* [PATCH 2/2] net/macvtap: add vhost support
From: Arnd Bergmann @ 2010-02-13 10:35 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, Ed Swierk, Patrick McHardy, Sridhar Samudrala,
qemu-devel, Michael S. Tsirkin
In-Reply-To: <201002131133.43028.arnd@arndb.de>
This adds support for passing a macvtap file descriptor into
vhost-net, much like we already do for tun/tap.
Most of the new code is taken from the respective patch
in the tun driver and may get consolidated in the future.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
drivers/net/macvtap.c | 98 ++++++++++++++++++++++++++++++++++---------
drivers/vhost/net.c | 8 +++-
include/linux/if_macvlan.h | 13 ++++++
3 files changed, 96 insertions(+), 23 deletions(-)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 7050997..e354501 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -58,6 +58,8 @@ static unsigned int macvtap_major;
static struct class *macvtap_class;
static struct cdev macvtap_cdev;
+static const struct proto_ops macvtap_socket_ops;
+
/*
* RCU usage:
* The macvtap_queue and the macvlan_dev are loosely coupled, the
@@ -176,7 +178,7 @@ static int macvtap_forward(struct net_device *dev, struct sk_buff *skb)
return -ENOLINK;
skb_queue_tail(&q->sk.sk_receive_queue, skb);
- wake_up(q->sk.sk_sleep);
+ wake_up_interruptible_poll(q->sk.sk_sleep, POLLIN | POLLRDNORM | POLLRDBAND);
return 0;
}
@@ -242,7 +244,7 @@ static void macvtap_sock_write_space(struct sock *sk)
return;
if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible_sync(sk->sk_sleep);
+ wake_up_interruptible_poll(sk->sk_sleep, POLLOUT | POLLWRNORM | POLLWRBAND);
}
static int macvtap_open(struct inode *inode, struct file *file)
@@ -270,6 +272,8 @@ static int macvtap_open(struct inode *inode, struct file *file)
init_waitqueue_head(&q->sock.wait);
q->sock.type = SOCK_RAW;
q->sock.state = SS_CONNECTED;
+ q->sock.file = file;
+ q->sock.ops = &macvtap_socket_ops;
sock_init_data(&q->sock, &q->sk);
q->sk.sk_write_space = macvtap_sock_write_space;
@@ -387,32 +391,20 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
rcu_read_lock_bh();
vlan = rcu_dereference(q->vlan);
- macvlan_count_rx(vlan, len, ret == 0, 0);
+ if (vlan)
+ macvlan_count_rx(vlan, len, ret == 0, 0);
rcu_read_unlock_bh();
return ret ? ret : len;
}
-static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
- unsigned long count, loff_t pos)
+static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb,
+ const struct iovec *iv, unsigned long len,
+ int noblock)
{
- struct file *file = iocb->ki_filp;
- struct macvtap_queue *q = file->private_data;
-
DECLARE_WAITQUEUE(wait, current);
struct sk_buff *skb;
- ssize_t len, ret = 0;
-
- if (!q) {
- ret = -ENOLINK;
- goto out;
- }
-
- len = iov_length(iv, count);
- if (len < 0) {
- ret = -EINVAL;
- goto out;
- }
+ ssize_t ret = 0;
add_wait_queue(q->sk.sk_sleep, &wait);
while (len) {
@@ -421,7 +413,7 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
/* Read frames from the queue */
skb = skb_dequeue(&q->sk.sk_receive_queue);
if (!skb) {
- if (file->f_flags & O_NONBLOCK) {
+ if (noblock) {
ret = -EAGAIN;
break;
}
@@ -440,7 +432,24 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
current->state = TASK_RUNNING;
remove_wait_queue(q->sk.sk_sleep, &wait);
+ return ret;
+}
+
+static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
+ unsigned long count, loff_t pos)
+{
+ struct file *file = iocb->ki_filp;
+ struct macvtap_queue *q = file->private_data;
+ ssize_t len, ret = 0;
+ len = iov_length(iv, count);
+ if (len < 0) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = macvtap_do_read(q, iocb, iv, len, file->f_flags & O_NONBLOCK);
+ ret = min_t(ssize_t, ret, len); /* XXX copied from tun.c. Why? */
out:
return ret;
}
@@ -538,6 +547,53 @@ static const struct file_operations macvtap_fops = {
#endif
};
+static int macvtap_sendmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t total_len)
+{
+ struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock);
+ return macvtap_get_user(q, m->msg_iov, total_len,
+ m->msg_flags & MSG_DONTWAIT);
+}
+
+static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t total_len,
+ int flags)
+{
+ struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock);
+ int ret;
+ if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
+ return -EINVAL;
+ ret = macvtap_do_read(q, 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;
+}
+
+/* Ops structure to mimic raw sockets with tun */
+static const struct proto_ops macvtap_socket_ops = {
+ .sendmsg = macvtap_sendmsg,
+ .recvmsg = macvtap_recvmsg,
+};
+
+/* Get an underlying socket object from tun file. Returns error unless file is
+ * attached to a device. The returned object works like a packet socket, it
+ * can be used for sock_sendmsg/sock_recvmsg. The caller is responsible for
+ * holding a reference to the file for as long as the socket is in use. */
+struct socket *macvtap_get_socket(struct file *file)
+{
+ struct macvtap_queue *q;
+ if (file->f_op != &macvtap_fops)
+ return ERR_PTR(-EINVAL);
+ q = file->private_data;
+ if (!q)
+ return ERR_PTR(-EBADFD);
+ return &q->sock;
+}
+EXPORT_SYMBOL_GPL(macvtap_get_socket);
+
static int macvtap_init(void)
{
int err;
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 4c89283..91a324c 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -22,6 +22,7 @@
#include <linux/if_packet.h>
#include <linux/if_arp.h>
#include <linux/if_tun.h>
+#include <linux/if_macvlan.h>
#include <net/sock.h>
@@ -452,13 +453,16 @@ err:
return ERR_PTR(r);
}
-static struct socket *get_tun_socket(int fd)
+static struct socket *get_tap_socket(int fd)
{
struct file *file = fget(fd);
struct socket *sock;
if (!file)
return ERR_PTR(-EBADF);
sock = tun_get_socket(file);
+ if (!IS_ERR(sock))
+ return sock;
+ sock = macvtap_get_socket(file);
if (IS_ERR(sock))
fput(file);
return sock;
@@ -473,7 +477,7 @@ static struct socket *get_socket(int fd)
sock = get_raw_socket(fd);
if (!IS_ERR(sock))
return sock;
- sock = get_tun_socket(fd);
+ sock = get_tap_socket(fd);
if (!IS_ERR(sock))
return sock;
return ERR_PTR(-ENOTSOCK);
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 51f1512..7d7f1e3 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -7,6 +7,19 @@
#include <linux/netlink.h>
#include <net/netlink.h>
+#if defined(CONFIG_MACVTAP) || defined(CONFIG_MACVTAP_MODULE)
+struct socket *macvtap_get_socket(struct file *);
+#else
+#include <linux/err.h>
+#include <linux/errno.h>
+struct file;
+struct socket;
+static inline struct socket *macvtap_get_socket(struct file *f)
+{
+ return ERR_PTR(-EINVAL);
+}
+#endif /* CONFIG_MACVTAP */
+
struct macvlan_port;
struct macvtap_queue;
--
1.6.3.3
^ permalink raw reply related
* [PATCH 1/2] macvtap: rework object lifetime rules
From: Arnd Bergmann @ 2010-02-13 10:33 UTC (permalink / raw)
To: Arnd Bergmann
Cc: netdev, linux-kernel, Ed Swierk, Patrick McHardy,
Sridhar Samudrala, qemu-devel, Michael S. Tsirkin
The original macvtap code has a number of problems
resulting from the use of RCU for protecting the
access to struct macvtap_queue from open files.
This includes
- need for GFP_ATOMIC allocations for skbs
- potential deadlocks when copy_*_user sleeps
- inability to work with vhost-net
Changing the lifetime of macvtap_queue to always
depend on the open file solves all these. The
RCU reference simply moves one step down to
the reference on the macvlan_dev, which we
only need for nonblocking operations.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
drivers/net/macvtap.c | 170 +++++++++++++++++++++++++-----------------------
1 files changed, 89 insertions(+), 81 deletions(-)
This patch replaces the previous one that cleans up the locking in a different way.
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index ad1f6ef..7050997 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -60,29 +60,19 @@ static struct cdev macvtap_cdev;
/*
* RCU usage:
- * The macvtap_queue is referenced both from the chardev struct file
- * and from the struct macvlan_dev using rcu_read_lock.
+ * The macvtap_queue and the macvlan_dev are loosely coupled, the
+ * pointers from one to the other can only be read while rcu_read_lock
+ * or macvtap_lock is held.
*
- * We never actually update the contents of a macvtap_queue atomically
- * with RCU but it is used for race-free destruction of a queue when
- * either the file or the macvlan_dev goes away. Pointers back to
- * the dev and the file are implicitly valid as long as the queue
- * exists.
+ * Both the file and the macvlan_dev hold a reference on the macvtap_queue
+ * through sock_hold(&q->sk). When the macvlan_dev goes away first,
+ * q->vlan becomes inaccessible. When the files gets closed,
+ * macvtap_get_queue() fails.
*
- * The callbacks from macvlan are always done with rcu_read_lock held
- * already, while in the file_operations, we get it ourselves.
- *
- * When destroying a queue, we remove the pointers from the file and
- * from the dev and then synchronize_rcu to make sure no thread is
- * still using the queue. There may still be references to the struct
- * sock inside of the queue from outbound SKBs, but these never
- * reference back to the file or the dev. The data structure is freed
- * through __sk_free when both our references and any pending SKBs
- * are gone.
- *
- * macvtap_lock is only used to prevent multiple concurrent open()
- * calls to assign a new vlan->tap pointer. It could be moved into
- * the macvlan_dev itself but is extremely rarely used.
+ * There may still be references to the struct sock inside of the
+ * queue from outbound SKBs, but these never reference back to the
+ * file or the dev. The data structure is freed through __sk_free
+ * when both our references and any pending SKBs are gone.
*/
static DEFINE_SPINLOCK(macvtap_lock);
@@ -100,11 +90,12 @@ static int macvtap_set_queue(struct net_device *dev, struct file *file,
goto out;
err = 0;
- q->vlan = vlan;
+ rcu_assign_pointer(q->vlan, vlan);
rcu_assign_pointer(vlan->tap, q);
+ sock_hold(&q->sk);
q->file = file;
- rcu_assign_pointer(file->private_data, q);
+ file->private_data = q;
out:
spin_unlock(&macvtap_lock);
@@ -112,28 +103,25 @@ out:
}
/*
- * We must destroy each queue exactly once, when either
- * the netdev or the file go away.
+ * The file owning the queue got closed, give up both
+ * the reference that the files holds as well as the
+ * one from the macvlan_dev if that still exists.
*
* Using the spinlock makes sure that we don't get
* to the queue again after destroying it.
- *
- * synchronize_rcu serializes with the packet flow
- * that uses rcu_read_lock.
*/
-static void macvtap_del_queue(struct macvtap_queue **qp)
+static void macvtap_put_queue(struct macvtap_queue *q)
{
- struct macvtap_queue *q;
+ struct macvlan_dev *vlan;
spin_lock(&macvtap_lock);
- q = rcu_dereference(*qp);
- if (!q) {
- spin_unlock(&macvtap_lock);
- return;
+ vlan = rcu_dereference(q->vlan);
+ if (vlan) {
+ rcu_assign_pointer(vlan->tap, NULL);
+ rcu_assign_pointer(q->vlan, NULL);
+ sock_put(&q->sk);
}
- rcu_assign_pointer(q->vlan->tap, NULL);
- rcu_assign_pointer(q->file->private_data, NULL);
spin_unlock(&macvtap_lock);
synchronize_rcu();
@@ -151,21 +139,29 @@ static struct macvtap_queue *macvtap_get_queue(struct net_device *dev,
return rcu_dereference(vlan->tap);
}
+/*
+ * The net_device is going away, give up the reference
+ * that it holds on the queue (all the queues one day)
+ * and safely set the pointer from the queues to NULL.
+ */
static void macvtap_del_queues(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
- macvtap_del_queue(&vlan->tap);
-}
+ struct macvtap_queue *q;
-static inline struct macvtap_queue *macvtap_file_get_queue(struct file *file)
-{
- rcu_read_lock_bh();
- return rcu_dereference(file->private_data);
-}
+ spin_lock(&macvtap_lock);
+ q = rcu_dereference(vlan->tap);
+ if (!q) {
+ spin_unlock(&macvtap_lock);
+ return;
+ }
-static inline void macvtap_file_put_queue(void)
-{
- rcu_read_unlock_bh();
+ rcu_assign_pointer(vlan->tap, NULL);
+ rcu_assign_pointer(q->vlan, NULL);
+ spin_unlock(&macvtap_lock);
+
+ synchronize_rcu();
+ sock_put(&q->sk);
}
/*
@@ -275,7 +271,6 @@ static int macvtap_open(struct inode *inode, struct file *file)
q->sock.type = SOCK_RAW;
q->sock.state = SS_CONNECTED;
sock_init_data(&q->sock, &q->sk);
- q->sk.sk_allocation = GFP_ATOMIC; /* for now */
q->sk.sk_write_space = macvtap_sock_write_space;
err = macvtap_set_queue(dev, file, q);
@@ -291,13 +286,14 @@ out:
static int macvtap_release(struct inode *inode, struct file *file)
{
- macvtap_del_queue((struct macvtap_queue **)&file->private_data);
+ struct macvtap_queue *q = file->private_data;
+ macvtap_put_queue(q);
return 0;
}
static unsigned int macvtap_poll(struct file *file, poll_table * wait)
{
- struct macvtap_queue *q = macvtap_file_get_queue(file);
+ struct macvtap_queue *q = file->private_data;
unsigned int mask = POLLERR;
if (!q)
@@ -315,7 +311,6 @@ static unsigned int macvtap_poll(struct file *file, poll_table * wait)
mask |= POLLOUT | POLLWRNORM;
out:
- macvtap_file_put_queue();
return mask;
}
@@ -325,6 +320,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q,
int noblock)
{
struct sk_buff *skb;
+ struct macvlan_dev *vlan;
size_t len = count;
int err;
@@ -332,26 +328,37 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q,
return -EINVAL;
skb = sock_alloc_send_skb(&q->sk, NET_IP_ALIGN + len, noblock, &err);
-
- if (!skb) {
- macvlan_count_rx(q->vlan, 0, false, false);
- return err;
- }
+ if (!skb)
+ goto err;
skb_reserve(skb, NET_IP_ALIGN);
skb_put(skb, count);
- if (skb_copy_datagram_from_iovec(skb, 0, iv, 0, len)) {
- macvlan_count_rx(q->vlan, 0, false, false);
- kfree_skb(skb);
- return -EFAULT;
- }
+ err = skb_copy_datagram_from_iovec(skb, 0, iv, 0, len);
+ if (err)
+ goto err;
skb_set_network_header(skb, ETH_HLEN);
-
- macvlan_start_xmit(skb, q->vlan->dev);
+ rcu_read_lock_bh();
+ vlan = rcu_dereference(q->vlan);
+ if (vlan)
+ macvlan_start_xmit(skb, vlan->dev);
+ else
+ kfree_skb(skb);
+ rcu_read_unlock_bh();
return count;
+
+err:
+ rcu_read_lock_bh();
+ vlan = rcu_dereference(q->vlan);
+ if (vlan)
+ macvlan_count_rx(q->vlan, 0, false, false);
+ rcu_read_unlock_bh();
+
+ kfree_skb(skb);
+
+ return err;
}
static ssize_t macvtap_aio_write(struct kiocb *iocb, const struct iovec *iv,
@@ -359,15 +366,10 @@ static ssize_t macvtap_aio_write(struct kiocb *iocb, const struct iovec *iv,
{
struct file *file = iocb->ki_filp;
ssize_t result = -ENOLINK;
- struct macvtap_queue *q = macvtap_file_get_queue(file);
-
- if (!q)
- goto out;
+ struct macvtap_queue *q = file->private_data;
result = macvtap_get_user(q, iv, iov_length(iv, count),
file->f_flags & O_NONBLOCK);
-out:
- macvtap_file_put_queue();
return result;
}
@@ -376,14 +378,17 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
const struct sk_buff *skb,
const struct iovec *iv, int len)
{
- struct macvlan_dev *vlan = q->vlan;
+ struct macvlan_dev *vlan;
int ret;
len = min_t(int, skb->len, len);
ret = skb_copy_datagram_const_iovec(skb, 0, iv, 0, len);
+ rcu_read_lock_bh();
+ vlan = rcu_dereference(q->vlan);
macvlan_count_rx(vlan, len, ret == 0, 0);
+ rcu_read_unlock_bh();
return ret ? ret : len;
}
@@ -392,7 +397,7 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
unsigned long count, loff_t pos)
{
struct file *file = iocb->ki_filp;
- struct macvtap_queue *q = macvtap_file_get_queue(file);
+ struct macvtap_queue *q = file->private_data;
DECLARE_WAITQUEUE(wait, current);
struct sk_buff *skb;
@@ -437,7 +442,6 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
remove_wait_queue(q->sk.sk_sleep, &wait);
out:
- macvtap_file_put_queue();
return ret;
}
@@ -447,12 +451,13 @@ out:
static long macvtap_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
- struct macvtap_queue *q;
+ struct macvtap_queue *q = file->private_data;
+ struct macvlan_dev *vlan;
void __user *argp = (void __user *)arg;
struct ifreq __user *ifr = argp;
unsigned int __user *up = argp;
unsigned int u;
- char devname[IFNAMSIZ];
+ int ret;
switch (cmd) {
case TUNSETIFF:
@@ -464,16 +469,21 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
return 0;
case TUNGETIFF:
- q = macvtap_file_get_queue(file);
- if (!q)
+ rcu_read_lock_bh();
+ vlan = rcu_dereference(q->vlan);
+ if (vlan)
+ dev_hold(vlan->dev);
+ rcu_read_unlock_bh();
+
+ if (!vlan)
return -ENOLINK;
- memcpy(devname, q->vlan->dev->name, sizeof(devname));
- macvtap_file_put_queue();
+ ret = 0;
if (copy_to_user(&ifr->ifr_name, q->vlan->dev->name, IFNAMSIZ) ||
put_user((TUN_TAP_DEV | TUN_NO_PI), &ifr->ifr_flags))
- return -EFAULT;
- return 0;
+ ret = -EFAULT;
+ dev_put(vlan->dev);
+ return ret;
case TUNGETFEATURES:
if (put_user((IFF_TAP | IFF_NO_PI), up))
@@ -484,9 +494,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
if (get_user(u, up))
return -EFAULT;
- q = macvtap_file_get_queue(file);
q->sk.sk_sndbuf = u;
- macvtap_file_put_queue();
return 0;
case TUNSETOFFLOAD:
--
1.6.3.3
^ permalink raw reply related
* PROPOSAL READ ATTACHMENT AND GET BACK TO ME
From: Mr. Johnson @ 2010-02-13 8:54 UTC (permalink / raw)
[-- Attachment #1: Type: text/plain, Size: 45 bytes --]
PROPOSAL READ ATTACHMENT AND GET BACK TO ME
[-- Attachment #2: MR. JOHNSON KHUNE.jpg --]
[-- Type: image/jpeg, Size: 233512 bytes --]
^ permalink raw reply
* Re: [PATCH net-next-2.6] macvtap: Add GSO/csum offload support
From: Sridhar Samudrala @ 2010-02-13 6:58 UTC (permalink / raw)
To: David Miller; +Cc: Arnd Bergmann, Herbert Xu, netdev
In-Reply-To: <1266013667.6105.18.camel@w-sridhar.beaverton.ibm.com>
Please ignore my original version of the patch. It has some trailing
whitespace errors. Here is an updated version that should apply cleanly.
This patch adds GSO/checksum offload support to macvtap driver and applies
on top of Arnd's refcnt bugfix.
http://patchwork.ozlabs.org/patch/45136/
Added flags field to macvtap_queue to enable/disable processing of
virtio_net_hdr via IFF_VNET_HDR. This flag is checked to prepend virtio_net_hdr
in the receive path and process/skip virtio_net_hdr in the send path.
Signed-off-by: Sridhar Samudrala <sri@us.ibm.com>
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index fe7656b..5f70f13 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -17,6 +17,7 @@
#include <net/net_namespace.h>
#include <net/rtnetlink.h>
#include <net/sock.h>
+#include <linux/virtio_net.h>
/*
* A macvtap queue is the central object of this driver, it connects
@@ -37,6 +38,7 @@ struct macvtap_queue {
struct socket sock;
struct macvlan_dev *vlan;
struct file *file;
+ unsigned int flags;
};
static struct proto macvtap_proto = {
@@ -286,6 +288,7 @@ static int macvtap_open(struct inode *inode, struct file *file)
sock_init_data(&q->sock, &q->sk);
q->sk.sk_allocation = GFP_ATOMIC; /* for now */
q->sk.sk_write_space = macvtap_sock_write_space;
+ q->flags = IFF_VNET_HDR;
err = macvtap_set_queue(dev, file, q);
if (err)
@@ -328,6 +331,29 @@ out:
return mask;
}
+static inline struct sk_buff *macvtap_alloc_skb(struct sock *sk, size_t prepad,
+ size_t len, size_t linear,
+ int noblock, int *err)
+{
+ struct sk_buff *skb;
+
+ /* Under a page? Don't bother with paged skb. */
+ if (prepad + len < PAGE_SIZE || !linear)
+ linear = len;
+
+ skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
+ err);
+ if (!skb)
+ return NULL;
+
+ skb_reserve(skb, prepad);
+ skb_put(skb, linear);
+ skb->data_len = len - linear;
+ skb->len += len - linear;
+
+ return skb;
+}
+
/* Get packet from user space buffer */
static ssize_t macvtap_get_user(struct macvtap_queue *q,
const struct iovec *iv, size_t count,
@@ -336,31 +362,99 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q,
struct sk_buff *skb;
size_t len = count;
int err;
+ struct virtio_net_hdr vnet_hdr = { 0 };
+ int vnet_hdr_len = 0;
+ unsigned short gso_type = 0;
+
+ if (q->flags & IFF_VNET_HDR) {
+ vnet_hdr_len = sizeof(vnet_hdr);
+
+ err = -EINVAL;
+ if ((len -= vnet_hdr_len) < 0)
+ goto out;
+
+ err = (memcpy_fromiovecend((void *)&vnet_hdr, iv, 0,
+ vnet_hdr_len));
+ if (err < 0)
+ goto out;
+
+ if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
+ vnet_hdr.csum_start + vnet_hdr.csum_offset + 2 >
+ vnet_hdr.hdr_len)
+ vnet_hdr.hdr_len = vnet_hdr.csum_start +
+ vnet_hdr.csum_offset + 2;
+
+ err = -EINVAL;
+ if (vnet_hdr.hdr_len > len)
+ goto out;
+
+ if (vnet_hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+ switch (vnet_hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+ case VIRTIO_NET_HDR_GSO_TCPV4:
+ gso_type = SKB_GSO_TCPV4;
+ break;
+ case VIRTIO_NET_HDR_GSO_TCPV6:
+ gso_type = SKB_GSO_TCPV6;
+ break;
+ case VIRTIO_NET_HDR_GSO_UDP:
+ gso_type = SKB_GSO_UDP;
+ break;
+ default:
+ goto out;
+ }
+
+ if (vnet_hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN)
+ gso_type |= SKB_GSO_TCP_ECN;
+
+ if (vnet_hdr.gso_size == 0)
+ goto out;
+ }
+ }
if (unlikely(len < ETH_HLEN))
- return -EINVAL;
+ goto out;
- skb = sock_alloc_send_skb(&q->sk, NET_IP_ALIGN + len, noblock, &err);
+ skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, len, vnet_hdr.hdr_len,
+ noblock, &err);
+ if (!skb)
+ goto out;
- if (!skb) {
- macvlan_count_rx(q->vlan, 0, false, false);
- return err;
- }
+ err = -EFAULT;
+ if (skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len, len))
+ goto out_free;
- skb_reserve(skb, NET_IP_ALIGN);
- skb_put(skb, count);
+ skb_set_network_header(skb, ETH_HLEN);
+ skb_reset_mac_header(skb);
+ skb->protocol = eth_hdr(skb)->h_proto;
+
+ if (vnet_hdr_len) {
+ if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
+ err = -EINVAL;
+ if (!skb_partial_csum_set(skb, vnet_hdr.csum_start,
+ vnet_hdr.csum_offset))
+ goto out_free;
+ }
- if (skb_copy_datagram_from_iovec(skb, 0, iv, 0, len)) {
- macvlan_count_rx(q->vlan, 0, false, false);
- kfree_skb(skb);
- return -EFAULT;
- }
+ if (vnet_hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+ skb_shinfo(skb)->gso_size = vnet_hdr.gso_size;
+ skb_shinfo(skb)->gso_type = gso_type;
- skb_set_network_header(skb, ETH_HLEN);
+ /* Header must be checked, and gso_segs computed. */
+ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
+ skb_shinfo(skb)->gso_segs = 0;
+ }
+ }
macvlan_start_xmit(skb, q->vlan->dev);
+ macvlan_count_rx(q->vlan, skb->len, 1, 0);
return count;
+
+out_free:
+ kfree_skb(skb);
+out:
+ macvlan_count_rx(q->vlan, 0, false, false);
+ return -EINVAL;
}
static ssize_t macvtap_aio_write(struct kiocb *iocb, const struct iovec *iv,
@@ -387,14 +481,54 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
{
struct macvlan_dev *vlan = q->vlan;
int ret;
+ int vnet_hdr_len = 0;
+
+ if (q->flags & IFF_VNET_HDR) {
+ struct virtio_net_hdr vnet_hdr = { 0 };
+
+ vnet_hdr_len = sizeof(vnet_hdr);
+ if ((len -= vnet_hdr_len) < 0)
+ return -EINVAL;
+
+ if (skb_is_gso(skb)) {
+ struct skb_shared_info *sinfo = skb_shinfo(skb);
+
+ /* This is a hint as to how much should be linear. */
+ vnet_hdr.hdr_len = skb_headlen(skb);
+ vnet_hdr.gso_size = sinfo->gso_size;
+ if (sinfo->gso_type & SKB_GSO_TCPV4)
+ vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
+ else if (sinfo->gso_type & SKB_GSO_TCPV6)
+ vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+ else if (sinfo->gso_type & SKB_GSO_UDP)
+ vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP;
+ else
+ BUG();
+ if (sinfo->gso_type & SKB_GSO_TCP_ECN)
+ vnet_hdr.gso_type |= VIRTIO_NET_HDR_GSO_ECN;
+ } else
+ vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE;
+
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ vnet_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
+ vnet_hdr.csum_start = skb->csum_start -
+ skb_headroom(skb);
+ vnet_hdr.csum_offset = skb->csum_offset;
+ } /* else everything is zero */
+
+ if (unlikely(memcpy_toiovecend(iv, (void *)&vnet_hdr, 0,
+ vnet_hdr_len)))
+ return -EFAULT;
+ }
+
len = min_t(int, skb->len, len);
- ret = skb_copy_datagram_const_iovec(skb, 0, iv, 0, len);
+ ret = skb_copy_datagram_const_iovec(skb, 0, iv, vnet_hdr_len, len);
macvlan_count_rx(vlan, len, ret == 0, 0);
- return ret ? ret : len;
+ return ret ? ret : (len + vnet_hdr_len);
}
static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
@@ -460,14 +594,23 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
unsigned int __user *up = argp;
unsigned int u;
char devname[IFNAMSIZ];
+ int ret;
switch (cmd) {
case TUNSETIFF:
/* ignore the name, just look at flags */
if (get_user(u, &ifr->ifr_flags))
return -EFAULT;
- if (u != (IFF_TAP | IFF_NO_PI))
- return -EINVAL;
+ q = macvtap_file_get_queue(file);
+ if (!q)
+ return -ENOLINK;
+
+ if (u & IFF_VNET_HDR)
+ q->flags |= IFF_VNET_HDR;
+ else
+ q->flags &= ~IFF_VNET_HDR;
+
+ macvtap_file_put_queue(q);
return 0;
case TUNGETIFF:
@@ -475,17 +618,23 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
if (!q)
return -ENOLINK;
memcpy(devname, q->vlan->dev->name, sizeof(devname));
- macvtap_file_put_queue(q);
+ ret = 0;
if (copy_to_user(&ifr->ifr_name, q->vlan->dev->name, IFNAMSIZ) ||
- put_user((TUN_TAP_DEV | TUN_NO_PI), &ifr->ifr_flags))
- return -EFAULT;
- return 0;
+ put_user(q->flags, &ifr->ifr_flags))
+ ret = -EFAULT;
+ macvtap_file_put_queue(q);
+ return ret;
case TUNGETFEATURES:
- if (put_user((IFF_TAP | IFF_NO_PI), up))
- return -EFAULT;
- return 0;
+ q = macvtap_file_get_queue(file);
+ if (!q)
+ return -ENOLINK;
+ ret = 0;
+ if (put_user(q->flags, up))
+ ret = -EFAULT;
+ macvtap_file_put_queue(q);
+ return ret;
case TUNSETSNDBUF:
if (get_user(u, up))
@@ -499,18 +648,14 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
return 0;
case TUNSETOFFLOAD:
- /* let the user check for future flags */
- if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
- TUN_F_TSO_ECN | TUN_F_UFO))
- return -EINVAL;
-
- /* TODO: add support for these, so far we don't
- support any offload */
- if (arg & (TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
- TUN_F_TSO_ECN | TUN_F_UFO))
- return -EINVAL;
-
- return 0;
+ q = macvtap_file_get_queue(file);
+ if (!q)
+ return -ENOLINK;
+ ret = 0;
+ if (!(q->flags & IFF_VNET_HDR))
+ ret = -EINVAL;
+ macvtap_file_put_queue(q);
+ return ret;
default:
return -EINVAL;
^ permalink raw reply related
* Re: [RFC PATCH net-next 0/7] Add netdev_printk and netif_printk macros
From: David Miller @ 2010-02-13 4:40 UTC (permalink / raw)
To: joe; +Cc: netdev, bhutchings
In-Reply-To: <1266034336.14805.84.camel@Joe-Laptop>
From: Joe Perches <joe@perches.com>
Date: Fri, 12 Feb 2010 20:12:16 -0800
> If you want to take the RFC patches, OK, but I could send
> a patchset that compiles all cases cleanly. Want that?
I've already fixed things up (by changing the arg in these macros to
"__dev") and pushed it out to net-next-2.6
^ permalink raw reply
* Re: [RFC PATCH net-next 0/7] Add netdev_printk and netif_printk macros
From: Joe Perches @ 2010-02-13 4:12 UTC (permalink / raw)
To: David Miller; +Cc: netdev, bhutchings
In-Reply-To: <20100212.131004.197405614.davem@davemloft.net>
On Fri, 2010-02-12 at 13:10 -0800, David Miller wrote:
> From: David Miller <davem@davemloft.net>
> Date: Fri, 12 Feb 2010 12:31:29 -0800 (PST)
> > All applied to net-next-2.6, thanks!
> Hmmm, some build problems:
>
> drivers/net/atl1e/atl1e_main.c: In function 'atl1e_vlan_rx_register':
> drivers/net/atl1e/atl1e_main.c:322: error: 'struct net_device' has no member named 'adapter'
> drivers/net/atl1e/atl1e_main.c:322: error: 'struct net_device' has no member named 'adapter'
> drivers/net/atl1e/atl1e_main.c: In function 'atl1e_restore_vlan':
> drivers/net/atl1e/atl1e_main.c:343: error: 'struct net_device' has no member named 'adapter'
> drivers/net/atl1e/atl1e_main.c:343: error: 'struct net_device' has no member named 'adapter'
> ...
>
> Passing in a derference like "adapter->netdev" as an argument doesn't work with these macros
> end up giving us things like:
>
> dev_driver_string((adapter->netdev)->adapter->netdev.parent)
> and
> dev_name((adapter->netdev)->adapter->netdev.parent)
>
> The issue seems to be the netdev_dbg() define when DEBUG is not set and
> CONFIG_DYNAMIC_DEBUG is set.
>
> It goes "(dev)->dev.parent" and CPP has fun with that.
>
> I'll use a different name for the first macro argument to netdev_dbg() and see
> if that's enough to fix this.
Hi David.
Been out a couple of days.
I sent it as an RFC not meaning them to be applied.
It's actually the dev_name((dev)->dev. expansion.
I've redone these patches using (netdev) as the argument
to dev_name.
If you want to take the RFC patches, OK, but I could send
a patchset that compiles all cases cleanly. Want that?
^ permalink raw reply
* Re: [net-next PATCH v3 3/3] net: TCP thin dupack
From: Eric W. Biederman @ 2010-02-13 2:13 UTC (permalink / raw)
To: Andreas Petlund
Cc: netdev@vger.kernel.org, Ilpo Järvinen, Eric Dumazet,
Arnd Hannemann, LKML, shemminger, David Miller,
william.allen.simpson, damian
In-Reply-To: <4B73F31F.9000204@simula.no>
Andreas Petlund <apetlund@simula.no> writes:
> Major changes:
> -Possible to disable mechanisms by socket option
> -Socket option value boundary check
>
>
> Signed-off-by: Andreas Petlund <apetlund@simula.no>
> ---
> include/linux/sysctl.h | 1 +
> include/linux/tcp.h | 4 +++-
> include/net/tcp.h | 1 +
> net/ipv4/sysctl_net_ipv4.c | 7 +++++++
> net/ipv4/tcp.c | 7 +++++++
> net/ipv4/tcp_input.c | 11 +++++++++++
> 6 files changed, 30 insertions(+), 1 deletions(-)
>
> diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
> index d840d75..ded3f20 100644
> --- a/include/linux/sysctl.h
> +++ b/include/linux/sysctl.h
> @@ -426,6 +426,7 @@ enum
> NET_TCP_MAX_SSTHRESH=124,
> NET_TCP_FRTO_RESPONSE=125,
> NET_TCP_FORCE_THIN_LINEAR_TIMEOUTS=126,
> + NET_TCP_FORCE_THIN_LINEAR_DUPACK=127,
There is no need to allocate a binary sysctl here.
Eric
^ permalink raw reply
* Re: [PATCH 0/9] tg3: Bugfixes
From: David Miller @ 2010-02-13 1:06 UTC (permalink / raw)
To: mcarlson; +Cc: netdev, andy
In-Reply-To: <1266022033-3546-1-git-send-email-mcarlson@broadcom.com>
From: "Matt Carlson" <mcarlson@broadcom.com>
Date: Fri, 12 Feb 2010 16:47:04 -0800
> This patchset implements some critical bugfixes for the tg3 driver.
All applied to net-next-2.6, thanks.
^ permalink raw reply
* Re: [net-next-2.6 PATCH v3 5/5] igb: support for VF configuration tools
From: David Miller @ 2010-02-13 0:57 UTC (permalink / raw)
To: jeffrey.t.kirsher; +Cc: netdev, gospo, mitch.a.williams
In-Reply-To: <20100210114422.14483.27089.stgit@localhost.localdomain>
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Wed, 10 Feb 2010 03:44:24 -0800
> From: Williams, Mitch A <mitch.a.williams@intel.com>
>
> Add support to the igb driver for VF configuration mechanisms through the
> PF interface.
>
> Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Applied to net-next-2.6
^ permalink raw reply
* Re: [net-next-2.6 PATCH v3 4/5] rtnetlink: Add VF config code to rtnetlink
From: David Miller @ 2010-02-13 0:56 UTC (permalink / raw)
To: jeffrey.t.kirsher; +Cc: netdev, gospo, mitch.a.williams
In-Reply-To: <20100210114403.14483.11004.stgit@localhost.localdomain>
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Wed, 10 Feb 2010 03:44:05 -0800
> From: Williams, Mitch A <mitch.a.williams@intel.com>
>
> Add code to allow rtnetlink clients to query and set VF information through
> the PF driver.
> Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Applied to net-next-2.6
^ permalink raw reply
* Re: [net-next-2.6 PATCH v3 3/5] net: Add netdev ops for SR-IOV configuration
From: David Miller @ 2010-02-13 0:56 UTC (permalink / raw)
To: jeffrey.t.kirsher; +Cc: netdev, gospo, mitch.a.williams
In-Reply-To: <20100210114344.14483.81331.stgit@localhost.localdomain>
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Wed, 10 Feb 2010 03:43:46 -0800
> From: Williams, Mitch A <mitch.a.williams@intel.com>
>
> Add netdev ops for configuring SR-IOV VF devices through the PF driver.
>
> Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Applied to net-next-2.6
^ permalink raw reply
* Re: [net-next-2.6 PATCH v3 2/5] if_link: Add SR-IOV configuration methods
From: David Miller @ 2010-02-13 0:56 UTC (permalink / raw)
To: jeffrey.t.kirsher; +Cc: netdev, gospo, mitch.a.williams
In-Reply-To: <20100210114322.14483.35528.stgit@localhost.localdomain>
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Wed, 10 Feb 2010 03:43:24 -0800
> From: Williams, Mitch A <mitch.a.williams@intel.com>
>
> Add SR-IOV VF management methods to IFLA_LINKINFO. This allows userspace to
> use rtnetlink to configure VF network devices.
>
> Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Applied to net-next-2.6
^ permalink raw reply
* Re: [net-next-2.6 PATCH v3 1/5] pci: Add SR-IOV convenience functions and macros
From: David Miller @ 2010-02-13 0:56 UTC (permalink / raw)
To: jeffrey.t.kirsher; +Cc: netdev, gospo, mitch.a.williams
In-Reply-To: <20100210114303.14483.71368.stgit@localhost.localdomain>
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Wed, 10 Feb 2010 03:43:04 -0800
> From: Williams, Mitch A <mitch.a.williams@intel.com>
>
> Add and export pci_num_vf to allow other subsystems to determine how many
> virtual function devices are associated with an SR-IOV physical function
> device.
> Add macros dev_is_pci, dev_is_ps, and dev_num_vf to make it easier for
> non-PCI specific code to determine SR-IOV capabilities.
>
> Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Applied to net-next-2.6
^ permalink raw reply
* Re: [PATCH 0/9] tg3: Bugfixes
From: Matt Carlson @ 2010-02-13 0:51 UTC (permalink / raw)
To: David Miller; +Cc: Matthew Carlson, netdev@vger.kernel.org, andy@greyhouse.net
In-Reply-To: <20100212.165033.23809145.davem@davemloft.net>
On Fri, Feb 12, 2010 at 04:50:33PM -0800, David Miller wrote:
> From: "Matt Carlson" <mcarlson@broadcom.com>
> Date: Fri, 12 Feb 2010 16:47:04 -0800
>
> > This patchset implements some critical bugfixes for the tg3 driver.
>
> These are way too late for net-2.6, these are going to have to go into
> net-next-2.6
That was my intent. I should have labelled it as such. Sorry.
^ permalink raw reply
* Re: net-2.6 [PATCH 0/2] udp/dccp: MSG_TRUNC
From: David Miller @ 2010-02-13 0:51 UTC (permalink / raw)
To: gerrit; +Cc: dccp, netdev
In-Reply-To: <1265869579-5829-1-git-send-email-gerrit@erg.abdn.ac.uk>
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Thu, 11 Feb 2010 07:26:17 +0100
> I have here two datagram-API patches, both submitted for net-2.6:
These are not appropriate for net-2.6, so I will apply them to
net-next-2.6
> Patch #1: Resolves missing MSG_TRUNC support. Since DCCP is datagram-based,
> the user-space API is broken/incomplete without.
>
> Patch #2: UDP recvmsg() cleanup, remove redundant variable.
Applied, thanks.
^ permalink raw reply
* Re: [PATCH 0/9] tg3: Bugfixes
From: David Miller @ 2010-02-13 0:50 UTC (permalink / raw)
To: mcarlson; +Cc: netdev, andy
In-Reply-To: <1266022033-3546-1-git-send-email-mcarlson@broadcom.com>
From: "Matt Carlson" <mcarlson@broadcom.com>
Date: Fri, 12 Feb 2010 16:47:04 -0800
> This patchset implements some critical bugfixes for the tg3 driver.
These are way too late for net-2.6, these are going to have to go into
net-next-2.6
^ permalink raw reply
* [PATCH 6/9] tg3: Reset phy during bringup when using phylib
From: Matt Carlson @ 2010-02-13 0:47 UTC (permalink / raw)
To: davem; +Cc: netdev, andy, mcarlson
The driver puts the phy into low-power mode when it releases the device.
If the device were to be reacquired, the phy needs a reset to bring it
back to full powered operation. This patch allows phylib-enabled
devices to reset the phy.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Reviewed-by: Benjamin Li <benli@broadcom.com>
---
drivers/net/tg3.c | 3 +--
1 files changed, 1 insertions(+), 2 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 1c545a8..9c4d88a 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -7595,8 +7595,7 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
tg3_abort_hw(tp, 1);
}
- if (reset_phy &&
- !(tp->tg3_flags3 & TG3_FLG3_USE_PHYLIB))
+ if (reset_phy)
tg3_phy_reset(tp);
err = tg3_chip_reset(tp);
--
1.6.4.4
^ permalink raw reply related
* [PATCH 7/9] tg3: Fix napi assignments in loopback test
From: Matt Carlson @ 2010-02-13 0:47 UTC (permalink / raw)
To: davem; +Cc: netdev, andy, mcarlson
The 57765 lacks TSS support. This renders the napi assignments
incorrect in the loopback test function. This patch fixes the problem.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Reviewed-by: Benjamin Li <benli@broadcom.com>
---
drivers/net/tg3.c | 8 ++++----
1 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 9c4d88a..74fa6d5 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -10780,12 +10780,12 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode)
struct tg3_napi *tnapi, *rnapi;
struct tg3_rx_prodring_set *tpr = &tp->prodring[0];
+ tnapi = &tp->napi[0];
+ rnapi = &tp->napi[0];
if (tp->irq_cnt > 1) {
- tnapi = &tp->napi[1];
rnapi = &tp->napi[1];
- } else {
- tnapi = &tp->napi[0];
- rnapi = &tp->napi[0];
+ if (tp->tg3_flags3 & TG3_FLG3_ENABLE_TSS)
+ tnapi = &tp->napi[1];
}
coal_now = tnapi->coal_now | rnapi->coal_now;
--
1.6.4.4
^ permalink raw reply related
* [PATCH 4/9] tg3: Fix 57765 A0 bootcode race condition
From: Matt Carlson @ 2010-02-13 0:47 UTC (permalink / raw)
To: davem; +Cc: netdev, andy, mcarlson, Benjamin Li
On A0 revision of 57765 asic rev devices, the bootcode will perform some
hardware operations, after the magic signature is presented, that will
collide with setup operations performed by the driver. The best way to
avoid the contention is to have the driver delay an additional 10
milliseconds. B0 revisions of the chip will make this workaround
unnecessary.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Benjamin Li <benli@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/tg3.c | 7 +++++++
drivers/net/tg3.h | 1 +
2 files changed, 8 insertions(+), 0 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index e6ee291..d1452d3 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -6721,6 +6721,13 @@ static int tg3_poll_fw(struct tg3 *tp)
tp->dev->name);
}
+ if (tp->pci_chip_rev_id == CHIPREV_ID_57765_A0) {
+ /* The 57765 A0 needs a little more
+ * time to do some important work.
+ */
+ mdelay(10);
+ }
+
return 0;
}
diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h
index cc8bf7d..46db4ad 100644
--- a/drivers/net/tg3.h
+++ b/drivers/net/tg3.h
@@ -110,6 +110,7 @@
#define CHIPREV_ID_57780_A0 0x57780000
#define CHIPREV_ID_57780_A1 0x57780001
#define CHIPREV_ID_5717_A0 0x05717000
+#define CHIPREV_ID_57765_A0 0x57785000
#define GET_ASIC_REV(CHIP_REV_ID) ((CHIP_REV_ID) >> 12)
#define ASIC_REV_5700 0x07
#define ASIC_REV_5701 0x00
--
1.6.4.4
^ permalink raw reply related
* [PATCH 1/9] tg3: Give MSI-X vec 1 rx backlog space
From: Matt Carlson @ 2010-02-13 0:47 UTC (permalink / raw)
To: davem; +Cc: netdev, andy, mcarlson, Michael Chan
RSS ring 1 is responsible for submitting new rx buffers to the
hardware on behalf of all the other RSS rx return rings. Up until now
this ring submitted its new rx buffers to the producer ring directly.
The following patch will require that this ring have a place to put
backlogged rx packets. As a consequence, it can no longer submit new
buffers to the producer ring.
This patch adds code to allocate an extra shadow producer ring for this
RSS ring and adds RSS ring 1 to the list of rings needing buffer
transfers.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Reviewed-by: Benjamin Li <benli@broadcom.com>
---
drivers/net/tg3.c | 46 +++++++++++++++++++++-------------------------
drivers/net/tg3.h | 2 +-
2 files changed, 22 insertions(+), 26 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 7195bde..6874ce5 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -4733,7 +4733,7 @@ next_pkt_nopost:
tw32_rx_mbox(tnapi->consmbox, sw_idx);
/* Refill RX ring(s). */
- if (!(tp->tg3_flags3 & TG3_FLG3_ENABLE_RSS) || tnapi == &tp->napi[1]) {
+ if (!(tp->tg3_flags3 & TG3_FLG3_ENABLE_RSS)) {
if (work_mask & RXD_OPAQUE_RING_STD) {
tpr->rx_std_prod_idx = std_prod_idx % TG3_RX_RING_SIZE;
tw32_rx_mbox(TG3_RX_STD_PROD_IDX_REG,
@@ -4755,7 +4755,8 @@ next_pkt_nopost:
tpr->rx_std_prod_idx = std_prod_idx % TG3_RX_RING_SIZE;
tpr->rx_jmb_prod_idx = jmb_prod_idx % TG3_RX_JUMBO_RING_SIZE;
- napi_schedule(&tp->napi[1].napi);
+ if (tnapi != &tp->napi[1])
+ napi_schedule(&tp->napi[1].napi);
}
return received;
@@ -4893,25 +4894,23 @@ static int tg3_poll_work(struct tg3_napi *tnapi, int work_done, int budget)
work_done += tg3_rx(tnapi, budget - work_done);
if ((tp->tg3_flags3 & TG3_FLG3_ENABLE_RSS) && tnapi == &tp->napi[1]) {
+ struct tg3_rx_prodring_set *dpr = &tp->prodring[0];
int i;
- u32 std_prod_idx = tp->prodring[0].rx_std_prod_idx;
- u32 jmb_prod_idx = tp->prodring[0].rx_jmb_prod_idx;
+ u32 std_prod_idx = dpr->rx_std_prod_idx;
+ u32 jmb_prod_idx = dpr->rx_jmb_prod_idx;
- for (i = 2; i < tp->irq_cnt; i++)
- tg3_rx_prodring_xfer(tp, tnapi->prodring,
- tp->napi[i].prodring);
+ for (i = 1; i < tp->irq_cnt; i++)
+ tg3_rx_prodring_xfer(tp, dpr, tp->napi[i].prodring);
wmb();
- if (std_prod_idx != tp->prodring[0].rx_std_prod_idx) {
- u32 mbox = TG3_RX_STD_PROD_IDX_REG;
- tw32_rx_mbox(mbox, tp->prodring[0].rx_std_prod_idx);
- }
+ if (std_prod_idx != dpr->rx_std_prod_idx)
+ tw32_rx_mbox(TG3_RX_STD_PROD_IDX_REG,
+ dpr->rx_std_prod_idx);
- if (jmb_prod_idx != tp->prodring[0].rx_jmb_prod_idx) {
- u32 mbox = TG3_RX_JMB_PROD_IDX_REG;
- tw32_rx_mbox(mbox, tp->prodring[0].rx_jmb_prod_idx);
- }
+ if (jmb_prod_idx != dpr->rx_jmb_prod_idx)
+ tw32_rx_mbox(TG3_RX_JMB_PROD_IDX_REG,
+ dpr->rx_jmb_prod_idx);
mmiowb();
}
@@ -6173,8 +6172,7 @@ static void tg3_free_rings(struct tg3 *tp)
dev_kfree_skb_any(skb);
}
- if (tp->irq_cnt == 1 || j != tp->irq_cnt - 1)
- tg3_rx_prodring_free(tp, &tp->prodring[j]);
+ tg3_rx_prodring_free(tp, &tp->prodring[j]);
}
}
@@ -6210,9 +6208,10 @@ static int tg3_init_rings(struct tg3 *tp)
if (tnapi->rx_rcb)
memset(tnapi->rx_rcb, 0, TG3_RX_RCB_RING_BYTES(tp));
- if ((tp->irq_cnt == 1 || i != tp->irq_cnt - 1) &&
- tg3_rx_prodring_alloc(tp, &tp->prodring[i]))
+ if (tg3_rx_prodring_alloc(tp, &tp->prodring[i])) {
+ tg3_free_rings(tp);
return -ENOMEM;
+ }
}
return 0;
@@ -6259,7 +6258,7 @@ static void tg3_free_consistent(struct tg3 *tp)
tp->hw_stats = NULL;
}
- for (i = 0; i < (tp->irq_cnt == 1 ? 1 : tp->irq_cnt - 1); i++)
+ for (i = 0; i < tp->irq_cnt; i++)
tg3_rx_prodring_fini(tp, &tp->prodring[i]);
}
@@ -6271,7 +6270,7 @@ static int tg3_alloc_consistent(struct tg3 *tp)
{
int i;
- for (i = 0; i < (tp->irq_cnt == 1 ? 1 : tp->irq_cnt - 1); i++) {
+ for (i = 0; i < tp->irq_cnt; i++) {
if (tg3_rx_prodring_init(tp, &tp->prodring[i]))
goto err_out;
}
@@ -6336,10 +6335,7 @@ static int tg3_alloc_consistent(struct tg3 *tp)
break;
}
- if (tp->irq_cnt == 1)
- tnapi->prodring = &tp->prodring[0];
- else if (i)
- tnapi->prodring = &tp->prodring[i - 1];
+ tnapi->prodring = &tp->prodring[i];
/*
* If multivector RSS is enabled, vector 0 does not handle
diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h
index e7f6214..88a87bb 100644
--- a/drivers/net/tg3.h
+++ b/drivers/net/tg3.h
@@ -2717,7 +2717,7 @@ struct tg3 {
struct vlan_group *vlgrp;
#endif
- struct tg3_rx_prodring_set prodring[TG3_IRQ_MAX_VECS - 1];
+ struct tg3_rx_prodring_set prodring[TG3_IRQ_MAX_VECS];
/* begin "everything else" cacheline(s) section */
--
1.6.4.4
^ permalink raw reply related
* [PATCH 3/9] tg3: Unwedge stuck MSI-X vectors
From: Matt Carlson @ 2010-02-13 0:47 UTC (permalink / raw)
To: davem; +Cc: netdev, andy, mcarlson
The previous patch changed the code so that new rx buffer submissions to
the hardware stall if a new submission would overwrite data needed by an
unserviced rx packet. On very busy 5717 and 57765 asic rev devices,
there is a corner case where the hardware will fail to assert an MSI-X
interrupt for rx traffic. If that vector's interrupt never has another
reason to assert, any rx buffers held will never be serviced. If the
buffers are never serviced and the hardware consumes all the available
rx packets for other rx rings, deadlock will result.
The most reliable and least intrusive way to work around the problem is
to detect the case where new submissions would overwrite existing data
and force all rx interrupt vectors to fire.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Reviewed-by: Benjamin Li <benli@broadcom.com>
---
drivers/net/tg3.c | 29 +++++++++++++++++++----------
drivers/net/tg3.h | 1 +
2 files changed, 20 insertions(+), 10 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 115fb7c..e6ee291 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -642,7 +642,6 @@ static void tg3_disable_ints(struct tg3 *tp)
static void tg3_enable_ints(struct tg3 *tp)
{
int i;
- u32 coal_now = 0;
tp->irq_sync = 0;
wmb();
@@ -650,13 +649,14 @@ static void tg3_enable_ints(struct tg3 *tp)
tw32(TG3PCI_MISC_HOST_CTRL,
(tp->misc_host_ctrl & ~MISC_HOST_CTRL_MASK_PCI_INT));
+ tp->coal_now = tp->coalesce_mode | HOSTCC_MODE_ENABLE;
for (i = 0; i < tp->irq_cnt; i++) {
struct tg3_napi *tnapi = &tp->napi[i];
tw32_mailbox_f(tnapi->int_mbox, tnapi->last_tag << 24);
if (tp->tg3_flags2 & TG3_FLG2_1SHOT_MSI)
tw32_mailbox_f(tnapi->int_mbox, tnapi->last_tag << 24);
- coal_now |= tnapi->coal_now;
+ tp->coal_now |= tnapi->coal_now;
}
/* Force an initial interrupt */
@@ -664,8 +664,9 @@ static void tg3_enable_ints(struct tg3 *tp)
(tp->napi[0].hw_status->status & SD_STATUS_UPDATED))
tw32(GRC_LOCAL_CTRL, tp->grc_local_ctrl | GRC_LCLCTRL_SETINT);
else
- tw32(HOSTCC_MODE, tp->coalesce_mode |
- HOSTCC_MODE_ENABLE | coal_now);
+ tw32(HOSTCC_MODE, tp->coal_now);
+
+ tp->coal_now &= ~(tp->napi[0].coal_now | tp->napi[1].coal_now);
}
static inline unsigned int tg3_has_work(struct tg3_napi *tnapi)
@@ -4794,12 +4795,12 @@ static void tg3_poll_link(struct tg3 *tp)
}
}
-static void tg3_rx_prodring_xfer(struct tg3 *tp,
- struct tg3_rx_prodring_set *dpr,
- struct tg3_rx_prodring_set *spr)
+static int tg3_rx_prodring_xfer(struct tg3 *tp,
+ struct tg3_rx_prodring_set *dpr,
+ struct tg3_rx_prodring_set *spr)
{
u32 si, di, cpycnt, src_prod_idx;
- int i;
+ int i, err = 0;
while (1) {
src_prod_idx = spr->rx_std_prod_idx;
@@ -4825,6 +4826,7 @@ static void tg3_rx_prodring_xfer(struct tg3 *tp,
for (i = di; i < di + cpycnt; i++) {
if (dpr->rx_std_buffers[i].skb) {
cpycnt = i - di;
+ err = -ENOSPC;
break;
}
}
@@ -4881,6 +4883,7 @@ static void tg3_rx_prodring_xfer(struct tg3 *tp,
for (i = di; i < di + cpycnt; i++) {
if (dpr->rx_jmb_buffers[i].skb) {
cpycnt = i - di;
+ err = -ENOSPC;
break;
}
}
@@ -4911,6 +4914,8 @@ static void tg3_rx_prodring_xfer(struct tg3 *tp,
dpr->rx_jmb_prod_idx = (dpr->rx_jmb_prod_idx + cpycnt) %
TG3_RX_JUMBO_RING_SIZE;
}
+
+ return err;
}
static int tg3_poll_work(struct tg3_napi *tnapi, int work_done, int budget)
@@ -4933,12 +4938,13 @@ static int tg3_poll_work(struct tg3_napi *tnapi, int work_done, int budget)
if ((tp->tg3_flags3 & TG3_FLG3_ENABLE_RSS) && tnapi == &tp->napi[1]) {
struct tg3_rx_prodring_set *dpr = &tp->prodring[0];
- int i;
+ int i, err = 0;
u32 std_prod_idx = dpr->rx_std_prod_idx;
u32 jmb_prod_idx = dpr->rx_jmb_prod_idx;
for (i = 1; i < tp->irq_cnt; i++)
- tg3_rx_prodring_xfer(tp, dpr, tp->napi[i].prodring);
+ err |= tg3_rx_prodring_xfer(tp, dpr,
+ tp->napi[i].prodring);
wmb();
@@ -4951,6 +4957,9 @@ static int tg3_poll_work(struct tg3_napi *tnapi, int work_done, int budget)
dpr->rx_jmb_prod_idx);
mmiowb();
+
+ if (err)
+ tw32_f(HOSTCC_MODE, tp->coal_now);
}
return work_done;
diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h
index 88a87bb..cc8bf7d 100644
--- a/drivers/net/tg3.h
+++ b/drivers/net/tg3.h
@@ -2699,6 +2699,7 @@ struct tg3 {
struct net_device *dev;
struct pci_dev *pdev;
+ u32 coal_now;
u32 msg_enable;
/* begin "tx thread" cacheline section */
--
1.6.4.4
^ permalink raw reply related
* [PATCH 2/9] tg3: Prevent rx producer ring overruns
From: Matt Carlson @ 2010-02-13 0:47 UTC (permalink / raw)
To: davem; +Cc: netdev, andy, mcarlson, Michael Chan
When operating in RSS mode, it is possible for one rx return ring to
submit enough rx buffers back to the hardware such that it inadvertently
overwrites data needed by another rx return ring. This patch addresses
the problem by looking for non-NULL skb pointers in the
rx_[std|jmb]_buffers rings that parallel the rx producer rings.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Reviewed-by: Benjamin Li <benli@broadcom.com>
---
drivers/net/tg3.c | 38 ++++++++++++++++++++++++++++++++++++++
1 files changed, 38 insertions(+), 0 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 6874ce5..115fb7c 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -4552,6 +4552,12 @@ static void tg3_recycle_rx(struct tg3_napi *tnapi,
pci_unmap_addr(src_map, mapping));
dest_desc->addr_hi = src_desc->addr_hi;
dest_desc->addr_lo = src_desc->addr_lo;
+
+ /* Ensure that the update to the skb happens after the physical
+ * addresses have been transferred to the new BD location.
+ */
+ smp_wmb();
+
src_map->skb = NULL;
}
@@ -4816,6 +4822,22 @@ static void tg3_rx_prodring_xfer(struct tg3 *tp,
si = spr->rx_std_cons_idx;
di = dpr->rx_std_prod_idx;
+ for (i = di; i < di + cpycnt; i++) {
+ if (dpr->rx_std_buffers[i].skb) {
+ cpycnt = i - di;
+ break;
+ }
+ }
+
+ if (!cpycnt)
+ break;
+
+ /* Ensure that updates to the rx_std_buffers ring and the
+ * shadowed hardware producer ring from tg3_recycle_skb() are
+ * ordered correctly WRT the skb check above.
+ */
+ smp_rmb();
+
memcpy(&dpr->rx_std_buffers[di],
&spr->rx_std_buffers[si],
cpycnt * sizeof(struct ring_info));
@@ -4856,6 +4878,22 @@ static void tg3_rx_prodring_xfer(struct tg3 *tp,
si = spr->rx_jmb_cons_idx;
di = dpr->rx_jmb_prod_idx;
+ for (i = di; i < di + cpycnt; i++) {
+ if (dpr->rx_jmb_buffers[i].skb) {
+ cpycnt = i - di;
+ break;
+ }
+ }
+
+ if (!cpycnt)
+ break;
+
+ /* Ensure that updates to the rx_jmb_buffers ring and the
+ * shadowed hardware producer ring from tg3_recycle_skb() are
+ * ordered correctly WRT the skb check above.
+ */
+ smp_rmb();
+
memcpy(&dpr->rx_jmb_buffers[di],
&spr->rx_jmb_buffers[si],
cpycnt * sizeof(struct ring_info));
--
1.6.4.4
^ permalink raw reply related
* [PATCH 0/9] tg3: Bugfixes
From: Matt Carlson @ 2010-02-13 0:47 UTC (permalink / raw)
To: davem; +Cc: netdev, andy, mcarlson
This patchset implements some critical bugfixes for the tg3 driver.
^ permalink raw reply
* [PATCH 8/9] tg3: Fix AC131 loopback test errors for 5785
From: Matt Carlson @ 2010-02-13 0:47 UTC (permalink / raw)
To: davem; +Cc: netdev, andy, mcarlson
The AC131 does not enable the forced transmit clock settings
immediately. The workaround is to read the register again to get the
setting to take effect.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Reviewed-by: Benjamin Li <benli@broadcom.com>
---
drivers/net/tg3.c | 8 ++++++--
drivers/net/tg3.h | 3 +++
2 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 74fa6d5..5b03231 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -10822,8 +10822,12 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode)
mac_mode = tp->mac_mode & ~MAC_MODE_PORT_MODE_MASK;
if (tp->tg3_flags3 & TG3_FLG3_PHY_IS_FET) {
- if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906)
- tg3_writephy(tp, MII_TG3_FET_PTEST, 0x1800);
+ tg3_writephy(tp, MII_TG3_FET_PTEST,
+ MII_TG3_FET_PTEST_FRC_TX_LINK |
+ MII_TG3_FET_PTEST_FRC_TX_LOCK);
+ /* The write needs to be flushed for the AC131 */
+ if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5785)
+ tg3_readphy(tp, MII_TG3_FET_PTEST, &val);
mac_mode |= MAC_MODE_PORT_MODE_MII;
} else
mac_mode |= MAC_MODE_PORT_MODE_GMII;
diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h
index a8fb53a..b4fd596 100644
--- a/drivers/net/tg3.h
+++ b/drivers/net/tg3.h
@@ -2112,6 +2112,9 @@
/* Fast Ethernet Tranceiver definitions */
#define MII_TG3_FET_PTEST 0x17
+#define MII_TG3_FET_PTEST_FRC_TX_LINK 0x1000
+#define MII_TG3_FET_PTEST_FRC_TX_LOCK 0x0800
+
#define MII_TG3_FET_TEST 0x1f
#define MII_TG3_FET_SHADOW_EN 0x0080
--
1.6.4.4
^ permalink raw reply related
* [PATCH 9/9] tg3: Update driver version to 3.107
From: Matt Carlson @ 2010-02-13 0:47 UTC (permalink / raw)
To: davem; +Cc: netdev, andy, mcarlson
This patch updates the tg3 version to 3.107.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
---
drivers/net/tg3.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 5b03231..34b0d3c 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -68,8 +68,8 @@
#define DRV_MODULE_NAME "tg3"
#define PFX DRV_MODULE_NAME ": "
-#define DRV_MODULE_VERSION "3.106"
-#define DRV_MODULE_RELDATE "January 12, 2010"
+#define DRV_MODULE_VERSION "3.107"
+#define DRV_MODULE_RELDATE "February 12, 2010"
#define TG3_DEF_MAC_MODE 0
#define TG3_DEF_RX_MODE 0
--
1.6.4.4
^ 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