diff options
Diffstat (limited to 'drivers/net/ethernet/amazon/ena/ena_netdev.c')
| -rw-r--r-- | drivers/net/ethernet/amazon/ena/ena_netdev.c | 1356 |
1 files changed, 737 insertions, 619 deletions
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 0b2fd96b93d7..d350eeec8bad 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1,33 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* - * Copyright 2015 Amazon.com, Inc. or its affiliates. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. + * Copyright 2015-2020 Amazon.com, Inc. or its affiliates. All rights reserved. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -49,23 +22,17 @@ #include <linux/bpf_trace.h> #include "ena_pci_id_tbl.h" -static char version[] = DEVICE_NAME " v" DRV_MODULE_VERSION "\n"; - MODULE_AUTHOR("Amazon.com, Inc. or its affiliates"); MODULE_DESCRIPTION(DEVICE_NAME); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_MODULE_VERSION); /* Time in jiffies before concluding the transmitter is hung. */ #define TX_TIMEOUT (5 * HZ) -#define ENA_NAPI_BUDGET 64 +#define ENA_MAX_RINGS min_t(unsigned int, ENA_MAX_NUM_IO_QUEUES, num_possible_cpus()) #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | \ NETIF_MSG_TX_DONE | NETIF_MSG_TX_ERR | NETIF_MSG_RX_ERR) -static int debug = -1; -module_param(debug, int, 0); -MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); static struct ena_aenq_handlers aenq_handlers; @@ -108,6 +75,21 @@ static void ena_unmap_tx_buff(struct ena_ring *tx_ring, static int ena_create_io_tx_queues_in_range(struct ena_adapter *adapter, int first_index, int count); +/* Increase a stat by cnt while holding syncp seqlock on 32bit machines */ +static void ena_increase_stat(u64 *statp, u64 cnt, + struct u64_stats_sync *syncp) +{ + u64_stats_update_begin(syncp); + (*statp) += cnt; + u64_stats_update_end(syncp); +} + +static void ena_ring_tx_doorbell(struct ena_ring *tx_ring) +{ + ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq); + ena_increase_stat(&tx_ring->tx_stats.doorbells, 1, &tx_ring->syncp); +} + static void ena_tx_timeout(struct net_device *dev, unsigned int txqueue) { struct ena_adapter *adapter = netdev_priv(dev); @@ -119,10 +101,8 @@ static void ena_tx_timeout(struct net_device *dev, unsigned int txqueue) if (test_and_set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags)) return; - adapter->reset_reason = ENA_REGS_RESET_OS_NETDEV_WD; - u64_stats_update_begin(&adapter->syncp); - adapter->dev_stats.tx_timeout++; - u64_stats_update_end(&adapter->syncp); + ena_reset_device(adapter, ENA_REGS_RESET_OS_NETDEV_WD); + ena_increase_stat(&adapter->dev_stats.tx_timeout, 1, &adapter->syncp); netif_err(adapter, tx_err, dev, "Transmit time out\n"); } @@ -142,7 +122,7 @@ static int ena_change_mtu(struct net_device *dev, int new_mtu) ret = ena_com_set_dev_mtu(adapter->ena_dev, new_mtu); if (!ret) { - netif_dbg(adapter, drv, dev, "set MTU to %d\n", new_mtu); + netif_dbg(adapter, drv, dev, "Set MTU to %d\n", new_mtu); update_rx_ring_mtu(adapter, new_mtu); dev->mtu = new_mtu; } else { @@ -168,7 +148,7 @@ static int ena_xmit_common(struct net_device *dev, netif_dbg(adapter, tx_queued, dev, "llq tx max burst size of queue %d achieved, writing doorbell to send burst\n", ring->qid); - ena_com_write_sq_doorbell(ring->ena_com_io_sq); + ena_ring_tx_doorbell(ring); } /* prepare the packet's descriptors to dma engine */ @@ -181,15 +161,12 @@ static int ena_xmit_common(struct net_device *dev, */ if (unlikely(rc)) { netif_err(adapter, tx_queued, dev, - "failed to prepare tx bufs\n"); - u64_stats_update_begin(&ring->syncp); - ring->tx_stats.prepare_ctx_err++; - u64_stats_update_end(&ring->syncp); - if (rc != -ENOMEM) { - adapter->reset_reason = - ENA_REGS_RESET_DRIVER_INVALID_STATE; - set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); - } + "Failed to prepare tx bufs\n"); + ena_increase_stat(&ring->tx_stats.prepare_ctx_err, 1, + &ring->syncp); + if (rc != -ENOMEM) + ena_reset_device(adapter, + ENA_REGS_RESET_DRIVER_INVALID_STATE); return rc; } @@ -219,7 +196,6 @@ static int ena_xdp_io_poll(struct napi_struct *napi, int budget) int ret; xdp_ring = ena_napi->xdp_ring; - xdp_ring->first_interrupt = ena_napi->first_interrupt; xdp_budget = budget; @@ -251,125 +227,159 @@ static int ena_xdp_io_poll(struct napi_struct *napi, int budget) xdp_ring->tx_stats.napi_comp += napi_comp_call; xdp_ring->tx_stats.tx_poll++; u64_stats_update_end(&xdp_ring->syncp); + xdp_ring->tx_stats.last_napi_jiffies = jiffies; return ret; } -static int ena_xdp_tx_map_buff(struct ena_ring *xdp_ring, - struct ena_tx_buffer *tx_info, - struct xdp_buff *xdp, - void **push_hdr, - u32 *push_len) +static int ena_xdp_tx_map_frame(struct ena_ring *xdp_ring, + struct ena_tx_buffer *tx_info, + struct xdp_frame *xdpf, + struct ena_com_tx_ctx *ena_tx_ctx) { struct ena_adapter *adapter = xdp_ring->adapter; struct ena_com_buf *ena_buf; - dma_addr_t dma = 0; + int push_len = 0; + dma_addr_t dma; + void *data; u32 size; - tx_info->xdpf = convert_to_xdp_frame(xdp); + tx_info->xdpf = xdpf; + data = tx_info->xdpf->data; size = tx_info->xdpf->len; - ena_buf = tx_info->bufs; - /* llq push buffer */ - *push_len = min_t(u32, size, xdp_ring->tx_max_header_size); - *push_hdr = tx_info->xdpf->data; + if (xdp_ring->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) { + /* Designate part of the packet for LLQ */ + push_len = min_t(u32, size, xdp_ring->tx_max_header_size); + + ena_tx_ctx->push_header = data; + + size -= push_len; + data += push_len; + } + + ena_tx_ctx->header_len = push_len; - if (size - *push_len > 0) { + if (size > 0) { dma = dma_map_single(xdp_ring->dev, - *push_hdr + *push_len, - size - *push_len, + data, + size, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(xdp_ring->dev, dma))) goto error_report_dma_error; - tx_info->map_linear_data = 1; - tx_info->num_of_bufs = 1; - } + tx_info->map_linear_data = 0; - ena_buf->paddr = dma; - ena_buf->len = size; + ena_buf = tx_info->bufs; + ena_buf->paddr = dma; + ena_buf->len = size; + + ena_tx_ctx->ena_bufs = ena_buf; + ena_tx_ctx->num_bufs = tx_info->num_of_bufs = 1; + } return 0; error_report_dma_error: - u64_stats_update_begin(&xdp_ring->syncp); - xdp_ring->tx_stats.dma_mapping_err++; - u64_stats_update_end(&xdp_ring->syncp); - netdev_warn(adapter->netdev, "failed to map xdp buff\n"); - - xdp_return_frame_rx_napi(tx_info->xdpf); - tx_info->xdpf = NULL; - tx_info->num_of_bufs = 0; + ena_increase_stat(&xdp_ring->tx_stats.dma_mapping_err, 1, + &xdp_ring->syncp); + netif_warn(adapter, tx_queued, adapter->netdev, "Failed to map xdp buff\n"); return -EINVAL; } -static int ena_xdp_xmit_buff(struct net_device *dev, - struct xdp_buff *xdp, - int qid, - struct ena_rx_buffer *rx_info) +static int ena_xdp_xmit_frame(struct ena_ring *xdp_ring, + struct net_device *dev, + struct xdp_frame *xdpf, + int flags) { - struct ena_adapter *adapter = netdev_priv(dev); - struct ena_com_tx_ctx ena_tx_ctx = {0}; + struct ena_com_tx_ctx ena_tx_ctx = {}; struct ena_tx_buffer *tx_info; - struct ena_ring *xdp_ring; u16 next_to_use, req_id; int rc; - void *push_hdr; - u32 push_len; - xdp_ring = &adapter->tx_ring[qid]; next_to_use = xdp_ring->next_to_use; req_id = xdp_ring->free_ids[next_to_use]; tx_info = &xdp_ring->tx_buffer_info[req_id]; tx_info->num_of_bufs = 0; - page_ref_inc(rx_info->page); - tx_info->xdp_rx_page = rx_info->page; - rc = ena_xdp_tx_map_buff(xdp_ring, tx_info, xdp, &push_hdr, &push_len); + rc = ena_xdp_tx_map_frame(xdp_ring, tx_info, xdpf, &ena_tx_ctx); if (unlikely(rc)) - goto error_drop_packet; + return rc; - ena_tx_ctx.ena_bufs = tx_info->bufs; - ena_tx_ctx.push_header = push_hdr; - ena_tx_ctx.num_bufs = tx_info->num_of_bufs; ena_tx_ctx.req_id = req_id; - ena_tx_ctx.header_len = push_len; rc = ena_xmit_common(dev, xdp_ring, tx_info, &ena_tx_ctx, next_to_use, - xdp->data_end - xdp->data); + xdpf->len); if (rc) goto error_unmap_dma; - /* trigger the dma engine. ena_com_write_sq_doorbell() - * has a mb + + /* trigger the dma engine. ena_ring_tx_doorbell() + * calls a memory barrier inside it. */ - ena_com_write_sq_doorbell(xdp_ring->ena_com_io_sq); - u64_stats_update_begin(&xdp_ring->syncp); - xdp_ring->tx_stats.doorbells++; - u64_stats_update_end(&xdp_ring->syncp); + if (flags & XDP_XMIT_FLUSH) + ena_ring_tx_doorbell(xdp_ring); - return NETDEV_TX_OK; + return rc; error_unmap_dma: ena_unmap_tx_buff(xdp_ring, tx_info); tx_info->xdpf = NULL; -error_drop_packet: + return rc; +} - return NETDEV_TX_OK; +static int ena_xdp_xmit(struct net_device *dev, int n, + struct xdp_frame **frames, u32 flags) +{ + struct ena_adapter *adapter = netdev_priv(dev); + struct ena_ring *xdp_ring; + int qid, i, nxmit = 0; + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + return -EINVAL; + + if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags)) + return -ENETDOWN; + + /* We assume that all rings have the same XDP program */ + if (!READ_ONCE(adapter->rx_ring->xdp_bpf_prog)) + return -ENXIO; + + qid = smp_processor_id() % adapter->xdp_num_queues; + qid += adapter->xdp_first_ring; + xdp_ring = &adapter->tx_ring[qid]; + + /* Other CPU ids might try to send thorugh this queue */ + spin_lock(&xdp_ring->xdp_tx_lock); + + for (i = 0; i < n; i++) { + if (ena_xdp_xmit_frame(xdp_ring, dev, frames[i], 0)) + break; + nxmit++; + } + + /* Ring doorbell to make device aware of the packets */ + if (flags & XDP_XMIT_FLUSH) + ena_ring_tx_doorbell(xdp_ring); + + spin_unlock(&xdp_ring->xdp_tx_lock); + + /* Return number of packets sent */ + return nxmit; } -static int ena_xdp_execute(struct ena_ring *rx_ring, - struct xdp_buff *xdp, - struct ena_rx_buffer *rx_info) +static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp) { struct bpf_prog *xdp_prog; + struct ena_ring *xdp_ring; u32 verdict = XDP_PASS; + struct xdp_frame *xdpf; + u64 *xdp_stat; - rcu_read_lock(); xdp_prog = READ_ONCE(rx_ring->xdp_bpf_prog); if (!xdp_prog) @@ -377,17 +387,55 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, verdict = bpf_prog_run_xdp(xdp_prog, xdp); - if (verdict == XDP_TX) - ena_xdp_xmit_buff(rx_ring->netdev, - xdp, - rx_ring->qid + rx_ring->adapter->num_io_queues, - rx_info); - else if (unlikely(verdict == XDP_ABORTED)) + switch (verdict) { + case XDP_TX: + xdpf = xdp_convert_buff_to_frame(xdp); + if (unlikely(!xdpf)) { + trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict); + xdp_stat = &rx_ring->rx_stats.xdp_aborted; + verdict = XDP_ABORTED; + break; + } + + /* Find xmit queue */ + xdp_ring = rx_ring->xdp_ring; + + /* The XDP queues are shared between XDP_TX and XDP_REDIRECT */ + spin_lock(&xdp_ring->xdp_tx_lock); + + if (ena_xdp_xmit_frame(xdp_ring, rx_ring->netdev, xdpf, + XDP_XMIT_FLUSH)) + xdp_return_frame(xdpf); + + spin_unlock(&xdp_ring->xdp_tx_lock); + xdp_stat = &rx_ring->rx_stats.xdp_tx; + break; + case XDP_REDIRECT: + if (likely(!xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog))) { + xdp_stat = &rx_ring->rx_stats.xdp_redirect; + break; + } + trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict); + xdp_stat = &rx_ring->rx_stats.xdp_aborted; + verdict = XDP_ABORTED; + break; + case XDP_ABORTED: trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict); - else if (unlikely(verdict > XDP_TX)) - bpf_warn_invalid_xdp_action(verdict); + xdp_stat = &rx_ring->rx_stats.xdp_aborted; + break; + case XDP_DROP: + xdp_stat = &rx_ring->rx_stats.xdp_drop; + break; + case XDP_PASS: + xdp_stat = &rx_ring->rx_stats.xdp_pass; + break; + default: + bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, verdict); + xdp_stat = &rx_ring->rx_stats.xdp_invalid; + } + + ena_increase_stat(xdp_stat, 1, &rx_ring->syncp); out: - rcu_read_unlock(); return verdict; } @@ -431,7 +479,7 @@ static int ena_xdp_register_rxq_info(struct ena_ring *rx_ring) { int rc; - rc = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, rx_ring->qid); + rc = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, rx_ring->qid, 0); if (rc) { netif_err(rx_ring->adapter, ifup, rx_ring->netdev, @@ -460,10 +508,9 @@ static void ena_xdp_unregister_rxq_info(struct ena_ring *rx_ring) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); } -void ena_xdp_exchange_program_rx_in_range(struct ena_adapter *adapter, - struct bpf_prog *prog, - int first, - int count) +static void ena_xdp_exchange_program_rx_in_range(struct ena_adapter *adapter, + struct bpf_prog *prog, + int first, int count) { struct ena_ring *rx_ring; int i = 0; @@ -476,13 +523,13 @@ void ena_xdp_exchange_program_rx_in_range(struct ena_adapter *adapter, rx_ring->rx_headroom = XDP_PACKET_HEADROOM; } else { ena_xdp_unregister_rxq_info(rx_ring); - rx_ring->rx_headroom = 0; + rx_ring->rx_headroom = NET_SKB_PAD; } } } -void ena_xdp_exchange_program(struct ena_adapter *adapter, - struct bpf_prog *prog) +static void ena_xdp_exchange_program(struct ena_adapter *adapter, + struct bpf_prog *prog) { struct bpf_prog *old_bpf_prog = xchg(&adapter->xdp_bpf_prog, prog); @@ -553,7 +600,7 @@ static int ena_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf) if (!old_bpf_prog) netif_info(adapter, drv, adapter->netdev, - "xdp program set, changing the max_mtu from %d to %d", + "XDP program is set, changing the max_mtu from %d to %d", prev_mtu, netdev->max_mtu); } else if (rc == ENA_XDP_CURRENT_MTU_TOO_LARGE) { @@ -580,15 +627,9 @@ static int ena_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf) */ static int ena_xdp(struct net_device *netdev, struct netdev_bpf *bpf) { - struct ena_adapter *adapter = netdev_priv(netdev); - switch (bpf->command) { case XDP_SETUP_PROG: return ena_xdp_set(netdev, bpf); - case XDP_QUERY_PROG: - bpf->prog_id = adapter->xdp_bpf_prog ? - adapter->xdp_bpf_prog->aux->id : 0; - break; default: return -EINVAL; } @@ -631,7 +672,6 @@ static void ena_init_io_rings_common(struct ena_adapter *adapter, ring->ena_dev = adapter->ena_dev; ring->per_napi_packets = 0; ring->cpu = 0; - ring->first_interrupt = false; ring->no_interrupt_event_cnt = 0; u64_stats_init(&ring->syncp); } @@ -659,6 +699,8 @@ static void ena_init_io_rings(struct ena_adapter *adapter, txr->sgl_size = adapter->max_tx_sgl_size; txr->smoothed_interval = ena_com_get_nonadaptive_moderation_interval_tx(ena_dev); + txr->disable_meta_caching = adapter->disable_meta_caching; + spin_lock_init(&txr->xdp_tx_lock); /* Don't init RX queues for xdp queues */ if (!ENA_IS_XDP_INDEX(adapter, i)) { @@ -672,7 +714,9 @@ static void ena_init_io_rings(struct ena_adapter *adapter, rxr->smoothed_interval = ena_com_get_nonadaptive_moderation_interval_rx(ena_dev); rxr->empty_rx_queue = 0; + rxr->rx_headroom = NET_SKB_PAD; adapter->ena_napi[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; + rxr->xdp_ring = &adapter->tx_ring[i + adapter->num_io_queues]; } } } @@ -810,24 +854,6 @@ static void ena_free_all_io_tx_resources(struct ena_adapter *adapter) adapter->num_io_queues); } -static int validate_rx_req_id(struct ena_ring *rx_ring, u16 req_id) -{ - if (likely(req_id < rx_ring->ring_size)) - return 0; - - netif_err(rx_ring->adapter, rx_err, rx_ring->netdev, - "Invalid rx req_id: %hu\n", req_id); - - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.bad_req_id++; - u64_stats_update_end(&rx_ring->syncp); - - /* Trigger device reset */ - rx_ring->adapter->reset_reason = ENA_REGS_RESET_INV_RX_REQ_ID; - set_bit(ENA_FLAG_TRIGGER_RESET, &rx_ring->adapter->flags); - return -EFAULT; -} - /* ena_setup_rx_resources - allocate I/O Rx resources (Descriptors) * @adapter: network interface device structure * @qid: queue index @@ -944,52 +970,84 @@ static void ena_free_all_io_rx_resources(struct ena_adapter *adapter) ena_free_rx_resources(adapter, i); } -static int ena_alloc_rx_page(struct ena_ring *rx_ring, - struct ena_rx_buffer *rx_info, gfp_t gfp) +static struct page *ena_alloc_map_page(struct ena_ring *rx_ring, + dma_addr_t *dma) { + struct page *page; + + /* This would allocate the page on the same NUMA node the executing code + * is running on. + */ + page = dev_alloc_page(); + if (!page) { + ena_increase_stat(&rx_ring->rx_stats.page_alloc_fail, 1, + &rx_ring->syncp); + return ERR_PTR(-ENOSPC); + } + + /* To enable NIC-side port-mirroring, AKA SPAN port, + * we make the buffer readable from the nic as well + */ + *dma = dma_map_page(rx_ring->dev, page, 0, ENA_PAGE_SIZE, + DMA_BIDIRECTIONAL); + if (unlikely(dma_mapping_error(rx_ring->dev, *dma))) { + ena_increase_stat(&rx_ring->rx_stats.dma_mapping_err, 1, + &rx_ring->syncp); + __free_page(page); + return ERR_PTR(-EIO); + } + + return page; +} + +static int ena_alloc_rx_buffer(struct ena_ring *rx_ring, + struct ena_rx_buffer *rx_info) +{ + int headroom = rx_ring->rx_headroom; struct ena_com_buf *ena_buf; struct page *page; dma_addr_t dma; + int tailroom; + + /* restore page offset value in case it has been changed by device */ + rx_info->page_offset = headroom; /* if previous allocated page is not used */ if (unlikely(rx_info->page)) return 0; - page = alloc_page(gfp); - if (unlikely(!page)) { - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.page_alloc_fail++; - u64_stats_update_end(&rx_ring->syncp); - return -ENOMEM; - } + /* We handle DMA here */ + page = ena_alloc_map_page(rx_ring, &dma); + if (unlikely(IS_ERR(page))) + return PTR_ERR(page); - dma = dma_map_page(rx_ring->dev, page, 0, ENA_PAGE_SIZE, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(rx_ring->dev, dma))) { - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.dma_mapping_err++; - u64_stats_update_end(&rx_ring->syncp); - - __free_page(page); - return -EIO; - } netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, - "alloc page %p, rx_info %p\n", page, rx_info); + "Allocate page %p, rx_info %p\n", page, rx_info); + + tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); rx_info->page = page; - rx_info->page_offset = 0; ena_buf = &rx_info->ena_buf; - ena_buf->paddr = dma + rx_ring->rx_headroom; - ena_buf->len = ENA_PAGE_SIZE - rx_ring->rx_headroom; + ena_buf->paddr = dma + headroom; + ena_buf->len = ENA_PAGE_SIZE - headroom - tailroom; return 0; } +static void ena_unmap_rx_buff(struct ena_ring *rx_ring, + struct ena_rx_buffer *rx_info) +{ + struct ena_com_buf *ena_buf = &rx_info->ena_buf; + + dma_unmap_page(rx_ring->dev, ena_buf->paddr - rx_ring->rx_headroom, + ENA_PAGE_SIZE, + DMA_BIDIRECTIONAL); +} + static void ena_free_rx_page(struct ena_ring *rx_ring, struct ena_rx_buffer *rx_info) { struct page *page = rx_info->page; - struct ena_com_buf *ena_buf = &rx_info->ena_buf; if (unlikely(!page)) { netif_warn(rx_ring->adapter, rx_err, rx_ring->netdev, @@ -997,10 +1055,7 @@ static void ena_free_rx_page(struct ena_ring *rx_ring, return; } - dma_unmap_page(rx_ring->dev, - ena_buf->paddr - rx_ring->rx_headroom, - ENA_PAGE_SIZE, - DMA_FROM_DEVICE); + ena_unmap_rx_buff(rx_ring, rx_info); __free_page(page); rx_info->page = NULL; @@ -1018,18 +1073,13 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num) struct ena_rx_buffer *rx_info; req_id = rx_ring->free_ids[next_to_use]; - rc = validate_rx_req_id(rx_ring, req_id); - if (unlikely(rc < 0)) - break; rx_info = &rx_ring->rx_buffer_info[req_id]; - - rc = ena_alloc_rx_page(rx_ring, rx_info, - GFP_ATOMIC | __GFP_COMP); + rc = ena_alloc_rx_buffer(rx_ring, rx_info); if (unlikely(rc < 0)) { netif_warn(rx_ring->adapter, rx_err, rx_ring->netdev, - "failed to alloc buffer for rx queue %d\n", + "Failed to allocate buffer for rx queue %d\n", rx_ring->qid); break; } @@ -1038,7 +1088,7 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num) req_id); if (unlikely(rc)) { netif_warn(rx_ring->adapter, rx_status, rx_ring->netdev, - "failed to add buffer for rx queue %d\n", + "Failed to add buffer for rx queue %d\n", rx_ring->qid); break; } @@ -1047,12 +1097,11 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num) } if (unlikely(i < num)) { - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.refil_partial++; - u64_stats_update_end(&rx_ring->syncp); - netdev_warn(rx_ring->netdev, - "refilled rx qid %d with only %d buffers (from %d)\n", - rx_ring->qid, i, num); + ena_increase_stat(&rx_ring->rx_stats.refil_partial, 1, + &rx_ring->syncp); + netif_warn(rx_ring->adapter, rx_err, rx_ring->netdev, + "Refilled rx qid %d with only %d buffers (from %d)\n", + rx_ring->qid, i, num); } /* ena_com_write_sq_doorbell issues a wmb() */ @@ -1093,7 +1142,7 @@ static void ena_refill_all_rx_bufs(struct ena_adapter *adapter) if (unlikely(rc != bufs_num)) netif_warn(rx_ring->adapter, rx_status, rx_ring->netdev, - "refilling Queue %d failed. allocated %d buffers from: %d\n", + "Refilling Queue %d failed. allocated %d buffers from: %d\n", i, rc, bufs_num); } } @@ -1151,14 +1200,14 @@ static void ena_free_tx_bufs(struct ena_ring *tx_ring) continue; if (print_once) { - netdev_notice(tx_ring->netdev, - "free uncompleted tx skb qid %d idx 0x%x\n", - tx_ring->qid, i); + netif_notice(tx_ring->adapter, ifdown, tx_ring->netdev, + "Free uncompleted tx skb qid %d idx 0x%x\n", + tx_ring->qid, i); print_once = false; } else { - netdev_dbg(tx_ring->netdev, - "free uncompleted tx skb qid %d idx 0x%x\n", - tx_ring->qid, i); + netif_dbg(tx_ring->adapter, ifdown, tx_ring->netdev, + "Free uncompleted tx skb qid %d idx 0x%x\n", + tx_ring->qid, i); } ena_unmap_tx_buff(tx_ring, tx_info); @@ -1216,47 +1265,39 @@ static int handle_invalid_req_id(struct ena_ring *ring, u16 req_id, netif_err(ring->adapter, tx_done, ring->netdev, - "tx_info doesn't have valid %s", - is_xdp ? "xdp frame" : "skb"); + "tx_info doesn't have valid %s. qid %u req_id %u", + is_xdp ? "xdp frame" : "skb", ring->qid, req_id); else netif_err(ring->adapter, tx_done, ring->netdev, - "Invalid req_id: %hu\n", - req_id); + "Invalid req_id %u in qid %u\n", + req_id, ring->qid); - u64_stats_update_begin(&ring->syncp); - ring->tx_stats.bad_req_id++; - u64_stats_update_end(&ring->syncp); + ena_increase_stat(&ring->tx_stats.bad_req_id, 1, &ring->syncp); + ena_reset_device(ring->adapter, ENA_REGS_RESET_INV_TX_REQ_ID); - /* Trigger device reset */ - ring->adapter->reset_reason = ENA_REGS_RESET_INV_TX_REQ_ID; - set_bit(ENA_FLAG_TRIGGER_RESET, &ring->adapter->flags); return -EFAULT; } static int validate_tx_req_id(struct ena_ring *tx_ring, u16 req_id) { - struct ena_tx_buffer *tx_info = NULL; + struct ena_tx_buffer *tx_info; - if (likely(req_id < tx_ring->ring_size)) { - tx_info = &tx_ring->tx_buffer_info[req_id]; - if (likely(tx_info->skb)) - return 0; - } + tx_info = &tx_ring->tx_buffer_info[req_id]; + if (likely(tx_info->skb)) + return 0; return handle_invalid_req_id(tx_ring, req_id, tx_info, false); } static int validate_xdp_req_id(struct ena_ring *xdp_ring, u16 req_id) { - struct ena_tx_buffer *tx_info = NULL; + struct ena_tx_buffer *tx_info; - if (likely(req_id < xdp_ring->ring_size)) { - tx_info = &xdp_ring->tx_buffer_info[req_id]; - if (likely(tx_info->xdpf)) - return 0; - } + tx_info = &xdp_ring->tx_buffer_info[req_id]; + if (likely(tx_info->xdpf)) + return 0; return handle_invalid_req_id(xdp_ring, req_id, tx_info, true); } @@ -1281,9 +1322,14 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget) rc = ena_com_tx_comp_req_id_get(tx_ring->ena_com_io_cq, &req_id); - if (rc) + if (rc) { + if (unlikely(rc == -EINVAL)) + handle_invalid_req_id(tx_ring, req_id, NULL, + false); break; + } + /* validate that the request id points to a valid skb */ rc = validate_tx_req_id(tx_ring, req_id); if (rc) break; @@ -1338,9 +1384,8 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget) if (netif_tx_queue_stopped(txq) && above_thresh && test_bit(ENA_FLAG_DEV_UP, &tx_ring->adapter->flags)) { netif_tx_wake_queue(txq); - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->tx_stats.queue_wakeup++; - u64_stats_update_end(&tx_ring->syncp); + ena_increase_stat(&tx_ring->tx_stats.queue_wakeup, 1, + &tx_ring->syncp); } __netif_tx_unlock(txq); } @@ -1348,22 +1393,22 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget) return tx_pkts; } -static struct sk_buff *ena_alloc_skb(struct ena_ring *rx_ring, bool frags) +static struct sk_buff *ena_alloc_skb(struct ena_ring *rx_ring, void *first_frag) { struct sk_buff *skb; - if (frags) - skb = napi_get_frags(rx_ring->napi); + if (!first_frag) + skb = napi_alloc_skb(rx_ring->napi, rx_ring->rx_copybreak); else - skb = netdev_alloc_skb_ip_align(rx_ring->netdev, - rx_ring->rx_copybreak); + skb = napi_build_skb(first_frag, ENA_PAGE_SIZE); if (unlikely(!skb)) { - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.skb_alloc_fail++; - u64_stats_update_end(&rx_ring->syncp); + ena_increase_stat(&rx_ring->rx_stats.skb_alloc_fail, 1, + &rx_ring->syncp); + netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev, - "Failed to allocate skb. frags: %d\n", frags); + "Failed to allocate skb. first_frag %s\n", + first_frag ? "provided" : "not provided"); return NULL; } @@ -1375,18 +1420,25 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, u32 descs, u16 *next_to_clean) { - struct sk_buff *skb; struct ena_rx_buffer *rx_info; + struct ena_adapter *adapter; u16 len, req_id, buf = 0; - void *va; + struct sk_buff *skb; + void *page_addr; + u32 page_offset; + void *data_addr; len = ena_bufs[buf].len; req_id = ena_bufs[buf].req_id; + rx_info = &rx_ring->rx_buffer_info[req_id]; if (unlikely(!rx_info->page)) { - netif_err(rx_ring->adapter, rx_err, rx_ring->netdev, - "Page is NULL\n"); + adapter = rx_ring->adapter; + netif_err(adapter, rx_err, rx_ring->netdev, + "Page is NULL. qid %u req_id %u\n", rx_ring->qid, req_id); + ena_increase_stat(&rx_ring->rx_stats.bad_req_id, 1, &rx_ring->syncp); + ena_reset_device(adapter, ENA_REGS_RESET_INV_RX_REQ_ID); return NULL; } @@ -1395,16 +1447,19 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, rx_info, rx_info->page); /* save virt address of first buffer */ - va = page_address(rx_info->page) + rx_info->page_offset; - prefetch(va + NET_IP_ALIGN); + page_addr = page_address(rx_info->page); + page_offset = rx_info->page_offset; + data_addr = page_addr + page_offset; + + prefetch(data_addr); if (len <= rx_ring->rx_copybreak) { - skb = ena_alloc_skb(rx_ring, false); + skb = ena_alloc_skb(rx_ring, NULL); if (unlikely(!skb)) return NULL; netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, - "rx allocated small packet. len %d. data_len %d\n", + "RX allocated small packet. len %d. data_len %d\n", skb->len, skb->data_len); /* sync this buffer for CPU use */ @@ -1412,7 +1467,7 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, dma_unmap_addr(&rx_info->ena_buf, paddr), len, DMA_FROM_DEVICE); - skb_copy_to_linear_data(skb, va, len); + skb_copy_to_linear_data(skb, data_addr, len); dma_sync_single_for_device(rx_ring->dev, dma_unmap_addr(&rx_info->ena_buf, paddr), len, @@ -1426,20 +1481,20 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, return skb; } - skb = ena_alloc_skb(rx_ring, true); + ena_unmap_rx_buff(rx_ring, rx_info); + + skb = ena_alloc_skb(rx_ring, page_addr); if (unlikely(!skb)) return NULL; - do { - dma_unmap_page(rx_ring->dev, - dma_unmap_addr(&rx_info->ena_buf, paddr), - ENA_PAGE_SIZE, DMA_FROM_DEVICE); - - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page, - rx_info->page_offset, len, ENA_PAGE_SIZE); + /* Populate skb's linear part */ + skb_reserve(skb, page_offset); + skb_put(skb, len); + skb->protocol = eth_type_trans(skb, rx_ring->netdev); + do { netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, - "rx skb updated. len %d. data_len %d\n", + "RX skb updated. len %d. data_len %d\n", skb->len, skb->data_len); rx_info->page = NULL; @@ -1454,7 +1509,14 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, buf++; len = ena_bufs[buf].len; req_id = ena_bufs[buf].req_id; + rx_info = &rx_ring->rx_buffer_info[req_id]; + + ena_unmap_rx_buff(rx_ring, rx_info); + + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page, + rx_info->page_offset, len, ENA_PAGE_SIZE); + } while (1); return skb; @@ -1486,9 +1548,8 @@ static void ena_rx_checksum(struct ena_ring *rx_ring, (ena_rx_ctx->l3_csum_err))) { /* ipv4 checksum error */ skb->ip_summed = CHECKSUM_NONE; - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.bad_csum++; - u64_stats_update_end(&rx_ring->syncp); + ena_increase_stat(&rx_ring->rx_stats.csum_bad, 1, + &rx_ring->syncp); netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev, "RX IPv4 header checksum error\n"); return; @@ -1499,9 +1560,8 @@ static void ena_rx_checksum(struct ena_ring *rx_ring, (ena_rx_ctx->l4_proto == ENA_ETH_IO_L4_PROTO_UDP))) { if (unlikely(ena_rx_ctx->l4_csum_err)) { /* TCP/UDP checksum error */ - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.bad_csum++; - u64_stats_update_end(&rx_ring->syncp); + ena_increase_stat(&rx_ring->rx_stats.csum_bad, 1, + &rx_ring->syncp); netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev, "RX L4 checksum error\n"); skb->ip_summed = CHECKSUM_NONE; @@ -1510,13 +1570,11 @@ static void ena_rx_checksum(struct ena_ring *rx_ring, if (likely(ena_rx_ctx->l4_csum_checked)) { skb->ip_summed = CHECKSUM_UNNECESSARY; - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.csum_good++; - u64_stats_update_end(&rx_ring->syncp); + ena_increase_stat(&rx_ring->rx_stats.csum_good, 1, + &rx_ring->syncp); } else { - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.csum_unchecked++; - u64_stats_update_end(&rx_ring->syncp); + ena_increase_stat(&rx_ring->rx_stats.csum_unchecked, 1, + &rx_ring->syncp); skb->ip_summed = CHECKSUM_NONE; } } else { @@ -1548,24 +1606,22 @@ static void ena_set_rx_hash(struct ena_ring *rx_ring, } } -int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp) +static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp) { struct ena_rx_buffer *rx_info; int ret; rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]; - xdp->data = page_address(rx_info->page) + - rx_info->page_offset + rx_ring->rx_headroom; - xdp_set_data_meta_invalid(xdp); - xdp->data_hard_start = page_address(rx_info->page); - xdp->data_end = xdp->data + rx_ring->ena_bufs[0].len; + xdp_prepare_buff(xdp, page_address(rx_info->page), + rx_info->page_offset, + rx_ring->ena_bufs[0].len, false); /* If for some reason we received a bigger packet than * we expect, then we simply drop it */ if (unlikely(rx_ring->ena_bufs[0].len > ENA_XDP_MAX_MTU)) return XDP_DROP; - ret = ena_xdp_execute(rx_ring, xdp, rx_info); + ret = ena_xdp_execute(rx_ring, xdp); /* The xdp program might expand the headers */ if (ret == XDP_PASS) { @@ -1587,6 +1643,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, { u16 next_to_clean = rx_ring->next_to_clean; struct ena_com_rx_ctx ena_rx_ctx; + struct ena_rx_buffer *rx_info; struct ena_adapter *adapter; u32 res_budget, work_done; int rx_copybreak_pkt = 0; @@ -1594,6 +1651,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, struct sk_buff *skb; int refill_required; struct xdp_buff xdp; + int xdp_flags = 0; int total_len = 0; int xdp_verdict; int rc = 0; @@ -1602,7 +1660,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "%s qid %d\n", __func__, rx_ring->qid); res_budget = budget; - xdp.rxq = &rx_ring->xdp_rxq; + xdp_init_buff(&xdp, ENA_PAGE_SIZE, &rx_ring->xdp_rxq); do { xdp_verdict = XDP_PASS; @@ -1610,6 +1668,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, ena_rx_ctx.ena_bufs = rx_ring->ena_bufs; ena_rx_ctx.max_bufs = rx_ring->sgl_size; ena_rx_ctx.descs = 0; + ena_rx_ctx.pkt_offset = 0; rc = ena_com_rx_pkt(rx_ring->ena_com_io_cq, rx_ring->ena_com_io_sq, &ena_rx_ctx); @@ -1619,6 +1678,10 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, if (unlikely(ena_rx_ctx.descs == 0)) break; + /* First descriptor might have an offset set by the device */ + rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]; + rx_info->page_offset += ena_rx_ctx.pkt_offset; + netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "rx_poll: q %d got packet from ena. descs #: %d l3 proto %d l4 proto %d hash: %x\n", rx_ring->qid, ena_rx_ctx.descs, ena_rx_ctx.l3_proto, @@ -1635,20 +1698,28 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, &next_to_clean); if (unlikely(!skb)) { - if (xdp_verdict == XDP_TX) { - ena_free_rx_page(rx_ring, - &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]); - res_budget--; - } for (i = 0; i < ena_rx_ctx.descs; i++) { - rx_ring->free_ids[next_to_clean] = - rx_ring->ena_bufs[i].req_id; + int req_id = rx_ring->ena_bufs[i].req_id; + + rx_ring->free_ids[next_to_clean] = req_id; next_to_clean = ENA_RX_RING_IDX_NEXT(next_to_clean, rx_ring->ring_size); + + /* Packets was passed for transmission, unmap it + * from RX side. + */ + if (xdp_verdict == XDP_TX || xdp_verdict == XDP_REDIRECT) { + ena_unmap_rx_buff(rx_ring, + &rx_ring->rx_buffer_info[req_id]); + rx_ring->rx_buffer_info[req_id].page = NULL; + } } - if (xdp_verdict == XDP_TX || xdp_verdict == XDP_DROP) + if (xdp_verdict != XDP_PASS) { + xdp_flags |= xdp_verdict; + res_budget--; continue; + } break; } @@ -1658,14 +1729,12 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, skb_record_rx_queue(skb, rx_ring->qid); - if (rx_ring->ena_bufs[0].len <= rx_ring->rx_copybreak) { - total_len += rx_ring->ena_bufs[0].len; + if (rx_ring->ena_bufs[0].len <= rx_ring->rx_copybreak) rx_copybreak_pkt++; - napi_gro_receive(napi, skb); - } else { - total_len += skb->len; - napi_gro_frags(napi); - } + + total_len += skb->len; + + napi_gro_receive(napi, skb); res_budget--; } while (likely(res_budget)); @@ -1680,7 +1749,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, rx_ring->next_to_clean = next_to_clean; - refill_required = ena_com_free_desc(rx_ring->ena_com_io_sq); + refill_required = ena_com_free_q_entries(rx_ring->ena_com_io_sq); refill_threshold = min_t(int, rx_ring->ring_size / ENA_RX_REFILL_THRESH_DIVIDER, ENA_RX_REFILL_THRESH_PACKET); @@ -1691,19 +1760,23 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, ena_refill_rx_bufs(rx_ring, refill_required); } + if (xdp_flags & XDP_REDIRECT) + xdp_do_flush_map(); + return work_done; error: adapter = netdev_priv(rx_ring->netdev); - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.bad_desc_num++; - u64_stats_update_end(&rx_ring->syncp); - - /* Too many desc from the device. Trigger reset */ - adapter->reset_reason = ENA_REGS_RESET_TOO_MANY_RX_DESCS; - set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); - + if (rc == -ENOSPC) { + ena_increase_stat(&rx_ring->rx_stats.bad_desc_num, 1, + &rx_ring->syncp); + ena_reset_device(adapter, ENA_REGS_RESET_TOO_MANY_RX_DESCS); + } else { + ena_increase_stat(&rx_ring->rx_stats.bad_req_id, 1, + &rx_ring->syncp); + ena_reset_device(adapter, ENA_REGS_RESET_INV_RX_REQ_ID); + } return 0; } @@ -1759,6 +1832,9 @@ static void ena_unmask_interrupt(struct ena_ring *tx_ring, tx_ring->smoothed_interval, true); + ena_increase_stat(&tx_ring->tx_stats.unmask_interrupt, 1, + &tx_ring->syncp); + /* It is a shared MSI-X. * Tx and Rx CQ have pointer to it. * So we use one of them to reach the intr reg @@ -1815,9 +1891,14 @@ static int ena_clean_xdp_irq(struct ena_ring *xdp_ring, u32 budget) rc = ena_com_tx_comp_req_id_get(xdp_ring->ena_com_io_cq, &req_id); - if (rc) + if (rc) { + if (unlikely(rc == -EINVAL)) + handle_invalid_req_id(xdp_ring, req_id, NULL, + true); break; + } + /* validate that the request id points to a valid xdp_frame */ rc = validate_xdp_req_id(xdp_ring, req_id); if (rc) break; @@ -1837,7 +1918,7 @@ static int ena_clean_xdp_irq(struct ena_ring *xdp_ring, u32 budget) tx_pkts++; total_done += tx_info->tx_descs; - __free_page(tx_info->xdp_rx_page); + xdp_return_frame(xdpf); xdp_ring->free_ids[next_to_clean] = req_id; next_to_clean = ENA_TX_RING_IDX_NEXT(next_to_clean, xdp_ring->ring_size); @@ -1867,9 +1948,6 @@ static int ena_io_poll(struct napi_struct *napi, int budget) tx_ring = ena_napi->tx_ring; rx_ring = ena_napi->rx_ring; - tx_ring->first_interrupt = ena_napi->first_interrupt; - rx_ring->first_interrupt = ena_napi->first_interrupt; - tx_budget = tx_ring->ring_size / ENA_TX_POLL_BUDGET_DIVIDER; if (!test_bit(ENA_FLAG_DEV_UP, &tx_ring->adapter->flags) || @@ -1899,7 +1977,10 @@ static int ena_io_poll(struct napi_struct *napi, int budget) /* Update numa and unmask the interrupt only when schedule * from the interrupt context (vs from sk_busy_loop) */ - if (napi_complete_done(napi, rx_work_done)) { + if (napi_complete_done(napi, rx_work_done) && + READ_ONCE(ena_napi->interrupts_masked)) { + smp_rmb(); /* make sure interrupts_masked is read */ + WRITE_ONCE(ena_napi->interrupts_masked, false); /* We apply adaptive moderation on Rx path only. * Tx uses static interrupt moderation. */ @@ -1921,6 +2002,8 @@ static int ena_io_poll(struct napi_struct *napi, int budget) tx_ring->tx_stats.tx_poll++; u64_stats_update_end(&tx_ring->syncp); + tx_ring->tx_stats.last_napi_jiffies = jiffies; + return ret; } @@ -1945,7 +2028,11 @@ static irqreturn_t ena_intr_msix_io(int irq, void *data) { struct ena_napi *ena_napi = data; - ena_napi->first_interrupt = true; + /* Used to check HW health */ + WRITE_ONCE(ena_napi->first_interrupt, true); + + WRITE_ONCE(ena_napi->interrupts_masked, true); + smp_wmb(); /* write interrupts_masked before calling napi */ napi_schedule_irqoff(&ena_napi->napi); @@ -1968,9 +2055,9 @@ static int ena_enable_msix(struct ena_adapter *adapter) } /* Reserved the max msix vectors we might need */ - msix_vecs = ENA_MAX_MSIX_VEC(adapter->num_io_queues); + msix_vecs = ENA_MAX_MSIX_VEC(adapter->max_num_io_queues); netif_dbg(adapter, probe, adapter->netdev, - "trying to enable MSI-X, vectors %d\n", msix_vecs); + "Trying to enable MSI-X, vectors %d\n", msix_vecs); irq_cnt = pci_alloc_irq_vectors(adapter->pdev, ENA_MIN_MSIX_VEC, msix_vecs, PCI_IRQ_MSIX); @@ -1983,7 +2070,7 @@ static int ena_enable_msix(struct ena_adapter *adapter) if (irq_cnt != msix_vecs) { netif_notice(adapter, probe, adapter->netdev, - "enable only %d MSI-X (out of %d), reduce the number of queues\n", + "Enable only %d MSI-X (out of %d), reduce the number of queues\n", irq_cnt, msix_vecs); adapter->num_io_queues = irq_cnt - ENA_ADMIN_MSIX_VEC; } @@ -2053,12 +2140,12 @@ static int ena_request_mgmnt_irq(struct ena_adapter *adapter) irq->data); if (rc) { netif_err(adapter, probe, adapter->netdev, - "failed to request admin irq\n"); + "Failed to request admin irq\n"); return rc; } netif_dbg(adapter, probe, adapter->netdev, - "set affinity hint of mgmnt irq.to 0x%lx (irq vector: %d)\n", + "Set affinity hint of mgmnt irq.to 0x%lx (irq vector: %d)\n", irq->affinity_hint_mask.bits[0], irq->vector); irq_set_affinity_hint(irq->vector, &irq->affinity_hint_mask); @@ -2068,6 +2155,7 @@ static int ena_request_mgmnt_irq(struct ena_adapter *adapter) static int ena_request_io_irq(struct ena_adapter *adapter) { + u32 io_queue_count = adapter->num_io_queues + adapter->xdp_num_queues; unsigned long flags = 0; struct ena_irq *irq; int rc = 0, i, k; @@ -2078,7 +2166,7 @@ static int ena_request_io_irq(struct ena_adapter *adapter) return -EINVAL; } - for (i = ENA_IO_IRQ_FIRST_IDX; i < adapter->msix_vecs; i++) { + for (i = ENA_IO_IRQ_FIRST_IDX; i < ENA_MAX_MSIX_VEC(io_queue_count); i++) { irq = &adapter->irq_tbl[i]; rc = request_irq(irq->vector, irq->handler, flags, irq->name, irq->data); @@ -2090,7 +2178,7 @@ static int ena_request_io_irq(struct ena_adapter *adapter) } netif_dbg(adapter, ifup, adapter->netdev, - "set affinity hint of irq. index %d to 0x%lx (irq vector: %d)\n", + "Set affinity hint of irq. index %d to 0x%lx (irq vector: %d)\n", i, irq->affinity_hint_mask.bits[0], irq->vector); irq_set_affinity_hint(irq->vector, &irq->affinity_hint_mask); @@ -2119,6 +2207,7 @@ static void ena_free_mgmnt_irq(struct ena_adapter *adapter) static void ena_free_io_irq(struct ena_adapter *adapter) { + u32 io_queue_count = adapter->num_io_queues + adapter->xdp_num_queues; struct ena_irq *irq; int i; @@ -2129,7 +2218,7 @@ static void ena_free_io_irq(struct ena_adapter *adapter) } #endif /* CONFIG_RFS_ACCEL */ - for (i = ENA_IO_IRQ_FIRST_IDX; i < adapter->msix_vecs; i++) { + for (i = ENA_IO_IRQ_FIRST_IDX; i < ENA_MAX_MSIX_VEC(io_queue_count); i++) { irq = &adapter->irq_tbl[i]; irq_set_affinity_hint(irq->vector, NULL); free_irq(irq->vector, irq->data); @@ -2144,12 +2233,13 @@ static void ena_disable_msix(struct ena_adapter *adapter) static void ena_disable_io_intr_sync(struct ena_adapter *adapter) { + u32 io_queue_count = adapter->num_io_queues + adapter->xdp_num_queues; int i; if (!netif_running(adapter->netdev)) return; - for (i = ENA_IO_IRQ_FIRST_IDX; i < adapter->msix_vecs; i++) + for (i = ENA_IO_IRQ_FIRST_IDX; i < ENA_MAX_MSIX_VEC(io_queue_count); i++) synchronize_irq(adapter->irq_tbl[i].vector); } @@ -2160,29 +2250,23 @@ static void ena_del_napi_in_range(struct ena_adapter *adapter, int i; for (i = first_index; i < first_index + count; i++) { - /* Check if napi was initialized before */ - if (!ENA_IS_XDP_INDEX(adapter, i) || - adapter->ena_napi[i].xdp_ring) - netif_napi_del(&adapter->ena_napi[i].napi); - else - WARN_ON(ENA_IS_XDP_INDEX(adapter, i) && - adapter->ena_napi[i].xdp_ring); + netif_napi_del(&adapter->ena_napi[i].napi); + + WARN_ON(!ENA_IS_XDP_INDEX(adapter, i) && + adapter->ena_napi[i].xdp_ring); } } static void ena_init_napi_in_range(struct ena_adapter *adapter, int first_index, int count) { - struct ena_napi *napi = {0}; int i; for (i = first_index; i < first_index + count; i++) { - napi = &adapter->ena_napi[i]; + struct ena_napi *napi = &adapter->ena_napi[i]; - netif_napi_add(adapter->netdev, - &adapter->ena_napi[i].napi, - ENA_IS_XDP_INDEX(adapter, i) ? ena_xdp_io_poll : ena_io_poll, - ENA_NAPI_BUDGET); + netif_napi_add(adapter->netdev, &napi->napi, + ENA_IS_XDP_INDEX(adapter, i) ? ena_xdp_io_poll : ena_io_poll); if (!ENA_IS_XDP_INDEX(adapter, i)) { napi->rx_ring = &adapter->rx_ring[i]; @@ -2225,7 +2309,7 @@ static int ena_rss_configure(struct ena_adapter *adapter) rc = ena_rss_init_default(adapter); if (rc && (rc != -EOPNOTSUPP)) { netif_err(adapter, ifup, adapter->netdev, - "Failed to init RSS rc: %d\n", rc); + "Failed to init RSS rc: %d\n", rc); return rc; } } @@ -2298,7 +2382,7 @@ static int ena_create_io_tx_queue(struct ena_adapter *adapter, int qid) if (rc) { netif_err(adapter, ifup, adapter->netdev, "Failed to create I/O TX queue num %d rc: %d\n", - qid, rc); + qid, rc); return rc; } @@ -2447,7 +2531,7 @@ static int create_queues_with_size_backoff(struct ena_adapter *adapter) * ones due to past queue allocation failures. */ set_io_rings_size(adapter, adapter->requested_tx_ring_size, - adapter->requested_rx_ring_size); + adapter->requested_rx_ring_size); while (1) { if (ena_xdp_present(adapter)) { @@ -2488,7 +2572,7 @@ err_setup_tx: if (rc != -ENOMEM) { netif_err(adapter, ifup, adapter->netdev, "Queue creation failed with error code %d\n", - rc); + rc); return rc; } @@ -2511,7 +2595,7 @@ err_setup_tx: new_rx_ring_size = cur_rx_ring_size / 2; if (new_tx_ring_size < ENA_MIN_RING_SIZE || - new_rx_ring_size < ENA_MIN_RING_SIZE) { + new_rx_ring_size < ENA_MIN_RING_SIZE) { netif_err(adapter, ifup, adapter->netdev, "Queue creation failed with the smallest possible queue size of %d for both queues. Not retrying with smaller queues\n", ENA_MIN_RING_SIZE); @@ -2532,7 +2616,7 @@ static int ena_up(struct ena_adapter *adapter) { int io_queue_count, rc, i; - netdev_dbg(adapter->netdev, "%s\n", __func__); + netif_dbg(adapter, ifup, adapter->netdev, "%s\n", __func__); io_queue_count = adapter->num_io_queues + adapter->xdp_num_queues; ena_setup_io_intr(adapter); @@ -2559,9 +2643,8 @@ static int ena_up(struct ena_adapter *adapter) if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags)) netif_carrier_on(adapter->netdev); - u64_stats_update_begin(&adapter->syncp); - adapter->dev_stats.interface_up++; - u64_stats_update_end(&adapter->syncp); + ena_increase_stat(&adapter->dev_stats.interface_up, 1, + &adapter->syncp); set_bit(ENA_FLAG_DEV_UP, &adapter->flags); @@ -2599,9 +2682,8 @@ static void ena_down(struct ena_adapter *adapter) clear_bit(ENA_FLAG_DEV_UP, &adapter->flags); - u64_stats_update_begin(&adapter->syncp); - adapter->dev_stats.interface_down++; - u64_stats_update_end(&adapter->syncp); + ena_increase_stat(&adapter->dev_stats.interface_down, 1, + &adapter->syncp); netif_carrier_off(adapter->netdev); netif_tx_disable(adapter->netdev); @@ -2616,7 +2698,8 @@ static void ena_down(struct ena_adapter *adapter) rc = ena_com_dev_reset(adapter->ena_dev, adapter->reset_reason); if (rc) - dev_err(&adapter->pdev->dev, "Device reset failed\n"); + netif_err(adapter, ifdown, adapter->netdev, + "Device reset failed\n"); /* stop submitting admin commands on a device that was reset */ ena_com_set_admin_running_state(adapter->ena_dev, false); } @@ -2759,7 +2842,9 @@ int ena_update_queue_count(struct ena_adapter *adapter, u32 new_channel_count) return dev_was_up ? ena_open(adapter->netdev) : 0; } -static void ena_tx_csum(struct ena_com_tx_ctx *ena_tx_ctx, struct sk_buff *skb) +static void ena_tx_csum(struct ena_com_tx_ctx *ena_tx_ctx, + struct sk_buff *skb, + bool disable_meta_caching) { u32 mss = skb_shinfo(skb)->gso_size; struct ena_com_tx_meta *ena_meta = &ena_tx_ctx->ena_meta; @@ -2803,7 +2888,9 @@ static void ena_tx_csum(struct ena_com_tx_ctx *ena_tx_ctx, struct sk_buff *skb) ena_meta->l3_hdr_len = skb_network_header_len(skb); ena_meta->l3_hdr_offset = skb_network_offset(skb); ena_tx_ctx->meta_valid = 1; - + } else if (disable_meta_caching) { + memset(ena_meta, 0, sizeof(*ena_meta)); + ena_tx_ctx->meta_valid = 1; } else { ena_tx_ctx->meta_valid = 0; } @@ -2824,15 +2911,12 @@ static int ena_check_and_linearize_skb(struct ena_ring *tx_ring, (header_len < tx_ring->tx_max_header_size)) return 0; - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->tx_stats.linearize++; - u64_stats_update_end(&tx_ring->syncp); + ena_increase_stat(&tx_ring->tx_stats.linearize, 1, &tx_ring->syncp); rc = skb_linearize(skb); if (unlikely(rc)) { - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->tx_stats.linearize_failed++; - u64_stats_update_end(&tx_ring->syncp); + ena_increase_stat(&tx_ring->tx_stats.linearize_failed, 1, + &tx_ring->syncp); } return rc; @@ -2872,9 +2956,8 @@ static int ena_tx_map_skb(struct ena_ring *tx_ring, tx_ring->push_buf_intermediate_buf); *header_len = push_len; if (unlikely(skb->data != *push_hdr)) { - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->tx_stats.llq_buffer_copy++; - u64_stats_update_end(&tx_ring->syncp); + ena_increase_stat(&tx_ring->tx_stats.llq_buffer_copy, 1, + &tx_ring->syncp); delta = push_len - skb_head_len; } @@ -2931,10 +3014,9 @@ static int ena_tx_map_skb(struct ena_ring *tx_ring, return 0; error_report_dma_error: - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->tx_stats.dma_mapping_err++; - u64_stats_update_end(&tx_ring->syncp); - netdev_warn(adapter->netdev, "failed to map skb\n"); + ena_increase_stat(&tx_ring->tx_stats.dma_mapping_err, 1, + &tx_ring->syncp); + netif_warn(adapter, tx_queued, adapter->netdev, "Failed to map skb\n"); tx_info->skb = NULL; @@ -2987,7 +3069,7 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) ena_tx_ctx.header_len = header_len; /* set flags and meta data */ - ena_tx_csum(&ena_tx_ctx, skb); + ena_tx_csum(&ena_tx_ctx, skb, tx_ring->disable_meta_caching); rc = ena_xmit_common(dev, tx_ring, @@ -3010,9 +3092,8 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) __func__, qid); netif_tx_stop_queue(txq); - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->tx_stats.queue_stop++; - u64_stats_update_end(&tx_ring->syncp); + ena_increase_stat(&tx_ring->tx_stats.queue_stop, 1, + &tx_ring->syncp); /* There is a rare condition where this function decide to * stop the queue but meanwhile clean_tx_irq updates @@ -3027,21 +3108,16 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) if (ena_com_sq_have_enough_space(tx_ring->ena_com_io_sq, ENA_TX_WAKEUP_THRESH)) { netif_tx_wake_queue(txq); - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->tx_stats.queue_wakeup++; - u64_stats_update_end(&tx_ring->syncp); + ena_increase_stat(&tx_ring->tx_stats.queue_wakeup, 1, + &tx_ring->syncp); } } - if (netif_xmit_stopped(txq) || !netdev_xmit_more()) { - /* trigger the dma engine. ena_com_write_sq_doorbell() - * has a mb + if (netif_xmit_stopped(txq) || !netdev_xmit_more()) + /* trigger the dma engine. ena_ring_tx_doorbell() + * calls a memory barrier inside it. */ - ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq); - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->tx_stats.doorbells++; - u64_stats_update_end(&tx_ring->syncp); - } + ena_ring_tx_doorbell(tx_ring); return NETDEV_TX_OK; @@ -3070,16 +3146,16 @@ static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb, return qid; } -static void ena_config_host_info(struct ena_com_dev *ena_dev, - struct pci_dev *pdev) +static void ena_config_host_info(struct ena_com_dev *ena_dev, struct pci_dev *pdev) { + struct device *dev = &pdev->dev; struct ena_admin_host_info *host_info; int rc; /* Allocate only the host info */ rc = ena_com_allocate_host_info(ena_dev); if (rc) { - pr_err("Cannot allocate host info\n"); + dev_err(dev, "Cannot allocate host info\n"); return; } @@ -3088,27 +3164,30 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev, host_info->bdf = (pdev->bus->number << 8) | pdev->devfn; host_info->os_type = ENA_ADMIN_OS_LINUX; host_info->kernel_ver = LINUX_VERSION_CODE; - strlcpy(host_info->kernel_ver_str, utsname()->version, + strscpy(host_info->kernel_ver_str, utsname()->version, sizeof(host_info->kernel_ver_str) - 1); host_info->os_dist = 0; strncpy(host_info->os_dist_str, utsname()->release, sizeof(host_info->os_dist_str) - 1); host_info->driver_version = - (DRV_MODULE_VER_MAJOR) | - (DRV_MODULE_VER_MINOR << ENA_ADMIN_HOST_INFO_MINOR_SHIFT) | - (DRV_MODULE_VER_SUBMINOR << ENA_ADMIN_HOST_INFO_SUB_MINOR_SHIFT) | + (DRV_MODULE_GEN_MAJOR) | + (DRV_MODULE_GEN_MINOR << ENA_ADMIN_HOST_INFO_MINOR_SHIFT) | + (DRV_MODULE_GEN_SUBMINOR << ENA_ADMIN_HOST_INFO_SUB_MINOR_SHIFT) | ("K"[0] << ENA_ADMIN_HOST_INFO_MODULE_TYPE_SHIFT); host_info->num_cpus = num_online_cpus(); host_info->driver_supported_features = - ENA_ADMIN_HOST_INFO_INTERRUPT_MODERATION_MASK; + ENA_ADMIN_HOST_INFO_RX_OFFSET_MASK | + ENA_ADMIN_HOST_INFO_INTERRUPT_MODERATION_MASK | + ENA_ADMIN_HOST_INFO_RX_BUF_MIRRORING_MASK | + ENA_ADMIN_HOST_INFO_RSS_CONFIGURABLE_FUNCTION_KEY_MASK; rc = ena_com_set_host_attributes(ena_dev); if (rc) { if (rc == -EOPNOTSUPP) - pr_warn("Cannot set host attributes\n"); + dev_warn(dev, "Cannot set host attributes\n"); else - pr_err("Cannot set host attributes\n"); + dev_err(dev, "Cannot set host attributes\n"); goto err; } @@ -3136,7 +3215,8 @@ static void ena_config_debug_area(struct ena_adapter *adapter) rc = ena_com_allocate_debug_area(adapter->ena_dev, debug_area_size); if (rc) { - pr_err("Cannot allocate debug area\n"); + netif_err(adapter, drv, adapter->netdev, + "Cannot allocate debug area\n"); return; } @@ -3156,6 +3236,19 @@ err: ena_com_delete_debug_area(adapter->ena_dev); } +int ena_update_hw_stats(struct ena_adapter *adapter) +{ + int rc; + + rc = ena_com_get_eni_stats(adapter->ena_dev, &adapter->eni_stats); + if (rc) { + netdev_err(adapter->netdev, "Failed to get ENI stats\n"); + return rc; + } + + return 0; +} + static void ena_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { @@ -3163,6 +3256,7 @@ static void ena_get_stats64(struct net_device *netdev, struct ena_ring *rx_ring, *tx_ring; unsigned int start; u64 rx_drops; + u64 tx_drops; int i; if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags)) @@ -3197,9 +3291,11 @@ static void ena_get_stats64(struct net_device *netdev, do { start = u64_stats_fetch_begin_irq(&adapter->syncp); rx_drops = adapter->dev_stats.rx_drops; + tx_drops = adapter->dev_stats.tx_drops; } while (u64_stats_fetch_retry_irq(&adapter->syncp, start)); stats->rx_dropped = rx_drops; + stats->tx_dropped = tx_drops; stats->multicast = 0; stats->collisions = 0; @@ -3226,6 +3322,7 @@ static const struct net_device_ops ena_netdev_ops = { .ndo_set_mac_address = NULL, .ndo_validate_addr = eth_validate_addr, .ndo_bpf = ena_xdp, + .ndo_xdp_xmit = ena_xdp_xmit, }; static int ena_device_validate_params(struct ena_adapter *adapter, @@ -3251,10 +3348,71 @@ static int ena_device_validate_params(struct ena_adapter *adapter, return 0; } +static void set_default_llq_configurations(struct ena_llq_configurations *llq_config) +{ + llq_config->llq_header_location = ENA_ADMIN_INLINE_HEADER; + llq_config->llq_stride_ctrl = ENA_ADMIN_MULTIPLE_DESCS_PER_ENTRY; + llq_config->llq_num_decs_before_header = ENA_ADMIN_LLQ_NUM_DESCS_BEFORE_HEADER_2; + llq_config->llq_ring_entry_size = ENA_ADMIN_LIST_ENTRY_SIZE_128B; + llq_config->llq_ring_entry_size_value = 128; +} + +static int ena_set_queues_placement_policy(struct pci_dev *pdev, + struct ena_com_dev *ena_dev, + struct ena_admin_feature_llq_desc *llq, + struct ena_llq_configurations *llq_default_configurations) +{ + int rc; + u32 llq_feature_mask; + + llq_feature_mask = 1 << ENA_ADMIN_LLQ; + if (!(ena_dev->supported_features & llq_feature_mask)) { + dev_warn(&pdev->dev, + "LLQ is not supported Fallback to host mode policy.\n"); + ena_dev->tx_mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST; + return 0; + } + + rc = ena_com_config_dev_mode(ena_dev, llq, llq_default_configurations); + if (unlikely(rc)) { + dev_err(&pdev->dev, + "Failed to configure the device mode. Fallback to host mode policy.\n"); + ena_dev->tx_mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST; + } + + return 0; +} + +static int ena_map_llq_mem_bar(struct pci_dev *pdev, struct ena_com_dev *ena_dev, + int bars) +{ + bool has_mem_bar = !!(bars & BIT(ENA_MEM_BAR)); + + if (!has_mem_bar) { + if (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) { + dev_err(&pdev->dev, + "ENA device does not expose LLQ bar. Fallback to host mode policy.\n"); + ena_dev->tx_mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST; + } + + return 0; + } + + ena_dev->mem_bar = devm_ioremap_wc(&pdev->dev, + pci_resource_start(pdev, ENA_MEM_BAR), + pci_resource_len(pdev, ENA_MEM_BAR)); + + if (!ena_dev->mem_bar) + return -EFAULT; + + return 0; +} + static int ena_device_init(struct ena_com_dev *ena_dev, struct pci_dev *pdev, struct ena_com_dev_get_features_ctx *get_feat_ctx, bool *wd_state) { + struct ena_llq_configurations llq_config; struct device *dev = &pdev->dev; bool readless_supported; u32 aenq_groups; @@ -3263,7 +3421,7 @@ static int ena_device_init(struct ena_com_dev *ena_dev, struct pci_dev *pdev, rc = ena_com_mmio_reg_read_request_init(ena_dev); if (rc) { - dev_err(dev, "failed to init mmio read less\n"); + dev_err(dev, "Failed to init mmio read less\n"); return rc; } @@ -3281,7 +3439,7 @@ static int ena_device_init(struct ena_com_dev *ena_dev, struct pci_dev *pdev, rc = ena_com_validate_version(ena_dev); if (rc) { - dev_err(dev, "device version is too low\n"); + dev_err(dev, "Device version is too low\n"); goto err_mmio_read_less; } @@ -3292,16 +3450,9 @@ static int ena_device_init(struct ena_com_dev *ena_dev, struct pci_dev *pdev, goto err_mmio_read_less; } - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(dma_width)); + rc = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(dma_width)); if (rc) { - dev_err(dev, "pci_set_dma_mask failed 0x%x\n", rc); - goto err_mmio_read_less; - } - - rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(dma_width)); - if (rc) { - dev_err(dev, "err_pci_set_consistent_dma_mask failed 0x%x\n", - rc); + dev_err(dev, "dma_set_mask_and_coherent failed %d\n", rc); goto err_mmio_read_less; } @@ -3345,6 +3496,15 @@ static int ena_device_init(struct ena_com_dev *ena_dev, struct pci_dev *pdev, *wd_state = !!(aenq_groups & BIT(ENA_ADMIN_KEEP_ALIVE)); + set_default_llq_configurations(&llq_config); + + rc = ena_set_queues_placement_policy(pdev, ena_dev, &get_feat_ctx->llq, + &llq_config); + if (rc) { + dev_err(dev, "ENA device init failed\n"); + goto err_admin_init; + } + return 0; err_admin_init: @@ -3427,6 +3587,7 @@ static void ena_destroy_device(struct ena_adapter *adapter, bool graceful) ena_com_mmio_reg_read_request_destroy(ena_dev); + /* return reset reason to default value */ adapter->reset_reason = ENA_REGS_RESET_NORMAL; clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); @@ -3476,9 +3637,7 @@ static int ena_restore_device(struct ena_adapter *adapter) netif_carrier_on(adapter->netdev); mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); - dev_err(&pdev->dev, - "Device reset completed successfully, Driver info: %s\n", - version); + adapter->last_keep_alive_jiffies = jiffies; return rc; err_disable_msix: @@ -3503,23 +3662,25 @@ static void ena_fw_reset_device(struct work_struct *work) { struct ena_adapter *adapter = container_of(work, struct ena_adapter, reset_task); - struct pci_dev *pdev = adapter->pdev; - if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { - dev_err(&pdev->dev, - "device reset schedule while reset bit is off\n"); - return; - } rtnl_lock(); - ena_destroy_device(adapter, false); - ena_restore_device(adapter); + + if (likely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { + ena_destroy_device(adapter, false); + ena_restore_device(adapter); + + dev_err(&adapter->pdev->dev, "Device reset completed successfully\n"); + } + rtnl_unlock(); } static int check_for_rx_interrupt_queue(struct ena_adapter *adapter, struct ena_ring *rx_ring) { - if (likely(rx_ring->first_interrupt)) + struct ena_napi *ena_napi = container_of(rx_ring->napi, struct ena_napi, napi); + + if (likely(READ_ONCE(ena_napi->first_interrupt))) return 0; if (ena_com_cq_empty(rx_ring->ena_com_io_cq)) @@ -3531,9 +3692,8 @@ static int check_for_rx_interrupt_queue(struct ena_adapter *adapter, netif_err(adapter, rx_err, adapter->netdev, "Potential MSIX issue on Rx side Queue = %d. Reset the device\n", rx_ring->qid); - adapter->reset_reason = ENA_REGS_RESET_MISS_INTERRUPT; - smp_mb__before_atomic(); - set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + + ena_reset_device(adapter, ENA_REGS_RESET_MISS_INTERRUPT); return -EIO; } @@ -3543,6 +3703,10 @@ static int check_for_rx_interrupt_queue(struct ena_adapter *adapter, static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter, struct ena_ring *tx_ring) { + struct ena_napi *ena_napi = container_of(tx_ring->napi, struct ena_napi, napi); + unsigned int time_since_last_napi; + unsigned int missing_tx_comp_to; + bool is_tx_comp_time_expired; struct ena_tx_buffer *tx_buf; unsigned long last_jiffies; u32 missed_tx = 0; @@ -3556,26 +3720,31 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter, /* no pending Tx at this location */ continue; - if (unlikely(!tx_ring->first_interrupt && time_is_before_jiffies(last_jiffies + - 2 * adapter->missing_tx_completion_to))) { + is_tx_comp_time_expired = time_is_before_jiffies(last_jiffies + + 2 * adapter->missing_tx_completion_to); + + if (unlikely(!READ_ONCE(ena_napi->first_interrupt) && is_tx_comp_time_expired)) { /* If after graceful period interrupt is still not * received, we schedule a reset */ netif_err(adapter, tx_err, adapter->netdev, "Potential MSIX issue on Tx side Queue = %d. Reset the device\n", tx_ring->qid); - adapter->reset_reason = ENA_REGS_RESET_MISS_INTERRUPT; - smp_mb__before_atomic(); - set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + ena_reset_device(adapter, ENA_REGS_RESET_MISS_INTERRUPT); return -EIO; } - if (unlikely(time_is_before_jiffies(last_jiffies + - adapter->missing_tx_completion_to))) { - if (!tx_buf->print_once) + is_tx_comp_time_expired = time_is_before_jiffies(last_jiffies + + adapter->missing_tx_completion_to); + + if (unlikely(is_tx_comp_time_expired)) { + if (!tx_buf->print_once) { + time_since_last_napi = jiffies_to_usecs(jiffies - tx_ring->tx_stats.last_napi_jiffies); + missing_tx_comp_to = jiffies_to_msecs(adapter->missing_tx_completion_to); netif_notice(adapter, tx_err, adapter->netdev, - "Found a Tx that wasn't completed on time, qid %d, index %d.\n", - tx_ring->qid, i); + "Found a Tx that wasn't completed on time, qid %d, index %d. %u usecs have passed since last napi execution. Missing Tx timeout value %u msecs\n", + tx_ring->qid, i, time_since_last_napi, missing_tx_comp_to); + } tx_buf->print_once = 1; missed_tx++; @@ -3587,15 +3756,12 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter, "The number of lost tx completions is above the threshold (%d > %d). Reset the device\n", missed_tx, adapter->missing_tx_completion_threshold); - adapter->reset_reason = - ENA_REGS_RESET_MISS_TX_CMPL; - set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + ena_reset_device(adapter, ENA_REGS_RESET_MISS_TX_CMPL); rc = -EIO; } - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->tx_stats.missed_tx = missed_tx; - u64_stats_update_end(&tx_ring->syncp); + ena_increase_stat(&tx_ring->tx_stats.missed_tx, missed_tx, + &tx_ring->syncp); return rc; } @@ -3673,18 +3839,16 @@ static void check_for_empty_rx_ring(struct ena_adapter *adapter) for (i = 0; i < adapter->num_io_queues; i++) { rx_ring = &adapter->rx_ring[i]; - refill_required = - ena_com_free_desc(rx_ring->ena_com_io_sq); + refill_required = ena_com_free_q_entries(rx_ring->ena_com_io_sq); if (unlikely(refill_required == (rx_ring->ring_size - 1))) { rx_ring->empty_rx_queue++; if (rx_ring->empty_rx_queue >= EMPTY_RX_REFILL) { - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.empty_rx_ring++; - u64_stats_update_end(&rx_ring->syncp); + ena_increase_stat(&rx_ring->rx_stats.empty_rx_ring, 1, + &rx_ring->syncp); netif_err(adapter, drv, adapter->netdev, - "trigger refill for ring %d\n", i); + "Trigger refill for ring %d\n", i); napi_schedule(rx_ring->napi); rx_ring->empty_rx_queue = 0; @@ -3711,11 +3875,9 @@ static void check_for_missing_keep_alive(struct ena_adapter *adapter) if (unlikely(time_is_before_jiffies(keep_alive_expired))) { netif_err(adapter, drv, adapter->netdev, "Keep alive watchdog timeout.\n"); - u64_stats_update_begin(&adapter->syncp); - adapter->dev_stats.wd_expired++; - u64_stats_update_end(&adapter->syncp); - adapter->reset_reason = ENA_REGS_RESET_KEEP_ALIVE_TO; - set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + ena_increase_stat(&adapter->dev_stats.wd_expired, 1, + &adapter->syncp); + ena_reset_device(adapter, ENA_REGS_RESET_KEEP_ALIVE_TO); } } @@ -3724,11 +3886,9 @@ static void check_for_admin_com_state(struct ena_adapter *adapter) if (unlikely(!ena_com_get_admin_running_state(adapter->ena_dev))) { netif_err(adapter, drv, adapter->netdev, "ENA admin queue is not in running state!\n"); - u64_stats_update_begin(&adapter->syncp); - adapter->dev_stats.admin_q_pause++; - u64_stats_update_end(&adapter->syncp); - adapter->reset_reason = ENA_REGS_RESET_ADMIN_TO; - set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + ena_increase_stat(&adapter->dev_stats.admin_q_pause, 1, + &adapter->syncp); + ena_reset_device(adapter, ENA_REGS_RESET_ADMIN_TO); } } @@ -3812,11 +3972,11 @@ static void ena_timer_service(struct timer_list *t) mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); } -static int ena_calc_max_io_queue_num(struct pci_dev *pdev, +static u32 ena_calc_max_io_queue_num(struct pci_dev *pdev, struct ena_com_dev *ena_dev, struct ena_com_dev_get_features_ctx *get_feat_ctx) { - int io_tx_sq_num, io_tx_cq_num, io_rx_num, max_num_io_queues; + u32 io_tx_sq_num, io_tx_cq_num, io_rx_num, max_num_io_queues; if (ena_dev->supported_features & BIT(ENA_ADMIN_MAX_QUEUES_EXT)) { struct ena_admin_queue_ext_feature_fields *max_queue_ext = @@ -3842,64 +4002,12 @@ static int ena_calc_max_io_queue_num(struct pci_dev *pdev, max_num_io_queues = min_t(u32, max_num_io_queues, io_rx_num); max_num_io_queues = min_t(u32, max_num_io_queues, io_tx_sq_num); max_num_io_queues = min_t(u32, max_num_io_queues, io_tx_cq_num); - /* 1 IRQ for for mgmnt and 1 IRQs for each IO direction */ + /* 1 IRQ for mgmnt and 1 IRQs for each IO direction */ max_num_io_queues = min_t(u32, max_num_io_queues, pci_msix_vec_count(pdev) - 1); - if (unlikely(!max_num_io_queues)) { - dev_err(&pdev->dev, "The device doesn't have io queues\n"); - return -EFAULT; - } return max_num_io_queues; } -static int ena_set_queues_placement_policy(struct pci_dev *pdev, - struct ena_com_dev *ena_dev, - struct ena_admin_feature_llq_desc *llq, - struct ena_llq_configurations *llq_default_configurations) -{ - bool has_mem_bar; - int rc; - u32 llq_feature_mask; - - llq_feature_mask = 1 << ENA_ADMIN_LLQ; - if (!(ena_dev->supported_features & llq_feature_mask)) { - dev_err(&pdev->dev, - "LLQ is not supported Fallback to host mode policy.\n"); - ena_dev->tx_mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST; - return 0; - } - - has_mem_bar = pci_select_bars(pdev, IORESOURCE_MEM) & BIT(ENA_MEM_BAR); - - rc = ena_com_config_dev_mode(ena_dev, llq, llq_default_configurations); - if (unlikely(rc)) { - dev_err(&pdev->dev, - "Failed to configure the device mode. Fallback to host mode policy.\n"); - ena_dev->tx_mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST; - return 0; - } - - /* Nothing to config, exit */ - if (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_HOST) - return 0; - - if (!has_mem_bar) { - dev_err(&pdev->dev, - "ENA device does not expose LLQ bar. Fallback to host mode policy.\n"); - ena_dev->tx_mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST; - return 0; - } - - ena_dev->mem_bar = devm_ioremap_wc(&pdev->dev, - pci_resource_start(pdev, ENA_MEM_BAR), - pci_resource_len(pdev, ENA_MEM_BAR)); - - if (!ena_dev->mem_bar) - return -EFAULT; - - return 0; -} - static void ena_set_dev_offloads(struct ena_com_dev_get_features_ctx *feat, struct net_device *netdev) { @@ -3952,7 +4060,7 @@ static void ena_set_conf_feat_params(struct ena_adapter *adapter, ether_addr_copy(adapter->mac_addr, netdev->dev_addr); } else { ether_addr_copy(adapter->mac_addr, feat->dev_attr.mac_addr); - ether_addr_copy(netdev->dev_addr, adapter->mac_addr); + eth_hw_addr_set(netdev, adapter->mac_addr); } /* Set offload features */ @@ -3980,13 +4088,13 @@ static int ena_rss_init_default(struct ena_adapter *adapter) val = ethtool_rxfh_indir_default(i, adapter->num_io_queues); rc = ena_com_indirect_table_fill_entry(ena_dev, i, ENA_IO_RXQ_IDX(val)); - if (unlikely(rc && (rc != -EOPNOTSUPP))) { + if (unlikely(rc)) { dev_err(dev, "Cannot fill indirect table\n"); goto err_fill_indir; } } - rc = ena_com_fill_hash_function(ena_dev, ENA_ADMIN_CRC32, NULL, + rc = ena_com_fill_hash_function(ena_dev, ENA_ADMIN_TOEPLITZ, NULL, ENA_HASH_KEY_SIZE, 0xFFFFFFFF); if (unlikely(rc && (rc != -EOPNOTSUPP))) { dev_err(dev, "Cannot fill hash function\n"); @@ -4015,19 +4123,12 @@ static void ena_release_bars(struct ena_com_dev *ena_dev, struct pci_dev *pdev) pci_release_selected_regions(pdev, release_bars); } -static void set_default_llq_configurations(struct ena_llq_configurations *llq_config) -{ - llq_config->llq_header_location = ENA_ADMIN_INLINE_HEADER; - llq_config->llq_ring_entry_size = ENA_ADMIN_LIST_ENTRY_SIZE_128B; - llq_config->llq_stride_ctrl = ENA_ADMIN_MULTIPLE_DESCS_PER_ENTRY; - llq_config->llq_num_decs_before_header = ENA_ADMIN_LLQ_NUM_DESCS_BEFORE_HEADER_2; - llq_config->llq_ring_entry_size_value = 128; -} -static int ena_calc_io_queue_size(struct ena_calc_queue_size_ctx *ctx) +static void ena_calc_io_queue_size(struct ena_adapter *adapter, + struct ena_com_dev_get_features_ctx *get_feat_ctx) { - struct ena_admin_feature_llq_desc *llq = &ctx->get_feat_ctx->llq; - struct ena_com_dev *ena_dev = ctx->ena_dev; + struct ena_admin_feature_llq_desc *llq = &get_feat_ctx->llq; + struct ena_com_dev *ena_dev = adapter->ena_dev; u32 tx_queue_size = ENA_DEFAULT_RING_SIZE; u32 rx_queue_size = ENA_DEFAULT_RING_SIZE; u32 max_tx_queue_size; @@ -4035,7 +4136,7 @@ static int ena_calc_io_queue_size(struct ena_calc_queue_size_ctx *ctx) if (ena_dev->supported_features & BIT(ENA_ADMIN_MAX_QUEUES_EXT)) { struct ena_admin_queue_ext_feature_fields *max_queue_ext = - &ctx->get_feat_ctx->max_queue_ext.max_queue_ext; + &get_feat_ctx->max_queue_ext.max_queue_ext; max_rx_queue_size = min_t(u32, max_queue_ext->max_rx_cq_depth, max_queue_ext->max_rx_sq_depth); max_tx_queue_size = max_queue_ext->max_tx_cq_depth; @@ -4047,13 +4148,13 @@ static int ena_calc_io_queue_size(struct ena_calc_queue_size_ctx *ctx) max_tx_queue_size = min_t(u32, max_tx_queue_size, max_queue_ext->max_tx_sq_depth); - ctx->max_tx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS, - max_queue_ext->max_per_packet_tx_descs); - ctx->max_rx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS, - max_queue_ext->max_per_packet_rx_descs); + adapter->max_tx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS, + max_queue_ext->max_per_packet_tx_descs); + adapter->max_rx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS, + max_queue_ext->max_per_packet_rx_descs); } else { struct ena_admin_queue_feature_desc *max_queues = - &ctx->get_feat_ctx->max_queues; + &get_feat_ctx->max_queues; max_rx_queue_size = min_t(u32, max_queues->max_cq_depth, max_queues->max_sq_depth); max_tx_queue_size = max_queues->max_cq_depth; @@ -4065,10 +4166,10 @@ static int ena_calc_io_queue_size(struct ena_calc_queue_size_ctx *ctx) max_tx_queue_size = min_t(u32, max_tx_queue_size, max_queues->max_sq_depth); - ctx->max_tx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS, - max_queues->max_packet_tx_descs); - ctx->max_rx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS, - max_queues->max_packet_rx_descs); + adapter->max_tx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS, + max_queues->max_packet_tx_descs); + adapter->max_rx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS, + max_queues->max_packet_rx_descs); } max_tx_queue_size = rounddown_pow_of_two(max_tx_queue_size); @@ -4082,12 +4183,10 @@ static int ena_calc_io_queue_size(struct ena_calc_queue_size_ctx *ctx) tx_queue_size = rounddown_pow_of_two(tx_queue_size); rx_queue_size = rounddown_pow_of_two(rx_queue_size); - ctx->max_tx_queue_size = max_tx_queue_size; - ctx->max_rx_queue_size = max_rx_queue_size; - ctx->tx_queue_size = tx_queue_size; - ctx->rx_queue_size = rx_queue_size; - - return 0; + adapter->max_tx_ring_size = max_tx_queue_size; + adapter->max_rx_ring_size = max_rx_queue_size; + adapter->requested_tx_ring_size = tx_queue_size; + adapter->requested_rx_ring_size = rx_queue_size; } /* ena_probe - Device Initialization Routine @@ -4103,27 +4202,28 @@ static int ena_calc_io_queue_size(struct ena_calc_queue_size_ctx *ctx) static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct ena_com_dev_get_features_ctx get_feat_ctx; - struct ena_calc_queue_size_ctx calc_queue_ctx = { 0 }; - struct ena_llq_configurations llq_config; struct ena_com_dev *ena_dev = NULL; struct ena_adapter *adapter; struct net_device *netdev; static int adapters_found; u32 max_num_io_queues; - char *queue_type_str; bool wd_state; int bars, rc; dev_dbg(&pdev->dev, "%s\n", __func__); - dev_info_once(&pdev->dev, "%s", version); - rc = pci_enable_device_mem(pdev); if (rc) { dev_err(&pdev->dev, "pci_enable_device_mem() failed!\n"); return rc; } + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(ENA_MAX_PHYS_ADDR_SIZE_BITS)); + if (rc) { + dev_err(&pdev->dev, "dma_set_mask_and_coherent failed %d\n", rc); + goto err_disable_device; + } + pci_set_master(pdev); ena_dev = vzalloc(sizeof(*ena_dev)); @@ -4144,85 +4244,77 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_resource_start(pdev, ENA_REG_BAR), pci_resource_len(pdev, ENA_REG_BAR)); if (!ena_dev->reg_bar) { - dev_err(&pdev->dev, "failed to remap regs bar\n"); + dev_err(&pdev->dev, "Failed to remap regs bar\n"); rc = -EFAULT; goto err_free_region; } + ena_dev->ena_min_poll_delay_us = ENA_ADMIN_POLL_DELAY_US; + ena_dev->dmadev = &pdev->dev; + netdev = alloc_etherdev_mq(sizeof(struct ena_adapter), ENA_MAX_RINGS); + if (!netdev) { + dev_err(&pdev->dev, "alloc_etherdev_mq failed\n"); + rc = -ENOMEM; + goto err_free_region; + } + + SET_NETDEV_DEV(netdev, &pdev->dev); + adapter = netdev_priv(netdev); + adapter->ena_dev = ena_dev; + adapter->netdev = netdev; + adapter->pdev = pdev; + adapter->msg_enable = DEFAULT_MSG_ENABLE; + + ena_dev->net_device = netdev; + + pci_set_drvdata(pdev, adapter); + rc = ena_device_init(ena_dev, pdev, &get_feat_ctx, &wd_state); if (rc) { - dev_err(&pdev->dev, "ena device init failed\n"); + dev_err(&pdev->dev, "ENA device init failed\n"); if (rc == -ETIME) rc = -EPROBE_DEFER; - goto err_free_region; + goto err_netdev_destroy; } - set_default_llq_configurations(&llq_config); - - rc = ena_set_queues_placement_policy(pdev, ena_dev, &get_feat_ctx.llq, - &llq_config); + rc = ena_map_llq_mem_bar(pdev, ena_dev, bars); if (rc) { - dev_err(&pdev->dev, "ena device init failed\n"); + dev_err(&pdev->dev, "ENA llq bar mapping failed\n"); goto err_device_destroy; } - calc_queue_ctx.ena_dev = ena_dev; - calc_queue_ctx.get_feat_ctx = &get_feat_ctx; - calc_queue_ctx.pdev = pdev; - - /* Initial Tx and RX interrupt delay. Assumes 1 usec granularity. + /* Initial TX and RX interrupt delay. Assumes 1 usec granularity. * Updated during device initialization with the real granularity */ ena_dev->intr_moder_tx_interval = ENA_INTR_INITIAL_TX_INTERVAL_USECS; ena_dev->intr_moder_rx_interval = ENA_INTR_INITIAL_RX_INTERVAL_USECS; ena_dev->intr_delay_resolution = ENA_DEFAULT_INTR_DELAY_RESOLUTION; max_num_io_queues = ena_calc_max_io_queue_num(pdev, ena_dev, &get_feat_ctx); - rc = ena_calc_io_queue_size(&calc_queue_ctx); - if (rc || !max_num_io_queues) { + ena_calc_io_queue_size(adapter, &get_feat_ctx); + if (unlikely(!max_num_io_queues)) { rc = -EFAULT; goto err_device_destroy; } - /* dev zeroed in init_etherdev */ - netdev = alloc_etherdev_mq(sizeof(struct ena_adapter), max_num_io_queues); - if (!netdev) { - dev_err(&pdev->dev, "alloc_etherdev_mq failed\n"); - rc = -ENOMEM; - goto err_device_destroy; - } - - SET_NETDEV_DEV(netdev, &pdev->dev); - - adapter = netdev_priv(netdev); - pci_set_drvdata(pdev, adapter); - - adapter->ena_dev = ena_dev; - adapter->netdev = netdev; - adapter->pdev = pdev; - ena_set_conf_feat_params(adapter, &get_feat_ctx); - adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); adapter->reset_reason = ENA_REGS_RESET_NORMAL; - adapter->requested_tx_ring_size = calc_queue_ctx.tx_queue_size; - adapter->requested_rx_ring_size = calc_queue_ctx.rx_queue_size; - adapter->max_tx_ring_size = calc_queue_ctx.max_tx_queue_size; - adapter->max_rx_ring_size = calc_queue_ctx.max_rx_queue_size; - adapter->max_tx_sgl_size = calc_queue_ctx.max_tx_sgl_size; - adapter->max_rx_sgl_size = calc_queue_ctx.max_rx_sgl_size; - adapter->num_io_queues = max_num_io_queues; adapter->max_num_io_queues = max_num_io_queues; + adapter->last_monitored_tx_qid = 0; adapter->xdp_first_ring = 0; adapter->xdp_num_queues = 0; - adapter->last_monitored_tx_qid = 0; - adapter->rx_copybreak = ENA_DEFAULT_RX_COPYBREAK; + if (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) + adapter->disable_meta_caching = + !!(get_feat_ctx.llq.accel_mode.u.get.supported_flags & + BIT(ENA_ADMIN_DISABLE_META_CACHING)); + adapter->wd_state = wd_state; snprintf(adapter->name, ENA_NAME_MAX_LEN, "ena_%d", adapters_found); @@ -4231,7 +4323,7 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) { dev_err(&pdev->dev, "Failed to query interrupt moderation feature\n"); - goto err_netdev_destroy; + goto err_device_destroy; } ena_init_io_rings(adapter, 0, @@ -4282,15 +4374,10 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) timer_setup(&adapter->timer_service, ena_timer_service, 0); mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); - if (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_HOST) - queue_type_str = "Regular"; - else - queue_type_str = "Low Latency"; - dev_info(&pdev->dev, - "%s found at mem %lx, mac addr %pM, Placement policy: %s\n", + "%s found at mem %lx, mac addr %pM\n", DEVICE_NAME, (long)pci_resource_start(pdev, 0), - netdev->dev_addr, queue_type_str); + netdev->dev_addr); set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); @@ -4309,11 +4396,11 @@ err_free_msix: ena_disable_msix(adapter); err_worker_destroy: del_timer(&adapter->timer_service); -err_netdev_destroy: - free_netdev(netdev); err_device_destroy: ena_com_delete_host_info(ena_dev); ena_com_admin_destroy(ena_dev); +err_netdev_destroy: + free_netdev(netdev); err_free_region: ena_release_bars(ena_dev, pdev); err_free_ena_dev: @@ -4325,13 +4412,15 @@ err_disable_device: /*****************************************************************************/ -/* ena_remove - Device Removal Routine +/* __ena_shutoff - Helper used in both PCI remove/shutdown routines * @pdev: PCI device information struct + * @shutdown: Is it a shutdown operation? If false, means it is a removal * - * ena_remove is called by the PCI subsystem to alert the driver - * that it should release a PCI device. + * __ena_shutoff is a helper routine that does the real work on shutdown and + * removal paths; the difference between those paths is with regards to whether + * dettach or unregister the netdevice. */ -static void ena_remove(struct pci_dev *pdev) +static void __ena_shutoff(struct pci_dev *pdev, bool shutdown) { struct ena_adapter *adapter = pci_get_drvdata(pdev); struct ena_com_dev *ena_dev; @@ -4346,17 +4435,25 @@ static void ena_remove(struct pci_dev *pdev) netdev->rx_cpu_rmap = NULL; } #endif /* CONFIG_RFS_ACCEL */ - del_timer_sync(&adapter->timer_service); + /* Make sure timer and reset routine won't be called after + * freeing device resources. + */ + del_timer_sync(&adapter->timer_service); cancel_work_sync(&adapter->reset_task); - rtnl_lock(); + rtnl_lock(); /* lock released inside the below if-else block */ + adapter->reset_reason = ENA_REGS_RESET_SHUTDOWN; ena_destroy_device(adapter, true); - rtnl_unlock(); - - unregister_netdev(netdev); - - free_netdev(netdev); + if (shutdown) { + netif_device_detach(netdev); + dev_close(netdev); + rtnl_unlock(); + } else { + rtnl_unlock(); + unregister_netdev(netdev); + free_netdev(netdev); + } ena_com_rss_destroy(ena_dev); @@ -4371,23 +4468,44 @@ static void ena_remove(struct pci_dev *pdev) vfree(ena_dev); } -#ifdef CONFIG_PM -/* ena_suspend - PM suspend callback +/* ena_remove - Device Removal Routine + * @pdev: PCI device information struct + * + * ena_remove is called by the PCI subsystem to alert the driver + * that it should release a PCI device. + */ + +static void ena_remove(struct pci_dev *pdev) +{ + __ena_shutoff(pdev, false); +} + +/* ena_shutdown - Device Shutdown Routine * @pdev: PCI device information struct - * @state:power state + * + * ena_shutdown is called by the PCI subsystem to alert the driver that + * a shutdown/reboot (or kexec) is happening and device must be disabled. + */ + +static void ena_shutdown(struct pci_dev *pdev) +{ + __ena_shutoff(pdev, true); +} + +/* ena_suspend - PM suspend callback + * @dev_d: Device information struct */ -static int ena_suspend(struct pci_dev *pdev, pm_message_t state) +static int __maybe_unused ena_suspend(struct device *dev_d) { + struct pci_dev *pdev = to_pci_dev(dev_d); struct ena_adapter *adapter = pci_get_drvdata(pdev); - u64_stats_update_begin(&adapter->syncp); - adapter->dev_stats.suspend++; - u64_stats_update_end(&adapter->syncp); + ena_increase_stat(&adapter->dev_stats.suspend, 1, &adapter->syncp); rtnl_lock(); if (unlikely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { dev_err(&pdev->dev, - "ignoring device reset request as the device is being suspended\n"); + "Ignoring device reset request as the device is being suspended\n"); clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); } ena_destroy_device(adapter, true); @@ -4396,41 +4514,35 @@ static int ena_suspend(struct pci_dev *pdev, pm_message_t state) } /* ena_resume - PM resume callback - * @pdev: PCI device information struct - * + * @dev_d: Device information struct */ -static int ena_resume(struct pci_dev *pdev) +static int __maybe_unused ena_resume(struct device *dev_d) { - struct ena_adapter *adapter = pci_get_drvdata(pdev); + struct ena_adapter *adapter = dev_get_drvdata(dev_d); int rc; - u64_stats_update_begin(&adapter->syncp); - adapter->dev_stats.resume++; - u64_stats_update_end(&adapter->syncp); + ena_increase_stat(&adapter->dev_stats.resume, 1, &adapter->syncp); rtnl_lock(); rc = ena_restore_device(adapter); rtnl_unlock(); return rc; } -#endif + +static SIMPLE_DEV_PM_OPS(ena_pm_ops, ena_suspend, ena_resume); static struct pci_driver ena_pci_driver = { .name = DRV_MODULE_NAME, .id_table = ena_pci_tbl, .probe = ena_probe, .remove = ena_remove, -#ifdef CONFIG_PM - .suspend = ena_suspend, - .resume = ena_resume, -#endif + .shutdown = ena_shutdown, + .driver.pm = &ena_pm_ops, .sriov_configure = pci_sriov_configure_simple, }; static int __init ena_init(void) { - pr_info("%s", version); - ena_wq = create_singlethread_workqueue(DRV_MODULE_NAME); if (!ena_wq) { pr_err("Failed to create workqueue\n"); @@ -4466,7 +4578,7 @@ static void ena_update_on_link_change(void *adapter_data, ENA_ADMIN_AENQ_LINK_CHANGE_DESC_LINK_STATUS_MASK; if (status) { - netdev_dbg(adapter->netdev, "%s\n", __func__); + netif_dbg(adapter, ifup, adapter->netdev, "%s\n", __func__); set_bit(ENA_FLAG_LINK_UP, &adapter->flags); if (!test_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags)) netif_carrier_on(adapter->netdev); @@ -4482,14 +4594,20 @@ static void ena_keep_alive_wd(void *adapter_data, struct ena_adapter *adapter = (struct ena_adapter *)adapter_data; struct ena_admin_aenq_keep_alive_desc *desc; u64 rx_drops; + u64 tx_drops; desc = (struct ena_admin_aenq_keep_alive_desc *)aenq_e; adapter->last_keep_alive_jiffies = jiffies; rx_drops = ((u64)desc->rx_drops_high << 32) | desc->rx_drops_low; + tx_drops = ((u64)desc->tx_drops_high << 32) | desc->tx_drops_low; u64_stats_update_begin(&adapter->syncp); + /* These stats are accumulated by the device, so the counters indicate + * all drops since last reset. + */ adapter->dev_stats.rx_drops = rx_drops; + adapter->dev_stats.tx_drops = tx_drops; u64_stats_update_end(&adapter->syncp); } @@ -4504,7 +4622,7 @@ static void ena_notification(void *adapter_data, aenq_e->aenq_common_desc.group, ENA_ADMIN_NOTIFICATION); - switch (aenq_e->aenq_common_desc.syndrom) { + switch (aenq_e->aenq_common_desc.syndrome) { case ENA_ADMIN_UPDATE_HINTS: hints = (struct ena_admin_ena_hw_hints *) (&aenq_e->inline_data_w4); @@ -4513,7 +4631,7 @@ static void ena_notification(void *adapter_data, default: netif_err(adapter, drv, adapter->netdev, "Invalid aenq notification link state %d\n", - aenq_e->aenq_common_desc.syndrom); + aenq_e->aenq_common_desc.syndrome); } } |