From b9f7425239a09903629f71f719654983481b00aa Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 20 Jul 2023 04:38:38 -0400 Subject: virtio-net: convert rx mode setting to use workqueue This patch convert rx mode setting to be done in a workqueue, this is a must for allow to sleep when waiting for the cvq command to response since current code is executed under addr spin lock. Note that we need to disable and flush the workqueue during freeze, this means the rx mode setting is lost after resuming. This is not the bug of this patch as we never try to restore rx mode setting during resume. Signed-off-by: Jason Wang Message-Id: <20230720083839.481487-2-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Shannon Nelson --- drivers/net/virtio_net.c | 55 +++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 52 insertions(+), 3 deletions(-) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d7ce4a1011ea..46fc86fe62df 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -304,6 +304,12 @@ struct virtnet_info { /* Work struct for config space updates */ struct work_struct config_work; + /* Work struct for setting rx mode */ + struct work_struct rx_mode_work; + + /* OK to queue work setting RX mode? */ + bool rx_mode_work_enabled; + /* Does the affinity hint is set for virtqueues? */ bool affinity_hint_set; @@ -447,6 +453,20 @@ static void disable_delayed_refill(struct virtnet_info *vi) spin_unlock_bh(&vi->refill_lock); } +static void enable_rx_mode_work(struct virtnet_info *vi) +{ + rtnl_lock(); + vi->rx_mode_work_enabled = true; + rtnl_unlock(); +} + +static void disable_rx_mode_work(struct virtnet_info *vi) +{ + rtnl_lock(); + vi->rx_mode_work_enabled = false; + rtnl_unlock(); +} + static void virtqueue_napi_schedule(struct napi_struct *napi, struct virtqueue *vq) { @@ -2706,9 +2726,11 @@ static int virtnet_close(struct net_device *dev) return 0; } -static void virtnet_set_rx_mode(struct net_device *dev) +static void virtnet_rx_mode_work(struct work_struct *work) { - struct virtnet_info *vi = netdev_priv(dev); + struct virtnet_info *vi = + container_of(work, struct virtnet_info, rx_mode_work); + struct net_device *dev = vi->dev; struct scatterlist sg[2]; struct virtio_net_ctrl_mac *mac_data; struct netdev_hw_addr *ha; @@ -2721,6 +2743,8 @@ static void virtnet_set_rx_mode(struct net_device *dev) if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX)) return; + rtnl_lock(); + vi->ctrl->promisc = ((dev->flags & IFF_PROMISC) != 0); vi->ctrl->allmulti = ((dev->flags & IFF_ALLMULTI) != 0); @@ -2738,14 +2762,19 @@ static void virtnet_set_rx_mode(struct net_device *dev) dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n", vi->ctrl->allmulti ? "en" : "dis"); + netif_addr_lock_bh(dev); + uc_count = netdev_uc_count(dev); mc_count = netdev_mc_count(dev); /* MAC filter - use one buffer for both lists */ buf = kzalloc(((uc_count + mc_count) * ETH_ALEN) + (2 * sizeof(mac_data->entries)), GFP_ATOMIC); mac_data = buf; - if (!buf) + if (!buf) { + netif_addr_unlock_bh(dev); + rtnl_unlock(); return; + } sg_init_table(sg, 2); @@ -2766,6 +2795,8 @@ static void virtnet_set_rx_mode(struct net_device *dev) netdev_for_each_mc_addr(ha, dev) memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN); + netif_addr_unlock_bh(dev); + sg_set_buf(&sg[1], mac_data, sizeof(mac_data->entries) + (mc_count * ETH_ALEN)); @@ -2773,9 +2804,19 @@ static void virtnet_set_rx_mode(struct net_device *dev) VIRTIO_NET_CTRL_MAC_TABLE_SET, sg)) dev_warn(&dev->dev, "Failed to set MAC filter table.\n"); + rtnl_unlock(); + kfree(buf); } +static void virtnet_set_rx_mode(struct net_device *dev) +{ + struct virtnet_info *vi = netdev_priv(dev); + + if (vi->rx_mode_work_enabled) + schedule_work(&vi->rx_mode_work); +} + static int virtnet_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { @@ -3856,6 +3897,8 @@ static void virtnet_freeze_down(struct virtio_device *vdev) /* Make sure no work handler is accessing the device */ flush_work(&vi->config_work); + disable_rx_mode_work(vi); + flush_work(&vi->rx_mode_work); netif_tx_lock_bh(vi->dev); netif_device_detach(vi->dev); @@ -3878,6 +3921,7 @@ static int virtnet_restore_up(struct virtio_device *vdev) virtio_device_ready(vdev); enable_delayed_refill(vi); + enable_rx_mode_work(vi); if (netif_running(vi->dev)) { err = virtnet_open(vi->dev); @@ -4676,6 +4720,7 @@ static int virtnet_probe(struct virtio_device *vdev) vdev->priv = vi; INIT_WORK(&vi->config_work, virtnet_config_changed_work); + INIT_WORK(&vi->rx_mode_work, virtnet_rx_mode_work); spin_lock_init(&vi->refill_lock); if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) { @@ -4798,6 +4843,8 @@ static int virtnet_probe(struct virtio_device *vdev) if (vi->has_rss || vi->has_rss_hash_report) virtnet_init_default_rss(vi); + enable_rx_mode_work(vi); + /* serialize netdev register + virtio_device_ready() with ndo_open() */ rtnl_lock(); @@ -4895,6 +4942,8 @@ static void virtnet_remove(struct virtio_device *vdev) /* Make sure no work handler is accessing the device. */ flush_work(&vi->config_work); + disable_rx_mode_work(vi); + flush_work(&vi->rx_mode_work); unregister_netdev(vi->dev); -- cgit v1.2.3 From 0d197a14716481626f863d2091f4c328bf5412e3 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 20 Jul 2023 04:38:39 -0400 Subject: virtio-net: add cond_resched() to the command waiting loop Adding cond_resched() to the command waiting loop for a better co-operation with the scheduler. This allows to give CPU a breath to run other task(workqueue) instead of busy looping when preemption is not allowed on a device whose CVQ might be slow. Signed-off-by: Jason Wang Message-Id: <20230720083839.481487-3-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Shannon Nelson --- drivers/net/virtio_net.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 46fc86fe62df..e709d4411810 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2570,8 +2570,10 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, * into the hypervisor, so the request should be handled immediately. */ while (!virtqueue_get_buf(vi->cvq, &tmp) && - !virtqueue_is_broken(vi->cvq)) + !virtqueue_is_broken(vi->cvq)) { + cond_resched(); cpu_relax(); + } return vi->ctrl->status == VIRTIO_NET_OK; } -- cgit v1.2.3 From b1dc24aba789190dad0047c1f4c16049dd698769 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Thu, 29 Feb 2024 15:20:42 +0800 Subject: virtio_net: unify the code for recycling the xmit ptr There are two completely similar and independent implementations. This is inconvenient for the subsequent addition of new types. So extract a function from this piece of code and call this function uniformly to recover old xmit ptr. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20240229072044.77388-18-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- drivers/net/virtio_net.c | 82 +++++++++++++++++++++++------------------------- 1 file changed, 39 insertions(+), 43 deletions(-) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index e709d4411810..bc9217b3286b 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -80,6 +80,11 @@ struct virtnet_stat_desc { size_t offset; }; +struct virtnet_sq_free_stats { + u64 packets; + u64 bytes; +}; + struct virtnet_sq_stats { struct u64_stats_sync syncp; u64_stats_t packets; @@ -372,6 +377,31 @@ static struct xdp_frame *ptr_to_xdp(void *ptr) return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG); } +static void __free_old_xmit(struct send_queue *sq, bool in_napi, + struct virtnet_sq_free_stats *stats) +{ + unsigned int len; + void *ptr; + + while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { + ++stats->packets; + + if (!is_xdp_frame(ptr)) { + struct sk_buff *skb = ptr; + + pr_debug("Sent skb %p\n", skb); + + stats->bytes += skb->len; + napi_consume_skb(skb, in_napi); + } else { + struct xdp_frame *frame = ptr_to_xdp(ptr); + + stats->bytes += xdp_get_frame_len(frame); + xdp_return_frame(frame); + } + } +} + /* Converting between virtqueue no. and kernel tx/rx queue no. * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq */ @@ -798,37 +828,19 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf) static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) { - unsigned int len; - unsigned int packets = 0; - unsigned int bytes = 0; - void *ptr; + struct virtnet_sq_free_stats stats = {0}; - while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { - if (likely(!is_xdp_frame(ptr))) { - struct sk_buff *skb = ptr; - - pr_debug("Sent skb %p\n", skb); - - bytes += skb->len; - napi_consume_skb(skb, in_napi); - } else { - struct xdp_frame *frame = ptr_to_xdp(ptr); - - bytes += xdp_get_frame_len(frame); - xdp_return_frame(frame); - } - packets++; - } + __free_old_xmit(sq, in_napi, &stats); /* Avoid overhead when no packets have been processed * happens when called speculatively from start_xmit. */ - if (!packets) + if (!stats.packets) return; u64_stats_update_begin(&sq->stats.syncp); - u64_stats_add(&sq->stats.bytes, bytes); - u64_stats_add(&sq->stats.packets, packets); + u64_stats_add(&sq->stats.bytes, stats.bytes); + u64_stats_add(&sq->stats.packets, stats.packets); u64_stats_update_end(&sq->stats.syncp); } @@ -967,15 +979,12 @@ static int virtnet_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { struct virtnet_info *vi = netdev_priv(dev); + struct virtnet_sq_free_stats stats = {0}; struct receive_queue *rq = vi->rq; struct bpf_prog *xdp_prog; struct send_queue *sq; - unsigned int len; - int packets = 0; - int bytes = 0; int nxmit = 0; int kicks = 0; - void *ptr; int ret; int i; @@ -994,20 +1003,7 @@ static int virtnet_xdp_xmit(struct net_device *dev, } /* Free up any pending old buffers before queueing new ones. */ - while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { - if (likely(is_xdp_frame(ptr))) { - struct xdp_frame *frame = ptr_to_xdp(ptr); - - bytes += xdp_get_frame_len(frame); - xdp_return_frame(frame); - } else { - struct sk_buff *skb = ptr; - - bytes += skb->len; - napi_consume_skb(skb, false); - } - packets++; - } + __free_old_xmit(sq, false, &stats); for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; @@ -1027,8 +1023,8 @@ static int virtnet_xdp_xmit(struct net_device *dev, } out: u64_stats_update_begin(&sq->stats.syncp); - u64_stats_add(&sq->stats.bytes, bytes); - u64_stats_add(&sq->stats.packets, packets); + u64_stats_add(&sq->stats.bytes, stats.bytes); + u64_stats_add(&sq->stats.packets, stats.packets); u64_stats_add(&sq->stats.xdp_tx, n); u64_stats_add(&sq->stats.xdp_tx_drops, n - nxmit); u64_stats_add(&sq->stats.kicks, kicks); -- cgit v1.2.3 From 5da7137de79ca6ffae3ace77050588cdf5263d33 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Thu, 29 Feb 2024 15:20:43 +0800 Subject: virtio_net: rename free_old_xmit_skbs to free_old_xmit Since free_old_xmit_skbs not only deals with skb, but also xdp frame and subsequent added xsk, so change the name of this function to free_old_xmit. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20240229072044.77388-19-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- drivers/net/virtio_net.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index bc9217b3286b..c22d1118a133 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -826,7 +826,7 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf) virtnet_rq_free_buf(vi, rq, buf); } -static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) +static void free_old_xmit(struct send_queue *sq, bool in_napi) { struct virtnet_sq_free_stats stats = {0}; @@ -880,7 +880,7 @@ static void check_sq_full_and_disable(struct virtnet_info *vi, virtqueue_napi_schedule(&sq->napi, sq->vq); } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { /* More just got used, free them then recheck. */ - free_old_xmit_skbs(sq, false); + free_old_xmit(sq, false); if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) { netif_start_subqueue(dev, qnum); virtqueue_disable_cb(sq->vq); @@ -2176,7 +2176,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq) do { virtqueue_disable_cb(sq->vq); - free_old_xmit_skbs(sq, true); + free_old_xmit(sq, true); } while (unlikely(!virtqueue_enable_cb_delayed(sq->vq))); if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) @@ -2324,7 +2324,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget) txq = netdev_get_tx_queue(vi->dev, index); __netif_tx_lock(txq, raw_smp_processor_id()); virtqueue_disable_cb(sq->vq); - free_old_xmit_skbs(sq, true); + free_old_xmit(sq, true); if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) netif_tx_wake_queue(txq); @@ -2414,7 +2414,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) if (use_napi) virtqueue_disable_cb(sq->vq); - free_old_xmit_skbs(sq, false); + free_old_xmit(sq, false); } while (use_napi && kick && unlikely(!virtqueue_enable_cb_delayed(sq->vq))); -- cgit v1.2.3