* [RFC][PATCH v6 15/19] Add basic funcs and ioctl to mp device.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-15-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
The ioctl is used by mp device to bind an underlying
NIC, it will query hardware capability and declare the
NIC to use external buffers.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
memory leak fixed,
kconfig made,
do_unbind() made,
mp_chr_ioctl() cleanup
by Jeff Dike <jdike@linux.intel.com>
drivers/vhost/mpassthru.c | 681 +++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 681 insertions(+), 0 deletions(-)
create mode 100644 drivers/vhost/mpassthru.c
diff --git a/drivers/vhost/mpassthru.c b/drivers/vhost/mpassthru.c
new file mode 100644
index 0000000..25e2f3e
--- /dev/null
+++ b/drivers/vhost/mpassthru.c
@@ -0,0 +1,681 @@
+/*
+ * MPASSTHRU - Mediate passthrough device.
+ * Copyright (C) 2009 ZhaoYu, XinXiaohui, Dike, Jeffery G
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define DRV_NAME "mpassthru"
+#define DRV_DESCRIPTION "Mediate passthru device driver"
+#define DRV_COPYRIGHT "(C) 2009 ZhaoYu, XinXiaohui, Dike, Jeffery G"
+
+#include <linux/compat.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/major.h>
+#include <linux/slab.h>
+#include <linux/smp_lock.h>
+#include <linux/poll.h>
+#include <linux/fcntl.h>
+#include <linux/init.h>
+#include <linux/aio.h>
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/miscdevice.h>
+#include <linux/ethtool.h>
+#include <linux/rtnetlink.h>
+#include <linux/if.h>
+#include <linux/if_arp.h>
+#include <linux/if_ether.h>
+#include <linux/crc32.h>
+#include <linux/nsproxy.h>
+#include <linux/uaccess.h>
+#include <linux/virtio_net.h>
+#include <linux/mpassthru.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/rtnetlink.h>
+#include <net/sock.h>
+
+#include <asm/system.h>
+
+/* Uncomment to enable debugging */
+/* #define MPASSTHRU_DEBUG 1 */
+
+#ifdef MPASSTHRU_DEBUG
+static int debug;
+
+#define DBG if (mp->debug) printk
+#define DBG1 if (debug == 2) printk
+#else
+#define DBG(a...)
+#define DBG1(a...)
+#endif
+
+#define COPY_THRESHOLD (L1_CACHE_BYTES * 4)
+#define COPY_HDR_LEN (L1_CACHE_BYTES < 64 ? 64 : L1_CACHE_BYTES)
+
+struct frag {
+ u16 offset;
+ u16 size;
+};
+
+struct page_info {
+ struct list_head list;
+ int header;
+ /* indicate the actual length of bytes
+ * send/recv in the external buffers
+ */
+ int total;
+ int offset;
+ struct page *pages[MAX_SKB_FRAGS+1];
+ struct skb_frag_struct frag[MAX_SKB_FRAGS+1];
+ struct sk_buff *skb;
+ struct page_ctor *ctor;
+
+ /* The pointer relayed to skb, to indicate
+ * it's a external allocated skb or kernel
+ */
+ struct skb_external_page ext_page;
+ struct skb_shared_info ushinfo;
+
+#define INFO_READ 0
+#define INFO_WRITE 1
+ unsigned flags;
+ unsigned pnum;
+
+ /* It's meaningful for receive, means
+ * the max length allowed
+ */
+ size_t len;
+
+ /* The fields after that is for backend
+ * driver, now for vhost-net.
+ */
+
+ struct kiocb *iocb;
+ unsigned int desc_pos;
+ struct iovec hdr[MAX_SKB_FRAGS + 2];
+ struct iovec iov[MAX_SKB_FRAGS + 2];
+};
+
+static struct kmem_cache *ext_page_info_cache;
+
+struct page_ctor {
+ struct list_head readq;
+ int wq_len;
+ int rq_len;
+ spinlock_t read_lock;
+ /* record the locked pages */
+ int lock_pages;
+ struct rlimit o_rlim;
+ struct net_device *dev;
+ struct mpassthru_port port;
+};
+
+struct mp_struct {
+ struct mp_file *mfile;
+ struct net_device *dev;
+ struct page_ctor *ctor;
+ struct socket socket;
+
+#ifdef MPASSTHRU_DEBUG
+ int debug;
+#endif
+};
+
+struct mp_file {
+ atomic_t count;
+ struct mp_struct *mp;
+ struct net *net;
+};
+
+struct mp_sock {
+ struct sock sk;
+ struct mp_struct *mp;
+};
+
+static int mp_dev_change_flags(struct net_device *dev, unsigned flags)
+{
+ int ret = 0;
+
+ rtnl_lock();
+ ret = dev_change_flags(dev, flags);
+ rtnl_unlock();
+
+ if (ret < 0)
+ printk(KERN_ERR "failed to change dev state of %s", dev->name);
+
+ return ret;
+}
+
+static int page_ctor_attach(struct mp_struct *mp)
+{
+ int rc;
+ struct page_ctor *ctor;
+ struct net_device *dev = mp->dev;
+
+ /* locked by mp_mutex */
+ if (rcu_dereference(mp->ctor))
+ return -EBUSY;
+
+ ctor = kzalloc(sizeof(*ctor), GFP_KERNEL);
+ if (!ctor)
+ return -ENOMEM;
+ rc = netdev_mp_port_prep(dev, &ctor->port);
+ if (rc)
+ goto fail;
+
+ INIT_LIST_HEAD(&ctor->readq);
+ spin_lock_init(&ctor->read_lock);
+
+ ctor->rq_len = 0;
+ ctor->wq_len = 0;
+
+ dev_hold(dev);
+ ctor->dev = dev;
+ ctor->port.ctor = NULL;
+ ctor->port.sock = &mp->socket;
+ ctor->lock_pages = 0;
+ rc = netdev_mp_port_attach(dev, &ctor->port);
+ if (rc)
+ goto fail;
+
+ /* locked by mp_mutex */
+ rcu_assign_pointer(mp->ctor, ctor);
+
+ /* XXX:Need we do set_offload here ? */
+
+ return 0;
+
+fail:
+ kfree(ctor);
+ dev_put(dev);
+
+ return rc;
+}
+
+struct page_info *info_dequeue(struct page_ctor *ctor)
+{
+ unsigned long flags;
+ struct page_info *info = NULL;
+ spin_lock_irqsave(&ctor->read_lock, flags);
+ if (!list_empty(&ctor->readq)) {
+ info = list_first_entry(&ctor->readq,
+ struct page_info, list);
+ list_del(&info->list);
+ }
+ spin_unlock_irqrestore(&ctor->read_lock, flags);
+ return info;
+}
+
+static int set_memlock_rlimit(struct page_ctor *ctor, int resource,
+ unsigned long cur, unsigned long max)
+{
+ struct rlimit new_rlim, *old_rlim;
+ int retval;
+
+ if (resource != RLIMIT_MEMLOCK)
+ return -EINVAL;
+ new_rlim.rlim_cur = cur;
+ new_rlim.rlim_max = max;
+
+ old_rlim = current->signal->rlim + resource;
+
+ /* remember the old rlimit value when backend enabled */
+ ctor->o_rlim.rlim_cur = old_rlim->rlim_cur;
+ ctor->o_rlim.rlim_max = old_rlim->rlim_max;
+
+ if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
+ !capable(CAP_SYS_RESOURCE))
+ return -EPERM;
+
+ retval = security_task_setrlimit(resource, &new_rlim);
+ if (retval)
+ return retval;
+
+ task_lock(current->group_leader);
+ *old_rlim = new_rlim;
+ task_unlock(current->group_leader);
+ return 0;
+}
+
+static int page_ctor_detach(struct mp_struct *mp)
+{
+ struct page_ctor *ctor;
+ struct page_info *info;
+ struct kiocb *iocb = NULL;
+ int i;
+
+ /* locked by mp_mutex */
+ ctor = rcu_dereference(mp->ctor);
+ if (!ctor)
+ return -ENODEV;
+
+ while ((info = info_dequeue(ctor))) {
+ for (i = 0; i < info->pnum; i++)
+ if (info->pages[i])
+ put_page(info->pages[i]);
+ kmem_cache_free(ext_page_info_cache, info);
+ }
+ set_memlock_rlimit(ctor, RLIMIT_MEMLOCK,
+ ctor->o_rlim.rlim_cur,
+ ctor->o_rlim.rlim_max);
+ netdev_mp_port_detach(ctor->dev);
+ dev_put(ctor->dev);
+
+ /* locked by mp_mutex */
+ rcu_assign_pointer(mp->ctor, NULL);
+ synchronize_rcu();
+
+ kfree(ctor);
+ return 0;
+}
+
+static void __mp_detach(struct mp_struct *mp)
+{
+ mp->mfile = NULL;
+
+ mp_dev_change_flags(mp->dev, mp->dev->flags & ~IFF_UP);
+ page_ctor_detach(mp);
+ mp_dev_change_flags(mp->dev, mp->dev->flags | IFF_UP);
+
+ /* Drop the extra count on the net device */
+ dev_put(mp->dev);
+}
+
+static DEFINE_MUTEX(mp_mutex);
+
+static void mp_detach(struct mp_struct *mp)
+{
+ mutex_lock(&mp_mutex);
+ __mp_detach(mp);
+ mutex_unlock(&mp_mutex);
+}
+
+static struct mp_struct *mp_get(struct mp_file *mfile)
+{
+ struct mp_struct *mp = NULL;
+ if (atomic_inc_not_zero(&mfile->count))
+ mp = mfile->mp;
+
+ return mp;
+}
+
+static void mp_put(struct mp_file *mfile)
+{
+ if (atomic_dec_and_test(&mfile->count))
+ mp_detach(mfile->mp);
+}
+
+/* Ops structure to mimic raw sockets with mp device */
+static const struct proto_ops mp_socket_ops = {
+};
+
+static struct proto mp_proto = {
+ .name = "mp",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct mp_sock),
+};
+
+static int mp_chr_open(struct inode *inode, struct file * file)
+{
+ struct mp_file *mfile;
+ cycle_kernel_lock();
+ DBG1(KERN_INFO "mp: mp_chr_open\n");
+
+ mfile = kzalloc(sizeof(*mfile), GFP_KERNEL);
+ if (!mfile)
+ return -ENOMEM;
+ atomic_set(&mfile->count, 0);
+ mfile->mp = NULL;
+ mfile->net = get_net(current->nsproxy->net_ns);
+ file->private_data = mfile;
+ return 0;
+}
+
+static int mp_attach(struct mp_struct *mp, struct file *file)
+{
+ struct mp_file *mfile = file->private_data;
+ int err;
+
+ netif_tx_lock_bh(mp->dev);
+
+ err = -EINVAL;
+
+ if (mfile->mp)
+ goto out;
+
+ err = -EBUSY;
+ if (mp->mfile)
+ goto out;
+
+ err = 0;
+ mfile->mp = mp;
+ mp->mfile = mfile;
+ mp->socket.file = file;
+ dev_hold(mp->dev);
+ sock_hold(mp->socket.sk);
+ atomic_inc(&mfile->count);
+
+out:
+ netif_tx_unlock_bh(mp->dev);
+ return err;
+}
+
+static int do_unbind(struct mp_file *mfile)
+{
+ struct mp_struct *mp = mp_get(mfile);
+
+ if (!mp)
+ return -EINVAL;
+
+ mp_detach(mp);
+ sock_put(mp->socket.sk);
+ mp_put(mfile);
+ return 0;
+}
+
+static long mp_chr_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ struct mp_file *mfile = file->private_data;
+ struct mp_struct *mp;
+ struct net_device *dev;
+ void __user* argp = (void __user *)arg;
+ struct ifreq ifr;
+ struct sock *sk;
+ int ret;
+
+ ret = -EINVAL;
+
+ switch (cmd) {
+ case MPASSTHRU_BINDDEV:
+ ret = -EFAULT;
+ if (copy_from_user(&ifr, argp, sizeof ifr))
+ break;
+
+ ifr.ifr_name[IFNAMSIZ-1] = '\0';
+
+ ret = -ENODEV;
+ dev = dev_get_by_name(mfile->net, ifr.ifr_name);
+ if (!dev)
+ break;
+
+ mutex_lock(&mp_mutex);
+
+ ret = -EBUSY;
+
+ /* the device can be only bind once */
+ if (dev_is_mpassthru(dev))
+ goto err_dev_put;
+
+ mp = mfile->mp;
+ if (mp)
+ goto err_dev_put;
+
+ mp = kzalloc(sizeof(*mp), GFP_KERNEL);
+ if (!mp) {
+ ret = -ENOMEM;
+ goto err_dev_put;
+ }
+ mp->dev = dev;
+ ret = -ENOMEM;
+
+ sk = sk_alloc(mfile->net, AF_UNSPEC, GFP_KERNEL, &mp_proto);
+ if (!sk)
+ goto err_free_mp;
+
+ init_waitqueue_head(&mp->socket.wait);
+ mp->socket.ops = &mp_socket_ops;
+ sock_init_data(&mp->socket, sk);
+ sk->sk_sndbuf = INT_MAX;
+ container_of(sk, struct mp_sock, sk)->mp = mp;
+
+ sk->sk_destruct = NULL;
+ sk->sk_data_ready = NULL;
+ sk->sk_write_space = NULL;
+ sk->sk_state_change = NULL;
+ ret = mp_attach(mp, file);
+ if (ret < 0)
+ goto err_free_sk;
+
+ ret = page_ctor_attach(mp);
+ if (ret < 0)
+ goto err_free_sk;
+
+ mp_dev_change_flags(mp->dev, mp->dev->flags | IFF_UP);
+out:
+ mutex_unlock(&mp_mutex);
+ break;
+err_free_sk:
+ sk_free(sk);
+err_free_mp:
+ kfree(mp);
+err_dev_put:
+ dev_put(dev);
+ goto out;
+
+ case MPASSTHRU_UNBINDDEV:
+ ret = do_unbind(mfile);
+ break;
+
+ default:
+ break;
+ }
+ return ret;
+}
+
+static unsigned int mp_chr_poll(struct file *file, poll_table * wait)
+{
+ struct mp_file *mfile = file->private_data;
+ struct mp_struct *mp = mp_get(mfile);
+ struct sock *sk;
+ unsigned int mask = 0;
+
+ if (!mp)
+ return POLLERR;
+
+ sk = mp->socket.sk;
+
+ poll_wait(file, &mp->socket.wait, wait);
+
+ if (!skb_queue_empty(&sk->sk_receive_queue))
+ mask |= POLLIN | POLLRDNORM;
+
+ if (sock_writeable(sk) ||
+ (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+ sock_writeable(sk)))
+ mask |= POLLOUT | POLLWRNORM;
+
+ if (mp->dev->reg_state != NETREG_REGISTERED)
+ mask = POLLERR;
+
+ mp_put(mfile);
+ return mask;
+}
+
+static ssize_t mp_chr_aio_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long count, loff_t pos)
+{
+ struct file *file = iocb->ki_filp;
+ struct mp_struct *mp = mp_get(file->private_data);
+ struct sock *sk = mp->socket.sk;
+ struct sk_buff *skb;
+ int len, err;
+ ssize_t result = 0;
+
+ if (!mp)
+ return -EBADFD;
+
+ /* currently, async is not supported.
+ * but we may support real async aio from user application,
+ * maybe qemu virtio-net backend.
+ */
+ if (!is_sync_kiocb(iocb))
+ return -EFAULT;
+
+ len = iov_length(iov, count);
+
+ if (unlikely(len) < ETH_HLEN)
+ return -EINVAL;
+
+ skb = sock_alloc_send_skb(sk, len + NET_IP_ALIGN,
+ file->f_flags & O_NONBLOCK, &err);
+
+ if (!skb)
+ return -EFAULT;
+
+ skb_reserve(skb, NET_IP_ALIGN);
+ skb_put(skb, len);
+
+ if (skb_copy_datagram_from_iovec(skb, 0, iov, 0, len)) {
+ kfree_skb(skb);
+ return -EAGAIN;
+ }
+
+ skb->protocol = eth_type_trans(skb, mp->dev);
+ skb->dev = mp->dev;
+
+ dev_queue_xmit(skb);
+
+ mp_put(file->private_data);
+ return result;
+}
+
+static int mp_chr_close(struct inode *inode, struct file *file)
+{
+ struct mp_file *mfile = file->private_data;
+
+ /*
+ * Ignore return value since an error only means there was nothing to
+ * do
+ */
+ do_unbind(mfile);
+
+ put_net(mfile->net);
+ kfree(mfile);
+
+ return 0;
+}
+
+#ifdef CONFIG_COMPAT
+static long mp_chr_compat_ioctl(struct file *f, unsigned int ioctl,
+ unsigned long arg)
+{
+ return mp_chr_ioctl(f, ioctl, (unsigned long)compat_ptr(arg));
+}
+#endif
+
+static const struct file_operations mp_fops = {
+ .owner = THIS_MODULE,
+ .llseek = no_llseek,
+ .write = do_sync_write,
+ .aio_write = mp_chr_aio_write,
+ .poll = mp_chr_poll,
+ .unlocked_ioctl = mp_chr_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = mp_chr_compat_ioctl,
+#endif
+ .open = mp_chr_open,
+ .release = mp_chr_close,
+};
+
+static struct miscdevice mp_miscdev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "mp",
+ .nodename = "net/mp",
+ .fops = &mp_fops,
+};
+
+static int mp_device_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = ptr;
+ struct mpassthru_port *port;
+ struct mp_struct *mp = NULL;
+ struct socket *sock = NULL;
+
+ port = dev->mp_port;
+ if (port == NULL)
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_UNREGISTER:
+ sock = dev->mp_port->sock;
+ mp = container_of(sock->sk, struct mp_sock, sk)->mp;
+ do_unbind(mp->mfile);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block mp_notifier_block __read_mostly = {
+ .notifier_call = mp_device_event,
+};
+
+static int mp_init(void)
+{
+ int err = 0;
+
+ ext_page_info_cache = kmem_cache_create("skb_page_info",
+ sizeof(struct page_info),
+ 0, SLAB_HWCACHE_ALIGN, NULL);
+ if (!ext_page_info_cache)
+ return -ENOMEM;
+
+ err = misc_register(&mp_miscdev);
+ if (err) {
+ printk(KERN_ERR "mp: Can't register misc device\n");
+ kmem_cache_destroy(ext_page_info_cache);
+ } else {
+ printk(KERN_INFO "Registering mp misc device - minor = %d\n",
+ mp_miscdev.minor);
+ register_netdevice_notifier(&mp_notifier_block);
+ }
+ return err;
+}
+
+void mp_exit(void)
+{
+ unregister_netdevice_notifier(&mp_notifier_block);
+ misc_deregister(&mp_miscdev);
+ kmem_cache_destroy(ext_page_info_cache);
+}
+
+/* Get an underlying socket object from mp 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 *mp_get_socket(struct file *file)
+{
+ struct mp_file *mfile = file->private_data;
+ struct mp_struct *mp;
+
+ if (file->f_op != &mp_fops)
+ return ERR_PTR(-EINVAL);
+ mp = mp_get(mfile);
+ if (!mp)
+ return ERR_PTR(-EBADFD);
+ mp_put(mfile);
+ return &mp->socket;
+}
+EXPORT_SYMBOL_GPL(mp_get_socket);
+
+module_init(mp_init);
+module_exit(mp_exit);
+MODULE_AUTHOR(DRV_COPYRIGHT);
+MODULE_DESCRIPTION(DRV_DESCRIPTION);
+MODULE_LICENSE("GPL v2");
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 14/19] Add header file for mp device.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-14-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/mpassthru.h | 25 +++++++++++++++++++++++++
1 files changed, 25 insertions(+), 0 deletions(-)
create mode 100644 include/linux/mpassthru.h
diff --git a/include/linux/mpassthru.h b/include/linux/mpassthru.h
new file mode 100644
index 0000000..ba8f320
--- /dev/null
+++ b/include/linux/mpassthru.h
@@ -0,0 +1,25 @@
+#ifndef __MPASSTHRU_H
+#define __MPASSTHRU_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+/* ioctl defines */
+#define MPASSTHRU_BINDDEV _IOW('M', 213, int)
+#define MPASSTHRU_UNBINDDEV _IO('M', 214)
+
+#ifdef __KERNEL__
+#if defined(CONFIG_MEDIATE_PASSTHRU) || defined(CONFIG_MEDIATE_PASSTHRU_MODULE)
+struct socket *mp_get_socket(struct file *);
+#else
+#include <linux/err.h>
+#include <linux/errno.h>
+struct file;
+struct socket;
+static inline struct socket *mp_get_socket(struct file *f)
+{
+ return ERR_PTR(-EINVAL);
+}
+#endif /* CONFIG_MEDIATE_PASSTHRU */
+#endif /* __KERNEL__ */
+#endif /* __MPASSTHRU_H */
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 12/19] Add a hook to intercept external buffers from NIC driver.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-12-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
The hook is called in netif_receive_skb().
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
net/core/dev.c | 35 +++++++++++++++++++++++++++++++++++
1 files changed, 35 insertions(+), 0 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index 37b389a..dc2f225 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2548,6 +2548,37 @@ err:
EXPORT_SYMBOL(netdev_mp_port_prep);
#endif
+#if defined(CONFIG_MEDIATE_PASSTHRU) || defined(CONFIG_MEDIATE_PASSTHRU_MODULE)
+/* Add a hook to intercept mediate passthru(zero-copy) packets,
+ * and insert it to the socket queue owned by mp_port specially.
+ */
+static inline struct sk_buff *handle_mpassthru(struct sk_buff *skb,
+ struct packet_type **pt_prev,
+ int *ret,
+ struct net_device *orig_dev)
+{
+ struct mpassthru_port *mp_port = NULL;
+ struct sock *sk = NULL;
+
+ if (!dev_is_mpassthru(skb->dev))
+ return skb;
+ mp_port = skb->dev->mp_port;
+
+ if (*pt_prev) {
+ *ret = deliver_skb(skb, *pt_prev, orig_dev);
+ *pt_prev = NULL;
+ }
+
+ sk = mp_port->sock->sk;
+ skb_queue_tail(&sk->sk_receive_queue, skb);
+ sk->sk_state_change(sk);
+
+ return NULL;
+}
+#else
+#define handle_mpassthru(skb, pt_prev, ret, orig_dev) (skb)
+#endif
+
/**
* netif_receive_skb - process receive buffer from network
* @skb: buffer to process
@@ -2629,6 +2660,10 @@ int netif_receive_skb(struct sk_buff *skb)
ncls:
#endif
+ /* To intercept mediate passthru(zero-copy) packets here */
+ skb = handle_mpassthru(skb, &pt_prev, &ret, orig_dev);
+ if (!skb)
+ goto out;
skb = handle_bridge(skb, &pt_prev, &ret, orig_dev);
if (!skb)
goto out;
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 11/19] Use callback to deal with skb_release_data() specially.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-11-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
If buffer is external, then use the callback to destruct
buffers.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
net/core/skbuff.c | 11 +++++++++++
1 files changed, 11 insertions(+), 0 deletions(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 37587f0..418457c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -385,6 +385,11 @@ static void skb_clone_fraglist(struct sk_buff *skb)
static void skb_release_data(struct sk_buff *skb)
{
+ /* check if the skb has external buffers, we have use destructor_arg
+ * here to indicate
+ */
+ struct skb_external_page *ext_page = skb_shinfo(skb)->destructor_arg;
+
if (!skb->cloned ||
!atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
&skb_shinfo(skb)->dataref)) {
@@ -397,6 +402,12 @@ static void skb_release_data(struct sk_buff *skb)
if (skb_has_frags(skb))
skb_drop_fraglist(skb);
+ /* if the skb has external buffers, use destructor here,
+ * since after that skb->head will be kfree, in case skb->head
+ * from external buffer cannot use kfree to destroy.
+ */
+ if (dev_is_mpassthru(skb->dev) && ext_page && ext_page->dtor)
+ ext_page->dtor(ext_page);
kfree(skb->head);
}
}
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 10/19] Don't do skb recycle, if device use external buffer.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-10-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
net/core/skbuff.c | 6 ++++++
1 files changed, 6 insertions(+), 0 deletions(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 38d19d0..37587f0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -553,6 +553,12 @@ int skb_recycle_check(struct sk_buff *skb, int skb_size)
if (skb_shared(skb) || skb_cloned(skb))
return 0;
+ /* if the device wants to do mediate passthru, the skb may
+ * get external buffer, so don't recycle
+ */
+ if (dev_is_mpassthru(skb->dev))
+ return 0;
+
skb_release_head_state(skb);
shinfo = skb_shinfo(skb);
atomic_set(&shinfo->dataref, 1);
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 09/19] Ignore room skb_reserve() when device is using external buffer.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-9-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Make the skb->data and skb->head from external buffer
to be consistent, we ignore the room reserved by driver
for kernel skb.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/skbuff.h | 9 +++++++++
1 files changed, 9 insertions(+), 0 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5ff8c27..193b259 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1200,6 +1200,15 @@ static inline int skb_tailroom(const struct sk_buff *skb)
*/
static inline void skb_reserve(struct sk_buff *skb, int len)
{
+ /* Since skb_reserve() is only for an empty buffer,
+ * and when the skb is getting external buffer, we cannot
+ * retain the external buffer has the same reserved space
+ * in the header which kernel allocatd skb has, so have to
+ * ignore this. And we have recorded the external buffer
+ * info in the destructor_arg field, so use it as indicator.
+ */
+ if (skb_shinfo(skb)->destructor_arg)
+ return;
skb->data += len;
skb->tail += len;
}
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 07/19] Add interface to get external buffers.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-7-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Currently, it can get external buffers from mp device.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/skbuff.h | 12 ++++++++++++
net/core/skbuff.c | 16 ++++++++++++++++
2 files changed, 28 insertions(+), 0 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index cf309c9..281a1c0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1519,6 +1519,18 @@ static inline void netdev_free_page(struct net_device *dev, struct page *page)
__free_page(page);
}
+extern struct skb_external_page *netdev_alloc_external_pages(
+ struct net_device *dev,
+ struct sk_buff *skb, int npages);
+
+static inline struct skb_external_page *netdev_alloc_external_page(
+ struct net_device *dev,
+ struct sk_buff *skb, unsigned int size)
+{
+ return netdev_alloc_external_pages(dev, skb,
+ DIV_ROUND_UP(size, PAGE_SIZE));
+}
+
/**
* skb_clone_writable - is the header of a clone writable
* @skb: buffer to check
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 93c4e06..fbdb1f1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -278,6 +278,22 @@ struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask)
}
EXPORT_SYMBOL(__netdev_alloc_page);
+struct skb_external_page *netdev_alloc_external_pages(struct net_device *dev,
+ struct sk_buff *skb, int npages)
+{
+ struct mpassthru_port *port;
+ struct skb_external_page *ext_page = NULL;
+
+ port = rcu_dereference(dev->mp_port);
+ if (!port)
+ goto out;
+ WARN_ON(npages > port->npages);
+ ext_page = port->ctor(port, skb, npages);
+out:
+ return ext_page;
+}
+EXPORT_SYMBOL(netdev_alloc_external_pages);
+
void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
int size)
{
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 06/19] Add a function to indicate if device use external buffer.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-6-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/netdevice.h | 5 +++++
1 files changed, 5 insertions(+), 0 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 31d9c4a..0cb78f4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1602,6 +1602,11 @@ extern void netdev_mp_port_detach(struct net_device *dev);
extern int netdev_mp_port_prep(struct net_device *dev,
struct mpassthru_port *port);
+static inline bool dev_is_mpassthru(struct net_device *dev)
+{
+ return (dev && dev->mp_port);
+}
+
static inline void napi_free_frags(struct napi_struct *napi)
{
kfree_skb(napi->skb);
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 04/19] Add a ndo_mp_port_prep pointer to net_device_ops.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-4-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
If the driver want to allocate external buffers,
then it can export it's capability, as the skb
buffer header length, the page length can be DMA, etc.
The external buffers owner may utilize this.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/netdevice.h | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index efb575a..183c786 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -707,6 +707,10 @@ struct net_device_ops {
int (*ndo_fcoe_get_wwn)(struct net_device *dev,
u64 *wwn, int type);
#endif
+#if defined(CONFIG_MEDIATE_PASSTHRU) || defined(CONFIG_MEDIATE_PASSTHRU_MODULE)
+ int (*ndo_mp_port_prep)(struct net_device *dev,
+ struct mpassthru_port *port);
+#endif
};
/*
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 03/19] Export 2 func for device to assign/deassign new strucure
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-3-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/netdevice.h | 3 +++
net/core/dev.c | 28 ++++++++++++++++++++++++++++
2 files changed, 31 insertions(+), 0 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index bae725c..efb575a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1592,6 +1592,9 @@ extern gro_result_t napi_frags_finish(struct napi_struct *napi,
gro_result_t ret);
extern struct sk_buff * napi_frags_skb(struct napi_struct *napi);
extern gro_result_t napi_gro_frags(struct napi_struct *napi);
+extern int netdev_mp_port_attach(struct net_device *dev,
+ struct mpassthru_port *port);
+extern void netdev_mp_port_detach(struct net_device *dev);
static inline void napi_free_frags(struct napi_struct *napi)
{
diff --git a/net/core/dev.c b/net/core/dev.c
index f769098..ecbb6b1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2469,6 +2469,34 @@ void netif_nit_deliver(struct sk_buff *skb)
rcu_read_unlock();
}
+/* Export two functions to assign/de-assign mp_port pointer
+ * to a net device.
+ */
+
+int netdev_mp_port_attach(struct net_device *dev,
+ struct mpassthru_port *port)
+{
+ /* locked by mp_mutex */
+ if (rcu_dereference(dev->mp_port))
+ return -EBUSY;
+
+ rcu_assign_pointer(dev->mp_port, port);
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_mp_port_attach);
+
+void netdev_mp_port_detach(struct net_device *dev)
+{
+ /* locked by mp_mutex */
+ if (!rcu_dereference(dev->mp_port))
+ return;
+
+ rcu_assign_pointer(dev->mp_port, NULL);
+ synchronize_rcu();
+}
+EXPORT_SYMBOL(netdev_mp_port_detach);
+
/**
* netif_receive_skb - process receive buffer from network
* @skb: buffer to process
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 00/19] Provide a zero-copy method on KVM virtio-net.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike
We provide an zero-copy method which driver side may get external
buffers to DMA. Here external means driver don't use kernel space
to allocate skb buffers. Currently the external buffer can be from
guest virtio-net driver.
The idea is simple, just to pin the guest VM user space and then
let host NIC driver has the chance to directly DMA to it.
The patches are based on vhost-net backend driver. We add a device
which provides proto_ops as sendmsg/recvmsg to vhost-net to
send/recv directly to/from the NIC driver. KVM guest who use the
vhost-net backend may bind any ethX interface in the host side to
get copyless data transfer thru guest virtio-net frontend.
patch 01-13: net core changes.
patch 14-18: new device as interface to mantpulate external buffers.
patch 19: for vhost-net.
The guest virtio-net driver submits multiple requests thru vhost-net
backend driver to the kernel. And the requests are queued and then
completed after corresponding actions in h/w are done.
For read, user space buffers are dispensed to NIC driver for rx when
a page constructor API is invoked. Means NICs can allocate user buffers
from a page constructor. We add a hook in netif_receive_skb() function
to intercept the incoming packets, and notify the zero-copy device.
For write, the zero-copy deivce may allocates a new host skb and puts
payload on the skb_shinfo(skb)->frags, and copied the header to skb->data.
The request remains pending until the skb is transmitted by h/w.
Here, we have ever considered 2 ways to utilize the page constructor
API to dispense the user buffers.
One: Modify __alloc_skb() function a bit, it can only allocate a
structure of sk_buff, and the data pointer is pointing to a
user buffer which is coming from a page constructor API.
Then the shinfo of the skb is also from guest.
When packet is received from hardware, the skb->data is filled
directly by h/w. What we have done is in this way.
Pros: We can avoid any copy here.
Cons: Guest virtio-net driver needs to allocate skb as almost
the same method with the host NIC drivers, say the size
of netdev_alloc_skb() and the same reserved space in the
head of skb. Many NIC drivers are the same with guest and
ok for this. But some lastest NIC drivers reserves special
room in skb head. To deal with it, we suggest to provide
a method in guest virtio-net driver to ask for parameter
we interest from the NIC driver when we know which device
we have bind to do zero-copy. Then we ask guest to do so.
Two: Modify driver to get user buffer allocated from a page constructor
API(to substitute alloc_page()), the user buffer are used as payload
buffers and filled by h/w directly when packet is received. Driver
should associate the pages with skb (skb_shinfo(skb)->frags). For
the head buffer side, let host allocates skb, and h/w fills it.
After that, the data filled in host skb header will be copied into
guest header buffer which is submitted together with the payload buffer.
Pros: We could less care the way how guest or host allocates their
buffers.
Cons: We still need a bit copy here for the skb header.
We are not sure which way is the better here. This is the first thing we want
to get comments from the community. We wish the modification to the network
part will be generic which not used by vhost-net backend only, but a user
application may use it as well when the zero-copy device may provides async
read/write operations later.
We have got comments from Michael. And he said the first method will break
the compatiblity of virtio-net driver and may complicate the qemu live
migration. Currently, we tried to ignore the skb_reserve() if the device
is doing zero-copy. Then guest virtio-net driver wil not changed. So we now
continue to go with the first way.
But comments about the two ways are still appreicated.
We provide multiple submits and asynchronous notifiicaton to
vhost-net too.
Our goal is to improve the bandwidth and reduce the CPU usage.
Exact performance data will be provided later. But for simple
test with netperf, we found bindwidth up and CPU % up too,
but the bindwidth up ratio is much more than CPU % up ratio.
What we have not done yet:
packet split support
To support GRO
Performance tuning
what we have done in v1:
polish the RCU usage
deal with write logging in asynchroush mode in vhost
add notifier block for mp device
rename page_ctor to mp_port in netdevice.h to make it looks generic
add mp_dev_change_flags() for mp device to change NIC state
add CONIFG_VHOST_MPASSTHRU to limit the usage when module is not load
a small fix for missing dev_put when fail
using dynamic minor instead of static minor number
a __KERNEL__ protect to mp_get_sock()
what we have done in v2:
remove most of the RCU usage, since the ctor pointer is only
changed by BIND/UNBIND ioctl, and during that time, NIC will be
stopped to get good cleanup(all outstanding requests are finished),
so the ctor pointer cannot be raced into wrong situation.
Remove the struct vhost_notifier with struct kiocb.
Let vhost-net backend to alloc/free the kiocb and transfer them
via sendmsg/recvmsg.
use get_user_pages_fast() and set_page_dirty_lock() when read.
Add some comments for netdev_mp_port_prep() and handle_mpassthru().
what we have done in v3:
the async write logging is rewritten
a drafted synchronous write function for qemu live migration
a limit for locked pages from get_user_pages_fast() to prevent Dos
by using RLIMIT_MEMLOCK
what we have done in v4:
add iocb completion callback from vhost-net to queue iocb in mp device
replace vq->receiver by mp_sock_data_ready()
remove stuff in mp device which access structures from vhost-net
modify skb_reserve() to ignore host NIC driver reserved space
rebase to the latest vhost tree
split large patches into small pieces, especially for net core part.
what we have done in v5:
address Arnd Bergmann's comments
-remove IFF_MPASSTHRU_EXCL flag in mp device
-Add CONFIG_COMPAT macro
-remove mp_release ops
move dev_is_mpassthru() as inline func
fix a bug in memory relinquish
Apply to current git (2.6.34-rc6) tree.
what we have done in v6:
move create_iocb() out of page_dtor which may happen in interrupt context
-This remove the potential issues which lock called in interrupt context
make the cache used by mp, vhost as static, and created/destoryed during
modules init/exit functions.
-This makes multiple mp guest created at the same time.
performance:
using netperf with GSO/TSO disabled, 10G NIC,
disabled packet split mode, with raw socket case compared to vhost.
bindwidth will be from 1.1Gbps to 1.7Gbps
CPU % from 120%-140% to 140%-160%
We have retested the performance based on 2.6.34-rc6 in above situtation.
BW CPU %
vhost 1.4Gbps 120% ~ 130%
vhost + zero-copy 2.7Gbps 160% ~ 180%
^ permalink raw reply
* [RFC][PATCH v6 16/19] Manipulate external buffers in mp device.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin, Xiaohui
In-Reply-To: <1274434235-5929-16-git-send-email-xiaohui.xin@intel.com>
From: Xin, Xiaohui<xiaohui.xin@intel.com>
How external buffer comes from, how to destroy.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
drivers/vhost/mpassthru.c | 253 ++++++++++++++++++++++++++++++++++++++++++++-
1 files changed, 251 insertions(+), 2 deletions(-)
diff --git a/drivers/vhost/mpassthru.c b/drivers/vhost/mpassthru.c
index 25e2f3e..de07f1e 100644
--- a/drivers/vhost/mpassthru.c
+++ b/drivers/vhost/mpassthru.c
@@ -161,6 +161,39 @@ static int mp_dev_change_flags(struct net_device *dev, unsigned flags)
return ret;
}
+/* The main function to allocate external buffers */
+static struct skb_external_page *page_ctor(struct mpassthru_port *port,
+ struct sk_buff *skb, int npages)
+{
+ int i;
+ unsigned long flags;
+ struct page_ctor *ctor;
+ struct page_info *info = NULL;
+
+ ctor = container_of(port, struct page_ctor, port);
+
+ spin_lock_irqsave(&ctor->read_lock, flags);
+ if (!list_empty(&ctor->readq)) {
+ info = list_first_entry(&ctor->readq, struct page_info, list);
+ list_del(&info->list);
+ }
+ spin_unlock_irqrestore(&ctor->read_lock, flags);
+ if (!info)
+ return NULL;
+
+ for (i = 0; i < info->pnum; i++) {
+ get_page(info->pages[i]);
+ info->frag[i].page = info->pages[i];
+ info->frag[i].page_offset = i ? 0 : info->offset;
+ info->frag[i].size = port->npages > 1 ? PAGE_SIZE :
+ port->data_len;
+ }
+ info->skb = skb;
+ info->ext_page.frags = info->frag;
+ info->ext_page.ushinfo = &info->ushinfo;
+ return &info->ext_page;
+}
+
static int page_ctor_attach(struct mp_struct *mp)
{
int rc;
@@ -186,7 +219,7 @@ static int page_ctor_attach(struct mp_struct *mp)
dev_hold(dev);
ctor->dev = dev;
- ctor->port.ctor = NULL;
+ ctor->port.ctor = page_ctor;
ctor->port.sock = &mp->socket;
ctor->lock_pages = 0;
rc = netdev_mp_port_attach(dev, &ctor->port);
@@ -252,11 +285,66 @@ static int set_memlock_rlimit(struct page_ctor *ctor, int resource,
return 0;
}
+static void relinquish_resource(struct page_ctor *ctor)
+{
+ if (!(ctor->dev->flags & IFF_UP) &&
+ !(ctor->wq_len + ctor->rq_len))
+ printk(KERN_INFO "relinquish_resource\n");
+}
+
+static void mp_ki_dtor(struct kiocb *iocb)
+{
+ struct page_info *info = (struct page_info *)(iocb->private);
+ int i;
+
+ if (info->flags == INFO_READ) {
+ for (i = 0; i < info->pnum; i++) {
+ if (info->pages[i]) {
+ set_page_dirty_lock(info->pages[i]);
+ put_page(info->pages[i]);
+ }
+ }
+ info->skb->destructor = NULL;
+ kfree_skb(info->skb);
+ info->ctor->rq_len--;
+ } else
+ info->ctor->wq_len--;
+ /* Decrement the number of locked pages */
+ info->ctor->lock_pages -= info->pnum;
+ kmem_cache_free(ext_page_info_cache, info);
+ relinquish_resource(info->ctor);
+
+ return;
+}
+
+static struct kiocb *create_iocb(struct page_info *info, int size)
+{
+ struct kiocb *iocb = NULL;
+
+ iocb = info->iocb;
+ if (!iocb)
+ return iocb;
+ iocb->ki_flags = 0;
+ iocb->ki_users = 1;
+ iocb->ki_key = 0;
+ iocb->ki_ctx = NULL;
+ iocb->ki_cancel = NULL;
+ iocb->ki_retry = NULL;
+ iocb->ki_iovec = NULL;
+ iocb->ki_eventfd = NULL;
+ iocb->ki_pos = info->desc_pos;
+ iocb->ki_nbytes = size;
+ iocb->ki_dtor(iocb);
+ iocb->private = (void *)info;
+ iocb->ki_dtor = mp_ki_dtor;
+
+ return iocb;
+}
+
static int page_ctor_detach(struct mp_struct *mp)
{
struct page_ctor *ctor;
struct page_info *info;
- struct kiocb *iocb = NULL;
int i;
/* locked by mp_mutex */
@@ -268,11 +356,17 @@ static int page_ctor_detach(struct mp_struct *mp)
for (i = 0; i < info->pnum; i++)
if (info->pages[i])
put_page(info->pages[i]);
+ create_iocb(info, 0);
+ ctor->rq_len--;
kmem_cache_free(ext_page_info_cache, info);
}
+
+ relinquish_resource(ctor);
+
set_memlock_rlimit(ctor, RLIMIT_MEMLOCK,
ctor->o_rlim.rlim_cur,
ctor->o_rlim.rlim_max);
+
netdev_mp_port_detach(ctor->dev);
dev_put(ctor->dev);
@@ -320,6 +414,161 @@ static void mp_put(struct mp_file *mfile)
mp_detach(mfile->mp);
}
+/* The callback to destruct the external buffers or skb */
+static void page_dtor(struct skb_external_page *ext_page)
+{
+ struct page_info *info;
+ struct page_ctor *ctor;
+ struct sock *sk;
+ struct sk_buff *skb;
+ unsigned long flags;
+
+ if (!ext_page)
+ return;
+ info = container_of(ext_page, struct page_info, ext_page);
+ if (!info)
+ return;
+ ctor = info->ctor;
+ skb = info->skb;
+
+ if ((info->flags == INFO_READ) && info->skb)
+ info->skb->head = NULL;
+
+ /* If the info->total is 0, make it to be reused */
+ if (!info->total) {
+ spin_lock_irqsave(&ctor->read_lock, flags);
+ list_add(&info->list, &ctor->readq);
+ spin_unlock_irqrestore(&ctor->read_lock, flags);
+ return;
+ }
+
+ if (info->flags == INFO_READ)
+ return;
+
+ /* For transmit, we should wait for the DMA finish by hardware.
+ * Queue the notifier to wake up the backend driver
+ */
+
+ create_iocb(info, info->total);
+
+ sk = ctor->port.sock->sk;
+ sk->sk_write_space(sk);
+
+ return;
+}
+
+/* For small exteranl buffers transmit, we don't need to call
+ * get_user_pages().
+ */
+static struct page_info *alloc_small_page_info(struct page_ctor *ctor,
+ struct kiocb *iocb, int total)
+{
+ struct page_info *info =
+ kmem_cache_zalloc(ext_page_info_cache, GFP_KERNEL);
+
+ if (!info)
+ return NULL;
+ info->total = total;
+ info->ext_page.dtor = page_dtor;
+ info->ctor = ctor;
+ info->flags = INFO_WRITE;
+ info->iocb = iocb;
+ return info;
+}
+
+/* The main function to transform the guest user space address
+ * to host kernel address via get_user_pages(). Thus the hardware
+ * can do DMA directly to the external buffer address.
+ */
+static struct page_info *alloc_page_info(struct page_ctor *ctor,
+ struct kiocb *iocb, struct iovec *iov,
+ int count, struct frag *frags,
+ int npages, int total)
+{
+ int rc;
+ int i, j, n = 0;
+ int len;
+ unsigned long base, lock_limit;
+ struct page_info *info = NULL;
+
+ lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+ lock_limit >>= PAGE_SHIFT;
+
+ if (ctor->lock_pages + count > lock_limit) {
+ printk(KERN_INFO "exceed the locked memory rlimit.");
+ return NULL;
+ }
+
+ info = kmem_cache_zalloc(ext_page_info_cache, GFP_KERNEL);
+
+ if (!info)
+ return NULL;
+
+ for (i = j = 0; i < count; i++) {
+ base = (unsigned long)iov[i].iov_base;
+ len = iov[i].iov_len;
+
+ if (!len)
+ continue;
+ n = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+
+ rc = get_user_pages_fast(base, n, npages ? 1 : 0,
+ &info->pages[j]);
+ if (rc != n)
+ goto failed;
+
+ while (n--) {
+ frags[j].offset = base & ~PAGE_MASK;
+ frags[j].size = min_t(int, len,
+ PAGE_SIZE - frags[j].offset);
+ len -= frags[j].size;
+ base += frags[j].size;
+ j++;
+ }
+ }
+
+#ifdef CONFIG_HIGHMEM
+ if (npages && !(dev->features & NETIF_F_HIGHDMA)) {
+ for (i = 0; i < j; i++) {
+ if (PageHighMem(info->pages[i]))
+ goto failed;
+ }
+ }
+#endif
+
+ info->total = total;
+ info->ext_page.dtor = page_dtor;
+ info->ctor = ctor;
+ info->pnum = j;
+ info->iocb = iocb;
+ if (!npages)
+ info->flags = INFO_WRITE;
+ if (info->flags == INFO_READ) {
+ info->ext_page.start = (u8 *)(((unsigned long)
+ (pfn_to_kaddr(page_to_pfn(info->pages[0]))) +
+ frags[0].offset));
+#ifdef NET_SKBUFF_DATA_USES_OFFSET
+ info->ext_page.size = SKB_DATA_ALIGN(
+ iov[0].iov_len + NET_IP_ALIGN + NET_SKB_PAD);
+#else
+ info->ext_page.size = SKB_DATA_ALIGN(
+ iov[0].iov_len + NET_IP_ALIGN + NET_SKB_PAD) -
+ NET_IP_ALIGN - NET_SKB_PAD;
+#endif
+ }
+ /* increment the number of locked pages */
+ ctor->lock_pages += j;
+ return info;
+
+failed:
+ for (i = 0; i < j; i++)
+ put_page(info->pages[i]);
+
+ kmem_cache_free(ext_page_info_cache, info);
+
+ return NULL;
+}
+
/* Ops structure to mimic raw sockets with mp device */
static const struct proto_ops mp_socket_ops = {
};
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 13/19] To skip GRO if buffer is external currently.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-13-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
net/core/dev.c | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index dc2f225..6c6b2fe 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2787,6 +2787,10 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
if (skb_is_gso(skb) || skb_has_frags(skb))
goto normal;
+ /* currently GRO is not supported by mediate passthru */
+ if (dev_is_mpassthru(skb->dev))
+ goto normal;
+
rcu_read_lock();
list_for_each_entry_rcu(ptype, head, list) {
if (ptype->type != type || ptype->dev || !ptype->gro_receive)
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 08/19] Make __alloc_skb() to get external buffer.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-8-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Add a dev parameter to __alloc_skb(), skb->data
points to external buffer, recompute skb->head,
maintain shinfo of the external buffer, record
external buffer info into destructor_arg field.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
__alloc_skb() cleanup by
Jeff Dike <jdike@linux.intel.com>
include/linux/skbuff.h | 7 ++++---
net/core/skbuff.c | 43 +++++++++++++++++++++++++++++++++++++------
2 files changed, 41 insertions(+), 9 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 281a1c0..5ff8c27 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -442,17 +442,18 @@ extern void kfree_skb(struct sk_buff *skb);
extern void consume_skb(struct sk_buff *skb);
extern void __kfree_skb(struct sk_buff *skb);
extern struct sk_buff *__alloc_skb(unsigned int size,
- gfp_t priority, int fclone, int node);
+ gfp_t priority, int fclone,
+ int node, struct net_device *dev);
static inline struct sk_buff *alloc_skb(unsigned int size,
gfp_t priority)
{
- return __alloc_skb(size, priority, 0, -1);
+ return __alloc_skb(size, priority, 0, -1, NULL);
}
static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
gfp_t priority)
{
- return __alloc_skb(size, priority, 1, -1);
+ return __alloc_skb(size, priority, 1, -1, NULL);
}
extern int skb_recycle_check(struct sk_buff *skb, int skb_size);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index fbdb1f1..38d19d0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -161,7 +161,8 @@ EXPORT_SYMBOL(skb_under_panic);
* @fclone: allocate from fclone cache instead of head cache
* and allocate a cloned (child) skb
* @node: numa node to allocate memory on
- *
+ * @dev: a device owns the skb if the skb try to get external buffer.
+ * otherwise is NULL.
* Allocate a new &sk_buff. The returned buffer has no headroom and a
* tail room of size bytes. The object has a reference count of one.
* The return is the buffer. On a failure the return is %NULL.
@@ -170,12 +171,13 @@ EXPORT_SYMBOL(skb_under_panic);
* %GFP_ATOMIC.
*/
struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
- int fclone, int node)
+ int fclone, int node, struct net_device *dev)
{
struct kmem_cache *cache;
struct skb_shared_info *shinfo;
struct sk_buff *skb;
- u8 *data;
+ u8 *data = NULL;
+ struct skb_external_page *ext_page = NULL;
cache = fclone ? skbuff_fclone_cache : skbuff_head_cache;
@@ -185,8 +187,23 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
goto out;
size = SKB_DATA_ALIGN(size);
- data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info),
- gfp_mask, node);
+
+ /* If the device wants to do mediate passthru(zero-copy),
+ * the skb may try to get external buffers from outside.
+ * If fails, then fall back to alloc buffers from kernel.
+ */
+ if (dev && dev->mp_port) {
+ ext_page = netdev_alloc_external_page(dev, skb, size);
+ if (ext_page) {
+ data = ext_page->start;
+ size = ext_page->size;
+ }
+ }
+
+ if (!data)
+ data = kmalloc_node_track_caller(
+ size + sizeof(struct skb_shared_info),
+ gfp_mask, node);
if (!data)
goto nodata;
@@ -208,6 +225,15 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
skb->mac_header = ~0U;
#endif
+ /* If the skb get external buffers sucessfully, since the shinfo is
+ * at the end of the buffer, we may retain the shinfo once we
+ * need it sometime.
+ */
+ if (ext_page) {
+ skb->head = skb->data - NET_IP_ALIGN - NET_SKB_PAD;
+ memcpy(ext_page->ushinfo, skb_shinfo(skb),
+ sizeof(struct skb_shared_info));
+ }
/* make sure we initialize shinfo sequentially */
shinfo = skb_shinfo(skb);
atomic_set(&shinfo->dataref, 1);
@@ -231,6 +257,11 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
child->fclone = SKB_FCLONE_UNAVAILABLE;
}
+ /* Record the external buffer info in this field. It's not so good,
+ * but we cannot find another place easily.
+ */
+ shinfo->destructor_arg = ext_page;
+
out:
return skb;
nodata:
@@ -259,7 +290,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1;
struct sk_buff *skb;
- skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, node);
+ skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, node, dev);
if (likely(skb)) {
skb_reserve(skb, NET_SKB_PAD);
skb->dev = dev;
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 05/19] Add a function make external buffer owner to query capability.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-5-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
The external buffer owner can use the functions to get
the capability of the underlying NIC driver.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhaonew@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/netdevice.h | 2 +
net/core/dev.c | 51 +++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 53 insertions(+), 0 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 183c786..31d9c4a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1599,6 +1599,8 @@ extern gro_result_t napi_gro_frags(struct napi_struct *napi);
extern int netdev_mp_port_attach(struct net_device *dev,
struct mpassthru_port *port);
extern void netdev_mp_port_detach(struct net_device *dev);
+extern int netdev_mp_port_prep(struct net_device *dev,
+ struct mpassthru_port *port);
static inline void napi_free_frags(struct napi_struct *napi)
{
diff --git a/net/core/dev.c b/net/core/dev.c
index ecbb6b1..37b389a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2497,6 +2497,57 @@ void netdev_mp_port_detach(struct net_device *dev)
}
EXPORT_SYMBOL(netdev_mp_port_detach);
+/* To support meidate passthru(zero-copy) with NIC driver,
+ * we'd better query NIC driver for the capability it can
+ * provide, especially for packet split mode, now we only
+ * query for the header size, and the payload a descriptor
+ * may carry. If a driver does not use the API to export,
+ * then we may try to use a default value, currently,
+ * we use the default value from an IGB driver. Now,
+ * it's only called by mpassthru device.
+ */
+#if defined(CONFIG_MEDIATE_PASSTHRU) || defined(CONFIG_MEDIATE_PASSTHRU_MODULE)
+int netdev_mp_port_prep(struct net_device *dev,
+ struct mpassthru_port *port)
+{
+ int rc;
+ int npages, data_len;
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ /* needed by packet split */
+
+ if (ops->ndo_mp_port_prep) {
+ rc = ops->ndo_mp_port_prep(dev, port);
+ if (rc)
+ return rc;
+ } else {
+ /* If the NIC driver did not report this,
+ * then we try to use default value.
+ */
+ port->hdr_len = 128;
+ port->data_len = 2048;
+ port->npages = 1;
+ }
+
+ if (port->hdr_len <= 0)
+ goto err;
+
+ npages = port->npages;
+ data_len = port->data_len;
+ if (npages <= 0 || npages > MAX_SKB_FRAGS ||
+ (data_len < PAGE_SIZE * (npages - 1) ||
+ data_len > PAGE_SIZE * npages))
+ goto err;
+
+ return 0;
+err:
+ dev_warn(&dev->dev, "invalid page constructor parameters\n");
+
+ return -EINVAL;
+}
+EXPORT_SYMBOL(netdev_mp_port_prep);
+#endif
+
/**
* netif_receive_skb - process receive buffer from network
* @skb: buffer to process
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 02/19] Add a new struct for device to manipulate external buffer.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-2-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/netdevice.h | 19 ++++++++++++++++++-
1 files changed, 18 insertions(+), 1 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fa8b476..bae725c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -530,6 +530,22 @@ struct netdev_queue {
unsigned long tx_dropped;
} ____cacheline_aligned_in_smp;
+/* Add a structure in structure net_device, the new field is
+ * named as mp_port. It's for mediate passthru (zero-copy).
+ * It contains the capability for the net device driver,
+ * a socket, and an external buffer creator, external means
+ * skb buffer belongs to the device may not be allocated from
+ * kernel space.
+ */
+struct mpassthru_port {
+ int hdr_len;
+ int data_len;
+ int npages;
+ unsigned flags;
+ struct socket *sock;
+ struct skb_external_page *(*ctor)(struct mpassthru_port *,
+ struct sk_buff *, int);
+};
/*
* This structure defines the management hooks for network devices.
@@ -952,7 +968,8 @@ struct net_device {
struct macvlan_port *macvlan_port;
/* GARP */
struct garp_port *garp_port;
-
+ /* mpassthru */
+ struct mpassthru_port *mp_port;
/* class/net/name entry */
struct device dev;
/* space for optional device, statistics, and wireless sysfs groups */
--
1.5.4.4
^ permalink raw reply related
* [RFC][PATCH v6 01/19] Add a new structure for skb buffer from external.
From: xiaohui.xin @ 2010-05-21 9:30 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1274434235-5929-1-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/skbuff.h | 12 ++++++++++++
1 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 124f90c..cf309c9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -203,6 +203,18 @@ struct skb_shared_info {
void * destructor_arg;
};
+/* The structure is for a skb which skb->data may point to
+ * an external buffer, which is not allocated from kernel space.
+ * Since the buffer is external, then the shinfo or frags are
+ * also extern too. It also contains a destructor for itself.
+ */
+struct skb_external_page {
+ u8 *start;
+ int size;
+ struct skb_frag_struct *frags;
+ struct skb_shared_info *ushinfo;
+ void (*dtor)(struct skb_external_page *);
+};
/* We divide dataref into two halves. The higher 16 bits hold references
* to the payload part of skb->data. The lower 16 bits hold references to
* the entire skb->data. A clone of a headerless skb holds the length of
--
1.5.4.4
^ permalink raw reply related
* Re: linux-next: manual merge of the driver-core tree with the net tree
From: Eric W. Biederman @ 2010-05-21 7:43 UTC (permalink / raw)
To: David Miller; +Cc: sfr, greg, linux-next, linux-kernel, therbert, netdev
In-Reply-To: <20100520.235008.97331614.davem@davemloft.net>
David Miller <davem@davemloft.net> writes:
> From: ebiederm@xmission.com (Eric W. Biederman)
> Date: Thu, 20 May 2010 23:46:22 -0700
>
>> It looks right, except perhaps the RPS code looks like it will cause a
>> build failure with sysfs disabled, but that has nothing to do with your
>> changes.
>
> CONFIG_RPS depends upon CONFIG_SMP && CONFIG_SYSFS, so no that build
> failure is not possible.
That's the bit I'm missing. My apologies if I caused any unnecessary worry.
Eric
^ permalink raw reply
* Re: [PATCH v2] net: fix problem in dequeuing from input_pkt_queue
From: David Miller @ 2010-05-21 7:38 UTC (permalink / raw)
To: eric.dumazet; +Cc: therbert, xiaosuo, netdev
In-Reply-To: <1274424946.2439.7.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Fri, 21 May 2010 08:55:46 +0200
> Le jeudi 20 mai 2010 à 21:37 -0700, Tom Herbert a écrit :
>> Fix some issues introduced in batch skb dequeuing for input_pkt_queue.
>> The primary issue it that the queue head must be incremented only
>> after a packet has been processed, that is only after
>> __netif_receive_skb has been called. This is needed for the mechanism
>> to prevent OOO packet in RFS. Also when flushing the input_pkt_queue
>> and process_queue, the process queue should be done first to prevent
>> OOO packets.
>>
>> Because the input_pkt_queue has been effectively split into two queues,
>> the calculation of the tail ptr is no longer correct. The correct value
>> would be head+input_pkt_queue->len+process_queue->len. To avoid
>> this calculation we added an explict input_queue_tail in softnet_data.
>> The tail value is simply incremented when queuing to input_pkt_queue.
>>
>> Signed-off-by: Tom Herbert <therbert@google.com>
>> ---
>
> Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied, thanks everyone.
^ permalink raw reply
* Re: [PATCH v2] net: fix problem in dequeuing from input_pkt_queue
From: Eric Dumazet @ 2010-05-21 6:55 UTC (permalink / raw)
To: Tom Herbert; +Cc: davem, xiaosuo, netdev
In-Reply-To: <alpine.DEB.1.00.1005202101290.25742@pokey.mtv.corp.google.com>
Le jeudi 20 mai 2010 à 21:37 -0700, Tom Herbert a écrit :
> Fix some issues introduced in batch skb dequeuing for input_pkt_queue.
> The primary issue it that the queue head must be incremented only
> after a packet has been processed, that is only after
> __netif_receive_skb has been called. This is needed for the mechanism
> to prevent OOO packet in RFS. Also when flushing the input_pkt_queue
> and process_queue, the process queue should be done first to prevent
> OOO packets.
>
> Because the input_pkt_queue has been effectively split into two queues,
> the calculation of the tail ptr is no longer correct. The correct value
> would be head+input_pkt_queue->len+process_queue->len. To avoid
> this calculation we added an explict input_queue_tail in softnet_data.
> The tail value is simply incremented when queuing to input_pkt_queue.
>
> Signed-off-by: Tom Herbert <therbert@google.com>
> ---
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
^ permalink raw reply
* Re: linux-next: manual merge of the driver-core tree with the net tree
From: David Miller @ 2010-05-21 6:50 UTC (permalink / raw)
To: ebiederm; +Cc: sfr, greg, linux-next, linux-kernel, therbert, netdev
In-Reply-To: <m1tyq1wy4h.fsf@fess.ebiederm.org>
From: ebiederm@xmission.com (Eric W. Biederman)
Date: Thu, 20 May 2010 23:46:22 -0700
> It looks right, except perhaps the RPS code looks like it will cause a
> build failure with sysfs disabled, but that has nothing to do with your
> changes.
CONFIG_RPS depends upon CONFIG_SMP && CONFIG_SYSFS, so no that build
failure is not possible.
^ permalink raw reply
* Re: linux-next: manual merge of the driver-core tree with the net tree
From: Stephen Rothwell @ 2010-05-21 6:49 UTC (permalink / raw)
To: Eric W. Biederman
Cc: Greg KH, linux-next, linux-kernel, Tom Herbert, David Miller,
netdev
In-Reply-To: <m1tyq1wy4h.fsf@fess.ebiederm.org>
[-- Attachment #1: Type: text/plain, Size: 494 bytes --]
Hi Eric,
On Thu, 20 May 2010 23:46:22 -0700 ebiederm@xmission.com (Eric W. Biederman) wrote:
>
> It looks right, except perhaps the RPS code looks like it will cause a
> build failure with sysfs disabled, but that has nothing to do with your
> changes. I don't see any real conflicts here, just two patches passing
> very close to each other.
Thanks for the confirmation.
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
[-- Attachment #2: Type: application/pgp-signature, Size: 198 bytes --]
^ permalink raw reply
* Re: linux-next: manual merge of the driver-core tree with the net tree
From: Eric W. Biederman @ 2010-05-21 6:46 UTC (permalink / raw)
To: Stephen Rothwell
Cc: Greg KH, linux-next, linux-kernel, Tom Herbert, David Miller,
netdev
In-Reply-To: <20100521162134.6b6326bd.sfr@canb.auug.org.au>
Stephen Rothwell <sfr@canb.auug.org.au> writes:
> Hi Greg,
>
> Today's linux-next merge of the driver-core tree got a conflict in
> net/core/net-sysfs.c between commits
> 0a9627f2649a02bea165cfd529d7bcb625c2fcad ("rps: Receive Packet Steering")
> and fec5e652e58fa6017b2c9e06466cb2a6538de5b4 ("rfs: Receive Flow
> Steering") from the net tree and commits
> bc28c84244da26bafb0d3bce95ef45212b31c6b8 ("net/sysfs: Fix the bitrot in
> network device kobject namespace support") and
> 83dc0fbf37495691219d019ec16b40d8592d2956 ("net: Expose all network
> devices in a namespaces in sysfs") from the driver-core tree.
>
> I fixed it up (I think - see below) and can carry the fix as necessary.
It looks right, except perhaps the RPS code looks like it will cause a
build failure with sysfs disabled, but that has nothing to do with your
changes. I don't see any real conflicts here, just two patches passing
very close to each other.
Thanks for the heads up.
Eric
^ permalink raw reply
* Re: linux-next: manual merge of the driver-core tree with the net tree
From: Stephen Rothwell @ 2010-05-21 6:38 UTC (permalink / raw)
To: Greg KH
Cc: linux-next, linux-kernel, Tom Herbert, David Miller, netdev,
Eric W. Biederman
In-Reply-To: <20100521162134.6b6326bd.sfr@canb.auug.org.au>
[-- Attachment #1: Type: text/plain, Size: 943 bytes --]
Hi Greg,
On Fri, 21 May 2010 16:21:34 +1000 Stephen Rothwell <sfr@canb.auug.org.au> wrote:
>
> Today's linux-next merge of the driver-core tree got a conflict in
> net/core/net-sysfs.c between commits
> 0a9627f2649a02bea165cfd529d7bcb625c2fcad ("rps: Receive Packet Steering")
> and fec5e652e58fa6017b2c9e06466cb2a6538de5b4 ("rfs: Receive Flow
> Steering") from the net tree and commits
> bc28c84244da26bafb0d3bce95ef45212b31c6b8 ("net/sysfs: Fix the bitrot in
> network device kobject namespace support") and
> 83dc0fbf37495691219d019ec16b40d8592d2956 ("net: Expose all network
> devices in a namespaces in sysfs") from the driver-core tree.
>
> I fixed it up (I think - see below) and can carry the fix as necessary.
The net tree has been merged by Linus, so this should be fixable in the
driver-core tree now.
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
[-- Attachment #2: Type: application/pgp-signature, Size: 198 bytes --]
^ permalink raw reply
* Re: [PATCH net-next-2.6] can: SJA1000 add missing spin_lock_init()
From: David Miller @ 2010-05-21 6:21 UTC (permalink / raw)
To: socketcan; +Cc: netdev, socketcan-core, sam
In-Reply-To: <4BF415EE.8090307@hartkopp.net>
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Wed, 19 May 2010 18:46:38 +0200
> As remarked by Sam Ravnborg the spin_lock variable, that has been introduced
> in commit 57c8a456640fa3ca777652f11f2db4179a3e66b6 ("can: Fix SJA1000 command
> register writes on SMP systems") has not been initialized properly.
>
> This patch adds the initialization to allow spinlock debugging.
>
> Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Applied, thanks!
^ permalink raw reply
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