diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index fb8cd8469328e..35f26fa1ffe76 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -1077,68 +1077,10 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer, EXPORT_SYMBOL(vmbus_sendpacket); /* - * vmbus_sendpacket_pagebuffer - Send a range of single-page buffer - * packets using a GPADL Direct packet type. This interface allows you - * to control notifying the host. This will be useful for sending - * batched data. Also the sender can control the send flags - * explicitly. - */ -int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, - struct hv_page_buffer pagebuffers[], - u32 pagecount, void *buffer, u32 bufferlen, - u64 requestid) -{ - int i; - struct vmbus_channel_packet_page_buffer desc; - u32 descsize; - u32 packetlen; - u32 packetlen_aligned; - struct kvec bufferlist[3]; - u64 aligned_data = 0; - - if (pagecount > MAX_PAGE_BUFFER_COUNT) - return -EINVAL; - - /* - * Adjust the size down since vmbus_channel_packet_page_buffer is the - * largest size we support - */ - descsize = sizeof(struct vmbus_channel_packet_page_buffer) - - ((MAX_PAGE_BUFFER_COUNT - pagecount) * - sizeof(struct hv_page_buffer)); - packetlen = descsize + bufferlen; - packetlen_aligned = ALIGN(packetlen, sizeof(u64)); - - /* Setup the descriptor */ - desc.type = VM_PKT_DATA_USING_GPA_DIRECT; - desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED; - desc.dataoffset8 = descsize >> 3; /* in 8-bytes granularity */ - desc.length8 = (u16)(packetlen_aligned >> 3); - desc.transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ - desc.reserved = 0; - desc.rangecount = pagecount; - - for (i = 0; i < pagecount; i++) { - desc.range[i].len = pagebuffers[i].len; - desc.range[i].offset = pagebuffers[i].offset; - desc.range[i].pfn = pagebuffers[i].pfn; - } - - bufferlist[0].iov_base = &desc; - bufferlist[0].iov_len = descsize; - bufferlist[1].iov_base = buffer; - bufferlist[1].iov_len = bufferlen; - bufferlist[2].iov_base = &aligned_data; - bufferlist[2].iov_len = (packetlen_aligned - packetlen); - - return hv_ringbuffer_write(channel, bufferlist, 3, requestid, NULL); -} -EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer); - -/* - * vmbus_sendpacket_multipagebuffer - Send a multi-page buffer packet + * vmbus_sendpacket_mpb_desc - Send one or more multi-page buffer packets * using a GPADL Direct packet type. - * The buffer includes the vmbus descriptor. + * The desc argument must include space for the VMBus descriptor. The + * rangecount field must already be set. */ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, struct vmbus_packet_mpb_array *desc, @@ -1160,7 +1102,6 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, desc->length8 = (u16)(packetlen_aligned >> 3); desc->transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ desc->reserved = 0; - desc->rangecount = 1; bufferlist[0].iov_base = desc; bufferlist[0].iov_len = desc_size; diff --git a/drivers/infiniband/hw/mana/device.c b/drivers/infiniband/hw/mana/device.c index 7ac01918ef7c0..21e99baf06f53 100644 --- a/drivers/infiniband/hw/mana/device.c +++ b/drivers/infiniband/hw/mana/device.c @@ -51,6 +51,38 @@ static const struct ib_device_ops mana_ib_dev_ops = { ib_ind_table), }; +static int mana_ib_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct mana_ib_dev *dev = container_of(this, struct mana_ib_dev, nb); + struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + struct gdma_context *gc = dev->gdma_dev->gdma_context; + struct mana_context *mc = gc->mana.driver_data; + struct net_device *ndev; + + /* Only process events from our parent device */ + if (event_dev != mc->ports[0]) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_CHANGEUPPER: + ndev = mana_get_primary_netdev(mc, 0, &dev->dev_tracker); + /* + * RDMA core will setup GID based on updated netdev. + * It's not possible to race with the core as rtnl lock is being + * held. + */ + ib_device_set_netdev(&dev->ib_dev, ndev, 1); + + /* mana_get_primary_netdev() returns ndev with refcount held */ + netdev_put(ndev, &dev->dev_tracker); + + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + static int mana_ib_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id) { @@ -84,10 +116,8 @@ static int mana_ib_probe(struct auxiliary_device *adev, dev->ib_dev.num_comp_vectors = mdev->gdma_context->max_num_queues; dev->ib_dev.dev.parent = mdev->gdma_context->dev; - rcu_read_lock(); /* required to get primary netdev */ - ndev = mana_get_primary_netdev_rcu(mc, 0); + ndev = mana_get_primary_netdev(mc, 0, &dev->dev_tracker); if (!ndev) { - rcu_read_unlock(); ret = -ENODEV; ibdev_err(&dev->ib_dev, "Failed to get netdev for IB port 1"); goto free_ib_device; @@ -95,7 +125,8 @@ static int mana_ib_probe(struct auxiliary_device *adev, ether_addr_copy(mac_addr, ndev->dev_addr); addrconf_addr_eui48((u8 *)&dev->ib_dev.node_guid, ndev->dev_addr); ret = ib_device_set_netdev(&dev->ib_dev, ndev, 1); - rcu_read_unlock(); + /* mana_get_primary_netdev() returns ndev with refcount held */ + netdev_put(ndev, &dev->dev_tracker); if (ret) { ibdev_err(&dev->ib_dev, "Failed to set ib netdev, ret %d", ret); goto free_ib_device; @@ -109,17 +140,25 @@ static int mana_ib_probe(struct auxiliary_device *adev, } dev->gdma_dev = &mdev->gdma_context->mana_ib; + dev->nb.notifier_call = mana_ib_netdev_event; + ret = register_netdevice_notifier(&dev->nb); + if (ret) { + ibdev_err(&dev->ib_dev, "Failed to register net notifier, %d", + ret); + goto deregister_device; + } + ret = mana_ib_gd_query_adapter_caps(dev); if (ret) { ibdev_err(&dev->ib_dev, "Failed to query device caps, ret %d", ret); - goto deregister_device; + goto deregister_net_notifier; } ret = mana_ib_create_eqs(dev); if (ret) { ibdev_err(&dev->ib_dev, "Failed to create EQs, ret %d", ret); - goto deregister_device; + goto deregister_net_notifier; } ret = mana_ib_gd_create_rnic_adapter(dev); @@ -148,6 +187,8 @@ static int mana_ib_probe(struct auxiliary_device *adev, mana_ib_gd_destroy_rnic_adapter(dev); destroy_eqs: mana_ib_destroy_eqs(dev); +deregister_net_notifier: + unregister_netdevice_notifier(&dev->nb); deregister_device: mana_gd_deregister_device(dev->gdma_dev); free_ib_device: @@ -163,6 +204,7 @@ static void mana_ib_remove(struct auxiliary_device *adev) xa_destroy(&dev->qp_table_wq); mana_ib_gd_destroy_rnic_adapter(dev); mana_ib_destroy_eqs(dev); + unregister_netdevice_notifier(&dev->nb); mana_gd_deregister_device(dev->gdma_dev); ib_dealloc_device(&dev->ib_dev); } diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h index b53a5b4de908d..bb9c6b1af24e1 100644 --- a/drivers/infiniband/hw/mana/mana_ib.h +++ b/drivers/infiniband/hw/mana/mana_ib.h @@ -64,6 +64,8 @@ struct mana_ib_dev { struct gdma_queue **eqs; struct xarray qp_table_wq; struct mana_ib_adapter_caps adapter_caps; + netdevice_tracker dev_tracker; + struct notifier_block nb; }; struct mana_ib_wq { diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 469a98f3a846c..ffa3303c76d80 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -134,9 +134,10 @@ static int mana_gd_detect_devices(struct pci_dev *pdev) struct gdma_list_devices_resp resp = {}; struct gdma_general_req req = {}; struct gdma_dev_id dev; - u32 i, max_num_devs; + int found_dev = 0; u16 dev_type; int err; + u32 i; mana_gd_init_req_hdr(&req.hdr, GDMA_LIST_DEVICES, sizeof(req), sizeof(resp)); @@ -148,12 +149,17 @@ static int mana_gd_detect_devices(struct pci_dev *pdev) return err ? err : -EPROTO; } - max_num_devs = min_t(u32, MAX_NUM_GDMA_DEVICES, resp.num_of_devs); - - for (i = 0; i < max_num_devs; i++) { + for (i = 0; i < GDMA_DEV_LIST_SIZE && + found_dev < resp.num_of_devs; i++) { dev = resp.devs[i]; dev_type = dev.type; + /* Skip empty devices */ + if (dev.as_uint32 == 0) + continue; + + found_dev++; + /* HWC is already detected in mana_hwc_create_channel(). */ if (dev_type == GDMA_DEVICE_HWC) continue; @@ -666,8 +672,11 @@ int mana_gd_create_hwc_queue(struct gdma_dev *gd, gmi = &queue->mem_info; err = mana_gd_alloc_memory(gc, spec->queue_size, gmi); - if (err) + if (err) { + dev_err(gc->dev, "GDMA queue type: %d, size: %u, gdma memory allocation err: %d\n", + spec->type, spec->queue_size, err); goto free_q; + } queue->head = 0; queue->tail = 0; @@ -688,6 +697,8 @@ int mana_gd_create_hwc_queue(struct gdma_dev *gd, *queue_ptr = queue; return 0; out: + dev_err(gc->dev, "Failed to create queue type %d of size %u, err: %d\n", + spec->type, spec->queue_size, err); mana_gd_free_memory(gmi); free_q: kfree(queue); @@ -770,7 +781,13 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, } gmi->dma_region_handle = resp.dma_region_handle; + dev_dbg(gc->dev, "Created DMA region handle 0x%llx\n", + gmi->dma_region_handle); out: + if (err) + dev_dbg(gc->dev, + "Failed to create DMA region of length: %u, page_type: %d, status: 0x%x, err: %d\n", + length, req->gdma_page_type, resp.hdr.status, err); kfree(req); return err; } @@ -793,8 +810,11 @@ int mana_gd_create_mana_eq(struct gdma_dev *gd, gmi = &queue->mem_info; err = mana_gd_alloc_memory(gc, spec->queue_size, gmi); - if (err) + if (err) { + dev_err(gc->dev, "GDMA queue type: %d, size: %u, gdma memory allocation err: %d\n", + spec->type, spec->queue_size, err); goto free_q; + } err = mana_gd_create_dma_region(gd, gmi); if (err) @@ -815,6 +835,8 @@ int mana_gd_create_mana_eq(struct gdma_dev *gd, *queue_ptr = queue; return 0; out: + dev_err(gc->dev, "Failed to create queue type %d of size: %u, err: %d\n", + spec->type, spec->queue_size, err); mana_gd_free_memory(gmi); free_q: kfree(queue); @@ -841,8 +863,11 @@ int mana_gd_create_mana_wq_cq(struct gdma_dev *gd, gmi = &queue->mem_info; err = mana_gd_alloc_memory(gc, spec->queue_size, gmi); - if (err) + if (err) { + dev_err(gc->dev, "GDMA queue type: %d, size: %u, memory allocation err: %d\n", + spec->type, spec->queue_size, err); goto free_q; + } err = mana_gd_create_dma_region(gd, gmi); if (err) @@ -862,6 +887,8 @@ int mana_gd_create_mana_wq_cq(struct gdma_dev *gd, *queue_ptr = queue; return 0; out: + dev_err(gc->dev, "Failed to create queue type %d of size: %u, err: %d\n", + spec->type, spec->queue_size, err); mana_gd_free_memory(gmi); free_q: kfree(queue); @@ -1157,8 +1184,11 @@ int mana_gd_post_and_ring(struct gdma_queue *queue, int err; err = mana_gd_post_work_request(queue, wqe_req, wqe_info); - if (err) + if (err) { + dev_err(gc->dev, "Failed to post work req from queue type %d of size %u (err=%d)\n", + queue->type, queue->queue_size, err); return err; + } mana_gd_wq_ring_doorbell(gc, queue); @@ -1435,8 +1465,10 @@ static int mana_gd_setup(struct pci_dev *pdev) mana_smc_init(&gc->shm_channel, gc->dev, gc->shm_base); err = mana_gd_setup_irqs(pdev); - if (err) + if (err) { + dev_err(gc->dev, "Failed to setup IRQs: %d\n", err); return err; + } err = mana_hwc_create_channel(gc); if (err) @@ -1454,12 +1486,14 @@ static int mana_gd_setup(struct pci_dev *pdev) if (err) goto destroy_hwc; + dev_dbg(&pdev->dev, "mana gdma setup successful\n"); return 0; destroy_hwc: mana_hwc_destroy_channel(gc); remove_irq: mana_gd_remove_irqs(pdev); + dev_err(&pdev->dev, "%s failed (error %d)\n", __func__, err); return err; } @@ -1470,6 +1504,7 @@ static void mana_gd_cleanup(struct pci_dev *pdev) mana_hwc_destroy_channel(gc); mana_gd_remove_irqs(pdev); + dev_dbg(&pdev->dev, "mana gdma cleanup successful\n"); } static bool mana_is_pf(unsigned short dev_id) @@ -1488,8 +1523,10 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) BUILD_BUG_ON(2 * MAX_PORTS_IN_MANA_DEV * GDMA_EQE_SIZE > EQ_SIZE); err = pci_enable_device(pdev); - if (err) + if (err) { + dev_err(&pdev->dev, "Failed to enable pci device (err=%d)\n", err); return -ENXIO; + } pci_set_master(pdev); @@ -1498,9 +1535,10 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto disable_dev; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (err) + if (err) { + dev_err(&pdev->dev, "DMA set mask failed: %d\n", err); goto release_region; - + } dma_set_max_seg_size(&pdev->dev, UINT_MAX); err = -ENOMEM; @@ -1578,6 +1616,8 @@ static void mana_gd_remove(struct pci_dev *pdev) pci_release_regions(pdev); pci_disable_device(pdev); + + dev_dbg(&pdev->dev, "mana gdma remove successful\n"); } /* The 'state' parameter is not used. */ diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index a00f915c51881..1ba49602089bb 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -440,7 +440,8 @@ static int mana_hwc_alloc_dma_buf(struct hw_channel_context *hwc, u16 q_depth, gmi = &dma_buf->mem_info; err = mana_gd_alloc_memory(gc, buf_size, gmi); if (err) { - dev_err(hwc->dev, "Failed to allocate DMA buffer: %d\n", err); + dev_err(hwc->dev, "Failed to allocate DMA buffer size: %u, err %d\n", + buf_size, err); goto out; } @@ -529,6 +530,9 @@ static int mana_hwc_create_wq(struct hw_channel_context *hwc, out: if (err) mana_hwc_destroy_wq(hwc, hwc_wq); + + dev_err(hwc->dev, "Failed to create HWC queue size= %u type= %d err= %d\n", + queue_size, q_type, err); return err; } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 849b7621a51c7..d3d2445ddd012 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -52,10 +52,12 @@ static int mana_open(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); int err; - err = mana_alloc_queues(ndev); - if (err) + + if (err) { + netdev_err(ndev, "%s failed to allocate queues: %d\n", __func__, err); return err; + } apc->port_is_up = true; @@ -64,7 +66,7 @@ static int mana_open(struct net_device *ndev) netif_carrier_on(ndev); netif_tx_wake_all_queues(ndev); - + netdev_dbg(ndev, "%s successful\n", __func__); return 0; } @@ -176,6 +178,9 @@ static int mana_map_skb(struct sk_buff *skb, struct mana_port_context *apc, return 0; frag_err: + if (net_ratelimit()) + netdev_err(apc->ndev, "Failed to map skb of size %u to DMA\n", + skb->len); for (i = sg_i - 1; i >= hsg; i--) dma_unmap_page(dev, ash->dma_handle[i], ash->size[i], DMA_TO_DEVICE); @@ -256,6 +261,9 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (skb_cow_head(skb, MANA_HEADROOM)) goto tx_drop_count; + if (unlikely(ipv6_hopopt_jumbo_remove(skb))) + goto tx_drop_count; + txq = &apc->tx_qp[txq_idx].txq; gdma_sq = txq->gdma_sq; cq = &apc->tx_qp[txq_idx].tx_cq; @@ -652,30 +660,16 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu mpc->rxbpre_total = 0; for (i = 0; i < num_rxb; i++) { - if (mpc->rxbpre_alloc_size > PAGE_SIZE) { - va = netdev_alloc_frag(mpc->rxbpre_alloc_size); - if (!va) - goto error; - - page = virt_to_head_page(va); - /* Check if the frag falls back to single page */ - if (compound_order(page) < - get_order(mpc->rxbpre_alloc_size)) { - put_page(page); - goto error; - } - } else { - page = dev_alloc_page(); - if (!page) - goto error; + page = dev_alloc_pages(get_order(mpc->rxbpre_alloc_size)); + if (!page) + goto error; - va = page_to_virt(page); - } + va = page_to_virt(page); da = dma_map_single(dev, va + mpc->rxbpre_headroom, mpc->rxbpre_datasize, DMA_FROM_DEVICE); if (dma_mapping_error(dev, da)) { - put_page(virt_to_head_page(va)); + put_page(page); goto error; } @@ -687,6 +681,7 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu return 0; error: + netdev_err(mpc->ndev, "Failed to pre-allocate RX buffers for %d queues\n", num_queues); mana_pre_dealloc_rxbufs(mpc); return -ENOMEM; } @@ -1309,8 +1304,10 @@ static int mana_create_eq(struct mana_context *ac) for (i = 0; i < gc->max_num_queues; i++) { spec.eq.msix_index = (i + 1) % gc->num_msix_usable; err = mana_gd_create_mana_eq(gd, &spec, &ac->eqs[i].eq); - if (err) + if (err) { + dev_err(gc->dev, "Failed to create EQ %d : %d\n", i, err); goto out; + } mana_create_eq_debugfs(ac, i); } @@ -1665,7 +1662,7 @@ static void mana_rx_skb(void *buf_va, bool from_pool, } static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, - dma_addr_t *da, bool *from_pool, bool is_napi) + dma_addr_t *da, bool *from_pool) { struct page *page; void *va; @@ -1676,21 +1673,6 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, if (rxq->xdp_save_va) { va = rxq->xdp_save_va; rxq->xdp_save_va = NULL; - } else if (rxq->alloc_size > PAGE_SIZE) { - if (is_napi) - va = napi_alloc_frag(rxq->alloc_size); - else - va = netdev_alloc_frag(rxq->alloc_size); - - if (!va) - return NULL; - - page = virt_to_head_page(va); - /* Check if the frag falls back to single page */ - if (compound_order(page) < get_order(rxq->alloc_size)) { - put_page(page); - return NULL; - } } else { page = page_pool_dev_alloc_pages(rxq->page_pool); if (!page) @@ -1723,7 +1705,7 @@ static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq, dma_addr_t da; void *va; - va = mana_get_rxfrag(rxq, dev, &da, &from_pool, true); + va = mana_get_rxfrag(rxq, dev, &da, &from_pool); if (!va) return; @@ -2086,6 +2068,8 @@ static int mana_create_txq(struct mana_port_context *apc, return 0; out: + netdev_err(net, "Failed to create %d TX queues, %d\n", + apc->num_queues, err); mana_destroy_txq(apc); return err; } @@ -2163,7 +2147,7 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key, if (mpc->rxbufs_pre) va = mana_get_rxbuf_pre(rxq, &da); else - va = mana_get_rxfrag(rxq, dev, &da, &from_pool, false); + va = mana_get_rxfrag(rxq, dev, &da, &from_pool); if (!va) return -ENOMEM; @@ -2249,6 +2233,7 @@ static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc) pprm.nid = gc->numa_node; pprm.napi = &rxq->rx_cq.napi; pprm.netdev = rxq->ndev; + pprm.order = get_order(rxq->alloc_size); rxq->page_pool = page_pool_create(&pprm); @@ -2422,6 +2407,7 @@ static int mana_add_rx_queues(struct mana_port_context *apc, rxq = mana_create_rxq(apc, i, &ac->eqs[i], ndev); if (!rxq) { err = -ENOMEM; + netdev_err(ndev, "Failed to create rxq %d : %d\n", i, err); goto out; } @@ -2668,12 +2654,18 @@ int mana_alloc_queues(struct net_device *ndev) int err; err = mana_create_vport(apc, ndev); - if (err) + if (err) { + netdev_err(ndev, "Failed to create vPort %u : %d\n", apc->port_idx, err); return err; + } err = netif_set_real_num_tx_queues(ndev, apc->num_queues); - if (err) + if (err) { + netdev_err(ndev, + "netif_set_real_num_tx_queues () failed for ndev with num_queues %u : %d\n", + apc->num_queues, err); goto destroy_vport; + } err = mana_add_rx_queues(apc, ndev); if (err) @@ -2682,14 +2674,20 @@ int mana_alloc_queues(struct net_device *ndev) apc->rss_state = apc->num_queues > 1 ? TRI_STATE_TRUE : TRI_STATE_FALSE; err = netif_set_real_num_rx_queues(ndev, apc->num_queues); - if (err) + if (err) { + netdev_err(ndev, + "netif_set_real_num_rx_queues () failed for ndev with num_queues %u : %d\n", + apc->num_queues, err); goto destroy_vport; + } mana_rss_table_init(apc); err = mana_config_rss(apc, TRI_STATE_TRUE, true, true); - if (err) + if (err) { + netdev_err(ndev, "Failed to configure RSS table: %d\n", err); goto destroy_vport; + } if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode) { err = mana_pf_register_filter(apc); @@ -2830,8 +2828,10 @@ int mana_detach(struct net_device *ndev, bool from_close) if (apc->port_st_save) { err = mana_dealloc_queues(ndev); - if (err) + if (err) { + netdev_err(ndev, "%s failed to deallocate queues: %d\n", __func__, err); return err; + } } if (!from_close) { @@ -2880,6 +2880,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, ndev->dev_port = port_idx; SET_NETDEV_DEV(ndev, gc->dev); + netif_set_tso_max_size(ndev, GSO_MAX_SIZE); + netif_carrier_off(ndev); netdev_rss_key_fill(apc->hashkey, MANA_HASH_KEY_SIZE); @@ -2975,6 +2977,8 @@ static int add_adev(struct gdma_dev *gd) goto add_fail; gd->adev = adev; + dev_dbg(gd->gdma_context->dev, + "Auxiliary device added successfully\n"); return 0; add_fail: @@ -3017,8 +3021,10 @@ int mana_probe(struct gdma_dev *gd, bool resuming) } err = mana_create_eq(ac); - if (err) + if (err) { + dev_err(dev, "Failed to create EQs: %d\n", err); goto out; + } err = mana_query_device_cfg(ac, MANA_MAJOR_VERSION, MANA_MINOR_VERSION, MANA_MICRO_VERSION, &num_ports, &bm_hostmode); @@ -3076,8 +3082,14 @@ int mana_probe(struct gdma_dev *gd, bool resuming) err = add_adev(gd); out: - if (err) + if (err) { mana_remove(gd, false); + } else { + dev_dbg(dev, "gd=%p, id=%u, num_ports=%d, type=%u, instance=%u\n", + gd, gd->dev_id.as_uint32, ac->num_ports, + gd->dev_id.type, gd->dev_id.instance); + dev_dbg(dev, "%s succeeded\n", __func__); + } return err; } @@ -3139,23 +3151,30 @@ void mana_remove(struct gdma_dev *gd, bool suspending) gd->driver_data = NULL; gd->gdma_context = NULL; kfree(ac); + dev_dbg(dev, "%s succeeded\n", __func__); } -struct net_device *mana_get_primary_netdev_rcu(struct mana_context *ac, u32 port_index) +struct net_device *mana_get_primary_netdev(struct mana_context *ac, + u32 port_index, + netdevice_tracker *tracker) { struct net_device *ndev; - RCU_LOCKDEP_WARN(!rcu_read_lock_held(), - "Taking primary netdev without holding the RCU read lock"); if (port_index >= ac->num_ports) return NULL; - /* When mana is used in netvsc, the upper netdevice should be returned. */ - if (ac->ports[port_index]->flags & IFF_SLAVE) - ndev = netdev_master_upper_dev_get_rcu(ac->ports[port_index]); - else + rcu_read_lock(); + + /* If mana is used in netvsc, the upper netdevice should be returned. */ + ndev = netdev_master_upper_dev_get_rcu(ac->ports[port_index]); + + /* If there is no upper device, use the parent Ethernet device */ + if (!ndev) ndev = ac->ports[port_index]; + netdev_hold(ndev, tracker, GFP_ATOMIC); + rcu_read_unlock(); + return ndev; } -EXPORT_SYMBOL_NS(mana_get_primary_netdev_rcu, NET_MANA); +EXPORT_SYMBOL_NS(mana_get_primary_netdev, NET_MANA); diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index e690b95b1bbb4..e4e1f729a88c0 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -158,7 +158,6 @@ struct hv_netvsc_packet { u8 cp_partial; /* partial copy into send buffer */ u8 rmsg_size; /* RNDIS header and PPI size */ - u8 rmsg_pgcnt; /* page count of RNDIS header and PPI */ u8 page_buf_cnt; u16 q_idx; @@ -893,6 +892,18 @@ struct nvsp_message { sizeof(struct nvsp_message)) #define NETVSC_MIN_IN_MSG_SIZE sizeof(struct vmpacket_descriptor) +/* Maximum # of contiguous data ranges that can make up a trasmitted packet. + * Typically it's the max SKB fragments plus 2 for the rndis packet and the + * linear portion of the SKB. But if MAX_SKB_FRAGS is large, the value may + * need to be limited to MAX_PAGE_BUFFER_COUNT, which is the max # of entries + * in a GPA direct packet sent to netvsp over VMBus. + */ +#if MAX_SKB_FRAGS + 2 < MAX_PAGE_BUFFER_COUNT +#define MAX_DATA_RANGES (MAX_SKB_FRAGS + 2) +#else +#define MAX_DATA_RANGES MAX_PAGE_BUFFER_COUNT +#endif + /* Estimated requestor size: * out_ring_size/min_out_msg_size + in_ring_size/min_in_msg_size */ @@ -1166,6 +1177,8 @@ struct netvsc_device { u32 max_chn; u32 num_chn; + u32 netvsc_gso_max_size; + atomic_t open_chn; struct work_struct subchan_work; wait_queue_head_t subchan_open; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 2b6ec979a62f2..807465dd4c8e3 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -947,8 +947,7 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device, + pend_size; int i; u32 padding = 0; - u32 page_count = packet->cp_partial ? packet->rmsg_pgcnt : - packet->page_buf_cnt; + u32 page_count = packet->cp_partial ? 1 : packet->page_buf_cnt; u32 remain; /* Add padding */ @@ -1049,6 +1048,42 @@ static int netvsc_dma_map(struct hv_device *hv_dev, return 0; } +/* Build an "array" of mpb entries describing the data to be transferred + * over VMBus. After the desc header fields, each "array" entry is variable + * size, and each entry starts after the end of the previous entry. The + * "offset" and "len" fields for each entry imply the size of the entry. + * + * The pfns are in HV_HYP_PAGE_SIZE, because all communication with Hyper-V + * uses that granularity, even if the system page size of the guest is larger. + * Each entry in the input "pb" array must describe a contiguous range of + * guest physical memory so that the pfns are sequential if the range crosses + * a page boundary. The offset field must be < HV_HYP_PAGE_SIZE. + */ +static inline void netvsc_build_mpb_array(struct hv_page_buffer *pb, + u32 page_buffer_count, + struct vmbus_packet_mpb_array *desc, + u32 *desc_size) +{ + struct hv_mpb_array *mpb_entry = &desc->range; + int i, j; + + for (i = 0; i < page_buffer_count; i++) { + u32 offset = pb[i].offset; + u32 len = pb[i].len; + + mpb_entry->offset = offset; + mpb_entry->len = len; + + for (j = 0; j < HVPFN_UP(offset + len); j++) + mpb_entry->pfn_array[j] = pb[i].pfn + j; + + mpb_entry = (struct hv_mpb_array *)&mpb_entry->pfn_array[j]; + } + + desc->rangecount = page_buffer_count; + *desc_size = (char *)mpb_entry - (char *)desc; +} + static inline int netvsc_send_pkt( struct hv_device *device, struct hv_netvsc_packet *packet, @@ -1091,8 +1126,11 @@ static inline int netvsc_send_pkt( packet->dma_range = NULL; if (packet->page_buf_cnt) { + struct vmbus_channel_packet_page_buffer desc; + u32 desc_size; + if (packet->cp_partial) - pb += packet->rmsg_pgcnt; + pb++; ret = netvsc_dma_map(ndev_ctx->device_ctx, packet, pb); if (ret) { @@ -1100,11 +1138,12 @@ static inline int netvsc_send_pkt( goto exit; } - ret = vmbus_sendpacket_pagebuffer(out_channel, - pb, packet->page_buf_cnt, - &nvmsg, sizeof(nvmsg), - req_id); - + netvsc_build_mpb_array(pb, packet->page_buf_cnt, + (struct vmbus_packet_mpb_array *)&desc, + &desc_size); + ret = vmbus_sendpacket_mpb_desc(out_channel, + (struct vmbus_packet_mpb_array *)&desc, + desc_size, &nvmsg, sizeof(nvmsg), req_id); if (ret) netvsc_dma_unmap(ndev_ctx->device_ctx, packet); } else { @@ -1253,7 +1292,7 @@ int netvsc_send(struct net_device *ndev, packet->send_buf_index = section_index; if (packet->cp_partial) { - packet->page_buf_cnt -= packet->rmsg_pgcnt; + packet->page_buf_cnt--; packet->total_data_buflen = msd_len + packet->rmsg_size; } else { packet->page_buf_cnt = 0; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 23180f7b67b6a..2d23e955f8fb6 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -325,43 +325,10 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, return txq; } -static u32 fill_pg_buf(unsigned long hvpfn, u32 offset, u32 len, - struct hv_page_buffer *pb) -{ - int j = 0; - - hvpfn += offset >> HV_HYP_PAGE_SHIFT; - offset = offset & ~HV_HYP_PAGE_MASK; - - while (len > 0) { - unsigned long bytes; - - bytes = HV_HYP_PAGE_SIZE - offset; - if (bytes > len) - bytes = len; - pb[j].pfn = hvpfn; - pb[j].offset = offset; - pb[j].len = bytes; - - offset += bytes; - len -= bytes; - - if (offset == HV_HYP_PAGE_SIZE && len) { - hvpfn++; - offset = 0; - j++; - } - } - - return j + 1; -} - static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb, struct hv_netvsc_packet *packet, struct hv_page_buffer *pb) { - u32 slots_used = 0; - char *data = skb->data; int frags = skb_shinfo(skb)->nr_frags; int i; @@ -370,28 +337,27 @@ static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb, * 2. skb linear data * 3. skb fragment data */ - slots_used += fill_pg_buf(virt_to_hvpfn(hdr), - offset_in_hvpage(hdr), - len, - &pb[slots_used]); + pb[0].offset = offset_in_hvpage(hdr); + pb[0].len = len; + pb[0].pfn = virt_to_hvpfn(hdr); packet->rmsg_size = len; - packet->rmsg_pgcnt = slots_used; - slots_used += fill_pg_buf(virt_to_hvpfn(data), - offset_in_hvpage(data), - skb_headlen(skb), - &pb[slots_used]); + pb[1].offset = offset_in_hvpage(skb->data); + pb[1].len = skb_headlen(skb); + pb[1].pfn = virt_to_hvpfn(skb->data); for (i = 0; i < frags; i++) { skb_frag_t *frag = skb_shinfo(skb)->frags + i; + struct hv_page_buffer *cur_pb = &pb[i + 2]; + u64 pfn = page_to_hvpfn(skb_frag_page(frag)); + u32 offset = skb_frag_off(frag); - slots_used += fill_pg_buf(page_to_hvpfn(skb_frag_page(frag)), - skb_frag_off(frag), - skb_frag_size(frag), - &pb[slots_used]); + cur_pb->offset = offset_in_hvpage(offset); + cur_pb->len = skb_frag_size(frag); + cur_pb->pfn = pfn + (offset >> HV_HYP_PAGE_SHIFT); } - return slots_used; + return frags + 2; } static int count_skb_frag_slots(struct sk_buff *skb) @@ -482,7 +448,7 @@ static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx) struct net_device *vf_netdev; u32 rndis_msg_size; u32 hash; - struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT]; + struct hv_page_buffer pb[MAX_DATA_RANGES]; /* If VF is present and up then redirect packets to it. * Skip the VF if it is marked down or has no carrier. @@ -2461,6 +2427,21 @@ static int netvsc_vf_changed(struct net_device *vf_netdev, unsigned long event) } else { netdev_info(ndev, "Data path switched %s VF: %s\n", vf_is_up ? "to" : "from", vf_netdev->name); + + /* In Azure, when accelerated networking in enabled, other NICs + * like MANA, MLX, are configured as a bonded nic with + * Netvsc(failover) NIC. For bonded NICs, the min of the max + * pkt aggregate size of the members is propagated in the stack. + * In order to allow these NICs (MANA/MLX) to use up to + * GSO_MAX_SIZE gso packet size, we need to allow Netvsc NIC to + * also support this in the guest. + * This value is only increased for netvsc NIC when datapath is + * switched over to the VF + */ + if (vf_is_up) + netif_set_tso_max_size(ndev, vf_netdev->tso_max_size); + else + netif_set_tso_max_size(ndev, netvsc_dev->netvsc_gso_max_size); } return NOTIFY_OK; diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index ecc2128ca9b72..98549cf1d4138 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -225,8 +225,7 @@ static int rndis_filter_send_request(struct rndis_device *dev, struct rndis_request *req) { struct hv_netvsc_packet *packet; - struct hv_page_buffer page_buf[2]; - struct hv_page_buffer *pb = page_buf; + struct hv_page_buffer pb; int ret; /* Setup the packet to send it */ @@ -235,27 +234,14 @@ static int rndis_filter_send_request(struct rndis_device *dev, packet->total_data_buflen = req->request_msg.msg_len; packet->page_buf_cnt = 1; - pb[0].pfn = virt_to_phys(&req->request_msg) >> - HV_HYP_PAGE_SHIFT; - pb[0].len = req->request_msg.msg_len; - pb[0].offset = offset_in_hvpage(&req->request_msg); - - /* Add one page_buf when request_msg crossing page boundary */ - if (pb[0].offset + pb[0].len > HV_HYP_PAGE_SIZE) { - packet->page_buf_cnt++; - pb[0].len = HV_HYP_PAGE_SIZE - - pb[0].offset; - pb[1].pfn = virt_to_phys((void *)&req->request_msg - + pb[0].len) >> HV_HYP_PAGE_SHIFT; - pb[1].offset = 0; - pb[1].len = req->request_msg.msg_len - - pb[0].len; - } + pb.pfn = virt_to_phys(&req->request_msg) >> HV_HYP_PAGE_SHIFT; + pb.len = req->request_msg.msg_len; + pb.offset = offset_in_hvpage(&req->request_msg); trace_rndis_send(dev->ndev, 0, &req->request_msg); rcu_read_lock_bh(); - ret = netvsc_send(dev->ndev, packet, NULL, pb, NULL, false); + ret = netvsc_send(dev->ndev, packet, NULL, &pb, NULL, false); rcu_read_unlock_bh(); return ret; @@ -1351,9 +1337,10 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, struct net_device_context *net_device_ctx = netdev_priv(net); struct ndis_offload hwcaps; struct ndis_offload_params offloads; - unsigned int gso_max_size = GSO_LEGACY_MAX_SIZE; int ret; + nvdev->netvsc_gso_max_size = GSO_LEGACY_MAX_SIZE; + /* Find HW offload capabilities */ ret = rndis_query_hwcaps(rndis_device, nvdev, &hwcaps); if (ret != 0) @@ -1385,8 +1372,8 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, offloads.lso_v2_ipv4 = NDIS_OFFLOAD_PARAMETERS_LSOV2_ENABLED; net->hw_features |= NETIF_F_TSO; - if (hwcaps.lsov2.ip4_maxsz < gso_max_size) - gso_max_size = hwcaps.lsov2.ip4_maxsz; + if (hwcaps.lsov2.ip4_maxsz < nvdev->netvsc_gso_max_size) + nvdev->netvsc_gso_max_size = hwcaps.lsov2.ip4_maxsz; } if (hwcaps.csum.ip4_txcsum & NDIS_TXCSUM_CAP_UDP4) { @@ -1406,8 +1393,8 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, offloads.lso_v2_ipv6 = NDIS_OFFLOAD_PARAMETERS_LSOV2_ENABLED; net->hw_features |= NETIF_F_TSO6; - if (hwcaps.lsov2.ip6_maxsz < gso_max_size) - gso_max_size = hwcaps.lsov2.ip6_maxsz; + if (hwcaps.lsov2.ip6_maxsz < nvdev->netvsc_gso_max_size) + nvdev->netvsc_gso_max_size = hwcaps.lsov2.ip6_maxsz; } if (hwcaps.csum.ip6_txcsum & NDIS_TXCSUM_CAP_UDP6) { @@ -1433,7 +1420,7 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, */ net->features &= ~NETVSC_SUPPORTED_HW_FEATURES | net->hw_features; - netif_set_tso_max_size(net, gso_max_size); + netif_set_tso_max_size(net, nvdev->netvsc_gso_max_size); ret = rndis_filter_set_offload_params(net, nvdev, &offloads); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 3c58837b70a22..337852a9e23c3 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1815,6 +1815,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) return SCSI_MLQUEUE_DEVICE_BUSY; } + payload->rangecount = 1; payload->range.len = length; payload->range.offset = offset_in_hvpg; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 22c22fb910421..df45d1cbee66d 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1226,13 +1226,6 @@ extern int vmbus_sendpacket(struct vmbus_channel *channel, enum vmbus_packet_type type, u32 flags); -extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, - struct hv_page_buffer pagebuffers[], - u32 pagecount, - void *buffer, - u32 bufferlen, - u64 requestid); - extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, struct vmbus_packet_mpb_array *mpb, u32 desc_size, diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 90f56656b5724..62e9d76738628 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -408,8 +408,6 @@ struct gdma_context { struct gdma_dev mana_ib; }; -#define MAX_NUM_GDMA_DEVICES 4 - static inline bool mana_gd_is_mana(struct gdma_dev *gd) { return gd->dev_id.type == GDMA_DEVICE_MANA; @@ -556,11 +554,15 @@ enum { #define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3) #define GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT BIT(5) +/* Driver can handle holes (zeros) in the device list */ +#define GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP BIT(11) + #define GDMA_DRV_CAP_FLAGS1 \ (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \ GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG | \ - GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT) + GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT | \ + GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP) #define GDMA_DRV_CAP_FLAGS2 0 @@ -621,11 +623,12 @@ struct gdma_query_max_resources_resp { }; /* HW DATA */ /* GDMA_LIST_DEVICES */ +#define GDMA_DEV_LIST_SIZE 64 struct gdma_list_devices_resp { struct gdma_resp_hdr hdr; u32 num_of_devs; u32 reserved; - struct gdma_dev_id devs[64]; + struct gdma_dev_id devs[GDMA_DEV_LIST_SIZE]; }; /* HW DATA */ /* GDMA_REGISTER_DEVICE */ diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index e5555d03f6881..38238c1d00bf9 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -829,5 +829,7 @@ int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, u32 doorbell_pg_id); void mana_uncfg_vport(struct mana_port_context *apc); -struct net_device *mana_get_primary_netdev_rcu(struct mana_context *ac, u32 port_index); +struct net_device *mana_get_primary_netdev(struct mana_context *ac, + u32 port_index, + netdevice_tracker *tracker); #endif /* _MANA_H */