TC_SETUP_QDISC_TAPRIO: { struct tc_taprio_caps *caps = base->caps; - caps->broken_mqprio = true; + if (!(adapter->flags & IGC_FLAG_TSN_REVERSE_TXQ_PRIO)) + caps->broken_mqprio = true; if (hw->mac.type == igc_i225) { caps->supports_queue_max_sdu = true; @@ -6361,6 +6734,96 @@ static int igc_tc_query_caps(struct igc_adapter *adapter, } } +static void igc_save_mqprio_params(struct igc_adapter *adapter, u8 num_tc, + u16 *offset) +{ + int i; + + adapter->strict_priority_enable = true; + adapter->num_tc = num_tc; + + for (i = 0; i < num_tc; i++) + adapter->queue_per_tc[i] = offset[i]; +} + +static bool +igc_tsn_is_tc_to_queue_priority_ordered(struct tc_mqprio_qopt_offload *mqprio) +{ + int num_tc = mqprio->qopt.num_tc; + int i; + + for (i = 1; i < num_tc; i++) { + if (mqprio->qopt.offset[i - 1] > mqprio->qopt.offset[i]) + return false; + } + + return true; +} + +static int igc_tsn_enable_mqprio(struct igc_adapter *adapter, + struct tc_mqprio_qopt_offload *mqprio) +{ + struct igc_hw *hw = &adapter->hw; + int err, i; + + if (hw->mac.type != igc_i225) + return -EOPNOTSUPP; + + if (!mqprio->qopt.num_tc) { + adapter->strict_priority_enable = false; + igc_fpe_clear_preempt_queue(adapter); + netdev_reset_tc(adapter->netdev); + goto apply; + } + + /* There are as many TCs as Tx queues. */ + if (mqprio->qopt.num_tc != adapter->num_tx_queues) { + NL_SET_ERR_MSG_FMT_MOD(mqprio->extack, + "Only %d traffic classes supported", + adapter->num_tx_queues); + return -EOPNOTSUPP; + } + + /* Only one queue per TC is supported. */ + for (i = 0; i < mqprio->qopt.num_tc; i++) { + if (mqprio->qopt.count[i] != 1) { + NL_SET_ERR_MSG_MOD(mqprio->extack, + "Only one queue per TC supported"); + return -EOPNOTSUPP; + } + } + + if (!igc_tsn_is_tc_to_queue_priority_ordered(mqprio)) { + NL_SET_ERR_MSG_MOD(mqprio->extack, + "tc to queue mapping must preserve increasing priority (higher tc -> higher queue)"); + return -EOPNOTSUPP; + } + + igc_save_mqprio_params(adapter, mqprio->qopt.num_tc, + mqprio->qopt.offset); + + err = netdev_set_num_tc(adapter->netdev, adapter->num_tc); + if (err) + return err; + + for (i = 0; i < adapter->num_tc; i++) { + err = netdev_set_tc_queue(adapter->netdev, i, 1, + adapter->queue_per_tc[i]); + if (err) + return err; + } + + /* In case the card is configured with less than four queues. */ + for (; i < IGC_MAX_TX_QUEUES; i++) + adapter->queue_per_tc[i] = i; + + mqprio->qopt.hw = TC_MQPRIO_HW_OFFLOAD_TCS; + igc_fpe_save_preempt_queue(adapter, mqprio); + +apply: + return igc_tsn_offload_apply(adapter); +} + static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { @@ -6380,6 +6843,9 @@ static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type, case TC_SETUP_QDISC_CBS: return igc_tsn_enable_cbs(adapter, type_data); + case TC_SETUP_QDISC_MQPRIO: + return igc_tsn_enable_mqprio(adapter, type_data); + default: return -EOPNOTSUPP; } @@ -6407,15 +6873,15 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, int cpu = smp_processor_id(); struct netdev_queue *nq; struct igc_ring *ring; - int i, drops; + int i, nxmit; - if (unlikely(test_bit(__IGC_DOWN, &adapter->state))) + if (unlikely(!netif_carrier_ok(dev))) return -ENETDOWN; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; - ring = igc_xdp_get_tx_ring(adapter, cpu); + ring = igc_get_tx_ring(adapter, cpu); nq = txring_txq(ring); __netif_tx_lock(nq, cpu); @@ -6423,16 +6889,15 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, /* Avoid transmit queue timeout since we share it with the slow path */ txq_trans_cond_update(nq); - drops = 0; + nxmit = 0; for (i = 0; i < num_frames; i++) { int err; struct xdp_frame *xdpf = frames[i]; err = igc_xdp_init_tx_descriptor(ring, xdpf); - if (err) { - xdp_return_frame_rx_napi(xdpf); - drops++; - } + if (err) + break; + nxmit++; } if (flags & XDP_XMIT_FLUSH) @@ -6440,7 +6905,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, __netif_tx_unlock(nq); - return num_frames - drops; + return nxmit; } static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter, @@ -6480,6 +6945,24 @@ int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) return 0; } +static ktime_t igc_get_tstamp(struct net_device *dev, + const struct skb_shared_hwtstamps *hwtstamps, + bool cycles) +{ + struct igc_adapter *adapter = netdev_priv(dev); + struct igc_inline_rx_tstamps *tstamp; + ktime_t timestamp; + + tstamp = hwtstamps->netdev_data; + + if (cycles) + timestamp = igc_ptp_rx_pktstamp(adapter, tstamp->timer1); + else + timestamp = igc_ptp_rx_pktstamp(adapter, tstamp->timer0); + + return timestamp; +} + static const struct net_device_ops igc_netdev_ops = { .ndo_open = igc_open, .ndo_stop = igc_close, @@ -6492,52 +6975,15 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_fix_features = igc_fix_features, .ndo_set_features = igc_set_features, .ndo_features_check = igc_features_check, - .ndo_eth_ioctl = igc_ioctl, .ndo_setup_tc = igc_setup_tc, .ndo_bpf = igc_bpf, .ndo_xdp_xmit = igc_xdp_xmit, .ndo_xsk_wakeup = igc_xsk_wakeup, + .ndo_get_tstamp = igc_get_tstamp, + .ndo_hwtstamp_get = igc_ptp_hwtstamp_get, + .ndo_hwtstamp_set = igc_ptp_hwtstamp_set, }; -/* PCIe configuration access */ -void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - pci_read_config_word(adapter->pdev, reg, value); -} - -void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - pci_write_config_word(adapter->pdev, reg, *value); -} - -s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - if (!pci_is_pcie(adapter->pdev)) - return -IGC_ERR_CONFIG; - - pcie_capability_read_word(adapter->pdev, reg, value); - - return IGC_SUCCESS; -} - -s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - if (!pci_is_pcie(adapter->pdev)) - return -IGC_ERR_CONFIG; - - pcie_capability_write_word(adapter->pdev, reg, *value); - - return IGC_SUCCESS; -} - u32 igc_rd32(struct igc_hw *hw, u32 reg) { struct igc_adapter *igc = container_of(hw, struct igc_adapter, hw); @@ -6600,9 +7046,11 @@ static int igc_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash, static int igc_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp) { const struct igc_xdp_buff *ctx = (void *)_ctx; + struct igc_adapter *adapter = netdev_priv(ctx->xdp.rxq->dev); + struct igc_inline_rx_tstamps *tstamp = ctx->rx_ts; if (igc_test_staterr(ctx->rx_desc, IGC_RXDADV_STAT_TSIP)) { - *timestamp = ctx->rx_ts; + *timestamp = igc_ptp_rx_pktstamp(adapter, tstamp->timer0); return 0; } @@ -6619,8 +7067,11 @@ static enum hrtimer_restart igc_qbv_scheduling_timer(struct hrtimer *timer) { struct igc_adapter *adapter = container_of(timer, struct igc_adapter, hrtimer); + unsigned long flags; unsigned int i; + spin_lock_irqsave(&adapter->qbv_tx_lock, flags); + adapter->qbv_transition = true; for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *tx_ring = adapter->tx_ring[i]; @@ -6633,6 +7084,9 @@ static enum hrtimer_restart igc_qbv_scheduling_timer(struct hrtimer *timer) } } adapter->qbv_transition = false; + + spin_unlock_irqrestore(&adapter->qbv_tx_lock, flags); + return HRTIMER_NORESTART; } @@ -6695,6 +7149,17 @@ static int igc_probe(struct pci_dev *pdev, adapter->port_num = hw->bus.func; adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); + /* PCI config space info */ + hw->vendor_id = pdev->vendor; + hw->device_id = pdev->device; + hw->revision_id = pdev->revision; + hw->subsystem_vendor_id = pdev->subsystem_vendor; + hw->subsystem_device_id = pdev->subsystem_device; + + /* Disable ASPM L1.2 on I226 devices to avoid packet loss */ + if (igc_is_device_id_i226(hw)) + pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2); + err = pci_save_state(pdev); if (err) goto err_ioremap; @@ -6710,19 +7175,13 @@ static int igc_probe(struct pci_dev *pdev, netdev->netdev_ops = &igc_netdev_ops; netdev->xdp_metadata_ops = &igc_xdp_metadata_ops; + netdev->xsk_tx_metadata_ops = &igc_xsk_tx_metadata_ops; igc_ethtool_set_ops(netdev); netdev->watchdog_timeo = 5 * HZ; netdev->mem_start = pci_resource_start(pdev, 0); netdev->mem_end = pci_resource_end(pdev, 0); - /* PCI config space info */ - hw->vendor_id = pdev->vendor; - hw->device_id = pdev->device; - hw->revision_id = pdev->revision; - hw->subsystem_vendor_id = pdev->subsystem_vendor; - hw->subsystem_device_id = pdev->subsystem_device; - /* Copy the default MAC and PHY function pointers */ memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops)); memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops)); @@ -6773,6 +7232,9 @@ static int igc_probe(struct pci_dev *pdev, netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_XSK_ZEROCOPY; + /* enable HW vlan tag insertion/stripping by default */ + netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; + /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE; @@ -6805,8 +7267,8 @@ static int igc_probe(struct pci_dev *pdev, } /* configure RXPBSIZE and TXPBSIZE */ - wr32(IGC_RXPBS, I225_RXPBSIZE_DEFAULT); - wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); + wr32(IGC_RXPBS, IGC_RXPBSIZE_EXP_BMC_DEFAULT); + wr32(IGC_TXPBS, IGC_TXPBSIZE_DEFAULT); timer_setup(&adapter->watchdog_timer, igc_watchdog, 0); timer_setup(&adapter->phy_info_timer, igc_update_phy_info, 0); @@ -6814,12 +7276,11 @@ static int igc_probe(struct pci_dev *pdev, INIT_WORK(&adapter->reset_task, igc_reset_task); INIT_WORK(&adapter->watchdog_task, igc_watchdog_task); - hrtimer_init(&adapter->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - adapter->hrtimer.function = &igc_qbv_scheduling_timer; + hrtimer_setup(&adapter->hrtimer, &igc_qbv_scheduling_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); /* Initialize link properties that are user-changeable */ adapter->fc_autoneg = true; - hw->mac.autoneg = true; hw->phy.autoneg_advertised = 0xaf; hw->fc.requested_mode = igc_fc_default; @@ -6839,6 +7300,8 @@ static int igc_probe(struct pci_dev *pdev, igc_tsn_clear_schedule(adapter); + igc_fpe_init(adapter); + /* reset the hardware with the new settings */ igc_reset(adapter); @@ -6847,7 +7310,7 @@ static int igc_probe(struct pci_dev *pdev, */ igc_get_hw_control(adapter); - strncpy(netdev->name, "eth%d", IFNAMSIZ); + strscpy(netdev->name, "eth%d", sizeof(netdev->name)); err = register_netdev(netdev); if (err) goto err_register; @@ -6870,10 +7333,23 @@ static int igc_probe(struct pci_dev *pdev, pm_runtime_put_noidle(&pdev->dev); + if (IS_ENABLED(CONFIG_IGC_LEDS)) { + err = igc_led_setup(adapter); + if (err) { + netdev_warn_once(netdev, + "LED init failed (%d); continuing without LED support\n", + err); + adapter->leds_available = false; + } else { + adapter->leds_available = true; + } + } + return 0; err_register: igc_release_hw_control(adapter); + igc_ptp_stop(adapter); err_eeprom: if (!igc_check_reset_block(hw)) igc_reset_phy(hw); @@ -6915,13 +7391,16 @@ static void igc_remove(struct pci_dev *pdev) set_bit(__IGC_DOWN, &adapter->state); - del_timer_sync(&adapter->watchdog_timer); - del_timer_sync(&adapter->phy_info_timer); + timer_delete_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->phy_info_timer); cancel_work_sync(&adapter->reset_task); cancel_work_sync(&adapter->watchdog_task); hrtimer_cancel(&adapter->hrtimer); + if (IS_ENABLED(CONFIG_IGC_LEDS) && adapter->leds_available) + igc_led_free(adapter); + /* Release control of h/w to f/w. If f/w is AMT enabled, this * would have already happened in close and is redundant. */ @@ -7006,8 +7485,7 @@ static int __igc_shutdown(struct pci_dev *pdev, bool *enable_wake, return 0; } -#ifdef CONFIG_PM -static int __maybe_unused igc_runtime_suspend(struct device *dev) +static int igc_runtime_suspend(struct device *dev) { return __igc_shutdown(to_pci_dev(dev), NULL, 1); } @@ -7042,7 +7520,7 @@ static void igc_deliver_wake_packet(struct net_device *netdev) netif_rx(skb); } -static int __maybe_unused igc_resume(struct device *dev) +static int __igc_resume(struct device *dev, bool rpm) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -7052,7 +7530,6 @@ static int __maybe_unused igc_resume(struct device *dev) pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); - pci_save_state(pdev); if (!pci_device_is_present(pdev)) return -ENODEV; @@ -7066,6 +7543,9 @@ static int __maybe_unused igc_resume(struct device *dev) pci_enable_wake(pdev, PCI_D3hot, 0); pci_enable_wake(pdev, PCI_D3cold, 0); + if (igc_is_device_id_i226(hw)) + pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2); + if (igc_init_interrupt_scheme(adapter, true)) { netdev_err(netdev, "Unable to allocate memory for queues\n"); return -ENOMEM; @@ -7084,23 +7564,30 @@ static int __maybe_unused igc_resume(struct device *dev) wr32(IGC_WUS, ~0); - rtnl_lock(); - if (!err && netif_running(netdev)) + if (netif_running(netdev)) { + if (!rpm) + rtnl_lock(); err = __igc_open(netdev, true); - - if (!err) - netif_device_attach(netdev); - rtnl_unlock(); + if (!rpm) + rtnl_unlock(); + if (!err) + netif_device_attach(netdev); + } return err; } -static int __maybe_unused igc_runtime_resume(struct device *dev) +static int igc_resume(struct device *dev) { - return igc_resume(dev); + return __igc_resume(dev, false); } -static int __maybe_unused igc_suspend(struct device *dev) +static int igc_runtime_resume(struct device *dev) +{ + return __igc_resume(dev, true); +} + +static int igc_suspend(struct device *dev) { return __igc_shutdown(to_pci_dev(dev), NULL, 0); } @@ -7115,7 +7602,6 @@ static int __maybe_unused igc_runtime_idle(struct device *dev) return -EBUSY; } -#endif /* CONFIG_PM */ static void igc_shutdown(struct pci_dev *pdev) { @@ -7143,14 +7629,18 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = pci_get_drvdata(pdev); struct igc_adapter *adapter = netdev_priv(netdev); + rtnl_lock(); netif_device_detach(netdev); - if (state == pci_channel_io_perm_failure) + if (state == pci_channel_io_perm_failure) { + rtnl_unlock(); return PCI_ERS_RESULT_DISCONNECT; + } if (netif_running(netdev)) igc_down(adapter); pci_disable_device(pdev); + rtnl_unlock(); /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; @@ -7161,7 +7651,7 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev, * @pdev: Pointer to PCI device * * Restart the card from scratch, as if from a cold-boot. Implementation - * resembles the first-half of the igc_resume routine. + * resembles the first-half of the __igc_resume routine. **/ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) { @@ -7176,11 +7666,13 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) } else { pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); pci_enable_wake(pdev, PCI_D3hot, 0); pci_enable_wake(pdev, PCI_D3cold, 0); + if (igc_is_device_id_i226(hw)) + pci_disable_link_state_locked(pdev, PCIE_LINK_STATE_L1_2); + /* In case of PCI error, adapter loses its HW address * so we should re-assign it here. */ @@ -7200,7 +7692,7 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) * * This callback is called when the error recovery driver tells us that * its OK to resume normal operation. Implementation resembles the - * second-half of the igc_resume routine. + * second-half of the __igc_resume routine. */ static void igc_io_resume(struct pci_dev *pdev) { @@ -7210,6 +7702,7 @@ static void igc_io_resume(struct pci_dev *pdev) rtnl_lock(); if (netif_running(netdev)) { if (igc_open(netdev)) { + rtnl_unlock(); netdev_err(netdev, "igc_open failed after reset\n"); return; } @@ -7230,22 +7723,16 @@ static const struct pci_error_handlers igc_err_handler = { .resume = igc_io_resume, }; -#ifdef CONFIG_PM -static const struct dev_pm_ops igc_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(igc_suspend, igc_resume) - SET_RUNTIME_PM_OPS(igc_runtime_suspend, igc_runtime_resume, - igc_runtime_idle) -}; -#endif +static _DEFINE_DEV_PM_OPS(igc_pm_ops, igc_suspend, igc_resume, + igc_runtime_suspend, igc_runtime_resume, + igc_runtime_idle); static struct pci_driver igc_driver = { .name = igc_driver_name, .id_table = igc_pci_tbl, .probe = igc_probe, .remove = igc_remove, -#ifdef CONFIG_PM - .driver.pm = &igc_pm_ops, -#endif + .driver.pm = pm_ptr(&igc_pm_ops), .shutdown = igc_shutdown, .err_handler = &igc_err_handler, }; |