* [net-next RFC V2 PATCH 1/5] tuntap: move socket to tun_file
From: Jason Wang @ 2011-09-17 6:02 UTC (permalink / raw)
To: krkumar2, eric.dumazet, mst, netdev, linux-kernel, virtualization,
davem
Cc: kvm, rusty, qemu-devel, mirq-linux, joe, shemminger
In-Reply-To: <20110917055639.32666.89940.stgit@dhcp-91-7.nay.redhat.com.englab.nay.redhat.com>
In order to let tap can transmit skbs to multiple sockets, the first
step is to move socket from tun_device to tun_file. The reference
between tap device and socket was setup during TUNSETIFF as
usual. After this we can go ahead to allow multiple files to be
attached to tap device.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/tun.c | 347 +++++++++++++++++++++++++++--------------------------
1 files changed, 178 insertions(+), 169 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7bea9c6..b64ad05 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -109,9 +109,16 @@ struct tap_filter {
};
struct tun_file {
+ struct sock sk;
+ struct socket socket;
+ struct socket_wq wq;
+ int vnet_hdr_sz;
+ struct tap_filter txflt;
atomic_t count;
struct tun_struct *tun;
struct net *net;
+ struct fasync_struct *fasync;
+ unsigned int flags;
};
struct tun_sock;
@@ -126,29 +133,12 @@ struct tun_struct {
u32 set_features;
#define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
NETIF_F_TSO6|NETIF_F_UFO)
- struct fasync_struct *fasync;
-
- struct tap_filter txflt;
- struct socket socket;
- struct socket_wq wq;
-
- int vnet_hdr_sz;
#ifdef TUN_DEBUG
int debug;
#endif
};
-struct tun_sock {
- struct sock sk;
- struct tun_struct *tun;
-};
-
-static inline struct tun_sock *tun_sk(struct sock *sk)
-{
- return container_of(sk, struct tun_sock, sk);
-}
-
static int tun_attach(struct tun_struct *tun, struct file *file)
{
struct tun_file *tfile = file->private_data;
@@ -169,10 +159,9 @@ static int tun_attach(struct tun_struct *tun, struct file *file)
err = 0;
tfile->tun = tun;
tun->tfile = tfile;
- tun->socket.file = file;
netif_carrier_on(tun->dev);
dev_hold(tun->dev);
- sock_hold(tun->socket.sk);
+ sock_hold(&tfile->sk);
atomic_inc(&tfile->count);
out:
@@ -182,15 +171,15 @@ out:
static void __tun_detach(struct tun_struct *tun)
{
+ struct tun_file *tfile = tun->tfile;
/* Detach from net device */
netif_tx_lock_bh(tun->dev);
netif_carrier_off(tun->dev);
tun->tfile = NULL;
- tun->socket.file = NULL;
netif_tx_unlock_bh(tun->dev);
/* Drop read queue */
- skb_queue_purge(&tun->socket.sk->sk_receive_queue);
+ skb_queue_purge(&tfile->socket.sk->sk_receive_queue);
/* Drop the extra count on the net device */
dev_put(tun->dev);
@@ -349,19 +338,12 @@ static void tun_net_uninit(struct net_device *dev)
/* Inform the methods they need to stop using the dev.
*/
if (tfile) {
- wake_up_all(&tun->wq.wait);
+ wake_up_all(&tfile->wq.wait);
if (atomic_dec_and_test(&tfile->count))
__tun_detach(tun);
}
}
-static void tun_free_netdev(struct net_device *dev)
-{
- struct tun_struct *tun = netdev_priv(dev);
-
- sock_put(tun->socket.sk);
-}
-
/* Net device open. */
static int tun_net_open(struct net_device *dev)
{
@@ -380,24 +362,25 @@ static int tun_net_close(struct net_device *dev)
static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct tun_struct *tun = netdev_priv(dev);
+ struct tun_file *tfile = tun->tfile;
tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len);
/* Drop packet if interface is not attached */
- if (!tun->tfile)
+ if (!tfile)
goto drop;
/* Drop if the filter does not like it.
* This is a noop if the filter is disabled.
* Filter can be enabled only for the TAP devices. */
- if (!check_filter(&tun->txflt, skb))
+ if (!check_filter(&tfile->txflt, skb))
goto drop;
- if (tun->socket.sk->sk_filter &&
- sk_filter(tun->socket.sk, skb))
+ if (tfile->socket.sk->sk_filter &&
+ sk_filter(tfile->socket.sk, skb))
goto drop;
- if (skb_queue_len(&tun->socket.sk->sk_receive_queue) >= dev->tx_queue_len) {
+ if (skb_queue_len(&tfile->socket.sk->sk_receive_queue) >= dev->tx_queue_len) {
if (!(tun->flags & TUN_ONE_QUEUE)) {
/* Normal queueing mode. */
/* Packet scheduler handles dropping of further packets. */
@@ -418,12 +401,12 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
skb_orphan(skb);
/* Enqueue packet */
- skb_queue_tail(&tun->socket.sk->sk_receive_queue, skb);
+ skb_queue_tail(&tfile->socket.sk->sk_receive_queue, skb);
/* Notify and wake up reader process */
- if (tun->flags & TUN_FASYNC)
- kill_fasync(&tun->fasync, SIGIO, POLL_IN);
- wake_up_interruptible_poll(&tun->wq.wait, POLLIN |
+ if (tfile->flags & TUN_FASYNC)
+ kill_fasync(&tfile->fasync, SIGIO, POLL_IN);
+ wake_up_interruptible_poll(&tfile->wq.wait, POLLIN |
POLLRDNORM | POLLRDBAND);
return NETDEV_TX_OK;
@@ -550,11 +533,11 @@ static unsigned int tun_chr_poll(struct file *file, poll_table * wait)
if (!tun)
return POLLERR;
- sk = tun->socket.sk;
+ sk = tfile->socket.sk;
tun_debug(KERN_INFO, tun, "tun_chr_poll\n");
- poll_wait(file, &tun->wq.wait, wait);
+ poll_wait(file, &tfile->wq.wait, wait);
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= POLLIN | POLLRDNORM;
@@ -573,11 +556,11 @@ static unsigned int tun_chr_poll(struct file *file, poll_table * wait)
/* prepad is the amount to reserve at front. len is length after that.
* linear is a hint as to how much to copy (usually headers). */
-static struct sk_buff *tun_alloc_skb(struct tun_struct *tun,
+static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
size_t prepad, size_t len,
size_t linear, int noblock)
{
- struct sock *sk = tun->socket.sk;
+ struct sock *sk = tfile->socket.sk;
struct sk_buff *skb;
int err;
@@ -601,7 +584,7 @@ static struct sk_buff *tun_alloc_skb(struct tun_struct *tun,
}
/* Get packet from user space buffer */
-static ssize_t tun_get_user(struct tun_struct *tun,
+static ssize_t tun_get_user(struct tun_file *tfile,
const struct iovec *iv, size_t count,
int noblock)
{
@@ -610,8 +593,10 @@ static ssize_t tun_get_user(struct tun_struct *tun,
size_t len = count, align = NET_SKB_PAD;
struct virtio_net_hdr gso = { 0 };
int offset = 0;
+ struct tun_struct *tun = NULL;
+ bool drop = false, error = false;
- if (!(tun->flags & TUN_NO_PI)) {
+ if (!(tfile->flags & TUN_NO_PI)) {
if ((len -= sizeof(pi)) > count)
return -EINVAL;
@@ -620,8 +605,8 @@ static ssize_t tun_get_user(struct tun_struct *tun,
offset += sizeof(pi);
}
- if (tun->flags & TUN_VNET_HDR) {
- if ((len -= tun->vnet_hdr_sz) > count)
+ if (tfile->flags & TUN_VNET_HDR) {
+ if ((len -= tfile->vnet_hdr_sz) > count)
return -EINVAL;
if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso)))
@@ -633,41 +618,43 @@ static ssize_t tun_get_user(struct tun_struct *tun,
if (gso.hdr_len > len)
return -EINVAL;
- offset += tun->vnet_hdr_sz;
+ offset += tfile->vnet_hdr_sz;
}
- if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) {
+ if ((tfile->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) {
align += NET_IP_ALIGN;
if (unlikely(len < ETH_HLEN ||
(gso.hdr_len && gso.hdr_len < ETH_HLEN)))
return -EINVAL;
}
- skb = tun_alloc_skb(tun, align, len, gso.hdr_len, noblock);
+ skb = tun_alloc_skb(tfile, align, len, gso.hdr_len, noblock);
+
if (IS_ERR(skb)) {
if (PTR_ERR(skb) != -EAGAIN)
- tun->dev->stats.rx_dropped++;
- return PTR_ERR(skb);
+ drop = true;
+ count = PTR_ERR(skb);
+ goto err;
}
if (skb_copy_datagram_from_iovec(skb, 0, iv, offset, len)) {
- tun->dev->stats.rx_dropped++;
+ drop = true;
kfree_skb(skb);
- return -EFAULT;
+ count = -EFAULT;
+ goto err;
}
if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
if (!skb_partial_csum_set(skb, gso.csum_start,
gso.csum_offset)) {
- tun->dev->stats.rx_frame_errors++;
- kfree_skb(skb);
- return -EINVAL;
+ error = true;
+ goto err_free;
}
}
- switch (tun->flags & TUN_TYPE_MASK) {
+ switch (tfile->flags & TUN_TYPE_MASK) {
case TUN_TUN_DEV:
- if (tun->flags & TUN_NO_PI) {
+ if (tfile->flags & TUN_NO_PI) {
switch (skb->data[0] & 0xf0) {
case 0x40:
pi.proto = htons(ETH_P_IP);
@@ -676,18 +663,15 @@ static ssize_t tun_get_user(struct tun_struct *tun,
pi.proto = htons(ETH_P_IPV6);
break;
default:
- tun->dev->stats.rx_dropped++;
- kfree_skb(skb);
- return -EINVAL;
+ drop = true;
+ goto err_free;
}
}
skb_reset_mac_header(skb);
skb->protocol = pi.proto;
- skb->dev = tun->dev;
break;
case TUN_TAP_DEV:
- skb->protocol = eth_type_trans(skb, tun->dev);
break;
}
@@ -704,9 +688,8 @@ static ssize_t tun_get_user(struct tun_struct *tun,
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
break;
default:
- tun->dev->stats.rx_frame_errors++;
- kfree_skb(skb);
- return -EINVAL;
+ error = true;
+ goto err_free;
}
if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN)
@@ -714,9 +697,8 @@ static ssize_t tun_get_user(struct tun_struct *tun,
skb_shinfo(skb)->gso_size = gso.gso_size;
if (skb_shinfo(skb)->gso_size == 0) {
- tun->dev->stats.rx_frame_errors++;
- kfree_skb(skb);
- return -EINVAL;
+ error = true;
+ goto err_free;
}
/* Header must be checked, and gso_segs computed. */
@@ -724,11 +706,40 @@ static ssize_t tun_get_user(struct tun_struct *tun,
skb_shinfo(skb)->gso_segs = 0;
}
- netif_rx_ni(skb);
+ tun = __tun_get(tfile);
+ if (!tun) {
+ return -EBADFD;
+ }
+
+ switch (tfile->flags & TUN_TYPE_MASK) {
+ case TUN_TUN_DEV:
+ skb->dev = tun->dev;
+ break;
+ case TUN_TAP_DEV:
+ skb->protocol = eth_type_trans(skb, tun->dev);
+ break;
+ }
+ netif_rx_ni(skb);
tun->dev->stats.rx_packets++;
tun->dev->stats.rx_bytes += len;
+ tun_put(tun);
+ return count;
+err_free:
+ count = -EINVAL;
+ kfree_skb(skb);
+err:
+ tun = __tun_get(tfile);
+ if (!tun) {
+ return -EBADFD;
+ }
+
+ if (drop)
+ tun->dev->stats.rx_dropped++;
+ if (error)
+ tun->dev->stats.rx_frame_errors++;
+ tun_put(tun);
return count;
}
@@ -736,30 +747,25 @@ static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv,
unsigned long count, loff_t pos)
{
struct file *file = iocb->ki_filp;
- struct tun_struct *tun = tun_get(file);
+ struct tun_file *tfile = file->private_data;
ssize_t result;
- if (!tun)
- return -EBADFD;
-
- tun_debug(KERN_INFO, tun, "tun_chr_write %ld\n", count);
-
- result = tun_get_user(tun, iv, iov_length(iv, count),
+ result = tun_get_user(tfile, iv, iov_length(iv, count),
file->f_flags & O_NONBLOCK);
- tun_put(tun);
return result;
}
/* Put packet to the user space buffer */
-static ssize_t tun_put_user(struct tun_struct *tun,
+static ssize_t tun_put_user(struct tun_file *tfile,
struct sk_buff *skb,
const struct iovec *iv, int len)
{
+ struct tun_struct *tun = NULL;
struct tun_pi pi = { 0, skb->protocol };
ssize_t total = 0;
- if (!(tun->flags & TUN_NO_PI)) {
+ if (!(tfile->flags & TUN_NO_PI)) {
if ((len -= sizeof(pi)) < 0)
return -EINVAL;
@@ -773,9 +779,9 @@ static ssize_t tun_put_user(struct tun_struct *tun,
total += sizeof(pi);
}
- if (tun->flags & TUN_VNET_HDR) {
+ if (tfile->flags & TUN_VNET_HDR) {
struct virtio_net_hdr gso = { 0 }; /* no info leak */
- if ((len -= tun->vnet_hdr_sz) < 0)
+ if ((len -= tfile->vnet_hdr_sz) < 0)
return -EINVAL;
if (skb_is_gso(skb)) {
@@ -818,7 +824,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
if (unlikely(memcpy_toiovecend(iv, (void *)&gso, total,
sizeof(gso))))
return -EFAULT;
- total += tun->vnet_hdr_sz;
+ total += tfile->vnet_hdr_sz;
}
len = min_t(int, skb->len, len);
@@ -826,29 +832,32 @@ static ssize_t tun_put_user(struct tun_struct *tun,
skb_copy_datagram_const_iovec(skb, 0, iv, total, len);
total += skb->len;
- tun->dev->stats.tx_packets++;
- tun->dev->stats.tx_bytes += len;
+ tun = __tun_get(tfile);
+ if (tun) {
+ tun->dev->stats.tx_packets++;
+ tun->dev->stats.tx_bytes += len;
+ tun_put(tun);
+ }
return total;
}
-static ssize_t tun_do_read(struct tun_struct *tun,
+static ssize_t tun_do_read(struct tun_file *tfile,
struct kiocb *iocb, const struct iovec *iv,
ssize_t len, int noblock)
{
DECLARE_WAITQUEUE(wait, current);
struct sk_buff *skb;
ssize_t ret = 0;
-
- tun_debug(KERN_INFO, tun, "tun_chr_read\n");
+ struct tun_struct *tun = NULL;
if (unlikely(!noblock))
- add_wait_queue(&tun->wq.wait, &wait);
+ add_wait_queue(&tfile->wq.wait, &wait);
while (len) {
current->state = TASK_INTERRUPTIBLE;
/* Read frames from the queue */
- if (!(skb=skb_dequeue(&tun->socket.sk->sk_receive_queue))) {
+ if (!(skb=skb_dequeue(&tfile->socket.sk->sk_receive_queue))) {
if (noblock) {
ret = -EAGAIN;
break;
@@ -857,25 +866,38 @@ static ssize_t tun_do_read(struct tun_struct *tun,
ret = -ERESTARTSYS;
break;
}
+
+ tun = __tun_get(tfile);
+ if (!tun) {
+ ret = -EIO;
+ break;
+ }
if (tun->dev->reg_state != NETREG_REGISTERED) {
ret = -EIO;
+ tun_put(tun);
break;
}
+ tun_put(tun);
/* Nothing to read, let's sleep */
schedule();
continue;
}
- netif_wake_queue(tun->dev);
- ret = tun_put_user(tun, skb, iv, len);
+ tun = __tun_get(tfile);
+ if (tun) {
+ netif_wake_queue(tun->dev);
+ tun_put(tun);
+ }
+
+ ret = tun_put_user(tfile, skb, iv, len);
kfree_skb(skb);
break;
}
current->state = TASK_RUNNING;
if (unlikely(!noblock))
- remove_wait_queue(&tun->wq.wait, &wait);
+ remove_wait_queue(&tfile->wq.wait, &wait);
return ret;
}
@@ -885,21 +907,17 @@ static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv,
{
struct file *file = iocb->ki_filp;
struct tun_file *tfile = file->private_data;
- struct tun_struct *tun = __tun_get(tfile);
ssize_t len, ret;
- if (!tun)
- return -EBADFD;
len = iov_length(iv, count);
if (len < 0) {
ret = -EINVAL;
goto out;
}
- ret = tun_do_read(tun, iocb, iv, len, file->f_flags & O_NONBLOCK);
+ ret = tun_do_read(tfile, iocb, iv, len, file->f_flags & O_NONBLOCK);
ret = min_t(ssize_t, ret, len);
out:
- tun_put(tun);
return ret;
}
@@ -911,7 +929,7 @@ static void tun_setup(struct net_device *dev)
tun->group = -1;
dev->ethtool_ops = &tun_ethtool_ops;
- dev->destructor = tun_free_netdev;
+ dev->destructor = free_netdev;
}
/* Trivial set of netlink ops to allow deleting tun or tap
@@ -931,7 +949,7 @@ static struct rtnl_link_ops tun_link_ops __read_mostly = {
static void tun_sock_write_space(struct sock *sk)
{
- struct tun_struct *tun;
+ struct tun_file *tfile = NULL;
wait_queue_head_t *wqueue;
if (!sock_writeable(sk))
@@ -945,37 +963,38 @@ static void tun_sock_write_space(struct sock *sk)
wake_up_interruptible_sync_poll(wqueue, POLLOUT |
POLLWRNORM | POLLWRBAND);
- tun = tun_sk(sk)->tun;
- kill_fasync(&tun->fasync, SIGIO, POLL_OUT);
-}
-
-static void tun_sock_destruct(struct sock *sk)
-{
- free_netdev(tun_sk(sk)->tun->dev);
+ tfile = container_of(sk, struct tun_file, sk);
+ kill_fasync(&tfile->fasync, SIGIO, POLL_OUT);
}
static int tun_sendmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len)
{
- struct tun_struct *tun = container_of(sock, struct tun_struct, socket);
- return tun_get_user(tun, m->msg_iov, total_len,
- m->msg_flags & MSG_DONTWAIT);
+ struct tun_file *tfile = container_of(sock, struct tun_file, socket);
+ ssize_t result;
+
+ result= tun_get_user(tfile, m->msg_iov, total_len,
+ m->msg_flags & MSG_DONTWAIT);
+ return result;
}
static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len,
int flags)
{
- struct tun_struct *tun = container_of(sock, struct tun_struct, socket);
+ struct tun_file *tfile = container_of(sock, struct tun_file, socket);
int ret;
+
if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
return -EINVAL;
- ret = tun_do_read(tun, iocb, m->msg_iov, total_len,
+
+ ret = tun_do_read(tfile, iocb, m->msg_iov, total_len,
flags & MSG_DONTWAIT);
if (ret > total_len) {
m->msg_flags |= MSG_TRUNC;
ret = flags & MSG_TRUNC ? ret : total_len;
}
+
return ret;
}
@@ -988,7 +1007,7 @@ static const struct proto_ops tun_socket_ops = {
static struct proto tun_proto = {
.name = "tun",
.owner = THIS_MODULE,
- .obj_size = sizeof(struct tun_sock),
+ .obj_size = sizeof(struct tun_file),
};
static int tun_flags(struct tun_struct *tun)
@@ -1039,8 +1058,8 @@ static DEVICE_ATTR(group, 0444, tun_show_group, NULL);
static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
{
- struct sock *sk;
struct tun_struct *tun;
+ struct tun_file *tfile = file->private_data;
struct net_device *dev;
int err;
@@ -1061,7 +1080,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
(tun->group != -1 && !in_egroup_p(tun->group))) &&
!capable(CAP_NET_ADMIN))
return -EPERM;
- err = security_tun_dev_attach(tun->socket.sk);
+ err = security_tun_dev_attach(tfile->socket.sk);
if (err < 0)
return err;
@@ -1105,24 +1124,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
tun = netdev_priv(dev);
tun->dev = dev;
tun->flags = flags;
- tun->txflt.count = 0;
- tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
- err = -ENOMEM;
- sk = sk_alloc(net, AF_UNSPEC, GFP_KERNEL, &tun_proto);
- if (!sk)
- goto err_free_dev;
-
- tun->socket.wq = &tun->wq;
- init_waitqueue_head(&tun->wq.wait);
- tun->socket.ops = &tun_socket_ops;
- sock_init_data(&tun->socket, sk);
- sk->sk_write_space = tun_sock_write_space;
- sk->sk_sndbuf = INT_MAX;
-
- tun_sk(sk)->tun = tun;
-
- security_tun_dev_post_create(sk);
+ security_tun_dev_post_create(&tfile->sk);
tun_net_init(dev);
@@ -1132,15 +1135,13 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
err = register_netdevice(tun->dev);
if (err < 0)
- goto err_free_sk;
+ goto err_free_dev;
if (device_create_file(&tun->dev->dev, &dev_attr_tun_flags) ||
device_create_file(&tun->dev->dev, &dev_attr_owner) ||
device_create_file(&tun->dev->dev, &dev_attr_group))
pr_err("Failed to create tun sysfs files\n");
- sk->sk_destruct = tun_sock_destruct;
-
err = tun_attach(tun, file);
if (err < 0)
goto failed;
@@ -1163,6 +1164,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
else
tun->flags &= ~TUN_VNET_HDR;
+ /* Cache flags from tun device */
+ tfile->flags = tun->flags;
/* Make sure persistent devices do not get stuck in
* xoff state.
*/
@@ -1172,11 +1175,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
strcpy(ifr->ifr_name, tun->dev->name);
return 0;
- err_free_sk:
- sock_put(sk);
- err_free_dev:
+err_free_dev:
free_netdev(dev);
- failed:
+failed:
return err;
}
@@ -1348,9 +1349,9 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
case TUNSETTXFILTER:
/* Can be set only for TAPs */
ret = -EINVAL;
- if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ if ((tfile->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
break;
- ret = update_filter(&tun->txflt, (void __user *)arg);
+ ret = update_filter(&tfile->txflt, (void __user *)arg);
break;
case SIOCGIFHWADDR:
@@ -1370,7 +1371,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
break;
case TUNGETSNDBUF:
- sndbuf = tun->socket.sk->sk_sndbuf;
+ sndbuf = tfile->socket.sk->sk_sndbuf;
if (copy_to_user(argp, &sndbuf, sizeof(sndbuf)))
ret = -EFAULT;
break;
@@ -1381,11 +1382,11 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
break;
}
- tun->socket.sk->sk_sndbuf = sndbuf;
+ tfile->socket.sk->sk_sndbuf = sndbuf;
break;
case TUNGETVNETHDRSZ:
- vnet_hdr_sz = tun->vnet_hdr_sz;
+ vnet_hdr_sz = tfile->vnet_hdr_sz;
if (copy_to_user(argp, &vnet_hdr_sz, sizeof(vnet_hdr_sz)))
ret = -EFAULT;
break;
@@ -1400,27 +1401,27 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
break;
}
- tun->vnet_hdr_sz = vnet_hdr_sz;
+ tfile->vnet_hdr_sz = vnet_hdr_sz;
break;
case TUNATTACHFILTER:
/* Can be set only for TAPs */
ret = -EINVAL;
- if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ if ((tfile->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
break;
ret = -EFAULT;
if (copy_from_user(&fprog, argp, sizeof(fprog)))
break;
- ret = sk_attach_filter(&fprog, tun->socket.sk);
+ ret = sk_attach_filter(&fprog, tfile->socket.sk);
break;
case TUNDETACHFILTER:
/* Can be set only for TAPs */
ret = -EINVAL;
- if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ if ((tfile->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
break;
- ret = sk_detach_filter(tun->socket.sk);
+ ret = sk_detach_filter(tfile->socket.sk);
break;
default:
@@ -1472,43 +1473,50 @@ static long tun_chr_compat_ioctl(struct file *file,
static int tun_chr_fasync(int fd, struct file *file, int on)
{
- struct tun_struct *tun = tun_get(file);
+ struct tun_file *tfile = file->private_data;
int ret;
- if (!tun)
- return -EBADFD;
-
- tun_debug(KERN_INFO, tun, "tun_chr_fasync %d\n", on);
-
- if ((ret = fasync_helper(fd, file, on, &tun->fasync)) < 0)
+ if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0)
goto out;
if (on) {
ret = __f_setown(file, task_pid(current), PIDTYPE_PID, 0);
if (ret)
goto out;
- tun->flags |= TUN_FASYNC;
+ tfile->flags |= TUN_FASYNC;
} else
- tun->flags &= ~TUN_FASYNC;
+ tfile->flags &= ~TUN_FASYNC;
ret = 0;
out:
- tun_put(tun);
return ret;
}
static int tun_chr_open(struct inode *inode, struct file * file)
{
+ struct net *net = current->nsproxy->net_ns;
struct tun_file *tfile;
DBG1(KERN_INFO, "tunX: tun_chr_open\n");
- tfile = kmalloc(sizeof(*tfile), GFP_KERNEL);
+ tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
+ &tun_proto);
if (!tfile)
return -ENOMEM;
- atomic_set(&tfile->count, 0);
+
tfile->tun = NULL;
- tfile->net = get_net(current->nsproxy->net_ns);
+ tfile->net = net;
+ tfile->txflt.count = 0;
+ tfile->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
+ tfile->socket.wq = &tfile->wq;
+ init_waitqueue_head(&tfile->wq.wait);
+ tfile->socket.file = file;
+ tfile->socket.ops = &tun_socket_ops;
+ sock_init_data(&tfile->socket, &tfile->sk);
+
+ tfile->sk.sk_write_space = tun_sock_write_space;
+ tfile->sk.sk_sndbuf = INT_MAX;
file->private_data = tfile;
+
return 0;
}
@@ -1532,14 +1540,14 @@ static int tun_chr_close(struct inode *inode, struct file *file)
unregister_netdevice(dev);
rtnl_unlock();
}
- }
- tun = tfile->tun;
- if (tun)
- sock_put(tun->socket.sk);
+ /* drop the reference that netdevice holds */
+ sock_put(&tfile->sk);
- put_net(tfile->net);
- kfree(tfile);
+ }
+
+ /* drop the reference that file holds */
+ sock_put(&tfile->sk);
return 0;
}
@@ -1668,13 +1676,14 @@ static void tun_cleanup(void)
struct socket *tun_get_socket(struct file *file)
{
struct tun_struct *tun;
+ struct tun_file *tfile = file->private_data;
if (file->f_op != &tun_fops)
return ERR_PTR(-EINVAL);
tun = tun_get(file);
if (!tun)
return ERR_PTR(-EBADFD);
tun_put(tun);
- return &tun->socket;
+ return &tfile->socket;
}
EXPORT_SYMBOL_GPL(tun_get_socket);
^ permalink raw reply related
* [net-next RFC V2 PATCH 2/5] tuntap: categorize ioctl
From: Jason Wang @ 2011-09-17 6:02 UTC (permalink / raw)
To: krkumar2, eric.dumazet, mst, netdev, linux-kernel, virtualization,
davem
Cc: kvm, rusty, qemu-devel, mirq-linux, joe, shemminger
In-Reply-To: <20110917055639.32666.89940.stgit@dhcp-91-7.nay.redhat.com.englab.nay.redhat.com>
As we've moved socket related structure to file->private_data, we move
the ioctls that only touch socket out of tun_chr_ioctl() as it don't
need hold rtnl lock.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/tun.c | 52 ++++++++++++++++++++++++++++++++++------------------
1 files changed, 34 insertions(+), 18 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index b64ad05..dc768e0 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1238,10 +1238,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
struct tun_file *tfile = file->private_data;
struct tun_struct *tun;
void __user* argp = (void __user*)arg;
- struct sock_fprog fprog;
struct ifreq ifr;
- int sndbuf;
- int vnet_hdr_sz;
int ret;
if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89)
@@ -1346,14 +1343,6 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
ret = set_offload(tun, arg);
break;
- case TUNSETTXFILTER:
- /* Can be set only for TAPs */
- ret = -EINVAL;
- if ((tfile->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
- break;
- ret = update_filter(&tfile->txflt, (void __user *)arg);
- break;
-
case SIOCGIFHWADDR:
/* Get hw address */
memcpy(ifr.ifr_hwaddr.sa_data, tun->dev->dev_addr, ETH_ALEN);
@@ -1370,6 +1359,37 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
ret = dev_set_mac_address(tun->dev, &ifr.ifr_hwaddr);
break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+unlock:
+ rtnl_unlock();
+ if (tun)
+ tun_put(tun);
+ return ret;
+}
+
+static long __tun_socket_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg, int ifreq_len)
+{
+ struct tun_file *tfile = file->private_data;
+ void __user* argp = (void __user*)arg;
+ struct sock_fprog fprog;
+ int sndbuf;
+ int vnet_hdr_sz;
+ int ret = 0;
+
+ switch (cmd) {
+ case TUNSETTXFILTER:
+ /* Can be set only for TAPs */
+ ret = -EINVAL;
+ if ((tfile->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ break;
+ ret = update_filter(&tfile->txflt, (void __user *)arg);
+ break;
+
case TUNGETSNDBUF:
sndbuf = tfile->socket.sk->sk_sndbuf;
if (copy_to_user(argp, &sndbuf, sizeof(sndbuf)))
@@ -1425,21 +1445,17 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
break;
default:
- ret = -EINVAL;
+ ret = __tun_chr_ioctl(file, cmd, arg, ifreq_len);
break;
}
-unlock:
- rtnl_unlock();
- if (tun)
- tun_put(tun);
return ret;
}
static long tun_chr_ioctl(struct file *file,
unsigned int cmd, unsigned long arg)
{
- return __tun_chr_ioctl(file, cmd, arg, sizeof (struct ifreq));
+ return __tun_socket_ioctl(file, cmd, arg, sizeof (struct ifreq));
}
#ifdef CONFIG_COMPAT
@@ -1467,7 +1483,7 @@ static long tun_chr_compat_ioctl(struct file *file,
* driver are compatible though, we don't need to convert the
* contents.
*/
- return __tun_chr_ioctl(file, cmd, arg, sizeof(struct compat_ifreq));
+ return __tun_socket_ioctl(file, cmd, arg, sizeof(struct compat_ifreq));
}
#endif /* CONFIG_COMPAT */
^ permalink raw reply related
* [net-next RFC V2 PATCH 3/5] tuntap: introduce multiqueue flags
From: Jason Wang @ 2011-09-17 6:02 UTC (permalink / raw)
To: krkumar2, eric.dumazet, mst, netdev, linux-kernel, virtualization,
davem
Cc: kvm, rusty, qemu-devel, mirq-linux, joe, shemminger
In-Reply-To: <20110917055639.32666.89940.stgit@dhcp-91-7.nay.redhat.com.englab.nay.redhat.com>
Add flags to be used by creating multiqueue tuntap device.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
include/linux/if_tun.h | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index 06b1829..c92a291 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -34,6 +34,7 @@
#define TUN_ONE_QUEUE 0x0080
#define TUN_PERSIST 0x0100
#define TUN_VNET_HDR 0x0200
+#define TUN_TAP_MQ 0x0400
/* Ioctl defines */
#define TUNSETNOCSUM _IOW('T', 200, int)
@@ -61,6 +62,7 @@
#define IFF_ONE_QUEUE 0x2000
#define IFF_VNET_HDR 0x4000
#define IFF_TUN_EXCL 0x8000
+#define IFF_MULTI_QUEUE 0x0100
/* Features for GSO (TUNSETOFFLOAD). */
#define TUN_F_CSUM 0x01 /* You can hand me unchecksummed packets. */
^ permalink raw reply related
* [net-next RFC V2 PATCH 4/5] tuntap: multiqueue support
From: Jason Wang @ 2011-09-17 6:02 UTC (permalink / raw)
To: krkumar2, eric.dumazet, mst, netdev, linux-kernel, virtualization,
davem
Cc: kvm, rusty, qemu-devel, mirq-linux, joe, shemminger
In-Reply-To: <20110917055639.32666.89940.stgit@dhcp-91-7.nay.redhat.com.englab.nay.redhat.com>
This patch adds multiqueue support for tap device by allowing multiple
sockets to be attached to a tap device. Then we could parallize packets
transmission/reception by put them into different socket.
Following steps were used when choose tx queues:
1 For the packets comes from multiqueue nics, we would just choose the
tx queue based on the which physical queue the packets comes from.
2 Otherwise we try to use rxhash to choose the queue.
3 If all above fails, we always use the first queue.
In order to let the tx path lockless, like macvtap, netif_tx_loch_bh()
isr eplaced by RCU and NETIF_F_LLTX to synchronize between hot path
and systemcall.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/tun.c | 358 +++++++++++++++++++++++++++++++++--------------------
1 files changed, 223 insertions(+), 135 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index dc768e0..ec29f85 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -108,6 +108,8 @@ struct tap_filter {
unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN];
};
+#define MAX_TAP_QUEUES (NR_CPUS < 16 ? NR_CPUS : 16)
+
struct tun_file {
struct sock sk;
struct socket socket;
@@ -115,16 +117,18 @@ struct tun_file {
int vnet_hdr_sz;
struct tap_filter txflt;
atomic_t count;
- struct tun_struct *tun;
+ struct tun_struct __rcu *tun;
struct net *net;
struct fasync_struct *fasync;
unsigned int flags;
+ u16 queue_index;
};
struct tun_sock;
struct tun_struct {
- struct tun_file *tfile;
+ struct tun_file *tfiles[MAX_TAP_QUEUES];
+ unsigned int numqueues;
unsigned int flags;
uid_t owner;
gid_t group;
@@ -139,80 +143,160 @@ struct tun_struct {
#endif
};
-static int tun_attach(struct tun_struct *tun, struct file *file)
+static DEFINE_SPINLOCK(tun_lock);
+
+/*
+ * tun_get_queue(): calculate the queue index
+ * - if skbs comes from mq nics, we can just borrow
+ * - if not, calculate from the hash
+ */
+static struct tun_file *tun_get_queue(struct net_device *dev,
+ struct sk_buff *skb)
{
- struct tun_file *tfile = file->private_data;
- int err;
+ struct tun_struct *tun = netdev_priv(dev);
+ struct tun_file *tfile = NULL;
+ int numqueues = tun->numqueues;
+ __u32 rxq;
- ASSERT_RTNL();
+ BUG_ON(!rcu_read_lock_held());
- netif_tx_lock_bh(tun->dev);
+ if (!numqueues)
+ goto out;
- err = -EINVAL;
- if (tfile->tun)
+ if (numqueues == 1) {
+ tfile = rcu_dereference(tun->tfiles[0]);
goto out;
+ }
- err = -EBUSY;
- if (tun->tfile)
+ if (likely(skb_rx_queue_recorded(skb))) {
+ rxq = skb_get_rx_queue(skb);
+
+ while (unlikely(rxq >= numqueues))
+ rxq -= numqueues;
+
+ tfile = rcu_dereference(tun->tfiles[rxq]);
goto out;
+ }
- err = 0;
- tfile->tun = tun;
- tun->tfile = tfile;
- netif_carrier_on(tun->dev);
- dev_hold(tun->dev);
- sock_hold(&tfile->sk);
- atomic_inc(&tfile->count);
+ /* Check if we can use flow to select a queue */
+ rxq = skb_get_rxhash(skb);
+ if (rxq) {
+ u32 idx = ((u64)rxq * numqueues) >> 32;
+ tfile = rcu_dereference(tun->tfiles[idx]);
+ goto out;
+ }
+ tfile = rcu_dereference(tun->tfiles[0]);
out:
- netif_tx_unlock_bh(tun->dev);
- return err;
+ return tfile;
}
-static void __tun_detach(struct tun_struct *tun)
+static int tun_detach(struct tun_file *tfile, bool clean)
{
- struct tun_file *tfile = tun->tfile;
- /* Detach from net device */
- netif_tx_lock_bh(tun->dev);
- netif_carrier_off(tun->dev);
- tun->tfile = NULL;
- netif_tx_unlock_bh(tun->dev);
-
- /* Drop read queue */
- skb_queue_purge(&tfile->socket.sk->sk_receive_queue);
-
- /* Drop the extra count on the net device */
- dev_put(tun->dev);
-}
+ struct tun_struct *tun;
+ struct net_device *dev = NULL;
+ bool destroy = false;
-static void tun_detach(struct tun_struct *tun)
-{
- rtnl_lock();
- __tun_detach(tun);
- rtnl_unlock();
-}
+ spin_lock(&tun_lock);
-static struct tun_struct *__tun_get(struct tun_file *tfile)
-{
- struct tun_struct *tun = NULL;
+ tun = rcu_dereference_protected(tfile->tun,
+ lockdep_is_held(&tun_lock));
+ if (tun) {
+ u16 index = tfile->queue_index;
+ BUG_ON(index > tun->numqueues);
+ BUG_ON(!tun->tfiles[tun->numqueues - 1]);
+ dev = tun->dev;
+
+ rcu_assign_pointer(tun->tfiles[index],
+ tun->tfiles[tun->numqueues - 1]);
+ tun->tfiles[index]->queue_index = index;
+ rcu_assign_pointer(tfile->tun, NULL);
+ --tun->numqueues;
+ sock_put(&tfile->sk);
- if (atomic_inc_not_zero(&tfile->count))
- tun = tfile->tun;
+ if (tun->numqueues == 0 && !(tun->flags & TUN_PERSIST))
+ destroy = true;
+ }
+
+ spin_unlock(&tun_lock);
+
+ synchronize_rcu();
+ if (clean)
+ sock_put(&tfile->sk);
- return tun;
+ if (destroy) {
+ rtnl_lock();
+ if (dev->reg_state == NETREG_REGISTERED)
+ unregister_netdevice(dev);
+ rtnl_unlock();
+ }
+
+ return 0;
}
-static struct tun_struct *tun_get(struct file *file)
+static void tun_detach_all(struct net_device *dev)
{
- return __tun_get(file->private_data);
+ struct tun_struct *tun = netdev_priv(dev);
+ struct tun_file *tfile, *tfile_list[MAX_TAP_QUEUES];
+ int i, j = 0;
+
+ spin_lock(&tun_lock);
+
+ for (i = 0; i < MAX_TAP_QUEUES && tun->numqueues; i++) {
+ tfile = rcu_dereference_protected(tun->tfiles[i],
+ lockdep_is_held(&tun_lock));
+ BUG_ON(!tfile);
+ wake_up_all(&tfile->wq.wait);
+ tfile_list[j++] = tfile;
+ rcu_assign_pointer(tfile->tun, NULL);
+ --tun->numqueues;
+ }
+ BUG_ON(tun->numqueues != 0);
+ spin_unlock(&tun_lock);
+
+ synchronize_rcu();
+ for(--j; j >= 0; j--)
+ sock_put(&tfile_list[j]->sk);
}
-static void tun_put(struct tun_struct *tun)
+static int tun_attach(struct tun_struct *tun, struct file *file)
{
- struct tun_file *tfile = tun->tfile;
+ struct tun_file *tfile = file->private_data;
+ int err;
+
+ ASSERT_RTNL();
+
+ spin_lock(&tun_lock);
+
+ err = -EINVAL;
+ if (rcu_dereference_protected(tfile->tun, lockdep_is_held(&tun_lock)))
+ goto out;
+
+ err = -EBUSY;
+ if (!(tun->flags & TUN_TAP_MQ) &&
+ rcu_dereference_protected(tun->tfiles[0],
+ lockdep_is_held(&tun_lock))) {
+ /* Multiqueue is only for TAP */
+ goto out;
+ }
+
+ if (tun->numqueues == MAX_TAP_QUEUES)
+ goto out;
+
+ err = 0;
+ tfile->queue_index = tun->numqueues;
+ rcu_assign_pointer(tfile->tun, tun);
+ rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
+ sock_hold(&tfile->sk);
+ tun->numqueues++;
+
+ if (tun->numqueues == 1)
+ netif_carrier_on(tun->dev);
- if (atomic_dec_and_test(&tfile->count))
- tun_detach(tfile->tun);
+ /* device is allowed to go away first, so no need to hold extra refcnt. */
+out:
+ spin_unlock(&tun_lock);
+ return err;
}
/* TAP filtering */
@@ -332,16 +416,7 @@ static const struct ethtool_ops tun_ethtool_ops;
/* Net device detach from fd. */
static void tun_net_uninit(struct net_device *dev)
{
- struct tun_struct *tun = netdev_priv(dev);
- struct tun_file *tfile = tun->tfile;
-
- /* Inform the methods they need to stop using the dev.
- */
- if (tfile) {
- wake_up_all(&tfile->wq.wait);
- if (atomic_dec_and_test(&tfile->count))
- __tun_detach(tun);
- }
+ tun_detach_all(dev);
}
/* Net device open. */
@@ -361,10 +436,10 @@ static int tun_net_close(struct net_device *dev)
/* Net device start xmit */
static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
{
- struct tun_struct *tun = netdev_priv(dev);
- struct tun_file *tfile = tun->tfile;
+ struct tun_file *tfile = NULL;
- tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len);
+ rcu_read_lock();
+ tfile = tun_get_queue(dev, skb);
/* Drop packet if interface is not attached */
if (!tfile)
@@ -381,7 +456,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
goto drop;
if (skb_queue_len(&tfile->socket.sk->sk_receive_queue) >= dev->tx_queue_len) {
- if (!(tun->flags & TUN_ONE_QUEUE)) {
+ if (!(tfile->flags & TUN_ONE_QUEUE) && !(tfile->flags && TUN_TAP_MQ)) {
/* Normal queueing mode. */
/* Packet scheduler handles dropping of further packets. */
netif_stop_queue(dev);
@@ -390,7 +465,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
* error is more appropriate. */
dev->stats.tx_fifo_errors++;
} else {
- /* Single queue mode.
+ /* Single queue mode or multi queue mode.
* Driver handles dropping of all packets itself. */
goto drop;
}
@@ -408,9 +483,11 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
kill_fasync(&tfile->fasync, SIGIO, POLL_IN);
wake_up_interruptible_poll(&tfile->wq.wait, POLLIN |
POLLRDNORM | POLLRDBAND);
+ rcu_read_unlock();
return NETDEV_TX_OK;
drop:
+ rcu_read_unlock();
dev->stats.tx_dropped++;
kfree_skb(skb);
return NETDEV_TX_OK;
@@ -526,16 +603,22 @@ static void tun_net_init(struct net_device *dev)
static unsigned int tun_chr_poll(struct file *file, poll_table * wait)
{
struct tun_file *tfile = file->private_data;
- struct tun_struct *tun = __tun_get(tfile);
+ struct tun_struct *tun = NULL;
struct sock *sk;
unsigned int mask = 0;
- if (!tun)
+ if (!tfile)
return POLLERR;
- sk = tfile->socket.sk;
+ rcu_read_lock();
+ tun = rcu_dereference(tfile->tun);
+ if (!tun) {
+ rcu_read_unlock();
+ return POLLERR;
+ }
+ rcu_read_unlock();
- tun_debug(KERN_INFO, tun, "tun_chr_poll\n");
+ sk = &tfile->sk;
poll_wait(file, &tfile->wq.wait, wait);
@@ -547,10 +630,12 @@ static unsigned int tun_chr_poll(struct file *file, poll_table * wait)
sock_writeable(sk)))
mask |= POLLOUT | POLLWRNORM;
- if (tun->dev->reg_state != NETREG_REGISTERED)
+ rcu_read_lock();
+ tun = rcu_dereference(tfile->tun);
+ if (!tun || tun->dev->reg_state != NETREG_REGISTERED)
mask = POLLERR;
+ rcu_read_unlock();
- tun_put(tun);
return mask;
}
@@ -706,11 +791,12 @@ static ssize_t tun_get_user(struct tun_file *tfile,
skb_shinfo(skb)->gso_segs = 0;
}
- tun = __tun_get(tfile);
+ rcu_read_lock();
+ tun = rcu_dereference(tfile->tun);
if (!tun) {
+ rcu_read_unlock();
return -EBADFD;
}
-
switch (tfile->flags & TUN_TYPE_MASK) {
case TUN_TUN_DEV:
skb->dev = tun->dev;
@@ -719,27 +805,29 @@ static ssize_t tun_get_user(struct tun_file *tfile,
skb->protocol = eth_type_trans(skb, tun->dev);
break;
}
-
- netif_rx_ni(skb);
tun->dev->stats.rx_packets++;
tun->dev->stats.rx_bytes += len;
- tun_put(tun);
+ rcu_read_unlock();
+
+ netif_rx_ni(skb);
+
return count;
err_free:
count = -EINVAL;
kfree_skb(skb);
err:
- tun = __tun_get(tfile);
+ rcu_read_lock();
+ tun = rcu_dereference(tfile->tun);
if (!tun) {
+ rcu_read_unlock();
return -EBADFD;
}
-
if (drop)
tun->dev->stats.rx_dropped++;
if (error)
tun->dev->stats.rx_frame_errors++;
- tun_put(tun);
+ rcu_read_unlock();
return count;
}
@@ -832,12 +920,13 @@ static ssize_t tun_put_user(struct tun_file *tfile,
skb_copy_datagram_const_iovec(skb, 0, iv, total, len);
total += skb->len;
- tun = __tun_get(tfile);
+ rcu_read_lock();
+ tun = rcu_dereference(tfile->tun);
if (tun) {
tun->dev->stats.tx_packets++;
tun->dev->stats.tx_bytes += len;
- tun_put(tun);
}
+ rcu_read_unlock();
return total;
}
@@ -867,28 +956,31 @@ static ssize_t tun_do_read(struct tun_file *tfile,
break;
}
- tun = __tun_get(tfile);
+ rcu_read_lock();
+ tun = rcu_dereference(tfile->tun);
if (!tun) {
- ret = -EIO;
+ ret = -EBADFD;
+ rcu_read_unlock();
break;
}
if (tun->dev->reg_state != NETREG_REGISTERED) {
ret = -EIO;
- tun_put(tun);
+ rcu_read_unlock();
break;
}
- tun_put(tun);
+ rcu_read_unlock();
/* Nothing to read, let's sleep */
schedule();
continue;
}
- tun = __tun_get(tfile);
+ rcu_read_lock();
+ tun = rcu_dereference(tfile->tun);
if (tun) {
netif_wake_queue(tun->dev);
- tun_put(tun);
}
+ rcu_read_unlock();
ret = tun_put_user(tfile, skb, iv, len);
kfree_skb(skb);
@@ -1028,6 +1120,9 @@ static int tun_flags(struct tun_struct *tun)
if (tun->flags & TUN_VNET_HDR)
flags |= IFF_VNET_HDR;
+ if (tun->flags & TUN_TAP_MQ)
+ flags |= IFF_MULTI_QUEUE;
+
return flags;
}
@@ -1107,6 +1202,10 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
/* TAP device */
flags |= TUN_TAP_DEV;
name = "tap%d";
+ if (ifr->ifr_flags & IFF_MULTI_QUEUE) {
+ flags |= TUN_TAP_MQ;
+ name = "mqtap%d";
+ }
} else
return -EINVAL;
@@ -1132,6 +1231,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST |
TUN_USER_FEATURES;
dev->features = dev->hw_features;
+ if (ifr->ifr_flags & IFF_MULTI_QUEUE)
+ dev->features |= NETIF_F_LLTX;
err = register_netdevice(tun->dev);
if (err < 0)
@@ -1164,6 +1265,11 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
else
tun->flags &= ~TUN_VNET_HDR;
+ if (ifr->ifr_flags & IFF_MULTI_QUEUE)
+ tun->flags |= TUN_TAP_MQ;
+ else
+ tun->flags &= ~TUN_TAP_MQ;
+
/* Cache flags from tun device */
tfile->flags = tun->flags;
/* Make sure persistent devices do not get stuck in
@@ -1254,38 +1360,39 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
(unsigned int __user*)argp);
}
- rtnl_lock();
-
- tun = __tun_get(tfile);
- if (cmd == TUNSETIFF && !tun) {
+ ret = 0;
+ if (cmd == TUNSETIFF) {
+ rtnl_lock();
ifr.ifr_name[IFNAMSIZ-1] = '\0';
-
ret = tun_set_iff(tfile->net, file, &ifr);
-
+ rtnl_unlock();
if (ret)
- goto unlock;
-
+ return ret;
if (copy_to_user(argp, &ifr, ifreq_len))
- ret = -EFAULT;
- goto unlock;
+ return -EFAULT;
+ return ret;
}
+ rtnl_lock();
+
+ rcu_read_lock();
+
ret = -EBADFD;
+ tun = rcu_dereference(tfile->tun);
if (!tun)
goto unlock;
- tun_debug(KERN_INFO, tun, "tun_chr_ioctl cmd %d\n", cmd);
- ret = 0;
- switch (cmd) {
+ switch(cmd) {
case TUNGETIFF:
ret = tun_get_iff(current->nsproxy->net_ns, tun, &ifr);
+ rcu_read_unlock();
if (ret)
- break;
+ goto out;
if (copy_to_user(argp, &ifr, ifreq_len))
ret = -EFAULT;
- break;
+ goto out;
case TUNSETNOCSUM:
/* Disable/Enable checksum */
@@ -1347,9 +1454,10 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
/* Get hw address */
memcpy(ifr.ifr_hwaddr.sa_data, tun->dev->dev_addr, ETH_ALEN);
ifr.ifr_hwaddr.sa_family = tun->dev->type;
+ rcu_read_unlock();
if (copy_to_user(argp, &ifr, ifreq_len))
ret = -EFAULT;
- break;
+ goto out;
case SIOCSIFHWADDR:
/* Set hw address */
@@ -1365,9 +1473,9 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
}
unlock:
+ rcu_read_unlock();
+out:
rtnl_unlock();
- if (tun)
- tun_put(tun);
return ret;
}
@@ -1539,31 +1647,8 @@ static int tun_chr_open(struct inode *inode, struct file * file)
static int tun_chr_close(struct inode *inode, struct file *file)
{
struct tun_file *tfile = file->private_data;
- struct tun_struct *tun;
-
- tun = __tun_get(tfile);
- if (tun) {
- struct net_device *dev = tun->dev;
-
- tun_debug(KERN_INFO, tun, "tun_chr_close\n");
-
- __tun_detach(tun);
-
- /* If desirable, unregister the netdevice. */
- if (!(tun->flags & TUN_PERSIST)) {
- rtnl_lock();
- if (dev->reg_state == NETREG_REGISTERED)
- unregister_netdevice(dev);
- rtnl_unlock();
- }
-
- /* drop the reference that netdevice holds */
- sock_put(&tfile->sk);
-
- }
- /* drop the reference that file holds */
- sock_put(&tfile->sk);
+ tun_detach(tfile, true);
return 0;
}
@@ -1691,14 +1776,17 @@ static void tun_cleanup(void)
* holding a reference to the file for as long as the socket is in use. */
struct socket *tun_get_socket(struct file *file)
{
- struct tun_struct *tun;
+ struct tun_struct *tun = NULL;
struct tun_file *tfile = file->private_data;
if (file->f_op != &tun_fops)
return ERR_PTR(-EINVAL);
- tun = tun_get(file);
- if (!tun)
+ rcu_read_lock();
+ tun = rcu_dereference(tfile->tun);
+ if (!tun) {
+ rcu_read_unlock();
return ERR_PTR(-EBADFD);
- tun_put(tun);
+ }
+ rcu_read_unlock();
return &tfile->socket;
}
EXPORT_SYMBOL_GPL(tun_get_socket);
^ permalink raw reply related
* [net-next RFC V2 PATCH 5/5] tuntap: add ioctls to attach or detach a file form tap device
From: Jason Wang @ 2011-09-17 6:03 UTC (permalink / raw)
To: krkumar2, eric.dumazet, mst, netdev, linux-kernel, virtualization,
davem
Cc: kvm, rusty, qemu-devel, mirq-linux, joe, shemminger
In-Reply-To: <20110917055639.32666.89940.stgit@dhcp-91-7.nay.redhat.com.englab.nay.redhat.com>
New ioctls were added to let multiple files/sockets to be attached to
a tap device.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/tun.c | 25 ++++++++++++++++++++++---
include/linux/if_tun.h | 3 +++
2 files changed, 25 insertions(+), 3 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ec29f85..6a1b591 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1343,11 +1343,12 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
{
struct tun_file *tfile = file->private_data;
struct tun_struct *tun;
+ struct net_device *dev = NULL;
void __user* argp = (void __user*)arg;
struct ifreq ifr;
int ret;
- if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89)
+ if (cmd == TUNSETIFF || cmd == TUNATTACHQUEUE || _IOC_TYPE(cmd) == 0x89)
if (copy_from_user(&ifr, argp, ifreq_len))
return -EFAULT;
@@ -1356,7 +1357,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
* This is needed because we never checked for invalid flags on
* TUNSETIFF. */
return put_user(IFF_TUN | IFF_TAP | IFF_NO_PI | IFF_ONE_QUEUE |
- IFF_VNET_HDR,
+ IFF_VNET_HDR | IFF_MULTI_QUEUE,
(unsigned int __user*)argp);
}
@@ -1372,6 +1373,9 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
return -EFAULT;
return ret;
}
+ if (cmd == TUNDETACHQUEUE) {
+ return tun_detach(tfile, false);
+ }
rtnl_lock();
@@ -1379,7 +1383,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
ret = -EBADFD;
tun = rcu_dereference(tfile->tun);
- if (!tun)
+ if (!tun && cmd != TUNATTACHQUEUE)
goto unlock;
@@ -1394,6 +1398,21 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
ret = -EFAULT;
goto out;
+ case TUNATTACHQUEUE:
+ dev = __dev_get_by_name(tfile->net, ifr.ifr_name);
+ if (!dev || dev->netdev_ops != &tap_netdev_ops) {
+ ret = -EINVAL;
+ } else if (ifr.ifr_flags &
+ ~(IFF_TAP | IFF_NO_PI | IFF_VNET_HDR)) {
+ /* ignore illegal flag */
+ ret = -EINVAL;
+ } else {
+ tfile->flags = TUN_TAP_DEV | TUN_NO_PI | TUN_VNET_HDR;
+ tun = netdev_priv(dev);
+ ret = tun_attach(tun, file);
+ }
+ break;
+
case TUNSETNOCSUM:
/* Disable/Enable checksum */
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index c92a291..d3f24d8 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -54,6 +54,9 @@
#define TUNDETACHFILTER _IOW('T', 214, struct sock_fprog)
#define TUNGETVNETHDRSZ _IOR('T', 215, int)
#define TUNSETVNETHDRSZ _IOW('T', 216, int)
+#define TUNATTACHQUEUE _IOW('T', 217, int)
+#define TUNDETACHQUEUE _IOW('T', 218, int)
+
/* TUNSETIFF ifr flags */
#define IFF_TUN 0x0001
^ permalink raw reply related
* (unknown),
From: puyou.lu @ 2011-09-17 7:18 UTC (permalink / raw)
To: netdev
subscribe netdev
^ permalink raw reply
* [net-next 00/13][pull request] Intel Wired LAN Driver Updates
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, gospo
The following series contains updates to ixgb and igb. The ixgb patch
is a trivial fix. The remaining patches are for igb to do the following:
- cleanup/consolidate Tx descriptors
- trivial fix to remove _adv/_ADV since igb uses only advanced
descriptors
- performance enhancements to help with general and routing
This series of igb patches is the first of three to update/cleanup the igb
driver by Alex. So there are additional patches/changes coming to complete
this work.
The following are changes since commit 765cf9976e937f1cfe9159bf4534967c8bf8eb6d:
tcp: md5: remove one indirection level in tcp_md5sig_pool
and are available in the git repository at:
git://github.com/Jkirsher/net-next.git
Alexander Duyck (12):
igb: Update RXDCTL/TXDCTL configurations
igb: Update max_frame_size to account for an optional VLAN tag if
present
igb: drop support for single buffer mode
igb: streamline Rx buffer allocation and cleanup
igb: update ring and adapter structure to improve performance
igb: Refactor clean_rx_irq to reduce overhead and improve performance
igb: drop the "adv" off function names relating to descriptors
igb: Replace E1000_XX_DESC_ADV with IGB_XX_DESC
igb: Remove multi_tx_table and simplify igb_xmit_frame
igb: Make Tx budget for NAPI user adjustable
igb: split buffer_info into tx_buffer_info and rx_buffer_info
igb: Consolidate creation of Tx context descriptors into a single
function
Jesse Brandeburg (1):
ixgb: eliminate checkstack warnings
drivers/net/ethernet/intel/igb/igb.h | 160 +++--
drivers/net/ethernet/intel/igb/igb_ethtool.c | 36 +-
drivers/net/ethernet/intel/igb/igb_main.c | 972 +++++++++++++-------------
drivers/net/ethernet/intel/ixgb/ixgb_main.c | 10 +-
4 files changed, 586 insertions(+), 592 deletions(-)
--
1.7.6
^ permalink raw reply
* [net-next 01/13] ixgb: eliminate checkstack warnings
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Jesse Brandeburg, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Really trivial fix, use kzalloc/kree instead of stack space.
before:
[jbrandeb@jbrandeb-mobl2 linux-2.6]$ make checkstack|grep ixgb_
0x0210 ixgb_set_multi [ixgb]: 768
0x04f8 ixgb_check_options [ixgb]: 220
0x04334 ixgb_set_ringparam [ixgb]: 124
0x04516 ixgb_set_ringparam [ixgb]: 124
after:
0x04f8 ixgb_check_options [ixgb]: 220
0x04354 ixgb_set_ringparam [ixgb]: 124
0x04536 ixgb_set_ringparam [ixgb]: 124
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgb/ixgb_main.c | 10 ++++++++--
1 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index b8fb163..500823b 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -1120,8 +1120,12 @@ ixgb_set_multi(struct net_device *netdev)
rctl |= IXGB_RCTL_MPE;
IXGB_WRITE_REG(hw, RCTL, rctl);
} else {
- u8 mta[IXGB_MAX_NUM_MULTICAST_ADDRESSES *
- IXGB_ETH_LENGTH_OF_ADDRESS];
+ u8 *mta = kzalloc(IXGB_MAX_NUM_MULTICAST_ADDRESSES *
+ IXGB_ETH_LENGTH_OF_ADDRESS, GFP_KERNEL);
+ if (!mta) {
+ pr_err("allocation of multicast memory failed\n");
+ goto alloc_failed;
+ }
IXGB_WRITE_REG(hw, RCTL, rctl);
@@ -1131,8 +1135,10 @@ ixgb_set_multi(struct net_device *netdev)
ha->addr, IXGB_ETH_LENGTH_OF_ADDRESS);
ixgb_mc_addr_list_update(hw, mta, netdev_mc_count(netdev), 0);
+ kfree(mta);
}
+alloc_failed:
if (netdev->features & NETIF_F_HW_VLAN_RX)
ixgb_vlan_strip_enable(adapter);
else
--
1.7.6
^ permalink raw reply related
* [net-next 03/13] igb: Update max_frame_size to account for an optional VLAN tag if present
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch modifies the max_frame_size in order account for an optional
VLAN tag. In order to support this we must also increase the
MAX_STD_JUMBO_FRAME_SIZE to account for the 4 extra bytes.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb.h | 2 --
drivers/net/ethernet/intel/igb/igb_main.c | 19 ++++++++++++-------
2 files changed, 12 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 577fd3e..8e90b85 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -117,8 +117,6 @@ struct vf_data_storage {
#define IGB_RXBUFFER_2048 2048
#define IGB_RXBUFFER_16384 16384
-#define MAX_STD_JUMBO_FRAME_SIZE 9234
-
/* How many Tx Descriptors do we need to call netif_wake_queue ? */
#define IGB_TX_QUEUE_WAKE 16
/* How many Rx Buffers do we bundle into one write to the hardware ? */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index aa78c10..6156275 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2396,7 +2396,8 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter)
adapter->rx_itr_setting = IGB_DEFAULT_ITR;
adapter->tx_itr_setting = IGB_DEFAULT_ITR;
- adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
+ adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN +
+ VLAN_HLEN;
adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
spin_lock_init(&adapter->stats64_lock);
@@ -2962,16 +2963,19 @@ static inline int igb_set_vf_rlpml(struct igb_adapter *adapter, int size,
**/
static void igb_rlpml_set(struct igb_adapter *adapter)
{
- u32 max_frame_size;
+ u32 max_frame_size = adapter->max_frame_size;
struct e1000_hw *hw = &adapter->hw;
u16 pf_id = adapter->vfs_allocated_count;
- max_frame_size = adapter->max_frame_size + VLAN_TAG_SIZE;
-
- /* if vfs are enabled we set RLPML to the largest possible request
- * size and set the VMOLR RLPML to the size we need */
if (pf_id) {
igb_set_vf_rlpml(adapter, max_frame_size, pf_id);
+ /*
+ * If we're in VMDQ or SR-IOV mode, then set global RLPML
+ * to our max jumbo frame size, in case we need to enable
+ * jumbo frames on one of the rings later.
+ * This will not pass over-length frames into the default
+ * queue because it's gated by the VMOLR.RLPML.
+ */
max_frame_size = MAX_JUMBO_FRAME_SIZE;
}
@@ -4461,7 +4465,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
{
struct igb_adapter *adapter = netdev_priv(netdev);
struct pci_dev *pdev = adapter->pdev;
- int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
+ int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
u32 rx_buffer_len, i;
if ((new_mtu < 68) || (max_frame > MAX_JUMBO_FRAME_SIZE)) {
@@ -4469,6 +4473,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
return -EINVAL;
}
+#define MAX_STD_JUMBO_FRAME_SIZE 9238
if (max_frame > MAX_STD_JUMBO_FRAME_SIZE) {
dev_err(&pdev->dev, "MTU > 9216 not supported.\n");
return -EINVAL;
--
1.7.6
^ permalink raw reply related
* [net-next 02/13] igb: Update RXDCTL/TXDCTL configurations
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change cleans up the RXDCTL and TXDCTL configurations and optimizes RX
performance by allowing back write-backs on all hardware other than 82576.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb.h | 5 +++--
drivers/net/ethernet/intel/igb/igb_main.c | 23 +++++++++--------------
2 files changed, 12 insertions(+), 16 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 265e151..577fd3e 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -100,11 +100,12 @@ struct vf_data_storage {
*/
#define IGB_RX_PTHRESH 8
#define IGB_RX_HTHRESH 8
-#define IGB_RX_WTHRESH 1
#define IGB_TX_PTHRESH 8
#define IGB_TX_HTHRESH 1
+#define IGB_RX_WTHRESH ((hw->mac.type == e1000_82576 && \
+ adapter->msix_entries) ? 1 : 4)
#define IGB_TX_WTHRESH ((hw->mac.type == e1000_82576 && \
- adapter->msix_entries) ? 1 : 16)
+ adapter->msix_entries) ? 1 : 16)
/* this is the size past which hardware will drop packets when setting LPE=0 */
#define MAXIMUM_ETHERNET_VLAN_SIZE 1522
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 3cb1bc9..aa78c10 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2666,14 +2666,12 @@ void igb_configure_tx_ring(struct igb_adapter *adapter,
struct igb_ring *ring)
{
struct e1000_hw *hw = &adapter->hw;
- u32 txdctl;
+ u32 txdctl = 0;
u64 tdba = ring->dma;
int reg_idx = ring->reg_idx;
/* disable the queue */
- txdctl = rd32(E1000_TXDCTL(reg_idx));
- wr32(E1000_TXDCTL(reg_idx),
- txdctl & ~E1000_TXDCTL_QUEUE_ENABLE);
+ wr32(E1000_TXDCTL(reg_idx), 0);
wrfl();
mdelay(10);
@@ -2685,7 +2683,7 @@ void igb_configure_tx_ring(struct igb_adapter *adapter,
ring->head = hw->hw_addr + E1000_TDH(reg_idx);
ring->tail = hw->hw_addr + E1000_TDT(reg_idx);
- writel(0, ring->head);
+ wr32(E1000_TDH(reg_idx), 0);
writel(0, ring->tail);
txdctl |= IGB_TX_PTHRESH;
@@ -3028,12 +3026,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
struct e1000_hw *hw = &adapter->hw;
u64 rdba = ring->dma;
int reg_idx = ring->reg_idx;
- u32 srrctl, rxdctl;
+ u32 srrctl = 0, rxdctl = 0;
/* disable the queue */
- rxdctl = rd32(E1000_RXDCTL(reg_idx));
- wr32(E1000_RXDCTL(reg_idx),
- rxdctl & ~E1000_RXDCTL_QUEUE_ENABLE);
+ wr32(E1000_RXDCTL(reg_idx), 0);
/* Set DMA base address registers */
wr32(E1000_RDBAL(reg_idx),
@@ -3045,7 +3041,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
/* initialize head and tail */
ring->head = hw->hw_addr + E1000_RDH(reg_idx);
ring->tail = hw->hw_addr + E1000_RDT(reg_idx);
- writel(0, ring->head);
+ wr32(E1000_RDH(reg_idx), 0);
writel(0, ring->tail);
/* set descriptor configuration */
@@ -3076,13 +3072,12 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
/* set filtering for VMDQ pools */
igb_set_vmolr(adapter, reg_idx & 0x7, true);
- /* enable receive descriptor fetching */
- rxdctl = rd32(E1000_RXDCTL(reg_idx));
- rxdctl |= E1000_RXDCTL_QUEUE_ENABLE;
- rxdctl &= 0xFFF00000;
rxdctl |= IGB_RX_PTHRESH;
rxdctl |= IGB_RX_HTHRESH << 8;
rxdctl |= IGB_RX_WTHRESH << 16;
+
+ /* enable receive descriptor fetching */
+ rxdctl |= E1000_RXDCTL_QUEUE_ENABLE;
wr32(E1000_RXDCTL(reg_idx), rxdctl);
}
--
1.7.6
^ permalink raw reply related
* [net-next 04/13] igb: drop support for single buffer mode
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change removes support for single buffer mode from igb and makes the
driver function in packet split always. The advantage to doing this is
that we can reduce total memory allocation overhead significantly as we
will only need to allocate one 1K slab per packet and then make use of a
reusable half page instead of allocating a 2K slab per packet.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb.h | 7 +-
drivers/net/ethernet/intel/igb/igb_ethtool.c | 5 +-
drivers/net/ethernet/intel/igb/igb_main.c | 102 ++++++--------------------
3 files changed, 28 insertions(+), 86 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 8e90b85..50632b1 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -111,11 +111,9 @@ struct vf_data_storage {
#define MAXIMUM_ETHERNET_VLAN_SIZE 1522
/* Supported Rx Buffer Sizes */
-#define IGB_RXBUFFER_64 64 /* Used for packet split */
-#define IGB_RXBUFFER_128 128 /* Used for packet split */
-#define IGB_RXBUFFER_1024 1024
-#define IGB_RXBUFFER_2048 2048
+#define IGB_RXBUFFER_512 512
#define IGB_RXBUFFER_16384 16384
+#define IGB_RX_HDR_LEN IGB_RXBUFFER_512
/* How many Tx Descriptors do we need to call netif_wake_queue ? */
#define IGB_TX_QUEUE_WAKE 16
@@ -221,7 +219,6 @@ struct igb_ring {
struct {
struct igb_rx_queue_stats rx_stats;
struct u64_stats_sync rx_syncp;
- u32 rx_buffer_len;
};
};
};
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 414b022..04bc7a5 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -1368,7 +1368,6 @@ static int igb_setup_desc_rings(struct igb_adapter *adapter)
rx_ring->count = IGB_DEFAULT_RXD;
rx_ring->dev = &adapter->pdev->dev;
rx_ring->netdev = adapter->netdev;
- rx_ring->rx_buffer_len = IGB_RXBUFFER_2048;
rx_ring->reg_idx = adapter->vfs_allocated_count;
if (igb_setup_rx_resources(rx_ring)) {
@@ -1597,7 +1596,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
/* unmap rx buffer, will be remapped by alloc_rx_buffers */
dma_unmap_single(rx_ring->dev,
buffer_info->dma,
- rx_ring->rx_buffer_len,
+ IGB_RX_HDR_LEN,
DMA_FROM_DEVICE);
buffer_info->dma = 0;
@@ -1635,7 +1634,7 @@ static int igb_run_loopback_test(struct igb_adapter *adapter)
struct igb_ring *tx_ring = &adapter->test_tx_ring;
struct igb_ring *rx_ring = &adapter->test_rx_ring;
int i, j, lc, good_cnt, ret_val = 0;
- unsigned int size = 1024;
+ unsigned int size = IGB_RX_HDR_LEN;
netdev_tx_t tx_ret_val;
struct sk_buff *skb;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 6156275..022c442 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -517,16 +517,14 @@ rx_ring_summary:
DUMP_PREFIX_ADDRESS,
16, 1,
phys_to_virt(buffer_info->dma),
- rx_ring->rx_buffer_len, true);
- if (rx_ring->rx_buffer_len
- < IGB_RXBUFFER_1024)
- print_hex_dump(KERN_INFO, "",
- DUMP_PREFIX_ADDRESS,
- 16, 1,
- phys_to_virt(
- buffer_info->page_dma +
- buffer_info->page_offset),
- PAGE_SIZE/2, true);
+ IGB_RX_HDR_LEN, true);
+ print_hex_dump(KERN_INFO, "",
+ DUMP_PREFIX_ADDRESS,
+ 16, 1,
+ phys_to_virt(
+ buffer_info->page_dma +
+ buffer_info->page_offset),
+ PAGE_SIZE/2, true);
}
}
@@ -707,7 +705,6 @@ static int igb_alloc_queues(struct igb_adapter *adapter)
ring->queue_index = i;
ring->dev = &adapter->pdev->dev;
ring->netdev = adapter->netdev;
- ring->rx_buffer_len = MAXIMUM_ETHERNET_VLAN_SIZE;
ring->flags = IGB_RING_FLAG_RX_CSUM; /* enable rx checksum */
/* set flag indicating ring supports SCTP checksum offload */
if (adapter->hw.mac.type >= e1000_82576)
@@ -3049,22 +3046,13 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
writel(0, ring->tail);
/* set descriptor configuration */
- if (ring->rx_buffer_len < IGB_RXBUFFER_1024) {
- srrctl = ALIGN(ring->rx_buffer_len, 64) <<
- E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
+ srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
#if (PAGE_SIZE / 2) > IGB_RXBUFFER_16384
- srrctl |= IGB_RXBUFFER_16384 >>
- E1000_SRRCTL_BSIZEPKT_SHIFT;
+ srrctl |= IGB_RXBUFFER_16384 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
#else
- srrctl |= (PAGE_SIZE / 2) >>
- E1000_SRRCTL_BSIZEPKT_SHIFT;
+ srrctl |= (PAGE_SIZE / 2) >> E1000_SRRCTL_BSIZEPKT_SHIFT;
#endif
- srrctl |= E1000_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS;
- } else {
- srrctl = ALIGN(ring->rx_buffer_len, 1024) >>
- E1000_SRRCTL_BSIZEPKT_SHIFT;
- srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF;
- }
+ srrctl |= E1000_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS;
if (hw->mac.type == e1000_82580)
srrctl |= E1000_SRRCTL_TIMESTAMP;
/* Only set Drop Enable if we are supporting multiple queues */
@@ -3268,7 +3256,7 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring)
if (buffer_info->dma) {
dma_unmap_single(rx_ring->dev,
buffer_info->dma,
- rx_ring->rx_buffer_len,
+ IGB_RX_HDR_LEN,
DMA_FROM_DEVICE);
buffer_info->dma = 0;
}
@@ -4466,7 +4454,6 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
struct igb_adapter *adapter = netdev_priv(netdev);
struct pci_dev *pdev = adapter->pdev;
int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
- u32 rx_buffer_len, i;
if ((new_mtu < 68) || (max_frame > MAX_JUMBO_FRAME_SIZE)) {
dev_err(&pdev->dev, "Invalid MTU setting\n");
@@ -4485,30 +4472,6 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
/* igb_down has a dependency on max_frame_size */
adapter->max_frame_size = max_frame;
- /* NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN
- * means we reserve 2 more, this pushes us to allocate from the next
- * larger slab size.
- * i.e. RXBUFFER_2048 --> size-4096 slab
- */
-
- if (adapter->hw.mac.type == e1000_82580)
- max_frame += IGB_TS_HDR_LEN;
-
- if (max_frame <= IGB_RXBUFFER_1024)
- rx_buffer_len = IGB_RXBUFFER_1024;
- else if (max_frame <= MAXIMUM_ETHERNET_VLAN_SIZE)
- rx_buffer_len = MAXIMUM_ETHERNET_VLAN_SIZE;
- else
- rx_buffer_len = IGB_RXBUFFER_128;
-
- if ((max_frame == ETH_FRAME_LEN + ETH_FCS_LEN + IGB_TS_HDR_LEN) ||
- (max_frame == MAXIMUM_ETHERNET_VLAN_SIZE + IGB_TS_HDR_LEN))
- rx_buffer_len = MAXIMUM_ETHERNET_VLAN_SIZE + IGB_TS_HDR_LEN;
-
- if ((adapter->hw.mac.type == e1000_82580) &&
- (rx_buffer_len == IGB_RXBUFFER_128))
- rx_buffer_len += IGB_RXBUFFER_64;
-
if (netif_running(netdev))
igb_down(adapter);
@@ -4516,9 +4479,6 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
netdev->mtu, new_mtu);
netdev->mtu = new_mtu;
- for (i = 0; i < adapter->num_rx_queues; i++)
- adapter->rx_ring[i]->rx_buffer_len = rx_buffer_len;
-
if (netif_running(netdev))
igb_up(adapter);
else
@@ -5781,8 +5741,7 @@ static void igb_rx_hwtstamp(struct igb_q_vector *q_vector, u32 staterr,
igb_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval);
}
-static inline u16 igb_get_hlen(struct igb_ring *rx_ring,
- union e1000_adv_rx_desc *rx_desc)
+static inline u16 igb_get_hlen(union e1000_adv_rx_desc *rx_desc)
{
/* HW will not DMA in data larger than the given buffer, even if it
* parses the (NFS, of course) header to be larger. In that case, it
@@ -5790,8 +5749,8 @@ static inline u16 igb_get_hlen(struct igb_ring *rx_ring,
*/
u16 hlen = (le16_to_cpu(rx_desc->wb.lower.lo_dword.hdr_info) &
E1000_RXDADV_HDRBUFLEN_MASK) >> E1000_RXDADV_HDRBUFLEN_SHIFT;
- if (hlen > rx_ring->rx_buffer_len)
- hlen = rx_ring->rx_buffer_len;
+ if (hlen > IGB_RX_HDR_LEN)
+ hlen = IGB_RX_HDR_LEN;
return hlen;
}
@@ -5841,14 +5800,10 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
if (buffer_info->dma) {
dma_unmap_single(dev, buffer_info->dma,
- rx_ring->rx_buffer_len,
+ IGB_RX_HDR_LEN,
DMA_FROM_DEVICE);
buffer_info->dma = 0;
- if (rx_ring->rx_buffer_len >= IGB_RXBUFFER_1024) {
- skb_put(skb, length);
- goto send_up;
- }
- skb_put(skb, igb_get_hlen(rx_ring, rx_desc));
+ skb_put(skb, igb_get_hlen(rx_desc));
}
if (length) {
@@ -5879,7 +5834,7 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
next_buffer->dma = 0;
goto next_desc;
}
-send_up:
+
if (staterr & E1000_RXDEXT_ERR_FRAME_ERR_MASK) {
dev_kfree_skb_irq(skb);
goto next_desc;
@@ -5943,17 +5898,14 @@ void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, int cleaned_count)
struct igb_buffer *buffer_info;
struct sk_buff *skb;
unsigned int i;
- int bufsz;
i = rx_ring->next_to_use;
buffer_info = &rx_ring->buffer_info[i];
- bufsz = rx_ring->rx_buffer_len;
-
while (cleaned_count--) {
rx_desc = E1000_RX_DESC_ADV(*rx_ring, i);
- if ((bufsz < IGB_RXBUFFER_1024) && !buffer_info->page_dma) {
+ if (!buffer_info->page_dma) {
if (!buffer_info->page) {
buffer_info->page = netdev_alloc_page(netdev);
if (unlikely(!buffer_info->page)) {
@@ -5983,7 +5935,7 @@ void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, int cleaned_count)
skb = buffer_info->skb;
if (!skb) {
- skb = netdev_alloc_skb_ip_align(netdev, bufsz);
+ skb = netdev_alloc_skb_ip_align(netdev, IGB_RX_HDR_LEN);
if (unlikely(!skb)) {
u64_stats_update_begin(&rx_ring->rx_syncp);
rx_ring->rx_stats.alloc_failed++;
@@ -5996,7 +5948,7 @@ void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, int cleaned_count)
if (!buffer_info->dma) {
buffer_info->dma = dma_map_single(rx_ring->dev,
skb->data,
- bufsz,
+ IGB_RX_HDR_LEN,
DMA_FROM_DEVICE);
if (dma_mapping_error(rx_ring->dev,
buffer_info->dma)) {
@@ -6009,14 +5961,8 @@ void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, int cleaned_count)
}
/* Refresh the desc even if buffer_addrs didn't change because
* each write-back erases this info. */
- if (bufsz < IGB_RXBUFFER_1024) {
- rx_desc->read.pkt_addr =
- cpu_to_le64(buffer_info->page_dma);
- rx_desc->read.hdr_addr = cpu_to_le64(buffer_info->dma);
- } else {
- rx_desc->read.pkt_addr = cpu_to_le64(buffer_info->dma);
- rx_desc->read.hdr_addr = 0;
- }
+ rx_desc->read.pkt_addr = cpu_to_le64(buffer_info->page_dma);
+ rx_desc->read.hdr_addr = cpu_to_le64(buffer_info->dma);
i++;
if (i == rx_ring->count)
--
1.7.6
^ permalink raw reply related
* [net-next 05/13] igb: streamline Rx buffer allocation and cleanup
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change is meant to streamline the Rx buffer allocation and cleanup.
This is accomplished by reducing the number of writes by only having the Rx
descriptor ring written by software during allocation, and it will only be
read during cleanup.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb.h | 2 +-
drivers/net/ethernet/intel/igb/igb_main.c | 190 ++++++++++++++++-------------
2 files changed, 104 insertions(+), 88 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 50632b1..b2f2a8c 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -370,7 +370,7 @@ extern void igb_setup_rctl(struct igb_adapter *);
extern netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *, struct igb_ring *);
extern void igb_unmap_and_free_tx_resource(struct igb_ring *,
struct igb_buffer *);
-extern void igb_alloc_rx_buffers_adv(struct igb_ring *, int);
+extern void igb_alloc_rx_buffers_adv(struct igb_ring *, u16);
extern void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *);
extern bool igb_has_link(struct igb_adapter *adapter);
extern void igb_set_ethtool_ops(struct net_device *);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 022c442..af8c2f7 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -3243,16 +3243,15 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter)
**/
static void igb_clean_rx_ring(struct igb_ring *rx_ring)
{
- struct igb_buffer *buffer_info;
unsigned long size;
- unsigned int i;
+ u16 i;
if (!rx_ring->buffer_info)
return;
/* Free all the Rx ring sk_buffs */
for (i = 0; i < rx_ring->count; i++) {
- buffer_info = &rx_ring->buffer_info[i];
+ struct igb_buffer *buffer_info = &rx_ring->buffer_info[i];
if (buffer_info->dma) {
dma_unmap_single(rx_ring->dev,
buffer_info->dma,
@@ -5764,7 +5763,7 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
struct igb_buffer *buffer_info , *next_buffer;
struct sk_buff *skb;
bool cleaned = false;
- int cleaned_count = 0;
+ u16 cleaned_count = igb_desc_unused(rx_ring);
int current_node = numa_node_id();
unsigned int total_bytes = 0, total_packets = 0;
unsigned int i;
@@ -5848,7 +5847,6 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
igb_rx_checksum_adv(rx_ring, staterr, skb);
skb->protocol = eth_type_trans(skb, netdev);
- skb_record_rx_queue(skb, rx_ring->queue_index);
if (staterr & E1000_RXD_STAT_VP) {
u16 vid = le16_to_cpu(rx_desc->wb.upper.vlan);
@@ -5858,8 +5856,6 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
napi_gro_receive(&q_vector->napi, skb);
next_desc:
- rx_desc->wb.upper.status_error = 0;
-
/* return some buffers to hardware, one at a time is too slow */
if (cleaned_count >= IGB_RX_BUFFER_WRITE) {
igb_alloc_rx_buffers_adv(rx_ring, cleaned_count);
@@ -5873,110 +5869,130 @@ next_desc:
}
rx_ring->next_to_clean = i;
- cleaned_count = igb_desc_unused(rx_ring);
-
- if (cleaned_count)
- igb_alloc_rx_buffers_adv(rx_ring, cleaned_count);
-
- rx_ring->total_packets += total_packets;
- rx_ring->total_bytes += total_bytes;
u64_stats_update_begin(&rx_ring->rx_syncp);
rx_ring->rx_stats.packets += total_packets;
rx_ring->rx_stats.bytes += total_bytes;
u64_stats_update_end(&rx_ring->rx_syncp);
+ rx_ring->total_packets += total_packets;
+ rx_ring->total_bytes += total_bytes;
+
+ if (cleaned_count)
+ igb_alloc_rx_buffers_adv(rx_ring, cleaned_count);
+
return cleaned;
}
+static bool igb_alloc_mapped_skb(struct igb_ring *rx_ring,
+ struct igb_buffer *bi)
+{
+ struct sk_buff *skb = bi->skb;
+ dma_addr_t dma = bi->dma;
+
+ if (dma)
+ return true;
+
+ if (likely(!skb)) {
+ skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
+ IGB_RX_HDR_LEN);
+ bi->skb = skb;
+ if (!skb) {
+ rx_ring->rx_stats.alloc_failed++;
+ return false;
+ }
+
+ /* initialize skb for ring */
+ skb_record_rx_queue(skb, rx_ring->queue_index);
+ }
+
+ dma = dma_map_single(rx_ring->dev, skb->data,
+ IGB_RX_HDR_LEN, DMA_FROM_DEVICE);
+
+ if (dma_mapping_error(rx_ring->dev, dma)) {
+ rx_ring->rx_stats.alloc_failed++;
+ return false;
+ }
+
+ bi->dma = dma;
+ return true;
+}
+
+static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
+ struct igb_buffer *bi)
+{
+ struct page *page = bi->page;
+ dma_addr_t page_dma = bi->page_dma;
+ unsigned int page_offset = bi->page_offset ^ (PAGE_SIZE / 2);
+
+ if (page_dma)
+ return true;
+
+ if (!page) {
+ page = netdev_alloc_page(rx_ring->netdev);
+ bi->page = page;
+ if (unlikely(!page)) {
+ rx_ring->rx_stats.alloc_failed++;
+ return false;
+ }
+ }
+
+ page_dma = dma_map_page(rx_ring->dev, page,
+ page_offset, PAGE_SIZE / 2,
+ DMA_FROM_DEVICE);
+
+ if (dma_mapping_error(rx_ring->dev, page_dma)) {
+ rx_ring->rx_stats.alloc_failed++;
+ return false;
+ }
+
+ bi->page_dma = page_dma;
+ bi->page_offset = page_offset;
+ return true;
+}
+
/**
* igb_alloc_rx_buffers_adv - Replace used receive buffers; packet split
* @adapter: address of board private structure
**/
-void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, int cleaned_count)
+void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, u16 cleaned_count)
{
- struct net_device *netdev = rx_ring->netdev;
union e1000_adv_rx_desc *rx_desc;
- struct igb_buffer *buffer_info;
- struct sk_buff *skb;
- unsigned int i;
+ struct igb_buffer *bi;
+ u16 i = rx_ring->next_to_use;
- i = rx_ring->next_to_use;
- buffer_info = &rx_ring->buffer_info[i];
+ rx_desc = E1000_RX_DESC_ADV(*rx_ring, i);
+ bi = &rx_ring->buffer_info[i];
+ i -= rx_ring->count;
while (cleaned_count--) {
- rx_desc = E1000_RX_DESC_ADV(*rx_ring, i);
-
- if (!buffer_info->page_dma) {
- if (!buffer_info->page) {
- buffer_info->page = netdev_alloc_page(netdev);
- if (unlikely(!buffer_info->page)) {
- u64_stats_update_begin(&rx_ring->rx_syncp);
- rx_ring->rx_stats.alloc_failed++;
- u64_stats_update_end(&rx_ring->rx_syncp);
- goto no_buffers;
- }
- buffer_info->page_offset = 0;
- } else {
- buffer_info->page_offset ^= PAGE_SIZE / 2;
- }
- buffer_info->page_dma =
- dma_map_page(rx_ring->dev, buffer_info->page,
- buffer_info->page_offset,
- PAGE_SIZE / 2,
- DMA_FROM_DEVICE);
- if (dma_mapping_error(rx_ring->dev,
- buffer_info->page_dma)) {
- buffer_info->page_dma = 0;
- u64_stats_update_begin(&rx_ring->rx_syncp);
- rx_ring->rx_stats.alloc_failed++;
- u64_stats_update_end(&rx_ring->rx_syncp);
- goto no_buffers;
- }
- }
+ if (!igb_alloc_mapped_skb(rx_ring, bi))
+ break;
- skb = buffer_info->skb;
- if (!skb) {
- skb = netdev_alloc_skb_ip_align(netdev, IGB_RX_HDR_LEN);
- if (unlikely(!skb)) {
- u64_stats_update_begin(&rx_ring->rx_syncp);
- rx_ring->rx_stats.alloc_failed++;
- u64_stats_update_end(&rx_ring->rx_syncp);
- goto no_buffers;
- }
+ /* Refresh the desc even if buffer_addrs didn't change
+ * because each write-back erases this info. */
+ rx_desc->read.hdr_addr = cpu_to_le64(bi->dma);
- buffer_info->skb = skb;
- }
- if (!buffer_info->dma) {
- buffer_info->dma = dma_map_single(rx_ring->dev,
- skb->data,
- IGB_RX_HDR_LEN,
- DMA_FROM_DEVICE);
- if (dma_mapping_error(rx_ring->dev,
- buffer_info->dma)) {
- buffer_info->dma = 0;
- u64_stats_update_begin(&rx_ring->rx_syncp);
- rx_ring->rx_stats.alloc_failed++;
- u64_stats_update_end(&rx_ring->rx_syncp);
- goto no_buffers;
- }
- }
- /* Refresh the desc even if buffer_addrs didn't change because
- * each write-back erases this info. */
- rx_desc->read.pkt_addr = cpu_to_le64(buffer_info->page_dma);
- rx_desc->read.hdr_addr = cpu_to_le64(buffer_info->dma);
+ if (!igb_alloc_mapped_page(rx_ring, bi))
+ break;
+
+ rx_desc->read.pkt_addr = cpu_to_le64(bi->page_dma);
+ rx_desc++;
+ bi++;
i++;
- if (i == rx_ring->count)
- i = 0;
- buffer_info = &rx_ring->buffer_info[i];
+ if (unlikely(!i)) {
+ rx_desc = E1000_RX_DESC_ADV(*rx_ring, 0);
+ bi = rx_ring->buffer_info;
+ i -= rx_ring->count;
+ }
+
+ /* clear the hdr_addr for the next_to_use descriptor */
+ rx_desc->read.hdr_addr = 0;
}
-no_buffers:
+ i += rx_ring->count;
+
if (rx_ring->next_to_use != i) {
rx_ring->next_to_use = i;
- if (i == 0)
- i = (rx_ring->count - 1);
- else
- i--;
/* Force memory writes to complete before letting h/w
* know there are new descriptors to fetch. (Only
--
1.7.6
^ permalink raw reply related
* [net-next 06/13] igb: update ring and adapter structure to improve performance
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change is meant to improve performance by splitting the Tx and Rx
rings into 3 sections. The first is primarily a read only section
containing basic things like the indexes, a pointer to the dev and netdev
structures, and basic information. The second section contains the stats
and next_to_use and next_to_clean values. The third section is primarily
unused values that can just be placed at the end of the ring and are not
used in the hot path.
The adapter structure has several sections that are read in the hot path.
In order to improve performance there I am combining the frequent read
hot path items into a single cache line.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb.h | 83 ++++++++++++++++-------------
drivers/net/ethernet/intel/igb/igb_main.c | 4 +-
2 files changed, 46 insertions(+), 41 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index b2f2a8c..7036fd5 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -187,26 +187,26 @@ struct igb_q_vector {
};
struct igb_ring {
- struct igb_q_vector *q_vector; /* backlink to q_vector */
- struct net_device *netdev; /* back pointer to net_device */
- struct device *dev; /* device pointer for dma mapping */
- dma_addr_t dma; /* phys address of the ring */
- void *desc; /* descriptor ring memory */
- unsigned int size; /* length of desc. ring in bytes */
- u16 count; /* number of desc. in the ring */
+ struct igb_q_vector *q_vector; /* backlink to q_vector */
+ struct net_device *netdev; /* back pointer to net_device */
+ struct device *dev; /* device pointer for dma mapping */
+ struct igb_buffer *buffer_info; /* array of buffer info structs */
+ void *desc; /* descriptor ring memory */
+ unsigned long flags; /* ring specific flags */
+ void __iomem *tail; /* pointer to ring tail register */
+
+ u16 count; /* number of desc. in the ring */
+ u8 queue_index; /* logical index of the ring*/
+ u8 reg_idx; /* physical index of the ring */
+ u32 size; /* length of desc. ring in bytes */
+
+ /* everything past this point are written often */
+ u16 next_to_clean ____cacheline_aligned_in_smp;
u16 next_to_use;
- u16 next_to_clean;
- u8 queue_index;
- u8 reg_idx;
- void __iomem *head;
- void __iomem *tail;
- struct igb_buffer *buffer_info; /* array of buffer info structs */
unsigned int total_bytes;
unsigned int total_packets;
- u32 flags;
-
union {
/* TX */
struct {
@@ -221,6 +221,8 @@ struct igb_ring {
struct u64_stats_sync rx_syncp;
};
};
+ /* Items past this point are only used during ring alloc / free */
+ dma_addr_t dma; /* phys address of the ring */
};
#define IGB_RING_FLAG_RX_CSUM 0x00000001 /* RX CSUM enabled */
@@ -248,15 +250,15 @@ static inline int igb_desc_unused(struct igb_ring *ring)
/* board specific private data structure */
struct igb_adapter {
- struct timer_list watchdog_timer;
- struct timer_list phy_info_timer;
unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
- u16 mng_vlan_id;
- u32 bd_number;
- u32 wol;
- u32 en_mng_pt;
- u16 link_speed;
- u16 link_duplex;
+
+ struct net_device *netdev;
+
+ unsigned long state;
+ unsigned int flags;
+
+ unsigned int num_q_vectors;
+ struct msix_entry *msix_entries;
/* Interrupt Throttle Rate */
u32 rx_itr_setting;
@@ -264,27 +266,36 @@ struct igb_adapter {
u16 tx_itr;
u16 rx_itr;
- struct work_struct reset_task;
- struct work_struct watchdog_task;
- bool fc_autoneg;
- u8 tx_timeout_factor;
- struct timer_list blink_timer;
- unsigned long led_status;
-
/* TX */
- struct igb_ring *tx_ring[16];
u32 tx_timeout_count;
+ int num_tx_queues;
+ struct igb_ring *tx_ring[16];
/* RX */
- struct igb_ring *rx_ring[16];
- int num_tx_queues;
int num_rx_queues;
+ struct igb_ring *rx_ring[16];
u32 max_frame_size;
u32 min_frame_size;
+ struct timer_list watchdog_timer;
+ struct timer_list phy_info_timer;
+
+ u16 mng_vlan_id;
+ u32 bd_number;
+ u32 wol;
+ u32 en_mng_pt;
+ u16 link_speed;
+ u16 link_duplex;
+
+ struct work_struct reset_task;
+ struct work_struct watchdog_task;
+ bool fc_autoneg;
+ u8 tx_timeout_factor;
+ struct timer_list blink_timer;
+ unsigned long led_status;
+
/* OS defined structs */
- struct net_device *netdev;
struct pci_dev *pdev;
struct cyclecounter cycles;
struct timecounter clock;
@@ -306,15 +317,11 @@ struct igb_adapter {
int msg_enable;
- unsigned int num_q_vectors;
struct igb_q_vector *q_vector[MAX_Q_VECTORS];
- struct msix_entry *msix_entries;
u32 eims_enable_mask;
u32 eims_other;
/* to not mess up cache alignment, always add to the bottom */
- unsigned long state;
- unsigned int flags;
u32 eeprom_wol;
struct igb_ring *multi_tx_table[IGB_ABS_MAX_TX_QUEUES];
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index af8c2f7..9fa2ad0 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2679,7 +2679,6 @@ void igb_configure_tx_ring(struct igb_adapter *adapter,
tdba & 0x00000000ffffffffULL);
wr32(E1000_TDBAH(reg_idx), tdba >> 32);
- ring->head = hw->hw_addr + E1000_TDH(reg_idx);
ring->tail = hw->hw_addr + E1000_TDT(reg_idx);
wr32(E1000_TDH(reg_idx), 0);
writel(0, ring->tail);
@@ -3040,7 +3039,6 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
ring->count * sizeof(union e1000_adv_rx_desc));
/* initialize head and tail */
- ring->head = hw->hw_addr + E1000_RDH(reg_idx);
ring->tail = hw->hw_addr + E1000_RDT(reg_idx);
wr32(E1000_RDH(reg_idx), 0);
writel(0, ring->tail);
@@ -5653,7 +5651,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
" jiffies <%lx>\n"
" desc.status <%x>\n",
tx_ring->queue_index,
- readl(tx_ring->head),
+ rd32(E1000_TDH(tx_ring->reg_idx)),
readl(tx_ring->tail),
tx_ring->next_to_use,
tx_ring->next_to_clean,
--
1.7.6
^ permalink raw reply related
* [net-next 07/13] igb: Refactor clean_rx_irq to reduce overhead and improve performance
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change is meant to be a general cleanup and performance improvement
for clean_rx_irq. The previous patch should have updated the allocation so
that the rings can be treated as read-only within the clean_rx_irq
function. In addition I am re-ordering the operations such that several
goals are accomplished including reducing the overhead for packet
accounting, reducing the number of items on the stack, and improving
overall performance.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb_main.c | 96 ++++++++++++++---------------
1 files changed, 47 insertions(+), 49 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 9fa2ad0..dd85df0 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -138,7 +138,7 @@ static void igb_setup_dca(struct igb_adapter *);
#endif /* CONFIG_IGB_DCA */
static bool igb_clean_tx_irq(struct igb_q_vector *);
static int igb_poll(struct napi_struct *, int);
-static bool igb_clean_rx_irq_adv(struct igb_q_vector *, int *, int);
+static bool igb_clean_rx_irq_adv(struct igb_q_vector *, int);
static int igb_ioctl(struct net_device *, struct ifreq *, int cmd);
static void igb_tx_timeout(struct net_device *);
static void igb_reset_task(struct work_struct *);
@@ -5481,28 +5481,27 @@ static int igb_poll(struct napi_struct *napi, int budget)
struct igb_q_vector *q_vector = container_of(napi,
struct igb_q_vector,
napi);
- int tx_clean_complete = 1, work_done = 0;
+ bool clean_complete = true;
#ifdef CONFIG_IGB_DCA
if (q_vector->adapter->flags & IGB_FLAG_DCA_ENABLED)
igb_update_dca(q_vector);
#endif
if (q_vector->tx_ring)
- tx_clean_complete = igb_clean_tx_irq(q_vector);
+ clean_complete = !!igb_clean_tx_irq(q_vector);
if (q_vector->rx_ring)
- igb_clean_rx_irq_adv(q_vector, &work_done, budget);
+ clean_complete &= igb_clean_rx_irq_adv(q_vector, budget);
- if (!tx_clean_complete)
- work_done = budget;
+ /* If all work not completed, return budget and keep polling */
+ if (!clean_complete)
+ return budget;
/* If not enough Rx work done, exit the polling mode */
- if (work_done < budget) {
- napi_complete(napi);
- igb_ring_irq_enable(q_vector);
- }
+ napi_complete(napi);
+ igb_ring_irq_enable(q_vector);
- return work_done;
+ return 0;
}
/**
@@ -5751,37 +5750,26 @@ static inline u16 igb_get_hlen(union e1000_adv_rx_desc *rx_desc)
return hlen;
}
-static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
- int *work_done, int budget)
+static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector, int budget)
{
struct igb_ring *rx_ring = q_vector->rx_ring;
- struct net_device *netdev = rx_ring->netdev;
- struct device *dev = rx_ring->dev;
- union e1000_adv_rx_desc *rx_desc , *next_rxd;
- struct igb_buffer *buffer_info , *next_buffer;
- struct sk_buff *skb;
- bool cleaned = false;
- u16 cleaned_count = igb_desc_unused(rx_ring);
- int current_node = numa_node_id();
+ union e1000_adv_rx_desc *rx_desc;
+ const int current_node = numa_node_id();
unsigned int total_bytes = 0, total_packets = 0;
- unsigned int i;
u32 staterr;
- u16 length;
+ u16 cleaned_count = igb_desc_unused(rx_ring);
+ u16 i = rx_ring->next_to_clean;
- i = rx_ring->next_to_clean;
- buffer_info = &rx_ring->buffer_info[i];
rx_desc = E1000_RX_DESC_ADV(*rx_ring, i);
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
while (staterr & E1000_RXD_STAT_DD) {
- if (*work_done >= budget)
- break;
- (*work_done)++;
- rmb(); /* read descriptor and rx_buffer_info after status DD */
+ struct igb_buffer *buffer_info = &rx_ring->buffer_info[i];
+ struct sk_buff *skb = buffer_info->skb;
+ union e1000_adv_rx_desc *next_rxd;
- skb = buffer_info->skb;
- prefetch(skb->data - NET_IP_ALIGN);
buffer_info->skb = NULL;
+ prefetch(skb->data);
i++;
if (i == rx_ring->count)
@@ -5789,42 +5777,48 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
next_rxd = E1000_RX_DESC_ADV(*rx_ring, i);
prefetch(next_rxd);
- next_buffer = &rx_ring->buffer_info[i];
- length = le16_to_cpu(rx_desc->wb.upper.length);
- cleaned = true;
- cleaned_count++;
+ /*
+ * This memory barrier is needed to keep us from reading
+ * any other fields out of the rx_desc until we know the
+ * RXD_STAT_DD bit is set
+ */
+ rmb();
- if (buffer_info->dma) {
- dma_unmap_single(dev, buffer_info->dma,
+ if (!skb_is_nonlinear(skb)) {
+ __skb_put(skb, igb_get_hlen(rx_desc));
+ dma_unmap_single(rx_ring->dev, buffer_info->dma,
IGB_RX_HDR_LEN,
DMA_FROM_DEVICE);
buffer_info->dma = 0;
- skb_put(skb, igb_get_hlen(rx_desc));
}
- if (length) {
- dma_unmap_page(dev, buffer_info->page_dma,
- PAGE_SIZE / 2, DMA_FROM_DEVICE);
- buffer_info->page_dma = 0;
+ if (rx_desc->wb.upper.length) {
+ u16 length = le16_to_cpu(rx_desc->wb.upper.length);
skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
buffer_info->page,
buffer_info->page_offset,
length);
+ skb->len += length;
+ skb->data_len += length;
+ skb->truesize += length;
+
if ((page_count(buffer_info->page) != 1) ||
(page_to_nid(buffer_info->page) != current_node))
buffer_info->page = NULL;
else
get_page(buffer_info->page);
- skb->len += length;
- skb->data_len += length;
- skb->truesize += length;
+ dma_unmap_page(rx_ring->dev, buffer_info->page_dma,
+ PAGE_SIZE / 2, DMA_FROM_DEVICE);
+ buffer_info->page_dma = 0;
}
if (!(staterr & E1000_RXD_STAT_EOP)) {
+ struct igb_buffer *next_buffer;
+ next_buffer = &rx_ring->buffer_info[i];
buffer_info->skb = next_buffer->skb;
buffer_info->dma = next_buffer->dma;
next_buffer->skb = skb;
@@ -5833,7 +5827,7 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
}
if (staterr & E1000_RXDEXT_ERR_FRAME_ERR_MASK) {
- dev_kfree_skb_irq(skb);
+ dev_kfree_skb_any(skb);
goto next_desc;
}
@@ -5844,7 +5838,7 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
igb_rx_checksum_adv(rx_ring, staterr, skb);
- skb->protocol = eth_type_trans(skb, netdev);
+ skb->protocol = eth_type_trans(skb, rx_ring->netdev);
if (staterr & E1000_RXD_STAT_VP) {
u16 vid = le16_to_cpu(rx_desc->wb.upper.vlan);
@@ -5853,7 +5847,12 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
}
napi_gro_receive(&q_vector->napi, skb);
+ budget--;
next_desc:
+ if (!budget)
+ break;
+
+ cleaned_count++;
/* return some buffers to hardware, one at a time is too slow */
if (cleaned_count >= IGB_RX_BUFFER_WRITE) {
igb_alloc_rx_buffers_adv(rx_ring, cleaned_count);
@@ -5862,7 +5861,6 @@ next_desc:
/* use prefetched values */
rx_desc = next_rxd;
- buffer_info = next_buffer;
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
}
@@ -5877,7 +5875,7 @@ next_desc:
if (cleaned_count)
igb_alloc_rx_buffers_adv(rx_ring, cleaned_count);
- return cleaned;
+ return !!budget;
}
static bool igb_alloc_mapped_skb(struct igb_ring *rx_ring,
--
1.7.6
^ permalink raw reply related
* [net-next 08/13] igb: drop the "adv" off function names relating to descriptors
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
Many of the function names in the hot path are carrying an extra "_adv"
suffix on the end of them to represent the fact that they are using
advanced descriptors instead of legacy descriptors. However since all igb
uses are advanced descriptors adding the extra suffix doesn't really add
any additional data. Since this is the case it is easiest to just drop the
suffix and save us from having to store the extra characters.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb.h | 4 +-
drivers/net/ethernet/intel/igb/igb_ethtool.c | 6 +-
drivers/net/ethernet/intel/igb/igb_main.c | 62 +++++++++++++-------------
3 files changed, 36 insertions(+), 36 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 7036fd5..b1ca8ea 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -374,10 +374,10 @@ extern void igb_configure_tx_ring(struct igb_adapter *, struct igb_ring *);
extern void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *);
extern void igb_setup_tctl(struct igb_adapter *);
extern void igb_setup_rctl(struct igb_adapter *);
-extern netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *, struct igb_ring *);
+extern netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *);
extern void igb_unmap_and_free_tx_resource(struct igb_ring *,
struct igb_buffer *);
-extern void igb_alloc_rx_buffers_adv(struct igb_ring *, u16);
+extern void igb_alloc_rx_buffers(struct igb_ring *, u16);
extern void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *);
extern bool igb_has_link(struct igb_adapter *adapter);
extern void igb_set_ethtool_ops(struct net_device *);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 04bc7a5..67eee0a 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -1382,7 +1382,7 @@ static int igb_setup_desc_rings(struct igb_adapter *adapter)
igb_setup_rctl(adapter);
igb_configure_rx_ring(adapter, rx_ring);
- igb_alloc_rx_buffers_adv(rx_ring, igb_desc_unused(rx_ring));
+ igb_alloc_rx_buffers(rx_ring, igb_desc_unused(rx_ring));
return 0;
@@ -1622,7 +1622,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
}
/* re-map buffers to ring, store next to clean values */
- igb_alloc_rx_buffers_adv(rx_ring, count);
+ igb_alloc_rx_buffers(rx_ring, count);
rx_ring->next_to_clean = rx_ntc;
tx_ring->next_to_clean = tx_ntc;
@@ -1665,7 +1665,7 @@ static int igb_run_loopback_test(struct igb_adapter *adapter)
/* place 64 packets on the transmit queue*/
for (i = 0; i < 64; i++) {
skb_get(skb);
- tx_ret_val = igb_xmit_frame_ring_adv(skb, tx_ring);
+ tx_ret_val = igb_xmit_frame_ring(skb, tx_ring);
if (tx_ret_val == NETDEV_TX_OK)
good_cnt++;
}
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index dd85df0..9a0cfd6 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -122,7 +122,7 @@ static void igb_set_rx_mode(struct net_device *);
static void igb_update_phy_info(unsigned long);
static void igb_watchdog(unsigned long);
static void igb_watchdog_task(struct work_struct *);
-static netdev_tx_t igb_xmit_frame_adv(struct sk_buff *skb, struct net_device *);
+static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, struct net_device *);
static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats);
static int igb_change_mtu(struct net_device *, int);
@@ -138,7 +138,7 @@ static void igb_setup_dca(struct igb_adapter *);
#endif /* CONFIG_IGB_DCA */
static bool igb_clean_tx_irq(struct igb_q_vector *);
static int igb_poll(struct napi_struct *, int);
-static bool igb_clean_rx_irq_adv(struct igb_q_vector *, int);
+static bool igb_clean_rx_irq(struct igb_q_vector *, int);
static int igb_ioctl(struct net_device *, struct ifreq *, int cmd);
static void igb_tx_timeout(struct net_device *);
static void igb_reset_task(struct work_struct *);
@@ -1436,7 +1436,7 @@ static void igb_configure(struct igb_adapter *adapter)
* next_to_use != next_to_clean */
for (i = 0; i < adapter->num_rx_queues; i++) {
struct igb_ring *ring = adapter->rx_ring[i];
- igb_alloc_rx_buffers_adv(ring, igb_desc_unused(ring));
+ igb_alloc_rx_buffers(ring, igb_desc_unused(ring));
}
}
@@ -1784,7 +1784,7 @@ static int igb_set_features(struct net_device *netdev, u32 features)
static const struct net_device_ops igb_netdev_ops = {
.ndo_open = igb_open,
.ndo_stop = igb_close,
- .ndo_start_xmit = igb_xmit_frame_adv,
+ .ndo_start_xmit = igb_xmit_frame,
.ndo_get_stats64 = igb_get_stats64,
.ndo_set_rx_mode = igb_set_rx_mode,
.ndo_set_mac_address = igb_set_mac,
@@ -3955,8 +3955,8 @@ set_itr_now:
#define IGB_TX_FLAGS_VLAN_MASK 0xffff0000
#define IGB_TX_FLAGS_VLAN_SHIFT 16
-static inline int igb_tso_adv(struct igb_ring *tx_ring,
- struct sk_buff *skb, u32 tx_flags, u8 *hdr_len)
+static inline int igb_tso(struct igb_ring *tx_ring,
+ struct sk_buff *skb, u32 tx_flags, u8 *hdr_len)
{
struct e1000_adv_tx_context_desc *context_desc;
unsigned int i;
@@ -4035,8 +4035,8 @@ static inline int igb_tso_adv(struct igb_ring *tx_ring,
return true;
}
-static inline bool igb_tx_csum_adv(struct igb_ring *tx_ring,
- struct sk_buff *skb, u32 tx_flags)
+static inline bool igb_tx_csum(struct igb_ring *tx_ring,
+ struct sk_buff *skb, u32 tx_flags)
{
struct e1000_adv_tx_context_desc *context_desc;
struct device *dev = tx_ring->dev;
@@ -4120,8 +4120,8 @@ static inline bool igb_tx_csum_adv(struct igb_ring *tx_ring,
#define IGB_MAX_TXD_PWR 16
#define IGB_MAX_DATA_PER_TXD (1<<IGB_MAX_TXD_PWR)
-static inline int igb_tx_map_adv(struct igb_ring *tx_ring, struct sk_buff *skb,
- unsigned int first)
+static inline int igb_tx_map(struct igb_ring *tx_ring, struct sk_buff *skb,
+ unsigned int first)
{
struct igb_buffer *buffer_info;
struct device *dev = tx_ring->dev;
@@ -4196,9 +4196,9 @@ dma_error:
return 0;
}
-static inline void igb_tx_queue_adv(struct igb_ring *tx_ring,
- u32 tx_flags, int count, u32 paylen,
- u8 hdr_len)
+static inline void igb_tx_queue(struct igb_ring *tx_ring,
+ u32 tx_flags, int count, u32 paylen,
+ u8 hdr_len)
{
union e1000_adv_tx_desc *tx_desc;
struct igb_buffer *buffer_info;
@@ -4296,8 +4296,8 @@ static inline int igb_maybe_stop_tx(struct igb_ring *tx_ring, int size)
return __igb_maybe_stop_tx(tx_ring, size);
}
-netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
- struct igb_ring *tx_ring)
+netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
+ struct igb_ring *tx_ring)
{
int tso = 0, count;
u32 tx_flags = 0;
@@ -4329,7 +4329,7 @@ netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
first = tx_ring->next_to_use;
if (skb_is_gso(skb)) {
- tso = igb_tso_adv(tx_ring, skb, tx_flags, &hdr_len);
+ tso = igb_tso(tx_ring, skb, tx_flags, &hdr_len);
if (tso < 0) {
dev_kfree_skb_any(skb);
@@ -4339,7 +4339,7 @@ netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
if (tso)
tx_flags |= IGB_TX_FLAGS_TSO;
- else if (igb_tx_csum_adv(tx_ring, skb, tx_flags) &&
+ else if (igb_tx_csum(tx_ring, skb, tx_flags) &&
(skb->ip_summed == CHECKSUM_PARTIAL))
tx_flags |= IGB_TX_FLAGS_CSUM;
@@ -4347,7 +4347,7 @@ netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
* count reflects descriptors mapped, if 0 or less then mapping error
* has occurred and we need to rewind the descriptor queue
*/
- count = igb_tx_map_adv(tx_ring, skb, first);
+ count = igb_tx_map(tx_ring, skb, first);
if (!count) {
dev_kfree_skb_any(skb);
tx_ring->buffer_info[first].time_stamp = 0;
@@ -4355,7 +4355,7 @@ netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
return NETDEV_TX_OK;
}
- igb_tx_queue_adv(tx_ring, tx_flags, count, skb->len, hdr_len);
+ igb_tx_queue(tx_ring, tx_flags, count, skb->len, hdr_len);
/* Make sure there is space in the ring for the next send. */
igb_maybe_stop_tx(tx_ring, MAX_SKB_FRAGS + 4);
@@ -4363,8 +4363,8 @@ netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
return NETDEV_TX_OK;
}
-static netdev_tx_t igb_xmit_frame_adv(struct sk_buff *skb,
- struct net_device *netdev)
+static netdev_tx_t igb_xmit_frame(struct sk_buff *skb,
+ struct net_device *netdev)
{
struct igb_adapter *adapter = netdev_priv(netdev);
struct igb_ring *tx_ring;
@@ -4387,7 +4387,7 @@ static netdev_tx_t igb_xmit_frame_adv(struct sk_buff *skb,
* to a flow. Right now, performance is impacted slightly negatively
* if using multiple tx queues. If the stack breaks away from a
* single qdisc implementation, we can look at this again. */
- return igb_xmit_frame_ring_adv(skb, tx_ring);
+ return igb_xmit_frame_ring(skb, tx_ring);
}
/**
@@ -5491,7 +5491,7 @@ static int igb_poll(struct napi_struct *napi, int budget)
clean_complete = !!igb_clean_tx_irq(q_vector);
if (q_vector->rx_ring)
- clean_complete &= igb_clean_rx_irq_adv(q_vector, budget);
+ clean_complete &= igb_clean_rx_irq(q_vector, budget);
/* If all work not completed, return budget and keep polling */
if (!clean_complete)
@@ -5670,8 +5670,8 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
return count < tx_ring->count;
}
-static inline void igb_rx_checksum_adv(struct igb_ring *ring,
- u32 status_err, struct sk_buff *skb)
+static inline void igb_rx_checksum(struct igb_ring *ring,
+ u32 status_err, struct sk_buff *skb)
{
skb_checksum_none_assert(skb);
@@ -5750,7 +5750,7 @@ static inline u16 igb_get_hlen(union e1000_adv_rx_desc *rx_desc)
return hlen;
}
-static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector, int budget)
+static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget)
{
struct igb_ring *rx_ring = q_vector->rx_ring;
union e1000_adv_rx_desc *rx_desc;
@@ -5836,7 +5836,7 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector, int budget)
total_bytes += skb->len;
total_packets++;
- igb_rx_checksum_adv(rx_ring, staterr, skb);
+ igb_rx_checksum(rx_ring, staterr, skb);
skb->protocol = eth_type_trans(skb, rx_ring->netdev);
@@ -5855,7 +5855,7 @@ next_desc:
cleaned_count++;
/* return some buffers to hardware, one at a time is too slow */
if (cleaned_count >= IGB_RX_BUFFER_WRITE) {
- igb_alloc_rx_buffers_adv(rx_ring, cleaned_count);
+ igb_alloc_rx_buffers(rx_ring, cleaned_count);
cleaned_count = 0;
}
@@ -5873,7 +5873,7 @@ next_desc:
rx_ring->total_bytes += total_bytes;
if (cleaned_count)
- igb_alloc_rx_buffers_adv(rx_ring, cleaned_count);
+ igb_alloc_rx_buffers(rx_ring, cleaned_count);
return !!budget;
}
@@ -5946,10 +5946,10 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
}
/**
- * igb_alloc_rx_buffers_adv - Replace used receive buffers; packet split
+ * igb_alloc_rx_buffers - Replace used receive buffers; packet split
* @adapter: address of board private structure
**/
-void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, u16 cleaned_count)
+void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
{
union e1000_adv_rx_desc *rx_desc;
struct igb_buffer *bi;
--
1.7.6
^ permalink raw reply related
* [net-next 09/13] igb: Replace E1000_XX_DESC_ADV with IGB_XX_DESC
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
Since igb only uses advanced descriptors we might as well just use an IGB
specific define and drop the _ADV suffix for the descriptor declarations.
In addition this can be further reduced by assuming that it will be working
on pointers since that is normally how the Tx descriptors are handled.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb.h | 12 ++++++------
drivers/net/ethernet/intel/igb/igb_ethtool.c | 4 ++--
drivers/net/ethernet/intel/igb/igb_main.c | 24 ++++++++++++------------
3 files changed, 20 insertions(+), 20 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index b1ca8ea..8607a1d 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -232,12 +232,12 @@ struct igb_ring {
#define IGB_ADVTXD_DCMD (E1000_TXD_CMD_EOP | E1000_TXD_CMD_RS)
-#define E1000_RX_DESC_ADV(R, i) \
- (&(((union e1000_adv_rx_desc *)((R).desc))[i]))
-#define E1000_TX_DESC_ADV(R, i) \
- (&(((union e1000_adv_tx_desc *)((R).desc))[i]))
-#define E1000_TX_CTXTDESC_ADV(R, i) \
- (&(((struct e1000_adv_tx_context_desc *)((R).desc))[i]))
+#define IGB_RX_DESC(R, i) \
+ (&(((union e1000_adv_rx_desc *)((R)->desc))[i]))
+#define IGB_TX_DESC(R, i) \
+ (&(((union e1000_adv_tx_desc *)((R)->desc))[i]))
+#define IGB_TX_CTXTDESC(R, i) \
+ (&(((struct e1000_adv_tx_context_desc *)((R)->desc))[i]))
/* igb_desc_unused - calculate if we have unused descriptors */
static inline int igb_desc_unused(struct igb_ring *ring)
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 67eee0a..f231d82 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -1586,7 +1586,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
/* initialize next to clean and descriptor values */
rx_ntc = rx_ring->next_to_clean;
tx_ntc = tx_ring->next_to_clean;
- rx_desc = E1000_RX_DESC_ADV(*rx_ring, rx_ntc);
+ rx_desc = IGB_RX_DESC(rx_ring, rx_ntc);
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
while (staterr & E1000_RXD_STAT_DD) {
@@ -1617,7 +1617,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
tx_ntc = 0;
/* fetch next descriptor */
- rx_desc = E1000_RX_DESC_ADV(*rx_ring, rx_ntc);
+ rx_desc = IGB_RX_DESC(rx_ring, rx_ntc);
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
}
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 9a0cfd6..55d6431 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -413,7 +413,7 @@ static void igb_dump(struct igb_adapter *adapter)
"leng ntw timestamp bi->skb\n");
for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
- tx_desc = E1000_TX_DESC_ADV(*tx_ring, i);
+ tx_desc = IGB_TX_DESC(tx_ring, i);
buffer_info = &tx_ring->buffer_info[i];
u0 = (struct my_u0 *)tx_desc;
printk(KERN_INFO "T [0x%03X] %016llX %016llX %016llX"
@@ -494,7 +494,7 @@ rx_ring_summary:
for (i = 0; i < rx_ring->count; i++) {
buffer_info = &rx_ring->buffer_info[i];
- rx_desc = E1000_RX_DESC_ADV(*rx_ring, i);
+ rx_desc = IGB_RX_DESC(rx_ring, i);
u0 = (struct my_u0 *)rx_desc;
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
if (staterr & E1000_RXD_STAT_DD) {
@@ -3993,7 +3993,7 @@ static inline int igb_tso(struct igb_ring *tx_ring,
i = tx_ring->next_to_use;
buffer_info = &tx_ring->buffer_info[i];
- context_desc = E1000_TX_CTXTDESC_ADV(*tx_ring, i);
+ context_desc = IGB_TX_CTXTDESC(tx_ring, i);
/* VLAN MACLEN IPLEN */
if (tx_flags & IGB_TX_FLAGS_VLAN)
info |= (tx_flags & IGB_TX_FLAGS_VLAN_MASK);
@@ -4048,7 +4048,7 @@ static inline bool igb_tx_csum(struct igb_ring *tx_ring,
(tx_flags & IGB_TX_FLAGS_VLAN)) {
i = tx_ring->next_to_use;
buffer_info = &tx_ring->buffer_info[i];
- context_desc = E1000_TX_CTXTDESC_ADV(*tx_ring, i);
+ context_desc = IGB_TX_CTXTDESC(tx_ring, i);
if (tx_flags & IGB_TX_FLAGS_VLAN)
info |= (tx_flags & IGB_TX_FLAGS_VLAN_MASK);
@@ -4238,7 +4238,7 @@ static inline void igb_tx_queue(struct igb_ring *tx_ring,
do {
buffer_info = &tx_ring->buffer_info[i];
- tx_desc = E1000_TX_DESC_ADV(*tx_ring, i);
+ tx_desc = IGB_TX_DESC(tx_ring, i);
tx_desc->read.buffer_addr = cpu_to_le64(buffer_info->dma);
tx_desc->read.cmd_type_len =
cpu_to_le32(cmd_type_len | buffer_info->length);
@@ -5580,13 +5580,13 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
i = tx_ring->next_to_clean;
eop = tx_ring->buffer_info[i].next_to_watch;
- eop_desc = E1000_TX_DESC_ADV(*tx_ring, eop);
+ eop_desc = IGB_TX_DESC(tx_ring, eop);
while ((eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD)) &&
(count < tx_ring->count)) {
rmb(); /* read buffer_info after eop_desc status */
for (cleaned = false; !cleaned; count++) {
- tx_desc = E1000_TX_DESC_ADV(*tx_ring, i);
+ tx_desc = IGB_TX_DESC(tx_ring, i);
buffer_info = &tx_ring->buffer_info[i];
cleaned = (i == eop);
@@ -5605,7 +5605,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
i = 0;
}
eop = tx_ring->buffer_info[i].next_to_watch;
- eop_desc = E1000_TX_DESC_ADV(*tx_ring, eop);
+ eop_desc = IGB_TX_DESC(tx_ring, eop);
}
tx_ring->next_to_clean = i;
@@ -5760,7 +5760,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget)
u16 cleaned_count = igb_desc_unused(rx_ring);
u16 i = rx_ring->next_to_clean;
- rx_desc = E1000_RX_DESC_ADV(*rx_ring, i);
+ rx_desc = IGB_RX_DESC(rx_ring, i);
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
while (staterr & E1000_RXD_STAT_DD) {
@@ -5775,7 +5775,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget)
if (i == rx_ring->count)
i = 0;
- next_rxd = E1000_RX_DESC_ADV(*rx_ring, i);
+ next_rxd = IGB_RX_DESC(rx_ring, i);
prefetch(next_rxd);
/*
@@ -5955,7 +5955,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
struct igb_buffer *bi;
u16 i = rx_ring->next_to_use;
- rx_desc = E1000_RX_DESC_ADV(*rx_ring, i);
+ rx_desc = IGB_RX_DESC(rx_ring, i);
bi = &rx_ring->buffer_info[i];
i -= rx_ring->count;
@@ -5976,7 +5976,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
bi++;
i++;
if (unlikely(!i)) {
- rx_desc = E1000_RX_DESC_ADV(*rx_ring, 0);
+ rx_desc = IGB_RX_DESC(rx_ring, 0);
bi = rx_ring->buffer_info;
i -= rx_ring->count;
}
--
1.7.6
^ permalink raw reply related
* [net-next 10/13] igb: Remove multi_tx_table and simplify igb_xmit_frame
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
Instead of using the multi_tx_table to map possible Tx queues to Tx rings
we can just do simple subtraction for the unlikely event that the Tx queue
provided exceeds the number of Tx rings.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb.h | 4 +--
drivers/net/ethernet/intel/igb/igb_main.c | 36 +++++++++++++++++-----------
2 files changed, 23 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 8607a1d..b725937 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -63,8 +63,7 @@ struct igb_adapter;
/* Transmit and receive queues */
#define IGB_MAX_RX_QUEUES (adapter->vfs_allocated_count ? 2 : \
(hw->mac.type > e1000_82575 ? 8 : 4))
-#define IGB_ABS_MAX_TX_QUEUES 8
-#define IGB_MAX_TX_QUEUES IGB_MAX_RX_QUEUES
+#define IGB_MAX_TX_QUEUES 16
#define IGB_MAX_VF_MC_ENTRIES 30
#define IGB_MAX_VF_FUNCTIONS 8
@@ -324,7 +323,6 @@ struct igb_adapter {
/* to not mess up cache alignment, always add to the bottom */
u32 eeprom_wol;
- struct igb_ring *multi_tx_table[IGB_ABS_MAX_TX_QUEUES];
u16 tx_ring_count;
u16 rx_ring_count;
unsigned int vfs_allocated_count;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 55d6431..7ad25e8 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1875,7 +1875,7 @@ static int __devinit igb_probe(struct pci_dev *pdev,
err = -ENOMEM;
netdev = alloc_etherdev_mq(sizeof(struct igb_adapter),
- IGB_ABS_MAX_TX_QUEUES);
+ IGB_MAX_TX_QUEUES);
if (!netdev)
goto err_alloc_etherdev;
@@ -2620,10 +2620,6 @@ static int igb_setup_all_tx_resources(struct igb_adapter *adapter)
}
}
- for (i = 0; i < IGB_ABS_MAX_TX_QUEUES; i++) {
- int r_idx = i % adapter->num_tx_queues;
- adapter->multi_tx_table[i] = adapter->tx_ring[r_idx];
- }
return err;
}
@@ -4363,12 +4359,21 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
return NETDEV_TX_OK;
}
+static inline struct igb_ring *igb_tx_queue_mapping(struct igb_adapter *adapter,
+ struct sk_buff *skb)
+{
+ unsigned int r_idx = skb->queue_mapping;
+
+ if (r_idx >= adapter->num_tx_queues)
+ r_idx = r_idx % adapter->num_tx_queues;
+
+ return adapter->tx_ring[r_idx];
+}
+
static netdev_tx_t igb_xmit_frame(struct sk_buff *skb,
struct net_device *netdev)
{
struct igb_adapter *adapter = netdev_priv(netdev);
- struct igb_ring *tx_ring;
- int r_idx = 0;
if (test_bit(__IGB_DOWN, &adapter->state)) {
dev_kfree_skb_any(skb);
@@ -4380,14 +4385,17 @@ static netdev_tx_t igb_xmit_frame(struct sk_buff *skb,
return NETDEV_TX_OK;
}
- r_idx = skb->queue_mapping & (IGB_ABS_MAX_TX_QUEUES - 1);
- tx_ring = adapter->multi_tx_table[r_idx];
+ /*
+ * The minimum packet size with TCTL.PSP set is 17 so pad the skb
+ * in order to meet this minimum size requirement.
+ */
+ if (skb->len < 17) {
+ if (skb_padto(skb, 17))
+ return NETDEV_TX_OK;
+ skb->len = 17;
+ }
- /* This goes back to the question of how to logically map a tx queue
- * to a flow. Right now, performance is impacted slightly negatively
- * if using multiple tx queues. If the stack breaks away from a
- * single qdisc implementation, we can look at this again. */
- return igb_xmit_frame_ring(skb, tx_ring);
+ return igb_xmit_frame_ring(skb, igb_tx_queue_mapping(adapter, skb));
}
/**
--
1.7.6
^ permalink raw reply related
* [net-next 11/13] igb: Make Tx budget for NAPI user adjustable
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change is meant to make the NAPI budget limits for transmit
adjustable. By doing this it is possible to tune the value for optimal
performance with applications such as routing.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb.h | 3 +
drivers/net/ethernet/intel/igb/igb_ethtool.c | 6 +
drivers/net/ethernet/intel/igb/igb_main.c | 136 ++++++++++++++++----------
3 files changed, 92 insertions(+), 53 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index b725937..cfa590c8 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -47,6 +47,7 @@ struct igb_adapter;
/* TX/RX descriptor defines */
#define IGB_DEFAULT_TXD 256
+#define IXGBE_DEFAULT_TX_WORK 128
#define IGB_MIN_TXD 80
#define IGB_MAX_TXD 4096
@@ -177,6 +178,7 @@ struct igb_q_vector {
u32 eims_value;
u16 cpu;
+ u16 tx_work_limit;
u16 itr_val;
u8 set_itr;
@@ -266,6 +268,7 @@ struct igb_adapter {
u16 rx_itr;
/* TX */
+ u16 tx_work_limit;
u32 tx_timeout_count;
int num_tx_queues;
struct igb_ring *tx_ring[16];
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index f231d82..f6da820 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -1989,6 +1989,9 @@ static int igb_set_coalesce(struct net_device *netdev,
if ((adapter->flags & IGB_FLAG_QUEUE_PAIRS) && ec->tx_coalesce_usecs)
return -EINVAL;
+ if (ec->tx_max_coalesced_frames_irq)
+ adapter->tx_work_limit = ec->tx_max_coalesced_frames_irq;
+
/* If ITR is disabled, disable DMAC */
if (ec->rx_coalesce_usecs == 0) {
if (adapter->flags & IGB_FLAG_DMAC)
@@ -2011,6 +2014,7 @@ static int igb_set_coalesce(struct net_device *netdev,
for (i = 0; i < adapter->num_q_vectors; i++) {
struct igb_q_vector *q_vector = adapter->q_vector[i];
+ q_vector->tx_work_limit = adapter->tx_work_limit;
if (q_vector->rx_ring)
q_vector->itr_val = adapter->rx_itr_setting;
else
@@ -2033,6 +2037,8 @@ static int igb_get_coalesce(struct net_device *netdev,
else
ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2;
+ ec->tx_max_coalesced_frames_irq = adapter->tx_work_limit;
+
if (!(adapter->flags & IGB_FLAG_QUEUE_PAIRS)) {
if (adapter->tx_itr_setting <= 3)
ec->tx_coalesce_usecs = adapter->tx_itr_setting;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 7ad25e8..989e774 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -136,8 +136,8 @@ static irqreturn_t igb_msix_ring(int irq, void *);
static void igb_update_dca(struct igb_q_vector *);
static void igb_setup_dca(struct igb_adapter *);
#endif /* CONFIG_IGB_DCA */
-static bool igb_clean_tx_irq(struct igb_q_vector *);
static int igb_poll(struct napi_struct *, int);
+static bool igb_clean_tx_irq(struct igb_q_vector *);
static bool igb_clean_rx_irq(struct igb_q_vector *, int);
static int igb_ioctl(struct net_device *, struct ifreq *, int cmd);
static void igb_tx_timeout(struct net_device *);
@@ -1120,6 +1120,7 @@ static void igb_map_tx_ring_to_vector(struct igb_adapter *adapter,
q_vector->tx_ring = adapter->tx_ring[ring_idx];
q_vector->tx_ring->q_vector = q_vector;
q_vector->itr_val = adapter->tx_itr_setting;
+ q_vector->tx_work_limit = adapter->tx_work_limit;
if (q_vector->itr_val && q_vector->itr_val <= 3)
q_vector->itr_val = IGB_START_ITR;
}
@@ -2388,11 +2389,17 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter)
pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word);
+ /* set default ring sizes */
adapter->tx_ring_count = IGB_DEFAULT_TXD;
adapter->rx_ring_count = IGB_DEFAULT_RXD;
+
+ /* set default ITR values */
adapter->rx_itr_setting = IGB_DEFAULT_ITR;
adapter->tx_itr_setting = IGB_DEFAULT_ITR;
+ /* set default work limits */
+ adapter->tx_work_limit = IXGBE_DEFAULT_TX_WORK;
+
adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN +
VLAN_HLEN;
adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
@@ -5496,7 +5503,7 @@ static int igb_poll(struct napi_struct *napi, int budget)
igb_update_dca(q_vector);
#endif
if (q_vector->tx_ring)
- clean_complete = !!igb_clean_tx_irq(q_vector);
+ clean_complete = igb_clean_tx_irq(q_vector);
if (q_vector->rx_ring)
clean_complete &= igb_clean_rx_irq(q_vector, budget);
@@ -5578,64 +5585,69 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
{
struct igb_adapter *adapter = q_vector->adapter;
struct igb_ring *tx_ring = q_vector->tx_ring;
- struct net_device *netdev = tx_ring->netdev;
- struct e1000_hw *hw = &adapter->hw;
- struct igb_buffer *buffer_info;
- union e1000_adv_tx_desc *tx_desc, *eop_desc;
+ struct igb_buffer *tx_buffer;
+ union e1000_adv_tx_desc *tx_desc;
unsigned int total_bytes = 0, total_packets = 0;
- unsigned int i, eop, count = 0;
- bool cleaned = false;
+ unsigned int budget = q_vector->tx_work_limit;
+ u16 i = tx_ring->next_to_clean;
- i = tx_ring->next_to_clean;
- eop = tx_ring->buffer_info[i].next_to_watch;
- eop_desc = IGB_TX_DESC(tx_ring, eop);
+ if (test_bit(__IGB_DOWN, &adapter->state))
+ return true;
- while ((eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD)) &&
- (count < tx_ring->count)) {
- rmb(); /* read buffer_info after eop_desc status */
- for (cleaned = false; !cleaned; count++) {
- tx_desc = IGB_TX_DESC(tx_ring, i);
- buffer_info = &tx_ring->buffer_info[i];
- cleaned = (i == eop);
+ tx_buffer = &tx_ring->buffer_info[i];
+ tx_desc = IGB_TX_DESC(tx_ring, i);
- if (buffer_info->skb) {
- total_bytes += buffer_info->bytecount;
- /* gso_segs is currently only valid for tcp */
- total_packets += buffer_info->gso_segs;
- igb_tx_hwtstamp(q_vector, buffer_info);
- }
+ for (; budget; budget--) {
+ u16 eop = tx_buffer->next_to_watch;
+ union e1000_adv_tx_desc *eop_desc;
+
+ eop_desc = IGB_TX_DESC(tx_ring, eop);
+
+ /* if DD is not set pending work has not been completed */
+ if (!(eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD)))
+ break;
+
+ /* prevent any other reads prior to eop_desc being verified */
+ rmb();
- igb_unmap_and_free_tx_resource(tx_ring, buffer_info);
+ do {
tx_desc->wb.status = 0;
+ if (likely(tx_desc == eop_desc)) {
+ eop_desc = NULL;
+
+ total_bytes += tx_buffer->bytecount;
+ total_packets += tx_buffer->gso_segs;
+ igb_tx_hwtstamp(q_vector, tx_buffer);
+ }
+
+ igb_unmap_and_free_tx_resource(tx_ring, tx_buffer);
+ tx_buffer++;
+ tx_desc++;
i++;
- if (i == tx_ring->count)
+ if (unlikely(i == tx_ring->count)) {
i = 0;
- }
- eop = tx_ring->buffer_info[i].next_to_watch;
- eop_desc = IGB_TX_DESC(tx_ring, eop);
+ tx_buffer = tx_ring->buffer_info;
+ tx_desc = IGB_TX_DESC(tx_ring, 0);
+ }
+ } while (eop_desc);
}
tx_ring->next_to_clean = i;
+ u64_stats_update_begin(&tx_ring->tx_syncp);
+ tx_ring->tx_stats.bytes += total_bytes;
+ tx_ring->tx_stats.packets += total_packets;
+ u64_stats_update_end(&tx_ring->tx_syncp);
+ tx_ring->total_bytes += total_bytes;
+ tx_ring->total_packets += total_packets;
- if (unlikely(count &&
- netif_carrier_ok(netdev) &&
- igb_desc_unused(tx_ring) >= IGB_TX_QUEUE_WAKE)) {
- /* Make sure that anybody stopping the queue after this
- * sees the new next_to_clean.
- */
- smp_mb();
- if (__netif_subqueue_stopped(netdev, tx_ring->queue_index) &&
- !(test_bit(__IGB_DOWN, &adapter->state))) {
- netif_wake_subqueue(netdev, tx_ring->queue_index);
+ if (tx_ring->detect_tx_hung) {
+ struct e1000_hw *hw = &adapter->hw;
+ u16 eop = tx_ring->buffer_info[i].next_to_watch;
+ union e1000_adv_tx_desc *eop_desc;
- u64_stats_update_begin(&tx_ring->tx_syncp);
- tx_ring->tx_stats.restart_queue++;
- u64_stats_update_end(&tx_ring->tx_syncp);
- }
- }
+ eop_desc = IGB_TX_DESC(tx_ring, eop);
- if (tx_ring->detect_tx_hung) {
/* Detect a transmit hang in hardware, this serializes the
* check with the clearing of time_stamp and movement of i */
tx_ring->detect_tx_hung = false;
@@ -5666,16 +5678,34 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
eop,
jiffies,
eop_desc->wb.status);
- netif_stop_subqueue(netdev, tx_ring->queue_index);
+ netif_stop_subqueue(tx_ring->netdev,
+ tx_ring->queue_index);
+
+ /* we are about to reset, no point in enabling stuff */
+ return true;
}
}
- tx_ring->total_bytes += total_bytes;
- tx_ring->total_packets += total_packets;
- u64_stats_update_begin(&tx_ring->tx_syncp);
- tx_ring->tx_stats.bytes += total_bytes;
- tx_ring->tx_stats.packets += total_packets;
- u64_stats_update_end(&tx_ring->tx_syncp);
- return count < tx_ring->count;
+
+ if (unlikely(total_packets &&
+ netif_carrier_ok(tx_ring->netdev) &&
+ igb_desc_unused(tx_ring) >= IGB_TX_QUEUE_WAKE)) {
+ /* Make sure that anybody stopping the queue after this
+ * sees the new next_to_clean.
+ */
+ smp_mb();
+ if (__netif_subqueue_stopped(tx_ring->netdev,
+ tx_ring->queue_index) &&
+ !(test_bit(__IGB_DOWN, &adapter->state))) {
+ netif_wake_subqueue(tx_ring->netdev,
+ tx_ring->queue_index);
+
+ u64_stats_update_begin(&tx_ring->tx_syncp);
+ tx_ring->tx_stats.restart_queue++;
+ u64_stats_update_end(&tx_ring->tx_syncp);
+ }
+ }
+
+ return !!budget;
}
static inline void igb_rx_checksum(struct igb_ring *ring,
--
1.7.6
^ permalink raw reply related
* [net-next 12/13] igb: split buffer_info into tx_buffer_info and rx_buffer_info
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
In order to be able to improve the performance of the Tx path it has been
necessary to add addition info to the tx_buffer_info structure. However a
side effect is that the structure has gotten larger and this in turn has
also increased the size of the Rx buffer info structure. In order to avoid
this in the future I am splitting the single buffer_info structure into two
separate ones and instead I will join them by making the buffer_info
pointer in the ring a union of the two.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb.h | 42 +++++-----
drivers/net/ethernet/intel/igb/igb_ethtool.c | 15 ++--
drivers/net/ethernet/intel/igb/igb_main.c | 123 +++++++++++++-------------
3 files changed, 92 insertions(+), 88 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index cfa590c8..fab6e92 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -132,27 +132,24 @@ struct vf_data_storage {
/* wrapper around a pointer to a socket buffer,
* so a DMA handle can be stored along with the buffer */
-struct igb_buffer {
+struct igb_tx_buffer {
+ u16 next_to_watch;
+ unsigned long time_stamp;
+ dma_addr_t dma;
+ u32 length;
+ u32 tx_flags;
+ struct sk_buff *skb;
+ unsigned int bytecount;
+ u16 gso_segs;
+ u8 mapped_as_page;
+};
+
+struct igb_rx_buffer {
struct sk_buff *skb;
dma_addr_t dma;
- union {
- /* TX */
- struct {
- unsigned long time_stamp;
- u16 length;
- u16 next_to_watch;
- unsigned int bytecount;
- u16 gso_segs;
- u8 tx_flags;
- u8 mapped_as_page;
- };
- /* RX */
- struct {
- struct page *page;
- dma_addr_t page_dma;
- u16 page_offset;
- };
- };
+ struct page *page;
+ dma_addr_t page_dma;
+ u32 page_offset;
};
struct igb_tx_queue_stats {
@@ -191,7 +188,10 @@ struct igb_ring {
struct igb_q_vector *q_vector; /* backlink to q_vector */
struct net_device *netdev; /* back pointer to net_device */
struct device *dev; /* device pointer for dma mapping */
- struct igb_buffer *buffer_info; /* array of buffer info structs */
+ union { /* array of buffer info structs */
+ struct igb_tx_buffer *tx_buffer_info;
+ struct igb_rx_buffer *rx_buffer_info;
+ };
void *desc; /* descriptor ring memory */
unsigned long flags; /* ring specific flags */
void __iomem *tail; /* pointer to ring tail register */
@@ -377,7 +377,7 @@ extern void igb_setup_tctl(struct igb_adapter *);
extern void igb_setup_rctl(struct igb_adapter *);
extern netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *);
extern void igb_unmap_and_free_tx_resource(struct igb_ring *,
- struct igb_buffer *);
+ struct igb_tx_buffer *);
extern void igb_alloc_rx_buffers(struct igb_ring *, u16);
extern void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *);
extern bool igb_has_link(struct igb_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index f6da820..6bcfad1 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -1579,7 +1579,8 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
unsigned int size)
{
union e1000_adv_rx_desc *rx_desc;
- struct igb_buffer *buffer_info;
+ struct igb_rx_buffer *rx_buffer_info;
+ struct igb_tx_buffer *tx_buffer_info;
int rx_ntc, tx_ntc, count = 0;
u32 staterr;
@@ -1591,22 +1592,22 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
while (staterr & E1000_RXD_STAT_DD) {
/* check rx buffer */
- buffer_info = &rx_ring->buffer_info[rx_ntc];
+ rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc];
/* unmap rx buffer, will be remapped by alloc_rx_buffers */
dma_unmap_single(rx_ring->dev,
- buffer_info->dma,
+ rx_buffer_info->dma,
IGB_RX_HDR_LEN,
DMA_FROM_DEVICE);
- buffer_info->dma = 0;
+ rx_buffer_info->dma = 0;
/* verify contents of skb */
- if (!igb_check_lbtest_frame(buffer_info->skb, size))
+ if (!igb_check_lbtest_frame(rx_buffer_info->skb, size))
count++;
/* unmap buffer on tx side */
- buffer_info = &tx_ring->buffer_info[tx_ntc];
- igb_unmap_and_free_tx_resource(tx_ring, buffer_info);
+ tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc];
+ igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
/* increment rx/tx next to clean counters */
rx_ntc++;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 989e774..afa0ca9 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -339,7 +339,6 @@ static void igb_dump(struct igb_adapter *adapter)
struct igb_ring *tx_ring;
union e1000_adv_tx_desc *tx_desc;
struct my_u0 { u64 a; u64 b; } *u0;
- struct igb_buffer *buffer_info;
struct igb_ring *rx_ring;
union e1000_adv_rx_desc *rx_desc;
u32 staterr;
@@ -376,8 +375,9 @@ static void igb_dump(struct igb_adapter *adapter)
printk(KERN_INFO "Queue [NTU] [NTC] [bi(ntc)->dma ]"
" leng ntw timestamp\n");
for (n = 0; n < adapter->num_tx_queues; n++) {
+ struct igb_tx_buffer *buffer_info;
tx_ring = adapter->tx_ring[n];
- buffer_info = &tx_ring->buffer_info[tx_ring->next_to_clean];
+ buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_clean];
printk(KERN_INFO " %5d %5X %5X %016llX %04X %3X %016llX\n",
n, tx_ring->next_to_use, tx_ring->next_to_clean,
(u64)buffer_info->dma,
@@ -413,8 +413,9 @@ static void igb_dump(struct igb_adapter *adapter)
"leng ntw timestamp bi->skb\n");
for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
+ struct igb_tx_buffer *buffer_info;
tx_desc = IGB_TX_DESC(tx_ring, i);
- buffer_info = &tx_ring->buffer_info[i];
+ buffer_info = &tx_ring->tx_buffer_info[i];
u0 = (struct my_u0 *)tx_desc;
printk(KERN_INFO "T [0x%03X] %016llX %016llX %016llX"
" %04X %3X %016llX %p", i,
@@ -493,7 +494,8 @@ rx_ring_summary:
"<-- Adv Rx Write-Back format\n");
for (i = 0; i < rx_ring->count; i++) {
- buffer_info = &rx_ring->buffer_info[i];
+ struct igb_rx_buffer *buffer_info;
+ buffer_info = &rx_ring->rx_buffer_info[i];
rx_desc = IGB_RX_DESC(rx_ring, i);
u0 = (struct my_u0 *)rx_desc;
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
@@ -2576,9 +2578,9 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring)
struct device *dev = tx_ring->dev;
int size;
- size = sizeof(struct igb_buffer) * tx_ring->count;
- tx_ring->buffer_info = vzalloc(size);
- if (!tx_ring->buffer_info)
+ size = sizeof(struct igb_tx_buffer) * tx_ring->count;
+ tx_ring->tx_buffer_info = vzalloc(size);
+ if (!tx_ring->tx_buffer_info)
goto err;
/* round up to nearest 4K */
@@ -2598,7 +2600,7 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring)
return 0;
err:
- vfree(tx_ring->buffer_info);
+ vfree(tx_ring->tx_buffer_info);
dev_err(dev,
"Unable to allocate memory for the transmit descriptor ring\n");
return -ENOMEM;
@@ -2719,9 +2721,9 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
struct device *dev = rx_ring->dev;
int size, desc_len;
- size = sizeof(struct igb_buffer) * rx_ring->count;
- rx_ring->buffer_info = vzalloc(size);
- if (!rx_ring->buffer_info)
+ size = sizeof(struct igb_rx_buffer) * rx_ring->count;
+ rx_ring->rx_buffer_info = vzalloc(size);
+ if (!rx_ring->rx_buffer_info)
goto err;
desc_len = sizeof(union e1000_adv_rx_desc);
@@ -2744,8 +2746,8 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
return 0;
err:
- vfree(rx_ring->buffer_info);
- rx_ring->buffer_info = NULL;
+ vfree(rx_ring->rx_buffer_info);
+ rx_ring->rx_buffer_info = NULL;
dev_err(dev, "Unable to allocate memory for the receive descriptor"
" ring\n");
return -ENOMEM;
@@ -3107,8 +3109,8 @@ void igb_free_tx_resources(struct igb_ring *tx_ring)
{
igb_clean_tx_ring(tx_ring);
- vfree(tx_ring->buffer_info);
- tx_ring->buffer_info = NULL;
+ vfree(tx_ring->tx_buffer_info);
+ tx_ring->tx_buffer_info = NULL;
/* if not set, then don't free */
if (!tx_ring->desc)
@@ -3135,7 +3137,7 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter)
}
void igb_unmap_and_free_tx_resource(struct igb_ring *tx_ring,
- struct igb_buffer *buffer_info)
+ struct igb_tx_buffer *buffer_info)
{
if (buffer_info->dma) {
if (buffer_info->mapped_as_page)
@@ -3166,21 +3168,21 @@ void igb_unmap_and_free_tx_resource(struct igb_ring *tx_ring,
**/
static void igb_clean_tx_ring(struct igb_ring *tx_ring)
{
- struct igb_buffer *buffer_info;
+ struct igb_tx_buffer *buffer_info;
unsigned long size;
unsigned int i;
- if (!tx_ring->buffer_info)
+ if (!tx_ring->tx_buffer_info)
return;
/* Free all the Tx ring sk_buffs */
for (i = 0; i < tx_ring->count; i++) {
- buffer_info = &tx_ring->buffer_info[i];
+ buffer_info = &tx_ring->tx_buffer_info[i];
igb_unmap_and_free_tx_resource(tx_ring, buffer_info);
}
- size = sizeof(struct igb_buffer) * tx_ring->count;
- memset(tx_ring->buffer_info, 0, size);
+ size = sizeof(struct igb_tx_buffer) * tx_ring->count;
+ memset(tx_ring->tx_buffer_info, 0, size);
/* Zero out the descriptor ring */
memset(tx_ring->desc, 0, tx_ring->size);
@@ -3211,8 +3213,8 @@ void igb_free_rx_resources(struct igb_ring *rx_ring)
{
igb_clean_rx_ring(rx_ring);
- vfree(rx_ring->buffer_info);
- rx_ring->buffer_info = NULL;
+ vfree(rx_ring->rx_buffer_info);
+ rx_ring->rx_buffer_info = NULL;
/* if not set, then don't free */
if (!rx_ring->desc)
@@ -3247,12 +3249,12 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring)
unsigned long size;
u16 i;
- if (!rx_ring->buffer_info)
+ if (!rx_ring->rx_buffer_info)
return;
/* Free all the Rx ring sk_buffs */
for (i = 0; i < rx_ring->count; i++) {
- struct igb_buffer *buffer_info = &rx_ring->buffer_info[i];
+ struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i];
if (buffer_info->dma) {
dma_unmap_single(rx_ring->dev,
buffer_info->dma,
@@ -3279,8 +3281,8 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring)
}
}
- size = sizeof(struct igb_buffer) * rx_ring->count;
- memset(rx_ring->buffer_info, 0, size);
+ size = sizeof(struct igb_rx_buffer) * rx_ring->count;
+ memset(rx_ring->rx_buffer_info, 0, size);
/* Zero out the descriptor ring */
memset(rx_ring->desc, 0, rx_ring->size);
@@ -3964,7 +3966,7 @@ static inline int igb_tso(struct igb_ring *tx_ring,
struct e1000_adv_tx_context_desc *context_desc;
unsigned int i;
int err;
- struct igb_buffer *buffer_info;
+ struct igb_tx_buffer *buffer_info;
u32 info = 0, tu_cmd = 0;
u32 mss_l4len_idx;
u8 l4len;
@@ -3995,7 +3997,7 @@ static inline int igb_tso(struct igb_ring *tx_ring,
i = tx_ring->next_to_use;
- buffer_info = &tx_ring->buffer_info[i];
+ buffer_info = &tx_ring->tx_buffer_info[i];
context_desc = IGB_TX_CTXTDESC(tx_ring, i);
/* VLAN MACLEN IPLEN */
if (tx_flags & IGB_TX_FLAGS_VLAN)
@@ -4043,14 +4045,14 @@ static inline bool igb_tx_csum(struct igb_ring *tx_ring,
{
struct e1000_adv_tx_context_desc *context_desc;
struct device *dev = tx_ring->dev;
- struct igb_buffer *buffer_info;
+ struct igb_tx_buffer *buffer_info;
u32 info = 0, tu_cmd = 0;
unsigned int i;
if ((skb->ip_summed == CHECKSUM_PARTIAL) ||
(tx_flags & IGB_TX_FLAGS_VLAN)) {
i = tx_ring->next_to_use;
- buffer_info = &tx_ring->buffer_info[i];
+ buffer_info = &tx_ring->tx_buffer_info[i];
context_desc = IGB_TX_CTXTDESC(tx_ring, i);
if (tx_flags & IGB_TX_FLAGS_VLAN)
@@ -4126,7 +4128,7 @@ static inline bool igb_tx_csum(struct igb_ring *tx_ring,
static inline int igb_tx_map(struct igb_ring *tx_ring, struct sk_buff *skb,
unsigned int first)
{
- struct igb_buffer *buffer_info;
+ struct igb_tx_buffer *buffer_info;
struct device *dev = tx_ring->dev;
unsigned int hlen = skb_headlen(skb);
unsigned int count = 0, i;
@@ -4135,7 +4137,7 @@ static inline int igb_tx_map(struct igb_ring *tx_ring, struct sk_buff *skb,
i = tx_ring->next_to_use;
- buffer_info = &tx_ring->buffer_info[i];
+ buffer_info = &tx_ring->tx_buffer_info[i];
BUG_ON(hlen >= IGB_MAX_DATA_PER_TXD);
buffer_info->length = hlen;
/* set time_stamp *before* dma to help avoid a possible race */
@@ -4155,7 +4157,7 @@ static inline int igb_tx_map(struct igb_ring *tx_ring, struct sk_buff *skb,
if (i == tx_ring->count)
i = 0;
- buffer_info = &tx_ring->buffer_info[i];
+ buffer_info = &tx_ring->tx_buffer_info[i];
BUG_ON(len >= IGB_MAX_DATA_PER_TXD);
buffer_info->length = len;
buffer_info->time_stamp = jiffies;
@@ -4168,12 +4170,12 @@ static inline int igb_tx_map(struct igb_ring *tx_ring, struct sk_buff *skb,
}
- tx_ring->buffer_info[i].skb = skb;
- tx_ring->buffer_info[i].tx_flags = skb_shinfo(skb)->tx_flags;
+ buffer_info->skb = skb;
+ buffer_info->tx_flags = skb_shinfo(skb)->tx_flags;
/* multiply data chunks by size of headers */
- tx_ring->buffer_info[i].bytecount = ((gso_segs - 1) * hlen) + skb->len;
- tx_ring->buffer_info[i].gso_segs = gso_segs;
- tx_ring->buffer_info[first].next_to_watch = i;
+ buffer_info->bytecount = ((gso_segs - 1) * hlen) + skb->len;
+ buffer_info->gso_segs = gso_segs;
+ tx_ring->tx_buffer_info[first].next_to_watch = i;
return ++count;
@@ -4192,7 +4194,7 @@ dma_error:
if (i == 0)
i = tx_ring->count;
i--;
- buffer_info = &tx_ring->buffer_info[i];
+ buffer_info = &tx_ring->tx_buffer_info[i];
igb_unmap_and_free_tx_resource(tx_ring, buffer_info);
}
@@ -4204,7 +4206,7 @@ static inline void igb_tx_queue(struct igb_ring *tx_ring,
u8 hdr_len)
{
union e1000_adv_tx_desc *tx_desc;
- struct igb_buffer *buffer_info;
+ struct igb_tx_buffer *buffer_info;
u32 olinfo_status = 0, cmd_type_len;
unsigned int i = tx_ring->next_to_use;
@@ -4240,7 +4242,7 @@ static inline void igb_tx_queue(struct igb_ring *tx_ring,
olinfo_status |= ((paylen - hdr_len) << E1000_ADVTXD_PAYLEN_SHIFT);
do {
- buffer_info = &tx_ring->buffer_info[i];
+ buffer_info = &tx_ring->tx_buffer_info[i];
tx_desc = IGB_TX_DESC(tx_ring, i);
tx_desc->read.buffer_addr = cpu_to_le64(buffer_info->dma);
tx_desc->read.cmd_type_len =
@@ -4353,7 +4355,7 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
count = igb_tx_map(tx_ring, skb, first);
if (!count) {
dev_kfree_skb_any(skb);
- tx_ring->buffer_info[first].time_stamp = 0;
+ tx_ring->tx_buffer_info[first].time_stamp = 0;
tx_ring->next_to_use = first;
return NETDEV_TX_OK;
}
@@ -5551,13 +5553,14 @@ static void igb_systim_to_hwtstamp(struct igb_adapter *adapter,
/**
* igb_tx_hwtstamp - utility function which checks for TX time stamp
* @q_vector: pointer to q_vector containing needed info
- * @buffer: pointer to igb_buffer structure
+ * @buffer: pointer to igb_tx_buffer structure
*
* If we were asked to do hardware stamping and such a time stamp is
* available, then it must have been for this skb here because we only
* allow only one such packet into the queue.
*/
-static void igb_tx_hwtstamp(struct igb_q_vector *q_vector, struct igb_buffer *buffer_info)
+static void igb_tx_hwtstamp(struct igb_q_vector *q_vector,
+ struct igb_tx_buffer *buffer_info)
{
struct igb_adapter *adapter = q_vector->adapter;
struct e1000_hw *hw = &adapter->hw;
@@ -5585,7 +5588,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
{
struct igb_adapter *adapter = q_vector->adapter;
struct igb_ring *tx_ring = q_vector->tx_ring;
- struct igb_buffer *tx_buffer;
+ struct igb_tx_buffer *tx_buffer;
union e1000_adv_tx_desc *tx_desc;
unsigned int total_bytes = 0, total_packets = 0;
unsigned int budget = q_vector->tx_work_limit;
@@ -5594,7 +5597,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
if (test_bit(__IGB_DOWN, &adapter->state))
return true;
- tx_buffer = &tx_ring->buffer_info[i];
+ tx_buffer = &tx_ring->tx_buffer_info[i];
tx_desc = IGB_TX_DESC(tx_ring, i);
for (; budget; budget--) {
@@ -5627,7 +5630,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
i++;
if (unlikely(i == tx_ring->count)) {
i = 0;
- tx_buffer = tx_ring->buffer_info;
+ tx_buffer = tx_ring->tx_buffer_info;
tx_desc = IGB_TX_DESC(tx_ring, 0);
}
} while (eop_desc);
@@ -5643,7 +5646,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
if (tx_ring->detect_tx_hung) {
struct e1000_hw *hw = &adapter->hw;
- u16 eop = tx_ring->buffer_info[i].next_to_watch;
+ u16 eop = tx_ring->tx_buffer_info[i].next_to_watch;
union e1000_adv_tx_desc *eop_desc;
eop_desc = IGB_TX_DESC(tx_ring, eop);
@@ -5651,8 +5654,8 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
/* Detect a transmit hang in hardware, this serializes the
* check with the clearing of time_stamp and movement of i */
tx_ring->detect_tx_hung = false;
- if (tx_ring->buffer_info[i].time_stamp &&
- time_after(jiffies, tx_ring->buffer_info[i].time_stamp +
+ if (tx_ring->tx_buffer_info[i].time_stamp &&
+ time_after(jiffies, tx_ring->tx_buffer_info[i].time_stamp +
(adapter->tx_timeout_factor * HZ)) &&
!(rd32(E1000_STATUS) & E1000_STATUS_TXOFF)) {
@@ -5674,7 +5677,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
readl(tx_ring->tail),
tx_ring->next_to_use,
tx_ring->next_to_clean,
- tx_ring->buffer_info[eop].time_stamp,
+ tx_ring->tx_buffer_info[eop].time_stamp,
eop,
jiffies,
eop_desc->wb.status);
@@ -5802,7 +5805,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget)
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
while (staterr & E1000_RXD_STAT_DD) {
- struct igb_buffer *buffer_info = &rx_ring->buffer_info[i];
+ struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i];
struct sk_buff *skb = buffer_info->skb;
union e1000_adv_rx_desc *next_rxd;
@@ -5855,8 +5858,8 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget)
}
if (!(staterr & E1000_RXD_STAT_EOP)) {
- struct igb_buffer *next_buffer;
- next_buffer = &rx_ring->buffer_info[i];
+ struct igb_rx_buffer *next_buffer;
+ next_buffer = &rx_ring->rx_buffer_info[i];
buffer_info->skb = next_buffer->skb;
buffer_info->dma = next_buffer->dma;
next_buffer->skb = skb;
@@ -5917,7 +5920,7 @@ next_desc:
}
static bool igb_alloc_mapped_skb(struct igb_ring *rx_ring,
- struct igb_buffer *bi)
+ struct igb_rx_buffer *bi)
{
struct sk_buff *skb = bi->skb;
dma_addr_t dma = bi->dma;
@@ -5951,7 +5954,7 @@ static bool igb_alloc_mapped_skb(struct igb_ring *rx_ring,
}
static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
- struct igb_buffer *bi)
+ struct igb_rx_buffer *bi)
{
struct page *page = bi->page;
dma_addr_t page_dma = bi->page_dma;
@@ -5990,11 +5993,11 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
{
union e1000_adv_rx_desc *rx_desc;
- struct igb_buffer *bi;
+ struct igb_rx_buffer *bi;
u16 i = rx_ring->next_to_use;
rx_desc = IGB_RX_DESC(rx_ring, i);
- bi = &rx_ring->buffer_info[i];
+ bi = &rx_ring->rx_buffer_info[i];
i -= rx_ring->count;
while (cleaned_count--) {
@@ -6015,7 +6018,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
i++;
if (unlikely(!i)) {
rx_desc = IGB_RX_DESC(rx_ring, 0);
- bi = rx_ring->buffer_info;
+ bi = rx_ring->rx_buffer_info;
i -= rx_ring->count;
}
--
1.7.6
^ permalink raw reply related
* [net-next 13/13] igb: Consolidate creation of Tx context descriptors into a single function
From: Jeff Kirsher @ 2011-09-17 8:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316246677-8830-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch is meant to simplify the transmit path by reducing the overhead
for creating a transmit context descriptor. The current implementation is
split with igb_tso and igb_tx_csum doing two separate implementations on
how to setup the tx_buffer_info structure and the tx_desc. By combining
them it is possible to reduce code and simplify things since now only one
function will create context descriptors.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb_main.c | 233 +++++++++++++----------------
1 files changed, 106 insertions(+), 127 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index afa0ca9..563224a 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -45,6 +45,9 @@
#include <linux/pci-aspm.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <linux/sctp.h>
#include <linux/if_ether.h>
#include <linux/aer.h>
#include <linux/prefetch.h>
@@ -3960,16 +3963,39 @@ set_itr_now:
#define IGB_TX_FLAGS_VLAN_MASK 0xffff0000
#define IGB_TX_FLAGS_VLAN_SHIFT 16
+void igb_tx_ctxtdesc(struct igb_ring *tx_ring, u32 vlan_macip_lens,
+ u32 type_tucmd, u32 mss_l4len_idx)
+{
+ struct e1000_adv_tx_context_desc *context_desc;
+ u16 i = tx_ring->next_to_use;
+
+ context_desc = IGB_TX_CTXTDESC(tx_ring, i);
+
+ i++;
+ tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
+
+ /* set bits to identify this as an advanced context descriptor */
+ type_tucmd |= E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT;
+
+ /* For 82575, context index must be unique per ring. */
+ if (tx_ring->flags & IGB_RING_FLAG_TX_CTX_IDX)
+ mss_l4len_idx |= tx_ring->reg_idx << 4;
+
+ context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens);
+ context_desc->seqnum_seed = 0;
+ context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd);
+ context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx);
+}
+
static inline int igb_tso(struct igb_ring *tx_ring,
struct sk_buff *skb, u32 tx_flags, u8 *hdr_len)
{
- struct e1000_adv_tx_context_desc *context_desc;
- unsigned int i;
int err;
- struct igb_tx_buffer *buffer_info;
- u32 info = 0, tu_cmd = 0;
- u32 mss_l4len_idx;
- u8 l4len;
+ u32 vlan_macip_lens, type_tucmd;
+ u32 mss_l4len_idx, l4len;
+
+ if (!skb_is_gso(skb))
+ return 0;
if (skb_header_cloned(skb)) {
err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
@@ -3977,8 +4003,8 @@ static inline int igb_tso(struct igb_ring *tx_ring,
return err;
}
- l4len = tcp_hdrlen(skb);
- *hdr_len += l4len;
+ /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
+ type_tucmd = E1000_ADVTXD_TUCMD_L4T_TCP;
if (skb->protocol == htons(ETH_P_IP)) {
struct iphdr *iph = ip_hdr(skb);
@@ -3988,6 +4014,7 @@ static inline int igb_tso(struct igb_ring *tx_ring,
iph->daddr, 0,
IPPROTO_TCP,
0);
+ type_tucmd |= E1000_ADVTXD_TUCMD_IPV4;
} else if (skb_is_gso_v6(skb)) {
ipv6_hdr(skb)->payload_len = 0;
tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
@@ -3995,131 +4022,85 @@ static inline int igb_tso(struct igb_ring *tx_ring,
0, IPPROTO_TCP, 0);
}
- i = tx_ring->next_to_use;
-
- buffer_info = &tx_ring->tx_buffer_info[i];
- context_desc = IGB_TX_CTXTDESC(tx_ring, i);
- /* VLAN MACLEN IPLEN */
- if (tx_flags & IGB_TX_FLAGS_VLAN)
- info |= (tx_flags & IGB_TX_FLAGS_VLAN_MASK);
- info |= (skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT);
- *hdr_len += skb_network_offset(skb);
- info |= skb_network_header_len(skb);
- *hdr_len += skb_network_header_len(skb);
- context_desc->vlan_macip_lens = cpu_to_le32(info);
-
- /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
- tu_cmd |= (E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT);
-
- if (skb->protocol == htons(ETH_P_IP))
- tu_cmd |= E1000_ADVTXD_TUCMD_IPV4;
- tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
-
- context_desc->type_tucmd_mlhl = cpu_to_le32(tu_cmd);
+ l4len = tcp_hdrlen(skb);
+ *hdr_len = skb_transport_offset(skb) + l4len;
/* MSS L4LEN IDX */
- mss_l4len_idx = (skb_shinfo(skb)->gso_size << E1000_ADVTXD_MSS_SHIFT);
- mss_l4len_idx |= (l4len << E1000_ADVTXD_L4LEN_SHIFT);
+ mss_l4len_idx = l4len << E1000_ADVTXD_L4LEN_SHIFT;
+ mss_l4len_idx |= skb_shinfo(skb)->gso_size << E1000_ADVTXD_MSS_SHIFT;
- /* For 82575, context index must be unique per ring. */
- if (tx_ring->flags & IGB_RING_FLAG_TX_CTX_IDX)
- mss_l4len_idx |= tx_ring->reg_idx << 4;
-
- context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx);
- context_desc->seqnum_seed = 0;
-
- buffer_info->time_stamp = jiffies;
- buffer_info->next_to_watch = i;
- buffer_info->dma = 0;
- i++;
- if (i == tx_ring->count)
- i = 0;
+ /* VLAN MACLEN IPLEN */
+ vlan_macip_lens = skb_network_header_len(skb);
+ vlan_macip_lens |= skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT;
+ vlan_macip_lens |= tx_flags & IGB_TX_FLAGS_VLAN_MASK;
- tx_ring->next_to_use = i;
+ igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx);
- return true;
+ return 1;
}
static inline bool igb_tx_csum(struct igb_ring *tx_ring,
struct sk_buff *skb, u32 tx_flags)
{
- struct e1000_adv_tx_context_desc *context_desc;
- struct device *dev = tx_ring->dev;
- struct igb_tx_buffer *buffer_info;
- u32 info = 0, tu_cmd = 0;
- unsigned int i;
-
- if ((skb->ip_summed == CHECKSUM_PARTIAL) ||
- (tx_flags & IGB_TX_FLAGS_VLAN)) {
- i = tx_ring->next_to_use;
- buffer_info = &tx_ring->tx_buffer_info[i];
- context_desc = IGB_TX_CTXTDESC(tx_ring, i);
-
- if (tx_flags & IGB_TX_FLAGS_VLAN)
- info |= (tx_flags & IGB_TX_FLAGS_VLAN_MASK);
-
- info |= (skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT);
- if (skb->ip_summed == CHECKSUM_PARTIAL)
- info |= skb_network_header_len(skb);
-
- context_desc->vlan_macip_lens = cpu_to_le32(info);
-
- tu_cmd |= (E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT);
-
- if (skb->ip_summed == CHECKSUM_PARTIAL) {
- __be16 protocol;
+ u32 vlan_macip_lens = 0;
+ u32 mss_l4len_idx = 0;
+ u32 type_tucmd = 0;
- if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
- const struct vlan_ethhdr *vhdr =
- (const struct vlan_ethhdr*)skb->data;
-
- protocol = vhdr->h_vlan_encapsulated_proto;
- } else {
- protocol = skb->protocol;
+ if (skb->ip_summed != CHECKSUM_PARTIAL) {
+ if (!(tx_flags & IGB_TX_FLAGS_VLAN))
+ return false;
+ } else {
+ u8 l4_hdr = 0;
+ switch (skb->protocol) {
+ case __constant_htons(ETH_P_IP):
+ vlan_macip_lens |= skb_network_header_len(skb);
+ type_tucmd |= E1000_ADVTXD_TUCMD_IPV4;
+ l4_hdr = ip_hdr(skb)->protocol;
+ break;
+ case __constant_htons(ETH_P_IPV6):
+ vlan_macip_lens |= skb_network_header_len(skb);
+ l4_hdr = ipv6_hdr(skb)->nexthdr;
+ break;
+ default:
+ if (unlikely(net_ratelimit())) {
+ dev_warn(tx_ring->dev,
+ "partial checksum but proto=%x!\n",
+ skb->protocol);
}
+ break;
+ }
- switch (protocol) {
- case cpu_to_be16(ETH_P_IP):
- tu_cmd |= E1000_ADVTXD_TUCMD_IPV4;
- if (ip_hdr(skb)->protocol == IPPROTO_TCP)
- tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
- else if (ip_hdr(skb)->protocol == IPPROTO_SCTP)
- tu_cmd |= E1000_ADVTXD_TUCMD_L4T_SCTP;
- break;
- case cpu_to_be16(ETH_P_IPV6):
- /* XXX what about other V6 headers?? */
- if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
- tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
- else if (ipv6_hdr(skb)->nexthdr == IPPROTO_SCTP)
- tu_cmd |= E1000_ADVTXD_TUCMD_L4T_SCTP;
- break;
- default:
- if (unlikely(net_ratelimit()))
- dev_warn(dev,
- "partial checksum but proto=%x!\n",
- skb->protocol);
- break;
+ switch (l4_hdr) {
+ case IPPROTO_TCP:
+ type_tucmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
+ mss_l4len_idx = tcp_hdrlen(skb) <<
+ E1000_ADVTXD_L4LEN_SHIFT;
+ break;
+ case IPPROTO_SCTP:
+ type_tucmd |= E1000_ADVTXD_TUCMD_L4T_SCTP;
+ mss_l4len_idx = sizeof(struct sctphdr) <<
+ E1000_ADVTXD_L4LEN_SHIFT;
+ break;
+ case IPPROTO_UDP:
+ mss_l4len_idx = sizeof(struct udphdr) <<
+ E1000_ADVTXD_L4LEN_SHIFT;
+ break;
+ default:
+ if (unlikely(net_ratelimit())) {
+ dev_warn(tx_ring->dev,
+ "partial checksum but l4 proto=%x!\n",
+ l4_hdr);
}
+ break;
}
+ }
- context_desc->type_tucmd_mlhl = cpu_to_le32(tu_cmd);
- context_desc->seqnum_seed = 0;
- if (tx_ring->flags & IGB_RING_FLAG_TX_CTX_IDX)
- context_desc->mss_l4len_idx =
- cpu_to_le32(tx_ring->reg_idx << 4);
+ vlan_macip_lens |= skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT;
+ vlan_macip_lens |= tx_flags & IGB_TX_FLAGS_VLAN_MASK;
- buffer_info->time_stamp = jiffies;
- buffer_info->next_to_watch = i;
- buffer_info->dma = 0;
+ igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx);
- i++;
- if (i == tx_ring->count)
- i = 0;
- tx_ring->next_to_use = i;
-
- return true;
- }
- return false;
+ return (skb->ip_summed == CHECKSUM_PARTIAL);
}
#define IGB_MAX_TXD_PWR 16
@@ -4140,8 +4121,6 @@ static inline int igb_tx_map(struct igb_ring *tx_ring, struct sk_buff *skb,
buffer_info = &tx_ring->tx_buffer_info[i];
BUG_ON(hlen >= IGB_MAX_DATA_PER_TXD);
buffer_info->length = hlen;
- /* set time_stamp *before* dma to help avoid a possible race */
- buffer_info->time_stamp = jiffies;
buffer_info->next_to_watch = i;
buffer_info->dma = dma_map_single(dev, skb->data, hlen,
DMA_TO_DEVICE);
@@ -4160,7 +4139,6 @@ static inline int igb_tx_map(struct igb_ring *tx_ring, struct sk_buff *skb,
buffer_info = &tx_ring->tx_buffer_info[i];
BUG_ON(len >= IGB_MAX_DATA_PER_TXD);
buffer_info->length = len;
- buffer_info->time_stamp = jiffies;
buffer_info->next_to_watch = i;
buffer_info->mapped_as_page = true;
buffer_info->dma = skb_frag_dma_map(dev, frag, 0, len,
@@ -4176,6 +4154,7 @@ static inline int igb_tx_map(struct igb_ring *tx_ring, struct sk_buff *skb,
buffer_info->bytecount = ((gso_segs - 1) * hlen) + skb->len;
buffer_info->gso_segs = gso_segs;
tx_ring->tx_buffer_info[first].next_to_watch = i;
+ tx_ring->tx_buffer_info[first].time_stamp = jiffies;
return ++count;
@@ -4304,7 +4283,7 @@ static inline int igb_maybe_stop_tx(struct igb_ring *tx_ring, int size)
netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
struct igb_ring *tx_ring)
{
- int tso = 0, count;
+ int tso, count;
u32 tx_flags = 0;
u16 first;
u8 hdr_len = 0;
@@ -4333,16 +4312,12 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
tx_flags |= IGB_TX_FLAGS_IPV4;
first = tx_ring->next_to_use;
- if (skb_is_gso(skb)) {
- tso = igb_tso(tx_ring, skb, tx_flags, &hdr_len);
- if (tso < 0) {
- dev_kfree_skb_any(skb);
- return NETDEV_TX_OK;
- }
- }
+ tso = igb_tso(tx_ring, skb, tx_flags, &hdr_len);
- if (tso)
+ if (tso < 0)
+ goto out_drop;
+ else if (tso)
tx_flags |= IGB_TX_FLAGS_TSO;
else if (igb_tx_csum(tx_ring, skb, tx_flags) &&
(skb->ip_summed == CHECKSUM_PARTIAL))
@@ -4366,6 +4341,10 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
igb_maybe_stop_tx(tx_ring, MAX_SKB_FRAGS + 4);
return NETDEV_TX_OK;
+
+out_drop:
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
}
static inline struct igb_ring *igb_tx_queue_mapping(struct igb_adapter *adapter,
--
1.7.6
^ permalink raw reply related
* Re: [net-next 01/13] ixgb: eliminate checkstack warnings
From: Joe Perches @ 2011-09-17 8:43 UTC (permalink / raw)
To: Jeff Kirsher; +Cc: davem, Jesse Brandeburg, netdev, gospo
In-Reply-To: <1316246677-8830-2-git-send-email-jeffrey.t.kirsher@intel.com>
On Sat, 2011-09-17 at 01:04 -0700, Jeff Kirsher wrote:
> From: Jesse Brandeburg <jesse.brandeburg@intel.com>
> Really trivial fix, use kzalloc/kree instead of stack space.
Some more trivialities...
> diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c\
[]
> @@ -1120,8 +1120,12 @@ ixgb_set_multi(struct net_device *netdev)
> rctl |= IXGB_RCTL_MPE;
> IXGB_WRITE_REG(hw, RCTL, rctl);
> } else {
> - u8 mta[IXGB_MAX_NUM_MULTICAST_ADDRESSES *
> - IXGB_ETH_LENGTH_OF_ADDRESS];
> + u8 *mta = kzalloc(IXGB_MAX_NUM_MULTICAST_ADDRESSES *
> + IXGB_ETH_LENGTH_OF_ADDRESS, GFP_KERNEL);
This doesn't need to be kzalloc as every byte is overwritten.
It should be kmalloc.
Maybe delete the #define IXGB_ETH_LENGTH_OF_ADDRESS and
sed 's/\bIXGB_ETH_LENGTH_OF_ADDRESS\b/ETH_ALEN/g' ?
Perhaps this loop could be clearer without the multiply:
i = 0;
netdev_for_each_mc_addr(ha, netdev)
memcpy(&mta[i++ * IXGB_ETH_LENGTH_OF_ADDRESS],
ha->addr, IXGB_ETH_LENGTH_OF_ADDRESS);
Perhaps:
u8 *addr = mta;
netdev_for_each_mc_addr(ha, netdev) {
memcpy(addr, ha->addr, ETH_ALEN);
addr += ETH_ALEN;
}
^ permalink raw reply
* [PATCH 0/5] Pull request for 'davem.r8169.fixes' branch
From: Francois Romieu @ 2011-09-17 9:56 UTC (permalink / raw)
To: davem; +Cc: netdev, Realtek linux nic maintainers, Hayes Wang
Please pull from branch 'davem.r8169.fixes' in repository
git://violet.fr.zoreil.com/romieu/linux davem.r8169.fixes
to get the changes below.
Distance from 'davem' (8e2ec639173f325977818c45011ee176ef2b11f6)
----------------------------------------------------------------
2544bfc0eb2581e0eedbdfea1468b3866223d47e
e03f33af79f0772156e1a1a1e36bdddf8012b2e4
106633897e086e1b47126996aac1a427eb80eb1b
bbb8af75d0a6a5138ff00fe0b1b95c4824effd55
c2b0c1e7fb69b54e704cb2dae5a80cc78a8cb0b2
Diffstat
--------
drivers/net/r8169.c | 32 +++++++++++++++++++++++++++-----
1 files changed, 27 insertions(+), 5 deletions(-)
Shortlog
--------
Francois Romieu (2):
r8169: remove erroneous processing of always set bit.
r8169: do not enable the TBI for anything but the original 8169.
Hayes Wang (3):
r8169: fix the reset setting for 8111evl
r8169: add MODULE_FIRMWARE for the firmware of 8111evl
r8169: fix WOL setting for 8105 and 8111evl
Patch
-----
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index 02339b3..c236670 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -407,6 +407,7 @@ enum rtl_register_content {
RxOK = 0x0001,
/* RxStatusDesc */
+ RxBOVF = (1 << 24),
RxFOVF = (1 << 23),
RxRWT = (1 << 22),
RxRES = (1 << 21),
@@ -682,6 +683,7 @@ struct rtl8169_private {
struct mii_if_info mii;
struct rtl8169_counters counters;
u32 saved_wolopts;
+ u32 opts1_mask;
struct rtl_fw {
const struct firmware *fw;
@@ -710,6 +712,7 @@ MODULE_FIRMWARE(FIRMWARE_8168D_1);
MODULE_FIRMWARE(FIRMWARE_8168D_2);
MODULE_FIRMWARE(FIRMWARE_8168E_1);
MODULE_FIRMWARE(FIRMWARE_8168E_2);
+MODULE_FIRMWARE(FIRMWARE_8168E_3);
MODULE_FIRMWARE(FIRMWARE_8105E_1);
static int rtl8169_open(struct net_device *dev);
@@ -3077,6 +3080,14 @@ static void rtl8169_phy_reset(struct net_device *dev,
netif_err(tp, link, dev, "PHY reset failed\n");
}
+static bool rtl_tbi_enabled(struct rtl8169_private *tp)
+{
+ void __iomem *ioaddr = tp->mmio_addr;
+
+ return (tp->mac_version == RTL_GIGA_MAC_VER_01) &&
+ (RTL_R8(PHYstatus) & TBI_Enable);
+}
+
static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
{
void __iomem *ioaddr = tp->mmio_addr;
@@ -3109,7 +3120,7 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
ADVERTISED_1000baseT_Half |
ADVERTISED_1000baseT_Full : 0));
- if (RTL_R8(PHYstatus) & TBI_Enable)
+ if (rtl_tbi_enabled(tp))
netif_info(tp, link, dev, "TBI auto-negotiating\n");
}
@@ -3319,9 +3330,16 @@ static void r810x_phy_power_up(struct rtl8169_private *tp)
static void r810x_pll_power_down(struct rtl8169_private *tp)
{
+ void __iomem *ioaddr = tp->mmio_addr;
+
if (__rtl8169_get_wol(tp) & WAKE_ANY) {
rtl_writephy(tp, 0x1f, 0x0000);
rtl_writephy(tp, MII_BMCR, 0x0000);
+
+ if (tp->mac_version == RTL_GIGA_MAC_VER_29 ||
+ tp->mac_version == RTL_GIGA_MAC_VER_30)
+ RTL_W32(RxConfig, RTL_R32(RxConfig) | AcceptBroadcast |
+ AcceptMulticast | AcceptMyPhys);
return;
}
@@ -3417,7 +3435,8 @@ static void r8168_pll_power_down(struct rtl8169_private *tp)
rtl_writephy(tp, MII_BMCR, 0x0000);
if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
- tp->mac_version == RTL_GIGA_MAC_VER_33)
+ tp->mac_version == RTL_GIGA_MAC_VER_33 ||
+ tp->mac_version == RTL_GIGA_MAC_VER_34)
RTL_W32(RxConfig, RTL_R32(RxConfig) | AcceptBroadcast |
AcceptMulticast | AcceptMyPhys);
return;
@@ -3727,8 +3746,7 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
tp->features |= rtl_try_msi(pdev, ioaddr, cfg);
RTL_W8(Cfg9346, Cfg9346_Lock);
- if ((tp->mac_version <= RTL_GIGA_MAC_VER_06) &&
- (RTL_R8(PHYstatus) & TBI_Enable)) {
+ if (rtl_tbi_enabled(tp)) {
tp->set_speed = rtl8169_set_speed_tbi;
tp->get_settings = rtl8169_gset_tbi;
tp->phy_reset_enable = rtl8169_tbi_reset_enable;
@@ -3777,6 +3795,9 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
tp->intr_event = cfg->intr_event;
tp->napi_event = cfg->napi_event;
+ tp->opts1_mask = (tp->mac_version != RTL_GIGA_MAC_VER_01) ?
+ ~(RxBOVF | RxFOVF) : ~0;
+
init_timer(&tp->timer);
tp->timer.data = (unsigned long) dev;
tp->timer.function = rtl8169_phy_timer;
@@ -3988,6 +4009,7 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp)
while (RTL_R8(TxPoll) & NPQ)
udelay(20);
} else if (tp->mac_version == RTL_GIGA_MAC_VER_34) {
+ RTL_W8(ChipCmd, RTL_R8(ChipCmd) | StopReq);
while (!(RTL_R32(TxConfig) & TXCFG_EMPTY))
udelay(100);
} else {
@@ -5314,7 +5336,7 @@ static int rtl8169_rx_interrupt(struct net_device *dev,
u32 status;
rmb();
- status = le32_to_cpu(desc->opts1);
+ status = le32_to_cpu(desc->opts1) & tp->opts1_mask;
if (status & DescOwn)
break;
--
Ueimor
^ permalink raw reply related
* [PATCH 1/5] r8169: fix the reset setting for 8111evl
From: Francois Romieu @ 2011-09-17 9:57 UTC (permalink / raw)
To: davem; +Cc: netdev, Realtek linux nic maintainers, Hayes Wang
In-Reply-To: <20110917095617.GA21630@electric-eye.fr.zoreil.com>
rtl8111evl should stop any TLP requirement before resetting by
enabling register 0x37 bit 7.
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
---
drivers/net/r8169.c | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index 02339b3..a1c9070 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -3988,6 +3988,7 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp)
while (RTL_R8(TxPoll) & NPQ)
udelay(20);
} else if (tp->mac_version == RTL_GIGA_MAC_VER_34) {
+ RTL_W8(ChipCmd, RTL_R8(ChipCmd) | StopReq);
while (!(RTL_R32(TxConfig) & TXCFG_EMPTY))
udelay(100);
} else {
--
1.7.6
^ permalink raw reply related
* [PATCH 2/5] r8169: add MODULE_FIRMWARE for the firmware of 8111evl
From: Francois Romieu @ 2011-09-17 9:57 UTC (permalink / raw)
To: davem; +Cc: netdev, Realtek linux nic maintainers, Hayes Wang
In-Reply-To: <20110917095617.GA21630@electric-eye.fr.zoreil.com>
Add MODULE_FIRMWARE for the firmware of RTL8111E-VL
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
---
drivers/net/r8169.c | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index a1c9070..b55fba7 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -710,6 +710,7 @@ MODULE_FIRMWARE(FIRMWARE_8168D_1);
MODULE_FIRMWARE(FIRMWARE_8168D_2);
MODULE_FIRMWARE(FIRMWARE_8168E_1);
MODULE_FIRMWARE(FIRMWARE_8168E_2);
+MODULE_FIRMWARE(FIRMWARE_8168E_3);
MODULE_FIRMWARE(FIRMWARE_8105E_1);
static int rtl8169_open(struct net_device *dev);
--
1.7.6
^ permalink raw reply related
* [PATCH 3/5] r8169: fix WOL setting for 8105 and 8111evl
From: Francois Romieu @ 2011-09-17 9:58 UTC (permalink / raw)
To: davem; +Cc: netdev, Realtek linux nic maintainers, Hayes Wang
In-Reply-To: <20110917095617.GA21630@electric-eye.fr.zoreil.com>
rtl8105, rtl8111E, and rtl8111evl need enable RxConfig bit 1 ~ 3
for supporting wake on lan.
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
---
drivers/net/r8169.c | 10 +++++++++-
1 files changed, 9 insertions(+), 1 deletions(-)
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index b55fba7..78c1d58 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -3320,9 +3320,16 @@ static void r810x_phy_power_up(struct rtl8169_private *tp)
static void r810x_pll_power_down(struct rtl8169_private *tp)
{
+ void __iomem *ioaddr = tp->mmio_addr;
+
if (__rtl8169_get_wol(tp) & WAKE_ANY) {
rtl_writephy(tp, 0x1f, 0x0000);
rtl_writephy(tp, MII_BMCR, 0x0000);
+
+ if (tp->mac_version == RTL_GIGA_MAC_VER_29 ||
+ tp->mac_version == RTL_GIGA_MAC_VER_30)
+ RTL_W32(RxConfig, RTL_R32(RxConfig) | AcceptBroadcast |
+ AcceptMulticast | AcceptMyPhys);
return;
}
@@ -3418,7 +3425,8 @@ static void r8168_pll_power_down(struct rtl8169_private *tp)
rtl_writephy(tp, MII_BMCR, 0x0000);
if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
- tp->mac_version == RTL_GIGA_MAC_VER_33)
+ tp->mac_version == RTL_GIGA_MAC_VER_33 ||
+ tp->mac_version == RTL_GIGA_MAC_VER_34)
RTL_W32(RxConfig, RTL_R32(RxConfig) | AcceptBroadcast |
AcceptMulticast | AcceptMyPhys);
return;
--
1.7.6
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox