--- zzzz-none-000/linux-3.10.107/drivers/net/hyperv/netvsc.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/net/hyperv/netvsc.c 2021-02-04 17:41:59.000000000 +0000 @@ -11,8 +11,7 @@ * more details. * * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 Temple - * Place - Suite 330, Boston, MA 02111-1307 USA. + * this program; if not, see . * * Authors: * Haiyang Zhang @@ -29,6 +28,8 @@ #include #include #include +#include +#include #include "hyperv_net.h" @@ -37,21 +38,39 @@ { struct netvsc_device *net_device; struct net_device *ndev = hv_get_drvdata(device); + int i; net_device = kzalloc(sizeof(struct netvsc_device), GFP_KERNEL); if (!net_device) return NULL; + net_device->cb_buffer = kzalloc(NETVSC_PACKET_SIZE, GFP_KERNEL); + if (!net_device->cb_buffer) { + kfree(net_device); + return NULL; + } + init_waitqueue_head(&net_device->wait_drain); net_device->start_remove = false; net_device->destroy = false; net_device->dev = device; net_device->ndev = ndev; + net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT; + net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT; + + for (i = 0; i < num_online_cpus(); i++) + spin_lock_init(&net_device->msd[i].lock); hv_set_drvdata(device, net_device); return net_device; } +static void free_netvsc_device(struct netvsc_device *nvdev) +{ + kfree(nvdev->cb_buffer); + kfree(nvdev); +} + static struct netvsc_device *get_outbound_net_device(struct hv_device *device) { struct netvsc_device *net_device; @@ -81,7 +100,7 @@ } -static int netvsc_destroy_recv_buf(struct netvsc_device *net_device) +static int netvsc_destroy_buf(struct netvsc_device *net_device) { struct nvsp_message *revoke_packet; int ret = 0; @@ -137,8 +156,7 @@ if (net_device->recv_buf) { /* Free up the receive buffer */ - free_pages((unsigned long)net_device->recv_buf, - get_order(net_device->recv_buf_size)); + vfree(net_device->recv_buf); net_device->recv_buf = NULL; } @@ -148,25 +166,80 @@ net_device->recv_section = NULL; } + /* Deal with the send buffer we may have setup. + * If we got a send section size, it means we received a + * NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE msg (ie sent + * NVSP_MSG1_TYPE_SEND_SEND_BUF msg) therefore, we need + * to send a revoke msg here + */ + if (net_device->send_section_size) { + /* Send the revoke receive buffer */ + revoke_packet = &net_device->revoke_packet; + memset(revoke_packet, 0, sizeof(struct nvsp_message)); + + revoke_packet->hdr.msg_type = + NVSP_MSG1_TYPE_REVOKE_SEND_BUF; + revoke_packet->msg.v1_msg.revoke_send_buf.id = + NETVSC_SEND_BUFFER_ID; + + ret = vmbus_sendpacket(net_device->dev->channel, + revoke_packet, + sizeof(struct nvsp_message), + (unsigned long)revoke_packet, + VM_PKT_DATA_INBAND, 0); + /* If we failed here, we might as well return and + * have a leak rather than continue and a bugchk + */ + if (ret != 0) { + netdev_err(ndev, "unable to send " + "revoke send buffer to netvsp\n"); + return ret; + } + } + /* Teardown the gpadl on the vsp end */ + if (net_device->send_buf_gpadl_handle) { + ret = vmbus_teardown_gpadl(net_device->dev->channel, + net_device->send_buf_gpadl_handle); + + /* If we failed here, we might as well return and have a leak + * rather than continue and a bugchk + */ + if (ret != 0) { + netdev_err(ndev, + "unable to teardown send buffer's gpadl\n"); + return ret; + } + net_device->send_buf_gpadl_handle = 0; + } + if (net_device->send_buf) { + /* Free up the send buffer */ + vfree(net_device->send_buf); + net_device->send_buf = NULL; + } + kfree(net_device->send_section_map); + return ret; } -static int netvsc_init_recv_buf(struct hv_device *device) +static int netvsc_init_buf(struct hv_device *device) { int ret = 0; - int t; + unsigned long t; struct netvsc_device *net_device; struct nvsp_message *init_packet; struct net_device *ndev; + int node; net_device = get_outbound_net_device(device); if (!net_device) return -ENODEV; ndev = net_device->ndev; - net_device->recv_buf = - (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, - get_order(net_device->recv_buf_size)); + node = cpu_to_node(device->channel->target_cpu); + net_device->recv_buf = vzalloc_node(net_device->recv_buf_size, node); + if (!net_device->recv_buf) + net_device->recv_buf = vzalloc(net_device->recv_buf_size); + if (!net_device->recv_buf) { netdev_err(ndev, "unable to allocate receive " "buffer of size %d\n", net_device->recv_buf_size); @@ -252,10 +325,92 @@ goto cleanup; } + /* Now setup the send buffer. + */ + net_device->send_buf = vzalloc_node(net_device->send_buf_size, node); + if (!net_device->send_buf) + net_device->send_buf = vzalloc(net_device->send_buf_size); + if (!net_device->send_buf) { + netdev_err(ndev, "unable to allocate send " + "buffer of size %d\n", net_device->send_buf_size); + ret = -ENOMEM; + goto cleanup; + } + + /* Establish the gpadl handle for this buffer on this + * channel. Note: This call uses the vmbus connection rather + * than the channel to establish the gpadl handle. + */ + ret = vmbus_establish_gpadl(device->channel, net_device->send_buf, + net_device->send_buf_size, + &net_device->send_buf_gpadl_handle); + if (ret != 0) { + netdev_err(ndev, + "unable to establish send buffer's gpadl\n"); + goto cleanup; + } + + /* Notify the NetVsp of the gpadl handle */ + init_packet = &net_device->channel_init_pkt; + memset(init_packet, 0, sizeof(struct nvsp_message)); + init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_SEND_BUF; + init_packet->msg.v1_msg.send_send_buf.gpadl_handle = + net_device->send_buf_gpadl_handle; + init_packet->msg.v1_msg.send_send_buf.id = NETVSC_SEND_BUFFER_ID; + + /* Send the gpadl notification request */ + ret = vmbus_sendpacket(device->channel, init_packet, + sizeof(struct nvsp_message), + (unsigned long)init_packet, + VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (ret != 0) { + netdev_err(ndev, + "unable to send send buffer's gpadl to netvsp\n"); + goto cleanup; + } + + t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ); + BUG_ON(t == 0); + + /* Check the response */ + if (init_packet->msg.v1_msg. + send_send_buf_complete.status != NVSP_STAT_SUCCESS) { + netdev_err(ndev, "Unable to complete send buffer " + "initialization with NetVsp - status %d\n", + init_packet->msg.v1_msg. + send_send_buf_complete.status); + ret = -EINVAL; + goto cleanup; + } + + /* Parse the response */ + net_device->send_section_size = init_packet->msg. + v1_msg.send_send_buf_complete.section_size; + + /* Section count is simply the size divided by the section size. + */ + net_device->send_section_cnt = + net_device->send_buf_size/net_device->send_section_size; + + dev_info(&device->device, "Send section size: %d, Section count:%d\n", + net_device->send_section_size, net_device->send_section_cnt); + + /* Setup state for managing the send buffer. */ + net_device->map_words = DIV_ROUND_UP(net_device->send_section_cnt, + BITS_PER_LONG); + + net_device->send_section_map = + kzalloc(net_device->map_words * sizeof(ulong), GFP_KERNEL); + if (net_device->send_section_map == NULL) { + ret = -ENOMEM; + goto cleanup; + } + goto exit; cleanup: - netvsc_destroy_recv_buf(net_device); + netvsc_destroy_buf(net_device); exit: return ret; @@ -268,7 +423,8 @@ struct nvsp_message *init_packet, u32 nvsp_ver) { - int ret, t; + int ret; + unsigned long t; memset(init_packet, 0, sizeof(struct nvsp_message)); init_packet->hdr.msg_type = NVSP_MSG_TYPE_INIT; @@ -294,15 +450,19 @@ NVSP_STAT_SUCCESS) return -EINVAL; - if (nvsp_ver != NVSP_PROTOCOL_VERSION_2) + if (nvsp_ver == NVSP_PROTOCOL_VERSION_1) return 0; - /* NVSPv2 only: Send NDIS config */ + /* NVSPv2 or later: Send NDIS config */ memset(init_packet, 0, sizeof(struct nvsp_message)); init_packet->hdr.msg_type = NVSP_MSG2_TYPE_SEND_NDIS_CONFIG; - init_packet->msg.v2_msg.send_ndis_config.mtu = net_device->ndev->mtu; + init_packet->msg.v2_msg.send_ndis_config.mtu = net_device->ndev->mtu + + ETH_HLEN; init_packet->msg.v2_msg.send_ndis_config.capability.ieee8021q = 1; + if (nvsp_ver >= NVSP_PROTOCOL_VERSION_5) + init_packet->msg.v2_msg.send_ndis_config.capability.sriov = 1; + ret = vmbus_sendpacket(device->channel, init_packet, sizeof(struct nvsp_message), (unsigned long)init_packet, @@ -318,6 +478,9 @@ struct nvsp_message *init_packet; int ndis_version; struct net_device *ndev; + u32 ver_list[] = { NVSP_PROTOCOL_VERSION_1, NVSP_PROTOCOL_VERSION_2, + NVSP_PROTOCOL_VERSION_4, NVSP_PROTOCOL_VERSION_5 }; + int i, num_ver = 4; /* number of different NVSP versions */ net_device = get_outbound_net_device(device); if (!net_device) @@ -327,13 +490,14 @@ init_packet = &net_device->channel_init_pkt; /* Negotiate the latest NVSP protocol supported */ - if (negotiate_nvsp_ver(device, net_device, init_packet, - NVSP_PROTOCOL_VERSION_2) == 0) { - net_device->nvsp_version = NVSP_PROTOCOL_VERSION_2; - } else if (negotiate_nvsp_ver(device, net_device, init_packet, - NVSP_PROTOCOL_VERSION_1) == 0) { - net_device->nvsp_version = NVSP_PROTOCOL_VERSION_1; - } else { + for (i = num_ver - 1; i >= 0; i--) + if (negotiate_nvsp_ver(device, net_device, init_packet, + ver_list[i]) == 0) { + net_device->nvsp_version = ver_list[i]; + break; + } + + if (i < 0) { ret = -EPROTO; goto cleanup; } @@ -343,7 +507,10 @@ /* Send the ndis version */ memset(init_packet, 0, sizeof(struct nvsp_message)); - ndis_version = 0x00050001; + if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_4) + ndis_version = 0x00060001; + else + ndis_version = 0x0006001e; init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_NDIS_VER; init_packet->msg.v1_msg. @@ -362,7 +529,13 @@ goto cleanup; /* Post the big receive buffer to NetVSP */ - ret = netvsc_init_recv_buf(device); + if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_2) + net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE_LEGACY; + else + net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE; + net_device->send_buf_size = NETVSC_SEND_BUFFER_SIZE; + + ret = netvsc_init_buf(device); cleanup: return ret; @@ -370,7 +543,7 @@ static void netvsc_disconnect_vsp(struct netvsc_device *net_device) { - netvsc_destroy_recv_buf(net_device); + netvsc_destroy_buf(net_device); } /* @@ -379,7 +552,6 @@ int netvsc_device_remove(struct hv_device *device) { struct netvsc_device *net_device; - struct hv_netvsc_packet *netvsc_packet, *pos; unsigned long flags; net_device = hv_get_drvdata(device); @@ -408,13 +580,8 @@ vmbus_close(device->channel); /* Release all resources */ - list_for_each_entry_safe(netvsc_packet, pos, - &net_device->recv_pkt_list, list_ent) { - list_del(&netvsc_packet->list_ent); - kfree(netvsc_packet); - } - - kfree(net_device); + vfree(net_device->sub_cb_buf); + free_netvsc_device(net_device); return 0; } @@ -436,17 +603,21 @@ return avail_write * 100 / ring_info->ring_datasize; } -static void netvsc_send_completion(struct hv_device *device, +static inline void netvsc_free_send_slot(struct netvsc_device *net_device, + u32 index) +{ + sync_change_bit(index, net_device->send_section_map); +} + +static void netvsc_send_completion(struct netvsc_device *net_device, + struct hv_device *device, struct vmpacket_descriptor *packet) { - struct netvsc_device *net_device; struct nvsp_message *nvsp_packet; struct hv_netvsc_packet *nvsc_packet; struct net_device *ndev; + u32 send_index; - net_device = get_inbound_net_device(device); - if (!net_device) - return; ndev = net_device->ndev; nvsp_packet = (struct nvsp_message *)((unsigned long)packet + @@ -456,7 +627,9 @@ (nvsp_packet->hdr.msg_type == NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE) || (nvsp_packet->hdr.msg_type == - NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE)) { + NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE) || + (nvsp_packet->hdr.msg_type == + NVSP_MSG5_TYPE_SUBCHANNEL)) { /* Copy the response back */ memcpy(&net_device->channel_init_pkt, nvsp_packet, sizeof(struct nvsp_message)); @@ -464,28 +637,39 @@ } else if (nvsp_packet->hdr.msg_type == NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE) { int num_outstanding_sends; + u16 q_idx = 0; + struct vmbus_channel *channel = device->channel; + int queue_sends; /* Get the send context */ nvsc_packet = (struct hv_netvsc_packet *)(unsigned long) packet->trans_id; /* Notify the layer above us */ - if (nvsc_packet) - nvsc_packet->completion.send.send_completion( - nvsc_packet->completion.send. - send_completion_ctx); + if (nvsc_packet) { + send_index = nvsc_packet->send_buf_index; + if (send_index != NETVSC_INVALID_INDEX) + netvsc_free_send_slot(net_device, send_index); + q_idx = nvsc_packet->q_idx; + channel = nvsc_packet->channel; + nvsc_packet->send_completion(nvsc_packet-> + send_completion_ctx); + } num_outstanding_sends = atomic_dec_return(&net_device->num_outstanding_sends); + queue_sends = atomic_dec_return(&net_device-> + queue_sends[q_idx]); if (net_device->destroy && num_outstanding_sends == 0) wake_up(&net_device->wait_drain); - if (netif_queue_stopped(ndev) && !net_device->start_remove && - (hv_ringbuf_avail_percent(&device->channel->outbound) - > RING_AVAIL_PERCENT_HIWATER || - num_outstanding_sends < 1)) - netif_wake_queue(ndev); + if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) && + !net_device->start_remove && + (hv_ringbuf_avail_percent(&channel->outbound) > + RING_AVAIL_PERCENT_HIWATER || queue_sends < 1)) + netif_tx_wake_queue(netdev_get_tx_queue( + ndev, q_idx)); } else { netdev_err(ndev, "Unknown send completion packet type- " "%d received!!\n", nvsp_packet->hdr.msg_type); @@ -493,67 +677,158 @@ } -int netvsc_send(struct hv_device *device, - struct hv_netvsc_packet *packet) +static u32 netvsc_get_next_send_section(struct netvsc_device *net_device) { - struct netvsc_device *net_device; - int ret = 0; - struct nvsp_message sendMessage; - struct net_device *ndev; - u64 req_id; + unsigned long index; + u32 max_words = net_device->map_words; + unsigned long *map_addr = (unsigned long *)net_device->send_section_map; + u32 section_cnt = net_device->send_section_cnt; + int ret_val = NETVSC_INVALID_INDEX; + int i; + int prev_val; - net_device = get_outbound_net_device(device); - if (!net_device) - return -ENODEV; - ndev = net_device->ndev; + for (i = 0; i < max_words; i++) { + if (!~(map_addr[i])) + continue; + index = ffz(map_addr[i]); + prev_val = sync_test_and_set_bit(index, &map_addr[i]); + if (prev_val) + continue; + if ((index + (i * BITS_PER_LONG)) >= section_cnt) + break; + ret_val = (index + (i * BITS_PER_LONG)); + break; + } + return ret_val; +} + +static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device, + unsigned int section_index, + u32 pend_size, + struct hv_netvsc_packet *packet) +{ + char *start = net_device->send_buf; + char *dest = start + (section_index * net_device->send_section_size) + + pend_size; + int i; + u32 msg_size = 0; + u32 padding = 0; + u32 remain = packet->total_data_buflen % net_device->pkt_align; + u32 page_count = packet->cp_partial ? packet->rmsg_pgcnt : + packet->page_buf_cnt; + + /* Add padding */ + if (packet->is_data_pkt && packet->xmit_more && remain && + !packet->cp_partial) { + padding = net_device->pkt_align - remain; + packet->rndis_msg->msg_len += padding; + packet->total_data_buflen += padding; + } + + for (i = 0; i < page_count; i++) { + char *src = phys_to_virt(packet->page_buf[i].pfn << PAGE_SHIFT); + u32 offset = packet->page_buf[i].offset; + u32 len = packet->page_buf[i].len; + + memcpy(dest, (src + offset), len); + msg_size += len; + dest += len; + } + + if (padding) { + memset(dest, 0, padding); + msg_size += padding; + } + + return msg_size; +} - sendMessage.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT; +static inline int netvsc_send_pkt( + struct hv_netvsc_packet *packet, + struct netvsc_device *net_device) +{ + struct nvsp_message nvmsg; + struct vmbus_channel *out_channel = packet->channel; + u16 q_idx = packet->q_idx; + struct net_device *ndev = net_device->ndev; + u64 req_id; + int ret; + struct hv_page_buffer *pgbuf; + u32 ring_avail = hv_ringbuf_avail_percent(&out_channel->outbound); + + nvmsg.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT; if (packet->is_data_pkt) { /* 0 is RMC_DATA; */ - sendMessage.msg.v1_msg.send_rndis_pkt.channel_type = 0; + nvmsg.msg.v1_msg.send_rndis_pkt.channel_type = 0; } else { /* 1 is RMC_CONTROL; */ - sendMessage.msg.v1_msg.send_rndis_pkt.channel_type = 1; + nvmsg.msg.v1_msg.send_rndis_pkt.channel_type = 1; } - /* Not using send buffer section */ - sendMessage.msg.v1_msg.send_rndis_pkt.send_buf_section_index = - 0xFFFFFFFF; - sendMessage.msg.v1_msg.send_rndis_pkt.send_buf_section_size = 0; + nvmsg.msg.v1_msg.send_rndis_pkt.send_buf_section_index = + packet->send_buf_index; + if (packet->send_buf_index == NETVSC_INVALID_INDEX) + nvmsg.msg.v1_msg.send_rndis_pkt.send_buf_section_size = 0; + else + nvmsg.msg.v1_msg.send_rndis_pkt.send_buf_section_size = + packet->total_data_buflen; - if (packet->completion.send.send_completion) + if (packet->send_completion) req_id = (ulong)packet; else req_id = 0; + if (out_channel->rescind) + return -ENODEV; + + /* + * It is possible that once we successfully place this packet + * on the ringbuffer, we may stop the queue. In that case, we want + * to notify the host independent of the xmit_more flag. We don't + * need to be precise here; in the worst case we may signal the host + * unnecessarily. + */ + if (ring_avail < (RING_AVAIL_PERCENT_LOWATER + 1)) + packet->xmit_more = false; + if (packet->page_buf_cnt) { - ret = vmbus_sendpacket_pagebuffer(device->channel, - packet->page_buf, - packet->page_buf_cnt, - &sendMessage, - sizeof(struct nvsp_message), - req_id); + pgbuf = packet->cp_partial ? packet->page_buf + + packet->rmsg_pgcnt : packet->page_buf; + ret = vmbus_sendpacket_pagebuffer_ctl(out_channel, + pgbuf, + packet->page_buf_cnt, + &nvmsg, + sizeof(struct nvsp_message), + req_id, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED, + !packet->xmit_more); } else { - ret = vmbus_sendpacket(device->channel, &sendMessage, - sizeof(struct nvsp_message), - req_id, - VM_PKT_DATA_INBAND, - VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + ret = vmbus_sendpacket_ctl(out_channel, &nvmsg, + sizeof(struct nvsp_message), + req_id, + VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED, + !packet->xmit_more); } if (ret == 0) { atomic_inc(&net_device->num_outstanding_sends); - if (hv_ringbuf_avail_percent(&device->channel->outbound) < - RING_AVAIL_PERCENT_LOWATER) { - netif_stop_queue(ndev); + atomic_inc(&net_device->queue_sends[q_idx]); + + if (ring_avail < RING_AVAIL_PERCENT_LOWATER) { + netif_tx_stop_queue(netdev_get_tx_queue(ndev, q_idx)); + if (atomic_read(&net_device-> - num_outstanding_sends) < 1) - netif_wake_queue(ndev); + queue_sends[q_idx]) < 1) + netif_tx_wake_queue(netdev_get_tx_queue( + ndev, q_idx)); } } else if (ret == -EAGAIN) { - netif_stop_queue(ndev); - if (atomic_read(&net_device->num_outstanding_sends) < 1) { - netif_wake_queue(ndev); + netif_tx_stop_queue(netdev_get_tx_queue( + ndev, q_idx)); + if (atomic_read(&net_device->queue_sends[q_idx]) < 1) { + netif_tx_wake_queue(netdev_get_tx_queue( + ndev, q_idx)); ret = -ENOSPC; } } else { @@ -564,14 +839,127 @@ return ret; } +int netvsc_send(struct hv_device *device, + struct hv_netvsc_packet *packet) +{ + struct netvsc_device *net_device; + int ret = 0, m_ret = 0; + struct vmbus_channel *out_channel; + u16 q_idx = packet->q_idx; + u32 pktlen = packet->total_data_buflen, msd_len = 0; + unsigned int section_index = NETVSC_INVALID_INDEX; + unsigned long flag; + struct multi_send_data *msdp; + struct hv_netvsc_packet *msd_send = NULL, *cur_send = NULL; + bool try_batch; + + net_device = get_outbound_net_device(device); + if (!net_device) + return -ENODEV; + + out_channel = net_device->chn_table[q_idx]; + if (!out_channel) { + out_channel = device->channel; + q_idx = 0; + packet->q_idx = 0; + } + packet->channel = out_channel; + packet->send_buf_index = NETVSC_INVALID_INDEX; + packet->cp_partial = false; + + msdp = &net_device->msd[q_idx]; + + /* batch packets in send buffer if possible */ + spin_lock_irqsave(&msdp->lock, flag); + if (msdp->pkt) + msd_len = msdp->pkt->total_data_buflen; + + try_batch = packet->is_data_pkt && msd_len > 0 && msdp->count < + net_device->max_pkt; + + if (try_batch && msd_len + pktlen + net_device->pkt_align < + net_device->send_section_size) { + section_index = msdp->pkt->send_buf_index; + + } else if (try_batch && msd_len + packet->rmsg_size < + net_device->send_section_size) { + section_index = msdp->pkt->send_buf_index; + packet->cp_partial = true; + + } else if (packet->is_data_pkt && pktlen + net_device->pkt_align < + net_device->send_section_size) { + section_index = netvsc_get_next_send_section(net_device); + if (section_index != NETVSC_INVALID_INDEX) { + msd_send = msdp->pkt; + msdp->pkt = NULL; + msdp->count = 0; + msd_len = 0; + } + } + + if (section_index != NETVSC_INVALID_INDEX) { + netvsc_copy_to_send_buf(net_device, + section_index, msd_len, + packet); + + packet->send_buf_index = section_index; + + if (packet->cp_partial) { + packet->page_buf_cnt -= packet->rmsg_pgcnt; + packet->total_data_buflen = msd_len + packet->rmsg_size; + } else { + packet->page_buf_cnt = 0; + packet->total_data_buflen += msd_len; + } + + if (msdp->pkt) + netvsc_xmit_completion(msdp->pkt); + + if (packet->xmit_more && !packet->cp_partial) { + msdp->pkt = packet; + msdp->count++; + } else { + cur_send = packet; + msdp->pkt = NULL; + msdp->count = 0; + } + } else { + msd_send = msdp->pkt; + msdp->pkt = NULL; + msdp->count = 0; + cur_send = packet; + } + + spin_unlock_irqrestore(&msdp->lock, flag); + + if (msd_send) { + m_ret = netvsc_send_pkt(msd_send, net_device); + + if (m_ret != 0) { + netvsc_free_send_slot(net_device, + msd_send->send_buf_index); + netvsc_xmit_completion(msd_send); + } + } + + if (cur_send) + ret = netvsc_send_pkt(cur_send, net_device); + + if (ret != 0 && section_index != NETVSC_INVALID_INDEX) + netvsc_free_send_slot(net_device, section_index); + + return ret; +} + static void netvsc_send_recv_completion(struct hv_device *device, + struct vmbus_channel *channel, + struct netvsc_device *net_device, u64 transaction_id, u32 status) { struct nvsp_message recvcompMessage; int retries = 0; int ret; struct net_device *ndev; - struct netvsc_device *net_device = hv_get_drvdata(device); ndev = net_device->ndev; @@ -582,7 +970,7 @@ retry_send_cmplt: /* Send the completion */ - ret = vmbus_sendpacket(device->channel, &recvcompMessage, + ret = vmbus_sendpacket(channel, &recvcompMessage, sizeof(struct nvsp_message), transaction_id, VM_PKT_COMP, 0); if (ret == 0) { @@ -608,78 +996,20 @@ } } -/* Send a receive completion packet to RNDIS device (ie NetVsp) */ -static void netvsc_receive_completion(void *context) +static void netvsc_receive(struct netvsc_device *net_device, + struct vmbus_channel *channel, + struct hv_device *device, + struct vmpacket_descriptor *packet) { - struct hv_netvsc_packet *packet = context; - struct hv_device *device = packet->device; - struct netvsc_device *net_device; - u64 transaction_id = 0; - bool fsend_receive_comp = false; - unsigned long flags; - struct net_device *ndev; - u32 status = NVSP_STAT_NONE; - - /* - * Even though it seems logical to do a GetOutboundNetDevice() here to - * send out receive completion, we are using GetInboundNetDevice() - * since we may have disable outbound traffic already. - */ - net_device = get_inbound_net_device(device); - if (!net_device) - return; - ndev = net_device->ndev; - - /* Overloading use of the lock. */ - spin_lock_irqsave(&net_device->recv_pkt_list_lock, flags); - - if (packet->status != NVSP_STAT_SUCCESS) - packet->xfer_page_pkt->status = NVSP_STAT_FAIL; - - packet->xfer_page_pkt->count--; - - /* - * Last one in the line that represent 1 xfer page packet. - * Return the xfer page packet itself to the freelist - */ - if (packet->xfer_page_pkt->count == 0) { - fsend_receive_comp = true; - transaction_id = packet->completion.recv.recv_completion_tid; - status = packet->xfer_page_pkt->status; - list_add_tail(&packet->xfer_page_pkt->list_ent, - &net_device->recv_pkt_list); - - } - - /* Put the packet back */ - list_add_tail(&packet->list_ent, &net_device->recv_pkt_list); - spin_unlock_irqrestore(&net_device->recv_pkt_list_lock, flags); - - /* Send a receive completion for the xfer page packet */ - if (fsend_receive_comp) - netvsc_send_recv_completion(device, transaction_id, status); - -} - -static void netvsc_receive(struct hv_device *device, - struct vmpacket_descriptor *packet) -{ - struct netvsc_device *net_device; struct vmtransfer_page_packet_header *vmxferpage_packet; struct nvsp_message *nvsp_packet; - struct hv_netvsc_packet *netvsc_packet = NULL; - /* struct netvsc_driver *netvscDriver; */ - struct xferpage_packet *xferpage_packet = NULL; + struct hv_netvsc_packet nv_pkt; + struct hv_netvsc_packet *netvsc_packet = &nv_pkt; + u32 status = NVSP_STAT_SUCCESS; int i; int count = 0; - unsigned long flags; struct net_device *ndev; - LIST_HEAD(listHead); - - net_device = get_inbound_net_device(device); - if (!net_device) - return; ndev = net_device->ndev; /* @@ -712,77 +1042,13 @@ return; } - /* - * Grab free packets (range count + 1) to represent this xfer - * page packet. +1 to represent the xfer page packet itself. - * We grab it here so that we know exactly how many we can - * fulfil - */ - spin_lock_irqsave(&net_device->recv_pkt_list_lock, flags); - while (!list_empty(&net_device->recv_pkt_list)) { - list_move_tail(net_device->recv_pkt_list.next, &listHead); - if (++count == vmxferpage_packet->range_cnt + 1) - break; - } - spin_unlock_irqrestore(&net_device->recv_pkt_list_lock, flags); - - /* - * We need at least 2 netvsc pkts (1 to represent the xfer - * page and at least 1 for the range) i.e. we can handled - * some of the xfer page packet ranges... - */ - if (count < 2) { - netdev_err(ndev, "Got only %d netvsc pkt...needed " - "%d pkts. Dropping this xfer page packet completely!\n", - count, vmxferpage_packet->range_cnt + 1); - - /* Return it to the freelist */ - spin_lock_irqsave(&net_device->recv_pkt_list_lock, flags); - for (i = count; i != 0; i--) { - list_move_tail(listHead.next, - &net_device->recv_pkt_list); - } - spin_unlock_irqrestore(&net_device->recv_pkt_list_lock, - flags); - - netvsc_send_recv_completion(device, - vmxferpage_packet->d.trans_id, - NVSP_STAT_FAIL); - - return; - } - - /* Remove the 1st packet to represent the xfer page packet itself */ - xferpage_packet = (struct xferpage_packet *)listHead.next; - list_del(&xferpage_packet->list_ent); - xferpage_packet->status = NVSP_STAT_SUCCESS; - - /* This is how much we can satisfy */ - xferpage_packet->count = count - 1; - - if (xferpage_packet->count != vmxferpage_packet->range_cnt) { - netdev_err(ndev, "Needed %d netvsc pkts to satisfy " - "this xfer page...got %d\n", - vmxferpage_packet->range_cnt, xferpage_packet->count); - } + count = vmxferpage_packet->range_cnt; + netvsc_packet->channel = channel; /* Each range represents 1 RNDIS pkt that contains 1 ethernet frame */ - for (i = 0; i < (count - 1); i++) { - netvsc_packet = (struct hv_netvsc_packet *)listHead.next; - list_del(&netvsc_packet->list_ent); - + for (i = 0; i < count; i++) { /* Initialize the netvsc packet */ netvsc_packet->status = NVSP_STAT_SUCCESS; - netvsc_packet->xfer_page_pkt = xferpage_packet; - netvsc_packet->completion.recv.recv_completion = - netvsc_receive_completion; - netvsc_packet->completion.recv.recv_completion_ctx = - netvsc_packet; - netvsc_packet->device = device; - /* Save this so that we can send it back */ - netvsc_packet->completion.recv.recv_completion_tid = - vmxferpage_packet->d.trans_id; - netvsc_packet->data = (void *)((unsigned long)net_device-> recv_buf + vmxferpage_packet->ranges[i].byte_offset); netvsc_packet->total_data_buflen = @@ -791,49 +1057,111 @@ /* Pass it to the upper layer */ rndis_filter_receive(device, netvsc_packet); - netvsc_receive_completion(netvsc_packet-> - completion.recv.recv_completion_ctx); + if (netvsc_packet->status != NVSP_STAT_SUCCESS) + status = NVSP_STAT_FAIL; } + netvsc_send_recv_completion(device, channel, net_device, + vmxferpage_packet->d.trans_id, status); } -static void netvsc_channel_cb(void *context) + +static void netvsc_send_table(struct hv_device *hdev, + struct nvsp_message *nvmsg) +{ + struct netvsc_device *nvscdev; + struct net_device *ndev; + int i; + u32 count, *tab; + + nvscdev = get_outbound_net_device(hdev); + if (!nvscdev) + return; + ndev = nvscdev->ndev; + + count = nvmsg->msg.v5_msg.send_table.count; + if (count != VRSS_SEND_TAB_SIZE) { + netdev_err(ndev, "Received wrong send-table size:%u\n", count); + return; + } + + tab = (u32 *)((unsigned long)&nvmsg->msg.v5_msg.send_table + + nvmsg->msg.v5_msg.send_table.offset); + + for (i = 0; i < count; i++) + nvscdev->send_table[i] = tab[i]; +} + +static void netvsc_send_vf(struct netvsc_device *nvdev, + struct nvsp_message *nvmsg) +{ + nvdev->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; + nvdev->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; +} + +static inline void netvsc_receive_inband(struct hv_device *hdev, + struct netvsc_device *nvdev, + struct nvsp_message *nvmsg) +{ + switch (nvmsg->hdr.msg_type) { + case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE: + netvsc_send_table(hdev, nvmsg); + break; + + case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION: + netvsc_send_vf(nvdev, nvmsg); + break; + } +} + +void netvsc_channel_cb(void *context) { int ret; - struct hv_device *device = context; + struct vmbus_channel *channel = (struct vmbus_channel *)context; + struct hv_device *device; struct netvsc_device *net_device; u32 bytes_recvd; u64 request_id; - unsigned char *packet; struct vmpacket_descriptor *desc; unsigned char *buffer; int bufferlen = NETVSC_PACKET_SIZE; struct net_device *ndev; + struct nvsp_message *nvmsg; - packet = kzalloc(NETVSC_PACKET_SIZE * sizeof(unsigned char), - GFP_ATOMIC); - if (!packet) - return; - buffer = packet; + if (channel->primary_channel != NULL) + device = channel->primary_channel->device_obj; + else + device = channel->device_obj; net_device = get_inbound_net_device(device); if (!net_device) - goto out; + return; ndev = net_device->ndev; + buffer = get_per_channel_state(channel); do { - ret = vmbus_recvpacket_raw(device->channel, buffer, bufferlen, + ret = vmbus_recvpacket_raw(channel, buffer, bufferlen, &bytes_recvd, &request_id); if (ret == 0) { if (bytes_recvd > 0) { desc = (struct vmpacket_descriptor *)buffer; + nvmsg = (struct nvsp_message *)((unsigned long) + desc + (desc->offset8 << 3)); switch (desc->type) { case VM_PKT_COMP: - netvsc_send_completion(device, desc); + netvsc_send_completion(net_device, + device, desc); break; case VM_PKT_DATA_USING_XFER_PAGES: - netvsc_receive(device, desc); + netvsc_receive(net_device, channel, + device, desc); + break; + + case VM_PKT_DATA_INBAND: + netvsc_receive_inband(device, + net_device, + nvmsg); break; default: @@ -845,23 +1173,16 @@ break; } - /* reset */ - if (bufferlen > NETVSC_PACKET_SIZE) { - kfree(buffer); - buffer = packet; - bufferlen = NETVSC_PACKET_SIZE; - } } else { - /* reset */ - if (bufferlen > NETVSC_PACKET_SIZE) { - kfree(buffer); - buffer = packet; - bufferlen = NETVSC_PACKET_SIZE; - } - + /* + * We are done for this pass. + */ break; } + } else if (ret == -ENOBUFS) { + if (bufferlen > NETVSC_PACKET_SIZE) + kfree(buffer); /* Handle large packet */ buffer = kmalloc(bytes_recvd, GFP_ATOMIC); if (buffer == NULL) { @@ -876,8 +1197,8 @@ } } while (1); -out: - kfree(buffer); + if (bufferlen > NETVSC_PACKET_SIZE) + kfree(buffer); return; } @@ -888,18 +1209,16 @@ int netvsc_device_add(struct hv_device *device, void *additional_info) { int ret = 0; - int i; int ring_size = ((struct netvsc_device_info *)additional_info)->ring_size; struct netvsc_device *net_device; - struct hv_netvsc_packet *packet, *pos; struct net_device *ndev; net_device = alloc_net_device(device); - if (!net_device) { - ret = -ENOMEM; - goto cleanup; - } + if (!net_device) + return -ENOMEM; + + net_device->ring_size = ring_size; /* * Coming into this function, struct net_device * is @@ -910,26 +1229,18 @@ */ ndev = net_device->ndev; - /* Initialize the NetVSC channel extension */ - net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE; - spin_lock_init(&net_device->recv_pkt_list_lock); - - INIT_LIST_HEAD(&net_device->recv_pkt_list); - - for (i = 0; i < NETVSC_RECEIVE_PACKETLIST_COUNT; i++) { - packet = kzalloc(sizeof(struct hv_netvsc_packet), GFP_KERNEL); - if (!packet) - break; + /* Add netvsc_device context to netvsc_device */ + net_device->nd_ctx = netdev_priv(ndev); - list_add_tail(&packet->list_ent, - &net_device->recv_pkt_list); - } + /* Initialize the NetVSC channel extension */ init_completion(&net_device->channel_init_wait); + set_per_channel_state(device->channel, net_device->cb_buffer); + /* Open the channel */ ret = vmbus_open(device->channel, ring_size * PAGE_SIZE, ring_size * PAGE_SIZE, NULL, 0, - netvsc_channel_cb, device); + netvsc_channel_cb, device->channel); if (ret != 0) { netdev_err(ndev, "unable to open channel: %d\n", ret); @@ -939,6 +1250,8 @@ /* Channel is opened */ pr_info("hv_netvsc channel opened successfully\n"); + net_device->chn_table[0] = device->channel; + /* Connect with the NetVsp */ ret = netvsc_connect_vsp(device); if (ret != 0) { @@ -954,17 +1267,7 @@ vmbus_close(device->channel); cleanup: - - if (net_device) { - list_for_each_entry_safe(packet, pos, - &net_device->recv_pkt_list, - list_ent) { - list_del(&packet->list_ent); - kfree(packet); - } - - kfree(net_device); - } + free_netvsc_device(net_device); return ret; }