| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1284719154.3391.84.camel@edumazet-laptop>
Date: Fri, 17 Sep 2010 12:25:54 +0200
From: Eric Dumazet <eric.dumazet@...il.com>
To: Krishna Kumar <krkumar2@...ibm.com>
Cc: rusty@...tcorp.com.au, davem@...emloft.net, mst@...hat.com,
kvm@...r.kernel.org, arnd@...db.de, netdev@...r.kernel.org,
avi@...hat.com, anthony@...emonkey.ws
Subject: Re: [v2 RFC PATCH 2/4] Changes for virtio-net
Le vendredi 17 septembre 2010 à 15:33 +0530, Krishna Kumar a écrit :
> Implement mq virtio-net driver.
>
> Though struct virtio_net_config changes, it works with old
> qemu's since the last element is not accessed, unless qemu
> sets VIRTIO_NET_F_NUMTXQS.
>
> Signed-off-by: Krishna Kumar <krkumar2@...ibm.com>
> ---
> drivers/net/virtio_net.c | 213 ++++++++++++++++++++++++++---------
> include/linux/virtio_net.h | 3
> 2 files changed, 163 insertions(+), 53 deletions(-)
>
> diff -ruNp org2/include/linux/virtio_net.h tx_only2/include/linux/virtio_net.h
> --- org2/include/linux/virtio_net.h 2010-02-10 13:20:27.000000000 +0530
> +++ tx_only2/include/linux/virtio_net.h 2010-09-16 15:24:01.000000000 +0530
> @@ -26,6 +26,7 @@
> #define VIRTIO_NET_F_CTRL_RX 18 /* Control channel RX mode support */
> #define VIRTIO_NET_F_CTRL_VLAN 19 /* Control channel VLAN filtering */
> #define VIRTIO_NET_F_CTRL_RX_EXTRA 20 /* Extra RX mode control support */
> +#define VIRTIO_NET_F_NUMTXQS 21 /* Device supports multiple TX queue */
>
> #define VIRTIO_NET_S_LINK_UP 1 /* Link is up */
>
> @@ -34,6 +35,8 @@ struct virtio_net_config {
> __u8 mac[6];
> /* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
> __u16 status;
> + /* number of transmit queues */
> + __u16 numtxqs;
> } __attribute__((packed));
>
> /* This is the first element of the scatter-gather list. If you don't
> diff -ruNp org2/drivers/net/virtio_net.c tx_only2/drivers/net/virtio_net.c
> --- org2/drivers/net/virtio_net.c 2010-07-08 12:54:32.000000000 +0530
> +++ tx_only2/drivers/net/virtio_net.c 2010-09-16 15:24:01.000000000 +0530
> @@ -40,9 +40,20 @@ module_param(gso, bool, 0444);
>
> #define VIRTNET_SEND_COMMAND_SG_MAX 2
>
> +/* Our representation of a send virtqueue */
> +struct send_queue {
> + struct virtqueue *svq;
> +
> + /* TX: fragments + linear part + virtio header */
> + struct scatterlist tx_sg[MAX_SKB_FRAGS + 2];
> +};
You probably want ____cacheline_aligned_in_smp
> +
> struct virtnet_info {
> struct virtio_device *vdev;
> - struct virtqueue *rvq, *svq, *cvq;
> + int numtxqs; /* Number of tx queues */
> + struct send_queue *sq;
> + struct virtqueue *rvq;
> + struct virtqueue *cvq;
> struct net_device *dev;
struct napi will probably be dirtied by RX processing
You should make sure it doesnt dirty cache line of above (read mostly)
fields
> struct napi_struct napi;
> unsigned int status;
> @@ -62,9 +73,8 @@ struct virtnet_info {
> /* Chain pages by the private ptr. */
> struct page *pages;
>
> - /* fragments + linear part + virtio header */
> + /* RX: fragments + linear part + virtio header */
> struct scatterlist rx_sg[MAX_SKB_FRAGS + 2];
> - struct scatterlist tx_sg[MAX_SKB_FRAGS + 2];
> };
>
> struct skb_vnet_hdr {
> @@ -120,12 +130,13 @@ static struct page *get_a_page(struct vi
> static void skb_xmit_done(struct virtqueue *svq)
> {
> struct virtnet_info *vi = svq->vdev->priv;
> + int qnum = svq->queue_index - 1; /* 0 is RX vq */
>
> /* Suppress further interrupts. */
> virtqueue_disable_cb(svq);
>
> /* We were probably waiting for more output buffers. */
> - netif_wake_queue(vi->dev);
> + netif_wake_subqueue(vi->dev, qnum);
> }
>
> static void set_skb_frag(struct sk_buff *skb, struct page *page,
> @@ -495,12 +506,13 @@ again:
> return received;
> }
>
> -static unsigned int free_old_xmit_skbs(struct virtnet_info *vi)
> +static unsigned int free_old_xmit_skbs(struct virtnet_info *vi,
> + struct virtqueue *svq)
> {
> struct sk_buff *skb;
> unsigned int len, tot_sgs = 0;
>
> - while ((skb = virtqueue_get_buf(vi->svq, &len)) != NULL) {
> + while ((skb = virtqueue_get_buf(svq, &len)) != NULL) {
> pr_debug("Sent skb %p\n", skb);
> vi->dev->stats.tx_bytes += skb->len;
> vi->dev->stats.tx_packets++;
> @@ -510,7 +522,8 @@ static unsigned int free_old_xmit_skbs(s
> return tot_sgs;
> }
>
> -static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
> +static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb,
> + struct virtqueue *svq, struct scatterlist *tx_sg)
> {
> struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
> const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
> @@ -548,12 +561,12 @@ static int xmit_skb(struct virtnet_info
>
> /* Encode metadata header at front. */
> if (vi->mergeable_rx_bufs)
> - sg_set_buf(vi->tx_sg, &hdr->mhdr, sizeof hdr->mhdr);
> + sg_set_buf(tx_sg, &hdr->mhdr, sizeof hdr->mhdr);
> else
> - sg_set_buf(vi->tx_sg, &hdr->hdr, sizeof hdr->hdr);
> + sg_set_buf(tx_sg, &hdr->hdr, sizeof hdr->hdr);
>
> - hdr->num_sg = skb_to_sgvec(skb, vi->tx_sg + 1, 0, skb->len) + 1;
> - return virtqueue_add_buf(vi->svq, vi->tx_sg, hdr->num_sg,
> + hdr->num_sg = skb_to_sgvec(skb, tx_sg + 1, 0, skb->len) + 1;
> + return virtqueue_add_buf(svq, tx_sg, hdr->num_sg,
> 0, skb);
> }
>
> @@ -561,31 +574,34 @@ static netdev_tx_t start_xmit(struct sk_
> {
> struct virtnet_info *vi = netdev_priv(dev);
> int capacity;
> + int qnum = skb_get_queue_mapping(skb);
> + struct virtqueue *svq = vi->sq[qnum].svq;
>
> /* Free up any pending old buffers before queueing new ones. */
> - free_old_xmit_skbs(vi);
> + free_old_xmit_skbs(vi, svq);
>
> /* Try to transmit */
> - capacity = xmit_skb(vi, skb);
> + capacity = xmit_skb(vi, skb, svq, vi->sq[qnum].tx_sg);
>
> /* This can happen with OOM and indirect buffers. */
> if (unlikely(capacity < 0)) {
> if (net_ratelimit()) {
> if (likely(capacity == -ENOMEM)) {
> dev_warn(&dev->dev,
> - "TX queue failure: out of memory\n");
> + "TXQ (%d) failure: out of memory\n",
> + qnum);
> } else {
> dev->stats.tx_fifo_errors++;
> dev_warn(&dev->dev,
> - "Unexpected TX queue failure: %d\n",
> - capacity);
> + "Unexpected TXQ (%d) failure: %d\n",
> + qnum, capacity);
> }
> }
> dev->stats.tx_dropped++;
> kfree_skb(skb);
> return NETDEV_TX_OK;
> }
> - virtqueue_kick(vi->svq);
> + virtqueue_kick(svq);
>
> /* Don't wait up for transmitted skbs to be freed. */
> skb_orphan(skb);
> @@ -594,13 +610,13 @@ static netdev_tx_t start_xmit(struct sk_
> /* Apparently nice girls don't return TX_BUSY; stop the queue
> * before it gets out of hand. Naturally, this wastes entries. */
> if (capacity < 2+MAX_SKB_FRAGS) {
> - netif_stop_queue(dev);
> - if (unlikely(!virtqueue_enable_cb(vi->svq))) {
> + netif_stop_subqueue(dev, qnum);
> + if (unlikely(!virtqueue_enable_cb(svq))) {
> /* More just got used, free them then recheck. */
> - capacity += free_old_xmit_skbs(vi);
> + capacity += free_old_xmit_skbs(vi, svq);
> if (capacity >= 2+MAX_SKB_FRAGS) {
> - netif_start_queue(dev);
> - virtqueue_disable_cb(vi->svq);
> + netif_start_subqueue(dev, qnum);
> + virtqueue_disable_cb(svq);
> }
> }
> }
> @@ -871,10 +887,10 @@ static void virtnet_update_status(struct
>
> if (vi->status & VIRTIO_NET_S_LINK_UP) {
> netif_carrier_on(vi->dev);
> - netif_wake_queue(vi->dev);
> + netif_tx_wake_all_queues(vi->dev);
> } else {
> netif_carrier_off(vi->dev);
> - netif_stop_queue(vi->dev);
> + netif_tx_stop_all_queues(vi->dev);
> }
> }
>
> @@ -885,18 +901,112 @@ static void virtnet_config_changed(struc
> virtnet_update_status(vi);
> }
>
> +#define MAX_DEVICE_NAME 16
> +static int initialize_vqs(struct virtnet_info *vi, int numtxqs)
> +{
> + vq_callback_t **callbacks;
> + struct virtqueue **vqs;
> + int i, err = -ENOMEM;
> + int totalvqs;
> + char **names;
> +
> + /* Allocate send queues */
no check on numtxqs ? Hmm...
Please then use kcalloc(numtxqs, sizeof(*vi->sq), GFP_KERNEL) so that
some check is done for you ;)
> + vi->sq = kzalloc(numtxqs * sizeof(*vi->sq), GFP_KERNEL);
> + if (!vi->sq)
> + goto out;
> +
> + /* setup initial send queue parameters */
> + for (i = 0; i < numtxqs; i++)
> + sg_init_table(vi->sq[i].tx_sg, ARRAY_SIZE(vi->sq[i].tx_sg));
> +
> + /*
> + * We expect 1 RX virtqueue followed by 'numtxqs' TX virtqueues, and
> + * optionally one control virtqueue.
> + */
> + totalvqs = 1 + numtxqs +
> + virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ);
> +
> + /* Setup parameters for find_vqs */
> + vqs = kmalloc(totalvqs * sizeof(*vqs), GFP_KERNEL);
> + callbacks = kmalloc(totalvqs * sizeof(*callbacks), GFP_KERNEL);
> + names = kzalloc(totalvqs * sizeof(*names), GFP_KERNEL);
> + if (!vqs || !callbacks || !names)
> + goto free_mem;
> +
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists