diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ixgbe/ixgbe_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 572 |
1 files changed, 465 insertions, 107 deletions
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index a7a430a7be2c..22a29df1d29e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -49,6 +49,9 @@ #include <linux/if_macvlan.h> #include <linux/if_bridge.h> #include <linux/prefetch.h> +#include <linux/bpf.h> +#include <linux/bpf_trace.h> +#include <linux/atomic.h> #include <scsi/fc/fc_fcoe.h> #include <net/udp_tunnel.h> #include <net/pkt_cls.h> @@ -85,6 +88,7 @@ static const struct ixgbe_info *ixgbe_info_tbl[] = { [board_X540] = &ixgbe_X540_info, [board_X550] = &ixgbe_X550_info, [board_X550EM_x] = &ixgbe_X550EM_x_info, + [board_x550em_x_fw] = &ixgbe_x550em_x_fw_info, [board_x550em_a] = &ixgbe_x550em_a_info, [board_x550em_a_fw] = &ixgbe_x550em_a_fw_info, }; @@ -131,9 +135,11 @@ static const struct pci_device_id ixgbe_pci_tbl[] = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T), board_X550}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T1), board_X550}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KX4), board_X550EM_x}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_XFI), board_X550EM_x}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KR), board_X550EM_x}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_10G_T), board_X550EM_x}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_SFP), board_X550EM_x}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_1G_T), board_x550em_x_fw}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_KR), board_x550em_a }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_KR_L), board_x550em_a }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP_N), board_x550em_a }, @@ -508,7 +514,7 @@ static const struct ixgbe_reg_info ixgbe_reg_info_tbl[] = { */ static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo) { - int i = 0, j = 0; + int i; char rname[16]; u32 regs[64]; @@ -570,21 +576,38 @@ static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo) regs[i] = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i)); break; default: - pr_info("%-15s %08x\n", reginfo->name, - IXGBE_READ_REG(hw, reginfo->ofs)); + pr_info("%-15s %08x\n", + reginfo->name, IXGBE_READ_REG(hw, reginfo->ofs)); return; } - for (i = 0; i < 8; i++) { - snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i*8, i*8+7); - pr_err("%-15s", rname); + i = 0; + while (i < 64) { + int j; + char buf[9 * 8 + 1]; + char *p = buf; + + snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i, i + 7); for (j = 0; j < 8; j++) - pr_cont(" %08x", regs[i*8+j]); - pr_cont("\n"); + p += sprintf(p, " %08x", regs[i++]); + pr_err("%-15s%s\n", rname, buf); } } +static void ixgbe_print_buffer(struct ixgbe_ring *ring, int n) +{ + struct ixgbe_tx_buffer *tx_buffer; + + tx_buffer = &ring->tx_buffer_info[ring->next_to_clean]; + pr_info(" %5d %5X %5X %016llX %08X %p %016llX\n", + n, ring->next_to_use, ring->next_to_clean, + (u64)dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + tx_buffer->next_to_watch, + (u64)tx_buffer->time_stamp); +} + /* * ixgbe_dump - Print registers, tx-rings and rx-rings */ @@ -594,14 +617,13 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; struct ixgbe_reg_info *reginfo; int n = 0; - struct ixgbe_ring *tx_ring; + struct ixgbe_ring *ring; struct ixgbe_tx_buffer *tx_buffer; union ixgbe_adv_tx_desc *tx_desc; struct my_u0 { u64 a; u64 b; } *u0; struct ixgbe_ring *rx_ring; union ixgbe_adv_rx_desc *rx_desc; struct ixgbe_rx_buffer *rx_buffer_info; - u32 staterr; int i = 0; if (!netif_msg_hw(adapter)) @@ -635,14 +657,13 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) "Queue [NTU] [NTC] [bi(ntc)->dma ]", "leng", "ntw", "timestamp"); for (n = 0; n < adapter->num_tx_queues; n++) { - tx_ring = adapter->tx_ring[n]; - tx_buffer = &tx_ring->tx_buffer_info[tx_ring->next_to_clean]; - pr_info(" %5d %5X %5X %016llX %08X %p %016llX\n", - n, tx_ring->next_to_use, tx_ring->next_to_clean, - (u64)dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - tx_buffer->next_to_watch, - (u64)tx_buffer->time_stamp); + ring = adapter->tx_ring[n]; + ixgbe_print_buffer(ring, n); + } + + for (n = 0; n < adapter->num_xdp_queues; n++) { + ring = adapter->xdp_ring[n]; + ixgbe_print_buffer(ring, n); } /* Print TX Rings */ @@ -687,21 +708,32 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) */ for (n = 0; n < adapter->num_tx_queues; n++) { - tx_ring = adapter->tx_ring[n]; + ring = adapter->tx_ring[n]; pr_info("------------------------------------\n"); - pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index); + pr_info("TX QUEUE INDEX = %d\n", ring->queue_index); pr_info("------------------------------------\n"); pr_info("%s%s %s %s %s %s\n", "T [desc] [address 63:0 ] ", "[PlPOIdStDDt Ln] [bi->dma ] ", "leng", "ntw", "timestamp", "bi->skb"); - for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) { - tx_desc = IXGBE_TX_DESC(tx_ring, i); - tx_buffer = &tx_ring->tx_buffer_info[i]; + for (i = 0; ring->desc && (i < ring->count); i++) { + tx_desc = IXGBE_TX_DESC(ring, i); + tx_buffer = &ring->tx_buffer_info[i]; u0 = (struct my_u0 *)tx_desc; if (dma_unmap_len(tx_buffer, len) > 0) { - pr_info("T [0x%03X] %016llX %016llX %016llX %08X %p %016llX %p", + const char *ring_desc; + + if (i == ring->next_to_use && + i == ring->next_to_clean) + ring_desc = " NTC/U"; + else if (i == ring->next_to_use) + ring_desc = " NTU"; + else if (i == ring->next_to_clean) + ring_desc = " NTC"; + else + ring_desc = ""; + pr_info("T [0x%03X] %016llX %016llX %016llX %08X %p %016llX %p%s", i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), @@ -709,16 +741,8 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) dma_unmap_len(tx_buffer, len), tx_buffer->next_to_watch, (u64)tx_buffer->time_stamp, - tx_buffer->skb); - if (i == tx_ring->next_to_use && - i == tx_ring->next_to_clean) - pr_cont(" NTC/U\n"); - else if (i == tx_ring->next_to_use) - pr_cont(" NTU\n"); - else if (i == tx_ring->next_to_clean) - pr_cont(" NTC\n"); - else - pr_cont("\n"); + tx_buffer->skb, + ring_desc); if (netif_msg_pktdata(adapter) && tx_buffer->skb) @@ -797,34 +821,44 @@ rx_ring_summary: pr_info("------------------------------------\n"); pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index); pr_info("------------------------------------\n"); - pr_info("%s%s%s", + pr_info("%s%s%s\n", "R [desc] [ PktBuf A0] ", "[ HeadBuf DD] [bi->dma ] [bi->skb ] ", - "<-- Adv Rx Read format\n"); - pr_info("%s%s%s", + "<-- Adv Rx Read format"); + pr_info("%s%s%s\n", "RWB[desc] [PcsmIpSHl PtRs] ", "[vl er S cks ln] ---------------- [bi->skb ] ", - "<-- Adv Rx Write-Back format\n"); + "<-- Adv Rx Write-Back format"); for (i = 0; i < rx_ring->count; i++) { + const char *ring_desc; + + if (i == rx_ring->next_to_use) + ring_desc = " NTU"; + else if (i == rx_ring->next_to_clean) + ring_desc = " NTC"; + else + ring_desc = ""; + rx_buffer_info = &rx_ring->rx_buffer_info[i]; rx_desc = IXGBE_RX_DESC(rx_ring, i); u0 = (struct my_u0 *)rx_desc; - staterr = le32_to_cpu(rx_desc->wb.upper.status_error); - if (staterr & IXGBE_RXD_STAT_DD) { + if (rx_desc->wb.upper.length) { /* Descriptor Done */ - pr_info("RWB[0x%03X] %016llX " - "%016llX ---------------- %p", i, + pr_info("RWB[0x%03X] %016llX %016llX ---------------- %p%s\n", + i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), - rx_buffer_info->skb); + rx_buffer_info->skb, + ring_desc); } else { - pr_info("R [0x%03X] %016llX " - "%016llX %016llX %p", i, + pr_info("R [0x%03X] %016llX %016llX %016llX %p%s\n", + i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), (u64)rx_buffer_info->dma, - rx_buffer_info->skb); + rx_buffer_info->skb, + ring_desc); if (netif_msg_pktdata(adapter) && rx_buffer_info->dma) { @@ -835,14 +869,6 @@ rx_ring_summary: ixgbe_rx_bufsz(rx_ring), true); } } - - if (i == rx_ring->next_to_use) - pr_cont(" NTU\n"); - else if (i == rx_ring->next_to_clean) - pr_cont(" NTC\n"); - else - pr_cont("\n"); - } } } @@ -972,6 +998,10 @@ static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_tx_queues; i++) clear_bit(__IXGBE_HANG_CHECK_ARMED, &adapter->tx_ring[i]->state); + + for (i = 0; i < adapter->num_xdp_queues; i++) + clear_bit(__IXGBE_HANG_CHECK_ARMED, + &adapter->xdp_ring[i]->state); } static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter) @@ -1016,6 +1046,14 @@ static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter) if (xoff[tc]) clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state); } + + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i]; + + tc = xdp_ring->dcb_tc; + if (xoff[tc]) + clear_bit(__IXGBE_HANG_CHECK_ARMED, &xdp_ring->state); + } } static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring) @@ -1167,7 +1205,10 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, total_packets += tx_buffer->gso_segs; /* free the skb */ - napi_consume_skb(tx_buffer->skb, napi_budget); + if (ring_is_xdp(tx_ring)) + page_frag_free(tx_buffer->data); + else + napi_consume_skb(tx_buffer->skb, napi_budget); /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -1228,7 +1269,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) { /* schedule immediate reset if we believe we hung */ struct ixgbe_hw *hw = &adapter->hw; - e_err(drv, "Detected Tx Unit Hang\n" + e_err(drv, "Detected Tx Unit Hang %s\n" " Tx Queue <%d>\n" " TDH, TDT <%x>, <%x>\n" " next_to_use <%x>\n" @@ -1236,13 +1277,16 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, "tx_buffer_info[next_to_clean]\n" " time_stamp <%lx>\n" " jiffies <%lx>\n", + ring_is_xdp(tx_ring) ? "(XDP)" : "", tx_ring->queue_index, IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)), IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)), tx_ring->next_to_use, i, tx_ring->tx_buffer_info[i].time_stamp, jiffies); - netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); + if (!ring_is_xdp(tx_ring)) + netif_stop_subqueue(tx_ring->netdev, + tx_ring->queue_index); e_info(probe, "tx hang %d detected on queue %d, resetting adapter\n", @@ -1255,6 +1299,9 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, return true; } + if (ring_is_xdp(tx_ring)) + return !!budget; + netdev_tx_completed_queue(txring_txq(tx_ring), total_packets, total_bytes); @@ -1846,6 +1893,10 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, * @rx_desc: pointer to the EOP Rx descriptor * @skb: pointer to current skb being fixed * + * Check if the skb is valid in the XDP case it will be an error pointer. + * Return true in this case to abort processing and advance to next + * descriptor. + * * Check for corrupted packet headers caused by senders on the local L2 * embedded NIC switch not setting up their Tx Descriptors right. These * should be very rare. @@ -1864,6 +1915,10 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, { struct net_device *netdev = rx_ring->netdev; + /* XDP packets use error pointer so abort at this point */ + if (IS_ERR(skb)) + return true; + /* verify that the packet does not have any known errors */ if (unlikely(ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_FRAME_ERR_MASK) && @@ -2039,7 +2094,7 @@ static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring, /* hand second half of page back to the ring */ ixgbe_reuse_rx_page(rx_ring, rx_buffer); } else { - if (IXGBE_CB(skb)->dma == rx_buffer->dma) { + if (!IS_ERR(skb) && IXGBE_CB(skb)->dma == rx_buffer->dma) { /* the page has been released from the ring */ IXGBE_CB(skb)->page_released = true; } else { @@ -2060,21 +2115,22 @@ static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring, static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *rx_buffer, - union ixgbe_adv_rx_desc *rx_desc, - unsigned int size) + struct xdp_buff *xdp, + union ixgbe_adv_rx_desc *rx_desc) { - void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; + unsigned int size = xdp->data_end - xdp->data; #if (PAGE_SIZE < 8192) unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = SKB_DATA_ALIGN(size); + unsigned int truesize = SKB_DATA_ALIGN(xdp->data_end - + xdp->data_hard_start); #endif struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); + prefetch(xdp->data); #if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); + prefetch(xdp->data + L1_CACHE_BYTES); #endif /* allocate a skb to store the frags */ @@ -2087,7 +2143,7 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, IXGBE_CB(skb)->dma = rx_buffer->dma; skb_add_rx_frag(skb, 0, rx_buffer->page, - rx_buffer->page_offset, + xdp->data - page_address(rx_buffer->page), size, truesize); #if (PAGE_SIZE < 8192) rx_buffer->page_offset ^= truesize; @@ -2095,7 +2151,8 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, rx_buffer->page_offset += truesize; #endif } else { - memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); + memcpy(__skb_put(skb, size), + xdp->data, ALIGN(size, sizeof(long))); rx_buffer->pagecnt_bias++; } @@ -2104,32 +2161,32 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *rx_buffer, - union ixgbe_adv_rx_desc *rx_desc, - unsigned int size) + struct xdp_buff *xdp, + union ixgbe_adv_rx_desc *rx_desc) { - void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(IXGBE_SKB_PAD + size); + SKB_DATA_ALIGN(xdp->data_end - + xdp->data_hard_start); #endif struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); + prefetch(xdp->data); #if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); + prefetch(xdp->data + L1_CACHE_BYTES); #endif /* build an skb to around the page buffer */ - skb = build_skb(va - IXGBE_SKB_PAD, truesize); + skb = build_skb(xdp->data_hard_start, truesize); if (unlikely(!skb)) return NULL; /* update pointers within the skb to store the data */ - skb_reserve(skb, IXGBE_SKB_PAD); - __skb_put(skb, size); + skb_reserve(skb, xdp->data - xdp->data_hard_start); + __skb_put(skb, xdp->data_end - xdp->data); /* record DMA address if this is the start of a chain of buffers */ if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) @@ -2145,6 +2202,65 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, return skb; } +#define IXGBE_XDP_PASS 0 +#define IXGBE_XDP_CONSUMED 1 +#define IXGBE_XDP_TX 2 + +static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, + struct xdp_buff *xdp); + +static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring, + struct xdp_buff *xdp) +{ + int result = IXGBE_XDP_PASS; + struct bpf_prog *xdp_prog; + u32 act; + + rcu_read_lock(); + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + + if (!xdp_prog) + goto xdp_out; + + act = bpf_prog_run_xdp(xdp_prog, xdp); + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + result = ixgbe_xmit_xdp_ring(adapter, xdp); + break; + default: + bpf_warn_invalid_xdp_action(act); + case XDP_ABORTED: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + /* fallthrough -- handle aborts by dropping packet */ + case XDP_DROP: + result = IXGBE_XDP_CONSUMED; + break; + } +xdp_out: + rcu_read_unlock(); + return ERR_PTR(-result); +} + +static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *rx_buffer, + unsigned int size) +{ +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; + + rx_buffer->page_offset ^= truesize; +#else + unsigned int truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) : + SKB_DATA_ALIGN(size); + + rx_buffer->page_offset += truesize; +#endif +} + /** * ixgbe_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @q_vector: structure containing interrupt and ring information @@ -2163,17 +2279,19 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, const int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; -#ifdef IXGBE_FCOE struct ixgbe_adapter *adapter = q_vector->adapter; +#ifdef IXGBE_FCOE int ddp_bytes; unsigned int mss = 0; #endif /* IXGBE_FCOE */ u16 cleaned_count = ixgbe_desc_unused(rx_ring); + bool xdp_xmit = false; while (likely(total_rx_packets < budget)) { union ixgbe_adv_rx_desc *rx_desc; struct ixgbe_rx_buffer *rx_buffer; struct sk_buff *skb; + struct xdp_buff xdp; unsigned int size; /* return some buffers to hardware, one at a time is too slow */ @@ -2196,14 +2314,34 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size); /* retrieve a buffer from the ring */ - if (skb) + if (!skb) { + xdp.data = page_address(rx_buffer->page) + + rx_buffer->page_offset; + xdp.data_hard_start = xdp.data - + ixgbe_rx_offset(rx_ring); + xdp.data_end = xdp.data + size; + + skb = ixgbe_run_xdp(adapter, rx_ring, &xdp); + } + + if (IS_ERR(skb)) { + if (PTR_ERR(skb) == -IXGBE_XDP_TX) { + xdp_xmit = true; + ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size); + } else { + rx_buffer->pagecnt_bias++; + } + total_rx_packets++; + total_rx_bytes += size; + } else if (skb) { ixgbe_add_rx_frag(rx_ring, rx_buffer, skb, size); - else if (ring_uses_build_skb(rx_ring)) + } else if (ring_uses_build_skb(rx_ring)) { skb = ixgbe_build_skb(rx_ring, rx_buffer, - rx_desc, size); - else + &xdp, rx_desc); + } else { skb = ixgbe_construct_skb(rx_ring, rx_buffer, - rx_desc, size); + &xdp, rx_desc); + } /* exit if we failed to retrieve a buffer */ if (!skb) { @@ -2260,6 +2398,16 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, total_rx_packets++; } + if (xdp_xmit) { + struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); + } + u64_stats_update_begin(&rx_ring->syncp); rx_ring->stats.packets += total_rx_packets; rx_ring->stats.bytes += total_rx_bytes; @@ -3364,6 +3512,8 @@ static void ixgbe_configure_tx(struct ixgbe_adapter *adapter) /* Setup the HW Tx Head and Tail descriptor pointers */ for (i = 0; i < adapter->num_tx_queues; i++) ixgbe_configure_tx_ring(adapter, adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + ixgbe_configure_tx_ring(adapter, adapter->xdp_ring[i]); } static void ixgbe_enable_rx_drop(struct ixgbe_adapter *adapter, @@ -3489,6 +3639,28 @@ void ixgbe_store_key(struct ixgbe_adapter *adapter) } /** + * ixgbe_init_rss_key - Initialize adapter RSS key + * @adapter: device handle + * + * Allocates and initializes the RSS key if it is not allocated. + **/ +static inline int ixgbe_init_rss_key(struct ixgbe_adapter *adapter) +{ + u32 *rss_key; + + if (!adapter->rss_key) { + rss_key = kzalloc(IXGBE_RSS_KEY_SIZE, GFP_KERNEL); + if (unlikely(!rss_key)) + return -ENOMEM; + + netdev_rss_key_fill(rss_key, IXGBE_RSS_KEY_SIZE); + adapter->rss_key = rss_key; + } + + return 0; +} + +/** * ixgbe_store_reta - Write the RETA table to HW * @adapter: device handle * @@ -3590,7 +3762,7 @@ static void ixgbe_setup_vfreta(struct ixgbe_adapter *adapter) /* Fill out hash function seeds */ for (i = 0; i < 10; i++) IXGBE_WRITE_REG(hw, IXGBE_PFVFRSSRK(i, pf_pool), - adapter->rss_key[i]); + *(adapter->rss_key + i)); /* Fill out the redirection table */ for (i = 0, j = 0; i < 64; i++, j++) { @@ -3651,7 +3823,6 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV6_UDP) rss_field |= IXGBE_MRQC_RSS_FIELD_IPV6_UDP; - netdev_rss_key_fill(adapter->rss_key, sizeof(adapter->rss_key)); if ((hw->mac.type >= ixgbe_mac_X550) && (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) { unsigned int pf_pool = adapter->num_vfs; @@ -3802,7 +3973,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, /* Limit the maximum frame size so we don't overrun the skb */ if (ring_uses_build_skb(ring) && !test_bit(__IXGBE_RX_3K_BUFFER, &ring->state)) - rxdctl |= IXGBE_MAX_FRAME_BUILD_SKB | + rxdctl |= IXGBE_MAX_2K_FRAME_BUILD_SKB | IXGBE_RXDCTL_RLPML_EN; #endif } @@ -3972,8 +4143,8 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter) if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); - if ((max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)) || - (max_frame > IXGBE_MAX_FRAME_BUILD_SKB)) + if (IXGBE_2K_TOO_SMALL_WITH_PADDING || + (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN))) set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); #endif } @@ -5505,7 +5676,10 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) union ixgbe_adv_tx_desc *eop_desc, *tx_desc; /* Free all the Tx ring sk_buffs */ - dev_kfree_skb_any(tx_buffer->skb); + if (ring_is_xdp(tx_ring)) + page_frag_free(tx_buffer->data); + else + dev_kfree_skb_any(tx_buffer->skb); /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -5546,7 +5720,8 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) } /* reset BQL for queue */ - netdev_tx_reset_queue(txring_txq(tx_ring)); + if (!ring_is_xdp(tx_ring)) + netdev_tx_reset_queue(txring_txq(tx_ring)); /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; @@ -5575,6 +5750,8 @@ static void ixgbe_clean_all_tx_rings(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_tx_queues; i++) ixgbe_clean_tx_ring(adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + ixgbe_clean_tx_ring(adapter->xdp_ring[i]); } static void ixgbe_fdir_filter_exit(struct ixgbe_adapter *adapter) @@ -5669,6 +5846,11 @@ void ixgbe_down(struct ixgbe_adapter *adapter) u8 reg_idx = adapter->tx_ring[i]->reg_idx; IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); } + for (i = 0; i < adapter->num_xdp_queues; i++) { + u8 reg_idx = adapter->xdp_ring[i]->reg_idx; + + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); + } /* Disable the Tx DMA engine on 82599 and later MAC */ switch (hw->mac.type) { @@ -5854,6 +6036,9 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, if (!adapter->mac_table) return -ENOMEM; + if (ixgbe_init_rss_key(adapter)) + return -ENOMEM; + /* Set MAC specific capability flags and exceptions */ switch (hw->mac.type) { case ixgbe_mac_82598EB: @@ -5944,10 +6129,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, /* assign number of SR-IOV VFs */ if (hw->mac.type != ixgbe_mac_82598EB) { if (max_vfs > IXGBE_MAX_VFS_DRV_LIMIT) { - adapter->num_vfs = 0; + max_vfs = 0; e_dev_warn("max_vfs parameter out of range. Not assigning any SR-IOV VFs\n"); - } else { - adapter->num_vfs = max_vfs; } } #endif /* CONFIG_PCI_IOV */ @@ -6041,7 +6224,7 @@ err: **/ static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter) { - int i, err = 0; + int i, j = 0, err = 0; for (i = 0; i < adapter->num_tx_queues; i++) { err = ixgbe_setup_tx_resources(adapter->tx_ring[i]); @@ -6051,10 +6234,20 @@ static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter) e_err(probe, "Allocation for Tx Queue %u failed\n", i); goto err_setup_tx; } + for (j = 0; j < adapter->num_xdp_queues; j++) { + err = ixgbe_setup_tx_resources(adapter->xdp_ring[j]); + if (!err) + continue; + + e_err(probe, "Allocation for Tx Queue %u failed\n", j); + goto err_setup_tx; + } return 0; err_setup_tx: /* rewind the index freeing the rings as we go */ + while (j--) + ixgbe_free_tx_resources(adapter->xdp_ring[j]); while (i--) ixgbe_free_tx_resources(adapter->tx_ring[i]); return err; @@ -6066,7 +6259,8 @@ err_setup_tx: * * Returns 0 on success, negative on failure **/ -int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring) +int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring) { struct device *dev = rx_ring->dev; int orig_node = dev_to_node(dev); @@ -6105,6 +6299,8 @@ int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring) rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; + rx_ring->xdp_prog = adapter->xdp_prog; + return 0; err: vfree(rx_ring->rx_buffer_info); @@ -6128,7 +6324,7 @@ static int ixgbe_setup_all_rx_resources(struct ixgbe_adapter *adapter) int i, err = 0; for (i = 0; i < adapter->num_rx_queues; i++) { - err = ixgbe_setup_rx_resources(adapter->rx_ring[i]); + err = ixgbe_setup_rx_resources(adapter, adapter->rx_ring[i]); if (!err) continue; @@ -6184,6 +6380,9 @@ static void ixgbe_free_all_tx_resources(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_tx_queues; i++) if (adapter->tx_ring[i]->desc) ixgbe_free_tx_resources(adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + if (adapter->xdp_ring[i]->desc) + ixgbe_free_tx_resources(adapter->xdp_ring[i]); } /** @@ -6196,6 +6395,7 @@ void ixgbe_free_rx_resources(struct ixgbe_ring *rx_ring) { ixgbe_clean_rx_ring(rx_ring); + rx_ring->xdp_prog = NULL; vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; @@ -6602,6 +6802,14 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) bytes += tx_ring->stats.bytes; packets += tx_ring->stats.packets; } + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i]; + + restart_queue += xdp_ring->tx_stats.restart_queue; + tx_busy += xdp_ring->tx_stats.tx_busy; + bytes += xdp_ring->stats.bytes; + packets += xdp_ring->stats.packets; + } adapter->restart_queue = restart_queue; adapter->tx_busy = tx_busy; netdev->stats.tx_bytes = bytes; @@ -6795,6 +7003,9 @@ static void ixgbe_fdir_reinit_subtask(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_tx_queues; i++) set_bit(__IXGBE_TX_FDIR_INIT_DONE, &(adapter->tx_ring[i]->state)); + for (i = 0; i < adapter->num_xdp_queues; i++) + set_bit(__IXGBE_TX_FDIR_INIT_DONE, + &adapter->xdp_ring[i]->state); /* re-enable flow director interrupts */ IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_FLOW_DIR); } else { @@ -6828,6 +7039,8 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter) if (netif_carrier_ok(adapter->netdev)) { for (i = 0; i < adapter->num_tx_queues; i++) set_check_for_tx_hang(adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + set_check_for_tx_hang(adapter->xdp_ring[i]); } if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { @@ -7058,6 +7271,13 @@ static bool ixgbe_ring_tx_pending(struct ixgbe_adapter *adapter) return true; } + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *ring = adapter->xdp_ring[i]; + + if (ring->next_to_use != ring->next_to_clean) + return true; + } + return false; } @@ -8015,6 +8235,62 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, #endif } +static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, + struct xdp_buff *xdp) +{ + struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; + struct ixgbe_tx_buffer *tx_buffer; + union ixgbe_adv_tx_desc *tx_desc; + u32 len, cmd_type; + dma_addr_t dma; + u16 i; + + len = xdp->data_end - xdp->data; + + if (unlikely(!ixgbe_desc_unused(ring))) + return IXGBE_XDP_CONSUMED; + + dma = dma_map_single(ring->dev, xdp->data, len, DMA_TO_DEVICE); + if (dma_mapping_error(ring->dev, dma)) + return IXGBE_XDP_CONSUMED; + + /* record the location of the first descriptor for this packet */ + tx_buffer = &ring->tx_buffer_info[ring->next_to_use]; + tx_buffer->bytecount = len; + tx_buffer->gso_segs = 1; + tx_buffer->protocol = 0; + + i = ring->next_to_use; + tx_desc = IXGBE_TX_DESC(ring, i); + + dma_unmap_len_set(tx_buffer, len, len); + dma_unmap_addr_set(tx_buffer, dma, dma); + tx_buffer->data = xdp->data; + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + /* put descriptor type bits */ + cmd_type = IXGBE_ADVTXD_DTYP_DATA | + IXGBE_ADVTXD_DCMD_DEXT | + IXGBE_ADVTXD_DCMD_IFCS; + cmd_type |= len | IXGBE_TXD_CMD; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.olinfo_status = + cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT); + + /* Avoid any potential race with xdp_xmit and cleanup */ + smp_wmb(); + + /* set next_to_watch value indicating a packet is present */ + i++; + if (i == ring->count) + i = 0; + + tx_buffer->next_to_watch = tx_desc; + ring->next_to_use = i; + + return IXGBE_XDP_TX; +} + netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, struct ixgbe_adapter *adapter, struct ixgbe_ring *tx_ring) @@ -8306,6 +8582,23 @@ static void ixgbe_netpoll(struct net_device *netdev) #endif +static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats, + struct ixgbe_ring *ring) +{ + u64 bytes, packets; + unsigned int start; + + if (ring) { + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + stats->tx_packets += packets; + stats->tx_bytes += bytes; + } +} + static void ixgbe_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { @@ -8331,18 +8624,13 @@ static void ixgbe_get_stats64(struct net_device *netdev, for (i = 0; i < adapter->num_tx_queues; i++) { struct ixgbe_ring *ring = ACCESS_ONCE(adapter->tx_ring[i]); - u64 bytes, packets; - unsigned int start; - if (ring) { - do { - start = u64_stats_fetch_begin_irq(&ring->syncp); - packets = ring->stats.packets; - bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); - stats->tx_packets += packets; - stats->tx_bytes += bytes; - } + ixgbe_get_ring_stats64(stats, ring); + } + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *ring = ACCESS_ONCE(adapter->xdp_ring[i]); + + ixgbe_get_ring_stats64(stats, ring); } rcu_read_unlock(); @@ -8948,7 +9236,9 @@ static int __ixgbe_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return ixgbe_setup_tc(dev, tc->tc); + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return ixgbe_setup_tc(dev, tc->mqprio->num_tc); } #ifdef CONFIG_PCI_IOV @@ -9459,6 +9749,68 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev, return features; } +static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) +{ + int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct bpf_prog *old_prog; + + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + return -EINVAL; + + if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) + return -EINVAL; + + /* verify ixgbe ring attributes are sufficient for XDP */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *ring = adapter->rx_ring[i]; + + if (ring_is_rsc_enabled(ring)) + return -EINVAL; + + if (frame_size > ixgbe_rx_bufsz(ring)) + return -EINVAL; + } + + if (nr_cpu_ids > MAX_XDP_QUEUES) + return -ENOMEM; + + old_prog = xchg(&adapter->xdp_prog, prog); + + /* If transitioning XDP modes reconfigure rings */ + if (!!prog != !!old_prog) { + int err = ixgbe_setup_tc(dev, netdev_get_num_tc(dev)); + + if (err) { + rcu_assign_pointer(adapter->xdp_prog, old_prog); + return -EINVAL; + } + } else { + for (i = 0; i < adapter->num_rx_queues; i++) + xchg(&adapter->rx_ring[i]->xdp_prog, adapter->xdp_prog); + } + + if (old_prog) + bpf_prog_put(old_prog); + + return 0; +} + +static int ixgbe_xdp(struct net_device *dev, struct netdev_xdp *xdp) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + switch (xdp->command) { + case XDP_SETUP_PROG: + return ixgbe_xdp_setup(dev, xdp->prog); + case XDP_QUERY_PROG: + xdp->prog_attached = !!(adapter->xdp_prog); + return 0; + default: + return -EINVAL; + } +} + static const struct net_device_ops ixgbe_netdev_ops = { .ndo_open = ixgbe_open, .ndo_stop = ixgbe_close, @@ -9504,6 +9856,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_udp_tunnel_add = ixgbe_add_udp_tunnel_port, .ndo_udp_tunnel_del = ixgbe_del_udp_tunnel_port, .ndo_features_check = ixgbe_features_check, + .ndo_xdp = ixgbe_xdp, }; /** @@ -9808,7 +10161,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ixgbe_init_mbx_params_pf(hw); hw->mbx.ops = ii->mbx_ops; pci_sriov_set_totalvfs(pdev, IXGBE_MAX_VFS_DRV_LIMIT); - ixgbe_enable_sriov(adapter); + ixgbe_enable_sriov(adapter, max_vfs); skip_sriov: #endif @@ -9934,6 +10287,9 @@ skip_sriov: if (err) goto err_sw_init; + for (i = 0; i < adapter->num_xdp_queues; i++) + u64_stats_init(&adapter->xdp_ring[i]->syncp); + /* WOL not supported for all devices */ adapter->wol = 0; hw->eeprom.ops.read(hw, 0x2c, &adapter->eeprom_cap); @@ -10059,6 +10415,7 @@ err_sw_init: iounmap(adapter->io_addr); kfree(adapter->jump_tables[0]); kfree(adapter->mac_table); + kfree(adapter->rss_key); err_ioremap: disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); @@ -10143,6 +10500,7 @@ static void ixgbe_remove(struct pci_dev *pdev) } kfree(adapter->mac_table); + kfree(adapter->rss_key); disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); |